| 1 | /* |
| 2 | ******************************************************************************** |
| 3 | * Copyright (C) 1996-2014, International Business Machines |
| 4 | * Corporation and others. All Rights Reserved. |
| 5 | ******************************************************************************** |
| 6 | * |
| 7 | * File UCHAR.C |
| 8 | * |
| 9 | * Modification History: |
| 10 | * |
| 11 | * Date Name Description |
| 12 | * 04/02/97 aliu Creation. |
| 13 | * 4/15/99 Madhu Updated all the function definitions for C Implementation |
| 14 | * 5/20/99 Madhu Added the function u_getVersion() |
| 15 | * 8/19/1999 srl Upgraded scripts to Unicode3.0 |
| 16 | * 11/11/1999 weiv added u_isalnum(), cleaned comments |
| 17 | * 01/11/2000 helena Renamed u_getVersion to u_getUnicodeVersion. |
| 18 | * 06/20/2000 helena OS/400 port changes; mostly typecast. |
| 19 | ****************************************************************************** |
| 20 | */ |
| 21 | |
| 22 | #include "unicode/utypes.h" |
| 23 | #include "unicode/uchar.h" |
| 24 | #include "unicode/uscript.h" |
| 25 | #include "unicode/udata.h" |
| 26 | #include "uassert.h" |
| 27 | #include "cmemory.h" |
| 28 | #include "ucln_cmn.h" |
| 29 | #include "utrie2.h" |
| 30 | #include "udataswp.h" |
| 31 | #include "uprops.h" |
| 32 | #include "ustr_imp.h" |
| 33 | |
| 34 | /* uchar_props_data.h is machine-generated by genprops --csource */ |
| 35 | #define INCLUDED_FROM_UCHAR_C |
| 36 | #include "uchar_props_data.h" |
| 37 | |
| 38 | /* constants and macros for access to the data ------------------------------ */ |
| 39 | |
| 40 | /* getting a uint32_t properties word from the data */ |
| 41 | #define GET_PROPS(c, result) ((result)=UTRIE2_GET16(&propsTrie, c)); |
| 42 | |
| 43 | U_CFUNC UBool |
| 44 | uprv_haveProperties(UErrorCode *pErrorCode) { |
| 45 | if(U_FAILURE(*pErrorCode)) { |
| 46 | return FALSE; |
| 47 | } |
| 48 | return TRUE; |
| 49 | } |
| 50 | |
| 51 | /* API functions ------------------------------------------------------------ */ |
| 52 | |
| 53 | /* Gets the Unicode character's general category.*/ |
| 54 | U_CAPI int8_t U_EXPORT2 |
| 55 | u_charType(UChar32 c) { |
| 56 | uint32_t props; |
| 57 | GET_PROPS(c, props); |
| 58 | return (int8_t)GET_CATEGORY(props); |
| 59 | } |
| 60 | |
| 61 | /* Enumerate all code points with their general categories. */ |
| 62 | struct _EnumTypeCallback { |
| 63 | UCharEnumTypeRange *enumRange; |
| 64 | const void *context; |
| 65 | }; |
| 66 | |
| 67 | static uint32_t U_CALLCONV |
| 68 | _enumTypeValue(const void *context, uint32_t value) { |
| 69 | return GET_CATEGORY(value); |
| 70 | } |
| 71 | |
| 72 | static UBool U_CALLCONV |
| 73 | _enumTypeRange(const void *context, UChar32 start, UChar32 end, uint32_t value) { |
| 74 | /* just cast the value to UCharCategory */ |
| 75 | return ((struct _EnumTypeCallback *)context)-> |
| 76 | enumRange(((struct _EnumTypeCallback *)context)->context, |
| 77 | start, end+1, (UCharCategory)value); |
| 78 | } |
| 79 | |
| 80 | U_CAPI void U_EXPORT2 |
| 81 | u_enumCharTypes(UCharEnumTypeRange *enumRange, const void *context) { |
| 82 | struct _EnumTypeCallback callback; |
| 83 | |
| 84 | if(enumRange==NULL) { |
| 85 | return; |
| 86 | } |
| 87 | |
| 88 | callback.enumRange=enumRange; |
| 89 | callback.context=context; |
| 90 | utrie2_enum(&propsTrie, _enumTypeValue, _enumTypeRange, &callback); |
| 91 | } |
| 92 | |
| 93 | /* Checks if ch is a lower case letter.*/ |
| 94 | U_CAPI UBool U_EXPORT2 |
| 95 | u_islower(UChar32 c) { |
| 96 | uint32_t props; |
| 97 | GET_PROPS(c, props); |
| 98 | return (UBool)(GET_CATEGORY(props)==U_LOWERCASE_LETTER); |
| 99 | } |
| 100 | |
| 101 | /* Checks if ch is an upper case letter.*/ |
| 102 | U_CAPI UBool U_EXPORT2 |
| 103 | u_isupper(UChar32 c) { |
| 104 | uint32_t props; |
| 105 | GET_PROPS(c, props); |
| 106 | return (UBool)(GET_CATEGORY(props)==U_UPPERCASE_LETTER); |
| 107 | } |
| 108 | |
| 109 | /* Checks if ch is a title case letter; usually upper case letters.*/ |
| 110 | U_CAPI UBool U_EXPORT2 |
| 111 | u_istitle(UChar32 c) { |
| 112 | uint32_t props; |
| 113 | GET_PROPS(c, props); |
| 114 | return (UBool)(GET_CATEGORY(props)==U_TITLECASE_LETTER); |
| 115 | } |
| 116 | |
| 117 | /* Checks if ch is a decimal digit. */ |
| 118 | U_CAPI UBool U_EXPORT2 |
| 119 | u_isdigit(UChar32 c) { |
| 120 | uint32_t props; |
| 121 | GET_PROPS(c, props); |
| 122 | return (UBool)(GET_CATEGORY(props)==U_DECIMAL_DIGIT_NUMBER); |
| 123 | } |
| 124 | |
| 125 | U_CAPI UBool U_EXPORT2 |
| 126 | u_isxdigit(UChar32 c) { |
| 127 | uint32_t props; |
| 128 | |
| 129 | /* check ASCII and Fullwidth ASCII a-fA-F */ |
| 130 | if( |
| 131 | (c<=0x66 && c>=0x41 && (c<=0x46 || c>=0x61)) || |
| 132 | (c>=0xff21 && c<=0xff46 && (c<=0xff26 || c>=0xff41)) |
| 133 | ) { |
| 134 | return TRUE; |
| 135 | } |
| 136 | |
| 137 | GET_PROPS(c, props); |
| 138 | return (UBool)(GET_CATEGORY(props)==U_DECIMAL_DIGIT_NUMBER); |
| 139 | } |
| 140 | |
| 141 | /* Checks if the Unicode character is a letter.*/ |
| 142 | U_CAPI UBool U_EXPORT2 |
| 143 | u_isalpha(UChar32 c) { |
| 144 | uint32_t props; |
| 145 | GET_PROPS(c, props); |
| 146 | return (UBool)((CAT_MASK(props)&U_GC_L_MASK)!=0); |
| 147 | } |
| 148 | |
| 149 | U_CAPI UBool U_EXPORT2 |
| 150 | u_isUAlphabetic(UChar32 c) { |
| 151 | return (u_getUnicodeProperties(c, 1)&U_MASK(UPROPS_ALPHABETIC))!=0; |
| 152 | } |
| 153 | |
| 154 | /* Checks if c is a letter or a decimal digit */ |
| 155 | U_CAPI UBool U_EXPORT2 |
| 156 | u_isalnum(UChar32 c) { |
| 157 | uint32_t props; |
| 158 | GET_PROPS(c, props); |
| 159 | return (UBool)((CAT_MASK(props)&(U_GC_L_MASK|U_GC_ND_MASK))!=0); |
| 160 | } |
| 161 | |
| 162 | /** |
| 163 | * Checks if c is alphabetic, or a decimal digit; implements UCHAR_POSIX_ALNUM. |
| 164 | * @internal |
| 165 | */ |
| 166 | U_CFUNC UBool |
| 167 | u_isalnumPOSIX(UChar32 c) { |
| 168 | return (UBool)(u_isUAlphabetic(c) || u_isdigit(c)); |
| 169 | } |
| 170 | |
| 171 | /* Checks if ch is a unicode character with assigned character type.*/ |
| 172 | U_CAPI UBool U_EXPORT2 |
| 173 | u_isdefined(UChar32 c) { |
| 174 | uint32_t props; |
| 175 | GET_PROPS(c, props); |
| 176 | return (UBool)(GET_CATEGORY(props)!=0); |
| 177 | } |
| 178 | |
| 179 | /* Checks if the Unicode character is a base form character that can take a diacritic.*/ |
| 180 | U_CAPI UBool U_EXPORT2 |
| 181 | u_isbase(UChar32 c) { |
| 182 | uint32_t props; |
| 183 | GET_PROPS(c, props); |
| 184 | return (UBool)((CAT_MASK(props)&(U_GC_L_MASK|U_GC_N_MASK|U_GC_MC_MASK|U_GC_ME_MASK))!=0); |
| 185 | } |
| 186 | |
| 187 | /* Checks if the Unicode character is a control character.*/ |
| 188 | U_CAPI UBool U_EXPORT2 |
| 189 | u_iscntrl(UChar32 c) { |
| 190 | uint32_t props; |
| 191 | GET_PROPS(c, props); |
| 192 | return (UBool)((CAT_MASK(props)&(U_GC_CC_MASK|U_GC_CF_MASK|U_GC_ZL_MASK|U_GC_ZP_MASK))!=0); |
| 193 | } |
| 194 | |
| 195 | U_CAPI UBool U_EXPORT2 |
| 196 | u_isISOControl(UChar32 c) { |
| 197 | return (uint32_t)c<=0x9f && (c<=0x1f || c>=0x7f); |
| 198 | } |
| 199 | |
| 200 | /* Some control characters that are used as space. */ |
| 201 | #define IS_THAT_CONTROL_SPACE(c) \ |
| 202 | (c<=0x9f && ((c>=TAB && c<=CR) || (c>=0x1c && c <=0x1f) || c==NL)) |
| 203 | |
| 204 | /* Java has decided that U+0085 New Line is not whitespace any more. */ |
| 205 | #define IS_THAT_ASCII_CONTROL_SPACE(c) \ |
| 206 | (c<=0x1f && c>=TAB && (c<=CR || c>=0x1c)) |
| 207 | |
| 208 | /* Checks if the Unicode character is a space character.*/ |
| 209 | U_CAPI UBool U_EXPORT2 |
| 210 | u_isspace(UChar32 c) { |
| 211 | uint32_t props; |
| 212 | GET_PROPS(c, props); |
| 213 | return (UBool)((CAT_MASK(props)&U_GC_Z_MASK)!=0 || IS_THAT_CONTROL_SPACE(c)); |
| 214 | } |
| 215 | |
| 216 | U_CAPI UBool U_EXPORT2 |
| 217 | u_isJavaSpaceChar(UChar32 c) { |
| 218 | uint32_t props; |
| 219 | GET_PROPS(c, props); |
| 220 | return (UBool)((CAT_MASK(props)&U_GC_Z_MASK)!=0); |
| 221 | } |
| 222 | |
| 223 | /* Checks if the Unicode character is a whitespace character.*/ |
| 224 | U_CAPI UBool U_EXPORT2 |
| 225 | u_isWhitespace(UChar32 c) { |
| 226 | uint32_t props; |
| 227 | GET_PROPS(c, props); |
| 228 | return (UBool)( |
| 229 | ((CAT_MASK(props)&U_GC_Z_MASK)!=0 && |
| 230 | c!=NBSP && c!=FIGURESP && c!=NNBSP) || /* exclude no-break spaces */ |
| 231 | IS_THAT_ASCII_CONTROL_SPACE(c) |
| 232 | ); |
| 233 | } |
| 234 | |
| 235 | U_CAPI UBool U_EXPORT2 |
| 236 | u_isblank(UChar32 c) { |
| 237 | if((uint32_t)c<=0x9f) { |
| 238 | return c==9 || c==0x20; /* TAB or SPACE */ |
| 239 | } else { |
| 240 | /* Zs */ |
| 241 | uint32_t props; |
| 242 | GET_PROPS(c, props); |
| 243 | return (UBool)(GET_CATEGORY(props)==U_SPACE_SEPARATOR); |
| 244 | } |
| 245 | } |
| 246 | |
| 247 | U_CAPI UBool U_EXPORT2 |
| 248 | u_isUWhiteSpace(UChar32 c) { |
| 249 | return (u_getUnicodeProperties(c, 1)&U_MASK(UPROPS_WHITE_SPACE))!=0; |
| 250 | } |
| 251 | |
| 252 | /* Checks if the Unicode character is printable.*/ |
| 253 | U_CAPI UBool U_EXPORT2 |
| 254 | u_isprint(UChar32 c) { |
| 255 | uint32_t props; |
| 256 | GET_PROPS(c, props); |
| 257 | /* comparing ==0 returns FALSE for the categories mentioned */ |
| 258 | return (UBool)((CAT_MASK(props)&U_GC_C_MASK)==0); |
| 259 | } |
| 260 | |
| 261 | /** |
| 262 | * Checks if c is in \p{graph}\p{blank} - \p{cntrl}. |
| 263 | * Implements UCHAR_POSIX_PRINT. |
| 264 | * @internal |
| 265 | */ |
| 266 | U_CFUNC UBool |
| 267 | u_isprintPOSIX(UChar32 c) { |
| 268 | uint32_t props; |
| 269 | GET_PROPS(c, props); |
| 270 | /* |
| 271 | * The only cntrl character in graph+blank is TAB (in blank). |
| 272 | * Here we implement (blank-TAB)=Zs instead of calling u_isblank(). |
| 273 | */ |
| 274 | return (UBool)((GET_CATEGORY(props)==U_SPACE_SEPARATOR) || u_isgraphPOSIX(c)); |
| 275 | } |
| 276 | |
| 277 | U_CAPI UBool U_EXPORT2 |
| 278 | u_isgraph(UChar32 c) { |
| 279 | uint32_t props; |
| 280 | GET_PROPS(c, props); |
| 281 | /* comparing ==0 returns FALSE for the categories mentioned */ |
| 282 | return (UBool)((CAT_MASK(props)& |
| 283 | (U_GC_CC_MASK|U_GC_CF_MASK|U_GC_CS_MASK|U_GC_CN_MASK|U_GC_Z_MASK)) |
| 284 | ==0); |
| 285 | } |
| 286 | |
| 287 | /** |
| 288 | * Checks if c is in |
| 289 | * [^\p{space}\p{gc=Control}\p{gc=Surrogate}\p{gc=Unassigned}] |
| 290 | * with space=\p{Whitespace} and Control=Cc. |
| 291 | * Implements UCHAR_POSIX_GRAPH. |
| 292 | * @internal |
| 293 | */ |
| 294 | U_CFUNC UBool |
| 295 | u_isgraphPOSIX(UChar32 c) { |
| 296 | uint32_t props; |
| 297 | GET_PROPS(c, props); |
| 298 | /* \p{space}\p{gc=Control} == \p{gc=Z}\p{Control} */ |
| 299 | /* comparing ==0 returns FALSE for the categories mentioned */ |
| 300 | return (UBool)((CAT_MASK(props)& |
| 301 | (U_GC_CC_MASK|U_GC_CS_MASK|U_GC_CN_MASK|U_GC_Z_MASK)) |
| 302 | ==0); |
| 303 | } |
| 304 | |
| 305 | U_CAPI UBool U_EXPORT2 |
| 306 | u_ispunct(UChar32 c) { |
| 307 | uint32_t props; |
| 308 | GET_PROPS(c, props); |
| 309 | return (UBool)((CAT_MASK(props)&U_GC_P_MASK)!=0); |
| 310 | } |
| 311 | |
| 312 | /* Checks if the Unicode character can start a Unicode identifier.*/ |
| 313 | U_CAPI UBool U_EXPORT2 |
| 314 | u_isIDStart(UChar32 c) { |
| 315 | /* same as u_isalpha() */ |
| 316 | uint32_t props; |
| 317 | GET_PROPS(c, props); |
| 318 | return (UBool)((CAT_MASK(props)&(U_GC_L_MASK|U_GC_NL_MASK))!=0); |
| 319 | } |
| 320 | |
| 321 | /* Checks if the Unicode character can be a Unicode identifier part other than starting the |
| 322 | identifier.*/ |
| 323 | U_CAPI UBool U_EXPORT2 |
| 324 | u_isIDPart(UChar32 c) { |
| 325 | uint32_t props; |
| 326 | GET_PROPS(c, props); |
| 327 | return (UBool)( |
| 328 | (CAT_MASK(props)& |
| 329 | (U_GC_ND_MASK|U_GC_NL_MASK| |
| 330 | U_GC_L_MASK| |
| 331 | U_GC_PC_MASK|U_GC_MC_MASK|U_GC_MN_MASK) |
| 332 | )!=0 || |
| 333 | u_isIDIgnorable(c)); |
| 334 | } |
| 335 | |
| 336 | /*Checks if the Unicode character can be ignorable in a Java or Unicode identifier.*/ |
| 337 | U_CAPI UBool U_EXPORT2 |
| 338 | u_isIDIgnorable(UChar32 c) { |
| 339 | if(c<=0x9f) { |
| 340 | return u_isISOControl(c) && !IS_THAT_ASCII_CONTROL_SPACE(c); |
| 341 | } else { |
| 342 | uint32_t props; |
| 343 | GET_PROPS(c, props); |
| 344 | return (UBool)(GET_CATEGORY(props)==U_FORMAT_CHAR); |
| 345 | } |
| 346 | } |
| 347 | |
| 348 | /*Checks if the Unicode character can start a Java identifier.*/ |
| 349 | U_CAPI UBool U_EXPORT2 |
| 350 | u_isJavaIDStart(UChar32 c) { |
| 351 | uint32_t props; |
| 352 | GET_PROPS(c, props); |
| 353 | return (UBool)((CAT_MASK(props)&(U_GC_L_MASK|U_GC_SC_MASK|U_GC_PC_MASK))!=0); |
| 354 | } |
| 355 | |
| 356 | /*Checks if the Unicode character can be a Java identifier part other than starting the |
| 357 | * identifier. |
| 358 | */ |
| 359 | U_CAPI UBool U_EXPORT2 |
| 360 | u_isJavaIDPart(UChar32 c) { |
| 361 | uint32_t props; |
| 362 | GET_PROPS(c, props); |
| 363 | return (UBool)( |
| 364 | (CAT_MASK(props)& |
| 365 | (U_GC_ND_MASK|U_GC_NL_MASK| |
| 366 | U_GC_L_MASK| |
| 367 | U_GC_SC_MASK|U_GC_PC_MASK| |
| 368 | U_GC_MC_MASK|U_GC_MN_MASK) |
| 369 | )!=0 || |
| 370 | u_isIDIgnorable(c)); |
| 371 | } |
| 372 | |
| 373 | U_CAPI int32_t U_EXPORT2 |
| 374 | u_charDigitValue(UChar32 c) { |
| 375 | uint32_t props; |
| 376 | int32_t value; |
| 377 | GET_PROPS(c, props); |
| 378 | value=(int32_t)GET_NUMERIC_TYPE_VALUE(props)-UPROPS_NTV_DECIMAL_START; |
| 379 | if(value<=9) { |
| 380 | return value; |
| 381 | } else { |
| 382 | return -1; |
| 383 | } |
| 384 | } |
| 385 | |
| 386 | U_CAPI double U_EXPORT2 |
| 387 | u_getNumericValue(UChar32 c) { |
| 388 | uint32_t props; |
| 389 | int32_t ntv; |
| 390 | GET_PROPS(c, props); |
| 391 | ntv=(int32_t)GET_NUMERIC_TYPE_VALUE(props); |
| 392 | |
| 393 | if(ntv==UPROPS_NTV_NONE) { |
| 394 | return U_NO_NUMERIC_VALUE; |
| 395 | } else if(ntv<UPROPS_NTV_DIGIT_START) { |
| 396 | /* decimal digit */ |
| 397 | return ntv-UPROPS_NTV_DECIMAL_START; |
| 398 | } else if(ntv<UPROPS_NTV_NUMERIC_START) { |
| 399 | /* other digit */ |
| 400 | return ntv-UPROPS_NTV_DIGIT_START; |
| 401 | } else if(ntv<UPROPS_NTV_FRACTION_START) { |
| 402 | /* small integer */ |
| 403 | return ntv-UPROPS_NTV_NUMERIC_START; |
| 404 | } else if(ntv<UPROPS_NTV_LARGE_START) { |
| 405 | /* fraction */ |
| 406 | int32_t numerator=(ntv>>4)-12; |
| 407 | int32_t denominator=(ntv&0xf)+1; |
| 408 | return (double)numerator/denominator; |
| 409 | } else if(ntv<UPROPS_NTV_BASE60_START) { |
| 410 | /* large, single-significant-digit integer */ |
| 411 | double numValue; |
| 412 | int32_t mant=(ntv>>5)-14; |
| 413 | int32_t exp=(ntv&0x1f)+2; |
| 414 | numValue=mant; |
| 415 | |
| 416 | /* multiply by 10^exp without math.h */ |
| 417 | while(exp>=4) { |
| 418 | numValue*=10000.; |
| 419 | exp-=4; |
| 420 | } |
| 421 | switch(exp) { |
| 422 | case 3: |
| 423 | numValue*=1000.; |
| 424 | break; |
| 425 | case 2: |
| 426 | numValue*=100.; |
| 427 | break; |
| 428 | case 1: |
| 429 | numValue*=10.; |
| 430 | break; |
| 431 | case 0: |
| 432 | default: |
| 433 | break; |
| 434 | } |
| 435 | |
| 436 | return numValue; |
| 437 | } else if(ntv<UPROPS_NTV_RESERVED_START) { |
| 438 | /* sexagesimal (base 60) integer */ |
| 439 | int32_t numValue=(ntv>>2)-0xbf; |
| 440 | int32_t exp=(ntv&3)+1; |
| 441 | |
| 442 | switch(exp) { |
| 443 | case 4: |
| 444 | numValue*=60*60*60*60; |
| 445 | break; |
| 446 | case 3: |
| 447 | numValue*=60*60*60; |
| 448 | break; |
| 449 | case 2: |
| 450 | numValue*=60*60; |
| 451 | break; |
| 452 | case 1: |
| 453 | numValue*=60; |
| 454 | break; |
| 455 | case 0: |
| 456 | default: |
| 457 | break; |
| 458 | } |
| 459 | |
| 460 | return numValue; |
| 461 | } else { |
| 462 | /* reserved */ |
| 463 | return U_NO_NUMERIC_VALUE; |
| 464 | } |
| 465 | } |
| 466 | |
| 467 | U_CAPI int32_t U_EXPORT2 |
| 468 | u_digit(UChar32 ch, int8_t radix) { |
| 469 | int8_t value; |
| 470 | if((uint8_t)(radix-2)<=(36-2)) { |
| 471 | value=(int8_t)u_charDigitValue(ch); |
| 472 | if(value<0) { |
| 473 | /* ch is not a decimal digit, try latin letters */ |
| 474 | if(ch>=0x61 && ch<=0x7A) { |
| 475 | value=(int8_t)(ch-0x57); /* ch - 'a' + 10 */ |
| 476 | } else if(ch>=0x41 && ch<=0x5A) { |
| 477 | value=(int8_t)(ch-0x37); /* ch - 'A' + 10 */ |
| 478 | } else if(ch>=0xFF41 && ch<=0xFF5A) { |
| 479 | value=(int8_t)(ch-0xFF37); /* fullwidth ASCII a-z */ |
| 480 | } else if(ch>=0xFF21 && ch<=0xFF3A) { |
| 481 | value=(int8_t)(ch-0xFF17); /* fullwidth ASCII A-Z */ |
| 482 | } |
| 483 | } |
| 484 | } else { |
| 485 | value=-1; /* invalid radix */ |
| 486 | } |
| 487 | return (int8_t)((value<radix) ? value : -1); |
| 488 | } |
| 489 | |
| 490 | U_CAPI UChar32 U_EXPORT2 |
| 491 | u_forDigit(int32_t digit, int8_t radix) { |
| 492 | if((uint8_t)(radix-2)>(36-2) || (uint32_t)digit>=(uint32_t)radix) { |
| 493 | return 0; |
| 494 | } else if(digit<10) { |
| 495 | return (UChar32)(0x30+digit); |
| 496 | } else { |
| 497 | return (UChar32)((0x61-10)+digit); |
| 498 | } |
| 499 | } |
| 500 | |
| 501 | /* miscellaneous, and support for uprops.cpp -------------------------------- */ |
| 502 | |
| 503 | U_CAPI void U_EXPORT2 |
| 504 | u_getUnicodeVersion(UVersionInfo versionArray) { |
| 505 | if(versionArray!=NULL) { |
| 506 | uprv_memcpy(versionArray, dataVersion, U_MAX_VERSION_LENGTH); |
| 507 | } |
| 508 | } |
| 509 | |
| 510 | U_CFUNC uint32_t |
| 511 | u_getMainProperties(UChar32 c) { |
| 512 | uint32_t props; |
| 513 | GET_PROPS(c, props); |
| 514 | return props; |
| 515 | } |
| 516 | |
| 517 | U_CFUNC uint32_t |
| 518 | u_getUnicodeProperties(UChar32 c, int32_t column) { |
| 519 | U_ASSERT(column>=0); |
| 520 | if(column>=propsVectorsColumns) { |
| 521 | return 0; |
| 522 | } else { |
| 523 | uint16_t vecIndex=UTRIE2_GET16(&propsVectorsTrie, c); |
| 524 | return propsVectors[vecIndex+column]; |
| 525 | } |
| 526 | } |
| 527 | |
| 528 | U_CFUNC int32_t |
| 529 | uprv_getMaxValues(int32_t column) { |
| 530 | switch(column) { |
| 531 | case 0: |
| 532 | return indexes[UPROPS_MAX_VALUES_INDEX]; |
| 533 | case 2: |
| 534 | return indexes[UPROPS_MAX_VALUES_2_INDEX]; |
| 535 | default: |
| 536 | return 0; |
| 537 | } |
| 538 | } |
| 539 | |
| 540 | U_CAPI void U_EXPORT2 |
| 541 | u_charAge(UChar32 c, UVersionInfo versionArray) { |
| 542 | if(versionArray!=NULL) { |
| 543 | uint32_t version=u_getUnicodeProperties(c, 0)>>UPROPS_AGE_SHIFT; |
| 544 | versionArray[0]=(uint8_t)(version>>4); |
| 545 | versionArray[1]=(uint8_t)(version&0xf); |
| 546 | versionArray[2]=versionArray[3]=0; |
| 547 | } |
| 548 | } |
| 549 | |
| 550 | U_CAPI UScriptCode U_EXPORT2 |
| 551 | uscript_getScript(UChar32 c, UErrorCode *pErrorCode) { |
| 552 | uint32_t scriptX; |
| 553 | if(pErrorCode==NULL || U_FAILURE(*pErrorCode)) { |
| 554 | return USCRIPT_INVALID_CODE; |
| 555 | } |
| 556 | if((uint32_t)c>0x10ffff) { |
| 557 | *pErrorCode=U_ILLEGAL_ARGUMENT_ERROR; |
| 558 | return USCRIPT_INVALID_CODE; |
| 559 | } |
| 560 | scriptX=u_getUnicodeProperties(c, 0)&UPROPS_SCRIPT_X_MASK; |
| 561 | if(scriptX<UPROPS_SCRIPT_X_WITH_COMMON) { |
| 562 | return (UScriptCode)scriptX; |
| 563 | } else if(scriptX<UPROPS_SCRIPT_X_WITH_INHERITED) { |
| 564 | return USCRIPT_COMMON; |
| 565 | } else if(scriptX<UPROPS_SCRIPT_X_WITH_OTHER) { |
| 566 | return USCRIPT_INHERITED; |
| 567 | } else { |
| 568 | return (UScriptCode)scriptExtensions[scriptX&UPROPS_SCRIPT_MASK]; |
| 569 | } |
| 570 | } |
| 571 | |
| 572 | U_CAPI UBool U_EXPORT2 |
| 573 | uscript_hasScript(UChar32 c, UScriptCode sc) { |
| 574 | const uint16_t *scx; |
| 575 | uint32_t scriptX=u_getUnicodeProperties(c, 0)&UPROPS_SCRIPT_X_MASK; |
| 576 | if(scriptX<UPROPS_SCRIPT_X_WITH_COMMON) { |
| 577 | return sc==(UScriptCode)scriptX; |
| 578 | } |
| 579 | |
| 580 | scx=scriptExtensions+(scriptX&UPROPS_SCRIPT_MASK); |
| 581 | if(scriptX>=UPROPS_SCRIPT_X_WITH_OTHER) { |
| 582 | scx=scriptExtensions+scx[1]; |
| 583 | } |
| 584 | if(sc>=USCRIPT_CODE_LIMIT) { |
| 585 | /* Guard against bogus input that would make us go past the Script_Extensions terminator. */ |
| 586 | return FALSE; |
| 587 | } |
| 588 | while(sc>*scx) { |
| 589 | ++scx; |
| 590 | } |
| 591 | return sc==(*scx&0x7fff); |
| 592 | } |
| 593 | |
| 594 | U_CAPI int32_t U_EXPORT2 |
| 595 | uscript_getScriptExtensions(UChar32 c, |
| 596 | UScriptCode *scripts, int32_t capacity, |
| 597 | UErrorCode *pErrorCode) { |
| 598 | uint32_t scriptX; |
| 599 | int32_t length; |
| 600 | const uint16_t *scx; |
| 601 | uint16_t sx; |
| 602 | if(pErrorCode==NULL || U_FAILURE(*pErrorCode)) { |
| 603 | return 0; |
| 604 | } |
| 605 | if(capacity<0 || (capacity>0 && scripts==NULL)) { |
| 606 | *pErrorCode=U_ILLEGAL_ARGUMENT_ERROR; |
| 607 | return 0; |
| 608 | } |
| 609 | scriptX=u_getUnicodeProperties(c, 0)&UPROPS_SCRIPT_X_MASK; |
| 610 | if(scriptX<UPROPS_SCRIPT_X_WITH_COMMON) { |
| 611 | if(capacity==0) { |
| 612 | *pErrorCode=U_BUFFER_OVERFLOW_ERROR; |
| 613 | } else { |
| 614 | scripts[0]=(UScriptCode)scriptX; |
| 615 | } |
| 616 | return 1; |
| 617 | } |
| 618 | |
| 619 | scx=scriptExtensions+(scriptX&UPROPS_SCRIPT_MASK); |
| 620 | if(scriptX>=UPROPS_SCRIPT_X_WITH_OTHER) { |
| 621 | scx=scriptExtensions+scx[1]; |
| 622 | } |
| 623 | length=0; |
| 624 | do { |
| 625 | sx=*scx++; |
| 626 | if(length<capacity) { |
| 627 | scripts[length]=(UScriptCode)(sx&0x7fff); |
| 628 | } |
| 629 | ++length; |
| 630 | } while(sx<0x8000); |
| 631 | if(length>capacity) { |
| 632 | *pErrorCode=U_BUFFER_OVERFLOW_ERROR; |
| 633 | } |
| 634 | return length; |
| 635 | } |
| 636 | |
| 637 | U_CAPI UBlockCode U_EXPORT2 |
| 638 | ublock_getCode(UChar32 c) { |
| 639 | return (UBlockCode)((u_getUnicodeProperties(c, 0)&UPROPS_BLOCK_MASK)>>UPROPS_BLOCK_SHIFT); |
| 640 | } |
| 641 | |
| 642 | /* property starts for UnicodeSet ------------------------------------------- */ |
| 643 | |
| 644 | static UBool U_CALLCONV |
| 645 | _enumPropertyStartsRange(const void *context, UChar32 start, UChar32 end, uint32_t value) { |
| 646 | /* add the start code point to the USet */ |
| 647 | const USetAdder *sa=(const USetAdder *)context; |
| 648 | sa->add(sa->set, start); |
| 649 | return TRUE; |
| 650 | } |
| 651 | |
| 652 | #define USET_ADD_CP_AND_NEXT(sa, cp) sa->add(sa->set, cp); sa->add(sa->set, cp+1) |
| 653 | |
| 654 | U_CFUNC void U_EXPORT2 |
| 655 | uchar_addPropertyStarts(const USetAdder *sa, UErrorCode *pErrorCode) { |
| 656 | if(U_FAILURE(*pErrorCode)) { |
| 657 | return; |
| 658 | } |
| 659 | |
| 660 | /* add the start code point of each same-value range of the main trie */ |
| 661 | utrie2_enum(&propsTrie, NULL, _enumPropertyStartsRange, sa); |
| 662 | |
| 663 | /* add code points with hardcoded properties, plus the ones following them */ |
| 664 | |
| 665 | /* add for u_isblank() */ |
| 666 | USET_ADD_CP_AND_NEXT(sa, TAB); |
| 667 | |
| 668 | /* add for IS_THAT_CONTROL_SPACE() */ |
| 669 | sa->add(sa->set, CR+1); /* range TAB..CR */ |
| 670 | sa->add(sa->set, 0x1c); |
| 671 | sa->add(sa->set, 0x1f+1); |
| 672 | USET_ADD_CP_AND_NEXT(sa, NL); |
| 673 | |
| 674 | /* add for u_isIDIgnorable() what was not added above */ |
| 675 | sa->add(sa->set, DEL); /* range DEL..NBSP-1, NBSP added below */ |
| 676 | sa->add(sa->set, HAIRSP); |
| 677 | sa->add(sa->set, RLM+1); |
| 678 | sa->add(sa->set, INHSWAP); |
| 679 | sa->add(sa->set, NOMDIG+1); |
| 680 | USET_ADD_CP_AND_NEXT(sa, ZWNBSP); |
| 681 | |
| 682 | /* add no-break spaces for u_isWhitespace() what was not added above */ |
| 683 | USET_ADD_CP_AND_NEXT(sa, NBSP); |
| 684 | USET_ADD_CP_AND_NEXT(sa, FIGURESP); |
| 685 | USET_ADD_CP_AND_NEXT(sa, NNBSP); |
| 686 | |
| 687 | /* add for u_digit() */ |
| 688 | sa->add(sa->set, U_a); |
| 689 | sa->add(sa->set, U_z+1); |
| 690 | sa->add(sa->set, U_A); |
| 691 | sa->add(sa->set, U_Z+1); |
| 692 | sa->add(sa->set, U_FW_a); |
| 693 | sa->add(sa->set, U_FW_z+1); |
| 694 | sa->add(sa->set, U_FW_A); |
| 695 | sa->add(sa->set, U_FW_Z+1); |
| 696 | |
| 697 | /* add for u_isxdigit() */ |
| 698 | sa->add(sa->set, U_f+1); |
| 699 | sa->add(sa->set, U_F+1); |
| 700 | sa->add(sa->set, U_FW_f+1); |
| 701 | sa->add(sa->set, U_FW_F+1); |
| 702 | |
| 703 | /* add for UCHAR_DEFAULT_IGNORABLE_CODE_POINT what was not added above */ |
| 704 | sa->add(sa->set, WJ); /* range WJ..NOMDIG */ |
| 705 | sa->add(sa->set, 0xfff0); |
| 706 | sa->add(sa->set, 0xfffb+1); |
| 707 | sa->add(sa->set, 0xe0000); |
| 708 | sa->add(sa->set, 0xe0fff+1); |
| 709 | |
| 710 | /* add for UCHAR_GRAPHEME_BASE and others */ |
| 711 | USET_ADD_CP_AND_NEXT(sa, CGJ); |
| 712 | } |
| 713 | |
| 714 | U_CFUNC void U_EXPORT2 |
| 715 | upropsvec_addPropertyStarts(const USetAdder *sa, UErrorCode *pErrorCode) { |
| 716 | if(U_FAILURE(*pErrorCode)) { |
| 717 | return; |
| 718 | } |
| 719 | |
| 720 | /* add the start code point of each same-value range of the properties vectors trie */ |
| 721 | if(propsVectorsColumns>0) { |
| 722 | /* if propsVectorsColumns==0 then the properties vectors trie may not be there at all */ |
| 723 | utrie2_enum(&propsVectorsTrie, NULL, _enumPropertyStartsRange, sa); |
| 724 | } |
| 725 | } |