1/* $OpenLDAP$ */ 2/* This work is part of OpenLDAP Software <http://www.openldap.org/>. 3 * 4 * Copyright 1998-2011 The OpenLDAP Foundation. 5 * All rights reserved. 6 * 7 * Redistribution and use in source and binary forms, with or without 8 * modification, are permitted only as authorized by the OpenLDAP 9 * Public License. 10 * 11 * A copy of this license is available in file LICENSE in the 12 * top-level directory of the distribution or, alternatively, at 13 * <http://www.OpenLDAP.org/license.html>. 14 */ 15/* Copyright 2001 Computing Research Labs, New Mexico State University 16 * 17 * Permission is hereby granted, free of charge, to any person obtaining a 18 * copy of this software and associated documentation files (the "Software"), 19 * to deal in the Software without restriction, including without limitation 20 * the rights to use, copy, modify, merge, publish, distribute, sublicense, 21 * and/or sell copies of the Software, and to permit persons to whom the 22 * Software is furnished to do so, subject to the following conditions: 23 * 24 * The above copyright notice and this permission notice shall be included in 25 * all copies or substantial portions of the Software. 26 * 27 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 28 * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 29 * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 30 * THE COMPUTING RESEARCH LAB OR NEW MEXICO STATE UNIVERSITY BE LIABLE FOR ANY 31 * CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT 32 * OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR 33 * THE USE OR OTHER DEALINGS IN THE SOFTWARE. 34 */ 35/* $Id: ucdata.h,v 1.6 2001/01/02 18:46:20 mleisher Exp $ */ 36 37#ifndef _h_ucdata 38#define _h_ucdata 39 40LDAP_BEGIN_DECL 41 42#define UCDATA_VERSION "2.4" 43 44/************************************************************************** 45 * 46 * Masks and macros for character properties. 47 * 48 **************************************************************************/ 49 50/* 51 * Values that can appear in the `mask1' parameter of the ucisprop() 52 * function. 53 */ 54#define UC_MN 0x00000001 /* Mark, Non-Spacing */ 55#define UC_MC 0x00000002 /* Mark, Spacing Combining */ 56#define UC_ME 0x00000004 /* Mark, Enclosing */ 57#define UC_ND 0x00000008 /* Number, Decimal Digit */ 58#define UC_NL 0x00000010 /* Number, Letter */ 59#define UC_NO 0x00000020 /* Number, Other */ 60#define UC_ZS 0x00000040 /* Separator, Space */ 61#define UC_ZL 0x00000080 /* Separator, Line */ 62#define UC_ZP 0x00000100 /* Separator, Paragraph */ 63#define UC_CC 0x00000200 /* Other, Control */ 64#define UC_CF 0x00000400 /* Other, Format */ 65#define UC_OS 0x00000800 /* Other, Surrogate */ 66#define UC_CO 0x00001000 /* Other, Private Use */ 67#define UC_CN 0x00002000 /* Other, Not Assigned */ 68#define UC_LU 0x00004000 /* Letter, Uppercase */ 69#define UC_LL 0x00008000 /* Letter, Lowercase */ 70#define UC_LT 0x00010000 /* Letter, Titlecase */ 71#define UC_LM 0x00020000 /* Letter, Modifier */ 72#define UC_LO 0x00040000 /* Letter, Other */ 73#define UC_PC 0x00080000 /* Punctuation, Connector */ 74#define UC_PD 0x00100000 /* Punctuation, Dash */ 75#define UC_PS 0x00200000 /* Punctuation, Open */ 76#define UC_PE 0x00400000 /* Punctuation, Close */ 77#define UC_PO 0x00800000 /* Punctuation, Other */ 78#define UC_SM 0x01000000 /* Symbol, Math */ 79#define UC_SC 0x02000000 /* Symbol, Currency */ 80#define UC_SK 0x04000000 /* Symbol, Modifier */ 81#define UC_SO 0x08000000 /* Symbol, Other */ 82#define UC_L 0x10000000 /* Left-To-Right */ 83#define UC_R 0x20000000 /* Right-To-Left */ 84#define UC_EN 0x40000000 /* European Number */ 85#define UC_ES 0x80000000 /* European Number Separator */ 86 87/* 88 * Values that can appear in the `mask2' parameter of the ucisprop() 89 * function. 90 */ 91#define UC_ET 0x00000001 /* European Number Terminator */ 92#define UC_AN 0x00000002 /* Arabic Number */ 93#define UC_CS 0x00000004 /* Common Number Separator */ 94#define UC_B 0x00000008 /* Block Separator */ 95#define UC_S 0x00000010 /* Segment Separator */ 96#define UC_WS 0x00000020 /* Whitespace */ 97#define UC_ON 0x00000040 /* Other Neutrals */ 98/* 99 * Implementation specific character properties. 100 */ 101#define UC_CM 0x00000080 /* Composite */ 102#define UC_NB 0x00000100 /* Non-Breaking */ 103#define UC_SY 0x00000200 /* Symmetric */ 104#define UC_HD 0x00000400 /* Hex Digit */ 105#define UC_QM 0x00000800 /* Quote Mark */ 106#define UC_MR 0x00001000 /* Mirroring */ 107#define UC_SS 0x00002000 /* Space, other */ 108 109#define UC_CP 0x00004000 /* Defined */ 110 111/* 112 * Added for UnicodeData-2.1.3. 113 */ 114#define UC_PI 0x00008000 /* Punctuation, Initial */ 115#define UC_PF 0x00010000 /* Punctuation, Final */ 116 117/* 118 * This is the primary function for testing to see if a character has some set 119 * of properties. The macros that test for various character properties all 120 * call this function with some set of masks. 121 */ 122LDAP_LUNICODE_F (int) 123ucisprop LDAP_P((ac_uint4 code, ac_uint4 mask1, ac_uint4 mask2)); 124 125#define ucisalpha(cc) ucisprop(cc, UC_LU|UC_LL|UC_LM|UC_LO|UC_LT, 0) 126#define ucisdigit(cc) ucisprop(cc, UC_ND, 0) 127#define ucisalnum(cc) ucisprop(cc, UC_LU|UC_LL|UC_LM|UC_LO|UC_LT|UC_ND, 0) 128#define uciscntrl(cc) ucisprop(cc, UC_CC|UC_CF, 0) 129#define ucisspace(cc) ucisprop(cc, UC_ZS|UC_SS, 0) 130#define ucisblank(cc) ucisprop(cc, UC_ZS, 0) 131#define ucispunct(cc) ucisprop(cc, UC_PD|UC_PS|UC_PE|UC_PO, UC_PI|UC_PF) 132#define ucisgraph(cc) ucisprop(cc, UC_MN|UC_MC|UC_ME|UC_ND|UC_NL|UC_NO|\ 133 UC_LU|UC_LL|UC_LT|UC_LM|UC_LO|UC_PC|UC_PD|\ 134 UC_PS|UC_PE|UC_PO|UC_SM|UC_SM|UC_SC|UC_SK|\ 135 UC_SO, UC_PI|UC_PF) 136#define ucisprint(cc) ucisprop(cc, UC_MN|UC_MC|UC_ME|UC_ND|UC_NL|UC_NO|\ 137 UC_LU|UC_LL|UC_LT|UC_LM|UC_LO|UC_PC|UC_PD|\ 138 UC_PS|UC_PE|UC_PO|UC_SM|UC_SM|UC_SC|UC_SK|\ 139 UC_SO|UC_ZS, UC_PI|UC_PF) 140#define ucisupper(cc) ucisprop(cc, UC_LU, 0) 141#define ucislower(cc) ucisprop(cc, UC_LL, 0) 142#define ucistitle(cc) ucisprop(cc, UC_LT, 0) 143#define ucisxdigit(cc) ucisprop(cc, 0, UC_HD) 144 145#define ucisisocntrl(cc) ucisprop(cc, UC_CC, 0) 146#define ucisfmtcntrl(cc) ucisprop(cc, UC_CF, 0) 147 148#define ucissymbol(cc) ucisprop(cc, UC_SM|UC_SC|UC_SO|UC_SK, 0) 149#define ucisnumber(cc) ucisprop(cc, UC_ND|UC_NO|UC_NL, 0) 150#define ucisnonspacing(cc) ucisprop(cc, UC_MN, 0) 151#define ucisopenpunct(cc) ucisprop(cc, UC_PS, 0) 152#define ucisclosepunct(cc) ucisprop(cc, UC_PE, 0) 153#define ucisinitialpunct(cc) ucisprop(cc, 0, UC_PI) 154#define ucisfinalpunct(cc) ucisprop(cc, 0, UC_PF) 155 156#define uciscomposite(cc) ucisprop(cc, 0, UC_CM) 157#define ucishex(cc) ucisprop(cc, 0, UC_HD) 158#define ucisquote(cc) ucisprop(cc, 0, UC_QM) 159#define ucissymmetric(cc) ucisprop(cc, 0, UC_SY) 160#define ucismirroring(cc) ucisprop(cc, 0, UC_MR) 161#define ucisnonbreaking(cc) ucisprop(cc, 0, UC_NB) 162 163/* 164 * Directionality macros. 165 */ 166#define ucisrtl(cc) ucisprop(cc, UC_R, 0) 167#define ucisltr(cc) ucisprop(cc, UC_L, 0) 168#define ucisstrong(cc) ucisprop(cc, UC_L|UC_R, 0) 169#define ucisweak(cc) ucisprop(cc, UC_EN|UC_ES, UC_ET|UC_AN|UC_CS) 170#define ucisneutral(cc) ucisprop(cc, 0, UC_B|UC_S|UC_WS|UC_ON) 171#define ucisseparator(cc) ucisprop(cc, 0, UC_B|UC_S) 172 173/* 174 * Other macros inspired by John Cowan. 175 */ 176#define ucismark(cc) ucisprop(cc, UC_MN|UC_MC|UC_ME, 0) 177#define ucismodif(cc) ucisprop(cc, UC_LM, 0) 178#define ucisletnum(cc) ucisprop(cc, UC_NL, 0) 179#define ucisconnect(cc) ucisprop(cc, UC_PC, 0) 180#define ucisdash(cc) ucisprop(cc, UC_PD, 0) 181#define ucismath(cc) ucisprop(cc, UC_SM, 0) 182#define uciscurrency(cc) ucisprop(cc, UC_SC, 0) 183#define ucismodifsymbol(cc) ucisprop(cc, UC_SK, 0) 184#define ucisnsmark(cc) ucisprop(cc, UC_MN, 0) 185#define ucisspmark(cc) ucisprop(cc, UC_MC, 0) 186#define ucisenclosing(cc) ucisprop(cc, UC_ME, 0) 187#define ucisprivate(cc) ucisprop(cc, UC_CO, 0) 188#define ucissurrogate(cc) ucisprop(cc, UC_OS, 0) 189#define ucislsep(cc) ucisprop(cc, UC_ZL, 0) 190#define ucispsep(cc) ucisprop(cc, UC_ZP, 0) 191 192#define ucisidentstart(cc) ucisprop(cc, UC_LU|UC_LL|UC_LT|UC_LO|UC_NL, 0) 193#define ucisidentpart(cc) ucisprop(cc, UC_LU|UC_LL|UC_LT|UC_LO|UC_NL|\ 194 UC_MN|UC_MC|UC_ND|UC_PC|UC_CF, 0) 195 196#define ucisdefined(cc) ucisprop(cc, 0, UC_CP) 197#define ucisundefined(cc) !ucisprop(cc, 0, UC_CP) 198 199/* 200 * Other miscellaneous character property macros. 201 */ 202#define ucishan(cc) (((cc) >= 0x4e00 && (cc) <= 0x9fff) ||\ 203 ((cc) >= 0xf900 && (cc) <= 0xfaff)) 204#define ucishangul(cc) ((cc) >= 0xac00 && (cc) <= 0xd7ff) 205 206/************************************************************************** 207 * 208 * Functions for case conversion. 209 * 210 **************************************************************************/ 211 212LDAP_LUNICODE_F (ac_uint4) uctoupper LDAP_P((ac_uint4 code)); 213LDAP_LUNICODE_F (ac_uint4) uctolower LDAP_P((ac_uint4 code)); 214LDAP_LUNICODE_F (ac_uint4) uctotitle LDAP_P((ac_uint4 code)); 215 216/************************************************************************** 217 * 218 * Functions for getting compositions. 219 * 220 **************************************************************************/ 221 222/* 223 * This routine determines if there exists a composition of node1 and node2. 224 * If it returns 0, there is no composition. Any other value indicates a 225 * composition was returned in comp. 226 */ 227LDAP_LUNICODE_F (int) uccomp LDAP_P((ac_uint4 node1, ac_uint4 node2, 228 ac_uint4 *comp)); 229 230/* 231 * Does Hangul composition on the string str with length len, and returns 232 * the length of the composed string. 233 */ 234LDAP_LUNICODE_F (int) uccomp_hangul LDAP_P((ac_uint4 *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 */ 240LDAP_LUNICODE_F (int) uccanoncomp LDAP_P((ac_uint4 *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 */ 253LDAP_LUNICODE_F (int) 254ucdecomp LDAP_P((ac_uint4 code, ac_uint4 *num, 255 ac_uint4 **decomp)); 256 257/* 258 * Equivalent to ucdecomp() except that it includes compatibility 259 * decompositions. 260 */ 261LDAP_LUNICODE_F (int) 262uckdecomp LDAP_P((ac_uint4 code, ac_uint4 *num, 263 ac_uint4 **decomp)); 264 265/* 266 * If the code is a Hangul syllable, this routine decomposes it into the array 267 * passed. The array size should be at least 3. 268 */ 269LDAP_LUNICODE_F (int) 270ucdecomp_hangul LDAP_P((ac_uint4 code, ac_uint4 *num, 271 ac_uint4 decomp[])); 272 273/* 274 * This routine does canonical decomposition of the string in of length 275 * inlen, and returns the decomposed string in out with length outlen. 276 * The memory for out is allocated by this routine. It returns the length 277 * of the decomposed string if okay, and -1 on error. 278 */ 279LDAP_LUNICODE_F (int) 280uccanondecomp LDAP_P((const ac_uint4 *in, int inlen, 281 ac_uint4 **out, int *outlen, void *ctx)); 282 283/* 284 * Equivalent to uccanondecomp() except that it includes compatibility 285 * decompositions. 286 */ 287LDAP_LUNICODE_F (int) 288uccompatdecomp LDAP_P((const ac_uint4 *in, int inlen, 289 ac_uint4 **out, int *outlen, void *ctx)); 290 291/************************************************************************** 292 * 293 * Functions for getting combining classes. 294 * 295 **************************************************************************/ 296 297/* 298 * This will return the combining class for a character to be used with the 299 * Canonical Ordering algorithm. 300 */ 301LDAP_LUNICODE_F (ac_uint4) uccombining_class LDAP_P((ac_uint4 code)); 302 303/************************************************************************** 304 * 305 * Functions for getting numbers and digits. 306 * 307 **************************************************************************/ 308 309struct ucnumber { 310 int numerator; 311 int denominator; 312}; 313 314LDAP_LUNICODE_F (int) 315ucnumber_lookup LDAP_P((ac_uint4 code, struct ucnumber *num)); 316 317LDAP_LUNICODE_F (int) 318ucdigit_lookup LDAP_P((ac_uint4 code, int *digit)); 319 320/* 321 * For compatibility with John Cowan's "uctype" package. 322 */ 323LDAP_LUNICODE_F (struct ucnumber) ucgetnumber LDAP_P((ac_uint4 code)); 324LDAP_LUNICODE_F (int) ucgetdigit LDAP_P((ac_uint4 code)); 325 326/************************************************************************** 327 * 328 * Functions library initialization and cleanup. 329 * 330 **************************************************************************/ 331 332/* 333 * Macros for specifying the data tables to be loaded, unloaded, or reloaded 334 * by the ucdata_load(), ucdata_unload(), and ucdata_reload() routines. 335 */ 336#define UCDATA_CASE 0x01 337#define UCDATA_CTYPE 0x02 338#define UCDATA_DECOMP 0x04 339#define UCDATA_CMBCL 0x08 340#define UCDATA_NUM 0x10 341#define UCDATA_COMP 0x20 342#define UCDATA_KDECOMP 0x40 343 344#define UCDATA_ALL (UCDATA_CASE|UCDATA_CTYPE|UCDATA_DECOMP|\ 345 UCDATA_CMBCL|UCDATA_NUM|UCDATA_COMP|UCDATA_KDECOMP) 346 347/* 348 * Functions to load, unload, and reload specific data files. 349 */ 350LDAP_LUNICODE_F (int) ucdata_load LDAP_P((char *paths, int mask)); 351LDAP_LUNICODE_F (void) ucdata_unload LDAP_P((int mask)); 352LDAP_LUNICODE_F (int) ucdata_reload LDAP_P((char *paths, int mask)); 353 354#ifdef UCDATA_DEPRECATED 355/* 356 * Deprecated functions, now just compatibility macros. 357 */ 358#define ucdata_setup(p) ucdata_load(p, UCDATA_ALL) 359#define ucdata_cleanup() ucdata_unload(UCDATA_ALL) 360#endif 361 362LDAP_END_DECL 363 364#endif /* _h_ucdata */ 365