From 402883c78e2f448694e8be62c4cb9f3e203487ad Mon Sep 17 00:00:00 2001 From: "Steven G. Johnson" Date: Fri, 6 Mar 2015 12:43:37 -0500 Subject: rename back to utf8proc now that we are taking over maintenance --- Makefile | 30 ++--- README.md | 50 ++++---- mojibake.h | 424 ------------------------------------------------------------- tests.h | 2 +- utf8proc.c | 12 +- utf8proc.h | 424 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ 6 files changed, 468 insertions(+), 474 deletions(-) delete mode 100644 mojibake.h create mode 100644 utf8proc.h diff --git a/Makefile b/Makefile index 7f3aaa0..8517192 100644 --- a/Makefile +++ b/Makefile @@ -1,4 +1,4 @@ -# libmojibake Makefile +# libutf8proc Makefile CURL=curl RUBY=ruby @@ -7,7 +7,7 @@ MAKE=make # settings -cflags = -O2 -std=c99 -pedantic -Wall -fpic -DMOJIBAKE_EXPORTS $(CFLAGS) +cflags = -O2 -std=c99 -pedantic -Wall -fpic -DUTF8PROC_EXPORTS $(CFLAGS) cc = $(CC) $(cflags) AR = ar @@ -22,10 +22,10 @@ endif all: c-library -c-library: libmojibake.a libmojibake.$(SHLIB_EXT) +c-library: libutf8proc.a libutf8proc.$(SHLIB_EXT) clean: - rm -f utf8proc.o libmojibake.a libmojibake.$(SHLIB_EXT) normtest graphemetest UnicodeData.txt DerivedCoreProperties.txt CompositionExclusions.txt CaseFolding.txt NormalizationTest.txt GraphemeBreakTest.txt + rm -f utf8proc.o libutf8proc.a libutf8proc.$(SHLIB_EXT) normtest graphemetest UnicodeData.txt DerivedCoreProperties.txt CompositionExclusions.txt CaseFolding.txt NormalizationTest.txt GraphemeBreakTest.txt $(MAKE) -C bench clean update: utf8proc_data.c.new @@ -51,18 +51,18 @@ CompositionExclusions.txt: CaseFolding.txt: $(CURL) -O http://www.unicode.org/Public/UNIDATA/CaseFolding.txt -utf8proc.o: mojibake.h utf8proc.c utf8proc_data.c +utf8proc.o: utf8proc.h utf8proc.c utf8proc_data.c $(cc) -c -o utf8proc.o utf8proc.c -libmojibake.a: utf8proc.o - rm -f libmojibake.a - $(AR) rs libmojibake.a utf8proc.o +libutf8proc.a: utf8proc.o + rm -f libutf8proc.a + $(AR) rs libutf8proc.a utf8proc.o -libmojibake.so: utf8proc.o - $(cc) -shared -o libmojibake.$(SHLIB_EXT) utf8proc.o - chmod a-x libmojibake.$(SHLIB_EXT) +libutf8proc.so: utf8proc.o + $(cc) -shared -o libutf8proc.$(SHLIB_EXT) utf8proc.o + chmod a-x libutf8proc.$(SHLIB_EXT) -libmojibake.dylib: utf8proc.o +libutf8proc.dylib: utf8proc.o $(cc) -dynamiclib -o $@ $^ -install_name $(libdir)/$@ @@ -74,13 +74,13 @@ NormalizationTest.txt: GraphemeBreakTest.txt: $(CURL) http://www.unicode.org/Public/UCD/latest/ucd/auxiliary/GraphemeBreakTest.txt | $(PERL) -pe 's,÷,/,g;s,×,+,g' > $@ -normtest: normtest.c utf8proc.o mojibake.h tests.h +normtest: normtest.c utf8proc.o utf8proc.h tests.h $(cc) normtest.c utf8proc.o -o $@ -graphemetest: graphemetest.c utf8proc.o mojibake.h tests.h +graphemetest: graphemetest.c utf8proc.o utf8proc.h tests.h $(cc) graphemetest.c utf8proc.o -o $@ -printproperty: printproperty.c utf8proc.o mojibake.h tests.h +printproperty: printproperty.c utf8proc.o utf8proc.h tests.h $(cc) printproperty.c utf8proc.o -o $@ check: normtest NormalizationTest.txt graphemetest GraphemeBreakTest.txt diff --git a/README.md b/README.md index 2bf3cd4..5db6da7 100644 --- a/README.md +++ b/README.md @@ -1,30 +1,27 @@ -# libmojibake -[![Build Status](https://travis-ci.org/JuliaLang/libmojibake.png)](https://travis-ci.org/JuliaLang/libmojibake) - -[libmojibake](https://github.com/JuliaLang/libmojibake) is a -development fork of the [utf8proc -library](http://www.public-software-group.org/utf8proc) from Jan +# utf8proc +[![Build Status](https://travis-ci.org/JuliaLang/utf8proc.png)](https://travis-ci.org/JuliaLang/utf8proc) + +[utf8proc](https://github.com/JuliaLang/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) from 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: 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). The -main difference from utf8proc is that the Unicode support in -libmojibake is more up-to-date (Unicode 7 vs. Unicode 5). - -The reason for this fork is that utf8proc is used for basic Unicode -support in the [Julia language](http://julialang.org/) and the Julia -developers wanted Unicode 7 support and other features, but the Public -Software Group is currently occupied with other projects. As we implement -and test new features in libmojibake, we are contributing patches back -to utf8proc with the hope that they can be merged upstream. +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 libmojibake in order to focus exclusively on the C -library for the time being. We will strive to keep API changes to a minimum, -so libmojibake should still be usable with the old plug-in code.) +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.) -Like utf8proc, the libmojibake package is licensed under the +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 @@ -38,8 +35,8 @@ For compilation of the C library run `make`. ## General Information ## The C library is found in this directory after successful compilation -and is named `libmojibake.a` (for the static library) and -`libmojibake.so` (for the dynamic library). +and is named `libutf8proc.a` (for the static library) and +`libutf8proc.so` (for the dynamic library). The Unicode version being supported is 7.0.0. @@ -58,10 +55,9 @@ strings, unless you want to allocate memory yourself. ## To Do ## -See the Github [issues list](https://github.com/JuliaLang/libmojibake/issues). +See the Github [issues list](https://github.com/JuliaLang/utf8proc/issues). ## Contact ## Bug reports, feature requests, and other queries can be filed at -the [libmojibake issues page on Github](https://github.com/JuliaLang/libmojibake/issues). - +the [utf8proc issues page on Github](https://github.com/JuliaLang/utf8proc/issues). diff --git a/mojibake.h b/mojibake.h deleted file mode 100644 index ce97d36..0000000 --- a/mojibake.h +++ /dev/null @@ -1,424 +0,0 @@ -/* - * 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. - */ - - -/* - * File name: mojibake.h (formerly utf8proc.h) - * - * Description: - * Header files for libmojibake, which is a mapping tool for UTF-8 strings - * with following features: - * - decomposing and composing of strings - * - replacing compatibility characters with their equivalents - * - stripping of "default ignorable characters" - * like SOFT-HYPHEN or ZERO-WIDTH-SPACE - * - folding of certain characters for string comparison - * (e.g. HYPHEN U+2010 and MINUS U+2212 to ASCII "-") - * (see "LUMP" option) - * - optional rejection of strings containing non-assigned code points - * - stripping of control characters - * - stripping of character marks (accents, etc.) - * - transformation of LF, CRLF, CR and NEL to line-feed (LF) - * or to the unicode chararacters for paragraph separation (PS) - * or line separation (LS). - * - unicode case folding (for case insensitive string comparisons) - * - rejection of illegal UTF-8 data - * (i.e. UTF-8 encoded UTF-16 surrogates) - * - support for korean hangul characters - * Unicode Version 7.0.0 is supported. - */ - - -#ifndef UTF8PROC_H -#define UTF8PROC_H - - -#include -#include -#ifdef _MSC_VER -typedef signed char int8_t; -typedef unsigned char uint8_t; -typedef short int16_t; -typedef unsigned short uint16_t; -typedef int int32_t; -# ifdef _WIN64 -# define ssize_t __int64 -# else -# define ssize_t int -# endif -# ifndef __cplusplus -typedef unsigned char bool; -enum {false, true}; -# endif -#else -# include -# include -#endif -#include - -#ifdef _WIN32 -# ifdef MOJIBAKE_EXPORTS -# define DLLEXPORT __declspec(dllexport) -# else -# define DLLEXPORT __declspec(dllimport) -# endif -#elif __GNUC__ >= 4 -# define DLLEXPORT __attribute__ ((visibility("default"))) -#else -# define DLLEXPORT -#endif - -#ifdef __cplusplus -extern "C" { -#endif - -#ifndef SSIZE_MAX -#define SSIZE_MAX ((size_t)SIZE_MAX/2) -#endif - -#define UTF8PROC_NULLTERM (1<<0) -#define UTF8PROC_STABLE (1<<1) -#define UTF8PROC_COMPAT (1<<2) -#define UTF8PROC_COMPOSE (1<<3) -#define UTF8PROC_DECOMPOSE (1<<4) -#define UTF8PROC_IGNORE (1<<5) -#define UTF8PROC_REJECTNA (1<<6) -#define UTF8PROC_NLF2LS (1<<7) -#define UTF8PROC_NLF2PS (1<<8) -#define UTF8PROC_NLF2LF (UTF8PROC_NLF2LS | UTF8PROC_NLF2PS) -#define UTF8PROC_STRIPCC (1<<9) -#define UTF8PROC_CASEFOLD (1<<10) -#define UTF8PROC_CHARBOUND (1<<11) -#define UTF8PROC_LUMP (1<<12) -#define UTF8PROC_STRIPMARK (1<<13) -/* - * Flags being regarded by several functions in the library: - * NULLTERM: The given UTF-8 input is NULL terminated. - * STABLE: Unicode Versioning Stability has to be respected. - * COMPAT: Compatibility decomposition - * (i.e. formatting information is lost) - * COMPOSE: Return a result with composed characters. - * DECOMPOSE: Return a result with decomposed characters. - * IGNORE: Strip "default ignorable characters" - * REJECTNA: Return an error, if the input contains unassigned - * code points. - * NLF2LS: Indicating that NLF-sequences (LF, CRLF, CR, NEL) are - * representing a line break, and should be converted to the - * unicode character for line separation (LS). - * NLF2PS: Indicating that NLF-sequences are representing a paragraph - * break, and should be converted to the unicode character for - * paragraph separation (PS). - * NLF2LF: Indicating that the meaning of NLF-sequences is unknown. - * STRIPCC: 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. - * CASEFOLD: Performs unicode case folding, to be able to do a - * case-insensitive string comparison. - * CHARBOUND: Inserts 0xFF bytes at the beginning of each sequence which - * is representing a single grapheme cluster (see UAX#29). - * LUMP: Lumps certain characters together - * (e.g. HYPHEN U+2010 and MINUS U+2212 to ASCII "-"). - * (See lump.txt for details.) - * If NLF2LF is set, this includes a transformation of - * paragraph and line separators to ASCII line-feed (LF). - * STRIPMARK: Strips all character markings - * (non-spacing, spacing and enclosing) (i.e. accents) - * NOTE: this option works only with COMPOSE or DECOMPOSE - */ - -#define UTF8PROC_ERROR_NOMEM -1 -#define UTF8PROC_ERROR_OVERFLOW -2 -#define UTF8PROC_ERROR_INVALIDUTF8 -3 -#define UTF8PROC_ERROR_NOTASSIGNED -4 -#define UTF8PROC_ERROR_INVALIDOPTS -5 -/* - * Error codes being returned by almost all functions: - * ERROR_NOMEM: Memory could not be allocated. - * ERROR_OVERFLOW: The given string is too long to be processed. - * ERROR_INVALIDUTF8: The given string is not a legal UTF-8 string. - * ERROR_NOTASSIGNED: The REJECTNA flag was set, - * and an unassigned code point was found. - * ERROR_INVALIDOPTS: Invalid options have been used. - */ - -typedef int16_t utf8proc_propval_t; -typedef struct utf8proc_property_struct { - utf8proc_propval_t category; - utf8proc_propval_t combining_class; - utf8proc_propval_t bidi_class; - utf8proc_propval_t decomp_type; - const int32_t *decomp_mapping; - const int32_t *casefold_mapping; - int32_t uppercase_mapping; - int32_t lowercase_mapping; - int32_t titlecase_mapping; - int32_t comb1st_index; - int32_t comb2nd_index; - unsigned bidi_mirrored:1; - unsigned comp_exclusion:1; - unsigned ignorable:1; - unsigned control_boundary:1; - unsigned boundclass:4; -} utf8proc_property_t; - -#define UTF8PROC_CATEGORY_CN 0 -#define UTF8PROC_CATEGORY_LU 1 -#define UTF8PROC_CATEGORY_LL 2 -#define UTF8PROC_CATEGORY_LT 3 -#define UTF8PROC_CATEGORY_LM 4 -#define UTF8PROC_CATEGORY_LO 5 -#define UTF8PROC_CATEGORY_MN 6 -#define UTF8PROC_CATEGORY_MC 7 -#define UTF8PROC_CATEGORY_ME 8 -#define UTF8PROC_CATEGORY_ND 9 -#define UTF8PROC_CATEGORY_NL 10 -#define UTF8PROC_CATEGORY_NO 11 -#define UTF8PROC_CATEGORY_PC 12 -#define UTF8PROC_CATEGORY_PD 13 -#define UTF8PROC_CATEGORY_PS 14 -#define UTF8PROC_CATEGORY_PE 15 -#define UTF8PROC_CATEGORY_PI 16 -#define UTF8PROC_CATEGORY_PF 17 -#define UTF8PROC_CATEGORY_PO 18 -#define UTF8PROC_CATEGORY_SM 19 -#define UTF8PROC_CATEGORY_SC 20 -#define UTF8PROC_CATEGORY_SK 21 -#define UTF8PROC_CATEGORY_SO 22 -#define UTF8PROC_CATEGORY_ZS 23 -#define UTF8PROC_CATEGORY_ZL 24 -#define UTF8PROC_CATEGORY_ZP 25 -#define UTF8PROC_CATEGORY_CC 26 -#define UTF8PROC_CATEGORY_CF 27 -#define UTF8PROC_CATEGORY_CS 28 -#define UTF8PROC_CATEGORY_CO 29 -#define UTF8PROC_BIDI_CLASS_L 1 -#define UTF8PROC_BIDI_CLASS_LRE 2 -#define UTF8PROC_BIDI_CLASS_LRO 3 -#define UTF8PROC_BIDI_CLASS_R 4 -#define UTF8PROC_BIDI_CLASS_AL 5 -#define UTF8PROC_BIDI_CLASS_RLE 6 -#define UTF8PROC_BIDI_CLASS_RLO 7 -#define UTF8PROC_BIDI_CLASS_PDF 8 -#define UTF8PROC_BIDI_CLASS_EN 9 -#define UTF8PROC_BIDI_CLASS_ES 10 -#define UTF8PROC_BIDI_CLASS_ET 11 -#define UTF8PROC_BIDI_CLASS_AN 12 -#define UTF8PROC_BIDI_CLASS_CS 13 -#define UTF8PROC_BIDI_CLASS_NSM 14 -#define UTF8PROC_BIDI_CLASS_BN 15 -#define UTF8PROC_BIDI_CLASS_B 16 -#define UTF8PROC_BIDI_CLASS_S 17 -#define UTF8PROC_BIDI_CLASS_WS 18 -#define UTF8PROC_BIDI_CLASS_ON 19 -#define UTF8PROC_BIDI_CLASS_LRI 20 /* new in Unicode 6.3 */ -#define UTF8PROC_BIDI_CLASS_RLI 21 /* new in Unicode 6.3 */ -#define UTF8PROC_BIDI_CLASS_FSI 22 /* new in Unicode 6.3 */ -#define UTF8PROC_BIDI_CLASS_PDI 23 /* new in Unicode 6.3 */ -#define UTF8PROC_DECOMP_TYPE_FONT 1 -#define UTF8PROC_DECOMP_TYPE_NOBREAK 2 -#define UTF8PROC_DECOMP_TYPE_INITIAL 3 -#define UTF8PROC_DECOMP_TYPE_MEDIAL 4 -#define UTF8PROC_DECOMP_TYPE_FINAL 5 -#define UTF8PROC_DECOMP_TYPE_ISOLATED 6 -#define UTF8PROC_DECOMP_TYPE_CIRCLE 7 -#define UTF8PROC_DECOMP_TYPE_SUPER 8 -#define UTF8PROC_DECOMP_TYPE_SUB 9 -#define UTF8PROC_DECOMP_TYPE_VERTICAL 10 -#define UTF8PROC_DECOMP_TYPE_WIDE 11 -#define UTF8PROC_DECOMP_TYPE_NARROW 12 -#define UTF8PROC_DECOMP_TYPE_SMALL 13 -#define UTF8PROC_DECOMP_TYPE_SQUARE 14 -#define UTF8PROC_DECOMP_TYPE_FRACTION 15 -#define UTF8PROC_DECOMP_TYPE_COMPAT 16 - -/* values for boundclass property: */ -#define UTF8PROC_BOUNDCLASS_START 0 -#define UTF8PROC_BOUNDCLASS_OTHER 1 -#define UTF8PROC_BOUNDCLASS_CR 2 -#define UTF8PROC_BOUNDCLASS_LF 3 -#define UTF8PROC_BOUNDCLASS_CONTROL 4 -#define UTF8PROC_BOUNDCLASS_EXTEND 5 -#define UTF8PROC_BOUNDCLASS_L 6 -#define UTF8PROC_BOUNDCLASS_V 7 -#define UTF8PROC_BOUNDCLASS_T 8 -#define UTF8PROC_BOUNDCLASS_LV 9 -#define UTF8PROC_BOUNDCLASS_LVT 10 -#define UTF8PROC_BOUNDCLASS_REGIONAL_INDICATOR 11 -#define UTF8PROC_BOUNDCLASS_SPACINGMARK 12 - -DLLEXPORT extern const int8_t utf8proc_utf8class[256]; - -DLLEXPORT const char *utf8proc_version(void); - -DLLEXPORT const char *utf8proc_errmsg(ssize_t errcode); -/* - * Returns a static error string for the given error code. - */ - -DLLEXPORT ssize_t utf8proc_iterate(const uint8_t *str, ssize_t strlen, int32_t *dst); -/* - * Reads a single char from the UTF-8 sequence being pointed to by 'str'. - * The maximum number of bytes read is 'strlen', unless 'strlen' is - * negative. - * If a valid unicode char could be read, it is stored in the variable - * being pointed to by 'dst', 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. - */ - -DLLEXPORT bool utf8proc_codepoint_valid(int32_t uc); -/* - * Returns 1, if the given unicode code-point is valid, otherwise 0. - */ - -DLLEXPORT ssize_t utf8proc_encode_char(int32_t uc, uint8_t *dst); -/* - * Encodes the unicode char with the code point 'uc' as an UTF-8 string in - * the byte array being pointed to by 'dst'. This array has to be at least - * 4 bytes long. - * In case of success the number of bytes written is returned, - * otherwise 0. - * This function does not check if 'uc' is a valid unicode code point. - */ - -DLLEXPORT const utf8proc_property_t *utf8proc_get_property(int32_t uc); -/* - * Returns a pointer to a (constant) struct containing information about - * the unicode char with the given code point 'uc'. - * If the character is not existent a pointer to a special struct is - * returned, where 'category' is 0 (UTF8PROC_CATEGORY_CN). - * WARNING: The parameter 'uc' has to be in the range of 0x0000 to - * 0x10FFFF, otherwise the program might crash! - */ - -DLLEXPORT ssize_t utf8proc_decompose_char( - int32_t uc, int32_t *dst, ssize_t bufsize, - int options, int *last_boundclass -); -/* - * Writes a decomposition of the unicode char 'uc' into the array being - * pointed to by 'dst'. - * Following flags in the 'options' field are regarded: - * REJECTNA: an unassigned unicode code point leads to an error - * IGNORE: "default ignorable" chars are stripped - * CASEFOLD: unicode casefolding is applied - * COMPAT: replace certain characters with their - * compatibility decomposition - * CHARBOUND: Inserts 0xFF bytes before each grapheme cluster - * LUMP: lumps certain different characters together - * STRIPMARK: removes all character marks - * The pointer 'last_boundclass' has to point to an integer variable which - * is storing the last character boundary class, if the CHARBOUND option - * is used. - * In case of success the number of chars written is returned, - * in case of an error, a negative error code is returned. - * If the number of written chars would be bigger than 'bufsize', - * the buffer (up to 'bufsize') has inpredictable data, and the needed - * buffer size is returned. - * WARNING: The parameter 'uc' has to be in the range of 0x0000 to - * 0x10FFFF, otherwise the program might crash! - */ - -DLLEXPORT ssize_t utf8proc_decompose( - const uint8_t *str, ssize_t strlen, - int32_t *buffer, ssize_t bufsize, int options -); -/* - * Does the same as 'utf8proc_decompose_char', but acts on a whole UTF-8 - * string, and orders the decomposed sequences correctly. - * If the NULLTERM flag in 'options' is set, processing will be stopped, - * when a NULL byte is encounted, otherwise 'strlen' bytes are processed. - * The result in form of unicode code points is written into the buffer - * being pointed to by 'buffer', having the length of 'bufsize' entries. - * In case of success the number of chars written is returned, - * in case of an error, a negative error code is returned. - * If the number of written chars would be bigger than 'bufsize', - * the buffer (up to 'bufsize') has inpredictable data, and the needed - * buffer size is returned. - */ - -DLLEXPORT ssize_t utf8proc_reencode(int32_t *buffer, ssize_t length, int options); -/* - * Reencodes the sequence of unicode characters given by the pointer - * 'buffer' and 'length' as UTF-8. - * The result is stored in the same memory area where the data is read. - * Following flags in the 'options' field are regarded: - * NLF2LS: converts LF, CRLF, CR and NEL into LS - * NLF2PS: converts LF, CRLF, CR and NEL into PS - * NLF2LF: converts LF, CRLF, CR and NEL into LF - * STRIPCC: strips or converts all non-affected control characters - * COMPOSE: tries to combine decomposed characters into composite - * characters - * STABLE: prohibits combining characters which would violate - * the unicode versioning stability - * In case of success the length of the resulting UTF-8 string is - * returned, otherwise a negative error code is returned. - * WARNING: The amount of free space being pointed to by 'buffer', has to - * 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 of 0x0000 to 0x10FFFF, otherwise the program might - * crash! - */ - -DLLEXPORT bool utf8proc_grapheme_break(int32_t c1, int32_t c2); -/* - * Given a pair of consecutive codepoints (c1,c2), return whether a grapheme break is - * permitted between them (as defined by the extended grapheme clusters in UAX#29). - */ - -DLLEXPORT ssize_t utf8proc_map( - const uint8_t *str, ssize_t strlen, uint8_t **dstptr, int options -); -/* - * Maps the given UTF-8 string being pointed to by 'str' to a new UTF-8 - * string, which is allocated dynamically, and afterwards pointed to by - * the pointer being pointed to by 'dstptr'. - * If the 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 - * before). Other flags in the 'options' field are passed to the functions - * defined above, and regarded as described. - * In case of success the length of the new string is returned, - * otherwise a negative error code is returned. - * NOTICE: The memory of the new UTF-8 string will have been allocated with - * 'malloc', and has theirfore to be freed with 'free'. - */ - -DLLEXPORT uint8_t *utf8proc_NFD(const uint8_t *str); -DLLEXPORT uint8_t *utf8proc_NFC(const uint8_t *str); -DLLEXPORT uint8_t *utf8proc_NFKD(const uint8_t *str); -DLLEXPORT uint8_t *utf8proc_NFKC(const uint8_t *str); -/* - * Returns a pointer to newly allocated memory of a NFD, NFC, NFKD or NFKC - * normalized version of the null-terminated string 'str'. - */ - -#ifdef __cplusplus -} -#endif - -#endif - diff --git a/tests.h b/tests.h index e3c1cf5..aee3a57 100644 --- a/tests.h +++ b/tests.h @@ -6,7 +6,7 @@ #include #include -#include "mojibake.h" +#include "utf8proc.h" size_t lineno = 0; diff --git a/utf8proc.c b/utf8proc.c index 15acecc..4035876 100644 --- a/utf8proc.c +++ b/utf8proc.c @@ -39,7 +39,7 @@ */ -#include "mojibake.h" +#include "utf8proc.h" #include "utf8proc_data.c" @@ -81,13 +81,11 @@ DLLEXPORT const int8_t utf8proc_utf8class[256] = { #define UTF8PROC_HANGUL_S_START 0xAC00 #define UTF8PROC_HANGUL_S_END 0xD7A4 -/* in libmojibake, we append "m" to whatever version of utf8proc - we have merged with most recently + whatever increment would - correspond to semantic versioning rules. Currently, we use 1.2m - since we started with utf8proc 1.1.6 and added features (Unicode 7 - support) in a backwards-compatible manner. */ +/* 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.): */ DLLEXPORT const char *utf8proc_version(void) { - return "1.2m"; + return "1.2-dev"; } DLLEXPORT const char *utf8proc_errmsg(ssize_t errcode) { diff --git a/utf8proc.h b/utf8proc.h new file mode 100644 index 0000000..06346c8 --- /dev/null +++ b/utf8proc.h @@ -0,0 +1,424 @@ +/* + * 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. + */ + + +/* + * File name: utf8proc.h + * + * Description: + * Header files for utf8proc, which is a mapping tool for UTF-8 strings + * with following features: + * - decomposing and composing of strings + * - replacing compatibility characters with their equivalents + * - stripping of "default ignorable characters" + * like SOFT-HYPHEN or ZERO-WIDTH-SPACE + * - folding of certain characters for string comparison + * (e.g. HYPHEN U+2010 and MINUS U+2212 to ASCII "-") + * (see "LUMP" option) + * - optional rejection of strings containing non-assigned code points + * - stripping of control characters + * - stripping of character marks (accents, etc.) + * - transformation of LF, CRLF, CR and NEL to line-feed (LF) + * or to the unicode chararacters for paragraph separation (PS) + * or line separation (LS). + * - unicode case folding (for case insensitive string comparisons) + * - rejection of illegal UTF-8 data + * (i.e. UTF-8 encoded UTF-16 surrogates) + * - support for korean hangul characters + * Unicode Version 7.0.0 is supported. + */ + + +#ifndef UTF8PROC_H +#define UTF8PROC_H + + +#include +#include +#ifdef _MSC_VER +typedef signed char int8_t; +typedef unsigned char uint8_t; +typedef short int16_t; +typedef unsigned short uint16_t; +typedef int int32_t; +# ifdef _WIN64 +# define ssize_t __int64 +# else +# define ssize_t int +# endif +# ifndef __cplusplus +typedef unsigned char bool; +enum {false, true}; +# endif +#else +# include +# include +#endif +#include + +#ifdef _WIN32 +# ifdef UTF8PROC_EXPORTS +# define DLLEXPORT __declspec(dllexport) +# else +# define DLLEXPORT __declspec(dllimport) +# endif +#elif __GNUC__ >= 4 +# define DLLEXPORT __attribute__ ((visibility("default"))) +#else +# define DLLEXPORT +#endif + +#ifdef __cplusplus +extern "C" { +#endif + +#ifndef SSIZE_MAX +#define SSIZE_MAX ((size_t)SIZE_MAX/2) +#endif + +#define UTF8PROC_NULLTERM (1<<0) +#define UTF8PROC_STABLE (1<<1) +#define UTF8PROC_COMPAT (1<<2) +#define UTF8PROC_COMPOSE (1<<3) +#define UTF8PROC_DECOMPOSE (1<<4) +#define UTF8PROC_IGNORE (1<<5) +#define UTF8PROC_REJECTNA (1<<6) +#define UTF8PROC_NLF2LS (1<<7) +#define UTF8PROC_NLF2PS (1<<8) +#define UTF8PROC_NLF2LF (UTF8PROC_NLF2LS | UTF8PROC_NLF2PS) +#define UTF8PROC_STRIPCC (1<<9) +#define UTF8PROC_CASEFOLD (1<<10) +#define UTF8PROC_CHARBOUND (1<<11) +#define UTF8PROC_LUMP (1<<12) +#define UTF8PROC_STRIPMARK (1<<13) +/* + * Flags being regarded by several functions in the library: + * NULLTERM: The given UTF-8 input is NULL terminated. + * STABLE: Unicode Versioning Stability has to be respected. + * COMPAT: Compatibility decomposition + * (i.e. formatting information is lost) + * COMPOSE: Return a result with composed characters. + * DECOMPOSE: Return a result with decomposed characters. + * IGNORE: Strip "default ignorable characters" + * REJECTNA: Return an error, if the input contains unassigned + * code points. + * NLF2LS: Indicating that NLF-sequences (LF, CRLF, CR, NEL) are + * representing a line break, and should be converted to the + * unicode character for line separation (LS). + * NLF2PS: Indicating that NLF-sequences are representing a paragraph + * break, and should be converted to the unicode character for + * paragraph separation (PS). + * NLF2LF: Indicating that the meaning of NLF-sequences is unknown. + * STRIPCC: 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. + * CASEFOLD: Performs unicode case folding, to be able to do a + * case-insensitive string comparison. + * CHARBOUND: Inserts 0xFF bytes at the beginning of each sequence which + * is representing a single grapheme cluster (see UAX#29). + * LUMP: Lumps certain characters together + * (e.g. HYPHEN U+2010 and MINUS U+2212 to ASCII "-"). + * (See lump.txt for details.) + * If NLF2LF is set, this includes a transformation of + * paragraph and line separators to ASCII line-feed (LF). + * STRIPMARK: Strips all character markings + * (non-spacing, spacing and enclosing) (i.e. accents) + * NOTE: this option works only with COMPOSE or DECOMPOSE + */ + +#define UTF8PROC_ERROR_NOMEM -1 +#define UTF8PROC_ERROR_OVERFLOW -2 +#define UTF8PROC_ERROR_INVALIDUTF8 -3 +#define UTF8PROC_ERROR_NOTASSIGNED -4 +#define UTF8PROC_ERROR_INVALIDOPTS -5 +/* + * Error codes being returned by almost all functions: + * ERROR_NOMEM: Memory could not be allocated. + * ERROR_OVERFLOW: The given string is too long to be processed. + * ERROR_INVALIDUTF8: The given string is not a legal UTF-8 string. + * ERROR_NOTASSIGNED: The REJECTNA flag was set, + * and an unassigned code point was found. + * ERROR_INVALIDOPTS: Invalid options have been used. + */ + +typedef int16_t utf8proc_propval_t; +typedef struct utf8proc_property_struct { + utf8proc_propval_t category; + utf8proc_propval_t combining_class; + utf8proc_propval_t bidi_class; + utf8proc_propval_t decomp_type; + const int32_t *decomp_mapping; + const int32_t *casefold_mapping; + int32_t uppercase_mapping; + int32_t lowercase_mapping; + int32_t titlecase_mapping; + int32_t comb1st_index; + int32_t comb2nd_index; + unsigned bidi_mirrored:1; + unsigned comp_exclusion:1; + unsigned ignorable:1; + unsigned control_boundary:1; + unsigned boundclass:4; +} utf8proc_property_t; + +#define UTF8PROC_CATEGORY_CN 0 +#define UTF8PROC_CATEGORY_LU 1 +#define UTF8PROC_CATEGORY_LL 2 +#define UTF8PROC_CATEGORY_LT 3 +#define UTF8PROC_CATEGORY_LM 4 +#define UTF8PROC_CATEGORY_LO 5 +#define UTF8PROC_CATEGORY_MN 6 +#define UTF8PROC_CATEGORY_MC 7 +#define UTF8PROC_CATEGORY_ME 8 +#define UTF8PROC_CATEGORY_ND 9 +#define UTF8PROC_CATEGORY_NL 10 +#define UTF8PROC_CATEGORY_NO 11 +#define UTF8PROC_CATEGORY_PC 12 +#define UTF8PROC_CATEGORY_PD 13 +#define UTF8PROC_CATEGORY_PS 14 +#define UTF8PROC_CATEGORY_PE 15 +#define UTF8PROC_CATEGORY_PI 16 +#define UTF8PROC_CATEGORY_PF 17 +#define UTF8PROC_CATEGORY_PO 18 +#define UTF8PROC_CATEGORY_SM 19 +#define UTF8PROC_CATEGORY_SC 20 +#define UTF8PROC_CATEGORY_SK 21 +#define UTF8PROC_CATEGORY_SO 22 +#define UTF8PROC_CATEGORY_ZS 23 +#define UTF8PROC_CATEGORY_ZL 24 +#define UTF8PROC_CATEGORY_ZP 25 +#define UTF8PROC_CATEGORY_CC 26 +#define UTF8PROC_CATEGORY_CF 27 +#define UTF8PROC_CATEGORY_CS 28 +#define UTF8PROC_CATEGORY_CO 29 +#define UTF8PROC_BIDI_CLASS_L 1 +#define UTF8PROC_BIDI_CLASS_LRE 2 +#define UTF8PROC_BIDI_CLASS_LRO 3 +#define UTF8PROC_BIDI_CLASS_R 4 +#define UTF8PROC_BIDI_CLASS_AL 5 +#define UTF8PROC_BIDI_CLASS_RLE 6 +#define UTF8PROC_BIDI_CLASS_RLO 7 +#define UTF8PROC_BIDI_CLASS_PDF 8 +#define UTF8PROC_BIDI_CLASS_EN 9 +#define UTF8PROC_BIDI_CLASS_ES 10 +#define UTF8PROC_BIDI_CLASS_ET 11 +#define UTF8PROC_BIDI_CLASS_AN 12 +#define UTF8PROC_BIDI_CLASS_CS 13 +#define UTF8PROC_BIDI_CLASS_NSM 14 +#define UTF8PROC_BIDI_CLASS_BN 15 +#define UTF8PROC_BIDI_CLASS_B 16 +#define UTF8PROC_BIDI_CLASS_S 17 +#define UTF8PROC_BIDI_CLASS_WS 18 +#define UTF8PROC_BIDI_CLASS_ON 19 +#define UTF8PROC_BIDI_CLASS_LRI 20 /* new in Unicode 6.3 */ +#define UTF8PROC_BIDI_CLASS_RLI 21 /* new in Unicode 6.3 */ +#define UTF8PROC_BIDI_CLASS_FSI 22 /* new in Unicode 6.3 */ +#define UTF8PROC_BIDI_CLASS_PDI 23 /* new in Unicode 6.3 */ +#define UTF8PROC_DECOMP_TYPE_FONT 1 +#define UTF8PROC_DECOMP_TYPE_NOBREAK 2 +#define UTF8PROC_DECOMP_TYPE_INITIAL 3 +#define UTF8PROC_DECOMP_TYPE_MEDIAL 4 +#define UTF8PROC_DECOMP_TYPE_FINAL 5 +#define UTF8PROC_DECOMP_TYPE_ISOLATED 6 +#define UTF8PROC_DECOMP_TYPE_CIRCLE 7 +#define UTF8PROC_DECOMP_TYPE_SUPER 8 +#define UTF8PROC_DECOMP_TYPE_SUB 9 +#define UTF8PROC_DECOMP_TYPE_VERTICAL 10 +#define UTF8PROC_DECOMP_TYPE_WIDE 11 +#define UTF8PROC_DECOMP_TYPE_NARROW 12 +#define UTF8PROC_DECOMP_TYPE_SMALL 13 +#define UTF8PROC_DECOMP_TYPE_SQUARE 14 +#define UTF8PROC_DECOMP_TYPE_FRACTION 15 +#define UTF8PROC_DECOMP_TYPE_COMPAT 16 + +/* values for boundclass property: */ +#define UTF8PROC_BOUNDCLASS_START 0 +#define UTF8PROC_BOUNDCLASS_OTHER 1 +#define UTF8PROC_BOUNDCLASS_CR 2 +#define UTF8PROC_BOUNDCLASS_LF 3 +#define UTF8PROC_BOUNDCLASS_CONTROL 4 +#define UTF8PROC_BOUNDCLASS_EXTEND 5 +#define UTF8PROC_BOUNDCLASS_L 6 +#define UTF8PROC_BOUNDCLASS_V 7 +#define UTF8PROC_BOUNDCLASS_T 8 +#define UTF8PROC_BOUNDCLASS_LV 9 +#define UTF8PROC_BOUNDCLASS_LVT 10 +#define UTF8PROC_BOUNDCLASS_REGIONAL_INDICATOR 11 +#define UTF8PROC_BOUNDCLASS_SPACINGMARK 12 + +DLLEXPORT extern const int8_t utf8proc_utf8class[256]; + +DLLEXPORT const char *utf8proc_version(void); + +DLLEXPORT const char *utf8proc_errmsg(ssize_t errcode); +/* + * Returns a static error string for the given error code. + */ + +DLLEXPORT ssize_t utf8proc_iterate(const uint8_t *str, ssize_t strlen, int32_t *dst); +/* + * Reads a single char from the UTF-8 sequence being pointed to by 'str'. + * The maximum number of bytes read is 'strlen', unless 'strlen' is + * negative. + * If a valid unicode char could be read, it is stored in the variable + * being pointed to by 'dst', 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. + */ + +DLLEXPORT bool utf8proc_codepoint_valid(int32_t uc); +/* + * Returns 1, if the given unicode code-point is valid, otherwise 0. + */ + +DLLEXPORT ssize_t utf8proc_encode_char(int32_t uc, uint8_t *dst); +/* + * Encodes the unicode char with the code point 'uc' as an UTF-8 string in + * the byte array being pointed to by 'dst'. This array has to be at least + * 4 bytes long. + * In case of success the number of bytes written is returned, + * otherwise 0. + * This function does not check if 'uc' is a valid unicode code point. + */ + +DLLEXPORT const utf8proc_property_t *utf8proc_get_property(int32_t uc); +/* + * Returns a pointer to a (constant) struct containing information about + * the unicode char with the given code point 'uc'. + * If the character is not existent a pointer to a special struct is + * returned, where 'category' is 0 (UTF8PROC_CATEGORY_CN). + * WARNING: The parameter 'uc' has to be in the range of 0x0000 to + * 0x10FFFF, otherwise the program might crash! + */ + +DLLEXPORT ssize_t utf8proc_decompose_char( + int32_t uc, int32_t *dst, ssize_t bufsize, + int options, int *last_boundclass +); +/* + * Writes a decomposition of the unicode char 'uc' into the array being + * pointed to by 'dst'. + * Following flags in the 'options' field are regarded: + * REJECTNA: an unassigned unicode code point leads to an error + * IGNORE: "default ignorable" chars are stripped + * CASEFOLD: unicode casefolding is applied + * COMPAT: replace certain characters with their + * compatibility decomposition + * CHARBOUND: Inserts 0xFF bytes before each grapheme cluster + * LUMP: lumps certain different characters together + * STRIPMARK: removes all character marks + * The pointer 'last_boundclass' has to point to an integer variable which + * is storing the last character boundary class, if the CHARBOUND option + * is used. + * In case of success the number of chars written is returned, + * in case of an error, a negative error code is returned. + * If the number of written chars would be bigger than 'bufsize', + * the buffer (up to 'bufsize') has inpredictable data, and the needed + * buffer size is returned. + * WARNING: The parameter 'uc' has to be in the range of 0x0000 to + * 0x10FFFF, otherwise the program might crash! + */ + +DLLEXPORT ssize_t utf8proc_decompose( + const uint8_t *str, ssize_t strlen, + int32_t *buffer, ssize_t bufsize, int options +); +/* + * Does the same as 'utf8proc_decompose_char', but acts on a whole UTF-8 + * string, and orders the decomposed sequences correctly. + * If the NULLTERM flag in 'options' is set, processing will be stopped, + * when a NULL byte is encounted, otherwise 'strlen' bytes are processed. + * The result in form of unicode code points is written into the buffer + * being pointed to by 'buffer', having the length of 'bufsize' entries. + * In case of success the number of chars written is returned, + * in case of an error, a negative error code is returned. + * If the number of written chars would be bigger than 'bufsize', + * the buffer (up to 'bufsize') has inpredictable data, and the needed + * buffer size is returned. + */ + +DLLEXPORT ssize_t utf8proc_reencode(int32_t *buffer, ssize_t length, int options); +/* + * Reencodes the sequence of unicode characters given by the pointer + * 'buffer' and 'length' as UTF-8. + * The result is stored in the same memory area where the data is read. + * Following flags in the 'options' field are regarded: + * NLF2LS: converts LF, CRLF, CR and NEL into LS + * NLF2PS: converts LF, CRLF, CR and NEL into PS + * NLF2LF: converts LF, CRLF, CR and NEL into LF + * STRIPCC: strips or converts all non-affected control characters + * COMPOSE: tries to combine decomposed characters into composite + * characters + * STABLE: prohibits combining characters which would violate + * the unicode versioning stability + * In case of success the length of the resulting UTF-8 string is + * returned, otherwise a negative error code is returned. + * WARNING: The amount of free space being pointed to by 'buffer', has to + * 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 of 0x0000 to 0x10FFFF, otherwise the program might + * crash! + */ + +DLLEXPORT bool utf8proc_grapheme_break(int32_t c1, int32_t c2); +/* + * Given a pair of consecutive codepoints (c1,c2), return whether a grapheme break is + * permitted between them (as defined by the extended grapheme clusters in UAX#29). + */ + +DLLEXPORT ssize_t utf8proc_map( + const uint8_t *str, ssize_t strlen, uint8_t **dstptr, int options +); +/* + * Maps the given UTF-8 string being pointed to by 'str' to a new UTF-8 + * string, which is allocated dynamically, and afterwards pointed to by + * the pointer being pointed to by 'dstptr'. + * If the 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 + * before). Other flags in the 'options' field are passed to the functions + * defined above, and regarded as described. + * In case of success the length of the new string is returned, + * otherwise a negative error code is returned. + * NOTICE: The memory of the new UTF-8 string will have been allocated with + * 'malloc', and has theirfore to be freed with 'free'. + */ + +DLLEXPORT uint8_t *utf8proc_NFD(const uint8_t *str); +DLLEXPORT uint8_t *utf8proc_NFC(const uint8_t *str); +DLLEXPORT uint8_t *utf8proc_NFKD(const uint8_t *str); +DLLEXPORT uint8_t *utf8proc_NFKC(const uint8_t *str); +/* + * Returns a pointer to newly allocated memory of a NFD, NFC, NFKD or NFKC + * normalized version of the null-terminated string 'str'. + */ + +#ifdef __cplusplus +} +#endif + +#endif + -- cgit v1.2.3