utf8proc: 61a89ecc2fb9 utf8proc.h

utf8proc

view utf8proc.h @ 1:61a89ecc2fb9

Version 0.2

- changed behaviour of PostgreSQL function to return NULL in case of invalid input, rather than raising an exceptional condition
- improved efficiency of PostgreSQL function (no transformation to C string is done)
- added -fpic compiler flag in Makefile
- fixed bug in the C code for the ruby library (usage of non-existent function)

author	jbe
date	Tue Jun 20 12:00:00 2006 +0200 (2006-06-20)
parents	a0368662434c
children	aaad485d5335

line source

2 * Copyright (c) 2006, FlexiGuided GmbH, Berlin, Germany

3 * Author: Jan Behrens <jan.behrens@flexiguided.de>

4 * All rights reserved.

6 * Redistribution and use in source and binary forms, with or without

7 * modification, are permitted provided that the following conditions are

8 * met:

10 * 1. Redistributions of source code must retain the above copyright

11 * notice, this list of conditions and the following disclaimer.

12 * 2. Redistributions in binary form must reproduce the above copyright

13 * notice, this list of conditions and the following disclaimer in the

14 * documentation and/or other materials provided with the distribution.

15 * 3. Neither the name of the FlexiGuided GmbH nor the names of its

16 * contributors may be used to endorse or promote products derived from

17 * this software without specific prior written permission.

19 * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS

20 * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT

21 * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A

22 * PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER

23 * OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,

24 * EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,

25 * PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR

26 * PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF

27 * LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING

28 * NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS

29 * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.

32 * This library contains derived data from a modified version of the

33 * Unicode data files.

35 * The original data files are available at

36 * http://www.unicode.org/Public/UNIDATA/

38 * Please notice the copyright statement in the file "utf8proc_data.c".

44 * File name: utf8proc.h

45 * Version: 0.2

46 * Last changed: 2006-05-31

48 * Description:

49 * Header files for libutf8proc, which is a mapping tool for UTF-8 strings

50 * with following features:

51 * - decomposing and composing of strings

52 * - replacing compatibility characters with their equivalents

53 * - stripping of "default ignorable characters"

54 * like SOFT-HYPHEN or ZERO-WIDTH-SPACE

55 * - optional rejection of strings containing non-assigned code points

56 * - stripping of control characters

57 * - transformation of LF, CRLF, CR and NEL to line-feed (LF)

58 * or to the unicode chararacters for paragraph separation (PS)

59 * or line separation (LS).

60 * - unicode case folding (for case insensitive string comparisons)

61 * - rejection of illegal UTF-8 data (i.e. UTF-8 encoded UTF-16 surrogates)

62 * - support for korean hangul characters

63 * Unicode Version 4.1.0 is supported.

67 #ifndef UTF8PROC_H

68 #define UTF8PROC_H

71 #include <stdlib.h>

72 #include <stdbool.h>

73 #include <sys/types.h>

74 #include <inttypes.h>

75 #include <limits.h>

77 #ifndef SSIZE_MAX

78 #define SSIZE_MAX (SIZE_MAX/2)

79 #endif

81 #define UTF8PROC_NULLTERM (1<<0)

82 #define UTF8PROC_STABLE (1<<1)

83 #define UTF8PROC_COMPAT (1<<2)

84 #define UTF8PROC_COMPOSE (1<<3)

85 #define UTF8PROC_IGNORE (1<<4)

86 #define UTF8PROC_REJECTNA (1<<5)

87 #define UTF8PROC_NLF2LS (1<<6)

88 #define UTF8PROC_NLF2PS (1<<7)

89 #define UTF8PROC_NLF2LF (UTF8PROC_NLF2LS | UTF8PROC_NLF2PS)

90 #define UTF8PROC_STRIPCC (1<<8)

91 #define UTF8PROC_CASEFOLD (1<<9)

93 * Flags being regarded by several functions in the library:

94 * NULLTERM: The given UTF-8 input is NULL terminated.

95 * STABLE: Unicode Versioning Stability has to be respected.

96 * COMPAT: Compatiblity decomposition (i.e. formatting information is lost)

97 * COMPOSE: Return a result with composed characters, instead of decomposed.

98 * IGNORE: Strip "default ignorable characters"

99 * REJECTNA: Return an error, if the input contains unassigned code points.

100 * NLF2LS: Indicating that NLF-sequences (LF, CRLF, CR, NEL) are

101 * representing a line break, and should be converted to the

102 * unicode character for line separation (LS).

103 * NLF2PS: Indicating that NLF-sequences are representing a paragraph

104 * break, and should be converted to the unicode character for

105 * paragraph separation (PS).

106 * NLF2LF: Indicating that the meaning of NLF-sequences is unknown.

107 * STRIPCC: Strips and/or convers control characters.

108 * NLF-sequences are transformed into space, except if one of the

109 * NLF2LS/PS/LF options is given.

110 * HorizontalTab (HT) and FormFeed (FF) are treated as a

111 * NLF-sequence in this case.

112 * All other control characters are simply removed.

113 * CASEFOLD: Performs unicode case folding, to be able to do a

114 * case-insensitive string comparison.

117 #define UTF8PROC_ERROR_NOMEM -1

118 #define UTF8PROC_ERROR_OVERFLOW -2

119 #define UTF8PROC_ERROR_INVALIDUTF8 -3

120 #define UTF8PROC_ERROR_NOTASSIGNED -4

122 * Error codes being returned by almost all functions:

123 * ERROR_NOMEM: Memory could not be allocated.

124 * ERROR_OVERFLOW: The given string is too long to be processed.

125 * ERROR_INVALIDUTF8: The given string is not a legal UTF-8 string.

126 * ERROR_NOTASSIGNED: The REJECTNA flag was set,

127 * and an unassigned code point was found.

130 typedef struct utf8proc_property_struct {

131 const char *category;

132 const int16_t combining_class;

133 const char *bidi_class;

134 const char *decomp_type;

135 const int32_t *decomp_mapping;

136 const unsigned bidi_mirrored:1;

137 const int32_t uppercase_mapping;

138 const int32_t lowercase_mapping;

139 const int32_t titlecase_mapping;

140 const int32_t comb1st_index;

141 const int32_t comb2nd_index;

142 const unsigned comp_exclusion:1;

143 const unsigned ignorable:1;

144 const int32_t *casefold_mapping;

145 } utf8proc_property_t;

147 extern const int8_t utf8proc_utf8class[256];

149 const char *utf8proc_errmsg(ssize_t errcode);

151 * Returns a static error string for the given error code.

154 ssize_t utf8proc_iterate(uint8_t *str, ssize_t strlen, int32_t *dst);

156 * Reads a single char from the UTF-8 sequence being pointed to by 'str'.

157 * The maximum number of bytes read is 'strlen', unless 'strlen' is

158 * negative.

159 * If a valid unicode char could be read, it is stored in the variable

160 * being pointed to by 'dst', otherwise that variable will be set to -1.

161 * In case of success the number of bytes read is returned, otherwise a

162 * negative error code is returned.

165 ssize_t utf8proc_encode_char(int32_t uc, uint8_t *dst);

167 * Encodes the unicode char with the code point 'uc' as an UTF-8 string in

168 * the byte array being pointed to by 'dst'. This array has to be at least

169 * 4 bytes long.

170 * In case of success the number of bytes written is returned, otherwise 0.

171 * This function does not check if 'uc' is a valid unicode code point.

174 const utf8proc_property_t *utf8proc_get_property(int32_t uc);

176 * Returns a pointer to a (constant) struct containing information about

177 * the unicode char with the given code point 'uc'.

178 * If the character is not existent a pointer to a special struct is

179 * returned, where 'category' is a NULL pointer.

180 * WARNING: The parameter 'uc' has to be in the range of 0x0000 to

181 * 0x10FFFF, otherwise the program might crash!

184 ssize_t utf8proc_decompose_char(int32_t uc, int32_t *dst, ssize_t bufsize,

185 int options);

187 * Writes a decomposition of the unicode char 'uc' into the array being

188 * pointed to by 'dst'.

189 * Following flags in the 'options' field are regarded:

190 * REJECTNA: an unassigned unicode code point leads to an error

191 * IGNORE: "default ignorable" chars are stripped

192 * CASEFOLD: unicode casefolding is applied

193 * COMPAT: replace certain characters with their

194 * compatibility decomposition

195 * In case of success the number of chars written is returned,

196 * in case of an error, a negative error code is returned.

197 * If the number of written chars would be bigger than 'bufsize',

198 * the buffer (up to 'bufsize') has inpredictable data, and the needed

199 * buffer size is returned.

200 * WARNING: The parameter 'uc' has to be in the range of 0x0000 to

201 * 0x10FFFF, otherwise the program might crash!

204 ssize_t utf8proc_decompose(uint8_t *str, ssize_t strlen,

205 int32_t *buffer, ssize_t bufsize, int options);

207 * Does the same as 'utf8proc_decompose_char', but acts on a whole UTF-8

208 * string, and orders the decomposed sequences correctly.

209 * If the NULLTERM flag in 'options' is set, processing will be stopped,

210 * when a NULL byte is encounted, otherwise 'strlen' bytes are processed.

211 * The result in form of unicode code points is written into the buffer

212 * being pointed to by 'buffer', having the length of 'bufsize' entries.

213 * In case of success the number of chars written is returned,

214 * in case of an error, a negative error code is returned.

215 * If the number of written chars would be bigger than 'bufsize',

216 * the buffer (up to 'bufsize') has inpredictable data, and the needed

217 * buffer size is returned.

220 ssize_t utf8proc_reencode(int32_t *buffer, ssize_t length, int options);

222 * Reencodes the sequence of unicode characters given by the pointer

223 * 'buffer' and 'length' as UTF-8.

224 * The result is stored in the same memory area where the data is read.

225 * Following flags in the 'options' field are regarded:

226 * NLF2LS: converts LF, CRLF, CR and NEL into LS

227 * NLF2PS: converts LF, CRLF, CR and NEL into PS

228 * NLF2LF: converts LF, CRLF, CR and NEL into LF

229 * STRIPCC: strips or converts all non-affected control characters

230 * COMPOSE: tries to combine decomposed characters into composite characters

231 * STABLE: prohibits combining characters which would violate

232 * the unicode versioning stability

233 * In case of success the length of the resulting UTF-8 string is returned,

234 * otherwise a negative error code is returned.

235 * WARNING: The amount of free space being pointed to by 'buffer', has to

236 * exceed the amount of the input data by one byte, and the

237 * entries of the array pointed to by 'str' have to be in the

238 * range of 0x0000 to 0x10FFFF, otherwise the program might crash!

241 ssize_t utf8proc_map(uint8_t *str, ssize_t strlen, uint8_t **dstptr,

242 int options);

244 * Maps the given UTF-8 string being pointed to by 'str' to a new UTF-8

245 * string, which is allocated dynamically, and afterwards pointed to by the

246 * pointer being pointed to by 'dstptr'.

247 * If the NULLTERM flag in the 'options' field is set, the length is

248 * determined by a NULL terminator, otherwise the parameter 'strlen' is

249 * evaluated to determine the string length, but in any case the result

250 * will be NULL terminated (though it might contain NULL characters before).

251 * Other flags in the 'options' field are passed to the functions defined

252 * above, and regarded as described.

253 * In case of success the length of the new string is returned,

254 * otherwise a negative error code is returned.

255 * NOTICE: The memory of the new UTF-8 string will have been allocated with

256 * 'malloc', and has theirfore to be freed with 'free'.

259 uint8_t *utf8proc_NFD(uint8_t *str);

260 uint8_t *utf8proc_NFC(uint8_t *str);

261 uint8_t *utf8proc_NFKD(uint8_t *str);

262 uint8_t *utf8proc_NFKC(uint8_t *str);

264 * Returns a pointer to newly allocated memory of a NFD, NFC, NFKD or NFKC

265 * normalized version of the null-terminated string 'str'.

269 #endif

Impressum / About Us