LeenkxTeam/LNXSDK
3
3
Fork 4
Code Issues 16 Pull Requests Actions Packages Projects Releases Wiki Activity

Update

Browse Source
This commit is contained in:
Dante
2026-05-22 11:54:15 -07:00
parent 05f197c291
commit b47ea35fe4
935 changed files with 1016163 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
Kha/Backends/Kore-hxcpp/khacpp/project/thirdparty/pcre2-10.42-16/.bazelrc vendored Normal file
View File

@ -0,0 +1,3 @@
common --experimental_enable_bzlmod
build --incompatible_enable_cc_toolchain_resolution
build --incompatible_strict_action_env

105
Kha/Backends/Kore-hxcpp/khacpp/project/thirdparty/pcre2-10.42-16/.github/workflows/build.yml vendored Normal file
View File

@ -0,0 +1,105 @@
name: Build
on: [push, pull_request]
jobs:
linux:
name: Linux
runs-on: ubuntu-latest
steps:
- name: Checkout
uses: actions/checkout@v3
- name: Autogen
run: ./autogen.sh
- name: Configure
run: ./configure CPPFLAGS='-Wall -Wextra' --enable-jit --enable-pcre2-8 --enable-pcre2-16 --enable-pcre2-32
- name: Build
run: make
- name: Test (main test script)
run: ./RunTest
- name: Test (JIT test program)
run: ./pcre2_jit_test
- name: Test (pcre2grep test script)
run: ./RunGrepTest
alpine:
name: alpine
runs-on: ubuntu-latest
container: alpine
steps:
- name: Checkout
uses: actions/checkout@v3
- name: Setup
run: apk add --no-cache automake autoconf gcc libtool make musl-dev
- name: Autogen
run: ./autogen.sh
- name: Configure
run: ./configure CPPFLAGS='-Wall -Wextra' --enable-jit --enable-pcre2-8 --enable-pcre2-16 --enable-pcre2-32
- name: Build
run: make
- name: Test (main test script)
run: ./RunTest
- name: Test (JIT test program)
run: ./pcre2_jit_test
- name: Test (pcre2grep test script)
run: ./RunGrepTest
macos:
name: macOS universal
runs-on: macos-latest
steps:
- name: Checkout
uses: actions/checkout@v3
- name: Configure
run: cmake -DPCRE2_SUPPORT_JIT=ON -DPCRE2_BUILD_PCRE2_16=ON -DPCRE2_BUILD_PCRE2_32=ON -DCMAKE_OSX_ARCHITECTURES='arm64;x86_64' -DCMAKE_C_FLAGS='-Wall -Wextra' -B build
- name: Build
run: cmake --build build
- name: Test (main test script)
run: |
cd build
../RunTest
- name: Test (JIT test program)
run: |
cd build
./pcre2_jit_test
- name: Test (pcre2grep test script)
run: |
cd build
../RunGrepTest
windows:
name: 32bit Windows
runs-on: windows-latest
steps:
- name: Checkout
uses: actions/checkout@v3
- name: Configure
run: cmake -DPCRE2_SUPPORT_JIT=ON -DPCRE2_BUILD_PCRE2_16=ON -DPCRE2_BUILD_PCRE2_32=ON -DCMAKE_IGNORE_PREFIX_PATH=C:/Strawberry/c -B build -A Win32
- name: Build
run: cmake --build build
- name: Test
run: |
cd build\Debug
..\..\RunTest.bat

24
Kha/Backends/Kore-hxcpp/khacpp/project/thirdparty/pcre2-10.42-16/.github/workflows/cifuzz.yml vendored Normal file
View File

@ -0,0 +1,24 @@
name: CIFuzz
on: [pull_request]
jobs:
Fuzzing:
runs-on: ubuntu-latest
steps:
- name: Build Fuzzers
id: build
uses: google/oss-fuzz/infra/cifuzz/actions/build_fuzzers@master
with:
oss-fuzz-project-name: 'pcre2'
dry-run: false
- name: Run Fuzzers
uses: google/oss-fuzz/infra/cifuzz/actions/run_fuzzers@master
with:
oss-fuzz-project-name: 'pcre2'
fuzz-seconds: 300
dry-run: false
- name: Upload Crash
uses: actions/upload-artifact@v3
if: failure() && steps.build.outcome == 'success'
with:
name: artifacts
path: ./out/artifacts

73
Kha/Backends/Kore-hxcpp/khacpp/project/thirdparty/pcre2-10.42-16/.github/workflows/codeql.yml vendored Normal file
View File

@ -0,0 +1,73 @@
# For most projects, this workflow file will not need changing; you simply need
# to commit it to your repository.
#
# You may wish to alter this file to override the set of languages analyzed,
# or to provide custom queries or build logic.
#
# ******** NOTE ********
# We have attempted to detect the languages in your repository. Please check
# the `language` matrix defined below to confirm you have the correct set of
# supported CodeQL languages.
#
name: "CodeQL"
on:
push:
branches: [ master ]
pull_request:
# The branches below must be a subset of the branches above
branches: [ master ]
schedule:
- cron: '27 6 * * 4'
# Declare default permissions as read only.
permissions: read-all
jobs:
analyze:
name: Analyze
runs-on: ubuntu-latest
permissions:
actions: read
contents: read
security-events: write
strategy:
fail-fast: false
matrix:
language: [ 'cpp', 'python' ]
# CodeQL supports [ 'cpp', 'csharp', 'go', 'java', 'javascript', 'python', 'ruby' ]
# Learn more about CodeQL language support at https://git.io/codeql-language-support
steps:
- name: Checkout repository
uses: actions/checkout@v3
# Initializes the CodeQL tools for scanning.
- name: Initialize CodeQL
uses: github/codeql-action/init@v2
with:
languages: ${{ matrix.language }}
# If you wish to specify custom queries, you can do so here or in a config file.
# By default, queries listed here will override any specified in a config file.
# Prefix the list here with "+" to use these queries and those in the config file.
# queries: ./path/to/local/query, your-org/your-repo/queries@main
# Autobuild attempts to build any compiled languages (C/C++, C#, or Java).
# If this step fails, then you should remove it and run the build manually (see below)
- name: Autobuild
uses: github/codeql-action/autobuild@v2
# ℹ️ Command-line programs to run using the OS shell.
# 📚 https://git.io/JvXDl
# ✏️ If the Autobuild fails above, remove it and uncomment the following three lines
# and modify them (or add more) to build your code if your project
# uses a compiled language
#- run: |
# make bootstrap
# make release
- name: Perform CodeQL Analysis
uses: github/codeql-action/analyze@v2

55
Kha/Backends/Kore-hxcpp/khacpp/project/thirdparty/pcre2-10.42-16/.github/workflows/scorecards.yml vendored Normal file
View File

@ -0,0 +1,55 @@
name: Scorecards supply-chain security
on:
# Only the default branch is supported.
branch_protection_rule:
schedule:
- cron: '23 17 * * 1'
push:
branches: [ master ]
# Declare default permissions as read only.
permissions: read-all
jobs:
analysis:
name: Scorecards analysis
runs-on: ubuntu-latest
permissions:
# Needed to upload the results to code-scanning dashboard.
security-events: write
actions: read
contents: read
steps:
- name: "Checkout code"
uses: actions/checkout@v3
with:
persist-credentials: false
- name: "Run analysis"
uses: ossf/scorecard-action@c1aec4ac820532bab364f02a81873c555a0ba3a1 # v1.0.4
with:
results_file: results.sarif
results_format: sarif
# Read-only PAT token. To create it,
# follow the steps in https://github.com/ossf/scorecard-action#pat-token-creation.
repo_token: ${{ secrets.SCORECARD_READ_TOKEN }}
# Publish the results to enable scorecard badges. For more details, see
# https://github.com/ossf/scorecard-action#publishing-results.
# For private repositories, `publish_results` will automatically be set to `false`,
# regardless of the value entered here.
publish_results: true
# Upload the results as artifacts (optional).
- name: "Upload artifact"
uses: actions/upload-artifact@82c141cc518b40d92cc801eee768e7aafc9c2fa2 # v2.3.1
with:
name: SARIF file
path: results.sarif
retention-days: 5
# Upload the results to GitHub's code scanning dashboard.
- name: "Upload to code-scanning"
uses: github/codeql-action/upload-sarif@5f532563584d71fdef14ee64d17bafb34f751ce5 # v1.0.26
with:
sarif_file: results.sarif

314
Kha/Backends/Kore-hxcpp/khacpp/project/thirdparty/pcre2-10.42-16/132html vendored Normal file
View File

@ -0,0 +1,314 @@
#! /usr/bin/perl -w
# Script to turn PCRE2 man pages into HTML
# Subroutine to handle font changes and other escapes
sub do_line {
my($s) = $_[0];
$s =~ s/</&#60;/g; # Deal with < and >
$s =~ s/>/&#62;/g;
$s =~ s"\\fI(.*?)\\f[RP]"<i>$1</i>"g;
$s =~ s"\\fB(.*?)\\f[RP]"<b>$1</b>"g;
$s =~ s"\\e"\\"g;
$s =~ s/(?<=Copyright )\(c\)/&copy;/g;
$s;
}
# Subroutine to ensure not in a paragraph
sub end_para {
if ($inpara)
{
print TEMP "</PRE>\n" if ($inpre);
print TEMP "</P>\n";
}
$inpara = $inpre = 0;
$wrotetext = 0;
}
# Subroutine to start a new paragraph
sub new_para {
&end_para();
print TEMP "<P>\n";
$inpara = 1;
}
# Main program
$innf = 0;
$inpara = 0;
$inpre = 0;
$wrotetext = 0;
$toc = 0;
$ref = 1;
while ($#ARGV >= 0 && $ARGV[0] =~ /^-/)
{
$toc = 1 if $ARGV[0] eq "-toc";
shift;
}
# Initial output to STDOUT
print <<End ;
<html>
<head>
<title>$ARGV[0] specification</title>
</head>
<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB">
<h1>$ARGV[0] man page</h1>
<p>
Return to the <a href="index.html">PCRE2 index page</a>.
</p>
<p>
This page is part of the PCRE2 HTML documentation. It was generated
automatically from the original man page. If there is any nonsense in it,
please consult the man page, in case the conversion went wrong.
<br>
End
print "<ul>\n" if ($toc);
open(TEMP, ">/tmp/$$") || die "Can't open /tmp/$$ for output\n";
while (<STDIN>)
{
# Handle lines beginning with a dot
if (/^\./)
{
# Some of the PCRE2 man pages used to contain instances of .br. However,
# they should have all been removed because they cause trouble in some
# (other) automated systems that translate man pages to HTML. Complain if
# we find .br or .in (another macro that is deprecated).
if (/^\.br/ || /^\.in/)
{
print STDERR "\n*** Deprecated macro encountered - rewrite needed\n";
print STDERR "*** $_\n";
die "*** Processing abandoned\n";
}
# Instead of .br, relevant "literal" sections are enclosed in .nf/.fi.
elsif (/^\.nf/)
{
$innf = 1;
}
elsif (/^\.fi/)
{
$innf = 0;
}
# Handling .sp is subtle. If it is inside a literal section, do nothing if
# the next line is a non literal text line; similarly, if not inside a
# literal section, do nothing if a literal follows, unless we are inside
# a .nf/.fi section or about to enter one. The point being that the <pre>
# and </pre> that delimit literal sections will do the spacing. Always skip
# if no previous output.
elsif (/^\.sp/)
{
if ($wrotetext)
{
$_ = <STDIN>;
if ($inpre)
{
print TEMP "\n" if (/^[\s.]/);
}
else
{
print TEMP "<br>\n<br>\n" if ($innf || /^\.nf/ || !/^[\s.]/);
}
redo; # Now process the lookahead line we just read
}
}
elsif (/^\.TP/ || /^\.PP/ || /^\.P/)
{
&new_para();
}
elsif (/^\.SH\s*("?)(.*)\1/)
{
# Ignore the NAME section
if ($2 =~ /^NAME\b/)
{
<STDIN>;
next;
}
&end_para();
my($title) = &do_line($2);
if ($toc)
{
printf("<li><a name=\"TOC%d\" href=\"#SEC%d\">$title</a>\n",
$ref, $ref);
printf TEMP ("<br><a name=\"SEC%d\" href=\"#TOC1\">$title</a><br>\n",
$ref);
$ref++;
}
else
{
print TEMP "<br><b>\n$title\n</b><br>\n";
}
}
elsif (/^\.SS\s*("?)(.*)\1/)
{
&end_para();
my($title) = &do_line($2);
print TEMP "<br><b>\n$title\n</b><br>\n";
}
elsif (/^\.B\s*(.*)/)
{
&new_para() if (!$inpara);
$_ = &do_line($1);
s/"(.*?)"/$1/g;
print TEMP "<b>$_</b>\n";
$wrotetext = 1;
}
elsif (/^\.I\s*(.*)/)
{
&new_para() if (!$inpara);
$_ = &do_line($1);
s/"(.*?)"/$1/g;
print TEMP "<i>$_</i>\n";
$wrotetext = 1;
}
# A comment that starts "HREF" takes the next line as a name that
# is turned into a hyperlink, using the text given, which might be
# in a special font. If it ends in () or (digits) or punctuation, they
# aren't part of the link.
elsif (/^\.\\"\s*HREF/)
{
$_=<STDIN>;
chomp;
$_ = &do_line($_);
$_ =~ s/\s+$//;
$_ =~ /^(?:<.>)?([^<(]+)(?:\(\))?(?:<\/.>)?(?:\(\d+\))?[.,;:]?$/;
print TEMP "<a href=\"$1.html\">$_</a>\n";
}
# A comment that starts "HTML" inserts literal HTML
elsif (/^\.\\"\s*HTML\s*(.*)/)
{
print TEMP $1;
}
# A comment that starts < inserts that HTML at the end of the
# *next* input line - so as not to get a newline between them.
elsif (/^\.\\"\s*(<.*>)/)
{
my($markup) = $1;
$_=<STDIN>;
chomp;
$_ = &do_line($_);
$_ =~ s/\s+$//;
print TEMP "$_$markup\n";
}
# A comment that starts JOIN joins the next two lines together, with one
# space between them. Then that line is processed. This is used in some
# displays where two lines are needed for the "man" version. JOINSH works
# the same, except that it assumes this is a shell command, so removes
# continuation backslashes.
elsif (/^\.\\"\s*JOIN(SH)?/)
{
my($one,$two);
$one = <STDIN>;
$two = <STDIN>;
$one =~ s/\s*\\e\s*$// if (defined($1));
chomp($one);
$two =~ s/^\s+//;
$_ = "$one $two";
redo; # Process the joined lines
}
# .EX/.EE are used in the pcre2demo page to bracket the entire program,
# which is unmodified except for turning backslash into "\e".
elsif (/^\.EX\s*$/)
{
print TEMP "<PRE>\n";
while (<STDIN>)
{
last if /^\.EE\s*$/;
s/\\e/\\/g;
s/&/&amp;/g;
s/</&lt;/g;
s/>/&gt;/g;
print TEMP;
}
}
# Ignore anything not recognized
next;
}
# Line does not begin with a dot. Replace blank lines with new paragraphs
if (/^\s*$/)
{
&end_para() if ($wrotetext);
next;
}
# Convert fonts changes and output an ordinary line. Ensure that indented
# lines are marked as literal.
$_ = &do_line($_);
&new_para() if (!$inpara);
if (/^\s/)
{
if (!$inpre)
{
print TEMP "<pre>\n";
$inpre = 1;
}
}
elsif ($inpre)
{
print TEMP "</pre>\n";
$inpre = 0;
}
# Add <br> to the end of a non-literal line if we are within .nf/.fi
$_ .= "<br>\n" if (!$inpre && $innf);
print TEMP;
$wrotetext = 1;
}
# The TOC, if present, will have been written - terminate it
print "</ul>\n" if ($toc);
# Copy the remainder to the standard output
close(TEMP);
open(TEMP, "/tmp/$$") || die "Can't open /tmp/$$ for input\n";
print while (<TEMP>);
print <<End ;
<p>
Return to the <a href="index.html">PCRE2 index page</a>.
</p>
End
close(TEMP);
unlink("/tmp/$$");
# End

36
Kha/Backends/Kore-hxcpp/khacpp/project/thirdparty/pcre2-10.42-16/AUTHORS vendored Normal file
View File

@ -0,0 +1,36 @@
THE MAIN PCRE2 LIBRARY CODE
---------------------------
Written by: Philip Hazel
Email local part: Philip.Hazel
Email domain: gmail.com
Retired from University of Cambridge Computing Service,
Cambridge, England.
Copyright (c) 1997-2022 University of Cambridge
All rights reserved
PCRE2 JUST-IN-TIME COMPILATION SUPPORT
--------------------------------------
Written by: Zoltan Herczeg
Email local part: hzmester
Emain domain: freemail.hu
Copyright(c) 2010-2022 Zoltan Herczeg
All rights reserved.
STACK-LESS JUST-IN-TIME COMPILER
--------------------------------
Written by: Zoltan Herczeg
Email local part: hzmester
Emain domain: freemail.hu
Copyright(c) 2009-2022 Zoltan Herczeg
All rights reserved.
####

72
Kha/Backends/Kore-hxcpp/khacpp/project/thirdparty/pcre2-10.42-16/BUILD.bazel vendored Normal file
View File

@ -0,0 +1,72 @@
load("@rules_cc//cc:defs.bzl", "cc_library", "cc_test")
load("@bazel_skylib//rules:copy_file.bzl", "copy_file")
copy_file(
name = "config_h_generic",
src = "src/config.h.generic",
out = "src/config.h",
)
copy_file(
name = "pcre2_h_generic",
src = "src/pcre2.h.generic",
out = "src/pcre2.h",
)
copy_file(
name = "pcre2_chartables_c",
src = "src/pcre2_chartables.c.dist",
out = "src/pcre2_chartables.c",
)
cc_library(
name = "pcre2",
srcs = [
"src/pcre2_auto_possess.c",
"src/pcre2_compile.c",
"src/pcre2_config.c",
"src/pcre2_context.c",
"src/pcre2_convert.c",
"src/pcre2_dfa_match.c",
"src/pcre2_error.c",
"src/pcre2_extuni.c",
"src/pcre2_find_bracket.c",
"src/pcre2_maketables.c",
"src/pcre2_match.c",
"src/pcre2_match_data.c",
"src/pcre2_newline.c",
"src/pcre2_ord2utf.c",
"src/pcre2_pattern_info.c",
"src/pcre2_script_run.c",
"src/pcre2_serialize.c",
"src/pcre2_string_utils.c",
"src/pcre2_study.c",
"src/pcre2_substitute.c",
"src/pcre2_substring.c",
"src/pcre2_tables.c",
"src/pcre2_ucd.c",
"src/pcre2_ucptables.c",
"src/pcre2_valid_utf.c",
"src/pcre2_xclass.c",
":pcre2_chartables_c",
],
hdrs = glob(["src/*.h"]) + [
":config_h_generic",
":pcre2_h_generic",
],
defines = [
"HAVE_CONFIG_H",
"PCRE2_CODE_UNIT_WIDTH=8",
"PCRE2_STATIC",
],
includes = ["src"],
strip_include_prefix = "src",
visibility = ["//visibility:public"],
)
cc_binary(
name = "pcre2demo",
srcs = ["src/pcre2demo.c"],
visibility = ["//visibility:public"],
deps = [":pcre2"],
)

1201
Kha/Backends/Kore-hxcpp/khacpp/project/thirdparty/pcre2-10.42-16/CMakeLists.txt vendored Normal file
View File

File diff suppressed because it is too large Load Diff

5
Kha/Backends/Kore-hxcpp/khacpp/project/thirdparty/pcre2-10.42-16/COPYING vendored Normal file
View File

@ -0,0 +1,5 @@
PCRE2 LICENCE
Please see the file LICENCE in the PCRE2 distribution for licensing details.
End

2827
Kha/Backends/Kore-hxcpp/khacpp/project/thirdparty/pcre2-10.42-16/ChangeLog vendored Normal file
View File

File diff suppressed because it is too large Load Diff

78
Kha/Backends/Kore-hxcpp/khacpp/project/thirdparty/pcre2-10.42-16/CheckMan vendored Normal file
View File

@ -0,0 +1,78 @@
#! /usr/bin/perl
# A script to scan PCRE2's man pages to check for typos in the control
# sequences. I use only a small set of the available repertoire, so it is
# straightforward to check that nothing else has slipped in by mistake. This
# script should be called in the doc directory.
$yield = 0;
while (scalar(@ARGV) > 0)
{
$line = 0;
$file = shift @ARGV;
open (IN, $file) || die "Failed to open $file\n";
while (<IN>)
{
$count = 0;
$line++;
if (/^\s*$/)
{
printf "Empty line $line of $file\n";
$yield = 1;
}
elsif (/^\./)
{
if (!/^\.\s*$|
^\.B\s+\S|
^\.TH\s\S|
^\.SH\s\S|
^\.SS\s\S|
^\.TP(?:\s?\d+)?\s*$|
^\.SM\s*$|
^\.br\s*$|
^\.rs\s*$|
^\.sp\s*$|
^\.nf\s*$|
^\.fi\s*$|
^\.P\s*$|
^\.PP\s*$|
^\.\\"(?:\ HREF)?\s*$|
^\.\\"\sHTML\s<a\shref="[^"]+?">\s*$|
^\.\\"\sHTML\s<a\sname="[^"]+?"><\/a>\s*$|
^\.\\"\s<\/a>\s*$|
^\.\\"\sJOINSH\s*$|
^\.\\"\sJOIN\s*$/x
)
{
printf "Bad control line $line of $file\n";
$yield = 1;
}
}
elsif (/\\[^ef]|\\f[^IBP]/)
{
printf "Bad backslash in line $line of $file\n";
$yield = 1;
}
while (/\\f[BI]/g)
{
$count++;
}
while (/\\fP/g)
{
$count--;
}
if ($count != 0)
{
printf "Mismatching formatting in line $line of $file\n";
$yield = 1;
}
}
close(IN);
}
exit $yield;
# End

113
Kha/Backends/Kore-hxcpp/khacpp/project/thirdparty/pcre2-10.42-16/CleanTxt vendored Normal file
View File

@ -0,0 +1,113 @@
#! /usr/bin/perl -w
# Script to take the output of nroff -man and remove all the backspacing and
# the page footers and the screen commands etc so that it is more usefully
# readable online. In fact, in the latest nroff, intermediate footers don't
# seem to be generated any more.
$blankcount = 0;
$lastwascut = 0;
$firstheader = 1;
# Input on STDIN; output to STDOUT.
while (<STDIN>)
{
s/\x1b\[\d+m//g; # Remove screen controls "ESC [ number m"
s/.\x8//g; # Remove "char, backspace"
# Handle header lines. Retain only the first one we encounter, but remove
# the blank line that follows. Any others (e.g. at end of document) and the
# following blank line are dropped.
if (/^PCRE(\w*)\(([13])\)\s+PCRE\1\(\2\)$/)
{
if ($firstheader)
{
$firstheader = 0;
print;
$lastprinted = $_;
$lastwascut = 0;
}
$_=<STDIN>; # Remove a blank that follows
next;
}
# Count runs of empty lines
if (/^\s*$/)
{
$blankcount++;
$lastwascut = 0;
next;
}
# If a chunk of lines has been cut out (page footer) and the next line
# has a different indentation, put back one blank line.
if ($lastwascut && $blankcount < 1 && defined($lastprinted))
{
($a) = $lastprinted =~ /^(\s*)/;
($b) = $_ =~ /^(\s*)/;
$blankcount++ if ($a ne $b);
}
# We get here only when we have a non-blank line in hand. If it was preceded
# by 3 or more blank lines, read the next 3 lines and see if they are blank.
# If so, remove all 7 lines, and remember that we have just done a cut.
if ($blankcount >= 3)
{
for ($i = 0; $i < 3; $i++)
{
$next[$i] = <STDIN>;
$next[$i] = "" if !defined $next[$i];
$next[$i] =~ s/\x1b\[\d+m//g; # Remove screen controls "ESC [ number m"
$next[$i] =~ s/.\x8//g; # Remove "char, backspace"
}
# Cut out chunks of the form <3 blanks><non-blank><3 blanks>
if ($next[0] =~ /^\s*$/ &&
$next[1] =~ /^\s*$/ &&
$next[2] =~ /^\s*$/)
{
$blankcount -= 3;
$lastwascut = 1;
}
# Otherwise output the saved blanks, the current, and the next three
# lines. Remember the last printed line.
else
{
for ($i = 0; $i < $blankcount; $i++) { print "\n"; }
print;
for ($i = 0; $i < 3; $i++)
{
$next[$i] =~ s/.\x8//g;
print $next[$i];
$lastprinted = $_;
}
$lastwascut = 0;
$blankcount = 0;
}
}
# This non-blank line is not preceded by 3 or more blank lines. Output
# any blanks there are, and the line. Remember it. Force two blank lines
# before headings.
else
{
$blankcount = 2 if /^\S/ && !/^Last updated/ && !/^Copyright/ &&
defined($lastprinted);
for ($i = 0; $i < $blankcount; $i++) { print "\n"; }
print;
$lastprinted = $_;
$lastwascut = 0;
$blankcount = 0;
}
}
# End

35
Kha/Backends/Kore-hxcpp/khacpp/project/thirdparty/pcre2-10.42-16/Detrail vendored Normal file
View File

@ -0,0 +1,35 @@
#!/usr/bin/perl
# This is a script for removing trailing whitespace from lines in files that
# are listed on the command line.
# This subroutine does the work for one file.
sub detrail {
my($file) = $_[0];
my($changed) = 0;
open(IN, "$file") || die "Can't open $file for input";
@lines = <IN>;
close(IN);
foreach (@lines)
{
if (/\s+\n$/)
{
s/\s+\n$/\n/;
$changed = 1;
}
}
if ($changed)
{
open(OUT, ">$file") || die "Can't open $file for output";
print OUT @lines;
close(OUT);
}
}
# This is the main program
$, = ""; # Output field separator
for ($i = 0; $i < @ARGV; $i++) { &detrail($ARGV[$i]); }
# End

830
Kha/Backends/Kore-hxcpp/khacpp/project/thirdparty/pcre2-10.42-16/HACKING vendored Normal file
View File

@ -0,0 +1,830 @@
Technical Notes about PCRE2
---------------------------
These are very rough technical notes that record potentially useful information
about PCRE2 internals. PCRE2 is a library based on the original PCRE library,
but with a revised (and incompatible) API. To avoid confusion, the original
library is referred to as PCRE1 below. For information about testing PCRE2, see
the pcre2test documentation and the comment at the head of the RunTest file.
PCRE1 releases were up to 8.3x when PCRE2 was developed, and later bug fix
releases carried on the 8.xx series, up to the final 8.45 release. PCRE2
releases started at 10.00 to avoid confusion with PCRE1.
Historical note 1
-----------------
Many years ago I implemented some regular expression functions to an algorithm
suggested by Martin Richards. The rather simple patterns were not Unix-like in
form, and were quite restricted in what they could do by comparison with Perl.
The interesting part about the algorithm was that the amount of space required
to hold the compiled form of an expression was known in advance. The code to
apply an expression did not operate by backtracking, as the original Henry
Spencer code and current PCRE2 and Perl code does, but instead checked all
possibilities simultaneously by keeping a list of current states and checking
all of them as it advanced through the subject string. In the terminology of
Jeffrey Friedl's book, it was a "DFA algorithm", though it was not a
traditional Finite State Machine (FSM). When the pattern was all used up, all
remaining states were possible matches, and the one matching the longest subset
of the subject string was chosen. This did not necessarily maximize the
individual wild portions of the pattern, as is expected in Unix and Perl-style
regular expressions.
Historical note 2
-----------------
By contrast, the code originally written by Henry Spencer (which was
subsequently heavily modified for Perl) compiles the expression twice: once in
a dummy mode in order to find out how much store will be needed, and then for
real. (The Perl version may or may not still do this; I'm talking about the
original library.) The execution function operates by backtracking and
maximizing (or, optionally, minimizing, in Perl) the amount of the subject that
matches individual wild portions of the pattern. This is an "NFA algorithm" in
Friedl's terminology.
OK, here's the real stuff
-------------------------
For the set of functions that formed the original PCRE1 library in 1997 (which
are unrelated to those mentioned above), I tried at first to invent an
algorithm that used an amount of store bounded by a multiple of the number of
characters in the pattern, to save on compiling time. However, because of the
greater complexity in Perl regular expressions, I couldn't do this, even though
the then current Perl 5.004 patterns were much simpler than those supported
nowadays. In any case, a first pass through the pattern is helpful for other
reasons.
Support for 16-bit and 32-bit data strings
-------------------------------------------
The PCRE2 library can be compiled in any combination of 8-bit, 16-bit or 32-bit
modes, creating up to three different libraries. In the description that
follows, the word "short" is used for a 16-bit data quantity, and the phrase
"code unit" is used for a quantity that is a byte in 8-bit mode, a short in
16-bit mode and a 32-bit word in 32-bit mode. The names of PCRE2 functions are
given in generic form, without the _8, _16, or _32 suffix.
Computing the memory requirement: how it was
--------------------------------------------
Up to and including release 6.7, PCRE1 worked by running a very degenerate
first pass to calculate a maximum memory requirement, and then a second pass to
do the real compile - which might use a bit less than the predicted amount of
memory. The idea was that this would turn out faster than the Henry Spencer
code because the first pass is degenerate and the second pass can just store
stuff straight into memory, which it knows is big enough.
Computing the memory requirement: how it is
-------------------------------------------
By the time I was working on a potential 6.8 release, the degenerate first pass
had become very complicated and hard to maintain. Indeed one of the early
things I did for 6.8 was to fix Yet Another Bug in the memory computation. Then
I had a flash of inspiration as to how I could run the real compile function in
a "fake" mode that enables it to compute how much memory it would need, while
in most cases only ever using a small amount of working memory, and without too
many tests of the mode that might slow it down. So I refactored the compiling
functions to work this way. This got rid of about 600 lines of source and made
further maintenance and development easier. As this was such a major change, I
never released 6.8, instead upping the number to 7.0 (other quite major changes
were also present in the 7.0 release).
A side effect of this work was that the previous limit of 200 on the nesting
depth of parentheses was removed. However, there was a downside: compiling ran
more slowly than before (30% or more, depending on the pattern) because it now
did a full analysis of the pattern. My hope was that this would not be a big
issue, and in the event, nobody has commented on it.
At release 8.34, a limit on the nesting depth of parentheses was re-introduced
(default 250, settable at build time) so as to put a limit on the amount of
system stack used by the compile function, which uses recursive function calls
for nested parenthesized groups. This is a safety feature for environments with
small stacks where the patterns are provided by users.
Yet another pattern scan
------------------------
History repeated itself for PCRE2 release 10.20. A number of bugs relating to
named subpatterns had been discovered by fuzzers. Most of these were related to
the handling of forward references when it was not known if the named group was
unique. (References to non-unique names use a different opcode and more
memory.) The use of duplicate group numbers (the (?| facility) also caused
issues.
To get around these problems I adopted a new approach by adding a third pass
over the pattern (really a "pre-pass"), which did nothing other than identify
all the named subpatterns and their corresponding group numbers. This means
that the actual compile (both the memory-computing dummy run and the real
compile) has full knowledge of group names and numbers throughout. Several
dozen lines of messy code were eliminated, though the new pre-pass was not
short. In particular, parsing and skipping over [] classes is complicated.
While working on 10.22 I realized that I could simplify yet again by moving
more of the parsing into the pre-pass, thus avoiding doing it in two places, so
after 10.22 was released, the code underwent yet another big refactoring. This
is how it is from 10.23 onwards:
The function called parse_regex() scans the pattern characters, parsing them
into literal data and meta characters. It converts escapes such as \x{123}
into literals, handles \Q...\E, and skips over comments and non-significant
white space. The result of the scanning is put into a vector of 32-bit unsigned
integers. Values less than 0x80000000 are literal data. Higher values represent
meta-characters. The top 16-bits of such values identify the meta-character,
and these are given names such as META_CAPTURE. The lower 16-bits are available
for data, for example, the capturing group number. The only situation in which
literal data values greater than 0x7fffffff can appear is when the 32-bit
library is running in non-UTF mode. This is handled by having a special
meta-character that is followed by the 32-bit data value.
The size of the parsed pattern vector, when auto-callouts are not enabled, is
bounded by the length of the pattern (with one exception). The code is written
so that each item in the pattern uses no more vector elements than the number
of code units in the item itself. The exception is the aforementioned large
32-bit number handling. For this reason, 32-bit non-UTF patterns are scanned in
advance to check for such values. When auto-callouts are enabled, the generous
assumption is made that there will be a callout for each pattern code unit
(which of course is only actually true if all code units are literals) plus one
at the end. A default parsed pattern vector is defined on the system stack, to
minimize memory handling, but if this is not big enough, heap memory is used.
As before, the actual compiling function is run twice, the first time to
determine the amount of memory needed for the final compiled pattern. It
now processes the parsed pattern vector, not the pattern itself, although some
of the parsed items refer to strings in the pattern - for example, group
names. As escapes and comments have already been processed, the code is a bit
simpler than before.
Most errors can be diagnosed during the parsing scan. For those that cannot
(for example, "lookbehind assertion is not fixed length"), the parsed code
contains offsets into the pattern so that the actual compiling code can
report where errors are.
The elements of the parsed pattern vector
-----------------------------------------
The word "offset" below means a code unit offset into the pattern. When
PCRE2_SIZE (which is usually size_t) is no bigger than uint32_t, an offset is
stored in a single parsed pattern element. Otherwise (typically on 64-bit
systems) it occupies two elements. The following meta items occupy just one
element, with no data:
META_ACCEPT (*ACCEPT)
META_ASTERISK *
META_ASTERISK_PLUS *+
META_ASTERISK_QUERY *?
META_ATOMIC (?> start of atomic group
META_CIRCUMFLEX ^ metacharacter
META_CLASS [ start of non-empty class
META_CLASS_EMPTY [] empty class - only with PCRE2_ALLOW_EMPTY_CLASS
META_CLASS_EMPTY_NOT [^] negative empty class - ditto
META_CLASS_END ] end of non-empty class
META_CLASS_NOT [^ start non-empty negative class
META_COMMIT (*COMMIT) - no argument (see below for with argument)
META_COND_ASSERT (?(?assertion)
META_DOLLAR $ metacharacter
META_DOT . metacharacter
META_END End of pattern (this value is 0x80000000)
META_FAIL (*FAIL)
META_KET ) closing parenthesis
META_LOOKAHEAD (?= start of lookahead
META_LOOKAHEAD_NA (*napla: start of non-atomic lookahead
META_LOOKAHEADNOT (?! start of negative lookahead
META_NOCAPTURE (?: no capture parens
META_PLUS +
META_PLUS_PLUS ++
META_PLUS_QUERY +?
META_PRUNE (*PRUNE) - no argument (see below for with argument)
META_QUERY ?
META_QUERY_PLUS ?+
META_QUERY_QUERY ??
META_RANGE_ESCAPED hyphen in class range with at least one escape
META_RANGE_LITERAL hyphen in class range defined literally
META_SKIP (*SKIP) - no argument (see below for with argument)
META_THEN (*THEN) - no argument (see below for with argument)
The two RANGE values occur only in character classes. They are positioned
between two literals that define the start and end of the range. In an EBCDIC
environment it is necessary to know whether either of the range values was
specified as an escape. In an ASCII/Unicode environment the distinction is not
relevant.
The following have data in the lower 16 bits, and may be followed by other data
elements:
META_ALT | alternation
META_BACKREF back reference
META_CAPTURE start of capturing group
META_ESCAPE non-literal escape sequence
META_RECURSE recursion call
If the data for META_ALT is non-zero, it is inside a lookbehind, and the data
is the length of its branch, for which OP_REVERSE must be generated.
META_BACKREF, META_CAPTURE, and META_RECURSE have the capture group number as
their data in the lower 16 bits of the element. META_RECURSE is followed by an
offset, for use in error messages.
META_BACKREF is followed by an offset if the back reference group number is 10
or more. The offsets of the first occurrences of references to groups whose
numbers are less than 10 are put in cb->small_ref_offset[] (only the first
occurrence is useful). On 64-bit systems this avoids using more than two parsed
pattern elements for items such as \3. The offset is used when an error occurs
because the reference is to a non-existent group.
META_ESCAPE has an ESC_xxx value as its data. For ESC_P and ESC_p, the next
element contains the 16-bit type and data property values, packed together.
ESC_g and ESC_k are used only for named references - numerical ones are turned
into META_RECURSE or META_BACKREF as appropriate. ESC_g and ESC_k are followed
by a length and an offset into the pattern to specify the name.
The following have one data item that follows in the next vector element:
META_BIGVALUE Next is a literal >= META_END
META_OPTIONS (?i) and friends (data is new option bits)
META_POSIX POSIX class item (data identifies the class)
META_POSIX_NEG negative POSIX class item (ditto)
The following are followed by a length element, then a number of character code
values (which should match with the length):
META_MARK (*MARK:xxxx)
META_COMMIT_ARG )*COMMIT:xxxx)
META_PRUNE_ARG (*PRUNE:xxx)
META_SKIP_ARG (*SKIP:xxxx)
META_THEN_ARG (*THEN:xxxx)
The following are followed by a length element, then an offset in the pattern
that identifies the name:
META_COND_NAME (?(<name>) or (?('name') or (?(name)
META_COND_RNAME (?(R&name)
META_COND_RNUMBER (?(Rdigits)
META_RECURSE_BYNAME (?&name)
META_BACKREF_BYNAME \k'name'
META_COND_RNUMBER is used for names that start with R and continue with digits,
because this is an ambiguous case. It could be a back reference to a group with
that name, or it could be a recursion test on a numbered group.
This one is followed by an offset, for use in error messages, then a number:
META_COND_NUMBER (?([+-]digits)
The following is followed just by an offset, for use in error messages:
META_COND_DEFINE (?(DEFINE)
The following are also followed just by an offset, but also the lower 16 bits
of the main word contain the length of the first branch of the lookbehind
group; this is used when generating OP_REVERSE for that branch.
META_LOOKBEHIND (?<= start of lookbehind
META_LOOKBEHIND_NA (*naplb: start of non-atomic lookbehind
META_LOOKBEHINDNOT (?<! start of negative lookbehind
The following are followed by two elements, the minimum and maximum. The
maximum value is limited to 65535 (MAX_REPEAT). A maximum value of "unlimited"
is represented by UNLIMITED_REPEAT, which is bigger than MAX_REPEAT:
META_MINMAX {n,m} repeat
META_MINMAX_PLUS {n,m}+ repeat
META_MINMAX_QUERY {n,m}? repeat
This one is followed by three elements. The first is 0 for '>' and 1 for '>=';
the next two are the major and minor numbers:
META_COND_VERSION (?(VERSION<op>x.y)
Callouts are converted into one of two items:
META_CALLOUT_NUMBER (?C with numerical argument
META_CALLOUT_STRING (?C with string argument
In both cases, the next two elements contain the offset and length of the next
item in the pattern. Then there is either one callout number, or a length and
an offset for the string argument. The length includes both delimiters.
Traditional matching function
-----------------------------
The "traditional", and original, matching function is called pcre2_match(), and
it implements an NFA algorithm, similar to the original Henry Spencer algorithm
and the way that Perl works. This is not surprising, since it is intended to be
as compatible with Perl as possible. This is the function most users of PCRE2
will use most of the time. If PCRE2 is compiled with just-in-time (JIT)
support, and studying a compiled pattern with JIT is successful, the JIT code
is run instead of the normal pcre2_match() code, but the result is the same.
Supplementary matching function
-------------------------------
There is also a supplementary matching function called pcre2_dfa_match(). This
implements a DFA matching algorithm that searches simultaneously for all
possible matches that start at one point in the subject string. (Going back to
my roots: see Historical Note 1 above.) This function intreprets the same
compiled pattern data as pcre2_match(); however, not all the facilities are
available, and those that are do not always work in quite the same way. See the
user documentation for details.
The algorithm that is used for pcre2_dfa_match() is not a traditional FSM,
because it may have a number of states active at one time. More work would be
needed at compile time to produce a traditional FSM where only one state is
ever active at once. I believe some other regex matchers work this way. JIT
support is not available for this kind of matching.
Changeable options
------------------
The /i, /m, or /s options (PCRE2_CASELESS, PCRE2_MULTILINE, PCRE2_DOTALL) and
some others may be changed in the middle of patterns by items such as (?i).
Their processing is handled entirely at compile time by generating different
opcodes for the different settings. The runtime functions do not need to keep
track of an option's state.
PCRE2_DUPNAMES, PCRE2_EXTENDED, PCRE2_EXTENDED_MORE, and PCRE2_NO_AUTO_CAPTURE
are tracked and processed during the parsing pre-pass. The others are handled
from META_OPTIONS items during the main compile phase.
Format of compiled patterns
---------------------------
The compiled form of a pattern is a vector of unsigned code units (bytes in
8-bit mode, shorts in 16-bit mode, 32-bit words in 32-bit mode), containing
items of variable length. The first code unit in an item contains an opcode,
and the length of the item is either implicit in the opcode or contained in the
data that follows it.
In many cases listed below, LINK_SIZE data values are specified for offsets
within the compiled pattern. LINK_SIZE always specifies a number of bytes. The
default value for LINK_SIZE is 2, except for the 32-bit library, where it can
only be 4. The 8-bit library can be compiled to used 3-byte or 4-byte values,
and the 16-bit library can be compiled to use 4-byte values, though this
impairs performance. Specifying a LINK_SIZE larger than 2 for these libraries is
necessary only when patterns whose compiled length is greater than 65535 code
units are going to be processed. When a LINK_SIZE value uses more than one code
unit, the most significant unit is first.
In this description, we assume the "normal" compilation options. Data values
that are counts (e.g. quantifiers) are always two bytes long in 8-bit mode
(most significant byte first), and one code unit in 16-bit and 32-bit modes.
Opcodes with no following data
------------------------------
These items are all just one unit long:
OP_END end of pattern
OP_ANY match any one character other than newline
OP_ALLANY match any one character, including newline
OP_ANYBYTE match any single code unit, even in UTF-8/16 mode
OP_SOD match start of data: \A
OP_SOM, start of match (subject + offset): \G
OP_SET_SOM, set start of match (\K)
OP_CIRC ^ (start of data)
OP_CIRCM ^ multiline mode (start of data or after newline)
OP_NOT_WORD_BOUNDARY \W
OP_WORD_BOUNDARY \w
OP_NOT_DIGIT \D
OP_DIGIT \d
OP_NOT_HSPACE \H
OP_HSPACE \h
OP_NOT_WHITESPACE \S
OP_WHITESPACE \s
OP_NOT_VSPACE \V
OP_VSPACE \v
OP_NOT_WORDCHAR \W
OP_WORDCHAR \w
OP_EODN match end of data or newline at end: \Z
OP_EOD match end of data: \z
OP_DOLL $ (end of data, or before final newline)
OP_DOLLM $ multiline mode (end of data or before newline)
OP_EXTUNI match an extended Unicode grapheme cluster
OP_ANYNL match any Unicode newline sequence
OP_ASSERT_ACCEPT )
OP_ACCEPT ) These are Perl 5.10's "backtracking control
OP_COMMIT ) verbs". If OP_ACCEPT is inside capturing
OP_FAIL ) parentheses, it may be preceded by one or more
OP_PRUNE ) OP_CLOSE, each followed by a number that
OP_SKIP ) indicates which parentheses must be closed.
OP_THEN )
OP_ASSERT_ACCEPT is used when (*ACCEPT) is encountered within an assertion.
This ends the assertion, not the entire pattern match. The assertion (?!) is
always optimized to OP_FAIL.
OP_ALLANY is used for '.' when PCRE2_DOTALL is set. It is also used for \C in
non-UTF modes and in UTF-32 mode (since one code unit still equals one
character). Another use is for [^] when empty classes are permitted
(PCRE2_ALLOW_EMPTY_CLASS is set).
Backtracking control verbs
--------------------------
Verbs with no arguments generate opcodes with no following data (as listed
in the section above).
(*MARK:NAME) generates OP_MARK followed by the mark name, preceded by a
length in one code unit, and followed by a binary zero. The name length is
limited by the size of the code unit.
(*ACCEPT:NAME) and (*FAIL:NAME) are compiled as (*MARK:NAME)(*ACCEPT) and
(*MARK:NAME)(*FAIL) respectively.
For (*COMMIT:NAME), (*PRUNE:NAME), (*SKIP:NAME), and (*THEN:NAME), the opcodes
OP_COMMIT_ARG, OP_PRUNE_ARG, OP_SKIP_ARG, and OP_THEN_ARG are used, with the
name following in the same format as for OP_MARK.
Matching literal characters
---------------------------
The OP_CHAR opcode is followed by a single character that is to be matched
casefully. For caseless matching of characters that have at most two
case-equivalent code points, OP_CHARI is used. In UTF-8 or UTF-16 modes, the
character may be more than one code unit long. In UTF-32 mode, characters are
always exactly one code unit long.
If there is only one character in a character class, OP_CHAR or OP_CHARI is
used for a positive class, and OP_NOT or OP_NOTI for a negative one (that is,
for something like [^a]).
Caseless matching (positive or negative) of characters that have more than two
case-equivalent code points (which is possible only in UTF mode) is handled by
compiling a Unicode property item (see below), with the pseudo-property
PT_CLIST. The value of this property is an offset in a vector called
"ucd_caseless_sets" which identifies the start of a short list of case
equivalent characters, terminated by the value NOTACHAR (0xffffffff).
Repeating single characters
---------------------------
The common repeats (*, +, ?), when applied to a single character, use the
following opcodes, which come in caseful and caseless versions:
Caseful Caseless
OP_STAR OP_STARI
OP_MINSTAR OP_MINSTARI
OP_POSSTAR OP_POSSTARI
OP_PLUS OP_PLUSI
OP_MINPLUS OP_MINPLUSI
OP_POSPLUS OP_POSPLUSI
OP_QUERY OP_QUERYI
OP_MINQUERY OP_MINQUERYI
OP_POSQUERY OP_POSQUERYI
Each opcode is followed by the character that is to be repeated. In ASCII or
UTF-32 modes, these are two-code-unit items; in UTF-8 or UTF-16 modes, the
length is variable. Those with "MIN" in their names are the minimizing
versions. Those with "POS" in their names are possessive versions. Other kinds
of repeat make use of these opcodes:
Caseful Caseless
OP_UPTO OP_UPTOI
OP_MINUPTO OP_MINUPTOI
OP_POSUPTO OP_POSUPTOI
OP_EXACT OP_EXACTI
Each of these is followed by a count and then the repeated character. The count
is two bytes long in 8-bit mode (most significant byte first), or one code unit
in 16-bit and 32-bit modes.
OP_UPTO matches from 0 to the given number. A repeat with a non-zero minimum
and a fixed maximum is coded as an OP_EXACT followed by an OP_UPTO (or
OP_MINUPTO or OPT_POSUPTO).
Another set of matching repeating opcodes (called OP_NOTSTAR, OP_NOTSTARI,
etc.) are used for repeated, negated, single-character classes such as [^a]*.
The normal single-character opcodes (OP_STAR, etc.) are used for repeated
positive single-character classes.
Repeating character types
-------------------------
Repeats of things like \d are done exactly as for single characters, except
that instead of a character, the opcode for the type (e.g. OP_DIGIT) is stored
in the next code unit. The opcodes are:
OP_TYPESTAR
OP_TYPEMINSTAR
OP_TYPEPOSSTAR
OP_TYPEPLUS
OP_TYPEMINPLUS
OP_TYPEPOSPLUS
OP_TYPEQUERY
OP_TYPEMINQUERY
OP_TYPEPOSQUERY
OP_TYPEUPTO
OP_TYPEMINUPTO
OP_TYPEPOSUPTO
OP_TYPEEXACT
Match by Unicode property
-------------------------
OP_PROP and OP_NOTPROP are used for positive and negative matches of a
character by testing its Unicode property (the \p and \P escape sequences).
Each is followed by two code units that encode the desired property as a type
and a value. The types are a set of #defines of the form PT_xxx, and the values
are enumerations of the form ucp_xx, defined in the pcre2_ucp.h source file.
The value is relevant only for PT_GC (General Category), PT_PC (Particular
Category), PT_SC (Script), PT_BIDICL (Bidi Class), PT_BOOL (Boolean property),
and the pseudo-property PT_CLIST, which is used to identify a list of
case-equivalent characters when there are three or more (see above).
Repeats of these items use the OP_TYPESTAR etc. set of opcodes, followed by
three code units: OP_PROP or OP_NOTPROP, and then the desired property type and
value.
Character classes
-----------------
If there is only one character in a class, OP_CHAR or OP_CHARI is used for a
positive class, and OP_NOT or OP_NOTI for a negative one (that is, for
something like [^a]), except when caselessly matching a character that has more
than two case-equivalent code points (which can happen only in UTF mode). In
this case a Unicode property item is used, as described above in "Matching
literal characters".
A set of repeating opcodes (called OP_NOTSTAR etc.) are used for repeated,
negated, single-character classes. The normal single-character opcodes
(OP_STAR, etc.) are used for repeated positive single-character classes.
When there is more than one character in a class, and all the code points are
less than 256, OP_CLASS is used for a positive class, and OP_NCLASS for a
negative one. In either case, the opcode is followed by a 32-byte (16-short,
8-word) bit map containing a 1 bit for every character that is acceptable. The
bits are counted from the least significant end of each unit. In caseless mode,
bits for both cases are set.
The reason for having both OP_CLASS and OP_NCLASS is so that, in UTF-8 and
16-bit and 32-bit modes, subject characters with values greater than 255 can be
handled correctly. For OP_CLASS they do not match, whereas for OP_NCLASS they
do.
For classes containing characters with values greater than 255 or that contain
\p or \P, OP_XCLASS is used. It optionally uses a bit map if any acceptable
code points are less than 256, followed by a list of pairs (for a range) and/or
single characters and/or properties. In caseless mode, all equivalent
characters are explicitly listed.
OP_XCLASS is followed by a LINK_SIZE value containing the total length of the
opcode and its data. This is followed by a code unit containing flag bits:
XCL_NOT indicates that this is a negative class, and XCL_MAP indicates that a
bit map is present. There follows the bit map, if XCL_MAP is set, and then a
sequence of items coded as follows:
XCL_END marks the end of the list
XCL_SINGLE one character follows
XCL_RANGE two characters follow
XCL_PROP a Unicode property (type, value) follows
XCL_NOTPROP a Unicode property (type, value) follows
If a range starts with a code point less than 256 and ends with one greater
than 255, it is split into two ranges, with characters less than 256 being
indicated in the bit map, and the rest with XCL_RANGE.
When XCL_NOT is set, the bit map, if present, contains bits for characters that
are allowed (exactly as for OP_NCLASS), but the list of items that follow it
specifies characters and properties that are not allowed.
Back references
---------------
OP_REF (caseful) or OP_REFI (caseless) is followed by a count containing the
reference number when the reference is to a unique capturing group (either by
number or by name). When named groups are used, there may be more than one
group with the same name. In this case, a reference to such a group by name
generates OP_DNREF or OP_DNREFI. These are followed by two counts: the index
(not the byte offset) in the group name table of the first entry for the
required name, followed by the number of groups with the same name. The
matching code can then search for the first one that is set.
Repeating character classes and back references
-----------------------------------------------
Single-character classes are handled specially (see above). This section
applies to other classes and also to back references. In both cases, the repeat
information follows the base item. The matching code looks at the following
opcode to see if it is one of these:
OP_CRSTAR
OP_CRMINSTAR
OP_CRPOSSTAR
OP_CRPLUS
OP_CRMINPLUS
OP_CRPOSPLUS
OP_CRQUERY
OP_CRMINQUERY
OP_CRPOSQUERY
OP_CRRANGE
OP_CRMINRANGE
OP_CRPOSRANGE
All but the last three are single-code-unit items, with no data. The range
opcodes are followed by the minimum and maximum repeat counts.
Brackets and alternation
------------------------
A pair of non-capturing round brackets is wrapped round each expression at
compile time, so alternation always happens in the context of brackets.
[Note for North Americans: "bracket" to some English speakers, including
myself, can be round, square, curly, or pointy. Hence this usage rather than
"parentheses".]
Non-capturing brackets use the opcode OP_BRA, capturing brackets use OP_CBRA. A
bracket opcode is followed by a LINK_SIZE value which gives the offset to the
next alternative OP_ALT or, if there aren't any branches, to the terminating
opcode. Each OP_ALT is followed by a LINK_SIZE value giving the offset to the
next one, or to the final opcode. For capturing brackets, the bracket number is
a count that immediately follows the offset.
There are several opcodes that mark the end of a subpattern group. OP_KET is
used for subpatterns that do not repeat indefinitely, OP_KETRMIN and
OP_KETRMAX are used for indefinite repetitions, minimally or maximally
respectively, and OP_KETRPOS for possessive repetitions (see below for more
details). All four are followed by a LINK_SIZE value giving (as a positive
number) the offset back to the matching opening bracket opcode.
If a subpattern is quantified such that it is permitted to match zero times, it
is preceded by one of OP_BRAZERO, OP_BRAMINZERO, or OP_SKIPZERO. These are
single-unit opcodes that tell the matcher that skipping the following
subpattern entirely is a valid match. In the case of the first two, not
skipping the pattern is also valid (greedy and non-greedy). The third is used
when a pattern has the quantifier {0,0}. It cannot be entirely discarded,
because it may be called as a subroutine from elsewhere in the pattern.
A subpattern with an indefinite maximum repetition is replicated in the
compiled data its minimum number of times (or once with OP_BRAZERO if the
minimum is zero), with the final copy terminating with OP_KETRMIN or OP_KETRMAX
as appropriate.
A subpattern with a bounded maximum repetition is replicated in a nested
fashion up to the maximum number of times, with OP_BRAZERO or OP_BRAMINZERO
before each replication after the minimum, so that, for example, (abc){2,5} is
compiled as (abc)(abc)((abc)((abc)(abc)?)?)?, except that each bracketed group
has the same number.
When a repeated subpattern has an unbounded upper limit, it is checked to see
whether it could match an empty string. If this is the case, the opcode in the
final replication is changed to OP_SBRA or OP_SCBRA. This tells the matcher
that it needs to check for matching an empty string when it hits OP_KETRMIN or
OP_KETRMAX, and if so, to break the loop.
Possessive brackets
-------------------
When a repeated group (capturing or non-capturing) is marked as possessive by
the "+" notation, e.g. (abc)++, different opcodes are used. Their names all
have POS on the end, e.g. OP_BRAPOS instead of OP_BRA and OP_SCBRAPOS instead
of OP_SCBRA. The end of such a group is marked by OP_KETRPOS. If the minimum
repetition is zero, the group is preceded by OP_BRAPOSZERO.
Once-only (atomic) groups
-------------------------
These are just like other subpatterns, but they start with the opcode OP_ONCE.
The check for matching an empty string in an unbounded repeat is handled
entirely at runtime, so there is just this one opcode for atomic groups.
Assertions
----------
Forward assertions are also just like other subpatterns, but starting with one
of the opcodes OP_ASSERT, OP_ASSERT_NA (non-atomic assertion), or
OP_ASSERT_NOT. Backward assertions use the opcodes OP_ASSERTBACK,
OP_ASSERTBACK_NA, and OP_ASSERTBACK_NOT, and the first opcode inside the
assertion is OP_REVERSE, followed by a count of the number of characters to
move back the pointer in the subject string. In ASCII or UTF-32 mode, the count
is also the number of code units, but in UTF-8/16 mode each character may
occupy more than one code unit. A separate count is present in each alternative
of a lookbehind assertion, allowing each branch to have a different (but fixed)
length.
Conditional subpatterns
-----------------------
These are like other subpatterns, but they start with the opcode OP_COND, or
OP_SCOND for one that might match an empty string in an unbounded repeat.
If the condition is a back reference, this is stored at the start of the
subpattern using the opcode OP_CREF followed by a count containing the
reference number, provided that the reference is to a unique capturing group.
If the reference was by name and there is more than one group with that name,
OP_DNCREF is used instead. It is followed by two counts: the index in the group
names table, and the number of groups with the same name. The allows the
matcher to check if any group with the given name is set.
If the condition is "in recursion" (coded as "(?(R)"), or "in recursion of
group x" (coded as "(?(Rx)"), the group number is stored at the start of the
subpattern using the opcode OP_RREF (with a value of RREF_ANY (0xffff) for "the
whole pattern") or OP_DNRREF (with data as for OP_DNCREF).
For a DEFINE condition, OP_FALSE is used (with no associated data). During
compilation, however, a DEFINE condition is coded as OP_DEFINE so that, when
the conditional group is complete, there can be a check to ensure that it
contains only one top-level branch. Once this has happened, the opcode is
changed to OP_FALSE, so the matcher never sees OP_DEFINE.
There is a special PCRE2-specific condition of the form (VERSION[>]=x.y), which
tests the PCRE2 version number. This compiles into one of the opcodes OP_TRUE
or OP_FALSE.
If a condition is not a back reference, recursion test, DEFINE, or VERSION, it
must start with a parenthesized atomic assertion, whose opcode normally
immediately follows OP_COND or OP_SCOND. However, if automatic callouts are
enabled, a callout is inserted immediately before the assertion. It is also
possible to insert a manual callout at this point. Only assertion conditions
may have callouts preceding the condition.
A condition that is the negative assertion (?!) is optimized to OP_FAIL in all
parts of the pattern, so this is another opcode that may appear as a condition.
It is treated the same as OP_FALSE.
Recursion
---------
Recursion either matches the current pattern, or some subexpression. The opcode
OP_RECURSE is followed by a LINK_SIZE value that is the offset to the starting
bracket from the start of the whole pattern. OP_RECURSE is also used for
"subroutine" calls, even though they are not strictly a recursion. Up till
release 10.30 recursions were treated as atomic groups, making them
incompatible with Perl (but PCRE had them well before Perl did). From 10.30,
backtracking into recursions is supported.
Repeated recursions used to be wrapped inside OP_ONCE brackets, which not only
forced no backtracking, but also allowed repetition to be handled as for other
bracketed groups. From 10.30 onwards, repeated recursions are duplicated for
their minimum repetitions, and then wrapped in non-capturing brackets for the
remainder. For example, (?1){3} is treated as (?1)(?1)(?1), and (?1){2,4} is
treated as (?1)(?1)(?:(?1)){0,2}.
Callouts
--------
A callout may have either a numerical argument or a string argument. These use
OP_CALLOUT or OP_CALLOUT_STR, respectively. In each case these are followed by
two LINK_SIZE values giving the offset in the pattern string to the start of
the following item, and another count giving the length of this item. These
values make it possible for pcre2test to output useful tracing information
using callouts.
In the case of a numeric callout, after these two values there is a single code
unit containing the callout number, in the range 0-255, with 255 being used for
callouts that are automatically inserted as a result of the PCRE2_AUTO_CALLOUT
option. Thus, this opcode item is of fixed length:
[OP_CALLOUT] [PATTERN_OFFSET] [PATTERN_LENGTH] [NUMBER]
For callouts with string arguments, OP_CALLOUT_STR has three more data items:
a LINK_SIZE value giving the complete length of the entire opcode item, a
LINK_SIZE item containing the offset within the pattern string to the start of
the string argument, and the string itself, preceded by its starting delimiter
and followed by a binary zero. When a callout function is called, a pointer to
the actual string is passed, but the delimiter can be accessed as string[-1] if
the application needs it. In the 8-bit library, the callout in /X(?C'abc')Y/ is
compiled as the following bytes (decimal numbers represent binary values):
[OP_CALLOUT_STR] [0] [10] [0] [1] [0] [14] [0] [5] ['] [a] [b] [c] [0]
-------- ------- -------- -------
| | | |
------- LINK_SIZE items ------
Opcode table checking
---------------------
The last opcode that is defined in pcre2_internal.h is OP_TABLE_LENGTH. This is
not a real opcode, but is used to check at compile time that tables indexed by
opcode are the correct length, in order to catch updating errors.
Philip Hazel
April 2022

94
Kha/Backends/Kore-hxcpp/khacpp/project/thirdparty/pcre2-10.42-16/LICENCE vendored Normal file
View File

@ -0,0 +1,94 @@
PCRE2 LICENCE
-------------
PCRE2 is a library of functions to support regular expressions whose syntax
and semantics are as close as possible to those of the Perl 5 language.
Releases 10.00 and above of PCRE2 are distributed under the terms of the "BSD"
licence, as specified below, with one exemption for certain binary
redistributions. The documentation for PCRE2, supplied in the "doc" directory,
is distributed under the same terms as the software itself. The data in the
testdata directory is not copyrighted and is in the public domain.
The basic library functions are written in C and are freestanding. Also
included in the distribution is a just-in-time compiler that can be used to
optimize pattern matching. This is an optional feature that can be omitted when
the library is built.
THE BASIC LIBRARY FUNCTIONS
---------------------------
Written by: Philip Hazel
Email local part: Philip.Hazel
Email domain: gmail.com
Retired from University of Cambridge Computing Service,
Cambridge, England.
Copyright (c) 1997-2022 University of Cambridge
All rights reserved.
PCRE2 JUST-IN-TIME COMPILATION SUPPORT
--------------------------------------
Written by: Zoltan Herczeg
Email local part: hzmester
Email domain: freemail.hu
Copyright(c) 2010-2022 Zoltan Herczeg
All rights reserved.
STACK-LESS JUST-IN-TIME COMPILER
--------------------------------
Written by: Zoltan Herczeg
Email local part: hzmester
Email domain: freemail.hu
Copyright(c) 2009-2022 Zoltan Herczeg
All rights reserved.
THE "BSD" LICENCE
-----------------
Redistribution and use in source and binary forms, with or without
modification, are permitted provided that the following conditions are met:
* Redistributions of source code must retain the above copyright notices,
this list of conditions and the following disclaimer.
* Redistributions in binary form must reproduce the above copyright
notices, this list of conditions and the following disclaimer in the
documentation and/or other materials provided with the distribution.
* Neither the name of the University of Cambridge nor the names of any
contributors may be used to endorse or promote products derived from this
software without specific prior written permission.
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
POSSIBILITY OF SUCH DAMAGE.
EXEMPTION FOR BINARY LIBRARY-LIKE PACKAGES
------------------------------------------
The second condition in the BSD licence (covering binary redistributions) does
not apply all the way down a chain of software. If binary package A includes
PCRE2, it must respect the condition, but if package B is software that
includes package A, the condition is not imposed on package B unless it uses
PCRE2 independently.
End

8
Kha/Backends/Kore-hxcpp/khacpp/project/thirdparty/pcre2-10.42-16/MODULE.bazel vendored Normal file
View File

@ -0,0 +1,8 @@
module(
name = "pcre2",
version = "10.40",
compatibility_level = 1,
)
bazel_dep(name = "rules_cc", version = "0.0.1")
bazel_dep(name = "bazel_skylib", version = "1.2.1")

900
Kha/Backends/Kore-hxcpp/khacpp/project/thirdparty/pcre2-10.42-16/Makefile.am vendored Normal file
View File

@ -0,0 +1,900 @@
## Process this file with automake to produce Makefile.in.
AUTOMAKE_OPTIONS = subdir-objects
ACLOCAL_AMFLAGS = -I m4
## This seems to have become necessary for building in non-source directory.
AM_CPPFLAGS="-I$(srcdir)/src"
## Specify the documentation files that are distributed.
dist_doc_DATA = \
AUTHORS \
COPYING \
ChangeLog \
LICENCE \
NEWS \
README \
doc/pcre2.txt \
doc/pcre2-config.txt \
doc/pcre2grep.txt \
doc/pcre2test.txt
dist_html_DATA = \
doc/html/NON-AUTOTOOLS-BUILD.txt \
doc/html/README.txt \
doc/html/index.html \
doc/html/pcre2-config.html \
doc/html/pcre2.html \
doc/html/pcre2_callout_enumerate.html \
doc/html/pcre2_code_copy.html \
doc/html/pcre2_code_copy_with_tables.html \
doc/html/pcre2_code_free.html \
doc/html/pcre2_compile.html \
doc/html/pcre2_compile_context_copy.html \
doc/html/pcre2_compile_context_create.html \
doc/html/pcre2_compile_context_free.html \
doc/html/pcre2_config.html \
doc/html/pcre2_convert_context_copy.html \
doc/html/pcre2_convert_context_create.html \
doc/html/pcre2_convert_context_free.html \
doc/html/pcre2_converted_pattern_free.html \
doc/html/pcre2_dfa_match.html \
doc/html/pcre2_general_context_copy.html \
doc/html/pcre2_general_context_create.html \
doc/html/pcre2_general_context_free.html \
doc/html/pcre2_get_error_message.html \
doc/html/pcre2_get_mark.html \
doc/html/pcre2_get_match_data_size.html \
doc/html/pcre2_get_ovector_count.html \
doc/html/pcre2_get_ovector_pointer.html \
doc/html/pcre2_get_startchar.html \
doc/html/pcre2_jit_compile.html \
doc/html/pcre2_jit_free_unused_memory.html \
doc/html/pcre2_jit_match.html \
doc/html/pcre2_jit_stack_assign.html \
doc/html/pcre2_jit_stack_create.html \
doc/html/pcre2_jit_stack_free.html \
doc/html/pcre2_maketables.html \
doc/html/pcre2_maketables_free.html \
doc/html/pcre2_match.html \
doc/html/pcre2_match_context_copy.html \
doc/html/pcre2_match_context_create.html \
doc/html/pcre2_match_context_free.html \
doc/html/pcre2_match_data_create.html \
doc/html/pcre2_match_data_create_from_pattern.html \
doc/html/pcre2_match_data_free.html \
doc/html/pcre2_pattern_convert.html \
doc/html/pcre2_pattern_info.html \
doc/html/pcre2_serialize_decode.html \
doc/html/pcre2_serialize_encode.html \
doc/html/pcre2_serialize_free.html \
doc/html/pcre2_serialize_get_number_of_codes.html \
doc/html/pcre2_set_bsr.html \
doc/html/pcre2_set_callout.html \
doc/html/pcre2_set_character_tables.html \
doc/html/pcre2_set_compile_extra_options.html \
doc/html/pcre2_set_compile_recursion_guard.html \
doc/html/pcre2_set_depth_limit.html \
doc/html/pcre2_set_glob_escape.html \
doc/html/pcre2_set_glob_separator.html \
doc/html/pcre2_set_heap_limit.html \
doc/html/pcre2_set_match_limit.html \
doc/html/pcre2_set_max_pattern_length.html \
doc/html/pcre2_set_offset_limit.html \
doc/html/pcre2_set_newline.html \
doc/html/pcre2_set_parens_nest_limit.html \
doc/html/pcre2_set_recursion_limit.html \
doc/html/pcre2_set_recursion_memory_management.html \
doc/html/pcre2_set_substitute_callout.html \
doc/html/pcre2_substitute.html \
doc/html/pcre2_substring_copy_byname.html \
doc/html/pcre2_substring_copy_bynumber.html \
doc/html/pcre2_substring_free.html \
doc/html/pcre2_substring_get_byname.html \
doc/html/pcre2_substring_get_bynumber.html \
doc/html/pcre2_substring_length_byname.html \
doc/html/pcre2_substring_length_bynumber.html \
doc/html/pcre2_substring_list_free.html \
doc/html/pcre2_substring_list_get.html \
doc/html/pcre2_substring_nametable_scan.html \
doc/html/pcre2_substring_number_from_name.html \
doc/html/pcre2api.html \
doc/html/pcre2build.html \
doc/html/pcre2callout.html \
doc/html/pcre2compat.html \
doc/html/pcre2convert.html \
doc/html/pcre2demo.html \
doc/html/pcre2grep.html \
doc/html/pcre2jit.html \
doc/html/pcre2limits.html \
doc/html/pcre2matching.html \
doc/html/pcre2partial.html \
doc/html/pcre2pattern.html \
doc/html/pcre2perform.html \
doc/html/pcre2posix.html \
doc/html/pcre2sample.html \
doc/html/pcre2serialize.html \
doc/html/pcre2syntax.html \
doc/html/pcre2test.html \
doc/html/pcre2unicode.html
dist_man_MANS = \
doc/pcre2-config.1 \
doc/pcre2.3 \
doc/pcre2_callout_enumerate.3 \
doc/pcre2_code_copy.3 \
doc/pcre2_code_copy_with_tables.3 \
doc/pcre2_code_free.3 \
doc/pcre2_compile.3 \
doc/pcre2_compile_context_copy.3 \
doc/pcre2_compile_context_create.3 \
doc/pcre2_compile_context_free.3 \
doc/pcre2_config.3 \
doc/pcre2_convert_context_copy.3 \
doc/pcre2_convert_context_create.3 \
doc/pcre2_convert_context_free.3 \
doc/pcre2_converted_pattern_free.3 \
doc/pcre2_dfa_match.3 \
doc/pcre2_general_context_copy.3 \
doc/pcre2_general_context_create.3 \
doc/pcre2_general_context_free.3 \
doc/pcre2_get_error_message.3 \
doc/pcre2_get_mark.3 \
doc/pcre2_get_match_data_size.3 \
doc/pcre2_get_ovector_count.3 \
doc/pcre2_get_ovector_pointer.3 \
doc/pcre2_get_startchar.3 \
doc/pcre2_jit_compile.3 \
doc/pcre2_jit_free_unused_memory.3 \
doc/pcre2_jit_match.3 \
doc/pcre2_jit_stack_assign.3 \
doc/pcre2_jit_stack_create.3 \
doc/pcre2_jit_stack_free.3 \
doc/pcre2_maketables.3 \
doc/pcre2_maketables_free.3 \
doc/pcre2_match.3 \
doc/pcre2_match_context_copy.3 \
doc/pcre2_match_context_create.3 \
doc/pcre2_match_context_free.3 \
doc/pcre2_match_data_create.3 \
doc/pcre2_match_data_create_from_pattern.3 \
doc/pcre2_match_data_free.3 \
doc/pcre2_pattern_convert.3 \
doc/pcre2_pattern_info.3 \
doc/pcre2_serialize_decode.3 \
doc/pcre2_serialize_encode.3 \
doc/pcre2_serialize_free.3 \
doc/pcre2_serialize_get_number_of_codes.3 \
doc/pcre2_set_bsr.3 \
doc/pcre2_set_callout.3 \
doc/pcre2_set_character_tables.3 \
doc/pcre2_set_compile_extra_options.3 \
doc/pcre2_set_compile_recursion_guard.3 \
doc/pcre2_set_depth_limit.3 \
doc/pcre2_set_glob_escape.3 \
doc/pcre2_set_glob_separator.3 \
doc/pcre2_set_heap_limit.3 \
doc/pcre2_set_match_limit.3 \
doc/pcre2_set_max_pattern_length.3 \
doc/pcre2_set_offset_limit.3 \
doc/pcre2_set_newline.3 \
doc/pcre2_set_parens_nest_limit.3 \
doc/pcre2_set_recursion_limit.3 \
doc/pcre2_set_recursion_memory_management.3 \
doc/pcre2_set_substitute_callout.3 \
doc/pcre2_substitute.3 \
doc/pcre2_substring_copy_byname.3 \
doc/pcre2_substring_copy_bynumber.3 \
doc/pcre2_substring_free.3 \
doc/pcre2_substring_get_byname.3 \
doc/pcre2_substring_get_bynumber.3 \
doc/pcre2_substring_length_byname.3 \
doc/pcre2_substring_length_bynumber.3 \
doc/pcre2_substring_list_free.3 \
doc/pcre2_substring_list_get.3 \
doc/pcre2_substring_nametable_scan.3 \
doc/pcre2_substring_number_from_name.3 \
doc/pcre2api.3 \
doc/pcre2build.3 \
doc/pcre2callout.3 \
doc/pcre2compat.3 \
doc/pcre2convert.3 \
doc/pcre2demo.3 \
doc/pcre2grep.1 \
doc/pcre2jit.3 \
doc/pcre2limits.3 \
doc/pcre2matching.3 \
doc/pcre2partial.3 \
doc/pcre2pattern.3 \
doc/pcre2perform.3 \
doc/pcre2posix.3 \
doc/pcre2sample.3 \
doc/pcre2serialize.3 \
doc/pcre2syntax.3 \
doc/pcre2test.1 \
doc/pcre2unicode.3
# The Libtool libraries to install. We'll add to this later.
lib_LTLIBRARIES =
# Unit tests you want to run when people type 'make check'.
# TESTS is for binary unit tests, check_SCRIPTS for script-based tests
TESTS =
check_SCRIPTS =
dist_noinst_SCRIPTS =
# Some of the binaries we make are to be installed, and others are
# (non-user-visible) helper programs needed to build the libraries.
bin_PROGRAMS =
noinst_PROGRAMS =
# Additional files to delete on 'make clean', 'make distclean',
# and 'make maintainer-clean'.
CLEANFILES =
DISTCLEANFILES = src/config.h.in~
MAINTAINERCLEANFILES =
# Additional files to bundle with the distribution, over and above what
# the Autotools include by default.
EXTRA_DIST =
# These files contain additional m4 macros that are used by autoconf.
EXTRA_DIST += \
m4/ax_pthread.m4 m4/pcre2_visibility.m4
# These files contain maintenance information
EXTRA_DIST += \
NON-AUTOTOOLS-BUILD \
HACKING
# These files are used in the preparation of a release
EXTRA_DIST += \
PrepareRelease \
CheckMan \
CleanTxt \
Detrail \
132html \
doc/index.html.src
# These files are usable versions of pcre2.h and config.h that are distributed
# for the benefit of people who are building PCRE2 manually, without the
# Autotools support.
EXTRA_DIST += \
src/pcre2.h.generic \
src/config.h.generic
# The only difference between pcre2.h.in and pcre2.h is the setting of the PCRE
# version number. Therefore, we can create the generic version just by copying.
src/pcre2.h.generic: src/pcre2.h.in configure.ac
rm -f $@
cp -p src/pcre2.h $@
# It is more complicated for config.h.generic. We need the version that results
# from a default configuration so as to get all the default values for PCRE
# configuration macros such as MATCH_LIMIT and NEWLINE. We can get this by
# doing a configure in a temporary directory. However, some trickery is needed,
# because the source directory may already be configured. If you just try
# running configure in a new directory, it complains. For this reason, we move
# config.status out of the way while doing the default configuration. The
# resulting config.h is munged by perl to put #ifdefs round any #defines for
# macros with values, and to #undef all boolean macros such as HAVE_xxx and
# SUPPORT_xxx. We also get rid of any gcc-specific visibility settings. Make
# sure that PCRE2_EXP_DEFN is unset (in case it has visibility settings).
src/config.h.generic: configure.ac
rm -rf $@ _generic
mkdir _generic
cs=$(srcdir)/config.status; test ! -f $$cs || mv -f $$cs $$cs.aside
cd _generic && $(abs_top_srcdir)/configure || :
cs=$(srcdir)/config.status; test ! -f $$cs.aside || mv -f $$cs.aside $$cs
test -f _generic/src/config.h
perl -n \
-e 'BEGIN{$$blank=0;}' \
-e 'if(/PCRE2_EXP_DEFN/){print"/* #undef PCRE2_EXP_DEFN */\n";$$blank=0;next;}' \
-e 'if(/to make a symbol visible/){next;}' \
-e 'if(/__attribute__ \(\(visibility/){next;}' \
-e 'if(/LT_OBJDIR/){print"/* This is ignored unless you are using libtool. */\n";}' \
-e 'if(/^#define\s((?:HAVE|SUPPORT|STDC)_\w+)/){print"/* #undef $$1 */\n";$$blank=0;next;}' \
-e 'if(/^#define\s(?!PACKAGE|VERSION)(\w+)/){print"#ifndef $$1\n$$_#endif\n";$$blank=0;next;}' \
-e 'if(/^\s*$$/){print unless $$blank; $$blank=1;} else{print;$$blank=0;}' \
_generic/src/config.h >$@
rm -rf _generic
MAINTAINERCLEANFILES += src/pcre2.h.generic src/config.h.generic
# These are the header files we'll install. We do not distribute pcre2.h
# because it is generated from pcre2.h.in.
nodist_include_HEADERS = src/pcre2.h
include_HEADERS = src/pcre2posix.h
# This is the "config" script.
bin_SCRIPTS = pcre2-config
## ---------------------------------------------------------------
## The pcre2_dftables program is used to rebuild character tables before
## compiling PCRE2, if --enable-rebuild-chartables is specified. It is not an
## installed program. The default (when --enable-rebuild-chartables is not
## specified) is to copy a distributed set of tables that are defined for ASCII
## code. In this case, pcre2_dftables is not needed.
if WITH_REBUILD_CHARTABLES
noinst_PROGRAMS += pcre2_dftables
pcre2_dftables_SOURCES = src/pcre2_dftables.c
src/pcre2_chartables.c: pcre2_dftables$(EXEEXT)
rm -f $@
./pcre2_dftables$(EXEEXT) $@
else
src/pcre2_chartables.c: $(srcdir)/src/pcre2_chartables.c.dist
rm -f $@
$(LN_S) $(abs_srcdir)/src/pcre2_chartables.c.dist $(abs_builddir)/src/pcre2_chartables.c
endif # WITH_REBUILD_CHARTABLES
BUILT_SOURCES = src/pcre2_chartables.c
NODIST_SOURCES = src/pcre2_chartables.c
## Define the list of common sources, then arrange to build whichever of the
## 8-, 16-, or 32-bit libraries are configured.
COMMON_SOURCES = \
src/pcre2_auto_possess.c \
src/pcre2_compile.c \
src/pcre2_config.c \
src/pcre2_context.c \
src/pcre2_convert.c \
src/pcre2_dfa_match.c \
src/pcre2_error.c \
src/pcre2_extuni.c \
src/pcre2_find_bracket.c \
src/pcre2_internal.h \
src/pcre2_intmodedep.h \
src/pcre2_jit_compile.c \
src/pcre2_jit_neon_inc.h \
src/pcre2_jit_simd_inc.h \
src/pcre2_maketables.c \
src/pcre2_match.c \
src/pcre2_match_data.c \
src/pcre2_newline.c \
src/pcre2_ord2utf.c \
src/pcre2_pattern_info.c \
src/pcre2_script_run.c \
src/pcre2_serialize.c \
src/pcre2_string_utils.c \
src/pcre2_study.c \
src/pcre2_substitute.c \
src/pcre2_substring.c \
src/pcre2_tables.c \
src/pcre2_ucd.c \
src/pcre2_ucp.h \
src/pcre2_valid_utf.c \
src/pcre2_xclass.c
# The pcre2_ucptables.c file is #included by pcre2_tables.c
EXTRA_DIST += src/pcre2_ucptables.c
if WITH_PCRE2_8
lib_LTLIBRARIES += libpcre2-8.la
libpcre2_8_la_SOURCES = \
$(COMMON_SOURCES)
nodist_libpcre2_8_la_SOURCES = \
$(NODIST_SOURCES)
libpcre2_8_la_CFLAGS = \
-DPCRE2_CODE_UNIT_WIDTH=8 \
$(VISIBILITY_CFLAGS) \
$(CET_CFLAGS) \
$(AM_CFLAGS)
libpcre2_8_la_LIBADD =
endif # WITH_PCRE2_8
if WITH_PCRE2_16
lib_LTLIBRARIES += libpcre2-16.la
libpcre2_16_la_SOURCES = \
$(COMMON_SOURCES)
nodist_libpcre2_16_la_SOURCES = \
$(NODIST_SOURCES)
libpcre2_16_la_CFLAGS = \
-DPCRE2_CODE_UNIT_WIDTH=16 \
$(VISIBILITY_CFLAGS) \
$(CET_CFLAGS) \
$(AM_CFLAGS)
libpcre2_16_la_LIBADD =
endif # WITH_PCRE2_16
if WITH_PCRE2_32
lib_LTLIBRARIES += libpcre2-32.la
libpcre2_32_la_SOURCES = \
$(COMMON_SOURCES)
nodist_libpcre2_32_la_SOURCES = \
$(NODIST_SOURCES)
libpcre2_32_la_CFLAGS = \
-DPCRE2_CODE_UNIT_WIDTH=32 \
$(VISIBILITY_CFLAGS) \
$(CET_CFLAGS) \
$(AM_CFLAGS)
libpcre2_32_la_LIBADD =
endif # WITH_PCRE2_32
# The pcre2_chartables.c.dist file is the default version of
# pcre2_chartables.c, used unless --enable-rebuild-chartables is specified.
EXTRA_DIST += src/pcre2_chartables.c.dist
CLEANFILES += src/pcre2_chartables.c
# The JIT compiler lives in a separate directory, but its files are #included
# when pcre2_jit_compile.c is processed, so they must be distributed.
EXTRA_DIST += \
src/sljit/sljitConfig.h \
src/sljit/sljitConfigInternal.h \
src/sljit/sljitExecAllocator.c \
src/sljit/sljitLir.c \
src/sljit/sljitLir.h \
src/sljit/sljitNativeARM_32.c \
src/sljit/sljitNativeARM_64.c \
src/sljit/sljitNativeARM_T2_32.c \
src/sljit/sljitNativeMIPS_32.c \
src/sljit/sljitNativeMIPS_64.c \
src/sljit/sljitNativeMIPS_common.c \
src/sljit/sljitNativePPC_32.c \
src/sljit/sljitNativePPC_64.c \
src/sljit/sljitNativePPC_common.c \
src/sljit/sljitNativeRISCV_32.c \
src/sljit/sljitNativeRISCV_64.c \
src/sljit/sljitNativeRISCV_common.c \
src/sljit/sljitNativeS390X.c \
src/sljit/sljitNativeX86_32.c \
src/sljit/sljitNativeX86_64.c \
src/sljit/sljitNativeX86_common.c \
src/sljit/sljitProtExecAllocator.c \
src/sljit/sljitUtils.c \
src/sljit/sljitWXExecAllocator.c
# Some of the JIT sources are also in separate files that are #included.
EXTRA_DIST += \
src/pcre2_jit_match.c \
src/pcre2_jit_misc.c
if WITH_PCRE2_8
libpcre2_8_la_LDFLAGS = $(EXTRA_LIBPCRE2_8_LDFLAGS)
endif # WITH_PCRE2_8
if WITH_PCRE2_16
libpcre2_16_la_LDFLAGS = $(EXTRA_LIBPCRE2_16_LDFLAGS)
endif # WITH_PCRE2_16
if WITH_PCRE2_32
libpcre2_32_la_LDFLAGS = $(EXTRA_LIBPCRE2_32_LDFLAGS)
endif # WITH_PCRE2_32
if WITH_VALGRIND
if WITH_PCRE2_8
libpcre2_8_la_CFLAGS += $(VALGRIND_CFLAGS)
endif # WITH_PCRE2_8
if WITH_PCRE2_16
libpcre2_16_la_CFLAGS += $(VALGRIND_CFLAGS)
endif # WITH_PCRE2_16
if WITH_PCRE2_32
libpcre2_32_la_CFLAGS += $(VALGRIND_CFLAGS)
endif # WITH_PCRE2_32
endif # WITH_VALGRIND
if WITH_GCOV
if WITH_PCRE2_8
libpcre2_8_la_CFLAGS += $(GCOV_CFLAGS)
endif # WITH_PCRE2_8
if WITH_PCRE2_16
libpcre2_16_la_CFLAGS += $(GCOV_CFLAGS)
endif # WITH_PCRE2_16
if WITH_PCRE2_32
libpcre2_32_la_CFLAGS += $(GCOV_CFLAGS)
endif # WITH_PCRE2_32
endif # WITH_GCOV
## A version of the 8-bit library that has a POSIX API.
if WITH_PCRE2_8
lib_LTLIBRARIES += libpcre2-posix.la
libpcre2_posix_la_SOURCES = src/pcre2posix.c
libpcre2_posix_la_CFLAGS = \
-DPCRE2_CODE_UNIT_WIDTH=8 \
$(VISIBILITY_CFLAGS) $(AM_CFLAGS)
libpcre2_posix_la_LDFLAGS = $(EXTRA_LIBPCRE2_POSIX_LDFLAGS)
libpcre2_posix_la_LIBADD = libpcre2-8.la
if WITH_GCOV
libpcre2_posix_la_CFLAGS += $(GCOV_CFLAGS)
endif # WITH_GCOV
endif # WITH_PCRE2_8
## Build pcre2grep and optional fuzzer stuff if the 8-bit library is enabled
if WITH_PCRE2_8
bin_PROGRAMS += pcre2grep
pcre2grep_SOURCES = src/pcre2grep.c
pcre2grep_CFLAGS = $(AM_CFLAGS)
pcre2grep_LDADD = $(LIBZ) $(LIBBZ2)
pcre2grep_LDADD += libpcre2-8.la
if WITH_GCOV
pcre2grep_CFLAGS += $(GCOV_CFLAGS)
pcre2grep_LDADD += $(GCOV_LIBS)
endif # WITH_GCOV
## If fuzzer support is enabled, build a non-distributed library containing the
## fuzzing function. Also build the standalone checking binary from the same
## source but using -DSTANDALONE.
if WITH_FUZZ_SUPPORT
noinst_LIBRARIES = .libs/libpcre2-fuzzsupport.a
_libs_libpcre2_fuzzsupport_a_SOURCES = src/pcre2_fuzzsupport.c
_libs_libpcre2_fuzzsupport_a_CFLAGS = $(AM_CFLAGS)
_libs_libpcre2_fuzzsupport_a_LIBADD =
noinst_PROGRAMS += pcre2fuzzcheck
pcre2fuzzcheck_SOURCES = src/pcre2_fuzzsupport.c
pcre2fuzzcheck_CFLAGS = -DSTANDALONE $(AM_CFLAGS)
pcre2fuzzcheck_LDADD = libpcre2-8.la
if WITH_GCOV
pcre2fuzzcheck_CFLAGS += $(GCOV_CFLAGS)
pcre2fuzzcheck_LDADD += $(GCOV_LIBS)
endif # WITH_GCOV
endif # WITH FUZZ_SUPPORT
endif # WITH_PCRE2_8
## -------- Testing ----------
## If the 8-bit library is enabled, build the POSIX wrapper test program and
## arrange for it to run.
if WITH_PCRE2_8
TESTS += pcre2posix_test
noinst_PROGRAMS += pcre2posix_test
pcre2posix_test_SOURCES = src/pcre2posix_test.c
pcre2posix_test_CFLAGS = $(AM_CFLAGS)
pcre2posix_test_LDADD = libpcre2-posix.la libpcre2-8.la
endif # WITH_PCRE2_8
## If JIT support is enabled, arrange for the JIT test program to run.
if WITH_JIT
TESTS += pcre2_jit_test
noinst_PROGRAMS += pcre2_jit_test
pcre2_jit_test_SOURCES = src/pcre2_jit_test.c
pcre2_jit_test_CFLAGS = $(AM_CFLAGS)
pcre2_jit_test_LDADD =
if WITH_PCRE2_8
pcre2_jit_test_LDADD += libpcre2-8.la
endif # WITH_PCRE2_8
if WITH_PCRE2_16
pcre2_jit_test_LDADD += libpcre2-16.la
endif # WITH_PCRE2_16
if WITH_PCRE2_32
pcre2_jit_test_LDADD += libpcre2-32.la
endif # WITH_PCRE2_32
if WITH_GCOV
pcre2_jit_test_CFLAGS += $(GCOV_CFLAGS)
pcre2_jit_test_LDADD += $(GCOV_LIBS)
endif # WITH_GCOV
endif # WITH_JIT
# Build the general pcre2test program. The file src/pcre2_printint.c is
# #included by pcre2test as many times as needed, at different code unit
# widths.
bin_PROGRAMS += pcre2test
EXTRA_DIST += src/pcre2_printint.c
pcre2test_SOURCES = src/pcre2test.c
pcre2test_CFLAGS = $(AM_CFLAGS)
pcre2test_LDADD = $(LIBREADLINE)
if WITH_PCRE2_8
pcre2test_LDADD += libpcre2-8.la libpcre2-posix.la
endif # WITH_PCRE2_8
if WITH_PCRE2_16
pcre2test_LDADD += libpcre2-16.la
endif # WITH_PCRE2_16
if WITH_PCRE2_32
pcre2test_LDADD += libpcre2-32.la
endif # WITH_PCRE2_32
if WITH_VALGRIND
pcre2test_CFLAGS += $(VALGRIND_CFLAGS)
endif # WITH_VALGRIND
if WITH_GCOV
pcre2test_CFLAGS += $(GCOV_CFLAGS)
pcre2test_LDADD += $(GCOV_LIBS)
endif # WITH_GCOV
## The main library tests. Each test is a binary plus a script that runs that
## binary in various ways. We install these test binaries in case folks find it
## helpful. The two .bat files are for running the tests under Windows.
TESTS += RunTest
EXTRA_DIST += RunTest.bat
dist_noinst_SCRIPTS += RunTest
## When the 8-bit library is configured, pcre2grep will have been built.
if WITH_PCRE2_8
TESTS += RunGrepTest
EXTRA_DIST += RunGrepTest.bat
dist_noinst_SCRIPTS += RunGrepTest
endif # WITH_PCRE2_8
## Distribute all the test data files
EXTRA_DIST += \
testdata/grepbinary \
testdata/grepfilelist \
testdata/grepinput \
testdata/grepinput3 \
testdata/grepinput8 \
testdata/grepinputC.bz2 \
testdata/grepinputC.gz \
testdata/grepinputM \
testdata/grepinputv \
testdata/grepinputx \
testdata/greplist \
testdata/grepnot.bz2 \
testdata/grepoutput \
testdata/grepoutput8 \
testdata/grepoutputC \
testdata/grepoutputCN \
testdata/grepoutputCNU \
testdata/grepoutputCU \
testdata/grepoutputCbz2 \
testdata/grepoutputCgz \
testdata/grepoutputN \
testdata/grepoutputUN \
testdata/greppatN4 \
testdata/testbtables \
testdata/testinput1 \
testdata/testinput2 \
testdata/testinput3 \
testdata/testinput4 \
testdata/testinput5 \
testdata/testinput6 \
testdata/testinput7 \
testdata/testinput8 \
testdata/testinput9 \
testdata/testinput10 \
testdata/testinput11 \
testdata/testinput12 \
testdata/testinput13 \
testdata/testinput14 \
testdata/testinput15 \
testdata/testinput16 \
testdata/testinput17 \
testdata/testinput18 \
testdata/testinput19 \
testdata/testinput20 \
testdata/testinput21 \
testdata/testinput22 \
testdata/testinput23 \
testdata/testinput24 \
testdata/testinput25 \
testdata/testinput26 \
testdata/testinputEBC \
testdata/testinputheap \
testdata/testoutput1 \
testdata/testoutput2 \
testdata/testoutput3 \
testdata/testoutput3A \
testdata/testoutput3B \
testdata/testoutput4 \
testdata/testoutput5 \
testdata/testoutput6 \
testdata/testoutput7 \
testdata/testoutput8-16-2 \
testdata/testoutput8-16-3 \
testdata/testoutput8-16-4 \
testdata/testoutput8-32-2 \
testdata/testoutput8-32-3 \
testdata/testoutput8-32-4 \
testdata/testoutput8-8-2 \
testdata/testoutput8-8-3 \
testdata/testoutput8-8-4 \
testdata/testoutput9 \
testdata/testoutput10 \
testdata/testoutput11-16 \
testdata/testoutput11-32 \
testdata/testoutput12-16 \
testdata/testoutput12-32 \
testdata/testoutput13 \
testdata/testoutput14-16 \
testdata/testoutput14-32 \
testdata/testoutput14-8 \
testdata/testoutput15 \
testdata/testoutput16 \
testdata/testoutput17 \
testdata/testoutput18 \
testdata/testoutput19 \
testdata/testoutput20 \
testdata/testoutput21 \
testdata/testoutput22-16 \
testdata/testoutput22-32 \
testdata/testoutput22-8 \
testdata/testoutput23 \
testdata/testoutput24 \
testdata/testoutput25 \
testdata/testoutput26 \
testdata/testoutputEBC \
testdata/testoutputheap-16 \
testdata/testoutputheap-32 \
testdata/testoutputheap-8 \
testdata/valgrind-jit.supp \
testdata/wintestinput3 \
testdata/wintestoutput3 \
perltest.sh
# RunTest and RunGrepTest should clean up after themselves, but just in case
# they don't, add their working files to CLEANFILES.
CLEANFILES += \
testSinput \
test3input \
test3output \
test3outputA \
test3outputB \
testtry \
teststdout \
teststderr \
teststderrgrep \
testtemp1grep \
testtemp2grep \
testtrygrep \
testNinputgrep
## ------------ End of testing -------------
# PCRE2 demonstration program. Not built automatically. The point is that the
# users should build it themselves. So just distribute the source.
EXTRA_DIST += src/pcre2demo.c
# We have .pc files for pkg-config users.
pkgconfigdir = $(libdir)/pkgconfig
pkgconfig_DATA =
if WITH_PCRE2_8
pkgconfig_DATA += libpcre2-8.pc libpcre2-posix.pc
endif
if WITH_PCRE2_16
pkgconfig_DATA += libpcre2-16.pc
endif
if WITH_PCRE2_32
pkgconfig_DATA += libpcre2-32.pc
endif
# gcov/lcov code coverage reporting
#
# Coverage reporting targets:
#
# coverage: Create a coverage report from 'make check'
# coverage-baseline: Capture baseline coverage information
# coverage-reset: This zeros the coverage counters only
# coverage-report: This creates the coverage report only
# coverage-clean-report: This removes the generated coverage report
# without cleaning the coverage data itself
# coverage-clean-data: This removes the captured coverage data without
# removing the coverage files created at compile time (*.gcno)
# coverage-clean: This cleans all coverage data including the generated
# coverage report.
if WITH_GCOV
COVERAGE_TEST_NAME = $(PACKAGE)
COVERAGE_NAME = $(PACKAGE)-$(VERSION)
COVERAGE_OUTPUT_FILE = $(COVERAGE_NAME)-coverage.info
COVERAGE_OUTPUT_DIR = $(COVERAGE_NAME)-coverage
COVERAGE_LCOV_EXTRA_FLAGS =
COVERAGE_GENHTML_EXTRA_FLAGS =
coverage_quiet = $(coverage_quiet_$(V))
coverage_quiet_ = $(coverage_quiet_$(AM_DEFAULT_VERBOSITY))
coverage_quiet_0 = --quiet
coverage-check: all
-$(MAKE) $(AM_MAKEFLAGS) -k check
coverage-baseline:
$(LCOV) $(coverage_quiet) \
--directory $(top_builddir) \
--output-file "$(COVERAGE_OUTPUT_FILE)" \
--capture \
--initial
coverage-report:
$(LCOV) $(coverage_quiet) \
--directory $(top_builddir) \
--capture \
--output-file "$(COVERAGE_OUTPUT_FILE).tmp" \
--test-name "$(COVERAGE_TEST_NAME)" \
--no-checksum \
--compat-libtool \
$(COVERAGE_LCOV_EXTRA_FLAGS)
$(LCOV) $(coverage_quiet) \
--directory $(top_builddir) \
--output-file "$(COVERAGE_OUTPUT_FILE)" \
--remove "$(COVERAGE_OUTPUT_FILE).tmp" \
"/tmp/*" \
"/usr/include/*" \
"$(includedir)/*"
-@rm -f "$(COVERAGE_OUTPUT_FILE).tmp"
LANG=C $(GENHTML) $(coverage_quiet) \
--prefix $(top_builddir) \
--output-directory "$(COVERAGE_OUTPUT_DIR)" \
--title "$(PACKAGE) $(VERSION) Code Coverage Report" \
--show-details "$(COVERAGE_OUTPUT_FILE)" \
--legend \
$(COVERAGE_GENHTML_EXTRA_FLAGS)
@echo "Code coverage report written to file://$(abs_builddir)/$(COVERAGE_OUTPUT_DIR)/index.html"
coverage-reset:
-$(LCOV) $(coverage_quiet) --zerocounters --directory $(top_builddir)
coverage-clean-report:
-rm -f "$(COVERAGE_OUTPUT_FILE)" "$(COVERAGE_OUTPUT_FILE).tmp"
-rm -rf "$(COVERAGE_OUTPUT_DIR)"
coverage-clean-data:
-find $(top_builddir) -name "*.gcda" -delete
coverage-clean: coverage-reset coverage-clean-report coverage-clean-data
-find $(top_builddir) -name "*.gcno" -delete
coverage-distclean: coverage-clean
coverage: coverage-reset coverage-baseline coverage-check coverage-report
clean-local: coverage-clean
distclean-local: coverage-distclean
.PHONY: coverage coverage-baseline coverage-check coverage-report coverage-reset coverage-clean-report coverage-clean-data coverage-clean coverage-distclean
# Without coverage support, still arrange for 'make distclean' to get rid of
# any coverage files that may have been left from a different configuration.
else
coverage:
@echo "Configuring with --enable-coverage is required to generate code coverage report."
DISTCLEANFILES += src/*.gcda src/*.gcno
distclean-local:
rm -rf $(PACKAGE)-$(VERSION)-coverage*
endif # WITH_GCOV
## CMake support
EXTRA_DIST += \
cmake/COPYING-CMAKE-SCRIPTS \
cmake/FindEditline.cmake \
cmake/FindPackageHandleStandardArgs.cmake \
cmake/FindReadline.cmake \
cmake/pcre2-config-version.cmake.in \
cmake/pcre2-config.cmake.in \
CMakeLists.txt \
config-cmake.h.in
## end Makefile.am

436
Kha/Backends/Kore-hxcpp/khacpp/project/thirdparty/pcre2-10.42-16/NEWS vendored Normal file
View File

@ -0,0 +1,436 @@
News about PCRE2 releases
-------------------------
Version 10.42 11-December-2022
------------------------------
This is an unexpectedly early release to fix a problem that was introduced in
10.41. ChangeLog number 19 (GitHub #139) added the default definition of
PCRE2_CALL_CONVENTION to pcre2posix.c instead of pcre2posix.h, which meant that
programs including pcre2posix.h but not pcre2.h couldn't compile. A new test
that checks this case has been added.
A couple of other minor issues are also fixed, and a patch for an intermittent
JIT fault is also included. See ChangeLog and the Git log.
Version 10.41 06-December-2022
------------------------------
This is another mainly bug-fixing and code-tidying release. There is one
significant upgrade to pcre2grep: it now behaves like GNU grep when matching
more than one pattern and a later pattern matches at an earlier point in the
subject when the matched substrings are being identified by colour or by
offsets.
Version 10.40 15-April-2022
---------------------------
This is mostly a bug-fixing and code-tidying release. However, there are some
extensions to Unicode property handling:
* Added support for Bidi_Class and a number of binary Unicode properties,
including Bidi_Control.
* A number of changes to script matching for \p and \P:
(a) Script extensions for a character are now coded as a bitmap instead of
a list of script numbers, which should be faster and does not need a
loop.
(b) Added the syntax \p{script:xxx} and \p{script_extensions:xxx} (synonyms
sc and scx).
(c) Changed \p{scriptname} from being the same as \p{sc:scriptname} to being
the same as \p{scx:scriptname} because this change happened in Perl at
release 5.26.
(d) The standard Unicode 4-letter abbreviations for script names are now
recognized.
(e) In accordance with Unicode and Perl's "loose matching" rules, spaces,
hyphens, and underscores are ignored in property names, which are then
matched independent of case.
As always, see ChangeLog for a list of all changes (also the Git log).
Version 10.39 29-October-2021
-----------------------------
This release is happening soon after 10.38 because the bug fix is important.
1. Fix incorrect detection of alternatives in first character search in JIT.
2. Update to Unicode 14.0.0.
3. Some code cleanups (see ChangeLog).
Version 10.38 01-October-2021
-----------------------------
As well as some bug fixes and tidies (as always, see ChangeLog for details),
the documentation is updated to list the new URLs, following the move of the
source repository to GitHub and the mailing list to Google Groups.
* The CMake build system can now build both static and shared libraries in one
go.
* Following Perl's lead, \K is now locked out in lookaround assertions by
default, but an option is provided to re-enable the previous behaviour.
Version 10.37 26-May-2021
-------------------------
A few more bug fixes and tidies. The only change of real note is the removal of
the actual POSIX names regcomp etc. from the POSIX wrapper library because
these have caused issues for some applications (see 10.33 #2 below).
Version 10.36 04-December-2020
------------------------------
Again, mainly bug fixes and tidies. The only enhancements are the addition of
GNU grep's -m (aka --max-count) option to pcre2grep, and also unifying the
handling of substitution strings for both -O and callouts in pcre2grep, with
the addition of $x{...} and $o{...} to allow for characters whose code points
are greater than 255 in Unicode mode.
NOTE: there is an outstanding issue with JIT support for MacOS on arm64
hardware. For details, please see Bugzilla issue #2618.
Version 10.35 15-April-2020
---------------------------
Bugfixes, tidies, and a few new enhancements.
1. Capturing groups that contain recursive backreferences to themselves are no
longer automatically atomic, because the restriction is no longer necessary
as a result of the 10.30 restructuring.
2. Several new options for pcre2_substitute().
3. When Unicode is supported and PCRE2_UCP is set without PCRE2_UTF, Unicode
character properties are used for upper/lower case computations on characters
whose code points are greater than 127.
4. The character tables (for low-valued characters) can now more easily be
saved and restored in binary.
5. Updated to Unicode 13.0.0.
Version 10.34 21-November-2019
------------------------------
Another release with a few enhancements as well as bugfixes and tidies. The
main new features are:
1. There is now some support for matching in invalid UTF strings.
2. Non-atomic positive lookarounds are implemented in the pcre2_match()
interpreter, but not in JIT.
3. Added two new functions: pcre2_get_match_data_size() and
pcre2_maketables_free().
4. Upgraded to Unicode 12.1.0.
Version 10.33 16-April-2019
---------------------------
Yet more bugfixes, tidies, and a few enhancements, summarized here (see
ChangeLog for the full list):
1. Callouts from pcre2_substitute() are now available.
2. The POSIX functions are now all called pcre2_regcomp() etc., with wrapper
functions that use the standard POSIX names. However, in pcre2posix.h the POSIX
names are defined as macros. This should help avoid linking with the wrong
library in some environments, while still exporting the POSIX names for
pre-existing programs that use them.
3. Some new options:
(a) PCRE2_EXTRA_ESCAPED_CR_IS_LF makes \r behave as \n.
(b) PCRE2_EXTRA_ALT_BSUX enables support for ECMAScript 6's \u{hh...}
construct.
(c) PCRE2_COPY_MATCHED_SUBJECT causes a copy of a matched subject to be
made, instead of just remembering a pointer.
4. Some new Perl features:
(a) Perl 5.28's experimental alphabetic names for atomic groups and
lookaround assertions, for example, (*pla:...) and (*atomic:...).
(b) The new Perl "script run" features (*script_run:...) and
(*atomic_script_run:...) aka (*sr:...) and (*asr:...).
(c) When PCRE2_UTF is set, allow non-ASCII letters and decimal digits in
capture group names.
5. --disable-percent-zt disables the use of %zu and %td in formatting strings
in pcre2test. They were already automatically disabled for VC and older C
compilers.
6. Some changes related to callouts in pcre2grep:
(a) Support for running an external program under VMS has been added, in
addition to Windows and fork() support.
(b) --disable-pcre2grep-callout-fork restricts the callout support in
to the inbuilt echo facility.
Version 10.32 10-September-2018
-------------------------------
This is another mainly bugfix and tidying release with a few minor
enhancements. These are the main ones:
1. pcre2grep now supports the inclusion of binary zeros in patterns that are
read from files via the -f option.
2. ./configure now supports --enable-jit=auto, which automatically enables JIT
if the hardware supports it.
3. In pcre2_dfa_match(), internal recursive calls no longer use the stack for
local workspace and local ovectors. Instead, an initial block of stack is
reserved, but if this is insufficient, heap memory is used. The heap limit
parameter now applies to pcre2_dfa_match().
4. Updated to Unicode version 11.0.0.
5. (*ACCEPT:ARG), (*FAIL:ARG), and (*COMMIT:ARG) are now supported.
6. Added support for \N{U+dddd}, but only in Unicode mode.
7. Added support for (?^) to unset all imnsx options.
Version 10.31 12-February-2018
------------------------------
This is mainly a bugfix and tidying release (see ChangeLog for full details).
However, there are some minor enhancements.
1. New pcre2_config() options: PCRE2_CONFIG_NEVER_BACKSLASH_C and
PCRE2_CONFIG_COMPILED_WIDTHS.
2. New pcre2_pattern_info() option PCRE2_INFO_EXTRAOPTIONS to retrieve the
extra compile time options.
3. There are now public names for all the pcre2_compile() error numbers.
4. Added PCRE2_CALLOUT_STARTMATCH and PCRE2_CALLOUT_BACKTRACK bits to a new
field callout_flags in callout blocks.
Version 10.30 14-August-2017
----------------------------
The full list of changes that includes bugfixes and tidies is, as always, in
ChangeLog. These are the most important new features:
1. The main interpreter, pcre2_match(), has been refactored into a new version
that does not use recursive function calls (and therefore the system stack) for
remembering backtracking positions. This makes --disable-stack-for-recursion a
NOOP. The new implementation allows backtracking into recursive group calls in
patterns, making it more compatible with Perl, and also fixes some other
previously hard-to-do issues. For patterns that have a lot of backtracking, the
heap is now used, and there is an explicit limit on the amount, settable by
pcre2_set_heap_limit() or (*LIMIT_HEAP=xxx). The "recursion limit" is retained,
but is renamed as "depth limit" (though the old names remain for
compatibility).
There is also a change in the way callouts from pcre2_match() are handled. The
offset_vector field in the callout block is no longer a pointer to the
actual ovector that was passed to the matching function in the match data
block. Instead it points to an internal ovector of a size large enough to hold
all possible captured substrings in the pattern.
2. The new option PCRE2_ENDANCHORED insists that a pattern match must end at
the end of the subject.
3. The new option PCRE2_EXTENDED_MORE implements Perl's /xx feature, and
pcre2test is upgraded to support it. Setting within the pattern by (?xx) is
also supported.
4. (?n) can be used to set PCRE2_NO_AUTO_CAPTURE, because Perl now has this.
5. Additional compile options in the compile context are now available, and the
first two are: PCRE2_EXTRA_ALLOW_SURROGATE_ESCAPES and
PCRE2_EXTRA_BAD_ESCAPE_IS_LITERAL.
6. The newline type PCRE2_NEWLINE_NUL is now available.
7. The match limit value now also applies to pcre2_dfa_match() as there are
patterns that can use up a lot of resources without necessarily recursing very
deeply.
8. The option REG_PEND (a GNU extension) is now available for the POSIX
wrapper. Also there is a new option PCRE2_LITERAL which is used to support
REG_NOSPEC.
9. PCRE2_EXTRA_MATCH_LINE and PCRE2_EXTRA_MATCH_WORD are implemented for the
benefit of pcre2grep, and pcre2grep's -F, -w, and -x options are re-implemented
using PCRE2_LITERAL, PCRE2_EXTRA_MATCH_WORD, and PCRE2_EXTRA_MATCH_LINE. This
is tidier and also fixes some bugs.
10. The Unicode tables are upgraded from Unicode 8.0.0 to Unicode 10.0.0.
11. There are some experimental functions for converting foreign patterns
(globs and POSIX patterns) into PCRE2 patterns.
Version 10.23 14-February-2017
------------------------------
1. ChangeLog has the details of a lot of bug fixes and tidies.
2. There has been a major re-factoring of the pcre2_compile.c file. Most syntax
checking is now done in the pre-pass that identifies capturing groups. This has
reduced the amount of duplication and made the code tidier. While doing this,
some minor bugs and Perl incompatibilities were fixed (see ChangeLog for
details.)
3. Back references are now permitted in lookbehind assertions when there are
no duplicated group numbers (that is, (?| has not been used), and, if the
reference is by name, there is only one group of that name. The referenced
group must, of course be of fixed length.
4. \g{+<number>} (e.g. \g{+2} ) is now supported. It is a "forward back
reference" and can be useful in repetitions (compare \g{-<number>} ). Perl does
not recognize this syntax.
5. pcre2grep now automatically expands its buffer up to a maximum set by
--max-buffer-size.
6. The -t option (grand total) has been added to pcre2grep.
7. A new function called pcre2_code_copy_with_tables() exists to copy a
compiled pattern along with a private copy of the character tables that is
uses.
8. A user supplied a number of patches to upgrade pcre2grep under Windows and
tidy the code.
9. Several updates have been made to pcre2test and test scripts (see
ChangeLog).
Version 10.22 29-July-2016
--------------------------
1. ChangeLog has the details of a number of bug fixes.
2. The POSIX wrapper function regcomp() did not used to support back references
and subroutine calls if called with the REG_NOSUB option. It now does.
3. A new function, pcre2_code_copy(), is added, to make a copy of a compiled
pattern.
4. Support for string callouts is added to pcre2grep.
5. Added the PCRE2_NO_JIT option to pcre2_match().
6. The pcre2_get_error_message() function now returns with a negative error
code if the error number it is given is unknown.
7. Several updates have been made to pcre2test and test scripts (see
ChangeLog).
Version 10.21 12-January-2016
-----------------------------
1. Many bugs have been fixed. A large number of them were provoked only by very
strange pattern input, and were discovered by fuzzers. Some others were
discovered by code auditing. See ChangeLog for details.
2. The Unicode tables have been updated to Unicode version 8.0.0.
3. For Perl compatibility in EBCDIC environments, ranges such as a-z in a
class, where both values are literal letters in the same case, omit the
non-letter EBCDIC code points within the range.
4. There have been a number of enhancements to the pcre2_substitute() function,
giving more flexibility to replacement facilities. It is now also possible to
cause the function to return the needed buffer size if the one given is too
small.
5. The PCRE2_ALT_VERBNAMES option causes the "name" parts of special verbs such
as (*THEN:name) to be processed for backslashes and to take note of
PCRE2_EXTENDED.
6. PCRE2_INFO_HASBACKSLASHC makes it possible for a client to find out if a
pattern uses \C, and --never-backslash-C makes it possible to compile a version
PCRE2 in which the use of \C is always forbidden.
7. A limit to the length of pattern that can be handled can now be set by
calling pcre2_set_max_pattern_length().
8. When matching an unanchored pattern, a match can be required to begin within
a given number of code units after the start of the subject by calling
pcre2_set_offset_limit().
9. The pcre2test program has been extended to test new facilities, and it can
now run the tests when LF on its own is not a valid newline sequence.
10. The RunTest script has also been updated to enable more tests to be run.
11. There have been some minor performance enhancements.
Version 10.20 30-June-2015
--------------------------
1. Callouts with string arguments and the pcre2_callout_enumerate() function
have been implemented.
2. The PCRE2_NEVER_BACKSLASH_C option, which locks out the use of \C, is added.
3. The PCRE2_ALT_CIRCUMFLEX option lets ^ match after a newline at the end of a
subject in multiline mode.
4. The way named subpatterns are handled has been refactored. The previous
approach had several bugs.
5. The handling of \c in EBCDIC environments has been changed to conform to the
perlebcdic document. This is an incompatible change.
6. Bugs have been mended, many of them discovered by fuzzers.
Version 10.10 06-March-2015
---------------------------
1. Serialization and de-serialization functions have been added to the API,
making it possible to save and restore sets of compiled patterns, though
restoration must be done in the same environment that was used for compilation.
2. The (*NO_JIT) feature has been added; this makes it possible for a pattern
creator to specify that JIT is not to be used.
3. A number of bugs have been fixed. In particular, bugs that caused building
on Windows using CMake to fail have been mended.
Version 10.00 05-January-2015
-----------------------------
Version 10.00 is the first release of PCRE2, a revised API for the PCRE
library. Changes prior to 10.00 are logged in the ChangeLog file for the old
API, up to item 20 for release 8.36. New programs are recommended to use the
new library. Programs that use the original (PCRE1) API will need changing
before linking with the new library.
****

415
Kha/Backends/Kore-hxcpp/khacpp/project/thirdparty/pcre2-10.42-16/NON-AUTOTOOLS-BUILD vendored Normal file
View File

@ -0,0 +1,415 @@
Building PCRE2 without using autotools
--------------------------------------
This document contains the following sections:
General
Generic instructions for the PCRE2 C library
Stack size in Windows environments
Linking programs in Windows environments
Calling conventions in Windows environments
Comments about Win32 builds
Building PCRE2 on Windows with CMake
Building PCRE2 on Windows with Visual Studio
Testing with RunTest.bat
Building PCRE2 on native z/OS and z/VM
GENERAL
The basic PCRE2 library consists entirely of code written in Standard C, and so
should compile successfully on any system that has a Standard C compiler and
library.
The PCRE2 distribution includes a "configure" file for use by the
configure/make (autotools) build system, as found in many Unix-like
environments. The README file contains information about the options for
"configure".
There is also support for CMake, which some users prefer, especially in Windows
environments, though it can also be run in Unix-like environments. See the
section entitled "Building PCRE2 on Windows with CMake" below.
Versions of src/config.h and src/pcre2.h are distributed in the PCRE2 tarballs
under the names src/config.h.generic and src/pcre2.h.generic. These are
provided for those who build PCRE2 without using "configure" or CMake. If you
use "configure" or CMake, the .generic versions are not used.
GENERIC INSTRUCTIONS FOR THE PCRE2 C LIBRARY
The following are generic instructions for building the PCRE2 C library "by
hand". If you are going to use CMake, this section does not apply to you; you
can skip ahead to the CMake section. Note that the settings concerned with
8-bit, 16-bit, and 32-bit code units relate to the type of data string that
PCRE2 processes. They are NOT referring to the underlying operating system bit
width. You do not have to do anything special to compile in a 64-bit
environment, for example.
(1) Copy or rename the file src/config.h.generic as src/config.h, and edit the
macro settings that it contains to whatever is appropriate for your
environment. In particular, you can alter the definition of the NEWLINE
macro to specify what character(s) you want to be interpreted as line
terminators by default.
When you subsequently compile any of the PCRE2 modules, you must specify
-DHAVE_CONFIG_H to your compiler so that src/config.h is included in the
sources.
An alternative approach is not to edit src/config.h, but to use -D on the
compiler command line to make any changes that you need to the
configuration options. In this case -DHAVE_CONFIG_H must not be set.
NOTE: There have been occasions when the way in which certain parameters
in src/config.h are used has changed between releases. (In the
configure/make world, this is handled automatically.) When upgrading to a
new release, you are strongly advised to review src/config.h.generic
before re-using what you had previously.
Note also that the src/config.h.generic file is created from a config.h
that was generated by Autotools, which automatically includes settings of
a number of macros that are not actually used by PCRE2 (for example,
HAVE_DLFCN_H).
(2) Copy or rename the file src/pcre2.h.generic as src/pcre2.h.
(3) EITHER:
Copy or rename file src/pcre2_chartables.c.dist as
src/pcre2_chartables.c.
OR:
Compile src/pcre2_dftables.c as a stand-alone program (using
-DHAVE_CONFIG_H if you have set up src/config.h), and then run it with
the single argument "src/pcre2_chartables.c". This generates a set of
standard character tables and writes them to that file. The tables are
generated using the default C locale for your system. If you want to use
a locale that is specified by LC_xxx environment variables, add the -L
option to the pcre2_dftables command. You must use this method if you
are building on a system that uses EBCDIC code.
The tables in src/pcre2_chartables.c are defaults. The caller of PCRE2 can
specify alternative tables at run time.
(4) For a library that supports 8-bit code units in the character strings that
it processes, compile the following source files from the src directory,
setting -DPCRE2_CODE_UNIT_WIDTH=8 as a compiler option. Also set
-DHAVE_CONFIG_H if you have set up src/config.h with your configuration,
or else use other -D settings to change the configuration as required.
pcre2_auto_possess.c
pcre2_chartables.c
pcre2_compile.c
pcre2_config.c
pcre2_context.c
pcre2_convert.c
pcre2_dfa_match.c
pcre2_error.c
pcre2_extuni.c
pcre2_find_bracket.c
pcre2_jit_compile.c
pcre2_maketables.c
pcre2_match.c
pcre2_match_data.c
pcre2_newline.c
pcre2_ord2utf.c
pcre2_pattern_info.c
pcre2_script_run.c
pcre2_serialize.c
pcre2_string_utils.c
pcre2_study.c
pcre2_substitute.c
pcre2_substring.c
pcre2_tables.c
pcre2_ucd.c
pcre2_ucptables.c
pcre2_valid_utf.c
pcre2_xclass.c
Make sure that you include -I. in the compiler command (or equivalent for
an unusual compiler) so that all included PCRE2 header files are first
sought in the src directory under the current directory. Otherwise you run
the risk of picking up a previously-installed file from somewhere else.
Note that you must compile pcre2_jit_compile.c, even if you have not
defined SUPPORT_JIT in src/config.h, because when JIT support is not
configured, dummy functions are compiled. When JIT support IS configured,
pcre2_jit_compile.c #includes other files from the sljit subdirectory,
all of whose names begin with "sljit". It also #includes
src/pcre2_jit_match.c and src/pcre2_jit_misc.c, so you should not compile
those yourself.
Note also that the pcre2_fuzzsupport.c file contains special code that is
useful to those who want to run fuzzing tests on the PCRE2 library. Unless
you are doing that, you can ignore it.
(5) Now link all the compiled code into an object library in whichever form
your system keeps such libraries. This is the basic PCRE2 C 8-bit library.
If your system has static and shared libraries, you may have to do this
once for each type.
(6) If you want to build a library that supports 16-bit or 32-bit code units,
(as well as, or instead of the 8-bit library) just supply 16 or 32 as the
value of -DPCRE2_CODE_UNIT_WIDTH when you are compiling.
(7) If you want to build the POSIX wrapper functions (which apply only to the
8-bit library), ensure that you have the src/pcre2posix.h file and then
compile src/pcre2posix.c. Link the result (on its own) as the pcre2posix
library.
(8) The pcre2test program can be linked with any combination of the 8-bit,
16-bit and 32-bit libraries (depending on what you selected in
src/config.h). Compile src/pcre2test.c; don't forget -DHAVE_CONFIG_H if
necessary, but do NOT define PCRE2_CODE_UNIT_WIDTH. Then link with the
appropriate library/ies. If you compiled an 8-bit library, pcre2test also
needs the pcre2posix wrapper library.
(9) Run pcre2test on the testinput files in the testdata directory, and check
that the output matches the corresponding testoutput files. There are
comments about what each test does in the section entitled "Testing PCRE2"
in the README file. If you compiled more than one of the 8-bit, 16-bit and
32-bit libraries, you need to run pcre2test with the -16 option to do
16-bit tests and with the -32 option to do 32-bit tests.
Some tests are relevant only when certain build-time options are selected.
For example, test 4 is for Unicode support, and will not run if you have
built PCRE2 without it. See the comments at the start of each testinput
file. If you have a suitable Unix-like shell, the RunTest script will run
the appropriate tests for you. The command "RunTest list" will output a
list of all the tests.
Note that the supplied files are in Unix format, with just LF characters
as line terminators. You may need to edit them to change this if your
system uses a different convention.
(10) If you have built PCRE2 with SUPPORT_JIT, the JIT features can be tested
by running pcre2test with the -jit option. This is done automatically by
the RunTest script. You might also like to build and run the freestanding
JIT test program, src/pcre2_jit_test.c.
(11) The pcre2test program tests the POSIX wrapper library, but there is also a
freestanding test program in src/pcre2posix_test.c. It must be linked with
both the pcre2posix library and the 8-bit PCRE2 library.
(12) If you want to use the pcre2grep command, compile and link
src/pcre2grep.c; it uses only the basic 8-bit PCRE2 library (it does not
need the pcre2posix library). If you have built the PCRE2 library with JIT
support by defining SUPPORT_JIT in src/config.h, you can also define
SUPPORT_PCRE2GREP_JIT, which causes pcre2grep to make use of JIT (unless
it is run with --no-jit). If you define SUPPORT_PCRE2GREP_JIT without
defining SUPPORT_JIT, pcre2grep does not try to make use of JIT.
STACK SIZE IN WINDOWS ENVIRONMENTS
Prior to release 10.30 the default system stack size of 1MiB in some Windows
environments caused issues with some tests. This should no longer be the case
for 10.30 and later releases.
LINKING PROGRAMS IN WINDOWS ENVIRONMENTS
If you want to statically link a program against a PCRE2 library in the form of
a non-dll .a file, you must define PCRE2_STATIC before including src/pcre2.h.
CALLING CONVENTIONS IN WINDOWS ENVIRONMENTS
It is possible to compile programs to use different calling conventions using
MSVC. Search the web for "calling conventions" for more information. To make it
easier to change the calling convention for the exported functions in the
PCRE2 library, the macro PCRE2_CALL_CONVENTION is present in all the external
definitions. It can be set externally when compiling (e.g. in CFLAGS). If it is
not set, it defaults to empty; the default calling convention is then used
(which is what is wanted most of the time).
COMMENTS ABOUT WIN32 BUILDS (see also "BUILDING PCRE2 ON WINDOWS WITH CMAKE")
There are two ways of building PCRE2 using the "configure, make, make install"
paradigm on Windows systems: using MinGW or using Cygwin. These are not at all
the same thing; they are completely different from each other. There is also
support for building using CMake, which some users find a more straightforward
way of building PCRE2 under Windows.
The MinGW home page (http://www.mingw.org/) says this:
MinGW: A collection of freely available and freely distributable Windows
specific header files and import libraries combined with GNU toolsets that
allow one to produce native Windows programs that do not rely on any
3rd-party C runtime DLLs.
The Cygwin home page (http://www.cygwin.com/) says this:
Cygwin is a Linux-like environment for Windows. It consists of two parts:
. A DLL (cygwin1.dll) which acts as a Linux API emulation layer providing
substantial Linux API functionality
. A collection of tools which provide Linux look and feel.
On both MinGW and Cygwin, PCRE2 should build correctly using:
./configure && make && make install
This should create two libraries called libpcre2-8 and libpcre2-posix. These
are independent libraries: when you link with libpcre2-posix you must also link
with libpcre2-8, which contains the basic functions.
Using Cygwin's compiler generates libraries and executables that depend on
cygwin1.dll. If a library that is generated this way is distributed,
cygwin1.dll has to be distributed as well. Since cygwin1.dll is under the GPL
licence, this forces not only PCRE2 to be under the GPL, but also the entire
application. A distributor who wants to keep their own code proprietary must
purchase an appropriate Cygwin licence.
MinGW has no such restrictions. The MinGW compiler generates a library or
executable that can run standalone on Windows without any third party dll or
licensing issues.
But there is more complication:
If a Cygwin user uses the -mno-cygwin Cygwin gcc flag, what that really does is
to tell Cygwin's gcc to use the MinGW gcc. Cygwin's gcc is only acting as a
front end to MinGW's gcc (if you install Cygwin's gcc, you get both Cygwin's
gcc and MinGW's gcc). So, a user can:
. Build native binaries by using MinGW or by getting Cygwin and using
-mno-cygwin.
. Build binaries that depend on cygwin1.dll by using Cygwin with the normal
compiler flags.
The test files that are supplied with PCRE2 are in UNIX format, with LF
characters as line terminators. Unless your PCRE2 library uses a default
newline option that includes LF as a valid newline, it may be necessary to
change the line terminators in the test files to get some of the tests to work.
BUILDING PCRE2 ON WINDOWS WITH CMAKE
CMake is an alternative configuration facility that can be used instead of
"configure". CMake creates project files (make files, solution files, etc.)
tailored to numerous development environments, including Visual Studio,
Borland, Msys, MinGW, NMake, and Unix. If possible, use short paths with no
spaces in the names for your CMake installation and your PCRE2 source and build
directories.
The following instructions were contributed by a PCRE1 user, but they should
also work for PCRE2. If they are not followed exactly, errors may occur. In the
event that errors do occur, it is recommended that you delete the CMake cache
before attempting to repeat the CMake build process. In the CMake GUI, the
cache can be deleted by selecting "File > Delete Cache".
1. Install the latest CMake version available from http://www.cmake.org/, and
ensure that cmake\bin is on your path.
2. Unzip (retaining folder structure) the PCRE2 source tree into a source
directory such as C:\pcre2. You should ensure your local date and time
is not earlier than the file dates in your source dir if the release is
very new.
3. Create a new, empty build directory, preferably a subdirectory of the
source dir. For example, C:\pcre2\pcre2-xx\build.
4. Run cmake-gui from the Shell environment of your build tool, for example,
Msys for Msys/MinGW or Visual Studio Command Prompt for VC/VC++. Do not try
to start Cmake from the Windows Start menu, as this can lead to errors.
5. Enter C:\pcre2\pcre2-xx and C:\pcre2\pcre2-xx\build for the source and
build directories, respectively.
6. Hit the "Configure" button.
7. Select the particular IDE / build tool that you are using (Visual
Studio, MSYS makefiles, MinGW makefiles, etc.)
8. The GUI will then list several configuration options. This is where
you can disable Unicode support or select other PCRE2 optional features.
9. Hit "Configure" again. The adjacent "Generate" button should now be
active.
10. Hit "Generate".
11. The build directory should now contain a usable build system, be it a
solution file for Visual Studio, makefiles for MinGW, etc. Exit from
cmake-gui and use the generated build system with your compiler or IDE.
E.g., for MinGW you can run "make", or for Visual Studio, open the PCRE2
solution, select the desired configuration (Debug, or Release, etc.) and
build the ALL_BUILD project.
12. If during configuration with cmake-gui you've elected to build the test
programs, you can execute them by building the test project. E.g., for
MinGW: "make test"; for Visual Studio build the RUN_TESTS project. The
most recent build configuration is targeted by the tests. A summary of
test results is presented. Complete test output is subsequently
available for review in Testing\Temporary under your build dir.
BUILDING PCRE2 ON WINDOWS WITH VISUAL STUDIO
The code currently cannot be compiled without an inttypes.h header, which is
available only with Visual Studio 2013 or newer. However, this portable and
permissively-licensed implementation of the stdint.h header could be used as an
alternative:
http://www.azillionmonkeys.com/qed/pstdint.h
Just rename it and drop it into the top level of the build tree.
TESTING WITH RUNTEST.BAT
If configured with CMake, building the test project ("make test" or building
ALL_TESTS in Visual Studio) creates (and runs) pcre2_test.bat (and depending
on your configuration options, possibly other test programs) in the build
directory. The pcre2_test.bat script runs RunTest.bat with correct source and
exe paths.
For manual testing with RunTest.bat, provided the build dir is a subdirectory
of the source directory: Open command shell window. Chdir to the location
of your pcre2test.exe and pcre2grep.exe programs. Call RunTest.bat with
"..\RunTest.Bat" or "..\..\RunTest.bat" as appropriate.
To run only a particular test with RunTest.Bat provide a test number argument.
Otherwise:
1. Copy RunTest.bat into the directory where pcre2test.exe and pcre2grep.exe
have been created.
2. Edit RunTest.bat to identify the full or relative location of
the pcre2 source (wherein which the testdata folder resides), e.g.:
set srcdir=C:\pcre2\pcre2-10.00
3. In a Windows command environment, chdir to the location of your bat and
exe programs.
4. Run RunTest.bat. Test outputs will automatically be compared to expected
results, and discrepancies will be identified in the console output.
To independently test the just-in-time compiler, run pcre2_jit_test.exe.
BUILDING PCRE2 ON NATIVE Z/OS AND Z/VM
z/OS and z/VM are operating systems for mainframe computers, produced by IBM.
The character code used is EBCDIC, not ASCII or Unicode. In z/OS, UNIX APIs and
applications can be supported through UNIX System Services, and in such an
environment it should be possible to build PCRE2 in the same way as in other
systems, with the EBCDIC related configuration settings, but it is not known if
anybody has tried this.
In native z/OS (without UNIX System Services) and in z/VM, special ports are
required. For details, please see file 939 on this web site:
http://www.cbttape.org
Everything in that location, source and executable, is in EBCDIC and native
z/OS file formats. The port provides an API for LE languages such as COBOL and
for the z/OS and z/VM versions of the Rexx languages.
==============================
Last Updated: 10 December 2022
==============================

239
Kha/Backends/Kore-hxcpp/khacpp/project/thirdparty/pcre2-10.42-16/PrepareRelease vendored Normal file
View File

@ -0,0 +1,239 @@
#/bin/sh
# Script to prepare the files for building a PCRE2 release. It does some
# processing of the documentation, detrails files, and creates pcre2.h.generic
# and config.h.generic (for use by builders who can't run ./configure).
# You must run this script before runnning "make dist". If its first argument
# is "doc", it stops after preparing the documentation. There are no other
# arguments. The script makes use of the following files:
# 132html A Perl script that converts a .1 or .3 man page into HTML. It
# "knows" the relevant troff constructs that are used in the PCRE2
# man pages.
# CheckMan A Perl script that checks man pages for typos in the mark up.
# CleanTxt A Perl script that cleans up the output of "nroff -man" by
# removing backspaces and other redundant text so as to produce
# a readable .txt file.
# Detrail A Perl script that removes trailing spaces from files.
# doc/index.html.src
# A file that is copied as index.html into the doc/html directory
# when the HTML documentation is built. It works like this so that
# doc/html can be deleted and re-created from scratch.
# README & NON-AUTOTOOLS-BUILD
# These files are copied into the doc/html directory, with .txt
# extensions so that they can by hyperlinked from the HTML
# documentation, because some people just go to the HTML without
# looking for text files.
# First, sort out the documentation. Remove pcre2demo.3 first because it won't
# pass the markup check (it is created below, using markup that none of the
# other pages use).
cd doc
echo Processing documentation
/bin/rm -f pcre2demo.3
# Check the remaining man pages
perl ../CheckMan *.1 *.3
if [ $? != 0 ] ; then exit 1; fi
# Make Text form of the documentation. It needs some mangling to make it
# tidy for online reading. Concatenate all the .3 stuff, but omit the
# individual function pages.
cat <<End >pcre2.txt
-----------------------------------------------------------------------------
This file contains a concatenation of the PCRE2 man pages, converted to plain
text format for ease of searching with a text editor, or for use on systems
that do not have a man page processor. The small individual files that give
synopses of each function in the library have not been included. Neither has
the pcre2demo program. There are separate text files for the pcre2grep and
pcre2test commands.
-----------------------------------------------------------------------------
End
echo "Making pcre2.txt"
for file in pcre2 pcre2api pcre2build pcre2callout pcre2compat pcre2jit \
pcre2limits pcre2matching pcre2partial pcre2pattern pcre2perform \
pcre2posix pcre2sample pcre2serialize pcre2syntax \
pcre2unicode ; do
echo " Processing $file.3"
nroff -c -man $file.3 >$file.rawtxt
perl ../CleanTxt <$file.rawtxt >>pcre2.txt
/bin/rm $file.rawtxt
echo "------------------------------------------------------------------------------" >>pcre2.txt
if [ "$file" != "pcre2sample" ] ; then
echo " " >>pcre2.txt
echo " " >>pcre2.txt
fi
done
# The three commands
for file in pcre2test pcre2grep pcre2-config ; do
echo Making $file.txt
nroff -c -man $file.1 >$file.rawtxt
perl ../CleanTxt <$file.rawtxt >$file.txt
/bin/rm $file.rawtxt
done
# Make pcre2demo.3 from the pcre2demo.c source file
echo "Making pcre2demo.3"
perl <<"END" >pcre2demo.3
open(IN, "../src/pcre2demo.c") || die "Failed to open src/pcre2demo.c\n";
open(OUT, ">pcre2demo.3") || die "Failed to open pcre2demo.3\n";
print OUT ".SH NAME\n" .
"// - A demonstration C program for PCRE2 - //\n" .
".sp\n" .
".\\\" Start example.\n" .
".de EX\n" .
". nr mE \\\\n(.f\n" .
". nf\n" .
". nh\n" .
". ft CW\n" .
"..\n" .
".\n" .
".\n" .
".\\\" End example.\n" .
".de EE\n" .
". ft \\\\n(mE\n" .
". fi\n" .
". hy \\\\n(HY\n" .
"..\n" .
".\n" .
".EX\n" ;
while (<IN>)
{
s/\\/\\e/g;
print OUT;
}
print OUT ".EE\n";
close(IN);
close(OUT);
END
if [ $? != 0 ] ; then exit 1; fi
# Make HTML form of the documentation.
echo "Making HTML documentation"
/bin/rm html/*
cp index.html.src html/index.html
cp ../README html/README.txt
cp ../NON-AUTOTOOLS-BUILD html/NON-AUTOTOOLS-BUILD.txt
for file in *.1 ; do
base=`basename $file .1`
echo " Making $base.html"
perl ../132html -toc $base <$file >html/$base.html
done
# Exclude table of contents for function summaries. It seems that expr
# forces an anchored regex. Also exclude them for small pages that have
# only one section.
for file in *.3 ; do
base=`basename $file .3`
toc=-toc
if [ `expr $base : '.*_'` -ne 0 ] ; then toc="" ; fi
if [ "$base" = "pcre2sample" ] || \
[ "$base" = "pcre2compat" ] || \
[ "$base" = "pcre2limits" ] || \
[ "$base" = "pcre2unicode" ] ; then
toc=""
fi
echo " Making $base.html"
perl ../132html $toc $base <$file >html/$base.html
if [ $? != 0 ] ; then exit 1; fi
done
# End of documentation processing; stop if only documentation required.
cd ..
echo Documentation done
if [ "$1" = "doc" ] ; then exit; fi
# These files are detrailed; do not detrail the test data because there may be
# significant trailing spaces. Do not detrail RunTest.bat, because it has CRLF
# line endings and the detrail script removes all trailing white space. The
# configure files are also omitted from the detrailing.
files="\
Makefile.am \
configure.ac \
README \
LICENCE \
COPYING \
AUTHORS \
NEWS \
NON-AUTOTOOLS-BUILD \
INSTALL \
132html \
CleanTxt \
Detrail \
ChangeLog \
CMakeLists.txt \
RunGrepTest \
RunTest \
pcre2-config.in \
perltest.sh \
libpcre2-8.pc.in \
libpcre2-16.pc.in \
libpcre2-32.pc.in \
libpcre2-posix.pc.in \
src/pcre2_dftables.c \
src/pcre2.h.in \
src/pcre2_auto_possess.c \
src/pcre2_compile.c \
src/pcre2_config.c \
src/pcre2_context.c \
src/pcre2_convert.c \
src/pcre2_dfa_match.c \
src/pcre2_error.c \
src/pcre2_extuni.c \
src/pcre2_find_bracket.c \
src/pcre2_internal.h \
src/pcre2_intmodedep.h \
src/pcre2_jit_compile.c \
src/pcre2_jit_match.c \
src/pcre2_jit_misc.c \
src/pcre2_jit_test.c \
src/pcre2_maketables.c \
src/pcre2_match.c \
src/pcre2_match_data.c \
src/pcre2_newline.c \
src/pcre2_ord2utf.c \
src/pcre2_pattern_info.c \
src/pcre2_printint.c \
src/pcre2_string_utils.c \
src/pcre2_study.c \
src/pcre2_substring.c \
src/pcre2_tables.c \
src/pcre2_ucd.c \
src/pcre2_ucp.h \
src/pcre2_valid_utf.c \
src/pcre2_xclass.c \
src/pcre2demo.c \
src/pcre2grep.c \
src/pcre2posix.c \
src/pcre2posix.h \
src/pcre2test.c"
echo Detrailing
perl ./Detrail $files doc/p* doc/html/*
echo Done
#End

924
Kha/Backends/Kore-hxcpp/khacpp/project/thirdparty/pcre2-10.42-16/README vendored Normal file
View File

@ -0,0 +1,924 @@
README file for PCRE2 (Perl-compatible regular expression library)
------------------------------------------------------------------
PCRE2 is a re-working of the original PCRE1 library to provide an entirely new
API. Since its initial release in 2015, there has been further development of
the code and it now differs from PCRE1 in more than just the API. There are new
features, and the internals have been improved. The original PCRE1 library is
now obsolete and no longer maintained. The latest release of PCRE2 is available
in .tar.gz, tar.bz2, or .zip form from this GitHub repository:
https://github.com/PCRE2Project/pcre2/releases
There is a mailing list for discussion about the development of PCRE2 at
pcre2-dev@googlegroups.com. You can subscribe by sending an email to
pcre2-dev+subscribe@googlegroups.com.
You can access the archives and also subscribe or manage your subscription
here:
https://groups.google.com/g/pcre2-dev
Please read the NEWS file if you are upgrading from a previous release. The
contents of this README file are:
The PCRE2 APIs
Documentation for PCRE2
Contributions by users of PCRE2
Building PCRE2 on non-Unix-like systems
Building PCRE2 without using autotools
Building PCRE2 using autotools
Retrieving configuration information
Shared libraries
Cross-compiling using autotools
Making new tarballs
Testing PCRE2
Character tables
File manifest
The PCRE2 APIs
--------------
PCRE2 is written in C, and it has its own API. There are three sets of
functions, one for the 8-bit library, which processes strings of bytes, one for
the 16-bit library, which processes strings of 16-bit values, and one for the
32-bit library, which processes strings of 32-bit values. Unlike PCRE1, there
are no C++ wrappers.
The distribution does contain a set of C wrapper functions for the 8-bit
library that are based on the POSIX regular expression API (see the pcre2posix
man page). These are built into a library called libpcre2-posix. Note that this
just provides a POSIX calling interface to PCRE2; the regular expressions
themselves still follow Perl syntax and semantics. The POSIX API is restricted,
and does not give full access to all of PCRE2's facilities.
The header file for the POSIX-style functions is called pcre2posix.h. The
official POSIX name is regex.h, but I did not want to risk possible problems
with existing files of that name by distributing it that way. To use PCRE2 with
an existing program that uses the POSIX API, pcre2posix.h will have to be
renamed or pointed at by a link (or the program modified, of course). See the
pcre2posix documentation for more details.
Documentation for PCRE2
-----------------------
If you install PCRE2 in the normal way on a Unix-like system, you will end up
with a set of man pages whose names all start with "pcre2". The one that is
just called "pcre2" lists all the others. In addition to these man pages, the
PCRE2 documentation is supplied in two other forms:
1. There are files called doc/pcre2.txt, doc/pcre2grep.txt, and
doc/pcre2test.txt in the source distribution. The first of these is a
concatenation of the text forms of all the section 3 man pages except the
listing of pcre2demo.c and those that summarize individual functions. The
other two are the text forms of the section 1 man pages for the pcre2grep
and pcre2test commands. These text forms are provided for ease of scanning
with text editors or similar tools. They are installed in
<prefix>/share/doc/pcre2, where <prefix> is the installation prefix
(defaulting to /usr/local).
2. A set of files containing all the documentation in HTML form, hyperlinked
in various ways, and rooted in a file called index.html, is distributed in
doc/html and installed in <prefix>/share/doc/pcre2/html.
Building PCRE2 on non-Unix-like systems
---------------------------------------
For a non-Unix-like system, please read the file NON-AUTOTOOLS-BUILD, though if
your system supports the use of "configure" and "make" you may be able to build
PCRE2 using autotools in the same way as for many Unix-like systems.
PCRE2 can also be configured using CMake, which can be run in various ways
(command line, GUI, etc). This creates Makefiles, solution files, etc. The file
NON-AUTOTOOLS-BUILD has information about CMake.
PCRE2 has been compiled on many different operating systems. It should be
straightforward to build PCRE2 on any system that has a Standard C compiler and
library, because it uses only Standard C functions.
Building PCRE2 without using autotools
--------------------------------------
The use of autotools (in particular, libtool) is problematic in some
environments, even some that are Unix or Unix-like. See the NON-AUTOTOOLS-BUILD
file for ways of building PCRE2 without using autotools.
Building PCRE2 using autotools
------------------------------
The following instructions assume the use of the widely used "configure; make;
make install" (autotools) process.
If you have downloaded and unpacked a PCRE2 release tarball, run the
"configure" command from the PCRE2 directory, with your current directory set
to the directory where you want the files to be created. This command is a
standard GNU "autoconf" configuration script, for which generic instructions
are supplied in the file INSTALL.
The files in the GitHub repository do not contain "configure". If you have
downloaded the PCRE2 source files from GitHub, before you can run "configure"
you must run the shell script called autogen.sh. This runs a number of
autotools to create a "configure" script (you must of course have the autotools
commands installed in order to do this).
Most commonly, people build PCRE2 within its own distribution directory, and in
this case, on many systems, just running "./configure" is sufficient. However,
the usual methods of changing standard defaults are available. For example:
CFLAGS='-O2 -Wall' ./configure --prefix=/opt/local
This command specifies that the C compiler should be run with the flags '-O2
-Wall' instead of the default, and that "make install" should install PCRE2
under /opt/local instead of the default /usr/local.
If you want to build in a different directory, just run "configure" with that
directory as current. For example, suppose you have unpacked the PCRE2 source
into /source/pcre2/pcre2-xxx, but you want to build it in
/build/pcre2/pcre2-xxx:
cd /build/pcre2/pcre2-xxx
/source/pcre2/pcre2-xxx/configure
PCRE2 is written in C and is normally compiled as a C library. However, it is
possible to build it as a C++ library, though the provided building apparatus
does not have any features to support this.
There are some optional features that can be included or omitted from the PCRE2
library. They are also documented in the pcre2build man page.
. By default, both shared and static libraries are built. You can change this
by adding one of these options to the "configure" command:
--disable-shared
--disable-static
(See also "Shared libraries on Unix-like systems" below.)
. By default, only the 8-bit library is built. If you add --enable-pcre2-16 to
the "configure" command, the 16-bit library is also built. If you add
--enable-pcre2-32 to the "configure" command, the 32-bit library is also
built. If you want only the 16-bit or 32-bit library, use --disable-pcre2-8
to disable building the 8-bit library.
. If you want to include support for just-in-time (JIT) compiling, which can
give large performance improvements on certain platforms, add --enable-jit to
the "configure" command. This support is available only for certain hardware
architectures. If you try to enable it on an unsupported architecture, there
will be a compile time error. If in doubt, use --enable-jit=auto, which
enables JIT only if the current hardware is supported.
. If you are enabling JIT under SELinux environment you may also want to add
--enable-jit-sealloc, which enables the use of an executable memory allocator
that is compatible with SELinux. Warning: this allocator is experimental!
It does not support fork() operation and may crash when no disk space is
available. This option has no effect if JIT is disabled.
. If you do not want to make use of the default support for UTF-8 Unicode
character strings in the 8-bit library, UTF-16 Unicode character strings in
the 16-bit library, or UTF-32 Unicode character strings in the 32-bit
library, you can add --disable-unicode to the "configure" command. This
reduces the size of the libraries. It is not possible to configure one
library with Unicode support, and another without, in the same configuration.
It is also not possible to use --enable-ebcdic (see below) with Unicode
support, so if this option is set, you must also use --disable-unicode.
When Unicode support is available, the use of a UTF encoding still has to be
enabled by setting the PCRE2_UTF option at run time or starting a pattern
with (*UTF). When PCRE2 is compiled with Unicode support, its input can only
either be ASCII or UTF-8/16/32, even when running on EBCDIC platforms.
As well as supporting UTF strings, Unicode support includes support for the
\P, \p, and \X sequences that recognize Unicode character properties.
However, only a subset of Unicode properties are supported; see the
pcre2pattern man page for details. Escape sequences such as \d and \w in
patterns do not by default make use of Unicode properties, but can be made to
do so by setting the PCRE2_UCP option or starting a pattern with (*UCP).
. You can build PCRE2 to recognize either CR or LF or the sequence CRLF, or any
of the preceding, or any of the Unicode newline sequences, or the NUL (zero)
character as indicating the end of a line. Whatever you specify at build time
is the default; the caller of PCRE2 can change the selection at run time. The
default newline indicator is a single LF character (the Unix standard). You
can specify the default newline indicator by adding --enable-newline-is-cr,
--enable-newline-is-lf, --enable-newline-is-crlf,
--enable-newline-is-anycrlf, --enable-newline-is-any, or
--enable-newline-is-nul to the "configure" command, respectively.
. By default, the sequence \R in a pattern matches any Unicode line ending
sequence. This is independent of the option specifying what PCRE2 considers
to be the end of a line (see above). However, the caller of PCRE2 can
restrict \R to match only CR, LF, or CRLF. You can make this the default by
adding --enable-bsr-anycrlf to the "configure" command (bsr = "backslash R").
. In a pattern, the escape sequence \C matches a single code unit, even in a
UTF mode. This can be dangerous because it breaks up multi-code-unit
characters. You can build PCRE2 with the use of \C permanently locked out by
adding --enable-never-backslash-C (note the upper case C) to the "configure"
command. When \C is allowed by the library, individual applications can lock
it out by calling pcre2_compile() with the PCRE2_NEVER_BACKSLASH_C option.
. PCRE2 has a counter that limits the depth of nesting of parentheses in a
pattern. This limits the amount of system stack that a pattern uses when it
is compiled. The default is 250, but you can change it by setting, for
example,
--with-parens-nest-limit=500
. PCRE2 has a counter that can be set to limit the amount of computing resource
it uses when matching a pattern. If the limit is exceeded during a match, the
match fails. The default is ten million. You can change the default by
setting, for example,
--with-match-limit=500000
on the "configure" command. This is just the default; individual calls to
pcre2_match() or pcre2_dfa_match() can supply their own value. There is more
discussion in the pcre2api man page (search for pcre2_set_match_limit).
. There is a separate counter that limits the depth of nested backtracking
(pcre2_match()) or nested function calls (pcre2_dfa_match()) during a
matching process, which indirectly limits the amount of heap memory that is
used, and in the case of pcre2_dfa_match() the amount of stack as well. This
counter also has a default of ten million, which is essentially "unlimited".
You can change the default by setting, for example,
--with-match-limit-depth=5000
There is more discussion in the pcre2api man page (search for
pcre2_set_depth_limit).
. You can also set an explicit limit on the amount of heap memory used by
the pcre2_match() and pcre2_dfa_match() interpreters:
--with-heap-limit=500
The units are kibibytes (units of 1024 bytes). This limit does not apply when
the JIT optimization (which has its own memory control features) is used.
There is more discussion on the pcre2api man page (search for
pcre2_set_heap_limit).
. In the 8-bit library, the default maximum compiled pattern size is around
64 kibibytes. You can increase this by adding --with-link-size=3 to the
"configure" command. PCRE2 then uses three bytes instead of two for offsets
to different parts of the compiled pattern. In the 16-bit library,
--with-link-size=3 is the same as --with-link-size=4, which (in both
libraries) uses four-byte offsets. Increasing the internal link size reduces
performance in the 8-bit and 16-bit libraries. In the 32-bit library, the
link size setting is ignored, as 4-byte offsets are always used.
. For speed, PCRE2 uses four tables for manipulating and identifying characters
whose code point values are less than 256. By default, it uses a set of
tables for ASCII encoding that is part of the distribution. If you specify
--enable-rebuild-chartables
a program called pcre2_dftables is compiled and run in the default C locale
when you obey "make". It builds a source file called pcre2_chartables.c. If
you do not specify this option, pcre2_chartables.c is created as a copy of
pcre2_chartables.c.dist. See "Character tables" below for further
information.
. It is possible to compile PCRE2 for use on systems that use EBCDIC as their
character code (as opposed to ASCII/Unicode) by specifying
--enable-ebcdic --disable-unicode
This automatically implies --enable-rebuild-chartables (see above). However,
when PCRE2 is built this way, it always operates in EBCDIC. It cannot support
both EBCDIC and UTF-8/16/32. There is a second option, --enable-ebcdic-nl25,
which specifies that the code value for the EBCDIC NL character is 0x25
instead of the default 0x15.
. If you specify --enable-debug, additional debugging code is included in the
build. This option is intended for use by the PCRE2 maintainers.
. In environments where valgrind is installed, if you specify
--enable-valgrind
PCRE2 will use valgrind annotations to mark certain memory regions as
unaddressable. This allows it to detect invalid memory accesses, and is
mostly useful for debugging PCRE2 itself.
. In environments where the gcc compiler is used and lcov is installed, if you
specify
--enable-coverage
the build process implements a code coverage report for the test suite. The
report is generated by running "make coverage". If ccache is installed on
your system, it must be disabled when building PCRE2 for coverage reporting.
You can do this by setting the environment variable CCACHE_DISABLE=1 before
running "make" to build PCRE2. There is more information about coverage
reporting in the "pcre2build" documentation.
. When JIT support is enabled, pcre2grep automatically makes use of it, unless
you add --disable-pcre2grep-jit to the "configure" command.
. There is support for calling external programs during matching in the
pcre2grep command, using PCRE2's callout facility with string arguments. This
support can be disabled by adding --disable-pcre2grep-callout to the
"configure" command. There are two kinds of callout: one that generates
output from inbuilt code, and another that calls an external program. The
latter has special support for Windows and VMS; otherwise it assumes the
existence of the fork() function. This facility can be disabled by adding
--disable-pcre2grep-callout-fork to the "configure" command.
. The pcre2grep program currently supports only 8-bit data files, and so
requires the 8-bit PCRE2 library. It is possible to compile pcre2grep to use
libz and/or libbz2, in order to read .gz and .bz2 files (respectively), by
specifying one or both of
--enable-pcre2grep-libz
--enable-pcre2grep-libbz2
Of course, the relevant libraries must be installed on your system.
. The default starting size (in bytes) of the internal buffer used by pcre2grep
can be set by, for example:
--with-pcre2grep-bufsize=51200
The value must be a plain integer. The default is 20480. The amount of memory
used by pcre2grep is actually three times this number, to allow for "before"
and "after" lines. If very long lines are encountered, the buffer is
automatically enlarged, up to a fixed maximum size.
. The default maximum size of pcre2grep's internal buffer can be set by, for
example:
--with-pcre2grep-max-bufsize=2097152
The default is either 1048576 or the value of --with-pcre2grep-bufsize,
whichever is the larger.
. It is possible to compile pcre2test so that it links with the libreadline
or libedit libraries, by specifying, respectively,
--enable-pcre2test-libreadline or --enable-pcre2test-libedit
If this is done, when pcre2test's input is from a terminal, it reads it using
the readline() function. This provides line-editing and history facilities.
Note that libreadline is GPL-licenced, so if you distribute a binary of
pcre2test linked in this way, there may be licensing issues. These can be
avoided by linking with libedit (which has a BSD licence) instead.
Enabling libreadline causes the -lreadline option to be added to the
pcre2test build. In many operating environments with a sytem-installed
readline library this is sufficient. However, in some environments (e.g. if
an unmodified distribution version of readline is in use), it may be
necessary to specify something like LIBS="-lncurses" as well. This is
because, to quote the readline INSTALL, "Readline uses the termcap functions,
but does not link with the termcap or curses library itself, allowing
applications which link with readline the option to choose an appropriate
library." If you get error messages about missing functions tgetstr, tgetent,
tputs, tgetflag, or tgoto, this is the problem, and linking with the ncurses
library should fix it.
. The C99 standard defines formatting modifiers z and t for size_t and
ptrdiff_t values, respectively. By default, PCRE2 uses these modifiers in
environments other than Microsoft Visual Studio versions earlier than 2013
when __STDC_VERSION__ is defined and has a value greater than or equal to
199901L (indicating C99). However, there is at least one environment that
claims to be C99 but does not support these modifiers. If
--disable-percent-zt is specified, no use is made of the z or t modifiers.
Instead of %td or %zu, %lu is used, with a cast for size_t values.
. There is a special option called --enable-fuzz-support for use by people who
want to run fuzzing tests on PCRE2. At present this applies only to the 8-bit
library. If set, it causes an extra library called libpcre2-fuzzsupport.a to
be built, but not installed. This contains a single function called
LLVMFuzzerTestOneInput() whose arguments are a pointer to a string and the
length of the string. When called, this function tries to compile the string
as a pattern, and if that succeeds, to match it. This is done both with no
options and with some random options bits that are generated from the string.
Setting --enable-fuzz-support also causes a binary called pcre2fuzzcheck to
be created. This is normally run under valgrind or used when PCRE2 is
compiled with address sanitizing enabled. It calls the fuzzing function and
outputs information about what it is doing. The input strings are specified
by arguments: if an argument starts with "=" the rest of it is a literal
input string. Otherwise, it is assumed to be a file name, and the contents
of the file are the test string.
. Releases before 10.30 could be compiled with --disable-stack-for-recursion,
which caused pcre2_match() to use individual blocks on the heap for
backtracking instead of recursive function calls (which use the stack). This
is now obsolete because pcre2_match() was refactored always to use the heap
(in a much more efficient way than before). This option is retained for
backwards compatibility, but has no effect other than to output a warning.
The "configure" script builds the following files for the basic C library:
. Makefile the makefile that builds the library
. src/config.h build-time configuration options for the library
. src/pcre2.h the public PCRE2 header file
. pcre2-config script that shows the building settings such as CFLAGS
that were set for "configure"
. libpcre2-8.pc )
. libpcre2-16.pc ) data for the pkg-config command
. libpcre2-32.pc )
. libpcre2-posix.pc )
. libtool script that builds shared and/or static libraries
Versions of config.h and pcre2.h are distributed in the src directory of PCRE2
tarballs under the names config.h.generic and pcre2.h.generic. These are
provided for those who have to build PCRE2 without using "configure" or CMake.
If you use "configure" or CMake, the .generic versions are not used.
The "configure" script also creates config.status, which is an executable
script that can be run to recreate the configuration, and config.log, which
contains compiler output from tests that "configure" runs.
Once "configure" has run, you can run "make". This builds whichever of the
libraries libpcre2-8, libpcre2-16 and libpcre2-32 are configured, and a test
program called pcre2test. If you enabled JIT support with --enable-jit, another
test program called pcre2_jit_test is built as well. If the 8-bit library is
built, libpcre2-posix, pcre2posix_test, and the pcre2grep command are also
built. Running "make" with the -j option may speed up compilation on
multiprocessor systems.
The command "make check" runs all the appropriate tests. Details of the PCRE2
tests are given below in a separate section of this document. The -j option of
"make" can also be used when running the tests.
You can use "make install" to install PCRE2 into live directories on your
system. The following are installed (file names are all relative to the
<prefix> that is set when "configure" is run):
Commands (bin):
pcre2test
pcre2grep (if 8-bit support is enabled)
pcre2-config
Libraries (lib):
libpcre2-8 (if 8-bit support is enabled)
libpcre2-16 (if 16-bit support is enabled)
libpcre2-32 (if 32-bit support is enabled)
libpcre2-posix (if 8-bit support is enabled)
Configuration information (lib/pkgconfig):
libpcre2-8.pc
libpcre2-16.pc
libpcre2-32.pc
libpcre2-posix.pc
Header files (include):
pcre2.h
pcre2posix.h
Man pages (share/man/man{1,3}):
pcre2grep.1
pcre2test.1
pcre2-config.1
pcre2.3
pcre2*.3 (lots more pages, all starting "pcre2")
HTML documentation (share/doc/pcre2/html):
index.html
*.html (lots more pages, hyperlinked from index.html)
Text file documentation (share/doc/pcre2):
AUTHORS
COPYING
ChangeLog
LICENCE
NEWS
README
pcre2.txt (a concatenation of the man(3) pages)
pcre2test.txt the pcre2test man page
pcre2grep.txt the pcre2grep man page
pcre2-config.txt the pcre2-config man page
If you want to remove PCRE2 from your system, you can run "make uninstall".
This removes all the files that "make install" installed. However, it does not
remove any directories, because these are often shared with other programs.
Retrieving configuration information
------------------------------------
Running "make install" installs the command pcre2-config, which can be used to
recall information about the PCRE2 configuration and installation. For example:
pcre2-config --version
prints the version number, and
pcre2-config --libs8
outputs information about where the 8-bit library is installed. This command
can be included in makefiles for programs that use PCRE2, saving the programmer
from having to remember too many details. Run pcre2-config with no arguments to
obtain a list of possible arguments.
The pkg-config command is another system for saving and retrieving information
about installed libraries. Instead of separate commands for each library, a
single command is used. For example:
pkg-config --libs libpcre2-16
The data is held in *.pc files that are installed in a directory called
<prefix>/lib/pkgconfig.
Shared libraries
----------------
The default distribution builds PCRE2 as shared libraries and static libraries,
as long as the operating system supports shared libraries. Shared library
support relies on the "libtool" script which is built as part of the
"configure" process.
The libtool script is used to compile and link both shared and static
libraries. They are placed in a subdirectory called .libs when they are newly
built. The programs pcre2test and pcre2grep are built to use these uninstalled
libraries (by means of wrapper scripts in the case of shared libraries). When
you use "make install" to install shared libraries, pcre2grep and pcre2test are
automatically re-built to use the newly installed shared libraries before being
installed themselves. However, the versions left in the build directory still
use the uninstalled libraries.
To build PCRE2 using static libraries only you must use --disable-shared when
configuring it. For example:
./configure --prefix=/usr/gnu --disable-shared
Then run "make" in the usual way. Similarly, you can use --disable-static to
build only shared libraries.
Cross-compiling using autotools
-------------------------------
You can specify CC and CFLAGS in the normal way to the "configure" command, in
order to cross-compile PCRE2 for some other host. However, you should NOT
specify --enable-rebuild-chartables, because if you do, the pcre2_dftables.c
source file is compiled and run on the local host, in order to generate the
inbuilt character tables (the pcre2_chartables.c file). This will probably not
work, because pcre2_dftables.c needs to be compiled with the local compiler,
not the cross compiler.
When --enable-rebuild-chartables is not specified, pcre2_chartables.c is
created by making a copy of pcre2_chartables.c.dist, which is a default set of
tables that assumes ASCII code. Cross-compiling with the default tables should
not be a problem.
If you need to modify the character tables when cross-compiling, you should
move pcre2_chartables.c.dist out of the way, then compile pcre2_dftables.c by
hand and run it on the local host to make a new version of
pcre2_chartables.c.dist. See the pcre2build section "Creating character tables
at build time" for more details.
Making new tarballs
-------------------
The command "make dist" creates three PCRE2 tarballs, in tar.gz, tar.bz2, and
zip formats. The command "make distcheck" does the same, but then does a trial
build of the new distribution to ensure that it works.
If you have modified any of the man page sources in the doc directory, you
should first run the PrepareRelease script before making a distribution. This
script creates the .txt and HTML forms of the documentation from the man pages.
Testing PCRE2
-------------
To test the basic PCRE2 library on a Unix-like system, run the RunTest script.
There is another script called RunGrepTest that tests the pcre2grep command.
When the 8-bit library is built, a test program for the POSIX wrapper, called
pcre2posix_test, is compiled, and when JIT support is enabled, a test program
called pcre2_jit_test is built. The scripts and the program tests are all run
when you obey "make check". For other environments, see the instructions in
NON-AUTOTOOLS-BUILD.
The RunTest script runs the pcre2test test program (which is documented in its
own man page) on each of the relevant testinput files in the testdata
directory, and compares the output with the contents of the corresponding
testoutput files. RunTest uses a file called testtry to hold the main output
from pcre2test. Other files whose names begin with "test" are used as working
files in some tests.
Some tests are relevant only when certain build-time options were selected. For
example, the tests for UTF-8/16/32 features are run only when Unicode support
is available. RunTest outputs a comment when it skips a test.
Many (but not all) of the tests that are not skipped are run twice if JIT
support is available. On the second run, JIT compilation is forced. This
testing can be suppressed by putting "-nojit" on the RunTest command line.
The entire set of tests is run once for each of the 8-bit, 16-bit and 32-bit
libraries that are enabled. If you want to run just one set of tests, call
RunTest with either the -8, -16 or -32 option.
If valgrind is installed, you can run the tests under it by putting "-valgrind"
on the RunTest command line. To run pcre2test on just one or more specific test
files, give their numbers as arguments to RunTest, for example:
RunTest 2 7 11
You can also specify ranges of tests such as 3-6 or 3- (meaning 3 to the
end), or a number preceded by ~ to exclude a test. For example:
Runtest 3-15 ~10
This runs tests 3 to 15, excluding test 10, and just ~13 runs all the tests
except test 13. Whatever order the arguments are in, the tests are always run
in numerical order.
You can also call RunTest with the single argument "list" to cause it to output
a list of tests.
The test sequence starts with "test 0", which is a special test that has no
input file, and whose output is not checked. This is because it will be
different on different hardware and with different configurations. The test
exists in order to exercise some of pcre2test's code that would not otherwise
be run.
Tests 1 and 2 can always be run, as they expect only plain text strings (not
UTF) and make no use of Unicode properties. The first test file can be fed
directly into the perltest.sh script to check that Perl gives the same results.
The only difference you should see is in the first few lines, where the Perl
version is given instead of the PCRE2 version. The second set of tests check
auxiliary functions, error detection, and run-time flags that are specific to
PCRE2. It also uses the debugging flags to check some of the internals of
pcre2_compile().
If you build PCRE2 with a locale setting that is not the standard C locale, the
character tables may be different (see next paragraph). In some cases, this may
cause failures in the second set of tests. For example, in a locale where the
isprint() function yields TRUE for characters in the range 128-255, the use of
[:isascii:] inside a character class defines a different set of characters, and
this shows up in this test as a difference in the compiled code, which is being
listed for checking. For example, where the comparison test output contains
[\x00-\x7f] the test might contain [\x00-\xff], and similarly in some other
cases. This is not a bug in PCRE2.
Test 3 checks pcre2_maketables(), the facility for building a set of character
tables for a specific locale and using them instead of the default tables. The
script uses the "locale" command to check for the availability of the "fr_FR",
"french", or "fr" locale, and uses the first one that it finds. If the "locale"
command fails, or if its output doesn't include "fr_FR", "french", or "fr" in
the list of available locales, the third test cannot be run, and a comment is
output to say why. If running this test produces an error like this:
** Failed to set locale "fr_FR"
it means that the given locale is not available on your system, despite being
listed by "locale". This does not mean that PCRE2 is broken. There are three
alternative output files for the third test, because three different versions
of the French locale have been encountered. The test passes if its output
matches any one of them.
Tests 4 and 5 check UTF and Unicode property support, test 4 being compatible
with the perltest.sh script, and test 5 checking PCRE2-specific things.
Tests 6 and 7 check the pcre2_dfa_match() alternative matching function, in
non-UTF mode and UTF-mode with Unicode property support, respectively.
Test 8 checks some internal offsets and code size features, but it is run only
when Unicode support is enabled. The output is different in 8-bit, 16-bit, and
32-bit modes and for different link sizes, so there are different output files
for each mode and link size.
Tests 9 and 10 are run only in 8-bit mode, and tests 11 and 12 are run only in
16-bit and 32-bit modes. These are tests that generate different output in
8-bit mode. Each pair are for general cases and Unicode support, respectively.
Test 13 checks the handling of non-UTF characters greater than 255 by
pcre2_dfa_match() in 16-bit and 32-bit modes.
Test 14 contains some special UTF and UCP tests that give different output for
different code unit widths.
Test 15 contains a number of tests that must not be run with JIT. They check,
among other non-JIT things, the match-limiting features of the interpretive
matcher.
Test 16 is run only when JIT support is not available. It checks that an
attempt to use JIT has the expected behaviour.
Test 17 is run only when JIT support is available. It checks JIT complete and
partial modes, match-limiting under JIT, and other JIT-specific features.
Tests 18 and 19 are run only in 8-bit mode. They check the POSIX interface to
the 8-bit library, without and with Unicode support, respectively.
Test 20 checks the serialization functions by writing a set of compiled
patterns to a file, and then reloading and checking them.
Tests 21 and 22 test \C support when the use of \C is not locked out, without
and with UTF support, respectively. Test 23 tests \C when it is locked out.
Tests 24 and 25 test the experimental pattern conversion functions, without and
with UTF support, respectively.
Test 26 checks Unicode property support using tests that are generated
automatically from the Unicode data tables.
Character tables
----------------
For speed, PCRE2 uses four tables for manipulating and identifying characters
whose code point values are less than 256. By default, a set of tables that is
built into the library is used. The pcre2_maketables() function can be called
by an application to create a new set of tables in the current locale. This are
passed to PCRE2 by calling pcre2_set_character_tables() to put a pointer into a
compile context.
The source file called pcre2_chartables.c contains the default set of tables.
By default, this is created as a copy of pcre2_chartables.c.dist, which
contains tables for ASCII coding. However, if --enable-rebuild-chartables is
specified for ./configure, a new version of pcre2_chartables.c is built by the
program pcre2_dftables (compiled from pcre2_dftables.c), which uses the ANSI C
character handling functions such as isalnum(), isalpha(), isupper(),
islower(), etc. to build the table sources. This means that the default C
locale that is set for your system will control the contents of these default
tables. You can change the default tables by editing pcre2_chartables.c and
then re-building PCRE2. If you do this, you should take care to ensure that the
file does not get automatically re-generated. The best way to do this is to
move pcre2_chartables.c.dist out of the way and replace it with your customized
tables.
When the pcre2_dftables program is run as a result of specifying
--enable-rebuild-chartables, it uses the default C locale that is set on your
system. It does not pay attention to the LC_xxx environment variables. In other
words, it uses the system's default locale rather than whatever the compiling
user happens to have set. If you really do want to build a source set of
character tables in a locale that is specified by the LC_xxx variables, you can
run the pcre2_dftables program by hand with the -L option. For example:
./pcre2_dftables -L pcre2_chartables.c.special
The second argument names the file where the source code for the tables is
written. The first two 256-byte tables provide lower casing and case flipping
functions, respectively. The next table consists of a number of 32-byte bit
maps which identify certain character classes such as digits, "word"
characters, white space, etc. These are used when building 32-byte bit maps
that represent character classes for code points less than 256. The final
256-byte table has bits indicating various character types, as follows:
1 white space character
2 letter
4 lower case letter
8 decimal digit
16 alphanumeric or '_'
You can also specify -b (with or without -L) when running pcre2_dftables. This
causes the tables to be written in binary instead of as source code. A set of
binary tables can be loaded into memory by an application and passed to
pcre2_compile() in the same way as tables created dynamically by calling
pcre2_maketables(). The tables are just a string of bytes, independent of
hardware characteristics such as endianness. This means they can be bundled
with an application that runs in different environments, to ensure consistent
behaviour.
See also the pcre2build section "Creating character tables at build time".
File manifest
-------------
The distribution should contain the files listed below.
(A) Source files for the PCRE2 library functions and their headers are found in
the src directory:
src/pcre2_dftables.c auxiliary program for building pcre2_chartables.c
when --enable-rebuild-chartables is specified
src/pcre2_chartables.c.dist a default set of character tables that assume
ASCII coding; unless --enable-rebuild-chartables is
specified, used by copying to pcre2_chartables.c
src/pcre2posix.c )
src/pcre2_auto_possess.c )
src/pcre2_compile.c )
src/pcre2_config.c )
src/pcre2_context.c )
src/pcre2_convert.c )
src/pcre2_dfa_match.c )
src/pcre2_error.c )
src/pcre2_extuni.c )
src/pcre2_find_bracket.c )
src/pcre2_jit_compile.c )
src/pcre2_jit_match.c ) sources for the functions in the library,
src/pcre2_jit_misc.c ) and some internal functions that they use
src/pcre2_maketables.c )
src/pcre2_match.c )
src/pcre2_match_data.c )
src/pcre2_newline.c )
src/pcre2_ord2utf.c )
src/pcre2_pattern_info.c )
src/pcre2_script_run.c )
src/pcre2_serialize.c )
src/pcre2_string_utils.c )
src/pcre2_study.c )
src/pcre2_substitute.c )
src/pcre2_substring.c )
src/pcre2_tables.c )
src/pcre2_ucd.c )
src/pcre2_ucptables.c )
src/pcre2_valid_utf.c )
src/pcre2_xclass.c )
src/pcre2_printint.c debugging function that is used by pcre2test,
src/pcre2_fuzzsupport.c function for (optional) fuzzing support
src/config.h.in template for config.h, when built by "configure"
src/pcre2.h.in template for pcre2.h when built by "configure"
src/pcre2posix.h header for the external POSIX wrapper API
src/pcre2_internal.h header for internal use
src/pcre2_intmodedep.h a mode-specific internal header
src/pcre2_jit_neon_inc.h header used by JIT
src/pcre2_jit_simd_inc.h header used by JIT
src/pcre2_ucp.h header for Unicode property handling
sljit/* source files for the JIT compiler
(B) Source files for programs that use PCRE2:
src/pcre2demo.c simple demonstration of coding calls to PCRE2
src/pcre2grep.c source of a grep utility that uses PCRE2
src/pcre2test.c comprehensive test program
src/pcre2_jit_test.c JIT test program
src/pcre2posix_test.c POSIX wrapper API test program
(C) Auxiliary files:
132html script to turn "man" pages into HTML
AUTHORS information about the author of PCRE2
ChangeLog log of changes to the code
CleanTxt script to clean nroff output for txt man pages
Detrail script to remove trailing spaces
HACKING some notes about the internals of PCRE2
INSTALL generic installation instructions
LICENCE conditions for the use of PCRE2
COPYING the same, using GNU's standard name
Makefile.in ) template for Unix Makefile, which is built by
) "configure"
Makefile.am ) the automake input that was used to create
) Makefile.in
NEWS important changes in this release
NON-AUTOTOOLS-BUILD notes on building PCRE2 without using autotools
PrepareRelease script to make preparations for "make dist"
README this file
RunTest a Unix shell script for running tests
RunGrepTest a Unix shell script for pcre2grep tests
aclocal.m4 m4 macros (generated by "aclocal")
config.guess ) files used by libtool,
config.sub ) used only when building a shared library
configure a configuring shell script (built by autoconf)
configure.ac ) the autoconf input that was used to build
) "configure" and config.h
depcomp ) script to find program dependencies, generated by
) automake
doc/*.3 man page sources for PCRE2
doc/*.1 man page sources for pcre2grep and pcre2test
doc/index.html.src the base HTML page
doc/html/* HTML documentation
doc/pcre2.txt plain text version of the man pages
doc/pcre2test.txt plain text documentation of test program
install-sh a shell script for installing files
libpcre2-8.pc.in template for libpcre2-8.pc for pkg-config
libpcre2-16.pc.in template for libpcre2-16.pc for pkg-config
libpcre2-32.pc.in template for libpcre2-32.pc for pkg-config
libpcre2-posix.pc.in template for libpcre2-posix.pc for pkg-config
ltmain.sh file used to build a libtool script
missing ) common stub for a few missing GNU programs while
) installing, generated by automake
mkinstalldirs script for making install directories
perltest.sh Script for running a Perl test program
pcre2-config.in source of script which retains PCRE2 information
testdata/testinput* test data for main library tests
testdata/testoutput* expected test results
testdata/grep* input and output for pcre2grep tests
testdata/* other supporting test files
(D) Auxiliary files for cmake support
cmake/COPYING-CMAKE-SCRIPTS
cmake/FindPackageHandleStandardArgs.cmake
cmake/FindEditline.cmake
cmake/FindReadline.cmake
CMakeLists.txt
config-cmake.h.in
(E) Auxiliary files for building PCRE2 "by hand"
src/pcre2.h.generic ) a version of the public PCRE2 header file
) for use in non-"configure" environments
src/config.h.generic ) a version of config.h for use in non-"configure"
) environments
Philip Hazel
Email local part: Philip.Hazel
Email domain: gmail.com
Last updated: 10 December 2022

56
Kha/Backends/Kore-hxcpp/khacpp/project/thirdparty/pcre2-10.42-16/README.md vendored Normal file
View File

@ -0,0 +1,56 @@
# PCRE2 - Perl-Compatible Regular Expressions
The PCRE2 library is a set of C functions that implement regular expression
pattern matching using the same syntax and semantics as Perl 5. PCRE2 has its
own native API, as well as a set of wrapper functions that correspond to the
POSIX regular expression API. The PCRE2 library is free, even for building
proprietary software. It comes in three forms, for processing 8-bit, 16-bit,
or 32-bit code units, in either literal or UTF encoding.
PCRE2 was first released in 2015 to replace the API in the original PCRE
library, which is now obsolete and no longer maintained. As well as a more
flexible API, the code of PCRE2 has been much improved since the fork.
## Download
As well as downloading from the
[GitHub site](https://github.com/PCRE2Project/pcre2), you can download PCRE2
or the older, unmaintained PCRE1 library from an
[*unofficial* mirror](https://sourceforge.net/projects/pcre/files/) at SourceForge.
You can check out the PCRE2 source code via Git or Subversion:
git clone https://github.com/PCRE2Project/pcre2.git
svn co https://github.com/PCRE2Project/pcre2.git
## Contributed Ports
If you just need the command-line PCRE2 tools on Windows, precompiled binary
versions are available at this
[Rexegg page](http://www.rexegg.com/pcregrep-pcretest.html).
A PCRE2 port for z/OS, a mainframe operating system which uses EBCDIC as its
default character encoding, can be found at
[http://www.cbttape.org](http://www.cbttape.org/) (File 939).
## Documentation
You can read the PCRE2 documentation
[here](https://PCRE2Project.github.io/pcre2/doc/html/index.html).
Comparisons to Perl's regular expression semantics can be found in the
community authored Wikipedia entry for PCRE.
There is a curated summary of changes for each PCRE release, copies of
documentation from older releases, and other useful information from the third
party authored
[RexEgg PCRE Documentation and Change Log page](http://www.rexegg.com/pcre-documentation.html).
## Contact
To report a problem with the PCRE2 library, or to make a feature request, please
use the PCRE2 GitHub issues tracker. There is a mailing list for discussion of
PCRE2 issues and development at pcre2-dev@googlegroups.com, which is where any
announcements will be made. You can browse the
[list archives](https://groups.google.com/g/pcre2-dev).

1045
Kha/Backends/Kore-hxcpp/khacpp/project/thirdparty/pcre2-10.42-16/RunGrepTest vendored Normal file
View File

File diff suppressed because it is too large Load Diff

699
Kha/Backends/Kore-hxcpp/khacpp/project/thirdparty/pcre2-10.42-16/RunGrepTest.bat vendored Normal file
View File

@ -0,0 +1,699 @@
@echo off
:: Run pcre2grep tests. The assumption is that the PCRE2 tests check the library
:: itself. What we are checking here is the file handling and options that are
:: supported by pcre2grep. This script must be run in the build directory.
:: (jmh: I've only tested in the main directory, using my own builds.)
setlocal enabledelayedexpansion
:: Remove any non-default colouring that the caller may have set.
set PCRE2GREP_COLOUR=
set PCRE2GREP_COLOR=
set PCREGREP_COLOUR=
set PCREGREP_COLOR=
set GREP_COLORS=
set GREP_COLOR=
:: Remember the current (build) directory and set the program to be tested.
set builddir="%CD%"
set pcre2grep=%builddir%\pcre2grep.exe
set pcre2test=%builddir%\pcre2test.exe
if NOT exist %pcre2grep% (
echo ** %pcre2grep% does not exist.
exit /b 1
)
if NOT exist %pcre2test% (
echo ** %pcre2test% does not exist.
exit /b 1
)
for /f "delims=" %%a in ('"%pcre2grep%" -V') do set pcre2grep_version=%%a
echo Testing %pcre2grep_version%
:: Set up a suitable "diff" command for comparison. Some systems have a diff
:: that lacks a -u option. Try to deal with this; better do the test for the -b
:: option as well. Use FC if there's no diff, taking care to ignore equality.
set cf=
set cfout=
diff -b nul nul 2>nul && set cf=diff -b
diff -u nul nul 2>nul && set cf=diff -u
diff -ub nul nul 2>nul && set cf=diff -ub
if NOT defined cf (
set cf=fc /n
set "cfout=>testcf || (type testcf & cmd /c exit /b 1)"
)
:: Set srcdir to the current or parent directory, whichever one contains the
:: test data. Subsequently, we run most of the pcre2grep tests in the source
:: directory so that the file names in the output are always the same.
if NOT defined srcdir set srcdir=.
if NOT exist %srcdir%\testdata\ (
if exist testdata\ (
set srcdir=.
) else if exist ..\testdata\ (
set srcdir=..
) else if exist ..\..\testdata\ (
set srcdir=..\..
) else (
echo Cannot find the testdata directory
exit /b 1
)
)
:: Check for the availability of UTF-8 support
%pcre2test% -C unicode >nul
set utf8=%ERRORLEVEL%
:: Check default newline convention. If it does not include LF, force LF.
for /f %%a in ('"%pcre2test%" -C newline') do set nl=%%a
if NOT "%nl%" == "LF" if NOT "%nl%" == "ANY" if NOT "%nl%" == "ANYCRLF" (
set pcre2grep=%pcre2grep% -N LF
echo Default newline setting forced to LF
)
:: Create a simple printf via cscript/JScript (an actual printf may translate
:: LF to CRLF, which this one does not).
echo WScript.StdOut.Write(WScript.Arguments(0).replace(/\\r/g, "\r").replace(/\\n/g, "\n")) >printf.js
set printf=cscript //nologo printf.js
:: ------ Normal tests ------
echo Testing pcre2grep main features
echo ---------------------------- Test 1 ------------------------------>testtrygrep
(pushd %srcdir% & %pcre2grep% PATTERN ./testdata/grepinput & popd) >>testtrygrep
echo RC=^%ERRORLEVEL%>>testtrygrep
echo ---------------------------- Test 2 ------------------------------>>testtrygrep
(pushd %srcdir% & %pcre2grep% "^PATTERN" ./testdata/grepinput & popd) >>testtrygrep
echo RC=^%ERRORLEVEL%>>testtrygrep
echo ---------------------------- Test 3 ------------------------------>>testtrygrep
(pushd %srcdir% & %pcre2grep% -in PATTERN ./testdata/grepinput & popd) >>testtrygrep
echo RC=^%ERRORLEVEL%>>testtrygrep
echo ---------------------------- Test 4 ------------------------------>>testtrygrep
(pushd %srcdir% & %pcre2grep% -ic PATTERN ./testdata/grepinput & popd) >>testtrygrep
echo RC=^%ERRORLEVEL%>>testtrygrep
echo ---------------------------- Test 5 ------------------------------>>testtrygrep
(pushd %srcdir% & %pcre2grep% -in PATTERN ./testdata/grepinput ./testdata/grepinputx & popd) >>testtrygrep
echo RC=^%ERRORLEVEL%>>testtrygrep
echo ---------------------------- Test 6 ------------------------------>>testtrygrep
(pushd %srcdir% & %pcre2grep% -inh PATTERN ./testdata/grepinput ./testdata/grepinputx & popd) >>testtrygrep
echo RC=^%ERRORLEVEL%>>testtrygrep
echo ---------------------------- Test 7 ------------------------------>>testtrygrep
(pushd %srcdir% & %pcre2grep% -il PATTERN ./testdata/grepinput ./testdata/grepinputx & popd) >>testtrygrep
echo RC=^%ERRORLEVEL%>>testtrygrep
echo ---------------------------- Test 8 ------------------------------>>testtrygrep
(pushd %srcdir% & %pcre2grep% -l PATTERN ./testdata/grepinput ./testdata/grepinputx & popd) >>testtrygrep
echo RC=^%ERRORLEVEL%>>testtrygrep
echo ---------------------------- Test 9 ------------------------------>>testtrygrep
(pushd %srcdir% & %pcre2grep% -q PATTERN ./testdata/grepinput ./testdata/grepinputx & popd) >>testtrygrep
echo RC=^%ERRORLEVEL%>>testtrygrep
echo ---------------------------- Test 10 ----------------------------->>testtrygrep
(pushd %srcdir% & %pcre2grep% -q NEVER-PATTERN ./testdata/grepinput ./testdata/grepinputx & popd) >>testtrygrep
echo RC=^%ERRORLEVEL%>>testtrygrep
echo ---------------------------- Test 11 ----------------------------->>testtrygrep
(pushd %srcdir% & %pcre2grep% -vn pattern ./testdata/grepinputx & popd) >>testtrygrep
echo RC=^%ERRORLEVEL%>>testtrygrep
echo ---------------------------- Test 12 ----------------------------->>testtrygrep
(pushd %srcdir% & %pcre2grep% -ix pattern ./testdata/grepinputx & popd) >>testtrygrep
echo RC=^%ERRORLEVEL%>>testtrygrep
echo ---------------------------- Test 13 ----------------------------->>testtrygrep
echo seventeen >testtemp1grep
(pushd %srcdir% & %pcre2grep% -f./testdata/greplist -f %builddir%\testtemp1grep ./testdata/grepinputx & popd) >>testtrygrep
echo RC=^%ERRORLEVEL%>>testtrygrep
echo ---------------------------- Test 14 ----------------------------->>testtrygrep
(pushd %srcdir% & %pcre2grep% -w pat ./testdata/grepinput ./testdata/grepinputx & popd) >>testtrygrep
echo RC=^%ERRORLEVEL%>>testtrygrep
echo ---------------------------- Test 15 ----------------------------->>testtrygrep
(pushd %srcdir% & %pcre2grep% "abc^*" ./testdata/grepinput & popd) >>testtrygrep 2>&1
echo RC=^%ERRORLEVEL%>>testtrygrep
echo ---------------------------- Test 16 ----------------------------->>testtrygrep
(pushd %srcdir% & %pcre2grep% abc ./testdata/grepinput ./testdata/nonexistfile & popd) >>testtrygrep 2>&1
echo RC=^%ERRORLEVEL%>>testtrygrep
echo ---------------------------- Test 17 ----------------------------->>testtrygrep
(pushd %srcdir% & %pcre2grep% -M "the\noutput" ./testdata/grepinput & popd) >>testtrygrep
echo RC=^%ERRORLEVEL%>>testtrygrep
echo ---------------------------- Test 18 ----------------------------->>testtrygrep
(pushd %srcdir% & %pcre2grep% -Mn "(the\noutput|dog\.\n--)" ./testdata/grepinput & popd) >>testtrygrep
echo RC=^%ERRORLEVEL%>>testtrygrep
echo ---------------------------- Test 19 ----------------------------->>testtrygrep
(pushd %srcdir% & %pcre2grep% -Mix "Pattern" ./testdata/grepinputx & popd) >>testtrygrep
echo RC=^%ERRORLEVEL%>>testtrygrep
echo ---------------------------- Test 20 ----------------------------->>testtrygrep
(pushd %srcdir% & %pcre2grep% -Mixn "complete pair\nof lines" ./testdata/grepinputx & popd) >>testtrygrep
echo RC=^%ERRORLEVEL%>>testtrygrep
echo ---------------------------- Test 21 ----------------------------->>testtrygrep
(pushd %srcdir% & %pcre2grep% -nA3 "four" ./testdata/grepinputx & popd) >>testtrygrep
echo RC=^%ERRORLEVEL%>>testtrygrep
echo ---------------------------- Test 22 ----------------------------->>testtrygrep
(pushd %srcdir% & %pcre2grep% -nB3 "four" ./testdata/grepinputx & popd) >>testtrygrep
echo RC=^%ERRORLEVEL%>>testtrygrep
echo ---------------------------- Test 23 ----------------------------->>testtrygrep
(pushd %srcdir% & %pcre2grep% -C3 "four" ./testdata/grepinputx & popd) >>testtrygrep
echo RC=^%ERRORLEVEL%>>testtrygrep
echo ---------------------------- Test 24 ----------------------------->>testtrygrep
(pushd %srcdir% & %pcre2grep% -A9 "four" ./testdata/grepinputx & popd) >>testtrygrep
echo RC=^%ERRORLEVEL%>>testtrygrep
echo ---------------------------- Test 25 ----------------------------->>testtrygrep
(pushd %srcdir% & %pcre2grep% -nB9 "four" ./testdata/grepinputx & popd) >>testtrygrep
echo RC=^%ERRORLEVEL%>>testtrygrep
echo ---------------------------- Test 26 ----------------------------->>testtrygrep
(pushd %srcdir% & %pcre2grep% -A9 -B9 "four" ./testdata/grepinputx & popd) >>testtrygrep
echo RC=^%ERRORLEVEL%>>testtrygrep
echo ---------------------------- Test 27 ----------------------------->>testtrygrep
(pushd %srcdir% & %pcre2grep% -A10 "four" ./testdata/grepinputx & popd) >>testtrygrep
echo RC=^%ERRORLEVEL%>>testtrygrep
echo ---------------------------- Test 28 ----------------------------->>testtrygrep
(pushd %srcdir% & %pcre2grep% -nB10 "four" ./testdata/grepinputx & popd) >>testtrygrep
echo RC=^%ERRORLEVEL%>>testtrygrep
echo ---------------------------- Test 29 ----------------------------->>testtrygrep
(pushd %srcdir% & %pcre2grep% -C12 -B10 "four" ./testdata/grepinputx & popd) >>testtrygrep
echo RC=^%ERRORLEVEL%>>testtrygrep
echo ---------------------------- Test 30 ----------------------------->>testtrygrep
(pushd %srcdir% & %pcre2grep% -inB3 "pattern" ./testdata/grepinput ./testdata/grepinputx & popd) >>testtrygrep
echo RC=^%ERRORLEVEL%>>testtrygrep
echo ---------------------------- Test 31 ----------------------------->>testtrygrep
(pushd %srcdir% & %pcre2grep% -inA3 "pattern" ./testdata/grepinput ./testdata/grepinputx & popd) >>testtrygrep
echo RC=^%ERRORLEVEL%>>testtrygrep
echo ---------------------------- Test 32 ----------------------------->>testtrygrep
(pushd %srcdir% & %pcre2grep% -L "fox" ./testdata/grepinput ./testdata/grepinputx & popd) >>testtrygrep
echo RC=^%ERRORLEVEL%>>testtrygrep
echo ---------------------------- Test 33 ----------------------------->>testtrygrep
(pushd %srcdir% & %pcre2grep% "fox" ./testdata/grepnonexist & popd) >>testtrygrep 2>&1
echo RC=^%ERRORLEVEL%>>testtrygrep
echo ---------------------------- Test 34 ----------------------------->>testtrygrep
(pushd %srcdir% & %pcre2grep% -s "fox" ./testdata/grepnonexist & popd) >>testtrygrep 2>&1
echo RC=^%ERRORLEVEL%>>testtrygrep
echo ---------------------------- Test 35 ----------------------------->>testtrygrep
(pushd %srcdir% & %pcre2grep% -L -r --include=grepinputx --include grepinput8 --exclude-dir="^\." "fox" ./testdata | sort & popd) >>testtrygrep
echo RC=^%ERRORLEVEL%>>testtrygrep
echo ---------------------------- Test 36 ----------------------------->>testtrygrep
(pushd %srcdir% & %pcre2grep% -L -r --include=grepinput --exclude "grepinput$" --exclude=grepinput8 --exclude-dir="^\." "fox" ./testdata | sort & popd) >>testtrygrep
echo RC=^%ERRORLEVEL%>>testtrygrep
echo ---------------------------- Test 37 ----------------------------->>testtrygrep
(pushd %srcdir% & %pcre2grep% "^(a+)*\d" ./testdata/grepinput & popd) >>testtrygrep 2>teststderrgrep
echo RC=^%ERRORLEVEL%>>testtrygrep
echo ======== STDERR ========>>testtrygrep
type teststderrgrep >>testtrygrep
echo ---------------------------- Test 38 ------------------------------>>testtrygrep
(pushd %srcdir% & %pcre2grep% ">\x00<" ./testdata/grepinput & popd) >>testtrygrep
echo RC=^%ERRORLEVEL%>>testtrygrep
echo ---------------------------- Test 39 ------------------------------>>testtrygrep
(pushd %srcdir% & %pcre2grep% -A1 "before the binary zero" ./testdata/grepinput & popd) >>testtrygrep
echo RC=^%ERRORLEVEL%>>testtrygrep
echo ---------------------------- Test 40 ------------------------------>>testtrygrep
(pushd %srcdir% & %pcre2grep% -B1 "after the binary zero" ./testdata/grepinput & popd) >>testtrygrep
echo RC=^%ERRORLEVEL%>>testtrygrep
echo ---------------------------- Test 41 ------------------------------>>testtrygrep
(pushd %srcdir% & %pcre2grep% -B1 -o "\w+ the binary zero" ./testdata/grepinput & popd) >>testtrygrep
echo RC=^%ERRORLEVEL%>>testtrygrep
echo ---------------------------- Test 42 ------------------------------>>testtrygrep
(pushd %srcdir% & %pcre2grep% -B1 -onH "\w+ the binary zero" ./testdata/grepinput & popd) >>testtrygrep
echo RC=^%ERRORLEVEL%>>testtrygrep
echo ---------------------------- Test 43 ------------------------------>>testtrygrep
(pushd %srcdir% & %pcre2grep% -on "before|zero|after" ./testdata/grepinput & popd) >>testtrygrep
echo RC=^%ERRORLEVEL%>>testtrygrep
echo ---------------------------- Test 44 ------------------------------>>testtrygrep
(pushd %srcdir% & %pcre2grep% -on -e before -ezero -e after ./testdata/grepinput & popd) >>testtrygrep
echo RC=^%ERRORLEVEL%>>testtrygrep
echo ---------------------------- Test 45 ------------------------------>>testtrygrep
(pushd %srcdir% & %pcre2grep% -on -f ./testdata/greplist -e binary ./testdata/grepinput & popd) >>testtrygrep
echo RC=^%ERRORLEVEL%>>testtrygrep
echo ---------------------------- Test 46 ------------------------------>>testtrygrep
(pushd %srcdir% & %pcre2grep% -eabc -e "(unclosed" ./testdata/grepinput & popd) >>testtrygrep 2>&1
echo RC=^%ERRORLEVEL%>>testtrygrep
echo ---------------------------- Test 47 ------------------------------>>testtrygrep
(pushd %srcdir% & %pcre2grep% -Fx AB.VE^
elephant ./testdata/grepinput & popd) >>testtrygrep
echo RC=^%ERRORLEVEL%>>testtrygrep
echo ---------------------------- Test 48 ------------------------------>>testtrygrep
(pushd %srcdir% & %pcre2grep% -F AB.VE^
elephant ./testdata/grepinput & popd) >>testtrygrep
echo RC=^%ERRORLEVEL%>>testtrygrep
echo ---------------------------- Test 49 ------------------------------>>testtrygrep
(pushd %srcdir% & %pcre2grep% -F -e DATA -e AB.VE^
elephant ./testdata/grepinput & popd) >>testtrygrep
echo RC=^%ERRORLEVEL%>>testtrygrep
echo ---------------------------- Test 50 ------------------------------>>testtrygrep
(pushd %srcdir% & %pcre2grep% "^(abc|def|ghi|jkl)" ./testdata/grepinputx & popd) >>testtrygrep
echo RC=^%ERRORLEVEL%>>testtrygrep
echo ---------------------------- Test 51 ------------------------------>>testtrygrep
(pushd %srcdir% & %pcre2grep% -Mv "brown\sfox" ./testdata/grepinputv & popd) >>testtrygrep
echo RC=^%ERRORLEVEL%>>testtrygrep
echo ---------------------------- Test 52 ------------------------------>>testtrygrep
(pushd %srcdir% & %pcre2grep% --colour=always jumps ./testdata/grepinputv & popd) >>testtrygrep
echo RC=^%ERRORLEVEL%>>testtrygrep
echo ---------------------------- Test 53 ------------------------------>>testtrygrep
(pushd %srcdir% & %pcre2grep% --file-offsets "before|zero|after" ./testdata/grepinput & popd) >>testtrygrep
echo RC=^%ERRORLEVEL%>>testtrygrep
echo ---------------------------- Test 54 ------------------------------>>testtrygrep
(pushd %srcdir% & %pcre2grep% --line-offsets "before|zero|after" ./testdata/grepinput & popd) >>testtrygrep
echo RC=^%ERRORLEVEL%>>testtrygrep
echo ---------------------------- Test 55 ----------------------------->>testtrygrep
(pushd %srcdir% & %pcre2grep% -f./testdata/greplist --color=always ./testdata/grepinputx & popd) >>testtrygrep
echo RC=^%ERRORLEVEL%>>testtrygrep
echo ---------------------------- Test 56 ----------------------------->>testtrygrep
(pushd %srcdir% & %pcre2grep% -c lazy ./testdata/grepinput* & popd) >>testtrygrep
echo RC=^%ERRORLEVEL%>>testtrygrep
echo ---------------------------- Test 57 ----------------------------->>testtrygrep
(pushd %srcdir% & %pcre2grep% -c -l lazy ./testdata/grepinput* & popd) >>testtrygrep
echo RC=^%ERRORLEVEL%>>testtrygrep
echo ---------------------------- Test 58 ----------------------------->>testtrygrep
(pushd %srcdir% & %pcre2grep% --regex=PATTERN ./testdata/grepinput & popd) >>testtrygrep
echo RC=^%ERRORLEVEL%>>testtrygrep
echo ---------------------------- Test 59 ----------------------------->>testtrygrep
(pushd %srcdir% & %pcre2grep% --regexp=PATTERN ./testdata/grepinput & popd) >>testtrygrep
echo RC=^%ERRORLEVEL%>>testtrygrep
echo ---------------------------- Test 60 ----------------------------->>testtrygrep
(pushd %srcdir% & %pcre2grep% --regex PATTERN ./testdata/grepinput & popd) >>testtrygrep
echo RC=^%ERRORLEVEL%>>testtrygrep
echo ---------------------------- Test 61 ----------------------------->>testtrygrep
(pushd %srcdir% & %pcre2grep% --regexp PATTERN ./testdata/grepinput & popd) >>testtrygrep
echo RC=^%ERRORLEVEL%>>testtrygrep
echo ---------------------------- Test 62 ----------------------------->>testtrygrep
(pushd %srcdir% & %pcre2grep% --match-limit=1000 --no-jit -M "This is a file(.|\R)*file." ./testdata/grepinput & popd) >>testtrygrep 2>&1
echo RC=^%ERRORLEVEL%>>testtrygrep
echo ---------------------------- Test 63 ----------------------------->>testtrygrep
(pushd %srcdir% & %pcre2grep% --recursion-limit=1000 --no-jit -M "This is a file(.|\R)*file." ./testdata/grepinput & popd) >>testtrygrep 2>&1
echo RC=^%ERRORLEVEL%>>testtrygrep
echo ---------------------------- Test 64 ------------------------------>>testtrygrep
(pushd %srcdir% & %pcre2grep% -o1 "(?<=PAT)TERN (ap(pear)s)" ./testdata/grepinput & popd) >>testtrygrep
echo RC=^%ERRORLEVEL%>>testtrygrep
echo ---------------------------- Test 65 ------------------------------>>testtrygrep
(pushd %srcdir% & %pcre2grep% -o2 "(?<=PAT)TERN (ap(pear)s)" ./testdata/grepinput & popd) >>testtrygrep
echo RC=^%ERRORLEVEL%>>testtrygrep
echo ---------------------------- Test 66 ------------------------------>>testtrygrep
(pushd %srcdir% & %pcre2grep% -o3 "(?<=PAT)TERN (ap(pear)s)" ./testdata/grepinput & popd) >>testtrygrep
echo RC=^%ERRORLEVEL%>>testtrygrep
echo ---------------------------- Test 67 ------------------------------>>testtrygrep
(pushd %srcdir% & %pcre2grep% -o12 "(?<=PAT)TERN (ap(pear)s)" ./testdata/grepinput & popd) >>testtrygrep
echo RC=^%ERRORLEVEL%>>testtrygrep
echo ---------------------------- Test 68 ------------------------------>>testtrygrep
(pushd %srcdir% & %pcre2grep% --only-matching=2 "(?<=PAT)TERN (ap(pear)s)" ./testdata/grepinput & popd) >>testtrygrep
echo RC=^%ERRORLEVEL%>>testtrygrep
echo ---------------------------- Test 69 ----------------------------->>testtrygrep
(pushd %srcdir% & %pcre2grep% -vn --colour=always pattern ./testdata/grepinputx & popd) >>testtrygrep
echo RC=^%ERRORLEVEL%>>testtrygrep
echo ---------------------------- Test 70 ----------------------------->>testtrygrep
(pushd %srcdir% & %pcre2grep% --color=always -M "triple:\t.*\n\n" ./testdata/grepinput3 & popd) >>testtrygrep
echo RC=^%ERRORLEVEL%>>testtrygrep
echo ---------------------------- Test 71 ----------------------------->>testtrygrep
(pushd %srcdir% & %pcre2grep% -o "^01|^02|^03" ./testdata/grepinput & popd) >>testtrygrep
echo RC=^%ERRORLEVEL%>>testtrygrep
echo ---------------------------- Test 72 ----------------------------->>testtrygrep
(pushd %srcdir% & %pcre2grep% --color=always "^01|^02|^03" ./testdata/grepinput & popd) >>testtrygrep
echo RC=^%ERRORLEVEL%>>testtrygrep
echo ---------------------------- Test 73 ----------------------------->>testtrygrep
(pushd %srcdir% & %pcre2grep% -o --colour=always "^01|^02|^03" ./testdata/grepinput & popd) >>testtrygrep
echo RC=^%ERRORLEVEL%>>testtrygrep
echo ---------------------------- Test 74 ----------------------------->>testtrygrep
(pushd %srcdir% & %pcre2grep% -o "^01|02|^03" ./testdata/grepinput & popd) >>testtrygrep
echo RC=^%ERRORLEVEL%>>testtrygrep
echo ---------------------------- Test 75 ----------------------------->>testtrygrep
(pushd %srcdir% & %pcre2grep% --color=always "^01|02|^03" ./testdata/grepinput & popd) >>testtrygrep
echo RC=^%ERRORLEVEL%>>testtrygrep
echo ---------------------------- Test 76 ----------------------------->>testtrygrep
(pushd %srcdir% & %pcre2grep% -o --colour=always "^01|02|^03" ./testdata/grepinput & popd) >>testtrygrep
echo RC=^%ERRORLEVEL%>>testtrygrep
echo ---------------------------- Test 77 ----------------------------->>testtrygrep
(pushd %srcdir% & %pcre2grep% -o "^01|^02|03" ./testdata/grepinput & popd) >>testtrygrep
echo RC=^%ERRORLEVEL%>>testtrygrep
echo ---------------------------- Test 78 ----------------------------->>testtrygrep
(pushd %srcdir% & %pcre2grep% --color=always "^01|^02|03" ./testdata/grepinput & popd) >>testtrygrep
echo RC=^%ERRORLEVEL%>>testtrygrep
echo ---------------------------- Test 79 ----------------------------->>testtrygrep
(pushd %srcdir% & %pcre2grep% -o --colour=always "^01|^02|03" ./testdata/grepinput & popd) >>testtrygrep
echo RC=^%ERRORLEVEL%>>testtrygrep
echo ---------------------------- Test 80 ----------------------------->>testtrygrep
(pushd %srcdir% & %pcre2grep% -o "\b01|\b02" ./testdata/grepinput & popd) >>testtrygrep
echo RC=^%ERRORLEVEL%>>testtrygrep
echo ---------------------------- Test 81 ----------------------------->>testtrygrep
(pushd %srcdir% & %pcre2grep% --color=always "\b01|\b02" ./testdata/grepinput & popd) >>testtrygrep
echo RC=^%ERRORLEVEL%>>testtrygrep
echo ---------------------------- Test 82 ----------------------------->>testtrygrep
(pushd %srcdir% & %pcre2grep% -o --colour=always "\b01|\b02" ./testdata/grepinput & popd) >>testtrygrep
echo RC=^%ERRORLEVEL%>>testtrygrep
echo ---------------------------- Test 83 ----------------------------->>testtrygrep
(pushd %srcdir% & %pcre2grep% --buffer-size=10 --max-buffer-size=100 "^a" ./testdata/grepinput3 & popd) >>testtrygrep 2>&1
echo RC=^%ERRORLEVEL%>>testtrygrep
echo ---------------------------- Test 84 ----------------------------->>testtrygrep
echo testdata/grepinput3 >testtemp1grep
(pushd %srcdir% & %pcre2grep% --file-list ./testdata/grepfilelist --file-list %builddir%\testtemp1grep "fox|complete|t7" & popd) >>testtrygrep 2>&1
echo RC=^%ERRORLEVEL%>>testtrygrep
echo ---------------------------- Test 85 ----------------------------->>testtrygrep
(pushd %srcdir% & %pcre2grep% --file-list=./testdata/grepfilelist "dolor" ./testdata/grepinput3 & popd) >>testtrygrep 2>&1
echo RC=^%ERRORLEVEL%>>testtrygrep
echo ---------------------------- Test 86 ----------------------------->>testtrygrep
(pushd %srcdir% & %pcre2grep% "dog" ./testdata/grepbinary & popd) >>testtrygrep 2>&1
echo RC=^%ERRORLEVEL%>>testtrygrep
echo ---------------------------- Test 87 ----------------------------->>testtrygrep
(pushd %srcdir% & %pcre2grep% "cat" ./testdata/grepbinary & popd) >>testtrygrep 2>&1
echo RC=^%ERRORLEVEL%>>testtrygrep
echo ---------------------------- Test 88 ----------------------------->>testtrygrep
(pushd %srcdir% & %pcre2grep% -v "cat" ./testdata/grepbinary & popd) >>testtrygrep 2>&1
echo RC=^%ERRORLEVEL%>>testtrygrep
echo ---------------------------- Test 89 ----------------------------->>testtrygrep
(pushd %srcdir% & %pcre2grep% -I "dog" ./testdata/grepbinary & popd) >>testtrygrep 2>&1
echo RC=^%ERRORLEVEL%>>testtrygrep
echo ---------------------------- Test 90 ----------------------------->>testtrygrep
(pushd %srcdir% & %pcre2grep% --binary-files=without-match "dog" ./testdata/grepbinary & popd) >>testtrygrep 2>&1
echo RC=^%ERRORLEVEL%>>testtrygrep
echo ---------------------------- Test 91 ----------------------------->>testtrygrep
(pushd %srcdir% & %pcre2grep% -a "dog" ./testdata/grepbinary & popd) >>testtrygrep 2>&1
echo RC=^%ERRORLEVEL%>>testtrygrep
echo ---------------------------- Test 92 ----------------------------->>testtrygrep
(pushd %srcdir% & %pcre2grep% --binary-files=text "dog" ./testdata/grepbinary & popd) >>testtrygrep 2>&1
echo RC=^%ERRORLEVEL%>>testtrygrep
echo ---------------------------- Test 93 ----------------------------->>testtrygrep
(pushd %srcdir% & %pcre2grep% --text "dog" ./testdata/grepbinary & popd) >>testtrygrep 2>&1
echo RC=^%ERRORLEVEL%>>testtrygrep
echo ---------------------------- Test 94 ----------------------------->>testtrygrep
(pushd %srcdir% & %pcre2grep% -L -r --include=grepinputx --include grepinput8 "fox" ./testdata/grepinput* | sort & popd) >>testtrygrep
echo RC=^%ERRORLEVEL%>>testtrygrep
echo ---------------------------- Test 95 ----------------------------->>testtrygrep
(pushd %srcdir% & %pcre2grep% --file-list ./testdata/grepfilelist --exclude grepinputv "fox|complete" & popd) >>testtrygrep 2>&1
echo RC=^%ERRORLEVEL%>>testtrygrep
echo ---------------------------- Test 96 ----------------------------->>testtrygrep
(pushd %srcdir% & %pcre2grep% -L -r --include-dir=testdata --exclude "^^(?^!grepinput)" "fox" ./test* | sort & popd) >>testtrygrep
echo RC=^%ERRORLEVEL%>>testtrygrep
echo ---------------------------- Test 97 ----------------------------->>testtrygrep
echo grepinput$>testtemp1grep
echo grepinput8>>testtemp1grep
(pushd %srcdir% & %pcre2grep% -L -r --include=grepinput --exclude-from %builddir%\testtemp1grep --exclude-dir="^\." "fox" ./testdata | sort & popd) >>testtrygrep
echo RC=^%ERRORLEVEL%>>testtrygrep
echo ---------------------------- Test 98 ----------------------------->>testtrygrep
echo grepinput$>testtemp1grep
echo grepinput8>>testtemp1grep
(pushd %srcdir% & %pcre2grep% -L -r --exclude=grepinput3 --include=grepinput --exclude-from %builddir%\testtemp1grep --exclude-dir="^\." "fox" ./testdata | sort & popd) >>testtrygrep
echo RC=^%ERRORLEVEL%>>testtrygrep
echo ---------------------------- Test 99 ----------------------------->>testtrygrep
echo grepinput$>testtemp1grep
echo grepinput8>testtemp2grep
(pushd %srcdir% & %pcre2grep% -L -r --include grepinput --exclude-from %builddir%\testtemp1grep --exclude-from=%builddir%\testtemp2grep --exclude-dir="^\." "fox" ./testdata | sort & popd) >>testtrygrep
echo RC=^%ERRORLEVEL%>>testtrygrep
echo ---------------------------- Test 100 ------------------------------>>testtrygrep
(pushd %srcdir% & %pcre2grep% -Ho2 --only-matching=1 -o3 "(\w+) binary (\w+)(\.)?" ./testdata/grepinput & popd) >>testtrygrep
echo RC=^%ERRORLEVEL%>>testtrygrep
echo ---------------------------- Test 101 ------------------------------>>testtrygrep
(pushd %srcdir% & %pcre2grep% -o3 -Ho2 -o12 --only-matching=1 -o3 --colour=always --om-separator="|" "(\w+) binary (\w+)(\.)?" ./testdata/grepinput & popd) >>testtrygrep
echo RC=^%ERRORLEVEL%>>testtrygrep
echo ---------------------------- Test 102 ----------------------------->>testtrygrep
(pushd %srcdir% & %pcre2grep% -n "^$" ./testdata/grepinput3 & popd) >>testtrygrep 2>&1
echo RC=^%ERRORLEVEL%>>testtrygrep
echo ---------------------------- Test 103 ----------------------------->>testtrygrep
(pushd %srcdir% & %pcre2grep% --only-matching "^$" ./testdata/grepinput3 & popd) >>testtrygrep 2>&1
echo RC=^%ERRORLEVEL%>>testtrygrep
echo ---------------------------- Test 104 ----------------------------->>testtrygrep
(pushd %srcdir% & %pcre2grep% -n --only-matching "^$" ./testdata/grepinput3 & popd) >>testtrygrep 2>&1
echo RC=^%ERRORLEVEL%>>testtrygrep
echo ---------------------------- Test 105 ----------------------------->>testtrygrep
(pushd %srcdir% & %pcre2grep% --colour=always "ipsum|" ./testdata/grepinput3 & popd) >>testtrygrep 2>&1
echo RC=^%ERRORLEVEL%>>testtrygrep
echo ---------------------------- Test 106 ----------------------------->>testtrygrep
(pushd %srcdir% & echo a| %pcre2grep% -M "|a" & popd) >>testtrygrep 2>&1
echo RC=^%ERRORLEVEL%>>testtrygrep
echo ---------------------------- Test 107 ----------------------------->>testtrygrep
echo a>testtemp1grep
echo aaaaa>>testtemp1grep
(pushd %srcdir% & %pcre2grep% --line-offsets "(?<=\Ka)" %builddir%\testtemp1grep & popd) >>testtrygrep 2>&1
echo RC=^%ERRORLEVEL%>>testtrygrep
echo ---------------------------- Test 108 ------------------------------>>testtrygrep
(pushd %srcdir% & %pcre2grep% -lq PATTERN ./testdata/grepinput ./testdata/grepinputx & popd) >>testtrygrep
echo RC=^%ERRORLEVEL%>>testtrygrep
echo ---------------------------- Test 109 ----------------------------->>testtrygrep
(pushd %srcdir% & %pcre2grep% -cq lazy ./testdata/grepinput* & popd) >>testtrygrep
echo RC=^%ERRORLEVEL%>>testtrygrep
echo ---------------------------- Test 110 ----------------------------->>testtrygrep
(pushd %srcdir% & %pcre2grep% --om-separator / -Mo0 -o1 -o2 "match (\d+):\n (.)\n" testdata/grepinput & popd) >>testtrygrep
echo RC=^%ERRORLEVEL%>>testtrygrep
echo ---------------------------- Test 111 ----------------------------->>testtrygrep
(pushd %srcdir% & %pcre2grep% --line-offsets -M "match (\d+):\n (.)\n" testdata/grepinput & popd) >>testtrygrep
echo RC=^%ERRORLEVEL%>>testtrygrep
echo ---------------------------- Test 112 ----------------------------->>testtrygrep
(pushd %srcdir% & %pcre2grep% --file-offsets -M "match (\d+):\n (.)\n" testdata/grepinput & popd) >>testtrygrep
echo RC=^%ERRORLEVEL%>>testtrygrep
echo ---------------------------- Test 113 ----------------------------->>testtrygrep
(pushd %srcdir% & %pcre2grep% --total-count "the" testdata/grepinput* & popd) >>testtrygrep
echo RC=^%ERRORLEVEL%>>testtrygrep
echo ---------------------------- Test 114 ----------------------------->>testtrygrep
(pushd %srcdir% & %pcre2grep% -tc "the" testdata/grepinput* & popd) >>testtrygrep
echo RC=^%ERRORLEVEL%>>testtrygrep
echo ---------------------------- Test 115 ----------------------------->>testtrygrep
(pushd %srcdir% & %pcre2grep% -tlc "the" testdata/grepinput* & popd) >>testtrygrep
echo RC=^%ERRORLEVEL%>>testtrygrep
echo ---------------------------- Test 116 ----------------------------->>testtrygrep
(pushd %srcdir% & %pcre2grep% -th "the" testdata/grepinput* & popd) >>testtrygrep
echo RC=^%ERRORLEVEL%>>testtrygrep
echo ---------------------------- Test 117 ----------------------------->>testtrygrep
(pushd %srcdir% & %pcre2grep% -tch "the" testdata/grepinput* & popd) >>testtrygrep
echo RC=^%ERRORLEVEL%>>testtrygrep
echo ---------------------------- Test 118 ----------------------------->>testtrygrep
(pushd %srcdir% & %pcre2grep% -tL "the" testdata/grepinput* & popd) >>testtrygrep
echo RC=^%ERRORLEVEL%>>testtrygrep
echo ---------------------------- Test 119 ----------------------------->>testtrygrep
%printf% "123\n456\n789\n---abc\ndef\nxyz\n---\n" >testNinputgrep
%pcre2grep% -Mo "(\n|[^-])*---" testNinputgrep >>testtrygrep
echo RC=^%ERRORLEVEL%>>testtrygrep
echo ---------------------------- Test 120 ------------------------------>>testtrygrep
(pushd %srcdir% & %pcre2grep% -HO "$0:$2$1$3" "(\w+) binary (\w+)(\.)?" ./testdata/grepinput & popd) >>testtrygrep
echo RC=^%ERRORLEVEL%>>testtrygrep
:: Now compare the results.
%cf% %srcdir%\testdata\grepoutput testtrygrep %cfout%
if ERRORLEVEL 1 exit /b 1
:: These tests require UTF-8 support
if %utf8% neq 0 (
echo Testing pcre2grep UTF-8 features
echo ---------------------------- Test U1 ------------------------------>testtrygrep
(pushd %srcdir% & %pcre2grep% -n -u --newline=any "^X" ./testdata/grepinput8 & popd) >>testtrygrep
echo RC=^%ERRORLEVEL%>>testtrygrep
echo ---------------------------- Test U2 ------------------------------>>testtrygrep
(pushd %srcdir% & %pcre2grep% -n -u -C 3 --newline=any "Match" ./testdata/grepinput8 & popd) >>testtrygrep
echo RC=^%ERRORLEVEL%>>testtrygrep
echo ---------------------------- Test U3 ------------------------------>>testtrygrep
(pushd %srcdir% & %pcre2grep% --line-offsets -u --newline=any "(?<=\K\x{17f})" ./testdata/grepinput8 & popd) >>testtrygrep
echo RC=^%ERRORLEVEL%>>testtrygrep
%cf% %srcdir%\testdata\grepoutput8 testtrygrep %cfout%
if ERRORLEVEL 1 exit /b 1
) else (
echo Skipping pcre2grep UTF-8 tests: no UTF-8 support in PCRE2 library
)
:: We go to some contortions to try to ensure that the tests for the various
:: newline settings will work in environments where the normal newline sequence
:: is not \n. Do not use exported files, whose line endings might be changed.
:: Instead, create an input file so that its contents are exactly what we want.
:: These tests are run in the build directory.
echo Testing pcre2grep newline settings
%printf% "abc\rdef\r\nghi\njkl" >testNinputgrep
echo ---------------------------- Test N1 ------------------------------>testtrygrep
%pcre2grep% -n -N CR "^(abc|def|ghi|jkl)" testNinputgrep >>testtrygrep
echo ---------------------------- Test N2 ------------------------------>>testtrygrep
%pcre2grep% -n --newline=crlf "^(abc|def|ghi|jkl)" testNinputgrep >>testtrygrep
echo ---------------------------- Test N3 ------------------------------>>testtrygrep
for /f %%a in ('%printf% "def\rjkl"') do set pattern=%%a
%pcre2grep% -n --newline=cr -F "!pattern!" testNinputgrep >>testtrygrep
echo ---------------------------- Test N4 ------------------------------>>testtrygrep
%pcre2grep% -n --newline=crlf -F -f %srcdir%/testdata/greppatN4 testNinputgrep >>testtrygrep
echo ---------------------------- Test N5 ------------------------------>>testtrygrep
%pcre2grep% -n --newline=any "^(abc|def|ghi|jkl)" testNinputgrep >>testtrygrep
echo ---------------------------- Test N6 ------------------------------>>testtrygrep
%pcre2grep% -n --newline=anycrlf "^(abc|def|ghi|jkl)" testNinputgrep >>testtrygrep
%cf% %srcdir%\testdata\grepoutputN testtrygrep %cfout%
if ERRORLEVEL 1 exit /b 1
:: If pcre2grep supports script callouts, run some tests on them.
%pcre2grep% --help | %pcre2grep% -q "callout scripts in patterns are supported"
if %ERRORLEVEL% equ 0 (
echo Testing pcre2grep script callouts
%pcre2grep% "(T)(..(.))(?C'cmd|/c echo|Arg1: [$1] [$2] [$3]|Arg2: ^$|${1}^$| ($4) ($14) ($0)')()" %srcdir%/testdata/grepinputv >testtrygrep
%pcre2grep% "(T)(..(.))()()()()()()()(..)(?C'cmd|/c echo|Arg1: [$11] [${11}]')" %srcdir%/testdata/grepinputv >>testtrygrep
%pcre2grep% "(T)(?C'|$0:$1$n')" %srcdir%/testdata/grepinputv >>testtrygrep
%pcre2grep% "(T)(?C'|$1$n')(*F)" %srcdir%/testdata/grepinputv >>testtrygrep
%pcre2grep% --help | %pcre2grep% -q "Non-script callout scripts in patterns are supported"
if %ERRORLEVEL% equ 0 (
%cf% %srcdir%\testdata\grepoutputCN testtrygrep %cfout%
) else (
%cf% %srcdir%\testdata\grepoutputC testtrygrep %cfout%
)
if ERRORLEVEL 1 exit /b 1
) else (
echo Script callouts are not supported
)
:: Finally, some tests to exercise code that is not tested above, just to be
:: sure that it runs OK. Doing this improves the coverage statistics. The output
:: is not checked.
echo Testing miscellaneous pcre2grep arguments (unchecked)
%printf% "" >testtrygrep
call :checkspecial "-xxxxx" 2 || exit /b 1
call :checkspecial "--help" 0 || exit /b 1
call :checkspecial "--line-buffered --colour=auto abc nul" 1 || exit /b 1
:: Clean up local working files
del testcf printf.js testNinputgrep teststderrgrep testtrygrep testtemp1grep testtemp2grep
exit /b 0
:: ------ Function to run and check a special pcre2grep arguments test -------
:checkspecial
%pcre2grep% %~1 >>testtrygrep 2>&1
if %ERRORLEVEL% neq %2 (
echo ** pcre2grep %~1 failed - check testtrygrep
exit /b 1
)
exit /b 0
:: End

916
Kha/Backends/Kore-hxcpp/khacpp/project/thirdparty/pcre2-10.42-16/RunTest vendored Normal file
View File

@ -0,0 +1,916 @@
#! /bin/sh
###############################################################################
# Run the PCRE2 tests using the pcre2test program. The appropriate tests are
# selected, depending on which build-time options were used.
#
# When JIT support is available, all appropriate tests are run with and without
# JIT, unless "-nojit" is given on the command line. There are also two tests
# for JIT-specific features, one to be run when JIT support is available
# (unless "-nojit" is specified), and one when it is not.
#
# Whichever of the 8-, 16- and 32-bit libraries exist are tested. It is also
# possible to select which to test by giving "-8", "-16" or "-32" on the
# command line.
#
# As well as "-nojit", "-8", "-16", and "-32", arguments for this script are
# individual test numbers, ranges of tests such as 3-6 or 3- (meaning 3 to the
# end), or a number preceded by ~ to exclude a test. For example, "3-15 ~10"
# runs tests 3 to 15, excluding test 10, and just "~10" runs all the tests
# except test 10. Whatever order the arguments are in, these tests are always
# run in numerical order.
#
# If no specific tests are selected (which is the case when this script is run
# via 'make check') the default is to run all the numbered tests.
#
# There may also be named (as well as numbered) tests for special purposes. At
# present there is just one, called "heap". This test's output contains the
# sizes of heap frames and frame vectors, which depend on the environment. It
# is therefore not run unless explicitly requested.
#
# Inappropriate tests are automatically skipped (with a comment to say so). For
# example, if JIT support is not compiled, test 16 is skipped, whereas if JIT
# support is compiled, test 15 is skipped.
#
# Other arguments can be one of the words "-valgrind", "-valgrind-log", or
# "-sim" followed by an argument to run cross-compiled executables under a
# simulator, for example:
#
# RunTest 3 -sim "qemu-arm -s 8388608"
#
# For backwards compatibility, -nojit, -valgrind, -valgrind-log, and -sim may
# be given without the leading "-" character.
#
# When PCRE2 is compiled by clang with -fsanitize arguments, some tests need
# very much more stack than normal. In environments where the stack can be
# set at runtime, -bigstack sets a gigantic stack.
#
# There are two special cases where only one argument is allowed:
#
# If the first and only argument is "ebcdic", the script runs the special
# EBCDIC test that can be useful for checking certain EBCDIC features, even
# when run in an ASCII environment. PCRE2 must be built with EBCDIC support for
# this test to be run.
#
# If the script is obeyed as "RunTest list", a list of available tests is
# output, but none of them are run.
###############################################################################
# Define test titles in variables so that they can be output as a list. Some
# of them are modified (e.g. with -8 or -16) when used in the actual tests.
title0="Test 0: Unchecked pcre2test argument tests (to improve coverage)"
title1="Test 1: Main non-UTF, non-UCP functionality (compatible with Perl >= 5.10)"
title2="Test 2: API, errors, internals and non-Perl stuff"
title3="Test 3: Locale-specific features"
title4A="Test 4: UTF"
title4B=" and Unicode property support (compatible with Perl >= 5.10)"
title5A="Test 5: API, internals, and non-Perl stuff for UTF"
title5B=" and UCP support"
title6="Test 6: DFA matching main non-UTF, non-UCP functionality"
title7A="Test 7: DFA matching with UTF"
title7B=" and Unicode property support"
title8="Test 8: Internal offsets and code size tests"
title9="Test 9: Specials for the basic 8-bit library"
title10="Test 10: Specials for the 8-bit library with UTF-8 and UCP support"
title11="Test 11: Specials for the basic 16-bit and 32-bit libraries"
title12="Test 12: Specials for the 16-bit and 32-bit libraries UTF and UCP support"
title13="Test 13: DFA specials for the basic 16-bit and 32-bit libraries"
title14="Test 14: DFA specials for UTF and UCP support"
title15="Test 15: Non-JIT limits and other non-JIT tests"
title16="Test 16: JIT-specific features when JIT is not available"
title17="Test 17: JIT-specific features when JIT is available"
title18="Test 18: Tests of the POSIX interface, excluding UTF/UCP"
title19="Test 19: Tests of the POSIX interface with UTF/UCP"
title20="Test 20: Serialization and code copy tests"
title21="Test 21: \C tests without UTF (supported for DFA matching)"
title22="Test 22: \C tests with UTF (not supported for DFA matching)"
title23="Test 23: \C disabled test"
title24="Test 24: Non-UTF pattern conversion tests"
title25="Test 25: UTF pattern conversion tests"
title26="Test 26: Auto-generated unicode property tests"
maxtest=26
titleheap="Test 'heap': Environment-specific heap tests"
if [ $# -eq 1 -a "$1" = "list" ]; then
echo $title0
echo $title1
echo $title2 "(not UTF or UCP)"
echo $title3
echo $title4A $title4B
echo $title5A $title5B
echo $title6
echo $title7A $title7B
echo $title8
echo $title9
echo $title10
echo $title11
echo $title12
echo $title13
echo $title14
echo $title15
echo $title16
echo $title17
echo $title18
echo $title19
echo $title20
echo $title21
echo $title22
echo $title23
echo $title24
echo $title25
echo $title26
echo ""
echo $titleheap
echo ""
echo "Numbered tests are automatically run if nothing selected."
echo "Named tests must be explicitly selected."
exit 0
fi
# Set up a suitable "diff" command for comparison. Some systems
# have a diff that lacks a -u option. Try to deal with this.
cf="diff"
diff -u /dev/null /dev/null 2>/dev/null && cf="diff -u"
# Find the test data
if [ -n "$srcdir" -a -d "$srcdir" ] ; then
testdata="$srcdir/testdata"
elif [ -d "./testdata" ] ; then
testdata=./testdata
elif [ -d "../testdata" ] ; then
testdata=../testdata
else
echo "Cannot find the testdata directory"
exit 1
fi
# ------ Function to check results of a test -------
# This function is called with three parameters:
#
# $1 the value of $? after a call to pcre2test
# $2 the suffix of the output file to compare with
# $3 the $opt value (empty, -jit, or -dfa)
#
# Note: must define using name(), not "function name", for Solaris.
checkresult()
{
if [ $1 -ne 0 ] ; then
echo "** pcre2test failed - check testtry"
exit 1
fi
case "$3" in
-jit) with=" with JIT";;
-dfa) with=" with DFA";;
*) with="";;
esac
$cf $testdata/testoutput$2 testtry
if [ $? != 0 ] ; then
echo ""
echo "** Test $2 failed$with"
exit 1
fi
echo " OK$with"
}
# ------ Function to run and check a special pcre2test arguments test -------
checkspecial()
{
$valgrind $vjs ./pcre2test $1 >>testtry
if [ $? -ne 0 ] ; then
echo "** pcre2test $1 failed - check testtry"
exit 1
fi
}
# ------ Special EBCDIC Test -------
if [ $# -eq 1 -a "$1" = "ebcdic" ]; then
$valgrind ./pcre2test -C ebcdic >/dev/null
ebcdic=$?
if [ $ebcdic -ne 1 ] ; then
echo "Cannot run EBCDIC tests: EBCDIC support not compiled"
exit 1
fi
for opt in "" "-dfa"; do
./pcre2test -q $opt $testdata/testinputEBC >testtry
checkresult $? EBC "$opt"
done
exit 0
fi
# ------ Normal Tests ------
# Default values
arg8=
arg16=
arg32=
nojit=
bigstack=
sim=
skip=
valgrind=
vjs=
# This is in case the caller has set aliases (as I do - PH)
unset cp ls mv rm
# Process options and select which tests to run; for those that are explicitly
# requested, check that the necessary optional facilities are available.
do0=no
do1=no
do2=no
do3=no
do4=no
do5=no
do6=no
do7=no
do8=no
do9=no
do10=no
do11=no
do12=no
do13=no
do14=no
do15=no
do16=no
do17=no
do18=no
do19=no
do20=no
do21=no
do22=no
do23=no
do24=no
do25=no
do26=no
doheap=no
while [ $# -gt 0 ] ; do
case $1 in
0) do0=yes;;
1) do1=yes;;
2) do2=yes;;
3) do3=yes;;
4) do4=yes;;
5) do5=yes;;
6) do6=yes;;
7) do7=yes;;
8) do8=yes;;
9) do9=yes;;
10) do10=yes;;
11) do11=yes;;
12) do12=yes;;
13) do13=yes;;
14) do14=yes;;
15) do15=yes;;
16) do16=yes;;
17) do17=yes;;
18) do18=yes;;
19) do19=yes;;
20) do20=yes;;
21) do21=yes;;
22) do22=yes;;
23) do23=yes;;
24) do24=yes;;
25) do25=yes;;
26) do26=yes;;
heap) doheap=yes;;
-8) arg8=yes;;
-16) arg16=yes;;
-32) arg32=yes;;
bigstack|-bigstack) bigstack=yes;;
nojit|-nojit) nojit=yes;;
sim|-sim) shift; sim=$1;;
valgrind|-valgrind) valgrind="valgrind --tool=memcheck -q --smc-check=all-non-file";;
valgrind-log|-valgrind-log) valgrind="valgrind --tool=memcheck --num-callers=30 --leak-check=no --error-limit=no --smc-check=all-non-file --log-file=report.%p ";;
~*)
if expr "$1" : '~[0-9][0-9]*$' >/dev/null; then
skip="$skip `expr "$1" : '~\([0-9]*\)*$'`"
else
echo "Unknown option or test selector '$1'"; exit 1
fi
;;
*-*)
if expr "$1" : '[0-9][0-9]*-[0-9]*$' >/dev/null; then
tf=`expr "$1" : '\([0-9]*\)'`
tt=`expr "$1" : '.*-\([0-9]*\)'`
if [ "$tt" = "" ] ; then tt=$maxtest; fi
if expr \( "$tt" ">" "$maxtest" \) >/dev/null; then
echo "Invalid test range '$1'"; exit 1
fi
while expr "$tf" "<=" "$tt" >/dev/null; do
eval do${tf}=yes
tf=`expr $tf + 1`
done
else
echo "Invalid test range '$1'"; exit 1
fi
;;
*) echo "Unknown option or test selector '$1'"; exit 1;;
esac
shift
done
# Find which optional facilities are available.
$sim ./pcre2test -C linksize >/dev/null
link_size=$?
if [ $link_size -lt 2 ] ; then
echo "RunTest: Failed to find internal link size"
exit 1
fi
if [ $link_size -gt 4 ] ; then
echo "RunTest: Failed to find internal link size"
exit 1
fi
# If it is possible to set the system stack size and -bigstack was given,
# set up a large stack.
$sim ./pcre2test -S 64 /dev/null /dev/null
support_setstack=$?
if [ $support_setstack -eq 0 -a "$bigstack" != "" ] ; then
setstack="-S 64"
else
setstack=""
fi
# All of 8-bit, 16-bit, and 32-bit character strings may be supported, but only
# one need be.
$sim ./pcre2test -C pcre2-8 >/dev/null
support8=$?
$sim ./pcre2test -C pcre2-16 >/dev/null
support16=$?
$sim ./pcre2test -C pcre2-32 >/dev/null
support32=$?
# \C may be disabled
$sim ./pcre2test -C backslash-C >/dev/null
supportBSC=$?
# Initialize all bitsizes skipped
test8=skip
test16=skip
test32=skip
# If no bitsize arguments, select all that are available
if [ "$arg8$arg16$arg32" = "" ] ; then
if [ $support8 -ne 0 ] ; then
test8=-8
fi
if [ $support16 -ne 0 ] ; then
test16=-16
fi
if [ $support32 -ne 0 ] ; then
test32=-32
fi
# Otherwise, select requested bit sizes
else
if [ "$arg8" = yes ] ; then
if [ $support8 -eq 0 ] ; then
echo "Cannot run 8-bit library tests: 8-bit library not compiled"
exit 1
fi
test8=-8
fi
if [ "$arg16" = yes ] ; then
if [ $support16 -eq 0 ] ; then
echo "Cannot run 16-bit library tests: 16-bit library not compiled"
exit 1
fi
test16=-16
fi
if [ "$arg32" = yes ] ; then
if [ $support32 -eq 0 ] ; then
echo "Cannot run 32-bit library tests: 32-bit library not compiled"
exit 1
fi
test32=-32
fi
fi
# UTF support is implied by Unicode support, and it always applies to all bit
# sizes if both are supported; we can't have UTF-8 support without UTF-16 or
# UTF-32 support.
$sim ./pcre2test -C unicode >/dev/null
utf=$?
# When JIT is used with valgrind, we need to set up valgrind suppressions as
# otherwise there are a lot of false positive valgrind reports when the
# the hardware supports SSE2.
jitopt=
$sim ./pcre2test -C jit >/dev/null
jit=$?
if [ $jit -ne 0 -a "$nojit" != "yes" ] ; then
jitopt=-jit
if [ "$valgrind" != "" ] ; then
vjs="--suppressions=$testdata/valgrind-jit.supp"
fi
fi
# If no specific tests were requested, select all the numbered tests. Those
# that are not relevant will be automatically skipped.
if [ $do0 = no -a $do1 = no -a $do2 = no -a $do3 = no -a \
$do4 = no -a $do5 = no -a $do6 = no -a $do7 = no -a \
$do8 = no -a $do9 = no -a $do10 = no -a $do11 = no -a \
$do12 = no -a $do13 = no -a $do14 = no -a $do15 = no -a \
$do16 = no -a $do17 = no -a $do18 = no -a $do19 = no -a \
$do20 = no -a $do21 = no -a $do22 = no -a $do23 = no -a \
$do24 = no -a $do25 = no -a $do26 = no -a $doheap = no \
]; then
do0=yes
do1=yes
do2=yes
do3=yes
do4=yes
do5=yes
do6=yes
do7=yes
do8=yes
do9=yes
do10=yes
do11=yes
do12=yes
do13=yes
do14=yes
do15=yes
do16=yes
do17=yes
do18=yes
do19=yes
do20=yes
do21=yes
do22=yes
do23=yes
do24=yes
do25=yes
do26=yes
fi
# Handle any explicit skips at this stage, so that an argument list may consist
# only of explicit skips.
for i in $skip; do eval do$i=no; done
# Show which release and which test data
echo ""
echo PCRE2 C library tests using test data from $testdata
$sim ./pcre2test /dev/null
echo ""
for bmode in "$test8" "$test16" "$test32"; do
case "$bmode" in
skip) continue;;
-16) if [ "$test8$test32" != "skipskip" ] ; then echo ""; fi
bits=16; echo "---- Testing 16-bit library ----"; echo "";;
-32) if [ "$test8$test16" != "skipskip" ] ; then echo ""; fi
bits=32; echo "---- Testing 32-bit library ----"; echo "";;
-8) bits=8; echo "---- Testing 8-bit library ----"; echo "";;
esac
# Test 0 is a special test. Its output is not checked, because it will
# be different on different hardware and with different configurations.
# Running this test just exercises the code.
if [ $do0 = yes ] ; then
echo $title0
echo '/abc/jit,memory,framesize' >testSinput
echo ' abc' >>testSinput
echo '' >testtry
checkspecial '-C'
checkspecial '--help'
if [ $support_setstack -eq 0 ] ; then
checkspecial '-S 1 -t 10 testSinput'
fi
echo " OK"
fi
# Primary non-UTF test, compatible with JIT and all versions of Perl >= 5.8
if [ $do1 = yes ] ; then
echo $title1
for opt in "" $jitopt; do
$sim $valgrind ${opt:+$vjs} ./pcre2test -q $setstack $bmode $opt $testdata/testinput1 testtry
checkresult $? 1 "$opt"
done
fi
# PCRE2 tests that are not Perl-compatible: API, errors, internals. We copy
# the testbtables file to the current directory for use by this test.
if [ $do2 = yes ] ; then
echo $title2 "(excluding UTF-$bits)"
cp $testdata/testbtables .
for opt in "" $jitopt; do
$sim $valgrind ${opt:+$vjs} ./pcre2test -q $setstack $bmode $opt $testdata/testinput2 testtry
saverc=$?
if [ $saverc = 0 ] ; then
$sim $valgrind ${opt:+$vjs} ./pcre2test -q $bmode $opt -error -70,-62,-2,-1,0,100,101,191,200 >>testtry
checkresult $? 2 "$opt"
else
checkresult $saverc 2 "$opt"
fi
done
fi
# Locale-specific tests, provided that either the "fr_FR", "fr_CA", "french"
# or "fr" locale is available. The first two are Unix-like standards; the
# last two are for Windows. Unfortunately, different versions of the French
# locale give different outputs for some items. This test passes if the
# output matches any one of the alternative output files.
if [ $do3 = yes ] ; then
locale=
# In some environments locales that are listed by the "locale -a"
# command do not seem to work with setlocale(). Therefore, we do
# a preliminary test to see if pcre2test can set one before going
# on to use it.
for loc in 'fr_FR' 'french' 'fr' 'fr_CA'; do
locale -a | grep "^$loc\$" >/dev/null
if [ $? -eq 0 ] ; then
echo "/a/locale=$loc" | \
$sim $valgrind ./pcre2test -q $bmode | \
grep "Failed to set locale" >/dev/null
if [ $? -ne 0 ] ; then
locale=$loc
if [ "$locale" = "fr_FR" ] ; then
infile=$testdata/testinput3
outfile=$testdata/testoutput3
outfile2=$testdata/testoutput3A
outfile3=$testdata/testoutput3B
else
infile=test3input
outfile=test3output
outfile2=test3outputA
outfile3=test3outputB
sed "s/fr_FR/$loc/" $testdata/testinput3 >test3input
sed "s/fr_FR/$loc/" $testdata/testoutput3 >test3output
sed "s/fr_FR/$loc/" $testdata/testoutput3A >test3outputA
sed "s/fr_FR/$loc/" $testdata/testoutput3B >test3outputB
fi
break
fi
fi
done
if [ "$locale" != "" ] ; then
echo $title3 "(using '$locale' locale)"
for opt in "" $jitopt; do
$sim $valgrind ${opt:+$vjs} ./pcre2test -q $setstack $bmode $opt $infile testtry
if [ $? = 0 ] ; then
case "$opt" in
-jit) with=" with JIT";;
*) with="";;
esac
if $cf $outfile testtry >teststdout || \
$cf $outfile2 testtry >teststdout || \
$cf $outfile3 testtry >teststdout
then
echo " OK$with"
else
echo "** Locale test did not run successfully$with. The output did not match"
echo " $outfile, $outfile2 or $outfile3."
echo " This may mean that there is a problem with the locale settings rather"
echo " than a bug in PCRE2."
exit 1
fi
else exit 1
fi
done
else
echo "Cannot test locale-specific features - none of the 'fr_FR', 'fr_CA',"
echo "'fr' or 'french' locales can be set, or the \"locale\" command is"
echo "not available to check for them."
echo " "
fi
fi
# Tests for UTF and Unicode property support
if [ $do4 = yes ] ; then
echo ${title4A}-${bits}${title4B}
if [ $utf -eq 0 ] ; then
echo " Skipped because UTF-$bits support is not available"
else
for opt in "" $jitopt; do
$sim $valgrind ${opt:+$vjs} ./pcre2test -q $setstack $bmode $opt $testdata/testinput4 testtry
checkresult $? 4 "$opt"
done
fi
fi
if [ $do5 = yes ] ; then
echo ${title5A}-${bits}$title5B
if [ $utf -eq 0 ] ; then
echo " Skipped because UTF-$bits support is not available"
else
for opt in "" $jitopt; do
$sim $valgrind ${opt:+$vjs} ./pcre2test -q $setstack $bmode $opt $testdata/testinput5 testtry
checkresult $? 5 "$opt"
done
fi
fi
# Tests for DFA matching support
if [ $do6 = yes ] ; then
echo $title6
$sim $valgrind ./pcre2test -q $setstack $bmode $testdata/testinput6 testtry
checkresult $? 6 ""
fi
if [ $do7 = yes ] ; then
echo ${title7A}-${bits}$title7B
if [ $utf -eq 0 ] ; then
echo " Skipped because UTF-$bits support is not available"
else
$sim $valgrind ./pcre2test -q $setstack $bmode $opt $testdata/testinput7 testtry
checkresult $? 7 ""
fi
fi
# Test of internal offsets and code sizes. This test is run only when there
# is UTF/UCP support. The actual tests are mostly the same as in some of the
# above, but in this test we inspect some offsets and sizes. This is a
# doublecheck for the maintainer, just in case something changes unexpectedly.
# The output from this test is different in 8-bit, 16-bit, and 32-bit modes
# and for different link sizes, so there are different output files for each
# mode and link size.
if [ $do8 = yes ] ; then
echo $title8
if [ $utf -eq 0 ] ; then
echo " Skipped because UTF-$bits support is not available"
else
$sim $valgrind ./pcre2test -q $setstack $bmode $testdata/testinput8 testtry
checkresult $? 8-$bits-$link_size ""
fi
fi
# Tests for 8-bit-specific features
if [ "$do9" = yes ] ; then
echo $title9
if [ "$bits" = "16" -o "$bits" = "32" ] ; then
echo " Skipped when running 16/32-bit tests"
else
for opt in "" $jitopt; do
$sim $valgrind ${opt:+$vjs} ./pcre2test -q $setstack $bmode $opt $testdata/testinput9 testtry
checkresult $? 9 "$opt"
done
fi
fi
# Tests for UTF-8 and UCP 8-bit-specific features
if [ "$do10" = yes ] ; then
echo $title10
if [ "$bits" = "16" -o "$bits" = "32" ] ; then
echo " Skipped when running 16/32-bit tests"
elif [ $utf -eq 0 ] ; then
echo " Skipped because UTF-$bits support is not available"
else
for opt in "" $jitopt; do
$sim $valgrind ${opt:+$vjs} ./pcre2test -q $setstack $bmode $opt $testdata/testinput10 testtry
checkresult $? 10 "$opt"
done
fi
fi
# Tests for 16-bit and 32-bit features. Output is different for the two widths.
if [ $do11 = yes ] ; then
echo $title11
if [ "$bits" = "8" ] ; then
echo " Skipped when running 8-bit tests"
else
for opt in "" $jitopt; do
$sim $valgrind ${opt:+$vjs} ./pcre2test -q $setstack $bmode $opt $testdata/testinput11 testtry
checkresult $? 11-$bits "$opt"
done
fi
fi
# Tests for 16-bit and 32-bit features with UTF-16/32 and UCP support. Output
# is different for the two widths.
if [ $do12 = yes ] ; then
echo $title12
if [ "$bits" = "8" ] ; then
echo " Skipped when running 8-bit tests"
elif [ $utf -eq 0 ] ; then
echo " Skipped because UTF-$bits support is not available"
else
for opt in "" $jitopt; do
$sim $valgrind ${opt:+$vjs} ./pcre2test -q $setstack $bmode $opt $testdata/testinput12 testtry
checkresult $? 12-$bits "$opt"
done
fi
fi
# Tests for 16/32-bit-specific features in DFA non-UTF modes
if [ $do13 = yes ] ; then
echo $title13
if [ "$bits" = "8" ] ; then
echo " Skipped when running 8-bit tests"
else
$sim $valgrind ./pcre2test -q $setstack $bmode $testdata/testinput13 testtry
checkresult $? 13 ""
fi
fi
# Tests for DFA UTF and UCP features. Output is different for the different widths.
if [ $do14 = yes ] ; then
echo $title14
if [ $utf -eq 0 ] ; then
echo " Skipped because UTF-$bits support is not available"
else
$sim $valgrind ./pcre2test -q $setstack $bmode $opt $testdata/testinput14 testtry
checkresult $? 14-$bits ""
fi
fi
# Test non-JIT match and recursion limits
if [ $do15 = yes ] ; then
echo $title15
$sim $valgrind ./pcre2test -q $setstack $bmode $testdata/testinput15 testtry
checkresult $? 15 ""
fi
# Test JIT-specific features when JIT is not available
if [ $do16 = yes ] ; then
echo $title16
if [ $jit -ne 0 ] ; then
echo " Skipped because JIT is available"
else
$sim $valgrind ./pcre2test -q $setstack $bmode $testdata/testinput16 testtry
checkresult $? 16 ""
fi
fi
# Test JIT-specific features when JIT is available
if [ $do17 = yes ] ; then
echo $title17
if [ $jit -eq 0 -o "$nojit" = "yes" ] ; then
echo " Skipped because JIT is not available or nojit was specified"
else
$sim $valgrind $vjs ./pcre2test -q $setstack $bmode $testdata/testinput17 testtry
checkresult $? 17 ""
fi
fi
# Tests for the POSIX interface without UTF/UCP (8-bit only)
if [ $do18 = yes ] ; then
echo $title18
if [ "$bits" = "16" -o "$bits" = "32" ] ; then
echo " Skipped when running 16/32-bit tests"
else
$sim $valgrind ./pcre2test -q $setstack $bmode $testdata/testinput18 testtry
checkresult $? 18 ""
fi
fi
# Tests for the POSIX interface with UTF/UCP (8-bit only)
if [ $do19 = yes ] ; then
echo $title19
if [ "$bits" = "16" -o "$bits" = "32" ] ; then
echo " Skipped when running 16/32-bit tests"
elif [ $utf -eq 0 ] ; then
echo " Skipped because UTF-$bits support is not available"
else
$sim $valgrind ./pcre2test -q $setstack $bmode $testdata/testinput19 testtry
checkresult $? 19 ""
fi
fi
# Serialization tests
if [ $do20 = yes ] ; then
echo $title20
$sim $valgrind ./pcre2test -q $setstack $bmode $testdata/testinput20 testtry
checkresult $? 20 ""
fi
# \C tests without UTF - DFA matching is supported
if [ "$do21" = yes ] ; then
echo $title21
if [ $supportBSC -eq 0 ] ; then
echo " Skipped because \C is disabled"
else
for opt in "" $jitopt -dfa; do
$sim $valgrind ${opt:+$vjs} ./pcre2test -q $setstack $bmode $opt $testdata/testinput21 testtry
checkresult $? 21 "$opt"
done
fi
fi
# \C tests with UTF - DFA matching is not supported for \C in UTF mode
if [ "$do22" = yes ] ; then
echo $title22
if [ $supportBSC -eq 0 ] ; then
echo " Skipped because \C is disabled"
elif [ $utf -eq 0 ] ; then
echo " Skipped because UTF-$bits support is not available"
else
for opt in "" $jitopt; do
$sim $valgrind ${opt:+$vjs} ./pcre2test -q $setstack $bmode $opt $testdata/testinput22 testtry
checkresult $? 22-$bits "$opt"
done
fi
fi
# Test when \C is disabled
if [ "$do23" = yes ] ; then
echo $title23
if [ $supportBSC -ne 0 ] ; then
echo " Skipped because \C is not disabled"
else
$sim $valgrind ./pcre2test -q $setstack $bmode $testdata/testinput23 testtry
checkresult $? 23 ""
fi
fi
# Non-UTF pattern conversion tests
if [ "$do24" = yes ] ; then
echo $title24
$sim $valgrind ./pcre2test -q $setstack $bmode $testdata/testinput24 testtry
checkresult $? 24 ""
fi
# UTF pattern conversion tests
if [ "$do25" = yes ] ; then
echo $title25
if [ $utf -eq 0 ] ; then
echo " Skipped because UTF-$bits support is not available"
else
$sim $valgrind ./pcre2test -q $setstack $bmode $testdata/testinput25 testtry
checkresult $? 25 ""
fi
fi
# Auto-generated unicode property tests
if [ $do26 = yes ] ; then
echo $title26
if [ $utf -eq 0 ] ; then
echo " Skipped because UTF-$bits support is not available"
else
for opt in "" $jitopt; do
$sim $valgrind ${opt:+$vjs} ./pcre2test -q $setstack $bmode $opt $testdata/testinput26 testtry
checkresult $? 26 "$opt"
done
fi
fi
# Manually selected heap tests - output may vary in different environments,
# which is why that are not automatically run.
if [ $doheap = yes ] ; then
echo $titleheap
$sim $valgrind ./pcre2test -q $setstack $bmode $testdata/testinputheap testtry
checkresult $? heap-$bits ""
fi
# End of loop for 8/16/32-bit tests
done
# Clean up local working files
rm -f testbtables testSinput test3input testsaved1 testsaved2 test3output test3outputA test3outputB teststdout teststderr testtry
# End

525
Kha/Backends/Kore-hxcpp/khacpp/project/thirdparty/pcre2-10.42-16/RunTest.bat vendored Normal file
View File

@ -0,0 +1,525 @@
@echo off
@rem
@rem MS Windows batch file to run pcre2test on testfiles with the correct
@rem options. This file must use CRLF linebreaks to function properly,
@rem and requires both pcre2test and pcre2grep.
@rem
@rem ------------------------ HISTORY ----------------------------------
@rem This file was originally contributed to PCRE1 by Ralf Junker, and touched
@rem up by Daniel Richard G. Tests 10-12 added by Philip H.
@rem Philip H also changed test 3 to use "wintest" files.
@rem
@rem Updated by Tom Fortmann to support explicit test numbers on the command
@rem line. Added argument validation and added error reporting.
@rem
@rem Sheri Pierce added logic to skip feature dependent tests
@rem tests 4 5 7 10 12 14 19 and 22 require Unicode support
@rem 8 requires Unicode and link size 2
@rem 16 requires absence of jit support
@rem 17 requires presence of jit support
@rem Sheri P also added override tests for study and jit testing
@rem Zoltan Herczeg added libpcre16 support
@rem Zoltan Herczeg added libpcre32 support
@rem -------------------------------------------------------------------
@rem
@rem The file was converted for PCRE2 by PH, February 2015.
@rem Updated for new test 14 (moving others up a number), August 2015.
@rem Tidied and updated for new tests 21, 22, 23 by PH, October 2015.
@rem PH added missing "set type" for test 22, April 2016.
@rem PH added copy command for new testbtables file, November 2020
setlocal enabledelayedexpansion
if [%srcdir%]==[] (
if exist testdata\ set srcdir=.)
if [%srcdir%]==[] (
if exist ..\testdata\ set srcdir=..)
if [%srcdir%]==[] (
if exist ..\..\testdata\ set srcdir=..\..)
if NOT exist %srcdir%\testdata\ (
Error: echo distribution testdata folder not found!
call :conferror
exit /b 1
goto :eof
)
if [%pcre2test%]==[] set pcre2test=.\pcre2test.exe
echo source dir is %srcdir%
echo pcre2test=%pcre2test%
if NOT exist %pcre2test% (
echo Error: %pcre2test% not found!
echo.
call :conferror
exit /b 1
)
%pcre2test% -C linksize >NUL
set link_size=%ERRORLEVEL%
%pcre2test% -C pcre2-8 >NUL
set support8=%ERRORLEVEL%
%pcre2test% -C pcre2-16 >NUL
set support16=%ERRORLEVEL%
%pcre2test% -C pcre2-32 >NUL
set support32=%ERRORLEVEL%
%pcre2test% -C unicode >NUL
set unicode=%ERRORLEVEL%
%pcre2test% -C jit >NUL
set jit=%ERRORLEVEL%
%pcre2test% -C backslash-C >NUL
set supportBSC=%ERRORLEVEL%
if %support8% EQU 1 (
if not exist testout8 md testout8
if not exist testoutjit8 md testoutjit8
)
if %support16% EQU 1 (
if not exist testout16 md testout16
if not exist testoutjit16 md testoutjit16
)
if %support16% EQU 1 (
if not exist testout32 md testout32
if not exist testoutjit32 md testoutjit32
)
set do1=no
set do2=no
set do3=no
set do4=no
set do5=no
set do6=no
set do7=no
set do8=no
set do9=no
set do10=no
set do11=no
set do12=no
set do13=no
set do14=no
set do15=no
set do16=no
set do17=no
set do18=no
set do19=no
set do20=no
set do21=no
set do22=no
set do23=no
set all=yes
for %%a in (%*) do (
set valid=no
for %%v in (1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23) do if %%v == %%a set valid=yes
if "!valid!" == "yes" (
set do%%a=yes
set all=no
) else (
echo Invalid test number - %%a!
echo Usage %0 [ test_number ] ...
echo Where test_number is one or more optional test numbers 1 through 23, default is all tests.
exit /b 1
)
)
set failed="no"
if "%all%" == "yes" (
set do1=yes
set do2=yes
set do3=yes
set do4=yes
set do5=yes
set do6=yes
set do7=yes
set do8=yes
set do9=yes
set do10=no
set do11=yes
set do12=no
set do13=yes
set do14=yes
set do15=yes
set do16=yes
set do17=yes
set do18=yes
set do19=yes
set do20=yes
set do21=yes
set do22=yes
set do23=yes
)
@echo RunTest.bat's pcre2test output is written to newly created subfolders
@echo named testout{8,16,32} and testoutjit{8,16,32}.
@echo.
set mode=
set bits=8
:nextMode
if "%mode%" == "" (
if %support8% EQU 0 goto modeSkip
echo.
echo ---- Testing 8-bit library ----
echo.
)
if "%mode%" == "-16" (
if %support16% EQU 0 goto modeSkip
echo.
echo ---- Testing 16-bit library ----
echo.
)
if "%mode%" == "-32" (
if %support32% EQU 0 goto modeSkip
echo.
echo ---- Testing 32-bit library ----
echo.
)
if "%do1%" == "yes" call :do1
if "%do2%" == "yes" call :do2
if "%do3%" == "yes" call :do3
if "%do4%" == "yes" call :do4
if "%do5%" == "yes" call :do5
if "%do6%" == "yes" call :do6
if "%do7%" == "yes" call :do7
if "%do8%" == "yes" call :do8
if "%do9%" == "yes" call :do9
if "%do10%" == "yes" call :do10
if "%do11%" == "yes" call :do11
if "%do12%" == "yes" call :do12
if "%do13%" == "yes" call :do13
if "%do14%" == "yes" call :do14
if "%do15%" == "yes" call :do15
if "%do16%" == "yes" call :do16
if "%do17%" == "yes" call :do17
if "%do18%" == "yes" call :do18
if "%do19%" == "yes" call :do19
if "%do20%" == "yes" call :do20
if "%do21%" == "yes" call :do21
if "%do22%" == "yes" call :do22
if "%do23%" == "yes" call :do23
:modeSkip
if "%mode%" == "" (
set mode=-16
set bits=16
goto nextMode
)
if "%mode%" == "-16" (
set mode=-32
set bits=32
goto nextMode
)
@rem If mode is -32, testing is finished
if %failed% == "yes" (
echo In above output, one or more of the various tests failed!
exit /b 1
)
echo All OK
goto :eof
:runsub
@rem Function to execute pcre2test and compare the output
@rem Arguments are as follows:
@rem
@rem 1 = test number
@rem 2 = outputdir
@rem 3 = test name use double quotes
@rem 4 - 9 = pcre2test options
if [%1] == [] (
echo Missing test number argument!
exit /b 1
)
if [%2] == [] (
echo Missing outputdir!
exit /b 1
)
if [%3] == [] (
echo Missing test name argument!
exit /b 1
)
if %1 == 8 (
set outnum=8-%bits%-%link_size%
) else (
set outnum=%1
)
set testinput=testinput%1
set testoutput=testoutput%outnum%
if exist %srcdir%\testdata\win%testinput% (
set testinput=wintestinput%1
set testoutput=wintestoutput%outnum%
)
echo Test %1: %3
%pcre2test% %mode% %4 %5 %6 %7 %8 %9 %srcdir%\testdata\%testinput% >%2%bits%\%testoutput%
if errorlevel 1 (
echo. failed executing command-line:
echo. %pcre2test% %mode% %4 %5 %6 %7 %8 %9 %srcdir%\testdata\%testinput% ^>%2%bits%\%testoutput%
set failed="yes"
goto :eof
) else if [%1]==[2] (
%pcre2test% %mode% %4 %5 %6 %7 %8 %9 -error -70,-62,-2,-1,0,100,101,191,200 >>%2%bits%\%testoutput%
)
set type=
if [%1]==[11] (
set type=-%bits%
)
if [%1]==[12] (
set type=-%bits%
)
if [%1]==[14] (
set type=-%bits%
)
if [%1]==[22] (
set type=-%bits%
)
fc /n %srcdir%\testdata\%testoutput%%type% %2%bits%\%testoutput% >NUL
if errorlevel 1 (
echo. failed comparison: fc /n %srcdir%\testdata\%testoutput% %2%bits%\%testoutput%
if [%1]==[3] (
echo.
echo ** Test 3 failure usually means french locale is not
echo ** available on the system, rather than a bug or problem with PCRE2.
echo.
goto :eof
)
set failed="yes"
goto :eof
)
echo. Passed.
goto :eof
:do1
call :runsub 1 testout "Main non-UTF, non-UCP functionality (Compatible with Perl >= 5.10)" -q
if %jit% EQU 1 call :runsub 1 testoutjit "Test with JIT Override" -q -jit
goto :eof
:do2
copy /y %srcdir%\testdata\testbtables testbtables
call :runsub 2 testout "API, errors, internals, and non-Perl stuff" -q
if %jit% EQU 1 call :runsub 2 testoutjit "Test with JIT Override" -q -jit
goto :eof
:do3
call :runsub 3 testout "Locale-specific features" -q
if %jit% EQU 1 call :runsub 3 testoutjit "Test with JIT Override" -q -jit
goto :eof
:do4
if %unicode% EQU 0 (
echo Test 4 Skipped due to absence of Unicode support.
goto :eof
)
call :runsub 4 testout "UTF-%bits% and Unicode property support - (Compatible with Perl >= 5.10)" -q
if %jit% EQU 1 call :runsub 4 testoutjit "Test with JIT Override" -q -jit
goto :eof
:do5
if %unicode% EQU 0 (
echo Test 5 Skipped due to absence of Unicode support.
goto :eof
)
call :runsub 5 testout "API, internals, and non-Perl stuff for UTF-%bits% and UCP" -q
if %jit% EQU 1 call :runsub 5 testoutjit "Test with JIT Override" -q -jit
goto :eof
:do6
call :runsub 6 testout "DFA matching main non-UTF, non-UCP functionality" -q
goto :eof
:do7
if %unicode% EQU 0 (
echo Test 7 Skipped due to absence of Unicode support.
goto :eof
)
call :runsub 7 testout "DFA matching with UTF-%bits% and Unicode property support" -q
goto :eof
:do8
if NOT %link_size% EQU 2 (
echo Test 8 Skipped because link size is not 2.
goto :eof
)
if %unicode% EQU 0 (
echo Test 8 Skipped due to absence of Unicode support.
goto :eof
)
call :runsub 8 testout "Internal offsets and code size tests" -q
goto :eof
:do9
if NOT %bits% EQU 8 (
echo Test 9 Skipped when running 16/32-bit tests.
goto :eof
)
call :runsub 9 testout "Specials for the basic 8-bit library" -q
if %jit% EQU 1 call :runsub 9 testoutjit "Test with JIT Override" -q -jit
goto :eof
:do10
if NOT %bits% EQU 8 (
echo Test 10 Skipped when running 16/32-bit tests.
goto :eof
)
if %unicode% EQU 0 (
echo Test 10 Skipped due to absence of Unicode support.
goto :eof
)
call :runsub 10 testout "Specials for the 8-bit library with Unicode support" -q
if %jit% EQU 1 call :runsub 10 testoutjit "Test with JIT Override" -q -jit
goto :eof
:do11
if %bits% EQU 8 (
echo Test 11 Skipped when running 8-bit tests.
goto :eof
)
call :runsub 11 testout "Specials for the basic 16/32-bit library" -q
if %jit% EQU 1 call :runsub 11 testoutjit "Test with JIT Override" -q -jit
goto :eof
:do12
if %bits% EQU 8 (
echo Test 12 Skipped when running 8-bit tests.
goto :eof
)
if %unicode% EQU 0 (
echo Test 12 Skipped due to absence of Unicode support.
goto :eof
)
call :runsub 12 testout "Specials for the 16/32-bit library with Unicode support" -q
if %jit% EQU 1 call :runsub 12 testoutjit "Test with JIT Override" -q -jit
goto :eof
:do13
if %bits% EQU 8 (
echo Test 13 Skipped when running 8-bit tests.
goto :eof
)
call :runsub 13 testout "DFA specials for the basic 16/32-bit library" -q
goto :eof
:do14
if %unicode% EQU 0 (
echo Test 14 Skipped due to absence of Unicode support.
goto :eof
)
call :runsub 14 testout "DFA specials for UTF and UCP support" -q
goto :eof
:do15
call :runsub 15 testout "Non-JIT limits and other non_JIT tests" -q
goto :eof
:do16
if %jit% EQU 1 (
echo Test 16 Skipped due to presence of JIT support.
goto :eof
)
call :runsub 16 testout "JIT-specific features when JIT is not available" -q
goto :eof
:do17
if %jit% EQU 0 (
echo Test 17 Skipped due to absence of JIT support.
goto :eof
)
call :runsub 17 testout "JIT-specific features when JIT is available" -q
goto :eof
:do18
if %bits% EQU 16 (
echo Test 18 Skipped when running 16-bit tests.
goto :eof
)
if %bits% EQU 32 (
echo Test 18 Skipped when running 32-bit tests.
goto :eof
)
call :runsub 18 testout "POSIX interface, excluding UTF-8 and UCP" -q
goto :eof
:do19
if %bits% EQU 16 (
echo Test 19 Skipped when running 16-bit tests.
goto :eof
)
if %bits% EQU 32 (
echo Test 19 Skipped when running 32-bit tests.
goto :eof
)
if %unicode% EQU 0 (
echo Test 19 Skipped due to absence of Unicode support.
goto :eof
)
call :runsub 19 testout "POSIX interface with UTF-8 and UCP" -q
goto :eof
:do20
call :runsub 20 testout "Serialization tests" -q
goto :eof
:do21
if %supportBSC% EQU 0 (
echo Test 21 Skipped due to absence of backslash-C support.
goto :eof
)
call :runsub 21 testout "Backslash-C tests without UTF" -q
call :runsub 21 testout "Backslash-C tests without UTF (DFA)" -q -dfa
if %jit% EQU 1 call :runsub 21 testoutjit "Test with JIT Override" -q -jit
goto :eof
:do22
if %supportBSC% EQU 0 (
echo Test 22 Skipped due to absence of backslash-C support.
goto :eof
)
if %unicode% EQU 0 (
echo Test 22 Skipped due to absence of Unicode support.
goto :eof
)
call :runsub 22 testout "Backslash-C tests with UTF" -q
if %jit% EQU 1 call :runsub 22 testoutjit "Test with JIT Override" -q -jit
goto :eof
:do23
if %supportBSC% EQU 1 (
echo Test 23 Skipped due to presence of backslash-C support.
goto :eof
)
call :runsub 23 testout "Backslash-C disabled test" -q
goto :eof
:conferror
@echo.
@echo Either your build is incomplete or you have a configuration error.
@echo.
@echo If configured with cmake and executed via "make test" or the MSVC "RUN_TESTS"
@echo project, pcre2_test.bat defines variables and automatically calls RunTest.bat.
@echo For manual testing of all available features, after configuring with cmake
@echo and building, you can run the built pcre2_test.bat. For best results with
@echo cmake builds and tests avoid directories with full path names that include
@echo spaces for source or build.
@echo.
@echo Otherwise, if the build dir is in a subdir of the source dir, testdata needed
@echo for input and verification should be found automatically when (from the
@echo location of the the built exes) you call RunTest.bat. By default RunTest.bat
@echo runs all tests compatible with the linked pcre2 library but it can be given
@echo a test number as an argument.
@echo.
@echo If the build dir is not under the source dir you can either copy your exes
@echo to the source folder or copy RunTest.bat and the testdata folder to the
@echo location of your built exes and then run RunTest.bat.
@echo.

1
Kha/Backends/Kore-hxcpp/khacpp/project/thirdparty/pcre2-10.42-16/WORKSPACE.bazel vendored Normal file
View File

@ -0,0 +1 @@
# See MODULE.bazel

45
Kha/Backends/Kore-hxcpp/khacpp/project/thirdparty/pcre2-10.42-16/autogen.sh vendored Normal file
View File

@ -0,0 +1,45 @@
#!/bin/sh
# Running aclocal here first (as happened for a while) caused the macros that
# libtoolize puts in the m4 directory to be newer than the aclocal.m4 file that
# aclocal creates. This meant that the next "make" cause aclocal to be run
# again. Moving aclocal to after libtoolize does not seem to cause any
# problems, and it fixes this issue.
# GNU libtool is named differently on some systems. This code tries several
# variants like glibtoolize (MacOSX) and libtoolize1x (FreeBSD)
set +ex
echo "Looking for a version of libtoolize (which can have different names)..."
libtoolize=""
for l in glibtoolize libtoolize15 libtoolize14 libtoolize ; do
$l --version > /dev/null 2>&1
if [ $? = 0 ]; then
libtoolize=$l
echo "Found $l"
break
fi
echo "Did not find $l"
done
if [ "x$libtoolize" = "x" ]; then
echo "Can't find libtoolize on your system"
exit 1
fi
set -ex
$libtoolize -c -f
rm -rf autom4te.cache Makefile.in aclocal.m4
aclocal --force -I m4
autoconf -f -W all,no-obsolete
autoheader -f -W all
# Added no-portability to suppress automake 1.12's warning about the use
# of recursive variables.
automake -a -c -f -W all,no-portability
rm -rf autom4te.cache
exit 0
# end autogen.sh

22
Kha/Backends/Kore-hxcpp/khacpp/project/thirdparty/pcre2-10.42-16/cmake/COPYING-CMAKE-SCRIPTS vendored Normal file
View File

@ -0,0 +1,22 @@
Redistribution and use in source and binary forms, with or without
modification, are permitted provided that the following conditions
are met:
1. Redistributions of source code must retain the copyright
notice, this list of conditions and the following disclaimer.
2. Redistributions in binary form must reproduce the copyright
notice, this list of conditions and the following disclaimer in the
documentation and/or other materials provided with the distribution.
3. The name of the author may not be used to endorse or promote products
derived from this software without specific prior written permission.
THIS SOFTWARE IS PROVIDED BY THE AUTHOR ``AS IS'' AND ANY EXPRESS OR
IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES
OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED.
IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY DIRECT, INDIRECT,
INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT
NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF
THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.

16
Kha/Backends/Kore-hxcpp/khacpp/project/thirdparty/pcre2-10.42-16/cmake/FindEditline.cmake vendored Normal file
View File

@ -0,0 +1,16 @@
# Modified from FindReadline.cmake (PH Feb 2012)
if(EDITLINE_INCLUDE_DIR AND EDITLINE_LIBRARY)
set(EDITLINE_FOUND TRUE)
else(EDITLINE_INCLUDE_DIR AND EDITLINE_LIBRARY)
FIND_PATH(EDITLINE_INCLUDE_DIR readline.h PATH_SUFFIXES
editline
edit/readline
)
FIND_LIBRARY(EDITLINE_LIBRARY NAMES edit)
include(FindPackageHandleStandardArgs)
FIND_PACKAGE_HANDLE_STANDARD_ARGS(Editline DEFAULT_MSG EDITLINE_INCLUDE_DIR EDITLINE_LIBRARY)
MARK_AS_ADVANCED(EDITLINE_INCLUDE_DIR EDITLINE_LIBRARY)
endif(EDITLINE_INCLUDE_DIR AND EDITLINE_LIBRARY)

58
Kha/Backends/Kore-hxcpp/khacpp/project/thirdparty/pcre2-10.42-16/cmake/FindPackageHandleStandardArgs.cmake vendored Normal file
View File

@ -0,0 +1,58 @@
# FIND_PACKAGE_HANDLE_STANDARD_ARGS(NAME (DEFAULT_MSG|"Custom failure message") VAR1 ... )
# This macro is intended to be used in FindXXX.cmake modules files.
# It handles the REQUIRED and QUIET argument to FIND_PACKAGE() and
# it also sets the <UPPERCASED_NAME>_FOUND variable.
# The package is found if all variables listed are TRUE.
# Example:
#
# FIND_PACKAGE_HANDLE_STANDARD_ARGS(LibXml2 DEFAULT_MSG LIBXML2_LIBRARIES LIBXML2_INCLUDE_DIR)
#
# LibXml2 is considered to be found, if both LIBXML2_LIBRARIES and
# LIBXML2_INCLUDE_DIR are valid. Then also LIBXML2_FOUND is set to TRUE.
# If it is not found and REQUIRED was used, it fails with FATAL_ERROR,
# independent whether QUIET was used or not.
# If it is found, the location is reported using the VAR1 argument, so
# here a message "Found LibXml2: /usr/lib/libxml2.so" will be printed out.
# If the second argument is DEFAULT_MSG, the message in the failure case will
# be "Could NOT find LibXml2", if you don't like this message you can specify
# your own custom failure message there.
MACRO(FIND_PACKAGE_HANDLE_STANDARD_ARGS _NAME _FAIL_MSG _VAR1 )
IF("${_FAIL_MSG}" STREQUAL "DEFAULT_MSG")
IF (${_NAME}_FIND_REQUIRED)
SET(_FAIL_MESSAGE "Could not find REQUIRED package ${_NAME}")
ELSE (${_NAME}_FIND_REQUIRED)
SET(_FAIL_MESSAGE "Could not find OPTIONAL package ${_NAME}")
ENDIF (${_NAME}_FIND_REQUIRED)
ELSE("${_FAIL_MSG}" STREQUAL "DEFAULT_MSG")
SET(_FAIL_MESSAGE "${_FAIL_MSG}")
ENDIF("${_FAIL_MSG}" STREQUAL "DEFAULT_MSG")
STRING(TOUPPER ${_NAME} _NAME_UPPER)
SET(${_NAME_UPPER}_FOUND TRUE)
IF(NOT ${_VAR1})
SET(${_NAME_UPPER}_FOUND FALSE)
ENDIF(NOT ${_VAR1})
FOREACH(_CURRENT_VAR ${ARGN})
IF(NOT ${_CURRENT_VAR})
SET(${_NAME_UPPER}_FOUND FALSE)
ENDIF(NOT ${_CURRENT_VAR})
ENDFOREACH(_CURRENT_VAR)
IF (${_NAME_UPPER}_FOUND)
IF (NOT ${_NAME}_FIND_QUIETLY)
MESSAGE(STATUS "Found ${_NAME}: ${${_VAR1}}")
ENDIF (NOT ${_NAME}_FIND_QUIETLY)
ELSE (${_NAME_UPPER}_FOUND)
IF (${_NAME}_FIND_REQUIRED)
MESSAGE(FATAL_ERROR "${_FAIL_MESSAGE}")
ELSE (${_NAME}_FIND_REQUIRED)
IF (NOT ${_NAME}_FIND_QUIETLY)
MESSAGE(STATUS "${_FAIL_MESSAGE}")
ENDIF (NOT ${_NAME}_FIND_QUIETLY)
ENDIF (${_NAME}_FIND_REQUIRED)
ENDIF (${_NAME_UPPER}_FOUND)
ENDMACRO(FIND_PACKAGE_HANDLE_STANDARD_ARGS)

29
Kha/Backends/Kore-hxcpp/khacpp/project/thirdparty/pcre2-10.42-16/cmake/FindReadline.cmake vendored Normal file
View File

@ -0,0 +1,29 @@
# from http://websvn.kde.org/trunk/KDE/kdeedu/cmake/modules/FindReadline.cmake
# http://websvn.kde.org/trunk/KDE/kdeedu/cmake/modules/COPYING-CMAKE-SCRIPTS
# --> BSD licensed
#
# GNU Readline library finder
if(READLINE_INCLUDE_DIR AND READLINE_LIBRARY AND NCURSES_LIBRARY)
set(READLINE_FOUND TRUE)
else(READLINE_INCLUDE_DIR AND READLINE_LIBRARY AND NCURSES_LIBRARY)
FIND_PATH(READLINE_INCLUDE_DIR readline/readline.h
/usr/include/readline
)
# 2008-04-22 The next clause used to read like this:
#
# FIND_LIBRARY(READLINE_LIBRARY NAMES readline)
# FIND_LIBRARY(NCURSES_LIBRARY NAMES ncurses )
# include(FindPackageHandleStandardArgs)
# FIND_PACKAGE_HANDLE_STANDARD_ARGS(Readline DEFAULT_MSG NCURSES_LIBRARY READLINE_INCLUDE_DIR READLINE_LIBRARY )
#
# I was advised to modify it such that it will find an ncurses library if
# required, but not if one was explicitly given, that is, it allows the
# default to be overridden. PH
FIND_LIBRARY(READLINE_LIBRARY NAMES readline)
include(FindPackageHandleStandardArgs)
FIND_PACKAGE_HANDLE_STANDARD_ARGS(Readline DEFAULT_MSG READLINE_INCLUDE_DIR READLINE_LIBRARY )
MARK_AS_ADVANCED(READLINE_INCLUDE_DIR READLINE_LIBRARY)
endif(READLINE_INCLUDE_DIR AND READLINE_LIBRARY AND NCURSES_LIBRARY)

15
Kha/Backends/Kore-hxcpp/khacpp/project/thirdparty/pcre2-10.42-16/cmake/pcre2-config-version.cmake.in vendored Normal file
View File

@ -0,0 +1,15 @@
set(PACKAGE_VERSION_MAJOR @PCRE2_MAJOR@)
set(PACKAGE_VERSION_MINOR @PCRE2_MINOR@)
set(PACKAGE_VERSION_PATCH 0)
set(PACKAGE_VERSION @PCRE2_MAJOR@.@PCRE2_MINOR@.0)
# Check whether the requested PACKAGE_FIND_VERSION is compatible
if(PACKAGE_VERSION VERSION_LESS PACKAGE_FIND_VERSION OR
PACKAGE_VERSION_MAJOR GREATER PACKAGE_FIND_VERSION_MAJOR)
set(PACKAGE_VERSION_COMPATIBLE FALSE)
else()
set(PACKAGE_VERSION_COMPATIBLE TRUE)
if(PACKAGE_VERSION VERSION_EQUAL PACKAGE_FIND_VERSION)
set(PACKAGE_VERSION_EXACT TRUE)
endif()
endif()

145
Kha/Backends/Kore-hxcpp/khacpp/project/thirdparty/pcre2-10.42-16/cmake/pcre2-config.cmake.in vendored Normal file
View File

@ -0,0 +1,145 @@
# pcre2-config.cmake
# ----------------
#
# Finds the PCRE2 library, specify the starting search path in PCRE2_ROOT.
#
# Static vs. shared
# -----------------
# To make use of the static library instead of the shared one, one needs
# to set the variable PCRE2_USE_STATIC_LIBS to ON before calling find_package.
# Example:
# set(PCRE2_USE_STATIC_LIBS ON)
# find_package(PCRE2 CONFIG COMPONENTS 8BIT)
#
# This will define the following variables:
#
# PCRE2_FOUND - True if the system has the PCRE2 library.
# PCRE2_VERSION - The version of the PCRE2 library which was found.
#
# and the following imported targets:
#
# PCRE2::8BIT - The 8 bit PCRE2 library.
# PCRE2::16BIT - The 16 bit PCRE2 library.
# PCRE2::32BIT - The 32 bit PCRE2 library.
# PCRE2::POSIX - The POSIX PCRE2 library.
set(PCRE2_NON_STANDARD_LIB_PREFIX @NON_STANDARD_LIB_PREFIX@)
set(PCRE2_NON_STANDARD_LIB_SUFFIX @NON_STANDARD_LIB_SUFFIX@)
set(PCRE2_8BIT_NAME pcre2-8)
set(PCRE2_16BIT_NAME pcre2-16)
set(PCRE2_32BIT_NAME pcre2-32)
set(PCRE2_POSIX_NAME pcre2-posix)
find_path(PCRE2_INCLUDE_DIR NAMES pcre2.h DOC "PCRE2 include directory")
if (PCRE2_USE_STATIC_LIBS)
if (MSVC)
set(PCRE2_8BIT_NAME pcre2-8-static)
set(PCRE2_16BIT_NAME pcre2-16-static)
set(PCRE2_32BIT_NAME pcre2-32-static)
set(PCRE2_POSIX_NAME pcre2-posix-static)
endif ()
set(PCRE2_PREFIX ${CMAKE_STATIC_LIBRARY_PREFIX})
set(PCRE2_SUFFIX ${CMAKE_STATIC_LIBRARY_SUFFIX})
else ()
set(PCRE2_PREFIX ${CMAKE_SHARED_LIBRARY_PREFIX})
if (MINGW AND PCRE2_NON_STANDARD_LIB_PREFIX)
set(PCRE2_PREFIX "")
endif ()
set(PCRE2_SUFFIX ${CMAKE_SHARED_LIBRARY_SUFFIX})
if (MINGW AND PCRE2_NON_STANDARD_LIB_SUFFIX)
set(PCRE2_SUFFIX "-0.dll")
endif ()
endif ()
find_library(PCRE2_8BIT_LIBRARY NAMES ${PCRE2_PREFIX}${PCRE2_8BIT_NAME}${PCRE2_SUFFIX} ${PCRE2_PREFIX}${PCRE2_8BIT_NAME}d${PCRE2_SUFFIX} DOC "8 bit PCRE2 library")
find_library(PCRE2_16BIT_LIBRARY NAMES ${PCRE2_PREFIX}${PCRE2_16BIT_NAME}${PCRE2_SUFFIX} ${PCRE2_PREFIX}${PCRE2_8BIT_NAME}d${PCRE2_SUFFIX} DOC "16 bit PCRE2 library")
find_library(PCRE2_32BIT_LIBRARY NAMES ${PCRE2_PREFIX}${PCRE2_32BIT_NAME}${PCRE2_SUFFIX} ${PCRE2_PREFIX}${PCRE2_8BIT_NAME}d${PCRE2_SUFFIX} DOC "32 bit PCRE2 library")
find_library(PCRE2_POSIX_LIBRARY NAMES ${PCRE2_PREFIX}${PCRE2_POSIX_NAME}${PCRE2_SUFFIX} ${PCRE2_PREFIX}${PCRE2_8BIT_NAME}d${PCRE2_SUFFIX} DOC "8 bit POSIX PCRE2 library")
unset(PCRE2_NON_STANDARD_LIB_PREFIX)
unset(PCRE2_NON_STANDARD_LIB_SUFFIX)
unset(PCRE2_8BIT_NAME)
unset(PCRE2_16BIT_NAME)
unset(PCRE2_32BIT_NAME)
unset(PCRE2_POSIX_NAME)
# Set version
if (PCRE2_INCLUDE_DIR)
set(PCRE2_VERSION "@PCRE2_MAJOR@.@PCRE2_MINOR@.0")
endif ()
# Which components have been found.
if (PCRE2_8BIT_LIBRARY)
set(PCRE2_8BIT_FOUND TRUE)
endif ()
if (PCRE2_16BIT_LIBRARY)
set(PCRE2_16BIT_FOUND TRUE)
endif ()
if (PCRE2_32BIT_LIBRARY)
set(PCRE2_32BIT_FOUND TRUE)
endif ()
if (PCRE2_POSIX_LIBRARY)
set(PCRE2_POSIX_FOUND TRUE)
endif ()
# Check if at least one component has been specified.
list(LENGTH PCRE2_FIND_COMPONENTS PCRE2_NCOMPONENTS)
if (PCRE2_NCOMPONENTS LESS 1)
message(FATAL_ERROR "No components have been specified. This is not allowed. Please, specify at least one component.")
endif ()
unset(PCRE2_NCOMPONENTS)
# When POSIX component has been specified make sure that also 8BIT component is specified.
set(PCRE2_8BIT_COMPONENT FALSE)
set(PCRE2_POSIX_COMPONENT FALSE)
foreach(component ${PCRE2_FIND_COMPONENTS})
if (component STREQUAL "8BIT")
set(PCRE2_8BIT_COMPONENT TRUE)
elseif (component STREQUAL "POSIX")
set(PCRE2_POSIX_COMPONENT TRUE)
endif ()
endforeach()
if (PCRE2_POSIX_COMPONENT AND NOT PCRE2_8BIT_COMPONENT)
message(FATAL_ERROR "The component POSIX is specified while the 8BIT one is not. This is not allowed. Please, also specify the 8BIT component.")
endif()
unset(PCRE2_8BIT_COMPONENT)
unset(PCRE2_POSIX_COMPONENT)
include(FindPackageHandleStandardArgs)
set(${CMAKE_FIND_PACKAGE_NAME}_CONFIG "${CMAKE_CURRENT_LIST_FILE}")
find_package_handle_standard_args(PCRE2
FOUND_VAR PCRE2_FOUND
REQUIRED_VARS PCRE2_INCLUDE_DIR
HANDLE_COMPONENTS
VERSION_VAR PCRE2_VERSION
CONFIG_MODE
)
set(PCRE2_LIBRARIES)
if (PCRE2_FOUND)
foreach(component ${PCRE2_FIND_COMPONENTS})
if (PCRE2_USE_STATIC_LIBS)
add_library(PCRE2::${component} STATIC IMPORTED)
target_compile_definitions(PCRE2::${component} INTERFACE PCRE2_STATIC)
else ()
add_library(PCRE2::${component} SHARED IMPORTED)
endif ()
set_target_properties(PCRE2::${component} PROPERTIES
IMPORTED_LOCATION "${PCRE2_${component}_LIBRARY}"
INTERFACE_INCLUDE_DIRECTORIES "${PCRE2_INCLUDE_DIR}"
)
if (component STREQUAL "POSIX")
set_target_properties(PCRE2::${component} PROPERTIES
INTERFACE_LINK_LIBRARIES "PCRE2::8BIT"
LINK_LIBRARIES "PCRE2::8BIT"
)
endif ()
set(PCRE2_LIBRARIES ${PCRE2_LIBRARIES} ${PCRE2_${component}_LIBRARY})
mark_as_advanced(PCRE2_${component}_LIBRARY)
endforeach()
endif ()
mark_as_advanced(
PCRE2_INCLUDE_DIR
)

54
Kha/Backends/Kore-hxcpp/khacpp/project/thirdparty/pcre2-10.42-16/config-cmake.h.in vendored Normal file
View File

@ -0,0 +1,54 @@
/* config.h for CMake builds */
#cmakedefine HAVE_ATTRIBUTE_UNINITIALIZED 1
#cmakedefine HAVE_DIRENT_H 1
#cmakedefine HAVE_STRERROR 1
#cmakedefine HAVE_SYS_STAT_H 1
#cmakedefine HAVE_SYS_TYPES_H 1
#cmakedefine HAVE_UNISTD_H 1
#cmakedefine HAVE_WINDOWS_H 1
#cmakedefine HAVE_BCOPY 1
#cmakedefine HAVE_MEMFD_CREATE 1
#cmakedefine HAVE_MEMMOVE 1
#cmakedefine HAVE_SECURE_GETENV 1
#cmakedefine HAVE_STRERROR 1
#cmakedefine SUPPORT_PCRE2_8 1
#cmakedefine SUPPORT_PCRE2_16 1
#cmakedefine SUPPORT_PCRE2_32 1
#cmakedefine PCRE2_DEBUG 1
#cmakedefine DISABLE_PERCENT_ZT 1
#cmakedefine SUPPORT_LIBBZ2 1
#cmakedefine SUPPORT_LIBEDIT 1
#cmakedefine SUPPORT_LIBREADLINE 1
#cmakedefine SUPPORT_LIBZ 1
#cmakedefine SUPPORT_JIT 1
#cmakedefine SLJIT_PROT_EXECUTABLE_ALLOCATOR 1
#cmakedefine SUPPORT_PCRE2GREP_JIT 1
#cmakedefine SUPPORT_PCRE2GREP_CALLOUT 1
#cmakedefine SUPPORT_PCRE2GREP_CALLOUT_FORK 1
#cmakedefine SUPPORT_UNICODE 1
#cmakedefine SUPPORT_VALGRIND 1
#cmakedefine BSR_ANYCRLF 1
#cmakedefine EBCDIC 1
#cmakedefine EBCDIC_NL25 1
#cmakedefine HEAP_MATCH_RECURSE 1
#cmakedefine NEVER_BACKSLASH_C 1
#define LINK_SIZE @PCRE2_LINK_SIZE@
#define HEAP_LIMIT @PCRE2_HEAP_LIMIT@
#define MATCH_LIMIT @PCRE2_MATCH_LIMIT@
#define MATCH_LIMIT_DEPTH @PCRE2_MATCH_LIMIT_DEPTH@
#define NEWLINE_DEFAULT @NEWLINE_DEFAULT@
#define PARENS_NEST_LIMIT @PCRE2_PARENS_NEST_LIMIT@
#define PCRE2GREP_BUFSIZE @PCRE2GREP_BUFSIZE@
#define PCRE2GREP_MAX_BUFSIZE @PCRE2GREP_MAX_BUFSIZE@
#define MAX_NAME_SIZE 32
#define MAX_NAME_COUNT 10000
/* end config.h for CMake builds */

1129
Kha/Backends/Kore-hxcpp/khacpp/project/thirdparty/pcre2-10.42-16/configure.ac vendored Normal file
View File

File diff suppressed because it is too large Load Diff

56
Kha/Backends/Kore-hxcpp/khacpp/project/thirdparty/pcre2-10.42-16/index.md vendored Normal file
View File

@ -0,0 +1,56 @@
# PCRE2 - Perl-Compatible Regular Expressions
The PCRE2 library is a set of C functions that implement regular expression
pattern matching using the same syntax and semantics as Perl 5. PCRE2 has its
own native API, as well as a set of wrapper functions that correspond to the
POSIX regular expression API. The PCRE2 library is free, even for building
proprietary software. It comes in three forms, for processing 8-bit, 16-bit,
or 32-bit code units, in either literal or UTF encoding.
PCRE2 was first released in 2015 to replace the API in the original PCRE
library, which is now obsolete and no longer maintained. As well as a more
flexible API, the code of PCRE2 has been much improved since the fork.
## Download
As well as downloading from the
[GitHub site](https://github.com/PCRE2Project/pcre2), you can download PCRE2
or the older, unmaintained PCRE1 library from an
[*unofficial* mirror](https://sourceforge.net/projects/pcre/files/) at SourceForge.
You can check out the PCRE2 source code via Git or Subversion:
git clone https://github.com/PCRE2Project/pcre2.git
svn co https://github.com/PCRE2Project/pcre2.git
## Contributed Ports
If you just need the command-line PCRE2 tools on Windows, precompiled binary
versions are available at this
[Rexegg page](http://www.rexegg.com/pcregrep-pcretest.html).
A PCRE2 port for z/OS, a mainframe operating system which uses EBCDIC as its
default character encoding, can be found at
[http://www.cbttape.org](http://www.cbttape.org/) (File 939).
## Documentation
You can read the PCRE2 documentation
[here](https://PCRE2Project.github.io/pcre2/doc/html/index.html).
Comparisons to Perl's regular expression semantics can be found in the
community authored Wikipedia entry for PCRE.
There is a curated summary of changes for each PCRE release, copies of
documentation from older releases, and other useful information from the third
party authored
[RexEgg PCRE Documentation and Change Log page](http://www.rexegg.com/pcre-documentation.html).
## Contact
To report a problem with the PCRE2 library, or to make a feature request, please
use the PCRE2 GitHub issues tracker. There is a mailing list for discussion of
PCRE2 issues and development at pcre2-dev@googlegroups.com, which is where any
announcements will be made. You can browse the
[list archives](https://groups.google.com/g/pcre2-dev).

13
Kha/Backends/Kore-hxcpp/khacpp/project/thirdparty/pcre2-10.42-16/libpcre2-16.pc.in vendored Normal file
View File

@ -0,0 +1,13 @@
# Package Information for pkg-config
prefix=@prefix@
exec_prefix=@exec_prefix@
libdir=@libdir@
includedir=@includedir@
Name: libpcre2-16
Description: PCRE2 - Perl compatible regular expressions C library (2nd API) with 16 bit character support
Version: @PACKAGE_VERSION@
Libs: -L${libdir} -lpcre2-16@LIB_POSTFIX@
Libs.private: @PTHREAD_CFLAGS@ @PTHREAD_LIBS@
Cflags: -I${includedir} @PCRE2_STATIC_CFLAG@

13
Kha/Backends/Kore-hxcpp/khacpp/project/thirdparty/pcre2-10.42-16/libpcre2-32.pc.in vendored Normal file
View File

@ -0,0 +1,13 @@
# Package Information for pkg-config
prefix=@prefix@
exec_prefix=@exec_prefix@
libdir=@libdir@
includedir=@includedir@
Name: libpcre2-32
Description: PCRE2 - Perl compatible regular expressions C library (2nd API) with 32 bit character support
Version: @PACKAGE_VERSION@
Libs: -L${libdir} -lpcre2-32@LIB_POSTFIX@
Libs.private: @PTHREAD_CFLAGS@ @PTHREAD_LIBS@
Cflags: -I${includedir} @PCRE2_STATIC_CFLAG@

13
Kha/Backends/Kore-hxcpp/khacpp/project/thirdparty/pcre2-10.42-16/libpcre2-8.pc.in vendored Normal file
View File

@ -0,0 +1,13 @@
# Package Information for pkg-config
prefix=@prefix@
exec_prefix=@exec_prefix@
libdir=@libdir@
includedir=@includedir@
Name: libpcre2-8
Description: PCRE2 - Perl compatible regular expressions C library (2nd API) with 8 bit character support
Version: @PACKAGE_VERSION@
Libs: -L${libdir} -lpcre2-8@LIB_POSTFIX@
Libs.private: @PTHREAD_CFLAGS@ @PTHREAD_LIBS@
Cflags: -I${includedir} @PCRE2_STATIC_CFLAG@

13
Kha/Backends/Kore-hxcpp/khacpp/project/thirdparty/pcre2-10.42-16/libpcre2-posix.pc.in vendored Normal file
View File

@ -0,0 +1,13 @@
# Package Information for pkg-config
prefix=@prefix@
exec_prefix=@exec_prefix@
libdir=@libdir@
includedir=@includedir@
Name: libpcre2-posix
Description: Posix compatible interface to libpcre2-8
Version: @PACKAGE_VERSION@
Libs: -L${libdir} -lpcre2-posix@LIB_POSTFIX@
Cflags: -I${includedir} @PCRE2_STATIC_CFLAG@
Requires.private: libpcre2-8

309
Kha/Backends/Kore-hxcpp/khacpp/project/thirdparty/pcre2-10.42-16/m4/ax_pthread.m4 vendored Normal file
View File

@ -0,0 +1,309 @@
# ===========================================================================
# http://www.gnu.org/software/autoconf-archive/ax_pthread.html
# ===========================================================================
#
# SYNOPSIS
#
# AX_PTHREAD([ACTION-IF-FOUND[, ACTION-IF-NOT-FOUND]])
#
# DESCRIPTION
#
# This macro figures out how to build C programs using POSIX threads. It
# sets the PTHREAD_LIBS output variable to the threads library and linker
# flags, and the PTHREAD_CFLAGS output variable to any special C compiler
# flags that are needed. (The user can also force certain compiler
# flags/libs to be tested by setting these environment variables.)
#
# Also sets PTHREAD_CC to any special C compiler that is needed for
# multi-threaded programs (defaults to the value of CC otherwise). (This
# is necessary on AIX to use the special cc_r compiler alias.)
#
# NOTE: You are assumed to not only compile your program with these flags,
# but also link it with them as well. e.g. you should link with
# $PTHREAD_CC $CFLAGS $PTHREAD_CFLAGS $LDFLAGS ... $PTHREAD_LIBS $LIBS
#
# If you are only building threads programs, you may wish to use these
# variables in your default LIBS, CFLAGS, and CC:
#
# LIBS="$PTHREAD_LIBS $LIBS"
# CFLAGS="$CFLAGS $PTHREAD_CFLAGS"
# CC="$PTHREAD_CC"
#
# In addition, if the PTHREAD_CREATE_JOINABLE thread-attribute constant
# has a nonstandard name, defines PTHREAD_CREATE_JOINABLE to that name
# (e.g. PTHREAD_CREATE_UNDETACHED on AIX).
#
# Also HAVE_PTHREAD_PRIO_INHERIT is defined if pthread is found and the
# PTHREAD_PRIO_INHERIT symbol is defined when compiling with
# PTHREAD_CFLAGS.
#
# ACTION-IF-FOUND is a list of shell commands to run if a threads library
# is found, and ACTION-IF-NOT-FOUND is a list of commands to run it if it
# is not found. If ACTION-IF-FOUND is not specified, the default action
# will define HAVE_PTHREAD.
#
# Please let the authors know if this macro fails on any platform, or if
# you have any other suggestions or comments. This macro was based on work
# by SGJ on autoconf scripts for FFTW (http://www.fftw.org/) (with help
# from M. Frigo), as well as ac_pthread and hb_pthread macros posted by
# Alejandro Forero Cuervo to the autoconf macro repository. We are also
# grateful for the helpful feedback of numerous users.
#
# Updated for Autoconf 2.68 by Daniel Richard G.
#
# LICENSE
#
# Copyright (c) 2008 Steven G. Johnson <stevenj@alum.mit.edu>
# Copyright (c) 2011 Daniel Richard G. <skunk@iSKUNK.ORG>
#
# This program is free software: you can redistribute it and/or modify it
# under the terms of the GNU General Public License as published by the
# Free Software Foundation, either version 3 of the License, or (at your
# option) any later version.
#
# This program is distributed in the hope that it will be useful, but
# WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General
# Public License for more details.
#
# You should have received a copy of the GNU General Public License along
# with this program. If not, see <http://www.gnu.org/licenses/>.
#
# As a special exception, the respective Autoconf Macro's copyright owner
# gives unlimited permission to copy, distribute and modify the configure
# scripts that are the output of Autoconf when processing the Macro. You
# need not follow the terms of the GNU General Public License when using
# or distributing such scripts, even though portions of the text of the
# Macro appear in them. The GNU General Public License (GPL) does govern
# all other use of the material that constitutes the Autoconf Macro.
#
# This special exception to the GPL applies to versions of the Autoconf
# Macro released by the Autoconf Archive. When you make and distribute a
# modified version of the Autoconf Macro, you may extend this special
# exception to the GPL to apply to your modified version as well.
#serial 18
AU_ALIAS([ACX_PTHREAD], [AX_PTHREAD])
AC_DEFUN([AX_PTHREAD], [
AC_REQUIRE([AC_CANONICAL_HOST])
AC_LANG_PUSH([C])
ax_pthread_ok=no
# We used to check for pthread.h first, but this fails if pthread.h
# requires special compiler flags (e.g. on True64 or Sequent).
# It gets checked for in the link test anyway.
# First of all, check if the user has set any of the PTHREAD_LIBS,
# etcetera environment variables, and if threads linking works using
# them:
if test x"$PTHREAD_LIBS$PTHREAD_CFLAGS" != x; then
save_CFLAGS="$CFLAGS"
CFLAGS="$CFLAGS $PTHREAD_CFLAGS"
save_LIBS="$LIBS"
LIBS="$PTHREAD_LIBS $LIBS"
AC_MSG_CHECKING([for pthread_join in LIBS=$PTHREAD_LIBS with CFLAGS=$PTHREAD_CFLAGS])
AC_TRY_LINK_FUNC(pthread_join, ax_pthread_ok=yes)
AC_MSG_RESULT($ax_pthread_ok)
if test x"$ax_pthread_ok" = xno; then
PTHREAD_LIBS=""
PTHREAD_CFLAGS=""
fi
LIBS="$save_LIBS"
CFLAGS="$save_CFLAGS"
fi
# We must check for the threads library under a number of different
# names; the ordering is very important because some systems
# (e.g. DEC) have both -lpthread and -lpthreads, where one of the
# libraries is broken (non-POSIX).
# Create a list of thread flags to try. Items starting with a "-" are
# C compiler flags, and other items are library names, except for "none"
# which indicates that we try without any flags at all, and "pthread-config"
# which is a program returning the flags for the Pth emulation library.
ax_pthread_flags="pthreads none -Kthread -kthread lthread -pthread -pthreads -mthreads pthread --thread-safe -mt pthread-config"
# The ordering *is* (sometimes) important. Some notes on the
# individual items follow:
# pthreads: AIX (must check this before -lpthread)
# none: in case threads are in libc; should be tried before -Kthread and
# other compiler flags to prevent continual compiler warnings
# -Kthread: Sequent (threads in libc, but -Kthread needed for pthread.h)
# -kthread: FreeBSD kernel threads (preferred to -pthread since SMP-able)
# lthread: LinuxThreads port on FreeBSD (also preferred to -pthread)
# -pthread: Linux/gcc (kernel threads), BSD/gcc (userland threads)
# -pthreads: Solaris/gcc
# -mthreads: Mingw32/gcc, Lynx/gcc
# -mt: Sun Workshop C (may only link SunOS threads [-lthread], but it
# doesn't hurt to check since this sometimes defines pthreads too;
# also defines -D_REENTRANT)
# ... -mt is also the pthreads flag for HP/aCC
# pthread: Linux, etcetera
# --thread-safe: KAI C++
# pthread-config: use pthread-config program (for GNU Pth library)
case ${host_os} in
solaris*)
# On Solaris (at least, for some versions), libc contains stubbed
# (non-functional) versions of the pthreads routines, so link-based
# tests will erroneously succeed. (We need to link with -pthreads/-mt/
# -lpthread.) (The stubs are missing pthread_cleanup_push, or rather
# a function called by this macro, so we could check for that, but
# who knows whether they'll stub that too in a future libc.) So,
# we'll just look for -pthreads and -lpthread first:
ax_pthread_flags="-pthreads pthread -mt -pthread $ax_pthread_flags"
;;
darwin*)
ax_pthread_flags="-pthread $ax_pthread_flags"
;;
esac
if test x"$ax_pthread_ok" = xno; then
for flag in $ax_pthread_flags; do
case $flag in
none)
AC_MSG_CHECKING([whether pthreads work without any flags])
;;
-*)
AC_MSG_CHECKING([whether pthreads work with $flag])
PTHREAD_CFLAGS="$flag"
;;
pthread-config)
AC_CHECK_PROG(ax_pthread_config, pthread-config, yes, no)
if test x"$ax_pthread_config" = xno; then continue; fi
PTHREAD_CFLAGS="`pthread-config --cflags`"
PTHREAD_LIBS="`pthread-config --ldflags` `pthread-config --libs`"
;;
*)
AC_MSG_CHECKING([for the pthreads library -l$flag])
PTHREAD_LIBS="-l$flag"
;;
esac
save_LIBS="$LIBS"
save_CFLAGS="$CFLAGS"
LIBS="$PTHREAD_LIBS $LIBS"
CFLAGS="$CFLAGS $PTHREAD_CFLAGS"
# Check for various functions. We must include pthread.h,
# since some functions may be macros. (On the Sequent, we
# need a special flag -Kthread to make this header compile.)
# We check for pthread_join because it is in -lpthread on IRIX
# while pthread_create is in libc. We check for pthread_attr_init
# due to DEC craziness with -lpthreads. We check for
# pthread_cleanup_push because it is one of the few pthread
# functions on Solaris that doesn't have a non-functional libc stub.
# We try pthread_create on general principles.
AC_LINK_IFELSE([AC_LANG_PROGRAM([#include <pthread.h>
static void routine(void *a) { a = 0; }
static void *start_routine(void *a) { return a; }],
[pthread_t th; pthread_attr_t attr;
pthread_create(&th, 0, start_routine, 0);
pthread_join(th, 0);
pthread_attr_init(&attr);
pthread_cleanup_push(routine, 0);
pthread_cleanup_pop(0) /* ; */])],
[ax_pthread_ok=yes],
[])
LIBS="$save_LIBS"
CFLAGS="$save_CFLAGS"
AC_MSG_RESULT($ax_pthread_ok)
if test "x$ax_pthread_ok" = xyes; then
break;
fi
PTHREAD_LIBS=""
PTHREAD_CFLAGS=""
done
fi
# Various other checks:
if test "x$ax_pthread_ok" = xyes; then
save_LIBS="$LIBS"
LIBS="$PTHREAD_LIBS $LIBS"
save_CFLAGS="$CFLAGS"
CFLAGS="$CFLAGS $PTHREAD_CFLAGS"
# Detect AIX lossage: JOINABLE attribute is called UNDETACHED.
AC_MSG_CHECKING([for joinable pthread attribute])
attr_name=unknown
for attr in PTHREAD_CREATE_JOINABLE PTHREAD_CREATE_UNDETACHED; do
AC_LINK_IFELSE([AC_LANG_PROGRAM([#include <pthread.h>],
[int attr = $attr; return attr /* ; */])],
[attr_name=$attr; break],
[])
done
AC_MSG_RESULT($attr_name)
if test "$attr_name" != PTHREAD_CREATE_JOINABLE; then
AC_DEFINE_UNQUOTED(PTHREAD_CREATE_JOINABLE, $attr_name,
[Define to necessary symbol if this constant
uses a non-standard name on your system.])
fi
AC_MSG_CHECKING([if more special flags are required for pthreads])
flag=no
case ${host_os} in
aix* | freebsd* | darwin*) flag="-D_THREAD_SAFE";;
osf* | hpux*) flag="-D_REENTRANT";;
solaris*)
if test "$GCC" = "yes"; then
flag="-D_REENTRANT"
else
flag="-mt -D_REENTRANT"
fi
;;
esac
AC_MSG_RESULT(${flag})
if test "x$flag" != xno; then
PTHREAD_CFLAGS="$flag $PTHREAD_CFLAGS"
fi
AC_CACHE_CHECK([for PTHREAD_PRIO_INHERIT],
ax_cv_PTHREAD_PRIO_INHERIT, [
AC_LINK_IFELSE([
AC_LANG_PROGRAM([[#include <pthread.h>]], [[int i = PTHREAD_PRIO_INHERIT;]])],
[ax_cv_PTHREAD_PRIO_INHERIT=yes],
[ax_cv_PTHREAD_PRIO_INHERIT=no])
])
AS_IF([test "x$ax_cv_PTHREAD_PRIO_INHERIT" = "xyes"],
AC_DEFINE([HAVE_PTHREAD_PRIO_INHERIT], 1, [Have PTHREAD_PRIO_INHERIT.]))
LIBS="$save_LIBS"
CFLAGS="$save_CFLAGS"
# More AIX lossage: must compile with xlc_r or cc_r
if test x"$GCC" != xyes; then
AC_CHECK_PROGS(PTHREAD_CC, xlc_r cc_r, ${CC})
else
PTHREAD_CC=$CC
fi
else
PTHREAD_CC="$CC"
fi
AC_SUBST(PTHREAD_LIBS)
AC_SUBST(PTHREAD_CFLAGS)
AC_SUBST(PTHREAD_CC)
# Finally, execute ACTION-IF-FOUND/ACTION-IF-NOT-FOUND:
if test x"$ax_pthread_ok" = xyes; then
ifelse([$1],,AC_DEFINE(HAVE_PTHREAD,1,[Define if you have POSIX threads libraries and header files.]),[$1])
:
else
ax_pthread_ok=no
$2
fi
AC_LANG_POP
])dnl AX_PTHREAD

87
Kha/Backends/Kore-hxcpp/khacpp/project/thirdparty/pcre2-10.42-16/m4/pcre2_visibility.m4 vendored Normal file
View File

@ -0,0 +1,87 @@
# visibility.m4 serial 4 (gettext-0.18.2)
dnl Copyright (C) 2005, 2008, 2010-2011 Free Software Foundation, Inc.
dnl This file is free software; the Free Software Foundation
dnl gives unlimited permission to copy and/or distribute it,
dnl with or without modifications, as long as this notice is preserved.
dnl From Bruno Haible.
dnl Tests whether the compiler supports the command-line option
dnl -fvisibility=hidden and the function and variable attributes
dnl __attribute__((__visibility__("hidden"))) and
dnl __attribute__((__visibility__("default"))).
dnl Does *not* test for __visibility__("protected") - which has tricky
dnl semantics (see the 'vismain' test in glibc) and does not exist e.g. on
dnl MacOS X.
dnl Does *not* test for __visibility__("internal") - which has processor
dnl dependent semantics.
dnl Does *not* test for #pragma GCC visibility push(hidden) - which is
dnl "really only recommended for legacy code".
dnl Set the variable CFLAG_VISIBILITY.
dnl Defines and sets the variable HAVE_VISIBILITY.
dnl Modified to fit with PCRE build environment by Cristian Rodríguez.
dnl Adjusted for PCRE2 by PH
AC_DEFUN([PCRE2_VISIBILITY],
[
AC_REQUIRE([AC_PROG_CC])
VISIBILITY_CFLAGS=
VISIBILITY_CXXFLAGS=
HAVE_VISIBILITY=0
if test -n "$GCC"; then
dnl First, check whether -Werror can be added to the command line, or
dnl whether it leads to an error because of some other option that the
dnl user has put into $CC $CFLAGS $CPPFLAGS.
AC_MSG_CHECKING([whether the -Werror option is usable])
AC_CACHE_VAL([pcre2_cv_cc_vis_werror], [
pcre2_save_CFLAGS="$CFLAGS"
CFLAGS="$CFLAGS -Werror"
AC_COMPILE_IFELSE(
[AC_LANG_PROGRAM([[]], [[]])],
[pcre2_cv_cc_vis_werror=yes],
[pcre2_cv_cc_vis_werror=no])
CFLAGS="$pcre2_save_CFLAGS"])
AC_MSG_RESULT([$pcre2_cv_cc_vis_werror])
dnl Now check whether visibility declarations are supported.
AC_MSG_CHECKING([for simple visibility declarations])
AC_CACHE_VAL([pcre2_cv_cc_visibility], [
pcre2_save_CFLAGS="$CFLAGS"
CFLAGS="$CFLAGS -fvisibility=hidden"
dnl We use the option -Werror and a function dummyfunc, because on some
dnl platforms (Cygwin 1.7) the use of -fvisibility triggers a warning
dnl "visibility attribute not supported in this configuration; ignored"
dnl at the first function definition in every compilation unit, and we
dnl don't want to use the option in this case.
if test $pcre2_cv_cc_vis_werror = yes; then
CFLAGS="$CFLAGS -Werror"
fi
AC_COMPILE_IFELSE(
[AC_LANG_PROGRAM(
[[extern __attribute__((__visibility__("hidden"))) int hiddenvar;
extern __attribute__((__visibility__("default"))) int exportedvar;
extern __attribute__((__visibility__("hidden"))) int hiddenfunc (void);
extern __attribute__((__visibility__("default"))) int exportedfunc (void);
void dummyfunc (void) {}
]],
[[]])],
[pcre2_cv_cc_visibility=yes],
[pcre2_cv_cc_visibility=no])
CFLAGS="$pcre2_save_CFLAGS"])
AC_MSG_RESULT([$pcre2_cv_cc_visibility])
if test $pcre2_cv_cc_visibility = yes; then
VISIBILITY_CFLAGS="-fvisibility=hidden"
VISIBILITY_CXXFLAGS="-fvisibility=hidden -fvisibility-inlines-hidden"
HAVE_VISIBILITY=1
AC_DEFINE(PCRE2_EXP_DECL, [extern __attribute__ ((visibility ("default")))], [to make a symbol visible])
AC_DEFINE(PCRE2_EXP_DEFN, [__attribute__ ((visibility ("default")))], [to make a symbol visible])
AC_DEFINE(PCRE2POSIX_EXP_DECL, [extern __attribute__ ((visibility ("default")))], [to make a symbol visible])
AC_DEFINE(PCRE2POSIX_EXP_DEFN, [extern __attribute__ ((visibility ("default")))], [to make a symbol visible])
fi
fi
AC_SUBST([VISIBILITY_CFLAGS])
AC_SUBST([VISIBILITY_CXXFLAGS])
AC_SUBST([HAVE_VISIBILITY])
AC_DEFINE_UNQUOTED([HAVE_VISIBILITY], [$HAVE_VISIBILITY],
[Define to 1 if the compiler supports simple visibility declarations.])
])

355
Kha/Backends/Kore-hxcpp/khacpp/project/thirdparty/pcre2-10.42-16/maint/GenerateCommon.py vendored Normal file
View File

@ -0,0 +1,355 @@
#! /usr/bin/python
# PCRE2 UNICODE PROPERTY SUPPORT
# ------------------------------
# This file is a Python module containing common lists and functions for the
# GenerateXXX scripts that create various.c and .h files from Unicode data
# files. It was created as part of a re-organizaton of these scripts in
# December 2021.
import re
# ---------------------------------------------------------------------------
# DATA LISTS
# ---------------------------------------------------------------------------
# BIDI classes in the DerivedBidiClass.txt file, with comments.
bidi_classes = [
'AL', 'Arabic letter',
'AN', 'Arabic number',
'B', 'Paragraph separator',
'BN', 'Boundary neutral',
'CS', 'Common separator',
'EN', 'European number',
'ES', 'European separator',
'ET', 'European terminator',
'FSI', 'First strong isolate',
'L', 'Left to right',
'LRE', 'Left to right embedding',
'LRI', 'Left to right isolate',
'LRO', 'Left to right override',
'NSM', 'Non-spacing mark',
'ON', 'Other neutral',
'PDF', 'Pop directional format',
'PDI', 'Pop directional isolate',
'R', 'Right to left',
'RLE', 'Right to left embedding',
'RLI', 'Right to left isolate',
'RLO', 'Right to left override',
'S', 'Segment separator',
'WS', 'White space'
]
# Particular category property names, with comments. NOTE: If ever this list
# is changed, the table called "catposstab" in the pcre2_auto_possess.c file
# must be edited to keep in step.
category_names = [
'Cc', 'Control',
'Cf', 'Format',
'Cn', 'Unassigned',
'Co', 'Private use',
'Cs', 'Surrogate',
'Ll', 'Lower case letter',
'Lm', 'Modifier letter',
'Lo', 'Other letter',
'Lt', 'Title case letter',
'Lu', 'Upper case letter',
'Mc', 'Spacing mark',
'Me', 'Enclosing mark',
'Mn', 'Non-spacing mark',
'Nd', 'Decimal number',
'Nl', 'Letter number',
'No', 'Other number',
'Pc', 'Connector punctuation',
'Pd', 'Dash punctuation',
'Pe', 'Close punctuation',
'Pf', 'Final punctuation',
'Pi', 'Initial punctuation',
'Po', 'Other punctuation',
'Ps', 'Open punctuation',
'Sc', 'Currency symbol',
'Sk', 'Modifier symbol',
'Sm', 'Mathematical symbol',
'So', 'Other symbol',
'Zl', 'Line separator',
'Zp', 'Paragraph separator',
'Zs', 'Space separator'
]
# The Extended_Pictographic property is not found in the file where all the
# others are (GraphemeBreakProperty.txt). It comes from the emoji-data.txt
# file, but we list it here so that the name has the correct index value.
break_properties = [
'CR', ' 0',
'LF', ' 1',
'Control', ' 2',
'Extend', ' 3',
'Prepend', ' 4',
'SpacingMark', ' 5',
'L', ' 6 Hangul syllable type L',
'V', ' 7 Hangul syllable type V',
'T', ' 8 Hangul syllable type T',
'LV', ' 9 Hangul syllable type LV',
'LVT', '10 Hangul syllable type LVT',
'Regional_Indicator', '11',
'Other', '12',
'ZWJ', '13',
'Extended_Pictographic', '14'
]
# List of files from which the names of Boolean properties are obtained, along
# with a list of regex patterns for properties to be ignored, and a list of
# extra pattern names to add.
bool_propsfiles = ['PropList.txt', 'DerivedCoreProperties.txt', 'emoji-data.txt']
bool_propsignore = [r'^Other_', r'^Hyphen$']
bool_propsextras = ['ASCII', 'Bidi_Mirrored']
# ---------------------------------------------------------------------------
# GET BOOLEAN PROPERTY NAMES
# ---------------------------------------------------------------------------
# Get a list of Boolean property names from a number of files.
def getbpropslist():
bplist = []
bplast = ""
for filename in bool_propsfiles:
try:
file = open('Unicode.tables/' + filename, 'r')
except IOError:
print(f"** Couldn't open {'Unicode.tables/' + filename}\n")
sys.exit(1)
for line in file:
line = re.sub(r'#.*', '', line)
data = list(map(str.strip, line.split(';')))
if len(data) <= 1 or data[1] == bplast:
continue
bplast = data[1]
for pat in bool_propsignore:
if re.match(pat, bplast) != None:
break
else:
bplist.append(bplast)
file.close()
bplist.extend(bool_propsextras)
bplist.sort()
return bplist
bool_properties = getbpropslist()
bool_props_list_item_size = (len(bool_properties) + 31) // 32
# ---------------------------------------------------------------------------
# COLLECTING PROPERTY NAMES AND ALIASES
# ---------------------------------------------------------------------------
script_names = ['Unknown']
abbreviations = {}
def collect_property_names():
global script_names
global abbreviations
names_re = re.compile(r'^[0-9A-F]{4,6}(?:\.\.[0-9A-F]{4,6})? +; ([A-Za-z_]+) #')
last_script_name = ""
with open("Unicode.tables/Scripts.txt") as f:
for line in f:
match_obj = names_re.match(line)
if match_obj == None or match_obj.group(1) == last_script_name:
continue
last_script_name = match_obj.group(1)
script_names.append(last_script_name)
# Sometimes there is comment in the line
# so splitting around semicolon is not enough
value_alias_re = re.compile(r' *([A-Za-z_]+) *; *([A-Za-z_]+) *; *([A-Za-z_]+)(?: *; *([A-Za-z_ ]+))?')
with open("Unicode.tables/PropertyValueAliases.txt") as f:
for line in f:
match_obj = value_alias_re.match(line)
if match_obj == None:
continue
if match_obj.group(1) == "sc":
if match_obj.group(2) == match_obj.group(3):
abbreviations[match_obj.group(3)] = ()
elif match_obj.group(4) == None:
abbreviations[match_obj.group(3)] = (match_obj.group(2),)
else:
abbreviations[match_obj.group(3)] = (match_obj.group(2), match_obj.group(4))
# We can also collect Boolean property abbreviations into the same dictionary
bin_alias_re = re.compile(r' *([A-Za-z_]+) *; *([A-Za-z_]+)(?: *; *([A-Za-z_]+))?')
with open("Unicode.tables/PropertyAliases.txt") as f:
for line in f:
match_obj = bin_alias_re.match(line)
if match_obj == None:
continue
if match_obj.group(2) in bool_properties:
if match_obj.group(3) == None:
abbreviations[match_obj.group(2)] = (match_obj.group(1),)
else:
abbreviations[match_obj.group(2)] = (match_obj.group(1), match_obj.group(3))
collect_property_names()
# ---------------------------------------------------------------------------
# REORDERING SCRIPT NAMES
# ---------------------------------------------------------------------------
script_abbrevs = []
def reorder_scripts():
global script_names
global script_abbrevs
global abbreviations
for name in script_names:
abbrevs = abbreviations[name]
script_abbrevs.append(name if len(abbrevs) == 0 else abbrevs[0])
extended_script_abbrevs = set()
with open("Unicode.tables/ScriptExtensions.txt") as f:
names_re = re.compile(r'^[0-9A-F]{4,6}(?:\.\.[0-9A-F]{4,6})? +; ([A-Za-z_ ]+) #')
for line in f:
match_obj = names_re.match(line)
if match_obj == None:
continue
for name in match_obj.group(1).split(" "):
extended_script_abbrevs.add(name)
new_script_names = []
new_script_abbrevs = []
for idx, abbrev in enumerate(script_abbrevs):
if abbrev in extended_script_abbrevs:
new_script_names.append(script_names[idx])
new_script_abbrevs.append(abbrev)
for idx, abbrev in enumerate(script_abbrevs):
if abbrev not in extended_script_abbrevs:
new_script_names.append(script_names[idx])
new_script_abbrevs.append(abbrev)
script_names = new_script_names
script_abbrevs = new_script_abbrevs
reorder_scripts()
script_list_item_size = (script_names.index('Unknown') + 31) // 32
# ---------------------------------------------------------------------------
# DERIVED LISTS
# ---------------------------------------------------------------------------
# Create general character property names from the first letters of the
# particular categories.
gcn_set = set(category_names[i][0] for i in range(0, len(category_names), 2))
general_category_names = list(gcn_set)
general_category_names.sort()
# ---------------------------------------------------------------------------
# FUNCTIONS
# ---------------------------------------------------------------------------
import sys
# Open an output file, using the command's argument or a default. Write common
# preliminary header information.
def open_output(default):
if len(sys.argv) > 2:
print('** Too many arguments: just give a file name')
sys.exit(1)
if len(sys.argv) == 2:
output_name = sys.argv[1]
else:
output_name = default
try:
file = open(output_name, "w")
except IOError:
print ("** Couldn't open %s" % output_name)
sys.exit(1)
script_name = sys.argv[0]
i = script_name.rfind('/')
if i >= 0:
script_name = script_name[i+1:]
file.write("""\
/*************************************************
* Perl-Compatible Regular Expressions *
*************************************************/
/* PCRE is a library of functions to support regular expressions whose syntax
and semantics are as close as possible to those of the Perl 5 language.
Written by Philip Hazel
Original API code Copyright (c) 1997-2012 University of Cambridge
New API code Copyright (c) 2016-2022 University of Cambridge
This module is auto-generated from Unicode data files. DO NOT EDIT MANUALLY!
""")
file.write("Instead, modify the maint/%s script and run it to generate\n"
"a new version of this code.\n\n" % script_name)
file.write("""\
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
modification, are permitted provided that the following conditions are met:
* Redistributions of source code must retain the above copyright notice,
this list of conditions and the following disclaimer.
* Redistributions in binary form must reproduce the above copyright
notice, this list of conditions and the following disclaimer in the
documentation and/or other materials provided with the distribution.
* Neither the name of the University of Cambridge nor the names of its
contributors may be used to endorse or promote products derived from
this software without specific prior written permission.
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
POSSIBILITY OF SUCH DAMAGE.
-----------------------------------------------------------------------------
*/
\n""")
return file
# End of UcpCommon.py

188
Kha/Backends/Kore-hxcpp/khacpp/project/thirdparty/pcre2-10.42-16/maint/GenerateTest26.py vendored Normal file
View File

@ -0,0 +1,188 @@
#! /usr/bin/python
# PCRE2 UNICODE PROPERTY SUPPORT
# ------------------------------
#
# This file auto-generates unicode property tests and their expected output.
# It is recommended to re-run this generator after the unicode files are
# updated. The names of the generated files are `testinput26` and `testoutput26`
import re
import sys
from GenerateCommon import \
script_names, \
script_abbrevs
def write_both(text):
input_file.write(text)
output_file.write(text)
def to_string_char(ch_idx):
if ch_idx < 128:
if ch_idx < 16:
return "\\x{0%x}" % ch_idx
if ch_idx >= 32:
return chr(ch_idx)
return "\\x{%x}" % ch_idx
output_directory = ""
if len(sys.argv) > 2:
print('** Too many arguments: just give a directory name')
sys.exit(1)
if len(sys.argv) == 2:
output_directory = sys.argv[1]
if not output_directory.endswith("/"):
output_directory += "/"
try:
input_file = open(output_directory + "testinput26", "w")
output_file = open(output_directory + "testoutput26", "w")
except IOError:
print ("** Couldn't open output files")
sys.exit(1)
write_both("# These tests are generated by maint/GenerateTest26.py, do not edit.\n\n")
# ---------------------------------------------------------------------------
# UNICODE SCRIPT EXTENSION TESTS
# ---------------------------------------------------------------------------
write_both("# Unicode Script Extension tests.\n\n")
def gen_script_tests():
script_data = [None] * len(script_names)
char_data = [None] * 0x110000
property_re = re.compile("^([0-9A-F]{4,6})(?:\\.\\.([0-9A-F]{4,6}))? +; ([A-Za-z_ ]+) #")
prev_name = ""
script_idx = -1
with open("Unicode.tables/Scripts.txt") as f:
for line in f:
match_obj = property_re.match(line)
if match_obj == None:
continue
name = match_obj.group(3)
if name != prev_name:
script_idx = script_names.index(name)
prev_name = name
low = int(match_obj.group(1), 16)
high = low
char_data[low] = name
if match_obj.group(2) != None:
high = int(match_obj.group(2), 16)
for idx in range(low + 1, high + 1):
char_data[idx] = name
if script_data[script_idx] == None:
script_data[script_idx] = [low, None, None, None, None]
script_data[script_idx][1] = high
extended_script_indicies = {}
with open("Unicode.tables/ScriptExtensions.txt") as f:
for line in f:
match_obj = property_re.match(line)
if match_obj == None:
continue
low = int(match_obj.group(1), 16)
high = low
if match_obj.group(2) != None:
high = int(match_obj.group(2), 16)
for abbrev in match_obj.group(3).split(" "):
if abbrev not in extended_script_indicies:
idx = script_abbrevs.index(abbrev)
extended_script_indicies[abbrev] = idx
rec = script_data[idx]
rec[2] = low
rec[3] = high
else:
idx = extended_script_indicies[abbrev]
rec = script_data[idx]
if rec[2] > low:
rec[2] = low
if rec[3] < high:
rec[3] = high
if rec[4] == None:
name = script_names[idx]
for idx in range(low, high + 1):
if char_data[idx] != name:
rec[4] = idx
break
long_property_name = False
for idx, rec in enumerate(script_data):
script_name = script_names[idx]
if script_name == "Unknown":
continue
script_abbrev = script_abbrevs[idx]
write_both("# Base script check\n")
write_both("/^\\p{sc=%s}/utf\n" % script_name)
write_both(" %s\n" % to_string_char(rec[0]))
output_file.write(" 0: %s\n" % to_string_char(rec[0]))
write_both("\n")
write_both("/^\\p{Script=%s}/utf\n" % script_abbrev)
write_both(" %s\n" % to_string_char(rec[1]))
output_file.write(" 0: %s\n" % to_string_char(rec[1]))
write_both("\n")
if rec[2] != None:
property_name = "scx"
if long_property_name:
property_name = "Script_Extensions"
write_both("# Script extension check\n")
write_both("/^\\p{%s}/utf\n" % script_name)
write_both(" %s\n" % to_string_char(rec[2]))
output_file.write(" 0: %s\n" % to_string_char(rec[2]))
write_both("\n")
write_both("/^\\p{%s=%s}/utf\n" % (property_name, script_abbrev))
write_both(" %s\n" % to_string_char(rec[3]))
output_file.write(" 0: %s\n" % to_string_char(rec[3]))
write_both("\n")
long_property_name = not long_property_name
if rec[4] != None:
write_both("# Script extension only character\n")
write_both("/^\\p{%s}/utf\n" % script_name)
write_both(" %s\n" % to_string_char(rec[4]))
output_file.write(" 0: %s\n" % to_string_char(rec[4]))
write_both("\n")
write_both("/^\\p{sc=%s}/utf\n" % script_name)
write_both(" %s\n" % to_string_char(rec[4]))
output_file.write("No match\n")
write_both("\n")
else:
print("External character has not found for %s" % script_name)
high = rec[1]
if rec[3] != None and rec[3] > rec[1]:
high = rec[3]
write_both("# Character not in script\n")
write_both("/^\\p{%s}/utf\n" % script_name)
write_both(" %s\n" % to_string_char(high + 1))
output_file.write("No match\n")
write_both("\n")
gen_script_tests()
write_both("# End of testinput26\n")

923
Kha/Backends/Kore-hxcpp/khacpp/project/thirdparty/pcre2-10.42-16/maint/GenerateUcd.py vendored Normal file
View File

@ -0,0 +1,923 @@
#! /usr/bin/python
# PCRE2 UNICODE PROPERTY SUPPORT
# ------------------------------
#
# This script generates the pcre2_ucd.c file from Unicode data files. This is
# the compressed Unicode property data used by PCRE2. The script was created in
# December 2021 as part of the Unicode data generation refactoring. It is
# basically a re-working of the MultiStage2.py script that was submitted to the
# PCRE project by Peter Kankowski in 2008 as part of a previous upgrading of
# Unicode property support. A number of extensions have since been added. The
# main difference in the 2021 upgrade (apart from comments and layout) is that
# the data tables (e.g. list of script names) are now listed in or generated by
# a separate Python module that is shared with the other Generate scripts.
#
# This script must be run in the "maint" directory. It requires the following
# Unicode data tables: BidiMirrorring.txt, CaseFolding.txt,
# DerivedBidiClass.txt, DerivedCoreProperties.txt, DerivedGeneralCategory.txt,
# GraphemeBreakProperty.txt, PropList.txt, PropertyAliases.txt,
# PropertyValueAliases.txt, ScriptExtensions.txt, Scripts.txt, and
# emoji-data.txt. These must be in the Unicode.tables subdirectory.
#
# The emoji-data.txt file is found in the "emoji" subdirectory even though it
# is technically part of a different (but coordinated) standard as shown
# in files associated with Unicode Technical Standard #51 ("Unicode Emoji"),
# for example:
#
# http://unicode.org/Public/emoji/13.0/ReadMe.txt
#
# DerivedBidiClass.txt and DerivedGeneralCategory.txt are in the "extracted"
# subdirectory of the Unicode database (UCD) on the Unicode web site;
# GraphemeBreakProperty.txt is in the "auxiliary" subdirectory. The other files
# are in the top-level UCD directory.
#
# -----------------------------------------------------------------------------
# Minor modifications made to the original script:
# Added #! line at start
# Removed tabs
# Made it work with Python 2.4 by rewriting two statements that needed 2.5
# Consequent code tidy
# Adjusted data file names to take from the Unicode.tables directory
# Adjusted global table names by prefixing _pcre_.
# Commented out stuff relating to the casefolding table, which isn't used;
# removed completely in 2012.
# Corrected size calculation
# Add #ifndef SUPPORT_UCP to use dummy tables when no UCP support is needed.
# Update for PCRE2: name changes, and SUPPORT_UCP is abolished.
#
# Major modifications made to the original script:
# Added code to add a grapheme break property field to records.
#
# Added code to search for sets of more than two characters that must match
# each other caselessly. A new table is output containing these sets, and
# offsets into the table are added to the main output records. This new
# code scans CaseFolding.txt instead of UnicodeData.txt, which is no longer
# used.
#
# Update for Python3:
# . Processed with 2to3, but that didn't fix everything
# . Changed string.strip to str.strip
# . Added encoding='utf-8' to the open() call
# . Inserted 'int' before blocksize/ELEMS_PER_LINE because an int is
# required and the result of the division is a float
#
# Added code to scan the emoji-data.txt file to find the Extended Pictographic
# property, which is used by PCRE2 as a grapheme breaking property. This was
# done when updating to Unicode 11.0.0 (July 2018).
#
# Added code to add a Script Extensions field to records. This has increased
# their size from 8 to 12 bytes, only 10 of which are currently used.
#
# Added code to add a bidi class field to records by scanning the
# DerivedBidiClass.txt and PropList.txt files. This uses one of the two spare
# bytes, so now 11 out of 12 are in use.
#
# 01-March-2010: Updated list of scripts for Unicode 5.2.0
# 30-April-2011: Updated list of scripts for Unicode 6.0.0
# July-2012: Updated list of scripts for Unicode 6.1.0
# 20-August-2012: Added scan of GraphemeBreakProperty.txt and added a new
# field in the record to hold the value. Luckily, the
# structure had a hole in it, so the resulting table is
# not much bigger than before.
# 18-September-2012: Added code for multiple caseless sets. This uses the
# final hole in the structure.
# 30-September-2012: Added RegionalIndicator break property from Unicode 6.2.0
# 13-May-2014: Updated for PCRE2
# 03-June-2014: Updated for Python 3
# 20-June-2014: Updated for Unicode 7.0.0
# 12-August-2014: Updated to put Unicode version into the file
# 19-June-2015: Updated for Unicode 8.0.0
# 02-July-2017: Updated for Unicode 10.0.0
# 03-July-2018: Updated for Unicode 11.0.0
# 07-July-2018: Added code to scan emoji-data.txt for the Extended
# Pictographic property.
# 01-October-2018: Added the 'Unknown' script name
# 03-October-2018: Added new field for Script Extensions
# 27-July-2019: Updated for Unicode 12.1.0
# 10-March-2020: Updated for Unicode 13.0.0
# PCRE2-10.39: Updated for Unicode 14.0.0
# 05-December-2021: Added code to scan DerivedBidiClass.txt for bidi class,
# and also PropList.txt for the Bidi_Control property
# 19-December-2021: Reworked script extensions lists to be bit maps instead
# of zero-terminated lists of script numbers.
# ----------------------------------------------------------------------------
#
# Changes to the refactored script:
#
# 26-December-2021: Refactoring completed
# 10-January-2022: Addition of general Boolean property support
# 12-January-2022: Merge scriptx and bidiclass fields
# 14-January-2022: Enlarge Boolean property offset to 12 bits
#
# ----------------------------------------------------------------------------
#
#
# The main tables generated by this script are used by macros defined in
# pcre2_internal.h. They look up Unicode character properties using short
# sequences of code that contains no branches, which makes for greater speed.
#
# Conceptually, there is a table of records (of type ucd_record), one for each
# Unicode character. Each record contains the script number, script extension
# value, character type, grapheme break type, offset to caseless matching set,
# offset to the character's other case, the bidi class, and offset to bitmap of
# Boolean properties.
#
# A real table covering all Unicode characters would be far too big. It can be
# efficiently compressed by observing that many characters have the same
# record, and many blocks of characters (taking 128 characters in a block) have
# the same set of records as other blocks. This leads to a 2-stage lookup
# process.
#
# This script constructs seven tables. The ucd_caseless_sets table contains
# lists of characters that all match each other caselessly. Each list is
# in order, and is terminated by NOTACHAR (0xffffffff), which is larger than
# any valid character. The first list is empty; this is used for characters
# that are not part of any list.
#
# The ucd_digit_sets table contains the code points of the '9' characters in
# each set of 10 decimal digits in Unicode. This is used to ensure that digits
# in script runs all come from the same set. The first element in the vector
# contains the number of subsequent elements, which are in ascending order.
#
# Scripts are partitioned into two groups. Scripts that appear in at least one
# character's script extension list come first, followed by "Unknown" and then
# all the rest. This sorting is done automatically in the GenerateCommon.py
# script. A script's number is its index in the script_names list.
#
# The ucd_script_sets table contains bitmaps that represent lists of scripts
# for Script Extensions properties. Each bitmap consists of a fixed number of
# unsigned 32-bit numbers, enough to allocate a bit for every script that is
# used in any character's extension list, that is, enough for every script
# whose number is less than ucp_Unknown. A character's script extension value
# in its ucd record is an offset into the ucd_script_sets vector. The first
# bitmap has no bits set; characters that have no script extensions have zero
# as their script extensions value so that they use this map.
#
# The ucd_boolprop_sets table contains bitmaps that represent lists of Boolean
# properties. Each bitmap consists of a fixed number of unsigned 32-bit
# numbers, enough to allocate a bit for each supported Boolean property.
#
# The ucd_records table contains one instance of every unique character record
# that is required. The ucd_stage1 table is indexed by a character's block
# number, which is the character's code point divided by 128, since 128 is the
# size of each block. The result of a lookup in ucd_stage1 a "virtual" block
# number.
#
# The ucd_stage2 table is a table of "virtual" blocks; each block is indexed by
# the offset of a character within its own block, and the result is the index
# number of the required record in the ucd_records vector.
#
# The following examples are correct for the Unicode 14.0.0 database. Future
# updates may make change the actual lookup values.
#
# Example: lowercase "a" (U+0061) is in block 0
# lookup 0 in stage1 table yields 0
# lookup 97 (0x61) in the first table in stage2 yields 35
# record 35 is { 0, 5, 12, 0, -32, 18432, 44 }
# 0 = ucp_Latin => Latin script
# 5 = ucp_Ll => Lower case letter
# 12 = ucp_gbOther => Grapheme break property "Other"
# 0 => Not part of a caseless set
# -32 (-0x20) => Other case is U+0041
# 18432 = 0x4800 => Combined Bidi class + script extension values
# 44 => Offset to Boolean properties
#
# The top 5 bits of the sixth field are the Bidi class, with the rest being the
# script extension value, giving:
#
# 9 = ucp_bidiL => Bidi class left-to-right
# 0 => No special script extension property
#
# Almost all lowercase latin characters resolve to the same record. One or two
# are different because they are part of a multi-character caseless set (for
# example, k, K and the Kelvin symbol are such a set).
#
# Example: hiragana letter A (U+3042) is in block 96 (0x60)
# lookup 96 in stage1 table yields 93
# lookup 66 (0x42) in table 93 in stage2 yields 819
# record 819 is { 20, 7, 12, 0, 0, 18432, 82 }
# 20 = ucp_Hiragana => Hiragana script
# 7 = ucp_Lo => Other letter
# 12 = ucp_gbOther => Grapheme break property "Other"
# 0 => Not part of a caseless set
# 0 => No other case
# 18432 = 0x4800 => Combined Bidi class + script extension values
# 82 => Offset to Boolean properties
#
# The top 5 bits of the sixth field are the Bidi class, with the rest being the
# script extension value, giving:
#
# 9 = ucp_bidiL => Bidi class left-to-right
# 0 => No special script extension property
#
# Example: vedic tone karshana (U+1CD0) is in block 57 (0x39)
# lookup 57 in stage1 table yields 55
# lookup 80 (0x50) in table 55 in stage2 yields 621
# record 621 is { 84, 12, 3, 0, 0, 26762, 96 }
# 84 = ucp_Inherited => Script inherited from predecessor
# 12 = ucp_Mn => Non-spacing mark
# 3 = ucp_gbExtend => Grapheme break property "Extend"
# 0 => Not part of a caseless set
# 0 => No other case
# 26762 = 0x688A => Combined Bidi class + script extension values
# 96 => Offset to Boolean properties
#
# The top 5 bits of the sixth field are the Bidi class, with the rest being the
# script extension value, giving:
#
# 13 = ucp_bidiNSM => Bidi class non-spacing mark
# 138 => Script Extension list offset = 138
#
# At offset 138 in the ucd_script_sets vector we find a bitmap with bits 1, 8,
# 18, and 47 set. This means that this character is expected to be used with
# any of those scripts, which are Bengali, Devanagari, Kannada, and Grantha.
#
# Philip Hazel, last updated 14 January 2022.
##############################################################################
# Import standard modules
import re
import string
import sys
# Import common data lists and functions
from GenerateCommon import \
bidi_classes, \
bool_properties, \
bool_propsfiles, \
bool_props_list_item_size, \
break_properties, \
category_names, \
general_category_names, \
script_abbrevs, \
script_list_item_size, \
script_names, \
open_output
# Some general parameters
MAX_UNICODE = 0x110000
NOTACHAR = 0xffffffff
# ---------------------------------------------------------------------------
# DEFINE FUNCTIONS
# ---------------------------------------------------------------------------
# Parse a line of Scripts.txt, GraphemeBreakProperty.txt, DerivedBidiClass.txt
# or DerivedGeneralCategory.txt
def make_get_names(enum):
return lambda chardata: enum.index(chardata[1])
# Parse a line of CaseFolding.txt
def get_other_case(chardata):
if chardata[1] == 'C' or chardata[1] == 'S':
return int(chardata[2], 16) - int(chardata[0], 16)
return 0
# Parse a line of ScriptExtensions.txt
def get_script_extension(chardata):
global last_script_extension
offset = len(script_lists) * script_list_item_size
if last_script_extension == chardata[1]:
return offset - script_list_item_size
last_script_extension = chardata[1]
script_lists.append(tuple(script_abbrevs.index(abbrev) for abbrev in last_script_extension.split(' ')))
return offset
# Read a whole table in memory, setting/checking the Unicode version
def read_table(file_name, get_value, default_value):
global unicode_version
f = re.match(r'^[^/]+/([^.]+)\.txt$', file_name)
file_base = f.group(1)
version_pat = r"^# " + re.escape(file_base) + r"-(\d+\.\d+\.\d+)\.txt$"
file = open(file_name, 'r', encoding='utf-8')
f = re.match(version_pat, file.readline())
version = f.group(1)
if unicode_version == "":
unicode_version = version
elif unicode_version != version:
print("WARNING: Unicode version differs in %s", file_name, file=sys.stderr)
table = [default_value] * MAX_UNICODE
for line in file:
line = re.sub(r'#.*', '', line)
chardata = list(map(str.strip, line.split(';')))
if len(chardata) <= 1:
continue
value = get_value(chardata)
m = re.match(r'([0-9a-fA-F]+)(\.\.([0-9a-fA-F]+))?$', chardata[0])
char = int(m.group(1), 16)
if m.group(3) is None:
last = char
else:
last = int(m.group(3), 16)
for i in range(char, last + 1):
# It is important not to overwrite a previously set value because in the
# CaseFolding file there are lines to be ignored (returning the default
# value of 0) which often come after a line which has already set data.
if table[i] == default_value:
table[i] = value
file.close()
return table
# Get the smallest possible C language type for the values in a table
def get_type_size(table):
type_size = [("uint8_t", 1), ("uint16_t", 2), ("uint32_t", 4),
("signed char", 1), ("int16_t", 2), ("int32_t", 4)]
limits = [(0, 255), (0, 65535), (0, 4294967295), (-128, 127),
(-32768, 32767), (-2147483648, 2147483647)]
minval = min(table)
maxval = max(table)
for num, (minlimit, maxlimit) in enumerate(limits):
if minlimit <= minval and maxval <= maxlimit:
return type_size[num]
raise OverflowError("Too large to fit into C types")
# Get the total size of a list of tables
def get_tables_size(*tables):
total_size = 0
for table in tables:
type, size = get_type_size(table)
total_size += size * len(table)
return total_size
# Compress a table into the two stages
def compress_table(table, block_size):
blocks = {} # Dictionary for finding identical blocks
stage1 = [] # Stage 1 table contains block numbers (indices into stage 2 table)
stage2 = [] # Stage 2 table contains the blocks with property values
table = tuple(table)
for i in range(0, len(table), block_size):
block = table[i:i+block_size]
start = blocks.get(block)
if start is None:
# Allocate a new block
start = len(stage2) / block_size
stage2 += block
blocks[block] = start
stage1.append(start)
return stage1, stage2
# Output a table
def write_table(table, table_name, block_size = None):
type, size = get_type_size(table)
ELEMS_PER_LINE = 16
s = "const %s %s[] = { /* %d bytes" % (type, table_name, size * len(table))
if block_size:
s += ", block = %d" % block_size
f.write(s + " */\n")
table = tuple(table)
if block_size is None:
fmt = "%3d," * ELEMS_PER_LINE + " /* U+%04X */\n"
mult = MAX_UNICODE / len(table)
for i in range(0, len(table), ELEMS_PER_LINE):
f.write(fmt % (table[i:i+ELEMS_PER_LINE] + (int(i * mult),)))
else:
if block_size > ELEMS_PER_LINE:
el = ELEMS_PER_LINE
else:
el = block_size
fmt = "%3d," * el + "\n"
if block_size > ELEMS_PER_LINE:
fmt = fmt * int(block_size / ELEMS_PER_LINE)
for i in range(0, len(table), block_size):
f.write(("\n/* block %d */\n" + fmt) % ((i / block_size,) + table[i:i+block_size]))
f.write("};\n\n")
# Extract the unique combinations of properties into records
def combine_tables(*tables):
records = {}
index = []
for t in zip(*tables):
i = records.get(t)
if i is None:
i = records[t] = len(records)
index.append(i)
return index, records
# Create a record struct
def get_record_size_struct(records):
size = 0
structure = 'typedef struct {\n'
for i in range(len(records[0])):
record_slice = [record[i] for record in records]
slice_type, slice_size = get_type_size(record_slice)
# add padding: round up to the nearest power of slice_size
size = (size + slice_size - 1) & -slice_size
size += slice_size
structure += '%s property_%d;\n' % (slice_type, i)
# round up to the first item of the next structure in array
record_slice = [record[0] for record in records]
slice_type, slice_size = get_type_size(record_slice)
size = (size + slice_size - 1) & -slice_size
structure += '} ucd_record;\n*/\n'
return size, structure
# Write records
def write_records(records, record_size):
f.write('const ucd_record PRIV(ucd_records)[] = { ' + \
'/* %d bytes, record size %d */\n' % (len(records) * record_size, record_size))
records = list(zip(list(records.keys()), list(records.values())))
records.sort(key = lambda x: x[1])
for i, record in enumerate(records):
f.write((' {' + '%6d, ' * len(record[0]) + '}, /* %3d */\n') % (record[0] + (i,)))
f.write('};\n\n')
# Write a bit set
def write_bitsets(list, item_size):
for d in list:
bitwords = [0] * item_size
for idx in d:
bitwords[idx // 32] |= 1 << (idx & 31)
s = " "
for x in bitwords:
f.write("%s" % s)
s = ", "
f.write("0x%08xu" % x)
f.write(",\n")
f.write("};\n\n")
# ---------------------------------------------------------------------------
# This bit of code must have been useful when the original script was being
# developed. Retain it just in case it is ever needed again.
# def test_record_size():
# tests = [ \
# ( [(3,), (6,), (6,), (1,)], 1 ), \
# ( [(300,), (600,), (600,), (100,)], 2 ), \
# ( [(25, 3), (6, 6), (34, 6), (68, 1)], 2 ), \
# ( [(300, 3), (6, 6), (340, 6), (690, 1)], 4 ), \
# ( [(3, 300), (6, 6), (6, 340), (1, 690)], 4 ), \
# ( [(300, 300), (6, 6), (6, 340), (1, 690)], 4 ), \
# ( [(3, 100000), (6, 6), (6, 123456), (1, 690)], 8 ), \
# ( [(100000, 300), (6, 6), (123456, 6), (1, 690)], 8 ), \
# ]
# for test in tests:
# size, struct = get_record_size_struct(test[0])
# assert(size == test[1])
# test_record_size()
# ---------------------------------------------------------------------------
# ---------------------------------------------------------------------------
# MAIN CODE FOR CREATING TABLES
# ---------------------------------------------------------------------------
unicode_version = ""
# Some of the tables imported from GenerateCommon.py have alternate comment
# strings for use by GenerateUcpHeader. The comments are not wanted here, so
# remove them.
bidi_classes = bidi_classes[::2]
break_properties = break_properties[::2]
category_names = category_names[::2]
# Create the various tables from Unicode data files
script = read_table('Unicode.tables/Scripts.txt', make_get_names(script_names), script_names.index('Unknown'))
category = read_table('Unicode.tables/DerivedGeneralCategory.txt', make_get_names(category_names), category_names.index('Cn'))
break_props = read_table('Unicode.tables/GraphemeBreakProperty.txt', make_get_names(break_properties), break_properties.index('Other'))
other_case = read_table('Unicode.tables/CaseFolding.txt', get_other_case, 0)
bidi_class = read_table('Unicode.tables/DerivedBidiClass.txt', make_get_names(bidi_classes), bidi_classes.index('L'))
# The grapheme breaking rules were changed for Unicode 11.0.0 (June 2018). Now
# we need to find the Extended_Pictographic property for emoji characters. This
# can be set as an additional grapheme break property, because the default for
# all the emojis is "other". We scan the emoji-data.txt file and modify the
# break-props table.
file = open('Unicode.tables/emoji-data.txt', 'r', encoding='utf-8')
for line in file:
line = re.sub(r'#.*', '', line)
chardata = list(map(str.strip, line.split(';')))
if len(chardata) <= 1:
continue
if chardata[1] != "Extended_Pictographic":
continue
m = re.match(r'([0-9a-fA-F]+)(\.\.([0-9a-fA-F]+))?$', chardata[0])
char = int(m.group(1), 16)
if m.group(3) is None:
last = char
else:
last = int(m.group(3), 16)
for i in range(char, last + 1):
if break_props[i] != break_properties.index('Other'):
print("WARNING: Emoji 0x%x has break property %s, not 'Other'",
i, break_properties[break_props[i]], file=sys.stderr)
break_props[i] = break_properties.index('Extended_Pictographic')
file.close()
# Handle script extensions. The get_script_extesion() function maintains a
# list of unique bitmaps representing lists of scripts, returning the offset
# in that list. Initialize the list with an empty set, which is used for
# characters that have no script extensions.
script_lists = [[]]
last_script_extension = ""
scriptx_bidi_class = read_table('Unicode.tables/ScriptExtensions.txt', get_script_extension, 0)
for idx in range(len(scriptx_bidi_class)):
scriptx_bidi_class[idx] = scriptx_bidi_class[idx] | (bidi_class[idx] << 11)
bidi_class = None
# Find the Boolean properties of each character. This next bit of magic creates
# a list of empty lists. Using [[]] * MAX_UNICODE gives a list of references to
# the *same* list, which is not what we want.
bprops = [[] for _ in range(MAX_UNICODE)]
# Collect the properties from the various files
for filename in bool_propsfiles:
try:
file = open('Unicode.tables/' + filename, 'r')
except IOError:
print(f"** Couldn't open {'Unicode.tables/' + filename}\n")
sys.exit(1)
for line in file:
line = re.sub(r'#.*', '', line)
data = list(map(str.strip, line.split(';')))
if len(data) <= 1:
continue
try:
ix = bool_properties.index(data[1])
except ValueError:
continue
m = re.match(r'([0-9a-fA-F]+)(\.\.([0-9a-fA-F]+))?$', data[0])
char = int(m.group(1), 16)
if m.group(3) is None:
last = char
else:
last = int(m.group(3), 16)
for i in range(char, last + 1):
bprops[i].append(ix)
file.close()
# The ASCII property isn't listed in any files, but it is easy enough to add
# it manually.
ix = bool_properties.index("ASCII")
for i in range(128):
bprops[i].append(ix)
# The Bidi_Mirrored property isn't listed in any property files. We have to
# deduce it from the file that lists the mirrored characters.
ix = bool_properties.index("Bidi_Mirrored")
try:
file = open('Unicode.tables/BidiMirroring.txt', 'r')
except IOError:
print(f"** Couldn't open {'Unicode.tables/BidiMirroring.txt'}\n")
sys.exit(1)
for line in file:
line = re.sub(r'#.*', '', line)
data = list(map(str.strip, line.split(';')))
if len(data) <= 1:
continue
c = int(data[0], 16)
bprops[c].append(ix)
file.close()
# Scan each character's boolean property list and created a list of unique
# lists, at the same time, setting the index in that list for each property in
# the bool_props vector.
bool_props = [0] * MAX_UNICODE
bool_props_lists = [[]]
for c in range(MAX_UNICODE):
s = set(bprops[c])
for i in range(len(bool_props_lists)):
if s == set(bool_props_lists[i]):
break;
else:
bool_props_lists.append(bprops[c])
i += 1
bool_props[c] = i * bool_props_list_item_size
# This block of code was added by PH in September 2012. It scans the other_case
# table to find sets of more than two characters that must all match each other
# caselessly. Later in this script a table of these sets is written out.
# However, we have to do this work here in order to compute the offsets in the
# table that are inserted into the main table.
# The CaseFolding.txt file lists pairs, but the common logic for reading data
# sets only one value, so first we go through the table and set "return"
# offsets for those that are not already set.
for c in range(MAX_UNICODE):
if other_case[c] != 0 and other_case[c + other_case[c]] == 0:
other_case[c + other_case[c]] = -other_case[c]
# Now scan again and create equivalence sets.
caseless_sets = []
for c in range(MAX_UNICODE):
o = c + other_case[c]
# Trigger when this character's other case does not point back here. We
# now have three characters that are case-equivalent.
if other_case[o] != -other_case[c]:
t = o + other_case[o]
# Scan the existing sets to see if any of the three characters are already
# part of a set. If so, unite the existing set with the new set.
appended = 0
for s in caseless_sets:
found = 0
for x in s:
if x == c or x == o or x == t:
found = 1
# Add new characters to an existing set
if found:
found = 0
for y in [c, o, t]:
for x in s:
if x == y:
found = 1
if not found:
s.append(y)
appended = 1
# If we have not added to an existing set, create a new one.
if not appended:
caseless_sets.append([c, o, t])
# End of loop looking for caseless sets.
# Now scan the sets and set appropriate offsets for the characters.
caseless_offsets = [0] * MAX_UNICODE
offset = 1;
for s in caseless_sets:
for x in s:
caseless_offsets[x] = offset
offset += len(s) + 1
# End of block of code for creating offsets for caseless matching sets.
# Combine all the tables
table, records = combine_tables(script, category, break_props,
caseless_offsets, other_case, scriptx_bidi_class, bool_props)
# Find the record size and create a string definition of the structure for
# outputting as a comment.
record_size, record_struct = get_record_size_struct(list(records.keys()))
# Find the optimum block size for the two-stage table
min_size = sys.maxsize
for block_size in [2 ** i for i in range(5,10)]:
size = len(records) * record_size
stage1, stage2 = compress_table(table, block_size)
size += get_tables_size(stage1, stage2)
#print "/* block size %5d => %5d bytes */" % (block_size, size)
if size < min_size:
min_size = size
min_stage1, min_stage2 = stage1, stage2
min_block_size = block_size
# ---------------------------------------------------------------------------
# MAIN CODE FOR WRITING THE OUTPUT FILE
# ---------------------------------------------------------------------------
# Open the output file (no return on failure). This call also writes standard
# header boilerplate.
f = open_output("pcre2_ucd.c")
# Output this file's heading text
f.write("""\
/* This file contains tables of Unicode properties that are extracted from
Unicode data files. See the comments at the start of maint/GenerateUcd.py for
details.
As well as being part of the PCRE2 library, this file is #included by the
pcre2test program, which redefines the PRIV macro to change table names from
_pcre2_xxx to xxxx, thereby avoiding name clashes with the library. At present,
just one of these tables is actually needed. When compiling the library, some
headers are needed. */
#ifndef PCRE2_PCRE2TEST
#ifdef HAVE_CONFIG_H
#include "config.h"
#endif
#include "pcre2_internal.h"
#endif /* PCRE2_PCRE2TEST */
/* The tables herein are needed only when UCP support is built, and in PCRE2
that happens automatically with UTF support. This module should not be
referenced otherwise, so it should not matter whether it is compiled or not.
However a comment was received about space saving - maybe the guy linked all
the modules rather than using a library - so we include a condition to cut out
the tables when not needed. But don't leave a totally empty module because some
compilers barf at that. Instead, just supply some small dummy tables. */
#ifndef SUPPORT_UNICODE
const ucd_record PRIV(ucd_records)[] = {{0,0,0,0,0,0,0}};
const uint16_t PRIV(ucd_stage1)[] = {0};
const uint16_t PRIV(ucd_stage2)[] = {0};
const uint32_t PRIV(ucd_caseless_sets)[] = {0};
#else
\n""")
# --- Output some variable heading stuff ---
f.write("/* Total size: %d bytes, block size: %d. */\n\n" % (min_size, min_block_size))
f.write('const char *PRIV(unicode_version) = "{}";\n\n'.format(unicode_version))
f.write("""\
/* When recompiling tables with a new Unicode version, please check the types
in this structure definition with those in pcre2_internal.h (the actual field
names will be different).
\n""")
f.write(record_struct)
f.write("""
/* If the 32-bit library is run in non-32-bit mode, character values greater
than 0x10ffff may be encountered. For these we set up a special record. */
#if PCRE2_CODE_UNIT_WIDTH == 32
const ucd_record PRIV(dummy_ucd_record)[] = {{
ucp_Unknown, /* script */
ucp_Cn, /* type unassigned */
ucp_gbOther, /* grapheme break property */
0, /* case set */
0, /* other case */
0 | (ucp_bidiL << UCD_BIDICLASS_SHIFT), /* script extension and bidi class */
0, /* bool properties offset */
}};
#endif
\n""")
# --- Output the table of caseless character sets ---
f.write("""\
/* This table contains lists of characters that are caseless sets of
more than one character. Each list is terminated by NOTACHAR. */
const uint32_t PRIV(ucd_caseless_sets)[] = {
NOTACHAR,
""")
for s in caseless_sets:
s = sorted(s)
for x in s:
f.write(' 0x%04x,' % x)
f.write(' NOTACHAR,\n')
f.write('};\n\n')
# --- Other tables are not needed by pcre2test ---
f.write("""\
/* When #included in pcre2test, we don't need the table of digit sets, nor the
the large main UCD tables. */
#ifndef PCRE2_PCRE2TEST
\n""")
# --- Read Scripts.txt again for the sets of 10 digits. ---
digitsets = []
file = open('Unicode.tables/Scripts.txt', 'r', encoding='utf-8')
for line in file:
m = re.match(r'([0-9a-fA-F]+)\.\.([0-9a-fA-F]+)\s+;\s+\S+\s+#\s+Nd\s+', line)
if m is None:
continue
first = int(m.group(1),16)
last = int(m.group(2),16)
if ((last - first + 1) % 10) != 0:
f.write("ERROR: %04x..%04x does not contain a multiple of 10 characters" % (first, last),
file=sys.stderr)
while first < last:
digitsets.append(first + 9)
first += 10
file.close()
digitsets.sort()
f.write("""\
/* This table lists the code points for the '9' characters in each set of
decimal digits. It is used to ensure that all the digits in a script run come
from the same set. */
const uint32_t PRIV(ucd_digit_sets)[] = {
""")
f.write(" %d, /* Number of subsequent values */" % len(digitsets))
count = 8
for d in digitsets:
if count == 8:
f.write("\n ")
count = 0
f.write(" 0x%05x," % d)
count += 1
f.write("\n};\n\n")
f.write("""\
/* This vector is a list of script bitsets for the Script Extension property.
The number of 32-bit words in each bitset is #defined in pcre2_ucp.h as
ucd_script_sets_item_size. */
const uint32_t PRIV(ucd_script_sets)[] = {
""")
write_bitsets(script_lists, script_list_item_size)
f.write("""\
/* This vector is a list of bitsets for Boolean properties. The number of
32_bit words in each bitset is #defined as ucd_boolprop_sets_item_size in
pcre2_ucp.h. */
const uint32_t PRIV(ucd_boolprop_sets)[] = {
""")
write_bitsets(bool_props_lists, bool_props_list_item_size)
# Output the main UCD tables.
f.write("""\
/* These are the main two-stage UCD tables. The fields in each record are:
script (8 bits), character type (8 bits), grapheme break property (8 bits),
offset to multichar other cases or zero (8 bits), offset to other case or zero
(32 bits, signed), bidi class (5 bits) and script extension (11 bits) packed
into a 16-bit field, and offset in binary properties table (16 bits). */
\n""")
write_records(records, record_size)
write_table(min_stage1, 'PRIV(ucd_stage1)')
write_table(min_stage2, 'PRIV(ucd_stage2)', min_block_size)
f.write("#if UCD_BLOCK_SIZE != %d\n" % min_block_size)
f.write("""\
#error Please correct UCD_BLOCK_SIZE in pcre2_internal.h
#endif
#endif /* SUPPORT_UNICODE */
#endif /* PCRE2_PCRE2TEST */
/* End of pcre2_ucd.c */
""")
f.close
# End

98
Kha/Backends/Kore-hxcpp/khacpp/project/thirdparty/pcre2-10.42-16/maint/GenerateUcpHeader.py vendored Normal file
View File

@ -0,0 +1,98 @@
#! /usr/bin/python
# PCRE2 UNICODE PROPERTY SUPPORT
# ------------------------------
# This script generates the pcre2_ucp.h file from Unicode data files. This
# header uses enumerations to give names to Unicode property types and script
# names.
# This script was created in December 2021 as part of the Unicode data
# generation refactoring.
# Import common data lists and functions
from GenerateCommon import \
bidi_classes, \
bool_properties, \
bool_props_list_item_size, \
break_properties, \
category_names, \
general_category_names, \
script_list_item_size, \
script_names, \
open_output
# Open the output file (no return on failure). This call also writes standard
# header boilerplate.
f = open_output("pcre2_ucp.h")
# Output this file's heading text
f.write("""\
#ifndef PCRE2_UCP_H_IDEMPOTENT_GUARD
#define PCRE2_UCP_H_IDEMPOTENT_GUARD
/* This file contains definitions of the Unicode property values that are
returned by the UCD access macros and used throughout PCRE2.
IMPORTANT: The specific values of the first two enums (general and particular
character categories) are assumed by the table called catposstab in the file
pcre2_auto_possess.c. They are unlikely to change, but should be checked after
an update. */
\n""")
f.write("/* These are the general character categories. */\n\nenum {\n")
for i in general_category_names:
f.write(" ucp_%s,\n" % i)
f.write("};\n\n")
f.write("/* These are the particular character categories. */\n\nenum {\n")
for i in range(0, len(category_names), 2):
f.write(" ucp_%s, /* %s */\n" % (category_names[i], category_names[i+1]))
f.write("};\n\n")
f.write("/* These are Boolean properties. */\n\nenum {\n")
for i in bool_properties:
f.write(" ucp_%s,\n" % i)
f.write(" /* This must be last */\n")
f.write(" ucp_Bprop_Count\n};\n\n")
f.write("/* Size of entries in ucd_boolprop_sets[] */\n\n")
f.write("#define ucd_boolprop_sets_item_size %d\n\n" % bool_props_list_item_size)
f.write("/* These are the bidi class values. */\n\nenum {\n")
for i in range(0, len(bidi_classes), 2):
sp = ' ' * (4 - len(bidi_classes[i]))
f.write(" ucp_bidi%s,%s /* %s */\n" % (bidi_classes[i], sp, bidi_classes[i+1]))
f.write("};\n\n")
f.write("/* These are grapheme break properties. The Extended Pictographic "
"property\ncomes from the emoji-data.txt file. */\n\nenum {\n")
for i in range(0, len(break_properties), 2):
sp = ' ' * (21 - len(break_properties[i]))
f.write(" ucp_gb%s,%s /* %s */\n" % (break_properties[i], sp, break_properties[i+1]))
f.write("};\n\n")
f.write("/* These are the script identifications. */\n\nenum {\n /* Scripts which has characters in other scripts. */\n")
for i in script_names:
if i == "Unknown":
f.write("\n /* Scripts which has no characters in other scripts. */\n")
f.write(" ucp_%s,\n" % i)
f.write("\n")
f.write(" /* This must be last */\n")
f.write(" ucp_Script_Count\n};\n\n")
f.write("/* Size of entries in ucd_script_sets[] */\n\n")
f.write("#define ucd_script_sets_item_size %d\n\n" % script_list_item_size)
f.write("#endif /* PCRE2_UCP_H_IDEMPOTENT_GUARD */\n\n")
f.write("/* End of pcre2_ucp.h */\n")
f.close()
# End

203
Kha/Backends/Kore-hxcpp/khacpp/project/thirdparty/pcre2-10.42-16/maint/GenerateUcpTables.py vendored Normal file
View File

@ -0,0 +1,203 @@
#! /usr/bin/python
# PCRE2 UNICODE PROPERTY SUPPORT
# ------------------------------
# This script generates the pcre2_ucptables.c file, which contains tables for
# recognizing Unicode property names. It is #included by pcre2_tables.c. In
# order to reduce the number of relocations when loading the PCRE2 library, the
# names are held as a single large string, with offsets in the table. This is
# tedious to maintain by hand. Therefore, a script is used to generate the
# table.
# This script was created in December 2021 based on the previous GenerateUtt
# script, whose output had to be manually edited into pcre2_tables.c. Here is
# the history of the original script:
# -----------------------------------------------------------------------------
# Modified by PH 17-March-2009 to generate the more verbose form that works
# for UTF-support in EBCDIC as well as ASCII environments.
# Modified by PH 01-March-2010 to add new scripts for Unicode 5.2.0.
# Modified by PH 04-May-2010 to add new "X.." special categories.
# Modified by PH 30-April-2011 to add new scripts for Unicode 6.0.0
# Modified by ChPe 30-September-2012 to add this note; no other changes were
# necessary for Unicode 6.2.0 support.
# Modfied by PH 26-February-2013 to add the Xuc special category.
# Comment modified by PH 13-May-2014 to update to PCRE2 file names.
# Script updated to Python 3 by running it through the 2to3 converter.
# Added script names for Unicode 7.0.0, 20-June-2014.
# Added script names for Unicode 8.0.0, 19-June-2015.
# Added script names for Unicode 10.0.0, 02-July-2017.
# Added script names for Unicode 11.0.0, 03-July-2018.
# Added 'Unknown' script, 01-October-2018.
# Added script names for Unicode 12.1.0, 27-July-2019.
# Added script names for Unicode 13.0.0, 10-March-2020.
# Added Script names for Unicode 14.0.0, PCRE2-10.39
# Added support for bidi class and bidi control, 06-December-2021
# This also involved lower casing strings and removing underscores, in
# accordance with Unicode's "loose matching" rules, which Perl observes.
# Changed default script type from PT_SC to PT_SCX, 18-December-2021
# -----------------------------------------------------------------------------
#
# Note subsequent changes here:
#
# 27-December-2021: Added support for 4-letter script abbreviations.
# 10-January-2022: Further updates for Boolean property support
# -----------------------------------------------------------------------------
# Import common data lists and functions
from GenerateCommon import \
abbreviations, \
bool_properties, \
bidi_classes, \
category_names, \
general_category_names, \
script_names, \
open_output
# Open the output file (no return on failure). This call also writes standard
# header boilerplate.
f = open_output("pcre2_ucptables.c")
# The list in bidi_classes contains just the Unicode classes such as AN, LRE,
# etc., along with comments. We need to add "bidi" in front of each value, in
# order to create names that don't clash with other types of property.
bidi_class_names = []
for i in range(0, len(bidi_classes), 2):
bidi_class_names.append("bidi" + bidi_classes[i])
# Remove the comments from other lists that contain them.
category_names = category_names[::2]
# Create standardized versions of the names by lowercasing and removing
# underscores.
def stdname(x):
return x.lower().replace('_', '')
def stdnames(x):
y = [''] * len(x)
for i in range(len(x)):
y[i] = stdname(x[i])
return y
std_category_names = stdnames(category_names)
std_general_category_names = stdnames(general_category_names)
std_bidi_class_names = stdnames(bidi_class_names)
std_bool_properties = stdnames(bool_properties)
# Create the table, starting with the Unicode script, category and bidi class
# names. We keep both the standardized name and the original, because the
# latter is used for the ucp_xx names. NOTE: for the script abbreviations, we
# still use the full original names.
utt_table = []
scx_end = script_names.index('Unknown')
for idx, name in enumerate(script_names):
pt_type = 'PT_SCX' if idx < scx_end else 'PT_SC'
utt_table.append((stdname(name), name, pt_type))
for abbrev in abbreviations[name]:
utt_table.append((stdname(abbrev), name, pt_type))
# Add the remaining property lists
utt_table += list(zip(std_category_names, category_names, ['PT_PC'] * len(category_names)))
utt_table += list(zip(std_general_category_names, general_category_names, ['PT_GC'] * len(general_category_names)))
utt_table += list(zip(std_bidi_class_names, bidi_class_names, ['PT_BIDICL'] * len(bidi_class_names)))
for name in bool_properties:
utt_table.append((stdname(name), name, 'PT_BOOL'))
if name in abbreviations:
for abbrev in abbreviations[name]:
utt_table.append((stdname(abbrev), name, 'PT_BOOL'))
# Now add specials and synonyms. Note both the standardized and capitalized
# forms are needed.
utt_table.append(('any', 'Any', 'PT_ANY'))
utt_table.append(('l&', 'L&', 'PT_LAMP'))
utt_table.append(('lc', 'LC', 'PT_LAMP'))
utt_table.append(('xan', 'Xan', 'PT_ALNUM'))
utt_table.append(('xps', 'Xps', 'PT_PXSPACE'))
utt_table.append(('xsp', 'Xsp', 'PT_SPACE'))
utt_table.append(('xuc', 'Xuc', 'PT_UCNC'))
utt_table.append(('xwd', 'Xwd', 'PT_WORD'))
# Remove duplicates from the table and then sort it.
utt_table = list(set(utt_table))
utt_table.sort()
# Output file-specific heading
f.write("""\
#ifdef SUPPORT_UNICODE
/* The PRIV(utt)[] table below translates Unicode property names into type and
code values. It is searched by binary chop, so must be in collating sequence of
name. Originally, the table contained pointers to the name strings in the first
field of each entry. However, that leads to a large number of relocations when
a shared library is dynamically loaded. A significant reduction is made by
putting all the names into a single, large string and using offsets instead.
All letters are lower cased, and underscores are removed, in accordance with
the "loose matching" rules that Unicode advises and Perl uses. */
\n""")
# We have to use STR_ macros to define the strings so that it all works in
# UTF-8 mode on EBCDIC platforms.
for utt in utt_table:
f.write('#define STRING_%s0' % (utt[0].replace('&', '_AMPERSAND')))
for c in utt[0]:
if c == '&':
f.write(' STR_AMPERSAND')
else:
f.write(' STR_%s' % c);
f.write(' "\\0"\n')
# Output the long string of concatenated names
f.write('\nconst char PRIV(utt_names)[] =\n');
last = ''
for utt in utt_table:
if utt == utt_table[-1]:
last = ';'
f.write(' STRING_%s0%s\n' % (utt[0].replace('&', '_AMPERSAND'), last))
# Output the property type table
f.write('\nconst ucp_type_table PRIV(utt)[] = {\n')
offset = 0
last = ','
for utt in utt_table:
if utt[2] in ('PT_ANY', 'PT_LAMP', 'PT_ALNUM', 'PT_PXSPACE',
'PT_SPACE', 'PT_UCNC', 'PT_WORD'):
value = '0'
else:
value = 'ucp_' + utt[1]
if utt == utt_table[-1]:
last = ''
f.write(' { %3d, %s, %s }%s\n' % (offset, utt[2], value, last))
offset += len(utt[0]) + 1
f.write('};\n\n')
# Ending text
f.write("""\
const size_t PRIV(utt_size) = sizeof(PRIV(utt)) / sizeof(ucp_type_table);
#endif /* SUPPORT_UNICODE */
/* End of pcre2_ucptables.c */
""")
f.close
# End

453
Kha/Backends/Kore-hxcpp/khacpp/project/thirdparty/pcre2-10.42-16/maint/ManyConfigTests vendored Normal file
View File

@ -0,0 +1,453 @@
#! /bin/sh
# This is a script for the use of PCRE2 maintainers. It configures and rebuilds
# PCRE2 with a variety of configuration options, and in each case runs the
# tests to ensure that all goes well. Every possible combination would take far
# too long, so we use a representative sample. This script should be run in the
# PCRE2 source directory.
# While debugging, it is sometimes useful to be able to cut out some of the
# tests, in order to run those that are giving errors. The following options
# do this:
#
# -noasan skip the test that uses -fsanitize=address
# -nousan skip the test that uses -fsanitize=undefined
# -nodebug skip the test that uses --enable-debug
# -nojit skip all JIT tests
# -nojitmain skip non-valgrind JIT tests
# -nojitvalgrind skip JIT tests with valgrind
# -nomain skip all the main (non-JIT) set of tests
# -nomainvalgrind skip the main (non-JIT) valgrind tests
# -notmp skip the test in a temporary directory
# -novalgrind skip all the valgrind tests
# Alternatively, if any of those names are given with '+' instead of '-no',
# only those groups named with '+' are run (e.g. +jit). If -dummy is given,
# no tests are actually run - this provides a means of testing the selectors.
# The -v option causes a call to 'pcre2test -C' to happen for each
# configuration.
useasan=1
useusan=1
usedebug=1
usejit=1
usejitvalgrind=1
usemain=1
usemainvalgrind=1
usetmp=1
usevalgrind=1
dummy=0
seenplus=0
verbose=0
while [ $# -gt 0 ] ; do
case $1 in
+*) if [ $seenplus -eq 0 ]; then
useasan=0
useusan=0
usedebug=0
usejit=0
usejitvalgrind=0
usemain=0
usemainvalgrind=0
usetmp=0
seenplus=1
fi;;
esac
case $1 in
-dummy) dummy=1;;
-v) verbose=1;;
-noasan) useasan=0;;
-nousan) useusan=0;;
-nodebug) usedebug=0;;
-nojit) usejit=0; usejitvalgrind=0;;
-nojitmain) usejit=0;;
-nojitvalgrind) usejitvalgrind=0;;
-nomain) usemain=0; usemainvalgrind=0;;
-nomainvalgrind) usemainvalgrind=0;;
-notmp) usetmp=0;;
-novalgrind) usevalgrind=0;;
+asan) useasan=1;;
+usan) useusan=1;;
+debug) usedebug=1;;
+jit) usejit=1; usejitvalgrind=1;;
+jitmain) usejit=1;;
+jitvalgrind) usejitvalgrind=1;;
+main) usemain=1; usemainvalgrind=1;;
+mainvalgrind) usemainvalgrind=1;;
+tmp) usetmp=1;;
+valgrind) usevalgrind=1; usejitvalgrind=1; usemainvalgrind=1;;
*) echo "Unknown option '$1'"; exit 1;;
esac
shift
done
if [ $usejitvalgrind -eq 0 -a $usemainvalgrind -eq 0 ] ; then
usevalgrind=0
fi
# This is in case the caller has set aliases (as I do - PH)
unset cp ls mv rm
# This is a temporary directory for testing out-of-line builds
tmp=/tmp/pcre2testing
# Don't bother with compiler optimization for most tests; it just slows down
# compilation a lot (and running the tests themselves is quick). However, one
# special test turns optimization on, because it can provoke some compiler
# warnings.
CFLAGS="-g"
OFLAGS="-O0"
ISGCC=0
# If the compiler is gcc, add a lot of warning switches.
cc --version >/tmp/pcre2ccversion 2>/dev/null
if [ $? -eq 0 ] && grep GCC /tmp/pcre2ccversion >/dev/null; then
ISGCC=1
CFLAGS="$CFLAGS -Wall"
CFLAGS="$CFLAGS -Wno-overlength-strings"
CFLAGS="$CFLAGS -Wpointer-arith"
CFLAGS="$CFLAGS -Wwrite-strings"
CFLAGS="$CFLAGS -Wundef -Wshadow"
CFLAGS="$CFLAGS -Wmissing-field-initializers"
CFLAGS="$CFLAGS -Wunused-parameter"
CFLAGS="$CFLAGS -Wextra -Wformat"
CFLAGS="$CFLAGS -Wbad-function-cast"
CFLAGS="$CFLAGS -Wmissing-declarations"
CFLAGS="$CFLAGS -Wnested-externs"
CFLAGS="$CFLAGS -pedantic"
CFLAGS="$CFLAGS -Wuninitialized"
CFLAGS="$CFLAGS -Wmaybe-uninitialized"
CFLAGS="$CFLAGS -Wmissing-prototypes"
CFLAGS="$CFLAGS -Wstrict-prototypes"
fi
rm -f /tmp/pcre2ccversion
# This function runs a single test with the set of configuration options that
# are in $opts. The source directory must be set in srcdir. The function must
# be defined as "runtest()" not "function runtest()" in order to run on
# Solaris.
runtest()
{
rm -f $srcdir/pcre2test $srcdir/pcre2grep $srcdir/pcre2_jit_test
testcount=`expr $testcount + 1`
if [ "$opts" = "" ] ; then
echo "[$testcount/$testtotal] Configuring with: default settings"
else
echo "[$testcount/$testtotal] Configuring with:"
echo " $opts"
fi
if [ $dummy -eq 1 ]; then return; fi
CFLAGS="$CFLAGS" \
$srcdir/configure $opts >/dev/null 2>teststderrM
if [ $? -ne 0 ]; then
echo " "
echo "******** Error while configuring ********"
cat teststderrM
exit 1
fi
# There is an infelicity in the Autotools world (as of October 2015) which
# causes the message
#
# ar: `u' modifier ignored since `D' is the default (see `U')
#
# to be output while linking. This triggers an unwanted error report from this
# script, because it expects no stderr output while making. To get round this
# we filter the stderr output through sed, removing all occurrences of the
# above lines. Just for paranoia, check that sed is available before doing
# this.
echo "Making"
make -j >/dev/null 2>teststderrM
makeRC=$?
if command -v sed >/dev/null 2>&1 ; then
sed "/\`u' modifier ignored since \`D' is the default/ d" \
teststderrM > teststderrMM
mv -f teststderrMM teststderrM
fi
if [ $makeRC -ne 0 -o -s teststderrM ]; then
echo " "
echo "******** Errors or warnings while making ********"
echo " "
cat teststderrM
exit 1
fi
if [ $verbose -eq 1 ]; then
./pcre2test -C
fi
./pcre2test -C jit >/dev/null
jit=$?
./pcre2test -C pcre2-8 >/dev/null
pcre2_8=$?
echo "Running PCRE2 library tests $withvalgrind"
$srcdir/RunTest $valgrind >teststdoutM 2>teststderrM
if [ $? -ne 0 -o -s teststderrM ]; then
echo " "
echo "**** Test failed ****"
if [ -s teststderrM ] ; then
cat teststderrM
else
cat teststdoutM
fi
exit 1
fi
if [ $pcre2_8 -gt 0 ]; then
echo "Running pcre2grep tests $withvalgrind"
$srcdir/RunGrepTest $valgrind >teststdoutM 2>teststderrM
if [ $? -ne 0 -o -s teststderrM ]; then
echo " "
echo "**** Test failed ****"
cat teststderrM
cat teststdoutM
exit 1
fi
else
echo "Skipping pcre2grep tests: 8-bit library not compiled"
fi
if [ "$jit" -gt 0 ]; then
echo "Running JIT regression tests $withvalgrind"
$jrvalgrind $srcdir/pcre2_jit_test >teststdoutM 2>teststderrM
if [ $? -ne 0 -o -s teststderrM ]; then
echo " "
echo "**** Test failed ****"
cat teststderrM
cat teststdoutM
exit 1
fi
else
echo "Skipping JIT regression tests: JIT is not enabled"
fi
}
# Update the total count whenever a new test is added; it is used to show
# progess as each test is run.
testtotal=`expr 17 \* $usemain + \
1 \* $usemain \* $usedebug + \
1 \* $usetmp + \
1 \* $ISGCC \* $usemain + \
1 \* $ISGCC \* $usemain \* $useasan + \
1 \* $ISGCC \* $usemain \* $useusan + \
13 \* $usejit + \
2 \* $usemainvalgrind + \
2 \* $usejitvalgrind`
testcount=0
if [ $testtotal -eq 0 ] ; then
echo "** No tests selected"
exit 1
fi
valgrind=
jrvalgrind=
withvalgrind=
srcdir=.
export srcdir
if [ $usejit -ne 0 ]; then
enable_jit=--enable-jit
else
enable_jit=
fi
# If gcc is in use, run a maximally configured test with -O2, because that can
# throw up warnings that are not detected with -O0. Then run a second test with
# -fsanitize=address, which also may throw up new warnings as well as checking
# things at runtime. Finally, run another test using -fsanitize=undefined
# -std-gnu99 to check for runtime actions that are not well defined. However,
# we also use -fno-sanitize=shift to avoid warnings for shifts of negative
# numbers, which occur in src/pcre2_jit_compile.c.
if [ $ISGCC -ne 0 -a $usemain -ne 0 ]; then
echo "---------- Maximally configured test with -O2 ----------"
SAVECFLAGS="$CFLAGS"
CFLAGS="-O2 $CFLAGS"
echo "CFLAGS=$CFLAGS"
opts="--disable-shared $enable_jit --enable-pcre2-16 --enable-pcre2-32"
runtest
if [ $useasan -ne 0 ]; then
echo "---------- Maximally configured test with -fsanitize=address ----------"
# Following a kernel change, sanitize address doesn't work unless the extra
# PIE options are also set.
CFLAGS="$OFLAGS $SAVECFLAGS -no-pie -fno-PIE -fsanitize=address"
echo "CFLAGS=$CFLAGS"
opts="--disable-shared $enable_jit --enable-pcre2-16 --enable-pcre2-32"
runtest
fi
# This also seems to be the case for sanitize undefined.
if [ $useusan -ne 0 ]; then
echo "------- Maximally configured test with -fsanitize=undefined -fno-sanitize=shift -fno-sanitize=alignment -std=gnu99 -------"
CFLAGS="$OFLAGS $SAVECFLAGS -no-pie -fno-PIE -fsanitize=undefined -fno-sanitize=shift -fno-sanitize=alignment -std=gnu99"
echo "CFLAGS=$CFLAGS"
opts="--disable-shared $enable_jit --enable-pcre2-16 --enable-pcre2-32"
runtest
fi
CFLAGS="$OFLAGS $SAVECFLAGS"
fi
# This set of tests builds PCRE2 and runs the tests with a variety of configure
# options, in the current (source) directory. The empty configuration builds
# with all the default settings. As well as testing that these options work, we
# use --disable-shared or --disable-static except for the default test (which
# builds both) to save a bit of time by building only one version of the
# library for the subsequent tests.
echo "---------- CFLAGS for the remaining tests ----------"
echo "CFLAGS=$CFLAGS"
if [ $usemain -ne 0 ]; then
if [ $usedebug -ne 0 ]; then
echo "---------- Maximally configured test with --enable-debug ----------"
opts="--disable-shared $enable_jit --enable-pcre2-16 --enable-pcre2-32 --enable-debug"
runtest
fi
echo "---------- Non-JIT tests in the current directory ----------"
for opts in \
"" \
"--disable-static" \
"--disable-shared" \
"--disable-unicode --disable-shared --enable-never-backslash-C" \
"--with-link-size=3 --disable-shared --disable-pcre2grep-callout" \
"--disable-unicode --enable-rebuild-chartables --disable-shared" \
"--disable-unicode --enable-newline-is-any --disable-shared" \
"--disable-unicode --enable-newline-is-cr --disable-shared" \
"--disable-unicode --enable-newline-is-crlf --disable-shared" \
"--disable-unicode --enable-newline-is-anycrlf --enable-bsr-anycrlf --disable-shared" \
"--enable-newline-is-any --disable-static" \
"--disable-unicode --enable-pcre2-16" \
"--enable-pcre2-16 --disable-shared" \
"--disable-unicode --enable-pcre2-32" \
"--enable-pcre2-32 --disable-shared" \
"--disable-unicode --enable-pcre2-32 --enable-pcre2-16 --disable-shared" \
"--disable-unicode --enable-pcre2-32 --enable-pcre2-16 --disable-pcre2-8 --disable-shared"
do
runtest
done
fi
# Now run the JIT tests unless disabled
if [ $usejit -ne 0 ]; then
echo "---------- JIT tests in the current directory ----------"
for opts in \
"--disable-unicode --enable-jit --disable-shared" \
"--enable-jit --disable-shared" \
"--enable-jit --with-link-size=3 --disable-shared" \
"--enable-jit --enable-pcre2-16 --disable-shared" \
"--disable-unicode --enable-jit --enable-pcre2-16 --disable-pcre2-8 --disable-shared" \
"--enable-jit --enable-pcre2-16 --disable-pcre2-8 --disable-shared" \
"--enable-jit --enable-pcre2-16 --with-link-size=3 --disable-shared" \
"--enable-jit --enable-pcre2-16 --with-link-size=4 --disable-shared" \
"--enable-jit --enable-pcre2-32 --disable-shared" \
"--disable-unicode --enable-jit --enable-pcre2-32 --disable-pcre2-8 --disable-shared" \
"--enable-jit --enable-pcre2-32 --disable-pcre2-8 --disable-shared" \
"--enable-jit --enable-pcre2-32 --with-link-size=4 --disable-shared" \
"--enable-jit --enable-pcre2-32 --enable-pcre2-16 --disable-pcre2-8 --enable-newline-is-anycrlf --enable-bsr-anycrlf --disable-shared"
do
runtest
done
fi
# Now re-run some of the tests under valgrind.
if [ $usevalgrind -ne 0 ]; then
echo "---------- Tests in the current directory using valgrind ----------"
valgrind=valgrind
withvalgrind="with valgrind"
if [ $usemainvalgrind -ne 0 ]; then
for opts in \
"--disable-shared" \
"--with-link-size=3 --enable-pcre2-16 --enable-pcre2-32 --disable-shared"
do
opts="--enable-valgrind $opts"
runtest
done
fi
if [ $usejitvalgrind -ne 0 ]; then
jrvalgrind="valgrind --tool=memcheck -q --smc-check=all-non-file --suppressions=$srcdir/testdata/valgrind-jit.supp"
for opts in \
"--enable-jit --disable-shared" \
"--enable-jit --enable-pcre2-16 --enable-pcre2-32"
do
opts="--enable-valgrind $opts"
runtest
done
fi
fi
valgrind=
jrvalgrind=
withvalgrind=
# Clean up the distribution and then do at least one build and test in a
# directory other than the source directory. It doesn't work unless the
# source directory is cleaned up first.
if [ -f Makefile ]; then
echo "Running 'make distclean'"
make distclean >/dev/null 2>&1
if [ $? -ne 0 ]; then
echo "** 'make distclean' failed"
exit 1
fi
fi
echo "---------- End of tests in the source directory ----------"
echo "Removing teststdoutM and teststderrM"
rm -rf teststdoutM teststderrM
if [ $usetmp -ne 0 ]; then
echo "---------- Tests in the $tmp directory ----------"
srcdir=`pwd`
export srcdir
if [ ! -e $tmp ]; then
mkdir $tmp
fi
if [ ! -d $tmp ]; then
echo "** Failed to create $tmp or it is not a directory"
exit 1
fi
cd $tmp
if [ $? -ne 0 ]; then
echo "** Failed to cd to $tmp"
exit 1
fi
for opts in \
"--disable-shared"
do
runtest
done
echo "Removing $tmp"
rm -rf $tmp
fi
echo "---------- All done ----------"
# End

460
Kha/Backends/Kore-hxcpp/khacpp/project/thirdparty/pcre2-10.42-16/maint/README vendored Normal file
View File

@ -0,0 +1,460 @@
MAINTENANCE README FOR PCRE2
============================
The files in the "maint" directory of the PCRE2 source contain data, scripts,
and programs that are used for the maintenance of PCRE2, but which do not form
part of the PCRE2 distribution tarballs. This document describes these files
and also contains some notes for maintainers. Its contents are:
Files in the maint directory
Updating to a new Unicode release
Preparing for a PCRE2 release
Making a PCRE2 release
Long-term ideas (wish list)
Files in the maint directory
============================
GenerateCommon.py
A Python module containing data and functions that are used by the other
Generate scripts.
GenerateTest26.py
A Python script that generates input and expected output test data for test
26, which tests certain aspects of Unicode property support.
GenerateUcd.py
A Python script that generates the file pcre2_ucd.c from GenerateCommon.py
and Unicode data files, which are themselves downloaded from the Unicode web
site. The generated file contains the tables for a 2-stage lookup of Unicode
properties, along with some auxiliary tables. The script starts with a long
comment that gives details of the tables it constructs.
GenerateUcpHeader.py
A Python script that generates the file pcre2_ucp.h from GenerateCommon.py
and Unicode data files. The generated file defines constants for various
Unicode property values.
GenerateUcpTables.py
A Python script that generates the file pcre2_ucptables.c from
GenerateCommon.py and Unicode data files. The generated file contains tables
for looking up Unicode property names.
ManyConfigTests
A shell script that runs "configure, make, test" a number of times with
different configuration settings.
pcre2_chartables.c.non-standard
This is a set of character tables that came from a Windows system. It has
characters greater than 128 that are set as spaces, amongst other things. I
kept it so that it can be used for testing from time to time.
README
This file.
Unicode.tables
The files in this directory were downloaded from the Unicode web site. They
contain information about Unicode characters and scripts, and are used by the
Generate scripts. There is also UnicodeData.txt, which is no longer used by
any script, because it is useful occasionally for manually looking up the
details of certain characters. However, note that character names in this
file such as "Arabic sign sanah" do NOT mean that the character is in a
particular script (in this case, Arabic). Scripts.txt and
ScriptExtensions.txt are where to look for script information.
ucptest.c
A program for testing the Unicode property macros that do lookups in the
pcre2_ucd.c data, mainly useful after rebuilding the Unicode property tables.
Compile and run this in the "maint" directory (see comments at its head).
This program can also be used to find characters with specific properties and
to list which properties are supported.
ucptestdata
A directory containing four files, testinput{1,2} and testoutput{1,2}, for
use in conjunction with the ucptest program.
utf8.c
A short, freestanding C program for converting a Unicode code point into a
sequence of bytes in the UTF-8 encoding, and vice versa. If its argument is a
hex number such as 0x1234, it outputs a list of the equivalent UTF-8 bytes.
If its argument is a sequence of concatenated UTF-8 bytes (e.g. 12e188b4) it
treats them as a UTF-8 string and outputs the equivalent code points in hex.
See comments at its head for details.
Updating to a new Unicode release
=================================
When there is a new release of Unicode, the files in Unicode.tables must be
refreshed from the web site. Once that is done, the four Python scripts that
generate files from the Unicode data can be run from within the "maint"
directory.
Note: Previously, it was necessary to update lists of scripts and their
abbreviations by hand before running the Python scripts. This is no longer
necessary because the scripts have been upgraded to extract this information
themselves. Also, there used to be explicit lists of scripts in two of the man
pages. This is no longer the case; the pcre2test program can now output a list
of supported scripts.
You can give an output file name as an argument to the following scripts, but
by default:
GenerateUcd.py creates pcre2_ucd.c )
GenerateUcpHeader.py creates pcre2_ucp.h ) in the current directory
GenerateUcpTables.py creates pcre2_ucptables.c )
These files can be compared against the existing versions in the src directory
to check on any changes before replacing the old files, but you can also
generate directly into the final location by running:
./GenerateUcd.py ../src/pcre2_ucd.c
./GenerateUcpHeader.py ../src/pcre2_ucp.h
./GenerateUcpTables.py ../src/pcre2_ucptables.c
Once the .c and .h files are in the ../src directory, the ucptest program can
be compiled and used to check that the new tables work properly. The data files
in ucptestdata are set up to check a number of test characters. See the
comments at the start of ucptest.c. If there are new scripts, adding a few
tests to the files in ucptestdata is a good idea.
Finally, you should run the GenerateTest26.py script to regenerate new versions
of the input and expected output from a series of Unicode property tests that
are automatically generated from the Unicode data files. By default, the files
are written to testinput26 and testoutput26 in the current directory, but you
can give an alternative directory name as an argument to the script. These
files should eventually be installed in the main testdata directory.
Preparing for a PCRE2 release
=============================
This section contains a checklist of things that I do before building a new
release.
. Ensure that the version number and version date are correct in configure.ac.
. Update the library version numbers in configure.ac according to the rules
given below.
. If new build options or new source files have been added, ensure that they
are added to the CMake files as well as to the autoconf files. The relevant
files are CMakeLists.txt and config-cmake.h.in. After making a release, test
it out with CMake if there have been changes here.
. Run ./autogen.sh to ensure everything is up-to-date.
. Compile and test with many different config options, and combinations of
options. Also, test with valgrind by running "RunTest valgrind" and
"RunGrepTest valgrind". The script maint/ManyConfigTests now encapsulates
this testing. It runs tests with different configurations, and it also runs
some of them with valgrind, all of which can take quite some time.
. Run tests in both 32-bit and 64-bit environments if possible. I can no longer
run 32-bit tests.
. Run tests with two or more different compilers (e.g. clang and gcc), and
make use of -fsanitize=address and friends where possible. For gcc,
-fsanitize=undefined -std=gnu99 picks up undefined behaviour at runtime, but
needs -fno-sanitize=shift to get rid of warnings for shifts of negative
numbers in the JIT compiler. For clang, -fsanitize=address,undefined,integer
can be used but -fno-sanitize=alignment,shift,unsigned-integer-overflow must
be added when compiling with JIT. Another useful clang option is
-fsanitize=signed-integer-overflow
. Do a test build using CMake. Remove src/config.h first, lest it override the
version that CMake creates. Also do a CMake unity build to check that it
still works: [c]cmake -DCMAKE_UNITY_BUILD=ON sets up a unity build.
. Run perltest.sh on the test data for tests 1 and 4. The output should match
the PCRE2 test output, apart from the version identification at the start of
each test. Sometimes there are other differences in test 4 if PCRE2 and Perl
are using different Unicode releases. The other tests are not Perl-compatible
(they use various PCRE2-specific features or options).
. It is possible to test with the emulated memmove() function by undefining
HAVE_MEMMOVE and HAVE_BCOPY in config.h, though I do not do this often.
. Documentation: check AUTHORS, ChangeLog (check version and date), LICENCE,
NEWS (check version and date), NON-AUTOTOOLS-BUILD, and README. Many of these
won't need changing, but over the long term things do change.
. I used to test new releases myself on a number of different operating
systems. For example, on Solaris it is helpful to test using Sun's cc
compiler as a change from gcc. Adding -xarch=v9 to the cc options does a
64-bit test, but it also needs -S 64 for pcre2test to increase the stack size
for test 2. Since I retired I can no longer do much of this. There are
automated tests under Ubuntu, Alpine, and Windows that are now set up as
GitHub actions. Check that they are running clean.
. The buildbots at http://buildfarm.opencsw.org/ do some automated testing
of PCRE2 and should also be checked before putting out a release.
Updating version info for libtool
=================================
This set of rules for updating library version information came from a web page
whose URL I have forgotten. The version information consists of three parts:
(current, revision, age).
1. Start with version information of 0:0:0 for each libtool library.
2. Update the version information only immediately before a public release of
your software. More frequent updates are unnecessary, and only guarantee
that the current interface number gets larger faster.
3. If the library source code has changed at all since the last update, then
increment revision; c:r:a becomes c:r+1:a.
4. If any interfaces have been added, removed, or changed since the last
update, increment current, and set revision to 0.
5. If any interfaces have been added since the last public release, then
increment age.
6. If any interfaces have been removed or changed since the last public
release, then set age to 0.
The following explanation may help in understanding the above rules a bit
better. Consider that there are three possible kinds of reaction from users to
changes in a shared library:
1. Programs using the previous version may use the new version as a drop-in
replacement, and programs using the new version can also work with the
previous one. In other words, no recompiling nor relinking is needed. In
this case, increment revision only, don't touch current or age.
2. Programs using the previous version may use the new version as a drop-in
replacement, but programs using the new version may use APIs not present in
the previous one. In other words, a program linking against the new version
may fail if linked against the old version at run time. In this case, set
revision to 0, increment current and age.
3. Programs may need to be changed, recompiled, relinked in order to use the
new version. Increment current, set revision and age to 0.
Making a PCRE2 release
======================
Run PrepareRelease and commit the files that it changes. The first thing this
script does is to run CheckMan on the man pages; if it finds any markup errors,
it reports them and then aborts. Otherwise it removes trailing spaces from
sources and refreshes the HTML documentation. Update the GitHub repository with
"git push".
Once PrepareRelease has run clean, run "make distcheck" to create the tarballs
and the zipball. I then sign these files. Double-check with "git status" that
the repository is fully up-to-date, then create a new tag and a release on
GitHub. Upload the tarballs, zipball, and the signatures as "assets" of the
GitHub release.
When the new release is out, don't forget to tell webmaster@pcre.org and the
mailing list.
Future ideas (wish list)
========================
This section records a list of ideas so that they do not get forgotten. They
vary enormously in their usefulness and potential for implementation. Some are
very sensible; some are rather wacky. Some have been on this list for many
years.
. Optimization
There are always ideas for new optimizations so as to speed up pattern
matching. Most of them try to save work by recognizing a non-match without
having to scan all the possibilities. These are some that I've recorded:
* /((A{0,5}){0,5}){0,5}(something complex)/ on a non-matching string is very
slow, though Perl is fast. Can we speed up somehow? Convert to {0,125}?
OTOH, this is pathological - the user could easily fix it.
* Turn ={4} into ==== ? (for speed). I once did an experiment, and it seems
to have little effect, and maybe makes things worse.
* "Ends with literal string" - note that a single character doesn't gain much
over the existing "required code unit" feature that just remembers one code
unit.
* Remember an initial string rather than just 1 code unit.
* A required code unit from alternatives - not just the last unit, but an
earlier one if common to all alternatives.
* Friedl contains other ideas.
* The code does not set initial code unit flags for Unicode property types
such as \p; I don't know how much benefit there would be for, for example,
setting the bits for 0-9 and all values >= xC0 (in 8-bit mode) when a
pattern starts with \p{N}.
. If Perl gets to a consistent state over the settings of capturing sub-
patterns inside repeats, see if we can match it. One example of the
difference is the matching of /(main(O)?)+/ against mainOmain, where PCRE2
leaves $2 set. In Perl, it's unset. Changing this in PCRE2 will be very hard
because I think it needs much more state to be remembered.
. A feature to suspend a match via a callout was once requested.
. An option to convert results into character offsets and character lengths.
. A (non-Unix) user wanted pcregrep options to (a) list a file name just once,
preceded by a blank line, instead of adding it to every matched line, and (b)
support --outputfile=name.
. Define a union for the results from pcre2_pattern_info().
. Provide a "random access to the subject" facility so that the way in which it
is stored is independent of PCRE2. For efficiency, it probably isn't possible
to switch this dynamically. It would have to be specified when PCRE2 was
compiled. PCRE2 would then call a function every time it wanted a character.
. pcre2grep: add -rs for a sorted recurse. Having to store file names and sort
them will of course slow it down.
. Someone suggested --disable-callout to save code space when callouts are
never wanted. This seems rather marginal.
. A user suggested a parameter to limit the length of string matched, for
example if the parameter is N, the current match should fail if the matched
substring exceeds N. This could apply to both match functions. The value
could be a new field in the match context. Compare the offset_limit feature,
which limits where a match must start.
. Write a function that generates random matching strings for a compiled
pattern.
. Pcre2grep: an option to specify the output line separator, either as a string
or select from a fixed list. This is not straightforward, because at the
moment it outputs whatever is in the input file.
. Improve the code for duplicate checking in pcre2_dfa_match(). An incomplete,
non-thread-safe patch showed that this can help performance for patterns
where there are many alternatives. However, a simple thread-safe
implementation that I tried made things worse in many simple cases, so this
is not an obviously good thing.
. PCRE2 cannot at present distinguish between subpatterns with different names,
but the same number (created by the use of ?|). In order to do so, a way of
remembering *which* subpattern numbered n matched is needed. (*MARK) can
perhaps be used as a way round this problem. However, note that Perl does not
distinguish: like PCRE2, a name is just an alias for a number in Perl.
. Instead of having #ifdef HAVE_CONFIG_H in each module, put #include
"something" and the the #ifdef appears only in one place, in "something".
. Implement something like (?(R2+)... to check outer recursions.
. If Perl ever supports the POSIX notation [[.something.]] PCRE2 should try
to follow.
. A user wanted a way of ignoring all Unicode "mark" characters so that, for
example "a" followed by an accent would, together, match "a". This can only
be done clumsily at present by using a lookahead such as /(?=a)\X/, which
works for "combining" characters.
. Perl supports [\N{x}-\N{y}] as a Unicode range, even in EBCDIC. PCRE2
supports \N{U+dd..} everywhere, but not in EBCDIC.
. Unicode stuff from Perl:
\b{gcb} or \b{g} grapheme cluster boundary
\b{sb} sentence boundary
\b{wb} word boundary
See Unicode TR 29. The last two are very much aimed at natural language.
. Allow a callout to specify a number of characters to skip. This can be done
compatibly via an extra callout field.
. Allow callouts to return *PRUNE, *COMMIT, *THEN, *SKIP, with and without
continuing (that is, with and without an implied *FAIL). A new option,
PCRE2_CALLOUT_EXTENDED say, would be needed. This is unlikely ever to be
implemented by JIT, so this could be an option for pcre2_match().
. A limit on substitutions: a user suggested somehow finding a way of making
match_limit apply to the whole operation instead of each match separately.
. Some #defines could be replaced with enums to improve robustness.
. There was a request for an option for pcre2_match() to return the longest
match. This would mean searching for all possible matches, of course.
. Perl's /a modifier sets Unicode, but restricts \d etc to ASCII characters,
which is the PCRE2 default for PCRE2_UTF (use PCRE2_UCP to change). However,
Perl also has /aa, which in addition, disables ASCII/non-ASCII caseless
matching. Perhaps we need a new option PCRE2_CASELESS_RESTRICT_ASCII. In
practice, this just means not using the ucd_caseless_sets[] table.
. There is more that could be done to the oss-fuzz setup (needs some research).
A seed corpus could be built. I noted something about $LIB_FUZZING_ENGINE.
The test function could make use of get_substrings() to cover more code.
. A neater way of handling recursion file names in pcre2grep, e.g. a single
buffer that can grow. See also GitHub issue #2 (recursion looping via
symlinks).
. A user suggested that before/after parameters in pcre2grep could have
negative values, to list lines near to the matched line, but not necessarily
the line itself. For example, --before-context=-1 would list the line *after*
each matched line, without showing the matched line. The problem here is what
to do with matches that are close together. Maybe a simpler way would be a
flag to disable showing matched lines, only valid with either -A or -B?
. There was a suggestiong for a pcre2grep colour default, or possibly a more
general PCRE2GREP_OPT, but only for some options - not file names or patterns.
. Breaking loops that match an empty string: perhaps find a way of continuing
if *something* has changed, but this might mean remembering additional data.
"Something" could be a capture value, but then a list of previous values
would be needed to avoid a cycle of changes.
. If a function could be written to find 3-character (or other length) fixed
strings, at least one of which must be present for a match, efficient
pre-searching of large datasets could be implemented.
. If pcre2grep had --first-line (match only in the first line) it could be
efficiently used to find files "starting with xxx". What about --last-line?
There was also the suggestion of an option for pcre2grep to scan only the
start of a file. I am not keen - this is the job of "head".
. A user requested a means of determining whether a failed match was failed by
the start-of-match optimizations, or by running the match engine. Easy enough
to define a bit in the match data, but all three matchers would need work.
. Would inlining "simple" recursions provide a useful performance boost for the
interpreters? JIT already does some of this, but it may not be worth it for
the interpreters.
. Redesign handling of class/nclass/xclass because the compile code logic is
currently very contorted and obscure. Also there was a request for a way of
re-defining \w (and therefore \W, \b, and \B). An in-pattern sequence such as
(?w=[...]) was suggested. Easiest way would be simply to inline the class,
with lookarounds for \b and \B. Ideally the setting should last till the end
of the group, which means remembering all previous settings; maybe a fixed
amount of stack would do - how deep would anyone want to nest these things?
See GitHub issue #13 for a compendium of character class issues, including
(?[...]) extended classes.
. A user suggested something like --with-build-info to set a build information
string that could be retrieved by pcre2_config(). However, there's no
facility for a length limit in pcre2_config(), and what would be the
encoding?
. Quantified groups with a fixed count currently operate by replicating the
group in the compiled bytecode. This may not really matter in these days of
gigabyte memory, but perhaps another implementation might be considered.
Needs coordination between the interpreters and JIT.
. There are regular requests for variable-length lookbehinds.
. See also any suggestions in the GitHub issues.
Philip Hazel
Email local part: Philip.Hazel
Email domain: gmail.com
Last updated: 25 April 2022

633
Kha/Backends/Kore-hxcpp/khacpp/project/thirdparty/pcre2-10.42-16/maint/Unicode.tables/BidiMirroring.txt vendored Normal file
View File

@ -0,0 +1,633 @@
# BidiMirroring-14.0.0.txt
# Date: 2021-08-08, 22:55:00 GMT [KW, RP]
# © 2021 Unicode®, Inc.
# For terms of use, see https://www.unicode.org/terms_of_use.html
#
# Unicode Character Database
# For documentation, see https://www.unicode.org/reports/tr44/
#
# Bidi_Mirroring_Glyph Property
#
# This file is an informative contributory data file in the
# Unicode Character Database.
#
# This data file lists characters that have the Bidi_Mirrored=Yes property
# value, for which there is another Unicode character that typically has a glyph
# that is the mirror image of the original character's glyph.
#
# The repertoire covered by the file is Unicode 14.0.0.
#
# The file contains a list of lines with mappings from one code point
# to another one for character-based mirroring.
# Note that for "real" mirroring, a rendering engine needs to select
# appropriate alternative glyphs, and that many Unicode characters do not
# have a mirror-image Unicode character.
#
# Each mapping line contains two fields, separated by a semicolon (';').
# Each of the two fields contains a code point represented as a
# variable-length hexadecimal value with 4 to 6 digits.
# A comment indicates where the characters are "BEST FIT" mirroring.
#
# Code points for which Bidi_Mirrored=Yes, but for which no appropriate
# characters exist with mirrored glyphs, are
# listed as comments at the end of the file.
#
# Formally, the default value of the Bidi_Mirroring_Glyph property
# for each code point is <none>, unless a mapping to
# some other character is specified in this data file. When a code
# point has the default value for the Bidi_Mirroring_Glyph property,
# that means that no other character exists whose glyph is suitable
# for character-based mirroring.
#
# For information on bidi mirroring, see UAX #9: Unicode Bidirectional Algorithm,
# at https://www.unicode.org/reports/tr9/
#
# This file was originally created by Markus Scherer.
# Extended for Unicode 3.2, 4.0, 4.1, 5.0, 5.1, 5.2, and 6.0 by Ken Whistler,
# and for subsequent versions by Ken Whistler, Laurentiu Iancu, and Roozbeh Pournader.
#
# Historical and Compatibility Information:
#
# The OpenType Mirroring Pairs List (OMPL) is frozen to match the
# Unicode 5.1 version of the Bidi_Mirroring_Glyph property (2008).
# See https://www.microsoft.com/typography/otspec/ompl.txt
#
# The Unicode 6.1 version of the Bidi_Mirroring_Glyph property (2011)
# added one mirroring pair: 27CB <--> 27CD.
#
# The Unicode 11.0 version of the Bidi_Mirroring_Glyph property (2018)
# underwent a substantial revision, to formally recognize all of the
# exact mirroring pairs and "BEST FIT" mirroring pairs that had been
# added after the freezing of the OMPL list. As a result, starting
# with Unicode 11.0, the bmg mapping values more accurately reflect
# the current status of glyphs for Bidi_Mirrored characters in
# the Unicode Standard, but this listing now extends significantly
# beyond the frozen OMPL list. Implementers should be aware of this
# intentional distinction.
#
# ############################################################
#
# Property: Bidi_Mirroring_Glyph
#
# @missing: 0000..10FFFF; <none>
0028; 0029 # LEFT PARENTHESIS
0029; 0028 # RIGHT PARENTHESIS
003C; 003E # LESS-THAN SIGN
003E; 003C # GREATER-THAN SIGN
005B; 005D # LEFT SQUARE BRACKET
005D; 005B # RIGHT SQUARE BRACKET
007B; 007D # LEFT CURLY BRACKET
007D; 007B # RIGHT CURLY BRACKET
00AB; 00BB # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
00BB; 00AB # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
0F3A; 0F3B # TIBETAN MARK GUG RTAGS GYON
0F3B; 0F3A # TIBETAN MARK GUG RTAGS GYAS
0F3C; 0F3D # TIBETAN MARK ANG KHANG GYON
0F3D; 0F3C # TIBETAN MARK ANG KHANG GYAS
169B; 169C # OGHAM FEATHER MARK
169C; 169B # OGHAM REVERSED FEATHER MARK
2039; 203A # SINGLE LEFT-POINTING ANGLE QUOTATION MARK
203A; 2039 # SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
2045; 2046 # LEFT SQUARE BRACKET WITH QUILL
2046; 2045 # RIGHT SQUARE BRACKET WITH QUILL
207D; 207E # SUPERSCRIPT LEFT PARENTHESIS
207E; 207D # SUPERSCRIPT RIGHT PARENTHESIS
208D; 208E # SUBSCRIPT LEFT PARENTHESIS
208E; 208D # SUBSCRIPT RIGHT PARENTHESIS
2208; 220B # ELEMENT OF
2209; 220C # [BEST FIT] NOT AN ELEMENT OF
220A; 220D # SMALL ELEMENT OF
220B; 2208 # CONTAINS AS MEMBER
220C; 2209 # [BEST FIT] DOES NOT CONTAIN AS MEMBER
220D; 220A # SMALL CONTAINS AS MEMBER
2215; 29F5 # DIVISION SLASH
221F; 2BFE # RIGHT ANGLE
2220; 29A3 # ANGLE
2221; 299B # MEASURED ANGLE
2222; 29A0 # SPHERICAL ANGLE
2224; 2AEE # DOES NOT DIVIDE
223C; 223D # TILDE OPERATOR
223D; 223C # REVERSED TILDE
2243; 22CD # ASYMPTOTICALLY EQUAL TO
2245; 224C # APPROXIMATELY EQUAL TO
224C; 2245 # ALL EQUAL TO
2252; 2253 # APPROXIMATELY EQUAL TO OR THE IMAGE OF
2253; 2252 # IMAGE OF OR APPROXIMATELY EQUAL TO
2254; 2255 # COLON EQUALS
2255; 2254 # EQUALS COLON
2264; 2265 # LESS-THAN OR EQUAL TO
2265; 2264 # GREATER-THAN OR EQUAL TO
2266; 2267 # LESS-THAN OVER EQUAL TO
2267; 2266 # GREATER-THAN OVER EQUAL TO
2268; 2269 # [BEST FIT] LESS-THAN BUT NOT EQUAL TO
2269; 2268 # [BEST FIT] GREATER-THAN BUT NOT EQUAL TO
226A; 226B # MUCH LESS-THAN
226B; 226A # MUCH GREATER-THAN
226E; 226F # [BEST FIT] NOT LESS-THAN
226F; 226E # [BEST FIT] NOT GREATER-THAN
2270; 2271 # [BEST FIT] NEITHER LESS-THAN NOR EQUAL TO
2271; 2270 # [BEST FIT] NEITHER GREATER-THAN NOR EQUAL TO
2272; 2273 # [BEST FIT] LESS-THAN OR EQUIVALENT TO
2273; 2272 # [BEST FIT] GREATER-THAN OR EQUIVALENT TO
2274; 2275 # [BEST FIT] NEITHER LESS-THAN NOR EQUIVALENT TO
2275; 2274 # [BEST FIT] NEITHER GREATER-THAN NOR EQUIVALENT TO
2276; 2277 # LESS-THAN OR GREATER-THAN
2277; 2276 # GREATER-THAN OR LESS-THAN
2278; 2279 # [BEST FIT] NEITHER LESS-THAN NOR GREATER-THAN
2279; 2278 # [BEST FIT] NEITHER GREATER-THAN NOR LESS-THAN
227A; 227B # PRECEDES
227B; 227A # SUCCEEDS
227C; 227D # PRECEDES OR EQUAL TO
227D; 227C # SUCCEEDS OR EQUAL TO
227E; 227F # [BEST FIT] PRECEDES OR EQUIVALENT TO
227F; 227E # [BEST FIT] SUCCEEDS OR EQUIVALENT TO
2280; 2281 # [BEST FIT] DOES NOT PRECEDE
2281; 2280 # [BEST FIT] DOES NOT SUCCEED
2282; 2283 # SUBSET OF
2283; 2282 # SUPERSET OF
2284; 2285 # [BEST FIT] NOT A SUBSET OF
2285; 2284 # [BEST FIT] NOT A SUPERSET OF
2286; 2287 # SUBSET OF OR EQUAL TO
2287; 2286 # SUPERSET OF OR EQUAL TO
2288; 2289 # [BEST FIT] NEITHER A SUBSET OF NOR EQUAL TO
2289; 2288 # [BEST FIT] NEITHER A SUPERSET OF NOR EQUAL TO
228A; 228B # [BEST FIT] SUBSET OF WITH NOT EQUAL TO
228B; 228A # [BEST FIT] SUPERSET OF WITH NOT EQUAL TO
228F; 2290 # SQUARE IMAGE OF
2290; 228F # SQUARE ORIGINAL OF
2291; 2292 # SQUARE IMAGE OF OR EQUAL TO
2292; 2291 # SQUARE ORIGINAL OF OR EQUAL TO
2298; 29B8 # CIRCLED DIVISION SLASH
22A2; 22A3 # RIGHT TACK
22A3; 22A2 # LEFT TACK
22A6; 2ADE # ASSERTION
22A8; 2AE4 # TRUE
22A9; 2AE3 # FORCES
22AB; 2AE5 # DOUBLE VERTICAL BAR DOUBLE RIGHT TURNSTILE
22B0; 22B1 # PRECEDES UNDER RELATION
22B1; 22B0 # SUCCEEDS UNDER RELATION
22B2; 22B3 # NORMAL SUBGROUP OF
22B3; 22B2 # CONTAINS AS NORMAL SUBGROUP
22B4; 22B5 # NORMAL SUBGROUP OF OR EQUAL TO
22B5; 22B4 # CONTAINS AS NORMAL SUBGROUP OR EQUAL TO
22B6; 22B7 # ORIGINAL OF
22B7; 22B6 # IMAGE OF
22B8; 27DC # MULTIMAP
22C9; 22CA # LEFT NORMAL FACTOR SEMIDIRECT PRODUCT
22CA; 22C9 # RIGHT NORMAL FACTOR SEMIDIRECT PRODUCT
22CB; 22CC # LEFT SEMIDIRECT PRODUCT
22CC; 22CB # RIGHT SEMIDIRECT PRODUCT
22CD; 2243 # REVERSED TILDE EQUALS
22D0; 22D1 # DOUBLE SUBSET
22D1; 22D0 # DOUBLE SUPERSET
22D6; 22D7 # LESS-THAN WITH DOT
22D7; 22D6 # GREATER-THAN WITH DOT
22D8; 22D9 # VERY MUCH LESS-THAN
22D9; 22D8 # VERY MUCH GREATER-THAN
22DA; 22DB # LESS-THAN EQUAL TO OR GREATER-THAN
22DB; 22DA # GREATER-THAN EQUAL TO OR LESS-THAN
22DC; 22DD # EQUAL TO OR LESS-THAN
22DD; 22DC # EQUAL TO OR GREATER-THAN
22DE; 22DF # EQUAL TO OR PRECEDES
22DF; 22DE # EQUAL TO OR SUCCEEDS
22E0; 22E1 # [BEST FIT] DOES NOT PRECEDE OR EQUAL
22E1; 22E0 # [BEST FIT] DOES NOT SUCCEED OR EQUAL
22E2; 22E3 # [BEST FIT] NOT SQUARE IMAGE OF OR EQUAL TO
22E3; 22E2 # [BEST FIT] NOT SQUARE ORIGINAL OF OR EQUAL TO
22E4; 22E5 # [BEST FIT] SQUARE IMAGE OF OR NOT EQUAL TO
22E5; 22E4 # [BEST FIT] SQUARE ORIGINAL OF OR NOT EQUAL TO
22E6; 22E7 # [BEST FIT] LESS-THAN BUT NOT EQUIVALENT TO
22E7; 22E6 # [BEST FIT] GREATER-THAN BUT NOT EQUIVALENT TO
22E8; 22E9 # [BEST FIT] PRECEDES BUT NOT EQUIVALENT TO
22E9; 22E8 # [BEST FIT] SUCCEEDS BUT NOT EQUIVALENT TO
22EA; 22EB # [BEST FIT] NOT NORMAL SUBGROUP OF
22EB; 22EA # [BEST FIT] DOES NOT CONTAIN AS NORMAL SUBGROUP
22EC; 22ED # [BEST FIT] NOT NORMAL SUBGROUP OF OR EQUAL TO
22ED; 22EC # [BEST FIT] DOES NOT CONTAIN AS NORMAL SUBGROUP OR EQUAL
22F0; 22F1 # UP RIGHT DIAGONAL ELLIPSIS
22F1; 22F0 # DOWN RIGHT DIAGONAL ELLIPSIS
22F2; 22FA # ELEMENT OF WITH LONG HORIZONTAL STROKE
22F3; 22FB # ELEMENT OF WITH VERTICAL BAR AT END OF HORIZONTAL STROKE
22F4; 22FC # SMALL ELEMENT OF WITH VERTICAL BAR AT END OF HORIZONTAL STROKE
22F6; 22FD # ELEMENT OF WITH OVERBAR
22F7; 22FE # SMALL ELEMENT OF WITH OVERBAR
22FA; 22F2 # CONTAINS WITH LONG HORIZONTAL STROKE
22FB; 22F3 # CONTAINS WITH VERTICAL BAR AT END OF HORIZONTAL STROKE
22FC; 22F4 # SMALL CONTAINS WITH VERTICAL BAR AT END OF HORIZONTAL STROKE
22FD; 22F6 # CONTAINS WITH OVERBAR
22FE; 22F7 # SMALL CONTAINS WITH OVERBAR
2308; 2309 # LEFT CEILING
2309; 2308 # RIGHT CEILING
230A; 230B # LEFT FLOOR
230B; 230A # RIGHT FLOOR
2329; 232A # LEFT-POINTING ANGLE BRACKET
232A; 2329 # RIGHT-POINTING ANGLE BRACKET
2768; 2769 # MEDIUM LEFT PARENTHESIS ORNAMENT
2769; 2768 # MEDIUM RIGHT PARENTHESIS ORNAMENT
276A; 276B # MEDIUM FLATTENED LEFT PARENTHESIS ORNAMENT
276B; 276A # MEDIUM FLATTENED RIGHT PARENTHESIS ORNAMENT
276C; 276D # MEDIUM LEFT-POINTING ANGLE BRACKET ORNAMENT
276D; 276C # MEDIUM RIGHT-POINTING ANGLE BRACKET ORNAMENT
276E; 276F # HEAVY LEFT-POINTING ANGLE QUOTATION MARK ORNAMENT
276F; 276E # HEAVY RIGHT-POINTING ANGLE QUOTATION MARK ORNAMENT
2770; 2771 # HEAVY LEFT-POINTING ANGLE BRACKET ORNAMENT
2771; 2770 # HEAVY RIGHT-POINTING ANGLE BRACKET ORNAMENT
2772; 2773 # LIGHT LEFT TORTOISE SHELL BRACKET ORNAMENT
2773; 2772 # LIGHT RIGHT TORTOISE SHELL BRACKET ORNAMENT
2774; 2775 # MEDIUM LEFT CURLY BRACKET ORNAMENT
2775; 2774 # MEDIUM RIGHT CURLY BRACKET ORNAMENT
27C3; 27C4 # OPEN SUBSET
27C4; 27C3 # OPEN SUPERSET
27C5; 27C6 # LEFT S-SHAPED BAG DELIMITER
27C6; 27C5 # RIGHT S-SHAPED BAG DELIMITER
27C8; 27C9 # REVERSE SOLIDUS PRECEDING SUBSET
27C9; 27C8 # SUPERSET PRECEDING SOLIDUS
27CB; 27CD # MATHEMATICAL RISING DIAGONAL
27CD; 27CB # MATHEMATICAL FALLING DIAGONAL
27D5; 27D6 # LEFT OUTER JOIN
27D6; 27D5 # RIGHT OUTER JOIN
27DC; 22B8 # LEFT MULTIMAP
27DD; 27DE # LONG RIGHT TACK
27DE; 27DD # LONG LEFT TACK
27E2; 27E3 # WHITE CONCAVE-SIDED DIAMOND WITH LEFTWARDS TICK
27E3; 27E2 # WHITE CONCAVE-SIDED DIAMOND WITH RIGHTWARDS TICK
27E4; 27E5 # WHITE SQUARE WITH LEFTWARDS TICK
27E5; 27E4 # WHITE SQUARE WITH RIGHTWARDS TICK
27E6; 27E7 # MATHEMATICAL LEFT WHITE SQUARE BRACKET
27E7; 27E6 # MATHEMATICAL RIGHT WHITE SQUARE BRACKET
27E8; 27E9 # MATHEMATICAL LEFT ANGLE BRACKET
27E9; 27E8 # MATHEMATICAL RIGHT ANGLE BRACKET
27EA; 27EB # MATHEMATICAL LEFT DOUBLE ANGLE BRACKET
27EB; 27EA # MATHEMATICAL RIGHT DOUBLE ANGLE BRACKET
27EC; 27ED # MATHEMATICAL LEFT WHITE TORTOISE SHELL BRACKET
27ED; 27EC # MATHEMATICAL RIGHT WHITE TORTOISE SHELL BRACKET
27EE; 27EF # MATHEMATICAL LEFT FLATTENED PARENTHESIS
27EF; 27EE # MATHEMATICAL RIGHT FLATTENED PARENTHESIS
2983; 2984 # LEFT WHITE CURLY BRACKET
2984; 2983 # RIGHT WHITE CURLY BRACKET
2985; 2986 # LEFT WHITE PARENTHESIS
2986; 2985 # RIGHT WHITE PARENTHESIS
2987; 2988 # Z NOTATION LEFT IMAGE BRACKET
2988; 2987 # Z NOTATION RIGHT IMAGE BRACKET
2989; 298A # Z NOTATION LEFT BINDING BRACKET
298A; 2989 # Z NOTATION RIGHT BINDING BRACKET
298B; 298C # LEFT SQUARE BRACKET WITH UNDERBAR
298C; 298B # RIGHT SQUARE BRACKET WITH UNDERBAR
298D; 2990 # LEFT SQUARE BRACKET WITH TICK IN TOP CORNER
298E; 298F # RIGHT SQUARE BRACKET WITH TICK IN BOTTOM CORNER
298F; 298E # LEFT SQUARE BRACKET WITH TICK IN BOTTOM CORNER
2990; 298D # RIGHT SQUARE BRACKET WITH TICK IN TOP CORNER
2991; 2992 # LEFT ANGLE BRACKET WITH DOT
2992; 2991 # RIGHT ANGLE BRACKET WITH DOT
2993; 2994 # LEFT ARC LESS-THAN BRACKET
2994; 2993 # RIGHT ARC GREATER-THAN BRACKET
2995; 2996 # DOUBLE LEFT ARC GREATER-THAN BRACKET
2996; 2995 # DOUBLE RIGHT ARC LESS-THAN BRACKET
2997; 2998 # LEFT BLACK TORTOISE SHELL BRACKET
2998; 2997 # RIGHT BLACK TORTOISE SHELL BRACKET
299B; 2221 # MEASURED ANGLE OPENING LEFT
29A0; 2222 # SPHERICAL ANGLE OPENING LEFT
29A3; 2220 # REVERSED ANGLE
29A4; 29A5 # ANGLE WITH UNDERBAR
29A5; 29A4 # REVERSED ANGLE WITH UNDERBAR
29A8; 29A9 # MEASURED ANGLE WITH OPEN ARM ENDING IN ARROW POINTING UP AND RIGHT
29A9; 29A8 # MEASURED ANGLE WITH OPEN ARM ENDING IN ARROW POINTING UP AND LEFT
29AA; 29AB # MEASURED ANGLE WITH OPEN ARM ENDING IN ARROW POINTING DOWN AND RIGHT
29AB; 29AA # MEASURED ANGLE WITH OPEN ARM ENDING IN ARROW POINTING DOWN AND LEFT
29AC; 29AD # MEASURED ANGLE WITH OPEN ARM ENDING IN ARROW POINTING RIGHT AND UP
29AD; 29AC # MEASURED ANGLE WITH OPEN ARM ENDING IN ARROW POINTING LEFT AND UP
29AE; 29AF # MEASURED ANGLE WITH OPEN ARM ENDING IN ARROW POINTING RIGHT AND DOWN
29AF; 29AE # MEASURED ANGLE WITH OPEN ARM ENDING IN ARROW POINTING LEFT AND DOWN
29B8; 2298 # CIRCLED REVERSE SOLIDUS
29C0; 29C1 # CIRCLED LESS-THAN
29C1; 29C0 # CIRCLED GREATER-THAN
29C4; 29C5 # SQUARED RISING DIAGONAL SLASH
29C5; 29C4 # SQUARED FALLING DIAGONAL SLASH
29CF; 29D0 # LEFT TRIANGLE BESIDE VERTICAL BAR
29D0; 29CF # VERTICAL BAR BESIDE RIGHT TRIANGLE
29D1; 29D2 # BOWTIE WITH LEFT HALF BLACK
29D2; 29D1 # BOWTIE WITH RIGHT HALF BLACK
29D4; 29D5 # TIMES WITH LEFT HALF BLACK
29D5; 29D4 # TIMES WITH RIGHT HALF BLACK
29D8; 29D9 # LEFT WIGGLY FENCE
29D9; 29D8 # RIGHT WIGGLY FENCE
29DA; 29DB # LEFT DOUBLE WIGGLY FENCE
29DB; 29DA # RIGHT DOUBLE WIGGLY FENCE
29E8; 29E9 # DOWN-POINTING TRIANGLE WITH LEFT HALF BLACK
29E9; 29E8 # DOWN-POINTING TRIANGLE WITH RIGHT HALF BLACK
29F5; 2215 # REVERSE SOLIDUS OPERATOR
29F8; 29F9 # BIG SOLIDUS
29F9; 29F8 # BIG REVERSE SOLIDUS
29FC; 29FD # LEFT-POINTING CURVED ANGLE BRACKET
29FD; 29FC # RIGHT-POINTING CURVED ANGLE BRACKET
2A2B; 2A2C # MINUS SIGN WITH FALLING DOTS
2A2C; 2A2B # MINUS SIGN WITH RISING DOTS
2A2D; 2A2E # PLUS SIGN IN LEFT HALF CIRCLE
2A2E; 2A2D # PLUS SIGN IN RIGHT HALF CIRCLE
2A34; 2A35 # MULTIPLICATION SIGN IN LEFT HALF CIRCLE
2A35; 2A34 # MULTIPLICATION SIGN IN RIGHT HALF CIRCLE
2A3C; 2A3D # INTERIOR PRODUCT
2A3D; 2A3C # RIGHTHAND INTERIOR PRODUCT
2A64; 2A65 # Z NOTATION DOMAIN ANTIRESTRICTION
2A65; 2A64 # Z NOTATION RANGE ANTIRESTRICTION
2A79; 2A7A # LESS-THAN WITH CIRCLE INSIDE
2A7A; 2A79 # GREATER-THAN WITH CIRCLE INSIDE
2A7B; 2A7C # [BEST FIT] LESS-THAN WITH QUESTION MARK ABOVE
2A7C; 2A7B # [BEST FIT] GREATER-THAN WITH QUESTION MARK ABOVE
2A7D; 2A7E # LESS-THAN OR SLANTED EQUAL TO
2A7E; 2A7D # GREATER-THAN OR SLANTED EQUAL TO
2A7F; 2A80 # LESS-THAN OR SLANTED EQUAL TO WITH DOT INSIDE
2A80; 2A7F # GREATER-THAN OR SLANTED EQUAL TO WITH DOT INSIDE
2A81; 2A82 # LESS-THAN OR SLANTED EQUAL TO WITH DOT ABOVE
2A82; 2A81 # GREATER-THAN OR SLANTED EQUAL TO WITH DOT ABOVE
2A83; 2A84 # LESS-THAN OR SLANTED EQUAL TO WITH DOT ABOVE RIGHT
2A84; 2A83 # GREATER-THAN OR SLANTED EQUAL TO WITH DOT ABOVE LEFT
2A85; 2A86 # [BEST FIT] LESS-THAN OR APPROXIMATE
2A86; 2A85 # [BEST FIT] GREATER-THAN OR APPROXIMATE
2A87; 2A88 # [BEST FIT] LESS-THAN AND SINGLE-LINE NOT EQUAL TO
2A88; 2A87 # [BEST FIT] GREATER-THAN AND SINGLE-LINE NOT EQUAL TO
2A89; 2A8A # [BEST FIT] LESS-THAN AND NOT APPROXIMATE
2A8A; 2A89 # [BEST FIT] GREATER-THAN AND NOT APPROXIMATE
2A8B; 2A8C # LESS-THAN ABOVE DOUBLE-LINE EQUAL ABOVE GREATER-THAN
2A8C; 2A8B # GREATER-THAN ABOVE DOUBLE-LINE EQUAL ABOVE LESS-THAN
2A8D; 2A8E # [BEST FIT] LESS-THAN ABOVE SIMILAR OR EQUAL
2A8E; 2A8D # [BEST FIT] GREATER-THAN ABOVE SIMILAR OR EQUAL
2A8F; 2A90 # [BEST FIT] LESS-THAN ABOVE SIMILAR ABOVE GREATER-THAN
2A90; 2A8F # [BEST FIT] GREATER-THAN ABOVE SIMILAR ABOVE LESS-THAN
2A91; 2A92 # LESS-THAN ABOVE GREATER-THAN ABOVE DOUBLE-LINE EQUAL
2A92; 2A91 # GREATER-THAN ABOVE LESS-THAN ABOVE DOUBLE-LINE EQUAL
2A93; 2A94 # LESS-THAN ABOVE SLANTED EQUAL ABOVE GREATER-THAN ABOVE SLANTED EQUAL
2A94; 2A93 # GREATER-THAN ABOVE SLANTED EQUAL ABOVE LESS-THAN ABOVE SLANTED EQUAL
2A95; 2A96 # SLANTED EQUAL TO OR LESS-THAN
2A96; 2A95 # SLANTED EQUAL TO OR GREATER-THAN
2A97; 2A98 # SLANTED EQUAL TO OR LESS-THAN WITH DOT INSIDE
2A98; 2A97 # SLANTED EQUAL TO OR GREATER-THAN WITH DOT INSIDE
2A99; 2A9A # DOUBLE-LINE EQUAL TO OR LESS-THAN
2A9A; 2A99 # DOUBLE-LINE EQUAL TO OR GREATER-THAN
2A9B; 2A9C # DOUBLE-LINE SLANTED EQUAL TO OR LESS-THAN
2A9C; 2A9B # DOUBLE-LINE SLANTED EQUAL TO OR GREATER-THAN
2A9D; 2A9E # [BEST FIT] SIMILAR OR LESS-THAN
2A9E; 2A9D # [BEST FIT] SIMILAR OR GREATER-THAN
2A9F; 2AA0 # [BEST FIT] SIMILAR ABOVE LESS-THAN ABOVE EQUALS SIGN
2AA0; 2A9F # [BEST FIT] SIMILAR ABOVE GREATER-THAN ABOVE EQUALS SIGN
2AA1; 2AA2 # DOUBLE NESTED LESS-THAN
2AA2; 2AA1 # DOUBLE NESTED GREATER-THAN
2AA6; 2AA7 # LESS-THAN CLOSED BY CURVE
2AA7; 2AA6 # GREATER-THAN CLOSED BY CURVE
2AA8; 2AA9 # LESS-THAN CLOSED BY CURVE ABOVE SLANTED EQUAL
2AA9; 2AA8 # GREATER-THAN CLOSED BY CURVE ABOVE SLANTED EQUAL
2AAA; 2AAB # SMALLER THAN
2AAB; 2AAA # LARGER THAN
2AAC; 2AAD # SMALLER THAN OR EQUAL TO
2AAD; 2AAC # LARGER THAN OR EQUAL TO
2AAF; 2AB0 # PRECEDES ABOVE SINGLE-LINE EQUALS SIGN
2AB0; 2AAF # SUCCEEDS ABOVE SINGLE-LINE EQUALS SIGN
2AB1; 2AB2 # [BEST FIT] PRECEDES ABOVE SINGLE-LINE NOT EQUAL TO
2AB2; 2AB1 # [BEST FIT] SUCCEEDS ABOVE SINGLE-LINE NOT EQUAL TO
2AB3; 2AB4 # PRECEDES ABOVE EQUALS SIGN
2AB4; 2AB3 # SUCCEEDS ABOVE EQUALS SIGN
2AB5; 2AB6 # [BEST FIT] PRECEDES ABOVE NOT EQUAL TO
2AB6; 2AB5 # [BEST FIT] SUCCEEDS ABOVE NOT EQUAL TO
2AB7; 2AB8 # [BEST FIT] PRECEDES ABOVE ALMOST EQUAL TO
2AB8; 2AB7 # [BEST FIT] SUCCEEDS ABOVE ALMOST EQUAL TO
2AB9; 2ABA # [BEST FIT] PRECEDES ABOVE NOT ALMOST EQUAL TO
2ABA; 2AB9 # [BEST FIT] SUCCEEDS ABOVE NOT ALMOST EQUAL TO
2ABB; 2ABC # DOUBLE PRECEDES
2ABC; 2ABB # DOUBLE SUCCEEDS
2ABD; 2ABE # SUBSET WITH DOT
2ABE; 2ABD # SUPERSET WITH DOT
2ABF; 2AC0 # SUBSET WITH PLUS SIGN BELOW
2AC0; 2ABF # SUPERSET WITH PLUS SIGN BELOW
2AC1; 2AC2 # SUBSET WITH MULTIPLICATION SIGN BELOW
2AC2; 2AC1 # SUPERSET WITH MULTIPLICATION SIGN BELOW
2AC3; 2AC4 # SUBSET OF OR EQUAL TO WITH DOT ABOVE
2AC4; 2AC3 # SUPERSET OF OR EQUAL TO WITH DOT ABOVE
2AC5; 2AC6 # SUBSET OF ABOVE EQUALS SIGN
2AC6; 2AC5 # SUPERSET OF ABOVE EQUALS SIGN
2AC7; 2AC8 # [BEST FIT] SUBSET OF ABOVE TILDE OPERATOR
2AC8; 2AC7 # [BEST FIT] SUPERSET OF ABOVE TILDE OPERATOR
2AC9; 2ACA # [BEST FIT] SUBSET OF ABOVE ALMOST EQUAL TO
2ACA; 2AC9 # [BEST FIT] SUPERSET OF ABOVE ALMOST EQUAL TO
2ACB; 2ACC # [BEST FIT] SUBSET OF ABOVE NOT EQUAL TO
2ACC; 2ACB # [BEST FIT] SUPERSET OF ABOVE NOT EQUAL TO
2ACD; 2ACE # SQUARE LEFT OPEN BOX OPERATOR
2ACE; 2ACD # SQUARE RIGHT OPEN BOX OPERATOR
2ACF; 2AD0 # CLOSED SUBSET
2AD0; 2ACF # CLOSED SUPERSET
2AD1; 2AD2 # CLOSED SUBSET OR EQUAL TO
2AD2; 2AD1 # CLOSED SUPERSET OR EQUAL TO
2AD3; 2AD4 # SUBSET ABOVE SUPERSET
2AD4; 2AD3 # SUPERSET ABOVE SUBSET
2AD5; 2AD6 # SUBSET ABOVE SUBSET
2AD6; 2AD5 # SUPERSET ABOVE SUPERSET
2ADE; 22A6 # SHORT LEFT TACK
2AE3; 22A9 # DOUBLE VERTICAL BAR LEFT TURNSTILE
2AE4; 22A8 # VERTICAL BAR DOUBLE LEFT TURNSTILE
2AE5; 22AB # DOUBLE VERTICAL BAR DOUBLE LEFT TURNSTILE
2AEC; 2AED # DOUBLE STROKE NOT SIGN
2AED; 2AEC # REVERSED DOUBLE STROKE NOT SIGN
2AEE; 2224 # DOES NOT DIVIDE WITH REVERSED NEGATION SLASH
2AF7; 2AF8 # TRIPLE NESTED LESS-THAN
2AF8; 2AF7 # TRIPLE NESTED GREATER-THAN
2AF9; 2AFA # DOUBLE-LINE SLANTED LESS-THAN OR EQUAL TO
2AFA; 2AF9 # DOUBLE-LINE SLANTED GREATER-THAN OR EQUAL TO
2BFE; 221F # REVERSED RIGHT ANGLE
2E02; 2E03 # LEFT SUBSTITUTION BRACKET
2E03; 2E02 # RIGHT SUBSTITUTION BRACKET
2E04; 2E05 # LEFT DOTTED SUBSTITUTION BRACKET
2E05; 2E04 # RIGHT DOTTED SUBSTITUTION BRACKET
2E09; 2E0A # LEFT TRANSPOSITION BRACKET
2E0A; 2E09 # RIGHT TRANSPOSITION BRACKET
2E0C; 2E0D # LEFT RAISED OMISSION BRACKET
2E0D; 2E0C # RIGHT RAISED OMISSION BRACKET
2E1C; 2E1D # LEFT LOW PARAPHRASE BRACKET
2E1D; 2E1C # RIGHT LOW PARAPHRASE BRACKET
2E20; 2E21 # LEFT VERTICAL BAR WITH QUILL
2E21; 2E20 # RIGHT VERTICAL BAR WITH QUILL
2E22; 2E23 # TOP LEFT HALF BRACKET
2E23; 2E22 # TOP RIGHT HALF BRACKET
2E24; 2E25 # BOTTOM LEFT HALF BRACKET
2E25; 2E24 # BOTTOM RIGHT HALF BRACKET
2E26; 2E27 # LEFT SIDEWAYS U BRACKET
2E27; 2E26 # RIGHT SIDEWAYS U BRACKET
2E28; 2E29 # LEFT DOUBLE PARENTHESIS
2E29; 2E28 # RIGHT DOUBLE PARENTHESIS
2E55; 2E56 # LEFT SQUARE BRACKET WITH STROKE
2E56; 2E55 # RIGHT SQUARE BRACKET WITH STROKE
2E57; 2E58 # LEFT SQUARE BRACKET WITH DOUBLE STROKE
2E58; 2E57 # RIGHT SQUARE BRACKET WITH DOUBLE STROKE
2E59; 2E5A # TOP HALF LEFT PARENTHESIS
2E5A; 2E59 # TOP HALF RIGHT PARENTHESIS
2E5B; 2E5C # BOTTOM HALF LEFT PARENTHESIS
2E5C; 2E5B # BOTTOM HALF RIGHT PARENTHESIS
3008; 3009 # LEFT ANGLE BRACKET
3009; 3008 # RIGHT ANGLE BRACKET
300A; 300B # LEFT DOUBLE ANGLE BRACKET
300B; 300A # RIGHT DOUBLE ANGLE BRACKET
300C; 300D # [BEST FIT] LEFT CORNER BRACKET
300D; 300C # [BEST FIT] RIGHT CORNER BRACKET
300E; 300F # [BEST FIT] LEFT WHITE CORNER BRACKET
300F; 300E # [BEST FIT] RIGHT WHITE CORNER BRACKET
3010; 3011 # LEFT BLACK LENTICULAR BRACKET
3011; 3010 # RIGHT BLACK LENTICULAR BRACKET
3014; 3015 # LEFT TORTOISE SHELL BRACKET
3015; 3014 # RIGHT TORTOISE SHELL BRACKET
3016; 3017 # LEFT WHITE LENTICULAR BRACKET
3017; 3016 # RIGHT WHITE LENTICULAR BRACKET
3018; 3019 # LEFT WHITE TORTOISE SHELL BRACKET
3019; 3018 # RIGHT WHITE TORTOISE SHELL BRACKET
301A; 301B # LEFT WHITE SQUARE BRACKET
301B; 301A # RIGHT WHITE SQUARE BRACKET
FE59; FE5A # SMALL LEFT PARENTHESIS
FE5A; FE59 # SMALL RIGHT PARENTHESIS
FE5B; FE5C # SMALL LEFT CURLY BRACKET
FE5C; FE5B # SMALL RIGHT CURLY BRACKET
FE5D; FE5E # SMALL LEFT TORTOISE SHELL BRACKET
FE5E; FE5D # SMALL RIGHT TORTOISE SHELL BRACKET
FE64; FE65 # SMALL LESS-THAN SIGN
FE65; FE64 # SMALL GREATER-THAN SIGN
FF08; FF09 # FULLWIDTH LEFT PARENTHESIS
FF09; FF08 # FULLWIDTH RIGHT PARENTHESIS
FF1C; FF1E # FULLWIDTH LESS-THAN SIGN
FF1E; FF1C # FULLWIDTH GREATER-THAN SIGN
FF3B; FF3D # FULLWIDTH LEFT SQUARE BRACKET
FF3D; FF3B # FULLWIDTH RIGHT SQUARE BRACKET
FF5B; FF5D # FULLWIDTH LEFT CURLY BRACKET
FF5D; FF5B # FULLWIDTH RIGHT CURLY BRACKET
FF5F; FF60 # FULLWIDTH LEFT WHITE PARENTHESIS
FF60; FF5F # FULLWIDTH RIGHT WHITE PARENTHESIS
FF62; FF63 # [BEST FIT] HALFWIDTH LEFT CORNER BRACKET
FF63; FF62 # [BEST FIT] HALFWIDTH RIGHT CORNER BRACKET
# The following characters have no appropriate mirroring character.
# For these characters it is up to the rendering system
# to provide mirrored glyphs.
# 2140; DOUBLE-STRUCK N-ARY SUMMATION
# 2201; COMPLEMENT
# 2202; PARTIAL DIFFERENTIAL
# 2203; THERE EXISTS
# 2204; THERE DOES NOT EXIST
# 2211; N-ARY SUMMATION
# 2216; SET MINUS
# 221A; SQUARE ROOT
# 221B; CUBE ROOT
# 221C; FOURTH ROOT
# 221D; PROPORTIONAL TO
# 2226; NOT PARALLEL TO
# 222B; INTEGRAL
# 222C; DOUBLE INTEGRAL
# 222D; TRIPLE INTEGRAL
# 222E; CONTOUR INTEGRAL
# 222F; SURFACE INTEGRAL
# 2230; VOLUME INTEGRAL
# 2231; CLOCKWISE INTEGRAL
# 2232; CLOCKWISE CONTOUR INTEGRAL
# 2233; ANTICLOCKWISE CONTOUR INTEGRAL
# 2239; EXCESS
# 223B; HOMOTHETIC
# 223E; INVERTED LAZY S
# 223F; SINE WAVE
# 2240; WREATH PRODUCT
# 2241; NOT TILDE
# 2242; MINUS TILDE
# 2244; NOT ASYMPTOTICALLY EQUAL TO
# 2246; APPROXIMATELY BUT NOT ACTUALLY EQUAL TO
# 2247; NEITHER APPROXIMATELY NOR ACTUALLY EQUAL TO
# 2248; ALMOST EQUAL TO
# 2249; NOT ALMOST EQUAL TO
# 224A; ALMOST EQUAL OR EQUAL TO
# 224B; TRIPLE TILDE
# 225F; QUESTIONED EQUAL TO
# 2260; NOT EQUAL TO
# 2262; NOT IDENTICAL TO
# 228C; MULTISET
# 22A7; MODELS
# 22AA; TRIPLE VERTICAL BAR RIGHT TURNSTILE
# 22AC; DOES NOT PROVE
# 22AD; NOT TRUE
# 22AE; DOES NOT FORCE
# 22AF; NEGATED DOUBLE VERTICAL BAR DOUBLE RIGHT TURNSTILE
# 22BE; RIGHT ANGLE WITH ARC
# 22BF; RIGHT TRIANGLE
# 22F5; ELEMENT OF WITH DOT ABOVE
# 22F8; ELEMENT OF WITH UNDERBAR
# 22F9; ELEMENT OF WITH TWO HORIZONTAL STROKES
# 22FF; Z NOTATION BAG MEMBERSHIP
# 2320; TOP HALF INTEGRAL
# 2321; BOTTOM HALF INTEGRAL
# 27C0; THREE DIMENSIONAL ANGLE
# 27CC; LONG DIVISION
# 27D3; LOWER RIGHT CORNER WITH DOT
# 27D4; UPPER LEFT CORNER WITH DOT
# 299C; RIGHT ANGLE VARIANT WITH SQUARE
# 299D; MEASURED RIGHT ANGLE WITH DOT
# 299E; ANGLE WITH S INSIDE
# 299F; ACUTE ANGLE
# 29A2; TURNED ANGLE
# 29A6; OBLIQUE ANGLE OPENING UP
# 29A7; OBLIQUE ANGLE OPENING DOWN
# 29C2; CIRCLE WITH SMALL CIRCLE TO THE RIGHT
# 29C3; CIRCLE WITH TWO HORIZONTAL STROKES TO THE RIGHT
# 29C9; TWO JOINED SQUARES
# 29CE; RIGHT TRIANGLE ABOVE LEFT TRIANGLE
# 29DC; INCOMPLETE INFINITY
# 29E1; INCREASES AS
# 29E3; EQUALS SIGN AND SLANTED PARALLEL
# 29E4; EQUALS SIGN AND SLANTED PARALLEL WITH TILDE ABOVE
# 29E5; IDENTICAL TO AND SLANTED PARALLEL
# 29F4; RULE-DELAYED
# 29F6; SOLIDUS WITH OVERBAR
# 29F7; REVERSE SOLIDUS WITH HORIZONTAL STROKE
# 2A0A; MODULO TWO SUM
# 2A0B; SUMMATION WITH INTEGRAL
# 2A0C; QUADRUPLE INTEGRAL OPERATOR
# 2A0D; FINITE PART INTEGRAL
# 2A0E; INTEGRAL WITH DOUBLE STROKE
# 2A0F; INTEGRAL AVERAGE WITH SLASH
# 2A10; CIRCULATION FUNCTION
# 2A11; ANTICLOCKWISE INTEGRATION
# 2A12; LINE INTEGRATION WITH RECTANGULAR PATH AROUND POLE
# 2A13; LINE INTEGRATION WITH SEMICIRCULAR PATH AROUND POLE
# 2A14; LINE INTEGRATION NOT INCLUDING THE POLE
# 2A15; INTEGRAL AROUND A POINT OPERATOR
# 2A16; QUATERNION INTEGRAL OPERATOR
# 2A17; INTEGRAL WITH LEFTWARDS ARROW WITH HOOK
# 2A18; INTEGRAL WITH TIMES SIGN
# 2A19; INTEGRAL WITH INTERSECTION
# 2A1A; INTEGRAL WITH UNION
# 2A1B; INTEGRAL WITH OVERBAR
# 2A1C; INTEGRAL WITH UNDERBAR
# 2A1E; LARGE LEFT TRIANGLE OPERATOR
# 2A1F; Z NOTATION SCHEMA COMPOSITION
# 2A20; Z NOTATION SCHEMA PIPING
# 2A21; Z NOTATION SCHEMA PROJECTION
# 2A24; PLUS SIGN WITH TILDE ABOVE
# 2A26; PLUS SIGN WITH TILDE BELOW
# 2A29; MINUS SIGN WITH COMMA ABOVE
# 2A3E; Z NOTATION RELATIONAL COMPOSITION
# 2A57; SLOPING LARGE OR
# 2A58; SLOPING LARGE AND
# 2A6A; TILDE OPERATOR WITH DOT ABOVE
# 2A6B; TILDE OPERATOR WITH RISING DOTS
# 2A6C; SIMILAR MINUS SIMILAR
# 2A6D; CONGRUENT WITH DOT ABOVE
# 2A6F; ALMOST EQUAL TO WITH CIRCUMFLEX ACCENT
# 2A70; APPROXIMATELY EQUAL OR EQUAL TO
# 2A73; EQUALS SIGN ABOVE TILDE OPERATOR
# 2A74; DOUBLE COLON EQUAL
# 2AA3; DOUBLE NESTED LESS-THAN WITH UNDERBAR
# 2ADC; FORKING
# 2AE2; VERTICAL BAR TRIPLE RIGHT TURNSTILE
# 2AE6; LONG DASH FROM LEFT MEMBER OF DOUBLE VERTICAL
# 2AF3; PARALLEL WITH TILDE OPERATOR
# 2AFB; TRIPLE SOLIDUS BINARY RELATION
# 2AFD; DOUBLE SOLIDUS OPERATOR
# 1D6DB; MATHEMATICAL BOLD PARTIAL DIFFERENTIAL
# 1D715; MATHEMATICAL ITALIC PARTIAL DIFFERENTIAL
# 1D74F; MATHEMATICAL BOLD ITALIC PARTIAL DIFFERENTIAL
# 1D789; MATHEMATICAL SANS-SERIF BOLD PARTIAL DIFFERENTIAL
# 1D7C3; MATHEMATICAL SANS-SERIF BOLD ITALIC PARTIAL DIFFERENTIAL
# EOF

1624
Kha/Backends/Kore-hxcpp/khacpp/project/thirdparty/pcre2-10.42-16/maint/Unicode.tables/CaseFolding.txt vendored Normal file
View File

File diff suppressed because it is too large Load Diff

2524
Kha/Backends/Kore-hxcpp/khacpp/project/thirdparty/pcre2-10.42-16/maint/Unicode.tables/DerivedBidiClass.txt vendored Normal file
View File

File diff suppressed because it is too large Load Diff

12416
Kha/Backends/Kore-hxcpp/khacpp/project/thirdparty/pcre2-10.42-16/maint/Unicode.tables/DerivedCoreProperties.txt vendored Normal file
View File

File diff suppressed because it is too large Load Diff

4192
Kha/Backends/Kore-hxcpp/khacpp/project/thirdparty/pcre2-10.42-16/maint/Unicode.tables/DerivedGeneralCategory.txt vendored Normal file
View File

File diff suppressed because it is too large Load Diff

1459
Kha/Backends/Kore-hxcpp/khacpp/project/thirdparty/pcre2-10.42-16/maint/Unicode.tables/GraphemeBreakProperty.txt vendored Normal file
View File

File diff suppressed because it is too large Load Diff

1743
Kha/Backends/Kore-hxcpp/khacpp/project/thirdparty/pcre2-10.42-16/maint/Unicode.tables/PropList.txt vendored Normal file
View File

File diff suppressed because it is too large Load Diff

212
Kha/Backends/Kore-hxcpp/khacpp/project/thirdparty/pcre2-10.42-16/maint/Unicode.tables/PropertyAliases.txt vendored Normal file
View File

@ -0,0 +1,212 @@
# PropertyAliases-14.0.0.txt
# Date: 2021-03-08, 19:35:48 GMT
# © 2021 Unicode®, Inc.
# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries.
# For terms of use, see http://www.unicode.org/terms_of_use.html
#
# Unicode Character Database
# For documentation, see http://www.unicode.org/reports/tr44/
#
# This file contains aliases for properties used in the UCD.
# These names can be used for XML formats of UCD data, for regular-expression
# property tests, and other programmatic textual descriptions of Unicode data.
#
# The names may be translated in appropriate environments, and additional
# aliases may be useful.
#
# FORMAT
#
# Each line has two or more fields, separated by semicolons.
#
# First Field: The first field is the short name for the property.
# It is typically an abbreviation, but in a number of cases it is simply
# a duplicate of the "long name" in the second field.
# For Unihan database tags, the short name is actually a longer string than
# the tag specified in the second field.
#
# Second Field: The second field is the long name for the property,
# typically the formal name used in documentation about the property.
#
# The above are the preferred aliases. Other aliases may be listed in additional fields.
#
# Loose matching should be applied to all property names and property values, with
# the exception of String Property values. With loose matching of property names and
# values, the case distinctions, whitespace, and '_' are ignored. For Numeric Property
# values, numeric equivalencies are applied: thus "01.00" is equivalent to "1".
#
# NOTE: Property value names are NOT unique across properties. For example:
#
# AL means Arabic Letter for the Bidi_Class property, and
# AL means Above_Left for the Combining_Class property, and
# AL means Alphabetic for the Line_Break property.
#
# In addition, some property names may be the same as some property value names.
# For example:
#
# sc means the Script property, and
# Sc means the General_Category property value Currency_Symbol (Sc)
#
# The combination of property value and property name is, however, unique.
#
# For more information, see UAX #44, Unicode Character Database, and
# UTS #18, Unicode Regular Expressions.
# ================================================
# ================================================
# Numeric Properties
# ================================================
cjkAccountingNumeric ; kAccountingNumeric
cjkOtherNumeric ; kOtherNumeric
cjkPrimaryNumeric ; kPrimaryNumeric
nv ; Numeric_Value
# ================================================
# String Properties
# ================================================
cf ; Case_Folding
cjkCompatibilityVariant ; kCompatibilityVariant
dm ; Decomposition_Mapping
FC_NFKC ; FC_NFKC_Closure
lc ; Lowercase_Mapping
NFKC_CF ; NFKC_Casefold
scf ; Simple_Case_Folding ; sfc
slc ; Simple_Lowercase_Mapping
stc ; Simple_Titlecase_Mapping
suc ; Simple_Uppercase_Mapping
tc ; Titlecase_Mapping
uc ; Uppercase_Mapping
# ================================================
# Miscellaneous Properties
# ================================================
bmg ; Bidi_Mirroring_Glyph
bpb ; Bidi_Paired_Bracket
cjkIICore ; kIICore
cjkIRG_GSource ; kIRG_GSource
cjkIRG_HSource ; kIRG_HSource
cjkIRG_JSource ; kIRG_JSource
cjkIRG_KPSource ; kIRG_KPSource
cjkIRG_KSource ; kIRG_KSource
cjkIRG_MSource ; kIRG_MSource
cjkIRG_SSource ; kIRG_SSource
cjkIRG_TSource ; kIRG_TSource
cjkIRG_UKSource ; kIRG_UKSource
cjkIRG_USource ; kIRG_USource
cjkIRG_VSource ; kIRG_VSource
cjkRSUnicode ; kRSUnicode ; Unicode_Radical_Stroke; URS
EqUIdeo ; Equivalent_Unified_Ideograph
isc ; ISO_Comment
JSN ; Jamo_Short_Name
na ; Name
na1 ; Unicode_1_Name
Name_Alias ; Name_Alias
scx ; Script_Extensions
# ================================================
# Catalog Properties
# ================================================
age ; Age
blk ; Block
sc ; Script
# ================================================
# Enumerated Properties
# ================================================
bc ; Bidi_Class
bpt ; Bidi_Paired_Bracket_Type
ccc ; Canonical_Combining_Class
dt ; Decomposition_Type
ea ; East_Asian_Width
gc ; General_Category
GCB ; Grapheme_Cluster_Break
hst ; Hangul_Syllable_Type
InPC ; Indic_Positional_Category
InSC ; Indic_Syllabic_Category
jg ; Joining_Group
jt ; Joining_Type
lb ; Line_Break
NFC_QC ; NFC_Quick_Check
NFD_QC ; NFD_Quick_Check
NFKC_QC ; NFKC_Quick_Check
NFKD_QC ; NFKD_Quick_Check
nt ; Numeric_Type
SB ; Sentence_Break
vo ; Vertical_Orientation
WB ; Word_Break
# ================================================
# Binary Properties
# ================================================
AHex ; ASCII_Hex_Digit
Alpha ; Alphabetic
Bidi_C ; Bidi_Control
Bidi_M ; Bidi_Mirrored
Cased ; Cased
CE ; Composition_Exclusion
CI ; Case_Ignorable
Comp_Ex ; Full_Composition_Exclusion
CWCF ; Changes_When_Casefolded
CWCM ; Changes_When_Casemapped
CWKCF ; Changes_When_NFKC_Casefolded
CWL ; Changes_When_Lowercased
CWT ; Changes_When_Titlecased
CWU ; Changes_When_Uppercased
Dash ; Dash
Dep ; Deprecated
DI ; Default_Ignorable_Code_Point
Dia ; Diacritic
EBase ; Emoji_Modifier_Base
EComp ; Emoji_Component
EMod ; Emoji_Modifier
Emoji ; Emoji
EPres ; Emoji_Presentation
Ext ; Extender
ExtPict ; Extended_Pictographic
Gr_Base ; Grapheme_Base
Gr_Ext ; Grapheme_Extend
Gr_Link ; Grapheme_Link
Hex ; Hex_Digit
Hyphen ; Hyphen
IDC ; ID_Continue
Ideo ; Ideographic
IDS ; ID_Start
IDSB ; IDS_Binary_Operator
IDST ; IDS_Trinary_Operator
Join_C ; Join_Control
LOE ; Logical_Order_Exception
Lower ; Lowercase
Math ; Math
NChar ; Noncharacter_Code_Point
OAlpha ; Other_Alphabetic
ODI ; Other_Default_Ignorable_Code_Point
OGr_Ext ; Other_Grapheme_Extend
OIDC ; Other_ID_Continue
OIDS ; Other_ID_Start
OLower ; Other_Lowercase
OMath ; Other_Math
OUpper ; Other_Uppercase
Pat_Syn ; Pattern_Syntax
Pat_WS ; Pattern_White_Space
PCM ; Prepended_Concatenation_Mark
QMark ; Quotation_Mark
Radical ; Radical
RI ; Regional_Indicator
SD ; Soft_Dotted
STerm ; Sentence_Terminal
Term ; Terminal_Punctuation
UIdeo ; Unified_Ideograph
Upper ; Uppercase
VS ; Variation_Selector
WSpace ; White_Space ; space
XIDC ; XID_Continue
XIDS ; XID_Start
XO_NFC ; Expands_On_NFC
XO_NFD ; Expands_On_NFD
XO_NFKC ; Expands_On_NFKC
XO_NFKD ; Expands_On_NFKD
# ================================================
# Total: 129
# EOF

1615
Kha/Backends/Kore-hxcpp/khacpp/project/thirdparty/pcre2-10.42-16/maint/Unicode.tables/PropertyValueAliases.txt vendored Normal file
View File

File diff suppressed because it is too large Load Diff

628
Kha/Backends/Kore-hxcpp/khacpp/project/thirdparty/pcre2-10.42-16/maint/Unicode.tables/ScriptExtensions.txt vendored Normal file
View File

@ -0,0 +1,628 @@
# ScriptExtensions-14.0.0.txt
# Date: 2021-06-04, 02:19:38 GMT
# © 2021 Unicode®, Inc.
# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries.
# For terms of use, see http://www.unicode.org/terms_of_use.html
#
# Unicode Character Database
# For documentation, see http://www.unicode.org/reports/tr44/
#
# The Script_Extensions property indicates which characters are commonly used
# with more than one script, but with a limited number of scripts.
# For each code point, there is one or more property values. Each such value is a Script property value.
# For more information, see:
# UAX #24, Unicode Script Property: https://www.unicode.org/reports/tr24/
# Especially the sections:
# https://www.unicode.org/reports/tr24/#Assignment_Script_Values
# https://www.unicode.org/reports/tr24/#Assignment_ScriptX_Values
#
# Each Script_Extensions value in this file consists of a set
# of one or more abbreviated Script property values. The ordering of the
# values in that set is not material, but for stability in presentation
# it is given here as alphabetical.
#
# The Script_Extensions values are presented in sorted order in the file.
# They are sorted first by the number of Script property values in their sets,
# and then alphabetically by first differing Script property value.
#
# Following each distinct Script_Extensions value is the list of code
# points associated with that value, listed in code point order.
#
# All code points not explicitly listed for Script_Extensions
# have as their value the corresponding Script property value
#
# @missing: 0000..10FFFF; <script>
# ================================================
# Property: Script_Extensions
# ================================================
# Script_Extensions=Beng
1CF7 ; Beng # Mc VEDIC SIGN ATIKRAMA
# Total code points: 1
# ================================================
# Script_Extensions=Deva
1CD1 ; Deva # Mn VEDIC TONE SHARA
1CD4 ; Deva # Mn VEDIC SIGN YAJURVEDIC MIDLINE SVARITA
1CDB ; Deva # Mn VEDIC TONE TRIPLE SVARITA
1CDE..1CDF ; Deva # Mn [2] VEDIC TONE TWO DOTS BELOW..VEDIC TONE THREE DOTS BELOW
1CE2..1CE8 ; Deva # Mn [7] VEDIC SIGN VISARGA SVARITA..VEDIC SIGN VISARGA ANUDATTA WITH TAIL
1CEB..1CEC ; Deva # Lo [2] VEDIC SIGN ANUSVARA VAMAGOMUKHA..VEDIC SIGN ANUSVARA VAMAGOMUKHA WITH TAIL
1CEE..1CF1 ; Deva # Lo [4] VEDIC SIGN HEXIFORM LONG ANUSVARA..VEDIC SIGN ANUSVARA UBHAYATO MUKHA
# Total code points: 18
# ================================================
# Script_Extensions=Dupl
1BCA0..1BCA3 ; Dupl # Cf [4] SHORTHAND FORMAT LETTER OVERLAP..SHORTHAND FORMAT UP STEP
# Total code points: 4
# ================================================
# Script_Extensions=Grek
0342 ; Grek # Mn COMBINING GREEK PERISPOMENI
0345 ; Grek # Mn COMBINING GREEK YPOGEGRAMMENI
1DC0..1DC1 ; Grek # Mn [2] COMBINING DOTTED GRAVE ACCENT..COMBINING DOTTED ACUTE ACCENT
# Total code points: 4
# ================================================
# Script_Extensions=Hani
3006 ; Hani # Lo IDEOGRAPHIC CLOSING MARK
303E..303F ; Hani # So [2] IDEOGRAPHIC VARIATION INDICATOR..IDEOGRAPHIC HALF FILL SPACE
3190..3191 ; Hani # So [2] IDEOGRAPHIC ANNOTATION LINKING MARK..IDEOGRAPHIC ANNOTATION REVERSE MARK
3192..3195 ; Hani # No [4] IDEOGRAPHIC ANNOTATION ONE MARK..IDEOGRAPHIC ANNOTATION FOUR MARK
3196..319F ; Hani # So [10] IDEOGRAPHIC ANNOTATION TOP MARK..IDEOGRAPHIC ANNOTATION MAN MARK
31C0..31E3 ; Hani # So [36] CJK STROKE T..CJK STROKE Q
3220..3229 ; Hani # No [10] PARENTHESIZED IDEOGRAPH ONE..PARENTHESIZED IDEOGRAPH TEN
322A..3247 ; Hani # So [30] PARENTHESIZED IDEOGRAPH MOON..CIRCLED IDEOGRAPH KOTO
3280..3289 ; Hani # No [10] CIRCLED IDEOGRAPH ONE..CIRCLED IDEOGRAPH TEN
328A..32B0 ; Hani # So [39] CIRCLED IDEOGRAPH MOON..CIRCLED IDEOGRAPH NIGHT
32C0..32CB ; Hani # So [12] IDEOGRAPHIC TELEGRAPH SYMBOL FOR JANUARY..IDEOGRAPHIC TELEGRAPH SYMBOL FOR DECEMBER
32FF ; Hani # So SQUARE ERA NAME REIWA
3358..3370 ; Hani # So [25] IDEOGRAPHIC TELEGRAPH SYMBOL FOR HOUR ZERO..IDEOGRAPHIC TELEGRAPH SYMBOL FOR HOUR TWENTY-FOUR
337B..337F ; Hani # So [5] SQUARE ERA NAME HEISEI..SQUARE CORPORATION
33E0..33FE ; Hani # So [31] IDEOGRAPHIC TELEGRAPH SYMBOL FOR DAY ONE..IDEOGRAPHIC TELEGRAPH SYMBOL FOR DAY THIRTY-ONE
1D360..1D371 ; Hani # No [18] COUNTING ROD UNIT DIGIT ONE..COUNTING ROD TENS DIGIT NINE
1F250..1F251 ; Hani # So [2] CIRCLED IDEOGRAPH ADVANTAGE..CIRCLED IDEOGRAPH ACCEPT
# Total code points: 238
# ================================================
# Script_Extensions=Latn
0363..036F ; Latn # Mn [13] COMBINING LATIN SMALL LETTER A..COMBINING LATIN SMALL LETTER X
# Total code points: 13
# ================================================
# Script_Extensions=Nand
1CFA ; Nand # Lo VEDIC SIGN DOUBLE ANUSVARA ANTARGOMUKHA
# Total code points: 1
# ================================================
# Script_Extensions=Syrc
1DFA ; Syrc # Mn COMBINING DOT BELOW LEFT
# Total code points: 1
# ================================================
# Script_Extensions=Arab Copt
102E0 ; Arab Copt # Mn COPTIC EPACT THOUSANDS MARK
102E1..102FB ; Arab Copt # No [27] COPTIC EPACT DIGIT ONE..COPTIC EPACT NUMBER NINE HUNDRED
# Total code points: 28
# ================================================
# Script_Extensions=Arab Rohg
06D4 ; Arab Rohg # Po ARABIC FULL STOP
# Total code points: 1
# ================================================
# Script_Extensions=Arab Nkoo
FD3E ; Arab Nkoo # Pe ORNATE LEFT PARENTHESIS
FD3F ; Arab Nkoo # Ps ORNATE RIGHT PARENTHESIS
# Total code points: 2
# ================================================
# Script_Extensions=Arab Syrc
064B..0655 ; Arab Syrc # Mn [11] ARABIC FATHATAN..ARABIC HAMZA BELOW
0670 ; Arab Syrc # Mn ARABIC LETTER SUPERSCRIPT ALEF
# Total code points: 12
# ================================================
# Script_Extensions=Arab Thaa
FDF2 ; Arab Thaa # Lo ARABIC LIGATURE ALLAH ISOLATED FORM
FDFD ; Arab Thaa # So ARABIC LIGATURE BISMILLAH AR-RAHMAN AR-RAHEEM
# Total code points: 2
# ================================================
# Script_Extensions=Beng Deva
1CD5..1CD6 ; Beng Deva # Mn [2] VEDIC TONE YAJURVEDIC AGGRAVATED INDEPENDENT SVARITA..VEDIC TONE YAJURVEDIC INDEPENDENT SVARITA
1CD8 ; Beng Deva # Mn VEDIC TONE CANDRA BELOW
1CE1 ; Beng Deva # Mc VEDIC TONE ATHARVAVEDIC INDEPENDENT SVARITA
1CEA ; Beng Deva # Lo VEDIC SIGN ANUSVARA BAHIRGOMUKHA
1CED ; Beng Deva # Mn VEDIC SIGN TIRYAK
1CF5..1CF6 ; Beng Deva # Lo [2] VEDIC SIGN JIHVAMULIYA..VEDIC SIGN UPADHMANIYA
A8F1 ; Beng Deva # Mn COMBINING DEVANAGARI SIGN AVAGRAHA
# Total code points: 9
# ================================================
# Script_Extensions=Bopo Hani
302A..302D ; Bopo Hani # Mn [4] IDEOGRAPHIC LEVEL TONE MARK..IDEOGRAPHIC ENTERING TONE MARK
# Total code points: 4
# ================================================
# Script_Extensions=Bugi Java
A9CF ; Bugi Java # Lm JAVANESE PANGRANGKEP
# Total code points: 1
# ================================================
# Script_Extensions=Cprt Linb
10102 ; Cprt Linb # Po AEGEAN CHECK MARK
10137..1013F ; Cprt Linb # So [9] AEGEAN WEIGHT BASE UNIT..AEGEAN MEASURE THIRD SUBUNIT
# Total code points: 10
# ================================================
# Script_Extensions=Cyrl Glag
0484 ; Cyrl Glag # Mn COMBINING CYRILLIC PALATALIZATION
0487 ; Cyrl Glag # Mn COMBINING CYRILLIC POKRYTIE
2E43 ; Cyrl Glag # Po DASH WITH LEFT UPTURN
A66F ; Cyrl Glag # Mn COMBINING CYRILLIC VZMET
# Total code points: 4
# ================================================
# Script_Extensions=Cyrl Latn
0485..0486 ; Cyrl Latn # Mn [2] COMBINING CYRILLIC DASIA PNEUMATA..COMBINING CYRILLIC PSILI PNEUMATA
# Total code points: 2
# ================================================
# Script_Extensions=Cyrl Perm
0483 ; Cyrl Perm # Mn COMBINING CYRILLIC TITLO
# Total code points: 1
# ================================================
# Script_Extensions=Cyrl Syrc
1DF8 ; Cyrl Syrc # Mn COMBINING DOT ABOVE LEFT
# Total code points: 1
# ================================================
# Script_Extensions=Deva Gran
1CD3 ; Deva Gran # Po VEDIC SIGN NIHSHVASA
1CF3 ; Deva Gran # Lo VEDIC SIGN ROTATED ARDHAVISARGA
1CF8..1CF9 ; Deva Gran # Mn [2] VEDIC TONE RING ABOVE..VEDIC TONE DOUBLE RING ABOVE
# Total code points: 4
# ================================================
# Script_Extensions=Deva Nand
1CE9 ; Deva Nand # Lo VEDIC SIGN ANUSVARA ANTARGOMUKHA
# Total code points: 1
# ================================================
# Script_Extensions=Deva Shrd
1CD7 ; Deva Shrd # Mn VEDIC TONE YAJURVEDIC KATHAKA INDEPENDENT SVARITA
1CD9 ; Deva Shrd # Mn VEDIC TONE YAJURVEDIC KATHAKA INDEPENDENT SVARITA SCHROEDER
1CDC..1CDD ; Deva Shrd # Mn [2] VEDIC TONE KATHAKA ANUDATTA..VEDIC TONE DOT BELOW
1CE0 ; Deva Shrd # Mn VEDIC TONE RIGVEDIC KASHMIRI INDEPENDENT SVARITA
# Total code points: 5
# ================================================
# Script_Extensions=Deva Taml
A8F3 ; Deva Taml # Lo DEVANAGARI SIGN CANDRABINDU VIRAMA
# Total code points: 1
# ================================================
# Script_Extensions=Geor Latn
10FB ; Geor Latn # Po GEORGIAN PARAGRAPH SEPARATOR
# Total code points: 1
# ================================================
# Script_Extensions=Gran Taml
0BE6..0BEF ; Gran Taml # Nd [10] TAMIL DIGIT ZERO..TAMIL DIGIT NINE
0BF0..0BF2 ; Gran Taml # No [3] TAMIL NUMBER TEN..TAMIL NUMBER ONE THOUSAND
0BF3 ; Gran Taml # So TAMIL DAY SIGN
11301 ; Gran Taml # Mn GRANTHA SIGN CANDRABINDU
11303 ; Gran Taml # Mc GRANTHA SIGN VISARGA
1133B..1133C ; Gran Taml # Mn [2] COMBINING BINDU BELOW..GRANTHA SIGN NUKTA
11FD0..11FD1 ; Gran Taml # No [2] TAMIL FRACTION ONE QUARTER..TAMIL FRACTION ONE HALF-1
11FD3 ; Gran Taml # No TAMIL FRACTION THREE QUARTERS
# Total code points: 21
# ================================================
# Script_Extensions=Gujr Khoj
0AE6..0AEF ; Gujr Khoj # Nd [10] GUJARATI DIGIT ZERO..GUJARATI DIGIT NINE
# Total code points: 10
# ================================================
# Script_Extensions=Guru Mult
0A66..0A6F ; Guru Mult # Nd [10] GURMUKHI DIGIT ZERO..GURMUKHI DIGIT NINE
# Total code points: 10
# ================================================
# Script_Extensions=Hani Latn
A700..A707 ; Hani Latn # Sk [8] MODIFIER LETTER CHINESE TONE YIN PING..MODIFIER LETTER CHINESE TONE YANG RU
# Total code points: 8
# ================================================
# Script_Extensions=Hira Kana
3031..3035 ; Hira Kana # Lm [5] VERTICAL KANA REPEAT MARK..VERTICAL KANA REPEAT MARK LOWER HALF
3099..309A ; Hira Kana # Mn [2] COMBINING KATAKANA-HIRAGANA VOICED SOUND MARK..COMBINING KATAKANA-HIRAGANA SEMI-VOICED SOUND MARK
309B..309C ; Hira Kana # Sk [2] KATAKANA-HIRAGANA VOICED SOUND MARK..KATAKANA-HIRAGANA SEMI-VOICED SOUND MARK
30A0 ; Hira Kana # Pd KATAKANA-HIRAGANA DOUBLE HYPHEN
30FC ; Hira Kana # Lm KATAKANA-HIRAGANA PROLONGED SOUND MARK
FF70 ; Hira Kana # Lm HALFWIDTH KATAKANA-HIRAGANA PROLONGED SOUND MARK
FF9E..FF9F ; Hira Kana # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDTH KATAKANA SEMI-VOICED SOUND MARK
# Total code points: 14
# ================================================
# Script_Extensions=Knda Nand
0CE6..0CEF ; Knda Nand # Nd [10] KANNADA DIGIT ZERO..KANNADA DIGIT NINE
# Total code points: 10
# ================================================
# Script_Extensions=Latn Mong
202F ; Latn Mong # Zs NARROW NO-BREAK SPACE
# Total code points: 1
# ================================================
# Script_Extensions=Mani Ougr
10AF2 ; Mani Ougr # Po MANICHAEAN PUNCTUATION DOUBLE DOT WITHIN DOT
# Total code points: 1
# ================================================
# Script_Extensions=Mong Phag
1802..1803 ; Mong Phag # Po [2] MONGOLIAN COMMA..MONGOLIAN FULL STOP
1805 ; Mong Phag # Po MONGOLIAN FOUR DOTS
# Total code points: 3
# ================================================
# Script_Extensions=Arab Syrc Thaa
061C ; Arab Syrc Thaa # Cf ARABIC LETTER MARK
# Total code points: 1
# ================================================
# Script_Extensions=Arab Thaa Yezi
0660..0669 ; Arab Thaa Yezi # Nd [10] ARABIC-INDIC DIGIT ZERO..ARABIC-INDIC DIGIT NINE
# Total code points: 10
# ================================================
# Script_Extensions=Beng Cakm Sylo
09E6..09EF ; Beng Cakm Sylo # Nd [10] BENGALI DIGIT ZERO..BENGALI DIGIT NINE
# Total code points: 10
# ================================================
# Script_Extensions=Cakm Mymr Tale
1040..1049 ; Cakm Mymr Tale # Nd [10] MYANMAR DIGIT ZERO..MYANMAR DIGIT NINE
# Total code points: 10
# ================================================
# Script_Extensions=Cpmn Cprt Linb
10100..10101 ; Cpmn Cprt Linb # Po [2] AEGEAN WORD SEPARATOR LINE..AEGEAN WORD SEPARATOR DOT
# Total code points: 2
# ================================================
# Script_Extensions=Cprt Lina Linb
10107..10133 ; Cprt Lina Linb # No [45] AEGEAN NUMBER ONE..AEGEAN NUMBER NINETY THOUSAND
# Total code points: 45
# ================================================
# Script_Extensions=Deva Gran Knda
1CF4 ; Deva Gran Knda # Mn VEDIC TONE CANDRA ABOVE
# Total code points: 1
# ================================================
# Script_Extensions=Deva Gran Latn
20F0 ; Deva Gran Latn # Mn COMBINING ASTERISK ABOVE
# Total code points: 1
# ================================================
# Script_Extensions=Hani Hira Kana
303C ; Hani Hira Kana # Lo MASU MARK
303D ; Hani Hira Kana # Po PART ALTERNATION MARK
# Total code points: 2
# ================================================
# Script_Extensions=Kali Latn Mymr
A92E ; Kali Latn Mymr # Po KAYAH LI SIGN CWI
# Total code points: 1
# ================================================
# Script_Extensions=Beng Deva Gran Knda
1CD0 ; Beng Deva Gran Knda # Mn VEDIC TONE KARSHANA
1CD2 ; Beng Deva Gran Knda # Mn VEDIC TONE PRENKHA
# Total code points: 2
# ================================================
# Script_Extensions=Buhd Hano Tagb Tglg
1735..1736 ; Buhd Hano Tagb Tglg # Po [2] PHILIPPINE SINGLE PUNCTUATION..PHILIPPINE DOUBLE PUNCTUATION
# Total code points: 2
# ================================================
# Script_Extensions=Deva Dogr Kthi Mahj
0966..096F ; Deva Dogr Kthi Mahj # Nd [10] DEVANAGARI DIGIT ZERO..DEVANAGARI DIGIT NINE
# Total code points: 10
# ================================================
# Script_Extensions=Bopo Hang Hani Hira Kana
3003 ; Bopo Hang Hani Hira Kana # Po DITTO MARK
3013 ; Bopo Hang Hani Hira Kana # So GETA MARK
301C ; Bopo Hang Hani Hira Kana # Pd WAVE DASH
301D ; Bopo Hang Hani Hira Kana # Ps REVERSED DOUBLE PRIME QUOTATION MARK
301E..301F ; Bopo Hang Hani Hira Kana # Pe [2] DOUBLE PRIME QUOTATION MARK..LOW DOUBLE PRIME QUOTATION MARK
3030 ; Bopo Hang Hani Hira Kana # Pd WAVY DASH
3037 ; Bopo Hang Hani Hira Kana # So IDEOGRAPHIC TELEGRAPH LINE FEED SEPARATOR SYMBOL
FE45..FE46 ; Bopo Hang Hani Hira Kana # Po [2] SESAME DOT..WHITE SESAME DOT
# Total code points: 10
# ================================================
# Script_Extensions=Arab Nkoo Rohg Syrc Thaa Yezi
060C ; Arab Nkoo Rohg Syrc Thaa Yezi # Po ARABIC COMMA
061B ; Arab Nkoo Rohg Syrc Thaa Yezi # Po ARABIC SEMICOLON
# Total code points: 2
# ================================================
# Script_Extensions=Bopo Hang Hani Hira Kana Yiii
3001..3002 ; Bopo Hang Hani Hira Kana Yiii # Po [2] IDEOGRAPHIC COMMA..IDEOGRAPHIC FULL STOP
3008 ; Bopo Hang Hani Hira Kana Yiii # Ps LEFT ANGLE BRACKET
3009 ; Bopo Hang Hani Hira Kana Yiii # Pe RIGHT ANGLE BRACKET
300A ; Bopo Hang Hani Hira Kana Yiii # Ps LEFT DOUBLE ANGLE BRACKET
300B ; Bopo Hang Hani Hira Kana Yiii # Pe RIGHT DOUBLE ANGLE BRACKET
300C ; Bopo Hang Hani Hira Kana Yiii # Ps LEFT CORNER BRACKET
300D ; Bopo Hang Hani Hira Kana Yiii # Pe RIGHT CORNER BRACKET
300E ; Bopo Hang Hani Hira Kana Yiii # Ps LEFT WHITE CORNER BRACKET
300F ; Bopo Hang Hani Hira Kana Yiii # Pe RIGHT WHITE CORNER BRACKET
3010 ; Bopo Hang Hani Hira Kana Yiii # Ps LEFT BLACK LENTICULAR BRACKET
3011 ; Bopo Hang Hani Hira Kana Yiii # Pe RIGHT BLACK LENTICULAR BRACKET
3014 ; Bopo Hang Hani Hira Kana Yiii # Ps LEFT TORTOISE SHELL BRACKET
3015 ; Bopo Hang Hani Hira Kana Yiii # Pe RIGHT TORTOISE SHELL BRACKET
3016 ; Bopo Hang Hani Hira Kana Yiii # Ps LEFT WHITE LENTICULAR BRACKET
3017 ; Bopo Hang Hani Hira Kana Yiii # Pe RIGHT WHITE LENTICULAR BRACKET
3018 ; Bopo Hang Hani Hira Kana Yiii # Ps LEFT WHITE TORTOISE SHELL BRACKET
3019 ; Bopo Hang Hani Hira Kana Yiii # Pe RIGHT WHITE TORTOISE SHELL BRACKET
301A ; Bopo Hang Hani Hira Kana Yiii # Ps LEFT WHITE SQUARE BRACKET
301B ; Bopo Hang Hani Hira Kana Yiii # Pe RIGHT WHITE SQUARE BRACKET
30FB ; Bopo Hang Hani Hira Kana Yiii # Po KATAKANA MIDDLE DOT
FF61 ; Bopo Hang Hani Hira Kana Yiii # Po HALFWIDTH IDEOGRAPHIC FULL STOP
FF62 ; Bopo Hang Hani Hira Kana Yiii # Ps HALFWIDTH LEFT CORNER BRACKET
FF63 ; Bopo Hang Hani Hira Kana Yiii # Pe HALFWIDTH RIGHT CORNER BRACKET
FF64..FF65 ; Bopo Hang Hani Hira Kana Yiii # Po [2] HALFWIDTH IDEOGRAPHIC COMMA..HALFWIDTH KATAKANA MIDDLE DOT
# Total code points: 26
# ================================================
# Script_Extensions=Deva Knda Mlym Orya Taml Telu
1CDA ; Deva Knda Mlym Orya Taml Telu # Mn VEDIC TONE DOUBLE SVARITA
# Total code points: 1
# ================================================
# Script_Extensions=Adlm Arab Nkoo Rohg Syrc Thaa Yezi
061F ; Adlm Arab Nkoo Rohg Syrc Thaa Yezi # Po ARABIC QUESTION MARK
# Total code points: 1
# ================================================
# Script_Extensions=Beng Deva Gran Knda Nand Orya Telu Tirh
1CF2 ; Beng Deva Gran Knda Nand Orya Telu Tirh # Lo VEDIC SIGN ARDHAVISARGA
# Total code points: 1
# ================================================
# Script_Extensions=Adlm Arab Mand Mani Ougr Phlp Rohg Sogd Syrc
0640 ; Adlm Arab Mand Mani Ougr Phlp Rohg Sogd Syrc # Lm ARABIC TATWEEL
# Total code points: 1
# ================================================
# Script_Extensions=Deva Dogr Gujr Guru Khoj Kthi Mahj Modi Sind Takr Tirh
A836..A837 ; Deva Dogr Gujr Guru Khoj Kthi Mahj Modi Sind Takr Tirh # So [2] NORTH INDIC QUARTER MARK..NORTH INDIC PLACEHOLDER MARK
A838 ; Deva Dogr Gujr Guru Khoj Kthi Mahj Modi Sind Takr Tirh # Sc NORTH INDIC RUPEE MARK
A839 ; Deva Dogr Gujr Guru Khoj Kthi Mahj Modi Sind Takr Tirh # So NORTH INDIC QUANTITY MARK
# Total code points: 4
# ================================================
# Script_Extensions=Beng Deva Gran Gujr Guru Knda Latn Mlym Orya Taml Telu Tirh
0952 ; Beng Deva Gran Gujr Guru Knda Latn Mlym Orya Taml Telu Tirh # Mn DEVANAGARI STRESS SIGN ANUDATTA
# Total code points: 1
# ================================================
# Script_Extensions=Beng Deva Gran Gujr Guru Knda Latn Mlym Orya Shrd Taml Telu Tirh
0951 ; Beng Deva Gran Gujr Guru Knda Latn Mlym Orya Shrd Taml Telu Tirh # Mn DEVANAGARI STRESS SIGN UDATTA
# Total code points: 1
# ================================================
# Script_Extensions=Deva Dogr Gujr Guru Khoj Knda Kthi Mahj Modi Nand Sind Takr Tirh
A833..A835 ; Deva Dogr Gujr Guru Khoj Knda Kthi Mahj Modi Nand Sind Takr Tirh # No [3] NORTH INDIC FRACTION ONE SIXTEENTH..NORTH INDIC FRACTION THREE SIXTEENTHS
# Total code points: 3
# ================================================
# Script_Extensions=Deva Dogr Gujr Guru Khoj Knda Kthi Mahj Mlym Modi Nand Sind Takr Tirh
A830..A832 ; Deva Dogr Gujr Guru Khoj Knda Kthi Mahj Mlym Modi Nand Sind Takr Tirh # No [3] NORTH INDIC FRACTION ONE QUARTER..NORTH INDIC FRACTION THREE QUARTERS
# Total code points: 3
# ================================================
# Script_Extensions=Beng Deva Dogr Gong Gonm Gran Gujr Guru Knda Mahj Mlym Nand Orya Sind Sinh Sylo Takr Taml Telu Tirh
0964 ; Beng Deva Dogr Gong Gonm Gran Gujr Guru Knda Mahj Mlym Nand Orya Sind Sinh Sylo Takr Taml Telu Tirh # Po DEVANAGARI DANDA
# Total code points: 1
# ================================================
# Script_Extensions=Beng Deva Dogr Gong Gonm Gran Gujr Guru Knda Limb Mahj Mlym Nand Orya Sind Sinh Sylo Takr Taml Telu Tirh
0965 ; Beng Deva Dogr Gong Gonm Gran Gujr Guru Knda Limb Mahj Mlym Nand Orya Sind Sinh Sylo Takr Taml Telu Tirh # Po DEVANAGARI DOUBLE DANDA
# Total code points: 1
# EOF

2991
Kha/Backends/Kore-hxcpp/khacpp/project/thirdparty/pcre2-10.42-16/maint/Unicode.tables/Scripts.txt vendored Normal file
View File

File diff suppressed because it is too large Load Diff

34626
Kha/Backends/Kore-hxcpp/khacpp/project/thirdparty/pcre2-10.42-16/maint/Unicode.tables/UnicodeData.txt vendored Normal file
View File

File diff suppressed because it is too large Load Diff

1297
Kha/Backends/Kore-hxcpp/khacpp/project/thirdparty/pcre2-10.42-16/maint/Unicode.tables/emoji-data.txt vendored Normal file
View File

File diff suppressed because it is too large Load Diff

141
Kha/Backends/Kore-hxcpp/khacpp/project/thirdparty/pcre2-10.42-16/maint/pcre2_chartables.c.non-standard vendored Normal file
View File

@ -0,0 +1,141 @@
const unsigned char _pcre_default_tables[] = {
0,1,2,3,4,5,6,7,
8,9,10,11,12,13,14,15,
16,17,18,19,20,21,22,23,
24,25,26,27,28,29,30,31,
32,33,34,35,36,37,38,39,
40,41,42,43,44,45,46,47,
48,49,50,51,52,53,54,55,
56,57,58,59,60,61,62,63,
64,97,98,99,100,101,102,103,
104,105,106,107,108,109,110,111,
112,113,114,115,116,117,118,119,
120,121,122,91,92,93,94,95,
96,97,98,99,100,101,102,103,
104,105,106,107,108,109,110,111,
112,113,114,115,116,117,118,119,
120,121,122,123,124,125,126,127,
128,129,130,131,132,133,134,135,
136,137,138,139,140,141,142,143,
144,145,146,147,148,149,150,151,
152,153,154,155,156,157,158,159,
160,161,162,163,164,165,166,167,
168,169,170,171,172,173,174,175,
176,177,178,179,180,181,182,183,
184,185,186,187,188,189,190,191,
224,225,226,227,228,229,230,231,
232,233,234,235,236,237,238,239,
240,241,242,243,244,245,246,215,
248,249,250,251,252,253,254,223,
224,225,226,227,228,229,230,231,
232,233,234,235,236,237,238,239,
240,241,242,243,244,245,246,247,
248,249,250,251,252,253,254,255,
0,1,2,3,4,5,6,7,
8,9,10,11,12,13,14,15,
16,17,18,19,20,21,22,23,
24,25,26,27,28,29,30,31,
32,33,34,35,36,37,38,39,
40,41,42,43,44,45,46,47,
48,49,50,51,52,53,54,55,
56,57,58,59,60,61,62,63,
64,97,98,99,100,101,102,103,
104,105,106,107,108,109,110,111,
112,113,114,115,116,117,118,119,
120,121,122,91,92,93,94,95,
96,65,66,67,68,69,70,71,
72,73,74,75,76,77,78,79,
80,81,82,83,84,85,86,87,
88,89,90,123,124,125,126,127,
128,129,130,131,132,133,134,135,
136,137,138,139,140,141,142,143,
144,145,146,147,148,149,150,151,
152,153,154,155,156,157,158,159,
160,161,162,163,164,165,166,167,
168,169,170,171,172,173,174,175,
176,177,178,179,180,181,182,183,
184,185,186,187,188,189,190,191,
224,225,226,227,228,229,230,231,
232,233,234,235,236,237,238,239,
240,241,242,243,244,245,246,215,
248,249,250,251,252,253,254,223,
192,193,194,195,196,197,198,199,
200,201,202,203,204,205,206,207,
208,209,210,211,212,213,214,247,
216,217,218,219,220,221,222,255,
0,62,0,0,1,0,0,0,
0,0,0,0,0,0,0,0,
32,0,0,0,1,0,0,0,
0,0,0,0,0,0,0,0,
0,0,0,0,0,0,255,3,
126,0,0,0,126,0,0,0,
0,0,0,0,0,0,0,0,
0,0,0,0,0,0,0,0,
0,0,0,0,0,0,255,3,
0,0,0,0,0,0,0,0,
0,0,0,0,0,0,12,2,
0,0,0,0,0,0,0,0,
0,0,0,0,0,0,0,0,
254,255,255,7,0,0,0,0,
0,0,0,0,0,0,0,0,
255,255,127,127,0,0,0,0,
0,0,0,0,0,0,0,0,
0,0,0,0,254,255,255,7,
0,0,0,0,0,4,32,4,
0,0,0,128,255,255,127,255,
0,0,0,0,0,0,255,3,
254,255,255,135,254,255,255,7,
0,0,0,0,0,4,44,6,
255,255,127,255,255,255,127,255,
0,0,0,0,254,255,255,255,
255,255,255,255,255,255,255,127,
0,0,0,0,254,255,255,255,
255,255,255,255,255,255,255,255,
0,2,0,0,255,255,255,255,
255,255,255,255,255,255,255,127,
0,0,0,0,255,255,255,255,
255,255,255,255,255,255,255,255,
0,0,0,0,254,255,0,252,
1,0,0,248,1,0,0,120,
0,0,0,0,254,255,255,255,
0,0,128,0,0,0,128,0,
255,255,255,255,0,0,0,0,
0,0,0,0,0,0,0,128,
255,255,255,255,0,0,0,0,
0,0,0,0,0,0,0,0,
/* Fiddled by hand when the table bits changed. May be broken! */
128,0,0,0,0,0,0,0,
0,1,1,1,1,1,0,0,
0,0,0,0,0,0,0,0,
0,0,0,0,0,0,0,0,
1,0,0,0,128,0,0,0,
128,128,128,128,0,0,128,0,
24,24,24,24,24,24,24,24,
24,24,0,0,0,0,0,128,
0,18,18,18,18,18,18,18,
18,18,18,18,18,18,18,18,
18,18,18,18,18,18,18,18,
18,18,18,128,128,0,128,16,
0,18,18,18,18,18,18,18,
18,18,18,18,18,18,18,18,
18,18,18,18,18,18,18,18,
18,18,18,128,128,0,0,0,
0,0,0,0,0,1,0,0,
0,0,0,0,0,0,0,0,
0,0,0,0,0,0,0,0,
0,0,0,0,0,0,0,0,
1,0,0,0,0,0,0,0,
0,0,18,0,0,0,0,0,
0,0,24,24,0,18,0,0,
0,24,18,0,0,0,0,0,
18,18,18,18,18,18,18,18,
18,18,18,18,18,18,18,18,
18,18,18,18,18,18,18,0,
18,18,18,18,18,18,18,18,
18,18,18,18,18,18,18,18,
18,18,18,18,18,18,18,18,
18,18,18,18,18,18,18,0,
18,18,18,18,18,18,18,18
};

1086
Kha/Backends/Kore-hxcpp/khacpp/project/thirdparty/pcre2-10.42-16/maint/ucptest.c vendored Normal file
View File

File diff suppressed because it is too large Load Diff

50
Kha/Backends/Kore-hxcpp/khacpp/project/thirdparty/pcre2-10.42-16/maint/ucptestdata/testinput1 vendored Normal file
View File

@ -0,0 +1,50 @@
findprop 00 01 02 03 04 05 06 07 08 09 0a 0b 0c 0d 0e 0f
findprop 10 11 12 13 14 15 16 17 18 19 1a 1b 1c 1d 1e 1f
findprop 20 21 22 23 24 25 26 27 28 29 2a 2b 2c 2d 2e 2f
findprop 30 31 32 33 34 35 36 37 38 39 3a 3b 3c 3d 3e 3f
findprop 40 41 42 43 44 45 46 47 48 49 4a 4b 4c 4d 4e 4f
findprop 50 51 52 53 54 55 56 57 58 59 5a 5b 5c 5d 5e 5f
findprop 60 61 62 63 64 65 66 67 68 69 6a 6b 6c 6d 6e 6f
findprop 70 71 72 73 74 75 76 77 78 79 7a 7b 7c 7d 7e 7f
findprop 80 81 82 83 84 85 86 87 88 89 8a 8b 8c 8d 8e 8f
findprop 90 91 92 93 94 95 96 97 98 99 9a 9b 9c 9d 9e 9f
findprop a0 a1 a2 a3 a4 a5 a6 a7 a8 a9 aa ab ac ad ae af
findprop b0 b1 b2 b3 b4 b5 b6 b7 b8 b9 ba bb bc bd be bf
findprop c0 c1 c2 c3 c4 c5 c6 c7 c8 c9 ca cb cc cd ce cf
findprop d0 d1 d2 d3 d4 d5 d6 d7 d8 d9 da db dc dd de df
findprop e0 e1 e2 e3 e4 e5 e6 e7 e8 e9 ea eb ec ed ee ef
findprop f0 f1 f2 f3 f4 f5 f6 f7 f8 f9 fa fb fc fd fe ff
findprop 0100 0101 0102 0103 0104 0105 0106
findprop ffe0 ffe1 ffe2 ffe3 ffe4 ffe5 ffe6 ffe7
findprop ffe8 ffe9 ffea ffeb ffec ffed ffee ffef
findprop fff8 fff9 fffa fffb fffc fffd fffe ffff
findprop 10000 10001 e01ef f0000 100000
findprop 1b00 12000 7c0 a840 10900
findprop 1d79 a77d
findprop 0800 083e a4d0 a4f7 aa80 aadf
findprop 10b00 10b35 13000 1342e 10840 10855
findprop 11100 1113c 11680 116c0
findprop 0d 0a 0e 0711 1b04 1111 1169 11fe ae4c ad89
findprop 118a0 11ac7 16ad0
findprop 11700 14400 108e0 11280 1d800
findprop 11800 1e903 11da9 10d27 11ee0 16e48 10f27 10f30
findprop a836 a833 1cf4 20f0 1cd0
findprop 32ff
findprop 1f16d
findprop U+10e93 U+10eaa
findprop 0602 202a 202b 202c 2068 2069 202d 202e 2067

19
Kha/Backends/Kore-hxcpp/khacpp/project/thirdparty/pcre2-10.42-16/maint/ucptestdata/testinput2 vendored Normal file
View File

@ -0,0 +1,19 @@
find script Han
find type Pe script Common scriptx Hangul
find type Sk
find type Pd
find gbreak LVT
find script Old_Uyghur
find bidi PDF
find bidi CS
find bidi CS type Sm
find bidi B
find bidi FSI
find bidi PDI
find bidi RLI
find bidi RLO
find bidi S
find bidi WS
find script bopo
find bool prependedconcatenationmark
find bool pcm

409
Kha/Backends/Kore-hxcpp/khacpp/project/thirdparty/pcre2-10.42-16/maint/ucptestdata/testoutput1 vendored Normal file
View File

@ -0,0 +1,409 @@
findprop 00 01 02 03 04 05 06 07 08 09 0a 0b 0c 0d 0e 0f
U+0000 BN Control: Control, common, Control, [ascii, patternwhitespace, whitespace]
U+0001 BN Control: Control, common, Control, [ascii, patternwhitespace, whitespace]
U+0002 BN Control: Control, common, Control, [ascii, patternwhitespace, whitespace]
U+0003 BN Control: Control, common, Control, [ascii, patternwhitespace, whitespace]
U+0004 BN Control: Control, common, Control, [ascii, patternwhitespace, whitespace]
U+0005 BN Control: Control, common, Control, [ascii, patternwhitespace, whitespace]
U+0006 BN Control: Control, common, Control, [ascii, patternwhitespace, whitespace]
U+0007 BN Control: Control, common, Control, [ascii, patternwhitespace, whitespace]
U+0008 BN Control: Control, common, Control, [ascii, patternwhitespace, whitespace]
U+0009 S Control: Control, common, Control, [ascii, graphemebase, patternsyntax, sentenceterminal, terminalpunctuation]
U+000A B Control: Control, common, LF, [ascii, graphemebase, patternsyntax, sentenceterminal, terminalpunctuation]
U+000B S Control: Control, common, Control, [ascii, graphemebase, patternsyntax, sentenceterminal, terminalpunctuation]
U+000C WS Control: Control, common, Control, [ascii, graphemebase, patternsyntax, sentenceterminal, terminalpunctuation]
U+000D B Control: Control, common, CR, [ascii, graphemebase, patternsyntax, sentenceterminal, terminalpunctuation]
U+000E BN Control: Control, common, Control, [ascii, patternwhitespace, whitespace]
U+000F BN Control: Control, common, Control, [ascii, patternwhitespace, whitespace]
findprop 10 11 12 13 14 15 16 17 18 19 1a 1b 1c 1d 1e 1f
U+0010 BN Control: Control, common, Control, [ascii, patternwhitespace, whitespace]
U+0011 BN Control: Control, common, Control, [ascii, patternwhitespace, whitespace]
U+0012 BN Control: Control, common, Control, [ascii, patternwhitespace, whitespace]
U+0013 BN Control: Control, common, Control, [ascii, patternwhitespace, whitespace]
U+0014 BN Control: Control, common, Control, [ascii, patternwhitespace, whitespace]
U+0015 BN Control: Control, common, Control, [ascii, patternwhitespace, whitespace]
U+0016 BN Control: Control, common, Control, [ascii, patternwhitespace, whitespace]
U+0017 BN Control: Control, common, Control, [ascii, patternwhitespace, whitespace]
U+0018 BN Control: Control, common, Control, [ascii, patternwhitespace, whitespace]
U+0019 BN Control: Control, common, Control, [ascii, patternwhitespace, whitespace]
U+001A BN Control: Control, common, Control, [ascii, patternwhitespace, whitespace]
U+001B BN Control: Control, common, Control, [ascii, patternwhitespace, whitespace]
U+001C B Control: Control, common, Control, [ascii, patternwhitespace, whitespace]
U+001D B Control: Control, common, Control, [ascii, patternwhitespace, whitespace]
U+001E B Control: Control, common, Control, [ascii, patternwhitespace, whitespace]
U+001F S Control: Control, common, Control, [ascii, patternwhitespace, whitespace]
findprop 20 21 22 23 24 25 26 27 28 29 2a 2b 2c 2d 2e 2f
U+0020 WS Separator: Space separator, common, Other, [ascii, emoji, emojicomponent, graphemebase, patternsyntax]
U+0021 ON Punctuation: Other punctuation, common, Other, [ascii, caseignorable, graphemebase, patternsyntax, quotationmark]
U+0022 ON Punctuation: Other punctuation, common, Other, [ascii, graphemebase, math, patternsyntax]
U+0023 ET Punctuation: Other punctuation, common, Other, [ascii, dash, graphemebase, patternsyntax]
U+0024 ET Symbol: Currency symbol, common, Other, [ascii, asciihexdigit, emoji, emojicomponent, graphemebase, hexdigit, idcontinue, xidcontinue]
U+0025 ET Punctuation: Other punctuation, common, Other, [ascii, asciihexdigit, emoji, emojicomponent, graphemebase, hexdigit, idcontinue, xidcontinue]
U+0026 ON Punctuation: Other punctuation, common, Other, [ascii, asciihexdigit, emoji, emojicomponent, graphemebase, hexdigit, idcontinue, xidcontinue]
U+0027 ON Punctuation: Other punctuation, common, Other, [ascii, bidimirrored, graphemebase, math, patternsyntax]
U+0028 ON Punctuation: Open punctuation, common, Other, [ascii, alphabetic, cased, changeswhencasefolded, changeswhencasemapped, changeswhenlowercased, graphemebase, idcontinue, idstart, uppercase, xidcontinue, xidstart]
U+0029 ON Punctuation: Close punctuation, common, Other, [ascii, alphabetic, cased, changeswhencasefolded, changeswhencasemapped, changeswhenlowercased, graphemebase, idcontinue, idstart, uppercase, xidcontinue, xidstart]
U+002A ON Punctuation: Other punctuation, common, Other, [ascii, dash, graphemebase, patternsyntax]
U+002B ES Symbol: Mathematical symbol, common, Other, [ascii, graphemebase, idcontinue, xidcontinue]
U+002C CS Punctuation: Other punctuation, common, Other, [ascii, asciihexdigit, alphabetic, cased, changeswhencasemapped, changeswhentitlecased, changeswhenuppercased, graphemebase, hexdigit, idcontinue, idstart, lowercase, xidcontinue, xidstart]
U+002D ES Punctuation: Dash punctuation, common, Other, [ascii, alphabetic, cased, changeswhencasemapped, changeswhentitlecased, changeswhenuppercased, graphemebase, idcontinue, idstart, lowercase, softdotted, xidcontinue, xidstart]
U+002E CS Punctuation: Other punctuation, common, Other, [graphemebase, whitespace]
U+002F CS Punctuation: Other punctuation, common, Other, [ascii, asciihexdigit, emoji, emojicomponent, graphemebase, hexdigit, idcontinue, xidcontinue]
findprop 30 31 32 33 34 35 36 37 38 39 3a 3b 3c 3d 3e 3f
U+0030 EN Number: Decimal number, common, Other, [caseignorable, diacritic, graphemebase]
U+0031 EN Number: Decimal number, common, Other, [caseignorable, diacritic, graphemebase]
U+0032 EN Number: Decimal number, common, Other, [caseignorable, diacritic, graphemebase]
U+0033 EN Number: Decimal number, common, Other, [caseignorable, diacritic, graphemebase]
U+0034 EN Number: Decimal number, common, Other, [caseignorable, diacritic, graphemebase]
U+0035 EN Number: Decimal number, common, Other, [caseignorable, diacritic, graphemebase]
U+0036 EN Number: Decimal number, common, Other, [caseignorable, diacritic, graphemebase]
U+0037 EN Number: Decimal number, common, Other, [caseignorable, diacritic, graphemebase]
U+0038 EN Number: Decimal number, common, Other, [caseignorable, diacritic, graphemebase]
U+0039 EN Number: Decimal number, common, Other, [caseignorable, diacritic, graphemebase]
U+003A CS Punctuation: Other punctuation, common, Other, [alphabetic, cased, graphemebase, idcontinue, idstart, lowercase, xidcontinue, xidstart]
U+003B ON Punctuation: Other punctuation, common, Other, [ascii, asciihexdigit, alphabetic, cased, changeswhencasemapped, changeswhentitlecased, changeswhenuppercased, graphemebase, hexdigit, idcontinue, idstart, lowercase, xidcontinue, xidstart]
U+003C ON Symbol: Mathematical symbol, common, Other, [graphemebase, math, patternsyntax]
U+003D ON Symbol: Mathematical symbol, common, Other, [ascii, graphemebase, idcontinue, xidcontinue]
U+003E ON Symbol: Mathematical symbol, common, Other, [graphemebase, math, patternsyntax]
U+003F ON Punctuation: Other punctuation, common, Other, [ascii, caseignorable, graphemebase, patternsyntax, quotationmark]
findprop 40 41 42 43 44 45 46 47 48 49 4a 4b 4c 4d 4e 4f
U+0040 ON Punctuation: Other punctuation, common, Other, [ascii, asciihexdigit, emoji, emojicomponent, graphemebase, hexdigit, idcontinue, xidcontinue]
U+0041 L Letter: Upper case letter, latin, Other, U+0061, [graphemebase]
U+0042 L Letter: Upper case letter, latin, Other, U+0062, [graphemebase]
U+0043 L Letter: Upper case letter, latin, Other, U+0063, [graphemebase]
U+0044 L Letter: Upper case letter, latin, Other, U+0064, [graphemebase]
U+0045 L Letter: Upper case letter, latin, Other, U+0065, [graphemebase]
U+0046 L Letter: Upper case letter, latin, Other, U+0066, [graphemebase]
U+0047 L Letter: Upper case letter, latin, Other, U+0067, [caseignorable, diacritic, extender, graphemebase, idcontinue, xidcontinue]
U+0048 L Letter: Upper case letter, latin, Other, U+0068, [caseignorable, diacritic, extender, graphemebase, idcontinue, xidcontinue]
U+0049 L Letter: Upper case letter, latin, Other, U+0069, [caseignorable, diacritic, extender, graphemebase, idcontinue, xidcontinue]
U+004A L Letter: Upper case letter, latin, Other, U+006A, [caseignorable, diacritic, extender, graphemebase, idcontinue, xidcontinue]
U+004B L Letter: Upper case letter, latin, Other, U+006B, U+212A, [caseignorable, diacritic, extender, graphemebase, idcontinue, xidcontinue]
U+004C L Letter: Upper case letter, latin, Other, U+006C, [caseignorable, diacritic, extender, graphemebase, idcontinue, xidcontinue]
U+004D L Letter: Upper case letter, latin, Other, U+006D, [caseignorable, diacritic, extender, graphemebase, idcontinue, xidcontinue]
U+004E L Letter: Upper case letter, latin, Other, U+006E, [caseignorable, diacritic, extender, graphemebase, idcontinue, xidcontinue]
U+004F L Letter: Upper case letter, latin, Other, U+006F, [caseignorable, diacritic, extender, graphemebase, idcontinue, xidcontinue]
findprop 50 51 52 53 54 55 56 57 58 59 5a 5b 5c 5d 5e 5f
U+0050 L Letter: Upper case letter, latin, Other, U+0070, [caseignorable, diacritic, extender, graphemebase, idcontinue, xidcontinue]
U+0051 L Letter: Upper case letter, latin, Other, U+0071, [caseignorable, diacritic, extender, graphemebase, idcontinue, xidcontinue]
U+0052 L Letter: Upper case letter, latin, Other, U+0072, [caseignorable, diacritic, extender, graphemebase, idcontinue, xidcontinue]
U+0053 L Letter: Upper case letter, latin, Other, U+0073, U+017F, [caseignorable, diacritic, extender, graphemebase, idcontinue, xidcontinue]
U+0054 L Letter: Upper case letter, latin, Other, U+0074, [caseignorable, diacritic, extender, graphemebase, idcontinue, xidcontinue]
U+0055 L Letter: Upper case letter, latin, Other, U+0075, [caseignorable, diacritic, extender, graphemebase, idcontinue, xidcontinue]
U+0056 L Letter: Upper case letter, latin, Other, U+0076, [caseignorable, diacritic, extender, graphemebase, idcontinue, xidcontinue]
U+0057 L Letter: Upper case letter, latin, Other, U+0077, [caseignorable, diacritic, extender, graphemebase, idcontinue, xidcontinue]
U+0058 L Letter: Upper case letter, latin, Other, U+0078, [caseignorable, diacritic, extender, graphemebase, idcontinue, xidcontinue]
U+0059 L Letter: Upper case letter, latin, Other, U+0079, [caseignorable, diacritic, extender, graphemebase, idcontinue, xidcontinue]
U+005A L Letter: Upper case letter, latin, Other, U+007A, [caseignorable, diacritic, extender, graphemebase, idcontinue, xidcontinue]
U+005B ON Punctuation: Open punctuation, common, Other, [ascii, alphabetic, cased, changeswhencasefolded, changeswhencasemapped, changeswhenlowercased, graphemebase, idcontinue, idstart, uppercase, xidcontinue, xidstart]
U+005C ON Punctuation: Other punctuation, common, Other, [ascii, asciihexdigit, emoji, emojicomponent, graphemebase, hexdigit, idcontinue, xidcontinue]
U+005D ON Punctuation: Close punctuation, common, Other, [ascii, alphabetic, cased, changeswhencasefolded, changeswhencasemapped, changeswhenlowercased, graphemebase, idcontinue, idstart, uppercase, xidcontinue, xidstart]
U+005E ON Symbol: Modifier symbol, common, Other, [alphabetic, cased, changeswhencasemapped, changeswhentitlecased, changeswhenuppercased, graphemebase, idcontinue, idstart, lowercase, xidcontinue, xidstart]
U+005F ON Punctuation: Connector punctuation, common, Other, [alphabetic, cased, changeswhencasefolded, changeswhencasemapped, changeswhentitlecased, changeswhenuppercased, deprecated, graphemebase, idcontinue, idstart, lowercase, xidcontinue, xidstart]
findprop 60 61 62 63 64 65 66 67 68 69 6a 6b 6c 6d 6e 6f
U+0060 ON Symbol: Modifier symbol, common, Other, [alphabetic, cased, changeswhencasefolded, changeswhencasemapped, changeswhenlowercased, changeswhentitlecased, graphemebase, idcontinue, idstart, uppercase, xidcontinue, xidstart]
U+0061 L Letter: Lower case letter, latin, Other, U+0041, [alphabetic, caseignorable, cased, diacritic, graphemebase, idcontinue, idstart, lowercase, xidcontinue, xidstart]
U+0062 L Letter: Lower case letter, latin, Other, U+0042, [alphabetic, caseignorable, cased, diacritic, graphemebase, idcontinue, idstart, lowercase, xidcontinue, xidstart]
U+0063 L Letter: Lower case letter, latin, Other, U+0043, [alphabetic, caseignorable, cased, diacritic, graphemebase, idcontinue, idstart, lowercase, xidcontinue, xidstart]
U+0064 L Letter: Lower case letter, latin, Other, U+0044, [alphabetic, caseignorable, cased, diacritic, graphemebase, idcontinue, idstart, lowercase, xidcontinue, xidstart]
U+0065 L Letter: Lower case letter, latin, Other, U+0045, [alphabetic, caseignorable, cased, diacritic, graphemebase, idcontinue, idstart, lowercase, xidcontinue, xidstart]
U+0066 L Letter: Lower case letter, latin, Other, U+0046, [alphabetic, caseignorable, cased, diacritic, graphemebase, idcontinue, idstart, lowercase, xidcontinue, xidstart]
U+0067 L Letter: Lower case letter, latin, Other, U+0047, [alphabetic, caseignorable, diacritic, graphemebase, idcontinue, idstart, xidcontinue, xidstart]
U+0068 L Letter: Lower case letter, latin, Other, U+0048, [alphabetic, caseignorable, diacritic, graphemebase, idcontinue, idstart, xidcontinue, xidstart]
U+0069 L Letter: Lower case letter, latin, Other, U+0049, [caseignorable, diacritic, graphemeextend, idcontinue, xidcontinue]
U+006A L Letter: Lower case letter, latin, Other, U+004A, [caseignorable, diacritic, graphemeextend, idcontinue, xidcontinue]
U+006B L Letter: Lower case letter, latin, Other, U+004B, U+212A, [alphabetic, caseignorable, diacritic, graphemebase, idcontinue, idstart, xidcontinue, xidstart]
U+006C L Letter: Lower case letter, latin, Other, U+004C, [alphabetic, caseignorable, diacritic, graphemebase, idcontinue, idstart, xidcontinue, xidstart]
U+006D L Letter: Lower case letter, latin, Other, U+004D, [alphabetic, caseignorable, diacritic, graphemebase, idcontinue, idstart, xidcontinue, xidstart]
U+006E L Letter: Lower case letter, latin, Other, U+004E, [alphabetic, caseignorable, diacritic, graphemebase, idcontinue, idstart, xidcontinue, xidstart]
U+006F L Letter: Lower case letter, latin, Other, U+004F, [alphabetic, caseignorable, diacritic, graphemebase, idcontinue, idstart, xidcontinue, xidstart]
findprop 70 71 72 73 74 75 76 77 78 79 7a 7b 7c 7d 7e 7f
U+0070 L Letter: Lower case letter, latin, Other, U+0050, [alphabetic, caseignorable, diacritic, graphemebase, idcontinue, idstart, xidcontinue, xidstart]
U+0071 L Letter: Lower case letter, latin, Other, U+0051, [alphabetic, caseignorable, diacritic, graphemebase, idcontinue, idstart, xidcontinue, xidstart]
U+0072 L Letter: Lower case letter, latin, Other, U+0052, [alphabetic, caseignorable, diacritic, graphemebase, idcontinue, idstart, xidcontinue, xidstart]
U+0073 L Letter: Lower case letter, latin, Other, U+0053, U+017F, [alphabetic, caseignorable, diacritic, graphemebase, idcontinue, idstart, xidcontinue, xidstart]
U+0074 L Letter: Lower case letter, latin, Other, U+0054, [alphabetic, caseignorable, diacritic, graphemebase, idcontinue, idstart, xidcontinue, xidstart]
U+0075 L Letter: Lower case letter, latin, Other, U+0055, [alphabetic, caseignorable, diacritic, graphemebase, idcontinue, idstart, xidcontinue, xidstart]
U+0076 L Letter: Lower case letter, latin, Other, U+0056, [alphabetic, caseignorable, diacritic, graphemebase, idcontinue, idstart, xidcontinue, xidstart]
U+0077 L Letter: Lower case letter, latin, Other, U+0057, [alphabetic, caseignorable, diacritic, graphemebase, idcontinue, idstart, xidcontinue, xidstart]
U+0078 L Letter: Lower case letter, latin, Other, U+0058, [alphabetic, caseignorable, diacritic, graphemebase, idcontinue, idstart, xidcontinue, xidstart]
U+0079 L Letter: Lower case letter, latin, Other, U+0059, [alphabetic, caseignorable, diacritic, graphemebase, idcontinue, idstart, xidcontinue, xidstart]
U+007A L Letter: Lower case letter, latin, Other, U+005A, [alphabetic, caseignorable, diacritic, graphemebase, idcontinue, idstart, xidcontinue, xidstart]
U+007B ON Punctuation: Open punctuation, common, Other, [ascii, alphabetic, cased, changeswhencasefolded, changeswhencasemapped, changeswhenlowercased, graphemebase, idcontinue, idstart, uppercase, xidcontinue, xidstart]
U+007C ON Symbol: Mathematical symbol, common, Other, [ascii, graphemebase, idcontinue, xidcontinue]
U+007D ON Punctuation: Close punctuation, common, Other, [ascii, alphabetic, cased, changeswhencasefolded, changeswhencasemapped, changeswhenlowercased, graphemebase, idcontinue, idstart, uppercase, xidcontinue, xidstart]
U+007E ON Symbol: Mathematical symbol, common, Other, [ascii, graphemebase, idcontinue, xidcontinue]
U+007F BN Control: Control, common, Control, [ascii, patternwhitespace, whitespace]
findprop 80 81 82 83 84 85 86 87 88 89 8a 8b 8c 8d 8e 8f
U+0080 BN Control: Control, common, Control
U+0081 BN Control: Control, common, Control
U+0082 BN Control: Control, common, Control
U+0083 BN Control: Control, common, Control
U+0084 BN Control: Control, common, Control
U+0085 B Control: Control, common, Control, [caseignorable, defaultignorablecodepoint, graphemeextend, idcontinue, xidcontinue]
U+0086 BN Control: Control, common, Control
U+0087 BN Control: Control, common, Control
U+0088 BN Control: Control, common, Control
U+0089 BN Control: Control, common, Control
U+008A BN Control: Control, common, Control
U+008B BN Control: Control, common, Control
U+008C BN Control: Control, common, Control
U+008D BN Control: Control, common, Control
U+008E BN Control: Control, common, Control
U+008F BN Control: Control, common, Control
findprop 90 91 92 93 94 95 96 97 98 99 9a 9b 9c 9d 9e 9f
U+0090 BN Control: Control, common, Control
U+0091 BN Control: Control, common, Control
U+0092 BN Control: Control, common, Control
U+0093 BN Control: Control, common, Control
U+0094 BN Control: Control, common, Control
U+0095 BN Control: Control, common, Control
U+0096 BN Control: Control, common, Control
U+0097 BN Control: Control, common, Control
U+0098 BN Control: Control, common, Control
U+0099 BN Control: Control, common, Control
U+009A BN Control: Control, common, Control
U+009B BN Control: Control, common, Control
U+009C BN Control: Control, common, Control
U+009D BN Control: Control, common, Control
U+009E BN Control: Control, common, Control
U+009F BN Control: Control, common, Control
findprop a0 a1 a2 a3 a4 a5 a6 a7 a8 a9 aa ab ac ad ae af
U+00A0 CS Separator: Space separator, common, Other, [alphabetic, caseignorable, cased, diacritic, graphemebase, idcontinue, idstart, lowercase]
U+00A1 ON Punctuation: Other punctuation, common, Other, [caseignorable, graphemebase, idcontinue, terminalpunctuation, xidcontinue]
U+00A2 ET Symbol: Currency symbol, common, Other, [caseignorable, graphemebase, idcontinue, terminalpunctuation, xidcontinue]
U+00A3 ET Symbol: Currency symbol, common, Other, [caseignorable, graphemebase, idcontinue, terminalpunctuation, xidcontinue]
U+00A4 ET Symbol: Currency symbol, common, Other, [caseignorable, graphemebase, idcontinue, terminalpunctuation, xidcontinue]
U+00A5 ET Symbol: Currency symbol, common, Other, [caseignorable, graphemebase, idcontinue, terminalpunctuation, xidcontinue]
U+00A6 ON Symbol: Other symbol, common, Other, [caseignorable, graphemebase, idcontinue, terminalpunctuation, xidcontinue]
U+00A7 ON Punctuation: Other punctuation, common, Other, [caseignorable, graphemebase, idcontinue, terminalpunctuation, xidcontinue]
U+00A8 ON Symbol: Modifier symbol, common, Other, [alphabetic, cased, graphemebase, idcontinue, idstart, math, uppercase, xidcontinue, xidstart]
U+00A9 ON Symbol: Other symbol, common, Extended Pictographic, [alphabetic, cased, changeswhencasefolded, changeswhencasemapped, changeswhenlowercased, graphemebase, idcontinue, idstart, math, uppercase, xidcontinue, xidstart]
U+00AA L Letter: Other letter, latin, Other, [caseignorable, graphemeextend]
U+00AB ON Punctuation: Initial punctuation, common, Other, [graphemebase, sentenceterminal, terminalpunctuation]
U+00AC ON Symbol: Mathematical symbol, common, Other, [alphabetic, caseignorable, diacritic, graphemeextend, idcontinue, xidcontinue]
U+00AD BN Control: Format, common, Control, [caseignorable, prependedconcatenationmark]
U+00AE ON Symbol: Other symbol, common, Extended Pictographic, [alphabetic, cased, changeswhencasefolded, changeswhencasemapped, changeswhenlowercased, graphemebase, idcontinue, idstart, math, uppercase, xidcontinue, xidstart]
U+00AF ON Symbol: Modifier symbol, common, Other, [alphabetic, cased, graphemebase, idcontinue, idstart, math, uppercase, xidcontinue, xidstart]
findprop b0 b1 b2 b3 b4 b5 b6 b7 b8 b9 ba bb bc bd be bf
U+00B0 ET Symbol: Other symbol, common, Other, [caseignorable, graphemebase, idcontinue, terminalpunctuation, xidcontinue]
U+00B1 ET Symbol: Mathematical symbol, common, Other, [alphabetic, caseignorable, diacritic, graphemeextend, idcontinue, xidcontinue]
U+00B2 EN Number: Other number, common, Other, [alphabetic, caseignorable, extender, graphemebase, idcontinue, idstart, xidcontinue, xidstart]
U+00B3 EN Number: Other number, common, Other, [alphabetic, caseignorable, extender, graphemebase, idcontinue, idstart, xidcontinue, xidstart]
U+00B4 ON Symbol: Modifier symbol, common, Other, [alphabetic, cased, graphemebase, idcontinue, idstart, math, uppercase, xidcontinue, xidstart]
U+00B5 L Letter: Lower case letter, common, Other, U+03BC, U+039C, [alphabetic, deprecated, graphemebase, idcontinue, idstart, xidcontinue, xidstart]
U+00B6 ON Punctuation: Other punctuation, common, Other, [caseignorable, graphemebase, idcontinue, terminalpunctuation, xidcontinue]
U+00B7 ON Punctuation: Other punctuation, common, Other, [alphabetic, graphemebase, idcontinue, xidcontinue]
U+00B8 ON Symbol: Modifier symbol, common, Other, [alphabetic, cased, graphemebase, idcontinue, idstart, math, uppercase, xidcontinue, xidstart]
U+00B9 EN Number: Other number, common, Other, [alphabetic, caseignorable, extender, graphemebase, idcontinue, idstart, xidcontinue, xidstart]
U+00BA L Letter: Other letter, latin, Other, [caseignorable, graphemeextend]
U+00BB ON Punctuation: Final punctuation, common, Other, [graphemebase, sentenceterminal, terminalpunctuation]
U+00BC ON Number: Other number, common, Other, [alphabetic, caseignorable, extender, graphemebase, idcontinue, idstart, xidcontinue, xidstart]
U+00BD ON Number: Other number, common, Other, [alphabetic, caseignorable, extender, graphemebase, idcontinue, idstart, xidcontinue, xidstart]
U+00BE ON Number: Other number, common, Other, [alphabetic, caseignorable, extender, graphemebase, idcontinue, idstart, xidcontinue, xidstart]
U+00BF ON Punctuation: Other punctuation, common, Other, [caseignorable, graphemebase, idcontinue, terminalpunctuation, xidcontinue]
findprop c0 c1 c2 c3 c4 c5 c6 c7 c8 c9 ca cb cc cd ce cf
U+00C0 L Letter: Upper case letter, latin, Other, U+00E0, [alphabetic, graphemeextend, idcontinue, xidcontinue]
U+00C1 L Letter: Upper case letter, latin, Other, U+00E1, [alphabetic, graphemeextend, idcontinue, xidcontinue]
U+00C2 L Letter: Upper case letter, latin, Other, U+00E2, [alphabetic, graphemeextend, idcontinue, xidcontinue]
U+00C3 L Letter: Upper case letter, latin, Other, U+00E3, [alphabetic, graphemeextend, idcontinue, xidcontinue]
U+00C4 L Letter: Upper case letter, latin, Other, U+00E4, [alphabetic, graphemeextend, idcontinue, xidcontinue]
U+00C5 L Letter: Upper case letter, latin, Other, U+00E5, U+212B, [alphabetic, graphemeextend, idcontinue, xidcontinue]
U+00C6 L Letter: Upper case letter, latin, Other, U+00E6, [alphabetic, graphemeextend, idcontinue, xidcontinue]
U+00C7 L Letter: Upper case letter, latin, Other, U+00E7, [alphabetic, graphemeextend, idcontinue, xidcontinue]
U+00C8 L Letter: Upper case letter, latin, Other, U+00E8, [alphabetic, graphemeextend, idcontinue, xidcontinue]
U+00C9 L Letter: Upper case letter, latin, Other, U+00E9, [alphabetic, graphemeextend, idcontinue, xidcontinue]
U+00CA L Letter: Upper case letter, latin, Other, U+00EA, [alphabetic, graphemeextend, idcontinue, xidcontinue]
U+00CB L Letter: Upper case letter, latin, Other, U+00EB, [alphabetic, graphemeextend, idcontinue, xidcontinue]
U+00CC L Letter: Upper case letter, latin, Other, U+00EC, [alphabetic, graphemeextend, idcontinue, xidcontinue]
U+00CD L Letter: Upper case letter, latin, Other, U+00ED, [alphabetic, graphemeextend, idcontinue, xidcontinue]
U+00CE L Letter: Upper case letter, latin, Other, U+00EE, [alphabetic, graphemeextend, idcontinue, xidcontinue]
U+00CF L Letter: Upper case letter, latin, Other, U+00EF, [alphabetic, graphemeextend, idcontinue, xidcontinue]
findprop d0 d1 d2 d3 d4 d5 d6 d7 d8 d9 da db dc dd de df
U+00D0 L Letter: Upper case letter, latin, Other, U+00F0, [alphabetic, graphemeextend, idcontinue, xidcontinue]
U+00D1 L Letter: Upper case letter, latin, Other, U+00F1, [alphabetic, graphemeextend, idcontinue, xidcontinue]
U+00D2 L Letter: Upper case letter, latin, Other, U+00F2, [alphabetic, graphemeextend, idcontinue, xidcontinue]
U+00D3 L Letter: Upper case letter, latin, Other, U+00F3, [alphabetic, graphemeextend, idcontinue, xidcontinue]
U+00D4 L Letter: Upper case letter, latin, Other, U+00F4, [alphabetic, graphemeextend, idcontinue, xidcontinue]
U+00D5 L Letter: Upper case letter, latin, Other, U+00F5, [alphabetic, graphemeextend, idcontinue, xidcontinue]
U+00D6 L Letter: Upper case letter, latin, Other, U+00F6, [alphabetic, graphemeextend, idcontinue, xidcontinue]
U+00D7 ON Symbol: Mathematical symbol, common, Other, [alphabetic, caseignorable, diacritic, graphemeextend, idcontinue, xidcontinue]
U+00D8 L Letter: Upper case letter, latin, Other, U+00F8, [alphabetic, graphemeextend, idcontinue, xidcontinue]
U+00D9 L Letter: Upper case letter, latin, Other, U+00F9, [alphabetic, graphemeextend, idcontinue, xidcontinue]
U+00DA L Letter: Upper case letter, latin, Other, U+00FA, [alphabetic, graphemeextend, idcontinue, xidcontinue]
U+00DB L Letter: Upper case letter, latin, Other, U+00FB, [alphabetic, graphemeextend, idcontinue, xidcontinue]
U+00DC L Letter: Upper case letter, latin, Other, U+00FC, [alphabetic, graphemeextend, idcontinue, xidcontinue]
U+00DD L Letter: Upper case letter, latin, Other, U+00FD, [alphabetic, graphemeextend, idcontinue, xidcontinue]
U+00DE L Letter: Upper case letter, latin, Other, U+00FE, [alphabetic, graphemeextend, idcontinue, xidcontinue]
U+00DF L Letter: Lower case letter, latin, Other, U+1E9E, [alphabetic, deprecated, graphemebase, idcontinue, idstart, xidcontinue, xidstart]
findprop e0 e1 e2 e3 e4 e5 e6 e7 e8 e9 ea eb ec ed ee ef
U+00E0 L Letter: Lower case letter, latin, Other, U+00C0, [alphabetic, graphemebase, idcontinue, idstart, xidcontinue]
U+00E1 L Letter: Lower case letter, latin, Other, U+00C1, [alphabetic, graphemebase, idcontinue, idstart, xidcontinue]
U+00E2 L Letter: Lower case letter, latin, Other, U+00C2, [alphabetic, graphemebase, idcontinue, idstart, xidcontinue]
U+00E3 L Letter: Lower case letter, latin, Other, U+00C3, [alphabetic, graphemebase, idcontinue, idstart, xidcontinue]
U+00E4 L Letter: Lower case letter, latin, Other, U+00C4, [alphabetic, graphemebase, idcontinue, idstart, xidcontinue]
U+00E5 L Letter: Lower case letter, latin, Other, U+00C5, U+212B, [alphabetic, graphemebase, idcontinue, idstart, xidcontinue]
U+00E6 L Letter: Lower case letter, latin, Other, U+00C6, [alphabetic, graphemebase, idcontinue, idstart, xidcontinue]
U+00E7 L Letter: Lower case letter, latin, Other, U+00C7, [alphabetic, graphemebase, idcontinue, idstart, xidcontinue]
U+00E8 L Letter: Lower case letter, latin, Other, U+00C8, [alphabetic, graphemebase, idcontinue, idstart, xidcontinue]
U+00E9 L Letter: Lower case letter, latin, Other, U+00C9, [alphabetic, graphemebase, idcontinue, idstart, xidcontinue]
U+00EA L Letter: Lower case letter, latin, Other, U+00CA, [alphabetic, graphemebase, idcontinue, idstart, xidcontinue]
U+00EB L Letter: Lower case letter, latin, Other, U+00CB, [alphabetic, graphemebase, idcontinue, idstart, xidcontinue]
U+00EC L Letter: Lower case letter, latin, Other, U+00CC, [alphabetic, graphemebase, idcontinue, idstart, xidcontinue]
U+00ED L Letter: Lower case letter, latin, Other, U+00CD, [alphabetic, graphemebase, idcontinue, idstart, xidcontinue]
U+00EE L Letter: Lower case letter, latin, Other, U+00CE, [alphabetic, graphemebase, idcontinue, idstart, xidcontinue]
U+00EF L Letter: Lower case letter, latin, Other, U+00CF, [alphabetic, graphemebase, idcontinue, idstart, xidcontinue]
findprop f0 f1 f2 f3 f4 f5 f6 f7 f8 f9 fa fb fc fd fe ff
U+00F0 L Letter: Lower case letter, latin, Other, U+00D0, [alphabetic, graphemebase, idcontinue, idstart, xidcontinue]
U+00F1 L Letter: Lower case letter, latin, Other, U+00D1, [alphabetic, graphemebase, idcontinue, idstart, xidcontinue]
U+00F2 L Letter: Lower case letter, latin, Other, U+00D2, [alphabetic, graphemebase, idcontinue, idstart, xidcontinue]
U+00F3 L Letter: Lower case letter, latin, Other, U+00D3, [alphabetic, graphemebase, idcontinue, idstart, xidcontinue]
U+00F4 L Letter: Lower case letter, latin, Other, U+00D4, [alphabetic, graphemebase, idcontinue, idstart, xidcontinue]
U+00F5 L Letter: Lower case letter, latin, Other, U+00D5, [alphabetic, graphemebase, idcontinue, idstart, xidcontinue]
U+00F6 L Letter: Lower case letter, latin, Other, U+00D6, [alphabetic, graphemebase, idcontinue, idstart, xidcontinue]
U+00F7 ON Symbol: Mathematical symbol, common, Other, [alphabetic, caseignorable, diacritic, graphemeextend, idcontinue, xidcontinue]
U+00F8 L Letter: Lower case letter, latin, Other, U+00D8, [alphabetic, graphemebase, idcontinue, idstart, xidcontinue]
U+00F9 L Letter: Lower case letter, latin, Other, U+00D9, [alphabetic, graphemebase, idcontinue, idstart, xidcontinue]
U+00FA L Letter: Lower case letter, latin, Other, U+00DA, [alphabetic, graphemebase, idcontinue, idstart, xidcontinue]
U+00FB L Letter: Lower case letter, latin, Other, U+00DB, [alphabetic, graphemebase, idcontinue, idstart, xidcontinue]
U+00FC L Letter: Lower case letter, latin, Other, U+00DC, [alphabetic, graphemebase, idcontinue, idstart, xidcontinue]
U+00FD L Letter: Lower case letter, latin, Other, U+00DD, [alphabetic, graphemebase, idcontinue, idstart, xidcontinue]
U+00FE L Letter: Lower case letter, latin, Other, U+00DE, [alphabetic, graphemebase, idcontinue, idstart, xidcontinue]
U+00FF L Letter: Lower case letter, latin, Other, U+0178, [alphabetic, graphemebase, idcontinue, idstart, xidcontinue]
findprop 0100 0101 0102 0103 0104 0105 0106
U+0100 L Letter: Upper case letter, latin, Other, U+0101, [alphabetic, graphemeextend, idcontinue, xidcontinue]
U+0101 L Letter: Lower case letter, latin, Other, U+0100, [alphabetic, graphemebase, idcontinue, idstart, xidcontinue]
U+0102 L Letter: Upper case letter, latin, Other, U+0103, [alphabetic, graphemeextend, idcontinue, xidcontinue]
U+0103 L Letter: Lower case letter, latin, Other, U+0102, [alphabetic, graphemebase, idcontinue, idstart, xidcontinue]
U+0104 L Letter: Upper case letter, latin, Other, U+0105, [alphabetic, graphemeextend, idcontinue, xidcontinue]
U+0105 L Letter: Lower case letter, latin, Other, U+0104, [alphabetic, graphemebase, idcontinue, idstart, xidcontinue]
U+0106 L Letter: Upper case letter, latin, Other, U+0107, [alphabetic, graphemeextend, idcontinue, xidcontinue]
findprop ffe0 ffe1 ffe2 ffe3 ffe4 ffe5 ffe6 ffe7
U+FFE0 ET Symbol: Currency symbol, common, Other, [alphabetic, caseignorable, extender, graphemebase, idcontinue, idstart, xidcontinue, xidstart]
U+FFE1 ET Symbol: Currency symbol, common, Other, [alphabetic, caseignorable, extender, graphemebase, idcontinue, idstart, xidcontinue, xidstart]
U+FFE2 ON Symbol: Mathematical symbol, common, Other, [emoji, extendedpictographic, graphemebase]
U+FFE3 ON Symbol: Modifier symbol, common, Other, [alphabetic, cased, graphemebase, idcontinue, idstart, math, uppercase, xidcontinue, xidstart]
U+FFE4 ON Symbol: Other symbol, common, Other, [alphabetic, caseignorable, extender, graphemebase, idcontinue, idstart, xidcontinue, xidstart]
U+FFE5 ET Symbol: Currency symbol, common, Other, [alphabetic, caseignorable, extender, graphemebase, idcontinue, idstart, xidcontinue, xidstart]
U+FFE6 ET Symbol: Currency symbol, common, Other, [alphabetic, caseignorable, extender, graphemebase, idcontinue, idstart, xidcontinue, xidstart]
U+FFE7 L Control: Unassigned, unknown, Other
findprop ffe8 ffe9 ffea ffeb ffec ffed ffee ffef
U+FFE8 ON Symbol: Other symbol, common, Other, [alphabetic, caseignorable, extender, graphemebase, idcontinue, idstart, xidcontinue, xidstart]
U+FFE9 ON Symbol: Mathematical symbol, common, Other, [emoji, extendedpictographic, graphemebase]
U+FFEA ON Symbol: Mathematical symbol, common, Other, [emoji, extendedpictographic, graphemebase]
U+FFEB ON Symbol: Mathematical symbol, common, Other, [emoji, extendedpictographic, graphemebase]
U+FFEC ON Symbol: Mathematical symbol, common, Other, [emoji, extendedpictographic, graphemebase]
U+FFED ON Symbol: Other symbol, common, Other, [alphabetic, caseignorable, extender, graphemebase, idcontinue, idstart, xidcontinue, xidstart]
U+FFEE ON Symbol: Other symbol, common, Other, [alphabetic, caseignorable, extender, graphemebase, idcontinue, idstart, xidcontinue, xidstart]
U+FFEF L Control: Unassigned, unknown, Other
findprop fff8 fff9 fffa fffb fffc fffd fffe ffff
U+FFF8 BN Control: Unassigned, unknown, Control, [dash, defaultignorablecodepoint, deprecated, extendedpictographic, joincontrol, lowercase, patternwhitespace, quotationmark, sentenceterminal, softdotted, xidcontinue, xidstart]
U+FFF9 ON Control: Format, common, Control, [changeswhenuppercased, deprecated, emojimodifier, emojipresentation, extender, sentenceterminal, xidcontinue, xidstart]
U+FFFA ON Control: Format, common, Control, [changeswhenuppercased, deprecated, emojimodifier, emojipresentation, extender, sentenceterminal, xidcontinue, xidstart]
U+FFFB ON Control: Format, common, Control, [changeswhenuppercased, deprecated, emojimodifier, emojipresentation, extender, sentenceterminal, xidcontinue, xidstart]
U+FFFC ON Symbol: Other symbol, common, Other, [alphabetic, caseignorable, extender, graphemebase, idcontinue, idstart, xidcontinue, xidstart]
U+FFFD ON Symbol: Other symbol, common, Other, [alphabetic, caseignorable, extender, graphemebase, idcontinue, idstart, xidcontinue, xidstart]
U+FFFE BN Control: Unassigned, unknown, Other, [changeswhenuppercased, deprecated, emojicomponent, emojimodifierbase, extender, quotationmark, sentenceterminal, xidcontinue, xidstart]
U+FFFF BN Control: Unassigned, unknown, Other, [changeswhenuppercased, deprecated, emojicomponent, emojimodifierbase, extender, quotationmark, sentenceterminal, xidcontinue, xidstart]
findprop 10000 10001 e01ef f0000 100000
U+10000 L Letter: Other letter, linearb, Other, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
U+10001 L Letter: Other letter, linearb, Other, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
U+E01EF NSM Mark: Non-spacing mark, inherited, Extend, []
U+F0000 L Control: Private use, unknown, Other
U+100000 L Control: Private use, unknown, Other
findprop 1b00 12000 7c0 a840 10900
U+1B00 NSM Mark: Non-spacing mark, balinese, Extend, [alphabetic, cased, changeswhencasefolded, changeswhencasemapped, changeswhenlowercased, graphemebase, uppercase]
U+12000 L Letter: Other letter, cuneiform, Other, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
U+07C0 R Number: Decimal number, nko, Other, [graphemebase, patternsyntax, terminalpunctuation]
U+A840 L Letter: Other letter, phagspa, Other, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
U+10900 R Letter: Other letter, phoenician, Other, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
findprop 1d79 a77d
U+1D79 L Letter: Lower case letter, latin, Other, U+A77D, [alphabetic, graphemebase, idcontinue, idstart, xidcontinue]
U+A77D L Letter: Upper case letter, latin, Other, U+1D79, [alphabetic, graphemeextend, idcontinue, xidcontinue]
findprop 0800 083e a4d0 a4f7 aa80 aadf
U+0800 R Letter: Other letter, samaritan, Other, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
U+083E R Punctuation: Other punctuation, samaritan, Other, [bidimirrored, graphemebase, math, patternsyntax]
U+A4D0 L Letter: Other letter, lisu, Other, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
U+A4F7 L Letter: Other letter, lisu, Other, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
U+AA80 L Letter: Other letter, taiviet, Other, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
U+AADF L Punctuation: Other punctuation, taiviet, Other, [graphemebase, patternsyntax, sentenceterminal, terminalpunctuation]
findprop 10b00 10b35 13000 1342e 10840 10855
U+10B00 R Letter: Other letter, avestan, Other, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
U+10B35 R Letter: Other letter, avestan, Other, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
U+13000 L Letter: Other letter, egyptianhieroglyphs, Other, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
U+1342E L Letter: Other letter, egyptianhieroglyphs, Other, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
U+10840 R Letter: Other letter, imperialaramaic, Other, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
U+10855 R Letter: Other letter, imperialaramaic, Other, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
findprop 11100 1113c 11680 116c0
U+11100 NSM Mark: Non-spacing mark, chakma, Extend, [alphabetic, cased, changeswhencasefolded, changeswhencasemapped, changeswhenlowercased, graphemebase, uppercase]
U+1113C L Number: Decimal number, chakma, Other, [graphemebase, patternsyntax, terminalpunctuation]
U+11680 L Letter: Other letter, takri, Other, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
U+116C0 L Number: Decimal number, takri, Other, [graphemebase, patternsyntax, terminalpunctuation]
findprop 0d 0a 0e 0711 1b04 1111 1169 11fe ae4c ad89
U+000D B Control: Control, common, CR, [ascii, graphemebase, patternsyntax, sentenceterminal, terminalpunctuation]
U+000A B Control: Control, common, LF, [ascii, graphemebase, patternsyntax, sentenceterminal, terminalpunctuation]
U+000E BN Control: Control, common, Control, [ascii, patternwhitespace, whitespace]
U+0711 NSM Mark: Non-spacing mark, syriac, Extend, [alphabetic, cased, changeswhencasefolded, changeswhencasemapped, changeswhenlowercased, graphemebase, uppercase]
U+1B04 L Mark: Spacing mark, balinese, SpacingMark, [dash, emoji, extendedpictographic, graphemebase, patternsyntax]
U+1111 L Letter: Other letter, hangul, Hangul syllable type L, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
U+1169 L Letter: Other letter, hangul, Hangul syllable type V, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
U+11FE L Letter: Other letter, hangul, Hangul syllable type T, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
U+AE4C L Letter: Other letter, hangul, Hangul syllable type LV, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
U+AD89 L Letter: Other letter, hangul, Hangul syllable type LVT, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
findprop 118a0 11ac7 16ad0
U+118A0 L Letter: Upper case letter, warangciti, Other, U+118C0, [alphabetic, graphemeextend, idcontinue, xidcontinue]
U+11AC7 L Letter: Other letter, paucinhau, Other, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
U+16AD0 L Letter: Other letter, bassavah, Other, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
findprop 11700 14400 108e0 11280 1d800
U+11700 L Letter: Other letter, ahom, Other, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
U+14400 L Letter: Other letter, anatolianhieroglyphs, Other, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
U+108E0 R Letter: Other letter, hatran, Other, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
U+11280 L Letter: Other letter, multani, Other, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
U+1D800 L Symbol: Other symbol, signwriting, Other, [alphabetic, caseignorable, extender, graphemebase, idcontinue, idstart, xidcontinue, xidstart]
findprop 11800 1e903 11da9 10d27 11ee0 16e48 10f27 10f30
U+11800 L Letter: Other letter, dogra, Other, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
U+1E903 R Letter: Upper case letter, adlam, Other, U+1E925, [alphabetic, graphemeextend, idcontinue, xidcontinue]
U+11DA9 L Number: Decimal number, gunjalagondi, Other, [graphemebase, patternsyntax, terminalpunctuation]
U+10D27 NSM Mark: Non-spacing mark, hanifirohingya, Extend, [extendedpictographic, graphemebase, patternsyntax]
U+11EE0 L Letter: Other letter, makasar, Other, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
U+16E48 L Letter: Upper case letter, medefaidrin, Other, U+16E68, [alphabetic, graphemeextend, idcontinue, xidcontinue]
U+10F27 R Letter: Other letter, oldsogdian, Other, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
U+10F30 AL Letter: Other letter, sogdian, Other, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
findprop a836 a833 1cf4 20f0 1cd0
U+A836 L Symbol: Other symbol, common, Other, [devanagari, gurmukhi, gujarati, kaithi, takri, khojki, mahajani, modi, khudawadi, tirhuta, dogra], [alphabetic, caseignorable, extender, graphemebase, idcontinue, idstart, xidcontinue, xidstart]
U+A833 L Number: Other number, common, Other, [devanagari, gurmukhi, gujarati, kannada, kaithi, takri, khojki, mahajani, modi, khudawadi, tirhuta, dogra, nandinagari], [alphabetic, caseignorable, extender, graphemebase, idcontinue, idstart, xidcontinue, xidstart]
U+1CF4 NSM Mark: Non-spacing mark, inherited, Extend, [devanagari, kannada, grantha], [alphabetic, cased, graphemebase, idcontinue, idstart, lowercase, softdotted, xidcontinue, xidstart]
U+20F0 NSM Mark: Non-spacing mark, inherited, Extend, [latin, devanagari, grantha], [caseignorable, graphemebase, patternsyntax, quotationmark]
U+1CD0 NSM Mark: Non-spacing mark, inherited, Extend, [devanagari, bengali, kannada, grantha], [alphabetic, cased, graphemebase, idcontinue, idstart, lowercase, softdotted, xidcontinue, xidstart]
findprop 32ff
U+32FF L Symbol: Other symbol, common, Other, [han], [alphabetic, caseignorable, extender, graphemebase, idcontinue, idstart, xidcontinue, xidstart]
findprop 1f16d
U+1F16D ON Symbol: Other symbol, common, Extended Pictographic, [ascii, sentenceterminal, unifiedideograph, whitespace, xidcontinue]
findprop U+10e93 U+10eaa
U+10E93 R Letter: Other letter, yezidi, Other, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
U+10EAA R Control: Unassigned, unknown, Other
findprop 0602 202a 202b 202c 2068 2069 202d 202e 2067
U+0602 AN Control: Format, arabic, Prepend, [alphabetic, cased, changeswhencasemapped, changeswhentitlecased, changeswhenuppercased, graphemebase, lowercase]
U+202A LRE Control: Format, common, Control, [extendedpictographic, graphemebase, math, patternsyntax]
U+202B RLE Control: Format, common, Control, [extendedpictographic, graphemebase, math, patternsyntax]
U+202C PDF Control: Format, common, Control, [extendedpictographic, graphemebase, math, patternsyntax]
U+2068 FSI Control: Format, common, Control, [extendedpictographic, graphemebase, math, patternsyntax]
U+2069 PDI Control: Format, common, Control, [extendedpictographic, graphemebase, math, patternsyntax]
U+202D LRO Control: Format, common, Control, [extendedpictographic, graphemebase, math, patternsyntax]
U+202E RLO Control: Format, common, Control, [extendedpictographic, graphemebase, math, patternsyntax]
U+2067 RLI Control: Format, common, Control, [extendedpictographic, graphemebase, math, patternsyntax]

298
Kha/Backends/Kore-hxcpp/khacpp/project/thirdparty/pcre2-10.42-16/maint/ucptestdata/testoutput2 vendored Normal file
View File

@ -0,0 +1,298 @@
find script Han
U+2E80..U+2E99 ON Symbol: Other symbol, han, Other, [ascii, sentenceterminal, unifiedideograph, whitespace, xidstart]
U+2E9B..U+2EF3 ON Symbol: Other symbol, han, Other, [ascii, sentenceterminal, unifiedideograph, whitespace, xidstart]
U+2F00..U+2FD5 ON Symbol: Other symbol, han, Other, [ascii, sentenceterminal, unifiedideograph, whitespace, xidstart]
U+3005 L Letter: Modifier letter, han, Other, [emoji, emojimodifierbase, emojipresentation, extendedpictographic, graphemebase, patternsyntax]
U+3007 L Number: Letter number, han, Other, [sentenceterminal, unifiedideograph, xidcontinue, xidstart]
U+3021..U+3029 L Number: Letter number, han, Other, [sentenceterminal, unifiedideograph, xidcontinue, xidstart]
U+3038..U+303A L Number: Letter number, han, Other, [sentenceterminal, unifiedideograph, xidcontinue, xidstart]
U+303B L Letter: Modifier letter, han, Other, [alphabetic, graphemebase, idcontinue, idstart, ideographic, xidcontinue, xidstart]
U+3400..U+4DBF L Letter: Other letter, han, Other, [changeswhenuppercased, deprecated, emojimodifier, emojimodifierbase, extender, quotationmark, sentenceterminal, xidcontinue, xidstart]
U+4E00..U+9FFF L Letter: Other letter, han, Other, [changeswhenuppercased, deprecated, emojimodifier, emojimodifierbase, extender, quotationmark, sentenceterminal, xidcontinue, xidstart]
U+F900..U+FA0D L Letter: Other letter, han, Other, [sentenceterminal, unifiedideograph, xidcontinue, xidstart]
U+FA0E..U+FA0F L Letter: Other letter, han, Other, [changeswhenuppercased, deprecated, emojimodifier, emojimodifierbase, extender, quotationmark, sentenceterminal, xidcontinue, xidstart]
U+FA10 L Letter: Other letter, han, Other, [sentenceterminal, unifiedideograph, xidcontinue, xidstart]
U+FA11 L Letter: Other letter, han, Other, [changeswhenuppercased, deprecated, emojimodifier, emojimodifierbase, extender, quotationmark, sentenceterminal, xidcontinue, xidstart]
U+FA12 L Letter: Other letter, han, Other, [sentenceterminal, unifiedideograph, xidcontinue, xidstart]
U+FA13..U+FA14 L Letter: Other letter, han, Other, [changeswhenuppercased, deprecated, emojimodifier, emojimodifierbase, extender, quotationmark, sentenceterminal, xidcontinue, xidstart]
U+FA15..U+FA1E L Letter: Other letter, han, Other, [sentenceterminal, unifiedideograph, xidcontinue, xidstart]
U+FA1F L Letter: Other letter, han, Other, [changeswhenuppercased, deprecated, emojimodifier, emojimodifierbase, extender, quotationmark, sentenceterminal, xidcontinue, xidstart]
U+FA20 L Letter: Other letter, han, Other, [sentenceterminal, unifiedideograph, xidcontinue, xidstart]
U+FA21 L Letter: Other letter, han, Other, [changeswhenuppercased, deprecated, emojimodifier, emojimodifierbase, extender, quotationmark, sentenceterminal, xidcontinue, xidstart]
U+FA22 L Letter: Other letter, han, Other, [sentenceterminal, unifiedideograph, xidcontinue, xidstart]
U+FA23..U+FA24 L Letter: Other letter, han, Other, [changeswhenuppercased, deprecated, emojimodifier, emojimodifierbase, extender, quotationmark, sentenceterminal, xidcontinue, xidstart]
U+FA25..U+FA26 L Letter: Other letter, han, Other, [sentenceterminal, unifiedideograph, xidcontinue, xidstart]
U+FA27..U+FA29 L Letter: Other letter, han, Other, [changeswhenuppercased, deprecated, emojimodifier, emojimodifierbase, extender, quotationmark, sentenceterminal, xidcontinue, xidstart]
U+FA2A..U+FA6D L Letter: Other letter, han, Other, [sentenceterminal, unifiedideograph, xidcontinue, xidstart]
U+FA70..U+FAD9 L Letter: Other letter, han, Other, [sentenceterminal, unifiedideograph, xidcontinue, xidstart]
U+16FE2 ON Punctuation: Other punctuation, han, Other, [alphabetic, caseignorable, extender, graphemebase, idcontinue, idstart, xidcontinue, xidstart]
U+16FE3 L Letter: Modifier letter, han, Other, [emoji, emojimodifierbase, emojipresentation, extendedpictographic, graphemebase, patternsyntax]
U+16FF0..U+16FF1 L Mark: Spacing mark, han, SpacingMark, [caseignorable, graphemeextend, idcontinue, ideographic, xidcontinue]
U+20000..U+2A6DF L Letter: Other letter, han, Other, [changeswhenuppercased, deprecated, emojimodifier, emojimodifierbase, extender, quotationmark, sentenceterminal, xidcontinue, xidstart]
U+2A700..U+2B738 L Letter: Other letter, han, Other, [changeswhenuppercased, deprecated, emojimodifier, emojimodifierbase, extender, quotationmark, sentenceterminal, xidcontinue, xidstart]
U+2B740..U+2B81D L Letter: Other letter, han, Other, [changeswhenuppercased, deprecated, emojimodifier, emojimodifierbase, extender, quotationmark, sentenceterminal, xidcontinue, xidstart]
U+2B820..U+2CEA1 L Letter: Other letter, han, Other, [changeswhenuppercased, deprecated, emojimodifier, emojimodifierbase, extender, quotationmark, sentenceterminal, xidcontinue, xidstart]
U+2CEB0..U+2EBE0 L Letter: Other letter, han, Other, [changeswhenuppercased, deprecated, emojimodifier, emojimodifierbase, extender, quotationmark, sentenceterminal, xidcontinue, xidstart]
U+2F800..U+2FA1D L Letter: Other letter, han, Other, [sentenceterminal, unifiedideograph, xidcontinue, xidstart]
U+30000..U+3134A L Letter: Other letter, han, Other, [changeswhenuppercased, deprecated, emojimodifier, emojimodifierbase, extender, quotationmark, sentenceterminal, xidcontinue, xidstart]
find type Pe script Common scriptx Hangul
U+3009 ON Punctuation: Close punctuation, common, Other, [hangul, hiragana, katakana, bopomofo, han, yiii], [ascii, alphabetic, cased, changeswhencasemapped, changeswhentitlecased, dash, emojimodifier, emojimodifierbase]
U+300B ON Punctuation: Close punctuation, common, Other, [hangul, hiragana, katakana, bopomofo, han, yiii], [ascii, alphabetic, cased, changeswhencasemapped, changeswhentitlecased, dash, emojimodifier, emojimodifierbase]
U+300D ON Punctuation: Close punctuation, common, Other, [hangul, hiragana, katakana, bopomofo, han, yiii], [graphemebase, sentenceterminal, terminalpunctuation]
U+300F ON Punctuation: Close punctuation, common, Other, [hangul, hiragana, katakana, bopomofo, han, yiii], [graphemebase, sentenceterminal, terminalpunctuation]
U+3011 ON Punctuation: Close punctuation, common, Other, [hangul, hiragana, katakana, bopomofo, han, yiii], [ascii, alphabetic, cased, changeswhencasemapped, changeswhentitlecased, dash, emojimodifier, emojimodifierbase]
U+3015 ON Punctuation: Close punctuation, common, Other, [hangul, hiragana, katakana, bopomofo, han, yiii], [ascii, alphabetic, cased, changeswhencasemapped, changeswhentitlecased, dash, emojimodifier, emojimodifierbase]
U+3017 ON Punctuation: Close punctuation, common, Other, [hangul, hiragana, katakana, bopomofo, han, yiii], [ascii, alphabetic, cased, changeswhencasemapped, changeswhentitlecased, dash, emojimodifier, emojimodifierbase]
U+3019 ON Punctuation: Close punctuation, common, Other, [hangul, hiragana, katakana, bopomofo, han, yiii], [ascii, alphabetic, cased, changeswhencasemapped, changeswhentitlecased, dash, emojimodifier, emojimodifierbase]
U+301B ON Punctuation: Close punctuation, common, Other, [hangul, hiragana, katakana, bopomofo, han, yiii], [ascii, alphabetic, cased, changeswhencasemapped, changeswhentitlecased, dash, emojimodifier, emojimodifierbase]
U+301E..U+301F ON Punctuation: Close punctuation, common, Other, [hangul, hiragana, katakana, bopomofo, han], [softdotted, terminalpunctuation, unifiedideograph, xidcontinue, xidstart]
U+FF63 ON Punctuation: Close punctuation, common, Other, [hangul, hiragana, katakana, bopomofo, han, yiii], [changeswhencasemapped, changeswhenlowercased, changeswhentitlecased, emojimodifier, emojimodifierbase]
find type Sk
U+005E ON Symbol: Modifier symbol, common, Other, [alphabetic, cased, changeswhencasemapped, changeswhentitlecased, changeswhenuppercased, graphemebase, idcontinue, idstart, lowercase, xidcontinue, xidstart]
U+0060 ON Symbol: Modifier symbol, common, Other, [alphabetic, cased, changeswhencasefolded, changeswhencasemapped, changeswhenlowercased, changeswhentitlecased, graphemebase, idcontinue, idstart, uppercase, xidcontinue, xidstart]
U+00A8 ON Symbol: Modifier symbol, common, Other, [alphabetic, cased, graphemebase, idcontinue, idstart, math, uppercase, xidcontinue, xidstart]
U+00AF ON Symbol: Modifier symbol, common, Other, [alphabetic, cased, graphemebase, idcontinue, idstart, math, uppercase, xidcontinue, xidstart]
U+00B4 ON Symbol: Modifier symbol, common, Other, [alphabetic, cased, graphemebase, idcontinue, idstart, math, uppercase, xidcontinue, xidstart]
U+00B8 ON Symbol: Modifier symbol, common, Other, [alphabetic, cased, graphemebase, idcontinue, idstart, math, uppercase, xidcontinue, xidstart]
U+02C2..U+02C5 ON Symbol: Modifier symbol, common, Other, [alphabetic, cased, graphemebase, idcontinue, idstart, math, uppercase, xidcontinue, xidstart]
U+02D2..U+02DF ON Symbol: Modifier symbol, common, Other, [alphabetic, cased, graphemebase, idcontinue, idstart, math, uppercase, xidcontinue, xidstart]
U+02E5..U+02E9 ON Symbol: Modifier symbol, common, Other, [alphabetic, cased, graphemebase, idcontinue, idstart, math, uppercase, xidcontinue, xidstart]
U+02EA..U+02EB ON Symbol: Modifier symbol, bopomofo, Other, [alphabetic, cased, graphemebase, idcontinue, idstart, math, uppercase, xidcontinue, xidstart]
U+02ED ON Symbol: Modifier symbol, common, Other, [alphabetic, cased, graphemebase, idcontinue, idstart, math, uppercase, xidcontinue, xidstart]
U+02EF..U+02FF ON Symbol: Modifier symbol, common, Other, [alphabetic, cased, graphemebase, idcontinue, idstart, math, uppercase, xidcontinue, xidstart]
U+0375 ON Symbol: Modifier symbol, greek, Other, [alphabetic, cased, graphemebase, idcontinue, idstart, math, uppercase, xidcontinue, xidstart]
U+0384 ON Symbol: Modifier symbol, greek, Other, [alphabetic, cased, graphemebase, idcontinue, idstart, math, uppercase, xidcontinue, xidstart]
U+0385 ON Symbol: Modifier symbol, common, Other, [alphabetic, cased, graphemebase, idcontinue, idstart, math, uppercase, xidcontinue, xidstart]
U+0888 AL Symbol: Modifier symbol, arabic, Other, [alphabetic, cased, graphemebase, idcontinue, idstart, lowercase, math, softdotted, xidcontinue, xidstart]
U+1FBD ON Symbol: Modifier symbol, greek, Other, [alphabetic, cased, graphemebase, idcontinue, idstart, math, uppercase, xidcontinue, xidstart]
U+1FBF..U+1FC1 ON Symbol: Modifier symbol, greek, Other, [alphabetic, cased, graphemebase, idcontinue, idstart, math, uppercase, xidcontinue, xidstart]
U+1FCD..U+1FCF ON Symbol: Modifier symbol, greek, Other, [alphabetic, cased, graphemebase, idcontinue, idstart, math, uppercase, xidcontinue, xidstart]
U+1FDD..U+1FDF ON Symbol: Modifier symbol, greek, Other, [alphabetic, cased, graphemebase, idcontinue, idstart, math, uppercase, xidcontinue, xidstart]
U+1FED..U+1FEF ON Symbol: Modifier symbol, greek, Other, [alphabetic, cased, graphemebase, idcontinue, idstart, math, uppercase, xidcontinue, xidstart]
U+1FFD..U+1FFE ON Symbol: Modifier symbol, greek, Other, [alphabetic, cased, graphemebase, idcontinue, idstart, math, uppercase, xidcontinue, xidstart]
U+309B..U+309C ON Symbol: Modifier symbol, common, Other, [hiragana, katakana], [alphabetic, bidimirrored, caseignorable, cased, changeswhencasefolded, changeswhenlowercased, changeswhentitlecased, changeswhenuppercased, dash, defaultignorablecodepoint, deprecated, diacritic, emoji, emojicomponent, emojimodifier, emojimodifierbase, emojipresentation, extendedpictographic, extender, graphemebase, graphemeextend, graphemelink, hexdigit, idsbinaryoperator, idstrinaryoperator, idcontinue, idstart, ideographic, sentenceterminal, unifiedideograph, whitespace, xidcontinue]
U+A700..U+A707 ON Symbol: Modifier symbol, common, Other, [latin, han], [alphabetic, cased, graphemebase, idcontinue, idstart, math, uppercase, xidcontinue, xidstart]
U+A708..U+A716 ON Symbol: Modifier symbol, common, Other, [alphabetic, cased, graphemebase, idcontinue, idstart, math, uppercase, xidcontinue, xidstart]
U+A720..U+A721 ON Symbol: Modifier symbol, common, Other, [alphabetic, cased, graphemebase, idcontinue, idstart, math, uppercase, xidcontinue, xidstart]
U+A789..U+A78A L Symbol: Modifier symbol, common, Other, [alphabetic, cased, graphemebase, idcontinue, idstart, math, uppercase, xidcontinue, xidstart]
U+AB5B L Symbol: Modifier symbol, common, Other, [alphabetic, cased, graphemebase, idcontinue, idstart, math, uppercase, xidcontinue, xidstart]
U+AB6A..U+AB6B ON Symbol: Modifier symbol, common, Other, [alphabetic, cased, graphemebase, idcontinue, idstart, math, uppercase, xidcontinue, xidstart]
U+FBB2..U+FBC2 AL Symbol: Modifier symbol, arabic, Other, [alphabetic, cased, graphemebase, idcontinue, idstart, lowercase, math, softdotted, xidcontinue, xidstart]
U+FF3E ON Symbol: Modifier symbol, common, Other, [asciihexdigit, bidicontrol, bidimirrored, cased, changeswhencasefolded, sentenceterminal, unifiedideograph, whitespace, xidstart]
U+FF40 ON Symbol: Modifier symbol, common, Other, [alphabetic, cased, graphemebase, idcontinue, idstart, math, uppercase, xidcontinue, xidstart]
U+FFE3 ON Symbol: Modifier symbol, common, Other, [alphabetic, cased, graphemebase, idcontinue, idstart, math, uppercase, xidcontinue, xidstart]
U+1F3FB..U+1F3FF ON Symbol: Modifier symbol, common, Extend, [changeswhencasemapped, changeswhenuppercased, emojimodifier, emojimodifierbase, math, patternsyntax, radical, sentenceterminal, terminalpunctuation]
find type Pd
U+002D ES Punctuation: Dash punctuation, common, Other, [ascii, alphabetic, cased, changeswhencasemapped, changeswhentitlecased, changeswhenuppercased, graphemebase, idcontinue, idstart, lowercase, softdotted, xidcontinue, xidstart]
U+058A ON Punctuation: Dash punctuation, armenian, Other, [emoji, emojipresentation, extendedpictographic, graphemebase, patternsyntax]
U+05BE R Punctuation: Dash punctuation, hebrew, Other, [emoji, emojipresentation, extendedpictographic, graphemebase, patternsyntax]
U+1400 ON Punctuation: Dash punctuation, canadianaboriginal, Other, [emoji, emojipresentation, extendedpictographic, graphemebase, patternsyntax]
U+1806 ON Punctuation: Dash punctuation, mongolian, Other, [emoji, emojipresentation, extendedpictographic, graphemebase, patternsyntax]
U+2010..U+2015 ON Punctuation: Dash punctuation, common, Other, [dash, defaultignorablecodepoint, deprecated, emojipresentation, joincontrol, lowercase, patternwhitespace, radical, regionalindicator, softdotted, xidcontinue, xidstart]
U+2E17 ON Punctuation: Dash punctuation, common, Other, [dash, defaultignorablecodepoint, deprecated, emojipresentation, joincontrol, lowercase, patternwhitespace, radical, regionalindicator, softdotted, xidcontinue, xidstart]
U+2E1A ON Punctuation: Dash punctuation, common, Other, [dash, defaultignorablecodepoint, deprecated, emojipresentation, joincontrol, lowercase, patternwhitespace, radical, regionalindicator, softdotted, xidcontinue, xidstart]
U+2E3A..U+2E3B ON Punctuation: Dash punctuation, common, Other, [dash, defaultignorablecodepoint, deprecated, emojipresentation, joincontrol, lowercase, patternwhitespace, radical, regionalindicator, softdotted, xidcontinue, xidstart]
U+2E40 ON Punctuation: Dash punctuation, common, Other, [dash, defaultignorablecodepoint, deprecated, emojipresentation, joincontrol, lowercase, patternwhitespace, radical, regionalindicator, softdotted, xidcontinue, xidstart]
U+2E5D ON Punctuation: Dash punctuation, common, Other, [dash, defaultignorablecodepoint, deprecated, emojipresentation, joincontrol, lowercase, patternwhitespace, radical, regionalindicator, softdotted, xidcontinue, xidstart]
U+301C ON Punctuation: Dash punctuation, common, Other, [hangul, hiragana, katakana, bopomofo, han], [dash, defaultignorablecodepoint, deprecated, emojipresentation, joincontrol, lowercase, patternwhitespace, radical, regionalindicator, softdotted, xidcontinue, xidstart]
U+3030 ON Punctuation: Dash punctuation, common, Extended Pictographic, [hangul, hiragana, katakana, bopomofo, han], [changeswhencasemapped, changeswhenuppercased, emojimodifier, emojimodifierbase, joincontrol, logicalorderexception, lowercase, prependedconcatenationmark, quotationmark, radical, regionalindicator, sentenceterminal, softdotted, terminalpunctuation, unifiedideograph, uppercase, variationselector, whitespace, xidcontinue, xidstart]
U+30A0 ON Punctuation: Dash punctuation, common, Other, [hiragana, katakana], [emoji, emojipresentation, extendedpictographic, graphemebase, patternsyntax]
U+FE31..U+FE32 ON Punctuation: Dash punctuation, common, Other, [emoji, emojipresentation, extendedpictographic, graphemebase, patternsyntax]
U+FE58 ON Punctuation: Dash punctuation, common, Other, [emoji, emojipresentation, extendedpictographic, graphemebase, patternsyntax]
U+FE63 ES Punctuation: Dash punctuation, common, Other, [caseignorable, sentenceterminal, unifiedideograph, xidcontinue]
U+FF0D ES Punctuation: Dash punctuation, common, Other, [emoji, emojipresentation, extendedpictographic, graphemebase, patternsyntax]
U+10EAD R Punctuation: Dash punctuation, yezidi, Other, [emoji, emojipresentation, extendedpictographic, graphemebase, patternsyntax]
find gbreak LVT
U+AC01..U+AC1B L Letter: Other letter, hangul, Hangul syllable type LVT, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
U+AC1D..U+AC37 L Letter: Other letter, hangul, Hangul syllable type LVT, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
U+AC39..U+AC53 L Letter: Other letter, hangul, Hangul syllable type LVT, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
U+AC55..U+AC6F L Letter: Other letter, hangul, Hangul syllable type LVT, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
U+AC71..U+AC8B L Letter: Other letter, hangul, Hangul syllable type LVT, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
U+AC8D..U+ACA7 L Letter: Other letter, hangul, Hangul syllable type LVT, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
U+ACA9..U+ACC3 L Letter: Other letter, hangul, Hangul syllable type LVT, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
U+ACC5..U+ACDF L Letter: Other letter, hangul, Hangul syllable type LVT, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
U+ACE1..U+ACFB L Letter: Other letter, hangul, Hangul syllable type LVT, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
U+ACFD..U+AD17 L Letter: Other letter, hangul, Hangul syllable type LVT, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
U+AD19..U+AD33 L Letter: Other letter, hangul, Hangul syllable type LVT, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
U+AD35..U+AD4F L Letter: Other letter, hangul, Hangul syllable type LVT, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
U+AD51..U+AD6B L Letter: Other letter, hangul, Hangul syllable type LVT, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
U+AD6D..U+AD87 L Letter: Other letter, hangul, Hangul syllable type LVT, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
U+AD89..U+ADA3 L Letter: Other letter, hangul, Hangul syllable type LVT, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
U+ADA5..U+ADBF L Letter: Other letter, hangul, Hangul syllable type LVT, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
U+ADC1..U+ADDB L Letter: Other letter, hangul, Hangul syllable type LVT, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
U+ADDD..U+ADF7 L Letter: Other letter, hangul, Hangul syllable type LVT, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
U+ADF9..U+AE13 L Letter: Other letter, hangul, Hangul syllable type LVT, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
U+AE15..U+AE2F L Letter: Other letter, hangul, Hangul syllable type LVT, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
U+AE31..U+AE4B L Letter: Other letter, hangul, Hangul syllable type LVT, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
U+AE4D..U+AE67 L Letter: Other letter, hangul, Hangul syllable type LVT, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
U+AE69..U+AE83 L Letter: Other letter, hangul, Hangul syllable type LVT, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
U+AE85..U+AE9F L Letter: Other letter, hangul, Hangul syllable type LVT, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
U+AEA1..U+AEBB L Letter: Other letter, hangul, Hangul syllable type LVT, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
U+AEBD..U+AED7 L Letter: Other letter, hangul, Hangul syllable type LVT, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
U+AED9..U+AEF3 L Letter: Other letter, hangul, Hangul syllable type LVT, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
U+AEF5..U+AF0F L Letter: Other letter, hangul, Hangul syllable type LVT, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
U+AF11..U+AF2B L Letter: Other letter, hangul, Hangul syllable type LVT, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
U+AF2D..U+AF47 L Letter: Other letter, hangul, Hangul syllable type LVT, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
U+AF49..U+AF63 L Letter: Other letter, hangul, Hangul syllable type LVT, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
U+AF65..U+AF7F L Letter: Other letter, hangul, Hangul syllable type LVT, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
U+AF81..U+AF9B L Letter: Other letter, hangul, Hangul syllable type LVT, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
U+AF9D..U+AFB7 L Letter: Other letter, hangul, Hangul syllable type LVT, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
U+AFB9..U+AFD3 L Letter: Other letter, hangul, Hangul syllable type LVT, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
U+AFD5..U+AFEF L Letter: Other letter, hangul, Hangul syllable type LVT, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
U+AFF1..U+B00B L Letter: Other letter, hangul, Hangul syllable type LVT, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
U+B00D..U+B027 L Letter: Other letter, hangul, Hangul syllable type LVT, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
U+B029..U+B043 L Letter: Other letter, hangul, Hangul syllable type LVT, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
U+B045..U+B05F L Letter: Other letter, hangul, Hangul syllable type LVT, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
U+B061..U+B07B L Letter: Other letter, hangul, Hangul syllable type LVT, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
U+B07D..U+B097 L Letter: Other letter, hangul, Hangul syllable type LVT, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
U+B099..U+B0B3 L Letter: Other letter, hangul, Hangul syllable type LVT, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
U+B0B5..U+B0CF L Letter: Other letter, hangul, Hangul syllable type LVT, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
U+B0D1..U+B0EB L Letter: Other letter, hangul, Hangul syllable type LVT, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
U+B0ED..U+B107 L Letter: Other letter, hangul, Hangul syllable type LVT, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
U+B109..U+B123 L Letter: Other letter, hangul, Hangul syllable type LVT, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
U+B125..U+B13F L Letter: Other letter, hangul, Hangul syllable type LVT, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
U+B141..U+B15B L Letter: Other letter, hangul, Hangul syllable type LVT, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
U+B15D..U+B177 L Letter: Other letter, hangul, Hangul syllable type LVT, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
U+B179..U+B193 L Letter: Other letter, hangul, Hangul syllable type LVT, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
U+B195..U+B1AF L Letter: Other letter, hangul, Hangul syllable type LVT, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
U+B1B1..U+B1CB L Letter: Other letter, hangul, Hangul syllable type LVT, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
U+B1CD..U+B1E7 L Letter: Other letter, hangul, Hangul syllable type LVT, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
U+B1E9..U+B203 L Letter: Other letter, hangul, Hangul syllable type LVT, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
U+B205..U+B21F L Letter: Other letter, hangul, Hangul syllable type LVT, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
U+B221..U+B23B L Letter: Other letter, hangul, Hangul syllable type LVT, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
U+B23D..U+B257 L Letter: Other letter, hangul, Hangul syllable type LVT, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
U+B259..U+B273 L Letter: Other letter, hangul, Hangul syllable type LVT, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
U+B275..U+B28F L Letter: Other letter, hangul, Hangul syllable type LVT, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
U+B291..U+B2AB L Letter: Other letter, hangul, Hangul syllable type LVT, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
U+B2AD..U+B2C7 L Letter: Other letter, hangul, Hangul syllable type LVT, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
U+B2C9..U+B2E3 L Letter: Other letter, hangul, Hangul syllable type LVT, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
U+B2E5..U+B2FF L Letter: Other letter, hangul, Hangul syllable type LVT, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
U+B301..U+B31B L Letter: Other letter, hangul, Hangul syllable type LVT, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
U+B31D..U+B337 L Letter: Other letter, hangul, Hangul syllable type LVT, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
U+B339..U+B353 L Letter: Other letter, hangul, Hangul syllable type LVT, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
U+B355..U+B36F L Letter: Other letter, hangul, Hangul syllable type LVT, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
U+B371..U+B38B L Letter: Other letter, hangul, Hangul syllable type LVT, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
U+B38D..U+B3A7 L Letter: Other letter, hangul, Hangul syllable type LVT, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
U+B3A9..U+B3C3 L Letter: Other letter, hangul, Hangul syllable type LVT, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
U+B3C5..U+B3DF L Letter: Other letter, hangul, Hangul syllable type LVT, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
U+B3E1..U+B3FB L Letter: Other letter, hangul, Hangul syllable type LVT, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
U+B3FD..U+B417 L Letter: Other letter, hangul, Hangul syllable type LVT, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
U+B419..U+B433 L Letter: Other letter, hangul, Hangul syllable type LVT, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
U+B435..U+B44F L Letter: Other letter, hangul, Hangul syllable type LVT, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
U+B451..U+B46B L Letter: Other letter, hangul, Hangul syllable type LVT, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
U+B46D..U+B487 L Letter: Other letter, hangul, Hangul syllable type LVT, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
U+B489..U+B4A3 L Letter: Other letter, hangul, Hangul syllable type LVT, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
U+B4A5..U+B4BF L Letter: Other letter, hangul, Hangul syllable type LVT, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
U+B4C1..U+B4DB L Letter: Other letter, hangul, Hangul syllable type LVT, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
U+B4DD..U+B4F7 L Letter: Other letter, hangul, Hangul syllable type LVT, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
U+B4F9..U+B513 L Letter: Other letter, hangul, Hangul syllable type LVT, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
U+B515..U+B52F L Letter: Other letter, hangul, Hangul syllable type LVT, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
U+B531..U+B54B L Letter: Other letter, hangul, Hangul syllable type LVT, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
U+B54D..U+B567 L Letter: Other letter, hangul, Hangul syllable type LVT, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
U+B569..U+B583 L Letter: Other letter, hangul, Hangul syllable type LVT, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
U+B585..U+B59F L Letter: Other letter, hangul, Hangul syllable type LVT, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
U+B5A1..U+B5BB L Letter: Other letter, hangul, Hangul syllable type LVT, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
U+B5BD..U+B5D7 L Letter: Other letter, hangul, Hangul syllable type LVT, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
U+B5D9..U+B5F3 L Letter: Other letter, hangul, Hangul syllable type LVT, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
U+B5F5..U+B60F L Letter: Other letter, hangul, Hangul syllable type LVT, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
U+B611..U+B62B L Letter: Other letter, hangul, Hangul syllable type LVT, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
U+B62D..U+B647 L Letter: Other letter, hangul, Hangul syllable type LVT, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
U+B649..U+B663 L Letter: Other letter, hangul, Hangul syllable type LVT, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
U+B665..U+B67F L Letter: Other letter, hangul, Hangul syllable type LVT, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
U+B681..U+B69B L Letter: Other letter, hangul, Hangul syllable type LVT, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
U+B69D..U+B6B7 L Letter: Other letter, hangul, Hangul syllable type LVT, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
U+B6B9..U+B6D3 L Letter: Other letter, hangul, Hangul syllable type LVT, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
U+B6D5..U+B6EF L Letter: Other letter, hangul, Hangul syllable type LVT, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
...
find script Old_Uyghur
U+10F70..U+10F81 R Letter: Other letter, olduyghur, Other, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
U+10F82..U+10F85 NSM Mark: Non-spacing mark, olduyghur, Extend, [alphabetic, cased, graphemebase, idcontinue, idstart, lowercase, softdotted, xidcontinue, xidstart]
U+10F86..U+10F89 R Punctuation: Other punctuation, olduyghur, Other, [bidimirrored, graphemebase, math, patternsyntax]
find bidi PDF
U+202C PDF Control: Format, common, Control, [extendedpictographic, graphemebase, math, patternsyntax]
find bidi CS
U+002C CS Punctuation: Other punctuation, common, Other, [ascii, asciihexdigit, alphabetic, cased, changeswhencasemapped, changeswhentitlecased, changeswhenuppercased, graphemebase, hexdigit, idcontinue, idstart, lowercase, xidcontinue, xidstart]
U+002E CS Punctuation: Other punctuation, common, Other, [graphemebase, whitespace]
U+002F CS Punctuation: Other punctuation, common, Other, [ascii, asciihexdigit, emoji, emojicomponent, graphemebase, hexdigit, idcontinue, xidcontinue]
U+003A CS Punctuation: Other punctuation, common, Other, [alphabetic, cased, graphemebase, idcontinue, idstart, lowercase, xidcontinue, xidstart]
U+00A0 CS Separator: Space separator, common, Other, [alphabetic, caseignorable, cased, diacritic, graphemebase, idcontinue, idstart, lowercase]
U+060C CS Punctuation: Other punctuation, common, Other, [arabic, syriac, thaana, nko, hanifirohingya, yezidi], [graphemebase, patternsyntax, sentenceterminal, terminalpunctuation]
U+202F CS Separator: Space separator, common, Other, [latin, mongolian], [alphabetic, caseignorable, cased, diacritic, graphemebase, idcontinue, idstart, lowercase]
U+2044 CS Symbol: Mathematical symbol, common, Other, [alphabetic, caseignorable, diacritic, graphemeextend, idcontinue, xidcontinue]
U+FE50 CS Punctuation: Other punctuation, common, Other, [graphemebase, patternsyntax, sentenceterminal, terminalpunctuation]
U+FE52 CS Punctuation: Other punctuation, common, Other, [changeswhenuppercased, deprecated, emojimodifier, emojimodifierbase, extender, quotationmark, sentenceterminal, xidcontinue, xidstart]
U+FE55 CS Punctuation: Other punctuation, common, Other, [changeswhencasemapped, changeswhenuppercased, emojimodifier, emojimodifierbase, joincontrol, noncharactercodepoint, patternwhitespace, prependedconcatenationmark]
U+FF0C CS Punctuation: Other punctuation, common, Other, [graphemebase, patternsyntax, sentenceterminal, terminalpunctuation]
U+FF0E CS Punctuation: Other punctuation, common, Other, [changeswhenuppercased, deprecated, emojimodifier, emojimodifierbase, extender, quotationmark, sentenceterminal, xidcontinue, xidstart]
U+FF0F CS Punctuation: Other punctuation, common, Other, [alphabetic, caseignorable, extender, graphemebase, idcontinue, idstart, xidcontinue, xidstart]
U+FF1A CS Punctuation: Other punctuation, common, Other, [changeswhencasemapped, changeswhenuppercased, emojimodifier, emojimodifierbase, joincontrol, noncharactercodepoint, patternwhitespace, prependedconcatenationmark]
find bidi CS type Sm
U+2044 CS Symbol: Mathematical symbol, common, Other, [alphabetic, caseignorable, diacritic, graphemeextend, idcontinue, xidcontinue]
find bidi B
U+000A B Control: Control, common, LF, [ascii, graphemebase, patternsyntax, sentenceterminal, terminalpunctuation]
U+000D B Control: Control, common, CR, [ascii, graphemebase, patternsyntax, sentenceterminal, terminalpunctuation]
U+001C..U+001E B Control: Control, common, Control, [ascii, patternwhitespace, whitespace]
U+0085 B Control: Control, common, Control, [caseignorable, defaultignorablecodepoint, graphemeextend, idcontinue, xidcontinue]
U+2029 B Separator: Paragraph separator, common, Control, [caseignorable, defaultignorablecodepoint, graphemeextend, idcontinue, xidcontinue]
find bidi FSI
U+2068 FSI Control: Format, common, Control, [extendedpictographic, graphemebase, math, patternsyntax]
find bidi PDI
U+2069 PDI Control: Format, common, Control, [extendedpictographic, graphemebase, math, patternsyntax]
find bidi RLI
U+2067 RLI Control: Format, common, Control, [extendedpictographic, graphemebase, math, patternsyntax]
find bidi RLO
U+202E RLO Control: Format, common, Control, [extendedpictographic, graphemebase, math, patternsyntax]
find bidi S
U+0009 S Control: Control, common, Control, [ascii, graphemebase, patternsyntax, sentenceterminal, terminalpunctuation]
U+000B S Control: Control, common, Control, [ascii, graphemebase, patternsyntax, sentenceterminal, terminalpunctuation]
U+001F S Control: Control, common, Control, [ascii, patternwhitespace, whitespace]
find bidi WS
U+000C WS Control: Control, common, Control, [ascii, graphemebase, patternsyntax, sentenceterminal, terminalpunctuation]
U+0020 WS Separator: Space separator, common, Other, [ascii, emoji, emojicomponent, graphemebase, patternsyntax]
U+1680 WS Separator: Space separator, ogham, Other, [alphabetic, caseignorable, cased, diacritic, graphemebase, idcontinue, idstart, lowercase]
U+2000..U+200A WS Separator: Space separator, common, Other, [alphabetic, caseignorable, cased, diacritic, graphemebase, idcontinue, idstart, lowercase]
U+2028 WS Separator: Line separator, common, Control, [caseignorable, defaultignorablecodepoint, graphemeextend, idcontinue, xidcontinue]
U+205F WS Separator: Space separator, common, Other, [alphabetic, caseignorable, cased, diacritic, graphemebase, idcontinue, idstart, lowercase]
U+3000 WS Separator: Space separator, common, Other, [alphabetic, caseignorable, cased, diacritic, graphemebase, idcontinue, idstart, lowercase]
find script bopo
U+02EA..U+02EB ON Symbol: Modifier symbol, bopomofo, Other, [alphabetic, cased, graphemebase, idcontinue, idstart, math, uppercase, xidcontinue, xidstart]
U+3105..U+312F L Letter: Other letter, bopomofo, Other, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
U+31A0..U+31BF L Letter: Other letter, bopomofo, Other, [alphabetic, diacritic, graphemebase, idcontinue, xidcontinue]
find bool prependedconcatenationmark
U+00AD BN Control: Format, common, Control, [caseignorable, prependedconcatenationmark]
U+180E BN Control: Format, mongolian, Control, [caseignorable, prependedconcatenationmark]
U+200B BN Control: Format, common, Control, [caseignorable, prependedconcatenationmark]
U+2060 BN Control: Format, common, Control, [caseignorable, prependedconcatenationmark]
U+2118 ON Symbol: Mathematical symbol, common, Other, [changeswhencasemapped, changeswhentitlecased, emojimodifier, emojimodifierbase, patternsyntax, patternwhitespace, prependedconcatenationmark, quotationmark, radical, regionalindicator, sentenceterminal, softdotted, terminalpunctuation, unifiedideograph, uppercase, variationselector, whitespace, xidcontinue, xidstart]
U+3030 ON Punctuation: Dash punctuation, common, Extended Pictographic, [hangul, hiragana, katakana, bopomofo, han], [changeswhencasemapped, changeswhenuppercased, emojimodifier, emojimodifierbase, joincontrol, logicalorderexception, lowercase, prependedconcatenationmark, quotationmark, radical, regionalindicator, sentenceterminal, softdotted, terminalpunctuation, unifiedideograph, uppercase, variationselector, whitespace, xidcontinue, xidstart]
U+AAC0 L Letter: Other letter, taiviet, Other, [changeswhencasemapped, changeswhenuppercased, emojimodifier, emojimodifierbase, logicalorderexception, lowercase, math, patternwhitespace, prependedconcatenationmark]
U+AAC2 L Letter: Other letter, taiviet, Other, [changeswhencasemapped, changeswhenuppercased, emojimodifier, emojimodifierbase, logicalorderexception, lowercase, math, patternwhitespace, prependedconcatenationmark]
U+FE0F NSM Mark: Non-spacing mark, inherited, Extend, [changeswhencasemapped, changeswhenuppercased, emojimodifier, emojimodifierbase, joincontrol, logicalorderexception, math, patternwhitespace, prependedconcatenationmark]
U+FE55 CS Punctuation: Other punctuation, common, Other, [changeswhencasemapped, changeswhenuppercased, emojimodifier, emojimodifierbase, joincontrol, noncharactercodepoint, patternwhitespace, prependedconcatenationmark]
U+FEFF BN Control: Format, common, Control, [caseignorable, prependedconcatenationmark]
U+FF1A CS Punctuation: Other punctuation, common, Other, [changeswhencasemapped, changeswhenuppercased, emojimodifier, emojimodifierbase, joincontrol, noncharactercodepoint, patternwhitespace, prependedconcatenationmark]
U+FF21..U+FF26 L Letter: Upper case letter, latin, Other, [changeswhencasemapped, changeswhenuppercased, emojimodifier, emojimodifierbase, logicalorderexception, lowercase, noncharactercodepoint, patternwhitespace, prependedconcatenationmark]
U+10D22..U+10D23 AL Letter: Other letter, hanifirohingya, Other, [changeswhencasemapped, changeswhenuppercased, emojimodifier, emojimodifierbase, logicalorderexception, lowercase, math, patternwhitespace, prependedconcatenationmark]
U+1135D L Letter: Other letter, grantha, Other, [changeswhencasemapped, changeswhentitlecased, emojimodifier, emojimodifierbase, graphemeextend, hexdigit, logicalorderexception, lowercase, math, noncharactercodepoint, patternsyntax, patternwhitespace, prependedconcatenationmark, quotationmark, radical, regionalindicator, sentenceterminal, softdotted, terminalpunctuation, unifiedideograph, uppercase, variationselector, whitespace, xidcontinue, xidstart]
U+1BCA0..U+1BCA3 BN Control: Format, common, Control, [duployan], [caseignorable, prependedconcatenationmark]
U+1D173..U+1D17A BN Control: Format, common, Control, [caseignorable, prependedconcatenationmark]
U+1F1E6..U+1F1FF L Symbol: Other symbol, common, Regional Indicator, [changeswhencasemapped, changeswhenuppercased, emojimodifier, emojimodifierbase, math, patternwhitespace, prependedconcatenationmark, quotationmark, radical, regionalindicator, sentenceterminal, softdotted, terminalpunctuation, unifiedideograph, uppercase, variationselector, whitespace, xidcontinue, xidstart]
find bool pcm
U+00AD BN Control: Format, common, Control, [caseignorable, prependedconcatenationmark]
U+180E BN Control: Format, mongolian, Control, [caseignorable, prependedconcatenationmark]
U+200B BN Control: Format, common, Control, [caseignorable, prependedconcatenationmark]
U+2060 BN Control: Format, common, Control, [caseignorable, prependedconcatenationmark]
U+2118 ON Symbol: Mathematical symbol, common, Other, [changeswhencasemapped, changeswhentitlecased, emojimodifier, emojimodifierbase, patternsyntax, patternwhitespace, prependedconcatenationmark, quotationmark, radical, regionalindicator, sentenceterminal, softdotted, terminalpunctuation, unifiedideograph, uppercase, variationselector, whitespace, xidcontinue, xidstart]
U+3030 ON Punctuation: Dash punctuation, common, Extended Pictographic, [hangul, hiragana, katakana, bopomofo, han], [changeswhencasemapped, changeswhenuppercased, emojimodifier, emojimodifierbase, joincontrol, logicalorderexception, lowercase, prependedconcatenationmark, quotationmark, radical, regionalindicator, sentenceterminal, softdotted, terminalpunctuation, unifiedideograph, uppercase, variationselector, whitespace, xidcontinue, xidstart]
U+AAC0 L Letter: Other letter, taiviet, Other, [changeswhencasemapped, changeswhenuppercased, emojimodifier, emojimodifierbase, logicalorderexception, lowercase, math, patternwhitespace, prependedconcatenationmark]
U+AAC2 L Letter: Other letter, taiviet, Other, [changeswhencasemapped, changeswhenuppercased, emojimodifier, emojimodifierbase, logicalorderexception, lowercase, math, patternwhitespace, prependedconcatenationmark]
U+FE0F NSM Mark: Non-spacing mark, inherited, Extend, [changeswhencasemapped, changeswhenuppercased, emojimodifier, emojimodifierbase, joincontrol, logicalorderexception, math, patternwhitespace, prependedconcatenationmark]
U+FE55 CS Punctuation: Other punctuation, common, Other, [changeswhencasemapped, changeswhenuppercased, emojimodifier, emojimodifierbase, joincontrol, noncharactercodepoint, patternwhitespace, prependedconcatenationmark]
U+FEFF BN Control: Format, common, Control, [caseignorable, prependedconcatenationmark]
U+FF1A CS Punctuation: Other punctuation, common, Other, [changeswhencasemapped, changeswhenuppercased, emojimodifier, emojimodifierbase, joincontrol, noncharactercodepoint, patternwhitespace, prependedconcatenationmark]
U+FF21..U+FF26 L Letter: Upper case letter, latin, Other, [changeswhencasemapped, changeswhenuppercased, emojimodifier, emojimodifierbase, logicalorderexception, lowercase, noncharactercodepoint, patternwhitespace, prependedconcatenationmark]
U+10D22..U+10D23 AL Letter: Other letter, hanifirohingya, Other, [changeswhencasemapped, changeswhenuppercased, emojimodifier, emojimodifierbase, logicalorderexception, lowercase, math, patternwhitespace, prependedconcatenationmark]
U+1135D L Letter: Other letter, grantha, Other, [changeswhencasemapped, changeswhentitlecased, emojimodifier, emojimodifierbase, graphemeextend, hexdigit, logicalorderexception, lowercase, math, noncharactercodepoint, patternsyntax, patternwhitespace, prependedconcatenationmark, quotationmark, radical, regionalindicator, sentenceterminal, softdotted, terminalpunctuation, unifiedideograph, uppercase, variationselector, whitespace, xidcontinue, xidstart]
U+1BCA0..U+1BCA3 BN Control: Format, common, Control, [duployan], [caseignorable, prependedconcatenationmark]
U+1D173..U+1D17A BN Control: Format, common, Control, [caseignorable, prependedconcatenationmark]
U+1F1E6..U+1F1FF L Symbol: Other symbol, common, Regional Indicator, [changeswhencasemapped, changeswhenuppercased, emojimodifier, emojimodifierbase, math, patternwhitespace, prependedconcatenationmark, quotationmark, radical, regionalindicator, sentenceterminal, softdotted, terminalpunctuation, unifiedideograph, uppercase, variationselector, whitespace, xidcontinue, xidstart]

347
Kha/Backends/Kore-hxcpp/khacpp/project/thirdparty/pcre2-10.42-16/maint/utf8.c vendored Normal file
View File

@ -0,0 +1,347 @@
/****************************************************
* PCRE maintainers' helper program: UTF-8 converter *
****************************************************/
/* This is a test program for converting character code points to UTF-8 and
vice versa. Note that this program conforms to the original definition of
UTF-8, which allows codepoints up to 7fffffff. The more recent definition
limits the validity of Unicode UTF-8 codepoints to a maximum of 10ffffff, and
forbids the "surrogate" code points. This program now gives warnings for these
invalid code points.
The arguments are either single code point values written as U+hh.. or 0xhh..
for conversion to UTF-8, or sequences of hex values, written without 0x and
optionally including spaces (but such arguments must be quoted), for conversion
from UTF-8 to codepoints. For example:
./utf8 0x1234
U+00001234 => e1 88 b4
./utf8 "e1 88 b4"
U+00001234 <= e1 88 b4
In the second case, a number of UTF-8 characters can be present in one
argument. In other words, each such argument is interpreted (after ignoring
spaces) as a string of UTF-8 bytes representing a string of characters:
./utf8 "65 e188b4 77"
0x00000065 <= 65
0x00001234 <= e1 88 b4
0x00000077 <= 77
If the option -s is given, the sequence of UTF-bytes is written out between
angle brackets at the end of the line. On a UTF-8 terminal, this will show the
appropriate graphic for the code point.
Errors provoke error messages, but the program carries on with the next
argument. The return code is always zero.
Philip Hazel
Original creation data: unknown
Code extended and tidied to avoid compiler warnings: 26 March 2020
*/
#include <stdio.h>
#include <stdlib.h>
#include <ctype.h>
#include <string.h>
/* The valid ranges for UTF-8 characters are:
0000 0000 to 0000 007f 1 byte (ascii)
0000 0080 to 0000 07ff 2 bytes
0000 0800 to 0000 ffff 3 bytes
0001 0000 to 001f ffff 4 bytes
0020 0000 to 03ff ffff 5 bytes
0400 0000 to 7fff ffff 6 bytes
*/
static const unsigned int utf8_table1[] = {
0x0000007f, 0x000007ff, 0x0000ffff, 0x001fffff, 0x03ffffff, 0x7fffffff};
static const int utf8_table2[] = {
0, 0xc0, 0xe0, 0xf0, 0xf8, 0xfc};
static const int utf8_table3[] = {
0xff, 0x1f, 0x0f, 0x07, 0x03, 0x01};
/*************************************************
* Convert character value to UTF-8 *
*************************************************/
/* This function takes an unsigned long integer value in the range 0 -
0x7fffffff and encodes it as a UTF-8 character in 1 to 6 bytes.
Arguments:
cvalue the character value
buffer pointer to buffer for result - at least 6 bytes long
Returns: number of bytes placed in the buffer
0 if input code point is too big
*/
static size_t
ord2utf8(unsigned long int cvalue, unsigned char *buffer)
{
size_t i, j;
for (i = 0; i < sizeof(utf8_table1)/sizeof(int); i++)
if (cvalue <= utf8_table1[i]) break;
if (i >= sizeof(utf8_table1)/sizeof(int)) return 0;
buffer += i;
for (j = i; j > 0; j--)
{
*buffer-- = 0x80 | (cvalue & 0x3f);
cvalue >>= 6;
}
*buffer = utf8_table2[i] | cvalue;
return i + 1;
}
/*************************************************
* Convert UTF-8 string to value *
*************************************************/
/* This function takes one or more bytes that represent a UTF-8 character from
the start of a string of bytes. It returns the value of the character, or the
offset of a malformation. For an overlong encoding that works but is not the
correct (shortest) one, the error offset is just after the last byte.
Argument:
buffer a pointer to the byte vector
buffend a pointer to the end of the buffer
vptr a pointer to a variable to receive the value
lenptr a pointer to a variable to receive the offset when error detected
Returns: > 0 => the number of bytes consumed
0 => invalid UTF-8: first byte missing 0x40 bit
-1 => invalid UTF-8: first byte has too many high-order 1-bits
-2 => incomplete sequence at end of string
-3 => incomplete sequence within string
-4 => overlong code sequence
*/
static int
utf82ord(unsigned char *buffer, unsigned char *buffend,
long unsigned int *vptr, int *lenptr)
{
unsigned int c = *buffer++;
unsigned int d = c;
int i, j, s;
/* Check for an ASCII character, or find the number of additional bytes in a
multibyte character. */
for (i = -1; i < 6; i++)
{
if ((d & 0x80) == 0) break;
d <<= 1;
}
switch (i)
{
case -1: /* ASCII character; first byte does not have 0x80 bit */
*vptr = c;
return 1;
case 0: /* First byte has 0x80 but is missing 0x40 bit */
*lenptr = 0;
return 0;
case 6:
*lenptr = 0; /* Too many high bits */
return -1;
default:
break;
}
/* i now has a value in the range 1-5 */
s = 6*i;
d = (c & utf8_table3[i]) << s;
for (j = 0; j < i; j++)
{
if (buffer >= buffend)
{
*lenptr = j + 1;
return -2;
}
c = *buffer++;
if ((c & 0xc0) != 0x80)
{
*lenptr = j + 1;
return -3;
}
s -= 6;
d |= (c & 0x3f) << s;
}
/* Valid UTF-8 syntax */
*vptr = d;
/* Check that encoding was the correct one, not overlong */
for (j = 0; j < (int)(sizeof(utf8_table1)/sizeof(int)); j++)
if (d <= utf8_table1[j]) break;
if (j != i)
{
*lenptr = i + 1;
return -4;
}
/* Valid value */
return i + 1;
}
/*************************************************
* Main Program *
*************************************************/
int
main(int argc, char **argv)
{
int i = 1;
int show = 0;
unsigned char buffer[64];
if (argc > 1 && strcmp(argv[1], "-s") == 0)
{
show = 1;
i = 2;
}
for (; i < argc; i++)
{
char *x = argv[i];
char *endptr;
if (strncmp(x, "0x", 2) == 0 || strncmp(x, "U+", 2) == 0)
{
size_t rc, j;
unsigned long int d = strtoul(x+2, &endptr, 16);
if (*endptr != 0)
{
printf("** Invalid hex number %s\n", x);
continue; /* With next argument */
}
rc = ord2utf8(d, buffer);
printf("U+%08lx => ", d);
if (rc == 0)
printf("** Code point greater than 0x7fffffff cannot be encoded");
else
{
for (j = 0; j < rc; j++) printf("%02x ", buffer[j]);
if (show)
{
printf(">");
for (j = 0; j < rc; j++) printf("%c", buffer[j]);
printf("< ");
}
if (d >= 0xd800 && d <= 0xdfff)
printf("** Invalid Unicode (surrogate)");
else if (d > 0x10ffff)
printf("** Invalid Unicode (greater than U+10ffff)");
}
printf("\n");
}
else
{
unsigned char *bptr;
unsigned char *buffend;
int len = 0;
int y = 0;
int z = 0;
for (;;)
{
while (*x == ' ') x++;
if (*x == 0 && !z) break;
if (!isxdigit(*x))
{
printf("** Malformed hex string: %s\n", argv[i]);
len = -1;
break;
}
y = y * 16 + tolower(*x) - ((isdigit(*x))? '0' : 'W');
x++;
if (z)
{
buffer[len++] = y;
y = 0;
}
z ^= 1;
}
if (len < 0) continue; /* With next argument after malformation */
bptr = buffer;
buffend = buffer + len;
while (bptr < buffend)
{
unsigned long int d;
int j;
int offset;
int rc = utf82ord(bptr, buffend, &d, &offset);
if (rc > 0)
{
printf("U+%08lx <= ", d);
for (j = 0; j < rc; j++) printf("%02x ", bptr[j]);
if (show)
{
printf(">");
for (j = 0; j < rc; j++) printf("%c", bptr[j]);
printf("<");
}
printf("\n");
bptr += rc;
}
else if (rc == -4)
{
printf("U+%08lx <= ", d);
for (j = 0; j < offset; j++) printf("%02x ", bptr[j]);
printf("** Overlong UTF-8 sequence\n");
bptr += offset;
}
else
{
switch (rc)
{
case 0: printf("** First byte missing 0x40 bit");
break;
case -1: printf("** First byte has too many high-order bits");
break;
case -2: printf("** Incomplete UTF-8 sequence at end of string");
break;
case -3: printf("** Incomplete UTF-8 sequence");
break;
default: printf("** Unexpected return %d from utf82ord()", rc);
break;
}
printf(" at offset %d in string ", offset);
while (bptr < buffend) printf("%02x ", *bptr++);
printf("\n");
break;
}
}
}
}
return 0;
}
/* End */

121
Kha/Backends/Kore-hxcpp/khacpp/project/thirdparty/pcre2-10.42-16/pcre2-config.in vendored Normal file
View File

@ -0,0 +1,121 @@
#!/bin/sh
prefix=@prefix@
exec_prefix=@exec_prefix@
exec_prefix_set=no
cflags="[--cflags]"
libs=
if test @enable_pcre2_16@ = yes ; then
libs="[--libs16] $libs"
fi
if test @enable_pcre2_32@ = yes ; then
libs="[--libs32] $libs"
fi
if test @enable_pcre2_8@ = yes ; then
libs="[--libs8] [--libs-posix] $libs"
cflags="$cflags [--cflags-posix]"
fi
usage="Usage: pcre2-config [--prefix] [--exec-prefix] [--version] $libs $cflags"
if test $# -eq 0; then
echo "${usage}" 1>&2
exit 1
fi
libR=
case `uname -s` in
*SunOS*)
libR=" -R@libdir@"
;;
*BSD*)
libR=" -Wl,-R@libdir@"
;;
esac
libS=
if test @libdir@ != /usr/lib ; then
libS=-L@libdir@
fi
while test $# -gt 0; do
case "$1" in
-*=*) optarg=`echo "$1" | sed 's/[-_a-zA-Z0-9]*=//'` ;;
*) optarg= ;;
esac
case $1 in
--prefix=*)
prefix=$optarg
if test $exec_prefix_set = no ; then
exec_prefix=$optarg
fi
;;
--prefix)
echo $prefix
;;
--exec-prefix=*)
exec_prefix=$optarg
exec_prefix_set=yes
;;
--exec-prefix)
echo $exec_prefix
;;
--version)
echo @PACKAGE_VERSION@
;;
--cflags)
if test @includedir@ != /usr/include ; then
includes=-I@includedir@
fi
echo $includes @PCRE2_STATIC_CFLAG@
;;
--cflags-posix)
if test @enable_pcre2_8@ = yes ; then
if test @includedir@ != /usr/include ; then
includes=-I@includedir@
fi
echo $includes @PCRE2_STATIC_CFLAG@
else
echo "${usage}" 1>&2
fi
;;
--libs-posix)
if test @enable_pcre2_8@ = yes ; then
echo $libS$libR -lpcre2-posix@LIB_POSTFIX@ -lpcre2-8@LIB_POSTFIX@
else
echo "${usage}" 1>&2
fi
;;
--libs8)
if test @enable_pcre2_8@ = yes ; then
echo $libS$libR -lpcre2-8@LIB_POSTFIX@
else
echo "${usage}" 1>&2
fi
;;
--libs16)
if test @enable_pcre2_16@ = yes ; then
echo $libS$libR -lpcre2-16@LIB_POSTFIX@
else
echo "${usage}" 1>&2
fi
;;
--libs32)
if test @enable_pcre2_32@ = yes ; then
echo $libS$libR -lpcre2-32@LIB_POSTFIX@
else
echo "${usage}" 1>&2
fi
;;
*)
echo "${usage}" 1>&2
exit 1
;;
esac
shift
done

50
Kha/Backends/Kore-hxcpp/khacpp/project/thirdparty/pcre2-10.42-16/pcre2_fuzzer.dict vendored Normal file
View File

@ -0,0 +1,50 @@
# This is attempt at a fuzzer dictionary for PCRE2.
"\\A"
"\\b"
"\\B"
"\\d"
"\\D"
"\\h"
"\\H"
"\\n"
"\\N"
"\\s"
"\\S"
"\\w"
"\\W"
"\\z"
"\\Z"
"(?"
"(?:"
"(?>"
"(?="
"(?!"
"(?<="
"(?<!"
"(?|"
"[:alnum:]"
"[:alpha:]"
"[:ascii:]"
"[:blank:]"
"[:cntrl:]"
"[:digit:]"
"[:graph:]"
"[:lower:]"
"[:print:]"
"[:punct:]"
"[:space:]"
"[:upper:]"
"[:word:]"
"[:xdigit:]"
"(*ACCEPT)"
"(*FAIL)"
"(*COMMIT)"
"(*PRUNE)"
"(*SKIP)"
"(*THEN)"
# End

2
Kha/Backends/Kore-hxcpp/khacpp/project/thirdparty/pcre2-10.42-16/pcre2_fuzzer.options vendored Normal file
View File

@ -0,0 +1,2 @@
[libfuzzer]
dict = pcre2_fuzzer.dict

400
Kha/Backends/Kore-hxcpp/khacpp/project/thirdparty/pcre2-10.42-16/perltest.sh vendored Normal file
View File

@ -0,0 +1,400 @@
#! /bin/sh
# Script for testing regular expressions with perl to check that PCRE2 handles
# them the same. For testing with different versions of Perl, if the first
# argument is -perl then the second is taken as the Perl command to use, and
# both are then removed. If the next argument is "-w", Perl is called with
# "-w", which turns on its warning mode.
#
# The Perl code has to have "use utf8" and "require Encode" at the start when
# running UTF-8 tests, but *not* for non-utf8 tests. (The "require" would
# actually be OK for non-utf8-tests, but is not always installed, so this way
# the script will always run for these tests.)
#
# The desired effect is achieved by making this a shell script that passes the
# Perl script to Perl through a pipe. If the next argument is "-utf8", a
# suitable prefix is set up.
#
# The remaining arguments, if any, are passed to Perl. They are an input file
# and an output file. If there is one argument, the output is written to
# STDOUT. If Perl receives no arguments, it opens /dev/tty as input, and writes
# output to STDOUT. (I haven't found a way of getting it to use STDIN, because
# of the contorted piping input.)
perl=perl
perlarg=''
prefix=''
if [ $# -gt 1 -a "$1" = "-perl" ] ; then
shift
perl=$1
shift
fi
if [ $# -gt 0 -a "$1" = "-w" ] ; then
perlarg="-w"
shift
fi
if [ $# -gt 0 -a "$1" = "-utf8" ] ; then
prefix="use utf8; require Encode;"
shift
fi
# The Perl script that follows has a similar specification to pcre2test, and so
# can be given identical input, except that input patterns can be followed only
# by Perl's lower case modifiers and certain other pcre2test modifiers that are
# either handled or ignored:
#
# aftertext interpreted as "print $' afterwards"
# afteralltext ignored
# dupnames ignored (Perl always allows)
# jitstack ignored
# mark show mark information
# no_auto_possess ignored
# no_start_optimize insert (??{""}) at pattern start (disables optimizing)
# -no_start_optimize ignored
# subject_literal does not process subjects for escapes
# ucp sets Perl's /u modifier
# utf invoke UTF-8 functionality
#
# Comment lines are ignored. The #pattern command can be used to set modifiers
# that will be added to each subsequent pattern, after any modifiers it may
# already have. NOTE: this is different to pcre2test where #pattern sets
# defaults which can be overridden on individual patterns. The #subject command
# may be used to set or unset a default "mark" modifier for data lines. This is
# the only use of #subject that is supported. The #perltest, #forbid_utf, and
# #newline_default commands, which are needed in the relevant pcre2test files,
# are ignored. Any other #-command is ignored, with a warning message.
#
# The pattern lines should use only / as the delimiter. The other characters
# that pcre2test supports cause problems with this script.
#
# The data lines must not have any pcre2test modifiers. Unless
# "subject_literal" is on the pattern, data lines are processed as
# Perl double-quoted strings, so if they contain " $ or @ characters, these
# have to be escaped. For this reason, all such characters in the
# Perl-compatible testinput1 and testinput4 files are escaped so that they can
# be used for perltest as well as for pcre2test. The output from this script
# should be same as from pcre2test, apart from the initial identifying banner.
#
# The other testinput files are not suitable for feeding to perltest.sh,
# because they make use of the special modifiers that pcre2test uses for
# testing features of PCRE2. Some of these files also contain malformed regular
# expressions, in order to check that PCRE2 diagnoses them correctly.
(echo "$prefix" ; cat <<'PERLEND'
# The alpha assertions currently give warnings even when -w is not specified.
no warnings "experimental::alpha_assertions";
no warnings "experimental::script_run";
# Function for turning a string into a string of printing chars.
sub pchars {
my($t) = "";
if ($utf8)
{
@p = unpack('U*', $_[0]);
foreach $c (@p)
{
if ($c >= 32 && $c < 127) { $t .= chr $c; }
else { $t .= sprintf("\\x{%02x}", $c);
}
}
}
else
{
foreach $c (split(//, $_[0]))
{
if (ord $c >= 32 && ord $c < 127) { $t .= $c; }
else { $t .= sprintf("\\x%02x", ord $c); }
}
}
$t;
}
# Read lines from a named file or stdin and write to a named file or stdout;
# lines consist of a regular expression, in delimiters and optionally followed
# by options, followed by a set of test data, terminated by an empty line.
# Sort out the input and output files
if (@ARGV > 0)
{
open(INFILE, "<$ARGV[0]") || die "Failed to open $ARGV[0]\n";
$infile = "INFILE";
$interact = 0;
}
else
{
open(INFILE, "</dev/tty") || die "Failed to open /dev/tty\n";
$infile = "INFILE";
$interact = 1;
}
if (@ARGV > 1)
{
open(OUTFILE, ">$ARGV[1]") || die "Failed to open $ARGV[1]\n";
$outfile = "OUTFILE";
}
else { $outfile = "STDOUT"; }
printf($outfile "Perl $^V\n\n");
$extra_modifiers = "";
$default_show_mark = 0;
# Main loop
NEXT_RE:
for (;;)
{
printf " re> " if $interact;
last if ! ($_ = <$infile>);
printf $outfile "$_" if ! $interact;
next if ($_ =~ /^\s*$/ || $_ =~ /^#[\s!]/);
# A few of pcre2test's #-commands are supported, or just ignored. Any others
# cause an error.
if ($_ =~ /^#pattern(.*)/)
{
$extra_modifiers = $1;
chomp($extra_modifiers);
$extra_modifiers =~ s/\s+$//;
next;
}
elsif ($_ =~ /^#subject(.*)/)
{
$mod = $1;
chomp($mod);
$mod =~ s/\s+$//;
if ($mod =~ s/(-?)mark,?//)
{
$minus = $1;
$default_show_mark = ($minus =~ /^$/);
}
if ($mod !~ /^\s*$/)
{
printf $outfile "** Warning: \"$mod\" in #subject ignored\n";
}
next;
}
elsif ($_ =~ /^#/)
{
if ($_ !~ /^#newline_default|^#perltest|^#forbid_utf/)
{
printf $outfile "** Warning: #-command ignored: %s", $_;
}
next;
}
$pattern = $_;
while ($pattern !~ /^\s*(.).*\1/s)
{
printf " > " if $interact;
last if ! ($_ = <$infile>);
printf $outfile "$_" if ! $interact;
$pattern .= $_;
}
chomp($pattern);
$pattern =~ s/\s+$//;
# Split the pattern from the modifiers and adjust them as necessary.
$pattern =~ /^\s*((.).*\2)(.*)$/s;
$pat = $1;
$del = $2;
$mod = "$3,$extra_modifiers";
$mod =~ s/^,\s*//;
# The private "aftertext" modifier means "print $' afterwards".
$showrest = ($mod =~ s/aftertext,?//);
# The "subject_literal" modifier disables escapes in subjects.
$subject_literal = ($mod =~ s/subject_literal,?//);
# "allaftertext" is used by pcre2test to print remainders after captures
$mod =~ s/allaftertext,?//;
# Detect utf
$utf8 = $mod =~ s/utf,?//;
# Remove "dupnames".
$mod =~ s/dupnames,?//;
# Remove "jitstack".
$mod =~ s/jitstack=\d+,?//;
# The "mark" modifier requests checking of MARK data */
$show_mark = $default_show_mark | ($mod =~ s/mark,?//);
# "ucp" asks pcre2test to set PCRE2_UCP; change this to /u for Perl
$mod =~ s/ucp,?/u/;
# Remove "no_auto_possess".
$mod =~ s/no_auto_possess,?//;
# Use no_start_optimize (disable PCRE2 start-up optimization) to disable Perl
# optimization by inserting (??{""}) at the start of the pattern. We may
# also encounter -no_start_optimize from a #pattern setting.
$mod =~ s/-no_start_optimize,?//;
if ($mod =~ s/no_start_optimize,?//) { $pat =~ s/$del/$del(??{""})/; }
# Add back retained modifiers and check that the pattern is valid.
$mod =~ s/,//g;
$pattern = "$pat$mod";
eval "\$_ =~ ${pattern}";
if ($@)
{
printf $outfile "Error: $@";
if (! $interact)
{
for (;;)
{
last if ! ($_ = <$infile>);
last if $_ =~ /^\s*$/;
}
}
next NEXT_RE;
}
# If the /g modifier is present, we want to put a loop round the matching;
# otherwise just a single "if".
$cmd = ($pattern =~ /g[a-z]*$/)? "while" : "if";
# If the pattern is actually the null string, Perl uses the most recently
# executed (and successfully compiled) regex is used instead. This is a
# nasty trap for the unwary! The PCRE2 test suite does contain null strings
# in places - if they are allowed through here all sorts of weird and
# unexpected effects happen. To avoid this, we replace such patterns with
# a non-null pattern that has the same effect.
$pattern = "/(?#)/$2" if ($pattern =~ /^(.)\1(.*)$/);
# Read data lines and test them
for (;;)
{
printf "data> " if $interact;
last NEXT_RE if ! ($_ = <$infile>);
chomp;
printf $outfile "%s", "$_\n" if ! $interact;
s/\s+$//; # Remove trailing space
s/^\s+//; # Remove leading space
last if ($_ eq "");
next if $_ =~ /^\\=(?:\s|$)/; # Comment line
if ($subject_literal)
{
$x = $_;
}
else
{
$x = eval "\"$_\""; # To get escapes processed
}
# Empty array for holding results, ensure $REGERROR and $REGMARK are
# unset, then do the matching.
@subs = ();
$pushes = "push \@subs,\$&;" .
"push \@subs,\$1;" .
"push \@subs,\$2;" .
"push \@subs,\$3;" .
"push \@subs,\$4;" .
"push \@subs,\$5;" .
"push \@subs,\$6;" .
"push \@subs,\$7;" .
"push \@subs,\$8;" .
"push \@subs,\$9;" .
"push \@subs,\$10;" .
"push \@subs,\$11;" .
"push \@subs,\$12;" .
"push \@subs,\$13;" .
"push \@subs,\$14;" .
"push \@subs,\$15;" .
"push \@subs,\$16;" .
"push \@subs,\$'; }";
undef $REGERROR;
undef $REGMARK;
eval "${cmd} (\$x =~ ${pattern}) {" . $pushes;
if ($@)
{
printf $outfile "Error: $@\n";
next NEXT_RE;
}
elsif (scalar(@subs) == 0)
{
printf $outfile "No match";
if ($show_mark && defined $REGERROR && $REGERROR != 1)
{ printf $outfile (", mark = %s", &pchars($REGERROR)); }
printf $outfile "\n";
}
else
{
while (scalar(@subs) != 0)
{
printf $outfile (" 0: %s\n", &pchars($subs[0]));
printf $outfile (" 0+ %s\n", &pchars($subs[17])) if $showrest;
$last_printed = 0;
for ($i = 1; $i <= 16; $i++)
{
if (defined $subs[$i])
{
while ($last_printed++ < $i-1)
{ printf $outfile ("%2d: <unset>\n", $last_printed); }
printf $outfile ("%2d: %s\n", $i, &pchars($subs[$i]));
$last_printed = $i;
}
}
splice(@subs, 0, 18);
}
# It seems that $REGMARK is not marked as UTF-8 even when use utf8 is
# set and the input pattern was a UTF-8 string. We can, however, force
# it to be so marked.
if ($show_mark && defined $REGMARK && $REGMARK != 1)
{
$xx = $REGMARK;
$xx = Encode::decode_utf8($xx) if $utf8;
printf $outfile ("MK: %s\n", &pchars($xx));
}
}
}
}
# By closing OUTFILE explicitly, we avoid a Perl warning in -w mode
# "main::OUTFILE" used only once".
close(OUTFILE) if $outfile eq "OUTFILE";
PERLEND
) | $perl $perlarg - $@
# End

460
Kha/Backends/Kore-hxcpp/khacpp/project/thirdparty/pcre2-10.42-16/src/config.h vendored Normal file
View File

@ -0,0 +1,460 @@
#define PCRE2_CODE_UNIT_WIDTH 16
#define SUPPORT_PCRE2_16
/* src/config.h. Generated from config.h.in by configure. */
/* src/config.h.in. Generated from configure.ac by autoheader. */
/* PCRE2 is written in Standard C, but there are a few non-standard things it
can cope with, allowing it to run on SunOS4 and other "close to standard"
systems.
In environments that support the GNU autotools, config.h.in is converted into
config.h by the "configure" script. In environments that use CMake,
config-cmake.in is converted into config.h. If you are going to build PCRE2 "by
hand" without using "configure" or CMake, you should copy the distributed
config.h.generic to config.h, and edit the macro definitions to be the way you
need them. You must then add -DHAVE_CONFIG_H to all of your compile commands,
so that config.h is included at the start of every source.
Alternatively, you can avoid editing by using -D on the compiler command line
to set the macro values. In this case, you do not have to set -DHAVE_CONFIG_H,
but if you do, default values will be taken from config.h for non-boolean
macros that are not defined on the command line.
Boolean macros such as HAVE_STDLIB_H and SUPPORT_PCRE2_8 should either be
defined (conventionally to 1) for TRUE, and not defined at all for FALSE. All
such macros are listed as a commented #undef in config.h.generic. Macros such
as MATCH_LIMIT, whose actual value is relevant, have defaults defined, but are
surrounded by #ifndef/#endif lines so that the value can be overridden by -D.
PCRE2 uses memmove() if HAVE_MEMMOVE is defined; otherwise it uses bcopy() if
HAVE_BCOPY is defined. If your system has neither bcopy() nor memmove(), make
sure both macros are undefined; an emulation function will then be used. */
/* By default, the \R escape sequence matches any Unicode line ending
character or sequence of characters. If BSR_ANYCRLF is defined (to any
value), this is changed so that backslash-R matches only CR, LF, or CRLF.
The build-time default can be overridden by the user of PCRE2 at runtime.
*/
/* #undef BSR_ANYCRLF */
/* Define to any value to disable the use of the z and t modifiers in
formatting settings such as %zu or %td (this is rarely needed). */
/* #undef DISABLE_PERCENT_ZT */
/* If you are compiling for a system that uses EBCDIC instead of ASCII
character codes, define this macro to any value. When EBCDIC is set, PCRE2
assumes that all input strings are in EBCDIC. If you do not define this
macro, PCRE2 will assume input strings are ASCII or UTF-8/16/32 Unicode. It
is not possible to build a version of PCRE2 that supports both EBCDIC and
UTF-8/16/32. */
/* #undef EBCDIC */
/* In an EBCDIC environment, define this macro to any value to arrange for the
NL character to be 0x25 instead of the default 0x15. NL plays the role that
LF does in an ASCII/Unicode environment. */
/* #undef EBCDIC_NL25 */
/* Define this if your compiler supports __attribute__((uninitialized)) */
/* #undef HAVE_ATTRIBUTE_UNINITIALIZED */
/* Define to 1 if you have the `bcopy' function. */
/* #undef HAVE_BCOPY */
/* Define to 1 if you have the <bzlib.h> header file. */
/* #undef HAVE_BZLIB_H */
/* Define to 1 if you have the <dirent.h> header file. */
/* #undef HAVE_DIRENT_H */
/* Define to 1 if you have the <dlfcn.h> header file. */
/* #undef HAVE_DLFCN_H */
/* Define to 1 if you have the <editline/readline.h> header file. */
/* #undef HAVE_EDITLINE_READLINE_H */
/* Define to 1 if you have the <edit/readline/readline.h> header file. */
/* #undef HAVE_EDIT_READLINE_READLINE_H */
/* Define to 1 if you have the <inttypes.h> header file. */
/* #undef HAVE_INTTYPES_H */
/* Define to 1 if you have the <limits.h> header file. */
/* #undef HAVE_LIMITS_H */
/* Define to 1 if you have the `memfd_create' function. */
/* #undef HAVE_MEMFD_CREATE */
/* Define to 1 if you have the `memmove' function. */
/* #undef HAVE_MEMMOVE */
/* Define to 1 if you have the <minix/config.h> header file. */
/* #undef HAVE_MINIX_CONFIG_H */
/* Define to 1 if you have the `mkostemp' function. */
/* #undef HAVE_MKOSTEMP */
/* Define if you have POSIX threads libraries and header files. */
/* #undef HAVE_PTHREAD */
/* Have PTHREAD_PRIO_INHERIT. */
/* #undef HAVE_PTHREAD_PRIO_INHERIT */
/* Define to 1 if you have the <readline.h> header file. */
/* #undef HAVE_READLINE_H */
/* Define to 1 if you have the <readline/history.h> header file. */
/* #undef HAVE_READLINE_HISTORY_H */
/* Define to 1 if you have the <readline/readline.h> header file. */
/* #undef HAVE_READLINE_READLINE_H */
/* Define to 1 if you have the `realpath' function. */
/* #undef HAVE_REALPATH */
/* Define to 1 if you have the `secure_getenv' function. */
/* #undef HAVE_SECURE_GETENV */
/* Define to 1 if you have the <stdint.h> header file. */
/* #undef HAVE_STDINT_H */
/* Define to 1 if you have the <stdio.h> header file. */
/* #undef HAVE_STDIO_H */
/* Define to 1 if you have the <stdlib.h> header file. */
/* #undef HAVE_STDLIB_H */
/* Define to 1 if you have the `strerror' function. */
/* #undef HAVE_STRERROR */
/* Define to 1 if you have the <strings.h> header file. */
/* #undef HAVE_STRINGS_H */
/* Define to 1 if you have the <string.h> header file. */
/* #undef HAVE_STRING_H */
/* Define to 1 if you have the <sys/stat.h> header file. */
/* #undef HAVE_SYS_STAT_H */
/* Define to 1 if you have the <sys/types.h> header file. */
/* #undef HAVE_SYS_TYPES_H */
/* Define to 1 if you have the <sys/wait.h> header file. */
/* #undef HAVE_SYS_WAIT_H */
/* Define to 1 if you have the <unistd.h> header file. */
/* #undef HAVE_UNISTD_H */
/* Define to 1 if the compiler supports simple visibility declarations. */
/* #undef HAVE_VISIBILITY */
/* Define to 1 if you have the <wchar.h> header file. */
/* #undef HAVE_WCHAR_H */
/* Define to 1 if you have the <windows.h> header file. */
/* #undef HAVE_WINDOWS_H */
/* Define to 1 if you have the <zlib.h> header file. */
/* #undef HAVE_ZLIB_H */
/* This limits the amount of memory that may be used while matching a pattern.
It applies to both pcre2_match() and pcre2_dfa_match(). It does not apply
to JIT matching. The value is in kibibytes (units of 1024 bytes). */
#ifndef HEAP_LIMIT
#define HEAP_LIMIT 20000000
#endif
/* The value of LINK_SIZE determines the number of bytes used to store links
as offsets within the compiled regex. The default is 2, which allows for
compiled patterns up to 65535 code units long. This covers the vast
majority of cases. However, PCRE2 can also be compiled to use 3 or 4 bytes
instead. This allows for longer patterns in extreme cases. */
#ifndef LINK_SIZE
#define LINK_SIZE 2
#endif
/* Define to the sub-directory where libtool stores uninstalled libraries. */
/* This is ignored unless you are using libtool. */
#ifndef LT_OBJDIR
#define LT_OBJDIR ".libs/"
#endif
/* The value of MATCH_LIMIT determines the default number of times the
pcre2_match() function can record a backtrack position during a single
matching attempt. The value is also used to limit a loop counter in
pcre2_dfa_match(). There is a runtime interface for setting a different
limit. The limit exists in order to catch runaway regular expressions that
take for ever to determine that they do not match. The default is set very
large so that it does not accidentally catch legitimate cases. */
#ifndef MATCH_LIMIT
#define MATCH_LIMIT 10000000
#endif
/* The above limit applies to all backtracks, whether or not they are nested.
In some environments it is desirable to limit the nesting of backtracking
(that is, the depth of tree that is searched) more strictly, in order to
restrict the maximum amount of heap memory that is used. The value of
MATCH_LIMIT_DEPTH provides this facility. To have any useful effect, it
must be less than the value of MATCH_LIMIT. The default is to use the same
value as MATCH_LIMIT. There is a runtime method for setting a different
limit. In the case of pcre2_dfa_match(), this limit controls the depth of
the internal nested function calls that are used for pattern recursions,
lookarounds, and atomic groups. */
#ifndef MATCH_LIMIT_DEPTH
#define MATCH_LIMIT_DEPTH MATCH_LIMIT
#endif
/* This limit is parameterized just in case anybody ever wants to change it.
Care must be taken if it is increased, because it guards against integer
overflow caused by enormously large patterns. */
#ifndef MAX_NAME_COUNT
#define MAX_NAME_COUNT 10000
#endif
/* This limit is parameterized just in case anybody ever wants to change it.
Care must be taken if it is increased, because it guards against integer
overflow caused by enormously large patterns. */
#ifndef MAX_NAME_SIZE
#define MAX_NAME_SIZE 32
#endif
/* Defining NEVER_BACKSLASH_C locks out the use of \C in all patterns. */
/* #undef NEVER_BACKSLASH_C */
/* The value of NEWLINE_DEFAULT determines the default newline character
sequence. PCRE2 client programs can override this by selecting other values
at run time. The valid values are 1 (CR), 2 (LF), 3 (CRLF), 4 (ANY), 5
(ANYCRLF), and 6 (NUL). */
#ifndef NEWLINE_DEFAULT
#define NEWLINE_DEFAULT 2
#endif
/* Name of package */
#define PACKAGE "pcre2"
/* Define to the address where bug reports for this package should be sent. */
#define PACKAGE_BUGREPORT ""
/* Define to the full name of this package. */
#define PACKAGE_NAME "PCRE2"
/* Define to the full name and version of this package. */
#define PACKAGE_STRING "PCRE2 10.42"
/* Define to the one symbol short name of this package. */
#define PACKAGE_TARNAME "pcre2"
/* Define to the home page for this package. */
#define PACKAGE_URL ""
/* Define to the version of this package. */
#define PACKAGE_VERSION "10.42"
/* The value of PARENS_NEST_LIMIT specifies the maximum depth of nested
parentheses (of any kind) in a pattern. This limits the amount of system
stack that is used while compiling a pattern. */
#ifndef PARENS_NEST_LIMIT
#define PARENS_NEST_LIMIT 250
#endif
/* The value of PCRE2GREP_BUFSIZE is the starting size of the buffer used by
pcre2grep to hold parts of the file it is searching. The buffer will be
expanded up to PCRE2GREP_MAX_BUFSIZE if necessary, for files containing
very long lines. The actual amount of memory used by pcre2grep is three
times this number, because it allows for the buffering of "before" and
"after" lines. */
#ifndef PCRE2GREP_BUFSIZE
#define PCRE2GREP_BUFSIZE 20480
#endif
/* The value of PCRE2GREP_MAX_BUFSIZE specifies the maximum size of the buffer
used by pcre2grep to hold parts of the file it is searching. The actual
amount of memory used by pcre2grep is three times this number, because it
allows for the buffering of "before" and "after" lines. */
#ifndef PCRE2GREP_MAX_BUFSIZE
#define PCRE2GREP_MAX_BUFSIZE 1048576
#endif
/* Define to any value to include debugging code. */
/* #undef PCRE2_DEBUG */
/* If you are compiling for a system other than a Unix-like system or
Win32, and it needs some magic to be inserted before the definition
of a function that is exported by the library, define this macro to
contain the relevant magic. If you do not define this macro, a suitable
__declspec value is used for Windows systems; in other environments
"extern" is used for a C compiler and "extern C" for a C++ compiler.
This macro apears at the start of every exported function that is part
of the external API. It does not appear on functions that are "external"
in the C sense, but which are internal to the library. */
/* #undef PCRE2_EXP_DEFN */
/* Define to any value if linking statically (TODO: make nice with Libtool) */
/* #undef PCRE2_STATIC */
/* Define to necessary symbol if this constant uses a non-standard name on
your system. */
/* #undef PTHREAD_CREATE_JOINABLE */
/* Define to any non-zero number to enable support for SELinux compatible
executable memory allocator in JIT. Note that this will have no effect
unless SUPPORT_JIT is also defined. */
/* #undef SLJIT_PROT_EXECUTABLE_ALLOCATOR */
/* Define to 1 if all of the C90 standard headers exist (not just the ones
required in a freestanding environment). This macro is provided for
backward compatibility; new code need not use it. */
/* #undef STDC_HEADERS */
/* Define to any value to enable support for Just-In-Time compiling. */
/* #undef SUPPORT_JIT */
/* Define to any value to allow pcre2grep to be linked with libbz2, so that it
is able to handle .bz2 files. */
/* #undef SUPPORT_LIBBZ2 */
/* Define to any value to allow pcre2test to be linked with libedit. */
/* #undef SUPPORT_LIBEDIT */
/* Define to any value to allow pcre2test to be linked with libreadline. */
/* #undef SUPPORT_LIBREADLINE */
/* Define to any value to allow pcre2grep to be linked with libz, so that it
is able to handle .gz files. */
/* #undef SUPPORT_LIBZ */
/* Define to any value to enable callout script support in pcre2grep. */
/* #undef SUPPORT_PCRE2GREP_CALLOUT */
/* Define to any value to enable fork support in pcre2grep callout scripts.
This will have no effect unless SUPPORT_PCRE2GREP_CALLOUT is also defined.
*/
/* #undef SUPPORT_PCRE2GREP_CALLOUT_FORK */
/* Define to any value to enable JIT support in pcre2grep. Note that this will
have no effect unless SUPPORT_JIT is also defined. */
/* #undef SUPPORT_PCRE2GREP_JIT */
/* Define to any value to enable the 16 bit PCRE2 library. */
/* #undef SUPPORT_PCRE2_16 */
/* Define to any value to enable the 32 bit PCRE2 library. */
/* #undef SUPPORT_PCRE2_32 */
/* Define to any value to enable the 8 bit PCRE2 library. */
/* #undef SUPPORT_PCRE2_8 */
/* Define to any value to enable support for Unicode and UTF encoding. This
will work even in an EBCDIC environment, but it is incompatible with the
EBCDIC macro. That is, PCRE2 can support *either* EBCDIC code *or*
ASCII/Unicode, but not both at once. */
/* #undef SUPPORT_UNICODE */
/* Define to any value for valgrind support to find invalid memory reads. */
/* #undef SUPPORT_VALGRIND */
/* Enable extensions on AIX 3, Interix. */
#ifndef _ALL_SOURCE
# define _ALL_SOURCE 1
#endif
/* Enable general extensions on macOS. */
#ifndef _DARWIN_C_SOURCE
# define _DARWIN_C_SOURCE 1
#endif
/* Enable general extensions on Solaris. */
#ifndef __EXTENSIONS__
# define __EXTENSIONS__ 1
#endif
/* Enable GNU extensions on systems that have them. */
#ifndef _GNU_SOURCE
# define _GNU_SOURCE 1
#endif
/* Enable X/Open compliant socket functions that do not require linking
with -lxnet on HP-UX 11.11. */
#ifndef _HPUX_ALT_XOPEN_SOCKET_API
# define _HPUX_ALT_XOPEN_SOCKET_API 1
#endif
/* Identify the host operating system as Minix.
This macro does not affect the system headers' behavior.
A future release of Autoconf may stop defining this macro. */
#ifndef _MINIX
/* # undef _MINIX */
#endif
/* Enable general extensions on NetBSD.
Enable NetBSD compatibility extensions on Minix. */
#ifndef _NETBSD_SOURCE
# define _NETBSD_SOURCE 1
#endif
/* Enable OpenBSD compatibility extensions on NetBSD.
Oddly enough, this does nothing on OpenBSD. */
#ifndef _OPENBSD_SOURCE
# define _OPENBSD_SOURCE 1
#endif
/* Define to 1 if needed for POSIX-compatible behavior. */
#ifndef _POSIX_SOURCE
/* # undef _POSIX_SOURCE */
#endif
/* Define to 2 if needed for POSIX-compatible behavior. */
#ifndef _POSIX_1_SOURCE
/* # undef _POSIX_1_SOURCE */
#endif
/* Enable POSIX-compatible threading on Solaris. */
#ifndef _POSIX_PTHREAD_SEMANTICS
# define _POSIX_PTHREAD_SEMANTICS 1
#endif
/* Enable extensions specified by ISO/IEC TS 18661-5:2014. */
#ifndef __STDC_WANT_IEC_60559_ATTRIBS_EXT__
# define __STDC_WANT_IEC_60559_ATTRIBS_EXT__ 1
#endif
/* Enable extensions specified by ISO/IEC TS 18661-1:2014. */
#ifndef __STDC_WANT_IEC_60559_BFP_EXT__
# define __STDC_WANT_IEC_60559_BFP_EXT__ 1
#endif
/* Enable extensions specified by ISO/IEC TS 18661-2:2015. */
#ifndef __STDC_WANT_IEC_60559_DFP_EXT__
# define __STDC_WANT_IEC_60559_DFP_EXT__ 1
#endif
/* Enable extensions specified by ISO/IEC TS 18661-4:2015. */
#ifndef __STDC_WANT_IEC_60559_FUNCS_EXT__
# define __STDC_WANT_IEC_60559_FUNCS_EXT__ 1
#endif
/* Enable extensions specified by ISO/IEC TS 18661-3:2015. */
#ifndef __STDC_WANT_IEC_60559_TYPES_EXT__
# define __STDC_WANT_IEC_60559_TYPES_EXT__ 1
#endif
/* Enable extensions specified by ISO/IEC TR 24731-2:2010. */
#ifndef __STDC_WANT_LIB_EXT2__
# define __STDC_WANT_LIB_EXT2__ 1
#endif
/* Enable extensions specified by ISO/IEC 24747:2009. */
#ifndef __STDC_WANT_MATH_SPEC_FUNCS__
# define __STDC_WANT_MATH_SPEC_FUNCS__ 1
#endif
/* Enable extensions on HP NonStop. */
#ifndef _TANDEM_SOURCE
# define _TANDEM_SOURCE 1
#endif
/* Enable X/Open extensions. Define to 500 only if necessary
to make mbstate_t available. */
#ifndef _XOPEN_SOURCE
/* # undef _XOPEN_SOURCE */
#endif
/* Version number of package */
#define VERSION "10.42"
/* Number of bits in a file offset, on hosts where this is settable. */
/* #undef _FILE_OFFSET_BITS */
/* Define for large files, on AIX-style hosts. */
/* #undef _LARGE_FILES */
/* Define to empty if `const' does not conform to ANSI C. */
/* #undef const */
/* Define to the type of a signed integer type of width exactly 64 bits if
such a type exists and the standard includes do not define it. */
/* #undef int64_t */
/* Define to `unsigned int' if <sys/types.h> does not define. */
/* #undef size_t */

445
Kha/Backends/Kore-hxcpp/khacpp/project/thirdparty/pcre2-10.42-16/src/config.h.in vendored Normal file
View File

@ -0,0 +1,445 @@
/* src/config.h.in. Generated from configure.ac by autoheader. */
/* PCRE2 is written in Standard C, but there are a few non-standard things it
can cope with, allowing it to run on SunOS4 and other "close to standard"
systems.
In environments that support the GNU autotools, config.h.in is converted into
config.h by the "configure" script. In environments that use CMake,
config-cmake.in is converted into config.h. If you are going to build PCRE2 "by
hand" without using "configure" or CMake, you should copy the distributed
config.h.generic to config.h, and edit the macro definitions to be the way you
need them. You must then add -DHAVE_CONFIG_H to all of your compile commands,
so that config.h is included at the start of every source.
Alternatively, you can avoid editing by using -D on the compiler command line
to set the macro values. In this case, you do not have to set -DHAVE_CONFIG_H,
but if you do, default values will be taken from config.h for non-boolean
macros that are not defined on the command line.
Boolean macros such as HAVE_STDLIB_H and SUPPORT_PCRE2_8 should either be
defined (conventionally to 1) for TRUE, and not defined at all for FALSE. All
such macros are listed as a commented #undef in config.h.generic. Macros such
as MATCH_LIMIT, whose actual value is relevant, have defaults defined, but are
surrounded by #ifndef/#endif lines so that the value can be overridden by -D.
PCRE2 uses memmove() if HAVE_MEMMOVE is defined; otherwise it uses bcopy() if
HAVE_BCOPY is defined. If your system has neither bcopy() nor memmove(), make
sure both macros are undefined; an emulation function will then be used. */
/* By default, the \R escape sequence matches any Unicode line ending
character or sequence of characters. If BSR_ANYCRLF is defined (to any
value), this is changed so that backslash-R matches only CR, LF, or CRLF.
The build-time default can be overridden by the user of PCRE2 at runtime.
*/
#undef BSR_ANYCRLF
/* Define to any value to disable the use of the z and t modifiers in
formatting settings such as %zu or %td (this is rarely needed). */
#undef DISABLE_PERCENT_ZT
/* If you are compiling for a system that uses EBCDIC instead of ASCII
character codes, define this macro to any value. When EBCDIC is set, PCRE2
assumes that all input strings are in EBCDIC. If you do not define this
macro, PCRE2 will assume input strings are ASCII or UTF-8/16/32 Unicode. It
is not possible to build a version of PCRE2 that supports both EBCDIC and
UTF-8/16/32. */
#undef EBCDIC
/* In an EBCDIC environment, define this macro to any value to arrange for the
NL character to be 0x25 instead of the default 0x15. NL plays the role that
LF does in an ASCII/Unicode environment. */
#undef EBCDIC_NL25
/* Define this if your compiler supports __attribute__((uninitialized)) */
#undef HAVE_ATTRIBUTE_UNINITIALIZED
/* Define to 1 if you have the `bcopy' function. */
#undef HAVE_BCOPY
/* Define to 1 if you have the <bzlib.h> header file. */
#undef HAVE_BZLIB_H
/* Define to 1 if you have the <dirent.h> header file. */
#undef HAVE_DIRENT_H
/* Define to 1 if you have the <dlfcn.h> header file. */
#undef HAVE_DLFCN_H
/* Define to 1 if you have the <editline/readline.h> header file. */
#undef HAVE_EDITLINE_READLINE_H
/* Define to 1 if you have the <edit/readline/readline.h> header file. */
#undef HAVE_EDIT_READLINE_READLINE_H
/* Define to 1 if you have the <inttypes.h> header file. */
#undef HAVE_INTTYPES_H
/* Define to 1 if you have the <limits.h> header file. */
#undef HAVE_LIMITS_H
/* Define to 1 if you have the `memfd_create' function. */
#undef HAVE_MEMFD_CREATE
/* Define to 1 if you have the `memmove' function. */
#undef HAVE_MEMMOVE
/* Define to 1 if you have the <minix/config.h> header file. */
#undef HAVE_MINIX_CONFIG_H
/* Define to 1 if you have the `mkostemp' function. */
#undef HAVE_MKOSTEMP
/* Define if you have POSIX threads libraries and header files. */
#undef HAVE_PTHREAD
/* Have PTHREAD_PRIO_INHERIT. */
#undef HAVE_PTHREAD_PRIO_INHERIT
/* Define to 1 if you have the <readline.h> header file. */
#undef HAVE_READLINE_H
/* Define to 1 if you have the <readline/history.h> header file. */
#undef HAVE_READLINE_HISTORY_H
/* Define to 1 if you have the <readline/readline.h> header file. */
#undef HAVE_READLINE_READLINE_H
/* Define to 1 if you have the `realpath' function. */
#undef HAVE_REALPATH
/* Define to 1 if you have the `secure_getenv' function. */
#undef HAVE_SECURE_GETENV
/* Define to 1 if you have the <stdint.h> header file. */
#undef HAVE_STDINT_H
/* Define to 1 if you have the <stdio.h> header file. */
#undef HAVE_STDIO_H
/* Define to 1 if you have the <stdlib.h> header file. */
#undef HAVE_STDLIB_H
/* Define to 1 if you have the `strerror' function. */
#undef HAVE_STRERROR
/* Define to 1 if you have the <strings.h> header file. */
#undef HAVE_STRINGS_H
/* Define to 1 if you have the <string.h> header file. */
#undef HAVE_STRING_H
/* Define to 1 if you have the <sys/stat.h> header file. */
#undef HAVE_SYS_STAT_H
/* Define to 1 if you have the <sys/types.h> header file. */
#undef HAVE_SYS_TYPES_H
/* Define to 1 if you have the <sys/wait.h> header file. */
#undef HAVE_SYS_WAIT_H
/* Define to 1 if you have the <unistd.h> header file. */
#undef HAVE_UNISTD_H
/* Define to 1 if the compiler supports simple visibility declarations. */
#undef HAVE_VISIBILITY
/* Define to 1 if you have the <wchar.h> header file. */
#undef HAVE_WCHAR_H
/* Define to 1 if you have the <windows.h> header file. */
#undef HAVE_WINDOWS_H
/* Define to 1 if you have the <zlib.h> header file. */
#undef HAVE_ZLIB_H
/* This limits the amount of memory that may be used while matching a pattern.
It applies to both pcre2_match() and pcre2_dfa_match(). It does not apply
to JIT matching. The value is in kibibytes (units of 1024 bytes). */
#undef HEAP_LIMIT
/* The value of LINK_SIZE determines the number of bytes used to store links
as offsets within the compiled regex. The default is 2, which allows for
compiled patterns up to 65535 code units long. This covers the vast
majority of cases. However, PCRE2 can also be compiled to use 3 or 4 bytes
instead. This allows for longer patterns in extreme cases. */
#undef LINK_SIZE
/* Define to the sub-directory where libtool stores uninstalled libraries. */
#undef LT_OBJDIR
/* The value of MATCH_LIMIT determines the default number of times the
pcre2_match() function can record a backtrack position during a single
matching attempt. The value is also used to limit a loop counter in
pcre2_dfa_match(). There is a runtime interface for setting a different
limit. The limit exists in order to catch runaway regular expressions that
take for ever to determine that they do not match. The default is set very
large so that it does not accidentally catch legitimate cases. */
#undef MATCH_LIMIT
/* The above limit applies to all backtracks, whether or not they are nested.
In some environments it is desirable to limit the nesting of backtracking
(that is, the depth of tree that is searched) more strictly, in order to
restrict the maximum amount of heap memory that is used. The value of
MATCH_LIMIT_DEPTH provides this facility. To have any useful effect, it
must be less than the value of MATCH_LIMIT. The default is to use the same
value as MATCH_LIMIT. There is a runtime method for setting a different
limit. In the case of pcre2_dfa_match(), this limit controls the depth of
the internal nested function calls that are used for pattern recursions,
lookarounds, and atomic groups. */
#undef MATCH_LIMIT_DEPTH
/* This limit is parameterized just in case anybody ever wants to change it.
Care must be taken if it is increased, because it guards against integer
overflow caused by enormously large patterns. */
#undef MAX_NAME_COUNT
/* This limit is parameterized just in case anybody ever wants to change it.
Care must be taken if it is increased, because it guards against integer
overflow caused by enormously large patterns. */
#undef MAX_NAME_SIZE
/* Defining NEVER_BACKSLASH_C locks out the use of \C in all patterns. */
#undef NEVER_BACKSLASH_C
/* The value of NEWLINE_DEFAULT determines the default newline character
sequence. PCRE2 client programs can override this by selecting other values
at run time. The valid values are 1 (CR), 2 (LF), 3 (CRLF), 4 (ANY), 5
(ANYCRLF), and 6 (NUL). */
#undef NEWLINE_DEFAULT
/* Name of package */
#undef PACKAGE
/* Define to the address where bug reports for this package should be sent. */
#undef PACKAGE_BUGREPORT
/* Define to the full name of this package. */
#undef PACKAGE_NAME
/* Define to the full name and version of this package. */
#undef PACKAGE_STRING
/* Define to the one symbol short name of this package. */
#undef PACKAGE_TARNAME
/* Define to the home page for this package. */
#undef PACKAGE_URL
/* Define to the version of this package. */
#undef PACKAGE_VERSION
/* The value of PARENS_NEST_LIMIT specifies the maximum depth of nested
parentheses (of any kind) in a pattern. This limits the amount of system
stack that is used while compiling a pattern. */
#undef PARENS_NEST_LIMIT
/* The value of PCRE2GREP_BUFSIZE is the starting size of the buffer used by
pcre2grep to hold parts of the file it is searching. The buffer will be
expanded up to PCRE2GREP_MAX_BUFSIZE if necessary, for files containing
very long lines. The actual amount of memory used by pcre2grep is three
times this number, because it allows for the buffering of "before" and
"after" lines. */
#undef PCRE2GREP_BUFSIZE
/* The value of PCRE2GREP_MAX_BUFSIZE specifies the maximum size of the buffer
used by pcre2grep to hold parts of the file it is searching. The actual
amount of memory used by pcre2grep is three times this number, because it
allows for the buffering of "before" and "after" lines. */
#undef PCRE2GREP_MAX_BUFSIZE
/* to make a symbol visible */
#undef PCRE2POSIX_EXP_DECL
/* to make a symbol visible */
#undef PCRE2POSIX_EXP_DEFN
/* Define to any value to include debugging code. */
#undef PCRE2_DEBUG
/* to make a symbol visible */
#undef PCRE2_EXP_DECL
/* If you are compiling for a system other than a Unix-like system or
Win32, and it needs some magic to be inserted before the definition
of a function that is exported by the library, define this macro to
contain the relevant magic. If you do not define this macro, a suitable
__declspec value is used for Windows systems; in other environments
"extern" is used for a C compiler and "extern C" for a C++ compiler.
This macro apears at the start of every exported function that is part
of the external API. It does not appear on functions that are "external"
in the C sense, but which are internal to the library. */
#undef PCRE2_EXP_DEFN
/* Define to any value if linking statically (TODO: make nice with Libtool) */
#undef PCRE2_STATIC
/* Define to necessary symbol if this constant uses a non-standard name on
your system. */
#undef PTHREAD_CREATE_JOINABLE
/* Define to any non-zero number to enable support for SELinux compatible
executable memory allocator in JIT. Note that this will have no effect
unless SUPPORT_JIT is also defined. */
#undef SLJIT_PROT_EXECUTABLE_ALLOCATOR
/* Define to 1 if all of the C90 standard headers exist (not just the ones
required in a freestanding environment). This macro is provided for
backward compatibility; new code need not use it. */
#undef STDC_HEADERS
/* Define to any value to enable support for Just-In-Time compiling. */
#undef SUPPORT_JIT
/* Define to any value to allow pcre2grep to be linked with libbz2, so that it
is able to handle .bz2 files. */
#undef SUPPORT_LIBBZ2
/* Define to any value to allow pcre2test to be linked with libedit. */
#undef SUPPORT_LIBEDIT
/* Define to any value to allow pcre2test to be linked with libreadline. */
#undef SUPPORT_LIBREADLINE
/* Define to any value to allow pcre2grep to be linked with libz, so that it
is able to handle .gz files. */
#undef SUPPORT_LIBZ
/* Define to any value to enable callout script support in pcre2grep. */
#undef SUPPORT_PCRE2GREP_CALLOUT
/* Define to any value to enable fork support in pcre2grep callout scripts.
This will have no effect unless SUPPORT_PCRE2GREP_CALLOUT is also defined.
*/
#undef SUPPORT_PCRE2GREP_CALLOUT_FORK
/* Define to any value to enable JIT support in pcre2grep. Note that this will
have no effect unless SUPPORT_JIT is also defined. */
#undef SUPPORT_PCRE2GREP_JIT
/* Define to any value to enable the 16 bit PCRE2 library. */
#undef SUPPORT_PCRE2_16
/* Define to any value to enable the 32 bit PCRE2 library. */
#undef SUPPORT_PCRE2_32
/* Define to any value to enable the 8 bit PCRE2 library. */
#undef SUPPORT_PCRE2_8
/* Define to any value to enable support for Unicode and UTF encoding. This
will work even in an EBCDIC environment, but it is incompatible with the
EBCDIC macro. That is, PCRE2 can support *either* EBCDIC code *or*
ASCII/Unicode, but not both at once. */
#undef SUPPORT_UNICODE
/* Define to any value for valgrind support to find invalid memory reads. */
#undef SUPPORT_VALGRIND
/* Enable extensions on AIX 3, Interix. */
#ifndef _ALL_SOURCE
# undef _ALL_SOURCE
#endif
/* Enable general extensions on macOS. */
#ifndef _DARWIN_C_SOURCE
# undef _DARWIN_C_SOURCE
#endif
/* Enable general extensions on Solaris. */
#ifndef __EXTENSIONS__
# undef __EXTENSIONS__
#endif
/* Enable GNU extensions on systems that have them. */
#ifndef _GNU_SOURCE
# undef _GNU_SOURCE
#endif
/* Enable X/Open compliant socket functions that do not require linking
with -lxnet on HP-UX 11.11. */
#ifndef _HPUX_ALT_XOPEN_SOCKET_API
# undef _HPUX_ALT_XOPEN_SOCKET_API
#endif
/* Identify the host operating system as Minix.
This macro does not affect the system headers' behavior.
A future release of Autoconf may stop defining this macro. */
#ifndef _MINIX
# undef _MINIX
#endif
/* Enable general extensions on NetBSD.
Enable NetBSD compatibility extensions on Minix. */
#ifndef _NETBSD_SOURCE
# undef _NETBSD_SOURCE
#endif
/* Enable OpenBSD compatibility extensions on NetBSD.
Oddly enough, this does nothing on OpenBSD. */
#ifndef _OPENBSD_SOURCE
# undef _OPENBSD_SOURCE
#endif
/* Define to 1 if needed for POSIX-compatible behavior. */
#ifndef _POSIX_SOURCE
# undef _POSIX_SOURCE
#endif
/* Define to 2 if needed for POSIX-compatible behavior. */
#ifndef _POSIX_1_SOURCE
# undef _POSIX_1_SOURCE
#endif
/* Enable POSIX-compatible threading on Solaris. */
#ifndef _POSIX_PTHREAD_SEMANTICS
# undef _POSIX_PTHREAD_SEMANTICS
#endif
/* Enable extensions specified by ISO/IEC TS 18661-5:2014. */
#ifndef __STDC_WANT_IEC_60559_ATTRIBS_EXT__
# undef __STDC_WANT_IEC_60559_ATTRIBS_EXT__
#endif
/* Enable extensions specified by ISO/IEC TS 18661-1:2014. */
#ifndef __STDC_WANT_IEC_60559_BFP_EXT__
# undef __STDC_WANT_IEC_60559_BFP_EXT__
#endif
/* Enable extensions specified by ISO/IEC TS 18661-2:2015. */
#ifndef __STDC_WANT_IEC_60559_DFP_EXT__
# undef __STDC_WANT_IEC_60559_DFP_EXT__
#endif
/* Enable extensions specified by ISO/IEC TS 18661-4:2015. */
#ifndef __STDC_WANT_IEC_60559_FUNCS_EXT__
# undef __STDC_WANT_IEC_60559_FUNCS_EXT__
#endif
/* Enable extensions specified by ISO/IEC TS 18661-3:2015. */
#ifndef __STDC_WANT_IEC_60559_TYPES_EXT__
# undef __STDC_WANT_IEC_60559_TYPES_EXT__
#endif
/* Enable extensions specified by ISO/IEC TR 24731-2:2010. */
#ifndef __STDC_WANT_LIB_EXT2__
# undef __STDC_WANT_LIB_EXT2__
#endif
/* Enable extensions specified by ISO/IEC 24747:2009. */
#ifndef __STDC_WANT_MATH_SPEC_FUNCS__
# undef __STDC_WANT_MATH_SPEC_FUNCS__
#endif
/* Enable extensions on HP NonStop. */
#ifndef _TANDEM_SOURCE
# undef _TANDEM_SOURCE
#endif
/* Enable X/Open extensions. Define to 500 only if necessary
to make mbstate_t available. */
#ifndef _XOPEN_SOURCE
# undef _XOPEN_SOURCE
#endif
/* Version number of package */
#undef VERSION
/* Number of bits in a file offset, on hosts where this is settable. */
#undef _FILE_OFFSET_BITS
/* Define for large files, on AIX-style hosts. */
#undef _LARGE_FILES
/* Define to empty if `const' does not conform to ANSI C. */
#undef const
/* Define to the type of a signed integer type of width exactly 64 bits if
such a type exists and the standard includes do not define it. */
#undef int64_t
/* Define to `unsigned int' if <sys/types.h> does not define. */
#undef size_t

993
Kha/Backends/Kore-hxcpp/khacpp/project/thirdparty/pcre2-10.42-16/src/pcre2.h vendored Normal file
View File

@ -0,0 +1,993 @@
/*************************************************
* Perl-Compatible Regular Expressions *
*************************************************/
/* This is the public header file for the PCRE library, second API, to be
#included by applications that call PCRE2 functions.
Copyright (c) 2016-2021 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
modification, are permitted provided that the following conditions are met:
* Redistributions of source code must retain the above copyright notice,
this list of conditions and the following disclaimer.
* Redistributions in binary form must reproduce the above copyright
notice, this list of conditions and the following disclaimer in the
documentation and/or other materials provided with the distribution.
* Neither the name of the University of Cambridge nor the names of its
contributors may be used to endorse or promote products derived from
this software without specific prior written permission.
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
POSSIBILITY OF SUCH DAMAGE.
-----------------------------------------------------------------------------
*/
#ifndef PCRE2_H_IDEMPOTENT_GUARD
#define PCRE2_H_IDEMPOTENT_GUARD
/* The current PCRE version information. */
#define PCRE2_MAJOR 10
#define PCRE2_MINOR 42
#define PCRE2_PRERELEASE
#define PCRE2_DATE 2022-12-11
/* When an application links to a PCRE DLL in Windows, the symbols that are
imported have to be identified as such. When building PCRE2, the appropriate
export setting is defined in pcre2_internal.h, which includes this file. So we
don't change existing definitions of PCRE2_EXP_DECL. */
#if defined(_WIN32) && !defined(PCRE2_STATIC)
# ifndef PCRE2_EXP_DECL
# define PCRE2_EXP_DECL extern __declspec(dllimport)
# endif
#endif
/* By default, we use the standard "extern" declarations. */
#ifndef PCRE2_EXP_DECL
# ifdef __cplusplus
# define PCRE2_EXP_DECL extern "C"
# else
# define PCRE2_EXP_DECL extern
# endif
#endif
/* When compiling with the MSVC compiler, it is sometimes necessary to include
a "calling convention" before exported function names. (This is secondhand
information; I know nothing about MSVC myself). For example, something like
void __cdecl function(....)
might be needed. In order so make this easy, all the exported functions have
PCRE2_CALL_CONVENTION just before their names. It is rarely needed; if not
set, we ensure here that it has no effect. */
#ifndef PCRE2_CALL_CONVENTION
#define PCRE2_CALL_CONVENTION
#endif
/* Have to include limits.h, stdlib.h, and inttypes.h to ensure that size_t and
uint8_t, UCHAR_MAX, etc are defined. Some systems that do have inttypes.h do
not have stdint.h, which is why we use inttypes.h, which according to the C
standard is a superset of stdint.h. If inttypes.h is not available the build
will break and the relevant values must be provided by some other means. */
#include <limits.h>
#include <stdlib.h>
#include <inttypes.h>
/* Allow for C++ users compiling this directly. */
#ifdef __cplusplus
extern "C" {
#endif
/* The following option bits can be passed to pcre2_compile(), pcre2_match(),
or pcre2_dfa_match(). PCRE2_NO_UTF_CHECK affects only the function to which it
is passed. Put these bits at the most significant end of the options word so
others can be added next to them */
#define PCRE2_ANCHORED 0x80000000u
#define PCRE2_NO_UTF_CHECK 0x40000000u
#define PCRE2_ENDANCHORED 0x20000000u
/* The following option bits can be passed only to pcre2_compile(). However,
they may affect compilation, JIT compilation, and/or interpretive execution.
The following tags indicate which:
C alters what is compiled by pcre2_compile()
J alters what is compiled by pcre2_jit_compile()
M is inspected during pcre2_match() execution
D is inspected during pcre2_dfa_match() execution
*/
#define PCRE2_ALLOW_EMPTY_CLASS 0x00000001u /* C */
#define PCRE2_ALT_BSUX 0x00000002u /* C */
#define PCRE2_AUTO_CALLOUT 0x00000004u /* C */
#define PCRE2_CASELESS 0x00000008u /* C */
#define PCRE2_DOLLAR_ENDONLY 0x00000010u /* J M D */
#define PCRE2_DOTALL 0x00000020u /* C */
#define PCRE2_DUPNAMES 0x00000040u /* C */
#define PCRE2_EXTENDED 0x00000080u /* C */
#define PCRE2_FIRSTLINE 0x00000100u /* J M D */
#define PCRE2_MATCH_UNSET_BACKREF 0x00000200u /* C J M */
#define PCRE2_MULTILINE 0x00000400u /* C */
#define PCRE2_NEVER_UCP 0x00000800u /* C */
#define PCRE2_NEVER_UTF 0x00001000u /* C */
#define PCRE2_NO_AUTO_CAPTURE 0x00002000u /* C */
#define PCRE2_NO_AUTO_POSSESS 0x00004000u /* C */
#define PCRE2_NO_DOTSTAR_ANCHOR 0x00008000u /* C */
#define PCRE2_NO_START_OPTIMIZE 0x00010000u /* J M D */
#define PCRE2_UCP 0x00020000u /* C J M D */
#define PCRE2_UNGREEDY 0x00040000u /* C */
#define PCRE2_UTF 0x00080000u /* C J M D */
#define PCRE2_NEVER_BACKSLASH_C 0x00100000u /* C */
#define PCRE2_ALT_CIRCUMFLEX 0x00200000u /* J M D */
#define PCRE2_ALT_VERBNAMES 0x00400000u /* C */
#define PCRE2_USE_OFFSET_LIMIT 0x00800000u /* J M D */
#define PCRE2_EXTENDED_MORE 0x01000000u /* C */
#define PCRE2_LITERAL 0x02000000u /* C */
#define PCRE2_MATCH_INVALID_UTF 0x04000000u /* J M D */
/* An additional compile options word is available in the compile context. */
#define PCRE2_EXTRA_ALLOW_SURROGATE_ESCAPES 0x00000001u /* C */
#define PCRE2_EXTRA_BAD_ESCAPE_IS_LITERAL 0x00000002u /* C */
#define PCRE2_EXTRA_MATCH_WORD 0x00000004u /* C */
#define PCRE2_EXTRA_MATCH_LINE 0x00000008u /* C */
#define PCRE2_EXTRA_ESCAPED_CR_IS_LF 0x00000010u /* C */
#define PCRE2_EXTRA_ALT_BSUX 0x00000020u /* C */
#define PCRE2_EXTRA_ALLOW_LOOKAROUND_BSK 0x00000040u /* C */
/* These are for pcre2_jit_compile(). */
#define PCRE2_JIT_COMPLETE 0x00000001u /* For full matching */
#define PCRE2_JIT_PARTIAL_SOFT 0x00000002u
#define PCRE2_JIT_PARTIAL_HARD 0x00000004u
#define PCRE2_JIT_INVALID_UTF 0x00000100u
/* These are for pcre2_match(), pcre2_dfa_match(), pcre2_jit_match(), and
pcre2_substitute(). Some are allowed only for one of the functions, and in
these cases it is noted below. Note that PCRE2_ANCHORED, PCRE2_ENDANCHORED and
PCRE2_NO_UTF_CHECK can also be passed to these functions (though
pcre2_jit_match() ignores the latter since it bypasses all sanity checks). */
#define PCRE2_NOTBOL 0x00000001u
#define PCRE2_NOTEOL 0x00000002u
#define PCRE2_NOTEMPTY 0x00000004u /* ) These two must be kept */
#define PCRE2_NOTEMPTY_ATSTART 0x00000008u /* ) adjacent to each other. */
#define PCRE2_PARTIAL_SOFT 0x00000010u
#define PCRE2_PARTIAL_HARD 0x00000020u
#define PCRE2_DFA_RESTART 0x00000040u /* pcre2_dfa_match() only */
#define PCRE2_DFA_SHORTEST 0x00000080u /* pcre2_dfa_match() only */
#define PCRE2_SUBSTITUTE_GLOBAL 0x00000100u /* pcre2_substitute() only */
#define PCRE2_SUBSTITUTE_EXTENDED 0x00000200u /* pcre2_substitute() only */
#define PCRE2_SUBSTITUTE_UNSET_EMPTY 0x00000400u /* pcre2_substitute() only */
#define PCRE2_SUBSTITUTE_UNKNOWN_UNSET 0x00000800u /* pcre2_substitute() only */
#define PCRE2_SUBSTITUTE_OVERFLOW_LENGTH 0x00001000u /* pcre2_substitute() only */
#define PCRE2_NO_JIT 0x00002000u /* Not for pcre2_dfa_match() */
#define PCRE2_COPY_MATCHED_SUBJECT 0x00004000u
#define PCRE2_SUBSTITUTE_LITERAL 0x00008000u /* pcre2_substitute() only */
#define PCRE2_SUBSTITUTE_MATCHED 0x00010000u /* pcre2_substitute() only */
#define PCRE2_SUBSTITUTE_REPLACEMENT_ONLY 0x00020000u /* pcre2_substitute() only */
/* Options for pcre2_pattern_convert(). */
#define PCRE2_CONVERT_UTF 0x00000001u
#define PCRE2_CONVERT_NO_UTF_CHECK 0x00000002u
#define PCRE2_CONVERT_POSIX_BASIC 0x00000004u
#define PCRE2_CONVERT_POSIX_EXTENDED 0x00000008u
#define PCRE2_CONVERT_GLOB 0x00000010u
#define PCRE2_CONVERT_GLOB_NO_WILD_SEPARATOR 0x00000030u
#define PCRE2_CONVERT_GLOB_NO_STARSTAR 0x00000050u
/* Newline and \R settings, for use in compile contexts. The newline values
must be kept in step with values set in config.h and both sets must all be
greater than zero. */
#define PCRE2_NEWLINE_CR 1
#define PCRE2_NEWLINE_LF 2
#define PCRE2_NEWLINE_CRLF 3
#define PCRE2_NEWLINE_ANY 4
#define PCRE2_NEWLINE_ANYCRLF 5
#define PCRE2_NEWLINE_NUL 6
#define PCRE2_BSR_UNICODE 1
#define PCRE2_BSR_ANYCRLF 2
/* Error codes for pcre2_compile(). Some of these are also used by
pcre2_pattern_convert(). */
#define PCRE2_ERROR_END_BACKSLASH 101
#define PCRE2_ERROR_END_BACKSLASH_C 102
#define PCRE2_ERROR_UNKNOWN_ESCAPE 103
#define PCRE2_ERROR_QUANTIFIER_OUT_OF_ORDER 104
#define PCRE2_ERROR_QUANTIFIER_TOO_BIG 105
#define PCRE2_ERROR_MISSING_SQUARE_BRACKET 106
#define PCRE2_ERROR_ESCAPE_INVALID_IN_CLASS 107
#define PCRE2_ERROR_CLASS_RANGE_ORDER 108
#define PCRE2_ERROR_QUANTIFIER_INVALID 109
#define PCRE2_ERROR_INTERNAL_UNEXPECTED_REPEAT 110
#define PCRE2_ERROR_INVALID_AFTER_PARENS_QUERY 111
#define PCRE2_ERROR_POSIX_CLASS_NOT_IN_CLASS 112
#define PCRE2_ERROR_POSIX_NO_SUPPORT_COLLATING 113
#define PCRE2_ERROR_MISSING_CLOSING_PARENTHESIS 114
#define PCRE2_ERROR_BAD_SUBPATTERN_REFERENCE 115
#define PCRE2_ERROR_NULL_PATTERN 116
#define PCRE2_ERROR_BAD_OPTIONS 117
#define PCRE2_ERROR_MISSING_COMMENT_CLOSING 118
#define PCRE2_ERROR_PARENTHESES_NEST_TOO_DEEP 119
#define PCRE2_ERROR_PATTERN_TOO_LARGE 120
#define PCRE2_ERROR_HEAP_FAILED 121
#define PCRE2_ERROR_UNMATCHED_CLOSING_PARENTHESIS 122
#define PCRE2_ERROR_INTERNAL_CODE_OVERFLOW 123
#define PCRE2_ERROR_MISSING_CONDITION_CLOSING 124
#define PCRE2_ERROR_LOOKBEHIND_NOT_FIXED_LENGTH 125
#define PCRE2_ERROR_ZERO_RELATIVE_REFERENCE 126
#define PCRE2_ERROR_TOO_MANY_CONDITION_BRANCHES 127
#define PCRE2_ERROR_CONDITION_ASSERTION_EXPECTED 128
#define PCRE2_ERROR_BAD_RELATIVE_REFERENCE 129
#define PCRE2_ERROR_UNKNOWN_POSIX_CLASS 130
#define PCRE2_ERROR_INTERNAL_STUDY_ERROR 131
#define PCRE2_ERROR_UNICODE_NOT_SUPPORTED 132
#define PCRE2_ERROR_PARENTHESES_STACK_CHECK 133
#define PCRE2_ERROR_CODE_POINT_TOO_BIG 134
#define PCRE2_ERROR_LOOKBEHIND_TOO_COMPLICATED 135
#define PCRE2_ERROR_LOOKBEHIND_INVALID_BACKSLASH_C 136
#define PCRE2_ERROR_UNSUPPORTED_ESCAPE_SEQUENCE 137
#define PCRE2_ERROR_CALLOUT_NUMBER_TOO_BIG 138
#define PCRE2_ERROR_MISSING_CALLOUT_CLOSING 139
#define PCRE2_ERROR_ESCAPE_INVALID_IN_VERB 140
#define PCRE2_ERROR_UNRECOGNIZED_AFTER_QUERY_P 141
#define PCRE2_ERROR_MISSING_NAME_TERMINATOR 142
#define PCRE2_ERROR_DUPLICATE_SUBPATTERN_NAME 143
#define PCRE2_ERROR_INVALID_SUBPATTERN_NAME 144
#define PCRE2_ERROR_UNICODE_PROPERTIES_UNAVAILABLE 145
#define PCRE2_ERROR_MALFORMED_UNICODE_PROPERTY 146
#define PCRE2_ERROR_UNKNOWN_UNICODE_PROPERTY 147
#define PCRE2_ERROR_SUBPATTERN_NAME_TOO_LONG 148
#define PCRE2_ERROR_TOO_MANY_NAMED_SUBPATTERNS 149
#define PCRE2_ERROR_CLASS_INVALID_RANGE 150
#define PCRE2_ERROR_OCTAL_BYTE_TOO_BIG 151
#define PCRE2_ERROR_INTERNAL_OVERRAN_WORKSPACE 152
#define PCRE2_ERROR_INTERNAL_MISSING_SUBPATTERN 153
#define PCRE2_ERROR_DEFINE_TOO_MANY_BRANCHES 154
#define PCRE2_ERROR_BACKSLASH_O_MISSING_BRACE 155
#define PCRE2_ERROR_INTERNAL_UNKNOWN_NEWLINE 156
#define PCRE2_ERROR_BACKSLASH_G_SYNTAX 157
#define PCRE2_ERROR_PARENS_QUERY_R_MISSING_CLOSING 158
/* Error 159 is obsolete and should now never occur */
#define PCRE2_ERROR_VERB_ARGUMENT_NOT_ALLOWED 159
#define PCRE2_ERROR_VERB_UNKNOWN 160
#define PCRE2_ERROR_SUBPATTERN_NUMBER_TOO_BIG 161
#define PCRE2_ERROR_SUBPATTERN_NAME_EXPECTED 162
#define PCRE2_ERROR_INTERNAL_PARSED_OVERFLOW 163
#define PCRE2_ERROR_INVALID_OCTAL 164
#define PCRE2_ERROR_SUBPATTERN_NAMES_MISMATCH 165
#define PCRE2_ERROR_MARK_MISSING_ARGUMENT 166
#define PCRE2_ERROR_INVALID_HEXADECIMAL 167
#define PCRE2_ERROR_BACKSLASH_C_SYNTAX 168
#define PCRE2_ERROR_BACKSLASH_K_SYNTAX 169
#define PCRE2_ERROR_INTERNAL_BAD_CODE_LOOKBEHINDS 170
#define PCRE2_ERROR_BACKSLASH_N_IN_CLASS 171
#define PCRE2_ERROR_CALLOUT_STRING_TOO_LONG 172
#define PCRE2_ERROR_UNICODE_DISALLOWED_CODE_POINT 173
#define PCRE2_ERROR_UTF_IS_DISABLED 174
#define PCRE2_ERROR_UCP_IS_DISABLED 175
#define PCRE2_ERROR_VERB_NAME_TOO_LONG 176
#define PCRE2_ERROR_BACKSLASH_U_CODE_POINT_TOO_BIG 177
#define PCRE2_ERROR_MISSING_OCTAL_OR_HEX_DIGITS 178
#define PCRE2_ERROR_VERSION_CONDITION_SYNTAX 179
#define PCRE2_ERROR_INTERNAL_BAD_CODE_AUTO_POSSESS 180
#define PCRE2_ERROR_CALLOUT_NO_STRING_DELIMITER 181
#define PCRE2_ERROR_CALLOUT_BAD_STRING_DELIMITER 182
#define PCRE2_ERROR_BACKSLASH_C_CALLER_DISABLED 183
#define PCRE2_ERROR_QUERY_BARJX_NEST_TOO_DEEP 184
#define PCRE2_ERROR_BACKSLASH_C_LIBRARY_DISABLED 185
#define PCRE2_ERROR_PATTERN_TOO_COMPLICATED 186
#define PCRE2_ERROR_LOOKBEHIND_TOO_LONG 187
#define PCRE2_ERROR_PATTERN_STRING_TOO_LONG 188
#define PCRE2_ERROR_INTERNAL_BAD_CODE 189
#define PCRE2_ERROR_INTERNAL_BAD_CODE_IN_SKIP 190
#define PCRE2_ERROR_NO_SURROGATES_IN_UTF16 191
#define PCRE2_ERROR_BAD_LITERAL_OPTIONS 192
#define PCRE2_ERROR_SUPPORTED_ONLY_IN_UNICODE 193
#define PCRE2_ERROR_INVALID_HYPHEN_IN_OPTIONS 194
#define PCRE2_ERROR_ALPHA_ASSERTION_UNKNOWN 195
#define PCRE2_ERROR_SCRIPT_RUN_NOT_AVAILABLE 196
#define PCRE2_ERROR_TOO_MANY_CAPTURES 197
#define PCRE2_ERROR_CONDITION_ATOMIC_ASSERTION_EXPECTED 198
#define PCRE2_ERROR_BACKSLASH_K_IN_LOOKAROUND 199
/* "Expected" matching error codes: no match and partial match. */
#define PCRE2_ERROR_NOMATCH (-1)
#define PCRE2_ERROR_PARTIAL (-2)
/* Error codes for UTF-8 validity checks */
#define PCRE2_ERROR_UTF8_ERR1 (-3)
#define PCRE2_ERROR_UTF8_ERR2 (-4)
#define PCRE2_ERROR_UTF8_ERR3 (-5)
#define PCRE2_ERROR_UTF8_ERR4 (-6)
#define PCRE2_ERROR_UTF8_ERR5 (-7)
#define PCRE2_ERROR_UTF8_ERR6 (-8)
#define PCRE2_ERROR_UTF8_ERR7 (-9)
#define PCRE2_ERROR_UTF8_ERR8 (-10)
#define PCRE2_ERROR_UTF8_ERR9 (-11)
#define PCRE2_ERROR_UTF8_ERR10 (-12)
#define PCRE2_ERROR_UTF8_ERR11 (-13)
#define PCRE2_ERROR_UTF8_ERR12 (-14)
#define PCRE2_ERROR_UTF8_ERR13 (-15)
#define PCRE2_ERROR_UTF8_ERR14 (-16)
#define PCRE2_ERROR_UTF8_ERR15 (-17)
#define PCRE2_ERROR_UTF8_ERR16 (-18)
#define PCRE2_ERROR_UTF8_ERR17 (-19)
#define PCRE2_ERROR_UTF8_ERR18 (-20)
#define PCRE2_ERROR_UTF8_ERR19 (-21)
#define PCRE2_ERROR_UTF8_ERR20 (-22)
#define PCRE2_ERROR_UTF8_ERR21 (-23)
/* Error codes for UTF-16 validity checks */
#define PCRE2_ERROR_UTF16_ERR1 (-24)
#define PCRE2_ERROR_UTF16_ERR2 (-25)
#define PCRE2_ERROR_UTF16_ERR3 (-26)
/* Error codes for UTF-32 validity checks */
#define PCRE2_ERROR_UTF32_ERR1 (-27)
#define PCRE2_ERROR_UTF32_ERR2 (-28)
/* Miscellaneous error codes for pcre2[_dfa]_match(), substring extraction
functions, context functions, and serializing functions. They are in numerical
order. Originally they were in alphabetical order too, but now that PCRE2 is
released, the numbers must not be changed. */
#define PCRE2_ERROR_BADDATA (-29)
#define PCRE2_ERROR_MIXEDTABLES (-30) /* Name was changed */
#define PCRE2_ERROR_BADMAGIC (-31)
#define PCRE2_ERROR_BADMODE (-32)
#define PCRE2_ERROR_BADOFFSET (-33)
#define PCRE2_ERROR_BADOPTION (-34)
#define PCRE2_ERROR_BADREPLACEMENT (-35)
#define PCRE2_ERROR_BADUTFOFFSET (-36)
#define PCRE2_ERROR_CALLOUT (-37) /* Never used by PCRE2 itself */
#define PCRE2_ERROR_DFA_BADRESTART (-38)
#define PCRE2_ERROR_DFA_RECURSE (-39)
#define PCRE2_ERROR_DFA_UCOND (-40)
#define PCRE2_ERROR_DFA_UFUNC (-41)
#define PCRE2_ERROR_DFA_UITEM (-42)
#define PCRE2_ERROR_DFA_WSSIZE (-43)
#define PCRE2_ERROR_INTERNAL (-44)
#define PCRE2_ERROR_JIT_BADOPTION (-45)
#define PCRE2_ERROR_JIT_STACKLIMIT (-46)
#define PCRE2_ERROR_MATCHLIMIT (-47)
#define PCRE2_ERROR_NOMEMORY (-48)
#define PCRE2_ERROR_NOSUBSTRING (-49)
#define PCRE2_ERROR_NOUNIQUESUBSTRING (-50)
#define PCRE2_ERROR_NULL (-51)
#define PCRE2_ERROR_RECURSELOOP (-52)
#define PCRE2_ERROR_DEPTHLIMIT (-53)
#define PCRE2_ERROR_RECURSIONLIMIT (-53) /* Obsolete synonym */
#define PCRE2_ERROR_UNAVAILABLE (-54)
#define PCRE2_ERROR_UNSET (-55)
#define PCRE2_ERROR_BADOFFSETLIMIT (-56)
#define PCRE2_ERROR_BADREPESCAPE (-57)
#define PCRE2_ERROR_REPMISSINGBRACE (-58)
#define PCRE2_ERROR_BADSUBSTITUTION (-59)
#define PCRE2_ERROR_BADSUBSPATTERN (-60)
#define PCRE2_ERROR_TOOMANYREPLACE (-61)
#define PCRE2_ERROR_BADSERIALIZEDDATA (-62)
#define PCRE2_ERROR_HEAPLIMIT (-63)
#define PCRE2_ERROR_CONVERT_SYNTAX (-64)
#define PCRE2_ERROR_INTERNAL_DUPMATCH (-65)
#define PCRE2_ERROR_DFA_UINVALID_UTF (-66)
/* Request types for pcre2_pattern_info() */
#define PCRE2_INFO_ALLOPTIONS 0
#define PCRE2_INFO_ARGOPTIONS 1
#define PCRE2_INFO_BACKREFMAX 2
#define PCRE2_INFO_BSR 3
#define PCRE2_INFO_CAPTURECOUNT 4
#define PCRE2_INFO_FIRSTCODEUNIT 5
#define PCRE2_INFO_FIRSTCODETYPE 6
#define PCRE2_INFO_FIRSTBITMAP 7
#define PCRE2_INFO_HASCRORLF 8
#define PCRE2_INFO_JCHANGED 9
#define PCRE2_INFO_JITSIZE 10
#define PCRE2_INFO_LASTCODEUNIT 11
#define PCRE2_INFO_LASTCODETYPE 12
#define PCRE2_INFO_MATCHEMPTY 13
#define PCRE2_INFO_MATCHLIMIT 14
#define PCRE2_INFO_MAXLOOKBEHIND 15
#define PCRE2_INFO_MINLENGTH 16
#define PCRE2_INFO_NAMECOUNT 17
#define PCRE2_INFO_NAMEENTRYSIZE 18
#define PCRE2_INFO_NAMETABLE 19
#define PCRE2_INFO_NEWLINE 20
#define PCRE2_INFO_DEPTHLIMIT 21
#define PCRE2_INFO_RECURSIONLIMIT 21 /* Obsolete synonym */
#define PCRE2_INFO_SIZE 22
#define PCRE2_INFO_HASBACKSLASHC 23
#define PCRE2_INFO_FRAMESIZE 24
#define PCRE2_INFO_HEAPLIMIT 25
#define PCRE2_INFO_EXTRAOPTIONS 26
/* Request types for pcre2_config(). */
#define PCRE2_CONFIG_BSR 0
#define PCRE2_CONFIG_JIT 1
#define PCRE2_CONFIG_JITTARGET 2
#define PCRE2_CONFIG_LINKSIZE 3
#define PCRE2_CONFIG_MATCHLIMIT 4
#define PCRE2_CONFIG_NEWLINE 5
#define PCRE2_CONFIG_PARENSLIMIT 6
#define PCRE2_CONFIG_DEPTHLIMIT 7
#define PCRE2_CONFIG_RECURSIONLIMIT 7 /* Obsolete synonym */
#define PCRE2_CONFIG_STACKRECURSE 8 /* Obsolete */
#define PCRE2_CONFIG_UNICODE 9
#define PCRE2_CONFIG_UNICODE_VERSION 10
#define PCRE2_CONFIG_VERSION 11
#define PCRE2_CONFIG_HEAPLIMIT 12
#define PCRE2_CONFIG_NEVER_BACKSLASH_C 13
#define PCRE2_CONFIG_COMPILED_WIDTHS 14
#define PCRE2_CONFIG_TABLES_LENGTH 15
/* Types for code units in patterns and subject strings. */
typedef uint8_t PCRE2_UCHAR8;
typedef uint16_t PCRE2_UCHAR16;
typedef uint32_t PCRE2_UCHAR32;
typedef const PCRE2_UCHAR8 *PCRE2_SPTR8;
typedef const PCRE2_UCHAR16 *PCRE2_SPTR16;
typedef const PCRE2_UCHAR32 *PCRE2_SPTR32;
/* The PCRE2_SIZE type is used for all string lengths and offsets in PCRE2,
including pattern offsets for errors and subject offsets after a match. We
define special values to indicate zero-terminated strings and unset offsets in
the offset vector (ovector). */
#define PCRE2_SIZE size_t
#define PCRE2_SIZE_MAX SIZE_MAX
#define PCRE2_ZERO_TERMINATED (~(PCRE2_SIZE)0)
#define PCRE2_UNSET (~(PCRE2_SIZE)0)
/* Generic types for opaque structures and JIT callback functions. These
declarations are defined in a macro that is expanded for each width later. */
#define PCRE2_TYPES_LIST \
struct pcre2_real_general_context; \
typedef struct pcre2_real_general_context pcre2_general_context; \
\
struct pcre2_real_compile_context; \
typedef struct pcre2_real_compile_context pcre2_compile_context; \
\
struct pcre2_real_match_context; \
typedef struct pcre2_real_match_context pcre2_match_context; \
\
struct pcre2_real_convert_context; \
typedef struct pcre2_real_convert_context pcre2_convert_context; \
\
struct pcre2_real_code; \
typedef struct pcre2_real_code pcre2_code; \
\
struct pcre2_real_match_data; \
typedef struct pcre2_real_match_data pcre2_match_data; \
\
struct pcre2_real_jit_stack; \
typedef struct pcre2_real_jit_stack pcre2_jit_stack; \
\
typedef pcre2_jit_stack *(*pcre2_jit_callback)(void *);
/* The structures for passing out data via callout functions. We use structures
so that new fields can be added on the end in future versions, without changing
the API of the function, thereby allowing old clients to work without
modification. Define the generic versions in a macro; the width-specific
versions are generated from this macro below. */
/* Flags for the callout_flags field. These are cleared after a callout. */
#define PCRE2_CALLOUT_STARTMATCH 0x00000001u /* Set for each bumpalong */
#define PCRE2_CALLOUT_BACKTRACK 0x00000002u /* Set after a backtrack */
#define PCRE2_STRUCTURE_LIST \
typedef struct pcre2_callout_block { \
uint32_t version; /* Identifies version of block */ \
/* ------------------------ Version 0 ------------------------------- */ \
uint32_t callout_number; /* Number compiled into pattern */ \
uint32_t capture_top; /* Max current capture */ \
uint32_t capture_last; /* Most recently closed capture */ \
PCRE2_SIZE *offset_vector; /* The offset vector */ \
PCRE2_SPTR mark; /* Pointer to current mark or NULL */ \
PCRE2_SPTR subject; /* The subject being matched */ \
PCRE2_SIZE subject_length; /* The length of the subject */ \
PCRE2_SIZE start_match; /* Offset to start of this match attempt */ \
PCRE2_SIZE current_position; /* Where we currently are in the subject */ \
PCRE2_SIZE pattern_position; /* Offset to next item in the pattern */ \
PCRE2_SIZE next_item_length; /* Length of next item in the pattern */ \
/* ------------------- Added for Version 1 -------------------------- */ \
PCRE2_SIZE callout_string_offset; /* Offset to string within pattern */ \
PCRE2_SIZE callout_string_length; /* Length of string compiled into pattern */ \
PCRE2_SPTR callout_string; /* String compiled into pattern */ \
/* ------------------- Added for Version 2 -------------------------- */ \
uint32_t callout_flags; /* See above for list */ \
/* ------------------------------------------------------------------ */ \
} pcre2_callout_block; \
\
typedef struct pcre2_callout_enumerate_block { \
uint32_t version; /* Identifies version of block */ \
/* ------------------------ Version 0 ------------------------------- */ \
PCRE2_SIZE pattern_position; /* Offset to next item in the pattern */ \
PCRE2_SIZE next_item_length; /* Length of next item in the pattern */ \
uint32_t callout_number; /* Number compiled into pattern */ \
PCRE2_SIZE callout_string_offset; /* Offset to string within pattern */ \
PCRE2_SIZE callout_string_length; /* Length of string compiled into pattern */ \
PCRE2_SPTR callout_string; /* String compiled into pattern */ \
/* ------------------------------------------------------------------ */ \
} pcre2_callout_enumerate_block; \
\
typedef struct pcre2_substitute_callout_block { \
uint32_t version; /* Identifies version of block */ \
/* ------------------------ Version 0 ------------------------------- */ \
PCRE2_SPTR input; /* Pointer to input subject string */ \
PCRE2_SPTR output; /* Pointer to output buffer */ \
PCRE2_SIZE output_offsets[2]; /* Changed portion of the output */ \
PCRE2_SIZE *ovector; /* Pointer to current ovector */ \
uint32_t oveccount; /* Count of pairs set in ovector */ \
uint32_t subscount; /* Substitution number */ \
/* ------------------------------------------------------------------ */ \
} pcre2_substitute_callout_block;
/* List the generic forms of all other functions in macros, which will be
expanded for each width below. Start with functions that give general
information. */
#define PCRE2_GENERAL_INFO_FUNCTIONS \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION pcre2_config(uint32_t, void *);
/* Functions for manipulating contexts. */
#define PCRE2_GENERAL_CONTEXT_FUNCTIONS \
PCRE2_EXP_DECL pcre2_general_context *PCRE2_CALL_CONVENTION \
pcre2_general_context_copy(pcre2_general_context *); \
PCRE2_EXP_DECL pcre2_general_context *PCRE2_CALL_CONVENTION \
pcre2_general_context_create(void *(*)(PCRE2_SIZE, void *), \
void (*)(void *, void *), void *); \
PCRE2_EXP_DECL void PCRE2_CALL_CONVENTION \
pcre2_general_context_free(pcre2_general_context *);
#define PCRE2_COMPILE_CONTEXT_FUNCTIONS \
PCRE2_EXP_DECL pcre2_compile_context *PCRE2_CALL_CONVENTION \
pcre2_compile_context_copy(pcre2_compile_context *); \
PCRE2_EXP_DECL pcre2_compile_context *PCRE2_CALL_CONVENTION \
pcre2_compile_context_create(pcre2_general_context *);\
PCRE2_EXP_DECL void PCRE2_CALL_CONVENTION \
pcre2_compile_context_free(pcre2_compile_context *); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_set_bsr(pcre2_compile_context *, uint32_t); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_set_character_tables(pcre2_compile_context *, const uint8_t *); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_set_compile_extra_options(pcre2_compile_context *, uint32_t); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_set_max_pattern_length(pcre2_compile_context *, PCRE2_SIZE); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_set_newline(pcre2_compile_context *, uint32_t); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_set_parens_nest_limit(pcre2_compile_context *, uint32_t); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_set_compile_recursion_guard(pcre2_compile_context *, \
int (*)(uint32_t, void *), void *);
#define PCRE2_MATCH_CONTEXT_FUNCTIONS \
PCRE2_EXP_DECL pcre2_match_context *PCRE2_CALL_CONVENTION \
pcre2_match_context_copy(pcre2_match_context *); \
PCRE2_EXP_DECL pcre2_match_context *PCRE2_CALL_CONVENTION \
pcre2_match_context_create(pcre2_general_context *); \
PCRE2_EXP_DECL void PCRE2_CALL_CONVENTION \
pcre2_match_context_free(pcre2_match_context *); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_set_callout(pcre2_match_context *, \
int (*)(pcre2_callout_block *, void *), void *); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_set_substitute_callout(pcre2_match_context *, \
int (*)(pcre2_substitute_callout_block *, void *), void *); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_set_depth_limit(pcre2_match_context *, uint32_t); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_set_heap_limit(pcre2_match_context *, uint32_t); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_set_match_limit(pcre2_match_context *, uint32_t); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_set_offset_limit(pcre2_match_context *, PCRE2_SIZE); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_set_recursion_limit(pcre2_match_context *, uint32_t); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_set_recursion_memory_management(pcre2_match_context *, \
void *(*)(PCRE2_SIZE, void *), void (*)(void *, void *), void *);
#define PCRE2_CONVERT_CONTEXT_FUNCTIONS \
PCRE2_EXP_DECL pcre2_convert_context *PCRE2_CALL_CONVENTION \
pcre2_convert_context_copy(pcre2_convert_context *); \
PCRE2_EXP_DECL pcre2_convert_context *PCRE2_CALL_CONVENTION \
pcre2_convert_context_create(pcre2_general_context *); \
PCRE2_EXP_DECL void PCRE2_CALL_CONVENTION \
pcre2_convert_context_free(pcre2_convert_context *); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_set_glob_escape(pcre2_convert_context *, uint32_t); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_set_glob_separator(pcre2_convert_context *, uint32_t);
/* Functions concerned with compiling a pattern to PCRE internal code. */
#define PCRE2_COMPILE_FUNCTIONS \
PCRE2_EXP_DECL pcre2_code *PCRE2_CALL_CONVENTION \
pcre2_compile(PCRE2_SPTR, PCRE2_SIZE, uint32_t, int *, PCRE2_SIZE *, \
pcre2_compile_context *); \
PCRE2_EXP_DECL void PCRE2_CALL_CONVENTION \
pcre2_code_free(pcre2_code *); \
PCRE2_EXP_DECL pcre2_code *PCRE2_CALL_CONVENTION \
pcre2_code_copy(const pcre2_code *); \
PCRE2_EXP_DECL pcre2_code *PCRE2_CALL_CONVENTION \
pcre2_code_copy_with_tables(const pcre2_code *);
/* Functions that give information about a compiled pattern. */
#define PCRE2_PATTERN_INFO_FUNCTIONS \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_pattern_info(const pcre2_code *, uint32_t, void *); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_callout_enumerate(const pcre2_code *, \
int (*)(pcre2_callout_enumerate_block *, void *), void *);
/* Functions for running a match and inspecting the result. */
#define PCRE2_MATCH_FUNCTIONS \
PCRE2_EXP_DECL pcre2_match_data *PCRE2_CALL_CONVENTION \
pcre2_match_data_create(uint32_t, pcre2_general_context *); \
PCRE2_EXP_DECL pcre2_match_data *PCRE2_CALL_CONVENTION \
pcre2_match_data_create_from_pattern(const pcre2_code *, \
pcre2_general_context *); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_dfa_match(const pcre2_code *, PCRE2_SPTR, PCRE2_SIZE, PCRE2_SIZE, \
uint32_t, pcre2_match_data *, pcre2_match_context *, int *, PCRE2_SIZE); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_match(const pcre2_code *, PCRE2_SPTR, PCRE2_SIZE, PCRE2_SIZE, \
uint32_t, pcre2_match_data *, pcre2_match_context *); \
PCRE2_EXP_DECL void PCRE2_CALL_CONVENTION \
pcre2_match_data_free(pcre2_match_data *); \
PCRE2_EXP_DECL PCRE2_SPTR PCRE2_CALL_CONVENTION \
pcre2_get_mark(pcre2_match_data *); \
PCRE2_EXP_DECL PCRE2_SIZE PCRE2_CALL_CONVENTION \
pcre2_get_match_data_size(pcre2_match_data *); \
PCRE2_EXP_DECL uint32_t PCRE2_CALL_CONVENTION \
pcre2_get_ovector_count(pcre2_match_data *); \
PCRE2_EXP_DECL PCRE2_SIZE *PCRE2_CALL_CONVENTION \
pcre2_get_ovector_pointer(pcre2_match_data *); \
PCRE2_EXP_DECL PCRE2_SIZE PCRE2_CALL_CONVENTION \
pcre2_get_startchar(pcre2_match_data *);
/* Convenience functions for handling matched substrings. */
#define PCRE2_SUBSTRING_FUNCTIONS \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_substring_copy_byname(pcre2_match_data *, PCRE2_SPTR, PCRE2_UCHAR *, \
PCRE2_SIZE *); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_substring_copy_bynumber(pcre2_match_data *, uint32_t, PCRE2_UCHAR *, \
PCRE2_SIZE *); \
PCRE2_EXP_DECL void PCRE2_CALL_CONVENTION \
pcre2_substring_free(PCRE2_UCHAR *); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_substring_get_byname(pcre2_match_data *, PCRE2_SPTR, PCRE2_UCHAR **, \
PCRE2_SIZE *); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_substring_get_bynumber(pcre2_match_data *, uint32_t, PCRE2_UCHAR **, \
PCRE2_SIZE *); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_substring_length_byname(pcre2_match_data *, PCRE2_SPTR, PCRE2_SIZE *); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_substring_length_bynumber(pcre2_match_data *, uint32_t, PCRE2_SIZE *); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_substring_nametable_scan(const pcre2_code *, PCRE2_SPTR, PCRE2_SPTR *, \
PCRE2_SPTR *); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_substring_number_from_name(const pcre2_code *, PCRE2_SPTR); \
PCRE2_EXP_DECL void PCRE2_CALL_CONVENTION \
pcre2_substring_list_free(PCRE2_SPTR *); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_substring_list_get(pcre2_match_data *, PCRE2_UCHAR ***, PCRE2_SIZE **);
/* Functions for serializing / deserializing compiled patterns. */
#define PCRE2_SERIALIZE_FUNCTIONS \
PCRE2_EXP_DECL int32_t PCRE2_CALL_CONVENTION \
pcre2_serialize_encode(const pcre2_code **, int32_t, uint8_t **, \
PCRE2_SIZE *, pcre2_general_context *); \
PCRE2_EXP_DECL int32_t PCRE2_CALL_CONVENTION \
pcre2_serialize_decode(pcre2_code **, int32_t, const uint8_t *, \
pcre2_general_context *); \
PCRE2_EXP_DECL int32_t PCRE2_CALL_CONVENTION \
pcre2_serialize_get_number_of_codes(const uint8_t *); \
PCRE2_EXP_DECL void PCRE2_CALL_CONVENTION \
pcre2_serialize_free(uint8_t *);
/* Convenience function for match + substitute. */
#define PCRE2_SUBSTITUTE_FUNCTION \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_substitute(const pcre2_code *, PCRE2_SPTR, PCRE2_SIZE, PCRE2_SIZE, \
uint32_t, pcre2_match_data *, pcre2_match_context *, PCRE2_SPTR, \
PCRE2_SIZE, PCRE2_UCHAR *, PCRE2_SIZE *);
/* Functions for converting pattern source strings. */
#define PCRE2_CONVERT_FUNCTIONS \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_pattern_convert(PCRE2_SPTR, PCRE2_SIZE, uint32_t, PCRE2_UCHAR **, \
PCRE2_SIZE *, pcre2_convert_context *); \
PCRE2_EXP_DECL void PCRE2_CALL_CONVENTION \
pcre2_converted_pattern_free(PCRE2_UCHAR *);
/* Functions for JIT processing */
#define PCRE2_JIT_FUNCTIONS \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_jit_compile(pcre2_code *, uint32_t); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_jit_match(const pcre2_code *, PCRE2_SPTR, PCRE2_SIZE, PCRE2_SIZE, \
uint32_t, pcre2_match_data *, pcre2_match_context *); \
PCRE2_EXP_DECL void PCRE2_CALL_CONVENTION \
pcre2_jit_free_unused_memory(pcre2_general_context *); \
PCRE2_EXP_DECL pcre2_jit_stack *PCRE2_CALL_CONVENTION \
pcre2_jit_stack_create(PCRE2_SIZE, PCRE2_SIZE, pcre2_general_context *); \
PCRE2_EXP_DECL void PCRE2_CALL_CONVENTION \
pcre2_jit_stack_assign(pcre2_match_context *, pcre2_jit_callback, void *); \
PCRE2_EXP_DECL void PCRE2_CALL_CONVENTION \
pcre2_jit_stack_free(pcre2_jit_stack *);
/* Other miscellaneous functions. */
#define PCRE2_OTHER_FUNCTIONS \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_get_error_message(int, PCRE2_UCHAR *, PCRE2_SIZE); \
PCRE2_EXP_DECL const uint8_t *PCRE2_CALL_CONVENTION \
pcre2_maketables(pcre2_general_context *); \
PCRE2_EXP_DECL void PCRE2_CALL_CONVENTION \
pcre2_maketables_free(pcre2_general_context *, const uint8_t *);
/* Define macros that generate width-specific names from generic versions. The
three-level macro scheme is necessary to get the macros expanded when we want
them to be. First we get the width from PCRE2_LOCAL_WIDTH, which is used for
generating three versions of everything below. After that, PCRE2_SUFFIX will be
re-defined to use PCRE2_CODE_UNIT_WIDTH, for use when macros such as
pcre2_compile are called by application code. */
#define PCRE2_JOIN(a,b) a ## b
#define PCRE2_GLUE(a,b) PCRE2_JOIN(a,b)
#define PCRE2_SUFFIX(a) PCRE2_GLUE(a,PCRE2_LOCAL_WIDTH)
/* Data types */
#define PCRE2_UCHAR PCRE2_SUFFIX(PCRE2_UCHAR)
#define PCRE2_SPTR PCRE2_SUFFIX(PCRE2_SPTR)
#define pcre2_code PCRE2_SUFFIX(pcre2_code_)
#define pcre2_jit_callback PCRE2_SUFFIX(pcre2_jit_callback_)
#define pcre2_jit_stack PCRE2_SUFFIX(pcre2_jit_stack_)
#define pcre2_real_code PCRE2_SUFFIX(pcre2_real_code_)
#define pcre2_real_general_context PCRE2_SUFFIX(pcre2_real_general_context_)
#define pcre2_real_compile_context PCRE2_SUFFIX(pcre2_real_compile_context_)
#define pcre2_real_convert_context PCRE2_SUFFIX(pcre2_real_convert_context_)
#define pcre2_real_match_context PCRE2_SUFFIX(pcre2_real_match_context_)
#define pcre2_real_jit_stack PCRE2_SUFFIX(pcre2_real_jit_stack_)
#define pcre2_real_match_data PCRE2_SUFFIX(pcre2_real_match_data_)
/* Data blocks */
#define pcre2_callout_block PCRE2_SUFFIX(pcre2_callout_block_)
#define pcre2_callout_enumerate_block PCRE2_SUFFIX(pcre2_callout_enumerate_block_)
#define pcre2_substitute_callout_block PCRE2_SUFFIX(pcre2_substitute_callout_block_)
#define pcre2_general_context PCRE2_SUFFIX(pcre2_general_context_)
#define pcre2_compile_context PCRE2_SUFFIX(pcre2_compile_context_)
#define pcre2_convert_context PCRE2_SUFFIX(pcre2_convert_context_)
#define pcre2_match_context PCRE2_SUFFIX(pcre2_match_context_)
#define pcre2_match_data PCRE2_SUFFIX(pcre2_match_data_)
/* Functions: the complete list in alphabetical order */
#define pcre2_callout_enumerate PCRE2_SUFFIX(pcre2_callout_enumerate_)
#define pcre2_code_copy PCRE2_SUFFIX(pcre2_code_copy_)
#define pcre2_code_copy_with_tables PCRE2_SUFFIX(pcre2_code_copy_with_tables_)
#define pcre2_code_free PCRE2_SUFFIX(pcre2_code_free_)
#define pcre2_compile PCRE2_SUFFIX(pcre2_compile_)
#define pcre2_compile_context_copy PCRE2_SUFFIX(pcre2_compile_context_copy_)
#define pcre2_compile_context_create PCRE2_SUFFIX(pcre2_compile_context_create_)
#define pcre2_compile_context_free PCRE2_SUFFIX(pcre2_compile_context_free_)
#define pcre2_config PCRE2_SUFFIX(pcre2_config_)
#define pcre2_convert_context_copy PCRE2_SUFFIX(pcre2_convert_context_copy_)
#define pcre2_convert_context_create PCRE2_SUFFIX(pcre2_convert_context_create_)
#define pcre2_convert_context_free PCRE2_SUFFIX(pcre2_convert_context_free_)
#define pcre2_converted_pattern_free PCRE2_SUFFIX(pcre2_converted_pattern_free_)
#define pcre2_dfa_match PCRE2_SUFFIX(pcre2_dfa_match_)
#define pcre2_general_context_copy PCRE2_SUFFIX(pcre2_general_context_copy_)
#define pcre2_general_context_create PCRE2_SUFFIX(pcre2_general_context_create_)
#define pcre2_general_context_free PCRE2_SUFFIX(pcre2_general_context_free_)
#define pcre2_get_error_message PCRE2_SUFFIX(pcre2_get_error_message_)
#define pcre2_get_mark PCRE2_SUFFIX(pcre2_get_mark_)
#define pcre2_get_match_data_size PCRE2_SUFFIX(pcre2_get_match_data_size_)
#define pcre2_get_ovector_pointer PCRE2_SUFFIX(pcre2_get_ovector_pointer_)
#define pcre2_get_ovector_count PCRE2_SUFFIX(pcre2_get_ovector_count_)
#define pcre2_get_startchar PCRE2_SUFFIX(pcre2_get_startchar_)
#define pcre2_jit_compile PCRE2_SUFFIX(pcre2_jit_compile_)
#define pcre2_jit_match PCRE2_SUFFIX(pcre2_jit_match_)
#define pcre2_jit_free_unused_memory PCRE2_SUFFIX(pcre2_jit_free_unused_memory_)
#define pcre2_jit_stack_assign PCRE2_SUFFIX(pcre2_jit_stack_assign_)
#define pcre2_jit_stack_create PCRE2_SUFFIX(pcre2_jit_stack_create_)
#define pcre2_jit_stack_free PCRE2_SUFFIX(pcre2_jit_stack_free_)
#define pcre2_maketables PCRE2_SUFFIX(pcre2_maketables_)
#define pcre2_maketables_free PCRE2_SUFFIX(pcre2_maketables_free_)
#define pcre2_match PCRE2_SUFFIX(pcre2_match_)
#define pcre2_match_context_copy PCRE2_SUFFIX(pcre2_match_context_copy_)
#define pcre2_match_context_create PCRE2_SUFFIX(pcre2_match_context_create_)
#define pcre2_match_context_free PCRE2_SUFFIX(pcre2_match_context_free_)
#define pcre2_match_data_create PCRE2_SUFFIX(pcre2_match_data_create_)
#define pcre2_match_data_create_from_pattern PCRE2_SUFFIX(pcre2_match_data_create_from_pattern_)
#define pcre2_match_data_free PCRE2_SUFFIX(pcre2_match_data_free_)
#define pcre2_pattern_convert PCRE2_SUFFIX(pcre2_pattern_convert_)
#define pcre2_pattern_info PCRE2_SUFFIX(pcre2_pattern_info_)
#define pcre2_serialize_decode PCRE2_SUFFIX(pcre2_serialize_decode_)
#define pcre2_serialize_encode PCRE2_SUFFIX(pcre2_serialize_encode_)
#define pcre2_serialize_free PCRE2_SUFFIX(pcre2_serialize_free_)
#define pcre2_serialize_get_number_of_codes PCRE2_SUFFIX(pcre2_serialize_get_number_of_codes_)
#define pcre2_set_bsr PCRE2_SUFFIX(pcre2_set_bsr_)
#define pcre2_set_callout PCRE2_SUFFIX(pcre2_set_callout_)
#define pcre2_set_character_tables PCRE2_SUFFIX(pcre2_set_character_tables_)
#define pcre2_set_compile_extra_options PCRE2_SUFFIX(pcre2_set_compile_extra_options_)
#define pcre2_set_compile_recursion_guard PCRE2_SUFFIX(pcre2_set_compile_recursion_guard_)
#define pcre2_set_depth_limit PCRE2_SUFFIX(pcre2_set_depth_limit_)
#define pcre2_set_glob_escape PCRE2_SUFFIX(pcre2_set_glob_escape_)
#define pcre2_set_glob_separator PCRE2_SUFFIX(pcre2_set_glob_separator_)
#define pcre2_set_heap_limit PCRE2_SUFFIX(pcre2_set_heap_limit_)
#define pcre2_set_match_limit PCRE2_SUFFIX(pcre2_set_match_limit_)
#define pcre2_set_max_pattern_length PCRE2_SUFFIX(pcre2_set_max_pattern_length_)
#define pcre2_set_newline PCRE2_SUFFIX(pcre2_set_newline_)
#define pcre2_set_parens_nest_limit PCRE2_SUFFIX(pcre2_set_parens_nest_limit_)
#define pcre2_set_offset_limit PCRE2_SUFFIX(pcre2_set_offset_limit_)
#define pcre2_set_substitute_callout PCRE2_SUFFIX(pcre2_set_substitute_callout_)
#define pcre2_substitute PCRE2_SUFFIX(pcre2_substitute_)
#define pcre2_substring_copy_byname PCRE2_SUFFIX(pcre2_substring_copy_byname_)
#define pcre2_substring_copy_bynumber PCRE2_SUFFIX(pcre2_substring_copy_bynumber_)
#define pcre2_substring_free PCRE2_SUFFIX(pcre2_substring_free_)
#define pcre2_substring_get_byname PCRE2_SUFFIX(pcre2_substring_get_byname_)
#define pcre2_substring_get_bynumber PCRE2_SUFFIX(pcre2_substring_get_bynumber_)
#define pcre2_substring_length_byname PCRE2_SUFFIX(pcre2_substring_length_byname_)
#define pcre2_substring_length_bynumber PCRE2_SUFFIX(pcre2_substring_length_bynumber_)
#define pcre2_substring_list_get PCRE2_SUFFIX(pcre2_substring_list_get_)
#define pcre2_substring_list_free PCRE2_SUFFIX(pcre2_substring_list_free_)
#define pcre2_substring_nametable_scan PCRE2_SUFFIX(pcre2_substring_nametable_scan_)
#define pcre2_substring_number_from_name PCRE2_SUFFIX(pcre2_substring_number_from_name_)
/* Keep this old function name for backwards compatibility */
#define pcre2_set_recursion_limit PCRE2_SUFFIX(pcre2_set_recursion_limit_)
/* Keep this obsolete function for backwards compatibility: it is now a noop. */
#define pcre2_set_recursion_memory_management PCRE2_SUFFIX(pcre2_set_recursion_memory_management_)
/* Now generate all three sets of width-specific structures and function
prototypes. */
#define PCRE2_TYPES_STRUCTURES_AND_FUNCTIONS \
PCRE2_TYPES_LIST \
PCRE2_STRUCTURE_LIST \
PCRE2_GENERAL_INFO_FUNCTIONS \
PCRE2_GENERAL_CONTEXT_FUNCTIONS \
PCRE2_COMPILE_CONTEXT_FUNCTIONS \
PCRE2_CONVERT_CONTEXT_FUNCTIONS \
PCRE2_CONVERT_FUNCTIONS \
PCRE2_MATCH_CONTEXT_FUNCTIONS \
PCRE2_COMPILE_FUNCTIONS \
PCRE2_PATTERN_INFO_FUNCTIONS \
PCRE2_MATCH_FUNCTIONS \
PCRE2_SUBSTRING_FUNCTIONS \
PCRE2_SERIALIZE_FUNCTIONS \
PCRE2_SUBSTITUTE_FUNCTION \
PCRE2_JIT_FUNCTIONS \
PCRE2_OTHER_FUNCTIONS
#define PCRE2_LOCAL_WIDTH 8
PCRE2_TYPES_STRUCTURES_AND_FUNCTIONS
#undef PCRE2_LOCAL_WIDTH
#define PCRE2_LOCAL_WIDTH 16
PCRE2_TYPES_STRUCTURES_AND_FUNCTIONS
#undef PCRE2_LOCAL_WIDTH
#define PCRE2_LOCAL_WIDTH 32
PCRE2_TYPES_STRUCTURES_AND_FUNCTIONS
#undef PCRE2_LOCAL_WIDTH
/* Undefine the list macros; they are no longer needed. */
#undef PCRE2_TYPES_LIST
#undef PCRE2_STRUCTURE_LIST
#undef PCRE2_GENERAL_INFO_FUNCTIONS
#undef PCRE2_GENERAL_CONTEXT_FUNCTIONS
#undef PCRE2_COMPILE_CONTEXT_FUNCTIONS
#undef PCRE2_CONVERT_CONTEXT_FUNCTIONS
#undef PCRE2_MATCH_CONTEXT_FUNCTIONS
#undef PCRE2_COMPILE_FUNCTIONS
#undef PCRE2_PATTERN_INFO_FUNCTIONS
#undef PCRE2_MATCH_FUNCTIONS
#undef PCRE2_SUBSTRING_FUNCTIONS
#undef PCRE2_SERIALIZE_FUNCTIONS
#undef PCRE2_SUBSTITUTE_FUNCTION
#undef PCRE2_JIT_FUNCTIONS
#undef PCRE2_OTHER_FUNCTIONS
#undef PCRE2_TYPES_STRUCTURES_AND_FUNCTIONS
/* PCRE2_CODE_UNIT_WIDTH must be defined. If it is 8, 16, or 32, redefine
PCRE2_SUFFIX to use it. If it is 0, undefine the other macros and make
PCRE2_SUFFIX a no-op. Otherwise, generate an error. */
#undef PCRE2_SUFFIX
#ifndef PCRE2_CODE_UNIT_WIDTH
#error PCRE2_CODE_UNIT_WIDTH must be defined before including pcre2.h.
#error Use 8, 16, or 32; or 0 for a multi-width application.
#else /* PCRE2_CODE_UNIT_WIDTH is defined */
#if PCRE2_CODE_UNIT_WIDTH == 8 || \
PCRE2_CODE_UNIT_WIDTH == 16 || \
PCRE2_CODE_UNIT_WIDTH == 32
#define PCRE2_SUFFIX(a) PCRE2_GLUE(a, PCRE2_CODE_UNIT_WIDTH)
#elif PCRE2_CODE_UNIT_WIDTH == 0
#undef PCRE2_JOIN
#undef PCRE2_GLUE
#define PCRE2_SUFFIX(a) a
#else
#error PCRE2_CODE_UNIT_WIDTH must be 0, 8, 16, or 32.
#endif
#endif /* PCRE2_CODE_UNIT_WIDTH is defined */
#ifdef __cplusplus
} /* extern "C" */
#endif
#endif /* PCRE2_H_IDEMPOTENT_GUARD */
/* End of pcre2.h */

993
Kha/Backends/Kore-hxcpp/khacpp/project/thirdparty/pcre2-10.42-16/src/pcre2.h.in vendored Normal file
View File

@ -0,0 +1,993 @@
/*************************************************
* Perl-Compatible Regular Expressions *
*************************************************/
/* This is the public header file for the PCRE library, second API, to be
#included by applications that call PCRE2 functions.
Copyright (c) 2016-2021 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
modification, are permitted provided that the following conditions are met:
* Redistributions of source code must retain the above copyright notice,
this list of conditions and the following disclaimer.
* Redistributions in binary form must reproduce the above copyright
notice, this list of conditions and the following disclaimer in the
documentation and/or other materials provided with the distribution.
* Neither the name of the University of Cambridge nor the names of its
contributors may be used to endorse or promote products derived from
this software without specific prior written permission.
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
POSSIBILITY OF SUCH DAMAGE.
-----------------------------------------------------------------------------
*/
#ifndef PCRE2_H_IDEMPOTENT_GUARD
#define PCRE2_H_IDEMPOTENT_GUARD
/* The current PCRE version information. */
#define PCRE2_MAJOR @PCRE2_MAJOR@
#define PCRE2_MINOR @PCRE2_MINOR@
#define PCRE2_PRERELEASE @PCRE2_PRERELEASE@
#define PCRE2_DATE @PCRE2_DATE@
/* When an application links to a PCRE DLL in Windows, the symbols that are
imported have to be identified as such. When building PCRE2, the appropriate
export setting is defined in pcre2_internal.h, which includes this file. So we
don't change existing definitions of PCRE2_EXP_DECL. */
#if defined(_WIN32) && !defined(PCRE2_STATIC)
# ifndef PCRE2_EXP_DECL
# define PCRE2_EXP_DECL extern __declspec(dllimport)
# endif
#endif
/* By default, we use the standard "extern" declarations. */
#ifndef PCRE2_EXP_DECL
# ifdef __cplusplus
# define PCRE2_EXP_DECL extern "C"
# else
# define PCRE2_EXP_DECL extern
# endif
#endif
/* When compiling with the MSVC compiler, it is sometimes necessary to include
a "calling convention" before exported function names. (This is secondhand
information; I know nothing about MSVC myself). For example, something like
void __cdecl function(....)
might be needed. In order so make this easy, all the exported functions have
PCRE2_CALL_CONVENTION just before their names. It is rarely needed; if not
set, we ensure here that it has no effect. */
#ifndef PCRE2_CALL_CONVENTION
#define PCRE2_CALL_CONVENTION
#endif
/* Have to include limits.h, stdlib.h, and inttypes.h to ensure that size_t and
uint8_t, UCHAR_MAX, etc are defined. Some systems that do have inttypes.h do
not have stdint.h, which is why we use inttypes.h, which according to the C
standard is a superset of stdint.h. If inttypes.h is not available the build
will break and the relevant values must be provided by some other means. */
#include <limits.h>
#include <stdlib.h>
#include <inttypes.h>
/* Allow for C++ users compiling this directly. */
#ifdef __cplusplus
extern "C" {
#endif
/* The following option bits can be passed to pcre2_compile(), pcre2_match(),
or pcre2_dfa_match(). PCRE2_NO_UTF_CHECK affects only the function to which it
is passed. Put these bits at the most significant end of the options word so
others can be added next to them */
#define PCRE2_ANCHORED 0x80000000u
#define PCRE2_NO_UTF_CHECK 0x40000000u
#define PCRE2_ENDANCHORED 0x20000000u
/* The following option bits can be passed only to pcre2_compile(). However,
they may affect compilation, JIT compilation, and/or interpretive execution.
The following tags indicate which:
C alters what is compiled by pcre2_compile()
J alters what is compiled by pcre2_jit_compile()
M is inspected during pcre2_match() execution
D is inspected during pcre2_dfa_match() execution
*/
#define PCRE2_ALLOW_EMPTY_CLASS 0x00000001u /* C */
#define PCRE2_ALT_BSUX 0x00000002u /* C */
#define PCRE2_AUTO_CALLOUT 0x00000004u /* C */
#define PCRE2_CASELESS 0x00000008u /* C */
#define PCRE2_DOLLAR_ENDONLY 0x00000010u /* J M D */
#define PCRE2_DOTALL 0x00000020u /* C */
#define PCRE2_DUPNAMES 0x00000040u /* C */
#define PCRE2_EXTENDED 0x00000080u /* C */
#define PCRE2_FIRSTLINE 0x00000100u /* J M D */
#define PCRE2_MATCH_UNSET_BACKREF 0x00000200u /* C J M */
#define PCRE2_MULTILINE 0x00000400u /* C */
#define PCRE2_NEVER_UCP 0x00000800u /* C */
#define PCRE2_NEVER_UTF 0x00001000u /* C */
#define PCRE2_NO_AUTO_CAPTURE 0x00002000u /* C */
#define PCRE2_NO_AUTO_POSSESS 0x00004000u /* C */
#define PCRE2_NO_DOTSTAR_ANCHOR 0x00008000u /* C */
#define PCRE2_NO_START_OPTIMIZE 0x00010000u /* J M D */
#define PCRE2_UCP 0x00020000u /* C J M D */
#define PCRE2_UNGREEDY 0x00040000u /* C */
#define PCRE2_UTF 0x00080000u /* C J M D */
#define PCRE2_NEVER_BACKSLASH_C 0x00100000u /* C */
#define PCRE2_ALT_CIRCUMFLEX 0x00200000u /* J M D */
#define PCRE2_ALT_VERBNAMES 0x00400000u /* C */
#define PCRE2_USE_OFFSET_LIMIT 0x00800000u /* J M D */
#define PCRE2_EXTENDED_MORE 0x01000000u /* C */
#define PCRE2_LITERAL 0x02000000u /* C */
#define PCRE2_MATCH_INVALID_UTF 0x04000000u /* J M D */
/* An additional compile options word is available in the compile context. */
#define PCRE2_EXTRA_ALLOW_SURROGATE_ESCAPES 0x00000001u /* C */
#define PCRE2_EXTRA_BAD_ESCAPE_IS_LITERAL 0x00000002u /* C */
#define PCRE2_EXTRA_MATCH_WORD 0x00000004u /* C */
#define PCRE2_EXTRA_MATCH_LINE 0x00000008u /* C */
#define PCRE2_EXTRA_ESCAPED_CR_IS_LF 0x00000010u /* C */
#define PCRE2_EXTRA_ALT_BSUX 0x00000020u /* C */
#define PCRE2_EXTRA_ALLOW_LOOKAROUND_BSK 0x00000040u /* C */
/* These are for pcre2_jit_compile(). */
#define PCRE2_JIT_COMPLETE 0x00000001u /* For full matching */
#define PCRE2_JIT_PARTIAL_SOFT 0x00000002u
#define PCRE2_JIT_PARTIAL_HARD 0x00000004u
#define PCRE2_JIT_INVALID_UTF 0x00000100u
/* These are for pcre2_match(), pcre2_dfa_match(), pcre2_jit_match(), and
pcre2_substitute(). Some are allowed only for one of the functions, and in
these cases it is noted below. Note that PCRE2_ANCHORED, PCRE2_ENDANCHORED and
PCRE2_NO_UTF_CHECK can also be passed to these functions (though
pcre2_jit_match() ignores the latter since it bypasses all sanity checks). */
#define PCRE2_NOTBOL 0x00000001u
#define PCRE2_NOTEOL 0x00000002u
#define PCRE2_NOTEMPTY 0x00000004u /* ) These two must be kept */
#define PCRE2_NOTEMPTY_ATSTART 0x00000008u /* ) adjacent to each other. */
#define PCRE2_PARTIAL_SOFT 0x00000010u
#define PCRE2_PARTIAL_HARD 0x00000020u
#define PCRE2_DFA_RESTART 0x00000040u /* pcre2_dfa_match() only */
#define PCRE2_DFA_SHORTEST 0x00000080u /* pcre2_dfa_match() only */
#define PCRE2_SUBSTITUTE_GLOBAL 0x00000100u /* pcre2_substitute() only */
#define PCRE2_SUBSTITUTE_EXTENDED 0x00000200u /* pcre2_substitute() only */
#define PCRE2_SUBSTITUTE_UNSET_EMPTY 0x00000400u /* pcre2_substitute() only */
#define PCRE2_SUBSTITUTE_UNKNOWN_UNSET 0x00000800u /* pcre2_substitute() only */
#define PCRE2_SUBSTITUTE_OVERFLOW_LENGTH 0x00001000u /* pcre2_substitute() only */
#define PCRE2_NO_JIT 0x00002000u /* Not for pcre2_dfa_match() */
#define PCRE2_COPY_MATCHED_SUBJECT 0x00004000u
#define PCRE2_SUBSTITUTE_LITERAL 0x00008000u /* pcre2_substitute() only */
#define PCRE2_SUBSTITUTE_MATCHED 0x00010000u /* pcre2_substitute() only */
#define PCRE2_SUBSTITUTE_REPLACEMENT_ONLY 0x00020000u /* pcre2_substitute() only */
/* Options for pcre2_pattern_convert(). */
#define PCRE2_CONVERT_UTF 0x00000001u
#define PCRE2_CONVERT_NO_UTF_CHECK 0x00000002u
#define PCRE2_CONVERT_POSIX_BASIC 0x00000004u
#define PCRE2_CONVERT_POSIX_EXTENDED 0x00000008u
#define PCRE2_CONVERT_GLOB 0x00000010u
#define PCRE2_CONVERT_GLOB_NO_WILD_SEPARATOR 0x00000030u
#define PCRE2_CONVERT_GLOB_NO_STARSTAR 0x00000050u
/* Newline and \R settings, for use in compile contexts. The newline values
must be kept in step with values set in config.h and both sets must all be
greater than zero. */
#define PCRE2_NEWLINE_CR 1
#define PCRE2_NEWLINE_LF 2
#define PCRE2_NEWLINE_CRLF 3
#define PCRE2_NEWLINE_ANY 4
#define PCRE2_NEWLINE_ANYCRLF 5
#define PCRE2_NEWLINE_NUL 6
#define PCRE2_BSR_UNICODE 1
#define PCRE2_BSR_ANYCRLF 2
/* Error codes for pcre2_compile(). Some of these are also used by
pcre2_pattern_convert(). */
#define PCRE2_ERROR_END_BACKSLASH 101
#define PCRE2_ERROR_END_BACKSLASH_C 102
#define PCRE2_ERROR_UNKNOWN_ESCAPE 103
#define PCRE2_ERROR_QUANTIFIER_OUT_OF_ORDER 104
#define PCRE2_ERROR_QUANTIFIER_TOO_BIG 105
#define PCRE2_ERROR_MISSING_SQUARE_BRACKET 106
#define PCRE2_ERROR_ESCAPE_INVALID_IN_CLASS 107
#define PCRE2_ERROR_CLASS_RANGE_ORDER 108
#define PCRE2_ERROR_QUANTIFIER_INVALID 109
#define PCRE2_ERROR_INTERNAL_UNEXPECTED_REPEAT 110
#define PCRE2_ERROR_INVALID_AFTER_PARENS_QUERY 111
#define PCRE2_ERROR_POSIX_CLASS_NOT_IN_CLASS 112
#define PCRE2_ERROR_POSIX_NO_SUPPORT_COLLATING 113
#define PCRE2_ERROR_MISSING_CLOSING_PARENTHESIS 114
#define PCRE2_ERROR_BAD_SUBPATTERN_REFERENCE 115
#define PCRE2_ERROR_NULL_PATTERN 116
#define PCRE2_ERROR_BAD_OPTIONS 117
#define PCRE2_ERROR_MISSING_COMMENT_CLOSING 118
#define PCRE2_ERROR_PARENTHESES_NEST_TOO_DEEP 119
#define PCRE2_ERROR_PATTERN_TOO_LARGE 120
#define PCRE2_ERROR_HEAP_FAILED 121
#define PCRE2_ERROR_UNMATCHED_CLOSING_PARENTHESIS 122
#define PCRE2_ERROR_INTERNAL_CODE_OVERFLOW 123
#define PCRE2_ERROR_MISSING_CONDITION_CLOSING 124
#define PCRE2_ERROR_LOOKBEHIND_NOT_FIXED_LENGTH 125
#define PCRE2_ERROR_ZERO_RELATIVE_REFERENCE 126
#define PCRE2_ERROR_TOO_MANY_CONDITION_BRANCHES 127
#define PCRE2_ERROR_CONDITION_ASSERTION_EXPECTED 128
#define PCRE2_ERROR_BAD_RELATIVE_REFERENCE 129
#define PCRE2_ERROR_UNKNOWN_POSIX_CLASS 130
#define PCRE2_ERROR_INTERNAL_STUDY_ERROR 131
#define PCRE2_ERROR_UNICODE_NOT_SUPPORTED 132
#define PCRE2_ERROR_PARENTHESES_STACK_CHECK 133
#define PCRE2_ERROR_CODE_POINT_TOO_BIG 134
#define PCRE2_ERROR_LOOKBEHIND_TOO_COMPLICATED 135
#define PCRE2_ERROR_LOOKBEHIND_INVALID_BACKSLASH_C 136
#define PCRE2_ERROR_UNSUPPORTED_ESCAPE_SEQUENCE 137
#define PCRE2_ERROR_CALLOUT_NUMBER_TOO_BIG 138
#define PCRE2_ERROR_MISSING_CALLOUT_CLOSING 139
#define PCRE2_ERROR_ESCAPE_INVALID_IN_VERB 140
#define PCRE2_ERROR_UNRECOGNIZED_AFTER_QUERY_P 141
#define PCRE2_ERROR_MISSING_NAME_TERMINATOR 142
#define PCRE2_ERROR_DUPLICATE_SUBPATTERN_NAME 143
#define PCRE2_ERROR_INVALID_SUBPATTERN_NAME 144
#define PCRE2_ERROR_UNICODE_PROPERTIES_UNAVAILABLE 145
#define PCRE2_ERROR_MALFORMED_UNICODE_PROPERTY 146
#define PCRE2_ERROR_UNKNOWN_UNICODE_PROPERTY 147
#define PCRE2_ERROR_SUBPATTERN_NAME_TOO_LONG 148
#define PCRE2_ERROR_TOO_MANY_NAMED_SUBPATTERNS 149
#define PCRE2_ERROR_CLASS_INVALID_RANGE 150
#define PCRE2_ERROR_OCTAL_BYTE_TOO_BIG 151
#define PCRE2_ERROR_INTERNAL_OVERRAN_WORKSPACE 152
#define PCRE2_ERROR_INTERNAL_MISSING_SUBPATTERN 153
#define PCRE2_ERROR_DEFINE_TOO_MANY_BRANCHES 154
#define PCRE2_ERROR_BACKSLASH_O_MISSING_BRACE 155
#define PCRE2_ERROR_INTERNAL_UNKNOWN_NEWLINE 156
#define PCRE2_ERROR_BACKSLASH_G_SYNTAX 157
#define PCRE2_ERROR_PARENS_QUERY_R_MISSING_CLOSING 158
/* Error 159 is obsolete and should now never occur */
#define PCRE2_ERROR_VERB_ARGUMENT_NOT_ALLOWED 159
#define PCRE2_ERROR_VERB_UNKNOWN 160
#define PCRE2_ERROR_SUBPATTERN_NUMBER_TOO_BIG 161
#define PCRE2_ERROR_SUBPATTERN_NAME_EXPECTED 162
#define PCRE2_ERROR_INTERNAL_PARSED_OVERFLOW 163
#define PCRE2_ERROR_INVALID_OCTAL 164
#define PCRE2_ERROR_SUBPATTERN_NAMES_MISMATCH 165
#define PCRE2_ERROR_MARK_MISSING_ARGUMENT 166
#define PCRE2_ERROR_INVALID_HEXADECIMAL 167
#define PCRE2_ERROR_BACKSLASH_C_SYNTAX 168
#define PCRE2_ERROR_BACKSLASH_K_SYNTAX 169
#define PCRE2_ERROR_INTERNAL_BAD_CODE_LOOKBEHINDS 170
#define PCRE2_ERROR_BACKSLASH_N_IN_CLASS 171
#define PCRE2_ERROR_CALLOUT_STRING_TOO_LONG 172
#define PCRE2_ERROR_UNICODE_DISALLOWED_CODE_POINT 173
#define PCRE2_ERROR_UTF_IS_DISABLED 174
#define PCRE2_ERROR_UCP_IS_DISABLED 175
#define PCRE2_ERROR_VERB_NAME_TOO_LONG 176
#define PCRE2_ERROR_BACKSLASH_U_CODE_POINT_TOO_BIG 177
#define PCRE2_ERROR_MISSING_OCTAL_OR_HEX_DIGITS 178
#define PCRE2_ERROR_VERSION_CONDITION_SYNTAX 179
#define PCRE2_ERROR_INTERNAL_BAD_CODE_AUTO_POSSESS 180
#define PCRE2_ERROR_CALLOUT_NO_STRING_DELIMITER 181
#define PCRE2_ERROR_CALLOUT_BAD_STRING_DELIMITER 182
#define PCRE2_ERROR_BACKSLASH_C_CALLER_DISABLED 183
#define PCRE2_ERROR_QUERY_BARJX_NEST_TOO_DEEP 184
#define PCRE2_ERROR_BACKSLASH_C_LIBRARY_DISABLED 185
#define PCRE2_ERROR_PATTERN_TOO_COMPLICATED 186
#define PCRE2_ERROR_LOOKBEHIND_TOO_LONG 187
#define PCRE2_ERROR_PATTERN_STRING_TOO_LONG 188
#define PCRE2_ERROR_INTERNAL_BAD_CODE 189
#define PCRE2_ERROR_INTERNAL_BAD_CODE_IN_SKIP 190
#define PCRE2_ERROR_NO_SURROGATES_IN_UTF16 191
#define PCRE2_ERROR_BAD_LITERAL_OPTIONS 192
#define PCRE2_ERROR_SUPPORTED_ONLY_IN_UNICODE 193
#define PCRE2_ERROR_INVALID_HYPHEN_IN_OPTIONS 194
#define PCRE2_ERROR_ALPHA_ASSERTION_UNKNOWN 195
#define PCRE2_ERROR_SCRIPT_RUN_NOT_AVAILABLE 196
#define PCRE2_ERROR_TOO_MANY_CAPTURES 197
#define PCRE2_ERROR_CONDITION_ATOMIC_ASSERTION_EXPECTED 198
#define PCRE2_ERROR_BACKSLASH_K_IN_LOOKAROUND 199
/* "Expected" matching error codes: no match and partial match. */
#define PCRE2_ERROR_NOMATCH (-1)
#define PCRE2_ERROR_PARTIAL (-2)
/* Error codes for UTF-8 validity checks */
#define PCRE2_ERROR_UTF8_ERR1 (-3)
#define PCRE2_ERROR_UTF8_ERR2 (-4)
#define PCRE2_ERROR_UTF8_ERR3 (-5)
#define PCRE2_ERROR_UTF8_ERR4 (-6)
#define PCRE2_ERROR_UTF8_ERR5 (-7)
#define PCRE2_ERROR_UTF8_ERR6 (-8)
#define PCRE2_ERROR_UTF8_ERR7 (-9)
#define PCRE2_ERROR_UTF8_ERR8 (-10)
#define PCRE2_ERROR_UTF8_ERR9 (-11)
#define PCRE2_ERROR_UTF8_ERR10 (-12)
#define PCRE2_ERROR_UTF8_ERR11 (-13)
#define PCRE2_ERROR_UTF8_ERR12 (-14)
#define PCRE2_ERROR_UTF8_ERR13 (-15)
#define PCRE2_ERROR_UTF8_ERR14 (-16)
#define PCRE2_ERROR_UTF8_ERR15 (-17)
#define PCRE2_ERROR_UTF8_ERR16 (-18)
#define PCRE2_ERROR_UTF8_ERR17 (-19)
#define PCRE2_ERROR_UTF8_ERR18 (-20)
#define PCRE2_ERROR_UTF8_ERR19 (-21)
#define PCRE2_ERROR_UTF8_ERR20 (-22)
#define PCRE2_ERROR_UTF8_ERR21 (-23)
/* Error codes for UTF-16 validity checks */
#define PCRE2_ERROR_UTF16_ERR1 (-24)
#define PCRE2_ERROR_UTF16_ERR2 (-25)
#define PCRE2_ERROR_UTF16_ERR3 (-26)
/* Error codes for UTF-32 validity checks */
#define PCRE2_ERROR_UTF32_ERR1 (-27)
#define PCRE2_ERROR_UTF32_ERR2 (-28)
/* Miscellaneous error codes for pcre2[_dfa]_match(), substring extraction
functions, context functions, and serializing functions. They are in numerical
order. Originally they were in alphabetical order too, but now that PCRE2 is
released, the numbers must not be changed. */
#define PCRE2_ERROR_BADDATA (-29)
#define PCRE2_ERROR_MIXEDTABLES (-30) /* Name was changed */
#define PCRE2_ERROR_BADMAGIC (-31)
#define PCRE2_ERROR_BADMODE (-32)
#define PCRE2_ERROR_BADOFFSET (-33)
#define PCRE2_ERROR_BADOPTION (-34)
#define PCRE2_ERROR_BADREPLACEMENT (-35)
#define PCRE2_ERROR_BADUTFOFFSET (-36)
#define PCRE2_ERROR_CALLOUT (-37) /* Never used by PCRE2 itself */
#define PCRE2_ERROR_DFA_BADRESTART (-38)
#define PCRE2_ERROR_DFA_RECURSE (-39)
#define PCRE2_ERROR_DFA_UCOND (-40)
#define PCRE2_ERROR_DFA_UFUNC (-41)
#define PCRE2_ERROR_DFA_UITEM (-42)
#define PCRE2_ERROR_DFA_WSSIZE (-43)
#define PCRE2_ERROR_INTERNAL (-44)
#define PCRE2_ERROR_JIT_BADOPTION (-45)
#define PCRE2_ERROR_JIT_STACKLIMIT (-46)
#define PCRE2_ERROR_MATCHLIMIT (-47)
#define PCRE2_ERROR_NOMEMORY (-48)
#define PCRE2_ERROR_NOSUBSTRING (-49)
#define PCRE2_ERROR_NOUNIQUESUBSTRING (-50)
#define PCRE2_ERROR_NULL (-51)
#define PCRE2_ERROR_RECURSELOOP (-52)
#define PCRE2_ERROR_DEPTHLIMIT (-53)
#define PCRE2_ERROR_RECURSIONLIMIT (-53) /* Obsolete synonym */
#define PCRE2_ERROR_UNAVAILABLE (-54)
#define PCRE2_ERROR_UNSET (-55)
#define PCRE2_ERROR_BADOFFSETLIMIT (-56)
#define PCRE2_ERROR_BADREPESCAPE (-57)
#define PCRE2_ERROR_REPMISSINGBRACE (-58)
#define PCRE2_ERROR_BADSUBSTITUTION (-59)
#define PCRE2_ERROR_BADSUBSPATTERN (-60)
#define PCRE2_ERROR_TOOMANYREPLACE (-61)
#define PCRE2_ERROR_BADSERIALIZEDDATA (-62)
#define PCRE2_ERROR_HEAPLIMIT (-63)
#define PCRE2_ERROR_CONVERT_SYNTAX (-64)
#define PCRE2_ERROR_INTERNAL_DUPMATCH (-65)
#define PCRE2_ERROR_DFA_UINVALID_UTF (-66)
/* Request types for pcre2_pattern_info() */
#define PCRE2_INFO_ALLOPTIONS 0
#define PCRE2_INFO_ARGOPTIONS 1
#define PCRE2_INFO_BACKREFMAX 2
#define PCRE2_INFO_BSR 3
#define PCRE2_INFO_CAPTURECOUNT 4
#define PCRE2_INFO_FIRSTCODEUNIT 5
#define PCRE2_INFO_FIRSTCODETYPE 6
#define PCRE2_INFO_FIRSTBITMAP 7
#define PCRE2_INFO_HASCRORLF 8
#define PCRE2_INFO_JCHANGED 9
#define PCRE2_INFO_JITSIZE 10
#define PCRE2_INFO_LASTCODEUNIT 11
#define PCRE2_INFO_LASTCODETYPE 12
#define PCRE2_INFO_MATCHEMPTY 13
#define PCRE2_INFO_MATCHLIMIT 14
#define PCRE2_INFO_MAXLOOKBEHIND 15
#define PCRE2_INFO_MINLENGTH 16
#define PCRE2_INFO_NAMECOUNT 17
#define PCRE2_INFO_NAMEENTRYSIZE 18
#define PCRE2_INFO_NAMETABLE 19
#define PCRE2_INFO_NEWLINE 20
#define PCRE2_INFO_DEPTHLIMIT 21
#define PCRE2_INFO_RECURSIONLIMIT 21 /* Obsolete synonym */
#define PCRE2_INFO_SIZE 22
#define PCRE2_INFO_HASBACKSLASHC 23
#define PCRE2_INFO_FRAMESIZE 24
#define PCRE2_INFO_HEAPLIMIT 25
#define PCRE2_INFO_EXTRAOPTIONS 26
/* Request types for pcre2_config(). */
#define PCRE2_CONFIG_BSR 0
#define PCRE2_CONFIG_JIT 1
#define PCRE2_CONFIG_JITTARGET 2
#define PCRE2_CONFIG_LINKSIZE 3
#define PCRE2_CONFIG_MATCHLIMIT 4
#define PCRE2_CONFIG_NEWLINE 5
#define PCRE2_CONFIG_PARENSLIMIT 6
#define PCRE2_CONFIG_DEPTHLIMIT 7
#define PCRE2_CONFIG_RECURSIONLIMIT 7 /* Obsolete synonym */
#define PCRE2_CONFIG_STACKRECURSE 8 /* Obsolete */
#define PCRE2_CONFIG_UNICODE 9
#define PCRE2_CONFIG_UNICODE_VERSION 10
#define PCRE2_CONFIG_VERSION 11
#define PCRE2_CONFIG_HEAPLIMIT 12
#define PCRE2_CONFIG_NEVER_BACKSLASH_C 13
#define PCRE2_CONFIG_COMPILED_WIDTHS 14
#define PCRE2_CONFIG_TABLES_LENGTH 15
/* Types for code units in patterns and subject strings. */
typedef uint8_t PCRE2_UCHAR8;
typedef uint16_t PCRE2_UCHAR16;
typedef uint32_t PCRE2_UCHAR32;
typedef const PCRE2_UCHAR8 *PCRE2_SPTR8;
typedef const PCRE2_UCHAR16 *PCRE2_SPTR16;
typedef const PCRE2_UCHAR32 *PCRE2_SPTR32;
/* The PCRE2_SIZE type is used for all string lengths and offsets in PCRE2,
including pattern offsets for errors and subject offsets after a match. We
define special values to indicate zero-terminated strings and unset offsets in
the offset vector (ovector). */
#define PCRE2_SIZE size_t
#define PCRE2_SIZE_MAX SIZE_MAX
#define PCRE2_ZERO_TERMINATED (~(PCRE2_SIZE)0)
#define PCRE2_UNSET (~(PCRE2_SIZE)0)
/* Generic types for opaque structures and JIT callback functions. These
declarations are defined in a macro that is expanded for each width later. */
#define PCRE2_TYPES_LIST \
struct pcre2_real_general_context; \
typedef struct pcre2_real_general_context pcre2_general_context; \
\
struct pcre2_real_compile_context; \
typedef struct pcre2_real_compile_context pcre2_compile_context; \
\
struct pcre2_real_match_context; \
typedef struct pcre2_real_match_context pcre2_match_context; \
\
struct pcre2_real_convert_context; \
typedef struct pcre2_real_convert_context pcre2_convert_context; \
\
struct pcre2_real_code; \
typedef struct pcre2_real_code pcre2_code; \
\
struct pcre2_real_match_data; \
typedef struct pcre2_real_match_data pcre2_match_data; \
\
struct pcre2_real_jit_stack; \
typedef struct pcre2_real_jit_stack pcre2_jit_stack; \
\
typedef pcre2_jit_stack *(*pcre2_jit_callback)(void *);
/* The structures for passing out data via callout functions. We use structures
so that new fields can be added on the end in future versions, without changing
the API of the function, thereby allowing old clients to work without
modification. Define the generic versions in a macro; the width-specific
versions are generated from this macro below. */
/* Flags for the callout_flags field. These are cleared after a callout. */
#define PCRE2_CALLOUT_STARTMATCH 0x00000001u /* Set for each bumpalong */
#define PCRE2_CALLOUT_BACKTRACK 0x00000002u /* Set after a backtrack */
#define PCRE2_STRUCTURE_LIST \
typedef struct pcre2_callout_block { \
uint32_t version; /* Identifies version of block */ \
/* ------------------------ Version 0 ------------------------------- */ \
uint32_t callout_number; /* Number compiled into pattern */ \
uint32_t capture_top; /* Max current capture */ \
uint32_t capture_last; /* Most recently closed capture */ \
PCRE2_SIZE *offset_vector; /* The offset vector */ \
PCRE2_SPTR mark; /* Pointer to current mark or NULL */ \
PCRE2_SPTR subject; /* The subject being matched */ \
PCRE2_SIZE subject_length; /* The length of the subject */ \
PCRE2_SIZE start_match; /* Offset to start of this match attempt */ \
PCRE2_SIZE current_position; /* Where we currently are in the subject */ \
PCRE2_SIZE pattern_position; /* Offset to next item in the pattern */ \
PCRE2_SIZE next_item_length; /* Length of next item in the pattern */ \
/* ------------------- Added for Version 1 -------------------------- */ \
PCRE2_SIZE callout_string_offset; /* Offset to string within pattern */ \
PCRE2_SIZE callout_string_length; /* Length of string compiled into pattern */ \
PCRE2_SPTR callout_string; /* String compiled into pattern */ \
/* ------------------- Added for Version 2 -------------------------- */ \
uint32_t callout_flags; /* See above for list */ \
/* ------------------------------------------------------------------ */ \
} pcre2_callout_block; \
\
typedef struct pcre2_callout_enumerate_block { \
uint32_t version; /* Identifies version of block */ \
/* ------------------------ Version 0 ------------------------------- */ \
PCRE2_SIZE pattern_position; /* Offset to next item in the pattern */ \
PCRE2_SIZE next_item_length; /* Length of next item in the pattern */ \
uint32_t callout_number; /* Number compiled into pattern */ \
PCRE2_SIZE callout_string_offset; /* Offset to string within pattern */ \
PCRE2_SIZE callout_string_length; /* Length of string compiled into pattern */ \
PCRE2_SPTR callout_string; /* String compiled into pattern */ \
/* ------------------------------------------------------------------ */ \
} pcre2_callout_enumerate_block; \
\
typedef struct pcre2_substitute_callout_block { \
uint32_t version; /* Identifies version of block */ \
/* ------------------------ Version 0 ------------------------------- */ \
PCRE2_SPTR input; /* Pointer to input subject string */ \
PCRE2_SPTR output; /* Pointer to output buffer */ \
PCRE2_SIZE output_offsets[2]; /* Changed portion of the output */ \
PCRE2_SIZE *ovector; /* Pointer to current ovector */ \
uint32_t oveccount; /* Count of pairs set in ovector */ \
uint32_t subscount; /* Substitution number */ \
/* ------------------------------------------------------------------ */ \
} pcre2_substitute_callout_block;
/* List the generic forms of all other functions in macros, which will be
expanded for each width below. Start with functions that give general
information. */
#define PCRE2_GENERAL_INFO_FUNCTIONS \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION pcre2_config(uint32_t, void *);
/* Functions for manipulating contexts. */
#define PCRE2_GENERAL_CONTEXT_FUNCTIONS \
PCRE2_EXP_DECL pcre2_general_context *PCRE2_CALL_CONVENTION \
pcre2_general_context_copy(pcre2_general_context *); \
PCRE2_EXP_DECL pcre2_general_context *PCRE2_CALL_CONVENTION \
pcre2_general_context_create(void *(*)(PCRE2_SIZE, void *), \
void (*)(void *, void *), void *); \
PCRE2_EXP_DECL void PCRE2_CALL_CONVENTION \
pcre2_general_context_free(pcre2_general_context *);
#define PCRE2_COMPILE_CONTEXT_FUNCTIONS \
PCRE2_EXP_DECL pcre2_compile_context *PCRE2_CALL_CONVENTION \
pcre2_compile_context_copy(pcre2_compile_context *); \
PCRE2_EXP_DECL pcre2_compile_context *PCRE2_CALL_CONVENTION \
pcre2_compile_context_create(pcre2_general_context *);\
PCRE2_EXP_DECL void PCRE2_CALL_CONVENTION \
pcre2_compile_context_free(pcre2_compile_context *); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_set_bsr(pcre2_compile_context *, uint32_t); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_set_character_tables(pcre2_compile_context *, const uint8_t *); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_set_compile_extra_options(pcre2_compile_context *, uint32_t); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_set_max_pattern_length(pcre2_compile_context *, PCRE2_SIZE); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_set_newline(pcre2_compile_context *, uint32_t); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_set_parens_nest_limit(pcre2_compile_context *, uint32_t); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_set_compile_recursion_guard(pcre2_compile_context *, \
int (*)(uint32_t, void *), void *);
#define PCRE2_MATCH_CONTEXT_FUNCTIONS \
PCRE2_EXP_DECL pcre2_match_context *PCRE2_CALL_CONVENTION \
pcre2_match_context_copy(pcre2_match_context *); \
PCRE2_EXP_DECL pcre2_match_context *PCRE2_CALL_CONVENTION \
pcre2_match_context_create(pcre2_general_context *); \
PCRE2_EXP_DECL void PCRE2_CALL_CONVENTION \
pcre2_match_context_free(pcre2_match_context *); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_set_callout(pcre2_match_context *, \
int (*)(pcre2_callout_block *, void *), void *); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_set_substitute_callout(pcre2_match_context *, \
int (*)(pcre2_substitute_callout_block *, void *), void *); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_set_depth_limit(pcre2_match_context *, uint32_t); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_set_heap_limit(pcre2_match_context *, uint32_t); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_set_match_limit(pcre2_match_context *, uint32_t); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_set_offset_limit(pcre2_match_context *, PCRE2_SIZE); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_set_recursion_limit(pcre2_match_context *, uint32_t); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_set_recursion_memory_management(pcre2_match_context *, \
void *(*)(PCRE2_SIZE, void *), void (*)(void *, void *), void *);
#define PCRE2_CONVERT_CONTEXT_FUNCTIONS \
PCRE2_EXP_DECL pcre2_convert_context *PCRE2_CALL_CONVENTION \
pcre2_convert_context_copy(pcre2_convert_context *); \
PCRE2_EXP_DECL pcre2_convert_context *PCRE2_CALL_CONVENTION \
pcre2_convert_context_create(pcre2_general_context *); \
PCRE2_EXP_DECL void PCRE2_CALL_CONVENTION \
pcre2_convert_context_free(pcre2_convert_context *); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_set_glob_escape(pcre2_convert_context *, uint32_t); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_set_glob_separator(pcre2_convert_context *, uint32_t);
/* Functions concerned with compiling a pattern to PCRE internal code. */
#define PCRE2_COMPILE_FUNCTIONS \
PCRE2_EXP_DECL pcre2_code *PCRE2_CALL_CONVENTION \
pcre2_compile(PCRE2_SPTR, PCRE2_SIZE, uint32_t, int *, PCRE2_SIZE *, \
pcre2_compile_context *); \
PCRE2_EXP_DECL void PCRE2_CALL_CONVENTION \
pcre2_code_free(pcre2_code *); \
PCRE2_EXP_DECL pcre2_code *PCRE2_CALL_CONVENTION \
pcre2_code_copy(const pcre2_code *); \
PCRE2_EXP_DECL pcre2_code *PCRE2_CALL_CONVENTION \
pcre2_code_copy_with_tables(const pcre2_code *);
/* Functions that give information about a compiled pattern. */
#define PCRE2_PATTERN_INFO_FUNCTIONS \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_pattern_info(const pcre2_code *, uint32_t, void *); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_callout_enumerate(const pcre2_code *, \
int (*)(pcre2_callout_enumerate_block *, void *), void *);
/* Functions for running a match and inspecting the result. */
#define PCRE2_MATCH_FUNCTIONS \
PCRE2_EXP_DECL pcre2_match_data *PCRE2_CALL_CONVENTION \
pcre2_match_data_create(uint32_t, pcre2_general_context *); \
PCRE2_EXP_DECL pcre2_match_data *PCRE2_CALL_CONVENTION \
pcre2_match_data_create_from_pattern(const pcre2_code *, \
pcre2_general_context *); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_dfa_match(const pcre2_code *, PCRE2_SPTR, PCRE2_SIZE, PCRE2_SIZE, \
uint32_t, pcre2_match_data *, pcre2_match_context *, int *, PCRE2_SIZE); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_match(const pcre2_code *, PCRE2_SPTR, PCRE2_SIZE, PCRE2_SIZE, \
uint32_t, pcre2_match_data *, pcre2_match_context *); \
PCRE2_EXP_DECL void PCRE2_CALL_CONVENTION \
pcre2_match_data_free(pcre2_match_data *); \
PCRE2_EXP_DECL PCRE2_SPTR PCRE2_CALL_CONVENTION \
pcre2_get_mark(pcre2_match_data *); \
PCRE2_EXP_DECL PCRE2_SIZE PCRE2_CALL_CONVENTION \
pcre2_get_match_data_size(pcre2_match_data *); \
PCRE2_EXP_DECL uint32_t PCRE2_CALL_CONVENTION \
pcre2_get_ovector_count(pcre2_match_data *); \
PCRE2_EXP_DECL PCRE2_SIZE *PCRE2_CALL_CONVENTION \
pcre2_get_ovector_pointer(pcre2_match_data *); \
PCRE2_EXP_DECL PCRE2_SIZE PCRE2_CALL_CONVENTION \
pcre2_get_startchar(pcre2_match_data *);
/* Convenience functions for handling matched substrings. */
#define PCRE2_SUBSTRING_FUNCTIONS \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_substring_copy_byname(pcre2_match_data *, PCRE2_SPTR, PCRE2_UCHAR *, \
PCRE2_SIZE *); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_substring_copy_bynumber(pcre2_match_data *, uint32_t, PCRE2_UCHAR *, \
PCRE2_SIZE *); \
PCRE2_EXP_DECL void PCRE2_CALL_CONVENTION \
pcre2_substring_free(PCRE2_UCHAR *); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_substring_get_byname(pcre2_match_data *, PCRE2_SPTR, PCRE2_UCHAR **, \
PCRE2_SIZE *); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_substring_get_bynumber(pcre2_match_data *, uint32_t, PCRE2_UCHAR **, \
PCRE2_SIZE *); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_substring_length_byname(pcre2_match_data *, PCRE2_SPTR, PCRE2_SIZE *); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_substring_length_bynumber(pcre2_match_data *, uint32_t, PCRE2_SIZE *); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_substring_nametable_scan(const pcre2_code *, PCRE2_SPTR, PCRE2_SPTR *, \
PCRE2_SPTR *); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_substring_number_from_name(const pcre2_code *, PCRE2_SPTR); \
PCRE2_EXP_DECL void PCRE2_CALL_CONVENTION \
pcre2_substring_list_free(PCRE2_SPTR *); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_substring_list_get(pcre2_match_data *, PCRE2_UCHAR ***, PCRE2_SIZE **);
/* Functions for serializing / deserializing compiled patterns. */
#define PCRE2_SERIALIZE_FUNCTIONS \
PCRE2_EXP_DECL int32_t PCRE2_CALL_CONVENTION \
pcre2_serialize_encode(const pcre2_code **, int32_t, uint8_t **, \
PCRE2_SIZE *, pcre2_general_context *); \
PCRE2_EXP_DECL int32_t PCRE2_CALL_CONVENTION \
pcre2_serialize_decode(pcre2_code **, int32_t, const uint8_t *, \
pcre2_general_context *); \
PCRE2_EXP_DECL int32_t PCRE2_CALL_CONVENTION \
pcre2_serialize_get_number_of_codes(const uint8_t *); \
PCRE2_EXP_DECL void PCRE2_CALL_CONVENTION \
pcre2_serialize_free(uint8_t *);
/* Convenience function for match + substitute. */
#define PCRE2_SUBSTITUTE_FUNCTION \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_substitute(const pcre2_code *, PCRE2_SPTR, PCRE2_SIZE, PCRE2_SIZE, \
uint32_t, pcre2_match_data *, pcre2_match_context *, PCRE2_SPTR, \
PCRE2_SIZE, PCRE2_UCHAR *, PCRE2_SIZE *);
/* Functions for converting pattern source strings. */
#define PCRE2_CONVERT_FUNCTIONS \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_pattern_convert(PCRE2_SPTR, PCRE2_SIZE, uint32_t, PCRE2_UCHAR **, \
PCRE2_SIZE *, pcre2_convert_context *); \
PCRE2_EXP_DECL void PCRE2_CALL_CONVENTION \
pcre2_converted_pattern_free(PCRE2_UCHAR *);
/* Functions for JIT processing */
#define PCRE2_JIT_FUNCTIONS \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_jit_compile(pcre2_code *, uint32_t); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_jit_match(const pcre2_code *, PCRE2_SPTR, PCRE2_SIZE, PCRE2_SIZE, \
uint32_t, pcre2_match_data *, pcre2_match_context *); \
PCRE2_EXP_DECL void PCRE2_CALL_CONVENTION \
pcre2_jit_free_unused_memory(pcre2_general_context *); \
PCRE2_EXP_DECL pcre2_jit_stack *PCRE2_CALL_CONVENTION \
pcre2_jit_stack_create(PCRE2_SIZE, PCRE2_SIZE, pcre2_general_context *); \
PCRE2_EXP_DECL void PCRE2_CALL_CONVENTION \
pcre2_jit_stack_assign(pcre2_match_context *, pcre2_jit_callback, void *); \
PCRE2_EXP_DECL void PCRE2_CALL_CONVENTION \
pcre2_jit_stack_free(pcre2_jit_stack *);
/* Other miscellaneous functions. */
#define PCRE2_OTHER_FUNCTIONS \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_get_error_message(int, PCRE2_UCHAR *, PCRE2_SIZE); \
PCRE2_EXP_DECL const uint8_t *PCRE2_CALL_CONVENTION \
pcre2_maketables(pcre2_general_context *); \
PCRE2_EXP_DECL void PCRE2_CALL_CONVENTION \
pcre2_maketables_free(pcre2_general_context *, const uint8_t *);
/* Define macros that generate width-specific names from generic versions. The
three-level macro scheme is necessary to get the macros expanded when we want
them to be. First we get the width from PCRE2_LOCAL_WIDTH, which is used for
generating three versions of everything below. After that, PCRE2_SUFFIX will be
re-defined to use PCRE2_CODE_UNIT_WIDTH, for use when macros such as
pcre2_compile are called by application code. */
#define PCRE2_JOIN(a,b) a ## b
#define PCRE2_GLUE(a,b) PCRE2_JOIN(a,b)
#define PCRE2_SUFFIX(a) PCRE2_GLUE(a,PCRE2_LOCAL_WIDTH)
/* Data types */
#define PCRE2_UCHAR PCRE2_SUFFIX(PCRE2_UCHAR)
#define PCRE2_SPTR PCRE2_SUFFIX(PCRE2_SPTR)
#define pcre2_code PCRE2_SUFFIX(pcre2_code_)
#define pcre2_jit_callback PCRE2_SUFFIX(pcre2_jit_callback_)
#define pcre2_jit_stack PCRE2_SUFFIX(pcre2_jit_stack_)
#define pcre2_real_code PCRE2_SUFFIX(pcre2_real_code_)
#define pcre2_real_general_context PCRE2_SUFFIX(pcre2_real_general_context_)
#define pcre2_real_compile_context PCRE2_SUFFIX(pcre2_real_compile_context_)
#define pcre2_real_convert_context PCRE2_SUFFIX(pcre2_real_convert_context_)
#define pcre2_real_match_context PCRE2_SUFFIX(pcre2_real_match_context_)
#define pcre2_real_jit_stack PCRE2_SUFFIX(pcre2_real_jit_stack_)
#define pcre2_real_match_data PCRE2_SUFFIX(pcre2_real_match_data_)
/* Data blocks */
#define pcre2_callout_block PCRE2_SUFFIX(pcre2_callout_block_)
#define pcre2_callout_enumerate_block PCRE2_SUFFIX(pcre2_callout_enumerate_block_)
#define pcre2_substitute_callout_block PCRE2_SUFFIX(pcre2_substitute_callout_block_)
#define pcre2_general_context PCRE2_SUFFIX(pcre2_general_context_)
#define pcre2_compile_context PCRE2_SUFFIX(pcre2_compile_context_)
#define pcre2_convert_context PCRE2_SUFFIX(pcre2_convert_context_)
#define pcre2_match_context PCRE2_SUFFIX(pcre2_match_context_)
#define pcre2_match_data PCRE2_SUFFIX(pcre2_match_data_)
/* Functions: the complete list in alphabetical order */
#define pcre2_callout_enumerate PCRE2_SUFFIX(pcre2_callout_enumerate_)
#define pcre2_code_copy PCRE2_SUFFIX(pcre2_code_copy_)
#define pcre2_code_copy_with_tables PCRE2_SUFFIX(pcre2_code_copy_with_tables_)
#define pcre2_code_free PCRE2_SUFFIX(pcre2_code_free_)
#define pcre2_compile PCRE2_SUFFIX(pcre2_compile_)
#define pcre2_compile_context_copy PCRE2_SUFFIX(pcre2_compile_context_copy_)
#define pcre2_compile_context_create PCRE2_SUFFIX(pcre2_compile_context_create_)
#define pcre2_compile_context_free PCRE2_SUFFIX(pcre2_compile_context_free_)
#define pcre2_config PCRE2_SUFFIX(pcre2_config_)
#define pcre2_convert_context_copy PCRE2_SUFFIX(pcre2_convert_context_copy_)
#define pcre2_convert_context_create PCRE2_SUFFIX(pcre2_convert_context_create_)
#define pcre2_convert_context_free PCRE2_SUFFIX(pcre2_convert_context_free_)
#define pcre2_converted_pattern_free PCRE2_SUFFIX(pcre2_converted_pattern_free_)
#define pcre2_dfa_match PCRE2_SUFFIX(pcre2_dfa_match_)
#define pcre2_general_context_copy PCRE2_SUFFIX(pcre2_general_context_copy_)
#define pcre2_general_context_create PCRE2_SUFFIX(pcre2_general_context_create_)
#define pcre2_general_context_free PCRE2_SUFFIX(pcre2_general_context_free_)
#define pcre2_get_error_message PCRE2_SUFFIX(pcre2_get_error_message_)
#define pcre2_get_mark PCRE2_SUFFIX(pcre2_get_mark_)
#define pcre2_get_match_data_size PCRE2_SUFFIX(pcre2_get_match_data_size_)
#define pcre2_get_ovector_pointer PCRE2_SUFFIX(pcre2_get_ovector_pointer_)
#define pcre2_get_ovector_count PCRE2_SUFFIX(pcre2_get_ovector_count_)
#define pcre2_get_startchar PCRE2_SUFFIX(pcre2_get_startchar_)
#define pcre2_jit_compile PCRE2_SUFFIX(pcre2_jit_compile_)
#define pcre2_jit_match PCRE2_SUFFIX(pcre2_jit_match_)
#define pcre2_jit_free_unused_memory PCRE2_SUFFIX(pcre2_jit_free_unused_memory_)
#define pcre2_jit_stack_assign PCRE2_SUFFIX(pcre2_jit_stack_assign_)
#define pcre2_jit_stack_create PCRE2_SUFFIX(pcre2_jit_stack_create_)
#define pcre2_jit_stack_free PCRE2_SUFFIX(pcre2_jit_stack_free_)
#define pcre2_maketables PCRE2_SUFFIX(pcre2_maketables_)
#define pcre2_maketables_free PCRE2_SUFFIX(pcre2_maketables_free_)
#define pcre2_match PCRE2_SUFFIX(pcre2_match_)
#define pcre2_match_context_copy PCRE2_SUFFIX(pcre2_match_context_copy_)
#define pcre2_match_context_create PCRE2_SUFFIX(pcre2_match_context_create_)
#define pcre2_match_context_free PCRE2_SUFFIX(pcre2_match_context_free_)
#define pcre2_match_data_create PCRE2_SUFFIX(pcre2_match_data_create_)
#define pcre2_match_data_create_from_pattern PCRE2_SUFFIX(pcre2_match_data_create_from_pattern_)
#define pcre2_match_data_free PCRE2_SUFFIX(pcre2_match_data_free_)
#define pcre2_pattern_convert PCRE2_SUFFIX(pcre2_pattern_convert_)
#define pcre2_pattern_info PCRE2_SUFFIX(pcre2_pattern_info_)
#define pcre2_serialize_decode PCRE2_SUFFIX(pcre2_serialize_decode_)
#define pcre2_serialize_encode PCRE2_SUFFIX(pcre2_serialize_encode_)
#define pcre2_serialize_free PCRE2_SUFFIX(pcre2_serialize_free_)
#define pcre2_serialize_get_number_of_codes PCRE2_SUFFIX(pcre2_serialize_get_number_of_codes_)
#define pcre2_set_bsr PCRE2_SUFFIX(pcre2_set_bsr_)
#define pcre2_set_callout PCRE2_SUFFIX(pcre2_set_callout_)
#define pcre2_set_character_tables PCRE2_SUFFIX(pcre2_set_character_tables_)
#define pcre2_set_compile_extra_options PCRE2_SUFFIX(pcre2_set_compile_extra_options_)
#define pcre2_set_compile_recursion_guard PCRE2_SUFFIX(pcre2_set_compile_recursion_guard_)
#define pcre2_set_depth_limit PCRE2_SUFFIX(pcre2_set_depth_limit_)
#define pcre2_set_glob_escape PCRE2_SUFFIX(pcre2_set_glob_escape_)
#define pcre2_set_glob_separator PCRE2_SUFFIX(pcre2_set_glob_separator_)
#define pcre2_set_heap_limit PCRE2_SUFFIX(pcre2_set_heap_limit_)
#define pcre2_set_match_limit PCRE2_SUFFIX(pcre2_set_match_limit_)
#define pcre2_set_max_pattern_length PCRE2_SUFFIX(pcre2_set_max_pattern_length_)
#define pcre2_set_newline PCRE2_SUFFIX(pcre2_set_newline_)
#define pcre2_set_parens_nest_limit PCRE2_SUFFIX(pcre2_set_parens_nest_limit_)
#define pcre2_set_offset_limit PCRE2_SUFFIX(pcre2_set_offset_limit_)
#define pcre2_set_substitute_callout PCRE2_SUFFIX(pcre2_set_substitute_callout_)
#define pcre2_substitute PCRE2_SUFFIX(pcre2_substitute_)
#define pcre2_substring_copy_byname PCRE2_SUFFIX(pcre2_substring_copy_byname_)
#define pcre2_substring_copy_bynumber PCRE2_SUFFIX(pcre2_substring_copy_bynumber_)
#define pcre2_substring_free PCRE2_SUFFIX(pcre2_substring_free_)
#define pcre2_substring_get_byname PCRE2_SUFFIX(pcre2_substring_get_byname_)
#define pcre2_substring_get_bynumber PCRE2_SUFFIX(pcre2_substring_get_bynumber_)
#define pcre2_substring_length_byname PCRE2_SUFFIX(pcre2_substring_length_byname_)
#define pcre2_substring_length_bynumber PCRE2_SUFFIX(pcre2_substring_length_bynumber_)
#define pcre2_substring_list_get PCRE2_SUFFIX(pcre2_substring_list_get_)
#define pcre2_substring_list_free PCRE2_SUFFIX(pcre2_substring_list_free_)
#define pcre2_substring_nametable_scan PCRE2_SUFFIX(pcre2_substring_nametable_scan_)
#define pcre2_substring_number_from_name PCRE2_SUFFIX(pcre2_substring_number_from_name_)
/* Keep this old function name for backwards compatibility */
#define pcre2_set_recursion_limit PCRE2_SUFFIX(pcre2_set_recursion_limit_)
/* Keep this obsolete function for backwards compatibility: it is now a noop. */
#define pcre2_set_recursion_memory_management PCRE2_SUFFIX(pcre2_set_recursion_memory_management_)
/* Now generate all three sets of width-specific structures and function
prototypes. */
#define PCRE2_TYPES_STRUCTURES_AND_FUNCTIONS \
PCRE2_TYPES_LIST \
PCRE2_STRUCTURE_LIST \
PCRE2_GENERAL_INFO_FUNCTIONS \
PCRE2_GENERAL_CONTEXT_FUNCTIONS \
PCRE2_COMPILE_CONTEXT_FUNCTIONS \
PCRE2_CONVERT_CONTEXT_FUNCTIONS \
PCRE2_CONVERT_FUNCTIONS \
PCRE2_MATCH_CONTEXT_FUNCTIONS \
PCRE2_COMPILE_FUNCTIONS \
PCRE2_PATTERN_INFO_FUNCTIONS \
PCRE2_MATCH_FUNCTIONS \
PCRE2_SUBSTRING_FUNCTIONS \
PCRE2_SERIALIZE_FUNCTIONS \
PCRE2_SUBSTITUTE_FUNCTION \
PCRE2_JIT_FUNCTIONS \
PCRE2_OTHER_FUNCTIONS
#define PCRE2_LOCAL_WIDTH 8
PCRE2_TYPES_STRUCTURES_AND_FUNCTIONS
#undef PCRE2_LOCAL_WIDTH
#define PCRE2_LOCAL_WIDTH 16
PCRE2_TYPES_STRUCTURES_AND_FUNCTIONS
#undef PCRE2_LOCAL_WIDTH
#define PCRE2_LOCAL_WIDTH 32
PCRE2_TYPES_STRUCTURES_AND_FUNCTIONS
#undef PCRE2_LOCAL_WIDTH
/* Undefine the list macros; they are no longer needed. */
#undef PCRE2_TYPES_LIST
#undef PCRE2_STRUCTURE_LIST
#undef PCRE2_GENERAL_INFO_FUNCTIONS
#undef PCRE2_GENERAL_CONTEXT_FUNCTIONS
#undef PCRE2_COMPILE_CONTEXT_FUNCTIONS
#undef PCRE2_CONVERT_CONTEXT_FUNCTIONS
#undef PCRE2_MATCH_CONTEXT_FUNCTIONS
#undef PCRE2_COMPILE_FUNCTIONS
#undef PCRE2_PATTERN_INFO_FUNCTIONS
#undef PCRE2_MATCH_FUNCTIONS
#undef PCRE2_SUBSTRING_FUNCTIONS
#undef PCRE2_SERIALIZE_FUNCTIONS
#undef PCRE2_SUBSTITUTE_FUNCTION
#undef PCRE2_JIT_FUNCTIONS
#undef PCRE2_OTHER_FUNCTIONS
#undef PCRE2_TYPES_STRUCTURES_AND_FUNCTIONS
/* PCRE2_CODE_UNIT_WIDTH must be defined. If it is 8, 16, or 32, redefine
PCRE2_SUFFIX to use it. If it is 0, undefine the other macros and make
PCRE2_SUFFIX a no-op. Otherwise, generate an error. */
#undef PCRE2_SUFFIX
#ifndef PCRE2_CODE_UNIT_WIDTH
#error PCRE2_CODE_UNIT_WIDTH must be defined before including pcre2.h.
#error Use 8, 16, or 32; or 0 for a multi-width application.
#else /* PCRE2_CODE_UNIT_WIDTH is defined */
#if PCRE2_CODE_UNIT_WIDTH == 8 || \
PCRE2_CODE_UNIT_WIDTH == 16 || \
PCRE2_CODE_UNIT_WIDTH == 32
#define PCRE2_SUFFIX(a) PCRE2_GLUE(a, PCRE2_CODE_UNIT_WIDTH)
#elif PCRE2_CODE_UNIT_WIDTH == 0
#undef PCRE2_JOIN
#undef PCRE2_GLUE
#define PCRE2_SUFFIX(a) a
#else
#error PCRE2_CODE_UNIT_WIDTH must be 0, 8, 16, or 32.
#endif
#endif /* PCRE2_CODE_UNIT_WIDTH is defined */
#ifdef __cplusplus
} /* extern "C" */
#endif
#endif /* PCRE2_H_IDEMPOTENT_GUARD */
/* End of pcre2.h */

1365
Kha/Backends/Kore-hxcpp/khacpp/project/thirdparty/pcre2-10.42-16/src/pcre2_auto_possess.c vendored Normal file
View File

File diff suppressed because it is too large Load Diff

202
Kha/Backends/Kore-hxcpp/khacpp/project/thirdparty/pcre2-10.42-16/src/pcre2_chartables.c vendored Normal file
View File

@ -0,0 +1,202 @@
/*************************************************
* Perl-Compatible Regular Expressions *
*************************************************/
/* This file was automatically written by the pcre2_dftables auxiliary
program. It contains character tables that are used when no external
tables are passed to PCRE2 by the application that calls it. The tables
are used only for characters whose code values are less than 256. */
/* This set of tables was written in the C locale. */
/* The pcre2_ftables program (which is distributed with PCRE2) can be used
to build alternative versions of this file. This is necessary if you are
running in an EBCDIC environment, or if you want to default to a different
encoding, for example ISO-8859-1. When pcre2_dftables is run, it creates
these tables in the "C" locale by default. This happens automatically if
PCRE2 is configured with --enable-rebuild-chartables. However, you can run
pcre2_dftables manually with the -L option to build tables using the LC_ALL
locale. */
/* The following #include is present because without it gcc 4.x may remove
the array definition from the final binary if PCRE2 is built into a static
library and dead code stripping is activated. This leads to link errors.
Pulling in the header ensures that the array gets flagged as "someone
outside this compilation unit might reference this" and so it will always
be supplied to the linker. */
#ifdef HAVE_CONFIG_H
#include "config.h"
#endif
#include "pcre2_internal.h"
const uint8_t PRIV(default_tables)[] = {
/* This table is a lower casing table. */
0, 1, 2, 3, 4, 5, 6, 7,
8, 9, 10, 11, 12, 13, 14, 15,
16, 17, 18, 19, 20, 21, 22, 23,
24, 25, 26, 27, 28, 29, 30, 31,
32, 33, 34, 35, 36, 37, 38, 39,
40, 41, 42, 43, 44, 45, 46, 47,
48, 49, 50, 51, 52, 53, 54, 55,
56, 57, 58, 59, 60, 61, 62, 63,
64, 97, 98, 99,100,101,102,103,
104,105,106,107,108,109,110,111,
112,113,114,115,116,117,118,119,
120,121,122, 91, 92, 93, 94, 95,
96, 97, 98, 99,100,101,102,103,
104,105,106,107,108,109,110,111,
112,113,114,115,116,117,118,119,
120,121,122,123,124,125,126,127,
128,129,130,131,132,133,134,135,
136,137,138,139,140,141,142,143,
144,145,146,147,148,149,150,151,
152,153,154,155,156,157,158,159,
160,161,162,163,164,165,166,167,
168,169,170,171,172,173,174,175,
176,177,178,179,180,181,182,183,
184,185,186,187,188,189,190,191,
192,193,194,195,196,197,198,199,
200,201,202,203,204,205,206,207,
208,209,210,211,212,213,214,215,
216,217,218,219,220,221,222,223,
224,225,226,227,228,229,230,231,
232,233,234,235,236,237,238,239,
240,241,242,243,244,245,246,247,
248,249,250,251,252,253,254,255,
/* This table is a case flipping table. */
0, 1, 2, 3, 4, 5, 6, 7,
8, 9, 10, 11, 12, 13, 14, 15,
16, 17, 18, 19, 20, 21, 22, 23,
24, 25, 26, 27, 28, 29, 30, 31,
32, 33, 34, 35, 36, 37, 38, 39,
40, 41, 42, 43, 44, 45, 46, 47,
48, 49, 50, 51, 52, 53, 54, 55,
56, 57, 58, 59, 60, 61, 62, 63,
64, 97, 98, 99,100,101,102,103,
104,105,106,107,108,109,110,111,
112,113,114,115,116,117,118,119,
120,121,122, 91, 92, 93, 94, 95,
96, 65, 66, 67, 68, 69, 70, 71,
72, 73, 74, 75, 76, 77, 78, 79,
80, 81, 82, 83, 84, 85, 86, 87,
88, 89, 90,123,124,125,126,127,
128,129,130,131,132,133,134,135,
136,137,138,139,140,141,142,143,
144,145,146,147,148,149,150,151,
152,153,154,155,156,157,158,159,
160,161,162,163,164,165,166,167,
168,169,170,171,172,173,174,175,
176,177,178,179,180,181,182,183,
184,185,186,187,188,189,190,191,
192,193,194,195,196,197,198,199,
200,201,202,203,204,205,206,207,
208,209,210,211,212,213,214,215,
216,217,218,219,220,221,222,223,
224,225,226,227,228,229,230,231,
232,233,234,235,236,237,238,239,
240,241,242,243,244,245,246,247,
248,249,250,251,252,253,254,255,
/* This table contains bit maps for various character classes. Each map is 32
bytes long and the bits run from the least significant end of each byte. The
classes that have their own maps are: space, xdigit, digit, upper, lower, word,
graph, print, punct, and cntrl. Other classes are built from combinations. */
0x00,0x3e,0x00,0x00,0x01,0x00,0x00,0x00, /* space */
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0xff,0x03, /* xdigit */
0x7e,0x00,0x00,0x00,0x7e,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0xff,0x03, /* digit */
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* upper */
0xfe,0xff,0xff,0x07,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* lower */
0x00,0x00,0x00,0x00,0xfe,0xff,0xff,0x07,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0xff,0x03, /* word */
0xfe,0xff,0xff,0x87,0xfe,0xff,0xff,0x07,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0xfe,0xff,0xff,0xff, /* graph */
0xff,0xff,0xff,0xff,0xff,0xff,0xff,0x7f,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0xff,0xff,0xff,0xff, /* print */
0xff,0xff,0xff,0xff,0xff,0xff,0xff,0x7f,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0xfe,0xff,0x00,0xfc, /* punct */
0x01,0x00,0x00,0xf8,0x01,0x00,0x00,0x78,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0xff,0xff,0xff,0xff,0x00,0x00,0x00,0x00, /* cntrl */
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x80,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
/* This table identifies various classes of character by individual bits:
0x01 white space character
0x02 letter
0x04 lower case letter
0x08 decimal digit
0x10 alphanumeric or '_'
*/
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 0- 7 */
0x00,0x01,0x01,0x01,0x01,0x01,0x00,0x00, /* 8- 15 */
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 16- 23 */
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 24- 31 */
0x01,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* - ' */
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* ( - / */
0x18,0x18,0x18,0x18,0x18,0x18,0x18,0x18, /* 0 - 7 */
0x18,0x18,0x00,0x00,0x00,0x00,0x00,0x00, /* 8 - ? */
0x00,0x12,0x12,0x12,0x12,0x12,0x12,0x12, /* @ - G */
0x12,0x12,0x12,0x12,0x12,0x12,0x12,0x12, /* H - O */
0x12,0x12,0x12,0x12,0x12,0x12,0x12,0x12, /* P - W */
0x12,0x12,0x12,0x00,0x00,0x00,0x00,0x10, /* X - _ */
0x00,0x16,0x16,0x16,0x16,0x16,0x16,0x16, /* ` - g */
0x16,0x16,0x16,0x16,0x16,0x16,0x16,0x16, /* h - o */
0x16,0x16,0x16,0x16,0x16,0x16,0x16,0x16, /* p - w */
0x16,0x16,0x16,0x00,0x00,0x00,0x00,0x00, /* x -127 */
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 128-135 */
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 136-143 */
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 144-151 */
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 152-159 */
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 160-167 */
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 168-175 */
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 176-183 */
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 184-191 */
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 192-199 */
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 200-207 */
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 208-215 */
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 216-223 */
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 224-231 */
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 232-239 */
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 240-247 */
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00};/* 248-255 */
/* End of pcre2_chartables.c */

10631
Kha/Backends/Kore-hxcpp/khacpp/project/thirdparty/pcre2-10.42-16/src/pcre2_compile.c vendored Normal file
View File

File diff suppressed because it is too large Load Diff

252
Kha/Backends/Kore-hxcpp/khacpp/project/thirdparty/pcre2-10.42-16/src/pcre2_config.c vendored Normal file
View File

@ -0,0 +1,252 @@
/*************************************************
* Perl-Compatible Regular Expressions *
*************************************************/
/* PCRE is a library of functions to support regular expressions whose syntax
and semantics are as close as possible to those of the Perl 5 language.
Written by Philip Hazel
Original API code Copyright (c) 1997-2012 University of Cambridge
New API code Copyright (c) 2016-2020 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
modification, are permitted provided that the following conditions are met:
* Redistributions of source code must retain the above copyright notice,
this list of conditions and the following disclaimer.
* Redistributions in binary form must reproduce the above copyright
notice, this list of conditions and the following disclaimer in the
documentation and/or other materials provided with the distribution.
* Neither the name of the University of Cambridge nor the names of its
contributors may be used to endorse or promote products derived from
this software without specific prior written permission.
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
POSSIBILITY OF SUCH DAMAGE.
-----------------------------------------------------------------------------
*/
#ifdef HAVE_CONFIG_H
#include "config.h"
#endif
/* Save the configured link size, which is in bytes. In 16-bit and 32-bit modes
its value gets changed by pcre2_intmodedep.h (included by pcre2_internal.h) to
be in code units. */
static int configured_link_size = LINK_SIZE;
#include "pcre2_internal.h"
/* These macros are the standard way of turning unquoted text into C strings.
They allow macros like PCRE2_MAJOR to be defined without quotes, which is
convenient for user programs that want to test their values. */
#define STRING(a) # a
#define XSTRING(s) STRING(s)
/*************************************************
* Return info about what features are configured *
*************************************************/
/* If where is NULL, the length of memory required is returned.
Arguments:
what what information is required
where where to put the information
Returns: 0 if a numerical value is returned
>= 0 if a string value
PCRE2_ERROR_BADOPTION if "where" not recognized
or JIT target requested when JIT not enabled
*/
PCRE2_EXP_DEFN int PCRE2_CALL_CONVENTION
pcre2_config(uint32_t what, void *where)
{
if (where == NULL) /* Requests a length */
{
switch(what)
{
default:
return PCRE2_ERROR_BADOPTION;
case PCRE2_CONFIG_BSR:
case PCRE2_CONFIG_COMPILED_WIDTHS:
case PCRE2_CONFIG_DEPTHLIMIT:
case PCRE2_CONFIG_HEAPLIMIT:
case PCRE2_CONFIG_JIT:
case PCRE2_CONFIG_LINKSIZE:
case PCRE2_CONFIG_MATCHLIMIT:
case PCRE2_CONFIG_NEVER_BACKSLASH_C:
case PCRE2_CONFIG_NEWLINE:
case PCRE2_CONFIG_PARENSLIMIT:
case PCRE2_CONFIG_STACKRECURSE: /* Obsolete */
case PCRE2_CONFIG_TABLES_LENGTH:
case PCRE2_CONFIG_UNICODE:
return sizeof(uint32_t);
/* These are handled below */
case PCRE2_CONFIG_JITTARGET:
case PCRE2_CONFIG_UNICODE_VERSION:
case PCRE2_CONFIG_VERSION:
break;
}
}
switch (what)
{
default:
return PCRE2_ERROR_BADOPTION;
case PCRE2_CONFIG_BSR:
#ifdef BSR_ANYCRLF
*((uint32_t *)where) = PCRE2_BSR_ANYCRLF;
#else
*((uint32_t *)where) = PCRE2_BSR_UNICODE;
#endif
break;
case PCRE2_CONFIG_COMPILED_WIDTHS:
*((uint32_t *)where) = 0
#ifdef SUPPORT_PCRE2_8
+ 1
#endif
#ifdef SUPPORT_PCRE2_16
+ 2
#endif
#ifdef SUPPORT_PCRE2_32
+ 4
#endif
;
break;
case PCRE2_CONFIG_DEPTHLIMIT:
*((uint32_t *)where) = MATCH_LIMIT_DEPTH;
break;
case PCRE2_CONFIG_HEAPLIMIT:
*((uint32_t *)where) = HEAP_LIMIT;
break;
case PCRE2_CONFIG_JIT:
#ifdef SUPPORT_JIT
*((uint32_t *)where) = 1;
#else
*((uint32_t *)where) = 0;
#endif
break;
case PCRE2_CONFIG_JITTARGET:
#ifdef SUPPORT_JIT
{
const char *v = PRIV(jit_get_target)();
return (int)(1 + ((where == NULL)?
strlen(v) : PRIV(strcpy_c8)((PCRE2_UCHAR *)where, v)));
}
#else
return PCRE2_ERROR_BADOPTION;
#endif
case PCRE2_CONFIG_LINKSIZE:
*((uint32_t *)where) = (uint32_t)configured_link_size;
break;
case PCRE2_CONFIG_MATCHLIMIT:
*((uint32_t *)where) = MATCH_LIMIT;
break;
case PCRE2_CONFIG_NEWLINE:
*((uint32_t *)where) = NEWLINE_DEFAULT;
break;
case PCRE2_CONFIG_NEVER_BACKSLASH_C:
#ifdef NEVER_BACKSLASH_C
*((uint32_t *)where) = 1;
#else
*((uint32_t *)where) = 0;
#endif
break;
case PCRE2_CONFIG_PARENSLIMIT:
*((uint32_t *)where) = PARENS_NEST_LIMIT;
break;
/* This is now obsolete. The stack is no longer used via recursion for
handling backtracking in pcre2_match(). */
case PCRE2_CONFIG_STACKRECURSE:
*((uint32_t *)where) = 0;
break;
case PCRE2_CONFIG_TABLES_LENGTH:
*((uint32_t *)where) = TABLES_LENGTH;
break;
case PCRE2_CONFIG_UNICODE_VERSION:
{
#if defined SUPPORT_UNICODE
const char *v = PRIV(unicode_version);
#else
const char *v = "Unicode not supported";
#endif
return (int)(1 + ((where == NULL)?
strlen(v) : PRIV(strcpy_c8)((PCRE2_UCHAR *)where, v)));
}
break;
case PCRE2_CONFIG_UNICODE:
#if defined SUPPORT_UNICODE
*((uint32_t *)where) = 1;
#else
*((uint32_t *)where) = 0;
#endif
break;
/* The hackery in setting "v" below is to cope with the case when
PCRE2_PRERELEASE is set to an empty string (which it is for real releases).
If the second alternative is used in this case, it does not leave a space
before the date. On the other hand, if all four macros are put into a single
XSTRING when PCRE2_PRERELEASE is not empty, an unwanted space is inserted.
There are problems using an "obvious" approach like this:
XSTRING(PCRE2_MAJOR) "." XSTRING(PCRE_MINOR)
XSTRING(PCRE2_PRERELEASE) " " XSTRING(PCRE_DATE)
because, when PCRE2_PRERELEASE is empty, this leads to an attempted expansion
of STRING(). The C standard states: "If (before argument substitution) any
argument consists of no preprocessing tokens, the behavior is undefined." It
turns out the gcc treats this case as a single empty string - which is what
we really want - but Visual C grumbles about the lack of an argument for the
macro. Unfortunately, both are within their rights. As there seems to be no
way to test for a macro's value being empty at compile time, we have to
resort to a runtime test. */
case PCRE2_CONFIG_VERSION:
{
const char *v = (XSTRING(Z PCRE2_PRERELEASE)[1] == 0)?
XSTRING(PCRE2_MAJOR.PCRE2_MINOR PCRE2_DATE) :
XSTRING(PCRE2_MAJOR.PCRE2_MINOR) XSTRING(PCRE2_PRERELEASE PCRE2_DATE);
return (int)(1 + ((where == NULL)?
strlen(v) : PRIV(strcpy_c8)((PCRE2_UCHAR *)where, v)));
}
}
return 0;
}
/* End of pcre2_config.c */

494
Kha/Backends/Kore-hxcpp/khacpp/project/thirdparty/pcre2-10.42-16/src/pcre2_context.c vendored Normal file
View File

@ -0,0 +1,494 @@
/*************************************************
* Perl-Compatible Regular Expressions *
*************************************************/
/* PCRE is a library of functions to support regular expressions whose syntax
and semantics are as close as possible to those of the Perl 5 language.
Written by Philip Hazel
Original API code Copyright (c) 1997-2012 University of Cambridge
New API code Copyright (c) 2016-2022 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
modification, are permitted provided that the following conditions are met:
* Redistributions of source code must retain the above copyright notice,
this list of conditions and the following disclaimer.
* Redistributions in binary form must reproduce the above copyright
notice, this list of conditions and the following disclaimer in the
documentation and/or other materials provided with the distribution.
* Neither the name of the University of Cambridge nor the names of its
contributors may be used to endorse or promote products derived from
this software without specific prior written permission.
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
POSSIBILITY OF SUCH DAMAGE.
-----------------------------------------------------------------------------
*/
#ifdef HAVE_CONFIG_H
#include "config.h"
#endif
#include "pcre2_internal.h"
/*************************************************
* Default malloc/free functions *
*************************************************/
/* Ignore the "user data" argument in each case. */
static void *default_malloc(size_t size, void *data)
{
(void)data;
return malloc(size);
}
static void default_free(void *block, void *data)
{
(void)data;
free(block);
}
/*************************************************
* Get a block and save memory control *
*************************************************/
/* This internal function is called to get a block of memory in which the
memory control data is to be stored at the start for future use.
Arguments:
size amount of memory required
memctl pointer to a memctl block or NULL
Returns: pointer to memory or NULL on failure
*/
extern void *
PRIV(memctl_malloc)(size_t size, pcre2_memctl *memctl)
{
pcre2_memctl *newmemctl;
void *yield = (memctl == NULL)? malloc(size) :
memctl->malloc(size, memctl->memory_data);
if (yield == NULL) return NULL;
newmemctl = (pcre2_memctl *)yield;
if (memctl == NULL)
{
newmemctl->malloc = default_malloc;
newmemctl->free = default_free;
newmemctl->memory_data = NULL;
}
else *newmemctl = *memctl;
return yield;
}
/*************************************************
* Create and initialize contexts *
*************************************************/
/* Initializing for compile and match contexts is done in separate, private
functions so that these can be called from functions such as pcre2_compile()
when an external context is not supplied. The initializing functions have an
option to set up default memory management. */
PCRE2_EXP_DEFN pcre2_general_context * PCRE2_CALL_CONVENTION
pcre2_general_context_create(void *(*private_malloc)(size_t, void *),
void (*private_free)(void *, void *), void *memory_data)
{
pcre2_general_context *gcontext;
if (private_malloc == NULL) private_malloc = default_malloc;
if (private_free == NULL) private_free = default_free;
gcontext = private_malloc(sizeof(pcre2_real_general_context), memory_data);
if (gcontext == NULL) return NULL;
gcontext->memctl.malloc = private_malloc;
gcontext->memctl.free = private_free;
gcontext->memctl.memory_data = memory_data;
return gcontext;
}
/* A default compile context is set up to save having to initialize at run time
when no context is supplied to the compile function. */
const pcre2_compile_context PRIV(default_compile_context) = {
{ default_malloc, default_free, NULL }, /* Default memory handling */
NULL, /* Stack guard */
NULL, /* Stack guard data */
PRIV(default_tables), /* Character tables */
PCRE2_UNSET, /* Max pattern length */
BSR_DEFAULT, /* Backslash R default */
NEWLINE_DEFAULT, /* Newline convention */
PARENS_NEST_LIMIT, /* As it says */
0 }; /* Extra options */
/* The create function copies the default into the new memory, but must
override the default memory handling functions if a gcontext was provided. */
PCRE2_EXP_DEFN pcre2_compile_context * PCRE2_CALL_CONVENTION
pcre2_compile_context_create(pcre2_general_context *gcontext)
{
pcre2_compile_context *ccontext = PRIV(memctl_malloc)(
sizeof(pcre2_real_compile_context), (pcre2_memctl *)gcontext);
if (ccontext == NULL) return NULL;
*ccontext = PRIV(default_compile_context);
if (gcontext != NULL)
*((pcre2_memctl *)ccontext) = *((pcre2_memctl *)gcontext);
return ccontext;
}
/* A default match context is set up to save having to initialize at run time
when no context is supplied to a match function. */
const pcre2_match_context PRIV(default_match_context) = {
{ default_malloc, default_free, NULL },
#ifdef SUPPORT_JIT
NULL, /* JIT callback */
NULL, /* JIT callback data */
#endif
NULL, /* Callout function */
NULL, /* Callout data */
NULL, /* Substitute callout function */
NULL, /* Substitute callout data */
PCRE2_UNSET, /* Offset limit */
HEAP_LIMIT,
MATCH_LIMIT,
MATCH_LIMIT_DEPTH };
/* The create function copies the default into the new memory, but must
override the default memory handling functions if a gcontext was provided. */
PCRE2_EXP_DEFN pcre2_match_context * PCRE2_CALL_CONVENTION
pcre2_match_context_create(pcre2_general_context *gcontext)
{
pcre2_match_context *mcontext = PRIV(memctl_malloc)(
sizeof(pcre2_real_match_context), (pcre2_memctl *)gcontext);
if (mcontext == NULL) return NULL;
*mcontext = PRIV(default_match_context);
if (gcontext != NULL)
*((pcre2_memctl *)mcontext) = *((pcre2_memctl *)gcontext);
return mcontext;
}
/* A default convert context is set up to save having to initialize at run time
when no context is supplied to the convert function. */
const pcre2_convert_context PRIV(default_convert_context) = {
{ default_malloc, default_free, NULL }, /* Default memory handling */
#ifdef _WIN32
CHAR_BACKSLASH, /* Default path separator */
CHAR_GRAVE_ACCENT /* Default escape character */
#else /* Not Windows */
CHAR_SLASH, /* Default path separator */
CHAR_BACKSLASH /* Default escape character */
#endif
};
/* The create function copies the default into the new memory, but must
override the default memory handling functions if a gcontext was provided. */
PCRE2_EXP_DEFN pcre2_convert_context * PCRE2_CALL_CONVENTION
pcre2_convert_context_create(pcre2_general_context *gcontext)
{
pcre2_convert_context *ccontext = PRIV(memctl_malloc)(
sizeof(pcre2_real_convert_context), (pcre2_memctl *)gcontext);
if (ccontext == NULL) return NULL;
*ccontext = PRIV(default_convert_context);
if (gcontext != NULL)
*((pcre2_memctl *)ccontext) = *((pcre2_memctl *)gcontext);
return ccontext;
}
/*************************************************
* Context copy functions *
*************************************************/
PCRE2_EXP_DEFN pcre2_general_context * PCRE2_CALL_CONVENTION
pcre2_general_context_copy(pcre2_general_context *gcontext)
{
pcre2_general_context *new =
gcontext->memctl.malloc(sizeof(pcre2_real_general_context),
gcontext->memctl.memory_data);
if (new == NULL) return NULL;
memcpy(new, gcontext, sizeof(pcre2_real_general_context));
return new;
}
PCRE2_EXP_DEFN pcre2_compile_context * PCRE2_CALL_CONVENTION
pcre2_compile_context_copy(pcre2_compile_context *ccontext)
{
pcre2_compile_context *new =
ccontext->memctl.malloc(sizeof(pcre2_real_compile_context),
ccontext->memctl.memory_data);
if (new == NULL) return NULL;
memcpy(new, ccontext, sizeof(pcre2_real_compile_context));
return new;
}
PCRE2_EXP_DEFN pcre2_match_context * PCRE2_CALL_CONVENTION
pcre2_match_context_copy(pcre2_match_context *mcontext)
{
pcre2_match_context *new =
mcontext->memctl.malloc(sizeof(pcre2_real_match_context),
mcontext->memctl.memory_data);
if (new == NULL) return NULL;
memcpy(new, mcontext, sizeof(pcre2_real_match_context));
return new;
}
PCRE2_EXP_DEFN pcre2_convert_context * PCRE2_CALL_CONVENTION
pcre2_convert_context_copy(pcre2_convert_context *ccontext)
{
pcre2_convert_context *new =
ccontext->memctl.malloc(sizeof(pcre2_real_convert_context),
ccontext->memctl.memory_data);
if (new == NULL) return NULL;
memcpy(new, ccontext, sizeof(pcre2_real_convert_context));
return new;
}
/*************************************************
* Context free functions *
*************************************************/
PCRE2_EXP_DEFN void PCRE2_CALL_CONVENTION
pcre2_general_context_free(pcre2_general_context *gcontext)
{
if (gcontext != NULL)
gcontext->memctl.free(gcontext, gcontext->memctl.memory_data);
}
PCRE2_EXP_DEFN void PCRE2_CALL_CONVENTION
pcre2_compile_context_free(pcre2_compile_context *ccontext)
{
if (ccontext != NULL)
ccontext->memctl.free(ccontext, ccontext->memctl.memory_data);
}
PCRE2_EXP_DEFN void PCRE2_CALL_CONVENTION
pcre2_match_context_free(pcre2_match_context *mcontext)
{
if (mcontext != NULL)
mcontext->memctl.free(mcontext, mcontext->memctl.memory_data);
}
PCRE2_EXP_DEFN void PCRE2_CALL_CONVENTION
pcre2_convert_context_free(pcre2_convert_context *ccontext)
{
if (ccontext != NULL)
ccontext->memctl.free(ccontext, ccontext->memctl.memory_data);
}
/*************************************************
* Set values in contexts *
*************************************************/
/* All these functions return 0 for success or PCRE2_ERROR_BADDATA if invalid
data is given. Only some of the functions are able to test the validity of the
data. */
/* ------------ Compile context ------------ */
PCRE2_EXP_DEFN int PCRE2_CALL_CONVENTION
pcre2_set_character_tables(pcre2_compile_context *ccontext,
const uint8_t *tables)
{
ccontext->tables = tables;
return 0;
}
PCRE2_EXP_DEFN int PCRE2_CALL_CONVENTION
pcre2_set_bsr(pcre2_compile_context *ccontext, uint32_t value)
{
switch(value)
{
case PCRE2_BSR_ANYCRLF:
case PCRE2_BSR_UNICODE:
ccontext->bsr_convention = value;
return 0;
default:
return PCRE2_ERROR_BADDATA;
}
}
PCRE2_EXP_DEFN int PCRE2_CALL_CONVENTION
pcre2_set_max_pattern_length(pcre2_compile_context *ccontext, PCRE2_SIZE length)
{
ccontext->max_pattern_length = length;
return 0;
}
PCRE2_EXP_DEFN int PCRE2_CALL_CONVENTION
pcre2_set_newline(pcre2_compile_context *ccontext, uint32_t newline)
{
switch(newline)
{
case PCRE2_NEWLINE_CR:
case PCRE2_NEWLINE_LF:
case PCRE2_NEWLINE_CRLF:
case PCRE2_NEWLINE_ANY:
case PCRE2_NEWLINE_ANYCRLF:
case PCRE2_NEWLINE_NUL:
ccontext->newline_convention = newline;
return 0;
default:
return PCRE2_ERROR_BADDATA;
}
}
PCRE2_EXP_DEFN int PCRE2_CALL_CONVENTION
pcre2_set_parens_nest_limit(pcre2_compile_context *ccontext, uint32_t limit)
{
ccontext->parens_nest_limit = limit;
return 0;
}
PCRE2_EXP_DEFN int PCRE2_CALL_CONVENTION
pcre2_set_compile_extra_options(pcre2_compile_context *ccontext, uint32_t options)
{
ccontext->extra_options = options;
return 0;
}
PCRE2_EXP_DEFN int PCRE2_CALL_CONVENTION
pcre2_set_compile_recursion_guard(pcre2_compile_context *ccontext,
int (*guard)(uint32_t, void *), void *user_data)
{
ccontext->stack_guard = guard;
ccontext->stack_guard_data = user_data;
return 0;
}
/* ------------ Match context ------------ */
PCRE2_EXP_DEFN int PCRE2_CALL_CONVENTION
pcre2_set_callout(pcre2_match_context *mcontext,
int (*callout)(pcre2_callout_block *, void *), void *callout_data)
{
mcontext->callout = callout;
mcontext->callout_data = callout_data;
return 0;
}
PCRE2_EXP_DEFN int PCRE2_CALL_CONVENTION
pcre2_set_substitute_callout(pcre2_match_context *mcontext,
int (*substitute_callout)(pcre2_substitute_callout_block *, void *),
void *substitute_callout_data)
{
mcontext->substitute_callout = substitute_callout;
mcontext->substitute_callout_data = substitute_callout_data;
return 0;
}
PCRE2_EXP_DEFN int PCRE2_CALL_CONVENTION
pcre2_set_heap_limit(pcre2_match_context *mcontext, uint32_t limit)
{
mcontext->heap_limit = limit;
return 0;
}
PCRE2_EXP_DEFN int PCRE2_CALL_CONVENTION
pcre2_set_match_limit(pcre2_match_context *mcontext, uint32_t limit)
{
mcontext->match_limit = limit;
return 0;
}
PCRE2_EXP_DEFN int PCRE2_CALL_CONVENTION
pcre2_set_depth_limit(pcre2_match_context *mcontext, uint32_t limit)
{
mcontext->depth_limit = limit;
return 0;
}
PCRE2_EXP_DEFN int PCRE2_CALL_CONVENTION
pcre2_set_offset_limit(pcre2_match_context *mcontext, PCRE2_SIZE limit)
{
mcontext->offset_limit = limit;
return 0;
}
/* These functions became obsolete at release 10.30. The first is kept as a
synonym for backwards compatibility. The second now does nothing. Exclude both
from coverage reports. */
/* LCOV_EXCL_START */
PCRE2_EXP_DEFN int PCRE2_CALL_CONVENTION
pcre2_set_recursion_limit(pcre2_match_context *mcontext, uint32_t limit)
{
return pcre2_set_depth_limit(mcontext, limit);
}
PCRE2_EXP_DEFN int PCRE2_CALL_CONVENTION
pcre2_set_recursion_memory_management(pcre2_match_context *mcontext,
void *(*mymalloc)(size_t, void *), void (*myfree)(void *, void *),
void *mydata)
{
(void)mcontext;
(void)mymalloc;
(void)myfree;
(void)mydata;
return 0;
}
/* LCOV_EXCL_STOP */
/* ------------ Convert context ------------ */
PCRE2_EXP_DEFN int PCRE2_CALL_CONVENTION
pcre2_set_glob_separator(pcre2_convert_context *ccontext, uint32_t separator)
{
if (separator != CHAR_SLASH && separator != CHAR_BACKSLASH &&
separator != CHAR_DOT) return PCRE2_ERROR_BADDATA;
ccontext->glob_separator = separator;
return 0;
}
PCRE2_EXP_DEFN int PCRE2_CALL_CONVENTION
pcre2_set_glob_escape(pcre2_convert_context *ccontext, uint32_t escape)
{
if (escape > 255 || (escape != 0 && !ispunct(escape)))
return PCRE2_ERROR_BADDATA;
ccontext->glob_escape = escape;
return 0;
}
/* End of pcre2_context.c */

1181
Kha/Backends/Kore-hxcpp/khacpp/project/thirdparty/pcre2-10.42-16/src/pcre2_convert.c vendored Normal file
View File

File diff suppressed because it is too large Load Diff

4069
Kha/Backends/Kore-hxcpp/khacpp/project/thirdparty/pcre2-10.42-16/src/pcre2_dfa_match.c vendored Normal file
View File

File diff suppressed because it is too large Load Diff

303
Kha/Backends/Kore-hxcpp/khacpp/project/thirdparty/pcre2-10.42-16/src/pcre2_dftables.c vendored Normal file
View File

@ -0,0 +1,303 @@
/*************************************************
* Perl-Compatible Regular Expressions *
*************************************************/
/* PCRE is a library of functions to support regular expressions whose syntax
and semantics are as close as possible to those of the Perl 5 language.
Written by Philip Hazel
Original API code Copyright (c) 1997-2012 University of Cambridge
New API code Copyright (c) 2016-2020 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
modification, are permitted provided that the following conditions are met:
* Redistributions of source code must retain the above copyright notice,
this list of conditions and the following disclaimer.
* Redistributions in binary form must reproduce the above copyright
notice, this list of conditions and the following disclaimer in the
documentation and/or other materials provided with the distribution.
* Neither the name of the University of Cambridge nor the names of its
contributors may be used to endorse or promote products derived from
this software without specific prior written permission.
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
POSSIBILITY OF SUCH DAMAGE.
-----------------------------------------------------------------------------
*/
/* This is a freestanding support program to generate a file containing
character tables for PCRE2. The tables are built using the pcre2_maketables()
function, which is part of the PCRE2 API. By default, the system's "C" locale
is used rather than what the building user happens to have set, but the -L
option can be used to select the current locale from the LC_ALL environment
variable. By default, the tables are written in source form, but if -b is
given, they are written in binary. */
#ifdef HAVE_CONFIG_H
#include "config.h"
#endif
#include <ctype.h>
#include <stdio.h>
#include <string.h>
#include <locale.h>
#define PCRE2_CODE_UNIT_WIDTH 0 /* Must be set, but not relevant here */
#include "pcre2_internal.h"
#define PCRE2_DFTABLES /* pcre2_maketables.c notices this */
#include "pcre2_maketables.c"
static const char *classlist[] =
{
"space", "xdigit", "digit", "upper", "lower",
"word", "graph", "print", "punct", "cntrl"
};
/*************************************************
* Usage *
*************************************************/
static void
usage(void)
{
(void)fprintf(stderr,
"Usage: pcre2_dftables [options] <output file>\n"
" -b Write output in binary (default is source code)\n"
" -L Use locale from LC_ALL (default is \"C\" locale)\n"
);
}
/*************************************************
* Entry point *
*************************************************/
int main(int argc, char **argv)
{
FILE *f;
int i;
int nclass = 0;
BOOL binary = FALSE;
char *env = (char *)"C";
const unsigned char *tables;
const unsigned char *base_of_tables;
/* Process options */
for (i = 1; i < argc; i++)
{
char *arg = argv[i];
if (*arg != '-') break;
if (strcmp(arg, "-help") == 0 || strcmp(arg, "--help") == 0)
{
usage();
return 0;
}
else if (strcmp(arg, "-L") == 0)
{
if (setlocale(LC_ALL, "") == NULL)
{
(void)fprintf(stderr, "pcre2_dftables: setlocale() failed\n");
return 1;
}
env = getenv("LC_ALL");
}
else if (strcmp(arg, "-b") == 0)
binary = TRUE;
else
{
(void)fprintf(stderr, "pcre2_dftables: unrecognized option %s\n", arg);
return 1;
}
}
if (i != argc - 1)
{
(void)fprintf(stderr, "pcre2_dftables: one filename argument is required\n");
return 1;
}
/* Make the tables */
tables = maketables();
base_of_tables = tables;
f = fopen(argv[i], "wb");
if (f == NULL)
{
fprintf(stderr, "pcre2_dftables: failed to open %s for writing\n", argv[1]);
return 1;
}
/* If -b was specified, we write the tables in binary. */
if (binary)
{
int yield = 0;
size_t len = fwrite(tables, 1, TABLES_LENGTH, f);
if (len != TABLES_LENGTH)
{
(void)fprintf(stderr, "pcre2_dftables: fwrite() returned wrong length %d "
"instead of %d\n", (int)len, TABLES_LENGTH);
yield = 1;
}
fclose(f);
free((void *)base_of_tables);
return yield;
}
/* Write the tables as source code for inclusion in the PCRE2 library. There
are several fprintf() calls here, because gcc in pedantic mode complains about
the very long string otherwise. */
(void)fprintf(f,
"/*************************************************\n"
"* Perl-Compatible Regular Expressions *\n"
"*************************************************/\n\n"
"/* This file was automatically written by the pcre2_dftables auxiliary\n"
"program. It contains character tables that are used when no external\n"
"tables are passed to PCRE2 by the application that calls it. The tables\n"
"are used only for characters whose code values are less than 256. */\n\n");
(void)fprintf(f,
"/* This set of tables was written in the %s locale. */\n\n", env);
(void)fprintf(f,
"/* The pcre2_ftables program (which is distributed with PCRE2) can be used\n"
"to build alternative versions of this file. This is necessary if you are\n"
"running in an EBCDIC environment, or if you want to default to a different\n"
"encoding, for example ISO-8859-1. When pcre2_dftables is run, it creates\n"
"these tables in the \"C\" locale by default. This happens automatically if\n"
"PCRE2 is configured with --enable-rebuild-chartables. However, you can run\n"
"pcre2_dftables manually with the -L option to build tables using the LC_ALL\n"
"locale. */\n\n");
/* Force config.h in z/OS */
#if defined NATIVE_ZOS
(void)fprintf(f,
"/* For z/OS, config.h is forced */\n"
"#ifndef HAVE_CONFIG_H\n"
"#define HAVE_CONFIG_H 1\n"
"#endif\n\n");
#endif
(void)fprintf(f,
"/* The following #include is present because without it gcc 4.x may remove\n"
"the array definition from the final binary if PCRE2 is built into a static\n"
"library and dead code stripping is activated. This leads to link errors.\n"
"Pulling in the header ensures that the array gets flagged as \"someone\n"
"outside this compilation unit might reference this\" and so it will always\n"
"be supplied to the linker. */\n\n");
(void)fprintf(f,
"#ifdef HAVE_CONFIG_H\n"
"#include \"config.h\"\n"
"#endif\n\n"
"#include \"pcre2_internal.h\"\n\n");
(void)fprintf(f,
"const uint8_t PRIV(default_tables)[] = {\n\n"
"/* This table is a lower casing table. */\n\n");
(void)fprintf(f, " ");
for (i = 0; i < 256; i++)
{
if ((i & 7) == 0 && i != 0) fprintf(f, "\n ");
fprintf(f, "%3d", *tables++);
if (i != 255) fprintf(f, ",");
}
(void)fprintf(f, ",\n\n");
(void)fprintf(f, "/* This table is a case flipping table. */\n\n");
(void)fprintf(f, " ");
for (i = 0; i < 256; i++)
{
if ((i & 7) == 0 && i != 0) fprintf(f, "\n ");
fprintf(f, "%3d", *tables++);
if (i != 255) fprintf(f, ",");
}
(void)fprintf(f, ",\n\n");
(void)fprintf(f,
"/* This table contains bit maps for various character classes. Each map is 32\n"
"bytes long and the bits run from the least significant end of each byte. The\n"
"classes that have their own maps are: space, xdigit, digit, upper, lower, word,\n"
"graph, print, punct, and cntrl. Other classes are built from combinations. */\n\n");
(void)fprintf(f, " ");
for (i = 0; i < cbit_length; i++)
{
if ((i & 7) == 0 && i != 0)
{
if ((i & 31) == 0) (void)fprintf(f, "\n");
if ((i & 24) == 8) (void)fprintf(f, " /* %s */", classlist[nclass++]);
(void)fprintf(f, "\n ");
}
(void)fprintf(f, "0x%02x", *tables++);
if (i != cbit_length - 1) (void)fprintf(f, ",");
}
(void)fprintf(f, ",\n\n");
(void)fprintf(f,
"/* This table identifies various classes of character by individual bits:\n"
" 0x%02x white space character\n"
" 0x%02x letter\n"
" 0x%02x lower case letter\n"
" 0x%02x decimal digit\n"
" 0x%02x alphanumeric or '_'\n*/\n\n",
ctype_space, ctype_letter, ctype_lcletter, ctype_digit, ctype_word);
(void)fprintf(f, " ");
for (i = 0; i < 256; i++)
{
if ((i & 7) == 0 && i != 0)
{
(void)fprintf(f, " /* ");
if (isprint(i-8)) (void)fprintf(f, " %c -", i-8);
else (void)fprintf(f, "%3d-", i-8);
if (isprint(i-1)) (void)fprintf(f, " %c ", i-1);
else (void)fprintf(f, "%3d", i-1);
(void)fprintf(f, " */\n ");
}
(void)fprintf(f, "0x%02x", *tables++);
if (i != 255) (void)fprintf(f, ",");
}
(void)fprintf(f, "};/* ");
if (isprint(i-8)) (void)fprintf(f, " %c -", i-8);
else (void)fprintf(f, "%3d-", i-8);
if (isprint(i-1)) (void)fprintf(f, " %c ", i-1);
else (void)fprintf(f, "%3d", i-1);
(void)fprintf(f, " */\n\n/* End of pcre2_chartables.c */\n");
fclose(f);
free((void *)base_of_tables);
return 0;
}
/* End of pcre2_dftables.c */

341
Kha/Backends/Kore-hxcpp/khacpp/project/thirdparty/pcre2-10.42-16/src/pcre2_error.c vendored Normal file
View File

@ -0,0 +1,341 @@
/*************************************************
* Perl-Compatible Regular Expressions *
*************************************************/
/* PCRE is a library of functions to support regular expressions whose syntax
and semantics are as close as possible to those of the Perl 5 language.
Written by Philip Hazel
Original API code Copyright (c) 1997-2012 University of Cambridge
New API code Copyright (c) 2016-2021 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
modification, are permitted provided that the following conditions are met:
* Redistributions of source code must retain the above copyright notice,
this list of conditions and the following disclaimer.
* Redistributions in binary form must reproduce the above copyright
notice, this list of conditions and the following disclaimer in the
documentation and/or other materials provided with the distribution.
* Neither the name of the University of Cambridge nor the names of its
contributors may be used to endorse or promote products derived from
this software without specific prior written permission.
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
POSSIBILITY OF SUCH DAMAGE.
-----------------------------------------------------------------------------
*/
#ifdef HAVE_CONFIG_H
#include "config.h"
#endif
#include "pcre2_internal.h"
#define STRING(a) # a
#define XSTRING(s) STRING(s)
/* The texts of compile-time error messages. Compile-time error numbers start
at COMPILE_ERROR_BASE (100).
This used to be a table of strings, but in order to reduce the number of
relocations needed when a shared library is loaded dynamically, it is now one
long string. We cannot use a table of offsets, because the lengths of inserts
such as XSTRING(MAX_NAME_SIZE) are not known. Instead,
pcre2_get_error_message() counts through to the one it wants - this isn't a
performance issue because these strings are used only when there is an error.
Each substring ends with \0 to insert a null character. This includes the final
substring, so that the whole string ends with \0\0, which can be detected when
counting through. */
static const unsigned char compile_error_texts[] =
"no error\0"
"\\ at end of pattern\0"
"\\c at end of pattern\0"
"unrecognized character follows \\\0"
"numbers out of order in {} quantifier\0"
/* 5 */
"number too big in {} quantifier\0"
"missing terminating ] for character class\0"
"escape sequence is invalid in character class\0"
"range out of order in character class\0"
"quantifier does not follow a repeatable item\0"
/* 10 */
"internal error: unexpected repeat\0"
"unrecognized character after (? or (?-\0"
"POSIX named classes are supported only within a class\0"
"POSIX collating elements are not supported\0"
"missing closing parenthesis\0"
/* 15 */
"reference to non-existent subpattern\0"
"pattern passed as NULL\0"
"unrecognised compile-time option bit(s)\0"
"missing ) after (?# comment\0"
"parentheses are too deeply nested\0"
/* 20 */
"regular expression is too large\0"
"failed to allocate heap memory\0"
"unmatched closing parenthesis\0"
"internal error: code overflow\0"
"missing closing parenthesis for condition\0"
/* 25 */
"lookbehind assertion is not fixed length\0"
"a relative value of zero is not allowed\0"
"conditional subpattern contains more than two branches\0"
"assertion expected after (?( or (?(?C)\0"
"digit expected after (?+ or (?-\0"
/* 30 */
"unknown POSIX class name\0"
"internal error in pcre2_study(): should not occur\0"
"this version of PCRE2 does not have Unicode support\0"
"parentheses are too deeply nested (stack check)\0"
"character code point value in \\x{} or \\o{} is too large\0"
/* 35 */
"lookbehind is too complicated\0"
"\\C is not allowed in a lookbehind assertion in UTF-" XSTRING(PCRE2_CODE_UNIT_WIDTH) " mode\0"
"PCRE2 does not support \\F, \\L, \\l, \\N{name}, \\U, or \\u\0"
"number after (?C is greater than 255\0"
"closing parenthesis for (?C expected\0"
/* 40 */
"invalid escape sequence in (*VERB) name\0"
"unrecognized character after (?P\0"
"syntax error in subpattern name (missing terminator?)\0"
"two named subpatterns have the same name (PCRE2_DUPNAMES not set)\0"
"subpattern name must start with a non-digit\0"
/* 45 */
"this version of PCRE2 does not have support for \\P, \\p, or \\X\0"
"malformed \\P or \\p sequence\0"
"unknown property after \\P or \\p\0"
"subpattern name is too long (maximum " XSTRING(MAX_NAME_SIZE) " code units)\0"
"too many named subpatterns (maximum " XSTRING(MAX_NAME_COUNT) ")\0"
/* 50 */
"invalid range in character class\0"
"octal value is greater than \\377 in 8-bit non-UTF-8 mode\0"
"internal error: overran compiling workspace\0"
"internal error: previously-checked referenced subpattern not found\0"
"DEFINE subpattern contains more than one branch\0"
/* 55 */
"missing opening brace after \\o\0"
"internal error: unknown newline setting\0"
"\\g is not followed by a braced, angle-bracketed, or quoted name/number or by a plain number\0"
"(?R (recursive pattern call) must be followed by a closing parenthesis\0"
/* "an argument is not allowed for (*ACCEPT), (*FAIL), or (*COMMIT)\0" */
"obsolete error (should not occur)\0" /* Was the above */
/* 60 */
"(*VERB) not recognized or malformed\0"
"subpattern number is too big\0"
"subpattern name expected\0"
"internal error: parsed pattern overflow\0"
"non-octal character in \\o{} (closing brace missing?)\0"
/* 65 */
"different names for subpatterns of the same number are not allowed\0"
"(*MARK) must have an argument\0"
"non-hex character in \\x{} (closing brace missing?)\0"
#ifndef EBCDIC
"\\c must be followed by a printable ASCII character\0"
#else
"\\c must be followed by a letter or one of [\\]^_?\0"
#endif
"\\k is not followed by a braced, angle-bracketed, or quoted name\0"
/* 70 */
"internal error: unknown meta code in check_lookbehinds()\0"
"\\N is not supported in a class\0"
"callout string is too long\0"
"disallowed Unicode code point (>= 0xd800 && <= 0xdfff)\0"
"using UTF is disabled by the application\0"
/* 75 */
"using UCP is disabled by the application\0"
"name is too long in (*MARK), (*PRUNE), (*SKIP), or (*THEN)\0"
"character code point value in \\u.... sequence is too large\0"
"digits missing in \\x{} or \\o{} or \\N{U+}\0"
"syntax error or number too big in (?(VERSION condition\0"
/* 80 */
"internal error: unknown opcode in auto_possessify()\0"
"missing terminating delimiter for callout with string argument\0"
"unrecognized string delimiter follows (?C\0"
"using \\C is disabled by the application\0"
"(?| and/or (?J: or (?x: parentheses are too deeply nested\0"
/* 85 */
"using \\C is disabled in this PCRE2 library\0"
"regular expression is too complicated\0"
"lookbehind assertion is too long\0"
"pattern string is longer than the limit set by the application\0"
"internal error: unknown code in parsed pattern\0"
/* 90 */
"internal error: bad code value in parsed_skip()\0"
"PCRE2_EXTRA_ALLOW_SURROGATE_ESCAPES is not allowed in UTF-16 mode\0"
"invalid option bits with PCRE2_LITERAL\0"
"\\N{U+dddd} is supported only in Unicode (UTF) mode\0"
"invalid hyphen in option setting\0"
/* 95 */
"(*alpha_assertion) not recognized\0"
"script runs require Unicode support, which this version of PCRE2 does not have\0"
"too many capturing groups (maximum 65535)\0"
"atomic assertion expected after (?( or (?(?C)\0"
"\\K is not allowed in lookarounds (but see PCRE2_EXTRA_ALLOW_LOOKAROUND_BSK)\0"
;
/* Match-time and UTF error texts are in the same format. */
static const unsigned char match_error_texts[] =
"no error\0"
"no match\0"
"partial match\0"
"UTF-8 error: 1 byte missing at end\0"
"UTF-8 error: 2 bytes missing at end\0"
/* 5 */
"UTF-8 error: 3 bytes missing at end\0"
"UTF-8 error: 4 bytes missing at end\0"
"UTF-8 error: 5 bytes missing at end\0"
"UTF-8 error: byte 2 top bits not 0x80\0"
"UTF-8 error: byte 3 top bits not 0x80\0"
/* 10 */
"UTF-8 error: byte 4 top bits not 0x80\0"
"UTF-8 error: byte 5 top bits not 0x80\0"
"UTF-8 error: byte 6 top bits not 0x80\0"
"UTF-8 error: 5-byte character is not allowed (RFC 3629)\0"
"UTF-8 error: 6-byte character is not allowed (RFC 3629)\0"
/* 15 */
"UTF-8 error: code points greater than 0x10ffff are not defined\0"
"UTF-8 error: code points 0xd800-0xdfff are not defined\0"
"UTF-8 error: overlong 2-byte sequence\0"
"UTF-8 error: overlong 3-byte sequence\0"
"UTF-8 error: overlong 4-byte sequence\0"
/* 20 */
"UTF-8 error: overlong 5-byte sequence\0"
"UTF-8 error: overlong 6-byte sequence\0"
"UTF-8 error: isolated byte with 0x80 bit set\0"
"UTF-8 error: illegal byte (0xfe or 0xff)\0"
"UTF-16 error: missing low surrogate at end\0"
/* 25 */
"UTF-16 error: invalid low surrogate\0"
"UTF-16 error: isolated low surrogate\0"
"UTF-32 error: code points 0xd800-0xdfff are not defined\0"
"UTF-32 error: code points greater than 0x10ffff are not defined\0"
"bad data value\0"
/* 30 */
"patterns do not all use the same character tables\0"
"magic number missing\0"
"pattern compiled in wrong mode: 8/16/32-bit error\0"
"bad offset value\0"
"bad option value\0"
/* 35 */
"invalid replacement string\0"
"bad offset into UTF string\0"
"callout error code\0" /* Never returned by PCRE2 itself */
"invalid data in workspace for DFA restart\0"
"too much recursion for DFA matching\0"
/* 40 */
"backreference condition or recursion test is not supported for DFA matching\0"
"function is not supported for DFA matching\0"
"pattern contains an item that is not supported for DFA matching\0"
"workspace size exceeded in DFA matching\0"
"internal error - pattern overwritten?\0"
/* 45 */
"bad JIT option\0"
"JIT stack limit reached\0"
"match limit exceeded\0"
"no more memory\0"
"unknown substring\0"
/* 50 */
"non-unique substring name\0"
"NULL argument passed with non-zero length\0"
"nested recursion at the same subject position\0"
"matching depth limit exceeded\0"
"requested value is not available\0"
/* 55 */
"requested value is not set\0"
"offset limit set without PCRE2_USE_OFFSET_LIMIT\0"
"bad escape sequence in replacement string\0"
"expected closing curly bracket in replacement string\0"
"bad substitution in replacement string\0"
/* 60 */
"match with end before start or start moved backwards is not supported\0"
"too many replacements (more than INT_MAX)\0"
"bad serialized data\0"
"heap limit exceeded\0"
"invalid syntax\0"
/* 65 */
"internal error - duplicate substitution match\0"
"PCRE2_MATCH_INVALID_UTF is not supported for DFA matching\0"
;
/*************************************************
* Return error message *
*************************************************/
/* This function copies an error message into a buffer whose units are of an
appropriate width. Error numbers are positive for compile-time errors, and
negative for match-time errors (except for UTF errors), but the numbers are all
distinct.
Arguments:
enumber error number
buffer where to put the message (zero terminated)
size size of the buffer in code units
Returns: length of message if all is well
negative on error
*/
PCRE2_EXP_DEFN int PCRE2_CALL_CONVENTION
pcre2_get_error_message(int enumber, PCRE2_UCHAR *buffer, PCRE2_SIZE size)
{
const unsigned char *message;
PCRE2_SIZE i;
int n;
if (size == 0) return PCRE2_ERROR_NOMEMORY;
if (enumber >= COMPILE_ERROR_BASE) /* Compile error */
{
message = compile_error_texts;
n = enumber - COMPILE_ERROR_BASE;
}
else if (enumber < 0) /* Match or UTF error */
{
message = match_error_texts;
n = -enumber;
}
else /* Invalid error number */
{
message = (unsigned char *)"\0"; /* Empty message list */
n = 1;
}
for (; n > 0; n--)
{
while (*message++ != CHAR_NUL) {};
if (*message == CHAR_NUL) return PCRE2_ERROR_BADDATA;
}
for (i = 0; *message != 0; i++)
{
if (i >= size - 1)
{
buffer[i] = 0; /* Terminate partial message */
return PCRE2_ERROR_NOMEMORY;
}
buffer[i] = *message++;
}
buffer[i] = 0;
return (int)i;
}
/* End of pcre2_error.c */

148
Kha/Backends/Kore-hxcpp/khacpp/project/thirdparty/pcre2-10.42-16/src/pcre2_extuni.c vendored Normal file
View File

@ -0,0 +1,148 @@
/*************************************************
* Perl-Compatible Regular Expressions *
*************************************************/
/* PCRE is a library of functions to support regular expressions whose syntax
and semantics are as close as possible to those of the Perl 5 language.
Written by Philip Hazel
Original API code Copyright (c) 1997-2012 University of Cambridge
New API code Copyright (c) 2016-2021 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
modification, are permitted provided that the following conditions are met:
* Redistributions of source code must retain the above copyright notice,
this list of conditions and the following disclaimer.
* Redistributions in binary form must reproduce the above copyright
notice, this list of conditions and the following disclaimer in the
documentation and/or other materials provided with the distribution.
* Neither the name of the University of Cambridge nor the names of its
contributors may be used to endorse or promote products derived from
this software without specific prior written permission.
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
POSSIBILITY OF SUCH DAMAGE.
-----------------------------------------------------------------------------
*/
/* This module contains an internal function that is used to match a Unicode
extended grapheme sequence. It is used by both pcre2_match() and
pcre2_def_match(). However, it is called only when Unicode support is being
compiled. Nevertheless, we provide a dummy function when there is no Unicode
support, because some compilers do not like functionless source files. */
#ifdef HAVE_CONFIG_H
#include "config.h"
#endif
#include "pcre2_internal.h"
/* Dummy function */
#ifndef SUPPORT_UNICODE
PCRE2_SPTR
PRIV(extuni)(uint32_t c, PCRE2_SPTR eptr, PCRE2_SPTR start_subject,
PCRE2_SPTR end_subject, BOOL utf, int *xcount)
{
(void)c;
(void)eptr;
(void)start_subject;
(void)end_subject;
(void)utf;
(void)xcount;
return NULL;
}
#else
/*************************************************
* Match an extended grapheme sequence *
*************************************************/
/*
Arguments:
c the first character
eptr pointer to next character
start_subject pointer to start of subject
end_subject pointer to end of subject
utf TRUE if in UTF mode
xcount pointer to count of additional characters,
or NULL if count not needed
Returns: pointer after the end of the sequence
*/
PCRE2_SPTR
PRIV(extuni)(uint32_t c, PCRE2_SPTR eptr, PCRE2_SPTR start_subject,
PCRE2_SPTR end_subject, BOOL utf, int *xcount)
{
int lgb = UCD_GRAPHBREAK(c);
while (eptr < end_subject)
{
int rgb;
int len = 1;
if (!utf) c = *eptr; else { GETCHARLEN(c, eptr, len); }
rgb = UCD_GRAPHBREAK(c);
if ((PRIV(ucp_gbtable)[lgb] & (1u << rgb)) == 0) break;
/* Not breaking between Regional Indicators is allowed only if there
are an even number of preceding RIs. */
if (lgb == ucp_gbRegional_Indicator && rgb == ucp_gbRegional_Indicator)
{
int ricount = 0;
PCRE2_SPTR bptr = eptr - 1;
if (utf) BACKCHAR(bptr);
/* bptr is pointing to the left-hand character */
while (bptr > start_subject)
{
bptr--;
if (utf)
{
BACKCHAR(bptr);
GETCHAR(c, bptr);
}
else
c = *bptr;
if (UCD_GRAPHBREAK(c) != ucp_gbRegional_Indicator) break;
ricount++;
}
if ((ricount & 1) != 0) break; /* Grapheme break required */
}
/* If Extend or ZWJ follows Extended_Pictographic, do not update lgb; this
allows any number of them before a following Extended_Pictographic. */
if ((rgb != ucp_gbExtend && rgb != ucp_gbZWJ) ||
lgb != ucp_gbExtended_Pictographic)
lgb = rgb;
eptr += len;
if (xcount != NULL) *xcount += 1;
}
return eptr;
}
#endif /* SUPPORT_UNICODE */
/* End of pcre2_extuni.c */

219
Kha/Backends/Kore-hxcpp/khacpp/project/thirdparty/pcre2-10.42-16/src/pcre2_find_bracket.c vendored Normal file
View File

@ -0,0 +1,219 @@
/*************************************************
* Perl-Compatible Regular Expressions *
*************************************************/
/* PCRE is a library of functions to support regular expressions whose syntax
and semantics are as close as possible to those of the Perl 5 language.
Written by Philip Hazel
Original API code Copyright (c) 1997-2012 University of Cambridge
New API code Copyright (c) 2016-2018 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
modification, are permitted provided that the following conditions are met:
* Redistributions of source code must retain the above copyright notice,
this list of conditions and the following disclaimer.
* Redistributions in binary form must reproduce the above copyright
notice, this list of conditions and the following disclaimer in the
documentation and/or other materials provided with the distribution.
* Neither the name of the University of Cambridge nor the names of its
contributors may be used to endorse or promote products derived from
this software without specific prior written permission.
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
POSSIBILITY OF SUCH DAMAGE.
-----------------------------------------------------------------------------
*/
/* This module contains a single function that scans through a compiled pattern
until it finds a capturing bracket with the given number, or, if the number is
negative, an instance of OP_REVERSE for a lookbehind. The function is called
from pcre2_compile.c and also from pcre2_study.c when finding the minimum
matching length. */
#ifdef HAVE_CONFIG_H
#include "config.h"
#endif
#include "pcre2_internal.h"
/*************************************************
* Scan compiled regex for specific bracket *
*************************************************/
/*
Arguments:
code points to start of expression
utf TRUE in UTF mode
number the required bracket number or negative to find a lookbehind
Returns: pointer to the opcode for the bracket, or NULL if not found
*/
PCRE2_SPTR
PRIV(find_bracket)(PCRE2_SPTR code, BOOL utf, int number)
{
for (;;)
{
PCRE2_UCHAR c = *code;
if (c == OP_END) return NULL;
/* XCLASS is used for classes that cannot be represented just by a bit map.
This includes negated single high-valued characters. CALLOUT_STR is used for
callouts with string arguments. In both cases the length in the table is
zero; the actual length is stored in the compiled code. */
if (c == OP_XCLASS) code += GET(code, 1);
else if (c == OP_CALLOUT_STR) code += GET(code, 1 + 2*LINK_SIZE);
/* Handle lookbehind */
else if (c == OP_REVERSE)
{
if (number < 0) return (PCRE2_UCHAR *)code;
code += PRIV(OP_lengths)[c];
}
/* Handle capturing bracket */
else if (c == OP_CBRA || c == OP_SCBRA ||
c == OP_CBRAPOS || c == OP_SCBRAPOS)
{
int n = (int)GET2(code, 1+LINK_SIZE);
if (n == number) return (PCRE2_UCHAR *)code;
code += PRIV(OP_lengths)[c];
}
/* Otherwise, we can get the item's length from the table, except that for
repeated character types, we have to test for \p and \P, which have an extra
two bytes of parameters, and for MARK/PRUNE/SKIP/THEN with an argument, we
must add in its length. */
else
{
switch(c)
{
case OP_TYPESTAR:
case OP_TYPEMINSTAR:
case OP_TYPEPLUS:
case OP_TYPEMINPLUS:
case OP_TYPEQUERY:
case OP_TYPEMINQUERY:
case OP_TYPEPOSSTAR:
case OP_TYPEPOSPLUS:
case OP_TYPEPOSQUERY:
if (code[1] == OP_PROP || code[1] == OP_NOTPROP) code += 2;
break;
case OP_TYPEUPTO:
case OP_TYPEMINUPTO:
case OP_TYPEEXACT:
case OP_TYPEPOSUPTO:
if (code[1 + IMM2_SIZE] == OP_PROP || code[1 + IMM2_SIZE] == OP_NOTPROP)
code += 2;
break;
case OP_MARK:
case OP_COMMIT_ARG:
case OP_PRUNE_ARG:
case OP_SKIP_ARG:
case OP_THEN_ARG:
code += code[1];
break;
}
/* Add in the fixed length from the table */
code += PRIV(OP_lengths)[c];
/* In UTF-8 and UTF-16 modes, opcodes that are followed by a character may be
followed by a multi-byte character. The length in the table is a minimum, so
we have to arrange to skip the extra bytes. */
#ifdef MAYBE_UTF_MULTI
if (utf) switch(c)
{
case OP_CHAR:
case OP_CHARI:
case OP_NOT:
case OP_NOTI:
case OP_EXACT:
case OP_EXACTI:
case OP_NOTEXACT:
case OP_NOTEXACTI:
case OP_UPTO:
case OP_UPTOI:
case OP_NOTUPTO:
case OP_NOTUPTOI:
case OP_MINUPTO:
case OP_MINUPTOI:
case OP_NOTMINUPTO:
case OP_NOTMINUPTOI:
case OP_POSUPTO:
case OP_POSUPTOI:
case OP_NOTPOSUPTO:
case OP_NOTPOSUPTOI:
case OP_STAR:
case OP_STARI:
case OP_NOTSTAR:
case OP_NOTSTARI:
case OP_MINSTAR:
case OP_MINSTARI:
case OP_NOTMINSTAR:
case OP_NOTMINSTARI:
case OP_POSSTAR:
case OP_POSSTARI:
case OP_NOTPOSSTAR:
case OP_NOTPOSSTARI:
case OP_PLUS:
case OP_PLUSI:
case OP_NOTPLUS:
case OP_NOTPLUSI:
case OP_MINPLUS:
case OP_MINPLUSI:
case OP_NOTMINPLUS:
case OP_NOTMINPLUSI:
case OP_POSPLUS:
case OP_POSPLUSI:
case OP_NOTPOSPLUS:
case OP_NOTPOSPLUSI:
case OP_QUERY:
case OP_QUERYI:
case OP_NOTQUERY:
case OP_NOTQUERYI:
case OP_MINQUERY:
case OP_MINQUERYI:
case OP_NOTMINQUERY:
case OP_NOTMINQUERYI:
case OP_POSQUERY:
case OP_POSQUERYI:
case OP_NOTPOSQUERY:
case OP_NOTPOSQUERYI:
if (HAS_EXTRALEN(code[-1])) code += GET_EXTRALEN(code[-1]);
break;
}
#else
(void)(utf); /* Keep compiler happy by referencing function argument */
#endif /* MAYBE_UTF_MULTI */
}
}
}
/* End of pcre2_find_bracket.c */

369
Kha/Backends/Kore-hxcpp/khacpp/project/thirdparty/pcre2-10.42-16/src/pcre2_fuzzsupport.c vendored Normal file
View File

@ -0,0 +1,369 @@
/***************************************************************************
Fuzzer driver for PCRE2. Given an arbitrary string of bytes and a length, it
tries to compile and match it, deriving options from the string itself. If
STANDALONE is defined, a main program that calls the driver with the contents
of specified files is compiled, and commentary on what is happening is output.
If an argument starts with '=' the rest of it it is taken as a literal string
rather than a file name. This allows easy testing of short strings.
Written by Philip Hazel, October 2016
***************************************************************************/
#include <errno.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#define PCRE2_CODE_UNIT_WIDTH 8
#include "pcre2.h"
#define MAX_MATCH_SIZE 1000
#define DFA_WORKSPACE_COUNT 100
#define ALLOWED_COMPILE_OPTIONS \
(PCRE2_ANCHORED|PCRE2_ALLOW_EMPTY_CLASS|PCRE2_ALT_BSUX|PCRE2_ALT_CIRCUMFLEX| \
PCRE2_ALT_VERBNAMES|PCRE2_AUTO_CALLOUT|PCRE2_CASELESS|PCRE2_DOLLAR_ENDONLY| \
PCRE2_DOTALL|PCRE2_DUPNAMES|PCRE2_ENDANCHORED|PCRE2_EXTENDED|PCRE2_FIRSTLINE| \
PCRE2_MATCH_UNSET_BACKREF|PCRE2_MULTILINE|PCRE2_NEVER_BACKSLASH_C| \
PCRE2_NO_AUTO_CAPTURE| \
PCRE2_NO_AUTO_POSSESS|PCRE2_NO_DOTSTAR_ANCHOR|PCRE2_NO_START_OPTIMIZE| \
PCRE2_UCP|PCRE2_UNGREEDY|PCRE2_USE_OFFSET_LIMIT| \
PCRE2_UTF)
#define ALLOWED_MATCH_OPTIONS \
(PCRE2_ANCHORED|PCRE2_ENDANCHORED|PCRE2_NOTBOL|PCRE2_NOTEOL|PCRE2_NOTEMPTY| \
PCRE2_NOTEMPTY_ATSTART|PCRE2_PARTIAL_HARD| \
PCRE2_PARTIAL_SOFT|PCRE2_NO_JIT)
/* This is the callout function. Its only purpose is to halt matching if there
are more than 100 callouts, as one way of stopping too much time being spent on
fruitless matches. The callout data is a pointer to the counter. */
static int callout_function(pcre2_callout_block *cb, void *callout_data)
{
(void)cb; /* Avoid unused parameter warning */
*((uint32_t *)callout_data) += 1;
return (*((uint32_t *)callout_data) > 100)? PCRE2_ERROR_CALLOUT : 0;
}
/* Putting in this apparently unnecessary prototype prevents gcc from giving a
"no previous prototype" warning when compiling at high warning level. */
int LLVMFuzzerTestOneInput(const unsigned char *, size_t);
/* Here's the driving function. */
int LLVMFuzzerTestOneInput(const unsigned char *data, size_t size)
{
uint32_t compile_options;
uint32_t match_options;
pcre2_match_data *match_data = NULL;
pcre2_match_context *match_context = NULL;
size_t match_size;
int dfa_workspace[DFA_WORKSPACE_COUNT];
int r1, r2;
int i;
if (size < 1) return 0;
/* Limiting the length of the subject for matching stops fruitless searches
in large trees taking too much time. */
match_size = (size > MAX_MATCH_SIZE)? MAX_MATCH_SIZE : size;
/* Figure out some options to use. Initialize the random number to ensure
repeatability. Ensure that we get a 32-bit unsigned random number for testing
options. (RAND_MAX is required to be at least 32767, but is commonly
2147483647, which excludes the top bit.) */
srand((unsigned int)(data[size/2]));
r1 = rand();
r2 = rand();
/* Ensure that all undefined option bits are zero (waste of time trying them)
and also that PCRE2_NO_UTF_CHECK is unset, as there is no guarantee that the
input is UTF-8. Also unset PCRE2_NEVER_UTF and PCRE2_NEVER_UCP as there is no
reason to disallow UTF and UCP. Force PCRE2_NEVER_BACKSLASH_C to be set because
\C in random patterns is highly likely to cause a crash. */
compile_options =
((((uint32_t)r1 << 16) | ((uint32_t)r2 & 0xffff)) & ALLOWED_COMPILE_OPTIONS) |
PCRE2_NEVER_BACKSLASH_C;
match_options =
((((uint32_t)r1 << 16) | ((uint32_t)r2 & 0xffff)) & ALLOWED_MATCH_OPTIONS);
/* Discard partial matching if PCRE2_ENDANCHORED is set, because they are not
allowed together and just give an immediate error return. */
if (((compile_options|match_options) & PCRE2_ENDANCHORED) != 0)
match_options &= ~(PCRE2_PARTIAL_HARD|PCRE2_PARTIAL_SOFT);
/* Do the compile with and without the options, and after a successful compile,
likewise do the match with and without the options. */
for (i = 0; i < 2; i++)
{
uint32_t callout_count;
int errorcode;
PCRE2_SIZE erroroffset;
pcre2_code *code;
#ifdef STANDALONE
printf("Compile options %.8x never_backslash_c", compile_options);
printf("%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s\n",
((compile_options & PCRE2_ALT_BSUX) != 0)? ",alt_bsux" : "",
((compile_options & PCRE2_ALT_CIRCUMFLEX) != 0)? ",alt_circumflex" : "",
((compile_options & PCRE2_ALT_VERBNAMES) != 0)? ",alt_verbnames" : "",
((compile_options & PCRE2_ALLOW_EMPTY_CLASS) != 0)? ",allow_empty_class" : "",
((compile_options & PCRE2_ANCHORED) != 0)? ",anchored" : "",
((compile_options & PCRE2_AUTO_CALLOUT) != 0)? ",auto_callout" : "",
((compile_options & PCRE2_CASELESS) != 0)? ",caseless" : "",
((compile_options & PCRE2_DOLLAR_ENDONLY) != 0)? ",dollar_endonly" : "",
((compile_options & PCRE2_DOTALL) != 0)? ",dotall" : "",
((compile_options & PCRE2_DUPNAMES) != 0)? ",dupnames" : "",
((compile_options & PCRE2_ENDANCHORED) != 0)? ",endanchored" : "",
((compile_options & PCRE2_EXTENDED) != 0)? ",extended" : "",
((compile_options & PCRE2_FIRSTLINE) != 0)? ",firstline" : "",
((compile_options & PCRE2_MATCH_UNSET_BACKREF) != 0)? ",match_unset_backref" : "",
((compile_options & PCRE2_MULTILINE) != 0)? ",multiline" : "",
((compile_options & PCRE2_NEVER_UCP) != 0)? ",never_ucp" : "",
((compile_options & PCRE2_NEVER_UTF) != 0)? ",never_utf" : "",
((compile_options & PCRE2_NO_AUTO_CAPTURE) != 0)? ",no_auto_capture" : "",
((compile_options & PCRE2_NO_AUTO_POSSESS) != 0)? ",no_auto_possess" : "",
((compile_options & PCRE2_NO_DOTSTAR_ANCHOR) != 0)? ",no_dotstar_anchor" : "",
((compile_options & PCRE2_NO_UTF_CHECK) != 0)? ",no_utf_check" : "",
((compile_options & PCRE2_NO_START_OPTIMIZE) != 0)? ",no_start_optimize" : "",
((compile_options & PCRE2_UCP) != 0)? ",ucp" : "",
((compile_options & PCRE2_UNGREEDY) != 0)? ",ungreedy" : "",
((compile_options & PCRE2_USE_OFFSET_LIMIT) != 0)? ",use_offset_limit" : "",
((compile_options & PCRE2_UTF) != 0)? ",utf" : "");
#endif
code = pcre2_compile((PCRE2_SPTR)data, (PCRE2_SIZE)size, compile_options,
&errorcode, &erroroffset, NULL);
/* Compilation succeeded */
if (code != NULL)
{
int j;
uint32_t save_match_options = match_options;
#ifdef SUPPORT_JIT
pcre2_jit_compile(code, PCRE2_JIT_COMPLETE);
#endif
/* Create match data and context blocks only when we first need them. Set
low match and depth limits to avoid wasting too much searching large
pattern trees. Almost all matches are going to fail. */
if (match_data == NULL)
{
match_data = pcre2_match_data_create(32, NULL);
if (match_data == NULL)
{
#ifdef STANDALONE
printf("** Failed to create match data block\n");
#endif
return 0;
}
}
if (match_context == NULL)
{
match_context = pcre2_match_context_create(NULL);
if (match_context == NULL)
{
#ifdef STANDALONE
printf("** Failed to create match context block\n");
#endif
return 0;
}
(void)pcre2_set_match_limit(match_context, 100);
(void)pcre2_set_depth_limit(match_context, 100);
(void)pcre2_set_callout(match_context, callout_function, &callout_count);
}
/* Match twice, with and without options. */
for (j = 0; j < 2; j++)
{
#ifdef STANDALONE
printf("Match options %.8x", match_options);
printf("%s%s%s%s%s%s%s%s%s%s\n",
((match_options & PCRE2_ANCHORED) != 0)? ",anchored" : "",
((match_options & PCRE2_ENDANCHORED) != 0)? ",endanchored" : "",
((match_options & PCRE2_NO_JIT) != 0)? ",no_jit" : "",
((match_options & PCRE2_NO_UTF_CHECK) != 0)? ",no_utf_check" : "",
((match_options & PCRE2_NOTBOL) != 0)? ",notbol" : "",
((match_options & PCRE2_NOTEMPTY) != 0)? ",notempty" : "",
((match_options & PCRE2_NOTEMPTY_ATSTART) != 0)? ",notempty_atstart" : "",
((match_options & PCRE2_NOTEOL) != 0)? ",noteol" : "",
((match_options & PCRE2_PARTIAL_HARD) != 0)? ",partial_hard" : "",
((match_options & PCRE2_PARTIAL_SOFT) != 0)? ",partial_soft" : "");
#endif
callout_count = 0;
errorcode = pcre2_match(code, (PCRE2_SPTR)data, (PCRE2_SIZE)match_size, 0,
match_options, match_data, match_context);
#ifdef STANDALONE
if (errorcode >= 0) printf("Match returned %d\n", errorcode); else
{
unsigned char buffer[256];
pcre2_get_error_message(errorcode, buffer, 256);
printf("Match failed: error %d: %s\n", errorcode, buffer);
}
#endif
match_options = 0; /* For second time */
}
/* Match with DFA twice, with and without options. */
match_options = save_match_options & ~PCRE2_NO_JIT; /* Not valid for DFA */
for (j = 0; j < 2; j++)
{
#ifdef STANDALONE
printf("DFA match options %.8x", match_options);
printf("%s%s%s%s%s%s%s%s%s\n",
((match_options & PCRE2_ANCHORED) != 0)? ",anchored" : "",
((match_options & PCRE2_ENDANCHORED) != 0)? ",endanchored" : "",
((match_options & PCRE2_NO_UTF_CHECK) != 0)? ",no_utf_check" : "",
((match_options & PCRE2_NOTBOL) != 0)? ",notbol" : "",
((match_options & PCRE2_NOTEMPTY) != 0)? ",notempty" : "",
((match_options & PCRE2_NOTEMPTY_ATSTART) != 0)? ",notempty_atstart" : "",
((match_options & PCRE2_NOTEOL) != 0)? ",noteol" : "",
((match_options & PCRE2_PARTIAL_HARD) != 0)? ",partial_hard" : "",
((match_options & PCRE2_PARTIAL_SOFT) != 0)? ",partial_soft" : "");
#endif
callout_count = 0;
errorcode = pcre2_dfa_match(code, (PCRE2_SPTR)data,
(PCRE2_SIZE)match_size, 0, match_options, match_data, match_context,
dfa_workspace, DFA_WORKSPACE_COUNT);
#ifdef STANDALONE
if (errorcode >= 0) printf("Match returned %d\n", errorcode); else
{
unsigned char buffer[256];
pcre2_get_error_message(errorcode, buffer, 256);
printf("Match failed: error %d: %s\n", errorcode, buffer);
}
#endif
match_options = 0; /* For second time */
}
match_options = save_match_options; /* Reset for the second compile */
pcre2_code_free(code);
}
/* Compilation failed */
else
{
unsigned char buffer[256];
pcre2_get_error_message(errorcode, buffer, 256);
#ifdef STANDALONE
printf("Error %d at offset %lu: %s\n", errorcode, erroroffset, buffer);
#else
if (strstr((const char *)buffer, "internal error") != NULL) abort();
#endif
}
compile_options = PCRE2_NEVER_BACKSLASH_C; /* For second time */
}
if (match_data != NULL) pcre2_match_data_free(match_data);
if (match_context != NULL) pcre2_match_context_free(match_context);
return 0;
}
/* Optional main program. */
#ifdef STANDALONE
int main(int argc, char **argv)
{
int i;
if (argc < 2)
{
printf("** No arguments given\n");
return 0;
}
for (i = 1; i < argc; i++)
{
size_t filelen;
size_t readsize;
unsigned char *buffer;
FILE *f;
/* Handle a literal string. Copy to an exact size buffer so that checks for
overrunning work. */
if (argv[i][0] == '=')
{
readsize = strlen(argv[i]) - 1;
printf("------ <Literal> ------\n");
printf("Length = %lu\n", readsize);
printf("%.*s\n", (int)readsize, argv[i]+1);
buffer = (unsigned char *)malloc(readsize);
if (buffer == NULL)
printf("** Failed to allocate %lu bytes of memory\n", readsize);
else
{
memcpy(buffer, argv[i]+1, readsize);
LLVMFuzzerTestOneInput(buffer, readsize);
free(buffer);
}
continue;
}
/* Handle a string given in a file */
f = fopen(argv[i], "rb");
if (f == NULL)
{
printf("** Failed to open %s: %s\n", argv[i], strerror(errno));
continue;
}
printf("------ %s ------\n", argv[i]);
fseek(f, 0, SEEK_END);
filelen = ftell(f);
fseek(f, 0, SEEK_SET);
buffer = (unsigned char *)malloc(filelen);
if (buffer == NULL)
{
printf("** Failed to allocate %lu bytes of memory\n", filelen);
fclose(f);
continue;
}
readsize = fread(buffer, 1, filelen, f);
fclose(f);
if (readsize != filelen)
printf("** File size is %lu but fread() returned %lu\n", filelen, readsize);
else
{
printf("Length = %lu\n", filelen);
LLVMFuzzerTestOneInput(buffer, filelen);
}
free(buffer);
}
return 0;
}
#endif /* STANDALONE */
/* End */

2047
Kha/Backends/Kore-hxcpp/khacpp/project/thirdparty/pcre2-10.42-16/src/pcre2_internal.h vendored Normal file
View File

File diff suppressed because it is too large Load Diff

934
Kha/Backends/Kore-hxcpp/khacpp/project/thirdparty/pcre2-10.42-16/src/pcre2_intmodedep.h vendored Normal file
View File

@ -0,0 +1,934 @@
/*************************************************
* Perl-Compatible Regular Expressions *
*************************************************/
/* PCRE is a library of functions to support regular expressions whose syntax
and semantics are as close as possible to those of the Perl 5 language.
Written by Philip Hazel
Original API code Copyright (c) 1997-2012 University of Cambridge
New API code Copyright (c) 2016-2022 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
modification, are permitted provided that the following conditions are met:
* Redistributions of source code must retain the above copyright notice,
this list of conditions and the following disclaimer.
* Redistributions in binary form must reproduce the above copyright
notice, this list of conditions and the following disclaimer in the
documentation and/or other materials provided with the distribution.
* Neither the name of the University of Cambridge nor the names of its
contributors may be used to endorse or promote products derived from
this software without specific prior written permission.
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
POSSIBILITY OF SUCH DAMAGE.
-----------------------------------------------------------------------------
*/
/* This module contains mode-dependent macro and structure definitions. The
file is #included by pcre2_internal.h if PCRE2_CODE_UNIT_WIDTH is defined.
These mode-dependent items are kept in a separate file so that they can also be
#included multiple times for different code unit widths by pcre2test in order
to have access to the hidden structures at all supported widths.
Some of the mode-dependent macros are required at different widths for
different parts of the pcre2test code (in particular, the included
pcre_printint.c file). We undefine them here so that they can be re-defined for
multiple inclusions. Not all of these are used in pcre2test, but it's easier
just to undefine them all. */
#undef ACROSSCHAR
#undef BACKCHAR
#undef BYTES2CU
#undef CHMAX_255
#undef CU2BYTES
#undef FORWARDCHAR
#undef FORWARDCHARTEST
#undef GET
#undef GET2
#undef GETCHAR
#undef GETCHARINC
#undef GETCHARINCTEST
#undef GETCHARLEN
#undef GETCHARLENTEST
#undef GETCHARTEST
#undef GET_EXTRALEN
#undef HAS_EXTRALEN
#undef IMM2_SIZE
#undef MAX_255
#undef MAX_MARK
#undef MAX_PATTERN_SIZE
#undef MAX_UTF_SINGLE_CU
#undef NOT_FIRSTCU
#undef PUT
#undef PUT2
#undef PUT2INC
#undef PUTCHAR
#undef PUTINC
#undef TABLE_GET
/* -------------------------- MACROS ----------------------------- */
/* PCRE keeps offsets in its compiled code as at least 16-bit quantities
(always stored in big-endian order in 8-bit mode) by default. These are used,
for example, to link from the start of a subpattern to its alternatives and its
end. The use of 16 bits per offset limits the size of an 8-bit compiled regex
to around 64K, which is big enough for almost everybody. However, I received a
request for an even bigger limit. For this reason, and also to make the code
easier to maintain, the storing and loading of offsets from the compiled code
unit string is now handled by the macros that are defined here.
The macros are controlled by the value of LINK_SIZE. This defaults to 2, but
values of 3 or 4 are also supported. */
/* ------------------- 8-bit support ------------------ */
#if PCRE2_CODE_UNIT_WIDTH == 8
#if LINK_SIZE == 2
#define PUT(a,n,d) \
(a[n] = (PCRE2_UCHAR)((d) >> 8)), \
(a[(n)+1] = (PCRE2_UCHAR)((d) & 255))
#define GET(a,n) \
(unsigned int)(((a)[n] << 8) | (a)[(n)+1])
#define MAX_PATTERN_SIZE (1 << 16)
#elif LINK_SIZE == 3
#define PUT(a,n,d) \
(a[n] = (PCRE2_UCHAR)((d) >> 16)), \
(a[(n)+1] = (PCRE2_UCHAR)((d) >> 8)), \
(a[(n)+2] = (PCRE2_UCHAR)((d) & 255))
#define GET(a,n) \
(unsigned int)(((a)[n] << 16) | ((a)[(n)+1] << 8) | (a)[(n)+2])
#define MAX_PATTERN_SIZE (1 << 24)
#elif LINK_SIZE == 4
#define PUT(a,n,d) \
(a[n] = (PCRE2_UCHAR)((d) >> 24)), \
(a[(n)+1] = (PCRE2_UCHAR)((d) >> 16)), \
(a[(n)+2] = (PCRE2_UCHAR)((d) >> 8)), \
(a[(n)+3] = (PCRE2_UCHAR)((d) & 255))
#define GET(a,n) \
(unsigned int)(((a)[n] << 24) | ((a)[(n)+1] << 16) | ((a)[(n)+2] << 8) | (a)[(n)+3])
#define MAX_PATTERN_SIZE (1 << 30) /* Keep it positive */
#else
#error LINK_SIZE must be 2, 3, or 4
#endif
/* ------------------- 16-bit support ------------------ */
#elif PCRE2_CODE_UNIT_WIDTH == 16
#if LINK_SIZE == 2
#undef LINK_SIZE
#define LINK_SIZE 1
#define PUT(a,n,d) \
(a[n] = (PCRE2_UCHAR)(d))
#define GET(a,n) \
(a[n])
#define MAX_PATTERN_SIZE (1 << 16)
#elif LINK_SIZE == 3 || LINK_SIZE == 4
#undef LINK_SIZE
#define LINK_SIZE 2
#define PUT(a,n,d) \
(a[n] = (PCRE2_UCHAR)((d) >> 16)), \
(a[(n)+1] = (PCRE2_UCHAR)((d) & 65535))
#define GET(a,n) \
(unsigned int)(((a)[n] << 16) | (a)[(n)+1])
#define MAX_PATTERN_SIZE (1 << 30) /* Keep it positive */
#else
#error LINK_SIZE must be 2, 3, or 4
#endif
/* ------------------- 32-bit support ------------------ */
#elif PCRE2_CODE_UNIT_WIDTH == 32
#undef LINK_SIZE
#define LINK_SIZE 1
#define PUT(a,n,d) \
(a[n] = (d))
#define GET(a,n) \
(a[n])
#define MAX_PATTERN_SIZE (1 << 30) /* Keep it positive */
#else
#error Unsupported compiling mode
#endif
/* --------------- Other mode-specific macros ----------------- */
/* PCRE uses some other (at least) 16-bit quantities that do not change when
the size of offsets changes. There are used for repeat counts and for other
things such as capturing parenthesis numbers in back references.
Define the number of code units required to hold a 16-bit count/offset, and
macros to load and store such a value. For reasons that I do not understand,
the expression in the 8-bit GET2 macro is treated by gcc as a signed
expression, even when a is declared as unsigned. It seems that any kind of
arithmetic results in a signed value. Hence the cast. */
#if PCRE2_CODE_UNIT_WIDTH == 8
#define IMM2_SIZE 2
#define GET2(a,n) (unsigned int)(((a)[n] << 8) | (a)[(n)+1])
#define PUT2(a,n,d) a[n] = (d) >> 8, a[(n)+1] = (d) & 255
#else /* Code units are 16 or 32 bits */
#define IMM2_SIZE 1
#define GET2(a,n) a[n]
#define PUT2(a,n,d) a[n] = d
#endif
/* Other macros that are different for 8-bit mode. The MAX_255 macro checks
whether its argument, which is assumed to be one code unit, is less than 256.
The CHMAX_255 macro does not assume one code unit. The maximum length of a MARK
name must fit in one code unit; currently it is set to 255 or 65535. The
TABLE_GET macro is used to access elements of tables containing exactly 256
items. Its argument is a code unit. When code points can be greater than 255, a
check is needed before accessing these tables. */
#if PCRE2_CODE_UNIT_WIDTH == 8
#define MAX_255(c) TRUE
#define MAX_MARK ((1u << 8) - 1)
#define TABLE_GET(c, table, default) ((table)[c])
#ifdef SUPPORT_UNICODE
#define SUPPORT_WIDE_CHARS
#define CHMAX_255(c) ((c) <= 255u)
#else
#define CHMAX_255(c) TRUE
#endif /* SUPPORT_UNICODE */
#else /* Code units are 16 or 32 bits */
#define CHMAX_255(c) ((c) <= 255u)
#define MAX_255(c) ((c) <= 255u)
#define MAX_MARK ((1u << 16) - 1)
#define SUPPORT_WIDE_CHARS
#define TABLE_GET(c, table, default) (MAX_255(c)? ((table)[c]):(default))
#endif
/* ----------------- Character-handling macros ----------------- */
/* There is a proposed future special "UTF-21" mode, in which only the lowest
21 bits of a 32-bit character are interpreted as UTF, with the remaining 11
high-order bits available to the application for other uses. In preparation for
the future implementation of this mode, there are macros that load a data item
and, if in this special mode, mask it to 21 bits. These macros all have names
starting with UCHAR21. In all other modes, including the normal 32-bit
library, the macros all have the same simple definitions. When the new mode is
implemented, it is expected that these definitions will be varied appropriately
using #ifdef when compiling the library that supports the special mode. */
#define UCHAR21(eptr) (*(eptr))
#define UCHAR21TEST(eptr) (*(eptr))
#define UCHAR21INC(eptr) (*(eptr)++)
#define UCHAR21INCTEST(eptr) (*(eptr)++)
/* When UTF encoding is being used, a character is no longer just a single
byte in 8-bit mode or a single short in 16-bit mode. The macros for character
handling generate simple sequences when used in the basic mode, and more
complicated ones for UTF characters. GETCHARLENTEST and other macros are not
used when UTF is not supported. To make sure they can never even appear when
UTF support is omitted, we don't even define them. */
#ifndef SUPPORT_UNICODE
/* #define MAX_UTF_SINGLE_CU */
/* #define HAS_EXTRALEN(c) */
/* #define GET_EXTRALEN(c) */
/* #define NOT_FIRSTCU(c) */
#define GETCHAR(c, eptr) c = *eptr;
#define GETCHARTEST(c, eptr) c = *eptr;
#define GETCHARINC(c, eptr) c = *eptr++;
#define GETCHARINCTEST(c, eptr) c = *eptr++;
#define GETCHARLEN(c, eptr, len) c = *eptr;
#define PUTCHAR(c, p) (*p = c, 1)
/* #define GETCHARLENTEST(c, eptr, len) */
/* #define BACKCHAR(eptr) */
/* #define FORWARDCHAR(eptr) */
/* #define FORWARCCHARTEST(eptr,end) */
/* #define ACROSSCHAR(condition, eptr, action) */
#else /* SUPPORT_UNICODE */
/* ------------------- 8-bit support ------------------ */
#if PCRE2_CODE_UNIT_WIDTH == 8
#define MAYBE_UTF_MULTI /* UTF chars may use multiple code units */
/* The largest UTF code point that can be encoded as a single code unit. */
#define MAX_UTF_SINGLE_CU 127
/* Tests whether the code point needs extra characters to decode. */
#define HAS_EXTRALEN(c) HASUTF8EXTRALEN(c)
/* Returns with the additional number of characters if IS_MULTICHAR(c) is TRUE.
Otherwise it has an undefined behaviour. */
#define GET_EXTRALEN(c) (PRIV(utf8_table4)[(c) & 0x3fu])
/* Returns TRUE, if the given value is not the first code unit of a UTF
sequence. */
#define NOT_FIRSTCU(c) (((c) & 0xc0u) == 0x80u)
/* Get the next UTF-8 character, not advancing the pointer. This is called when
we know we are in UTF-8 mode. */
#define GETCHAR(c, eptr) \
c = *eptr; \
if (c >= 0xc0u) GETUTF8(c, eptr);
/* Get the next UTF-8 character, testing for UTF-8 mode, and not advancing the
pointer. */
#define GETCHARTEST(c, eptr) \
c = *eptr; \
if (utf && c >= 0xc0u) GETUTF8(c, eptr);
/* Get the next UTF-8 character, advancing the pointer. This is called when we
know we are in UTF-8 mode. */
#define GETCHARINC(c, eptr) \
c = *eptr++; \
if (c >= 0xc0u) GETUTF8INC(c, eptr);
/* Get the next character, testing for UTF-8 mode, and advancing the pointer.
This is called when we don't know if we are in UTF-8 mode. */
#define GETCHARINCTEST(c, eptr) \
c = *eptr++; \
if (utf && c >= 0xc0u) GETUTF8INC(c, eptr);
/* Get the next UTF-8 character, not advancing the pointer, incrementing length
if there are extra bytes. This is called when we know we are in UTF-8 mode. */
#define GETCHARLEN(c, eptr, len) \
c = *eptr; \
if (c >= 0xc0u) GETUTF8LEN(c, eptr, len);
/* Get the next UTF-8 character, testing for UTF-8 mode, not advancing the
pointer, incrementing length if there are extra bytes. This is called when we
do not know if we are in UTF-8 mode. */
#define GETCHARLENTEST(c, eptr, len) \
c = *eptr; \
if (utf && c >= 0xc0u) GETUTF8LEN(c, eptr, len);
/* If the pointer is not at the start of a character, move it back until
it is. This is called only in UTF-8 mode - we don't put a test within the macro
because almost all calls are already within a block of UTF-8 only code. */
#define BACKCHAR(eptr) while((*eptr & 0xc0u) == 0x80u) eptr--
/* Same as above, just in the other direction. */
#define FORWARDCHAR(eptr) while((*eptr & 0xc0u) == 0x80u) eptr++
#define FORWARDCHARTEST(eptr,end) while(eptr < end && (*eptr & 0xc0u) == 0x80u) eptr++
/* Same as above, but it allows a fully customizable form. */
#define ACROSSCHAR(condition, eptr, action) \
while((condition) && ((*eptr) & 0xc0u) == 0x80u) action
/* Deposit a character into memory, returning the number of code units. */
#define PUTCHAR(c, p) ((utf && c > MAX_UTF_SINGLE_CU)? \
PRIV(ord2utf)(c,p) : (*p = c, 1))
/* ------------------- 16-bit support ------------------ */
#elif PCRE2_CODE_UNIT_WIDTH == 16
#define MAYBE_UTF_MULTI /* UTF chars may use multiple code units */
/* The largest UTF code point that can be encoded as a single code unit. */
#define MAX_UTF_SINGLE_CU 65535
/* Tests whether the code point needs extra characters to decode. */
#define HAS_EXTRALEN(c) (((c) & 0xfc00u) == 0xd800u)
/* Returns with the additional number of characters if IS_MULTICHAR(c) is TRUE.
Otherwise it has an undefined behaviour. */
#define GET_EXTRALEN(c) 1
/* Returns TRUE, if the given value is not the first code unit of a UTF
sequence. */
#define NOT_FIRSTCU(c) (((c) & 0xfc00u) == 0xdc00u)
/* Base macro to pick up the low surrogate of a UTF-16 character, not
advancing the pointer. */
#define GETUTF16(c, eptr) \
{ c = (((c & 0x3ffu) << 10) | (eptr[1] & 0x3ffu)) + 0x10000u; }
/* Get the next UTF-16 character, not advancing the pointer. This is called when
we know we are in UTF-16 mode. */
#define GETCHAR(c, eptr) \
c = *eptr; \
if ((c & 0xfc00u) == 0xd800u) GETUTF16(c, eptr);
/* Get the next UTF-16 character, testing for UTF-16 mode, and not advancing the
pointer. */
#define GETCHARTEST(c, eptr) \
c = *eptr; \
if (utf && (c & 0xfc00u) == 0xd800u) GETUTF16(c, eptr);
/* Base macro to pick up the low surrogate of a UTF-16 character, advancing
the pointer. */
#define GETUTF16INC(c, eptr) \
{ c = (((c & 0x3ffu) << 10) | (*eptr++ & 0x3ffu)) + 0x10000u; }
/* Get the next UTF-16 character, advancing the pointer. This is called when we
know we are in UTF-16 mode. */
#define GETCHARINC(c, eptr) \
c = *eptr++; \
if ((c & 0xfc00u) == 0xd800u) GETUTF16INC(c, eptr);
/* Get the next character, testing for UTF-16 mode, and advancing the pointer.
This is called when we don't know if we are in UTF-16 mode. */
#define GETCHARINCTEST(c, eptr) \
c = *eptr++; \
if (utf && (c & 0xfc00u) == 0xd800u) GETUTF16INC(c, eptr);
/* Base macro to pick up the low surrogate of a UTF-16 character, not
advancing the pointer, incrementing the length. */
#define GETUTF16LEN(c, eptr, len) \
{ c = (((c & 0x3ffu) << 10) | (eptr[1] & 0x3ffu)) + 0x10000u; len++; }
/* Get the next UTF-16 character, not advancing the pointer, incrementing
length if there is a low surrogate. This is called when we know we are in
UTF-16 mode. */
#define GETCHARLEN(c, eptr, len) \
c = *eptr; \
if ((c & 0xfc00u) == 0xd800u) GETUTF16LEN(c, eptr, len);
/* Get the next UTF-816character, testing for UTF-16 mode, not advancing the
pointer, incrementing length if there is a low surrogate. This is called when
we do not know if we are in UTF-16 mode. */
#define GETCHARLENTEST(c, eptr, len) \
c = *eptr; \
if (utf && (c & 0xfc00u) == 0xd800u) GETUTF16LEN(c, eptr, len);
/* If the pointer is not at the start of a character, move it back until
it is. This is called only in UTF-16 mode - we don't put a test within the
macro because almost all calls are already within a block of UTF-16 only
code. */
#define BACKCHAR(eptr) if ((*eptr & 0xfc00u) == 0xdc00u) eptr--
/* Same as above, just in the other direction. */
#define FORWARDCHAR(eptr) if ((*eptr & 0xfc00u) == 0xdc00u) eptr++
#define FORWARDCHARTEST(eptr,end) if (eptr < end && (*eptr & 0xfc00u) == 0xdc00u) eptr++
/* Same as above, but it allows a fully customizable form. */
#define ACROSSCHAR(condition, eptr, action) \
if ((condition) && ((*eptr) & 0xfc00u) == 0xdc00u) action
/* Deposit a character into memory, returning the number of code units. */
#define PUTCHAR(c, p) ((utf && c > MAX_UTF_SINGLE_CU)? \
PRIV(ord2utf)(c,p) : (*p = c, 1))
/* ------------------- 32-bit support ------------------ */
#else
/* These are trivial for the 32-bit library, since all UTF-32 characters fit
into one PCRE2_UCHAR unit. */
#define MAX_UTF_SINGLE_CU (0x10ffffu)
#define HAS_EXTRALEN(c) (0)
#define GET_EXTRALEN(c) (0)
#define NOT_FIRSTCU(c) (0)
/* Get the next UTF-32 character, not advancing the pointer. This is called when
we know we are in UTF-32 mode. */
#define GETCHAR(c, eptr) \
c = *(eptr);
/* Get the next UTF-32 character, testing for UTF-32 mode, and not advancing the
pointer. */
#define GETCHARTEST(c, eptr) \
c = *(eptr);
/* Get the next UTF-32 character, advancing the pointer. This is called when we
know we are in UTF-32 mode. */
#define GETCHARINC(c, eptr) \
c = *((eptr)++);
/* Get the next character, testing for UTF-32 mode, and advancing the pointer.
This is called when we don't know if we are in UTF-32 mode. */
#define GETCHARINCTEST(c, eptr) \
c = *((eptr)++);
/* Get the next UTF-32 character, not advancing the pointer, not incrementing
length (since all UTF-32 is of length 1). This is called when we know we are in
UTF-32 mode. */
#define GETCHARLEN(c, eptr, len) \
GETCHAR(c, eptr)
/* Get the next UTF-32character, testing for UTF-32 mode, not advancing the
pointer, not incrementing the length (since all UTF-32 is of length 1).
This is called when we do not know if we are in UTF-32 mode. */
#define GETCHARLENTEST(c, eptr, len) \
GETCHARTEST(c, eptr)
/* If the pointer is not at the start of a character, move it back until
it is. This is called only in UTF-32 mode - we don't put a test within the
macro because almost all calls are already within a block of UTF-32 only
code.
These are all no-ops since all UTF-32 characters fit into one PCRE2_UCHAR. */
#define BACKCHAR(eptr) do { } while (0)
/* Same as above, just in the other direction. */
#define FORWARDCHAR(eptr) do { } while (0)
#define FORWARDCHARTEST(eptr,end) do { } while (0)
/* Same as above, but it allows a fully customizable form. */
#define ACROSSCHAR(condition, eptr, action) do { } while (0)
/* Deposit a character into memory, returning the number of code units. */
#define PUTCHAR(c, p) (*p = c, 1)
#endif /* UTF-32 character handling */
#endif /* SUPPORT_UNICODE */
/* Mode-dependent macros that have the same definition in all modes. */
#define CU2BYTES(x) ((x)*((PCRE2_CODE_UNIT_WIDTH/8)))
#define BYTES2CU(x) ((x)/((PCRE2_CODE_UNIT_WIDTH/8)))
#define PUTINC(a,n,d) PUT(a,n,d), a += LINK_SIZE
#define PUT2INC(a,n,d) PUT2(a,n,d), a += IMM2_SIZE
/* ----------------------- HIDDEN STRUCTURES ----------------------------- */
/* NOTE: All these structures *must* start with a pcre2_memctl structure. The
code that uses them is simpler because it assumes this. */
/* The real general context structure. At present it holds only data for custom
memory control. */
typedef struct pcre2_real_general_context {
pcre2_memctl memctl;
} pcre2_real_general_context;
/* The real compile context structure */
typedef struct pcre2_real_compile_context {
pcre2_memctl memctl;
int (*stack_guard)(uint32_t, void *);
void *stack_guard_data;
const uint8_t *tables;
PCRE2_SIZE max_pattern_length;
uint16_t bsr_convention;
uint16_t newline_convention;
uint32_t parens_nest_limit;
uint32_t extra_options;
} pcre2_real_compile_context;
/* The real match context structure. */
typedef struct pcre2_real_match_context {
pcre2_memctl memctl;
#ifdef SUPPORT_JIT
pcre2_jit_callback jit_callback;
void *jit_callback_data;
#endif
int (*callout)(pcre2_callout_block *, void *);
void *callout_data;
int (*substitute_callout)(pcre2_substitute_callout_block *, void *);
void *substitute_callout_data;
PCRE2_SIZE offset_limit;
uint32_t heap_limit;
uint32_t match_limit;
uint32_t depth_limit;
} pcre2_real_match_context;
/* The real convert context structure. */
typedef struct pcre2_real_convert_context {
pcre2_memctl memctl;
uint32_t glob_separator;
uint32_t glob_escape;
} pcre2_real_convert_context;
/* The real compiled code structure. The type for the blocksize field is
defined specially because it is required in pcre2_serialize_decode() when
copying the size from possibly unaligned memory into a variable of the same
type. Use a macro rather than a typedef to avoid compiler warnings when this
file is included multiple times by pcre2test. LOOKBEHIND_MAX specifies the
largest lookbehind that is supported. (OP_REVERSE in a pattern has a 16-bit
argument in 8-bit and 16-bit modes, so we need no more than a 16-bit field
here.) */
#undef CODE_BLOCKSIZE_TYPE
#define CODE_BLOCKSIZE_TYPE size_t
#undef LOOKBEHIND_MAX
#define LOOKBEHIND_MAX UINT16_MAX
typedef struct pcre2_real_code {
pcre2_memctl memctl; /* Memory control fields */
const uint8_t *tables; /* The character tables */
void *executable_jit; /* Pointer to JIT code */
uint8_t start_bitmap[32]; /* Bitmap for starting code unit < 256 */
CODE_BLOCKSIZE_TYPE blocksize; /* Total (bytes) that was malloc-ed */
uint32_t magic_number; /* Paranoid and endianness check */
uint32_t compile_options; /* Options passed to pcre2_compile() */
uint32_t overall_options; /* Options after processing the pattern */
uint32_t extra_options; /* Taken from compile_context */
uint32_t flags; /* Various state flags */
uint32_t limit_heap; /* Limit set in the pattern */
uint32_t limit_match; /* Limit set in the pattern */
uint32_t limit_depth; /* Limit set in the pattern */
uint32_t first_codeunit; /* Starting code unit */
uint32_t last_codeunit; /* This codeunit must be seen */
uint16_t bsr_convention; /* What \R matches */
uint16_t newline_convention; /* What is a newline? */
uint16_t max_lookbehind; /* Longest lookbehind (characters) */
uint16_t minlength; /* Minimum length of match */
uint16_t top_bracket; /* Highest numbered group */
uint16_t top_backref; /* Highest numbered back reference */
uint16_t name_entry_size; /* Size (code units) of table entries */
uint16_t name_count; /* Number of name entries in the table */
} pcre2_real_code;
/* The real match data structure. Define ovector as large as it can ever
actually be so that array bound checkers don't grumble. Memory for this
structure is obtained by calling pcre2_match_data_create(), which sets the size
as the offset of ovector plus a pair of elements for each capturable string, so
the size varies from call to call. As the maximum number of capturing
subpatterns is 65535 we must allow for 65536 strings to include the overall
match. (See also the heapframe structure below.) */
struct heapframe; /* Forward reference */
typedef struct pcre2_real_match_data {
pcre2_memctl memctl; /* Memory control fields */
const pcre2_real_code *code; /* The pattern used for the match */
PCRE2_SPTR subject; /* The subject that was matched */
PCRE2_SPTR mark; /* Pointer to last mark */
struct heapframe *heapframes; /* Backtracking frames heap memory */
PCRE2_SIZE heapframes_size; /* Malloc-ed size */
PCRE2_SIZE leftchar; /* Offset to leftmost code unit */
PCRE2_SIZE rightchar; /* Offset to rightmost code unit */
PCRE2_SIZE startchar; /* Offset to starting code unit */
uint8_t matchedby; /* Type of match (normal, JIT, DFA) */
uint8_t flags; /* Various flags */
uint16_t oveccount; /* Number of pairs */
int rc; /* The return code from the match */
PCRE2_SIZE ovector[131072]; /* Must be last in the structure */
} pcre2_real_match_data;
/* ----------------------- PRIVATE STRUCTURES ----------------------------- */
/* These structures are not needed for pcre2test. */
#ifndef PCRE2_PCRE2TEST
/* Structures for checking for mutual recursion when scanning compiled or
parsed code. */
typedef struct recurse_check {
struct recurse_check *prev;
PCRE2_SPTR group;
} recurse_check;
typedef struct parsed_recurse_check {
struct parsed_recurse_check *prev;
uint32_t *groupptr;
} parsed_recurse_check;
/* Structure for building a cache when filling in recursion offsets. */
typedef struct recurse_cache {
PCRE2_SPTR group;
int groupnumber;
} recurse_cache;
/* Structure for maintaining a chain of pointers to the currently incomplete
branches, for testing for left recursion while compiling. */
typedef struct branch_chain {
struct branch_chain *outer;
PCRE2_UCHAR *current_branch;
} branch_chain;
/* Structure for building a list of named groups during the first pass of
compiling. */
typedef struct named_group {
PCRE2_SPTR name; /* Points to the name in the pattern */
uint32_t number; /* Group number */
uint16_t length; /* Length of the name */
uint16_t isdup; /* TRUE if a duplicate */
} named_group;
/* Structure for passing "static" information around between the functions
doing the compiling, so that they are thread-safe. */
typedef struct compile_block {
pcre2_real_compile_context *cx; /* Points to the compile context */
const uint8_t *lcc; /* Points to lower casing table */
const uint8_t *fcc; /* Points to case-flipping table */
const uint8_t *cbits; /* Points to character type table */
const uint8_t *ctypes; /* Points to table of type maps */
PCRE2_SPTR start_workspace; /* The start of working space */
PCRE2_SPTR start_code; /* The start of the compiled code */
PCRE2_SPTR start_pattern; /* The start of the pattern */
PCRE2_SPTR end_pattern; /* The end of the pattern */
PCRE2_UCHAR *name_table; /* The name/number table */
PCRE2_SIZE workspace_size; /* Size of workspace */
PCRE2_SIZE small_ref_offset[10]; /* Offsets for \1 to \9 */
PCRE2_SIZE erroroffset; /* Offset of error in pattern */
uint16_t names_found; /* Number of entries so far */
uint16_t name_entry_size; /* Size of each entry */
uint16_t parens_depth; /* Depth of nested parentheses */
uint16_t assert_depth; /* Depth of nested assertions */
open_capitem *open_caps; /* Chain of open capture items */
named_group *named_groups; /* Points to vector in pre-compile */
uint32_t named_group_list_size; /* Number of entries in the list */
uint32_t external_options; /* External (initial) options */
uint32_t external_flags; /* External flag bits to be set */
uint32_t bracount; /* Count of capturing parentheses */
uint32_t lastcapture; /* Last capture encountered */
uint32_t *parsed_pattern; /* Parsed pattern buffer */
uint32_t *parsed_pattern_end; /* Parsed pattern should not get here */
uint32_t *groupinfo; /* Group info vector */
uint32_t top_backref; /* Maximum back reference */
uint32_t backref_map; /* Bitmap of low back refs */
uint32_t nltype; /* Newline type */
uint32_t nllen; /* Newline string length */
uint32_t class_range_start; /* Overall class range start */
uint32_t class_range_end; /* Overall class range end */
PCRE2_UCHAR nl[4]; /* Newline string when fixed length */
uint32_t req_varyopt; /* "After variable item" flag for reqbyte */
int max_lookbehind; /* Maximum lookbehind (characters) */
BOOL had_accept; /* (*ACCEPT) encountered */
BOOL had_pruneorskip; /* (*PRUNE) or (*SKIP) encountered */
BOOL had_recurse; /* Had a recursion or subroutine call */
BOOL dupnames; /* Duplicate names exist */
} compile_block;
/* Structure for keeping the properties of the in-memory stack used
by the JIT matcher. */
typedef struct pcre2_real_jit_stack {
pcre2_memctl memctl;
void* stack;
} pcre2_real_jit_stack;
/* Structure for items in a linked list that represents an explicit recursive
call within the pattern when running pcre2_dfa_match(). */
typedef struct dfa_recursion_info {
struct dfa_recursion_info *prevrec;
PCRE2_SPTR subject_position;
uint32_t group_num;
} dfa_recursion_info;
/* Structure for "stack" frames that are used for remembering backtracking
positions during matching. As these are used in a vector, with the ovector item
being extended, the size of the structure must be a multiple of PCRE2_SIZE. The
only way to check this at compile time is to force an error by generating an
array with a negative size. By putting this in a typedef (which is never used),
we don't generate any code when all is well. */
typedef struct heapframe {
/* The first set of fields are variables that have to be preserved over calls
to RRMATCH(), but which do not need to be copied to new frames. */
PCRE2_SPTR ecode; /* The current position in the pattern */
PCRE2_SPTR temp_sptr[2]; /* Used for short-term PCRE_SPTR values */
PCRE2_SIZE length; /* Used for character, string, or code lengths */
PCRE2_SIZE back_frame; /* Amount to subtract on RRETURN */
PCRE2_SIZE temp_size; /* Used for short-term PCRE2_SIZE values */
uint32_t rdepth; /* "Recursion" depth */
uint32_t group_frame_type; /* Type information for group frames */
uint32_t temp_32[4]; /* Used for short-term 32-bit or BOOL values */
uint8_t return_id; /* Where to go on in internal "return" */
uint8_t op; /* Processing opcode */
/* At this point, the structure is 16-bit aligned. On most architectures
the alignment requirement for a pointer will ensure that the eptr field below
is 32-bit or 64-bit aligned. However, on m68k it is fine to have a pointer
that is 16-bit aligned. We must therefore ensure that what comes between here
and eptr is an odd multiple of 16 bits so as to get back into 32-bit
alignment. This happens naturally when PCRE2_UCHAR is 8 bits wide, but needs
fudges in the other cases. In the 32-bit case the padding comes first so that
the occu field itself is 32-bit aligned. Without the padding, this structure
is no longer a multiple of PCRE2_SIZE on m68k, and the check below fails. */
#if PCRE2_CODE_UNIT_WIDTH == 8
PCRE2_UCHAR occu[6]; /* Used for other case code units */
#elif PCRE2_CODE_UNIT_WIDTH == 16
PCRE2_UCHAR occu[2]; /* Used for other case code units */
uint8_t unused[2]; /* Ensure 32-bit alignment (see above) */
#else
uint8_t unused[2]; /* Ensure 32-bit alignment (see above) */
PCRE2_UCHAR occu[1]; /* Used for other case code units */
#endif
/* The rest have to be copied from the previous frame whenever a new frame
becomes current. The final field is specified as a large vector so that
runtime array bound checks don't catch references to it. However, for any
specific call to pcre2_match() the memory allocated for each frame structure
allows for exactly the right size ovector for the number of capturing
parentheses. (See also the comment for pcre2_real_match_data above.) */
PCRE2_SPTR eptr; /* MUST BE FIRST */
PCRE2_SPTR start_match; /* Can be adjusted by \K */
PCRE2_SPTR mark; /* Most recent mark on the success path */
uint32_t current_recurse; /* Current (deepest) recursion number */
uint32_t capture_last; /* Most recent capture */
PCRE2_SIZE last_group_offset; /* Saved offset to most recent group frame */
PCRE2_SIZE offset_top; /* Offset after highest capture */
PCRE2_SIZE ovector[131072]; /* Must be last in the structure */
} heapframe;
/* This typedef is a check that the size of the heapframe structure is a
multiple of PCRE2_SIZE. See various comments above. */
typedef char check_heapframe_size[
((sizeof(heapframe) % sizeof(PCRE2_SIZE)) == 0)? (+1):(-1)];
/* Structure for computing the alignment of heapframe. */
typedef struct heapframe_align {
char unalign; /* Completely unalign the current offset */
heapframe frame; /* Offset is its alignment */
} heapframe_align;
/* This define is the minimum alignment required for a heapframe, in bytes. */
#define HEAPFRAME_ALIGNMENT offsetof(heapframe_align, frame)
/* Structure for passing "static" information around between the functions
doing traditional NFA matching (pcre2_match() and friends). */
typedef struct match_block {
pcre2_memctl memctl; /* For general use */
PCRE2_SIZE heap_limit; /* As it says */
uint32_t match_limit; /* As it says */
uint32_t match_limit_depth; /* As it says */
uint32_t match_call_count; /* Number of times a new frame is created */
BOOL hitend; /* Hit the end of the subject at some point */
BOOL hasthen; /* Pattern contains (*THEN) */
BOOL allowemptypartial; /* Allow empty hard partial */
const uint8_t *lcc; /* Points to lower casing table */
const uint8_t *fcc; /* Points to case-flipping table */
const uint8_t *ctypes; /* Points to table of type maps */
PCRE2_SIZE start_offset; /* The start offset value */
PCRE2_SIZE end_offset_top; /* Highwater mark at end of match */
uint16_t partial; /* PARTIAL options */
uint16_t bsr_convention; /* \R interpretation */
uint16_t name_count; /* Number of names in name table */
uint16_t name_entry_size; /* Size of entry in names table */
PCRE2_SPTR name_table; /* Table of group names */
PCRE2_SPTR start_code; /* For use when recursing */
PCRE2_SPTR start_subject; /* Start of the subject string */
PCRE2_SPTR check_subject; /* Where UTF-checked from */
PCRE2_SPTR end_subject; /* End of the subject string */
PCRE2_SPTR end_match_ptr; /* Subject position at end match */
PCRE2_SPTR start_used_ptr; /* Earliest consulted character */
PCRE2_SPTR last_used_ptr; /* Latest consulted character */
PCRE2_SPTR mark; /* Mark pointer to pass back on success */
PCRE2_SPTR nomatch_mark; /* Mark pointer to pass back on failure */
PCRE2_SPTR verb_ecode_ptr; /* For passing back info */
PCRE2_SPTR verb_skip_ptr; /* For passing back a (*SKIP) name */
uint32_t verb_current_recurse; /* Current recurse when (*VERB) happens */
uint32_t moptions; /* Match options */
uint32_t poptions; /* Pattern options */
uint32_t skip_arg_count; /* For counting SKIP_ARGs */
uint32_t ignore_skip_arg; /* For re-run when SKIP arg name not found */
uint32_t nltype; /* Newline type */
uint32_t nllen; /* Newline string length */
PCRE2_UCHAR nl[4]; /* Newline string when fixed */
pcre2_callout_block *cb; /* Points to a callout block */
void *callout_data; /* To pass back to callouts */
int (*callout)(pcre2_callout_block *,void *); /* Callout function or NULL */
} match_block;
/* A similar structure is used for the same purpose by the DFA matching
functions. */
typedef struct dfa_match_block {
pcre2_memctl memctl; /* For general use */
PCRE2_SPTR start_code; /* Start of the compiled pattern */
PCRE2_SPTR start_subject ; /* Start of the subject string */
PCRE2_SPTR end_subject; /* End of subject string */
PCRE2_SPTR start_used_ptr; /* Earliest consulted character */
PCRE2_SPTR last_used_ptr; /* Latest consulted character */
const uint8_t *tables; /* Character tables */
PCRE2_SIZE start_offset; /* The start offset value */
PCRE2_SIZE heap_limit; /* As it says */
PCRE2_SIZE heap_used; /* As it says */
uint32_t match_limit; /* As it says */
uint32_t match_limit_depth; /* As it says */
uint32_t match_call_count; /* Number of calls of internal function */
uint32_t moptions; /* Match options */
uint32_t poptions; /* Pattern options */
uint32_t nltype; /* Newline type */
uint32_t nllen; /* Newline string length */
BOOL allowemptypartial; /* Allow empty hard partial */
PCRE2_UCHAR nl[4]; /* Newline string when fixed */
uint16_t bsr_convention; /* \R interpretation */
pcre2_callout_block *cb; /* Points to a callout block */
void *callout_data; /* To pass back to callouts */
int (*callout)(pcre2_callout_block *,void *); /* Callout function or NULL */
dfa_recursion_info *recursive; /* Linked list of recursion data */
} dfa_match_block;
#endif /* PCRE2_PCRE2TEST */
/* End of pcre2_intmodedep.h */

14507
Kha/Backends/Kore-hxcpp/khacpp/project/thirdparty/pcre2-10.42-16/src/pcre2_jit_compile.c vendored Normal file
View File

File diff suppressed because it is too large Load Diff

186
Kha/Backends/Kore-hxcpp/khacpp/project/thirdparty/pcre2-10.42-16/src/pcre2_jit_match.c vendored Normal file
View File

@ -0,0 +1,186 @@
/*************************************************
* Perl-Compatible Regular Expressions *
*************************************************/
/* PCRE is a library of functions to support regular expressions whose syntax
and semantics are as close as possible to those of the Perl 5 language.
Written by Philip Hazel
Original API code Copyright (c) 1997-2012 University of Cambridge
New API code Copyright (c) 2016-2018 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
modification, are permitted provided that the following conditions are met:
* Redistributions of source code must retain the above copyright notice,
this list of conditions and the following disclaimer.
* Redistributions in binary form must reproduce the above copyright
notice, this list of conditions and the following disclaimer in the
documentation and/or other materials provided with the distribution.
* Neither the name of the University of Cambridge nor the names of its
contributors may be used to endorse or promote products derived from
this software without specific prior written permission.
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
POSSIBILITY OF SUCH DAMAGE.
-----------------------------------------------------------------------------
*/
#ifndef INCLUDED_FROM_PCRE2_JIT_COMPILE
#error This file must be included from pcre2_jit_compile.c.
#endif
#ifdef SUPPORT_JIT
static SLJIT_NOINLINE int jit_machine_stack_exec(jit_arguments *arguments, jit_function executable_func)
{
sljit_u8 local_space[MACHINE_STACK_SIZE];
struct sljit_stack local_stack;
local_stack.min_start = local_space;
local_stack.start = local_space;
local_stack.end = local_space + MACHINE_STACK_SIZE;
local_stack.top = local_space + MACHINE_STACK_SIZE;
arguments->stack = &local_stack;
return executable_func(arguments);
}
#endif
/*************************************************
* Do a JIT pattern match *
*************************************************/
/* This function runs a JIT pattern match.
Arguments:
code points to the compiled expression
subject points to the subject string
length length of subject string (may contain binary zeros)
start_offset where to start in the subject string
options option bits
match_data points to a match_data block
mcontext points to a match context
Returns: > 0 => success; value is the number of ovector pairs filled
= 0 => success, but ovector is not big enough
-1 => failed to match (PCRE_ERROR_NOMATCH)
< -1 => some kind of unexpected problem
*/
PCRE2_EXP_DEFN int PCRE2_CALL_CONVENTION
pcre2_jit_match(const pcre2_code *code, PCRE2_SPTR subject, PCRE2_SIZE length,
PCRE2_SIZE start_offset, uint32_t options, pcre2_match_data *match_data,
pcre2_match_context *mcontext)
{
#ifndef SUPPORT_JIT
(void)code;
(void)subject;
(void)length;
(void)start_offset;
(void)options;
(void)match_data;
(void)mcontext;
return PCRE2_ERROR_JIT_BADOPTION;
#else /* SUPPORT_JIT */
pcre2_real_code *re = (pcre2_real_code *)code;
executable_functions *functions = (executable_functions *)re->executable_jit;
pcre2_jit_stack *jit_stack;
uint32_t oveccount = match_data->oveccount;
uint32_t max_oveccount;
union {
void *executable_func;
jit_function call_executable_func;
} convert_executable_func;
jit_arguments arguments;
int rc;
int index = 0;
if ((options & PCRE2_PARTIAL_HARD) != 0)
index = 2;
else if ((options & PCRE2_PARTIAL_SOFT) != 0)
index = 1;
if (functions == NULL || functions->executable_funcs[index] == NULL)
return PCRE2_ERROR_JIT_BADOPTION;
/* Sanity checks should be handled by pcre2_match. */
arguments.str = subject + start_offset;
arguments.begin = subject;
arguments.end = subject + length;
arguments.match_data = match_data;
arguments.startchar_ptr = subject;
arguments.mark_ptr = NULL;
arguments.options = options;
if (mcontext != NULL)
{
arguments.callout = mcontext->callout;
arguments.callout_data = mcontext->callout_data;
arguments.offset_limit = mcontext->offset_limit;
arguments.limit_match = (mcontext->match_limit < re->limit_match)?
mcontext->match_limit : re->limit_match;
if (mcontext->jit_callback != NULL)
jit_stack = mcontext->jit_callback(mcontext->jit_callback_data);
else
jit_stack = (pcre2_jit_stack *)mcontext->jit_callback_data;
}
else
{
arguments.callout = NULL;
arguments.callout_data = NULL;
arguments.offset_limit = PCRE2_UNSET;
arguments.limit_match = (MATCH_LIMIT < re->limit_match)?
MATCH_LIMIT : re->limit_match;
jit_stack = NULL;
}
max_oveccount = functions->top_bracket;
if (oveccount > max_oveccount)
oveccount = max_oveccount;
arguments.oveccount = oveccount << 1;
convert_executable_func.executable_func = functions->executable_funcs[index];
if (jit_stack != NULL)
{
arguments.stack = (struct sljit_stack *)(jit_stack->stack);
rc = convert_executable_func.call_executable_func(&arguments);
}
else
rc = jit_machine_stack_exec(&arguments, convert_executable_func.call_executable_func);
if (rc > (int)oveccount)
rc = 0;
match_data->code = re;
match_data->subject = (rc >= 0 || rc == PCRE2_ERROR_PARTIAL)? subject : NULL;
match_data->rc = rc;
match_data->startchar = arguments.startchar_ptr - subject;
match_data->leftchar = 0;
match_data->rightchar = 0;
match_data->mark = arguments.mark_ptr;
match_data->matchedby = PCRE2_MATCHEDBY_JIT;
return match_data->rc;
#endif /* SUPPORT_JIT */
}
/* End of pcre2_jit_match.c */

234
Kha/Backends/Kore-hxcpp/khacpp/project/thirdparty/pcre2-10.42-16/src/pcre2_jit_misc.c vendored Normal file
View File

@ -0,0 +1,234 @@
/*************************************************
* Perl-Compatible Regular Expressions *
*************************************************/
/* PCRE is a library of functions to support regular expressions whose syntax
and semantics are as close as possible to those of the Perl 5 language.
Written by Philip Hazel
Original API code Copyright (c) 1997-2012 University of Cambridge
New API code Copyright (c) 2016 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
modification, are permitted provided that the following conditions are met:
* Redistributions of source code must retain the above copyright notice,
this list of conditions and the following disclaimer.
* Redistributions in binary form must reproduce the above copyright
notice, this list of conditions and the following disclaimer in the
documentation and/or other materials provided with the distribution.
* Neither the name of the University of Cambridge nor the names of its
contributors may be used to endorse or promote products derived from
this software without specific prior written permission.
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
POSSIBILITY OF SUCH DAMAGE.
-----------------------------------------------------------------------------
*/
#ifndef INCLUDED_FROM_PCRE2_JIT_COMPILE
#error This file must be included from pcre2_jit_compile.c.
#endif
/*************************************************
* Free JIT read-only data *
*************************************************/
void
PRIV(jit_free_rodata)(void *current, void *allocator_data)
{
#ifndef SUPPORT_JIT
(void)current;
(void)allocator_data;
#else /* SUPPORT_JIT */
void *next;
SLJIT_UNUSED_ARG(allocator_data);
while (current != NULL)
{
next = *(void**)current;
SLJIT_FREE(current, allocator_data);
current = next;
}
#endif /* SUPPORT_JIT */
}
/*************************************************
* Free JIT compiled code *
*************************************************/
void
PRIV(jit_free)(void *executable_jit, pcre2_memctl *memctl)
{
#ifndef SUPPORT_JIT
(void)executable_jit;
(void)memctl;
#else /* SUPPORT_JIT */
executable_functions *functions = (executable_functions *)executable_jit;
void *allocator_data = memctl;
int i;
for (i = 0; i < JIT_NUMBER_OF_COMPILE_MODES; i++)
{
if (functions->executable_funcs[i] != NULL)
sljit_free_code(functions->executable_funcs[i], NULL);
PRIV(jit_free_rodata)(functions->read_only_data_heads[i], allocator_data);
}
SLJIT_FREE(functions, allocator_data);
#endif /* SUPPORT_JIT */
}
/*************************************************
* Free unused JIT memory *
*************************************************/
PCRE2_EXP_DEFN void PCRE2_CALL_CONVENTION
pcre2_jit_free_unused_memory(pcre2_general_context *gcontext)
{
#ifndef SUPPORT_JIT
(void)gcontext; /* Suppress warning */
#else /* SUPPORT_JIT */
SLJIT_UNUSED_ARG(gcontext);
#if (defined SLJIT_EXECUTABLE_ALLOCATOR && SLJIT_EXECUTABLE_ALLOCATOR)
sljit_free_unused_memory_exec();
#endif /* SLJIT_EXECUTABLE_ALLOCATOR */
#endif /* SUPPORT_JIT */
}
/*************************************************
* Allocate a JIT stack *
*************************************************/
PCRE2_EXP_DEFN pcre2_jit_stack * PCRE2_CALL_CONVENTION
pcre2_jit_stack_create(size_t startsize, size_t maxsize,
pcre2_general_context *gcontext)
{
#ifndef SUPPORT_JIT
(void)gcontext;
(void)startsize;
(void)maxsize;
return NULL;
#else /* SUPPORT_JIT */
pcre2_jit_stack *jit_stack;
if (startsize == 0 || maxsize == 0 || maxsize > SIZE_MAX - STACK_GROWTH_RATE)
return NULL;
if (startsize > maxsize)
startsize = maxsize;
startsize = (startsize + STACK_GROWTH_RATE - 1) & ~(STACK_GROWTH_RATE - 1);
maxsize = (maxsize + STACK_GROWTH_RATE - 1) & ~(STACK_GROWTH_RATE - 1);
jit_stack = PRIV(memctl_malloc)(sizeof(pcre2_real_jit_stack), (pcre2_memctl *)gcontext);
if (jit_stack == NULL) return NULL;
jit_stack->stack = sljit_allocate_stack(startsize, maxsize, &jit_stack->memctl);
if (jit_stack->stack == NULL)
{
jit_stack->memctl.free(jit_stack, jit_stack->memctl.memory_data);
return NULL;
}
return jit_stack;
#endif
}
/*************************************************
* Assign a JIT stack to a pattern *
*************************************************/
PCRE2_EXP_DEFN void PCRE2_CALL_CONVENTION
pcre2_jit_stack_assign(pcre2_match_context *mcontext, pcre2_jit_callback callback,
void *callback_data)
{
#ifndef SUPPORT_JIT
(void)mcontext;
(void)callback;
(void)callback_data;
#else /* SUPPORT_JIT */
if (mcontext == NULL) return;
mcontext->jit_callback = callback;
mcontext->jit_callback_data = callback_data;
#endif /* SUPPORT_JIT */
}
/*************************************************
* Free a JIT stack *
*************************************************/
PCRE2_EXP_DEFN void PCRE2_CALL_CONVENTION
pcre2_jit_stack_free(pcre2_jit_stack *jit_stack)
{
#ifndef SUPPORT_JIT
(void)jit_stack;
#else /* SUPPORT_JIT */
if (jit_stack != NULL)
{
sljit_free_stack((struct sljit_stack *)(jit_stack->stack), &jit_stack->memctl);
jit_stack->memctl.free(jit_stack, jit_stack->memctl.memory_data);
}
#endif /* SUPPORT_JIT */
}
/*************************************************
* Get target CPU type *
*************************************************/
const char*
PRIV(jit_get_target)(void)
{
#ifndef SUPPORT_JIT
return "JIT is not supported";
#else /* SUPPORT_JIT */
return sljit_get_platform_name();
#endif /* SUPPORT_JIT */
}
/*************************************************
* Get size of JIT code *
*************************************************/
size_t
PRIV(jit_get_size)(void *executable_jit)
{
#ifndef SUPPORT_JIT
(void)executable_jit;
return 0;
#else /* SUPPORT_JIT */
sljit_uw *executable_sizes = ((executable_functions *)executable_jit)->executable_sizes;
SLJIT_COMPILE_ASSERT(JIT_NUMBER_OF_COMPILE_MODES == 3, number_of_compile_modes_changed);
return executable_sizes[0] + executable_sizes[1] + executable_sizes[2];
#endif
}
/* End of pcre2_jit_misc.c */

349
Kha/Backends/Kore-hxcpp/khacpp/project/thirdparty/pcre2-10.42-16/src/pcre2_jit_neon_inc.h vendored Normal file
View File

@ -0,0 +1,349 @@
/*************************************************
* Perl-Compatible Regular Expressions *
*************************************************/
/* PCRE is a library of functions to support regular expressions whose syntax
and semantics are as close as possible to those of the Perl 5 language.
Written by Philip Hazel
This module by Zoltan Herczeg and Sebastian Pop
Original API code Copyright (c) 1997-2012 University of Cambridge
New API code Copyright (c) 2016-2019 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
modification, are permitted provided that the following conditions are met:
* Redistributions of source code must retain the above copyright notice,
this list of conditions and the following disclaimer.
* Redistributions in binary form must reproduce the above copyright
notice, this list of conditions and the following disclaimer in the
documentation and/or other materials provided with the distribution.
* Neither the name of the University of Cambridge nor the names of its
contributors may be used to endorse or promote products derived from
this software without specific prior written permission.
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
POSSIBILITY OF SUCH DAMAGE.
-----------------------------------------------------------------------------
*/
# if defined(FFCS)
# if defined(FF_UTF)
# define FF_FUN ffcs_utf
# else
# define FF_FUN ffcs
# endif
# elif defined(FFCS_2)
# if defined(FF_UTF)
# define FF_FUN ffcs_2_utf
# else
# define FF_FUN ffcs_2
# endif
# elif defined(FFCS_MASK)
# if defined(FF_UTF)
# define FF_FUN ffcs_mask_utf
# else
# define FF_FUN ffcs_mask
# endif
# elif defined(FFCPS_0)
# if defined (FF_UTF)
# define FF_FUN ffcps_0_utf
# else
# define FF_FUN ffcps_0
# endif
# elif defined (FFCPS_1)
# if defined (FF_UTF)
# define FF_FUN ffcps_1_utf
# else
# define FF_FUN ffcps_1
# endif
# elif defined (FFCPS_DEFAULT)
# if defined (FF_UTF)
# define FF_FUN ffcps_default_utf
# else
# define FF_FUN ffcps_default
# endif
# endif
static sljit_u8* SLJIT_FUNC FF_FUN(sljit_u8 *str_end, sljit_u8 *str_ptr, sljit_uw offs1, sljit_uw offs2, sljit_uw chars)
#undef FF_FUN
{
quad_word qw;
int_char ic;
SLJIT_UNUSED_ARG(offs1);
SLJIT_UNUSED_ARG(offs2);
ic.x = chars;
#if defined(FFCS)
sljit_u8 c1 = ic.c.c1;
vect_t vc1 = VDUPQ(c1);
#elif defined(FFCS_2)
sljit_u8 c1 = ic.c.c1;
vect_t vc1 = VDUPQ(c1);
sljit_u8 c2 = ic.c.c2;
vect_t vc2 = VDUPQ(c2);
#elif defined(FFCS_MASK)
sljit_u8 c1 = ic.c.c1;
vect_t vc1 = VDUPQ(c1);
sljit_u8 mask = ic.c.c2;
vect_t vmask = VDUPQ(mask);
#endif
#if defined(FFCPS)
compare_type compare1_type = compare_match1;
compare_type compare2_type = compare_match1;
vect_t cmp1a, cmp1b, cmp2a, cmp2b;
const sljit_u32 diff = IN_UCHARS(offs1 - offs2);
PCRE2_UCHAR char1a = ic.c.c1;
PCRE2_UCHAR char2a = ic.c.c3;
# ifdef FFCPS_CHAR1A2A
cmp1a = VDUPQ(char1a);
cmp2a = VDUPQ(char2a);
cmp1b = VDUPQ(0); /* to avoid errors on older compilers -Werror=maybe-uninitialized */
cmp2b = VDUPQ(0); /* to avoid errors on older compilers -Werror=maybe-uninitialized */
# else
PCRE2_UCHAR char1b = ic.c.c2;
PCRE2_UCHAR char2b = ic.c.c4;
if (char1a == char1b)
{
cmp1a = VDUPQ(char1a);
cmp1b = VDUPQ(0); /* to avoid errors on older compilers -Werror=maybe-uninitialized */
}
else
{
sljit_u32 bit1 = char1a ^ char1b;
if (is_powerof2(bit1))
{
compare1_type = compare_match1i;
cmp1a = VDUPQ(char1a | bit1);
cmp1b = VDUPQ(bit1);
}
else
{
compare1_type = compare_match2;
cmp1a = VDUPQ(char1a);
cmp1b = VDUPQ(char1b);
}
}
if (char2a == char2b)
{
cmp2a = VDUPQ(char2a);
cmp2b = VDUPQ(0); /* to avoid errors on older compilers -Werror=maybe-uninitialized */
}
else
{
sljit_u32 bit2 = char2a ^ char2b;
if (is_powerof2(bit2))
{
compare2_type = compare_match1i;
cmp2a = VDUPQ(char2a | bit2);
cmp2b = VDUPQ(bit2);
}
else
{
compare2_type = compare_match2;
cmp2a = VDUPQ(char2a);
cmp2b = VDUPQ(char2b);
}
}
# endif
str_ptr += IN_UCHARS(offs1);
#endif
#if PCRE2_CODE_UNIT_WIDTH != 8
vect_t char_mask = VDUPQ(0xff);
#endif
#if defined(FF_UTF)
restart:;
#endif
#if defined(FFCPS)
if (str_ptr >= str_end)
return NULL;
sljit_u8 *p1 = str_ptr - diff;
#endif
sljit_s32 align_offset = ((uint64_t)str_ptr & 0xf);
str_ptr = (sljit_u8 *) ((uint64_t)str_ptr & ~0xf);
vect_t data = VLD1Q(str_ptr);
#if PCRE2_CODE_UNIT_WIDTH != 8
data = VANDQ(data, char_mask);
#endif
#if defined(FFCS)
vect_t eq = VCEQQ(data, vc1);
#elif defined(FFCS_2)
vect_t eq1 = VCEQQ(data, vc1);
vect_t eq2 = VCEQQ(data, vc2);
vect_t eq = VORRQ(eq1, eq2);
#elif defined(FFCS_MASK)
vect_t eq = VORRQ(data, vmask);
eq = VCEQQ(eq, vc1);
#elif defined(FFCPS)
# if defined(FFCPS_DIFF1)
vect_t prev_data = data;
# endif
vect_t data2;
if (p1 < str_ptr)
{
data2 = VLD1Q(str_ptr - diff);
#if PCRE2_CODE_UNIT_WIDTH != 8
data2 = VANDQ(data2, char_mask);
#endif
}
else
data2 = shift_left_n_lanes(data, offs1 - offs2);
if (compare1_type == compare_match1)
data = VCEQQ(data, cmp1a);
else
data = fast_forward_char_pair_compare(compare1_type, data, cmp1a, cmp1b);
if (compare2_type == compare_match1)
data2 = VCEQQ(data2, cmp2a);
else
data2 = fast_forward_char_pair_compare(compare2_type, data2, cmp2a, cmp2b);
vect_t eq = VANDQ(data, data2);
#endif
VST1Q(qw.mem, eq);
/* Ignore matches before the first STR_PTR. */
if (align_offset < 8)
{
qw.dw[0] >>= align_offset * 8;
if (qw.dw[0])
{
str_ptr += align_offset + __builtin_ctzll(qw.dw[0]) / 8;
goto match;
}
if (qw.dw[1])
{
str_ptr += 8 + __builtin_ctzll(qw.dw[1]) / 8;
goto match;
}
}
else
{
qw.dw[1] >>= (align_offset - 8) * 8;
if (qw.dw[1])
{
str_ptr += align_offset + __builtin_ctzll(qw.dw[1]) / 8;
goto match;
}
}
str_ptr += 16;
while (str_ptr < str_end)
{
vect_t orig_data = VLD1Q(str_ptr);
#if PCRE2_CODE_UNIT_WIDTH != 8
orig_data = VANDQ(orig_data, char_mask);
#endif
data = orig_data;
#if defined(FFCS)
eq = VCEQQ(data, vc1);
#elif defined(FFCS_2)
eq1 = VCEQQ(data, vc1);
eq2 = VCEQQ(data, vc2);
eq = VORRQ(eq1, eq2);
#elif defined(FFCS_MASK)
eq = VORRQ(data, vmask);
eq = VCEQQ(eq, vc1);
#endif
#if defined(FFCPS)
# if defined (FFCPS_DIFF1)
data2 = VEXTQ(prev_data, data, VECTOR_FACTOR - 1);
# else
data2 = VLD1Q(str_ptr - diff);
# if PCRE2_CODE_UNIT_WIDTH != 8
data2 = VANDQ(data2, char_mask);
# endif
# endif
# ifdef FFCPS_CHAR1A2A
data = VCEQQ(data, cmp1a);
data2 = VCEQQ(data2, cmp2a);
# else
if (compare1_type == compare_match1)
data = VCEQQ(data, cmp1a);
else
data = fast_forward_char_pair_compare(compare1_type, data, cmp1a, cmp1b);
if (compare2_type == compare_match1)
data2 = VCEQQ(data2, cmp2a);
else
data2 = fast_forward_char_pair_compare(compare2_type, data2, cmp2a, cmp2b);
# endif
eq = VANDQ(data, data2);
#endif
VST1Q(qw.mem, eq);
if (qw.dw[0])
str_ptr += __builtin_ctzll(qw.dw[0]) / 8;
else if (qw.dw[1])
str_ptr += 8 + __builtin_ctzll(qw.dw[1]) / 8;
else {
str_ptr += 16;
#if defined (FFCPS_DIFF1)
prev_data = orig_data;
#endif
continue;
}
match:;
if (str_ptr >= str_end)
/* Failed match. */
return NULL;
#if defined(FF_UTF)
if (utf_continue((PCRE2_SPTR)str_ptr - offs1))
{
/* Not a match. */
str_ptr += IN_UCHARS(1);
goto restart;
}
#endif
/* Match. */
#if defined (FFCPS)
str_ptr -= IN_UCHARS(offs1);
#endif
return str_ptr;
}
/* Failed match. */
return NULL;
}

1858
Kha/Backends/Kore-hxcpp/khacpp/project/thirdparty/pcre2-10.42-16/src/pcre2_jit_simd_inc.h vendored Normal file
View File

File diff suppressed because it is too large Load Diff

2509
Kha/Backends/Kore-hxcpp/khacpp/project/thirdparty/pcre2-10.42-16/src/pcre2_jit_test.c vendored Normal file
View File

File diff suppressed because it is too large Load Diff

163
Kha/Backends/Kore-hxcpp/khacpp/project/thirdparty/pcre2-10.42-16/src/pcre2_maketables.c vendored Normal file
View File

@ -0,0 +1,163 @@
/*************************************************
* Perl-Compatible Regular Expressions *
*************************************************/
/* PCRE is a library of functions to support regular expressions whose syntax
and semantics are as close as possible to those of the Perl 5 language.
Written by Philip Hazel
Original API code Copyright (c) 1997-2012 University of Cambridge
New API code Copyright (c) 2016-2020 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
modification, are permitted provided that the following conditions are met:
* Redistributions of source code must retain the above copyright notice,
this list of conditions and the following disclaimer.
* Redistributions in binary form must reproduce the above copyright
notice, this list of conditions and the following disclaimer in the
documentation and/or other materials provided with the distribution.
* Neither the name of the University of Cambridge nor the names of its
contributors may be used to endorse or promote products derived from
this software without specific prior written permission.
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
POSSIBILITY OF SUCH DAMAGE.
-----------------------------------------------------------------------------
*/
/* This module contains the external function pcre2_maketables(), which builds
character tables for PCRE2 in the current locale. The file is compiled on its
own as part of the PCRE2 library. It is also included in the compilation of
pcre2_dftables.c as a freestanding program, in which case the macro
PCRE2_DFTABLES is defined. */
#ifndef PCRE2_DFTABLES /* Compiling the library */
# ifdef HAVE_CONFIG_H
# include "config.h"
# endif
# include "pcre2_internal.h"
#endif
/*************************************************
* Create PCRE2 character tables *
*************************************************/
/* This function builds a set of character tables for use by PCRE2 and returns
a pointer to them. They are build using the ctype functions, and consequently
their contents will depend upon the current locale setting. When compiled as
part of the library, the store is obtained via a general context malloc, if
supplied, but when PCRE2_DFTABLES is defined (when compiling the pcre2_dftables
freestanding auxiliary program) malloc() is used, and the function has a
different name so as not to clash with the prototype in pcre2.h.
Arguments: none when PCRE2_DFTABLES is defined
else a PCRE2 general context or NULL
Returns: pointer to the contiguous block of data
else NULL if memory allocation failed
*/
#ifdef PCRE2_DFTABLES /* Included in freestanding pcre2_dftables program */
static const uint8_t *maketables(void)
{
uint8_t *yield = (uint8_t *)malloc(TABLES_LENGTH);
#else /* Not PCRE2_DFTABLES, that is, compiling the library */
PCRE2_EXP_DEFN const uint8_t * PCRE2_CALL_CONVENTION
pcre2_maketables(pcre2_general_context *gcontext)
{
uint8_t *yield = (uint8_t *)((gcontext != NULL)?
gcontext->memctl.malloc(TABLES_LENGTH, gcontext->memctl.memory_data) :
malloc(TABLES_LENGTH));
#endif /* PCRE2_DFTABLES */
int i;
uint8_t *p;
if (yield == NULL) return NULL;
p = yield;
/* First comes the lower casing table */
for (i = 0; i < 256; i++) *p++ = tolower(i);
/* Next the case-flipping table */
for (i = 0; i < 256; i++) *p++ = islower(i)? toupper(i) : tolower(i);
/* Then the character class tables. Don't try to be clever and save effort on
exclusive ones - in some locales things may be different.
Note that the table for "space" includes everything "isspace" gives, including
VT in the default locale. This makes it work for the POSIX class [:space:].
From PCRE1 release 8.34 and for all PCRE2 releases it is also correct for Perl
space, because Perl added VT at release 5.18.
Note also that it is possible for a character to be alnum or alpha without
being lower or upper, such as "male and female ordinals" (\xAA and \xBA) in the
fr_FR locale (at least under Debian Linux's locales as of 12/2005). So we must
test for alnum specially. */
memset(p, 0, cbit_length);
for (i = 0; i < 256; i++)
{
if (isdigit(i)) p[cbit_digit + i/8] |= 1u << (i&7);
if (isupper(i)) p[cbit_upper + i/8] |= 1u << (i&7);
if (islower(i)) p[cbit_lower + i/8] |= 1u << (i&7);
if (isalnum(i)) p[cbit_word + i/8] |= 1u << (i&7);
if (i == '_') p[cbit_word + i/8] |= 1u << (i&7);
if (isspace(i)) p[cbit_space + i/8] |= 1u << (i&7);
if (isxdigit(i)) p[cbit_xdigit + i/8] |= 1u << (i&7);
if (isgraph(i)) p[cbit_graph + i/8] |= 1u << (i&7);
if (isprint(i)) p[cbit_print + i/8] |= 1u << (i&7);
if (ispunct(i)) p[cbit_punct + i/8] |= 1u << (i&7);
if (iscntrl(i)) p[cbit_cntrl + i/8] |= 1u << (i&7);
}
p += cbit_length;
/* Finally, the character type table. In this, we used to exclude VT from the
white space chars, because Perl didn't recognize it as such for \s and for
comments within regexes. However, Perl changed at release 5.18, so PCRE1
changed at release 8.34 and it's always been this way for PCRE2. */
for (i = 0; i < 256; i++)
{
int x = 0;
if (isspace(i)) x += ctype_space;
if (isalpha(i)) x += ctype_letter;
if (islower(i)) x += ctype_lcletter;
if (isdigit(i)) x += ctype_digit;
if (isalnum(i) || i == '_') x += ctype_word;
*p++ = x;
}
return yield;
}
#ifndef PCRE2_DFTABLES /* Compiling the library */
PCRE2_EXP_DEFN void PCRE2_CALL_CONVENTION
pcre2_maketables_free(pcre2_general_context *gcontext, const uint8_t *tables)
{
if (gcontext)
gcontext->memctl.free((void *)tables, gcontext->memctl.memory_data);
else
free((void *)tables);
}
#endif
/* End of pcre2_maketables.c */

Some files were not shown because too many files have changed in this diff Show More