mirror of
https://bitbucket.org/smil3y/katie.git
synced 2025-02-23 10:22:55 +00:00
reimplement character properties and character manipulation via ICU
Signed-off-by: Ivailo Monev <xakepa10@laimg.moc>
This commit is contained in:
Ivailo Monev
parent
df7225de36
commit
fa34c080f6
20 changed files with 403 additions and 23142 deletions
|
|
@ -13,7 +13,7 @@ services:
|
|||
- xvfb
|
||||
before_install:
|
||||
- sudo apt-get update -qq
|
||||
- sudo apt-get install -qq ninja-build libpcre3-dev libssl-dev zlib1g-dev libc6-dev libpng-dev libjpeg-dev libtiff-dev libmng-dev libcups2-dev libfreetype6-dev libfontconfig1-dev libdbus-1-dev unixodbc-dev libpq-dev libpqtypes-dev libmysqld-dev libaio-dev libwrap0-dev liblz4-dev libsqlite3-dev xorg-dev
|
||||
- sudo apt-get install -qq ninja-build libpcre3-dev libssl-dev zlib1g-dev libc6-dev libpng-dev libjpeg-dev libtiff-dev libmng-dev libcups2-dev libfreetype6-dev libfontconfig1-dev libdbus-1-dev libicu-dev unixodbc-dev libpq-dev libpqtypes-dev libmysqld-dev libaio-dev libwrap0-dev liblz4-dev libsqlite3-dev xorg-dev
|
||||
- wget 'http://mirrors.kernel.org/ubuntu/pool/universe/libz/libzstd/libzstd1_1.3.1+dfsg-1~ubuntu0.16.04.1_amd64.deb'
|
||||
- wget 'http://mirrors.kernel.org/ubuntu/pool/universe/libz/libzstd/libzstd1-dev_1.3.1+dfsg-1~ubuntu0.16.04.1_amd64.deb'
|
||||
- sudo dpkg -i *.deb
|
||||
|
|
|
|||
|
|
@ -225,6 +225,15 @@ set_package_properties(ZLIB PROPERTIES
|
|||
TYPE REQUIRED
|
||||
)
|
||||
|
||||
# v4.6 required for unorm2_getDecomposition
|
||||
find_package(ICU 4.6)
|
||||
set_package_properties(ICU PROPERTIES
|
||||
PURPOSE "Required for locales support"
|
||||
DESCRIPTION "Mature, widely used libraries providing Unicode and Globalization support"
|
||||
URL "http://site.icu-project.org/"
|
||||
TYPE REQUIRED
|
||||
)
|
||||
|
||||
# v0.7.3+ required for ZSTD_getDecompressedSize()
|
||||
find_package(ZSTD 0.7.3)
|
||||
set_package_properties(ZSTD PROPERTIES
|
||||
|
|
|
|||
56
cmake/modules/FindICU.cmake
Normal file
56
cmake/modules/FindICU.cmake
Normal file
|
|
@ -0,0 +1,56 @@
|
|||
# - Try to find International Components for Unicode
|
||||
# Once done this will define
|
||||
#
|
||||
# ICU_FOUND - system has ICU
|
||||
# ICU_INCLUDES - the ICU include directory
|
||||
# ICU_LIBRARIES - The libraries needed to use ICU
|
||||
#
|
||||
# Copyright (c) 2015-2019, Ivailo Monev, <xakepa10@gmail.com>
|
||||
#
|
||||
# Redistribution and use is allowed according to the terms of the BSD license.
|
||||
|
||||
if(ICU_INCLUDES AND ICU_LIBRARIES)
|
||||
set(ICU_FIND_QUIETLY TRUE)
|
||||
endif()
|
||||
|
||||
if(NOT WIN32)
|
||||
include(FindPkgConfig)
|
||||
pkg_check_modules(PC_ICU QUIET icu-i18n)
|
||||
endif()
|
||||
|
||||
find_path(ICU_INCLUDES
|
||||
NAMES
|
||||
unicode/unistr.h
|
||||
HINTS
|
||||
$ENV{ICUDIR}/include
|
||||
${PC_ICU_INCLUDEDIR}
|
||||
${INCLUDE_INSTALL_DIR}
|
||||
)
|
||||
|
||||
find_library(ICU_LIBRARIES
|
||||
icui18n
|
||||
HINTS
|
||||
$ENV{ICUDIR}/lib
|
||||
${PC_ICU_LIBDIR}
|
||||
${LIB_INSTALL_DIR}
|
||||
)
|
||||
|
||||
find_library(ICUUC_LIBRARIES
|
||||
icuuc
|
||||
HINTS
|
||||
$ENV{ICUDIR}/lib
|
||||
${PC_ICU_LIBDIR}
|
||||
${LIB_INSTALL_DIR}
|
||||
)
|
||||
|
||||
if(ICU_LIBRARIES AND ICUUC_LIBRARIES)
|
||||
set(ICU_LIBRARIES ${ICU_LIBRARIES} ${ICUUC_LIBRARIES})
|
||||
endif()
|
||||
|
||||
include(FindPackageHandleStandardArgs)
|
||||
find_package_handle_standard_args(ICU
|
||||
VERSION_VAR PC_ICU_VERSION
|
||||
REQUIRED_VARS ICU_LIBRARIES ICUUC_LIBRARIES ICU_INCLUDES
|
||||
)
|
||||
|
||||
mark_as_advanced(ICU_INCLUDES ICU_LIBRARIES ICUUC_LIBRARIES)
|
||||
|
|
@ -8,7 +8,7 @@ pkgdesc='C++ toolkit derived from the Qt 4.8 framework'
|
|||
arch=('i686' 'x86_64')
|
||||
url='https://github.com/fluxer/katie'
|
||||
license=('LGPL' 'FDL' 'custom')
|
||||
depends=('openssl' 'zlib' 'cups' 'libice' 'libsm' 'pcre' 'libxcursor'
|
||||
depends=('openssl' 'zlib' 'cups' 'libice' 'libsm' 'pcre' 'libxcursor' 'icu'
|
||||
'libxext' 'libxfixes' 'libxi' 'libxinerama' 'libxrandr' 'libxrender'
|
||||
'libx11' 'fontconfig' 'freetype2' 'libmng' 'zstd')
|
||||
makedepends=('cmake' 'git' 'postgresql' 'libmariadbclient' 'unixodbc' 'unifdef')
|
||||
|
|
|
|||
|
|
@ -9,13 +9,13 @@ Standards-Version: 4.9.0
|
|||
Build-Depends: debhelper (>= 9~), g++, libssl-dev, zlib1g-dev, libzstd-dev,
|
||||
libc6-dev, libpng-dev, libjpeg-dev, libtiff5-dev, libmng-dev, libcups2-dev,
|
||||
libfreetype6-dev, libfontconfig1-dev, libpcre3-dev, libdbus-1-dev,
|
||||
unixodbc-dev, libpq-dev, libpqtypes-dev, libmariadbclient-dev,
|
||||
unixodbc-dev, libpq-dev, libpqtypes-dev, libmariadbclient-dev, libicu-dev,
|
||||
libmariadbd-dev, libaio-dev, libsqlite3-dev, xorg-dev, cmake, git
|
||||
|
||||
Package: katie-git
|
||||
Architecture: i386 amd64
|
||||
Depends: ${shlibs:Depends}, ${misc:Depends}, openssl, zlib1g, libzstd1, libc6,
|
||||
libpng16-16, libjpeg62-turbo, libtiffxx5, libmng1, libcups2, libfreetype6,
|
||||
libfontconfig1, libpcre3, libdbus-1-3, libsqlite3-0
|
||||
libfontconfig1, libpcre3, libdbus-1-3, libsqlite3-0, libicu63
|
||||
Recommends: unixodbc, libpq5, libmariadbclient, xorg
|
||||
Description: C++ toolkit derived from the Qt 4.8 framework
|
||||
|
|
|
|||
|
|
@ -54,39 +54,7 @@ def printifrange(frommap):
|
|||
switchmap = {}
|
||||
rangemap = {}
|
||||
|
||||
if 'digit' in sys.argv:
|
||||
for line in readlines('extracted/DerivedNumericValues.txt'):
|
||||
tablesplit = line.split(';')
|
||||
codepoint = tablesplit[0].strip()
|
||||
value = tablesplit[3].strip()
|
||||
if '/' in value:
|
||||
# TODO: handle fraction
|
||||
continue
|
||||
mapdecideinsert(switchmap, rangemap, value, codepoint)
|
||||
printswitch(switchmap)
|
||||
printifrange(rangemap)
|
||||
elif 'joining' in sys.argv:
|
||||
for line in readlines('extracted/DerivedJoiningType.txt'):
|
||||
tablesplit = line.split(';')
|
||||
codepoint = tablesplit[0].strip()
|
||||
value = tablesplit[1].strip()
|
||||
if value == 'C':
|
||||
value = 'QChar::Causing'
|
||||
elif value == 'D':
|
||||
value = 'QChar::Dual'
|
||||
elif value == 'R':
|
||||
value = 'QChar::Right'
|
||||
elif value == 'L':
|
||||
value = 'QChar::Left'
|
||||
elif value == 'T':
|
||||
value = 'QChar::Transparent'
|
||||
else:
|
||||
print('Unhandled joining type: %s' % value)
|
||||
sys.exit(2)
|
||||
mapdecideinsert(switchmap, rangemap, value, codepoint)
|
||||
printswitch(switchmap)
|
||||
printifrange(rangemap)
|
||||
elif 'combining' in sys.argv:
|
||||
if 'combining' in sys.argv:
|
||||
for line in readlines('extracted/DerivedCombiningClass.txt'):
|
||||
tablesplit = line.split(';')
|
||||
codepoint = tablesplit[0].strip()
|
||||
|
|
@ -208,23 +176,6 @@ elif 'combining' in sys.argv:
|
|||
mapdecideinsert(switchmap, rangemap, value, codepoint)
|
||||
printswitch(switchmap)
|
||||
printifrange(rangemap)
|
||||
elif 'mirror' in sys.argv:
|
||||
for line in readlines('BidiMirroring.txt'):
|
||||
tablesplit = line.split(';')
|
||||
codepoint = tablesplit[0].strip()
|
||||
value = tablesplit[1].strip()
|
||||
mapdecideinsert(switchmap, rangemap, '0x%s' % value, codepoint)
|
||||
printswitch(switchmap)
|
||||
printifrange(rangemap)
|
||||
elif 'version' in sys.argv:
|
||||
for line in readlines('DerivedAge.txt'):
|
||||
tablesplit = line.split(';')
|
||||
codepoint = tablesplit[0].strip()
|
||||
value = tablesplit[1].strip()
|
||||
value = 'QChar::Unicode_%s' % value.replace('.', '_')
|
||||
mapdecideinsert(switchmap, rangemap, value, codepoint)
|
||||
printswitch(switchmap)
|
||||
printifrange(rangemap)
|
||||
elif 'word' in sys.argv:
|
||||
# only some are supported by harfbuzz
|
||||
supported = [
|
||||
|
|
@ -348,7 +299,7 @@ elif 'special' in sys.argv:
|
|||
print(' 0x%s, // %s' % (codepoint, value.replace('_', '')))
|
||||
scriptslist.append(value)
|
||||
else:
|
||||
print('''usage: <digit|joining|combining|mirror|version|word|sentence|line|script|special>
|
||||
print('''usage: <combining|word|sentence|line|script|special>
|
||||
|
||||
Data is from https://unicode.org/Public/12.1.0/ucd/UCD.zip''')
|
||||
sys.exit(1)
|
||||
|
|
|
|||
93
src/3rdparty/utf8proc/LICENSE.md
vendored
93
src/3rdparty/utf8proc/LICENSE.md
vendored
|
|
@ -1,93 +0,0 @@
|
|||
## utf8proc license ##
|
||||
|
||||
**utf8proc** is a software package originally developed
|
||||
by Jan Behrens and the rest of the Public Software Group, who
|
||||
deserve nearly all of the credit for this library, that is now maintained by the Julia-language developers. Like the original utf8proc,
|
||||
whose copyright and license statements are reproduced below, all new
|
||||
work on the utf8proc library is licensed under the [MIT "expat"
|
||||
license](http://opensource.org/licenses/MIT):
|
||||
|
||||
*Copyright © 2014-2019 by Steven G. Johnson, Jiahao Chen, Tony Kelman, Jonas Fonseca, and other contributors listed in the git history.*
|
||||
|
||||
Permission is hereby granted, free of charge, to any person obtaining a
|
||||
copy of this software and associated documentation files (the "Software"),
|
||||
to deal in the Software without restriction, including without limitation
|
||||
the rights to use, copy, modify, merge, publish, distribute, sublicense,
|
||||
and/or sell copies of the Software, and to permit persons to whom the
|
||||
Software is furnished to do so, subject to the following conditions:
|
||||
|
||||
The above copyright notice and this permission notice shall be included in
|
||||
all copies or substantial portions of the Software.
|
||||
|
||||
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
||||
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
||||
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
|
||||
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
|
||||
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
|
||||
FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
|
||||
DEALINGS IN THE SOFTWARE.
|
||||
|
||||
## Original utf8proc license ##
|
||||
|
||||
*Copyright (c) 2009, 2013 Public Software Group e. V., Berlin, Germany*
|
||||
|
||||
Permission is hereby granted, free of charge, to any person obtaining a
|
||||
copy of this software and associated documentation files (the "Software"),
|
||||
to deal in the Software without restriction, including without limitation
|
||||
the rights to use, copy, modify, merge, publish, distribute, sublicense,
|
||||
and/or sell copies of the Software, and to permit persons to whom the
|
||||
Software is furnished to do so, subject to the following conditions:
|
||||
|
||||
The above copyright notice and this permission notice shall be included in
|
||||
all copies or substantial portions of the Software.
|
||||
|
||||
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
||||
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
||||
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
|
||||
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
|
||||
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
|
||||
FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
|
||||
DEALINGS IN THE SOFTWARE.
|
||||
|
||||
## Unicode data license ##
|
||||
|
||||
This software contains data (`utf8proc_data.c`) derived from processing
|
||||
the Unicode data files. The following license applies to that data:
|
||||
|
||||
**COPYRIGHT AND PERMISSION NOTICE**
|
||||
|
||||
*Copyright (c) 1991-2007 Unicode, Inc. All rights reserved. Distributed
|
||||
under the Terms of Use in http://www.unicode.org/copyright.html.*
|
||||
|
||||
Permission is hereby granted, free of charge, to any person obtaining a
|
||||
copy of the Unicode data files and any associated documentation (the "Data
|
||||
Files") or Unicode software and any associated documentation (the
|
||||
"Software") to deal in the Data Files or Software without restriction,
|
||||
including without limitation the rights to use, copy, modify, merge,
|
||||
publish, distribute, and/or sell copies of the Data Files or Software, and
|
||||
to permit persons to whom the Data Files or Software are furnished to do
|
||||
so, provided that (a) the above copyright notice(s) and this permission
|
||||
notice appear with all copies of the Data Files or Software, (b) both the
|
||||
above copyright notice(s) and this permission notice appear in associated
|
||||
documentation, and (c) there is clear notice in each modified Data File or
|
||||
in the Software as well as in the documentation associated with the Data
|
||||
File(s) or Software that the data or software has been modified.
|
||||
|
||||
THE DATA FILES AND SOFTWARE ARE PROVIDED "AS IS", WITHOUT WARRANTY OF ANY
|
||||
KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
||||
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT OF
|
||||
THIRD PARTY RIGHTS. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR HOLDERS
|
||||
INCLUDED IN THIS NOTICE BE LIABLE FOR ANY CLAIM, OR ANY SPECIAL INDIRECT OR
|
||||
CONSEQUENTIAL DAMAGES, OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS OF
|
||||
USE, DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER
|
||||
TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR
|
||||
PERFORMANCE OF THE DATA FILES OR SOFTWARE.
|
||||
|
||||
Except as contained in this notice, the name of a copyright holder shall
|
||||
not be used in advertising or otherwise to promote the sale, use or other
|
||||
dealings in these Data Files or Software without prior written
|
||||
authorization of the copyright holder.
|
||||
|
||||
Unicode and the Unicode logo are trademarks of Unicode, Inc., and may be
|
||||
registered in some jurisdictions. All other trademarks and registered
|
||||
trademarks mentioned herein are the property of their respective owners.
|
||||
89
src/3rdparty/utf8proc/README.md
vendored
89
src/3rdparty/utf8proc/README.md
vendored
|
|
@ -1,89 +0,0 @@
|
|||
# utf8proc
|
||||
[](https://travis-ci.org/JuliaStrings/utf8proc)
|
||||
[](https://ci.appveyor.com/project/StevenGJohnson/utf8proc)
|
||||
|
||||
[utf8proc](http://juliastrings.github.io/utf8proc/) is a small, clean C
|
||||
library that provides Unicode normalization, case-folding, and other
|
||||
operations for data in the [UTF-8
|
||||
encoding](http://en.wikipedia.org/wiki/UTF-8). It was [initially
|
||||
developed](http://www.public-software-group.org/utf8proc) by Jan
|
||||
Behrens and the rest of the [Public Software
|
||||
Group](http://www.public-software-group.org/), who deserve *nearly all
|
||||
of the credit* for this package. With the blessing of the Public
|
||||
Software Group, the [Julia developers](http://julialang.org/) have
|
||||
taken over development of utf8proc, since the original developers have
|
||||
moved to other projects.
|
||||
|
||||
(utf8proc is used for basic Unicode
|
||||
support in the [Julia language](http://julialang.org/), and the Julia
|
||||
developers became involved because they wanted to add Unicode 7 support and other features.)
|
||||
|
||||
(The original utf8proc package also includes Ruby and PostgreSQL plug-ins.
|
||||
We removed those from utf8proc in order to focus exclusively on the C
|
||||
library for the time being, but plan to add them back in or release them as separate packages.)
|
||||
|
||||
The utf8proc package is licensed under the
|
||||
free/open-source [MIT "expat"
|
||||
license](http://opensource.org/licenses/MIT) (plus certain Unicode
|
||||
data governed by the similarly permissive [Unicode data
|
||||
license](http://www.unicode.org/copyright.html#Exhibit1)); please see
|
||||
the included `LICENSE.md` file for more detailed information.
|
||||
|
||||
## Quick Start
|
||||
|
||||
Typical users should download a [utf8proc release](http://juliastrings.github.io/utf8proc/releases/) rather than cloning directly from github.
|
||||
|
||||
For compilation of the C library, run `make`. You can also install the library and header file with `make install` (by default into `/usr/local/lib` and `/usr/local/bin`, but this can be changed by `make prefix=/some/dir`). `make check` runs some tests, and `make clean` deletes all of the generated files.
|
||||
|
||||
Alternatively, you can compile with `cmake`, e.g. by
|
||||
```sh
|
||||
mkdir build
|
||||
cd build
|
||||
cmake ..
|
||||
make
|
||||
```
|
||||
|
||||
### Using other compilers
|
||||
The included `Makefile` supports GNU/Linux flavors and MacOS with `gcc`-like compilers; Windows users will typically use `cmake`.
|
||||
|
||||
For other Unix-like systems and other compilers, you may need to pass modified settings to `make` in order to use the correct compilation flags for building shared libraries on your system.
|
||||
|
||||
For HP-UX with HP's `aCC` compiler and GNU Make (installed as `gmake`), you can compile with
|
||||
```
|
||||
gmake CC=/opt/aCC/bin/aCC CFLAGS="+O2" PICFLAG="+z" C99FLAG="-Ae" WCFLAGS="+w" LDFLAG_SHARED="-b" SOFLAG="-Wl,+h"
|
||||
```
|
||||
To run `gmake install` you will need GNU coreutils for the `install` command, and you may want to pass `prefix=/opt libdir=/opt/lib/hpux32` or similar to change the installation location.
|
||||
|
||||
## General Information
|
||||
|
||||
The C library is found in this directory after successful compilation
|
||||
and is named `libutf8proc.a` (for the static library) and
|
||||
`libutf8proc.so` (for the dynamic library).
|
||||
|
||||
The Unicode version supported is 12.1.0.
|
||||
|
||||
For Unicode normalizations, the following options are used:
|
||||
|
||||
* Normalization Form C: `STABLE`, `COMPOSE`
|
||||
* Normalization Form D: `STABLE`, `DECOMPOSE`
|
||||
* Normalization Form KC: `STABLE`, `COMPOSE`, `COMPAT`
|
||||
* Normalization Form KD: `STABLE`, `DECOMPOSE`, `COMPAT`
|
||||
|
||||
## C Library
|
||||
|
||||
The documentation for the C library is found in the `utf8proc.h` header file.
|
||||
`utf8proc_map` is function you will most likely be using for mapping UTF-8
|
||||
strings, unless you want to allocate memory yourself.
|
||||
|
||||
## To Do
|
||||
|
||||
See the Github [issues list](https://github.com/JuliaLang/utf8proc/issues).
|
||||
|
||||
## Contact
|
||||
|
||||
Bug reports, feature requests, and other queries can be filed at
|
||||
the [utf8proc issues page on Github](https://github.com/JuliaLang/utf8proc/issues).
|
||||
|
||||
## See also
|
||||
|
||||
An independent Lua translation of this library, [lua-mojibake](https://github.com/differentprogramming/lua-mojibake), is also available.
|
||||
27
src/3rdparty/utf8proc/lump.md
vendored
27
src/3rdparty/utf8proc/lump.md
vendored
|
|
@ -1,27 +0,0 @@
|
|||
```
|
||||
U+0020 <-- all space characters (general category Zs)
|
||||
U+0027 ' <-- left/right single quotation mark U+2018..2019,
|
||||
modifier letter apostrophe U+02BC,
|
||||
modifier letter vertical line U+02C8
|
||||
U+002D - <-- all dash characters (general category Pd),
|
||||
minus U+2212
|
||||
U+002F / <-- fraction slash U+2044,
|
||||
division slash U+2215
|
||||
U+003A : <-- ratio U+2236
|
||||
U+003C < <-- single left-pointing angle quotation mark U+2039,
|
||||
left-pointing angle bracket U+2329,
|
||||
left angle bracket U+3008
|
||||
U+003E > <-- single right-pointing angle quotation mark U+203A,
|
||||
right-pointing angle bracket U+232A,
|
||||
right angle bracket U+3009
|
||||
U+005C \ <-- set minus U+2216
|
||||
U+005E ^ <-- modifier letter up arrowhead U+02C4,
|
||||
modifier letter circumflex accent U+02C6,
|
||||
caret U+2038,
|
||||
up arrowhead U+2303
|
||||
U+005F _ <-- all connector characters (general category Pc),
|
||||
modifier letter low macron U+02CD
|
||||
U+0060 ` <-- modifier letter grave accent U+02CB
|
||||
U+007C | <-- divides U+2223
|
||||
U+007E ~ <-- tilde operator U+223C
|
||||
```
|
||||
773
src/3rdparty/utf8proc/utf8proc.c
vendored
773
src/3rdparty/utf8proc/utf8proc.c
vendored
|
|
@ -1,773 +0,0 @@
|
|||
/* -*- mode: c; c-basic-offset: 2; tab-width: 2; indent-tabs-mode: nil -*- */
|
||||
/*
|
||||
* Copyright (c) 2014-2019 Steven G. Johnson, Jiahao Chen, Peter Colberg, Tony Kelman, Scott P. Jones, and other contributors.
|
||||
* Copyright (c) 2009 Public Software Group e. V., Berlin, Germany
|
||||
*
|
||||
* Permission is hereby granted, free of charge, to any person obtaining a
|
||||
* copy of this software and associated documentation files (the "Software"),
|
||||
* to deal in the Software without restriction, including without limitation
|
||||
* the rights to use, copy, modify, merge, publish, distribute, sublicense,
|
||||
* and/or sell copies of the Software, and to permit persons to whom the
|
||||
* Software is furnished to do so, subject to the following conditions:
|
||||
*
|
||||
* The above copyright notice and this permission notice shall be included in
|
||||
* all copies or substantial portions of the Software.
|
||||
*
|
||||
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
||||
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
||||
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
|
||||
* AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
|
||||
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
|
||||
* FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
|
||||
* DEALINGS IN THE SOFTWARE.
|
||||
*/
|
||||
|
||||
/*
|
||||
* This library contains derived data from a modified version of the
|
||||
* Unicode data files.
|
||||
*
|
||||
* The original data files are available at
|
||||
* http://www.unicode.org/Public/UNIDATA/
|
||||
*
|
||||
* Please notice the copyright statement in the file "utf8proc_data.c".
|
||||
*/
|
||||
|
||||
|
||||
/*
|
||||
* File name: utf8proc.c
|
||||
*
|
||||
* Description:
|
||||
* Implementation of libutf8proc.
|
||||
*/
|
||||
|
||||
|
||||
#include "utf8proc.h"
|
||||
|
||||
#ifndef SSIZE_MAX
|
||||
#define SSIZE_MAX ((size_t)SIZE_MAX/2)
|
||||
#endif
|
||||
#ifndef UINT16_MAX
|
||||
# define UINT16_MAX 65535U
|
||||
#endif
|
||||
|
||||
#include "utf8proc_data.c"
|
||||
|
||||
|
||||
UTF8PROC_DLLEXPORT const utf8proc_int8_t utf8proc_utf8class[256] = {
|
||||
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
|
||||
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
|
||||
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
|
||||
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
|
||||
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
|
||||
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
|
||||
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
|
||||
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 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, 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, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
|
||||
2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
|
||||
2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
|
||||
3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3,
|
||||
4, 4, 4, 4, 4, 4, 4, 4, 0, 0, 0, 0, 0, 0, 0, 0 };
|
||||
|
||||
#define UTF8PROC_HANGUL_SBASE 0xAC00
|
||||
#define UTF8PROC_HANGUL_LBASE 0x1100
|
||||
#define UTF8PROC_HANGUL_VBASE 0x1161
|
||||
#define UTF8PROC_HANGUL_TBASE 0x11A7
|
||||
#define UTF8PROC_HANGUL_LCOUNT 19
|
||||
#define UTF8PROC_HANGUL_VCOUNT 21
|
||||
#define UTF8PROC_HANGUL_TCOUNT 28
|
||||
#define UTF8PROC_HANGUL_NCOUNT 588
|
||||
#define UTF8PROC_HANGUL_SCOUNT 11172
|
||||
/* END is exclusive */
|
||||
#define UTF8PROC_HANGUL_L_START 0x1100
|
||||
#define UTF8PROC_HANGUL_L_END 0x115A
|
||||
#define UTF8PROC_HANGUL_L_FILLER 0x115F
|
||||
#define UTF8PROC_HANGUL_V_START 0x1160
|
||||
#define UTF8PROC_HANGUL_V_END 0x11A3
|
||||
#define UTF8PROC_HANGUL_T_START 0x11A8
|
||||
#define UTF8PROC_HANGUL_T_END 0x11FA
|
||||
#define UTF8PROC_HANGUL_S_START 0xAC00
|
||||
#define UTF8PROC_HANGUL_S_END 0xD7A4
|
||||
|
||||
/* Should follow semantic-versioning rules (semver.org) based on API
|
||||
compatibility. (Note that the shared-library version number will
|
||||
be different, being based on ABI compatibility.): */
|
||||
#define STRINGIZEx(x) #x
|
||||
#define STRINGIZE(x) STRINGIZEx(x)
|
||||
UTF8PROC_DLLEXPORT const char *utf8proc_version(void) {
|
||||
return STRINGIZE(UTF8PROC_VERSION_MAJOR) "." STRINGIZE(UTF8PROC_VERSION_MINOR) "." STRINGIZE(UTF8PROC_VERSION_PATCH) "";
|
||||
}
|
||||
|
||||
UTF8PROC_DLLEXPORT const char *utf8proc_unicode_version(void) {
|
||||
return "12.1.0";
|
||||
}
|
||||
|
||||
UTF8PROC_DLLEXPORT const char *utf8proc_errmsg(utf8proc_ssize_t errcode) {
|
||||
switch (errcode) {
|
||||
case UTF8PROC_ERROR_NOMEM:
|
||||
return "Memory for processing UTF-8 data could not be allocated.";
|
||||
case UTF8PROC_ERROR_OVERFLOW:
|
||||
return "UTF-8 string is too long to be processed.";
|
||||
case UTF8PROC_ERROR_INVALIDUTF8:
|
||||
return "Invalid UTF-8 string";
|
||||
case UTF8PROC_ERROR_NOTASSIGNED:
|
||||
return "Unassigned Unicode code point found in UTF-8 string.";
|
||||
case UTF8PROC_ERROR_INVALIDOPTS:
|
||||
return "Invalid options for UTF-8 processing chosen.";
|
||||
default:
|
||||
return "An unknown error occurred while processing UTF-8 data.";
|
||||
}
|
||||
}
|
||||
|
||||
#define utf_cont(ch) (((ch) & 0xc0) == 0x80)
|
||||
UTF8PROC_DLLEXPORT utf8proc_ssize_t utf8proc_iterate(
|
||||
const utf8proc_uint8_t *str, utf8proc_ssize_t strlen, utf8proc_int32_t *dst
|
||||
) {
|
||||
utf8proc_uint32_t uc;
|
||||
const utf8proc_uint8_t *end;
|
||||
|
||||
*dst = -1;
|
||||
if (!strlen) return 0;
|
||||
end = str + ((strlen < 0) ? 4 : strlen);
|
||||
uc = *str++;
|
||||
if (uc < 0x80) {
|
||||
*dst = uc;
|
||||
return 1;
|
||||
}
|
||||
// Must be between 0xc2 and 0xf4 inclusive to be valid
|
||||
if ((uc - 0xc2) > (0xf4-0xc2)) return UTF8PROC_ERROR_INVALIDUTF8;
|
||||
if (uc < 0xe0) { // 2-byte sequence
|
||||
// Must have valid continuation character
|
||||
if (str >= end || !utf_cont(*str)) return UTF8PROC_ERROR_INVALIDUTF8;
|
||||
*dst = ((uc & 0x1f)<<6) | (*str & 0x3f);
|
||||
return 2;
|
||||
}
|
||||
if (uc < 0xf0) { // 3-byte sequence
|
||||
if ((str + 1 >= end) || !utf_cont(*str) || !utf_cont(str[1]))
|
||||
return UTF8PROC_ERROR_INVALIDUTF8;
|
||||
// Check for surrogate chars
|
||||
if (uc == 0xed && *str > 0x9f)
|
||||
return UTF8PROC_ERROR_INVALIDUTF8;
|
||||
uc = ((uc & 0xf)<<12) | ((*str & 0x3f)<<6) | (str[1] & 0x3f);
|
||||
if (uc < 0x800)
|
||||
return UTF8PROC_ERROR_INVALIDUTF8;
|
||||
*dst = uc;
|
||||
return 3;
|
||||
}
|
||||
// 4-byte sequence
|
||||
// Must have 3 valid continuation characters
|
||||
if ((str + 2 >= end) || !utf_cont(*str) || !utf_cont(str[1]) || !utf_cont(str[2]))
|
||||
return UTF8PROC_ERROR_INVALIDUTF8;
|
||||
// Make sure in correct range (0x10000 - 0x10ffff)
|
||||
if (uc == 0xf0) {
|
||||
if (*str < 0x90) return UTF8PROC_ERROR_INVALIDUTF8;
|
||||
} else if (uc == 0xf4) {
|
||||
if (*str > 0x8f) return UTF8PROC_ERROR_INVALIDUTF8;
|
||||
}
|
||||
*dst = ((uc & 7)<<18) | ((*str & 0x3f)<<12) | ((str[1] & 0x3f)<<6) | (str[2] & 0x3f);
|
||||
return 4;
|
||||
}
|
||||
|
||||
UTF8PROC_DLLEXPORT utf8proc_bool utf8proc_codepoint_valid(utf8proc_int32_t uc) {
|
||||
return (((utf8proc_uint32_t)uc)-0xd800 > 0x07ff) && ((utf8proc_uint32_t)uc < 0x110000);
|
||||
}
|
||||
|
||||
UTF8PROC_DLLEXPORT utf8proc_ssize_t utf8proc_encode_char(utf8proc_int32_t uc, utf8proc_uint8_t *dst) {
|
||||
if (uc < 0x00) {
|
||||
return 0;
|
||||
} else if (uc < 0x80) {
|
||||
dst[0] = (utf8proc_uint8_t) uc;
|
||||
return 1;
|
||||
} else if (uc < 0x800) {
|
||||
dst[0] = (utf8proc_uint8_t)(0xC0 + (uc >> 6));
|
||||
dst[1] = (utf8proc_uint8_t)(0x80 + (uc & 0x3F));
|
||||
return 2;
|
||||
// Note: we allow encoding 0xd800-0xdfff here, so as not to change
|
||||
// the API, however, these are actually invalid in UTF-8
|
||||
} else if (uc < 0x10000) {
|
||||
dst[0] = (utf8proc_uint8_t)(0xE0 + (uc >> 12));
|
||||
dst[1] = (utf8proc_uint8_t)(0x80 + ((uc >> 6) & 0x3F));
|
||||
dst[2] = (utf8proc_uint8_t)(0x80 + (uc & 0x3F));
|
||||
return 3;
|
||||
} else if (uc < 0x110000) {
|
||||
dst[0] = (utf8proc_uint8_t)(0xF0 + (uc >> 18));
|
||||
dst[1] = (utf8proc_uint8_t)(0x80 + ((uc >> 12) & 0x3F));
|
||||
dst[2] = (utf8proc_uint8_t)(0x80 + ((uc >> 6) & 0x3F));
|
||||
dst[3] = (utf8proc_uint8_t)(0x80 + (uc & 0x3F));
|
||||
return 4;
|
||||
} else return 0;
|
||||
}
|
||||
|
||||
/* internal version used for inserting 0xff bytes between graphemes */
|
||||
static utf8proc_ssize_t charbound_encode_char(utf8proc_int32_t uc, utf8proc_uint8_t *dst) {
|
||||
if (uc < 0x00) {
|
||||
if (uc == -1) { /* internal value used for grapheme breaks */
|
||||
dst[0] = (utf8proc_uint8_t)0xFF;
|
||||
return 1;
|
||||
}
|
||||
return 0;
|
||||
} else if (uc < 0x80) {
|
||||
dst[0] = (utf8proc_uint8_t)uc;
|
||||
return 1;
|
||||
} else if (uc < 0x800) {
|
||||
dst[0] = (utf8proc_uint8_t)(0xC0 + (uc >> 6));
|
||||
dst[1] = (utf8proc_uint8_t)(0x80 + (uc & 0x3F));
|
||||
return 2;
|
||||
} else if (uc < 0x10000) {
|
||||
dst[0] = (utf8proc_uint8_t)(0xE0 + (uc >> 12));
|
||||
dst[1] = (utf8proc_uint8_t)(0x80 + ((uc >> 6) & 0x3F));
|
||||
dst[2] = (utf8proc_uint8_t)(0x80 + (uc & 0x3F));
|
||||
return 3;
|
||||
} else if (uc < 0x110000) {
|
||||
dst[0] = (utf8proc_uint8_t)(0xF0 + (uc >> 18));
|
||||
dst[1] = (utf8proc_uint8_t)(0x80 + ((uc >> 12) & 0x3F));
|
||||
dst[2] = (utf8proc_uint8_t)(0x80 + ((uc >> 6) & 0x3F));
|
||||
dst[3] = (utf8proc_uint8_t)(0x80 + (uc & 0x3F));
|
||||
return 4;
|
||||
} else return 0;
|
||||
}
|
||||
|
||||
/* internal "unsafe" version that does not check whether uc is in range */
|
||||
static const utf8proc_property_t *unsafe_get_property(utf8proc_int32_t uc) {
|
||||
/* ASSERT: uc >= 0 && uc < 0x110000 */
|
||||
return utf8proc_properties + (
|
||||
utf8proc_stage2table[
|
||||
utf8proc_stage1table[uc >> 8] + (uc & 0xFF)
|
||||
]
|
||||
);
|
||||
}
|
||||
|
||||
UTF8PROC_DLLEXPORT const utf8proc_property_t *utf8proc_get_property(utf8proc_int32_t uc) {
|
||||
return uc < 0 || uc >= 0x110000 ? utf8proc_properties : unsafe_get_property(uc);
|
||||
}
|
||||
|
||||
/* return whether there is a grapheme break between boundclasses lbc and tbc
|
||||
(according to the definition of extended grapheme clusters)
|
||||
|
||||
Rule numbering refers to TR29 Version 29 (Unicode 9.0.0):
|
||||
http://www.unicode.org/reports/tr29/tr29-29.html
|
||||
|
||||
CAVEATS:
|
||||
Please note that evaluation of GB10 (grapheme breaks between emoji zwj sequences)
|
||||
and GB 12/13 (regional indicator code points) require knowledge of previous characters
|
||||
and are thus not handled by this function. This may result in an incorrect break before
|
||||
an E_Modifier class codepoint and an incorrectly missing break between two
|
||||
REGIONAL_INDICATOR class code points if such support does not exist in the caller.
|
||||
|
||||
See the special support in grapheme_break_extended, for required bookkeeping by the caller.
|
||||
*/
|
||||
static utf8proc_bool grapheme_break_simple(int lbc, int tbc) {
|
||||
return
|
||||
(lbc == UTF8PROC_BOUNDCLASS_START) ? true : // GB1
|
||||
(lbc == UTF8PROC_BOUNDCLASS_CR && // GB3
|
||||
tbc == UTF8PROC_BOUNDCLASS_LF) ? false : // ---
|
||||
(lbc >= UTF8PROC_BOUNDCLASS_CR && lbc <= UTF8PROC_BOUNDCLASS_CONTROL) ? true : // GB4
|
||||
(tbc >= UTF8PROC_BOUNDCLASS_CR && tbc <= UTF8PROC_BOUNDCLASS_CONTROL) ? true : // GB5
|
||||
(lbc == UTF8PROC_BOUNDCLASS_L && // GB6
|
||||
(tbc == UTF8PROC_BOUNDCLASS_L || // ---
|
||||
tbc == UTF8PROC_BOUNDCLASS_V || // ---
|
||||
tbc == UTF8PROC_BOUNDCLASS_LV || // ---
|
||||
tbc == UTF8PROC_BOUNDCLASS_LVT)) ? false : // ---
|
||||
((lbc == UTF8PROC_BOUNDCLASS_LV || // GB7
|
||||
lbc == UTF8PROC_BOUNDCLASS_V) && // ---
|
||||
(tbc == UTF8PROC_BOUNDCLASS_V || // ---
|
||||
tbc == UTF8PROC_BOUNDCLASS_T)) ? false : // ---
|
||||
((lbc == UTF8PROC_BOUNDCLASS_LVT || // GB8
|
||||
lbc == UTF8PROC_BOUNDCLASS_T) && // ---
|
||||
tbc == UTF8PROC_BOUNDCLASS_T) ? false : // ---
|
||||
(tbc == UTF8PROC_BOUNDCLASS_EXTEND || // GB9
|
||||
tbc == UTF8PROC_BOUNDCLASS_ZWJ || // ---
|
||||
tbc == UTF8PROC_BOUNDCLASS_SPACINGMARK || // GB9a
|
||||
lbc == UTF8PROC_BOUNDCLASS_PREPEND) ? false : // GB9b
|
||||
(lbc == UTF8PROC_BOUNDCLASS_E_ZWG && // GB11 (requires additional handling below)
|
||||
tbc == UTF8PROC_BOUNDCLASS_EXTENDED_PICTOGRAPHIC) ? false : // ----
|
||||
(lbc == UTF8PROC_BOUNDCLASS_REGIONAL_INDICATOR && // GB12/13 (requires additional handling below)
|
||||
tbc == UTF8PROC_BOUNDCLASS_REGIONAL_INDICATOR) ? false : // ----
|
||||
true; // GB999
|
||||
}
|
||||
|
||||
static utf8proc_bool grapheme_break_extended(int lbc, int tbc, utf8proc_int32_t *state)
|
||||
{
|
||||
int lbc_override = ((state && *state != UTF8PROC_BOUNDCLASS_START)
|
||||
? *state : lbc);
|
||||
utf8proc_bool break_permitted = grapheme_break_simple(lbc_override, tbc);
|
||||
if (state) {
|
||||
// Special support for GB 12/13 made possible by GB999. After two RI
|
||||
// class codepoints we want to force a break. Do this by resetting the
|
||||
// second RI's bound class to UTF8PROC_BOUNDCLASS_OTHER, to force a break
|
||||
// after that character according to GB999 (unless of course such a break is
|
||||
// forbidden by a different rule such as GB9).
|
||||
if (*state == tbc && tbc == UTF8PROC_BOUNDCLASS_REGIONAL_INDICATOR)
|
||||
*state = UTF8PROC_BOUNDCLASS_OTHER;
|
||||
// Special support for GB11 (emoji extend* zwj / emoji)
|
||||
else if (*state == UTF8PROC_BOUNDCLASS_EXTENDED_PICTOGRAPHIC) {
|
||||
if (tbc == UTF8PROC_BOUNDCLASS_EXTEND) // fold EXTEND codepoints into emoji
|
||||
*state = UTF8PROC_BOUNDCLASS_EXTENDED_PICTOGRAPHIC;
|
||||
else if (tbc == UTF8PROC_BOUNDCLASS_ZWJ)
|
||||
*state = UTF8PROC_BOUNDCLASS_E_ZWG; // state to record emoji+zwg combo
|
||||
else
|
||||
*state = tbc;
|
||||
}
|
||||
else
|
||||
*state = tbc;
|
||||
}
|
||||
return break_permitted;
|
||||
}
|
||||
|
||||
UTF8PROC_DLLEXPORT utf8proc_bool utf8proc_grapheme_break_stateful(
|
||||
utf8proc_int32_t c1, utf8proc_int32_t c2, utf8proc_int32_t *state) {
|
||||
|
||||
return grapheme_break_extended(utf8proc_get_property(c1)->boundclass,
|
||||
utf8proc_get_property(c2)->boundclass,
|
||||
state);
|
||||
}
|
||||
|
||||
|
||||
UTF8PROC_DLLEXPORT utf8proc_bool utf8proc_grapheme_break(
|
||||
utf8proc_int32_t c1, utf8proc_int32_t c2) {
|
||||
return utf8proc_grapheme_break_stateful(c1, c2, NULL);
|
||||
}
|
||||
|
||||
static utf8proc_int32_t seqindex_decode_entry(const utf8proc_uint16_t **entry)
|
||||
{
|
||||
utf8proc_int32_t entry_cp = **entry;
|
||||
if ((entry_cp & 0xF800) == 0xD800) {
|
||||
*entry = *entry + 1;
|
||||
entry_cp = ((entry_cp & 0x03FF) << 10) | (**entry & 0x03FF);
|
||||
entry_cp += 0x10000;
|
||||
}
|
||||
return entry_cp;
|
||||
}
|
||||
|
||||
static utf8proc_int32_t seqindex_decode_index(const utf8proc_uint32_t seqindex)
|
||||
{
|
||||
const utf8proc_uint16_t *entry = &utf8proc_sequences[seqindex];
|
||||
return seqindex_decode_entry(&entry);
|
||||
}
|
||||
|
||||
static utf8proc_ssize_t seqindex_write_char_decomposed(utf8proc_uint16_t seqindex, utf8proc_int32_t *dst, utf8proc_ssize_t bufsize, utf8proc_option_t options, int *last_boundclass) {
|
||||
utf8proc_ssize_t written = 0;
|
||||
const utf8proc_uint16_t *entry = &utf8proc_sequences[seqindex & 0x1FFF];
|
||||
int len = seqindex >> 13;
|
||||
if (len >= 7) {
|
||||
len = *entry;
|
||||
entry++;
|
||||
}
|
||||
for (; len >= 0; entry++, len--) {
|
||||
utf8proc_int32_t entry_cp = seqindex_decode_entry(&entry);
|
||||
|
||||
written += utf8proc_decompose_char(entry_cp, dst+written,
|
||||
(bufsize > written) ? (bufsize - written) : 0, options,
|
||||
last_boundclass);
|
||||
if (written < 0) return UTF8PROC_ERROR_OVERFLOW;
|
||||
}
|
||||
return written;
|
||||
}
|
||||
|
||||
UTF8PROC_DLLEXPORT utf8proc_int32_t utf8proc_tolower(utf8proc_int32_t c)
|
||||
{
|
||||
utf8proc_int32_t cl = utf8proc_get_property(c)->lowercase_seqindex;
|
||||
return cl != UINT16_MAX ? seqindex_decode_index(cl) : c;
|
||||
}
|
||||
|
||||
UTF8PROC_DLLEXPORT utf8proc_int32_t utf8proc_toupper(utf8proc_int32_t c)
|
||||
{
|
||||
utf8proc_int32_t cu = utf8proc_get_property(c)->uppercase_seqindex;
|
||||
return cu != UINT16_MAX ? seqindex_decode_index(cu) : c;
|
||||
}
|
||||
|
||||
UTF8PROC_DLLEXPORT utf8proc_int32_t utf8proc_totitle(utf8proc_int32_t c)
|
||||
{
|
||||
utf8proc_int32_t cu = utf8proc_get_property(c)->titlecase_seqindex;
|
||||
return cu != UINT16_MAX ? seqindex_decode_index(cu) : c;
|
||||
}
|
||||
|
||||
/* return a character width analogous to wcwidth (except portable and
|
||||
hopefully less buggy than most system wcwidth functions). */
|
||||
UTF8PROC_DLLEXPORT int utf8proc_charwidth(utf8proc_int32_t c) {
|
||||
return utf8proc_get_property(c)->charwidth;
|
||||
}
|
||||
|
||||
UTF8PROC_DLLEXPORT utf8proc_category_t utf8proc_category(utf8proc_int32_t c) {
|
||||
return utf8proc_get_property(c)->category;
|
||||
}
|
||||
|
||||
UTF8PROC_DLLEXPORT const char *utf8proc_category_string(utf8proc_int32_t c) {
|
||||
static const char s[][3] = {"Cn","Lu","Ll","Lt","Lm","Lo","Mn","Mc","Me","Nd","Nl","No","Pc","Pd","Ps","Pe","Pi","Pf","Po","Sm","Sc","Sk","So","Zs","Zl","Zp","Cc","Cf","Cs","Co"};
|
||||
return s[utf8proc_category(c)];
|
||||
}
|
||||
|
||||
#define utf8proc_decompose_lump(replacement_uc) \
|
||||
return utf8proc_decompose_char((replacement_uc), dst, bufsize, \
|
||||
options & ~UTF8PROC_LUMP, last_boundclass)
|
||||
|
||||
UTF8PROC_DLLEXPORT utf8proc_ssize_t utf8proc_decompose_char(utf8proc_int32_t uc, utf8proc_int32_t *dst, utf8proc_ssize_t bufsize, utf8proc_option_t options, int *last_boundclass) {
|
||||
const utf8proc_property_t *property;
|
||||
utf8proc_propval_t category;
|
||||
utf8proc_int32_t hangul_sindex;
|
||||
if (uc < 0 || uc >= 0x110000) return UTF8PROC_ERROR_NOTASSIGNED;
|
||||
property = unsafe_get_property(uc);
|
||||
category = property->category;
|
||||
hangul_sindex = uc - UTF8PROC_HANGUL_SBASE;
|
||||
if (options & (UTF8PROC_COMPOSE|UTF8PROC_DECOMPOSE)) {
|
||||
if (hangul_sindex >= 0 && hangul_sindex < UTF8PROC_HANGUL_SCOUNT) {
|
||||
utf8proc_int32_t hangul_tindex;
|
||||
if (bufsize >= 1) {
|
||||
dst[0] = UTF8PROC_HANGUL_LBASE +
|
||||
hangul_sindex / UTF8PROC_HANGUL_NCOUNT;
|
||||
if (bufsize >= 2) dst[1] = UTF8PROC_HANGUL_VBASE +
|
||||
(hangul_sindex % UTF8PROC_HANGUL_NCOUNT) / UTF8PROC_HANGUL_TCOUNT;
|
||||
}
|
||||
hangul_tindex = hangul_sindex % UTF8PROC_HANGUL_TCOUNT;
|
||||
if (!hangul_tindex) return 2;
|
||||
if (bufsize >= 3) dst[2] = UTF8PROC_HANGUL_TBASE + hangul_tindex;
|
||||
return 3;
|
||||
}
|
||||
}
|
||||
if (options & UTF8PROC_REJECTNA) {
|
||||
if (!category) return UTF8PROC_ERROR_NOTASSIGNED;
|
||||
}
|
||||
if (options & UTF8PROC_IGNORE) {
|
||||
if (property->ignorable) return 0;
|
||||
}
|
||||
if (options & UTF8PROC_STRIPNA) {
|
||||
if (!category) return 0;
|
||||
}
|
||||
if (options & UTF8PROC_LUMP) {
|
||||
if (category == UTF8PROC_CATEGORY_ZS) utf8proc_decompose_lump(0x0020);
|
||||
if (uc == 0x2018 || uc == 0x2019 || uc == 0x02BC || uc == 0x02C8)
|
||||
utf8proc_decompose_lump(0x0027);
|
||||
if (category == UTF8PROC_CATEGORY_PD || uc == 0x2212)
|
||||
utf8proc_decompose_lump(0x002D);
|
||||
if (uc == 0x2044 || uc == 0x2215) utf8proc_decompose_lump(0x002F);
|
||||
if (uc == 0x2236) utf8proc_decompose_lump(0x003A);
|
||||
if (uc == 0x2039 || uc == 0x2329 || uc == 0x3008)
|
||||
utf8proc_decompose_lump(0x003C);
|
||||
if (uc == 0x203A || uc == 0x232A || uc == 0x3009)
|
||||
utf8proc_decompose_lump(0x003E);
|
||||
if (uc == 0x2216) utf8proc_decompose_lump(0x005C);
|
||||
if (uc == 0x02C4 || uc == 0x02C6 || uc == 0x2038 || uc == 0x2303)
|
||||
utf8proc_decompose_lump(0x005E);
|
||||
if (category == UTF8PROC_CATEGORY_PC || uc == 0x02CD)
|
||||
utf8proc_decompose_lump(0x005F);
|
||||
if (uc == 0x02CB) utf8proc_decompose_lump(0x0060);
|
||||
if (uc == 0x2223) utf8proc_decompose_lump(0x007C);
|
||||
if (uc == 0x223C) utf8proc_decompose_lump(0x007E);
|
||||
if ((options & UTF8PROC_NLF2LS) && (options & UTF8PROC_NLF2PS)) {
|
||||
if (category == UTF8PROC_CATEGORY_ZL ||
|
||||
category == UTF8PROC_CATEGORY_ZP)
|
||||
utf8proc_decompose_lump(0x000A);
|
||||
}
|
||||
}
|
||||
if (options & UTF8PROC_STRIPMARK) {
|
||||
if (category == UTF8PROC_CATEGORY_MN ||
|
||||
category == UTF8PROC_CATEGORY_MC ||
|
||||
category == UTF8PROC_CATEGORY_ME) return 0;
|
||||
}
|
||||
if (options & UTF8PROC_CASEFOLD) {
|
||||
if (property->casefold_seqindex != UINT16_MAX) {
|
||||
return seqindex_write_char_decomposed(property->casefold_seqindex, dst, bufsize, options, last_boundclass);
|
||||
}
|
||||
}
|
||||
if (options & (UTF8PROC_COMPOSE|UTF8PROC_DECOMPOSE)) {
|
||||
if (property->decomp_seqindex != UINT16_MAX &&
|
||||
(!property->decomp_type || (options & UTF8PROC_COMPAT))) {
|
||||
return seqindex_write_char_decomposed(property->decomp_seqindex, dst, bufsize, options, last_boundclass);
|
||||
}
|
||||
}
|
||||
if (options & UTF8PROC_CHARBOUND) {
|
||||
utf8proc_bool boundary;
|
||||
int tbc = property->boundclass;
|
||||
boundary = grapheme_break_extended(*last_boundclass, tbc, last_boundclass);
|
||||
if (boundary) {
|
||||
if (bufsize >= 1) dst[0] = -1; /* sentinel value for grapheme break */
|
||||
if (bufsize >= 2) dst[1] = uc;
|
||||
return 2;
|
||||
}
|
||||
}
|
||||
if (bufsize >= 1) *dst = uc;
|
||||
return 1;
|
||||
}
|
||||
|
||||
UTF8PROC_DLLEXPORT utf8proc_ssize_t utf8proc_decompose(
|
||||
const utf8proc_uint8_t *str, utf8proc_ssize_t strlen,
|
||||
utf8proc_int32_t *buffer, utf8proc_ssize_t bufsize, utf8proc_option_t options
|
||||
) {
|
||||
return utf8proc_decompose_custom(str, strlen, buffer, bufsize, options, NULL, NULL);
|
||||
}
|
||||
|
||||
UTF8PROC_DLLEXPORT utf8proc_ssize_t utf8proc_decompose_custom(
|
||||
const utf8proc_uint8_t *str, utf8proc_ssize_t strlen,
|
||||
utf8proc_int32_t *buffer, utf8proc_ssize_t bufsize, utf8proc_option_t options,
|
||||
utf8proc_custom_func custom_func, void *custom_data
|
||||
) {
|
||||
/* strlen will be ignored, if UTF8PROC_NULLTERM is set in options */
|
||||
utf8proc_ssize_t wpos = 0;
|
||||
if ((options & UTF8PROC_COMPOSE) && (options & UTF8PROC_DECOMPOSE))
|
||||
return UTF8PROC_ERROR_INVALIDOPTS;
|
||||
if ((options & UTF8PROC_STRIPMARK) &&
|
||||
!(options & UTF8PROC_COMPOSE) && !(options & UTF8PROC_DECOMPOSE))
|
||||
return UTF8PROC_ERROR_INVALIDOPTS;
|
||||
{
|
||||
utf8proc_int32_t uc;
|
||||
utf8proc_ssize_t rpos = 0;
|
||||
utf8proc_ssize_t decomp_result;
|
||||
int boundclass = UTF8PROC_BOUNDCLASS_START;
|
||||
while (1) {
|
||||
if (options & UTF8PROC_NULLTERM) {
|
||||
rpos += utf8proc_iterate(str + rpos, -1, &uc);
|
||||
/* checking of return value is not necessary,
|
||||
as 'uc' is < 0 in case of error */
|
||||
if (uc < 0) return UTF8PROC_ERROR_INVALIDUTF8;
|
||||
if (rpos < 0) return UTF8PROC_ERROR_OVERFLOW;
|
||||
if (uc == 0) break;
|
||||
} else {
|
||||
if (rpos >= strlen) break;
|
||||
rpos += utf8proc_iterate(str + rpos, strlen - rpos, &uc);
|
||||
if (uc < 0) return UTF8PROC_ERROR_INVALIDUTF8;
|
||||
}
|
||||
if (custom_func != NULL) {
|
||||
uc = custom_func(uc, custom_data); /* user-specified custom mapping */
|
||||
}
|
||||
decomp_result = utf8proc_decompose_char(
|
||||
uc, buffer + wpos, (bufsize > wpos) ? (bufsize - wpos) : 0, options,
|
||||
&boundclass
|
||||
);
|
||||
if (decomp_result < 0) return decomp_result;
|
||||
wpos += decomp_result;
|
||||
/* prohibiting integer overflows due to too long strings: */
|
||||
if (wpos < 0 ||
|
||||
wpos > (utf8proc_ssize_t)(SSIZE_MAX/sizeof(utf8proc_int32_t)/2))
|
||||
return UTF8PROC_ERROR_OVERFLOW;
|
||||
}
|
||||
}
|
||||
if ((options & (UTF8PROC_COMPOSE|UTF8PROC_DECOMPOSE)) && bufsize >= wpos) {
|
||||
utf8proc_ssize_t pos = 0;
|
||||
while (pos < wpos-1) {
|
||||
utf8proc_int32_t uc1, uc2;
|
||||
const utf8proc_property_t *property1, *property2;
|
||||
uc1 = buffer[pos];
|
||||
uc2 = buffer[pos+1];
|
||||
property1 = unsafe_get_property(uc1);
|
||||
property2 = unsafe_get_property(uc2);
|
||||
if (property1->combining_class > property2->combining_class &&
|
||||
property2->combining_class > 0) {
|
||||
buffer[pos] = uc2;
|
||||
buffer[pos+1] = uc1;
|
||||
if (pos > 0) pos--; else pos++;
|
||||
} else {
|
||||
pos++;
|
||||
}
|
||||
}
|
||||
}
|
||||
return wpos;
|
||||
}
|
||||
|
||||
UTF8PROC_DLLEXPORT utf8proc_ssize_t utf8proc_normalize_utf32(utf8proc_int32_t *buffer, utf8proc_ssize_t length, utf8proc_option_t options) {
|
||||
/* UTF8PROC_NULLTERM option will be ignored, 'length' is never ignored */
|
||||
if (options & (UTF8PROC_NLF2LS | UTF8PROC_NLF2PS | UTF8PROC_STRIPCC)) {
|
||||
utf8proc_ssize_t rpos;
|
||||
utf8proc_ssize_t wpos = 0;
|
||||
utf8proc_int32_t uc;
|
||||
for (rpos = 0; rpos < length; rpos++) {
|
||||
uc = buffer[rpos];
|
||||
if (uc == 0x000D && rpos < length-1 && buffer[rpos+1] == 0x000A) rpos++;
|
||||
if (uc == 0x000A || uc == 0x000D || uc == 0x0085 ||
|
||||
((options & UTF8PROC_STRIPCC) && (uc == 0x000B || uc == 0x000C))) {
|
||||
if (options & UTF8PROC_NLF2LS) {
|
||||
if (options & UTF8PROC_NLF2PS) {
|
||||
buffer[wpos++] = 0x000A;
|
||||
} else {
|
||||
buffer[wpos++] = 0x2028;
|
||||
}
|
||||
} else {
|
||||
if (options & UTF8PROC_NLF2PS) {
|
||||
buffer[wpos++] = 0x2029;
|
||||
} else {
|
||||
buffer[wpos++] = 0x0020;
|
||||
}
|
||||
}
|
||||
} else if ((options & UTF8PROC_STRIPCC) &&
|
||||
(uc < 0x0020 || (uc >= 0x007F && uc < 0x00A0))) {
|
||||
if (uc == 0x0009) buffer[wpos++] = 0x0020;
|
||||
} else {
|
||||
buffer[wpos++] = uc;
|
||||
}
|
||||
}
|
||||
length = wpos;
|
||||
}
|
||||
if (options & UTF8PROC_COMPOSE) {
|
||||
utf8proc_int32_t *starter = NULL;
|
||||
utf8proc_int32_t current_char;
|
||||
const utf8proc_property_t *starter_property = NULL, *current_property;
|
||||
utf8proc_propval_t max_combining_class = -1;
|
||||
utf8proc_ssize_t rpos;
|
||||
utf8proc_ssize_t wpos = 0;
|
||||
utf8proc_int32_t composition;
|
||||
for (rpos = 0; rpos < length; rpos++) {
|
||||
current_char = buffer[rpos];
|
||||
current_property = unsafe_get_property(current_char);
|
||||
if (starter && current_property->combining_class > max_combining_class) {
|
||||
/* combination perhaps possible */
|
||||
utf8proc_int32_t hangul_lindex;
|
||||
utf8proc_int32_t hangul_sindex;
|
||||
hangul_lindex = *starter - UTF8PROC_HANGUL_LBASE;
|
||||
if (hangul_lindex >= 0 && hangul_lindex < UTF8PROC_HANGUL_LCOUNT) {
|
||||
utf8proc_int32_t hangul_vindex;
|
||||
hangul_vindex = current_char - UTF8PROC_HANGUL_VBASE;
|
||||
if (hangul_vindex >= 0 && hangul_vindex < UTF8PROC_HANGUL_VCOUNT) {
|
||||
*starter = UTF8PROC_HANGUL_SBASE +
|
||||
(hangul_lindex * UTF8PROC_HANGUL_VCOUNT + hangul_vindex) *
|
||||
UTF8PROC_HANGUL_TCOUNT;
|
||||
starter_property = NULL;
|
||||
continue;
|
||||
}
|
||||
}
|
||||
hangul_sindex = *starter - UTF8PROC_HANGUL_SBASE;
|
||||
if (hangul_sindex >= 0 && hangul_sindex < UTF8PROC_HANGUL_SCOUNT &&
|
||||
(hangul_sindex % UTF8PROC_HANGUL_TCOUNT) == 0) {
|
||||
utf8proc_int32_t hangul_tindex;
|
||||
hangul_tindex = current_char - UTF8PROC_HANGUL_TBASE;
|
||||
if (hangul_tindex >= 0 && hangul_tindex < UTF8PROC_HANGUL_TCOUNT) {
|
||||
*starter += hangul_tindex;
|
||||
starter_property = NULL;
|
||||
continue;
|
||||
}
|
||||
}
|
||||
if (!starter_property) {
|
||||
starter_property = unsafe_get_property(*starter);
|
||||
}
|
||||
if (starter_property->comb_index < 0x8000 &&
|
||||
current_property->comb_index != UINT16_MAX &&
|
||||
current_property->comb_index >= 0x8000) {
|
||||
int sidx = starter_property->comb_index;
|
||||
int idx = current_property->comb_index & 0x3FFF;
|
||||
if (idx >= utf8proc_combinations[sidx] && idx <= utf8proc_combinations[sidx + 1] ) {
|
||||
idx += sidx + 2 - utf8proc_combinations[sidx];
|
||||
if (current_property->comb_index & 0x4000) {
|
||||
composition = (utf8proc_combinations[idx] << 16) | utf8proc_combinations[idx+1];
|
||||
} else
|
||||
composition = utf8proc_combinations[idx];
|
||||
|
||||
if (composition > 0 && (!(options & UTF8PROC_STABLE) ||
|
||||
!(unsafe_get_property(composition)->comp_exclusion))) {
|
||||
*starter = composition;
|
||||
starter_property = NULL;
|
||||
continue;
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
buffer[wpos] = current_char;
|
||||
if (current_property->combining_class) {
|
||||
if (current_property->combining_class > max_combining_class) {
|
||||
max_combining_class = current_property->combining_class;
|
||||
}
|
||||
} else {
|
||||
starter = buffer + wpos;
|
||||
starter_property = NULL;
|
||||
max_combining_class = -1;
|
||||
}
|
||||
wpos++;
|
||||
}
|
||||
length = wpos;
|
||||
}
|
||||
return length;
|
||||
}
|
||||
|
||||
UTF8PROC_DLLEXPORT utf8proc_ssize_t utf8proc_reencode(utf8proc_int32_t *buffer, utf8proc_ssize_t length, utf8proc_option_t options) {
|
||||
/* UTF8PROC_NULLTERM option will be ignored, 'length' is never ignored
|
||||
ASSERT: 'buffer' has one spare byte of free space at the end! */
|
||||
length = utf8proc_normalize_utf32(buffer, length, options);
|
||||
if (length < 0) return length;
|
||||
{
|
||||
utf8proc_ssize_t rpos, wpos = 0;
|
||||
utf8proc_int32_t uc;
|
||||
if (options & UTF8PROC_CHARBOUND) {
|
||||
for (rpos = 0; rpos < length; rpos++) {
|
||||
uc = buffer[rpos];
|
||||
wpos += charbound_encode_char(uc, ((utf8proc_uint8_t *)buffer) + wpos);
|
||||
}
|
||||
} else {
|
||||
for (rpos = 0; rpos < length; rpos++) {
|
||||
uc = buffer[rpos];
|
||||
wpos += utf8proc_encode_char(uc, ((utf8proc_uint8_t *)buffer) + wpos);
|
||||
}
|
||||
}
|
||||
((utf8proc_uint8_t *)buffer)[wpos] = 0;
|
||||
return wpos;
|
||||
}
|
||||
}
|
||||
|
||||
UTF8PROC_DLLEXPORT utf8proc_ssize_t utf8proc_map(
|
||||
const utf8proc_uint8_t *str, utf8proc_ssize_t strlen, utf8proc_uint8_t **dstptr, utf8proc_option_t options
|
||||
) {
|
||||
return utf8proc_map_custom(str, strlen, dstptr, options, NULL, NULL);
|
||||
}
|
||||
|
||||
UTF8PROC_DLLEXPORT utf8proc_ssize_t utf8proc_map_custom(
|
||||
const utf8proc_uint8_t *str, utf8proc_ssize_t strlen, utf8proc_uint8_t **dstptr, utf8proc_option_t options,
|
||||
utf8proc_custom_func custom_func, void *custom_data
|
||||
) {
|
||||
utf8proc_int32_t *buffer;
|
||||
utf8proc_ssize_t result;
|
||||
*dstptr = NULL;
|
||||
result = utf8proc_decompose_custom(str, strlen, NULL, 0, options, custom_func, custom_data);
|
||||
if (result < 0) return result;
|
||||
buffer = (utf8proc_int32_t *) malloc(result * sizeof(utf8proc_int32_t) + 1);
|
||||
if (!buffer) return UTF8PROC_ERROR_NOMEM;
|
||||
result = utf8proc_decompose_custom(str, strlen, buffer, result, options, custom_func, custom_data);
|
||||
if (result < 0) {
|
||||
free(buffer);
|
||||
return result;
|
||||
}
|
||||
result = utf8proc_reencode(buffer, result, options);
|
||||
if (result < 0) {
|
||||
free(buffer);
|
||||
return result;
|
||||
}
|
||||
{
|
||||
utf8proc_int32_t *newptr;
|
||||
newptr = (utf8proc_int32_t *) realloc(buffer, (size_t)result+1);
|
||||
if (newptr) buffer = newptr;
|
||||
}
|
||||
*dstptr = (utf8proc_uint8_t *)buffer;
|
||||
return result;
|
||||
}
|
||||
|
||||
UTF8PROC_DLLEXPORT utf8proc_uint8_t *utf8proc_NFD(const utf8proc_uint8_t *str) {
|
||||
utf8proc_uint8_t *retval;
|
||||
utf8proc_map(str, 0, &retval, UTF8PROC_NULLTERM | UTF8PROC_STABLE |
|
||||
UTF8PROC_DECOMPOSE);
|
||||
return retval;
|
||||
}
|
||||
|
||||
UTF8PROC_DLLEXPORT utf8proc_uint8_t *utf8proc_NFC(const utf8proc_uint8_t *str) {
|
||||
utf8proc_uint8_t *retval;
|
||||
utf8proc_map(str, 0, &retval, UTF8PROC_NULLTERM | UTF8PROC_STABLE |
|
||||
UTF8PROC_COMPOSE);
|
||||
return retval;
|
||||
}
|
||||
|
||||
UTF8PROC_DLLEXPORT utf8proc_uint8_t *utf8proc_NFKD(const utf8proc_uint8_t *str) {
|
||||
utf8proc_uint8_t *retval;
|
||||
utf8proc_map(str, 0, &retval, UTF8PROC_NULLTERM | UTF8PROC_STABLE |
|
||||
UTF8PROC_DECOMPOSE | UTF8PROC_COMPAT);
|
||||
return retval;
|
||||
}
|
||||
|
||||
UTF8PROC_DLLEXPORT utf8proc_uint8_t *utf8proc_NFKC(const utf8proc_uint8_t *str) {
|
||||
utf8proc_uint8_t *retval;
|
||||
utf8proc_map(str, 0, &retval, UTF8PROC_NULLTERM | UTF8PROC_STABLE |
|
||||
UTF8PROC_COMPOSE | UTF8PROC_COMPAT);
|
||||
return retval;
|
||||
}
|
||||
|
||||
UTF8PROC_DLLEXPORT utf8proc_uint8_t *utf8proc_NFKC_Casefold(const utf8proc_uint8_t *str) {
|
||||
utf8proc_uint8_t *retval;
|
||||
utf8proc_map(str, 0, &retval, UTF8PROC_NULLTERM | UTF8PROC_STABLE |
|
||||
UTF8PROC_COMPOSE | UTF8PROC_COMPAT | UTF8PROC_CASEFOLD | UTF8PROC_IGNORE);
|
||||
return retval;
|
||||
}
|
||||
721
src/3rdparty/utf8proc/utf8proc.h
vendored
721
src/3rdparty/utf8proc/utf8proc.h
vendored
|
|
@ -1,721 +0,0 @@
|
|||
/*
|
||||
* Copyright (c) 2014-2019 Steven G. Johnson, Jiahao Chen, Peter Colberg, Tony Kelman, Scott P. Jones, and other contributors.
|
||||
* Copyright (c) 2009 Public Software Group e. V., Berlin, Germany
|
||||
*
|
||||
* Permission is hereby granted, free of charge, to any person obtaining a
|
||||
* copy of this software and associated documentation files (the "Software"),
|
||||
* to deal in the Software without restriction, including without limitation
|
||||
* the rights to use, copy, modify, merge, publish, distribute, sublicense,
|
||||
* and/or sell copies of the Software, and to permit persons to whom the
|
||||
* Software is furnished to do so, subject to the following conditions:
|
||||
*
|
||||
* The above copyright notice and this permission notice shall be included in
|
||||
* all copies or substantial portions of the Software.
|
||||
*
|
||||
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
||||
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
||||
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
|
||||
* AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
|
||||
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
|
||||
* FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
|
||||
* DEALINGS IN THE SOFTWARE.
|
||||
*/
|
||||
|
||||
|
||||
/**
|
||||
* @mainpage
|
||||
*
|
||||
* utf8proc is a free/open-source (MIT/expat licensed) C library
|
||||
* providing Unicode normalization, case-folding, and other operations
|
||||
* for strings in the UTF-8 encoding, supporting up-to-date Unicode versions.
|
||||
* See the utf8proc home page (http://julialang.org/utf8proc/)
|
||||
* for downloads and other information, or the source code on github
|
||||
* (https://github.com/JuliaLang/utf8proc).
|
||||
*
|
||||
* For the utf8proc API documentation, see: @ref utf8proc.h
|
||||
*
|
||||
* The features of utf8proc include:
|
||||
*
|
||||
* - Transformation of strings (@ref utf8proc_map) to:
|
||||
* - decompose (@ref UTF8PROC_DECOMPOSE) or compose (@ref UTF8PROC_COMPOSE) Unicode combining characters (http://en.wikipedia.org/wiki/Combining_character)
|
||||
* - canonicalize Unicode compatibility characters (@ref UTF8PROC_COMPAT)
|
||||
* - strip "ignorable" (@ref UTF8PROC_IGNORE) characters, control characters (@ref UTF8PROC_STRIPCC), or combining characters such as accents (@ref UTF8PROC_STRIPMARK)
|
||||
* - case-folding (@ref UTF8PROC_CASEFOLD)
|
||||
* - Unicode normalization: @ref utf8proc_NFD, @ref utf8proc_NFC, @ref utf8proc_NFKD, @ref utf8proc_NFKC
|
||||
* - Detecting grapheme boundaries (@ref utf8proc_grapheme_break and @ref UTF8PROC_CHARBOUND)
|
||||
* - Character-width computation: @ref utf8proc_charwidth
|
||||
* - Classification of characters by Unicode category: @ref utf8proc_category and @ref utf8proc_category_string
|
||||
* - Encode (@ref utf8proc_encode_char) and decode (@ref utf8proc_iterate) Unicode codepoints to/from UTF-8.
|
||||
*/
|
||||
|
||||
/** @file */
|
||||
|
||||
#ifndef UTF8PROC_H
|
||||
#define UTF8PROC_H
|
||||
|
||||
/** @name API version
|
||||
*
|
||||
* The utf8proc API version MAJOR.MINOR.PATCH, following
|
||||
* semantic-versioning rules (http://semver.org) based on API
|
||||
* compatibility.
|
||||
*
|
||||
* This is also returned at runtime by @ref utf8proc_version; however, the
|
||||
* runtime version may append a string like "-dev" to the version number
|
||||
* for prerelease versions.
|
||||
*
|
||||
* @note The shared-library version number in the Makefile
|
||||
* (and CMakeLists.txt, and MANIFEST) may be different,
|
||||
* being based on ABI compatibility rather than API compatibility.
|
||||
*/
|
||||
/** @{ */
|
||||
/** The MAJOR version number (increased when backwards API compatibility is broken). */
|
||||
#define UTF8PROC_VERSION_MAJOR 2
|
||||
/** The MINOR version number (increased when new functionality is added in a backwards-compatible manner). */
|
||||
#define UTF8PROC_VERSION_MINOR 4
|
||||
/** The PATCH version (increased for fixes that do not change the API). */
|
||||
#define UTF8PROC_VERSION_PATCH 0
|
||||
/** @} */
|
||||
|
||||
#include <stdlib.h>
|
||||
|
||||
#if defined(_MSC_VER) && _MSC_VER < 1800
|
||||
// MSVC prior to 2013 lacked stdbool.h and inttypes.h
|
||||
typedef signed char utf8proc_int8_t;
|
||||
typedef unsigned char utf8proc_uint8_t;
|
||||
typedef short utf8proc_int16_t;
|
||||
typedef unsigned short utf8proc_uint16_t;
|
||||
typedef int utf8proc_int32_t;
|
||||
typedef unsigned int utf8proc_uint32_t;
|
||||
# ifdef _WIN64
|
||||
typedef __int64 utf8proc_ssize_t;
|
||||
typedef unsigned __int64 utf8proc_size_t;
|
||||
# else
|
||||
typedef int utf8proc_ssize_t;
|
||||
typedef unsigned int utf8proc_size_t;
|
||||
# endif
|
||||
# ifndef __cplusplus
|
||||
// emulate C99 bool
|
||||
typedef unsigned char utf8proc_bool;
|
||||
# ifndef __bool_true_false_are_defined
|
||||
# define false 0
|
||||
# define true 1
|
||||
# define __bool_true_false_are_defined 1
|
||||
# endif
|
||||
# else
|
||||
typedef bool utf8proc_bool;
|
||||
# endif
|
||||
#else
|
||||
# include <stddef.h>
|
||||
# include <stdbool.h>
|
||||
# include <inttypes.h>
|
||||
typedef int8_t utf8proc_int8_t;
|
||||
typedef uint8_t utf8proc_uint8_t;
|
||||
typedef int16_t utf8proc_int16_t;
|
||||
typedef uint16_t utf8proc_uint16_t;
|
||||
typedef int32_t utf8proc_int32_t;
|
||||
typedef uint32_t utf8proc_uint32_t;
|
||||
typedef size_t utf8proc_size_t;
|
||||
typedef ptrdiff_t utf8proc_ssize_t;
|
||||
typedef bool utf8proc_bool;
|
||||
#endif
|
||||
#include <limits.h>
|
||||
|
||||
#ifdef UTF8PROC_STATIC
|
||||
# define UTF8PROC_DLLEXPORT
|
||||
#else
|
||||
# ifdef _WIN32
|
||||
# ifdef UTF8PROC_EXPORTS
|
||||
# define UTF8PROC_DLLEXPORT __declspec(dllexport)
|
||||
# else
|
||||
# define UTF8PROC_DLLEXPORT __declspec(dllimport)
|
||||
# endif
|
||||
# elif __GNUC__ >= 4
|
||||
# define UTF8PROC_DLLEXPORT __attribute__ ((visibility("default")))
|
||||
# else
|
||||
# define UTF8PROC_DLLEXPORT
|
||||
# endif
|
||||
#endif
|
||||
|
||||
#ifdef __cplusplus
|
||||
extern "C" {
|
||||
#endif
|
||||
|
||||
/**
|
||||
* Option flags used by several functions in the library.
|
||||
*/
|
||||
typedef enum {
|
||||
/** The given UTF-8 input is NULL terminated. */
|
||||
UTF8PROC_NULLTERM = (1<<0),
|
||||
/** Unicode Versioning Stability has to be respected. */
|
||||
UTF8PROC_STABLE = (1<<1),
|
||||
/** Compatibility decomposition (i.e. formatting information is lost). */
|
||||
UTF8PROC_COMPAT = (1<<2),
|
||||
/** Return a result with decomposed characters. */
|
||||
UTF8PROC_COMPOSE = (1<<3),
|
||||
/** Return a result with decomposed characters. */
|
||||
UTF8PROC_DECOMPOSE = (1<<4),
|
||||
/** Strip "default ignorable characters" such as SOFT-HYPHEN or ZERO-WIDTH-SPACE. */
|
||||
UTF8PROC_IGNORE = (1<<5),
|
||||
/** Return an error, if the input contains unassigned codepoints. */
|
||||
UTF8PROC_REJECTNA = (1<<6),
|
||||
/**
|
||||
* Indicating that NLF-sequences (LF, CRLF, CR, NEL) are representing a
|
||||
* line break, and should be converted to the codepoint for line
|
||||
* separation (LS).
|
||||
*/
|
||||
UTF8PROC_NLF2LS = (1<<7),
|
||||
/**
|
||||
* Indicating that NLF-sequences are representing a paragraph break, and
|
||||
* should be converted to the codepoint for paragraph separation
|
||||
* (PS).
|
||||
*/
|
||||
UTF8PROC_NLF2PS = (1<<8),
|
||||
/** Indicating that the meaning of NLF-sequences is unknown. */
|
||||
UTF8PROC_NLF2LF = (UTF8PROC_NLF2LS | UTF8PROC_NLF2PS),
|
||||
/** Strips and/or convers control characters.
|
||||
*
|
||||
* NLF-sequences are transformed into space, except if one of the
|
||||
* NLF2LS/PS/LF options is given. HorizontalTab (HT) and FormFeed (FF)
|
||||
* are treated as a NLF-sequence in this case. All other control
|
||||
* characters are simply removed.
|
||||
*/
|
||||
UTF8PROC_STRIPCC = (1<<9),
|
||||
/**
|
||||
* Performs unicode case folding, to be able to do a case-insensitive
|
||||
* string comparison.
|
||||
*/
|
||||
UTF8PROC_CASEFOLD = (1<<10),
|
||||
/**
|
||||
* Inserts 0xFF bytes at the beginning of each sequence which is
|
||||
* representing a single grapheme cluster (see UAX#29).
|
||||
*/
|
||||
UTF8PROC_CHARBOUND = (1<<11),
|
||||
/** Lumps certain characters together.
|
||||
*
|
||||
* E.g. HYPHEN U+2010 and MINUS U+2212 to ASCII "-". See lump.md for details.
|
||||
*
|
||||
* If NLF2LF is set, this includes a transformation of paragraph and
|
||||
* line separators to ASCII line-feed (LF).
|
||||
*/
|
||||
UTF8PROC_LUMP = (1<<12),
|
||||
/** Strips all character markings.
|
||||
*
|
||||
* This includes non-spacing, spacing and enclosing (i.e. accents).
|
||||
* @note This option works only with @ref UTF8PROC_COMPOSE or
|
||||
* @ref UTF8PROC_DECOMPOSE
|
||||
*/
|
||||
UTF8PROC_STRIPMARK = (1<<13),
|
||||
/**
|
||||
* Strip unassigned codepoints.
|
||||
*/
|
||||
UTF8PROC_STRIPNA = (1<<14),
|
||||
} utf8proc_option_t;
|
||||
|
||||
/** @name Error codes
|
||||
* Error codes being returned by almost all functions.
|
||||
*/
|
||||
/** @{ */
|
||||
/** Memory could not be allocated. */
|
||||
#define UTF8PROC_ERROR_NOMEM -1
|
||||
/** The given string is too long to be processed. */
|
||||
#define UTF8PROC_ERROR_OVERFLOW -2
|
||||
/** The given string is not a legal UTF-8 string. */
|
||||
#define UTF8PROC_ERROR_INVALIDUTF8 -3
|
||||
/** The @ref UTF8PROC_REJECTNA flag was set and an unassigned codepoint was found. */
|
||||
#define UTF8PROC_ERROR_NOTASSIGNED -4
|
||||
/** Invalid options have been used. */
|
||||
#define UTF8PROC_ERROR_INVALIDOPTS -5
|
||||
/** @} */
|
||||
|
||||
/* @name Types */
|
||||
|
||||
/** Holds the value of a property. */
|
||||
typedef utf8proc_int16_t utf8proc_propval_t;
|
||||
|
||||
/** Struct containing information about a codepoint. */
|
||||
typedef struct utf8proc_property_struct {
|
||||
/**
|
||||
* Unicode category.
|
||||
* @see utf8proc_category_t.
|
||||
*/
|
||||
utf8proc_propval_t category;
|
||||
utf8proc_propval_t combining_class;
|
||||
/**
|
||||
* Bidirectional class.
|
||||
* @see utf8proc_bidi_class_t.
|
||||
*/
|
||||
utf8proc_propval_t bidi_class;
|
||||
/**
|
||||
* @anchor Decomposition type.
|
||||
* @see utf8proc_decomp_type_t.
|
||||
*/
|
||||
utf8proc_propval_t decomp_type;
|
||||
utf8proc_uint16_t decomp_seqindex;
|
||||
utf8proc_uint16_t casefold_seqindex;
|
||||
utf8proc_uint16_t uppercase_seqindex;
|
||||
utf8proc_uint16_t lowercase_seqindex;
|
||||
utf8proc_uint16_t titlecase_seqindex;
|
||||
utf8proc_uint16_t comb_index;
|
||||
unsigned bidi_mirrored:1;
|
||||
unsigned comp_exclusion:1;
|
||||
/**
|
||||
* Can this codepoint be ignored?
|
||||
*
|
||||
* Used by @ref utf8proc_decompose_char when @ref UTF8PROC_IGNORE is
|
||||
* passed as an option.
|
||||
*/
|
||||
unsigned ignorable:1;
|
||||
unsigned control_boundary:1;
|
||||
/** The width of the codepoint. */
|
||||
unsigned charwidth:2;
|
||||
unsigned pad:2;
|
||||
/**
|
||||
* Boundclass.
|
||||
* @see utf8proc_boundclass_t.
|
||||
*/
|
||||
unsigned boundclass:8;
|
||||
} utf8proc_property_t;
|
||||
|
||||
/** Unicode categories. */
|
||||
typedef enum {
|
||||
UTF8PROC_CATEGORY_CN = 0, /**< Other, not assigned */
|
||||
UTF8PROC_CATEGORY_LU = 1, /**< Letter, uppercase */
|
||||
UTF8PROC_CATEGORY_LL = 2, /**< Letter, lowercase */
|
||||
UTF8PROC_CATEGORY_LT = 3, /**< Letter, titlecase */
|
||||
UTF8PROC_CATEGORY_LM = 4, /**< Letter, modifier */
|
||||
UTF8PROC_CATEGORY_LO = 5, /**< Letter, other */
|
||||
UTF8PROC_CATEGORY_MN = 6, /**< Mark, nonspacing */
|
||||
UTF8PROC_CATEGORY_MC = 7, /**< Mark, spacing combining */
|
||||
UTF8PROC_CATEGORY_ME = 8, /**< Mark, enclosing */
|
||||
UTF8PROC_CATEGORY_ND = 9, /**< Number, decimal digit */
|
||||
UTF8PROC_CATEGORY_NL = 10, /**< Number, letter */
|
||||
UTF8PROC_CATEGORY_NO = 11, /**< Number, other */
|
||||
UTF8PROC_CATEGORY_PC = 12, /**< Punctuation, connector */
|
||||
UTF8PROC_CATEGORY_PD = 13, /**< Punctuation, dash */
|
||||
UTF8PROC_CATEGORY_PS = 14, /**< Punctuation, open */
|
||||
UTF8PROC_CATEGORY_PE = 15, /**< Punctuation, close */
|
||||
UTF8PROC_CATEGORY_PI = 16, /**< Punctuation, initial quote */
|
||||
UTF8PROC_CATEGORY_PF = 17, /**< Punctuation, final quote */
|
||||
UTF8PROC_CATEGORY_PO = 18, /**< Punctuation, other */
|
||||
UTF8PROC_CATEGORY_SM = 19, /**< Symbol, math */
|
||||
UTF8PROC_CATEGORY_SC = 20, /**< Symbol, currency */
|
||||
UTF8PROC_CATEGORY_SK = 21, /**< Symbol, modifier */
|
||||
UTF8PROC_CATEGORY_SO = 22, /**< Symbol, other */
|
||||
UTF8PROC_CATEGORY_ZS = 23, /**< Separator, space */
|
||||
UTF8PROC_CATEGORY_ZL = 24, /**< Separator, line */
|
||||
UTF8PROC_CATEGORY_ZP = 25, /**< Separator, paragraph */
|
||||
UTF8PROC_CATEGORY_CC = 26, /**< Other, control */
|
||||
UTF8PROC_CATEGORY_CF = 27, /**< Other, format */
|
||||
UTF8PROC_CATEGORY_CS = 28, /**< Other, surrogate */
|
||||
UTF8PROC_CATEGORY_CO = 29, /**< Other, private use */
|
||||
} utf8proc_category_t;
|
||||
|
||||
/** Bidirectional character classes. */
|
||||
typedef enum {
|
||||
UTF8PROC_BIDI_CLASS_L = 1, /**< Left-to-Right */
|
||||
UTF8PROC_BIDI_CLASS_LRE = 2, /**< Left-to-Right Embedding */
|
||||
UTF8PROC_BIDI_CLASS_LRO = 3, /**< Left-to-Right Override */
|
||||
UTF8PROC_BIDI_CLASS_R = 4, /**< Right-to-Left */
|
||||
UTF8PROC_BIDI_CLASS_AL = 5, /**< Right-to-Left Arabic */
|
||||
UTF8PROC_BIDI_CLASS_RLE = 6, /**< Right-to-Left Embedding */
|
||||
UTF8PROC_BIDI_CLASS_RLO = 7, /**< Right-to-Left Override */
|
||||
UTF8PROC_BIDI_CLASS_PDF = 8, /**< Pop Directional Format */
|
||||
UTF8PROC_BIDI_CLASS_EN = 9, /**< European Number */
|
||||
UTF8PROC_BIDI_CLASS_ES = 10, /**< European Separator */
|
||||
UTF8PROC_BIDI_CLASS_ET = 11, /**< European Number Terminator */
|
||||
UTF8PROC_BIDI_CLASS_AN = 12, /**< Arabic Number */
|
||||
UTF8PROC_BIDI_CLASS_CS = 13, /**< Common Number Separator */
|
||||
UTF8PROC_BIDI_CLASS_NSM = 14, /**< Nonspacing Mark */
|
||||
UTF8PROC_BIDI_CLASS_BN = 15, /**< Boundary Neutral */
|
||||
UTF8PROC_BIDI_CLASS_B = 16, /**< Paragraph Separator */
|
||||
UTF8PROC_BIDI_CLASS_S = 17, /**< Segment Separator */
|
||||
UTF8PROC_BIDI_CLASS_WS = 18, /**< Whitespace */
|
||||
UTF8PROC_BIDI_CLASS_ON = 19, /**< Other Neutrals */
|
||||
UTF8PROC_BIDI_CLASS_LRI = 20, /**< Left-to-Right Isolate */
|
||||
UTF8PROC_BIDI_CLASS_RLI = 21, /**< Right-to-Left Isolate */
|
||||
UTF8PROC_BIDI_CLASS_FSI = 22, /**< First Strong Isolate */
|
||||
UTF8PROC_BIDI_CLASS_PDI = 23, /**< Pop Directional Isolate */
|
||||
} utf8proc_bidi_class_t;
|
||||
|
||||
/** Decomposition type. */
|
||||
typedef enum {
|
||||
UTF8PROC_DECOMP_TYPE_FONT = 1, /**< Font */
|
||||
UTF8PROC_DECOMP_TYPE_NOBREAK = 2, /**< Nobreak */
|
||||
UTF8PROC_DECOMP_TYPE_INITIAL = 3, /**< Initial */
|
||||
UTF8PROC_DECOMP_TYPE_MEDIAL = 4, /**< Medial */
|
||||
UTF8PROC_DECOMP_TYPE_FINAL = 5, /**< Final */
|
||||
UTF8PROC_DECOMP_TYPE_ISOLATED = 6, /**< Isolated */
|
||||
UTF8PROC_DECOMP_TYPE_CIRCLE = 7, /**< Circle */
|
||||
UTF8PROC_DECOMP_TYPE_SUPER = 8, /**< Super */
|
||||
UTF8PROC_DECOMP_TYPE_SUB = 9, /**< Sub */
|
||||
UTF8PROC_DECOMP_TYPE_VERTICAL = 10, /**< Vertical */
|
||||
UTF8PROC_DECOMP_TYPE_WIDE = 11, /**< Wide */
|
||||
UTF8PROC_DECOMP_TYPE_NARROW = 12, /**< Narrow */
|
||||
UTF8PROC_DECOMP_TYPE_SMALL = 13, /**< Small */
|
||||
UTF8PROC_DECOMP_TYPE_SQUARE = 14, /**< Square */
|
||||
UTF8PROC_DECOMP_TYPE_FRACTION = 15, /**< Fraction */
|
||||
UTF8PROC_DECOMP_TYPE_COMPAT = 16, /**< Compat */
|
||||
} utf8proc_decomp_type_t;
|
||||
|
||||
/** Boundclass property. (TR29) */
|
||||
typedef enum {
|
||||
UTF8PROC_BOUNDCLASS_START = 0, /**< Start */
|
||||
UTF8PROC_BOUNDCLASS_OTHER = 1, /**< Other */
|
||||
UTF8PROC_BOUNDCLASS_CR = 2, /**< Cr */
|
||||
UTF8PROC_BOUNDCLASS_LF = 3, /**< Lf */
|
||||
UTF8PROC_BOUNDCLASS_CONTROL = 4, /**< Control */
|
||||
UTF8PROC_BOUNDCLASS_EXTEND = 5, /**< Extend */
|
||||
UTF8PROC_BOUNDCLASS_L = 6, /**< L */
|
||||
UTF8PROC_BOUNDCLASS_V = 7, /**< V */
|
||||
UTF8PROC_BOUNDCLASS_T = 8, /**< T */
|
||||
UTF8PROC_BOUNDCLASS_LV = 9, /**< Lv */
|
||||
UTF8PROC_BOUNDCLASS_LVT = 10, /**< Lvt */
|
||||
UTF8PROC_BOUNDCLASS_REGIONAL_INDICATOR = 11, /**< Regional indicator */
|
||||
UTF8PROC_BOUNDCLASS_SPACINGMARK = 12, /**< Spacingmark */
|
||||
UTF8PROC_BOUNDCLASS_PREPEND = 13, /**< Prepend */
|
||||
UTF8PROC_BOUNDCLASS_ZWJ = 14, /**< Zero Width Joiner */
|
||||
|
||||
/* the following are no longer used in Unicode 11, but we keep
|
||||
the constants here for backward compatibility */
|
||||
UTF8PROC_BOUNDCLASS_E_BASE = 15, /**< Emoji Base */
|
||||
UTF8PROC_BOUNDCLASS_E_MODIFIER = 16, /**< Emoji Modifier */
|
||||
UTF8PROC_BOUNDCLASS_GLUE_AFTER_ZWJ = 17, /**< Glue_After_ZWJ */
|
||||
UTF8PROC_BOUNDCLASS_E_BASE_GAZ = 18, /**< E_BASE + GLUE_AFTER_ZJW */
|
||||
|
||||
/* the Extended_Pictographic property is used in the Unicode 11
|
||||
grapheme-boundary rules, so we store it in the boundclass field */
|
||||
UTF8PROC_BOUNDCLASS_EXTENDED_PICTOGRAPHIC = 19,
|
||||
UTF8PROC_BOUNDCLASS_E_ZWG = 20, /* UTF8PROC_BOUNDCLASS_EXTENDED_PICTOGRAPHIC + ZWJ */
|
||||
} utf8proc_boundclass_t;
|
||||
|
||||
/**
|
||||
* Function pointer type passed to @ref utf8proc_map_custom and
|
||||
* @ref utf8proc_decompose_custom, which is used to specify a user-defined
|
||||
* mapping of codepoints to be applied in conjunction with other mappings.
|
||||
*/
|
||||
typedef utf8proc_int32_t (*utf8proc_custom_func)(utf8proc_int32_t codepoint, void *data);
|
||||
|
||||
/**
|
||||
* Array containing the byte lengths of a UTF-8 encoded codepoint based
|
||||
* on the first byte.
|
||||
*/
|
||||
UTF8PROC_DLLEXPORT extern const utf8proc_int8_t utf8proc_utf8class[256];
|
||||
|
||||
/**
|
||||
* Returns the utf8proc API version as a string MAJOR.MINOR.PATCH
|
||||
* (http://semver.org format), possibly with a "-dev" suffix for
|
||||
* development versions.
|
||||
*/
|
||||
UTF8PROC_DLLEXPORT const char *utf8proc_version(void);
|
||||
|
||||
/**
|
||||
* Returns the utf8proc supported Unicode version as a string MAJOR.MINOR.PATCH.
|
||||
*/
|
||||
UTF8PROC_DLLEXPORT const char *utf8proc_unicode_version(void);
|
||||
|
||||
/**
|
||||
* Returns an informative error string for the given utf8proc error code
|
||||
* (e.g. the error codes returned by @ref utf8proc_map).
|
||||
*/
|
||||
UTF8PROC_DLLEXPORT const char *utf8proc_errmsg(utf8proc_ssize_t errcode);
|
||||
|
||||
/**
|
||||
* Reads a single codepoint from the UTF-8 sequence being pointed to by `str`.
|
||||
* The maximum number of bytes read is `strlen`, unless `strlen` is
|
||||
* negative (in which case up to 4 bytes are read).
|
||||
*
|
||||
* If a valid codepoint could be read, it is stored in the variable
|
||||
* pointed to by `codepoint_ref`, otherwise that variable will be set to -1.
|
||||
* In case of success, the number of bytes read is returned; otherwise, a
|
||||
* negative error code is returned.
|
||||
*/
|
||||
UTF8PROC_DLLEXPORT utf8proc_ssize_t utf8proc_iterate(const utf8proc_uint8_t *str, utf8proc_ssize_t strlen, utf8proc_int32_t *codepoint_ref);
|
||||
|
||||
/**
|
||||
* Check if a codepoint is valid (regardless of whether it has been
|
||||
* assigned a value by the current Unicode standard).
|
||||
*
|
||||
* @return 1 if the given `codepoint` is valid and otherwise return 0.
|
||||
*/
|
||||
UTF8PROC_DLLEXPORT utf8proc_bool utf8proc_codepoint_valid(utf8proc_int32_t codepoint);
|
||||
|
||||
/**
|
||||
* Encodes the codepoint as an UTF-8 string in the byte array pointed
|
||||
* to by `dst`. This array must be at least 4 bytes long.
|
||||
*
|
||||
* In case of success the number of bytes written is returned, and
|
||||
* otherwise 0 is returned.
|
||||
*
|
||||
* This function does not check whether `codepoint` is valid Unicode.
|
||||
*/
|
||||
UTF8PROC_DLLEXPORT utf8proc_ssize_t utf8proc_encode_char(utf8proc_int32_t codepoint, utf8proc_uint8_t *dst);
|
||||
|
||||
/**
|
||||
* Look up the properties for a given codepoint.
|
||||
*
|
||||
* @param codepoint The Unicode codepoint.
|
||||
*
|
||||
* @returns
|
||||
* A pointer to a (constant) struct containing information about
|
||||
* the codepoint.
|
||||
* @par
|
||||
* If the codepoint is unassigned or invalid, a pointer to a special struct is
|
||||
* returned in which `category` is 0 (@ref UTF8PROC_CATEGORY_CN).
|
||||
*/
|
||||
UTF8PROC_DLLEXPORT const utf8proc_property_t *utf8proc_get_property(utf8proc_int32_t codepoint);
|
||||
|
||||
/** Decompose a codepoint into an array of codepoints.
|
||||
*
|
||||
* @param codepoint the codepoint.
|
||||
* @param dst the destination buffer.
|
||||
* @param bufsize the size of the destination buffer.
|
||||
* @param options one or more of the following flags:
|
||||
* - @ref UTF8PROC_REJECTNA - return an error `codepoint` is unassigned
|
||||
* - @ref UTF8PROC_IGNORE - strip "default ignorable" codepoints
|
||||
* - @ref UTF8PROC_CASEFOLD - apply Unicode casefolding
|
||||
* - @ref UTF8PROC_COMPAT - replace certain codepoints with their
|
||||
* compatibility decomposition
|
||||
* - @ref UTF8PROC_CHARBOUND - insert 0xFF bytes before each grapheme cluster
|
||||
* - @ref UTF8PROC_LUMP - lump certain different codepoints together
|
||||
* - @ref UTF8PROC_STRIPMARK - remove all character marks
|
||||
* - @ref UTF8PROC_STRIPNA - remove unassigned codepoints
|
||||
* @param last_boundclass
|
||||
* Pointer to an integer variable containing
|
||||
* the previous codepoint's boundary class if the @ref UTF8PROC_CHARBOUND
|
||||
* option is used. Otherwise, this parameter is ignored.
|
||||
*
|
||||
* @return
|
||||
* In case of success, the number of codepoints written is returned; in case
|
||||
* of an error, a negative error code is returned (@ref utf8proc_errmsg).
|
||||
* @par
|
||||
* If the number of written codepoints would be bigger than `bufsize`, the
|
||||
* required buffer size is returned, while the buffer will be overwritten with
|
||||
* undefined data.
|
||||
*/
|
||||
UTF8PROC_DLLEXPORT utf8proc_ssize_t utf8proc_decompose_char(
|
||||
utf8proc_int32_t codepoint, utf8proc_int32_t *dst, utf8proc_ssize_t bufsize,
|
||||
utf8proc_option_t options, int *last_boundclass
|
||||
);
|
||||
|
||||
/**
|
||||
* The same as @ref utf8proc_decompose_char, but acts on a whole UTF-8
|
||||
* string and orders the decomposed sequences correctly.
|
||||
*
|
||||
* If the @ref UTF8PROC_NULLTERM flag in `options` is set, processing
|
||||
* will be stopped, when a NULL byte is encounted, otherwise `strlen`
|
||||
* bytes are processed. The result (in the form of 32-bit unicode
|
||||
* codepoints) is written into the buffer being pointed to by
|
||||
* `buffer` (which must contain at least `bufsize` entries). In case of
|
||||
* success, the number of codepoints written is returned; in case of an
|
||||
* error, a negative error code is returned (@ref utf8proc_errmsg).
|
||||
* See @ref utf8proc_decompose_custom to supply additional transformations.
|
||||
*
|
||||
* If the number of written codepoints would be bigger than `bufsize`, the
|
||||
* required buffer size is returned, while the buffer will be overwritten with
|
||||
* undefined data.
|
||||
*/
|
||||
UTF8PROC_DLLEXPORT utf8proc_ssize_t utf8proc_decompose(
|
||||
const utf8proc_uint8_t *str, utf8proc_ssize_t strlen,
|
||||
utf8proc_int32_t *buffer, utf8proc_ssize_t bufsize, utf8proc_option_t options
|
||||
);
|
||||
|
||||
/**
|
||||
* The same as @ref utf8proc_decompose, but also takes a `custom_func` mapping function
|
||||
* that is called on each codepoint in `str` before any other transformations
|
||||
* (along with a `custom_data` pointer that is passed through to `custom_func`).
|
||||
* The `custom_func` argument is ignored if it is `NULL`. See also @ref utf8proc_map_custom.
|
||||
*/
|
||||
UTF8PROC_DLLEXPORT utf8proc_ssize_t utf8proc_decompose_custom(
|
||||
const utf8proc_uint8_t *str, utf8proc_ssize_t strlen,
|
||||
utf8proc_int32_t *buffer, utf8proc_ssize_t bufsize, utf8proc_option_t options,
|
||||
utf8proc_custom_func custom_func, void *custom_data
|
||||
);
|
||||
|
||||
/**
|
||||
* Normalizes the sequence of `length` codepoints pointed to by `buffer`
|
||||
* in-place (i.e., the result is also stored in `buffer`).
|
||||
*
|
||||
* @param buffer the (native-endian UTF-32) unicode codepoints to re-encode.
|
||||
* @param length the length (in codepoints) of the buffer.
|
||||
* @param options a bitwise or (`|`) of one or more of the following flags:
|
||||
* - @ref UTF8PROC_NLF2LS - convert LF, CRLF, CR and NEL into LS
|
||||
* - @ref UTF8PROC_NLF2PS - convert LF, CRLF, CR and NEL into PS
|
||||
* - @ref UTF8PROC_NLF2LF - convert LF, CRLF, CR and NEL into LF
|
||||
* - @ref UTF8PROC_STRIPCC - strip or convert all non-affected control characters
|
||||
* - @ref UTF8PROC_COMPOSE - try to combine decomposed codepoints into composite
|
||||
* codepoints
|
||||
* - @ref UTF8PROC_STABLE - prohibit combining characters that would violate
|
||||
* the unicode versioning stability
|
||||
*
|
||||
* @return
|
||||
* In case of success, the length (in codepoints) of the normalized UTF-32 string is
|
||||
* returned; otherwise, a negative error code is returned (@ref utf8proc_errmsg).
|
||||
*
|
||||
* @warning The entries of the array pointed to by `str` have to be in the
|
||||
* range `0x0000` to `0x10FFFF`. Otherwise, the program might crash!
|
||||
*/
|
||||
UTF8PROC_DLLEXPORT utf8proc_ssize_t utf8proc_normalize_utf32(utf8proc_int32_t *buffer, utf8proc_ssize_t length, utf8proc_option_t options);
|
||||
|
||||
/**
|
||||
* Reencodes the sequence of `length` codepoints pointed to by `buffer`
|
||||
* UTF-8 data in-place (i.e., the result is also stored in `buffer`).
|
||||
* Can optionally normalize the UTF-32 sequence prior to UTF-8 conversion.
|
||||
*
|
||||
* @param buffer the (native-endian UTF-32) unicode codepoints to re-encode.
|
||||
* @param length the length (in codepoints) of the buffer.
|
||||
* @param options a bitwise or (`|`) of one or more of the following flags:
|
||||
* - @ref UTF8PROC_NLF2LS - convert LF, CRLF, CR and NEL into LS
|
||||
* - @ref UTF8PROC_NLF2PS - convert LF, CRLF, CR and NEL into PS
|
||||
* - @ref UTF8PROC_NLF2LF - convert LF, CRLF, CR and NEL into LF
|
||||
* - @ref UTF8PROC_STRIPCC - strip or convert all non-affected control characters
|
||||
* - @ref UTF8PROC_COMPOSE - try to combine decomposed codepoints into composite
|
||||
* codepoints
|
||||
* - @ref UTF8PROC_STABLE - prohibit combining characters that would violate
|
||||
* the unicode versioning stability
|
||||
* - @ref UTF8PROC_CHARBOUND - insert 0xFF bytes before each grapheme cluster
|
||||
*
|
||||
* @return
|
||||
* In case of success, the length (in bytes) of the resulting nul-terminated
|
||||
* UTF-8 string is returned; otherwise, a negative error code is returned
|
||||
* (@ref utf8proc_errmsg).
|
||||
*
|
||||
* @warning The amount of free space pointed to by `buffer` must
|
||||
* exceed the amount of the input data by one byte, and the
|
||||
* entries of the array pointed to by `str` have to be in the
|
||||
* range `0x0000` to `0x10FFFF`. Otherwise, the program might crash!
|
||||
*/
|
||||
UTF8PROC_DLLEXPORT utf8proc_ssize_t utf8proc_reencode(utf8proc_int32_t *buffer, utf8proc_ssize_t length, utf8proc_option_t options);
|
||||
|
||||
/**
|
||||
* Given a pair of consecutive codepoints, return whether a grapheme break is
|
||||
* permitted between them (as defined by the extended grapheme clusters in UAX#29).
|
||||
*
|
||||
* @param codepoint1 The first codepoint.
|
||||
* @param codepoint2 The second codepoint, occurring consecutively after `codepoint1`.
|
||||
* @param state Beginning with Version 29 (Unicode 9.0.0), this algorithm requires
|
||||
* state to break graphemes. This state can be passed in as a pointer
|
||||
* in the `state` argument and should initially be set to 0. If the
|
||||
* state is not passed in (i.e. a null pointer is passed), UAX#29 rules
|
||||
* GB10/12/13 which require this state will not be applied, essentially
|
||||
* matching the rules in Unicode 8.0.0.
|
||||
*
|
||||
* @warning If the state parameter is used, `utf8proc_grapheme_break_stateful` must
|
||||
* be called IN ORDER on ALL potential breaks in a string. However, it
|
||||
* is safe to reset the state to zero after a grapheme break.
|
||||
*/
|
||||
UTF8PROC_DLLEXPORT utf8proc_bool utf8proc_grapheme_break_stateful(
|
||||
utf8proc_int32_t codepoint1, utf8proc_int32_t codepoint2, utf8proc_int32_t *state);
|
||||
|
||||
/**
|
||||
* Same as @ref utf8proc_grapheme_break_stateful, except without support for the
|
||||
* Unicode 9 additions to the algorithm. Supported for legacy reasons.
|
||||
*/
|
||||
UTF8PROC_DLLEXPORT utf8proc_bool utf8proc_grapheme_break(
|
||||
utf8proc_int32_t codepoint1, utf8proc_int32_t codepoint2);
|
||||
|
||||
|
||||
/**
|
||||
* Given a codepoint `c`, return the codepoint of the corresponding
|
||||
* lower-case character, if any; otherwise (if there is no lower-case
|
||||
* variant, or if `c` is not a valid codepoint) return `c`.
|
||||
*/
|
||||
UTF8PROC_DLLEXPORT utf8proc_int32_t utf8proc_tolower(utf8proc_int32_t c);
|
||||
|
||||
/**
|
||||
* Given a codepoint `c`, return the codepoint of the corresponding
|
||||
* upper-case character, if any; otherwise (if there is no upper-case
|
||||
* variant, or if `c` is not a valid codepoint) return `c`.
|
||||
*/
|
||||
UTF8PROC_DLLEXPORT utf8proc_int32_t utf8proc_toupper(utf8proc_int32_t c);
|
||||
|
||||
/**
|
||||
* Given a codepoint `c`, return the codepoint of the corresponding
|
||||
* title-case character, if any; otherwise (if there is no title-case
|
||||
* variant, or if `c` is not a valid codepoint) return `c`.
|
||||
*/
|
||||
UTF8PROC_DLLEXPORT utf8proc_int32_t utf8proc_totitle(utf8proc_int32_t c);
|
||||
|
||||
/**
|
||||
* Given a codepoint, return a character width analogous to `wcwidth(codepoint)`,
|
||||
* except that a width of 0 is returned for non-printable codepoints
|
||||
* instead of -1 as in `wcwidth`.
|
||||
*
|
||||
* @note
|
||||
* If you want to check for particular types of non-printable characters,
|
||||
* (analogous to `isprint` or `iscntrl`), use @ref utf8proc_category. */
|
||||
UTF8PROC_DLLEXPORT int utf8proc_charwidth(utf8proc_int32_t codepoint);
|
||||
|
||||
/**
|
||||
* Return the Unicode category for the codepoint (one of the
|
||||
* @ref utf8proc_category_t constants.)
|
||||
*/
|
||||
UTF8PROC_DLLEXPORT utf8proc_category_t utf8proc_category(utf8proc_int32_t codepoint);
|
||||
|
||||
/**
|
||||
* Return the two-letter (nul-terminated) Unicode category string for
|
||||
* the codepoint (e.g. `"Lu"` or `"Co"`).
|
||||
*/
|
||||
UTF8PROC_DLLEXPORT const char *utf8proc_category_string(utf8proc_int32_t codepoint);
|
||||
|
||||
/**
|
||||
* Maps the given UTF-8 string pointed to by `str` to a new UTF-8
|
||||
* string, allocated dynamically by `malloc` and returned via `dstptr`.
|
||||
*
|
||||
* If the @ref UTF8PROC_NULLTERM flag in the `options` field is set,
|
||||
* the length is determined by a NULL terminator, otherwise the
|
||||
* parameter `strlen` is evaluated to determine the string length, but
|
||||
* in any case the result will be NULL terminated (though it might
|
||||
* contain NULL characters with the string if `str` contained NULL
|
||||
* characters). Other flags in the `options` field are passed to the
|
||||
* functions defined above, and regarded as described. See also
|
||||
* @ref utf8proc_map_custom to supply a custom codepoint transformation.
|
||||
*
|
||||
* In case of success the length of the new string is returned,
|
||||
* otherwise a negative error code is returned.
|
||||
*
|
||||
* @note The memory of the new UTF-8 string will have been allocated
|
||||
* with `malloc`, and should therefore be deallocated with `free`.
|
||||
*/
|
||||
UTF8PROC_DLLEXPORT utf8proc_ssize_t utf8proc_map(
|
||||
const utf8proc_uint8_t *str, utf8proc_ssize_t strlen, utf8proc_uint8_t **dstptr, utf8proc_option_t options
|
||||
);
|
||||
|
||||
/**
|
||||
* Like @ref utf8proc_map, but also takes a `custom_func` mapping function
|
||||
* that is called on each codepoint in `str` before any other transformations
|
||||
* (along with a `custom_data` pointer that is passed through to `custom_func`).
|
||||
* The `custom_func` argument is ignored if it is `NULL`.
|
||||
*/
|
||||
UTF8PROC_DLLEXPORT utf8proc_ssize_t utf8proc_map_custom(
|
||||
const utf8proc_uint8_t *str, utf8proc_ssize_t strlen, utf8proc_uint8_t **dstptr, utf8proc_option_t options,
|
||||
utf8proc_custom_func custom_func, void *custom_data
|
||||
);
|
||||
|
||||
/** @name Unicode normalization
|
||||
*
|
||||
* Returns a pointer to newly allocated memory of a NFD, NFC, NFKD, NFKC or
|
||||
* NFKC_Casefold normalized version of the null-terminated string `str`. These
|
||||
* are shortcuts to calling @ref utf8proc_map with @ref UTF8PROC_NULLTERM
|
||||
* combined with @ref UTF8PROC_STABLE and flags indicating the normalization.
|
||||
*/
|
||||
/** @{ */
|
||||
/** NFD normalization (@ref UTF8PROC_DECOMPOSE). */
|
||||
UTF8PROC_DLLEXPORT utf8proc_uint8_t *utf8proc_NFD(const utf8proc_uint8_t *str);
|
||||
/** NFC normalization (@ref UTF8PROC_COMPOSE). */
|
||||
UTF8PROC_DLLEXPORT utf8proc_uint8_t *utf8proc_NFC(const utf8proc_uint8_t *str);
|
||||
/** NFKD normalization (@ref UTF8PROC_DECOMPOSE and @ref UTF8PROC_COMPAT). */
|
||||
UTF8PROC_DLLEXPORT utf8proc_uint8_t *utf8proc_NFKD(const utf8proc_uint8_t *str);
|
||||
/** NFKC normalization (@ref UTF8PROC_COMPOSE and @ref UTF8PROC_COMPAT). */
|
||||
UTF8PROC_DLLEXPORT utf8proc_uint8_t *utf8proc_NFKC(const utf8proc_uint8_t *str);
|
||||
/**
|
||||
* NFKC_Casefold normalization (@ref UTF8PROC_COMPOSE and @ref UTF8PROC_COMPAT
|
||||
* and @ref UTF8PROC_CASEFOLD and @ref UTF8PROC_IGNORE).
|
||||
**/
|
||||
UTF8PROC_DLLEXPORT utf8proc_uint8_t *utf8proc_NFKC_Casefold(const utf8proc_uint8_t *str);
|
||||
/** @} */
|
||||
|
||||
#ifdef __cplusplus
|
||||
}
|
||||
#endif
|
||||
|
||||
#endif
|
||||
14820
src/3rdparty/utf8proc/utf8proc_data.c
vendored
14820
src/3rdparty/utf8proc/utf8proc_data.c
vendored
File diff suppressed because it is too large
Load diff
|
|
@ -1,5 +1,5 @@
|
|||
# add_definitions()
|
||||
set(EXTRA_CORE_LIBS ${ZLIB_LIBRARIES} ${OPENSSL_LIBRARIES} ${ZSTD_LIBRARIES})
|
||||
set(EXTRA_CORE_LIBS ${ZLIB_LIBRARIES} ${ICU_LIBRARIES} ${OPENSSL_LIBRARIES} ${ZSTD_LIBRARIES})
|
||||
|
||||
set(CORE_PUBLIC_HEADERS
|
||||
${CORE_PUBLIC_HEADERS}
|
||||
|
|
@ -239,19 +239,9 @@ include_directories(
|
|||
${CMAKE_BINARY_DIR}/include/QtCore
|
||||
${CMAKE_BINARY_DIR}/privateinclude/QtCore
|
||||
${ZLIB_INCLUDE_DIRS}
|
||||
${ICU_INCLUDES}
|
||||
${OPENSSL_INCLUDE_DIR}
|
||||
${ZSTD_INCLUDES}
|
||||
${CMAKE_SOURCE_DIR}/src/3rdparty/utf8proc
|
||||
)
|
||||
|
||||
set(CORE_SOURCES
|
||||
${CORE_SOURCES}
|
||||
${CMAKE_SOURCE_DIR}/src/3rdparty/utf8proc/utf8proc.c
|
||||
)
|
||||
|
||||
set(CORE_HEADERS
|
||||
${CORE_HEADERS}
|
||||
${CMAKE_SOURCE_DIR}/src/3rdparty/utf8proc/utf8proc.h
|
||||
)
|
||||
|
||||
if(${KATIE_PLATFORM} STREQUAL "linux")
|
||||
|
|
|
|||
|
|
@ -42,9 +42,9 @@
|
|||
#include "qchar.h"
|
||||
#include "qdatastream.h"
|
||||
#include "qtextcodec.h"
|
||||
#include "qunicodetables_p.h"
|
||||
|
||||
#include "utf8proc.h"
|
||||
#include <unicode/uchar.h>
|
||||
#include <unicode/unorm2.h>
|
||||
|
||||
QT_BEGIN_NAMESPACE
|
||||
|
||||
|
|
@ -407,22 +407,23 @@ static inline uint to_ascii_upper(uint ucs4)
|
|||
description of the values.
|
||||
|
||||
\value NoDecomposition
|
||||
\value Circle
|
||||
\value Compat
|
||||
\value Final
|
||||
\value Canonical
|
||||
\value Font
|
||||
\value Fraction
|
||||
\value Initial
|
||||
\value Isolated
|
||||
\value Medial
|
||||
\value Narrow
|
||||
\value NoBreak
|
||||
\value Small
|
||||
\value Square
|
||||
\value Sub
|
||||
\value Initial
|
||||
\value Medial
|
||||
\value Final
|
||||
\value Isolated
|
||||
\value Circle
|
||||
\value Super
|
||||
\value Sub
|
||||
\value Vertical
|
||||
\value Wide
|
||||
\value Narrow
|
||||
\value Small
|
||||
\value Square
|
||||
\value Compat
|
||||
\value Fraction
|
||||
|
||||
\sa decomposition()
|
||||
*/
|
||||
|
|
@ -600,15 +601,7 @@ QChar::QChar(const uchar ch)
|
|||
*/
|
||||
bool QChar::isPrint() const
|
||||
{
|
||||
const utf8proc_category_t category = utf8proc_category(ucs);
|
||||
switch (category) {
|
||||
case UTF8PROC_CATEGORY_CC:
|
||||
case UTF8PROC_CATEGORY_CN:
|
||||
return false;
|
||||
default:
|
||||
return true;
|
||||
}
|
||||
return true;
|
||||
return u_isprint(ucs);
|
||||
}
|
||||
|
||||
/*!
|
||||
|
|
@ -619,17 +612,7 @@ bool QChar::isSpace() const
|
|||
{
|
||||
if(ucs >= 9 && ucs <= 13)
|
||||
return true;
|
||||
|
||||
const utf8proc_category_t category = utf8proc_category(ucs);
|
||||
switch (category) {
|
||||
case UTF8PROC_CATEGORY_ZS:
|
||||
case UTF8PROC_CATEGORY_ZL:
|
||||
case UTF8PROC_CATEGORY_ZP:
|
||||
return true;
|
||||
default:
|
||||
return false;
|
||||
}
|
||||
return false;
|
||||
return u_isblank(ucs);
|
||||
}
|
||||
|
||||
/*!
|
||||
|
|
@ -640,11 +623,11 @@ bool QChar::isSpace() const
|
|||
*/
|
||||
bool QChar::isMark() const
|
||||
{
|
||||
const utf8proc_category_t category = utf8proc_category(ucs);
|
||||
const int8_t category = u_charType(ucs);
|
||||
switch (category) {
|
||||
case UTF8PROC_CATEGORY_MN:
|
||||
case UTF8PROC_CATEGORY_MC:
|
||||
case UTF8PROC_CATEGORY_ME:
|
||||
case U_NON_SPACING_MARK:
|
||||
case U_COMBINING_SPACING_MARK:
|
||||
case U_ENCLOSING_MARK:
|
||||
return true;
|
||||
default:
|
||||
return false;
|
||||
|
|
@ -658,20 +641,7 @@ bool QChar::isMark() const
|
|||
*/
|
||||
bool QChar::isPunct() const
|
||||
{
|
||||
const utf8proc_category_t category = utf8proc_category(ucs);
|
||||
switch (category) {
|
||||
case UTF8PROC_CATEGORY_PC:
|
||||
case UTF8PROC_CATEGORY_PD:
|
||||
case UTF8PROC_CATEGORY_PS:
|
||||
case UTF8PROC_CATEGORY_PE:
|
||||
case UTF8PROC_CATEGORY_PI:
|
||||
case UTF8PROC_CATEGORY_PF:
|
||||
case UTF8PROC_CATEGORY_PO:
|
||||
return true;
|
||||
default:
|
||||
return false;
|
||||
}
|
||||
return false;
|
||||
return u_ispunct(ucs);
|
||||
}
|
||||
|
||||
/*!
|
||||
|
|
@ -680,18 +650,7 @@ bool QChar::isPunct() const
|
|||
*/
|
||||
bool QChar::isLetter() const
|
||||
{
|
||||
const utf8proc_category_t category = utf8proc_category(ucs);
|
||||
switch (category) {
|
||||
case UTF8PROC_CATEGORY_LU:
|
||||
case UTF8PROC_CATEGORY_LL:
|
||||
case UTF8PROC_CATEGORY_LT:
|
||||
case UTF8PROC_CATEGORY_LM:
|
||||
case UTF8PROC_CATEGORY_LO:
|
||||
return true;
|
||||
default:
|
||||
return false;
|
||||
}
|
||||
return false;
|
||||
return u_isalpha(ucs);
|
||||
}
|
||||
|
||||
/*!
|
||||
|
|
@ -705,16 +664,7 @@ bool QChar::isNumber() const
|
|||
if (is_ascii_char(ucs)) {
|
||||
return is_ascii_number(ucs);
|
||||
}
|
||||
const utf8proc_category_t category = utf8proc_category(ucs);
|
||||
switch (category) {
|
||||
case UTF8PROC_CATEGORY_ND:
|
||||
case UTF8PROC_CATEGORY_NL:
|
||||
case UTF8PROC_CATEGORY_NO:
|
||||
return true;
|
||||
default:
|
||||
return false;
|
||||
}
|
||||
return false;
|
||||
return u_isxdigit(ucs);
|
||||
}
|
||||
|
||||
/*!
|
||||
|
|
@ -726,23 +676,7 @@ bool QChar::isLetterOrNumber() const
|
|||
if (is_ascii_char(ucs)) {
|
||||
return is_ascii_letterornumber(ucs);
|
||||
}
|
||||
const utf8proc_category_t category = utf8proc_category(ucs);
|
||||
switch (category) {
|
||||
// letter
|
||||
case UTF8PROC_CATEGORY_LU:
|
||||
case UTF8PROC_CATEGORY_LL:
|
||||
case UTF8PROC_CATEGORY_LT:
|
||||
case UTF8PROC_CATEGORY_LM:
|
||||
case UTF8PROC_CATEGORY_LO:
|
||||
// number
|
||||
case UTF8PROC_CATEGORY_ND:
|
||||
case UTF8PROC_CATEGORY_NL:
|
||||
case UTF8PROC_CATEGORY_NO:
|
||||
return true;
|
||||
default:
|
||||
return false;
|
||||
}
|
||||
return false;
|
||||
return u_isalnum(ucs);
|
||||
}
|
||||
|
||||
|
||||
|
|
@ -755,14 +689,7 @@ bool QChar::isDigit() const
|
|||
if (is_ascii_char(ucs)) {
|
||||
return is_ascii_number(ucs);
|
||||
}
|
||||
const utf8proc_category_t category = utf8proc_category(ucs);
|
||||
switch (category) {
|
||||
case UTF8PROC_CATEGORY_ND:
|
||||
return true;
|
||||
default:
|
||||
return false;
|
||||
}
|
||||
return false;
|
||||
return u_isdigit(ucs);
|
||||
}
|
||||
|
||||
|
||||
|
|
@ -772,12 +699,12 @@ bool QChar::isDigit() const
|
|||
*/
|
||||
bool QChar::isSymbol() const
|
||||
{
|
||||
const utf8proc_category_t category = utf8proc_category(ucs);
|
||||
const int8_t category = u_charType(ucs);
|
||||
switch (category) {
|
||||
case UTF8PROC_CATEGORY_SM:
|
||||
case UTF8PROC_CATEGORY_SC:
|
||||
case UTF8PROC_CATEGORY_SK:
|
||||
case UTF8PROC_CATEGORY_SO:
|
||||
case U_MATH_SYMBOL:
|
||||
case U_CURRENCY_SYMBOL:
|
||||
case U_MODIFIER_SYMBOL:
|
||||
case U_OTHER_SYMBOL:
|
||||
return true;
|
||||
default:
|
||||
return false;
|
||||
|
|
@ -859,7 +786,7 @@ bool QChar::isSymbol() const
|
|||
*/
|
||||
int QChar::digitValue() const
|
||||
{
|
||||
return QUnicodeTables::digitValue(ucs);
|
||||
return QChar::digitValue(ucs);
|
||||
}
|
||||
|
||||
/*!
|
||||
|
|
@ -869,7 +796,7 @@ int QChar::digitValue() const
|
|||
*/
|
||||
int QChar::digitValue(const ushort ucs2)
|
||||
{
|
||||
return QUnicodeTables::digitValue(ucs2);
|
||||
return QChar::digitValue(uint(ucs2));
|
||||
}
|
||||
|
||||
/*!
|
||||
|
|
@ -879,71 +806,71 @@ int QChar::digitValue(const ushort ucs2)
|
|||
*/
|
||||
int QChar::digitValue(const uint ucs4)
|
||||
{
|
||||
return QUnicodeTables::digitValue(ucs4);
|
||||
return u_digit(ucs4, 10);
|
||||
}
|
||||
|
||||
#define QCHAR_CATEGORY(c) \
|
||||
const utf8proc_category_t category = utf8proc_category(c); \
|
||||
const int8_t category = u_charType(c); \
|
||||
switch (category) { \
|
||||
case UTF8PROC_CATEGORY_CN: \
|
||||
case U_GENERAL_OTHER_TYPES: \
|
||||
return QChar::Other_NotAssigned; \
|
||||
case UTF8PROC_CATEGORY_LU: \
|
||||
case U_UPPERCASE_LETTER: \
|
||||
return QChar::Letter_Uppercase; \
|
||||
case UTF8PROC_CATEGORY_LL: \
|
||||
case U_LOWERCASE_LETTER: \
|
||||
return QChar::Letter_Lowercase; \
|
||||
case UTF8PROC_CATEGORY_LT: \
|
||||
case U_TITLECASE_LETTER: \
|
||||
return QChar::Letter_Titlecase; \
|
||||
case UTF8PROC_CATEGORY_LM: \
|
||||
case U_MODIFIER_LETTER: \
|
||||
return QChar::Letter_Modifier; \
|
||||
case UTF8PROC_CATEGORY_LO: \
|
||||
case U_OTHER_LETTER: \
|
||||
return QChar::Letter_Other; \
|
||||
case UTF8PROC_CATEGORY_MN: \
|
||||
case U_NON_SPACING_MARK: \
|
||||
return QChar::Mark_NonSpacing; \
|
||||
case UTF8PROC_CATEGORY_MC: \
|
||||
case U_COMBINING_SPACING_MARK: \
|
||||
return QChar::Mark_SpacingCombining; \
|
||||
case UTF8PROC_CATEGORY_ME: \
|
||||
case U_ENCLOSING_MARK: \
|
||||
return QChar::Mark_Enclosing; \
|
||||
case UTF8PROC_CATEGORY_ND: \
|
||||
case U_DECIMAL_DIGIT_NUMBER: \
|
||||
return QChar::Number_DecimalDigit; \
|
||||
case UTF8PROC_CATEGORY_NL: \
|
||||
case U_LETTER_NUMBER: \
|
||||
return QChar::Number_Letter; \
|
||||
case UTF8PROC_CATEGORY_NO: \
|
||||
case U_OTHER_NUMBER: \
|
||||
return QChar::Number_Other; \
|
||||
case UTF8PROC_CATEGORY_PC: \
|
||||
case U_CONNECTOR_PUNCTUATION: \
|
||||
return QChar::Punctuation_Connector; \
|
||||
case UTF8PROC_CATEGORY_PD: \
|
||||
case U_DASH_PUNCTUATION: \
|
||||
return QChar::Punctuation_Dash; \
|
||||
case UTF8PROC_CATEGORY_PS: \
|
||||
case U_START_PUNCTUATION: \
|
||||
return QChar::Punctuation_Open; \
|
||||
case UTF8PROC_CATEGORY_PE: \
|
||||
case U_END_PUNCTUATION: \
|
||||
return QChar::Punctuation_Close; \
|
||||
case UTF8PROC_CATEGORY_PI: \
|
||||
case U_INITIAL_PUNCTUATION: \
|
||||
return QChar::Punctuation_InitialQuote; \
|
||||
case UTF8PROC_CATEGORY_PF: \
|
||||
case U_FINAL_PUNCTUATION: \
|
||||
return QChar::Punctuation_FinalQuote; \
|
||||
case UTF8PROC_CATEGORY_PO: \
|
||||
case U_OTHER_PUNCTUATION: \
|
||||
return QChar::Punctuation_Other; \
|
||||
case UTF8PROC_CATEGORY_SM: \
|
||||
case U_MATH_SYMBOL: \
|
||||
return QChar::Symbol_Math; \
|
||||
case UTF8PROC_CATEGORY_SC: \
|
||||
case U_CURRENCY_SYMBOL: \
|
||||
return QChar::Symbol_Currency; \
|
||||
case UTF8PROC_CATEGORY_SK: \
|
||||
case U_MODIFIER_SYMBOL: \
|
||||
return QChar::Symbol_Modifier; \
|
||||
case UTF8PROC_CATEGORY_SO: \
|
||||
case U_OTHER_SYMBOL: \
|
||||
return QChar::Symbol_Other; \
|
||||
case UTF8PROC_CATEGORY_ZS: \
|
||||
case U_SPACE_SEPARATOR: \
|
||||
return QChar::Separator_Space; \
|
||||
case UTF8PROC_CATEGORY_ZL: \
|
||||
case U_LINE_SEPARATOR: \
|
||||
return QChar::Separator_Line; \
|
||||
case UTF8PROC_CATEGORY_ZP: \
|
||||
case U_PARAGRAPH_SEPARATOR: \
|
||||
return QChar::Separator_Paragraph; \
|
||||
case UTF8PROC_CATEGORY_CC: \
|
||||
case U_CONTROL_CHAR: \
|
||||
return QChar::Other_Control; \
|
||||
case UTF8PROC_CATEGORY_CF: \
|
||||
case U_FORMAT_CHAR: \
|
||||
return QChar::Other_Format; \
|
||||
case UTF8PROC_CATEGORY_CS: \
|
||||
case U_SURROGATE: \
|
||||
return QChar::Other_Surrogate; \
|
||||
case UTF8PROC_CATEGORY_CO: \
|
||||
case U_PRIVATE_USE_CHAR: \
|
||||
return QChar::Other_PrivateUse; \
|
||||
} \
|
||||
return QChar::Other_NotAssigned;
|
||||
|
|
@ -976,53 +903,53 @@ QChar::Category QChar::category(const ushort ucs2)
|
|||
}
|
||||
|
||||
#define QCHAR_DIRECTION(c) \
|
||||
const utf8proc_property_t *property = utf8proc_get_property(c); \
|
||||
switch (property->bidi_class) { \
|
||||
case UTF8PROC_BIDI_CLASS_L: \
|
||||
const UCharDirection direction = u_charDirection(c); \
|
||||
switch (direction) { \
|
||||
case U_LEFT_TO_RIGHT: \
|
||||
return QChar::DirL; \
|
||||
case UTF8PROC_BIDI_CLASS_LRE: \
|
||||
case U_LEFT_TO_RIGHT_EMBEDDING: \
|
||||
return QChar::DirLRE; \
|
||||
case UTF8PROC_BIDI_CLASS_LRO: \
|
||||
case U_LEFT_TO_RIGHT_OVERRIDE: \
|
||||
return QChar::DirLRO; \
|
||||
case UTF8PROC_BIDI_CLASS_R: \
|
||||
case U_RIGHT_TO_LEFT: \
|
||||
return QChar::DirR; \
|
||||
case UTF8PROC_BIDI_CLASS_AL: \
|
||||
case U_RIGHT_TO_LEFT_ARABIC: \
|
||||
return QChar::DirAL; \
|
||||
case UTF8PROC_BIDI_CLASS_RLE: \
|
||||
case U_RIGHT_TO_LEFT_EMBEDDING: \
|
||||
return QChar::DirRLE; \
|
||||
case UTF8PROC_BIDI_CLASS_RLO: \
|
||||
case U_RIGHT_TO_LEFT_OVERRIDE: \
|
||||
return QChar::DirRLO; \
|
||||
case UTF8PROC_BIDI_CLASS_PDF: \
|
||||
case U_POP_DIRECTIONAL_FORMAT: \
|
||||
return QChar::DirPDF; \
|
||||
case UTF8PROC_BIDI_CLASS_EN: \
|
||||
case U_EUROPEAN_NUMBER: \
|
||||
return QChar::DirEN; \
|
||||
case UTF8PROC_BIDI_CLASS_ES: \
|
||||
case U_EUROPEAN_NUMBER_SEPARATOR: \
|
||||
return QChar::DirES; \
|
||||
case UTF8PROC_BIDI_CLASS_ET: \
|
||||
case U_EUROPEAN_NUMBER_TERMINATOR: \
|
||||
return QChar::DirET; \
|
||||
case UTF8PROC_BIDI_CLASS_AN: \
|
||||
case U_ARABIC_NUMBER: \
|
||||
return QChar::DirAN; \
|
||||
case UTF8PROC_BIDI_CLASS_CS: \
|
||||
case U_COMMON_NUMBER_SEPARATOR: \
|
||||
return QChar::DirCS; \
|
||||
case UTF8PROC_BIDI_CLASS_NSM: \
|
||||
case U_DIR_NON_SPACING_MARK: \
|
||||
return QChar::DirNSM; \
|
||||
case UTF8PROC_BIDI_CLASS_BN: \
|
||||
case U_BOUNDARY_NEUTRAL: \
|
||||
return QChar::DirBN; \
|
||||
case UTF8PROC_BIDI_CLASS_B: \
|
||||
case U_BLOCK_SEPARATOR: \
|
||||
return QChar::DirB; \
|
||||
case UTF8PROC_BIDI_CLASS_S: \
|
||||
case U_SEGMENT_SEPARATOR: \
|
||||
return QChar::DirS; \
|
||||
case UTF8PROC_BIDI_CLASS_WS: \
|
||||
case U_WHITE_SPACE_NEUTRAL: \
|
||||
return QChar::DirWS; \
|
||||
case UTF8PROC_BIDI_CLASS_ON: \
|
||||
case U_OTHER_NEUTRAL: \
|
||||
return QChar::DirON; \
|
||||
case UTF8PROC_BIDI_CLASS_LRI: \
|
||||
case U_LEFT_TO_RIGHT_ISOLATE: \
|
||||
return QChar::DirLRI; \
|
||||
case UTF8PROC_BIDI_CLASS_RLI: \
|
||||
case U_RIGHT_TO_LEFT_ISOLATE: \
|
||||
return QChar::DirRLI; \
|
||||
case UTF8PROC_BIDI_CLASS_FSI: \
|
||||
case U_FIRST_STRONG_ISOLATE: \
|
||||
return QChar::DirFSI; \
|
||||
case UTF8PROC_BIDI_CLASS_PDI: \
|
||||
case U_POP_DIRECTIONAL_ISOLATE: \
|
||||
return QChar::DirPDI; \
|
||||
} \
|
||||
return QChar::DirL;
|
||||
|
|
@ -1059,18 +986,7 @@ QChar::Direction QChar::direction(const ushort ucs2)
|
|||
*/
|
||||
QChar::Joining QChar::joining() const
|
||||
{
|
||||
return QUnicodeTables::joining(ucs);
|
||||
}
|
||||
|
||||
/*!
|
||||
\overload
|
||||
Returns information about the joining properties of the UCS-4-encoded
|
||||
character specified by \a ucs4 (needed for certain languages such as
|
||||
Arabic).
|
||||
*/
|
||||
QChar::Joining QChar::joining(const uint ucs4)
|
||||
{
|
||||
return QUnicodeTables::joining(ucs4);
|
||||
return QChar::joining(uint(ucs));
|
||||
}
|
||||
|
||||
/*!
|
||||
|
|
@ -1081,9 +997,35 @@ QChar::Joining QChar::joining(const uint ucs4)
|
|||
*/
|
||||
QChar::Joining QChar::joining(const ushort ucs2)
|
||||
{
|
||||
return QUnicodeTables::joining(ucs2);
|
||||
return QChar::joining(uint(ucs2));
|
||||
}
|
||||
|
||||
/*!
|
||||
\overload
|
||||
Returns information about the joining properties of the UCS-4-encoded
|
||||
character specified by \a ucs4 (needed for certain languages such as
|
||||
Arabic).
|
||||
*/
|
||||
QChar::Joining QChar::joining(const uint ucs4)
|
||||
{
|
||||
const int32_t property = u_getIntPropertyValue(ucs4, UCHAR_JOINING_TYPE);
|
||||
switch (property) {
|
||||
case U_JT_JOIN_CAUSING:
|
||||
return QChar::Causing;
|
||||
case U_JT_DUAL_JOINING:
|
||||
return QChar::Dual;
|
||||
case U_JT_LEFT_JOINING:
|
||||
return QChar::Left;
|
||||
case U_JT_RIGHT_JOINING:
|
||||
return QChar::Right;
|
||||
case U_JT_TRANSPARENT:
|
||||
return QChar::Transparent;
|
||||
case U_JT_NON_JOINING:
|
||||
// for compatibility
|
||||
return QChar::OtherJoining;
|
||||
}
|
||||
return QChar::OtherJoining;
|
||||
}
|
||||
|
||||
/*!
|
||||
Returns true if the character should be reversed if the text
|
||||
|
|
@ -1098,18 +1040,7 @@ bool QChar::hasMirrored() const
|
|||
if (is_ascii_char(ucs)) {
|
||||
return false;
|
||||
}
|
||||
const utf8proc_property_t *property = utf8proc_get_property(ucs);
|
||||
switch (property->bidi_class) {
|
||||
case UTF8PROC_BIDI_CLASS_R:
|
||||
case UTF8PROC_BIDI_CLASS_AL:
|
||||
case UTF8PROC_BIDI_CLASS_RLE:
|
||||
case UTF8PROC_BIDI_CLASS_RLO:
|
||||
case UTF8PROC_BIDI_CLASS_RLI:
|
||||
return true;
|
||||
default:
|
||||
return false;
|
||||
}
|
||||
return false;
|
||||
return u_isMirrored(ucs);
|
||||
}
|
||||
|
||||
/*!
|
||||
|
|
@ -1167,19 +1098,7 @@ bool QChar::isTitleCase() const
|
|||
*/
|
||||
QChar QChar::mirroredChar() const
|
||||
{
|
||||
return QUnicodeTables::mirroredChar(ucs);
|
||||
}
|
||||
|
||||
/*!
|
||||
\overload
|
||||
Returns the mirrored character if the UCS-4-encoded character specified
|
||||
by \a ucs4 is a mirrored character; otherwise returns the character itself.
|
||||
|
||||
\sa hasMirrored()
|
||||
*/
|
||||
uint QChar::mirroredChar(const uint ucs4)
|
||||
{
|
||||
return QUnicodeTables::mirroredChar(ucs4);
|
||||
return QChar::mirroredChar(ucs);
|
||||
}
|
||||
|
||||
/*!
|
||||
|
|
@ -1191,7 +1110,19 @@ uint QChar::mirroredChar(const uint ucs4)
|
|||
*/
|
||||
ushort QChar::mirroredChar(const ushort ucs2)
|
||||
{
|
||||
return QUnicodeTables::mirroredChar(ucs2);
|
||||
return QChar::mirroredChar(uint(ucs2));
|
||||
}
|
||||
|
||||
/*!
|
||||
\overload
|
||||
Returns the mirrored character if the UCS-4-encoded character specified
|
||||
by \a ucs4 is a mirrored character; otherwise returns the character itself.
|
||||
|
||||
\sa hasMirrored()
|
||||
*/
|
||||
uint QChar::mirroredChar(const uint ucs4)
|
||||
{
|
||||
return u_charMirror(ucs4);
|
||||
}
|
||||
|
||||
/*!
|
||||
|
|
@ -1210,14 +1141,26 @@ QString QChar::decomposition() const
|
|||
*/
|
||||
QString QChar::decomposition(const uint ucs4)
|
||||
{
|
||||
int buffer[4]; // ### use utf8proc_charwidth?
|
||||
int boundclass;
|
||||
const ssize_t decresult = utf8proc_decompose_char(ucs4, buffer, sizeof(buffer), UTF8PROC_DECOMPOSE, &boundclass);
|
||||
if (Q_UNLIKELY(decresult < 1)) {
|
||||
qWarning("QChar::decomposition: %s", utf8proc_errmsg(decresult));
|
||||
UErrorCode errorcode = U_ZERO_ERROR;
|
||||
const UNormalizer2 *normalizer = unorm2_getNFDInstance(&errorcode);
|
||||
if (Q_UNLIKELY(U_FAILURE(errorcode))) {
|
||||
qWarning("QChar::decomposition: %s", u_errorName(errorcode));
|
||||
return QString();
|
||||
}
|
||||
return QString::fromUtf8(reinterpret_cast<char*>(buffer), decresult);
|
||||
|
||||
UChar buffer[4];
|
||||
const int32_t decresult = unorm2_getDecomposition(normalizer, ucs4, buffer, sizeof(buffer), &errorcode);
|
||||
if (Q_UNLIKELY(decresult < 1)) {
|
||||
// no decomposition value
|
||||
return QString();
|
||||
}
|
||||
|
||||
if (Q_UNLIKELY(U_FAILURE(errorcode))) {
|
||||
qWarning("QChar::decomposition: %s", u_errorName(errorcode));
|
||||
return QString();
|
||||
}
|
||||
|
||||
return QString::fromUtf16(reinterpret_cast<ushort*>(buffer), decresult);
|
||||
}
|
||||
|
||||
/*!
|
||||
|
|
@ -1236,40 +1179,44 @@ QChar::Decomposition QChar::decompositionTag() const
|
|||
*/
|
||||
QChar::Decomposition QChar::decompositionTag(const uint ucs4)
|
||||
{
|
||||
const utf8proc_property_t *property = utf8proc_get_property(ucs4);
|
||||
switch (property->decomp_type) {
|
||||
case UTF8PROC_DECOMP_TYPE_FONT:
|
||||
const int32_t property = u_getIntPropertyValue(ucs4, UCHAR_DECOMPOSITION_TYPE);
|
||||
switch (property) {
|
||||
case U_DT_CANONICAL:
|
||||
return QChar::Canonical;
|
||||
case U_DT_FONT:
|
||||
return QChar::Font;
|
||||
case UTF8PROC_DECOMP_TYPE_NOBREAK:
|
||||
case U_DT_NOBREAK:
|
||||
return QChar::NoBreak;
|
||||
case UTF8PROC_DECOMP_TYPE_INITIAL:
|
||||
case U_DT_INITIAL:
|
||||
return QChar::Initial;
|
||||
case UTF8PROC_DECOMP_TYPE_MEDIAL:
|
||||
case U_DT_MEDIAL:
|
||||
return QChar::Medial;
|
||||
case UTF8PROC_DECOMP_TYPE_FINAL:
|
||||
case U_DT_FINAL:
|
||||
return QChar::Final;
|
||||
case UTF8PROC_DECOMP_TYPE_ISOLATED:
|
||||
case U_DT_ISOLATED:
|
||||
return QChar::Isolated;
|
||||
case UTF8PROC_DECOMP_TYPE_CIRCLE:
|
||||
case U_DT_CIRCLE:
|
||||
return QChar::Circle;
|
||||
case UTF8PROC_DECOMP_TYPE_SUPER:
|
||||
case U_DT_SUPER:
|
||||
return QChar::Super;
|
||||
case UTF8PROC_DECOMP_TYPE_SUB:
|
||||
case U_DT_SUB:
|
||||
return QChar::Sub;
|
||||
case UTF8PROC_DECOMP_TYPE_VERTICAL:
|
||||
case U_DT_VERTICAL:
|
||||
return QChar::Vertical;
|
||||
case UTF8PROC_DECOMP_TYPE_WIDE:
|
||||
case U_DT_WIDE:
|
||||
return QChar::Wide;
|
||||
case UTF8PROC_DECOMP_TYPE_NARROW:
|
||||
case U_DT_NARROW:
|
||||
return QChar::Narrow;
|
||||
case UTF8PROC_DECOMP_TYPE_SMALL:
|
||||
case U_DT_SMALL:
|
||||
return QChar::Small;
|
||||
case UTF8PROC_DECOMP_TYPE_SQUARE:
|
||||
case U_DT_SQUARE:
|
||||
return QChar::Square;
|
||||
case UTF8PROC_DECOMP_TYPE_FRACTION:
|
||||
case U_DT_FRACTION:
|
||||
return QChar::Fraction;
|
||||
case UTF8PROC_DECOMP_TYPE_COMPAT:
|
||||
case U_DT_COMPAT:
|
||||
return QChar::Compat;
|
||||
U_DT_NONE:
|
||||
return QChar::NoDecomposition;
|
||||
}
|
||||
return QChar::NoDecomposition;
|
||||
}
|
||||
|
|
@ -1279,17 +1226,7 @@ QChar::Decomposition QChar::decompositionTag(const uint ucs4)
|
|||
*/
|
||||
QChar::UnicodeVersion QChar::unicodeVersion() const
|
||||
{
|
||||
return QUnicodeTables::unicodeVersion(ucs);
|
||||
}
|
||||
|
||||
/*!
|
||||
\overload
|
||||
Returns the Unicode version that introduced the character specified in
|
||||
its UCS-4-encoded form as \a ucs4.
|
||||
*/
|
||||
QChar::UnicodeVersion QChar::unicodeVersion(const uint ucs4)
|
||||
{
|
||||
return QUnicodeTables::unicodeVersion(ucs4);
|
||||
return QChar::unicodeVersion(ucs);
|
||||
}
|
||||
|
||||
/*!
|
||||
|
|
@ -1299,7 +1236,67 @@ QChar::UnicodeVersion QChar::unicodeVersion(const uint ucs4)
|
|||
*/
|
||||
QChar::UnicodeVersion QChar::unicodeVersion(const ushort ucs2)
|
||||
{
|
||||
return QUnicodeTables::unicodeVersion(ucs2);
|
||||
return QChar::unicodeVersion(uint(ucs2));
|
||||
}
|
||||
|
||||
/*!
|
||||
\overload
|
||||
Returns the Unicode version that introduced the character specified in
|
||||
its UCS-4-encoded form as \a ucs4.
|
||||
*/
|
||||
QChar::UnicodeVersion QChar::unicodeVersion(const uint ucs4)
|
||||
{
|
||||
UVersionInfo info;
|
||||
u_charAge(ucs4, info);
|
||||
QByteArray version(U_MAX_VERSION_STRING_LENGTH, Qt::Uninitialized);
|
||||
u_versionToString(info, version.data());
|
||||
|
||||
if (version == "1.1") {
|
||||
return QChar::Unicode_1_1;
|
||||
} else if (version == "2.0") {
|
||||
return QChar::Unicode_2_0;
|
||||
} else if (version == "2.1") {
|
||||
return QChar::Unicode_2_1;
|
||||
} else if (version == "3.0") {
|
||||
return QChar::Unicode_3_0;
|
||||
} else if (version == "3.1") {
|
||||
return QChar::Unicode_3_1;
|
||||
} else if (version == "3.2") {
|
||||
return QChar::Unicode_3_2;
|
||||
} else if (version == "4.0") {
|
||||
return QChar::Unicode_4_0;
|
||||
} else if (version == "4.1") {
|
||||
return QChar::Unicode_4_1;
|
||||
} else if (version == "5.0") {
|
||||
return QChar::Unicode_5_0;
|
||||
} else if (version == "5.1") {
|
||||
return QChar::Unicode_5_1;
|
||||
} else if (version == "5.2") {
|
||||
return QChar::Unicode_5_2;
|
||||
} else if (version == "6.0") {
|
||||
return QChar::Unicode_6_0;
|
||||
} else if (version == "6.1") {
|
||||
return QChar::Unicode_6_1;
|
||||
} else if (version == "6.2") {
|
||||
return QChar::Unicode_6_2;
|
||||
} else if (version == "6.3") {
|
||||
return QChar::Unicode_6_3;
|
||||
} else if (version == "7.0") {
|
||||
return QChar::Unicode_7_0;
|
||||
} else if (version == "8.0") {
|
||||
return QChar::Unicode_8_0;
|
||||
} else if (version == "9.0") {
|
||||
return QChar::Unicode_9_0;
|
||||
} else if (version == "10.0") {
|
||||
return QChar::Unicode_10_0;
|
||||
} else if (version == "11.0") {
|
||||
return QChar::Unicode_11_0;
|
||||
} else if (version == "12.0") {
|
||||
return QChar::Unicode_12_0;
|
||||
} else if (version == "12.1") {
|
||||
return QChar::Unicode_12_1;
|
||||
}
|
||||
return QChar::Unicode_Unassigned;
|
||||
}
|
||||
|
||||
/*!
|
||||
|
|
@ -1318,10 +1315,18 @@ QChar::UnicodeVersion QChar::currentUnicodeVersion()
|
|||
*/
|
||||
QChar QChar::toLower() const
|
||||
{
|
||||
if (is_ascii_char(ucs)) {
|
||||
return to_ascii_lower(ucs);
|
||||
}
|
||||
return utf8proc_tolower(ucs);
|
||||
return QChar::toLower(ucs);
|
||||
}
|
||||
|
||||
/*!
|
||||
\overload
|
||||
Returns the lowercase equivalent of the UCS-2-encoded character specified
|
||||
by \a ucs2 if the character is uppercase or titlecase; otherwise returns
|
||||
the character itself.
|
||||
*/
|
||||
ushort QChar::toLower(const ushort ucs2)
|
||||
{
|
||||
return QChar::toLower(uint(ucs2));
|
||||
}
|
||||
|
||||
/*!
|
||||
|
|
@ -1335,21 +1340,7 @@ uint QChar::toLower(const uint ucs4)
|
|||
if (is_ascii_char(ucs4)) {
|
||||
return to_ascii_lower(ucs4);
|
||||
}
|
||||
return utf8proc_tolower(ucs4);
|
||||
}
|
||||
|
||||
/*!
|
||||
\overload
|
||||
Returns the lowercase equivalent of the UCS-2-encoded character specified
|
||||
by \a ucs2 if the character is uppercase or titlecase; otherwise returns
|
||||
the character itself.
|
||||
*/
|
||||
ushort QChar::toLower(const ushort ucs2)
|
||||
{
|
||||
if (is_ascii_char(ucs2)) {
|
||||
return to_ascii_lower(ucs2);
|
||||
}
|
||||
return utf8proc_tolower(ucs2);
|
||||
return u_tolower(ucs4);
|
||||
}
|
||||
|
||||
/*!
|
||||
|
|
@ -1358,10 +1349,18 @@ ushort QChar::toLower(const ushort ucs2)
|
|||
*/
|
||||
QChar QChar::toUpper() const
|
||||
{
|
||||
if (is_ascii_char(ucs)) {
|
||||
return to_ascii_upper(ucs);
|
||||
}
|
||||
return utf8proc_toupper(ucs);
|
||||
return QChar::toUpper(ucs);
|
||||
}
|
||||
|
||||
/*!
|
||||
\overload
|
||||
Returns the uppercase equivalent of the UCS-2-encoded character specified
|
||||
by \a ucs2 if the character is lowercase or titlecase; otherwise returns
|
||||
the character itself.
|
||||
*/
|
||||
ushort QChar::toUpper(const ushort ucs2)
|
||||
{
|
||||
return QChar::toUpper(uint(ucs2));
|
||||
}
|
||||
|
||||
/*!
|
||||
|
|
@ -1375,21 +1374,7 @@ uint QChar::toUpper(const uint ucs4)
|
|||
if (is_ascii_char(ucs4)) {
|
||||
return to_ascii_upper(ucs4);
|
||||
}
|
||||
return utf8proc_toupper(ucs4);
|
||||
}
|
||||
|
||||
/*!
|
||||
\overload
|
||||
Returns the uppercase equivalent of the UCS-2-encoded character specified
|
||||
by \a ucs2 if the character is lowercase or titlecase; otherwise returns
|
||||
the character itself.
|
||||
*/
|
||||
ushort QChar::toUpper(const ushort ucs2)
|
||||
{
|
||||
if (is_ascii_char(ucs2)) {
|
||||
return to_ascii_upper(ucs2);
|
||||
}
|
||||
return utf8proc_toupper(ucs2);
|
||||
return u_toupper(ucs4);
|
||||
}
|
||||
|
||||
/*!
|
||||
|
|
@ -1398,10 +1383,18 @@ ushort QChar::toUpper(const ushort ucs2)
|
|||
*/
|
||||
QChar QChar::toTitleCase() const
|
||||
{
|
||||
if (is_ascii_char(ucs)) {
|
||||
return to_ascii_upper(ucs);
|
||||
}
|
||||
return utf8proc_totitle(ucs);
|
||||
return QChar::toTitleCase(ucs);
|
||||
}
|
||||
|
||||
/*!
|
||||
\overload
|
||||
Returns the title case equivalent of the UCS-2-encoded character specified
|
||||
by \a ucs2 if the character is lowercase or uppercase; otherwise returns
|
||||
the character itself.
|
||||
*/
|
||||
ushort QChar::toTitleCase(const ushort ucs2)
|
||||
{
|
||||
return QChar::toTitleCase(uint(ucs2));
|
||||
}
|
||||
|
||||
/*!
|
||||
|
|
@ -1415,21 +1408,7 @@ uint QChar::toTitleCase(const uint ucs4)
|
|||
if (is_ascii_char(ucs4)) {
|
||||
return to_ascii_upper(ucs4);
|
||||
}
|
||||
return utf8proc_totitle(ucs4);
|
||||
}
|
||||
|
||||
/*!
|
||||
\overload
|
||||
Returns the title case equivalent of the UCS-2-encoded character specified
|
||||
by \a ucs2 if the character is lowercase or uppercase; otherwise returns
|
||||
the character itself.
|
||||
*/
|
||||
ushort QChar::toTitleCase(const ushort ucs2)
|
||||
{
|
||||
if (is_ascii_char(ucs2)) {
|
||||
return to_ascii_upper(ucs2);
|
||||
}
|
||||
return utf8proc_totitle(ucs2);
|
||||
return u_totitle(ucs4);
|
||||
}
|
||||
|
||||
/*!
|
||||
|
|
@ -1438,17 +1417,17 @@ ushort QChar::toTitleCase(const ushort ucs2)
|
|||
*/
|
||||
QChar QChar::toCaseFolded() const
|
||||
{
|
||||
if (is_ascii_char(ucs)) {
|
||||
return to_ascii_lower(ucs);
|
||||
}
|
||||
int buffer[4]; // ### use utf8proc_charwidth?
|
||||
int boundclass;
|
||||
const ssize_t decresult = utf8proc_decompose_char(ucs, buffer, sizeof(buffer), UTF8PROC_CASEFOLD, &boundclass);
|
||||
if (Q_UNLIKELY(decresult < 1)) {
|
||||
qWarning("QChar::toCaseFolded: %s", utf8proc_errmsg(decresult));
|
||||
return QChar(ucs);
|
||||
}
|
||||
return QChar(*buffer);
|
||||
return QChar::toCaseFolded(ucs);
|
||||
}
|
||||
|
||||
/*!
|
||||
\overload
|
||||
Returns the case folded equivalent of the UCS-2-encoded character specified
|
||||
by \a ucs2. For most Unicode characters this is the same as toLowerCase().
|
||||
*/
|
||||
ushort QChar::toCaseFolded(const ushort ucs2)
|
||||
{
|
||||
return QChar::toCaseFolded(uint(ucs2));
|
||||
}
|
||||
|
||||
/*!
|
||||
|
|
@ -1461,37 +1440,9 @@ uint QChar::toCaseFolded(const uint ucs4)
|
|||
if (is_ascii_char(ucs4)) {
|
||||
return to_ascii_lower(ucs4);
|
||||
}
|
||||
int buffer[4]; // ### use utf8proc_charwidth?
|
||||
int boundclass;
|
||||
const ssize_t decresult = utf8proc_decompose_char(ucs4, buffer, sizeof(buffer), UTF8PROC_CASEFOLD, &boundclass);
|
||||
if (Q_UNLIKELY(decresult < 1)) {
|
||||
qWarning("QChar::toCaseFolded: %s", utf8proc_errmsg(decresult));
|
||||
return ucs4;
|
||||
}
|
||||
return uint(*buffer);
|
||||
return u_foldCase(ucs4, U_FOLD_CASE_DEFAULT);
|
||||
}
|
||||
|
||||
/*!
|
||||
\overload
|
||||
Returns the case folded equivalent of the UCS-2-encoded character specified
|
||||
by \a ucs2. For most Unicode characters this is the same as toLowerCase().
|
||||
*/
|
||||
ushort QChar::toCaseFolded(const ushort ucs2)
|
||||
{
|
||||
if (is_ascii_char(ucs2)) {
|
||||
return to_ascii_lower(ucs2);
|
||||
}
|
||||
int buffer[4]; // ### use utf8proc_charwidth?
|
||||
int boundclass;
|
||||
const ssize_t decresult = utf8proc_decompose_char(ucs2, buffer, sizeof(buffer), UTF8PROC_CASEFOLD, &boundclass);
|
||||
if (Q_UNLIKELY(decresult < 1)) {
|
||||
qWarning("QChar::toCaseFolded: %s", utf8proc_errmsg(decresult));
|
||||
return ucs2;
|
||||
}
|
||||
return ushort(*buffer);
|
||||
}
|
||||
|
||||
|
||||
/*!
|
||||
\fn char QChar::latin1() const
|
||||
|
||||
|
|
|
|||
|
|
@ -149,6 +149,7 @@ public:
|
|||
|
||||
enum Decomposition {
|
||||
NoDecomposition,
|
||||
Canonical,
|
||||
Font,
|
||||
NoBreak,
|
||||
Initial,
|
||||
|
|
|
|||
|
|
@ -50,7 +50,6 @@
|
|||
#include "qendian.h"
|
||||
#include "qmutex.h"
|
||||
#include "qcorecommon_p.h"
|
||||
#include "utf8proc.h"
|
||||
|
||||
#include <limits.h>
|
||||
#include <string.h>
|
||||
|
|
@ -58,6 +57,8 @@
|
|||
#include <stdio.h>
|
||||
#include <stdarg.h>
|
||||
|
||||
#include <unicode/unorm2.h>
|
||||
|
||||
QT_BEGIN_NAMESPACE
|
||||
|
||||
#ifndef QT_NO_TEXTCODEC
|
||||
|
|
@ -5756,31 +5757,51 @@ QString QString::repeated(int times) const
|
|||
void qt_string_normalize(QString *data, QString::NormalizationForm mode, QChar::UnicodeVersion version, int from)
|
||||
{
|
||||
Q_UNUSED(version);
|
||||
const utf8proc_uint8_t *d = reinterpret_cast<const utf8proc_uint8_t*>(data->constData() + from);
|
||||
utf8proc_uint8_t *p = Q_NULLPTR;
|
||||
UErrorCode errorcode = U_ZERO_ERROR;
|
||||
const UNormalizer2 *normalizer = Q_NULLPTR;
|
||||
|
||||
switch (mode) {
|
||||
case QString::NormalizationForm_D: {
|
||||
p = utf8proc_NFKD(d);
|
||||
normalizer = unorm2_getNFDInstance(&errorcode);
|
||||
break;
|
||||
}
|
||||
case QString::NormalizationForm_C: {
|
||||
p = utf8proc_NFC(d);
|
||||
normalizer = unorm2_getNFCInstance(&errorcode);
|
||||
break;
|
||||
}
|
||||
case QString::NormalizationForm_KD: {
|
||||
p = utf8proc_NFKD(d);
|
||||
normalizer = unorm2_getNFKDInstance(&errorcode);
|
||||
break;
|
||||
}
|
||||
case QString::NormalizationForm_KC: {
|
||||
p = utf8proc_NFKC(d);
|
||||
normalizer = unorm2_getNFKCInstance(&errorcode);
|
||||
break;
|
||||
}
|
||||
}
|
||||
|
||||
data->setUtf16(reinterpret_cast<const ushort*>(p), qstrlen(reinterpret_cast<char*>(p)));
|
||||
if (p)
|
||||
::free(p);
|
||||
if (Q_UNLIKELY(U_FAILURE(errorcode))) {
|
||||
qWarning("QString::normalized: %s", u_errorName(errorcode));
|
||||
data->clear();
|
||||
return;
|
||||
}
|
||||
|
||||
const int size = data->size() - from;
|
||||
UChar buffer[size * 2];
|
||||
const int32_t decresult = unorm2_normalize(normalizer, reinterpret_cast<const UChar*>(data->unicode() + from),
|
||||
size, buffer, sizeof(buffer), &errorcode);
|
||||
if (Q_UNLIKELY(decresult < 1)) {
|
||||
// no normalization value
|
||||
data->clear();
|
||||
return;
|
||||
}
|
||||
|
||||
if (Q_UNLIKELY(U_FAILURE(errorcode))) {
|
||||
qWarning("QString::normalized: %s", u_errorName(errorcode));
|
||||
data->clear();
|
||||
return;
|
||||
}
|
||||
|
||||
data->setUnicode(reinterpret_cast<const QChar*>(buffer), decresult);
|
||||
}
|
||||
|
||||
/*!
|
||||
|
|
|
|||
File diff suppressed because it is too large
Load diff
|
|
@ -53,21 +53,6 @@ QT_BEGIN_NAMESPACE
|
|||
|
||||
namespace QUnicodeTables {
|
||||
|
||||
// required by QChar
|
||||
Q_CORE_EXPORT int QT_FASTCALL digitValue(uint ucs4);
|
||||
inline int QT_FASTCALL digitValue(ushort ucs2)
|
||||
{ return QUnicodeTables::digitValue(uint(ucs2)); }
|
||||
Q_CORE_EXPORT QChar::Joining QT_FASTCALL joining(uint ucs4);
|
||||
inline QChar::Joining QT_FASTCALL joining(ushort ucs2)
|
||||
{ return QUnicodeTables::joining(uint(ucs2)); }
|
||||
Q_CORE_EXPORT uint QT_FASTCALL mirroredChar(uint ucs4);
|
||||
inline ushort QT_FASTCALL mirroredChar(ushort ucs2)
|
||||
{ return QUnicodeTables::mirroredChar(uint(ucs2)); }
|
||||
Q_CORE_EXPORT QChar::UnicodeVersion QT_FASTCALL unicodeVersion(uint ucs4);
|
||||
inline QChar::UnicodeVersion QT_FASTCALL unicodeVersion(ushort ucs2)
|
||||
{ return QUnicodeTables::unicodeVersion(uint(ucs2)); }
|
||||
|
||||
|
||||
// required by Harfbuzz
|
||||
enum CombiningClass {
|
||||
Combining_NotOrdered = 0,
|
||||
|
|
|
|||
|
|
@ -7,7 +7,7 @@ include_directories(
|
|||
${CMAKE_BINARY_DIR}/include/QtCore
|
||||
${CMAKE_BINARY_DIR}/privateinclude/QtCore
|
||||
${CMAKE_CURRENT_SOURCE_DIR}
|
||||
${CMAKE_SOURCE_DIR}/src/3rdparty/utf8proc
|
||||
${ICU_INCLUDES}
|
||||
)
|
||||
|
||||
set(MOC_SOURCES
|
||||
|
|
@ -87,11 +87,11 @@ set(BOOTSTRAP_SOURCES
|
|||
${CMAKE_SOURCE_DIR}/src/core/tools/qlocale_unix.cpp
|
||||
${CMAKE_SOURCE_DIR}/src/core/tools/qlocale_std.cpp
|
||||
${CMAKE_SOURCE_DIR}/src/core/tools/qunicodetables.cpp
|
||||
${CMAKE_SOURCE_DIR}/src/3rdparty/utf8proc/utf8proc.c
|
||||
)
|
||||
|
||||
add_executable(bootstrap_moc ${BOOTSTRAP_SOURCES} ${MOC_SOURCES})
|
||||
target_compile_definitions(bootstrap_moc PRIVATE ${BOOTSTRAP_DEFINITIONS})
|
||||
target_link_libraries(bootstrap_moc ${ICU_LIBRARIES})
|
||||
|
||||
add_executable(moc ${MOC_SOURCES})
|
||||
target_link_libraries(moc ${EXTRA_MOC_LIBS})
|
||||
|
|
|
|||
|
|
@ -44,10 +44,6 @@
|
|||
#include <QTextCodec>
|
||||
#include <QtTest/QtTest>
|
||||
|
||||
#if !defined(QWS) && defined(Q_OS_MAC)
|
||||
#include "qcore_mac_p.h"
|
||||
#endif
|
||||
|
||||
#ifdef Q_OS_UNIX
|
||||
#include <sys/ipc.h>
|
||||
#include <sys/mman.h>
|
||||
|
|
@ -83,18 +79,6 @@ private slots:
|
|||
void toLower() const;
|
||||
void toUpper() const;
|
||||
void toCaseFolded() const;
|
||||
|
||||
#if !defined(QWS) && defined(Q_OS_MAC)
|
||||
void QCFString_data() const;
|
||||
void QCFString_toCFStringRef_data() const;
|
||||
void QCFString_toCFStringRef() const;
|
||||
void QCFString_operatorCFStringRef_data() const;
|
||||
void QCFString_operatorCFStringRef() const;
|
||||
void QCFString_toQString_data() const;
|
||||
void QCFString_toQString() const;
|
||||
void QCFString_operatorQString_data() const;
|
||||
void QCFString_operatorQString() const;
|
||||
#endif // !defined(QWS) && defined(Q_OS_MAC)
|
||||
};
|
||||
|
||||
void tst_QString::equals() const
|
||||
|
|
|
|||
Loading…
Add table
Reference in a new issue