| rev |
line source |
|
yuuji@0
|
1 /* ========================================================================
|
|
yuuji@0
|
2 * Copyright 1988-2008 University of Washington
|
|
yuuji@0
|
3 *
|
|
yuuji@0
|
4 * Licensed under the Apache License, Version 2.0 (the "License");
|
|
yuuji@0
|
5 * you may not use this file except in compliance with the License.
|
|
yuuji@0
|
6 * You may obtain a copy of the License at
|
|
yuuji@0
|
7 *
|
|
yuuji@0
|
8 * http://www.apache.org/licenses/LICENSE-2.0
|
|
yuuji@0
|
9 *
|
|
yuuji@0
|
10 *
|
|
yuuji@0
|
11 * ========================================================================
|
|
yuuji@0
|
12 */
|
|
yuuji@0
|
13
|
|
yuuji@0
|
14 /*
|
|
yuuji@0
|
15 * Program: UTF-8 routines
|
|
yuuji@0
|
16 *
|
|
yuuji@0
|
17 * Author: Mark Crispin
|
|
yuuji@0
|
18 * Networks and Distributed Computing
|
|
yuuji@0
|
19 * Computing & Communications
|
|
yuuji@0
|
20 * University of Washington
|
|
yuuji@0
|
21 * Administration Building, AG-44
|
|
yuuji@0
|
22 * Seattle, WA 98195
|
|
yuuji@0
|
23 * Internet: MRC@CAC.Washington.EDU
|
|
yuuji@0
|
24 *
|
|
yuuji@0
|
25 * Date: 11 June 1997
|
|
yuuji@0
|
26 * Last Edited: 17 January 2008
|
|
yuuji@0
|
27 */
|
|
yuuji@0
|
28
|
|
yuuji@0
|
29 /* UTF-8 size and conversion routines from UCS-2 values (thus in the BMP).
|
|
yuuji@0
|
30 * Don't use these if UTF-16 data (surrogate pairs) are an issue.
|
|
yuuji@0
|
31 * For UCS-4 values, use the utf8_size() and utf8_put() functions.
|
|
yuuji@0
|
32 */
|
|
yuuji@0
|
33
|
|
yuuji@0
|
34 #define UTF8_SIZE_BMP(c) ((c & 0xff80) ? ((c & 0xf800) ? 3 : 2) : 1)
|
|
yuuji@0
|
35
|
|
yuuji@0
|
36 #define UTF8_PUT_BMP(b,c) { \
|
|
yuuji@0
|
37 if (c & 0xff80) { /* non-ASCII? */ \
|
|
yuuji@0
|
38 if (c & 0xf800) { /* three byte code */ \
|
|
yuuji@0
|
39 *b++ = 0xe0 | (c >> 12); \
|
|
yuuji@0
|
40 *b++ = 0x80 | ((c >> 6) & 0x3f); \
|
|
yuuji@0
|
41 } \
|
|
yuuji@0
|
42 else *b++ = 0xc0 | ((c >> 6) & 0x3f); \
|
|
yuuji@0
|
43 *b++ = 0x80 | (c & 0x3f); \
|
|
yuuji@0
|
44 } \
|
|
yuuji@0
|
45 else *b++ = c; \
|
|
yuuji@0
|
46 }
|
|
yuuji@0
|
47
|
|
yuuji@0
|
48 /* utf8_text() flag values */
|
|
yuuji@0
|
49
|
|
yuuji@0
|
50 #define U8T_CASECANON 2 /* canonicalize case */
|
|
yuuji@0
|
51 #define U8T_DECOMPOSE 4 /* decompose */
|
|
yuuji@0
|
52 /* full canonicalization */
|
|
yuuji@0
|
53 #define U8T_CANONICAL (U8T_CASECANON | U8T_DECOMPOSE)
|
|
yuuji@0
|
54
|
|
yuuji@0
|
55
|
|
yuuji@0
|
56 /* utf8_get() return values */
|
|
yuuji@0
|
57
|
|
yuuji@0
|
58 /* 0x0000 - 0xffff BMP plane */
|
|
yuuji@0
|
59 #define U8GM_NONBMP 0xffff0000 /* mask for non-BMP values */
|
|
yuuji@0
|
60 /* 0x10000 - 0x10ffff extended planes */
|
|
yuuji@0
|
61 /* 0x110000 - 0x7ffffff non-Unicode */
|
|
yuuji@0
|
62 #define U8G_ERROR 0x80000000 /* error flag */
|
|
yuuji@0
|
63 #define U8G_BADCONT U8G_ERROR+1 /* continuation when not in progress */
|
|
yuuji@0
|
64 #define U8G_INCMPLT U8G_ERROR+2 /* incomplete UTF-8 character */
|
|
yuuji@0
|
65 #define U8G_NOTUTF8 U8G_ERROR+3 /* not a valid UTF-8 octet */
|
|
yuuji@0
|
66 #define U8G_ENDSTRG U8G_ERROR+4 /* end of string */
|
|
yuuji@0
|
67 #define U8G_ENDSTRI U8G_ERROR+5 /* end of string w/ incomplete UTF-8 char */
|
|
yuuji@0
|
68 #define U8G_SURROGA U8G_ERROR+6 /* surrogate codepoint */
|
|
yuuji@0
|
69 #define U8G_NOTUNIC U8G_ERROR+7 /* non-Unicode codepoint */
|
|
yuuji@0
|
70
|
|
yuuji@0
|
71
|
|
yuuji@0
|
72 /* ucs4_width() return values */
|
|
yuuji@0
|
73
|
|
yuuji@0
|
74 #define U4W_ERROR 0x80000000 /* error flags */
|
|
yuuji@0
|
75 #define U4W_NOTUNCD U4W_ERROR+1 /* not a Unicode char */
|
|
yuuji@0
|
76 #define U4W_PRIVATE U4W_ERROR+2 /* private-space plane */
|
|
yuuji@0
|
77 #define U4W_SSPCHAR U4W_ERROR+3 /* Supplementary Special-purpose Plane */
|
|
yuuji@0
|
78 #define U4W_UNASSGN U4W_ERROR+4 /* unassigned space plane */
|
|
yuuji@0
|
79 #define U4W_CONTROL U4W_ERROR+5 /* C0/C1 control */
|
|
yuuji@0
|
80 #define U4W_CTLSRGT U4W_CONTROL /* in case legacy code references this */
|
|
yuuji@0
|
81
|
|
yuuji@0
|
82 /* ISO-2022 engine states */
|
|
yuuji@0
|
83
|
|
yuuji@0
|
84 #define I2S_CHAR 0 /* character */
|
|
yuuji@0
|
85 #define I2S_ESC 1 /* previous character was ESC */
|
|
yuuji@0
|
86 #define I2S_MUL 2 /* previous character was multi-byte code */
|
|
yuuji@0
|
87 #define I2S_INT 3 /* previous character was intermediate */
|
|
yuuji@0
|
88
|
|
yuuji@0
|
89
|
|
yuuji@0
|
90 /* ISO-2022 Gn selections */
|
|
yuuji@0
|
91
|
|
yuuji@0
|
92 #define I2C_G0 0 /* G0 */
|
|
yuuji@0
|
93 #define I2C_G1 1 /* G1 */
|
|
yuuji@0
|
94 #define I2C_G2 2 /* G2 */
|
|
yuuji@0
|
95 #define I2C_G3 3 /* G3 */
|
|
yuuji@0
|
96 #define I2C_SG2 (2 << 2) /* single shift G2 */
|
|
yuuji@0
|
97 #define I2C_SG3 (3 << 2) /* single shift G2 */
|
|
yuuji@0
|
98
|
|
yuuji@0
|
99
|
|
yuuji@0
|
100 /* ISO-2022 octet definitions */
|
|
yuuji@0
|
101
|
|
yuuji@0
|
102 #define I2C_ESC 0x1b /* ESCape */
|
|
yuuji@0
|
103
|
|
yuuji@0
|
104 /* Intermediate character */
|
|
yuuji@0
|
105 #define I2C_STRUCTURE 0x20 /* announce code structure */
|
|
yuuji@0
|
106 #define I2C_C0 0x21 /* C0 */
|
|
yuuji@0
|
107 #define I2C_C1 0x22 /* C1 */
|
|
yuuji@0
|
108 #define I2C_CONTROL 0x23 /* single control function */
|
|
yuuji@0
|
109 #define I2C_MULTI 0x24 /* multi-byte character set */
|
|
yuuji@0
|
110 #define I2C_OTHER 0x25 /* other coding system */
|
|
yuuji@0
|
111 #define I2C_REVISED 0x26 /* revised registration */
|
|
yuuji@0
|
112 #define I2C_G0_94 0x28 /* G0 94-character set */
|
|
yuuji@0
|
113 #define I2C_G1_94 0x29 /* G1 94-character set */
|
|
yuuji@0
|
114 #define I2C_G2_94 0x2A /* G2 94-character set */
|
|
yuuji@0
|
115 #define I2C_G3_94 0x2B /* G3 94-character set */
|
|
yuuji@0
|
116 #define I2C_G0_96 0x2C /* (not in ISO-2022) G0 96-character set */
|
|
yuuji@0
|
117 #define I2C_G1_96 0x2D /* G1 96-character set */
|
|
yuuji@0
|
118 #define I2C_G2_96 0x2E /* G2 96-character set */
|
|
yuuji@0
|
119 #define I2C_G3_96 0x2F /* G3 96-character set */
|
|
yuuji@0
|
120
|
|
yuuji@0
|
121 /* Locking shifts */
|
|
yuuji@0
|
122 #define I2C_SI 0x0f /* lock shift to G0 (Shift In) */
|
|
yuuji@0
|
123 #define I2C_SO 0x0e /* lock shift to G1 (Shift Out) */
|
|
yuuji@0
|
124 /* prefixed by ESC */
|
|
yuuji@0
|
125 #define I2C_LS2 0x6e /* lock shift to G2 */
|
|
yuuji@0
|
126 #define I2C_LS3 0x6f /* lock shift to G3 */
|
|
yuuji@0
|
127 #define I2C_LS1R 0x7e /* lock shift GR to G1 */
|
|
yuuji@0
|
128 #define I2C_LS2R 0x7d /* lock shift GR to G2 */
|
|
yuuji@0
|
129 #define I2C_LS3R 0x7c /* lock shift GR to G3 */
|
|
yuuji@0
|
130
|
|
yuuji@0
|
131 /* Single shifts */
|
|
yuuji@0
|
132 #define I2C_SS2_ALT 0x8e /* single shift to G2 (SS2) */
|
|
yuuji@0
|
133 #define I2C_SS3_ALT 0x8f /* single shift to G3 (SS3) */
|
|
yuuji@0
|
134 #define I2C_SS2_ALT_7 0x19 /* single shift to G2 (SS2) */
|
|
yuuji@0
|
135 #define I2C_SS3_ALT_7 0x1d /* single shift to G3 (SS3) */
|
|
yuuji@0
|
136 /* prefixed by ESC */
|
|
yuuji@0
|
137 #define I2C_SS2 0x4e /* single shift to G2 (SS2) */
|
|
yuuji@0
|
138 #define I2C_SS3 0x4f /* single shift to G3 (SS3) */
|
|
yuuji@0
|
139
|
|
yuuji@0
|
140 /* 94 character sets */
|
|
yuuji@0
|
141
|
|
yuuji@0
|
142 /* 4/0 ISO 646 IRV */
|
|
yuuji@0
|
143 #define I2CS_94_BRITISH 0x41 /* 4/1 ISO 646 British */
|
|
yuuji@0
|
144 #define I2CS_94_ASCII 0x42 /* 4/2 ISO 646 USA (ASCII) */
|
|
yuuji@0
|
145 /* 4/3 NATS Finland/Sweden (primary) */
|
|
yuuji@0
|
146 /* 4/4 NATS Finland/Sweden (secondary) */
|
|
yuuji@0
|
147 /* 4/5 NATS Denmark/Norway (primary) */
|
|
yuuji@0
|
148 /* 4/6 NATS Denmark/Norway (secondary) */
|
|
yuuji@0
|
149 /* 4/7 ISO 646 Swedish SEN 850200 */
|
|
yuuji@0
|
150 /* 4/8 ISO 646 Swedish names */
|
|
yuuji@0
|
151 #define I2CS_94_JIS_BUGROM 0x48 /* 4/8 some buggy software does this */
|
|
yuuji@0
|
152 #define I2CS_94_JIS_KANA 0x49 /* 4/9 JIS X 0201-1976 right half */
|
|
yuuji@0
|
153 #define I2CS_94_JIS_ROMAN 0x4a /* 4/a JIS X 0201-1976 left half */
|
|
yuuji@0
|
154 /* 4/b ISO 646 German */
|
|
yuuji@0
|
155 /* 4/c ISO 646 Portuguese (Olivetti) */
|
|
yuuji@0
|
156 /* 4/d ISO 6438 African */
|
|
yuuji@0
|
157 /* 4/e ISO 5427 Cyrillic (Honeywell-Bull) */
|
|
yuuji@0
|
158 /* 4/f DIN 31624 extended bibliography */
|
|
yuuji@0
|
159 /* 5/0 ISO 5426-1980 Bibliography */
|
|
yuuji@0
|
160 /* 5/1 ISO 5427-1981 Cyrillic*/
|
|
yuuji@0
|
161 /* 5/2 ISO 646 French (withdrawn) */
|
|
yuuji@0
|
162 /* 5/3 ISO 5428-1980 Greek bibliography */
|
|
yuuji@0
|
163 /* 5/4 GB 1988-80 Chinese */
|
|
yuuji@0
|
164 /* 5/5 Latin-Greek (Honeywell-Bull) */
|
|
yuuji@0
|
165 /* 5/6 UK Viewdata/Teletext */
|
|
yuuji@0
|
166 /* 5/7 INIS (IRV subset) */
|
|
yuuji@0
|
167 /* 5/8 ISO 5428 Greek Bibliography */
|
|
yuuji@0
|
168 /* 5/9 ISO 646 Italian (Olivetti) */
|
|
yuuji@0
|
169 /* 5/a ISO 646 Spanish (Olivetti) */
|
|
yuuji@0
|
170 /* 5/b Greek (Olivetti) */
|
|
yuuji@0
|
171 /* 5/c Latin-Greek (Olivetti) */
|
|
yuuji@0
|
172 /* 5/d INIS non-standard extension */
|
|
yuuji@0
|
173 /* 5/e INIS Cyrillic extension */
|
|
yuuji@0
|
174 /* 5/f Arabic CODAR-U IERA */
|
|
yuuji@0
|
175 /* 6/0 ISO 646 Norwegian */
|
|
yuuji@0
|
176 /* 6/1 Norwegian version 2 (withdrawn) */
|
|
yuuji@0
|
177 /* 6/2 Videotex supplementary */
|
|
yuuji@0
|
178 /* 6/3 Videotex supplementary #2 */
|
|
yuuji@0
|
179 /* 6/4 Videotex supplementary #3 */
|
|
yuuji@0
|
180 /* 6/5 APL */
|
|
yuuji@0
|
181 /* 6/6 ISO 646 French */
|
|
yuuji@0
|
182 /* 6/7 ISO 646 Portuguese (IBM) */
|
|
yuuji@0
|
183 /* 6/8 ISO 646 Spanish (IBM) */
|
|
yuuji@0
|
184 /* 6/9 ISO 646 Hungarian */
|
|
yuuji@0
|
185 /* 6/a Greek ELOT (withdrawn) */
|
|
yuuji@0
|
186 /* 6/b ISO 9036 Arabic 7-bit */
|
|
yuuji@0
|
187 /* 6/c ISO 646 IRV supplementary set */
|
|
yuuji@0
|
188 /* 6/d JIS C6229-1984 OCR-A */
|
|
yuuji@0
|
189 /* 6/e JIS C6229-1984 OCR-B */
|
|
yuuji@0
|
190 /* 6/f JIS C6229-1984 OCR-B additional */
|
|
yuuji@0
|
191 /* 7/0 JIS C6229-1984 hand-printed */
|
|
yuuji@0
|
192 /* 7/1 JIS C6229-1984 additional hand-printd */
|
|
yuuji@0
|
193 /* 7/2 JIS C6229-1984 katakana hand-printed */
|
|
yuuji@0
|
194 /* 7/3 E13B Japanese graphic */
|
|
yuuji@0
|
195 /* 7/4 Supplementary Videotex (withdrawn) */
|
|
yuuji@0
|
196 /* 7/5 Teletex primary CCITT T.61 */
|
|
yuuji@0
|
197 /* 7/6 Teletex secondary CCITT T.61 */
|
|
yuuji@0
|
198 /* 7/7 CSA Z 243.4-1985 Alternate primary #1 */
|
|
yuuji@0
|
199 /* 7/8 CSA Z 243.4-1985 Alternate primary #2 */
|
|
yuuji@0
|
200 /* 7/9 Mosaic CCITT T.101 */
|
|
yuuji@0
|
201 /* 7/a Serbocroatian/Slovenian Latin */
|
|
yuuji@0
|
202 /* 7/b Serbocroatian Cyrillic */
|
|
yuuji@0
|
203 /* 7/c Supplementary CCITT T.101 */
|
|
yuuji@0
|
204 /* 7/d Macedonian Cyrillic */
|
|
yuuji@0
|
205
|
|
yuuji@0
|
206 /* 94 character sets - second intermediate byte */
|
|
yuuji@0
|
207
|
|
yuuji@0
|
208 /* 4/0 Greek primary CCITT */
|
|
yuuji@0
|
209 /* 4/1 Cuba */
|
|
yuuji@0
|
210 /* 4/2 ISO/IEC 646 invariant */
|
|
yuuji@0
|
211 /* 4/3 Irish Gaelic 7-bit */
|
|
yuuji@0
|
212 /* 4/4 Turkmen */
|
|
yuuji@0
|
213
|
|
yuuji@0
|
214
|
|
yuuji@0
|
215 /* 94x94 character sets */
|
|
yuuji@0
|
216
|
|
yuuji@0
|
217 #define I2CS_94x94_JIS_OLD 0x40 /* 4/0 JIS X 0208-1978 */
|
|
yuuji@0
|
218 #define I2CS_94x94_GB 0x41 /* 4/1 GB 2312 */
|
|
yuuji@0
|
219 #define I2CS_94x94_JIS_NEW 0x42 /* 4/2 JIS X 0208-1983 */
|
|
yuuji@0
|
220 #define I2CS_94x94_KSC 0x43 /* 4/3 KSC 5601 */
|
|
yuuji@0
|
221 #define I2CS_94x94_JIS_EXT 0x44 /* 4/4 JIS X 0212-1990 */
|
|
yuuji@0
|
222 /* 4/5 CCITT Chinese */
|
|
yuuji@0
|
223 /* 4/6 Blisssymbol Graphic */
|
|
yuuji@0
|
224 #define I2CS_94x94_CNS1 0x47 /* 4/7 CNS 11643 plane 1 */
|
|
yuuji@0
|
225 #define I2CS_94x94_CNS2 0x48 /* 4/8 CNS 11643 plane 2 */
|
|
yuuji@0
|
226 #define I2CS_94x94_CNS3 0x49 /* 4/9 CNS 11643 plane 3 */
|
|
yuuji@0
|
227 #define I2CS_94x94_CNS4 0x4a /* 4/a CNS 11643 plane 4 */
|
|
yuuji@0
|
228 #define I2CS_94x94_CNS5 0x4b /* 4/b CNS 11643 plane 5 */
|
|
yuuji@0
|
229 #define I2CS_94x94_CNS6 0x4c /* 4/c CNS 11643 plane 6 */
|
|
yuuji@0
|
230 #define I2CS_94x94_CNS7 0x4d /* 4/d CNS 11643 plane 7 */
|
|
yuuji@0
|
231 /* 4/e DPRK (North Korea) KGCII */
|
|
yuuji@0
|
232 /* 4/f JGCII plane 1 */
|
|
yuuji@0
|
233 /* 5/0 JGCII plane 2 */
|
|
yuuji@0
|
234
|
|
yuuji@0
|
235 /* 96 character sets */
|
|
yuuji@0
|
236
|
|
yuuji@0
|
237 #define I2CS_96_ISO8859_1 0x41 /* 4/1 Latin-1 (Western Europe) */
|
|
yuuji@0
|
238 #define I2CS_96_ISO8859_2 0x42 /* 4/2 Latin-2 (Czech, Slovak) */
|
|
yuuji@0
|
239 #define I2CS_96_ISO8859_3 0x43 /* 4/3 Latin-3 (Dutch, Turkish) */
|
|
yuuji@0
|
240 #define I2CS_96_ISO8859_4 0x44 /* 4/4 Latin-4 (Scandinavian) */
|
|
yuuji@0
|
241 /* 4/5 CSA Z 243.4-1985 */
|
|
yuuji@0
|
242 #define I2CS_96_ISO8859_7 0x46 /* 4/6 Greek */
|
|
yuuji@0
|
243 #define I2CS_96_ISO8859_6 0x47 /* 4/7 Arabic */
|
|
yuuji@0
|
244 #define I2CS_96_ISO8859_8 0x48 /* 4/8 Hebrew */
|
|
yuuji@0
|
245 /* 4/9 Czechoslovak CSN 369103 */
|
|
yuuji@0
|
246 /* 4/a Supplementary Latin and non-alpha */
|
|
yuuji@0
|
247 /* 4/b Technical */
|
|
yuuji@0
|
248 #define I2CS_96_ISO8859_5 0x4c /* 4/c Cyrillic */
|
|
yuuji@0
|
249 #define I2CS_96_ISO8859_9 0x4d /* 4/d Latin-5 (Finnish, Portuguese) */
|
|
yuuji@0
|
250 /* 4/e ISO 6937-2 residual */
|
|
yuuji@0
|
251 /* 4/f Basic Cyrillic */
|
|
yuuji@0
|
252 /* 5/0 Supplementary Latin 1, 2 and 5 */
|
|
yuuji@0
|
253 /* 5/1 Basic Box */
|
|
yuuji@0
|
254 /* 5/2 Supplementary ISO/IEC 6937 : 1992 */
|
|
yuuji@0
|
255 /* 5/3 CCITT Hebrew supplementary */
|
|
yuuji@0
|
256 #define I2CS_96_TIS620 0x54 /* 5/4 TIS 620 */
|
|
yuuji@0
|
257 /* 5/5 Arabic/French/German */
|
|
yuuji@0
|
258 #define I2CS_96_ISO8859_10 0x56 /* 5/6 Latin-6 (Northern Europe) */
|
|
yuuji@0
|
259 /* 5/7 ??? */
|
|
yuuji@0
|
260 /* 5/8 Sami (Lappish) supplementary */
|
|
yuuji@0
|
261 #define I2CS_96_ISO8859_13 0x59 /* 5/9 Latin-7 (Baltic) */
|
|
yuuji@0
|
262 #define I2CS_96_VSCII 0x5a /* 5/a Vietnamese */
|
|
yuuji@0
|
263 /* 5/b Technical #1 IEC 1289 */
|
|
yuuji@0
|
264 #define I2CS_96_ISO8859_14 0x5c /* 5/c Latin-8 (Celtic) */
|
|
yuuji@0
|
265 /* 5/d Sami supplementary Latin */
|
|
yuuji@0
|
266 /* 5/e Latin/Hebrew */
|
|
yuuji@0
|
267 /* 5/f Celtic supplementary Latin */
|
|
yuuji@0
|
268 /* 6/0 Uralic supplementary Cyrillic */
|
|
yuuji@0
|
269 /* 6/1 Volgaic supplementary Cyrillic */
|
|
yuuji@0
|
270 #define I2CS_96_ISO8859_15 0x62 /* 6/2 Latin-9 (Euro) */
|
|
yuuji@0
|
271 /* 6/3 Latin-1 with Euro */
|
|
yuuji@0
|
272 /* 6/4 Latin-4 with Euro */
|
|
yuuji@0
|
273 /* 6/5 Latin-7 with Euro */
|
|
yuuji@0
|
274 #define I2CS_96_ISO8859_16 0x66 /* 6/6 Latin-10 (Balkan) */
|
|
yuuji@0
|
275 /* 6/7 Ogham */
|
|
yuuji@0
|
276 /* 6/8 Sami supplementary Latin #2 */
|
|
yuuji@0
|
277 /* 7/d Supplementary Mosaic for CCITT 101 */
|
|
yuuji@0
|
278
|
|
yuuji@0
|
279 /* 96x96 character sets */
|
|
yuuji@0
|
280
|
|
yuuji@0
|
281 /* Types of character sets */
|
|
yuuji@0
|
282
|
|
yuuji@0
|
283 #define I2CS_94 0x000 /* 94 character set */
|
|
yuuji@0
|
284 #define I2CS_96 0x100 /* 96 character set */
|
|
yuuji@0
|
285 #define I2CS_MUL 0x200 /* multi-byte */
|
|
yuuji@0
|
286 #define I2CS_94x94 (I2CS_MUL | I2CS_94)
|
|
yuuji@0
|
287 #define I2CS_96x96 (I2CS_MUL | I2CS_96)
|
|
yuuji@0
|
288
|
|
yuuji@0
|
289
|
|
yuuji@0
|
290 /* Character set identifiers stored in Gn */
|
|
yuuji@0
|
291
|
|
yuuji@0
|
292 #define I2CS_BRITISH (I2CS_94 | I2CS_94_BRITISH)
|
|
yuuji@0
|
293 #define I2CS_ASCII (I2CS_94 | I2CS_94_ASCII)
|
|
yuuji@0
|
294 #define I2CS_JIS_BUGROM (I2CS_94 | I2CS_94_JIS_BUGROM)
|
|
yuuji@0
|
295 #define I2CS_JIS_KANA (I2CS_94 | I2CS_94_JIS_KANA)
|
|
yuuji@0
|
296 #define I2CS_JIS_ROMAN (I2CS_94 | I2CS_94_JIS_ROMAN)
|
|
yuuji@0
|
297 #define I2CS_JIS_OLD (I2CS_94x94 | I2CS_94x94_JIS_OLD)
|
|
yuuji@0
|
298 #define I2CS_GB (I2CS_94x94 | I2CS_94x94_GB)
|
|
yuuji@0
|
299 #define I2CS_JIS_NEW (I2CS_94x94 | I2CS_94x94_JIS_NEW)
|
|
yuuji@0
|
300 #define I2CS_KSC (I2CS_94x94 | I2CS_94x94_KSC)
|
|
yuuji@0
|
301 #define I2CS_JIS_EXT (I2CS_94x94 | I2CS_94x94_JIS_EXT)
|
|
yuuji@0
|
302 #define I2CS_CNS1 (I2CS_94x94 | I2CS_94x94_CNS1)
|
|
yuuji@0
|
303 #define I2CS_CNS2 (I2CS_94x94 | I2CS_94x94_CNS2)
|
|
yuuji@0
|
304 #define I2CS_CNS3 (I2CS_94x94 | I2CS_94x94_CNS3)
|
|
yuuji@0
|
305 #define I2CS_CNS4 (I2CS_94x94 | I2CS_94x94_CNS4)
|
|
yuuji@0
|
306 #define I2CS_CNS5 (I2CS_94x94 | I2CS_94x94_CNS5)
|
|
yuuji@0
|
307 #define I2CS_CNS6 (I2CS_94x94 | I2CS_94x94_CNS6)
|
|
yuuji@0
|
308 #define I2CS_CNS7 (I2CS_94x94 | I2CS_94x94_CNS7)
|
|
yuuji@0
|
309 #define I2CS_ISO8859_1 (I2CS_96 | I2CS_96_ISO8859_1)
|
|
yuuji@0
|
310 #define I2CS_ISO8859_2 (I2CS_96 | I2CS_96_ISO8859_2)
|
|
yuuji@0
|
311 #define I2CS_ISO8859_3 (I2CS_96 | I2CS_96_ISO8859_3)
|
|
yuuji@0
|
312 #define I2CS_ISO8859_4 (I2CS_96 | I2CS_96_ISO8859_4)
|
|
yuuji@0
|
313 #define I2CS_ISO8859_7 (I2CS_96 | I2CS_96_ISO8859_7)
|
|
yuuji@0
|
314 #define I2CS_ISO8859_6 (I2CS_96 | I2CS_96_ISO8859_6)
|
|
yuuji@0
|
315 #define I2CS_ISO8859_8 (I2CS_96 | I2CS_96_ISO8859_8)
|
|
yuuji@0
|
316 #define I2CS_ISO8859_5 (I2CS_96 | I2CS_96_ISO8859_5)
|
|
yuuji@0
|
317 #define I2CS_ISO8859_9 (I2CS_96 | I2CS_96_ISO8859_9)
|
|
yuuji@0
|
318 #define I2CS_TIS620 (I2CS_96 | I2CS_96_TIS620)
|
|
yuuji@0
|
319 #define I2CS_ISO8859_10 (I2CS_96 | I2CS_96_ISO8859_10)
|
|
yuuji@0
|
320 #define I2CS_ISO8859_13 (I2CS_96 | I2CS_96_ISO8859_13)
|
|
yuuji@0
|
321 #define I2CS_VSCII (I2CS_96 | I2CS_96_VSCII)
|
|
yuuji@0
|
322 #define I2CS_ISO8859_14 (I2CS_96 | I2CS_96_ISO8859_14)
|
|
yuuji@0
|
323 #define I2CS_ISO8859_15 (I2CS_96 | I2CS_96_ISO8859_15)
|
|
yuuji@0
|
324 #define I2CS_ISO8859_16 (I2CS_96 | I2CS_96_ISO8859_16)
|
|
yuuji@0
|
325
|
|
yuuji@0
|
326
|
|
yuuji@0
|
327 /* Miscellaneous ISO 2022 definitions */
|
|
yuuji@0
|
328
|
|
yuuji@0
|
329 #define EUC_CS2 0x8e /* single shift CS2 */
|
|
yuuji@0
|
330 #define EUC_CS3 0x8f /* single shift CS3 */
|
|
yuuji@0
|
331
|
|
yuuji@0
|
332 #define BITS7 0x7f /* 7-bit value mask */
|
|
yuuji@0
|
333 #define BIT8 0x80 /* 8th bit mask */
|
|
yuuji@0
|
334
|
|
yuuji@0
|
335 /* The following saves us from having to have yet more charset tables */
|
|
yuuji@0
|
336
|
|
yuuji@0
|
337 /* Unicode codepoints */
|
|
yuuji@0
|
338
|
|
yuuji@0
|
339 #define UCS2_C0CONTROL 0x00 /* first C0 control */
|
|
yuuji@0
|
340 #define UCS2_C0CONTROLEND 0x1F /* last C0 control */
|
|
yuuji@0
|
341 #define UCS2_C1CONTROL 0x80 /* first C1 control */
|
|
yuuji@0
|
342 #define UCS2_C1CONTROLEND 0x9F /* last C1 control */
|
|
yuuji@0
|
343
|
|
yuuji@0
|
344 /* ISO 646 substituted Unicode codepoints */
|
|
yuuji@0
|
345 #define UCS2_POUNDSTERLING 0x00a3
|
|
yuuji@0
|
346 #define UCS2_YEN 0x00a5
|
|
yuuji@0
|
347 #define UCS2_OVERLINE 0x203e
|
|
yuuji@0
|
348 #define UCS2_EURO 0x20ac
|
|
yuuji@0
|
349 #define UCS2_KATAKANA 0xff61 /* first katakana codepoint */
|
|
yuuji@0
|
350 #define UCS2_BOM 0xfeff /* byte order mark */
|
|
yuuji@0
|
351 #define UCS2_BOGON 0xfffd /* replacement character */
|
|
yuuji@0
|
352 /* next two codepoints are not Unicode chars */
|
|
yuuji@0
|
353 #define UCS2_BOMCHECK 0xfffe /* used to check byte order with UCS2_BOM */
|
|
yuuji@0
|
354 #define UCS2_NOTCHAR 0xffff /* not a character */
|
|
yuuji@0
|
355
|
|
yuuji@0
|
356 #define UCS4_BMPBASE 0x0000 /* Basic Multilingual Plane */
|
|
yuuji@0
|
357 #define UCS4_SMPBASE 0x10000 /* Supplementary Multilinugual Plane */
|
|
yuuji@0
|
358 #define UCS4_SIPBASE 0x20000 /* Supplementary Ideographic Plane */
|
|
yuuji@0
|
359 /* EastAsianWidth says plane 3 is wide */
|
|
yuuji@0
|
360 #define UCS4_UNABASE 0x40000 /* unassigned space */
|
|
yuuji@0
|
361 #define UCS4_SSPBASE 0xe0000 /* Supplementary Special-purpose Plane */
|
|
yuuji@0
|
362 #define UCS4_PVTBASE 0xf0000 /* private-space (two planes) */
|
|
yuuji@0
|
363 #define UCS4_MAXUNICODE 0x10ffff/* highest Unicode codepoint */
|
|
yuuji@0
|
364
|
|
yuuji@0
|
365 #define UTF16_BASE 0x10000 /* base of codepoints needing surrogates */
|
|
yuuji@0
|
366 #define UTF16_SHIFT 10 /* surrogate shift */
|
|
yuuji@0
|
367 #define UTF16_MASK 0x3ff /* surrogate mask */
|
|
yuuji@0
|
368 #define UTF16_SURR 0xd800 /* UTF-16 surrogate area */
|
|
yuuji@0
|
369 #define UTF16_SURRH 0xd800 /* UTF-16 first high surrogate */
|
|
yuuji@0
|
370 #define UTF16_SURRHEND 0xdbff /* UTF-16 last high surrogate */
|
|
yuuji@0
|
371 #define UTF16_SURRL 0xdc00 /* UTF-16 first low surrogate */
|
|
yuuji@0
|
372 #define UTF16_SURRLEND 0xdfff /* UTF-16 last low surrogate */
|
|
yuuji@0
|
373 #define UTF16_MAXSURR 0xdfff /* end of UTF-16 surrogates */
|
|
yuuji@0
|
374
|
|
yuuji@0
|
375
|
|
yuuji@0
|
376 /* UBOGON is used to represent a codepoint in a character set which does not
|
|
yuuji@0
|
377 * map to Unicode. It is also used for mapping failures, e.g. incomplete
|
|
yuuji@0
|
378 * shift sequences. This name has the same text width as 0x????, for
|
|
yuuji@0
|
379 * convenience in the mapping tables.
|
|
yuuji@0
|
380 *
|
|
yuuji@0
|
381 * NOCHAR is used to represent a codepoint in Unicode which does not map to
|
|
yuuji@0
|
382 * the target character set in a reverse mapping table. This name has the
|
|
yuuji@0
|
383 * same text width as 0x???? in case we ever add static reverse mapping tables.
|
|
yuuji@0
|
384 */
|
|
yuuji@0
|
385
|
|
yuuji@0
|
386 #define UBOGON UCS2_BOGON
|
|
yuuji@0
|
387 #define NOCHAR UCS2_NOTCHAR
|
|
yuuji@0
|
388
|
|
yuuji@0
|
389 /* Codepoints in non-Unicode character sets */
|
|
yuuji@0
|
390
|
|
yuuji@0
|
391 /* Codepoints in ISO 646 character sets */
|
|
yuuji@0
|
392
|
|
yuuji@0
|
393 /* British ASCII codepoints */
|
|
yuuji@0
|
394
|
|
yuuji@0
|
395 #define BRITISH_POUNDSTERLING 0x23
|
|
yuuji@0
|
396
|
|
yuuji@0
|
397 /* JIS Roman codepoints */
|
|
yuuji@0
|
398
|
|
yuuji@0
|
399 #define JISROMAN_YEN 0x5c
|
|
yuuji@0
|
400 #define JISROMAN_OVERLINE 0x7e
|
|
yuuji@0
|
401
|
|
yuuji@0
|
402
|
|
yuuji@0
|
403 /* Hankaku katakana codepoints & parameters
|
|
yuuji@0
|
404 *
|
|
yuuji@0
|
405 * In earlier versions, MAX_KANA_7 and MAX_KANA_8 were the maximum codepoint
|
|
yuuji@0
|
406 * values. Although this made sense, it was confusing with the "max ku" and
|
|
yuuji@0
|
407 * "max ten" values used in the double-byte tables; there are 1-origin, but
|
|
yuuji@0
|
408 * the calculated values used for "ku" and "ten" are 0-origin (derived by
|
|
yuuji@0
|
409 * substracting the "base"). What this all meant is that for double byte
|
|
yuuji@0
|
410 * characters the limit test is of the form (value < max_ku), but for single
|
|
yuuji@0
|
411 * byte characters (which used the same cell to hold the max ku) the limit
|
|
yuuji@0
|
412 * test was (value <= max_ku).
|
|
yuuji@0
|
413 *
|
|
yuuji@0
|
414 * By making MAX_KANA_[78] be maximum+1, the same (value < max_ku) limit test
|
|
yuuji@0
|
415 * is used throughout. - 6/15/2006
|
|
yuuji@0
|
416 */
|
|
yuuji@0
|
417
|
|
yuuji@0
|
418 #define MIN_KANA_7 0x21
|
|
yuuji@0
|
419 #define MAX_KANA_7 0x60 /* maximum value + 1 */
|
|
yuuji@0
|
420 #define KANA_7 (UCS2_KATAKANA - MIN_KANA_7)
|
|
yuuji@0
|
421 #define MIN_KANA_8 (MIN_KANA_7 | BIT8)
|
|
yuuji@0
|
422 #define MAX_KANA_8 (MAX_KANA_7 | BIT8)
|
|
yuuji@0
|
423 #define KANA_8 (UCS2_KATAKANA - MIN_KANA_8)
|
|
yuuji@0
|
424
|
|
yuuji@0
|
425 /* Charset scripts */
|
|
yuuji@0
|
426
|
|
yuuji@0
|
427 /* The term "script" is used here in a very loose sense, enough to make
|
|
yuuji@0
|
428 * purists cringe. Basically, the idea is to give the main program some
|
|
yuuji@0
|
429 * idea of how it should treat the characters of text in a charset with
|
|
yuuji@0
|
430 * respect to font, drawing routines, etc.
|
|
yuuji@0
|
431 *
|
|
yuuji@0
|
432 * In some cases, "script" is associated with a charset; in other cases,
|
|
yuuji@0
|
433 * it's more closely tied to a language.
|
|
yuuji@0
|
434 */
|
|
yuuji@0
|
435
|
|
yuuji@0
|
436 #define SC_UNICODE 0x1 /* Unicode */
|
|
yuuji@0
|
437 #define SC_LATIN_1 0x10 /* Western Europe */
|
|
yuuji@0
|
438 #define SC_LATIN_2 0x20 /* Eastern Europe */
|
|
yuuji@0
|
439 #define SC_LATIN_3 0x40 /* Southern Europe */
|
|
yuuji@0
|
440 #define SC_LATIN_4 0x80 /* Northern Europe */
|
|
yuuji@0
|
441 #define SC_LATIN_5 0x100 /* Turkish */
|
|
yuuji@0
|
442 #define SC_LATIN_6 0x200 /* Nordic */
|
|
yuuji@0
|
443 #define SC_LATIN_7 0x400 /* Baltic */
|
|
yuuji@0
|
444 #define SC_LATIN_8 0x800 /* Celtic */
|
|
yuuji@0
|
445 #define SC_LATIN_9 0x1000 /* Euro */
|
|
yuuji@0
|
446 #define SC_LATIN_0 SC_LATIN_9 /* colloquial name for Latin-9 */
|
|
yuuji@0
|
447 #define SC_ARABIC 0x2000
|
|
yuuji@0
|
448 #define SC_CYRILLIC 0x4000
|
|
yuuji@0
|
449 #define SC_GREEK 0x8000
|
|
yuuji@0
|
450 #define SC_HEBREW 0x10000
|
|
yuuji@0
|
451 #define SC_THAI 0x20000
|
|
yuuji@0
|
452 #define SC_UKRANIAN 0x40000
|
|
yuuji@0
|
453 #define SC_LATIN_10 0x80000 /* Balkan */
|
|
yuuji@0
|
454 #define SC_VIETNAMESE 0x100000
|
|
yuuji@0
|
455 #define SC_CHINESE_SIMPLIFIED 0x1000000
|
|
yuuji@0
|
456 #define SC_CHINESE_TRADITIONAL 0x2000000
|
|
yuuji@0
|
457 #define SC_JAPANESE 0x4000000
|
|
yuuji@0
|
458 #define SC_KOREAN 0x8000000
|
|
yuuji@0
|
459
|
|
yuuji@0
|
460
|
|
yuuji@0
|
461 /* Script table */
|
|
yuuji@0
|
462
|
|
yuuji@0
|
463 typedef struct utf8_scent {
|
|
yuuji@0
|
464 char *name; /* script name */
|
|
yuuji@0
|
465 char *description; /* script description */
|
|
yuuji@0
|
466 unsigned long script; /* script bitmask */
|
|
yuuji@0
|
467 } SCRIPT;
|
|
yuuji@0
|
468
|
|
yuuji@0
|
469 /* Character set table support */
|
|
yuuji@0
|
470
|
|
yuuji@0
|
471 typedef struct utf8_csent {
|
|
yuuji@0
|
472 char *name; /* charset name */
|
|
yuuji@0
|
473 unsigned short type; /* type of charset */
|
|
yuuji@0
|
474 unsigned short flags; /* charset flags */
|
|
yuuji@0
|
475 void *tab; /* additional data */
|
|
yuuji@0
|
476 unsigned long script; /* script(s) implemented by this charset */
|
|
yuuji@0
|
477 char *preferred; /* preferred charset over this one */
|
|
yuuji@0
|
478 } CHARSET;
|
|
yuuji@0
|
479
|
|
yuuji@0
|
480
|
|
yuuji@0
|
481 struct utf8_eucparam {
|
|
yuuji@0
|
482 unsigned int base_ku : 8; /* base row */
|
|
yuuji@0
|
483 unsigned int base_ten : 8; /* base column */
|
|
yuuji@0
|
484 unsigned int max_ku : 8; /* maximum row */
|
|
yuuji@0
|
485 unsigned int max_ten : 8; /* maximum column */
|
|
yuuji@0
|
486 void *tab; /* conversion table */
|
|
yuuji@0
|
487 };
|
|
yuuji@0
|
488
|
|
yuuji@0
|
489
|
|
yuuji@0
|
490 /* Charset types */
|
|
yuuji@0
|
491
|
|
yuuji@0
|
492 #define CT_UNKNOWN 0 /* unknown 8-bit */
|
|
yuuji@0
|
493 #define CT_ASCII 1 /* 7-bit ASCII no table */
|
|
yuuji@0
|
494 #define CT_UCS2 2 /* 2 byte 16-bit Unicode no table */
|
|
yuuji@0
|
495 #define CT_UCS4 3 /* 4 byte 32-bit Unicode no table */
|
|
yuuji@0
|
496 #define CT_1BYTE0 10 /* 1 byte ISO 8859-1 no table */
|
|
yuuji@0
|
497 #define CT_1BYTE 11 /* 1 byte ASCII + table 0x80-0xff */
|
|
yuuji@0
|
498 #define CT_1BYTE8 12 /* 1 byte table 0x00 - 0xff */
|
|
yuuji@0
|
499 #define CT_EUC 100 /* 2 byte ASCII + utf8_eucparam base/CS2/CS3 */
|
|
yuuji@0
|
500 #define CT_DBYTE 101 /* 2 byte ASCII + utf8_eucparam */
|
|
yuuji@0
|
501 #define CT_DBYTE2 102 /* 2 byte ASCII + utf8_eucparam plane1/2 */
|
|
yuuji@0
|
502 #define CT_UTF16 1000 /* variable UTF-16 encoded Unicode no table */
|
|
yuuji@0
|
503 #define CT_UTF8 1001 /* variable UTF-8 encoded Unicode no table */
|
|
yuuji@0
|
504 #define CT_UTF7 1002 /* variable UTF-7 encoded Unicode no table */
|
|
yuuji@0
|
505 #define CT_2022 10000 /* variable ISO-2022 encoded no table */
|
|
yuuji@0
|
506 #define CT_SJIS 10001 /* 2 byte Shift-JIS encoded JIS no table */
|
|
yuuji@0
|
507
|
|
yuuji@0
|
508
|
|
yuuji@0
|
509 /* Character set flags */
|
|
yuuji@0
|
510
|
|
yuuji@0
|
511 #define CF_PRIMARY 0x1 /* primary name for this charset */
|
|
yuuji@0
|
512 #define CF_DISPLAY 0x2 /* charset used in displays */
|
|
yuuji@0
|
513 #define CF_POSTING 0x4 /* charset used in email posting */
|
|
yuuji@0
|
514 #define CF_UNSUPRT 0x8 /* charset unsupported (can't convert to it) */
|
|
yuuji@0
|
515 #define CF_NOEMAIL 0x10 /* charset not used in email */
|
|
yuuji@0
|
516
|
|
yuuji@0
|
517
|
|
yuuji@0
|
518 /* UTF-7 engine states */
|
|
yuuji@0
|
519
|
|
yuuji@0
|
520 #define U7_ASCII 0 /* ASCII character */
|
|
yuuji@0
|
521 #define U7_PLUS 1 /* plus seen */
|
|
yuuji@0
|
522 #define U7_UNICODE 2 /* Unicode characters */
|
|
yuuji@0
|
523 #define U7_MINUS 3 /* absorbed minus seen */
|
|
yuuji@0
|
524
|
|
yuuji@0
|
525 /* Function prototypes */
|
|
yuuji@0
|
526
|
|
yuuji@0
|
527 typedef unsigned long (*ucs4cn_t) (unsigned long c);
|
|
yuuji@0
|
528 typedef unsigned long (*ucs4de_t) (unsigned long c,void **more);
|
|
yuuji@0
|
529
|
|
yuuji@0
|
530 SCRIPT *utf8_script (char *script);
|
|
yuuji@0
|
531 const CHARSET *utf8_charset (char *charset);
|
|
yuuji@0
|
532 char *utf8_badcharset (char *charset);
|
|
yuuji@0
|
533 long utf8_text (SIZEDTEXT *text,char *charset,SIZEDTEXT *ret,long flags);
|
|
yuuji@0
|
534 long utf8_text_cs (SIZEDTEXT *text,const CHARSET *cs,SIZEDTEXT *ret,
|
|
yuuji@0
|
535 ucs4cn_t cv,ucs4de_t de);
|
|
yuuji@0
|
536 long utf8_cstext (SIZEDTEXT *text,char *charset,SIZEDTEXT *ret,
|
|
yuuji@0
|
537 unsigned long errch);
|
|
yuuji@0
|
538 long utf8_cstocstext (SIZEDTEXT *text,char *sc,SIZEDTEXT *ret,char *dc,
|
|
yuuji@0
|
539 unsigned long errch);
|
|
yuuji@0
|
540 unsigned short *utf8_rmap (char *charset);
|
|
yuuji@0
|
541 unsigned short *utf8_rmap_cs (const CHARSET *cs);
|
|
yuuji@0
|
542 unsigned short *utf8_rmap_gen (const CHARSET *cs,unsigned short *oldmap);
|
|
yuuji@0
|
543 long utf8_rmaptext (SIZEDTEXT *text,unsigned short *rmap,SIZEDTEXT *ret,
|
|
yuuji@0
|
544 unsigned long errch,long iso2022jp);
|
|
yuuji@0
|
545 unsigned long utf8_rmapsize (SIZEDTEXT *text,unsigned short *rmap,
|
|
yuuji@0
|
546 unsigned long errch,long iso2022jp);
|
|
yuuji@0
|
547 long ucs4_rmaptext (unsigned long *ucs4,unsigned long len,unsigned short *rmap,
|
|
yuuji@0
|
548 SIZEDTEXT *ret,unsigned long errch);
|
|
yuuji@0
|
549 long ucs4_rmaplen (unsigned long *ucs4,unsigned long len,unsigned short *rmap,
|
|
yuuji@0
|
550 unsigned long errch);
|
|
yuuji@0
|
551 long ucs4_rmapbuf (unsigned char *t,unsigned long *ucs4,unsigned long len,
|
|
yuuji@0
|
552 unsigned short *rmap,unsigned long errch);
|
|
yuuji@0
|
553 unsigned long utf8_get (unsigned char **s,unsigned long *i);
|
|
yuuji@0
|
554 unsigned long utf8_get_raw (unsigned char **s,unsigned long *i);
|
|
yuuji@0
|
555 unsigned long ucs4_cs_get (CHARSET *cs,unsigned char **s,unsigned long *i);
|
|
yuuji@0
|
556 unsigned long *utf8_csvalidmap (char *charsets[]);
|
|
yuuji@0
|
557 const CHARSET *utf8_infercharset (SIZEDTEXT *src);
|
|
yuuji@0
|
558 long utf8_validate (unsigned char *s,unsigned long i);
|
|
yuuji@0
|
559 void utf8_text_1byte0 (SIZEDTEXT *text,SIZEDTEXT *ret,ucs4cn_t cv,ucs4de_t de);
|
|
yuuji@0
|
560 void utf8_text_1byte (SIZEDTEXT *text,SIZEDTEXT *ret,void *tab,ucs4cn_t cv,
|
|
yuuji@0
|
561 ucs4de_t de);
|
|
yuuji@0
|
562 void utf8_text_1byte8 (SIZEDTEXT *text,SIZEDTEXT *ret,void *tab,ucs4cn_t cv,
|
|
yuuji@0
|
563 ucs4de_t de);
|
|
yuuji@0
|
564 void utf8_text_euc (SIZEDTEXT *text,SIZEDTEXT *ret,void *tab,ucs4cn_t cv,
|
|
yuuji@0
|
565 ucs4de_t de);
|
|
yuuji@0
|
566 void utf8_text_dbyte (SIZEDTEXT *text,SIZEDTEXT *ret,void *tab,ucs4cn_t cv,
|
|
yuuji@0
|
567 ucs4de_t de);
|
|
yuuji@0
|
568 void utf8_text_dbyte2 (SIZEDTEXT *text,SIZEDTEXT *ret,void *tab,ucs4cn_t cv,
|
|
yuuji@0
|
569 ucs4de_t de);
|
|
yuuji@0
|
570 void utf8_text_sjis (SIZEDTEXT *text,SIZEDTEXT *ret,ucs4cn_t cv,ucs4de_t de);
|
|
yuuji@0
|
571 void utf8_text_2022 (SIZEDTEXT *text,SIZEDTEXT *ret,ucs4cn_t cv,ucs4de_t de);
|
|
yuuji@0
|
572 void utf8_text_utf7 (SIZEDTEXT *text,SIZEDTEXT *ret,ucs4cn_t cv,ucs4de_t de);
|
|
yuuji@0
|
573 void utf8_text_utf8 (SIZEDTEXT *text,SIZEDTEXT *ret,ucs4cn_t cv,ucs4de_t de);
|
|
yuuji@0
|
574 void utf8_text_ucs2 (SIZEDTEXT *text,SIZEDTEXT *ret,ucs4cn_t cv,ucs4de_t de);
|
|
yuuji@0
|
575 void utf8_text_ucs4 (SIZEDTEXT *text,SIZEDTEXT *ret,ucs4cn_t cv,ucs4de_t de);
|
|
yuuji@0
|
576 void utf8_text_utf16 (SIZEDTEXT *text,SIZEDTEXT *ret,ucs4cn_t cv,ucs4de_t de);
|
|
yuuji@0
|
577 unsigned long utf8_size (unsigned long c);
|
|
yuuji@0
|
578 unsigned char *utf8_put (unsigned char *s,unsigned long c);
|
|
yuuji@0
|
579 unsigned long ucs4_titlecase (unsigned long c);
|
|
yuuji@0
|
580 long ucs4_width (unsigned long c);
|
|
yuuji@0
|
581 long utf8_strwidth (unsigned char *s);
|
|
yuuji@0
|
582 long utf8_textwidth (SIZEDTEXT *utf8);
|
|
yuuji@0
|
583 unsigned long ucs4_decompose (unsigned long c,void **more);
|
|
yuuji@0
|
584 unsigned long ucs4_decompose_recursive (unsigned long c,void **more);
|
