1 // © 2016 and later: Unicode, Inc. and others. 2 // License & terms of use: http://www.unicode.org/copyright.html 3 /* 4 ********************************************************************** 5 * Copyright (C) 1997-2016, International Business Machines 6 * Corporation and others. All Rights Reserved. 7 ********************************************************************** 8 * 9 * File UCHAR.H 10 * 11 * Modification History: 12 * 13 * Date Name Description 14 * 04/02/97 aliu Creation. 15 * 03/29/99 helena Updated for C APIs. 16 * 4/15/99 Madhu Updated for C Implementation and Javadoc 17 * 5/20/99 Madhu Added the function u_getVersion() 18 * 8/19/1999 srl Upgraded scripts to Unicode 3.0 19 * 8/27/1999 schererm UCharDirection constants: U_... 20 * 11/11/1999 weiv added u_isalnum(), cleaned comments 21 * 01/11/2000 helena Renamed u_getVersion to u_getUnicodeVersion(). 22 ****************************************************************************** 23 */ 24 25 #ifndef UCHAR_H 26 #define UCHAR_H 27 28 #include "unicode/utypes.h" 29 #include "unicode/stringoptions.h" 30 #include "unicode/ucpmap.h" 31 32 #if !defined(USET_DEFINED) && !defined(U_IN_DOXYGEN) 33 34 #define USET_DEFINED 35 36 /** 37 * USet is the C API type corresponding to C++ class UnicodeSet. 38 * It is forward-declared here to avoid including unicode/uset.h file if related 39 * APIs are not used. 40 * 41 * @see ucnv_getUnicodeSet 42 * @stable ICU 2.4 43 */ 44 typedef struct USet USet; 45 46 #endif 47 48 49 U_CDECL_BEGIN 50 51 /*==========================================================================*/ 52 /* Unicode version number */ 53 /*==========================================================================*/ 54 /** 55 * Unicode version number, default for the current ICU version. 56 * The actual Unicode Character Database (UCD) data is stored in uprops.dat 57 * and may be generated from UCD files from a different Unicode version. 58 * Call u_getUnicodeVersion to get the actual Unicode version of the data. 59 * 60 * @see u_getUnicodeVersion 61 * @stable ICU 2.0 62 */ 63 #define U_UNICODE_VERSION "15.0" 64 65 /** 66 * \file 67 * \brief C API: Unicode Properties 68 * 69 * This C API provides low-level access to the Unicode Character Database. 70 * In addition to raw property values, some convenience functions calculate 71 * derived properties, for example for Java-style programming. 72 * 73 * Unicode assigns each code point (not just assigned character) values for 74 * many properties. 75 * Most of them are simple boolean flags, or constants from a small enumerated list. 76 * For some properties, values are strings or other relatively more complex types. 77 * 78 * For more information see 79 * "About the Unicode Character Database" (http://www.unicode.org/ucd/) 80 * and the ICU User Guide chapter on Properties (https://unicode-org.github.io/icu/userguide/strings/properties). 81 * 82 * Many properties are accessible via generic functions that take a UProperty selector. 83 * - u_hasBinaryProperty() returns a binary value (true/false) per property and code point. 84 * - u_getIntPropertyValue() returns an integer value per property and code point. 85 * For each supported enumerated or catalog property, there is 86 * an enum type for all of the property's values, and 87 * u_getIntPropertyValue() returns the numeric values of those constants. 88 * - u_getBinaryPropertySet() returns a set for each ICU-supported binary property with 89 * all code points for which the property is true. 90 * - u_getIntPropertyMap() returns a map for each 91 * ICU-supported enumerated/catalog/int-valued property which 92 * maps all Unicode code points to their values for that property. 93 * 94 * Many functions are designed to match java.lang.Character functions. 95 * See the individual function documentation, 96 * and see the JDK 1.4 java.lang.Character documentation 97 * at http://java.sun.com/j2se/1.4/docs/api/java/lang/Character.html 98 * 99 * There are also functions that provide easy migration from C/POSIX functions 100 * like isblank(). Their use is generally discouraged because the C/POSIX 101 * standards do not define their semantics beyond the ASCII range, which means 102 * that different implementations exhibit very different behavior. 103 * Instead, Unicode properties should be used directly. 104 * 105 * There are also only a few, broad C/POSIX character classes, and they tend 106 * to be used for conflicting purposes. For example, the "isalpha()" class 107 * is sometimes used to determine word boundaries, while a more sophisticated 108 * approach would at least distinguish initial letters from continuation 109 * characters (the latter including combining marks). 110 * (In ICU, BreakIterator is the most sophisticated API for word boundaries.) 111 * Another example: There is no "istitle()" class for titlecase characters. 112 * 113 * ICU 3.4 and later provides API access for all twelve C/POSIX character classes. 114 * ICU implements them according to the Standard Recommendations in 115 * Annex C: Compatibility Properties of UTS #18 Unicode Regular Expressions 116 * (http://www.unicode.org/reports/tr18/#Compatibility_Properties). 117 * 118 * API access for C/POSIX character classes is as follows: 119 * - alpha: u_isUAlphabetic(c) or u_hasBinaryProperty(c, UCHAR_ALPHABETIC) 120 * - lower: u_isULowercase(c) or u_hasBinaryProperty(c, UCHAR_LOWERCASE) 121 * - upper: u_isUUppercase(c) or u_hasBinaryProperty(c, UCHAR_UPPERCASE) 122 * - punct: u_ispunct(c) 123 * - digit: u_isdigit(c) or u_charType(c)==U_DECIMAL_DIGIT_NUMBER 124 * - xdigit: u_isxdigit(c) or u_hasBinaryProperty(c, UCHAR_POSIX_XDIGIT) 125 * - alnum: u_hasBinaryProperty(c, UCHAR_POSIX_ALNUM) 126 * - space: u_isUWhiteSpace(c) or u_hasBinaryProperty(c, UCHAR_WHITE_SPACE) 127 * - blank: u_isblank(c) or u_hasBinaryProperty(c, UCHAR_POSIX_BLANK) 128 * - cntrl: u_charType(c)==U_CONTROL_CHAR 129 * - graph: u_hasBinaryProperty(c, UCHAR_POSIX_GRAPH) 130 * - print: u_hasBinaryProperty(c, UCHAR_POSIX_PRINT) 131 * 132 * Note: Some of the u_isxyz() functions in uchar.h predate, and do not match, 133 * the Standard Recommendations in UTS #18. Instead, they match Java 134 * functions according to their API documentation. 135 * 136 * \htmlonly 137 * The C/POSIX character classes are also available in UnicodeSet patterns, 138 * using patterns like [:graph:] or \p{graph}. 139 * \endhtmlonly 140 * 141 * Note: There are several ICU whitespace functions. 142 * Comparison: 143 * - u_isUWhiteSpace=UCHAR_WHITE_SPACE: Unicode White_Space property; 144 * most of general categories "Z" (separators) + most whitespace ISO controls 145 * (including no-break spaces, but excluding IS1..IS4) 146 * - u_isWhitespace: Java isWhitespace; Z + whitespace ISO controls but excluding no-break spaces 147 * - u_isJavaSpaceChar: Java isSpaceChar; just Z (including no-break spaces) 148 * - u_isspace: Z + whitespace ISO controls (including no-break spaces) 149 * - u_isblank: "horizontal spaces" = TAB + Zs 150 */ 151 152 /** 153 * Constants. 154 */ 155 156 /** The lowest Unicode code point value. Code points are non-negative. @stable ICU 2.0 */ 157 #define UCHAR_MIN_VALUE 0 158 159 /** 160 * The highest Unicode code point value (scalar value) according to 161 * The Unicode Standard. This is a 21-bit value (20.1 bits, rounded up). 162 * For a single character, UChar32 is a simple type that can hold any code point value. 163 * 164 * @see UChar32 165 * @stable ICU 2.0 166 */ 167 #define UCHAR_MAX_VALUE 0x10ffff 168 169 /** 170 * Get a single-bit bit set (a flag) from a bit number 0..31. 171 * @stable ICU 2.1 172 */ 173 #define U_MASK(x) ((uint32_t)1<<(x)) 174 175 /** 176 * Selection constants for Unicode properties. 177 * These constants are used in functions like u_hasBinaryProperty to select 178 * one of the Unicode properties. 179 * 180 * The properties APIs are intended to reflect Unicode properties as defined 181 * in the Unicode Character Database (UCD) and Unicode Technical Reports (UTR). 182 * 183 * For details about the properties see 184 * UAX #44: Unicode Character Database (http://www.unicode.org/reports/tr44/). 185 * 186 * Important: If ICU is built with UCD files from Unicode versions below, e.g., 3.2, 187 * then properties marked with "new in Unicode 3.2" are not or not fully available. 188 * Check u_getUnicodeVersion to be sure. 189 * 190 * @see u_hasBinaryProperty 191 * @see u_getIntPropertyValue 192 * @see u_getUnicodeVersion 193 * @stable ICU 2.1 194 */ 195 typedef enum UProperty { 196 /* 197 * Note: UProperty constants are parsed by preparseucd.py. 198 * It matches lines like 199 * UCHAR_<Unicode property name>=<integer>, 200 */ 201 202 /* Note: Place UCHAR_ALPHABETIC before UCHAR_BINARY_START so that 203 debuggers display UCHAR_ALPHABETIC as the symbolic name for 0, 204 rather than UCHAR_BINARY_START. Likewise for other *_START 205 identifiers. */ 206 207 /** Binary property Alphabetic. Same as u_isUAlphabetic, different from u_isalpha. 208 Lu+Ll+Lt+Lm+Lo+Nl+Other_Alphabetic @stable ICU 2.1 */ 209 UCHAR_ALPHABETIC=0, 210 /** First constant for binary Unicode properties. @stable ICU 2.1 */ 211 UCHAR_BINARY_START=UCHAR_ALPHABETIC, 212 /** Binary property ASCII_Hex_Digit. 0-9 A-F a-f @stable ICU 2.1 */ 213 UCHAR_ASCII_HEX_DIGIT=1, 214 /** Binary property Bidi_Control. 215 Format controls which have specific functions 216 in the Bidi Algorithm. @stable ICU 2.1 */ 217 UCHAR_BIDI_CONTROL=2, 218 /** Binary property Bidi_Mirrored. 219 Characters that may change display in RTL text. 220 Same as u_isMirrored. 221 See Bidi Algorithm, UTR 9. @stable ICU 2.1 */ 222 UCHAR_BIDI_MIRRORED=3, 223 /** Binary property Dash. Variations of dashes. @stable ICU 2.1 */ 224 UCHAR_DASH=4, 225 /** Binary property Default_Ignorable_Code_Point (new in Unicode 3.2). 226 Ignorable in most processing. 227 <2060..206F, FFF0..FFFB, E0000..E0FFF>+Other_Default_Ignorable_Code_Point+(Cf+Cc+Cs-White_Space) @stable ICU 2.1 */ 228 UCHAR_DEFAULT_IGNORABLE_CODE_POINT=5, 229 /** Binary property Deprecated (new in Unicode 3.2). 230 The usage of deprecated characters is strongly discouraged. @stable ICU 2.1 */ 231 UCHAR_DEPRECATED=6, 232 /** Binary property Diacritic. Characters that linguistically modify 233 the meaning of another character to which they apply. @stable ICU 2.1 */ 234 UCHAR_DIACRITIC=7, 235 /** Binary property Extender. 236 Extend the value or shape of a preceding alphabetic character, 237 e.g., length and iteration marks. @stable ICU 2.1 */ 238 UCHAR_EXTENDER=8, 239 /** Binary property Full_Composition_Exclusion. 240 CompositionExclusions.txt+Singleton Decompositions+ 241 Non-Starter Decompositions. @stable ICU 2.1 */ 242 UCHAR_FULL_COMPOSITION_EXCLUSION=9, 243 /** Binary property Grapheme_Base (new in Unicode 3.2). 244 For programmatic determination of grapheme cluster boundaries. 245 [0..10FFFF]-Cc-Cf-Cs-Co-Cn-Zl-Zp-Grapheme_Link-Grapheme_Extend-CGJ @stable ICU 2.1 */ 246 UCHAR_GRAPHEME_BASE=10, 247 /** Binary property Grapheme_Extend (new in Unicode 3.2). 248 For programmatic determination of grapheme cluster boundaries. 249 Me+Mn+Mc+Other_Grapheme_Extend-Grapheme_Link-CGJ @stable ICU 2.1 */ 250 UCHAR_GRAPHEME_EXTEND=11, 251 /** Binary property Grapheme_Link (new in Unicode 3.2). 252 For programmatic determination of grapheme cluster boundaries. @stable ICU 2.1 */ 253 UCHAR_GRAPHEME_LINK=12, 254 /** Binary property Hex_Digit. 255 Characters commonly used for hexadecimal numbers. @stable ICU 2.1 */ 256 UCHAR_HEX_DIGIT=13, 257 /** Binary property Hyphen. Dashes used to mark connections 258 between pieces of words, plus the Katakana middle dot. @stable ICU 2.1 */ 259 UCHAR_HYPHEN=14, 260 /** Binary property ID_Continue. 261 Characters that can continue an identifier. 262 DerivedCoreProperties.txt also says "NOTE: Cf characters should be filtered out." 263 ID_Start+Mn+Mc+Nd+Pc @stable ICU 2.1 */ 264 UCHAR_ID_CONTINUE=15, 265 /** Binary property ID_Start. 266 Characters that can start an identifier. 267 Lu+Ll+Lt+Lm+Lo+Nl @stable ICU 2.1 */ 268 UCHAR_ID_START=16, 269 /** Binary property Ideographic. 270 CJKV ideographs. @stable ICU 2.1 */ 271 UCHAR_IDEOGRAPHIC=17, 272 /** Binary property IDS_Binary_Operator (new in Unicode 3.2). 273 For programmatic determination of 274 Ideographic Description Sequences. @stable ICU 2.1 */ 275 UCHAR_IDS_BINARY_OPERATOR=18, 276 /** Binary property IDS_Trinary_Operator (new in Unicode 3.2). 277 For programmatic determination of 278 Ideographic Description Sequences. @stable ICU 2.1 */ 279 UCHAR_IDS_TRINARY_OPERATOR=19, 280 /** Binary property Join_Control. 281 Format controls for cursive joining and ligation. @stable ICU 2.1 */ 282 UCHAR_JOIN_CONTROL=20, 283 /** Binary property Logical_Order_Exception (new in Unicode 3.2). 284 Characters that do not use logical order and 285 require special handling in most processing. @stable ICU 2.1 */ 286 UCHAR_LOGICAL_ORDER_EXCEPTION=21, 287 /** Binary property Lowercase. Same as u_isULowercase, different from u_islower. 288 Ll+Other_Lowercase @stable ICU 2.1 */ 289 UCHAR_LOWERCASE=22, 290 /** Binary property Math. Sm+Other_Math @stable ICU 2.1 */ 291 UCHAR_MATH=23, 292 /** Binary property Noncharacter_Code_Point. 293 Code points that are explicitly defined as illegal 294 for the encoding of characters. @stable ICU 2.1 */ 295 UCHAR_NONCHARACTER_CODE_POINT=24, 296 /** Binary property Quotation_Mark. @stable ICU 2.1 */ 297 UCHAR_QUOTATION_MARK=25, 298 /** Binary property Radical (new in Unicode 3.2). 299 For programmatic determination of 300 Ideographic Description Sequences. @stable ICU 2.1 */ 301 UCHAR_RADICAL=26, 302 /** Binary property Soft_Dotted (new in Unicode 3.2). 303 Characters with a "soft dot", like i or j. 304 An accent placed on these characters causes 305 the dot to disappear. @stable ICU 2.1 */ 306 UCHAR_SOFT_DOTTED=27, 307 /** Binary property Terminal_Punctuation. 308 Punctuation characters that generally mark 309 the end of textual units. @stable ICU 2.1 */ 310 UCHAR_TERMINAL_PUNCTUATION=28, 311 /** Binary property Unified_Ideograph (new in Unicode 3.2). 312 For programmatic determination of 313 Ideographic Description Sequences. @stable ICU 2.1 */ 314 UCHAR_UNIFIED_IDEOGRAPH=29, 315 /** Binary property Uppercase. Same as u_isUUppercase, different from u_isupper. 316 Lu+Other_Uppercase @stable ICU 2.1 */ 317 UCHAR_UPPERCASE=30, 318 /** Binary property White_Space. 319 Same as u_isUWhiteSpace, different from u_isspace and u_isWhitespace. 320 Space characters+TAB+CR+LF-ZWSP-ZWNBSP @stable ICU 2.1 */ 321 UCHAR_WHITE_SPACE=31, 322 /** Binary property XID_Continue. 323 ID_Continue modified to allow closure under 324 normalization forms NFKC and NFKD. @stable ICU 2.1 */ 325 UCHAR_XID_CONTINUE=32, 326 /** Binary property XID_Start. ID_Start modified to allow 327 closure under normalization forms NFKC and NFKD. @stable ICU 2.1 */ 328 UCHAR_XID_START=33, 329 /** Binary property Case_Sensitive. Either the source of a case 330 mapping or _in_ the target of a case mapping. Not the same as 331 the general category Cased_Letter. @stable ICU 2.6 */ 332 UCHAR_CASE_SENSITIVE=34, 333 /** Binary property STerm (new in Unicode 4.0.1). 334 Sentence Terminal. Used in UAX #29: Text Boundaries 335 (http://www.unicode.org/reports/tr29/) 336 @stable ICU 3.0 */ 337 UCHAR_S_TERM=35, 338 /** Binary property Variation_Selector (new in Unicode 4.0.1). 339 Indicates all those characters that qualify as Variation Selectors. 340 For details on the behavior of these characters, 341 see StandardizedVariants.html and 15.6 Variation Selectors. 342 @stable ICU 3.0 */ 343 UCHAR_VARIATION_SELECTOR=36, 344 /** Binary property NFD_Inert. 345 ICU-specific property for characters that are inert under NFD, 346 i.e., they do not interact with adjacent characters. 347 See the documentation for the Normalizer2 class and the 348 Normalizer2::isInert() method. 349 @stable ICU 3.0 */ 350 UCHAR_NFD_INERT=37, 351 /** Binary property NFKD_Inert. 352 ICU-specific property for characters that are inert under NFKD, 353 i.e., they do not interact with adjacent characters. 354 See the documentation for the Normalizer2 class and the 355 Normalizer2::isInert() method. 356 @stable ICU 3.0 */ 357 UCHAR_NFKD_INERT=38, 358 /** Binary property NFC_Inert. 359 ICU-specific property for characters that are inert under NFC, 360 i.e., they do not interact with adjacent characters. 361 See the documentation for the Normalizer2 class and the 362 Normalizer2::isInert() method. 363 @stable ICU 3.0 */ 364 UCHAR_NFC_INERT=39, 365 /** Binary property NFKC_Inert. 366 ICU-specific property for characters that are inert under NFKC, 367 i.e., they do not interact with adjacent characters. 368 See the documentation for the Normalizer2 class and the 369 Normalizer2::isInert() method. 370 @stable ICU 3.0 */ 371 UCHAR_NFKC_INERT=40, 372 /** Binary Property Segment_Starter. 373 ICU-specific property for characters that are starters in terms of 374 Unicode normalization and combining character sequences. 375 They have ccc=0 and do not occur in non-initial position of the 376 canonical decomposition of any character 377 (like a-umlaut in NFD and a Jamo T in an NFD(Hangul LVT)). 378 ICU uses this property for segmenting a string for generating a set of 379 canonically equivalent strings, e.g. for canonical closure while 380 processing collation tailoring rules. 381 @stable ICU 3.0 */ 382 UCHAR_SEGMENT_STARTER=41, 383 /** Binary property Pattern_Syntax (new in Unicode 4.1). 384 See UAX #31 Identifier and Pattern Syntax 385 (http://www.unicode.org/reports/tr31/) 386 @stable ICU 3.4 */ 387 UCHAR_PATTERN_SYNTAX=42, 388 /** Binary property Pattern_White_Space (new in Unicode 4.1). 389 See UAX #31 Identifier and Pattern Syntax 390 (http://www.unicode.org/reports/tr31/) 391 @stable ICU 3.4 */ 392 UCHAR_PATTERN_WHITE_SPACE=43, 393 /** Binary property alnum (a C/POSIX character class). 394 Implemented according to the UTS #18 Annex C Standard Recommendation. 395 See the uchar.h file documentation. 396 @stable ICU 3.4 */ 397 UCHAR_POSIX_ALNUM=44, 398 /** Binary property blank (a C/POSIX character class). 399 Implemented according to the UTS #18 Annex C Standard Recommendation. 400 See the uchar.h file documentation. 401 @stable ICU 3.4 */ 402 UCHAR_POSIX_BLANK=45, 403 /** Binary property graph (a C/POSIX character class). 404 Implemented according to the UTS #18 Annex C Standard Recommendation. 405 See the uchar.h file documentation. 406 @stable ICU 3.4 */ 407 UCHAR_POSIX_GRAPH=46, 408 /** Binary property print (a C/POSIX character class). 409 Implemented according to the UTS #18 Annex C Standard Recommendation. 410 See the uchar.h file documentation. 411 @stable ICU 3.4 */ 412 UCHAR_POSIX_PRINT=47, 413 /** Binary property xdigit (a C/POSIX character class). 414 Implemented according to the UTS #18 Annex C Standard Recommendation. 415 See the uchar.h file documentation. 416 @stable ICU 3.4 */ 417 UCHAR_POSIX_XDIGIT=48, 418 /** Binary property Cased. For Lowercase, Uppercase and Titlecase characters. @stable ICU 4.4 */ 419 UCHAR_CASED=49, 420 /** Binary property Case_Ignorable. Used in context-sensitive case mappings. @stable ICU 4.4 */ 421 UCHAR_CASE_IGNORABLE=50, 422 /** Binary property Changes_When_Lowercased. @stable ICU 4.4 */ 423 UCHAR_CHANGES_WHEN_LOWERCASED=51, 424 /** Binary property Changes_When_Uppercased. @stable ICU 4.4 */ 425 UCHAR_CHANGES_WHEN_UPPERCASED=52, 426 /** Binary property Changes_When_Titlecased. @stable ICU 4.4 */ 427 UCHAR_CHANGES_WHEN_TITLECASED=53, 428 /** Binary property Changes_When_Casefolded. @stable ICU 4.4 */ 429 UCHAR_CHANGES_WHEN_CASEFOLDED=54, 430 /** Binary property Changes_When_Casemapped. @stable ICU 4.4 */ 431 UCHAR_CHANGES_WHEN_CASEMAPPED=55, 432 /** Binary property Changes_When_NFKC_Casefolded. @stable ICU 4.4 */ 433 UCHAR_CHANGES_WHEN_NFKC_CASEFOLDED=56, 434 /** 435 * Binary property Emoji. 436 * See http://www.unicode.org/reports/tr51/#Emoji_Properties 437 * 438 * @stable ICU 57 439 */ 440 UCHAR_EMOJI=57, 441 /** 442 * Binary property Emoji_Presentation. 443 * See http://www.unicode.org/reports/tr51/#Emoji_Properties 444 * 445 * @stable ICU 57 446 */ 447 UCHAR_EMOJI_PRESENTATION=58, 448 /** 449 * Binary property Emoji_Modifier. 450 * See http://www.unicode.org/reports/tr51/#Emoji_Properties 451 * 452 * @stable ICU 57 453 */ 454 UCHAR_EMOJI_MODIFIER=59, 455 /** 456 * Binary property Emoji_Modifier_Base. 457 * See http://www.unicode.org/reports/tr51/#Emoji_Properties 458 * 459 * @stable ICU 57 460 */ 461 UCHAR_EMOJI_MODIFIER_BASE=60, 462 /** 463 * Binary property Emoji_Component. 464 * See http://www.unicode.org/reports/tr51/#Emoji_Properties 465 * 466 * @stable ICU 60 467 */ 468 UCHAR_EMOJI_COMPONENT=61, 469 /** 470 * Binary property Regional_Indicator. 471 * @stable ICU 60 472 */ 473 UCHAR_REGIONAL_INDICATOR=62, 474 /** 475 * Binary property Prepended_Concatenation_Mark. 476 * @stable ICU 60 477 */ 478 UCHAR_PREPENDED_CONCATENATION_MARK=63, 479 /** 480 * Binary property Extended_Pictographic. 481 * See http://www.unicode.org/reports/tr51/#Emoji_Properties 482 * 483 * @stable ICU 62 484 */ 485 UCHAR_EXTENDED_PICTOGRAPHIC=64, 486 /** 487 * Binary property of strings Basic_Emoji. 488 * See https://www.unicode.org/reports/tr51/#Emoji_Sets 489 * 490 * @stable ICU 70 491 */ 492 UCHAR_BASIC_EMOJI=65, 493 /** 494 * Binary property of strings Emoji_Keycap_Sequence. 495 * See https://www.unicode.org/reports/tr51/#Emoji_Sets 496 * 497 * @stable ICU 70 498 */ 499 UCHAR_EMOJI_KEYCAP_SEQUENCE=66, 500 /** 501 * Binary property of strings RGI_Emoji_Modifier_Sequence. 502 * See https://www.unicode.org/reports/tr51/#Emoji_Sets 503 * 504 * @stable ICU 70 505 */ 506 UCHAR_RGI_EMOJI_MODIFIER_SEQUENCE=67, 507 /** 508 * Binary property of strings RGI_Emoji_Flag_Sequence. 509 * See https://www.unicode.org/reports/tr51/#Emoji_Sets 510 * 511 * @stable ICU 70 512 */ 513 UCHAR_RGI_EMOJI_FLAG_SEQUENCE=68, 514 /** 515 * Binary property of strings RGI_Emoji_Tag_Sequence. 516 * See https://www.unicode.org/reports/tr51/#Emoji_Sets 517 * 518 * @stable ICU 70 519 */ 520 UCHAR_RGI_EMOJI_TAG_SEQUENCE=69, 521 /** 522 * Binary property of strings RGI_Emoji_ZWJ_Sequence. 523 * See https://www.unicode.org/reports/tr51/#Emoji_Sets 524 * 525 * @stable ICU 70 526 */ 527 UCHAR_RGI_EMOJI_ZWJ_SEQUENCE=70, 528 /** 529 * Binary property of strings RGI_Emoji. 530 * See https://www.unicode.org/reports/tr51/#Emoji_Sets 531 * 532 * @stable ICU 70 533 */ 534 UCHAR_RGI_EMOJI=71, 535 #ifndef U_HIDE_DEPRECATED_API 536 /** 537 * One more than the last constant for binary Unicode properties. 538 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. 539 */ 540 UCHAR_BINARY_LIMIT=72, 541 #endif // U_HIDE_DEPRECATED_API 542 543 /** Enumerated property Bidi_Class. 544 Same as u_charDirection, returns UCharDirection values. @stable ICU 2.2 */ 545 UCHAR_BIDI_CLASS=0x1000, 546 /** First constant for enumerated/integer Unicode properties. @stable ICU 2.2 */ 547 UCHAR_INT_START=UCHAR_BIDI_CLASS, 548 /** Enumerated property Block. 549 Same as ublock_getCode, returns UBlockCode values. @stable ICU 2.2 */ 550 UCHAR_BLOCK=0x1001, 551 /** Enumerated property Canonical_Combining_Class. 552 Same as u_getCombiningClass, returns 8-bit numeric values. @stable ICU 2.2 */ 553 UCHAR_CANONICAL_COMBINING_CLASS=0x1002, 554 /** Enumerated property Decomposition_Type. 555 Returns UDecompositionType values. @stable ICU 2.2 */ 556 UCHAR_DECOMPOSITION_TYPE=0x1003, 557 /** Enumerated property East_Asian_Width. 558 See http://www.unicode.org/reports/tr11/ 559 Returns UEastAsianWidth values. @stable ICU 2.2 */ 560 UCHAR_EAST_ASIAN_WIDTH=0x1004, 561 /** Enumerated property General_Category. 562 Same as u_charType, returns UCharCategory values. @stable ICU 2.2 */ 563 UCHAR_GENERAL_CATEGORY=0x1005, 564 /** Enumerated property Joining_Group. 565 Returns UJoiningGroup values. @stable ICU 2.2 */ 566 UCHAR_JOINING_GROUP=0x1006, 567 /** Enumerated property Joining_Type. 568 Returns UJoiningType values. @stable ICU 2.2 */ 569 UCHAR_JOINING_TYPE=0x1007, 570 /** Enumerated property Line_Break. 571 Returns ULineBreak values. @stable ICU 2.2 */ 572 UCHAR_LINE_BREAK=0x1008, 573 /** Enumerated property Numeric_Type. 574 Returns UNumericType values. @stable ICU 2.2 */ 575 UCHAR_NUMERIC_TYPE=0x1009, 576 /** Enumerated property Script. 577 Same as uscript_getScript, returns UScriptCode values. @stable ICU 2.2 */ 578 UCHAR_SCRIPT=0x100A, 579 /** Enumerated property Hangul_Syllable_Type, new in Unicode 4. 580 Returns UHangulSyllableType values. @stable ICU 2.6 */ 581 UCHAR_HANGUL_SYLLABLE_TYPE=0x100B, 582 /** Enumerated property NFD_Quick_Check. 583 Returns UNormalizationCheckResult values. @stable ICU 3.0 */ 584 UCHAR_NFD_QUICK_CHECK=0x100C, 585 /** Enumerated property NFKD_Quick_Check. 586 Returns UNormalizationCheckResult values. @stable ICU 3.0 */ 587 UCHAR_NFKD_QUICK_CHECK=0x100D, 588 /** Enumerated property NFC_Quick_Check. 589 Returns UNormalizationCheckResult values. @stable ICU 3.0 */ 590 UCHAR_NFC_QUICK_CHECK=0x100E, 591 /** Enumerated property NFKC_Quick_Check. 592 Returns UNormalizationCheckResult values. @stable ICU 3.0 */ 593 UCHAR_NFKC_QUICK_CHECK=0x100F, 594 /** Enumerated property Lead_Canonical_Combining_Class. 595 ICU-specific property for the ccc of the first code point 596 of the decomposition, or lccc(c)=ccc(NFD(c)[0]). 597 Useful for checking for canonically ordered text; 598 see UNORM_FCD and http://www.unicode.org/notes/tn5/#FCD . 599 Returns 8-bit numeric values like UCHAR_CANONICAL_COMBINING_CLASS. @stable ICU 3.0 */ 600 UCHAR_LEAD_CANONICAL_COMBINING_CLASS=0x1010, 601 /** Enumerated property Trail_Canonical_Combining_Class. 602 ICU-specific property for the ccc of the last code point 603 of the decomposition, or tccc(c)=ccc(NFD(c)[last]). 604 Useful for checking for canonically ordered text; 605 see UNORM_FCD and http://www.unicode.org/notes/tn5/#FCD . 606 Returns 8-bit numeric values like UCHAR_CANONICAL_COMBINING_CLASS. @stable ICU 3.0 */ 607 UCHAR_TRAIL_CANONICAL_COMBINING_CLASS=0x1011, 608 /** Enumerated property Grapheme_Cluster_Break (new in Unicode 4.1). 609 Used in UAX #29: Text Boundaries 610 (http://www.unicode.org/reports/tr29/) 611 Returns UGraphemeClusterBreak values. @stable ICU 3.4 */ 612 UCHAR_GRAPHEME_CLUSTER_BREAK=0x1012, 613 /** Enumerated property Sentence_Break (new in Unicode 4.1). 614 Used in UAX #29: Text Boundaries 615 (http://www.unicode.org/reports/tr29/) 616 Returns USentenceBreak values. @stable ICU 3.4 */ 617 UCHAR_SENTENCE_BREAK=0x1013, 618 /** Enumerated property Word_Break (new in Unicode 4.1). 619 Used in UAX #29: Text Boundaries 620 (http://www.unicode.org/reports/tr29/) 621 Returns UWordBreakValues values. @stable ICU 3.4 */ 622 UCHAR_WORD_BREAK=0x1014, 623 /** Enumerated property Bidi_Paired_Bracket_Type (new in Unicode 6.3). 624 Used in UAX #9: Unicode Bidirectional Algorithm 625 (http://www.unicode.org/reports/tr9/) 626 Returns UBidiPairedBracketType values. @stable ICU 52 */ 627 UCHAR_BIDI_PAIRED_BRACKET_TYPE=0x1015, 628 /** 629 * Enumerated property Indic_Positional_Category. 630 * New in Unicode 6.0 as provisional property Indic_Matra_Category; 631 * renamed and changed to informative in Unicode 8.0. 632 * See http://www.unicode.org/reports/tr44/#IndicPositionalCategory.txt 633 * @stable ICU 63 634 */ 635 UCHAR_INDIC_POSITIONAL_CATEGORY=0x1016, 636 /** 637 * Enumerated property Indic_Syllabic_Category. 638 * New in Unicode 6.0 as provisional; informative since Unicode 8.0. 639 * See http://www.unicode.org/reports/tr44/#IndicSyllabicCategory.txt 640 * @stable ICU 63 641 */ 642 UCHAR_INDIC_SYLLABIC_CATEGORY=0x1017, 643 /** 644 * Enumerated property Vertical_Orientation. 645 * Used for UAX #50 Unicode Vertical Text Layout (https://www.unicode.org/reports/tr50/). 646 * New as a UCD property in Unicode 10.0. 647 * @stable ICU 63 648 */ 649 UCHAR_VERTICAL_ORIENTATION=0x1018, 650 #ifndef U_HIDE_DEPRECATED_API 651 /** 652 * One more than the last constant for enumerated/integer Unicode properties. 653 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. 654 */ 655 UCHAR_INT_LIMIT=0x1019, 656 #endif // U_HIDE_DEPRECATED_API 657 658 /** Bitmask property General_Category_Mask. 659 This is the General_Category property returned as a bit mask. 660 When used in u_getIntPropertyValue(c), same as U_MASK(u_charType(c)), 661 returns bit masks for UCharCategory values where exactly one bit is set. 662 When used with u_getPropertyValueName() and u_getPropertyValueEnum(), 663 a multi-bit mask is used for sets of categories like "Letters". 664 Mask values should be cast to uint32_t. 665 @stable ICU 2.4 */ 666 UCHAR_GENERAL_CATEGORY_MASK=0x2000, 667 /** First constant for bit-mask Unicode properties. @stable ICU 2.4 */ 668 UCHAR_MASK_START=UCHAR_GENERAL_CATEGORY_MASK, 669 #ifndef U_HIDE_DEPRECATED_API 670 /** 671 * One more than the last constant for bit-mask Unicode properties. 672 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. 673 */ 674 UCHAR_MASK_LIMIT=0x2001, 675 #endif // U_HIDE_DEPRECATED_API 676 677 /** Double property Numeric_Value. 678 Corresponds to u_getNumericValue. @stable ICU 2.4 */ 679 UCHAR_NUMERIC_VALUE=0x3000, 680 /** First constant for double Unicode properties. @stable ICU 2.4 */ 681 UCHAR_DOUBLE_START=UCHAR_NUMERIC_VALUE, 682 #ifndef U_HIDE_DEPRECATED_API 683 /** 684 * One more than the last constant for double Unicode properties. 685 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. 686 */ 687 UCHAR_DOUBLE_LIMIT=0x3001, 688 #endif // U_HIDE_DEPRECATED_API 689 690 /** String property Age. 691 Corresponds to u_charAge. @stable ICU 2.4 */ 692 UCHAR_AGE=0x4000, 693 /** First constant for string Unicode properties. @stable ICU 2.4 */ 694 UCHAR_STRING_START=UCHAR_AGE, 695 /** String property Bidi_Mirroring_Glyph. 696 Corresponds to u_charMirror. @stable ICU 2.4 */ 697 UCHAR_BIDI_MIRRORING_GLYPH=0x4001, 698 /** String property Case_Folding. 699 Corresponds to u_strFoldCase in ustring.h. @stable ICU 2.4 */ 700 UCHAR_CASE_FOLDING=0x4002, 701 #ifndef U_HIDE_DEPRECATED_API 702 /** Deprecated string property ISO_Comment. 703 Corresponds to u_getISOComment. @deprecated ICU 49 */ 704 UCHAR_ISO_COMMENT=0x4003, 705 #endif /* U_HIDE_DEPRECATED_API */ 706 /** String property Lowercase_Mapping. 707 Corresponds to u_strToLower in ustring.h. @stable ICU 2.4 */ 708 UCHAR_LOWERCASE_MAPPING=0x4004, 709 /** String property Name. 710 Corresponds to u_charName. @stable ICU 2.4 */ 711 UCHAR_NAME=0x4005, 712 /** String property Simple_Case_Folding. 713 Corresponds to u_foldCase. @stable ICU 2.4 */ 714 UCHAR_SIMPLE_CASE_FOLDING=0x4006, 715 /** String property Simple_Lowercase_Mapping. 716 Corresponds to u_tolower. @stable ICU 2.4 */ 717 UCHAR_SIMPLE_LOWERCASE_MAPPING=0x4007, 718 /** String property Simple_Titlecase_Mapping. 719 Corresponds to u_totitle. @stable ICU 2.4 */ 720 UCHAR_SIMPLE_TITLECASE_MAPPING=0x4008, 721 /** String property Simple_Uppercase_Mapping. 722 Corresponds to u_toupper. @stable ICU 2.4 */ 723 UCHAR_SIMPLE_UPPERCASE_MAPPING=0x4009, 724 /** String property Titlecase_Mapping. 725 Corresponds to u_strToTitle in ustring.h. @stable ICU 2.4 */ 726 UCHAR_TITLECASE_MAPPING=0x400A, 727 #ifndef U_HIDE_DEPRECATED_API 728 /** String property Unicode_1_Name. 729 This property is of little practical value. 730 Beginning with ICU 49, ICU APIs return an empty string for this property. 731 Corresponds to u_charName(U_UNICODE_10_CHAR_NAME). @deprecated ICU 49 */ 732 UCHAR_UNICODE_1_NAME=0x400B, 733 #endif /* U_HIDE_DEPRECATED_API */ 734 /** String property Uppercase_Mapping. 735 Corresponds to u_strToUpper in ustring.h. @stable ICU 2.4 */ 736 UCHAR_UPPERCASE_MAPPING=0x400C, 737 /** String property Bidi_Paired_Bracket (new in Unicode 6.3). 738 Corresponds to u_getBidiPairedBracket. @stable ICU 52 */ 739 UCHAR_BIDI_PAIRED_BRACKET=0x400D, 740 #ifndef U_HIDE_DEPRECATED_API 741 /** 742 * One more than the last constant for string Unicode properties. 743 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. 744 */ 745 UCHAR_STRING_LIMIT=0x400E, 746 #endif // U_HIDE_DEPRECATED_API 747 748 /** Miscellaneous property Script_Extensions (new in Unicode 6.0). 749 Some characters are commonly used in multiple scripts. 750 For more information, see UAX #24: http://www.unicode.org/reports/tr24/. 751 Corresponds to uscript_hasScript and uscript_getScriptExtensions in uscript.h. 752 @stable ICU 4.6 */ 753 UCHAR_SCRIPT_EXTENSIONS=0x7000, 754 /** First constant for Unicode properties with unusual value types. @stable ICU 4.6 */ 755 UCHAR_OTHER_PROPERTY_START=UCHAR_SCRIPT_EXTENSIONS, 756 #ifndef U_HIDE_DEPRECATED_API 757 /** 758 * One more than the last constant for Unicode properties with unusual value types. 759 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. 760 */ 761 UCHAR_OTHER_PROPERTY_LIMIT=0x7001, 762 #endif // U_HIDE_DEPRECATED_API 763 764 /** Represents a nonexistent or invalid property or property value. @stable ICU 2.4 */ 765 UCHAR_INVALID_CODE = -1 766 } UProperty; 767 768 /** 769 * Data for enumerated Unicode general category types. 770 * See http://www.unicode.org/Public/UNIDATA/UnicodeData.html . 771 * @stable ICU 2.0 772 */ 773 typedef enum UCharCategory 774 { 775 /* 776 * Note: UCharCategory constants and their API comments are parsed by preparseucd.py. 777 * It matches pairs of lines like 778 * / ** <Unicode 2-letter General_Category value> comment... * / 779 * U_<[A-Z_]+> = <integer>, 780 */ 781 782 /** Non-category for unassigned and non-character code points. @stable ICU 2.0 */ 783 U_UNASSIGNED = 0, 784 /** Cn "Other, Not Assigned (no characters in [UnicodeData.txt] have this property)" (same as U_UNASSIGNED!) @stable ICU 2.0 */ 785 U_GENERAL_OTHER_TYPES = 0, 786 /** Lu @stable ICU 2.0 */ 787 U_UPPERCASE_LETTER = 1, 788 /** Ll @stable ICU 2.0 */ 789 U_LOWERCASE_LETTER = 2, 790 /** Lt @stable ICU 2.0 */ 791 U_TITLECASE_LETTER = 3, 792 /** Lm @stable ICU 2.0 */ 793 U_MODIFIER_LETTER = 4, 794 /** Lo @stable ICU 2.0 */ 795 U_OTHER_LETTER = 5, 796 /** Mn @stable ICU 2.0 */ 797 U_NON_SPACING_MARK = 6, 798 /** Me @stable ICU 2.0 */ 799 U_ENCLOSING_MARK = 7, 800 /** Mc @stable ICU 2.0 */ 801 U_COMBINING_SPACING_MARK = 8, 802 /** Nd @stable ICU 2.0 */ 803 U_DECIMAL_DIGIT_NUMBER = 9, 804 /** Nl @stable ICU 2.0 */ 805 U_LETTER_NUMBER = 10, 806 /** No @stable ICU 2.0 */ 807 U_OTHER_NUMBER = 11, 808 /** Zs @stable ICU 2.0 */ 809 U_SPACE_SEPARATOR = 12, 810 /** Zl @stable ICU 2.0 */ 811 U_LINE_SEPARATOR = 13, 812 /** Zp @stable ICU 2.0 */ 813 U_PARAGRAPH_SEPARATOR = 14, 814 /** Cc @stable ICU 2.0 */ 815 U_CONTROL_CHAR = 15, 816 /** Cf @stable ICU 2.0 */ 817 U_FORMAT_CHAR = 16, 818 /** Co @stable ICU 2.0 */ 819 U_PRIVATE_USE_CHAR = 17, 820 /** Cs @stable ICU 2.0 */ 821 U_SURROGATE = 18, 822 /** Pd @stable ICU 2.0 */ 823 U_DASH_PUNCTUATION = 19, 824 /** Ps @stable ICU 2.0 */ 825 U_START_PUNCTUATION = 20, 826 /** Pe @stable ICU 2.0 */ 827 U_END_PUNCTUATION = 21, 828 /** Pc @stable ICU 2.0 */ 829 U_CONNECTOR_PUNCTUATION = 22, 830 /** Po @stable ICU 2.0 */ 831 U_OTHER_PUNCTUATION = 23, 832 /** Sm @stable ICU 2.0 */ 833 U_MATH_SYMBOL = 24, 834 /** Sc @stable ICU 2.0 */ 835 U_CURRENCY_SYMBOL = 25, 836 /** Sk @stable ICU 2.0 */ 837 U_MODIFIER_SYMBOL = 26, 838 /** So @stable ICU 2.0 */ 839 U_OTHER_SYMBOL = 27, 840 /** Pi @stable ICU 2.0 */ 841 U_INITIAL_PUNCTUATION = 28, 842 /** Pf @stable ICU 2.0 */ 843 U_FINAL_PUNCTUATION = 29, 844 /** 845 * One higher than the last enum UCharCategory constant. 846 * This numeric value is stable (will not change), see 847 * http://www.unicode.org/policies/stability_policy.html#Property_Value 848 * 849 * @stable ICU 2.0 850 */ 851 U_CHAR_CATEGORY_COUNT 852 } UCharCategory; 853 854 /** 855 * U_GC_XX_MASK constants are bit flags corresponding to Unicode 856 * general category values. 857 * For each category, the nth bit is set if the numeric value of the 858 * corresponding UCharCategory constant is n. 859 * 860 * There are also some U_GC_Y_MASK constants for groups of general categories 861 * like L for all letter categories. 862 * 863 * @see u_charType 864 * @see U_GET_GC_MASK 865 * @see UCharCategory 866 * @stable ICU 2.1 867 */ 868 #define U_GC_CN_MASK U_MASK(U_GENERAL_OTHER_TYPES) 869 870 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 871 #define U_GC_LU_MASK U_MASK(U_UPPERCASE_LETTER) 872 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 873 #define U_GC_LL_MASK U_MASK(U_LOWERCASE_LETTER) 874 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 875 #define U_GC_LT_MASK U_MASK(U_TITLECASE_LETTER) 876 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 877 #define U_GC_LM_MASK U_MASK(U_MODIFIER_LETTER) 878 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 879 #define U_GC_LO_MASK U_MASK(U_OTHER_LETTER) 880 881 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 882 #define U_GC_MN_MASK U_MASK(U_NON_SPACING_MARK) 883 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 884 #define U_GC_ME_MASK U_MASK(U_ENCLOSING_MARK) 885 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 886 #define U_GC_MC_MASK U_MASK(U_COMBINING_SPACING_MARK) 887 888 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 889 #define U_GC_ND_MASK U_MASK(U_DECIMAL_DIGIT_NUMBER) 890 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 891 #define U_GC_NL_MASK U_MASK(U_LETTER_NUMBER) 892 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 893 #define U_GC_NO_MASK U_MASK(U_OTHER_NUMBER) 894 895 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 896 #define U_GC_ZS_MASK U_MASK(U_SPACE_SEPARATOR) 897 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 898 #define U_GC_ZL_MASK U_MASK(U_LINE_SEPARATOR) 899 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 900 #define U_GC_ZP_MASK U_MASK(U_PARAGRAPH_SEPARATOR) 901 902 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 903 #define U_GC_CC_MASK U_MASK(U_CONTROL_CHAR) 904 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 905 #define U_GC_CF_MASK U_MASK(U_FORMAT_CHAR) 906 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 907 #define U_GC_CO_MASK U_MASK(U_PRIVATE_USE_CHAR) 908 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 909 #define U_GC_CS_MASK U_MASK(U_SURROGATE) 910 911 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 912 #define U_GC_PD_MASK U_MASK(U_DASH_PUNCTUATION) 913 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 914 #define U_GC_PS_MASK U_MASK(U_START_PUNCTUATION) 915 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 916 #define U_GC_PE_MASK U_MASK(U_END_PUNCTUATION) 917 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 918 #define U_GC_PC_MASK U_MASK(U_CONNECTOR_PUNCTUATION) 919 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 920 #define U_GC_PO_MASK U_MASK(U_OTHER_PUNCTUATION) 921 922 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 923 #define U_GC_SM_MASK U_MASK(U_MATH_SYMBOL) 924 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 925 #define U_GC_SC_MASK U_MASK(U_CURRENCY_SYMBOL) 926 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 927 #define U_GC_SK_MASK U_MASK(U_MODIFIER_SYMBOL) 928 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 929 #define U_GC_SO_MASK U_MASK(U_OTHER_SYMBOL) 930 931 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 932 #define U_GC_PI_MASK U_MASK(U_INITIAL_PUNCTUATION) 933 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 934 #define U_GC_PF_MASK U_MASK(U_FINAL_PUNCTUATION) 935 936 937 /** Mask constant for multiple UCharCategory bits (L Letters). @stable ICU 2.1 */ 938 #define U_GC_L_MASK \ 939 (U_GC_LU_MASK|U_GC_LL_MASK|U_GC_LT_MASK|U_GC_LM_MASK|U_GC_LO_MASK) 940 941 /** Mask constant for multiple UCharCategory bits (LC Cased Letters). @stable ICU 2.1 */ 942 #define U_GC_LC_MASK \ 943 (U_GC_LU_MASK|U_GC_LL_MASK|U_GC_LT_MASK) 944 945 /** Mask constant for multiple UCharCategory bits (M Marks). @stable ICU 2.1 */ 946 #define U_GC_M_MASK (U_GC_MN_MASK|U_GC_ME_MASK|U_GC_MC_MASK) 947 948 /** Mask constant for multiple UCharCategory bits (N Numbers). @stable ICU 2.1 */ 949 #define U_GC_N_MASK (U_GC_ND_MASK|U_GC_NL_MASK|U_GC_NO_MASK) 950 951 /** Mask constant for multiple UCharCategory bits (Z Separators). @stable ICU 2.1 */ 952 #define U_GC_Z_MASK (U_GC_ZS_MASK|U_GC_ZL_MASK|U_GC_ZP_MASK) 953 954 /** Mask constant for multiple UCharCategory bits (C Others). @stable ICU 2.1 */ 955 #define U_GC_C_MASK \ 956 (U_GC_CN_MASK|U_GC_CC_MASK|U_GC_CF_MASK|U_GC_CO_MASK|U_GC_CS_MASK) 957 958 /** Mask constant for multiple UCharCategory bits (P Punctuation). @stable ICU 2.1 */ 959 #define U_GC_P_MASK \ 960 (U_GC_PD_MASK|U_GC_PS_MASK|U_GC_PE_MASK|U_GC_PC_MASK|U_GC_PO_MASK| \ 961 U_GC_PI_MASK|U_GC_PF_MASK) 962 963 /** Mask constant for multiple UCharCategory bits (S Symbols). @stable ICU 2.1 */ 964 #define U_GC_S_MASK (U_GC_SM_MASK|U_GC_SC_MASK|U_GC_SK_MASK|U_GC_SO_MASK) 965 966 /** 967 * This specifies the language directional property of a character set. 968 * @stable ICU 2.0 969 */ 970 typedef enum UCharDirection { 971 /* 972 * Note: UCharDirection constants and their API comments are parsed by preparseucd.py. 973 * It matches pairs of lines like 974 * / ** <Unicode 1..3-letter Bidi_Class value> comment... * / 975 * U_<[A-Z_]+> = <integer>, 976 */ 977 978 /** L @stable ICU 2.0 */ 979 U_LEFT_TO_RIGHT = 0, 980 /** R @stable ICU 2.0 */ 981 U_RIGHT_TO_LEFT = 1, 982 /** EN @stable ICU 2.0 */ 983 U_EUROPEAN_NUMBER = 2, 984 /** ES @stable ICU 2.0 */ 985 U_EUROPEAN_NUMBER_SEPARATOR = 3, 986 /** ET @stable ICU 2.0 */ 987 U_EUROPEAN_NUMBER_TERMINATOR = 4, 988 /** AN @stable ICU 2.0 */ 989 U_ARABIC_NUMBER = 5, 990 /** CS @stable ICU 2.0 */ 991 U_COMMON_NUMBER_SEPARATOR = 6, 992 /** B @stable ICU 2.0 */ 993 U_BLOCK_SEPARATOR = 7, 994 /** S @stable ICU 2.0 */ 995 U_SEGMENT_SEPARATOR = 8, 996 /** WS @stable ICU 2.0 */ 997 U_WHITE_SPACE_NEUTRAL = 9, 998 /** ON @stable ICU 2.0 */ 999 U_OTHER_NEUTRAL = 10, 1000 /** LRE @stable ICU 2.0 */ 1001 U_LEFT_TO_RIGHT_EMBEDDING = 11, 1002 /** LRO @stable ICU 2.0 */ 1003 U_LEFT_TO_RIGHT_OVERRIDE = 12, 1004 /** AL @stable ICU 2.0 */ 1005 U_RIGHT_TO_LEFT_ARABIC = 13, 1006 /** RLE @stable ICU 2.0 */ 1007 U_RIGHT_TO_LEFT_EMBEDDING = 14, 1008 /** RLO @stable ICU 2.0 */ 1009 U_RIGHT_TO_LEFT_OVERRIDE = 15, 1010 /** PDF @stable ICU 2.0 */ 1011 U_POP_DIRECTIONAL_FORMAT = 16, 1012 /** NSM @stable ICU 2.0 */ 1013 U_DIR_NON_SPACING_MARK = 17, 1014 /** BN @stable ICU 2.0 */ 1015 U_BOUNDARY_NEUTRAL = 18, 1016 /** FSI @stable ICU 52 */ 1017 U_FIRST_STRONG_ISOLATE = 19, 1018 /** LRI @stable ICU 52 */ 1019 U_LEFT_TO_RIGHT_ISOLATE = 20, 1020 /** RLI @stable ICU 52 */ 1021 U_RIGHT_TO_LEFT_ISOLATE = 21, 1022 /** PDI @stable ICU 52 */ 1023 U_POP_DIRECTIONAL_ISOLATE = 22, 1024 #ifndef U_HIDE_DEPRECATED_API 1025 /** 1026 * One more than the highest UCharDirection value. 1027 * The highest value is available via u_getIntPropertyMaxValue(UCHAR_BIDI_CLASS). 1028 * 1029 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. 1030 */ 1031 U_CHAR_DIRECTION_COUNT 1032 #endif // U_HIDE_DEPRECATED_API 1033 } UCharDirection; 1034 1035 /** 1036 * Bidi Paired Bracket Type constants. 1037 * 1038 * @see UCHAR_BIDI_PAIRED_BRACKET_TYPE 1039 * @stable ICU 52 1040 */ 1041 typedef enum UBidiPairedBracketType { 1042 /* 1043 * Note: UBidiPairedBracketType constants are parsed by preparseucd.py. 1044 * It matches lines like 1045 * U_BPT_<Unicode Bidi_Paired_Bracket_Type value name> 1046 */ 1047 1048 /** Not a paired bracket. @stable ICU 52 */ 1049 U_BPT_NONE, 1050 /** Open paired bracket. @stable ICU 52 */ 1051 U_BPT_OPEN, 1052 /** Close paired bracket. @stable ICU 52 */ 1053 U_BPT_CLOSE, 1054 #ifndef U_HIDE_DEPRECATED_API 1055 /** 1056 * One more than the highest normal UBidiPairedBracketType value. 1057 * The highest value is available via u_getIntPropertyMaxValue(UCHAR_BIDI_PAIRED_BRACKET_TYPE). 1058 * 1059 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. 1060 */ 1061 U_BPT_COUNT /* 3 */ 1062 #endif // U_HIDE_DEPRECATED_API 1063 } UBidiPairedBracketType; 1064 1065 /** 1066 * Constants for Unicode blocks, see the Unicode Data file Blocks.txt 1067 * @stable ICU 2.0 1068 */ 1069 enum UBlockCode { 1070 /* 1071 * Note: UBlockCode constants are parsed by preparseucd.py. 1072 * It matches lines like 1073 * UBLOCK_<Unicode Block value name> = <integer>, 1074 */ 1075 1076 /** New No_Block value in Unicode 4. @stable ICU 2.6 */ 1077 UBLOCK_NO_BLOCK = 0, /*[none]*/ /* Special range indicating No_Block */ 1078 1079 /** @stable ICU 2.0 */ 1080 UBLOCK_BASIC_LATIN = 1, /*[0000]*/ 1081 1082 /** @stable ICU 2.0 */ 1083 UBLOCK_LATIN_1_SUPPLEMENT=2, /*[0080]*/ 1084 1085 /** @stable ICU 2.0 */ 1086 UBLOCK_LATIN_EXTENDED_A =3, /*[0100]*/ 1087 1088 /** @stable ICU 2.0 */ 1089 UBLOCK_LATIN_EXTENDED_B =4, /*[0180]*/ 1090 1091 /** @stable ICU 2.0 */ 1092 UBLOCK_IPA_EXTENSIONS =5, /*[0250]*/ 1093 1094 /** @stable ICU 2.0 */ 1095 UBLOCK_SPACING_MODIFIER_LETTERS =6, /*[02B0]*/ 1096 1097 /** @stable ICU 2.0 */ 1098 UBLOCK_COMBINING_DIACRITICAL_MARKS =7, /*[0300]*/ 1099 1100 /** 1101 * Unicode 3.2 renames this block to "Greek and Coptic". 1102 * @stable ICU 2.0 1103 */ 1104 UBLOCK_GREEK =8, /*[0370]*/ 1105 1106 /** @stable ICU 2.0 */ 1107 UBLOCK_CYRILLIC =9, /*[0400]*/ 1108 1109 /** @stable ICU 2.0 */ 1110 UBLOCK_ARMENIAN =10, /*[0530]*/ 1111 1112 /** @stable ICU 2.0 */ 1113 UBLOCK_HEBREW =11, /*[0590]*/ 1114 1115 /** @stable ICU 2.0 */ 1116 UBLOCK_ARABIC =12, /*[0600]*/ 1117 1118 /** @stable ICU 2.0 */ 1119 UBLOCK_SYRIAC =13, /*[0700]*/ 1120 1121 /** @stable ICU 2.0 */ 1122 UBLOCK_THAANA =14, /*[0780]*/ 1123 1124 /** @stable ICU 2.0 */ 1125 UBLOCK_DEVANAGARI =15, /*[0900]*/ 1126 1127 /** @stable ICU 2.0 */ 1128 UBLOCK_BENGALI =16, /*[0980]*/ 1129 1130 /** @stable ICU 2.0 */ 1131 UBLOCK_GURMUKHI =17, /*[0A00]*/ 1132 1133 /** @stable ICU 2.0 */ 1134 UBLOCK_GUJARATI =18, /*[0A80]*/ 1135 1136 /** @stable ICU 2.0 */ 1137 UBLOCK_ORIYA =19, /*[0B00]*/ 1138 1139 /** @stable ICU 2.0 */ 1140 UBLOCK_TAMIL =20, /*[0B80]*/ 1141 1142 /** @stable ICU 2.0 */ 1143 UBLOCK_TELUGU =21, /*[0C00]*/ 1144 1145 /** @stable ICU 2.0 */ 1146 UBLOCK_KANNADA =22, /*[0C80]*/ 1147 1148 /** @stable ICU 2.0 */ 1149 UBLOCK_MALAYALAM =23, /*[0D00]*/ 1150 1151 /** @stable ICU 2.0 */ 1152 UBLOCK_SINHALA =24, /*[0D80]*/ 1153 1154 /** @stable ICU 2.0 */ 1155 UBLOCK_THAI =25, /*[0E00]*/ 1156 1157 /** @stable ICU 2.0 */ 1158 UBLOCK_LAO =26, /*[0E80]*/ 1159 1160 /** @stable ICU 2.0 */ 1161 UBLOCK_TIBETAN =27, /*[0F00]*/ 1162 1163 /** @stable ICU 2.0 */ 1164 UBLOCK_MYANMAR =28, /*[1000]*/ 1165 1166 /** @stable ICU 2.0 */ 1167 UBLOCK_GEORGIAN =29, /*[10A0]*/ 1168 1169 /** @stable ICU 2.0 */ 1170 UBLOCK_HANGUL_JAMO =30, /*[1100]*/ 1171 1172 /** @stable ICU 2.0 */ 1173 UBLOCK_ETHIOPIC =31, /*[1200]*/ 1174 1175 /** @stable ICU 2.0 */ 1176 UBLOCK_CHEROKEE =32, /*[13A0]*/ 1177 1178 /** @stable ICU 2.0 */ 1179 UBLOCK_UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS =33, /*[1400]*/ 1180 1181 /** @stable ICU 2.0 */ 1182 UBLOCK_OGHAM =34, /*[1680]*/ 1183 1184 /** @stable ICU 2.0 */ 1185 UBLOCK_RUNIC =35, /*[16A0]*/ 1186 1187 /** @stable ICU 2.0 */ 1188 UBLOCK_KHMER =36, /*[1780]*/ 1189 1190 /** @stable ICU 2.0 */ 1191 UBLOCK_MONGOLIAN =37, /*[1800]*/ 1192 1193 /** @stable ICU 2.0 */ 1194 UBLOCK_LATIN_EXTENDED_ADDITIONAL =38, /*[1E00]*/ 1195 1196 /** @stable ICU 2.0 */ 1197 UBLOCK_GREEK_EXTENDED =39, /*[1F00]*/ 1198 1199 /** @stable ICU 2.0 */ 1200 UBLOCK_GENERAL_PUNCTUATION =40, /*[2000]*/ 1201 1202 /** @stable ICU 2.0 */ 1203 UBLOCK_SUPERSCRIPTS_AND_SUBSCRIPTS =41, /*[2070]*/ 1204 1205 /** @stable ICU 2.0 */ 1206 UBLOCK_CURRENCY_SYMBOLS =42, /*[20A0]*/ 1207 1208 /** 1209 * Unicode 3.2 renames this block to "Combining Diacritical Marks for Symbols". 1210 * @stable ICU 2.0 1211 */ 1212 UBLOCK_COMBINING_MARKS_FOR_SYMBOLS =43, /*[20D0]*/ 1213 1214 /** @stable ICU 2.0 */ 1215 UBLOCK_LETTERLIKE_SYMBOLS =44, /*[2100]*/ 1216 1217 /** @stable ICU 2.0 */ 1218 UBLOCK_NUMBER_FORMS =45, /*[2150]*/ 1219 1220 /** @stable ICU 2.0 */ 1221 UBLOCK_ARROWS =46, /*[2190]*/ 1222 1223 /** @stable ICU 2.0 */ 1224 UBLOCK_MATHEMATICAL_OPERATORS =47, /*[2200]*/ 1225 1226 /** @stable ICU 2.0 */ 1227 UBLOCK_MISCELLANEOUS_TECHNICAL =48, /*[2300]*/ 1228 1229 /** @stable ICU 2.0 */ 1230 UBLOCK_CONTROL_PICTURES =49, /*[2400]*/ 1231 1232 /** @stable ICU 2.0 */ 1233 UBLOCK_OPTICAL_CHARACTER_RECOGNITION =50, /*[2440]*/ 1234 1235 /** @stable ICU 2.0 */ 1236 UBLOCK_ENCLOSED_ALPHANUMERICS =51, /*[2460]*/ 1237 1238 /** @stable ICU 2.0 */ 1239 UBLOCK_BOX_DRAWING =52, /*[2500]*/ 1240 1241 /** @stable ICU 2.0 */ 1242 UBLOCK_BLOCK_ELEMENTS =53, /*[2580]*/ 1243 1244 /** @stable ICU 2.0 */ 1245 UBLOCK_GEOMETRIC_SHAPES =54, /*[25A0]*/ 1246 1247 /** @stable ICU 2.0 */ 1248 UBLOCK_MISCELLANEOUS_SYMBOLS =55, /*[2600]*/ 1249 1250 /** @stable ICU 2.0 */ 1251 UBLOCK_DINGBATS =56, /*[2700]*/ 1252 1253 /** @stable ICU 2.0 */ 1254 UBLOCK_BRAILLE_PATTERNS =57, /*[2800]*/ 1255 1256 /** @stable ICU 2.0 */ 1257 UBLOCK_CJK_RADICALS_SUPPLEMENT =58, /*[2E80]*/ 1258 1259 /** @stable ICU 2.0 */ 1260 UBLOCK_KANGXI_RADICALS =59, /*[2F00]*/ 1261 1262 /** @stable ICU 2.0 */ 1263 UBLOCK_IDEOGRAPHIC_DESCRIPTION_CHARACTERS =60, /*[2FF0]*/ 1264 1265 /** @stable ICU 2.0 */ 1266 UBLOCK_CJK_SYMBOLS_AND_PUNCTUATION =61, /*[3000]*/ 1267 1268 /** @stable ICU 2.0 */ 1269 UBLOCK_HIRAGANA =62, /*[3040]*/ 1270 1271 /** @stable ICU 2.0 */ 1272 UBLOCK_KATAKANA =63, /*[30A0]*/ 1273 1274 /** @stable ICU 2.0 */ 1275 UBLOCK_BOPOMOFO =64, /*[3100]*/ 1276 1277 /** @stable ICU 2.0 */ 1278 UBLOCK_HANGUL_COMPATIBILITY_JAMO =65, /*[3130]*/ 1279 1280 /** @stable ICU 2.0 */ 1281 UBLOCK_KANBUN =66, /*[3190]*/ 1282 1283 /** @stable ICU 2.0 */ 1284 UBLOCK_BOPOMOFO_EXTENDED =67, /*[31A0]*/ 1285 1286 /** @stable ICU 2.0 */ 1287 UBLOCK_ENCLOSED_CJK_LETTERS_AND_MONTHS =68, /*[3200]*/ 1288 1289 /** @stable ICU 2.0 */ 1290 UBLOCK_CJK_COMPATIBILITY =69, /*[3300]*/ 1291 1292 /** @stable ICU 2.0 */ 1293 UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_A =70, /*[3400]*/ 1294 1295 /** @stable ICU 2.0 */ 1296 UBLOCK_CJK_UNIFIED_IDEOGRAPHS =71, /*[4E00]*/ 1297 1298 /** @stable ICU 2.0 */ 1299 UBLOCK_YI_SYLLABLES =72, /*[A000]*/ 1300 1301 /** @stable ICU 2.0 */ 1302 UBLOCK_YI_RADICALS =73, /*[A490]*/ 1303 1304 /** @stable ICU 2.0 */ 1305 UBLOCK_HANGUL_SYLLABLES =74, /*[AC00]*/ 1306 1307 /** @stable ICU 2.0 */ 1308 UBLOCK_HIGH_SURROGATES =75, /*[D800]*/ 1309 1310 /** @stable ICU 2.0 */ 1311 UBLOCK_HIGH_PRIVATE_USE_SURROGATES =76, /*[DB80]*/ 1312 1313 /** @stable ICU 2.0 */ 1314 UBLOCK_LOW_SURROGATES =77, /*[DC00]*/ 1315 1316 /** 1317 * Same as UBLOCK_PRIVATE_USE. 1318 * Until Unicode 3.1.1, the corresponding block name was "Private Use", 1319 * and multiple code point ranges had this block. 1320 * Unicode 3.2 renames the block for the BMP PUA to "Private Use Area" and 1321 * adds separate blocks for the supplementary PUAs. 1322 * 1323 * @stable ICU 2.0 1324 */ 1325 UBLOCK_PRIVATE_USE_AREA =78, /*[E000]*/ 1326 /** 1327 * Same as UBLOCK_PRIVATE_USE_AREA. 1328 * Until Unicode 3.1.1, the corresponding block name was "Private Use", 1329 * and multiple code point ranges had this block. 1330 * Unicode 3.2 renames the block for the BMP PUA to "Private Use Area" and 1331 * adds separate blocks for the supplementary PUAs. 1332 * 1333 * @stable ICU 2.0 1334 */ 1335 UBLOCK_PRIVATE_USE = UBLOCK_PRIVATE_USE_AREA, 1336 1337 /** @stable ICU 2.0 */ 1338 UBLOCK_CJK_COMPATIBILITY_IDEOGRAPHS =79, /*[F900]*/ 1339 1340 /** @stable ICU 2.0 */ 1341 UBLOCK_ALPHABETIC_PRESENTATION_FORMS =80, /*[FB00]*/ 1342 1343 /** @stable ICU 2.0 */ 1344 UBLOCK_ARABIC_PRESENTATION_FORMS_A =81, /*[FB50]*/ 1345 1346 /** @stable ICU 2.0 */ 1347 UBLOCK_COMBINING_HALF_MARKS =82, /*[FE20]*/ 1348 1349 /** @stable ICU 2.0 */ 1350 UBLOCK_CJK_COMPATIBILITY_FORMS =83, /*[FE30]*/ 1351 1352 /** @stable ICU 2.0 */ 1353 UBLOCK_SMALL_FORM_VARIANTS =84, /*[FE50]*/ 1354 1355 /** @stable ICU 2.0 */ 1356 UBLOCK_ARABIC_PRESENTATION_FORMS_B =85, /*[FE70]*/ 1357 1358 /** @stable ICU 2.0 */ 1359 UBLOCK_SPECIALS =86, /*[FFF0]*/ 1360 1361 /** @stable ICU 2.0 */ 1362 UBLOCK_HALFWIDTH_AND_FULLWIDTH_FORMS =87, /*[FF00]*/ 1363 1364 /* New blocks in Unicode 3.1 */ 1365 1366 /** @stable ICU 2.0 */ 1367 UBLOCK_OLD_ITALIC = 88, /*[10300]*/ 1368 /** @stable ICU 2.0 */ 1369 UBLOCK_GOTHIC = 89, /*[10330]*/ 1370 /** @stable ICU 2.0 */ 1371 UBLOCK_DESERET = 90, /*[10400]*/ 1372 /** @stable ICU 2.0 */ 1373 UBLOCK_BYZANTINE_MUSICAL_SYMBOLS = 91, /*[1D000]*/ 1374 /** @stable ICU 2.0 */ 1375 UBLOCK_MUSICAL_SYMBOLS = 92, /*[1D100]*/ 1376 /** @stable ICU 2.0 */ 1377 UBLOCK_MATHEMATICAL_ALPHANUMERIC_SYMBOLS = 93, /*[1D400]*/ 1378 /** @stable ICU 2.0 */ 1379 UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_B = 94, /*[20000]*/ 1380 /** @stable ICU 2.0 */ 1381 UBLOCK_CJK_COMPATIBILITY_IDEOGRAPHS_SUPPLEMENT = 95, /*[2F800]*/ 1382 /** @stable ICU 2.0 */ 1383 UBLOCK_TAGS = 96, /*[E0000]*/ 1384 1385 /* New blocks in Unicode 3.2 */ 1386 1387 /** @stable ICU 3.0 */ 1388 UBLOCK_CYRILLIC_SUPPLEMENT = 97, /*[0500]*/ 1389 /** 1390 * Unicode 4.0.1 renames the "Cyrillic Supplementary" block to "Cyrillic Supplement". 1391 * @stable ICU 2.2 1392 */ 1393 UBLOCK_CYRILLIC_SUPPLEMENTARY = UBLOCK_CYRILLIC_SUPPLEMENT, 1394 /** @stable ICU 2.2 */ 1395 UBLOCK_TAGALOG = 98, /*[1700]*/ 1396 /** @stable ICU 2.2 */ 1397 UBLOCK_HANUNOO = 99, /*[1720]*/ 1398 /** @stable ICU 2.2 */ 1399 UBLOCK_BUHID = 100, /*[1740]*/ 1400 /** @stable ICU 2.2 */ 1401 UBLOCK_TAGBANWA = 101, /*[1760]*/ 1402 /** @stable ICU 2.2 */ 1403 UBLOCK_MISCELLANEOUS_MATHEMATICAL_SYMBOLS_A = 102, /*[27C0]*/ 1404 /** @stable ICU 2.2 */ 1405 UBLOCK_SUPPLEMENTAL_ARROWS_A = 103, /*[27F0]*/ 1406 /** @stable ICU 2.2 */ 1407 UBLOCK_SUPPLEMENTAL_ARROWS_B = 104, /*[2900]*/ 1408 /** @stable ICU 2.2 */ 1409 UBLOCK_MISCELLANEOUS_MATHEMATICAL_SYMBOLS_B = 105, /*[2980]*/ 1410 /** @stable ICU 2.2 */ 1411 UBLOCK_SUPPLEMENTAL_MATHEMATICAL_OPERATORS = 106, /*[2A00]*/ 1412 /** @stable ICU 2.2 */ 1413 UBLOCK_KATAKANA_PHONETIC_EXTENSIONS = 107, /*[31F0]*/ 1414 /** @stable ICU 2.2 */ 1415 UBLOCK_VARIATION_SELECTORS = 108, /*[FE00]*/ 1416 /** @stable ICU 2.2 */ 1417 UBLOCK_SUPPLEMENTARY_PRIVATE_USE_AREA_A = 109, /*[F0000]*/ 1418 /** @stable ICU 2.2 */ 1419 UBLOCK_SUPPLEMENTARY_PRIVATE_USE_AREA_B = 110, /*[100000]*/ 1420 1421 /* New blocks in Unicode 4 */ 1422 1423 /** @stable ICU 2.6 */ 1424 UBLOCK_LIMBU = 111, /*[1900]*/ 1425 /** @stable ICU 2.6 */ 1426 UBLOCK_TAI_LE = 112, /*[1950]*/ 1427 /** @stable ICU 2.6 */ 1428 UBLOCK_KHMER_SYMBOLS = 113, /*[19E0]*/ 1429 /** @stable ICU 2.6 */ 1430 UBLOCK_PHONETIC_EXTENSIONS = 114, /*[1D00]*/ 1431 /** @stable ICU 2.6 */ 1432 UBLOCK_MISCELLANEOUS_SYMBOLS_AND_ARROWS = 115, /*[2B00]*/ 1433 /** @stable ICU 2.6 */ 1434 UBLOCK_YIJING_HEXAGRAM_SYMBOLS = 116, /*[4DC0]*/ 1435 /** @stable ICU 2.6 */ 1436 UBLOCK_LINEAR_B_SYLLABARY = 117, /*[10000]*/ 1437 /** @stable ICU 2.6 */ 1438 UBLOCK_LINEAR_B_IDEOGRAMS = 118, /*[10080]*/ 1439 /** @stable ICU 2.6 */ 1440 UBLOCK_AEGEAN_NUMBERS = 119, /*[10100]*/ 1441 /** @stable ICU 2.6 */ 1442 UBLOCK_UGARITIC = 120, /*[10380]*/ 1443 /** @stable ICU 2.6 */ 1444 UBLOCK_SHAVIAN = 121, /*[10450]*/ 1445 /** @stable ICU 2.6 */ 1446 UBLOCK_OSMANYA = 122, /*[10480]*/ 1447 /** @stable ICU 2.6 */ 1448 UBLOCK_CYPRIOT_SYLLABARY = 123, /*[10800]*/ 1449 /** @stable ICU 2.6 */ 1450 UBLOCK_TAI_XUAN_JING_SYMBOLS = 124, /*[1D300]*/ 1451 /** @stable ICU 2.6 */ 1452 UBLOCK_VARIATION_SELECTORS_SUPPLEMENT = 125, /*[E0100]*/ 1453 1454 /* New blocks in Unicode 4.1 */ 1455 1456 /** @stable ICU 3.4 */ 1457 UBLOCK_ANCIENT_GREEK_MUSICAL_NOTATION = 126, /*[1D200]*/ 1458 /** @stable ICU 3.4 */ 1459 UBLOCK_ANCIENT_GREEK_NUMBERS = 127, /*[10140]*/ 1460 /** @stable ICU 3.4 */ 1461 UBLOCK_ARABIC_SUPPLEMENT = 128, /*[0750]*/ 1462 /** @stable ICU 3.4 */ 1463 UBLOCK_BUGINESE = 129, /*[1A00]*/ 1464 /** @stable ICU 3.4 */ 1465 UBLOCK_CJK_STROKES = 130, /*[31C0]*/ 1466 /** @stable ICU 3.4 */ 1467 UBLOCK_COMBINING_DIACRITICAL_MARKS_SUPPLEMENT = 131, /*[1DC0]*/ 1468 /** @stable ICU 3.4 */ 1469 UBLOCK_COPTIC = 132, /*[2C80]*/ 1470 /** @stable ICU 3.4 */ 1471 UBLOCK_ETHIOPIC_EXTENDED = 133, /*[2D80]*/ 1472 /** @stable ICU 3.4 */ 1473 UBLOCK_ETHIOPIC_SUPPLEMENT = 134, /*[1380]*/ 1474 /** @stable ICU 3.4 */ 1475 UBLOCK_GEORGIAN_SUPPLEMENT = 135, /*[2D00]*/ 1476 /** @stable ICU 3.4 */ 1477 UBLOCK_GLAGOLITIC = 136, /*[2C00]*/ 1478 /** @stable ICU 3.4 */ 1479 UBLOCK_KHAROSHTHI = 137, /*[10A00]*/ 1480 /** @stable ICU 3.4 */ 1481 UBLOCK_MODIFIER_TONE_LETTERS = 138, /*[A700]*/ 1482 /** @stable ICU 3.4 */ 1483 UBLOCK_NEW_TAI_LUE = 139, /*[1980]*/ 1484 /** @stable ICU 3.4 */ 1485 UBLOCK_OLD_PERSIAN = 140, /*[103A0]*/ 1486 /** @stable ICU 3.4 */ 1487 UBLOCK_PHONETIC_EXTENSIONS_SUPPLEMENT = 141, /*[1D80]*/ 1488 /** @stable ICU 3.4 */ 1489 UBLOCK_SUPPLEMENTAL_PUNCTUATION = 142, /*[2E00]*/ 1490 /** @stable ICU 3.4 */ 1491 UBLOCK_SYLOTI_NAGRI = 143, /*[A800]*/ 1492 /** @stable ICU 3.4 */ 1493 UBLOCK_TIFINAGH = 144, /*[2D30]*/ 1494 /** @stable ICU 3.4 */ 1495 UBLOCK_VERTICAL_FORMS = 145, /*[FE10]*/ 1496 1497 /* New blocks in Unicode 5.0 */ 1498 1499 /** @stable ICU 3.6 */ 1500 UBLOCK_NKO = 146, /*[07C0]*/ 1501 /** @stable ICU 3.6 */ 1502 UBLOCK_BALINESE = 147, /*[1B00]*/ 1503 /** @stable ICU 3.6 */ 1504 UBLOCK_LATIN_EXTENDED_C = 148, /*[2C60]*/ 1505 /** @stable ICU 3.6 */ 1506 UBLOCK_LATIN_EXTENDED_D = 149, /*[A720]*/ 1507 /** @stable ICU 3.6 */ 1508 UBLOCK_PHAGS_PA = 150, /*[A840]*/ 1509 /** @stable ICU 3.6 */ 1510 UBLOCK_PHOENICIAN = 151, /*[10900]*/ 1511 /** @stable ICU 3.6 */ 1512 UBLOCK_CUNEIFORM = 152, /*[12000]*/ 1513 /** @stable ICU 3.6 */ 1514 UBLOCK_CUNEIFORM_NUMBERS_AND_PUNCTUATION = 153, /*[12400]*/ 1515 /** @stable ICU 3.6 */ 1516 UBLOCK_COUNTING_ROD_NUMERALS = 154, /*[1D360]*/ 1517 1518 /* New blocks in Unicode 5.1 */ 1519 1520 /** @stable ICU 4.0 */ 1521 UBLOCK_SUNDANESE = 155, /*[1B80]*/ 1522 /** @stable ICU 4.0 */ 1523 UBLOCK_LEPCHA = 156, /*[1C00]*/ 1524 /** @stable ICU 4.0 */ 1525 UBLOCK_OL_CHIKI = 157, /*[1C50]*/ 1526 /** @stable ICU 4.0 */ 1527 UBLOCK_CYRILLIC_EXTENDED_A = 158, /*[2DE0]*/ 1528 /** @stable ICU 4.0 */ 1529 UBLOCK_VAI = 159, /*[A500]*/ 1530 /** @stable ICU 4.0 */ 1531 UBLOCK_CYRILLIC_EXTENDED_B = 160, /*[A640]*/ 1532 /** @stable ICU 4.0 */ 1533 UBLOCK_SAURASHTRA = 161, /*[A880]*/ 1534 /** @stable ICU 4.0 */ 1535 UBLOCK_KAYAH_LI = 162, /*[A900]*/ 1536 /** @stable ICU 4.0 */ 1537 UBLOCK_REJANG = 163, /*[A930]*/ 1538 /** @stable ICU 4.0 */ 1539 UBLOCK_CHAM = 164, /*[AA00]*/ 1540 /** @stable ICU 4.0 */ 1541 UBLOCK_ANCIENT_SYMBOLS = 165, /*[10190]*/ 1542 /** @stable ICU 4.0 */ 1543 UBLOCK_PHAISTOS_DISC = 166, /*[101D0]*/ 1544 /** @stable ICU 4.0 */ 1545 UBLOCK_LYCIAN = 167, /*[10280]*/ 1546 /** @stable ICU 4.0 */ 1547 UBLOCK_CARIAN = 168, /*[102A0]*/ 1548 /** @stable ICU 4.0 */ 1549 UBLOCK_LYDIAN = 169, /*[10920]*/ 1550 /** @stable ICU 4.0 */ 1551 UBLOCK_MAHJONG_TILES = 170, /*[1F000]*/ 1552 /** @stable ICU 4.0 */ 1553 UBLOCK_DOMINO_TILES = 171, /*[1F030]*/ 1554 1555 /* New blocks in Unicode 5.2 */ 1556 1557 /** @stable ICU 4.4 */ 1558 UBLOCK_SAMARITAN = 172, /*[0800]*/ 1559 /** @stable ICU 4.4 */ 1560 UBLOCK_UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS_EXTENDED = 173, /*[18B0]*/ 1561 /** @stable ICU 4.4 */ 1562 UBLOCK_TAI_THAM = 174, /*[1A20]*/ 1563 /** @stable ICU 4.4 */ 1564 UBLOCK_VEDIC_EXTENSIONS = 175, /*[1CD0]*/ 1565 /** @stable ICU 4.4 */ 1566 UBLOCK_LISU = 176, /*[A4D0]*/ 1567 /** @stable ICU 4.4 */ 1568 UBLOCK_BAMUM = 177, /*[A6A0]*/ 1569 /** @stable ICU 4.4 */ 1570 UBLOCK_COMMON_INDIC_NUMBER_FORMS = 178, /*[A830]*/ 1571 /** @stable ICU 4.4 */ 1572 UBLOCK_DEVANAGARI_EXTENDED = 179, /*[A8E0]*/ 1573 /** @stable ICU 4.4 */ 1574 UBLOCK_HANGUL_JAMO_EXTENDED_A = 180, /*[A960]*/ 1575 /** @stable ICU 4.4 */ 1576 UBLOCK_JAVANESE = 181, /*[A980]*/ 1577 /** @stable ICU 4.4 */ 1578 UBLOCK_MYANMAR_EXTENDED_A = 182, /*[AA60]*/ 1579 /** @stable ICU 4.4 */ 1580 UBLOCK_TAI_VIET = 183, /*[AA80]*/ 1581 /** @stable ICU 4.4 */ 1582 UBLOCK_MEETEI_MAYEK = 184, /*[ABC0]*/ 1583 /** @stable ICU 4.4 */ 1584 UBLOCK_HANGUL_JAMO_EXTENDED_B = 185, /*[D7B0]*/ 1585 /** @stable ICU 4.4 */ 1586 UBLOCK_IMPERIAL_ARAMAIC = 186, /*[10840]*/ 1587 /** @stable ICU 4.4 */ 1588 UBLOCK_OLD_SOUTH_ARABIAN = 187, /*[10A60]*/ 1589 /** @stable ICU 4.4 */ 1590 UBLOCK_AVESTAN = 188, /*[10B00]*/ 1591 /** @stable ICU 4.4 */ 1592 UBLOCK_INSCRIPTIONAL_PARTHIAN = 189, /*[10B40]*/ 1593 /** @stable ICU 4.4 */ 1594 UBLOCK_INSCRIPTIONAL_PAHLAVI = 190, /*[10B60]*/ 1595 /** @stable ICU 4.4 */ 1596 UBLOCK_OLD_TURKIC = 191, /*[10C00]*/ 1597 /** @stable ICU 4.4 */ 1598 UBLOCK_RUMI_NUMERAL_SYMBOLS = 192, /*[10E60]*/ 1599 /** @stable ICU 4.4 */ 1600 UBLOCK_KAITHI = 193, /*[11080]*/ 1601 /** @stable ICU 4.4 */ 1602 UBLOCK_EGYPTIAN_HIEROGLYPHS = 194, /*[13000]*/ 1603 /** @stable ICU 4.4 */ 1604 UBLOCK_ENCLOSED_ALPHANUMERIC_SUPPLEMENT = 195, /*[1F100]*/ 1605 /** @stable ICU 4.4 */ 1606 UBLOCK_ENCLOSED_IDEOGRAPHIC_SUPPLEMENT = 196, /*[1F200]*/ 1607 /** @stable ICU 4.4 */ 1608 UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_C = 197, /*[2A700]*/ 1609 1610 /* New blocks in Unicode 6.0 */ 1611 1612 /** @stable ICU 4.6 */ 1613 UBLOCK_MANDAIC = 198, /*[0840]*/ 1614 /** @stable ICU 4.6 */ 1615 UBLOCK_BATAK = 199, /*[1BC0]*/ 1616 /** @stable ICU 4.6 */ 1617 UBLOCK_ETHIOPIC_EXTENDED_A = 200, /*[AB00]*/ 1618 /** @stable ICU 4.6 */ 1619 UBLOCK_BRAHMI = 201, /*[11000]*/ 1620 /** @stable ICU 4.6 */ 1621 UBLOCK_BAMUM_SUPPLEMENT = 202, /*[16800]*/ 1622 /** @stable ICU 4.6 */ 1623 UBLOCK_KANA_SUPPLEMENT = 203, /*[1B000]*/ 1624 /** @stable ICU 4.6 */ 1625 UBLOCK_PLAYING_CARDS = 204, /*[1F0A0]*/ 1626 /** @stable ICU 4.6 */ 1627 UBLOCK_MISCELLANEOUS_SYMBOLS_AND_PICTOGRAPHS = 205, /*[1F300]*/ 1628 /** @stable ICU 4.6 */ 1629 UBLOCK_EMOTICONS = 206, /*[1F600]*/ 1630 /** @stable ICU 4.6 */ 1631 UBLOCK_TRANSPORT_AND_MAP_SYMBOLS = 207, /*[1F680]*/ 1632 /** @stable ICU 4.6 */ 1633 UBLOCK_ALCHEMICAL_SYMBOLS = 208, /*[1F700]*/ 1634 /** @stable ICU 4.6 */ 1635 UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_D = 209, /*[2B740]*/ 1636 1637 /* New blocks in Unicode 6.1 */ 1638 1639 /** @stable ICU 49 */ 1640 UBLOCK_ARABIC_EXTENDED_A = 210, /*[08A0]*/ 1641 /** @stable ICU 49 */ 1642 UBLOCK_ARABIC_MATHEMATICAL_ALPHABETIC_SYMBOLS = 211, /*[1EE00]*/ 1643 /** @stable ICU 49 */ 1644 UBLOCK_CHAKMA = 212, /*[11100]*/ 1645 /** @stable ICU 49 */ 1646 UBLOCK_MEETEI_MAYEK_EXTENSIONS = 213, /*[AAE0]*/ 1647 /** @stable ICU 49 */ 1648 UBLOCK_MEROITIC_CURSIVE = 214, /*[109A0]*/ 1649 /** @stable ICU 49 */ 1650 UBLOCK_MEROITIC_HIEROGLYPHS = 215, /*[10980]*/ 1651 /** @stable ICU 49 */ 1652 UBLOCK_MIAO = 216, /*[16F00]*/ 1653 /** @stable ICU 49 */ 1654 UBLOCK_SHARADA = 217, /*[11180]*/ 1655 /** @stable ICU 49 */ 1656 UBLOCK_SORA_SOMPENG = 218, /*[110D0]*/ 1657 /** @stable ICU 49 */ 1658 UBLOCK_SUNDANESE_SUPPLEMENT = 219, /*[1CC0]*/ 1659 /** @stable ICU 49 */ 1660 UBLOCK_TAKRI = 220, /*[11680]*/ 1661 1662 /* New blocks in Unicode 7.0 */ 1663 1664 /** @stable ICU 54 */ 1665 UBLOCK_BASSA_VAH = 221, /*[16AD0]*/ 1666 /** @stable ICU 54 */ 1667 UBLOCK_CAUCASIAN_ALBANIAN = 222, /*[10530]*/ 1668 /** @stable ICU 54 */ 1669 UBLOCK_COPTIC_EPACT_NUMBERS = 223, /*[102E0]*/ 1670 /** @stable ICU 54 */ 1671 UBLOCK_COMBINING_DIACRITICAL_MARKS_EXTENDED = 224, /*[1AB0]*/ 1672 /** @stable ICU 54 */ 1673 UBLOCK_DUPLOYAN = 225, /*[1BC00]*/ 1674 /** @stable ICU 54 */ 1675 UBLOCK_ELBASAN = 226, /*[10500]*/ 1676 /** @stable ICU 54 */ 1677 UBLOCK_GEOMETRIC_SHAPES_EXTENDED = 227, /*[1F780]*/ 1678 /** @stable ICU 54 */ 1679 UBLOCK_GRANTHA = 228, /*[11300]*/ 1680 /** @stable ICU 54 */ 1681 UBLOCK_KHOJKI = 229, /*[11200]*/ 1682 /** @stable ICU 54 */ 1683 UBLOCK_KHUDAWADI = 230, /*[112B0]*/ 1684 /** @stable ICU 54 */ 1685 UBLOCK_LATIN_EXTENDED_E = 231, /*[AB30]*/ 1686 /** @stable ICU 54 */ 1687 UBLOCK_LINEAR_A = 232, /*[10600]*/ 1688 /** @stable ICU 54 */ 1689 UBLOCK_MAHAJANI = 233, /*[11150]*/ 1690 /** @stable ICU 54 */ 1691 UBLOCK_MANICHAEAN = 234, /*[10AC0]*/ 1692 /** @stable ICU 54 */ 1693 UBLOCK_MENDE_KIKAKUI = 235, /*[1E800]*/ 1694 /** @stable ICU 54 */ 1695 UBLOCK_MODI = 236, /*[11600]*/ 1696 /** @stable ICU 54 */ 1697 UBLOCK_MRO = 237, /*[16A40]*/ 1698 /** @stable ICU 54 */ 1699 UBLOCK_MYANMAR_EXTENDED_B = 238, /*[A9E0]*/ 1700 /** @stable ICU 54 */ 1701 UBLOCK_NABATAEAN = 239, /*[10880]*/ 1702 /** @stable ICU 54 */ 1703 UBLOCK_OLD_NORTH_ARABIAN = 240, /*[10A80]*/ 1704 /** @stable ICU 54 */ 1705 UBLOCK_OLD_PERMIC = 241, /*[10350]*/ 1706 /** @stable ICU 54 */ 1707 UBLOCK_ORNAMENTAL_DINGBATS = 242, /*[1F650]*/ 1708 /** @stable ICU 54 */ 1709 UBLOCK_PAHAWH_HMONG = 243, /*[16B00]*/ 1710 /** @stable ICU 54 */ 1711 UBLOCK_PALMYRENE = 244, /*[10860]*/ 1712 /** @stable ICU 54 */ 1713 UBLOCK_PAU_CIN_HAU = 245, /*[11AC0]*/ 1714 /** @stable ICU 54 */ 1715 UBLOCK_PSALTER_PAHLAVI = 246, /*[10B80]*/ 1716 /** @stable ICU 54 */ 1717 UBLOCK_SHORTHAND_FORMAT_CONTROLS = 247, /*[1BCA0]*/ 1718 /** @stable ICU 54 */ 1719 UBLOCK_SIDDHAM = 248, /*[11580]*/ 1720 /** @stable ICU 54 */ 1721 UBLOCK_SINHALA_ARCHAIC_NUMBERS = 249, /*[111E0]*/ 1722 /** @stable ICU 54 */ 1723 UBLOCK_SUPPLEMENTAL_ARROWS_C = 250, /*[1F800]*/ 1724 /** @stable ICU 54 */ 1725 UBLOCK_TIRHUTA = 251, /*[11480]*/ 1726 /** @stable ICU 54 */ 1727 UBLOCK_WARANG_CITI = 252, /*[118A0]*/ 1728 1729 /* New blocks in Unicode 8.0 */ 1730 1731 /** @stable ICU 56 */ 1732 UBLOCK_AHOM = 253, /*[11700]*/ 1733 /** @stable ICU 56 */ 1734 UBLOCK_ANATOLIAN_HIEROGLYPHS = 254, /*[14400]*/ 1735 /** @stable ICU 56 */ 1736 UBLOCK_CHEROKEE_SUPPLEMENT = 255, /*[AB70]*/ 1737 /** @stable ICU 56 */ 1738 UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_E = 256, /*[2B820]*/ 1739 /** @stable ICU 56 */ 1740 UBLOCK_EARLY_DYNASTIC_CUNEIFORM = 257, /*[12480]*/ 1741 /** @stable ICU 56 */ 1742 UBLOCK_HATRAN = 258, /*[108E0]*/ 1743 /** @stable ICU 56 */ 1744 UBLOCK_MULTANI = 259, /*[11280]*/ 1745 /** @stable ICU 56 */ 1746 UBLOCK_OLD_HUNGARIAN = 260, /*[10C80]*/ 1747 /** @stable ICU 56 */ 1748 UBLOCK_SUPPLEMENTAL_SYMBOLS_AND_PICTOGRAPHS = 261, /*[1F900]*/ 1749 /** @stable ICU 56 */ 1750 UBLOCK_SUTTON_SIGNWRITING = 262, /*[1D800]*/ 1751 1752 /* New blocks in Unicode 9.0 */ 1753 1754 /** @stable ICU 58 */ 1755 UBLOCK_ADLAM = 263, /*[1E900]*/ 1756 /** @stable ICU 58 */ 1757 UBLOCK_BHAIKSUKI = 264, /*[11C00]*/ 1758 /** @stable ICU 58 */ 1759 UBLOCK_CYRILLIC_EXTENDED_C = 265, /*[1C80]*/ 1760 /** @stable ICU 58 */ 1761 UBLOCK_GLAGOLITIC_SUPPLEMENT = 266, /*[1E000]*/ 1762 /** @stable ICU 58 */ 1763 UBLOCK_IDEOGRAPHIC_SYMBOLS_AND_PUNCTUATION = 267, /*[16FE0]*/ 1764 /** @stable ICU 58 */ 1765 UBLOCK_MARCHEN = 268, /*[11C70]*/ 1766 /** @stable ICU 58 */ 1767 UBLOCK_MONGOLIAN_SUPPLEMENT = 269, /*[11660]*/ 1768 /** @stable ICU 58 */ 1769 UBLOCK_NEWA = 270, /*[11400]*/ 1770 /** @stable ICU 58 */ 1771 UBLOCK_OSAGE = 271, /*[104B0]*/ 1772 /** @stable ICU 58 */ 1773 UBLOCK_TANGUT = 272, /*[17000]*/ 1774 /** @stable ICU 58 */ 1775 UBLOCK_TANGUT_COMPONENTS = 273, /*[18800]*/ 1776 1777 // New blocks in Unicode 10.0 1778 1779 /** @stable ICU 60 */ 1780 UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_F = 274, /*[2CEB0]*/ 1781 /** @stable ICU 60 */ 1782 UBLOCK_KANA_EXTENDED_A = 275, /*[1B100]*/ 1783 /** @stable ICU 60 */ 1784 UBLOCK_MASARAM_GONDI = 276, /*[11D00]*/ 1785 /** @stable ICU 60 */ 1786 UBLOCK_NUSHU = 277, /*[1B170]*/ 1787 /** @stable ICU 60 */ 1788 UBLOCK_SOYOMBO = 278, /*[11A50]*/ 1789 /** @stable ICU 60 */ 1790 UBLOCK_SYRIAC_SUPPLEMENT = 279, /*[0860]*/ 1791 /** @stable ICU 60 */ 1792 UBLOCK_ZANABAZAR_SQUARE = 280, /*[11A00]*/ 1793 1794 // New blocks in Unicode 11.0 1795 1796 /** @stable ICU 62 */ 1797 UBLOCK_CHESS_SYMBOLS = 281, /*[1FA00]*/ 1798 /** @stable ICU 62 */ 1799 UBLOCK_DOGRA = 282, /*[11800]*/ 1800 /** @stable ICU 62 */ 1801 UBLOCK_GEORGIAN_EXTENDED = 283, /*[1C90]*/ 1802 /** @stable ICU 62 */ 1803 UBLOCK_GUNJALA_GONDI = 284, /*[11D60]*/ 1804 /** @stable ICU 62 */ 1805 UBLOCK_HANIFI_ROHINGYA = 285, /*[10D00]*/ 1806 /** @stable ICU 62 */ 1807 UBLOCK_INDIC_SIYAQ_NUMBERS = 286, /*[1EC70]*/ 1808 /** @stable ICU 62 */ 1809 UBLOCK_MAKASAR = 287, /*[11EE0]*/ 1810 /** @stable ICU 62 */ 1811 UBLOCK_MAYAN_NUMERALS = 288, /*[1D2E0]*/ 1812 /** @stable ICU 62 */ 1813 UBLOCK_MEDEFAIDRIN = 289, /*[16E40]*/ 1814 /** @stable ICU 62 */ 1815 UBLOCK_OLD_SOGDIAN = 290, /*[10F00]*/ 1816 /** @stable ICU 62 */ 1817 UBLOCK_SOGDIAN = 291, /*[10F30]*/ 1818 1819 // New blocks in Unicode 12.0 1820 1821 /** @stable ICU 64 */ 1822 UBLOCK_EGYPTIAN_HIEROGLYPH_FORMAT_CONTROLS = 292, /*[13430]*/ 1823 /** @stable ICU 64 */ 1824 UBLOCK_ELYMAIC = 293, /*[10FE0]*/ 1825 /** @stable ICU 64 */ 1826 UBLOCK_NANDINAGARI = 294, /*[119A0]*/ 1827 /** @stable ICU 64 */ 1828 UBLOCK_NYIAKENG_PUACHUE_HMONG = 295, /*[1E100]*/ 1829 /** @stable ICU 64 */ 1830 UBLOCK_OTTOMAN_SIYAQ_NUMBERS = 296, /*[1ED00]*/ 1831 /** @stable ICU 64 */ 1832 UBLOCK_SMALL_KANA_EXTENSION = 297, /*[1B130]*/ 1833 /** @stable ICU 64 */ 1834 UBLOCK_SYMBOLS_AND_PICTOGRAPHS_EXTENDED_A = 298, /*[1FA70]*/ 1835 /** @stable ICU 64 */ 1836 UBLOCK_TAMIL_SUPPLEMENT = 299, /*[11FC0]*/ 1837 /** @stable ICU 64 */ 1838 UBLOCK_WANCHO = 300, /*[1E2C0]*/ 1839 1840 // New blocks in Unicode 13.0 1841 1842 /** @stable ICU 66 */ 1843 UBLOCK_CHORASMIAN = 301, /*[10FB0]*/ 1844 /** @stable ICU 66 */ 1845 UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_G = 302, /*[30000]*/ 1846 /** @stable ICU 66 */ 1847 UBLOCK_DIVES_AKURU = 303, /*[11900]*/ 1848 /** @stable ICU 66 */ 1849 UBLOCK_KHITAN_SMALL_SCRIPT = 304, /*[18B00]*/ 1850 /** @stable ICU 66 */ 1851 UBLOCK_LISU_SUPPLEMENT = 305, /*[11FB0]*/ 1852 /** @stable ICU 66 */ 1853 UBLOCK_SYMBOLS_FOR_LEGACY_COMPUTING = 306, /*[1FB00]*/ 1854 /** @stable ICU 66 */ 1855 UBLOCK_TANGUT_SUPPLEMENT = 307, /*[18D00]*/ 1856 /** @stable ICU 66 */ 1857 UBLOCK_YEZIDI = 308, /*[10E80]*/ 1858 1859 // New blocks in Unicode 14.0 1860 1861 /** @stable ICU 70 */ 1862 UBLOCK_ARABIC_EXTENDED_B = 309, /*[0870]*/ 1863 /** @stable ICU 70 */ 1864 UBLOCK_CYPRO_MINOAN = 310, /*[12F90]*/ 1865 /** @stable ICU 70 */ 1866 UBLOCK_ETHIOPIC_EXTENDED_B = 311, /*[1E7E0]*/ 1867 /** @stable ICU 70 */ 1868 UBLOCK_KANA_EXTENDED_B = 312, /*[1AFF0]*/ 1869 /** @stable ICU 70 */ 1870 UBLOCK_LATIN_EXTENDED_F = 313, /*[10780]*/ 1871 /** @stable ICU 70 */ 1872 UBLOCK_LATIN_EXTENDED_G = 314, /*[1DF00]*/ 1873 /** @stable ICU 70 */ 1874 UBLOCK_OLD_UYGHUR = 315, /*[10F70]*/ 1875 /** @stable ICU 70 */ 1876 UBLOCK_TANGSA = 316, /*[16A70]*/ 1877 /** @stable ICU 70 */ 1878 UBLOCK_TOTO = 317, /*[1E290]*/ 1879 /** @stable ICU 70 */ 1880 UBLOCK_UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS_EXTENDED_A = 318, /*[11AB0]*/ 1881 /** @stable ICU 70 */ 1882 UBLOCK_VITHKUQI = 319, /*[10570]*/ 1883 /** @stable ICU 70 */ 1884 UBLOCK_ZNAMENNY_MUSICAL_NOTATION = 320, /*[1CF00]*/ 1885 1886 // New blocks in Unicode 15.0 1887 1888 /** @stable ICU 72 */ 1889 UBLOCK_ARABIC_EXTENDED_C = 321, /*[10EC0]*/ 1890 /** @stable ICU 72 */ 1891 UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_H = 322, /*[31350]*/ 1892 /** @stable ICU 72 */ 1893 UBLOCK_CYRILLIC_EXTENDED_D = 323, /*[1E030]*/ 1894 /** @stable ICU 72 */ 1895 UBLOCK_DEVANAGARI_EXTENDED_A = 324, /*[11B00]*/ 1896 /** @stable ICU 72 */ 1897 UBLOCK_KAKTOVIK_NUMERALS = 325, /*[1D2C0]*/ 1898 /** @stable ICU 72 */ 1899 UBLOCK_KAWI = 326, /*[11F00]*/ 1900 /** @stable ICU 72 */ 1901 UBLOCK_NAG_MUNDARI = 327, /*[1E4D0]*/ 1902 1903 #ifndef U_HIDE_DEPRECATED_API 1904 /** 1905 * One more than the highest normal UBlockCode value. 1906 * The highest value is available via u_getIntPropertyMaxValue(UCHAR_BLOCK). 1907 * 1908 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. 1909 */ 1910 UBLOCK_COUNT = 328, 1911 #endif // U_HIDE_DEPRECATED_API 1912 1913 /** @stable ICU 2.0 */ 1914 UBLOCK_INVALID_CODE=-1 1915 }; 1916 1917 /** @stable ICU 2.0 */ 1918 typedef enum UBlockCode UBlockCode; 1919 1920 /** 1921 * East Asian Width constants. 1922 * 1923 * @see UCHAR_EAST_ASIAN_WIDTH 1924 * @see u_getIntPropertyValue 1925 * @stable ICU 2.2 1926 */ 1927 typedef enum UEastAsianWidth { 1928 /* 1929 * Note: UEastAsianWidth constants are parsed by preparseucd.py. 1930 * It matches lines like 1931 * U_EA_<Unicode East_Asian_Width value name> 1932 */ 1933 1934 U_EA_NEUTRAL, /*[N]*/ 1935 U_EA_AMBIGUOUS, /*[A]*/ 1936 U_EA_HALFWIDTH, /*[H]*/ 1937 U_EA_FULLWIDTH, /*[F]*/ 1938 U_EA_NARROW, /*[Na]*/ 1939 U_EA_WIDE, /*[W]*/ 1940 #ifndef U_HIDE_DEPRECATED_API 1941 /** 1942 * One more than the highest normal UEastAsianWidth value. 1943 * The highest value is available via u_getIntPropertyMaxValue(UCHAR_EAST_ASIAN_WIDTH). 1944 * 1945 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. 1946 */ 1947 U_EA_COUNT 1948 #endif // U_HIDE_DEPRECATED_API 1949 } UEastAsianWidth; 1950 1951 /** 1952 * Selector constants for u_charName(). 1953 * u_charName() returns the "modern" name of a 1954 * Unicode character; or the name that was defined in 1955 * Unicode version 1.0, before the Unicode standard merged 1956 * with ISO-10646; or an "extended" name that gives each 1957 * Unicode code point a unique name. 1958 * 1959 * @see u_charName 1960 * @stable ICU 2.0 1961 */ 1962 typedef enum UCharNameChoice { 1963 /** Unicode character name (Name property). @stable ICU 2.0 */ 1964 U_UNICODE_CHAR_NAME, 1965 #ifndef U_HIDE_DEPRECATED_API 1966 /** 1967 * The Unicode_1_Name property value which is of little practical value. 1968 * Beginning with ICU 49, ICU APIs return an empty string for this name choice. 1969 * @deprecated ICU 49 1970 */ 1971 U_UNICODE_10_CHAR_NAME, 1972 #endif /* U_HIDE_DEPRECATED_API */ 1973 /** Standard or synthetic character name. @stable ICU 2.0 */ 1974 U_EXTENDED_CHAR_NAME = U_UNICODE_CHAR_NAME+2, 1975 /** Corrected name from NameAliases.txt. @stable ICU 4.4 */ 1976 U_CHAR_NAME_ALIAS, 1977 #ifndef U_HIDE_DEPRECATED_API 1978 /** 1979 * One more than the highest normal UCharNameChoice value. 1980 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. 1981 */ 1982 U_CHAR_NAME_CHOICE_COUNT 1983 #endif // U_HIDE_DEPRECATED_API 1984 } UCharNameChoice; 1985 1986 /** 1987 * Selector constants for u_getPropertyName() and 1988 * u_getPropertyValueName(). These selectors are used to choose which 1989 * name is returned for a given property or value. All properties and 1990 * values have a long name. Most have a short name, but some do not. 1991 * Unicode allows for additional names, beyond the long and short 1992 * name, which would be indicated by U_LONG_PROPERTY_NAME + i, where 1993 * i=1, 2,... 1994 * 1995 * @see u_getPropertyName() 1996 * @see u_getPropertyValueName() 1997 * @stable ICU 2.4 1998 */ 1999 typedef enum UPropertyNameChoice { 2000 U_SHORT_PROPERTY_NAME, 2001 U_LONG_PROPERTY_NAME, 2002 #ifndef U_HIDE_DEPRECATED_API 2003 /** 2004 * One more than the highest normal UPropertyNameChoice value. 2005 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. 2006 */ 2007 U_PROPERTY_NAME_CHOICE_COUNT 2008 #endif // U_HIDE_DEPRECATED_API 2009 } UPropertyNameChoice; 2010 2011 /** 2012 * Decomposition Type constants. 2013 * 2014 * @see UCHAR_DECOMPOSITION_TYPE 2015 * @stable ICU 2.2 2016 */ 2017 typedef enum UDecompositionType { 2018 /* 2019 * Note: UDecompositionType constants are parsed by preparseucd.py. 2020 * It matches lines like 2021 * U_DT_<Unicode Decomposition_Type value name> 2022 */ 2023 2024 U_DT_NONE, /*[none]*/ 2025 U_DT_CANONICAL, /*[can]*/ 2026 U_DT_COMPAT, /*[com]*/ 2027 U_DT_CIRCLE, /*[enc]*/ 2028 U_DT_FINAL, /*[fin]*/ 2029 U_DT_FONT, /*[font]*/ 2030 U_DT_FRACTION, /*[fra]*/ 2031 U_DT_INITIAL, /*[init]*/ 2032 U_DT_ISOLATED, /*[iso]*/ 2033 U_DT_MEDIAL, /*[med]*/ 2034 U_DT_NARROW, /*[nar]*/ 2035 U_DT_NOBREAK, /*[nb]*/ 2036 U_DT_SMALL, /*[sml]*/ 2037 U_DT_SQUARE, /*[sqr]*/ 2038 U_DT_SUB, /*[sub]*/ 2039 U_DT_SUPER, /*[sup]*/ 2040 U_DT_VERTICAL, /*[vert]*/ 2041 U_DT_WIDE, /*[wide]*/ 2042 #ifndef U_HIDE_DEPRECATED_API 2043 /** 2044 * One more than the highest normal UDecompositionType value. 2045 * The highest value is available via u_getIntPropertyMaxValue(UCHAR_DECOMPOSITION_TYPE). 2046 * 2047 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. 2048 */ 2049 U_DT_COUNT /* 18 */ 2050 #endif // U_HIDE_DEPRECATED_API 2051 } UDecompositionType; 2052 2053 /** 2054 * Joining Type constants. 2055 * 2056 * @see UCHAR_JOINING_TYPE 2057 * @stable ICU 2.2 2058 */ 2059 typedef enum UJoiningType { 2060 /* 2061 * Note: UJoiningType constants are parsed by preparseucd.py. 2062 * It matches lines like 2063 * U_JT_<Unicode Joining_Type value name> 2064 */ 2065 2066 U_JT_NON_JOINING, /*[U]*/ 2067 U_JT_JOIN_CAUSING, /*[C]*/ 2068 U_JT_DUAL_JOINING, /*[D]*/ 2069 U_JT_LEFT_JOINING, /*[L]*/ 2070 U_JT_RIGHT_JOINING, /*[R]*/ 2071 U_JT_TRANSPARENT, /*[T]*/ 2072 #ifndef U_HIDE_DEPRECATED_API 2073 /** 2074 * One more than the highest normal UJoiningType value. 2075 * The highest value is available via u_getIntPropertyMaxValue(UCHAR_JOINING_TYPE). 2076 * 2077 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. 2078 */ 2079 U_JT_COUNT /* 6 */ 2080 #endif // U_HIDE_DEPRECATED_API 2081 } UJoiningType; 2082 2083 /** 2084 * Joining Group constants. 2085 * 2086 * @see UCHAR_JOINING_GROUP 2087 * @stable ICU 2.2 2088 */ 2089 typedef enum UJoiningGroup { 2090 /* 2091 * Note: UJoiningGroup constants are parsed by preparseucd.py. 2092 * It matches lines like 2093 * U_JG_<Unicode Joining_Group value name> 2094 */ 2095 2096 U_JG_NO_JOINING_GROUP, 2097 U_JG_AIN, 2098 U_JG_ALAPH, 2099 U_JG_ALEF, 2100 U_JG_BEH, 2101 U_JG_BETH, 2102 U_JG_DAL, 2103 U_JG_DALATH_RISH, 2104 U_JG_E, 2105 U_JG_FEH, 2106 U_JG_FINAL_SEMKATH, 2107 U_JG_GAF, 2108 U_JG_GAMAL, 2109 U_JG_HAH, 2110 U_JG_TEH_MARBUTA_GOAL, /**< @stable ICU 4.6 */ 2111 U_JG_HAMZA_ON_HEH_GOAL=U_JG_TEH_MARBUTA_GOAL, 2112 U_JG_HE, 2113 U_JG_HEH, 2114 U_JG_HEH_GOAL, 2115 U_JG_HETH, 2116 U_JG_KAF, 2117 U_JG_KAPH, 2118 U_JG_KNOTTED_HEH, 2119 U_JG_LAM, 2120 U_JG_LAMADH, 2121 U_JG_MEEM, 2122 U_JG_MIM, 2123 U_JG_NOON, 2124 U_JG_NUN, 2125 U_JG_PE, 2126 U_JG_QAF, 2127 U_JG_QAPH, 2128 U_JG_REH, 2129 U_JG_REVERSED_PE, 2130 U_JG_SAD, 2131 U_JG_SADHE, 2132 U_JG_SEEN, 2133 U_JG_SEMKATH, 2134 U_JG_SHIN, 2135 U_JG_SWASH_KAF, 2136 U_JG_SYRIAC_WAW, 2137 U_JG_TAH, 2138 U_JG_TAW, 2139 U_JG_TEH_MARBUTA, 2140 U_JG_TETH, 2141 U_JG_WAW, 2142 U_JG_YEH, 2143 U_JG_YEH_BARREE, 2144 U_JG_YEH_WITH_TAIL, 2145 U_JG_YUDH, 2146 U_JG_YUDH_HE, 2147 U_JG_ZAIN, 2148 U_JG_FE, /**< @stable ICU 2.6 */ 2149 U_JG_KHAPH, /**< @stable ICU 2.6 */ 2150 U_JG_ZHAIN, /**< @stable ICU 2.6 */ 2151 U_JG_BURUSHASKI_YEH_BARREE, /**< @stable ICU 4.0 */ 2152 U_JG_FARSI_YEH, /**< @stable ICU 4.4 */ 2153 U_JG_NYA, /**< @stable ICU 4.4 */ 2154 U_JG_ROHINGYA_YEH, /**< @stable ICU 49 */ 2155 U_JG_MANICHAEAN_ALEPH, /**< @stable ICU 54 */ 2156 U_JG_MANICHAEAN_AYIN, /**< @stable ICU 54 */ 2157 U_JG_MANICHAEAN_BETH, /**< @stable ICU 54 */ 2158 U_JG_MANICHAEAN_DALETH, /**< @stable ICU 54 */ 2159 U_JG_MANICHAEAN_DHAMEDH, /**< @stable ICU 54 */ 2160 U_JG_MANICHAEAN_FIVE, /**< @stable ICU 54 */ 2161 U_JG_MANICHAEAN_GIMEL, /**< @stable ICU 54 */ 2162 U_JG_MANICHAEAN_HETH, /**< @stable ICU 54 */ 2163 U_JG_MANICHAEAN_HUNDRED, /**< @stable ICU 54 */ 2164 U_JG_MANICHAEAN_KAPH, /**< @stable ICU 54 */ 2165 U_JG_MANICHAEAN_LAMEDH, /**< @stable ICU 54 */ 2166 U_JG_MANICHAEAN_MEM, /**< @stable ICU 54 */ 2167 U_JG_MANICHAEAN_NUN, /**< @stable ICU 54 */ 2168 U_JG_MANICHAEAN_ONE, /**< @stable ICU 54 */ 2169 U_JG_MANICHAEAN_PE, /**< @stable ICU 54 */ 2170 U_JG_MANICHAEAN_QOPH, /**< @stable ICU 54 */ 2171 U_JG_MANICHAEAN_RESH, /**< @stable ICU 54 */ 2172 U_JG_MANICHAEAN_SADHE, /**< @stable ICU 54 */ 2173 U_JG_MANICHAEAN_SAMEKH, /**< @stable ICU 54 */ 2174 U_JG_MANICHAEAN_TAW, /**< @stable ICU 54 */ 2175 U_JG_MANICHAEAN_TEN, /**< @stable ICU 54 */ 2176 U_JG_MANICHAEAN_TETH, /**< @stable ICU 54 */ 2177 U_JG_MANICHAEAN_THAMEDH, /**< @stable ICU 54 */ 2178 U_JG_MANICHAEAN_TWENTY, /**< @stable ICU 54 */ 2179 U_JG_MANICHAEAN_WAW, /**< @stable ICU 54 */ 2180 U_JG_MANICHAEAN_YODH, /**< @stable ICU 54 */ 2181 U_JG_MANICHAEAN_ZAYIN, /**< @stable ICU 54 */ 2182 U_JG_STRAIGHT_WAW, /**< @stable ICU 54 */ 2183 U_JG_AFRICAN_FEH, /**< @stable ICU 58 */ 2184 U_JG_AFRICAN_NOON, /**< @stable ICU 58 */ 2185 U_JG_AFRICAN_QAF, /**< @stable ICU 58 */ 2186 2187 U_JG_MALAYALAM_BHA, /**< @stable ICU 60 */ 2188 U_JG_MALAYALAM_JA, /**< @stable ICU 60 */ 2189 U_JG_MALAYALAM_LLA, /**< @stable ICU 60 */ 2190 U_JG_MALAYALAM_LLLA, /**< @stable ICU 60 */ 2191 U_JG_MALAYALAM_NGA, /**< @stable ICU 60 */ 2192 U_JG_MALAYALAM_NNA, /**< @stable ICU 60 */ 2193 U_JG_MALAYALAM_NNNA, /**< @stable ICU 60 */ 2194 U_JG_MALAYALAM_NYA, /**< @stable ICU 60 */ 2195 U_JG_MALAYALAM_RA, /**< @stable ICU 60 */ 2196 U_JG_MALAYALAM_SSA, /**< @stable ICU 60 */ 2197 U_JG_MALAYALAM_TTA, /**< @stable ICU 60 */ 2198 2199 U_JG_HANIFI_ROHINGYA_KINNA_YA, /**< @stable ICU 62 */ 2200 U_JG_HANIFI_ROHINGYA_PA, /**< @stable ICU 62 */ 2201 2202 U_JG_THIN_YEH, /**< @stable ICU 70 */ 2203 U_JG_VERTICAL_TAIL, /**< @stable ICU 70 */ 2204 2205 #ifndef U_HIDE_DEPRECATED_API 2206 /** 2207 * One more than the highest normal UJoiningGroup value. 2208 * The highest value is available via u_getIntPropertyMaxValue(UCHAR_JOINING_GROUP). 2209 * 2210 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. 2211 */ 2212 U_JG_COUNT 2213 #endif // U_HIDE_DEPRECATED_API 2214 } UJoiningGroup; 2215 2216 /** 2217 * Grapheme Cluster Break constants. 2218 * 2219 * @see UCHAR_GRAPHEME_CLUSTER_BREAK 2220 * @stable ICU 3.4 2221 */ 2222 typedef enum UGraphemeClusterBreak { 2223 /* 2224 * Note: UGraphemeClusterBreak constants are parsed by preparseucd.py. 2225 * It matches lines like 2226 * U_GCB_<Unicode Grapheme_Cluster_Break value name> 2227 */ 2228 2229 U_GCB_OTHER = 0, /*[XX]*/ 2230 U_GCB_CONTROL = 1, /*[CN]*/ 2231 U_GCB_CR = 2, /*[CR]*/ 2232 U_GCB_EXTEND = 3, /*[EX]*/ 2233 U_GCB_L = 4, /*[L]*/ 2234 U_GCB_LF = 5, /*[LF]*/ 2235 U_GCB_LV = 6, /*[LV]*/ 2236 U_GCB_LVT = 7, /*[LVT]*/ 2237 U_GCB_T = 8, /*[T]*/ 2238 U_GCB_V = 9, /*[V]*/ 2239 /** @stable ICU 4.0 */ 2240 U_GCB_SPACING_MARK = 10, /*[SM]*/ /* from here on: new in Unicode 5.1/ICU 4.0 */ 2241 /** @stable ICU 4.0 */ 2242 U_GCB_PREPEND = 11, /*[PP]*/ 2243 /** @stable ICU 50 */ 2244 U_GCB_REGIONAL_INDICATOR = 12, /*[RI]*/ /* new in Unicode 6.2/ICU 50 */ 2245 /** @stable ICU 58 */ 2246 U_GCB_E_BASE = 13, /*[EB]*/ /* from here on: new in Unicode 9.0/ICU 58 */ 2247 /** @stable ICU 58 */ 2248 U_GCB_E_BASE_GAZ = 14, /*[EBG]*/ 2249 /** @stable ICU 58 */ 2250 U_GCB_E_MODIFIER = 15, /*[EM]*/ 2251 /** @stable ICU 58 */ 2252 U_GCB_GLUE_AFTER_ZWJ = 16, /*[GAZ]*/ 2253 /** @stable ICU 58 */ 2254 U_GCB_ZWJ = 17, /*[ZWJ]*/ 2255 2256 #ifndef U_HIDE_DEPRECATED_API 2257 /** 2258 * One more than the highest normal UGraphemeClusterBreak value. 2259 * The highest value is available via u_getIntPropertyMaxValue(UCHAR_GRAPHEME_CLUSTER_BREAK). 2260 * 2261 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. 2262 */ 2263 U_GCB_COUNT = 18 2264 #endif // U_HIDE_DEPRECATED_API 2265 } UGraphemeClusterBreak; 2266 2267 /** 2268 * Word Break constants. 2269 * (UWordBreak is a pre-existing enum type in ubrk.h for word break status tags.) 2270 * 2271 * @see UCHAR_WORD_BREAK 2272 * @stable ICU 3.4 2273 */ 2274 typedef enum UWordBreakValues { 2275 /* 2276 * Note: UWordBreakValues constants are parsed by preparseucd.py. 2277 * It matches lines like 2278 * U_WB_<Unicode Word_Break value name> 2279 */ 2280 2281 U_WB_OTHER = 0, /*[XX]*/ 2282 U_WB_ALETTER = 1, /*[LE]*/ 2283 U_WB_FORMAT = 2, /*[FO]*/ 2284 U_WB_KATAKANA = 3, /*[KA]*/ 2285 U_WB_MIDLETTER = 4, /*[ML]*/ 2286 U_WB_MIDNUM = 5, /*[MN]*/ 2287 U_WB_NUMERIC = 6, /*[NU]*/ 2288 U_WB_EXTENDNUMLET = 7, /*[EX]*/ 2289 /** @stable ICU 4.0 */ 2290 U_WB_CR = 8, /*[CR]*/ /* from here on: new in Unicode 5.1/ICU 4.0 */ 2291 /** @stable ICU 4.0 */ 2292 U_WB_EXTEND = 9, /*[Extend]*/ 2293 /** @stable ICU 4.0 */ 2294 U_WB_LF = 10, /*[LF]*/ 2295 /** @stable ICU 4.0 */ 2296 U_WB_MIDNUMLET =11, /*[MB]*/ 2297 /** @stable ICU 4.0 */ 2298 U_WB_NEWLINE =12, /*[NL]*/ 2299 /** @stable ICU 50 */ 2300 U_WB_REGIONAL_INDICATOR = 13, /*[RI]*/ /* new in Unicode 6.2/ICU 50 */ 2301 /** @stable ICU 52 */ 2302 U_WB_HEBREW_LETTER = 14, /*[HL]*/ /* from here on: new in Unicode 6.3/ICU 52 */ 2303 /** @stable ICU 52 */ 2304 U_WB_SINGLE_QUOTE = 15, /*[SQ]*/ 2305 /** @stable ICU 52 */ 2306 U_WB_DOUBLE_QUOTE = 16, /*[DQ]*/ 2307 /** @stable ICU 58 */ 2308 U_WB_E_BASE = 17, /*[EB]*/ /* from here on: new in Unicode 9.0/ICU 58 */ 2309 /** @stable ICU 58 */ 2310 U_WB_E_BASE_GAZ = 18, /*[EBG]*/ 2311 /** @stable ICU 58 */ 2312 U_WB_E_MODIFIER = 19, /*[EM]*/ 2313 /** @stable ICU 58 */ 2314 U_WB_GLUE_AFTER_ZWJ = 20, /*[GAZ]*/ 2315 /** @stable ICU 58 */ 2316 U_WB_ZWJ = 21, /*[ZWJ]*/ 2317 /** @stable ICU 62 */ 2318 U_WB_WSEGSPACE = 22, /*[WSEGSPACE]*/ 2319 2320 #ifndef U_HIDE_DEPRECATED_API 2321 /** 2322 * One more than the highest normal UWordBreakValues value. 2323 * The highest value is available via u_getIntPropertyMaxValue(UCHAR_WORD_BREAK). 2324 * 2325 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. 2326 */ 2327 U_WB_COUNT = 23 2328 #endif // U_HIDE_DEPRECATED_API 2329 } UWordBreakValues; 2330 2331 /** 2332 * Sentence Break constants. 2333 * 2334 * @see UCHAR_SENTENCE_BREAK 2335 * @stable ICU 3.4 2336 */ 2337 typedef enum USentenceBreak { 2338 /* 2339 * Note: USentenceBreak constants are parsed by preparseucd.py. 2340 * It matches lines like 2341 * U_SB_<Unicode Sentence_Break value name> 2342 */ 2343 2344 U_SB_OTHER = 0, /*[XX]*/ 2345 U_SB_ATERM = 1, /*[AT]*/ 2346 U_SB_CLOSE = 2, /*[CL]*/ 2347 U_SB_FORMAT = 3, /*[FO]*/ 2348 U_SB_LOWER = 4, /*[LO]*/ 2349 U_SB_NUMERIC = 5, /*[NU]*/ 2350 U_SB_OLETTER = 6, /*[LE]*/ 2351 U_SB_SEP = 7, /*[SE]*/ 2352 U_SB_SP = 8, /*[SP]*/ 2353 U_SB_STERM = 9, /*[ST]*/ 2354 U_SB_UPPER = 10, /*[UP]*/ 2355 U_SB_CR = 11, /*[CR]*/ /* from here on: new in Unicode 5.1/ICU 4.0 */ 2356 U_SB_EXTEND = 12, /*[EX]*/ 2357 U_SB_LF = 13, /*[LF]*/ 2358 U_SB_SCONTINUE = 14, /*[SC]*/ 2359 #ifndef U_HIDE_DEPRECATED_API 2360 /** 2361 * One more than the highest normal USentenceBreak value. 2362 * The highest value is available via u_getIntPropertyMaxValue(UCHAR_SENTENCE_BREAK). 2363 * 2364 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. 2365 */ 2366 U_SB_COUNT = 15 2367 #endif // U_HIDE_DEPRECATED_API 2368 } USentenceBreak; 2369 2370 /** 2371 * Line Break constants. 2372 * 2373 * @see UCHAR_LINE_BREAK 2374 * @stable ICU 2.2 2375 */ 2376 typedef enum ULineBreak { 2377 /* 2378 * Note: ULineBreak constants are parsed by preparseucd.py. 2379 * It matches lines like 2380 * U_LB_<Unicode Line_Break value name> 2381 */ 2382 2383 U_LB_UNKNOWN = 0, /*[XX]*/ 2384 U_LB_AMBIGUOUS = 1, /*[AI]*/ 2385 U_LB_ALPHABETIC = 2, /*[AL]*/ 2386 U_LB_BREAK_BOTH = 3, /*[B2]*/ 2387 U_LB_BREAK_AFTER = 4, /*[BA]*/ 2388 U_LB_BREAK_BEFORE = 5, /*[BB]*/ 2389 U_LB_MANDATORY_BREAK = 6, /*[BK]*/ 2390 U_LB_CONTINGENT_BREAK = 7, /*[CB]*/ 2391 U_LB_CLOSE_PUNCTUATION = 8, /*[CL]*/ 2392 U_LB_COMBINING_MARK = 9, /*[CM]*/ 2393 U_LB_CARRIAGE_RETURN = 10, /*[CR]*/ 2394 U_LB_EXCLAMATION = 11, /*[EX]*/ 2395 U_LB_GLUE = 12, /*[GL]*/ 2396 U_LB_HYPHEN = 13, /*[HY]*/ 2397 U_LB_IDEOGRAPHIC = 14, /*[ID]*/ 2398 /** Renamed from the misspelled "inseperable" in Unicode 4.0.1/ICU 3.0 @stable ICU 3.0 */ 2399 U_LB_INSEPARABLE = 15, /*[IN]*/ 2400 U_LB_INSEPERABLE = U_LB_INSEPARABLE, 2401 U_LB_INFIX_NUMERIC = 16, /*[IS]*/ 2402 U_LB_LINE_FEED = 17, /*[LF]*/ 2403 U_LB_NONSTARTER = 18, /*[NS]*/ 2404 U_LB_NUMERIC = 19, /*[NU]*/ 2405 U_LB_OPEN_PUNCTUATION = 20, /*[OP]*/ 2406 U_LB_POSTFIX_NUMERIC = 21, /*[PO]*/ 2407 U_LB_PREFIX_NUMERIC = 22, /*[PR]*/ 2408 U_LB_QUOTATION = 23, /*[QU]*/ 2409 U_LB_COMPLEX_CONTEXT = 24, /*[SA]*/ 2410 U_LB_SURROGATE = 25, /*[SG]*/ 2411 U_LB_SPACE = 26, /*[SP]*/ 2412 U_LB_BREAK_SYMBOLS = 27, /*[SY]*/ 2413 U_LB_ZWSPACE = 28, /*[ZW]*/ 2414 /** @stable ICU 2.6 */ 2415 U_LB_NEXT_LINE = 29, /*[NL]*/ /* from here on: new in Unicode 4/ICU 2.6 */ 2416 /** @stable ICU 2.6 */ 2417 U_LB_WORD_JOINER = 30, /*[WJ]*/ 2418 /** @stable ICU 3.4 */ 2419 U_LB_H2 = 31, /*[H2]*/ /* from here on: new in Unicode 4.1/ICU 3.4 */ 2420 /** @stable ICU 3.4 */ 2421 U_LB_H3 = 32, /*[H3]*/ 2422 /** @stable ICU 3.4 */ 2423 U_LB_JL = 33, /*[JL]*/ 2424 /** @stable ICU 3.4 */ 2425 U_LB_JT = 34, /*[JT]*/ 2426 /** @stable ICU 3.4 */ 2427 U_LB_JV = 35, /*[JV]*/ 2428 /** @stable ICU 4.4 */ 2429 U_LB_CLOSE_PARENTHESIS = 36, /*[CP]*/ /* new in Unicode 5.2/ICU 4.4 */ 2430 /** @stable ICU 49 */ 2431 U_LB_CONDITIONAL_JAPANESE_STARTER = 37,/*[CJ]*/ /* new in Unicode 6.1/ICU 49 */ 2432 /** @stable ICU 49 */ 2433 U_LB_HEBREW_LETTER = 38, /*[HL]*/ /* new in Unicode 6.1/ICU 49 */ 2434 /** @stable ICU 50 */ 2435 U_LB_REGIONAL_INDICATOR = 39,/*[RI]*/ /* new in Unicode 6.2/ICU 50 */ 2436 /** @stable ICU 58 */ 2437 U_LB_E_BASE = 40, /*[EB]*/ /* from here on: new in Unicode 9.0/ICU 58 */ 2438 /** @stable ICU 58 */ 2439 U_LB_E_MODIFIER = 41, /*[EM]*/ 2440 /** @stable ICU 58 */ 2441 U_LB_ZWJ = 42, /*[ZWJ]*/ 2442 #ifndef U_HIDE_DEPRECATED_API 2443 /** 2444 * One more than the highest normal ULineBreak value. 2445 * The highest value is available via u_getIntPropertyMaxValue(UCHAR_LINE_BREAK). 2446 * 2447 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. 2448 */ 2449 U_LB_COUNT = 43 2450 #endif // U_HIDE_DEPRECATED_API 2451 } ULineBreak; 2452 2453 /** 2454 * Numeric Type constants. 2455 * 2456 * @see UCHAR_NUMERIC_TYPE 2457 * @stable ICU 2.2 2458 */ 2459 typedef enum UNumericType { 2460 /* 2461 * Note: UNumericType constants are parsed by preparseucd.py. 2462 * It matches lines like 2463 * U_NT_<Unicode Numeric_Type value name> 2464 */ 2465 2466 U_NT_NONE, /*[None]*/ 2467 U_NT_DECIMAL, /*[de]*/ 2468 U_NT_DIGIT, /*[di]*/ 2469 U_NT_NUMERIC, /*[nu]*/ 2470 #ifndef U_HIDE_DEPRECATED_API 2471 /** 2472 * One more than the highest normal UNumericType value. 2473 * The highest value is available via u_getIntPropertyMaxValue(UCHAR_NUMERIC_TYPE). 2474 * 2475 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. 2476 */ 2477 U_NT_COUNT 2478 #endif // U_HIDE_DEPRECATED_API 2479 } UNumericType; 2480 2481 /** 2482 * Hangul Syllable Type constants. 2483 * 2484 * @see UCHAR_HANGUL_SYLLABLE_TYPE 2485 * @stable ICU 2.6 2486 */ 2487 typedef enum UHangulSyllableType { 2488 /* 2489 * Note: UHangulSyllableType constants are parsed by preparseucd.py. 2490 * It matches lines like 2491 * U_HST_<Unicode Hangul_Syllable_Type value name> 2492 */ 2493 2494 U_HST_NOT_APPLICABLE, /*[NA]*/ 2495 U_HST_LEADING_JAMO, /*[L]*/ 2496 U_HST_VOWEL_JAMO, /*[V]*/ 2497 U_HST_TRAILING_JAMO, /*[T]*/ 2498 U_HST_LV_SYLLABLE, /*[LV]*/ 2499 U_HST_LVT_SYLLABLE, /*[LVT]*/ 2500 #ifndef U_HIDE_DEPRECATED_API 2501 /** 2502 * One more than the highest normal UHangulSyllableType value. 2503 * The highest value is available via u_getIntPropertyMaxValue(UCHAR_HANGUL_SYLLABLE_TYPE). 2504 * 2505 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. 2506 */ 2507 U_HST_COUNT 2508 #endif // U_HIDE_DEPRECATED_API 2509 } UHangulSyllableType; 2510 2511 /** 2512 * Indic Positional Category constants. 2513 * 2514 * @see UCHAR_INDIC_POSITIONAL_CATEGORY 2515 * @stable ICU 63 2516 */ 2517 typedef enum UIndicPositionalCategory { 2518 /* 2519 * Note: UIndicPositionalCategory constants are parsed by preparseucd.py. 2520 * It matches lines like 2521 * U_INPC_<Unicode Indic_Positional_Category value name> 2522 */ 2523 2524 /** @stable ICU 63 */ 2525 U_INPC_NA, 2526 /** @stable ICU 63 */ 2527 U_INPC_BOTTOM, 2528 /** @stable ICU 63 */ 2529 U_INPC_BOTTOM_AND_LEFT, 2530 /** @stable ICU 63 */ 2531 U_INPC_BOTTOM_AND_RIGHT, 2532 /** @stable ICU 63 */ 2533 U_INPC_LEFT, 2534 /** @stable ICU 63 */ 2535 U_INPC_LEFT_AND_RIGHT, 2536 /** @stable ICU 63 */ 2537 U_INPC_OVERSTRUCK, 2538 /** @stable ICU 63 */ 2539 U_INPC_RIGHT, 2540 /** @stable ICU 63 */ 2541 U_INPC_TOP, 2542 /** @stable ICU 63 */ 2543 U_INPC_TOP_AND_BOTTOM, 2544 /** @stable ICU 63 */ 2545 U_INPC_TOP_AND_BOTTOM_AND_RIGHT, 2546 /** @stable ICU 63 */ 2547 U_INPC_TOP_AND_LEFT, 2548 /** @stable ICU 63 */ 2549 U_INPC_TOP_AND_LEFT_AND_RIGHT, 2550 /** @stable ICU 63 */ 2551 U_INPC_TOP_AND_RIGHT, 2552 /** @stable ICU 63 */ 2553 U_INPC_VISUAL_ORDER_LEFT, 2554 /** @stable ICU 66 */ 2555 U_INPC_TOP_AND_BOTTOM_AND_LEFT, 2556 } UIndicPositionalCategory; 2557 2558 /** 2559 * Indic Syllabic Category constants. 2560 * 2561 * @see UCHAR_INDIC_SYLLABIC_CATEGORY 2562 * @stable ICU 63 2563 */ 2564 typedef enum UIndicSyllabicCategory { 2565 /* 2566 * Note: UIndicSyllabicCategory constants are parsed by preparseucd.py. 2567 * It matches lines like 2568 * U_INSC_<Unicode Indic_Syllabic_Category value name> 2569 */ 2570 2571 /** @stable ICU 63 */ 2572 U_INSC_OTHER, 2573 /** @stable ICU 63 */ 2574 U_INSC_AVAGRAHA, 2575 /** @stable ICU 63 */ 2576 U_INSC_BINDU, 2577 /** @stable ICU 63 */ 2578 U_INSC_BRAHMI_JOINING_NUMBER, 2579 /** @stable ICU 63 */ 2580 U_INSC_CANTILLATION_MARK, 2581 /** @stable ICU 63 */ 2582 U_INSC_CONSONANT, 2583 /** @stable ICU 63 */ 2584 U_INSC_CONSONANT_DEAD, 2585 /** @stable ICU 63 */ 2586 U_INSC_CONSONANT_FINAL, 2587 /** @stable ICU 63 */ 2588 U_INSC_CONSONANT_HEAD_LETTER, 2589 /** @stable ICU 63 */ 2590 U_INSC_CONSONANT_INITIAL_POSTFIXED, 2591 /** @stable ICU 63 */ 2592 U_INSC_CONSONANT_KILLER, 2593 /** @stable ICU 63 */ 2594 U_INSC_CONSONANT_MEDIAL, 2595 /** @stable ICU 63 */ 2596 U_INSC_CONSONANT_PLACEHOLDER, 2597 /** @stable ICU 63 */ 2598 U_INSC_CONSONANT_PRECEDING_REPHA, 2599 /** @stable ICU 63 */ 2600 U_INSC_CONSONANT_PREFIXED, 2601 /** @stable ICU 63 */ 2602 U_INSC_CONSONANT_SUBJOINED, 2603 /** @stable ICU 63 */ 2604 U_INSC_CONSONANT_SUCCEEDING_REPHA, 2605 /** @stable ICU 63 */ 2606 U_INSC_CONSONANT_WITH_STACKER, 2607 /** @stable ICU 63 */ 2608 U_INSC_GEMINATION_MARK, 2609 /** @stable ICU 63 */ 2610 U_INSC_INVISIBLE_STACKER, 2611 /** @stable ICU 63 */ 2612 U_INSC_JOINER, 2613 /** @stable ICU 63 */ 2614 U_INSC_MODIFYING_LETTER, 2615 /** @stable ICU 63 */ 2616 U_INSC_NON_JOINER, 2617 /** @stable ICU 63 */ 2618 U_INSC_NUKTA, 2619 /** @stable ICU 63 */ 2620 U_INSC_NUMBER, 2621 /** @stable ICU 63 */ 2622 U_INSC_NUMBER_JOINER, 2623 /** @stable ICU 63 */ 2624 U_INSC_PURE_KILLER, 2625 /** @stable ICU 63 */ 2626 U_INSC_REGISTER_SHIFTER, 2627 /** @stable ICU 63 */ 2628 U_INSC_SYLLABLE_MODIFIER, 2629 /** @stable ICU 63 */ 2630 U_INSC_TONE_LETTER, 2631 /** @stable ICU 63 */ 2632 U_INSC_TONE_MARK, 2633 /** @stable ICU 63 */ 2634 U_INSC_VIRAMA, 2635 /** @stable ICU 63 */ 2636 U_INSC_VISARGA, 2637 /** @stable ICU 63 */ 2638 U_INSC_VOWEL, 2639 /** @stable ICU 63 */ 2640 U_INSC_VOWEL_DEPENDENT, 2641 /** @stable ICU 63 */ 2642 U_INSC_VOWEL_INDEPENDENT, 2643 } UIndicSyllabicCategory; 2644 2645 /** 2646 * Vertical Orientation constants. 2647 * 2648 * @see UCHAR_VERTICAL_ORIENTATION 2649 * @stable ICU 63 2650 */ 2651 typedef enum UVerticalOrientation { 2652 /* 2653 * Note: UVerticalOrientation constants are parsed by preparseucd.py. 2654 * It matches lines like 2655 * U_VO_<Unicode Vertical_Orientation value name> 2656 */ 2657 2658 /** @stable ICU 63 */ 2659 U_VO_ROTATED, 2660 /** @stable ICU 63 */ 2661 U_VO_TRANSFORMED_ROTATED, 2662 /** @stable ICU 63 */ 2663 U_VO_TRANSFORMED_UPRIGHT, 2664 /** @stable ICU 63 */ 2665 U_VO_UPRIGHT, 2666 } UVerticalOrientation; 2667 2668 /** 2669 * Check a binary Unicode property for a code point. 2670 * 2671 * Unicode, especially in version 3.2, defines many more properties than the 2672 * original set in UnicodeData.txt. 2673 * 2674 * The properties APIs are intended to reflect Unicode properties as defined 2675 * in the Unicode Character Database (UCD) and Unicode Technical Reports (UTR). 2676 * For details about the properties see http://www.unicode.org/ucd/ . 2677 * For names of Unicode properties see the UCD file PropertyAliases.txt. 2678 * 2679 * Important: If ICU is built with UCD files from Unicode versions below 3.2, 2680 * then properties marked with "new in Unicode 3.2" are not or not fully available. 2681 * 2682 * @param c Code point to test. 2683 * @param which UProperty selector constant, identifies which binary property to check. 2684 * Must be UCHAR_BINARY_START<=which<UCHAR_BINARY_LIMIT. 2685 * @return true or false according to the binary Unicode property value for c. 2686 * Also false if 'which' is out of bounds or if the Unicode version 2687 * does not have data for the property at all. 2688 * 2689 * @see UProperty 2690 * @see u_getBinaryPropertySet 2691 * @see u_getIntPropertyValue 2692 * @see u_getUnicodeVersion 2693 * @stable ICU 2.1 2694 */ 2695 U_CAPI UBool U_EXPORT2 2696 u_hasBinaryProperty(UChar32 c, UProperty which); 2697 2698 /** 2699 * Returns true if the property is true for the string. 2700 * Same as u_hasBinaryProperty(single code point, which) 2701 * if the string contains exactly one code point. 2702 * 2703 * Most properties apply only to single code points. 2704 * <a href="https://www.unicode.org/reports/tr51/#Emoji_Sets">UTS #51 Unicode Emoji</a> 2705 * defines several properties of strings. 2706 * 2707 * @param s String to test. 2708 * @param length Length of the string, or negative if NUL-terminated. 2709 * @param which UProperty selector constant, identifies which binary property to check. 2710 * Must be UCHAR_BINARY_START<=which<UCHAR_BINARY_LIMIT. 2711 * @return true or false according to the binary Unicode property value for the string. 2712 * Also false if 'which' is out of bounds or if the Unicode version 2713 * does not have data for the property at all. 2714 * 2715 * @see UProperty 2716 * @see u_hasBinaryProperty 2717 * @see u_getBinaryPropertySet 2718 * @see u_getIntPropertyValue 2719 * @see u_getUnicodeVersion 2720 * @stable ICU 70 2721 */ 2722 U_CAPI UBool U_EXPORT2 2723 u_stringHasBinaryProperty(const UChar *s, int32_t length, UProperty which); 2724 2725 /** 2726 * Returns a frozen USet for a binary property. 2727 * The library retains ownership over the returned object. 2728 * Sets an error code if the property number is not one for a binary property. 2729 * 2730 * The returned set contains all code points for which the property is true. 2731 * 2732 * @param property UCHAR_BINARY_START..UCHAR_BINARY_LIMIT-1 2733 * @param pErrorCode an in/out ICU UErrorCode 2734 * @return the property as a set 2735 * @see UProperty 2736 * @see u_hasBinaryProperty 2737 * @see Unicode::fromUSet 2738 * @stable ICU 63 2739 */ 2740 U_CAPI const USet * U_EXPORT2 2741 u_getBinaryPropertySet(UProperty property, UErrorCode *pErrorCode); 2742 2743 /** 2744 * Check if a code point has the Alphabetic Unicode property. 2745 * Same as u_hasBinaryProperty(c, UCHAR_ALPHABETIC). 2746 * This is different from u_isalpha! 2747 * @param c Code point to test 2748 * @return true if the code point has the Alphabetic Unicode property, false otherwise 2749 * 2750 * @see UCHAR_ALPHABETIC 2751 * @see u_isalpha 2752 * @see u_hasBinaryProperty 2753 * @stable ICU 2.1 2754 */ 2755 U_CAPI UBool U_EXPORT2 2756 u_isUAlphabetic(UChar32 c); 2757 2758 /** 2759 * Check if a code point has the Lowercase Unicode property. 2760 * Same as u_hasBinaryProperty(c, UCHAR_LOWERCASE). 2761 * This is different from u_islower! 2762 * @param c Code point to test 2763 * @return true if the code point has the Lowercase Unicode property, false otherwise 2764 * 2765 * @see UCHAR_LOWERCASE 2766 * @see u_islower 2767 * @see u_hasBinaryProperty 2768 * @stable ICU 2.1 2769 */ 2770 U_CAPI UBool U_EXPORT2 2771 u_isULowercase(UChar32 c); 2772 2773 /** 2774 * Check if a code point has the Uppercase Unicode property. 2775 * Same as u_hasBinaryProperty(c, UCHAR_UPPERCASE). 2776 * This is different from u_isupper! 2777 * @param c Code point to test 2778 * @return true if the code point has the Uppercase Unicode property, false otherwise 2779 * 2780 * @see UCHAR_UPPERCASE 2781 * @see u_isupper 2782 * @see u_hasBinaryProperty 2783 * @stable ICU 2.1 2784 */ 2785 U_CAPI UBool U_EXPORT2 2786 u_isUUppercase(UChar32 c); 2787 2788 /** 2789 * Check if a code point has the White_Space Unicode property. 2790 * Same as u_hasBinaryProperty(c, UCHAR_WHITE_SPACE). 2791 * This is different from both u_isspace and u_isWhitespace! 2792 * 2793 * Note: There are several ICU whitespace functions; please see the uchar.h 2794 * file documentation for a detailed comparison. 2795 * 2796 * @param c Code point to test 2797 * @return true if the code point has the White_Space Unicode property, false otherwise. 2798 * 2799 * @see UCHAR_WHITE_SPACE 2800 * @see u_isWhitespace 2801 * @see u_isspace 2802 * @see u_isJavaSpaceChar 2803 * @see u_hasBinaryProperty 2804 * @stable ICU 2.1 2805 */ 2806 U_CAPI UBool U_EXPORT2 2807 u_isUWhiteSpace(UChar32 c); 2808 2809 /** 2810 * Get the property value for an enumerated or integer Unicode property for a code point. 2811 * Also returns binary and mask property values. 2812 * 2813 * Unicode, especially in version 3.2, defines many more properties than the 2814 * original set in UnicodeData.txt. 2815 * 2816 * The properties APIs are intended to reflect Unicode properties as defined 2817 * in the Unicode Character Database (UCD) and Unicode Technical Reports (UTR). 2818 * For details about the properties see http://www.unicode.org/ . 2819 * For names of Unicode properties see the UCD file PropertyAliases.txt. 2820 * 2821 * Sample usage: 2822 * UEastAsianWidth ea=(UEastAsianWidth)u_getIntPropertyValue(c, UCHAR_EAST_ASIAN_WIDTH); 2823 * UBool b=(UBool)u_getIntPropertyValue(c, UCHAR_IDEOGRAPHIC); 2824 * 2825 * @param c Code point to test. 2826 * @param which UProperty selector constant, identifies which property to check. 2827 * Must be UCHAR_BINARY_START<=which<UCHAR_BINARY_LIMIT 2828 * or UCHAR_INT_START<=which<UCHAR_INT_LIMIT 2829 * or UCHAR_MASK_START<=which<UCHAR_MASK_LIMIT. 2830 * @return Numeric value that is directly the property value or, 2831 * for enumerated properties, corresponds to the numeric value of the enumerated 2832 * constant of the respective property value enumeration type 2833 * (cast to enum type if necessary). 2834 * Returns 0 or 1 (for false/true) for binary Unicode properties. 2835 * Returns a bit-mask for mask properties. 2836 * Returns 0 if 'which' is out of bounds or if the Unicode version 2837 * does not have data for the property at all, or not for this code point. 2838 * 2839 * @see UProperty 2840 * @see u_hasBinaryProperty 2841 * @see u_getIntPropertyMinValue 2842 * @see u_getIntPropertyMaxValue 2843 * @see u_getIntPropertyMap 2844 * @see u_getUnicodeVersion 2845 * @stable ICU 2.2 2846 */ 2847 U_CAPI int32_t U_EXPORT2 2848 u_getIntPropertyValue(UChar32 c, UProperty which); 2849 2850 /** 2851 * Get the minimum value for an enumerated/integer/binary Unicode property. 2852 * Can be used together with u_getIntPropertyMaxValue 2853 * to allocate arrays of UnicodeSet or similar. 2854 * 2855 * @param which UProperty selector constant, identifies which binary property to check. 2856 * Must be UCHAR_BINARY_START<=which<UCHAR_BINARY_LIMIT 2857 * or UCHAR_INT_START<=which<UCHAR_INT_LIMIT. 2858 * @return Minimum value returned by u_getIntPropertyValue for a Unicode property. 2859 * 0 if the property selector is out of range. 2860 * 2861 * @see UProperty 2862 * @see u_hasBinaryProperty 2863 * @see u_getUnicodeVersion 2864 * @see u_getIntPropertyMaxValue 2865 * @see u_getIntPropertyValue 2866 * @stable ICU 2.2 2867 */ 2868 U_CAPI int32_t U_EXPORT2 2869 u_getIntPropertyMinValue(UProperty which); 2870 2871 /** 2872 * Get the maximum value for an enumerated/integer/binary Unicode property. 2873 * Can be used together with u_getIntPropertyMinValue 2874 * to allocate arrays of UnicodeSet or similar. 2875 * 2876 * Examples for min/max values (for Unicode 3.2): 2877 * 2878 * - UCHAR_BIDI_CLASS: 0/18 (U_LEFT_TO_RIGHT/U_BOUNDARY_NEUTRAL) 2879 * - UCHAR_SCRIPT: 0/45 (USCRIPT_COMMON/USCRIPT_TAGBANWA) 2880 * - UCHAR_IDEOGRAPHIC: 0/1 (false/true) 2881 * 2882 * For undefined UProperty constant values, min/max values will be 0/-1. 2883 * 2884 * @param which UProperty selector constant, identifies which binary property to check. 2885 * Must be UCHAR_BINARY_START<=which<UCHAR_BINARY_LIMIT 2886 * or UCHAR_INT_START<=which<UCHAR_INT_LIMIT. 2887 * @return Maximum value returned by u_getIntPropertyValue for a Unicode property. 2888 * <=0 if the property selector is out of range. 2889 * 2890 * @see UProperty 2891 * @see u_hasBinaryProperty 2892 * @see u_getUnicodeVersion 2893 * @see u_getIntPropertyMaxValue 2894 * @see u_getIntPropertyValue 2895 * @stable ICU 2.2 2896 */ 2897 U_CAPI int32_t U_EXPORT2 2898 u_getIntPropertyMaxValue(UProperty which); 2899 2900 /** 2901 * Returns an immutable UCPMap for an enumerated/catalog/int-valued property. 2902 * The library retains ownership over the returned object. 2903 * Sets an error code if the property number is not one for an "int property". 2904 * 2905 * The returned object maps all Unicode code points to their values for that property. 2906 * For documentation of the integer values see u_getIntPropertyValue(). 2907 * 2908 * @param property UCHAR_INT_START..UCHAR_INT_LIMIT-1 2909 * @param pErrorCode an in/out ICU UErrorCode 2910 * @return the property as a map 2911 * @see UProperty 2912 * @see u_getIntPropertyValue 2913 * @stable ICU 63 2914 */ 2915 U_CAPI const UCPMap * U_EXPORT2 2916 u_getIntPropertyMap(UProperty property, UErrorCode *pErrorCode); 2917 2918 /** 2919 * Get the numeric value for a Unicode code point as defined in the 2920 * Unicode Character Database. 2921 * 2922 * A "double" return type is necessary because 2923 * some numeric values are fractions, negative, or too large for int32_t. 2924 * 2925 * For characters without any numeric values in the Unicode Character Database, 2926 * this function will return U_NO_NUMERIC_VALUE. 2927 * Note: This is different from the Unicode Standard which specifies NaN as the default value. 2928 * (NaN is not available on all platforms.) 2929 * 2930 * Similar to java.lang.Character.getNumericValue(), but u_getNumericValue() 2931 * also supports negative values, large values, and fractions, 2932 * while Java's getNumericValue() returns values 10..35 for ASCII letters. 2933 * 2934 * @param c Code point to get the numeric value for. 2935 * @return Numeric value of c, or U_NO_NUMERIC_VALUE if none is defined. 2936 * 2937 * @see U_NO_NUMERIC_VALUE 2938 * @stable ICU 2.2 2939 */ 2940 U_CAPI double U_EXPORT2 2941 u_getNumericValue(UChar32 c); 2942 2943 /** 2944 * Special value that is returned by u_getNumericValue when 2945 * no numeric value is defined for a code point. 2946 * 2947 * @see u_getNumericValue 2948 * @stable ICU 2.2 2949 */ 2950 #define U_NO_NUMERIC_VALUE ((double)-123456789.) 2951 2952 /** 2953 * Determines whether the specified code point has the general category "Ll" 2954 * (lowercase letter). 2955 * 2956 * Same as java.lang.Character.isLowerCase(). 2957 * 2958 * This misses some characters that are also lowercase but 2959 * have a different general category value. 2960 * In order to include those, use UCHAR_LOWERCASE. 2961 * 2962 * In addition to being equivalent to a Java function, this also serves 2963 * as a C/POSIX migration function. 2964 * See the comments about C/POSIX character classification functions in the 2965 * documentation at the top of this header file. 2966 * 2967 * @param c the code point to be tested 2968 * @return true if the code point is an Ll lowercase letter 2969 * 2970 * @see UCHAR_LOWERCASE 2971 * @see u_isupper 2972 * @see u_istitle 2973 * @stable ICU 2.0 2974 */ 2975 U_CAPI UBool U_EXPORT2 2976 u_islower(UChar32 c); 2977 2978 /** 2979 * Determines whether the specified code point has the general category "Lu" 2980 * (uppercase letter). 2981 * 2982 * Same as java.lang.Character.isUpperCase(). 2983 * 2984 * This misses some characters that are also uppercase but 2985 * have a different general category value. 2986 * In order to include those, use UCHAR_UPPERCASE. 2987 * 2988 * In addition to being equivalent to a Java function, this also serves 2989 * as a C/POSIX migration function. 2990 * See the comments about C/POSIX character classification functions in the 2991 * documentation at the top of this header file. 2992 * 2993 * @param c the code point to be tested 2994 * @return true if the code point is an Lu uppercase letter 2995 * 2996 * @see UCHAR_UPPERCASE 2997 * @see u_islower 2998 * @see u_istitle 2999 * @see u_tolower 3000 * @stable ICU 2.0 3001 */ 3002 U_CAPI UBool U_EXPORT2 3003 u_isupper(UChar32 c); 3004 3005 /** 3006 * Determines whether the specified code point is a titlecase letter. 3007 * True for general category "Lt" (titlecase letter). 3008 * 3009 * Same as java.lang.Character.isTitleCase(). 3010 * 3011 * @param c the code point to be tested 3012 * @return true if the code point is an Lt titlecase letter 3013 * 3014 * @see u_isupper 3015 * @see u_islower 3016 * @see u_totitle 3017 * @stable ICU 2.0 3018 */ 3019 U_CAPI UBool U_EXPORT2 3020 u_istitle(UChar32 c); 3021 3022 /** 3023 * Determines whether the specified code point is a digit character according to Java. 3024 * True for characters with general category "Nd" (decimal digit numbers). 3025 * Beginning with Unicode 4, this is the same as 3026 * testing for the Numeric_Type of Decimal. 3027 * 3028 * Same as java.lang.Character.isDigit(). 3029 * 3030 * In addition to being equivalent to a Java function, this also serves 3031 * as a C/POSIX migration function. 3032 * See the comments about C/POSIX character classification functions in the 3033 * documentation at the top of this header file. 3034 * 3035 * @param c the code point to be tested 3036 * @return true if the code point is a digit character according to Character.isDigit() 3037 * 3038 * @stable ICU 2.0 3039 */ 3040 U_CAPI UBool U_EXPORT2 3041 u_isdigit(UChar32 c); 3042 3043 /** 3044 * Determines whether the specified code point is a letter character. 3045 * True for general categories "L" (letters). 3046 * 3047 * Same as java.lang.Character.isLetter(). 3048 * 3049 * In addition to being equivalent to a Java function, this also serves 3050 * as a C/POSIX migration function. 3051 * See the comments about C/POSIX character classification functions in the 3052 * documentation at the top of this header file. 3053 * 3054 * @param c the code point to be tested 3055 * @return true if the code point is a letter character 3056 * 3057 * @see u_isdigit 3058 * @see u_isalnum 3059 * @stable ICU 2.0 3060 */ 3061 U_CAPI UBool U_EXPORT2 3062 u_isalpha(UChar32 c); 3063 3064 /** 3065 * Determines whether the specified code point is an alphanumeric character 3066 * (letter or digit) according to Java. 3067 * True for characters with general categories 3068 * "L" (letters) and "Nd" (decimal digit numbers). 3069 * 3070 * Same as java.lang.Character.isLetterOrDigit(). 3071 * 3072 * In addition to being equivalent to a Java function, this also serves 3073 * as a C/POSIX migration function. 3074 * See the comments about C/POSIX character classification functions in the 3075 * documentation at the top of this header file. 3076 * 3077 * @param c the code point to be tested 3078 * @return true if the code point is an alphanumeric character according to Character.isLetterOrDigit() 3079 * 3080 * @stable ICU 2.0 3081 */ 3082 U_CAPI UBool U_EXPORT2 3083 u_isalnum(UChar32 c); 3084 3085 /** 3086 * Determines whether the specified code point is a hexadecimal digit. 3087 * This is equivalent to u_digit(c, 16)>=0. 3088 * True for characters with general category "Nd" (decimal digit numbers) 3089 * as well as Latin letters a-f and A-F in both ASCII and Fullwidth ASCII. 3090 * (That is, for letters with code points 3091 * 0041..0046, 0061..0066, FF21..FF26, FF41..FF46.) 3092 * 3093 * In order to narrow the definition of hexadecimal digits to only ASCII 3094 * characters, use (c<=0x7f && u_isxdigit(c)). 3095 * 3096 * This is a C/POSIX migration function. 3097 * See the comments about C/POSIX character classification functions in the 3098 * documentation at the top of this header file. 3099 * 3100 * @param c the code point to be tested 3101 * @return true if the code point is a hexadecimal digit 3102 * 3103 * @stable ICU 2.6 3104 */ 3105 U_CAPI UBool U_EXPORT2 3106 u_isxdigit(UChar32 c); 3107 3108 /** 3109 * Determines whether the specified code point is a punctuation character. 3110 * True for characters with general categories "P" (punctuation). 3111 * 3112 * This is a C/POSIX migration function. 3113 * See the comments about C/POSIX character classification functions in the 3114 * documentation at the top of this header file. 3115 * 3116 * @param c the code point to be tested 3117 * @return true if the code point is a punctuation character 3118 * 3119 * @stable ICU 2.6 3120 */ 3121 U_CAPI UBool U_EXPORT2 3122 u_ispunct(UChar32 c); 3123 3124 /** 3125 * Determines whether the specified code point is a "graphic" character 3126 * (printable, excluding spaces). 3127 * true for all characters except those with general categories 3128 * "Cc" (control codes), "Cf" (format controls), "Cs" (surrogates), 3129 * "Cn" (unassigned), and "Z" (separators). 3130 * 3131 * This is a C/POSIX migration function. 3132 * See the comments about C/POSIX character classification functions in the 3133 * documentation at the top of this header file. 3134 * 3135 * @param c the code point to be tested 3136 * @return true if the code point is a "graphic" character 3137 * 3138 * @stable ICU 2.6 3139 */ 3140 U_CAPI UBool U_EXPORT2 3141 u_isgraph(UChar32 c); 3142 3143 /** 3144 * Determines whether the specified code point is a "blank" or "horizontal space", 3145 * a character that visibly separates words on a line. 3146 * The following are equivalent definitions: 3147 * 3148 * true for Unicode White_Space characters except for "vertical space controls" 3149 * where "vertical space controls" are the following characters: 3150 * U+000A (LF) U+000B (VT) U+000C (FF) U+000D (CR) U+0085 (NEL) U+2028 (LS) U+2029 (PS) 3151 * 3152 * same as 3153 * 3154 * true for U+0009 (TAB) and characters with general category "Zs" (space separators). 3155 * 3156 * Note: There are several ICU whitespace functions; please see the uchar.h 3157 * file documentation for a detailed comparison. 3158 * 3159 * This is a C/POSIX migration function. 3160 * See the comments about C/POSIX character classification functions in the 3161 * documentation at the top of this header file. 3162 * 3163 * @param c the code point to be tested 3164 * @return true if the code point is a "blank" 3165 * 3166 * @stable ICU 2.6 3167 */ 3168 U_CAPI UBool U_EXPORT2 3169 u_isblank(UChar32 c); 3170 3171 /** 3172 * Determines whether the specified code point is "defined", 3173 * which usually means that it is assigned a character. 3174 * True for general categories other than "Cn" (other, not assigned), 3175 * i.e., true for all code points mentioned in UnicodeData.txt. 3176 * 3177 * Note that non-character code points (e.g., U+FDD0) are not "defined" 3178 * (they are Cn), but surrogate code points are "defined" (Cs). 3179 * 3180 * Same as java.lang.Character.isDefined(). 3181 * 3182 * @param c the code point to be tested 3183 * @return true if the code point is assigned a character 3184 * 3185 * @see u_isdigit 3186 * @see u_isalpha 3187 * @see u_isalnum 3188 * @see u_isupper 3189 * @see u_islower 3190 * @see u_istitle 3191 * @stable ICU 2.0 3192 */ 3193 U_CAPI UBool U_EXPORT2 3194 u_isdefined(UChar32 c); 3195 3196 /** 3197 * Determines if the specified character is a space character or not. 3198 * 3199 * Note: There are several ICU whitespace functions; please see the uchar.h 3200 * file documentation for a detailed comparison. 3201 * 3202 * This is a C/POSIX migration function. 3203 * See the comments about C/POSIX character classification functions in the 3204 * documentation at the top of this header file. 3205 * 3206 * @param c the character to be tested 3207 * @return true if the character is a space character; false otherwise. 3208 * 3209 * @see u_isJavaSpaceChar 3210 * @see u_isWhitespace 3211 * @see u_isUWhiteSpace 3212 * @stable ICU 2.0 3213 */ 3214 U_CAPI UBool U_EXPORT2 3215 u_isspace(UChar32 c); 3216 3217 /** 3218 * Determine if the specified code point is a space character according to Java. 3219 * True for characters with general categories "Z" (separators), 3220 * which does not include control codes (e.g., TAB or Line Feed). 3221 * 3222 * Same as java.lang.Character.isSpaceChar(). 3223 * 3224 * Note: There are several ICU whitespace functions; please see the uchar.h 3225 * file documentation for a detailed comparison. 3226 * 3227 * @param c the code point to be tested 3228 * @return true if the code point is a space character according to Character.isSpaceChar() 3229 * 3230 * @see u_isspace 3231 * @see u_isWhitespace 3232 * @see u_isUWhiteSpace 3233 * @stable ICU 2.6 3234 */ 3235 U_CAPI UBool U_EXPORT2 3236 u_isJavaSpaceChar(UChar32 c); 3237 3238 /** 3239 * Determines if the specified code point is a whitespace character according to Java/ICU. 3240 * A character is considered to be a Java whitespace character if and only 3241 * if it satisfies one of the following criteria: 3242 * 3243 * - It is a Unicode Separator character (categories "Z" = "Zs" or "Zl" or "Zp"), but is not 3244 * also a non-breaking space (U+00A0 NBSP or U+2007 Figure Space or U+202F Narrow NBSP). 3245 * - It is U+0009 HORIZONTAL TABULATION. 3246 * - It is U+000A LINE FEED. 3247 * - It is U+000B VERTICAL TABULATION. 3248 * - It is U+000C FORM FEED. 3249 * - It is U+000D CARRIAGE RETURN. 3250 * - It is U+001C FILE SEPARATOR. 3251 * - It is U+001D GROUP SEPARATOR. 3252 * - It is U+001E RECORD SEPARATOR. 3253 * - It is U+001F UNIT SEPARATOR. 3254 * 3255 * This API tries to sync with the semantics of Java's 3256 * java.lang.Character.isWhitespace(), but it may not return 3257 * the exact same results because of the Unicode version 3258 * difference. 3259 * 3260 * Note: Unicode 4.0.1 changed U+200B ZERO WIDTH SPACE from a Space Separator (Zs) 3261 * to a Format Control (Cf). Since then, isWhitespace(0x200b) returns false. 3262 * See http://www.unicode.org/versions/Unicode4.0.1/ 3263 * 3264 * Note: There are several ICU whitespace functions; please see the uchar.h 3265 * file documentation for a detailed comparison. 3266 * 3267 * @param c the code point to be tested 3268 * @return true if the code point is a whitespace character according to Java/ICU 3269 * 3270 * @see u_isspace 3271 * @see u_isJavaSpaceChar 3272 * @see u_isUWhiteSpace 3273 * @stable ICU 2.0 3274 */ 3275 U_CAPI UBool U_EXPORT2 3276 u_isWhitespace(UChar32 c); 3277 3278 /** 3279 * Determines whether the specified code point is a control character 3280 * (as defined by this function). 3281 * A control character is one of the following: 3282 * - ISO 8-bit control character (U+0000..U+001f and U+007f..U+009f) 3283 * - U_CONTROL_CHAR (Cc) 3284 * - U_FORMAT_CHAR (Cf) 3285 * - U_LINE_SEPARATOR (Zl) 3286 * - U_PARAGRAPH_SEPARATOR (Zp) 3287 * 3288 * This is a C/POSIX migration function. 3289 * See the comments about C/POSIX character classification functions in the 3290 * documentation at the top of this header file. 3291 * 3292 * @param c the code point to be tested 3293 * @return true if the code point is a control character 3294 * 3295 * @see UCHAR_DEFAULT_IGNORABLE_CODE_POINT 3296 * @see u_isprint 3297 * @stable ICU 2.0 3298 */ 3299 U_CAPI UBool U_EXPORT2 3300 u_iscntrl(UChar32 c); 3301 3302 /** 3303 * Determines whether the specified code point is an ISO control code. 3304 * True for U+0000..U+001f and U+007f..U+009f (general category "Cc"). 3305 * 3306 * Same as java.lang.Character.isISOControl(). 3307 * 3308 * @param c the code point to be tested 3309 * @return true if the code point is an ISO control code 3310 * 3311 * @see u_iscntrl 3312 * @stable ICU 2.6 3313 */ 3314 U_CAPI UBool U_EXPORT2 3315 u_isISOControl(UChar32 c); 3316 3317 /** 3318 * Determines whether the specified code point is a printable character. 3319 * True for general categories <em>other</em> than "C" (controls). 3320 * 3321 * This is a C/POSIX migration function. 3322 * See the comments about C/POSIX character classification functions in the 3323 * documentation at the top of this header file. 3324 * 3325 * @param c the code point to be tested 3326 * @return true if the code point is a printable character 3327 * 3328 * @see UCHAR_DEFAULT_IGNORABLE_CODE_POINT 3329 * @see u_iscntrl 3330 * @stable ICU 2.0 3331 */ 3332 U_CAPI UBool U_EXPORT2 3333 u_isprint(UChar32 c); 3334 3335 /** 3336 * Non-standard: Determines whether the specified code point is a base character. 3337 * True for general categories "L" (letters), "N" (numbers), 3338 * "Mc" (spacing combining marks), and "Me" (enclosing marks). 3339 * 3340 * Note that this is different from the Unicode Standard definition in 3341 * chapter 3.6, conformance clause D51 “Base character”, 3342 * which defines base characters as the code points with general categories 3343 * Letter (L), Number (N), Punctuation (P), Symbol (S), or Space Separator (Zs). 3344 * 3345 * @param c the code point to be tested 3346 * @return true if the code point is a base character according to this function 3347 * 3348 * @see u_isalpha 3349 * @see u_isdigit 3350 * @stable ICU 2.0 3351 */ 3352 U_CAPI UBool U_EXPORT2 3353 u_isbase(UChar32 c); 3354 3355 /** 3356 * Returns the bidirectional category value for the code point, 3357 * which is used in the Unicode bidirectional algorithm 3358 * (UAX #9 http://www.unicode.org/reports/tr9/). 3359 * Note that some <em>unassigned</em> code points have bidi values 3360 * of R or AL because they are in blocks that are reserved 3361 * for Right-To-Left scripts. 3362 * 3363 * Same as java.lang.Character.getDirectionality() 3364 * 3365 * @param c the code point to be tested 3366 * @return the bidirectional category (UCharDirection) value 3367 * 3368 * @see UCharDirection 3369 * @stable ICU 2.0 3370 */ 3371 U_CAPI UCharDirection U_EXPORT2 3372 u_charDirection(UChar32 c); 3373 3374 /** 3375 * Determines whether the code point has the Bidi_Mirrored property. 3376 * This property is set for characters that are commonly used in 3377 * Right-To-Left contexts and need to be displayed with a "mirrored" 3378 * glyph. 3379 * 3380 * Same as java.lang.Character.isMirrored(). 3381 * Same as UCHAR_BIDI_MIRRORED 3382 * 3383 * @param c the code point to be tested 3384 * @return true if the character has the Bidi_Mirrored property 3385 * 3386 * @see UCHAR_BIDI_MIRRORED 3387 * @stable ICU 2.0 3388 */ 3389 U_CAPI UBool U_EXPORT2 3390 u_isMirrored(UChar32 c); 3391 3392 /** 3393 * Maps the specified character to a "mirror-image" character. 3394 * For characters with the Bidi_Mirrored property, implementations 3395 * sometimes need a "poor man's" mapping to another Unicode 3396 * character (code point) such that the default glyph may serve 3397 * as the mirror-image of the default glyph of the specified 3398 * character. This is useful for text conversion to and from 3399 * codepages with visual order, and for displays without glyph 3400 * selection capabilities. 3401 * 3402 * @param c the code point to be mapped 3403 * @return another Unicode code point that may serve as a mirror-image 3404 * substitute, or c itself if there is no such mapping or c 3405 * does not have the Bidi_Mirrored property 3406 * 3407 * @see UCHAR_BIDI_MIRRORED 3408 * @see u_isMirrored 3409 * @stable ICU 2.0 3410 */ 3411 U_CAPI UChar32 U_EXPORT2 3412 u_charMirror(UChar32 c); 3413 3414 /** 3415 * Maps the specified character to its paired bracket character. 3416 * For Bidi_Paired_Bracket_Type!=None, this is the same as u_charMirror(). 3417 * Otherwise c itself is returned. 3418 * See http://www.unicode.org/reports/tr9/ 3419 * 3420 * @param c the code point to be mapped 3421 * @return the paired bracket code point, 3422 * or c itself if there is no such mapping 3423 * (Bidi_Paired_Bracket_Type=None) 3424 * 3425 * @see UCHAR_BIDI_PAIRED_BRACKET 3426 * @see UCHAR_BIDI_PAIRED_BRACKET_TYPE 3427 * @see u_charMirror 3428 * @stable ICU 52 3429 */ 3430 U_CAPI UChar32 U_EXPORT2 3431 u_getBidiPairedBracket(UChar32 c); 3432 3433 /** 3434 * Returns the general category value for the code point. 3435 * 3436 * Same as java.lang.Character.getType(). 3437 * 3438 * @param c the code point to be tested 3439 * @return the general category (UCharCategory) value 3440 * 3441 * @see UCharCategory 3442 * @stable ICU 2.0 3443 */ 3444 U_CAPI int8_t U_EXPORT2 3445 u_charType(UChar32 c); 3446 3447 /** 3448 * Get a single-bit bit set for the general category of a character. 3449 * This bit set can be compared bitwise with U_GC_SM_MASK, U_GC_L_MASK, etc. 3450 * Same as U_MASK(u_charType(c)). 3451 * 3452 * @param c the code point to be tested 3453 * @return a single-bit mask corresponding to the general category (UCharCategory) value 3454 * 3455 * @see u_charType 3456 * @see UCharCategory 3457 * @see U_GC_CN_MASK 3458 * @stable ICU 2.1 3459 */ 3460 #define U_GET_GC_MASK(c) U_MASK(u_charType(c)) 3461 3462 /** 3463 * Callback from u_enumCharTypes(), is called for each contiguous range 3464 * of code points c (where start<=c<limit) 3465 * with the same Unicode general category ("character type"). 3466 * 3467 * The callback function can stop the enumeration by returning false. 3468 * 3469 * @param context an opaque pointer, as passed into utrie_enum() 3470 * @param start the first code point in a contiguous range with value 3471 * @param limit one past the last code point in a contiguous range with value 3472 * @param type the general category for all code points in [start..limit[ 3473 * @return false to stop the enumeration 3474 * 3475 * @stable ICU 2.1 3476 * @see UCharCategory 3477 * @see u_enumCharTypes 3478 */ 3479 typedef UBool U_CALLCONV 3480 UCharEnumTypeRange(const void *context, UChar32 start, UChar32 limit, UCharCategory type); 3481 3482 /** 3483 * Enumerate efficiently all code points with their Unicode general categories. 3484 * 3485 * This is useful for building data structures (e.g., UnicodeSet's), 3486 * for enumerating all assigned code points (type!=U_UNASSIGNED), etc. 3487 * 3488 * For each contiguous range of code points with a given general category ("character type"), 3489 * the UCharEnumTypeRange function is called. 3490 * Adjacent ranges have different types. 3491 * The Unicode Standard guarantees that the numeric value of the type is 0..31. 3492 * 3493 * @param enumRange a pointer to a function that is called for each contiguous range 3494 * of code points with the same general category 3495 * @param context an opaque pointer that is passed on to the callback function 3496 * 3497 * @stable ICU 2.1 3498 * @see UCharCategory 3499 * @see UCharEnumTypeRange 3500 */ 3501 U_CAPI void U_EXPORT2 3502 u_enumCharTypes(UCharEnumTypeRange *enumRange, const void *context); 3503 3504 #if !UCONFIG_NO_NORMALIZATION 3505 3506 /** 3507 * Returns the combining class of the code point as specified in UnicodeData.txt. 3508 * 3509 * @param c the code point of the character 3510 * @return the combining class of the character 3511 * @stable ICU 2.0 3512 */ 3513 U_CAPI uint8_t U_EXPORT2 3514 u_getCombiningClass(UChar32 c); 3515 3516 #endif 3517 3518 /** 3519 * Returns the decimal digit value of a decimal digit character. 3520 * Such characters have the general category "Nd" (decimal digit numbers) 3521 * and a Numeric_Type of Decimal. 3522 * 3523 * Unlike ICU releases before 2.6, no digit values are returned for any 3524 * Han characters because Han number characters are often used with a special 3525 * Chinese-style number format (with characters for powers of 10 in between) 3526 * instead of in decimal-positional notation. 3527 * Unicode 4 explicitly assigns Han number characters the Numeric_Type 3528 * Numeric instead of Decimal. 3529 * See Jitterbug 1483 for more details. 3530 * 3531 * Use u_getIntPropertyValue(c, UCHAR_NUMERIC_TYPE) and u_getNumericValue() 3532 * for complete numeric Unicode properties. 3533 * 3534 * @param c the code point for which to get the decimal digit value 3535 * @return the decimal digit value of c, 3536 * or -1 if c is not a decimal digit character 3537 * 3538 * @see u_getNumericValue 3539 * @stable ICU 2.0 3540 */ 3541 U_CAPI int32_t U_EXPORT2 3542 u_charDigitValue(UChar32 c); 3543 3544 /** 3545 * Returns the Unicode allocation block that contains the character. 3546 * 3547 * @param c the code point to be tested 3548 * @return the block value (UBlockCode) for c 3549 * 3550 * @see UBlockCode 3551 * @stable ICU 2.0 3552 */ 3553 U_CAPI UBlockCode U_EXPORT2 3554 ublock_getCode(UChar32 c); 3555 3556 /** 3557 * Retrieve the name of a Unicode character. 3558 * Depending on <code>nameChoice</code>, the character name written 3559 * into the buffer is the "modern" name or the name that was defined 3560 * in Unicode version 1.0. 3561 * The name contains only "invariant" characters 3562 * like A-Z, 0-9, space, and '-'. 3563 * Unicode 1.0 names are only retrieved if they are different from the modern 3564 * names and if the data file contains the data for them. gennames may or may 3565 * not be called with a command line option to include 1.0 names in unames.dat. 3566 * 3567 * @param code The character (code point) for which to get the name. 3568 * It must be <code>0<=code<=0x10ffff</code>. 3569 * @param nameChoice Selector for which name to get. 3570 * @param buffer Destination address for copying the name. 3571 * The name will always be zero-terminated. 3572 * If there is no name, then the buffer will be set to the empty string. 3573 * @param bufferLength <code>==sizeof(buffer)</code> 3574 * @param pErrorCode Pointer to a UErrorCode variable; 3575 * check for <code>U_SUCCESS()</code> after <code>u_charName()</code> 3576 * returns. 3577 * @return The length of the name, or 0 if there is no name for this character. 3578 * If the bufferLength is less than or equal to the length, then the buffer 3579 * contains the truncated name and the returned length indicates the full 3580 * length of the name. 3581 * The length does not include the zero-termination. 3582 * 3583 * @see UCharNameChoice 3584 * @see u_charFromName 3585 * @see u_enumCharNames 3586 * @stable ICU 2.0 3587 */ 3588 U_CAPI int32_t U_EXPORT2 3589 u_charName(UChar32 code, UCharNameChoice nameChoice, 3590 char *buffer, int32_t bufferLength, 3591 UErrorCode *pErrorCode); 3592 3593 #ifndef U_HIDE_DEPRECATED_API 3594 /** 3595 * Returns an empty string. 3596 * Used to return the ISO 10646 comment for a character. 3597 * The Unicode ISO_Comment property is deprecated and has no values. 3598 * 3599 * @param c The character (code point) for which to get the ISO comment. 3600 * It must be <code>0<=c<=0x10ffff</code>. 3601 * @param dest Destination address for copying the comment. 3602 * The comment will be zero-terminated if possible. 3603 * If there is no comment, then the buffer will be set to the empty string. 3604 * @param destCapacity <code>==sizeof(dest)</code> 3605 * @param pErrorCode Pointer to a UErrorCode variable; 3606 * check for <code>U_SUCCESS()</code> after <code>u_getISOComment()</code> 3607 * returns. 3608 * @return 0 3609 * 3610 * @deprecated ICU 49 3611 */ 3612 U_DEPRECATED int32_t U_EXPORT2 3613 u_getISOComment(UChar32 c, 3614 char *dest, int32_t destCapacity, 3615 UErrorCode *pErrorCode); 3616 #endif /* U_HIDE_DEPRECATED_API */ 3617 3618 /** 3619 * Find a Unicode character by its name and return its code point value. 3620 * The name is matched exactly and completely. 3621 * If the name does not correspond to a code point, <i>pErrorCode</i> 3622 * is set to <code>U_INVALID_CHAR_FOUND</code>. 3623 * A Unicode 1.0 name is matched only if it differs from the modern name. 3624 * Unicode names are all uppercase. Extended names are lowercase followed 3625 * by an uppercase hexadecimal number, and within angle brackets. 3626 * 3627 * @param nameChoice Selector for which name to match. 3628 * @param name The name to match. 3629 * @param pErrorCode Pointer to a UErrorCode variable 3630 * @return The Unicode value of the code point with the given name, 3631 * or an undefined value if there is no such code point. 3632 * 3633 * @see UCharNameChoice 3634 * @see u_charName 3635 * @see u_enumCharNames 3636 * @stable ICU 1.7 3637 */ 3638 U_CAPI UChar32 U_EXPORT2 3639 u_charFromName(UCharNameChoice nameChoice, 3640 const char *name, 3641 UErrorCode *pErrorCode); 3642 3643 /** 3644 * Type of a callback function for u_enumCharNames() that gets called 3645 * for each Unicode character with the code point value and 3646 * the character name. 3647 * If such a function returns false, then the enumeration is stopped. 3648 * 3649 * @param context The context pointer that was passed to u_enumCharNames(). 3650 * @param code The Unicode code point for the character with this name. 3651 * @param nameChoice Selector for which kind of names is enumerated. 3652 * @param name The character's name, zero-terminated. 3653 * @param length The length of the name. 3654 * @return true if the enumeration should continue, false to stop it. 3655 * 3656 * @see UCharNameChoice 3657 * @see u_enumCharNames 3658 * @stable ICU 1.7 3659 */ 3660 typedef UBool U_CALLCONV UEnumCharNamesFn(void *context, 3661 UChar32 code, 3662 UCharNameChoice nameChoice, 3663 const char *name, 3664 int32_t length); 3665 3666 /** 3667 * Enumerate all assigned Unicode characters between the start and limit 3668 * code points (start inclusive, limit exclusive) and call a function 3669 * for each, passing the code point value and the character name. 3670 * For Unicode 1.0 names, only those are enumerated that differ from the 3671 * modern names. 3672 * 3673 * @param start The first code point in the enumeration range. 3674 * @param limit One more than the last code point in the enumeration range 3675 * (the first one after the range). 3676 * @param fn The function that is to be called for each character name. 3677 * @param context An arbitrary pointer that is passed to the function. 3678 * @param nameChoice Selector for which kind of names to enumerate. 3679 * @param pErrorCode Pointer to a UErrorCode variable 3680 * 3681 * @see UCharNameChoice 3682 * @see UEnumCharNamesFn 3683 * @see u_charName 3684 * @see u_charFromName 3685 * @stable ICU 1.7 3686 */ 3687 U_CAPI void U_EXPORT2 3688 u_enumCharNames(UChar32 start, UChar32 limit, 3689 UEnumCharNamesFn *fn, 3690 void *context, 3691 UCharNameChoice nameChoice, 3692 UErrorCode *pErrorCode); 3693 3694 /** 3695 * Return the Unicode name for a given property, as given in the 3696 * Unicode database file PropertyAliases.txt. 3697 * 3698 * In addition, this function maps the property 3699 * UCHAR_GENERAL_CATEGORY_MASK to the synthetic names "gcm" / 3700 * "General_Category_Mask". These names are not in 3701 * PropertyAliases.txt. 3702 * 3703 * @param property UProperty selector other than UCHAR_INVALID_CODE. 3704 * If out of range, NULL is returned. 3705 * 3706 * @param nameChoice selector for which name to get. If out of range, 3707 * NULL is returned. All properties have a long name. Most 3708 * have a short name, but some do not. Unicode allows for 3709 * additional names; if present these will be returned by 3710 * U_LONG_PROPERTY_NAME + i, where i=1, 2,... 3711 * 3712 * @return a pointer to the name, or NULL if either the 3713 * property or the nameChoice is out of range. If a given 3714 * nameChoice returns NULL, then all larger values of 3715 * nameChoice will return NULL, with one exception: if NULL is 3716 * returned for U_SHORT_PROPERTY_NAME, then 3717 * U_LONG_PROPERTY_NAME (and higher) may still return a 3718 * non-NULL value. The returned pointer is valid until 3719 * u_cleanup() is called. 3720 * 3721 * @see UProperty 3722 * @see UPropertyNameChoice 3723 * @stable ICU 2.4 3724 */ 3725 U_CAPI const char* U_EXPORT2 3726 u_getPropertyName(UProperty property, 3727 UPropertyNameChoice nameChoice); 3728 3729 /** 3730 * Return the UProperty enum for a given property name, as specified 3731 * in the Unicode database file PropertyAliases.txt. Short, long, and 3732 * any other variants are recognized. 3733 * 3734 * In addition, this function maps the synthetic names "gcm" / 3735 * "General_Category_Mask" to the property 3736 * UCHAR_GENERAL_CATEGORY_MASK. These names are not in 3737 * PropertyAliases.txt. 3738 * 3739 * @param alias the property name to be matched. The name is compared 3740 * using "loose matching" as described in PropertyAliases.txt. 3741 * 3742 * @return a UProperty enum, or UCHAR_INVALID_CODE if the given name 3743 * does not match any property. 3744 * 3745 * @see UProperty 3746 * @stable ICU 2.4 3747 */ 3748 U_CAPI UProperty U_EXPORT2 3749 u_getPropertyEnum(const char* alias); 3750 3751 /** 3752 * Return the Unicode name for a given property value, as given in the 3753 * Unicode database file PropertyValueAliases.txt. 3754 * 3755 * Note: Some of the names in PropertyValueAliases.txt can only be 3756 * retrieved using UCHAR_GENERAL_CATEGORY_MASK, not 3757 * UCHAR_GENERAL_CATEGORY. These include: "C" / "Other", "L" / 3758 * "Letter", "LC" / "Cased_Letter", "M" / "Mark", "N" / "Number", "P" 3759 * / "Punctuation", "S" / "Symbol", and "Z" / "Separator". 3760 * 3761 * @param property UProperty selector constant. 3762 * Must be UCHAR_BINARY_START<=which<UCHAR_BINARY_LIMIT 3763 * or UCHAR_INT_START<=which<UCHAR_INT_LIMIT 3764 * or UCHAR_MASK_START<=which<UCHAR_MASK_LIMIT. 3765 * If out of range, NULL is returned. 3766 * 3767 * @param value selector for a value for the given property. If out 3768 * of range, NULL is returned. In general, valid values range 3769 * from 0 up to some maximum. There are a few exceptions: 3770 * (1.) UCHAR_BLOCK values begin at the non-zero value 3771 * UBLOCK_BASIC_LATIN. (2.) UCHAR_CANONICAL_COMBINING_CLASS 3772 * values are not contiguous and range from 0..240. (3.) 3773 * UCHAR_GENERAL_CATEGORY_MASK values are not values of 3774 * UCharCategory, but rather mask values produced by 3775 * U_GET_GC_MASK(). This allows grouped categories such as 3776 * [:L:] to be represented. Mask values range 3777 * non-contiguously from 1..U_GC_P_MASK. 3778 * 3779 * @param nameChoice selector for which name to get. If out of range, 3780 * NULL is returned. All values have a long name. Most have 3781 * a short name, but some do not. Unicode allows for 3782 * additional names; if present these will be returned by 3783 * U_LONG_PROPERTY_NAME + i, where i=1, 2,... 3784 3785 * @return a pointer to the name, or NULL if either the 3786 * property or the nameChoice is out of range. If a given 3787 * nameChoice returns NULL, then all larger values of 3788 * nameChoice will return NULL, with one exception: if NULL is 3789 * returned for U_SHORT_PROPERTY_NAME, then 3790 * U_LONG_PROPERTY_NAME (and higher) may still return a 3791 * non-NULL value. The returned pointer is valid until 3792 * u_cleanup() is called. 3793 * 3794 * @see UProperty 3795 * @see UPropertyNameChoice 3796 * @stable ICU 2.4 3797 */ 3798 U_CAPI const char* U_EXPORT2 3799 u_getPropertyValueName(UProperty property, 3800 int32_t value, 3801 UPropertyNameChoice nameChoice); 3802 3803 /** 3804 * Return the property value integer for a given value name, as 3805 * specified in the Unicode database file PropertyValueAliases.txt. 3806 * Short, long, and any other variants are recognized. 3807 * 3808 * Note: Some of the names in PropertyValueAliases.txt will only be 3809 * recognized with UCHAR_GENERAL_CATEGORY_MASK, not 3810 * UCHAR_GENERAL_CATEGORY. These include: "C" / "Other", "L" / 3811 * "Letter", "LC" / "Cased_Letter", "M" / "Mark", "N" / "Number", "P" 3812 * / "Punctuation", "S" / "Symbol", and "Z" / "Separator". 3813 * 3814 * @param property UProperty selector constant. 3815 * Must be UCHAR_BINARY_START<=which<UCHAR_BINARY_LIMIT 3816 * or UCHAR_INT_START<=which<UCHAR_INT_LIMIT 3817 * or UCHAR_MASK_START<=which<UCHAR_MASK_LIMIT. 3818 * If out of range, UCHAR_INVALID_CODE is returned. 3819 * 3820 * @param alias the value name to be matched. The name is compared 3821 * using "loose matching" as described in 3822 * PropertyValueAliases.txt. 3823 * 3824 * @return a value integer or UCHAR_INVALID_CODE if the given name 3825 * does not match any value of the given property, or if the 3826 * property is invalid. Note: UCHAR_GENERAL_CATEGORY_MASK values 3827 * are not values of UCharCategory, but rather mask values 3828 * produced by U_GET_GC_MASK(). This allows grouped 3829 * categories such as [:L:] to be represented. 3830 * 3831 * @see UProperty 3832 * @stable ICU 2.4 3833 */ 3834 U_CAPI int32_t U_EXPORT2 3835 u_getPropertyValueEnum(UProperty property, 3836 const char* alias); 3837 3838 /** 3839 * Determines if the specified character is permissible as the 3840 * first character in an identifier according to Unicode 3841 * (The Unicode Standard, Version 3.0, chapter 5.16 Identifiers). 3842 * True for characters with general categories "L" (letters) and "Nl" (letter numbers). 3843 * 3844 * Same as java.lang.Character.isUnicodeIdentifierStart(). 3845 * Same as UCHAR_ID_START 3846 * 3847 * @param c the code point to be tested 3848 * @return true if the code point may start an identifier 3849 * 3850 * @see UCHAR_ID_START 3851 * @see u_isalpha 3852 * @see u_isIDPart 3853 * @stable ICU 2.0 3854 */ 3855 U_CAPI UBool U_EXPORT2 3856 u_isIDStart(UChar32 c); 3857 3858 /** 3859 * Determines if the specified character is permissible 3860 * in an identifier according to Java. 3861 * True for characters with general categories "L" (letters), 3862 * "Nl" (letter numbers), "Nd" (decimal digits), 3863 * "Mc" and "Mn" (combining marks), "Pc" (connecting punctuation), and 3864 * u_isIDIgnorable(c). 3865 * 3866 * Same as java.lang.Character.isUnicodeIdentifierPart(). 3867 * Almost the same as Unicode's ID_Continue (UCHAR_ID_CONTINUE) 3868 * except that Unicode recommends to ignore Cf which is less than 3869 * u_isIDIgnorable(c). 3870 * 3871 * @param c the code point to be tested 3872 * @return true if the code point may occur in an identifier according to Java 3873 * 3874 * @see UCHAR_ID_CONTINUE 3875 * @see u_isIDStart 3876 * @see u_isIDIgnorable 3877 * @stable ICU 2.0 3878 */ 3879 U_CAPI UBool U_EXPORT2 3880 u_isIDPart(UChar32 c); 3881 3882 /** 3883 * Determines if the specified character should be regarded 3884 * as an ignorable character in an identifier, 3885 * according to Java. 3886 * True for characters with general category "Cf" (format controls) as well as 3887 * non-whitespace ISO controls 3888 * (U+0000..U+0008, U+000E..U+001B, U+007F..U+009F). 3889 * 3890 * Same as java.lang.Character.isIdentifierIgnorable(). 3891 * 3892 * Note that Unicode just recommends to ignore Cf (format controls). 3893 * 3894 * @param c the code point to be tested 3895 * @return true if the code point is ignorable in identifiers according to Java 3896 * 3897 * @see UCHAR_DEFAULT_IGNORABLE_CODE_POINT 3898 * @see u_isIDStart 3899 * @see u_isIDPart 3900 * @stable ICU 2.0 3901 */ 3902 U_CAPI UBool U_EXPORT2 3903 u_isIDIgnorable(UChar32 c); 3904 3905 /** 3906 * Determines if the specified character is permissible as the 3907 * first character in a Java identifier. 3908 * In addition to u_isIDStart(c), true for characters with 3909 * general categories "Sc" (currency symbols) and "Pc" (connecting punctuation). 3910 * 3911 * Same as java.lang.Character.isJavaIdentifierStart(). 3912 * 3913 * @param c the code point to be tested 3914 * @return true if the code point may start a Java identifier 3915 * 3916 * @see u_isJavaIDPart 3917 * @see u_isalpha 3918 * @see u_isIDStart 3919 * @stable ICU 2.0 3920 */ 3921 U_CAPI UBool U_EXPORT2 3922 u_isJavaIDStart(UChar32 c); 3923 3924 /** 3925 * Determines if the specified character is permissible 3926 * in a Java identifier. 3927 * In addition to u_isIDPart(c), true for characters with 3928 * general category "Sc" (currency symbols). 3929 * 3930 * Same as java.lang.Character.isJavaIdentifierPart(). 3931 * 3932 * @param c the code point to be tested 3933 * @return true if the code point may occur in a Java identifier 3934 * 3935 * @see u_isIDIgnorable 3936 * @see u_isJavaIDStart 3937 * @see u_isalpha 3938 * @see u_isdigit 3939 * @see u_isIDPart 3940 * @stable ICU 2.0 3941 */ 3942 U_CAPI UBool U_EXPORT2 3943 u_isJavaIDPart(UChar32 c); 3944 3945 /** 3946 * The given character is mapped to its lowercase equivalent according to 3947 * UnicodeData.txt; if the character has no lowercase equivalent, the character 3948 * itself is returned. 3949 * 3950 * Same as java.lang.Character.toLowerCase(). 3951 * 3952 * This function only returns the simple, single-code point case mapping. 3953 * Full case mappings should be used whenever possible because they produce 3954 * better results by working on whole strings. 3955 * They take into account the string context and the language and can map 3956 * to a result string with a different length as appropriate. 3957 * Full case mappings are applied by the string case mapping functions, 3958 * see ustring.h and the UnicodeString class. 3959 * See also the User Guide chapter on C/POSIX migration: 3960 * https://unicode-org.github.io/icu/userguide/icu/posix#case-mappings 3961 * 3962 * @param c the code point to be mapped 3963 * @return the Simple_Lowercase_Mapping of the code point, if any; 3964 * otherwise the code point itself. 3965 * @stable ICU 2.0 3966 */ 3967 U_CAPI UChar32 U_EXPORT2 3968 u_tolower(UChar32 c); 3969 3970 /** 3971 * The given character is mapped to its uppercase equivalent according to UnicodeData.txt; 3972 * if the character has no uppercase equivalent, the character itself is 3973 * returned. 3974 * 3975 * Same as java.lang.Character.toUpperCase(). 3976 * 3977 * This function only returns the simple, single-code point case mapping. 3978 * Full case mappings should be used whenever possible because they produce 3979 * better results by working on whole strings. 3980 * They take into account the string context and the language and can map 3981 * to a result string with a different length as appropriate. 3982 * Full case mappings are applied by the string case mapping functions, 3983 * see ustring.h and the UnicodeString class. 3984 * See also the User Guide chapter on C/POSIX migration: 3985 * https://unicode-org.github.io/icu/userguide/icu/posix#case-mappings 3986 * 3987 * @param c the code point to be mapped 3988 * @return the Simple_Uppercase_Mapping of the code point, if any; 3989 * otherwise the code point itself. 3990 * @stable ICU 2.0 3991 */ 3992 U_CAPI UChar32 U_EXPORT2 3993 u_toupper(UChar32 c); 3994 3995 /** 3996 * The given character is mapped to its titlecase equivalent 3997 * according to UnicodeData.txt; 3998 * if none is defined, the character itself is returned. 3999 * 4000 * Same as java.lang.Character.toTitleCase(). 4001 * 4002 * This function only returns the simple, single-code point case mapping. 4003 * Full case mappings should be used whenever possible because they produce 4004 * better results by working on whole strings. 4005 * They take into account the string context and the language and can map 4006 * to a result string with a different length as appropriate. 4007 * Full case mappings are applied by the string case mapping functions, 4008 * see ustring.h and the UnicodeString class. 4009 * See also the User Guide chapter on C/POSIX migration: 4010 * https://unicode-org.github.io/icu/userguide/icu/posix#case-mappings 4011 * 4012 * @param c the code point to be mapped 4013 * @return the Simple_Titlecase_Mapping of the code point, if any; 4014 * otherwise the code point itself. 4015 * @stable ICU 2.0 4016 */ 4017 U_CAPI UChar32 U_EXPORT2 4018 u_totitle(UChar32 c); 4019 4020 /** 4021 * The given character is mapped to its case folding equivalent according to 4022 * UnicodeData.txt and CaseFolding.txt; 4023 * if the character has no case folding equivalent, the character 4024 * itself is returned. 4025 * 4026 * This function only returns the simple, single-code point case mapping. 4027 * Full case mappings should be used whenever possible because they produce 4028 * better results by working on whole strings. 4029 * They take into account the string context and the language and can map 4030 * to a result string with a different length as appropriate. 4031 * Full case mappings are applied by the string case mapping functions, 4032 * see ustring.h and the UnicodeString class. 4033 * See also the User Guide chapter on C/POSIX migration: 4034 * https://unicode-org.github.io/icu/userguide/icu/posix#case-mappings 4035 * 4036 * @param c the code point to be mapped 4037 * @param options Either U_FOLD_CASE_DEFAULT or U_FOLD_CASE_EXCLUDE_SPECIAL_I 4038 * @return the Simple_Case_Folding of the code point, if any; 4039 * otherwise the code point itself. 4040 * @stable ICU 2.0 4041 */ 4042 U_CAPI UChar32 U_EXPORT2 4043 u_foldCase(UChar32 c, uint32_t options); 4044 4045 /** 4046 * Returns the decimal digit value of the code point in the 4047 * specified radix. 4048 * 4049 * If the radix is not in the range <code>2<=radix<=36</code> or if the 4050 * value of <code>c</code> is not a valid digit in the specified 4051 * radix, <code>-1</code> is returned. A character is a valid digit 4052 * if at least one of the following is true: 4053 * <ul> 4054 * <li>The character has a decimal digit value. 4055 * Such characters have the general category "Nd" (decimal digit numbers) 4056 * and a Numeric_Type of Decimal. 4057 * In this case the value is the character's decimal digit value.</li> 4058 * <li>The character is one of the uppercase Latin letters 4059 * <code>'A'</code> through <code>'Z'</code>. 4060 * In this case the value is <code>c-'A'+10</code>.</li> 4061 * <li>The character is one of the lowercase Latin letters 4062 * <code>'a'</code> through <code>'z'</code>. 4063 * In this case the value is <code>ch-'a'+10</code>.</li> 4064 * <li>Latin letters from both the ASCII range (0061..007A, 0041..005A) 4065 * as well as from the Fullwidth ASCII range (FF41..FF5A, FF21..FF3A) 4066 * are recognized.</li> 4067 * </ul> 4068 * 4069 * Same as java.lang.Character.digit(). 4070 * 4071 * @param ch the code point to be tested. 4072 * @param radix the radix. 4073 * @return the numeric value represented by the character in the 4074 * specified radix, 4075 * or -1 if there is no value or if the value exceeds the radix. 4076 * 4077 * @see UCHAR_NUMERIC_TYPE 4078 * @see u_forDigit 4079 * @see u_charDigitValue 4080 * @see u_isdigit 4081 * @stable ICU 2.0 4082 */ 4083 U_CAPI int32_t U_EXPORT2 4084 u_digit(UChar32 ch, int8_t radix); 4085 4086 /** 4087 * Determines the character representation for a specific digit in 4088 * the specified radix. If the value of <code>radix</code> is not a 4089 * valid radix, or the value of <code>digit</code> is not a valid 4090 * digit in the specified radix, the null character 4091 * (<code>U+0000</code>) is returned. 4092 * <p> 4093 * The <code>radix</code> argument is valid if it is greater than or 4094 * equal to 2 and less than or equal to 36. 4095 * The <code>digit</code> argument is valid if 4096 * <code>0 <= digit < radix</code>. 4097 * <p> 4098 * If the digit is less than 10, then 4099 * <code>'0' + digit</code> is returned. Otherwise, the value 4100 * <code>'a' + digit - 10</code> is returned. 4101 * 4102 * Same as java.lang.Character.forDigit(). 4103 * 4104 * @param digit the number to convert to a character. 4105 * @param radix the radix. 4106 * @return the <code>char</code> representation of the specified digit 4107 * in the specified radix. 4108 * 4109 * @see u_digit 4110 * @see u_charDigitValue 4111 * @see u_isdigit 4112 * @stable ICU 2.0 4113 */ 4114 U_CAPI UChar32 U_EXPORT2 4115 u_forDigit(int32_t digit, int8_t radix); 4116 4117 /** 4118 * Get the "age" of the code point. 4119 * The "age" is the Unicode version when the code point was first 4120 * designated (as a non-character or for Private Use) 4121 * or assigned a character. 4122 * This can be useful to avoid emitting code points to receiving 4123 * processes that do not accept newer characters. 4124 * The data is from the UCD file DerivedAge.txt. 4125 * 4126 * @param c The code point. 4127 * @param versionArray The Unicode version number array, to be filled in. 4128 * 4129 * @stable ICU 2.1 4130 */ 4131 U_CAPI void U_EXPORT2 4132 u_charAge(UChar32 c, UVersionInfo versionArray); 4133 4134 /** 4135 * Gets the Unicode version information. 4136 * The version array is filled in with the version information 4137 * for the Unicode standard that is currently used by ICU. 4138 * For example, Unicode version 3.1.1 is represented as an array with 4139 * the values { 3, 1, 1, 0 }. 4140 * 4141 * @param versionArray an output array that will be filled in with 4142 * the Unicode version number 4143 * @stable ICU 2.0 4144 */ 4145 U_CAPI void U_EXPORT2 4146 u_getUnicodeVersion(UVersionInfo versionArray); 4147 4148 #if !UCONFIG_NO_NORMALIZATION 4149 /** 4150 * Get the FC_NFKC_Closure property string for a character. 4151 * See Unicode Standard Annex #15 for details, search for "FC_NFKC_Closure" 4152 * or for "FNC": http://www.unicode.org/reports/tr15/ 4153 * 4154 * @param c The character (code point) for which to get the FC_NFKC_Closure string. 4155 * It must be <code>0<=c<=0x10ffff</code>. 4156 * @param dest Destination address for copying the string. 4157 * The string will be zero-terminated if possible. 4158 * If there is no FC_NFKC_Closure string, 4159 * then the buffer will be set to the empty string. 4160 * @param destCapacity <code>==sizeof(dest)</code> 4161 * @param pErrorCode Pointer to a UErrorCode variable. 4162 * @return The length of the string, or 0 if there is no FC_NFKC_Closure string for this character. 4163 * If the destCapacity is less than or equal to the length, then the buffer 4164 * contains the truncated name and the returned length indicates the full 4165 * length of the name. 4166 * The length does not include the zero-termination. 4167 * 4168 * @stable ICU 2.2 4169 */ 4170 U_CAPI int32_t U_EXPORT2 4171 u_getFC_NFKC_Closure(UChar32 c, UChar *dest, int32_t destCapacity, UErrorCode *pErrorCode); 4172 4173 #endif 4174 4175 4176 U_CDECL_END 4177 4178 #endif /*_UCHAR*/ 4179 /*eof*/ 4180