1 /* 2 * Copyright 1998-2008 The OpenLDAP Foundation. 3 * All rights reserved. 4 * 5 * Redistribution and use in source and binary forms, with or without 6 * modification, are permitted only as authorized by the OpenLDAP 7 * Public License. 8 * 9 * A copy of this license is available in file LICENSE in the 10 * top-level directory of the distribution or, alternatively, at 11 * <https://www.OpenLDAP.org/license.html>. 12 */ 13 /* Copyright 2001 Computing Research Labs, New Mexico State University 14 * 15 * Permission is hereby granted, free of charge, to any person obtaining a 16 * copy of this software and associated documentation files (the "Software"), 17 * to deal in the Software without restriction, including without limitation 18 * the rights to use, copy, modify, merge, publish, distribute, sublicense, 19 * and/or sell copies of the Software, and to permit persons to whom the 20 * Software is furnished to do so, subject to the following conditions: 21 * 22 * The above copyright notice and this permission notice shall be included in 23 * all copies or substantial portions of the Software. 24 * 25 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 26 * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 27 * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 28 * THE COMPUTING RESEARCH LAB OR NEW MEXICO STATE UNIVERSITY BE LIABLE FOR ANY 29 * CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT 30 * OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR 31 * THE USE OR OTHER DEALINGS IN THE SOFTWARE. 32 */ 33 34 /* 35 * This work is part of OpenLDAP Software <https://www.openldap.org/>. 36 * $OpenLDAP: pkg/ldap/libraries/liblunicode/ucdata/ucdata.h,v 1.21 2008/01/07 23:20:05 kurt Exp $ 37 * $Id: ucdata.h,v 1.6 2001/01/02 18:46:20 mleisher Exp $ 38 */ 39 40 #ifndef _h_ucdata 41 #define _h_ucdata 42 43 #define UCDATA_VERSION "2.4" 44 45 /************************************************************************** 46 * 47 * Masks and macros for character properties. 48 * 49 **************************************************************************/ 50 51 /* 52 * Values that can appear in the `mask1' parameter of the ucisprop() 53 * function. 54 */ 55 #define UC_MN 0x00000001 /* Mark, Non-Spacing */ 56 #define UC_MC 0x00000002 /* Mark, Spacing Combining */ 57 #define UC_ME 0x00000004 /* Mark, Enclosing */ 58 #define UC_ND 0x00000008 /* Number, Decimal Digit */ 59 #define UC_NL 0x00000010 /* Number, Letter */ 60 #define UC_NO 0x00000020 /* Number, Other */ 61 #define UC_ZS 0x00000040 /* Separator, Space */ 62 #define UC_ZL 0x00000080 /* Separator, Line */ 63 #define UC_ZP 0x00000100 /* Separator, Paragraph */ 64 #define UC_CC 0x00000200 /* Other, Control */ 65 #define UC_CF 0x00000400 /* Other, Format */ 66 #define UC_OS 0x00000800 /* Other, Surrogate */ 67 #define UC_CO 0x00001000 /* Other, Private Use */ 68 #define UC_CN 0x00002000 /* Other, Not Assigned */ 69 #define UC_LU 0x00004000 /* Letter, Uppercase */ 70 #define UC_LL 0x00008000 /* Letter, Lowercase */ 71 #define UC_LT 0x00010000 /* Letter, Titlecase */ 72 #define UC_LM 0x00020000 /* Letter, Modifier */ 73 #define UC_LO 0x00040000 /* Letter, Other */ 74 #define UC_PC 0x00080000 /* Punctuation, Connector */ 75 #define UC_PD 0x00100000 /* Punctuation, Dash */ 76 #define UC_PS 0x00200000 /* Punctuation, Open */ 77 #define UC_PE 0x00400000 /* Punctuation, Close */ 78 #define UC_PO 0x00800000 /* Punctuation, Other */ 79 #define UC_SM 0x01000000 /* Symbol, Math */ 80 #define UC_SC 0x02000000 /* Symbol, Currency */ 81 #define UC_SK 0x04000000 /* Symbol, Modifier */ 82 #define UC_SO 0x08000000 /* Symbol, Other */ 83 #define UC_L 0x10000000 /* Left-To-Right */ 84 #define UC_R 0x20000000 /* Right-To-Left */ 85 #define UC_EN 0x40000000 /* European Number */ 86 #define UC_ES 0x80000000 /* European Number Separator */ 87 88 /* 89 * Values that can appear in the `mask2' parameter of the ucisprop() 90 * function. 91 */ 92 #define UC_ET 0x00000001 /* European Number Terminator */ 93 #define UC_AN 0x00000002 /* Arabic Number */ 94 #define UC_CS 0x00000004 /* Common Number Separator */ 95 #define UC_B 0x00000008 /* Block Separator */ 96 #define UC_S 0x00000010 /* Segment Separator */ 97 #define UC_WS 0x00000020 /* Whitespace */ 98 #define UC_ON 0x00000040 /* Other Neutrals */ 99 /* 100 * Implementation specific character properties. 101 */ 102 #define UC_CM 0x00000080 /* Composite */ 103 #define UC_NB 0x00000100 /* Non-Breaking */ 104 #define UC_SY 0x00000200 /* Symmetric */ 105 #define UC_HD 0x00000400 /* Hex Digit */ 106 #define UC_QM 0x00000800 /* Quote Mark */ 107 #define UC_MR 0x00001000 /* Mirroring */ 108 #define UC_SS 0x00002000 /* Space, other */ 109 110 #define UC_CP 0x00004000 /* Defined */ 111 112 /* 113 * Added for UnicodeData-2.1.3. 114 */ 115 #define UC_PI 0x00008000 /* Punctuation, Initial */ 116 #define UC_PF 0x00010000 /* Punctuation, Final */ 117 118 /* 119 * This is the primary function for testing to see if a character has some set 120 * of properties. The macros that test for various character properties all 121 * call this function with some set of masks. 122 */ 123 int 124 ucisprop (krb5_ui_4 code, krb5_ui_4 mask1, krb5_ui_4 mask2); 125 126 #define ucisalpha(cc) ucisprop(cc, UC_LU|UC_LL|UC_LM|UC_LO|UC_LT, 0) 127 #define ucisdigit(cc) ucisprop(cc, UC_ND, 0) 128 #define ucisalnum(cc) ucisprop(cc, UC_LU|UC_LL|UC_LM|UC_LO|UC_LT|UC_ND, 0) 129 #define uciscntrl(cc) ucisprop(cc, UC_CC|UC_CF, 0) 130 #define ucisspace(cc) ucisprop(cc, UC_ZS|UC_SS, 0) 131 #define ucisblank(cc) ucisprop(cc, UC_ZS, 0) 132 #define ucispunct(cc) ucisprop(cc, UC_PD|UC_PS|UC_PE|UC_PO, UC_PI|UC_PF) 133 #define ucisgraph(cc) ucisprop(cc, UC_MN|UC_MC|UC_ME|UC_ND|UC_NL|UC_NO|\ 134 UC_LU|UC_LL|UC_LT|UC_LM|UC_LO|UC_PC|UC_PD|\ 135 UC_PS|UC_PE|UC_PO|UC_SM|UC_SM|UC_SC|UC_SK|\ 136 UC_SO, UC_PI|UC_PF) 137 #define ucisprint(cc) ucisprop(cc, UC_MN|UC_MC|UC_ME|UC_ND|UC_NL|UC_NO|\ 138 UC_LU|UC_LL|UC_LT|UC_LM|UC_LO|UC_PC|UC_PD|\ 139 UC_PS|UC_PE|UC_PO|UC_SM|UC_SM|UC_SC|UC_SK|\ 140 UC_SO|UC_ZS, UC_PI|UC_PF) 141 #define ucisupper(cc) ucisprop(cc, UC_LU, 0) 142 #define ucislower(cc) ucisprop(cc, UC_LL, 0) 143 #define ucistitle(cc) ucisprop(cc, UC_LT, 0) 144 #define ucisxdigit(cc) ucisprop(cc, 0, UC_HD) 145 146 #define ucisisocntrl(cc) ucisprop(cc, UC_CC, 0) 147 #define ucisfmtcntrl(cc) ucisprop(cc, UC_CF, 0) 148 149 #define ucissymbol(cc) ucisprop(cc, UC_SM|UC_SC|UC_SO|UC_SK, 0) 150 #define ucisnumber(cc) ucisprop(cc, UC_ND|UC_NO|UC_NL, 0) 151 #define ucisnonspacing(cc) ucisprop(cc, UC_MN, 0) 152 #define ucisopenpunct(cc) ucisprop(cc, UC_PS, 0) 153 #define ucisclosepunct(cc) ucisprop(cc, UC_PE, 0) 154 #define ucisinitialpunct(cc) ucisprop(cc, 0, UC_PI) 155 #define ucisfinalpunct(cc) ucisprop(cc, 0, UC_PF) 156 157 #define uciscomposite(cc) ucisprop(cc, 0, UC_CM) 158 #define ucishex(cc) ucisprop(cc, 0, UC_HD) 159 #define ucisquote(cc) ucisprop(cc, 0, UC_QM) 160 #define ucissymmetric(cc) ucisprop(cc, 0, UC_SY) 161 #define ucismirroring(cc) ucisprop(cc, 0, UC_MR) 162 #define ucisnonbreaking(cc) ucisprop(cc, 0, UC_NB) 163 164 /* 165 * Directionality macros. 166 */ 167 #define ucisrtl(cc) ucisprop(cc, UC_R, 0) 168 #define ucisltr(cc) ucisprop(cc, UC_L, 0) 169 #define ucisstrong(cc) ucisprop(cc, UC_L|UC_R, 0) 170 #define ucisweak(cc) ucisprop(cc, UC_EN|UC_ES, UC_ET|UC_AN|UC_CS) 171 #define ucisneutral(cc) ucisprop(cc, 0, UC_B|UC_S|UC_WS|UC_ON) 172 #define ucisseparator(cc) ucisprop(cc, 0, UC_B|UC_S) 173 174 /* 175 * Other macros inspired by John Cowan. 176 */ 177 #define ucismark(cc) ucisprop(cc, UC_MN|UC_MC|UC_ME, 0) 178 #define ucismodif(cc) ucisprop(cc, UC_LM, 0) 179 #define ucisletnum(cc) ucisprop(cc, UC_NL, 0) 180 #define ucisconnect(cc) ucisprop(cc, UC_PC, 0) 181 #define ucisdash(cc) ucisprop(cc, UC_PD, 0) 182 #define ucismath(cc) ucisprop(cc, UC_SM, 0) 183 #define uciscurrency(cc) ucisprop(cc, UC_SC, 0) 184 #define ucismodifsymbol(cc) ucisprop(cc, UC_SK, 0) 185 #define ucisnsmark(cc) ucisprop(cc, UC_MN, 0) 186 #define ucisspmark(cc) ucisprop(cc, UC_MC, 0) 187 #define ucisenclosing(cc) ucisprop(cc, UC_ME, 0) 188 #define ucisprivate(cc) ucisprop(cc, UC_CO, 0) 189 #define ucissurrogate(cc) ucisprop(cc, UC_OS, 0) 190 #define ucislsep(cc) ucisprop(cc, UC_ZL, 0) 191 #define ucispsep(cc) ucisprop(cc, UC_ZP, 0) 192 193 #define ucisidentstart(cc) ucisprop(cc, UC_LU|UC_LL|UC_LT|UC_LO|UC_NL, 0) 194 #define ucisidentpart(cc) ucisprop(cc, UC_LU|UC_LL|UC_LT|UC_LO|UC_NL|\ 195 UC_MN|UC_MC|UC_ND|UC_PC|UC_CF, 0) 196 197 #define ucisdefined(cc) ucisprop(cc, 0, UC_CP) 198 #define ucisundefined(cc) !ucisprop(cc, 0, UC_CP) 199 200 /* 201 * Other miscellaneous character property macros. 202 */ 203 #define ucishan(cc) (((cc) >= 0x4e00 && (cc) <= 0x9fff) ||\ 204 ((cc) >= 0xf900 && (cc) <= 0xfaff)) 205 #define ucishangul(cc) ((cc) >= 0xac00 && (cc) <= 0xd7ff) 206 207 /************************************************************************** 208 * 209 * Functions for case conversion. 210 * 211 **************************************************************************/ 212 213 krb5_ui_4 uctoupper(krb5_ui_4 code); 214 krb5_ui_4 uctolower(krb5_ui_4 code); 215 krb5_ui_4 uctotitle(krb5_ui_4 code); 216 217 /************************************************************************** 218 * 219 * Functions for getting compositions. 220 * 221 **************************************************************************/ 222 223 /* 224 * This routine determines if there exists a composition of node1 and node2. 225 * If it returns 0, there is no composition. Any other value indicates a 226 * composition was returned in comp. 227 */ 228 int uccomp(krb5_ui_4 node1, krb5_ui_4 node2, krb5_ui_4 *comp); 229 230 /* 231 * Does Hangul composition on the string str with length len, and returns 232 * the length of the composed string. 233 */ 234 int uccomp_hangul(krb5_ui_4 *str, int len); 235 236 /* 237 * Does canonical composition on the string str with length len, and returns 238 * the length of the composed string. 239 */ 240 int uccanoncomp(krb5_ui_4 *str, int len); 241 242 /************************************************************************** 243 * 244 * Functions for getting decompositions. 245 * 246 **************************************************************************/ 247 248 /* 249 * This routine determines if the code has a decomposition. If it returns 0, 250 * there is no decomposition. Any other value indicates a decomposition was 251 * returned. 252 */ 253 int ucdecomp(krb5_ui_4 code, krb5_ui_4 *num, krb5_ui_4 **decomp); 254 255 /* 256 * Equivalent to ucdecomp() except that it includes compatibility 257 * decompositions. 258 */ 259 int uckdecomp(krb5_ui_4 code, krb5_ui_4 *num, krb5_ui_4 **decomp); 260 261 /* 262 * If the code is a Hangul syllable, this routine decomposes it into the array 263 * passed. The array size should be at least 3. 264 */ 265 int ucdecomp_hangul(krb5_ui_4 code, krb5_ui_4 *num, krb5_ui_4 decomp[]); 266 267 /* 268 * This routine does canonical decomposition of the string in of length 269 * inlen, and returns the decomposed string in out with length outlen. 270 * The memory for out is allocated by this routine. It returns the length 271 * of the decomposed string if okay, and -1 on error. 272 */ 273 int uccanondecomp (const krb5_ui_4 *in, int inlen, 274 krb5_ui_4 **out, int *outlen); 275 276 /* 277 * Equivalent to uccanondecomp() except that it includes compatibility 278 * decompositions. 279 */ 280 int uccompatdecomp(const krb5_ui_4 *in, int inlen, 281 krb5_ui_4 **out, int *outlen); 282 283 /************************************************************************** 284 * 285 * Functions for getting combining classes. 286 * 287 **************************************************************************/ 288 289 /* 290 * This will return the combining class for a character to be used with the 291 * Canonical Ordering algorithm. 292 */ 293 krb5_ui_4 uccombining_class(krb5_ui_4 code); 294 295 /************************************************************************** 296 * 297 * Functions for getting numbers and digits. 298 * 299 **************************************************************************/ 300 301 struct ucnumber { 302 int numerator; 303 int denominator; 304 }; 305 306 int 307 ucnumber_lookup (krb5_ui_4 code, struct ucnumber *num); 308 309 int 310 ucdigit_lookup (krb5_ui_4 code, int *digit); 311 312 /* 313 * For compatibility with John Cowan's "uctype" package. 314 */ 315 struct ucnumber ucgetnumber (krb5_ui_4 code); 316 int ucgetdigit (krb5_ui_4 code); 317 318 /************************************************************************** 319 * 320 * Functions library initialization and cleanup. 321 * 322 **************************************************************************/ 323 324 /* 325 * Macros for specifying the data tables to be loaded, unloaded, or reloaded 326 * by the ucdata_load(), ucdata_unload(), and ucdata_reload() routines. 327 */ 328 #define UCDATA_CASE 0x01 329 #define UCDATA_CTYPE 0x02 330 #define UCDATA_DECOMP 0x04 331 #define UCDATA_CMBCL 0x08 332 #define UCDATA_NUM 0x10 333 #define UCDATA_COMP 0x20 334 #define UCDATA_KDECOMP 0x40 335 336 #define UCDATA_ALL (UCDATA_CASE|UCDATA_CTYPE|UCDATA_DECOMP|\ 337 UCDATA_CMBCL|UCDATA_NUM|UCDATA_COMP|UCDATA_KDECOMP) 338 339 /* 340 * Functions to load, unload, and reload specific data files. 341 */ 342 int ucdata_load (char *paths, int mask); 343 void ucdata_unload (int mask); 344 int ucdata_reload (char *paths, int mask); 345 346 #ifdef UCDATA_DEPRECATED 347 /* 348 * Deprecated functions, now just compatibility macros. 349 */ 350 #define ucdata_setup(p) ucdata_load(p, UCDATA_ALL) 351 #define ucdata_cleanup() ucdata_unload(UCDATA_ALL) 352 #endif 353 354 #endif /* _h_ucdata */ 355