uchar.h (155983B)
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 <stdbool.h> 29 #include "unicode/utypes.h" 30 #include "unicode/stringoptions.h" 31 #include "unicode/ucpmap.h" 32 33 #if !defined(USET_DEFINED) && !defined(U_IN_DOXYGEN) 34 35 #define USET_DEFINED 36 37 /** 38 * USet is the C API type corresponding to C++ class UnicodeSet. 39 * It is forward-declared here to avoid including unicode/uset.h file if related 40 * APIs are not used. 41 * 42 * @see ucnv_getUnicodeSet 43 * @stable ICU 2.4 44 */ 45 typedef struct USet USet; 46 47 #endif 48 49 50 U_CDECL_BEGIN 51 52 /*==========================================================================*/ 53 /* Unicode version number */ 54 /*==========================================================================*/ 55 /** 56 * Unicode version number, default for the current ICU version. 57 * The actual Unicode Character Database (UCD) data is stored in uprops.icu 58 * and may be generated from UCD files from a different Unicode version. 59 * Call u_getUnicodeVersion to get the actual Unicode version of the data. 60 * 61 * @see u_getUnicodeVersion 62 * @stable ICU 2.0 63 */ 64 #define U_UNICODE_VERSION "17.0" 65 66 /** 67 * \file 68 * \brief C API: Unicode Properties 69 * 70 * This C API provides low-level access to the Unicode Character Database. 71 * In addition to raw property values, some convenience functions calculate 72 * derived properties, for example for Java-style programming. 73 * 74 * Unicode assigns each code point (not just assigned character) values for 75 * many properties. 76 * Most of them are simple boolean flags, or constants from a small enumerated list. 77 * For some properties, values are strings or other relatively more complex types. 78 * 79 * For more information see 80 * "About the Unicode Character Database" (http://www.unicode.org/ucd/) 81 * and the ICU User Guide chapter on Properties (https://unicode-org.github.io/icu/userguide/strings/properties). 82 * 83 * Many properties are accessible via generic functions that take a UProperty selector. 84 * - u_hasBinaryProperty() returns a binary value (true/false) per property and code point. 85 * - u_getIntPropertyValue() returns an integer value per property and code point. 86 * For each supported enumerated or catalog property, there is 87 * an enum type for all of the property's values, and 88 * u_getIntPropertyValue() returns the numeric values of those constants. 89 * - u_getBinaryPropertySet() returns a set for each ICU-supported binary property with 90 * all code points for which the property is true. 91 * - u_getIntPropertyMap() returns a map for each 92 * ICU-supported enumerated/catalog/int-valued property which 93 * maps all Unicode code points to their values for that property. 94 * 95 * Many functions are designed to match java.lang.Character functions. 96 * See the individual function documentation, 97 * and see the JDK 1.4 java.lang.Character documentation 98 * at http://java.sun.com/j2se/1.4/docs/api/java/lang/Character.html 99 * 100 * There are also functions that provide easy migration from C/POSIX functions 101 * like isblank(). Their use is generally discouraged because the C/POSIX 102 * standards do not define their semantics beyond the ASCII range, which means 103 * that different implementations exhibit very different behavior. 104 * Instead, Unicode properties should be used directly. 105 * 106 * There are also only a few, broad C/POSIX character classes, and they tend 107 * to be used for conflicting purposes. For example, the "isalpha()" class 108 * is sometimes used to determine word boundaries, while a more sophisticated 109 * approach would at least distinguish initial letters from continuation 110 * characters (the latter including combining marks). 111 * (In ICU, BreakIterator is the most sophisticated API for word boundaries.) 112 * Another example: There is no "istitle()" class for titlecase characters. 113 * 114 * ICU 3.4 and later provides API access for all twelve C/POSIX character classes. 115 * ICU implements them according to the Standard Recommendations in 116 * Annex C: Compatibility Properties of UTS #18 Unicode Regular Expressions 117 * (http://www.unicode.org/reports/tr18/#Compatibility_Properties). 118 * 119 * API access for C/POSIX character classes is as follows: 120 * - alpha: u_isUAlphabetic(c) or u_hasBinaryProperty(c, UCHAR_ALPHABETIC) 121 * - lower: u_isULowercase(c) or u_hasBinaryProperty(c, UCHAR_LOWERCASE) 122 * - upper: u_isUUppercase(c) or u_hasBinaryProperty(c, UCHAR_UPPERCASE) 123 * - punct: u_ispunct(c) 124 * - digit: u_isdigit(c) or u_charType(c)==U_DECIMAL_DIGIT_NUMBER 125 * - xdigit: u_isxdigit(c) or u_hasBinaryProperty(c, UCHAR_POSIX_XDIGIT) 126 * - alnum: u_hasBinaryProperty(c, UCHAR_POSIX_ALNUM) 127 * - space: u_isUWhiteSpace(c) or u_hasBinaryProperty(c, UCHAR_WHITE_SPACE) 128 * - blank: u_isblank(c) or u_hasBinaryProperty(c, UCHAR_POSIX_BLANK) 129 * - cntrl: u_charType(c)==U_CONTROL_CHAR 130 * - graph: u_hasBinaryProperty(c, UCHAR_POSIX_GRAPH) 131 * - print: u_hasBinaryProperty(c, UCHAR_POSIX_PRINT) 132 * 133 * Note: Some of the u_isxyz() functions in uchar.h predate, and do not match, 134 * the Standard Recommendations in UTS #18. Instead, they match Java 135 * functions according to their API documentation. 136 * 137 * \htmlonly 138 * The C/POSIX character classes are also available in UnicodeSet patterns, 139 * using patterns like [:graph:] or \p{graph}. 140 * \endhtmlonly 141 * 142 * Note: There are several ICU whitespace functions. 143 * Comparison: 144 * - u_isUWhiteSpace=UCHAR_WHITE_SPACE: Unicode White_Space property; 145 * most of general categories "Z" (separators) + most whitespace ISO controls 146 * (including no-break spaces, but excluding IS1..IS4) 147 * - u_isWhitespace: Java isWhitespace; Z + whitespace ISO controls but excluding no-break spaces 148 * - u_isJavaSpaceChar: Java isSpaceChar; just Z (including no-break spaces) 149 * - u_isspace: Z + whitespace ISO controls (including no-break spaces) 150 * - u_isblank: "horizontal spaces" = TAB + Zs 151 */ 152 153 /** 154 * Constants. 155 */ 156 157 /** The lowest Unicode code point value. Code points are non-negative. @stable ICU 2.0 */ 158 #define UCHAR_MIN_VALUE 0 159 160 /** 161 * The highest Unicode code point value (scalar value) according to 162 * The Unicode Standard. This is a 21-bit value (20.1 bits, rounded up). 163 * For a single character, UChar32 is a simple type that can hold any code point value. 164 * 165 * @see UChar32 166 * @stable ICU 2.0 167 */ 168 #define UCHAR_MAX_VALUE 0x10ffff 169 170 /** 171 * Get a single-bit bit set (a flag) from a bit number 0..31. 172 * @stable ICU 2.1 173 */ 174 #define U_MASK(x) ((uint32_t)1<<(x)) 175 176 /** 177 * Selection constants for Unicode properties. 178 * These constants are used in functions like u_hasBinaryProperty to select 179 * one of the Unicode properties. 180 * 181 * The properties APIs are intended to reflect Unicode properties as defined 182 * in the Unicode Character Database (UCD) and Unicode Technical Reports (UTR). 183 * 184 * For details about the properties see 185 * UAX #44: Unicode Character Database (http://www.unicode.org/reports/tr44/). 186 * 187 * Important: If ICU is built with UCD files from Unicode versions below, e.g., 3.2, 188 * then properties marked with "new in Unicode 3.2" are not or not fully available. 189 * Check u_getUnicodeVersion to be sure. 190 * 191 * @see u_hasBinaryProperty 192 * @see u_getIntPropertyValue 193 * @see u_getUnicodeVersion 194 * @stable ICU 2.1 195 */ 196 typedef enum UProperty { 197 /* 198 * Note: UProperty constants are parsed by preparseucd.py. 199 * It matches lines like 200 * UCHAR_<Unicode property name>=<integer>, 201 */ 202 203 /* Note: Place UCHAR_ALPHABETIC before UCHAR_BINARY_START so that 204 debuggers display UCHAR_ALPHABETIC as the symbolic name for 0, 205 rather than UCHAR_BINARY_START. Likewise for other *_START 206 identifiers. */ 207 208 /** Binary property Alphabetic. Same as u_isUAlphabetic, different from u_isalpha. 209 Lu+Ll+Lt+Lm+Lo+Nl+Other_Alphabetic @stable ICU 2.1 */ 210 UCHAR_ALPHABETIC=0, 211 /** First constant for binary Unicode properties. @stable ICU 2.1 */ 212 UCHAR_BINARY_START=UCHAR_ALPHABETIC, 213 /** Binary property ASCII_Hex_Digit. 0-9 A-F a-f @stable ICU 2.1 */ 214 UCHAR_ASCII_HEX_DIGIT=1, 215 /** Binary property Bidi_Control. 216 Format controls which have specific functions 217 in the Bidi Algorithm. @stable ICU 2.1 */ 218 UCHAR_BIDI_CONTROL=2, 219 /** Binary property Bidi_Mirrored. 220 Characters that may change display in RTL text. 221 Same as u_isMirrored. 222 See Bidi Algorithm, UTR 9. @stable ICU 2.1 */ 223 UCHAR_BIDI_MIRRORED=3, 224 /** Binary property Dash. Variations of dashes. @stable ICU 2.1 */ 225 UCHAR_DASH=4, 226 /** Binary property Default_Ignorable_Code_Point (new in Unicode 3.2). 227 Ignorable in most processing. 228 <2060..206F, FFF0..FFFB, E0000..E0FFF>+Other_Default_Ignorable_Code_Point+(Cf+Cc+Cs-White_Space) @stable ICU 2.1 */ 229 UCHAR_DEFAULT_IGNORABLE_CODE_POINT=5, 230 /** Binary property Deprecated (new in Unicode 3.2). 231 The usage of deprecated characters is strongly discouraged. @stable ICU 2.1 */ 232 UCHAR_DEPRECATED=6, 233 /** Binary property Diacritic. Characters that linguistically modify 234 the meaning of another character to which they apply. @stable ICU 2.1 */ 235 UCHAR_DIACRITIC=7, 236 /** Binary property Extender. 237 Extend the value or shape of a preceding alphabetic character, 238 e.g., length and iteration marks. @stable ICU 2.1 */ 239 UCHAR_EXTENDER=8, 240 /** Binary property Full_Composition_Exclusion. 241 CompositionExclusions.txt+Singleton Decompositions+ 242 Non-Starter Decompositions. @stable ICU 2.1 */ 243 UCHAR_FULL_COMPOSITION_EXCLUSION=9, 244 /** Binary property Grapheme_Base (new in Unicode 3.2). 245 For programmatic determination of grapheme cluster boundaries. 246 [0..10FFFF]-Cc-Cf-Cs-Co-Cn-Zl-Zp-Grapheme_Link-Grapheme_Extend-CGJ @stable ICU 2.1 */ 247 UCHAR_GRAPHEME_BASE=10, 248 /** Binary property Grapheme_Extend (new in Unicode 3.2). 249 For programmatic determination of grapheme cluster boundaries. 250 Me+Mn+Mc+Other_Grapheme_Extend-Grapheme_Link-CGJ @stable ICU 2.1 */ 251 UCHAR_GRAPHEME_EXTEND=11, 252 /** Binary property Grapheme_Link (new in Unicode 3.2). 253 For programmatic determination of grapheme cluster boundaries. @stable ICU 2.1 */ 254 UCHAR_GRAPHEME_LINK=12, 255 /** Binary property Hex_Digit. 256 Characters commonly used for hexadecimal numbers. @stable ICU 2.1 */ 257 UCHAR_HEX_DIGIT=13, 258 /** Binary property Hyphen. Dashes used to mark connections 259 between pieces of words, plus the Katakana middle dot. @stable ICU 2.1 */ 260 UCHAR_HYPHEN=14, 261 /** Binary property ID_Continue. 262 Characters that can continue an identifier. 263 DerivedCoreProperties.txt also says "NOTE: Cf characters should be filtered out." 264 ID_Start+Mn+Mc+Nd+Pc @stable ICU 2.1 */ 265 UCHAR_ID_CONTINUE=15, 266 /** Binary property ID_Start. 267 Characters that can start an identifier. 268 Lu+Ll+Lt+Lm+Lo+Nl @stable ICU 2.1 */ 269 UCHAR_ID_START=16, 270 /** Binary property Ideographic. 271 CJKV ideographs. @stable ICU 2.1 */ 272 UCHAR_IDEOGRAPHIC=17, 273 /** Binary property IDS_Binary_Operator (new in Unicode 3.2). 274 For programmatic determination of 275 Ideographic Description Sequences. @stable ICU 2.1 */ 276 UCHAR_IDS_BINARY_OPERATOR=18, 277 /** Binary property IDS_Trinary_Operator (new in Unicode 3.2). 278 For programmatic determination of 279 Ideographic Description Sequences. @stable ICU 2.1 */ 280 UCHAR_IDS_TRINARY_OPERATOR=19, 281 /** Binary property Join_Control. 282 Format controls for cursive joining and ligation. @stable ICU 2.1 */ 283 UCHAR_JOIN_CONTROL=20, 284 /** Binary property Logical_Order_Exception (new in Unicode 3.2). 285 Characters that do not use logical order and 286 require special handling in most processing. @stable ICU 2.1 */ 287 UCHAR_LOGICAL_ORDER_EXCEPTION=21, 288 /** Binary property Lowercase. Same as u_isULowercase, different from u_islower. 289 Ll+Other_Lowercase @stable ICU 2.1 */ 290 UCHAR_LOWERCASE=22, 291 /** Binary property Math. Sm+Other_Math @stable ICU 2.1 */ 292 UCHAR_MATH=23, 293 /** Binary property Noncharacter_Code_Point. 294 Code points that are explicitly defined as illegal 295 for the encoding of characters. @stable ICU 2.1 */ 296 UCHAR_NONCHARACTER_CODE_POINT=24, 297 /** Binary property Quotation_Mark. @stable ICU 2.1 */ 298 UCHAR_QUOTATION_MARK=25, 299 /** Binary property Radical (new in Unicode 3.2). 300 For programmatic determination of 301 Ideographic Description Sequences. @stable ICU 2.1 */ 302 UCHAR_RADICAL=26, 303 /** Binary property Soft_Dotted (new in Unicode 3.2). 304 Characters with a "soft dot", like i or j. 305 An accent placed on these characters causes 306 the dot to disappear. @stable ICU 2.1 */ 307 UCHAR_SOFT_DOTTED=27, 308 /** Binary property Terminal_Punctuation. 309 Punctuation characters that generally mark 310 the end of textual units. @stable ICU 2.1 */ 311 UCHAR_TERMINAL_PUNCTUATION=28, 312 /** Binary property Unified_Ideograph (new in Unicode 3.2). 313 For programmatic determination of 314 Ideographic Description Sequences. @stable ICU 2.1 */ 315 UCHAR_UNIFIED_IDEOGRAPH=29, 316 /** Binary property Uppercase. Same as u_isUUppercase, different from u_isupper. 317 Lu+Other_Uppercase @stable ICU 2.1 */ 318 UCHAR_UPPERCASE=30, 319 /** Binary property White_Space. 320 Same as u_isUWhiteSpace, different from u_isspace and u_isWhitespace. 321 Space characters+TAB+CR+LF-ZWSP-ZWNBSP @stable ICU 2.1 */ 322 UCHAR_WHITE_SPACE=31, 323 /** Binary property XID_Continue. 324 ID_Continue modified to allow closure under 325 normalization forms NFKC and NFKD. @stable ICU 2.1 */ 326 UCHAR_XID_CONTINUE=32, 327 /** Binary property XID_Start. ID_Start modified to allow 328 closure under normalization forms NFKC and NFKD. @stable ICU 2.1 */ 329 UCHAR_XID_START=33, 330 /** Binary property Case_Sensitive. Either the source of a case 331 mapping or _in_ the target of a case mapping. Not the same as 332 the general category Cased_Letter. @stable ICU 2.6 */ 333 UCHAR_CASE_SENSITIVE=34, 334 /** Binary property STerm (new in Unicode 4.0.1). 335 Sentence Terminal. Used in UAX #29: Text Boundaries 336 (http://www.unicode.org/reports/tr29/) 337 @stable ICU 3.0 */ 338 UCHAR_S_TERM=35, 339 /** Binary property Variation_Selector (new in Unicode 4.0.1). 340 Indicates all those characters that qualify as Variation Selectors. 341 For details on the behavior of these characters, 342 see StandardizedVariants.html and 15.6 Variation Selectors. 343 @stable ICU 3.0 */ 344 UCHAR_VARIATION_SELECTOR=36, 345 /** Binary property NFD_Inert. 346 ICU-specific property for characters that are inert under NFD, 347 i.e., they do not interact with adjacent characters. 348 See the documentation for the Normalizer2 class and the 349 Normalizer2::isInert() method. 350 @stable ICU 3.0 */ 351 UCHAR_NFD_INERT=37, 352 /** Binary property NFKD_Inert. 353 ICU-specific property for characters that are inert under NFKD, 354 i.e., they do not interact with adjacent characters. 355 See the documentation for the Normalizer2 class and the 356 Normalizer2::isInert() method. 357 @stable ICU 3.0 */ 358 UCHAR_NFKD_INERT=38, 359 /** Binary property NFC_Inert. 360 ICU-specific property for characters that are inert under NFC, 361 i.e., they do not interact with adjacent characters. 362 See the documentation for the Normalizer2 class and the 363 Normalizer2::isInert() method. 364 @stable ICU 3.0 */ 365 UCHAR_NFC_INERT=39, 366 /** Binary property NFKC_Inert. 367 ICU-specific property for characters that are inert under NFKC, 368 i.e., they do not interact with adjacent characters. 369 See the documentation for the Normalizer2 class and the 370 Normalizer2::isInert() method. 371 @stable ICU 3.0 */ 372 UCHAR_NFKC_INERT=40, 373 /** Binary Property Segment_Starter. 374 ICU-specific property for characters that are starters in terms of 375 Unicode normalization and combining character sequences. 376 They have ccc=0 and do not occur in non-initial position of the 377 canonical decomposition of any character 378 (like a-umlaut in NFD and a Jamo T in an NFD(Hangul LVT)). 379 ICU uses this property for segmenting a string for generating a set of 380 canonically equivalent strings, e.g. for canonical closure while 381 processing collation tailoring rules. 382 @stable ICU 3.0 */ 383 UCHAR_SEGMENT_STARTER=41, 384 /** Binary property Pattern_Syntax (new in Unicode 4.1). 385 See UAX #31 Identifier and Pattern Syntax 386 (http://www.unicode.org/reports/tr31/) 387 @stable ICU 3.4 */ 388 UCHAR_PATTERN_SYNTAX=42, 389 /** Binary property Pattern_White_Space (new in Unicode 4.1). 390 See UAX #31 Identifier and Pattern Syntax 391 (http://www.unicode.org/reports/tr31/) 392 @stable ICU 3.4 */ 393 UCHAR_PATTERN_WHITE_SPACE=43, 394 /** Binary property alnum (a C/POSIX character class). 395 Implemented according to the UTS #18 Annex C Standard Recommendation. 396 See the uchar.h file documentation. 397 @stable ICU 3.4 */ 398 UCHAR_POSIX_ALNUM=44, 399 /** Binary property blank (a C/POSIX character class). 400 Implemented according to the UTS #18 Annex C Standard Recommendation. 401 See the uchar.h file documentation. 402 @stable ICU 3.4 */ 403 UCHAR_POSIX_BLANK=45, 404 /** Binary property graph (a C/POSIX character class). 405 Implemented according to the UTS #18 Annex C Standard Recommendation. 406 See the uchar.h file documentation. 407 @stable ICU 3.4 */ 408 UCHAR_POSIX_GRAPH=46, 409 /** Binary property print (a C/POSIX character class). 410 Implemented according to the UTS #18 Annex C Standard Recommendation. 411 See the uchar.h file documentation. 412 @stable ICU 3.4 */ 413 UCHAR_POSIX_PRINT=47, 414 /** Binary property xdigit (a C/POSIX character class). 415 Implemented according to the UTS #18 Annex C Standard Recommendation. 416 See the uchar.h file documentation. 417 @stable ICU 3.4 */ 418 UCHAR_POSIX_XDIGIT=48, 419 /** Binary property Cased. For Lowercase, Uppercase and Titlecase characters. @stable ICU 4.4 */ 420 UCHAR_CASED=49, 421 /** Binary property Case_Ignorable. Used in context-sensitive case mappings. @stable ICU 4.4 */ 422 UCHAR_CASE_IGNORABLE=50, 423 /** Binary property Changes_When_Lowercased. @stable ICU 4.4 */ 424 UCHAR_CHANGES_WHEN_LOWERCASED=51, 425 /** Binary property Changes_When_Uppercased. @stable ICU 4.4 */ 426 UCHAR_CHANGES_WHEN_UPPERCASED=52, 427 /** Binary property Changes_When_Titlecased. @stable ICU 4.4 */ 428 UCHAR_CHANGES_WHEN_TITLECASED=53, 429 /** Binary property Changes_When_Casefolded. @stable ICU 4.4 */ 430 UCHAR_CHANGES_WHEN_CASEFOLDED=54, 431 /** Binary property Changes_When_Casemapped. @stable ICU 4.4 */ 432 UCHAR_CHANGES_WHEN_CASEMAPPED=55, 433 /** Binary property Changes_When_NFKC_Casefolded. @stable ICU 4.4 */ 434 UCHAR_CHANGES_WHEN_NFKC_CASEFOLDED=56, 435 /** 436 * Binary property Emoji. 437 * See http://www.unicode.org/reports/tr51/#Emoji_Properties 438 * 439 * @stable ICU 57 440 */ 441 UCHAR_EMOJI=57, 442 /** 443 * Binary property Emoji_Presentation. 444 * See http://www.unicode.org/reports/tr51/#Emoji_Properties 445 * 446 * @stable ICU 57 447 */ 448 UCHAR_EMOJI_PRESENTATION=58, 449 /** 450 * Binary property Emoji_Modifier. 451 * See http://www.unicode.org/reports/tr51/#Emoji_Properties 452 * 453 * @stable ICU 57 454 */ 455 UCHAR_EMOJI_MODIFIER=59, 456 /** 457 * Binary property Emoji_Modifier_Base. 458 * See http://www.unicode.org/reports/tr51/#Emoji_Properties 459 * 460 * @stable ICU 57 461 */ 462 UCHAR_EMOJI_MODIFIER_BASE=60, 463 /** 464 * Binary property Emoji_Component. 465 * See http://www.unicode.org/reports/tr51/#Emoji_Properties 466 * 467 * @stable ICU 60 468 */ 469 UCHAR_EMOJI_COMPONENT=61, 470 /** 471 * Binary property Regional_Indicator. 472 * @stable ICU 60 473 */ 474 UCHAR_REGIONAL_INDICATOR=62, 475 /** 476 * Binary property Prepended_Concatenation_Mark. 477 * @stable ICU 60 478 */ 479 UCHAR_PREPENDED_CONCATENATION_MARK=63, 480 /** 481 * Binary property Extended_Pictographic. 482 * See http://www.unicode.org/reports/tr51/#Emoji_Properties 483 * 484 * @stable ICU 62 485 */ 486 UCHAR_EXTENDED_PICTOGRAPHIC=64, 487 /** 488 * Binary property of strings Basic_Emoji. 489 * See https://www.unicode.org/reports/tr51/#Emoji_Sets 490 * 491 * @stable ICU 70 492 */ 493 UCHAR_BASIC_EMOJI=65, 494 /** 495 * Binary property of strings Emoji_Keycap_Sequence. 496 * See https://www.unicode.org/reports/tr51/#Emoji_Sets 497 * 498 * @stable ICU 70 499 */ 500 UCHAR_EMOJI_KEYCAP_SEQUENCE=66, 501 /** 502 * Binary property of strings RGI_Emoji_Modifier_Sequence. 503 * See https://www.unicode.org/reports/tr51/#Emoji_Sets 504 * 505 * @stable ICU 70 506 */ 507 UCHAR_RGI_EMOJI_MODIFIER_SEQUENCE=67, 508 /** 509 * Binary property of strings RGI_Emoji_Flag_Sequence. 510 * See https://www.unicode.org/reports/tr51/#Emoji_Sets 511 * 512 * @stable ICU 70 513 */ 514 UCHAR_RGI_EMOJI_FLAG_SEQUENCE=68, 515 /** 516 * Binary property of strings RGI_Emoji_Tag_Sequence. 517 * See https://www.unicode.org/reports/tr51/#Emoji_Sets 518 * 519 * @stable ICU 70 520 */ 521 UCHAR_RGI_EMOJI_TAG_SEQUENCE=69, 522 /** 523 * Binary property of strings RGI_Emoji_ZWJ_Sequence. 524 * See https://www.unicode.org/reports/tr51/#Emoji_Sets 525 * 526 * @stable ICU 70 527 */ 528 UCHAR_RGI_EMOJI_ZWJ_SEQUENCE=70, 529 /** 530 * Binary property of strings RGI_Emoji. 531 * See https://www.unicode.org/reports/tr51/#Emoji_Sets 532 * 533 * @stable ICU 70 534 */ 535 UCHAR_RGI_EMOJI=71, 536 /** 537 * Binary property IDS_Unary_Operator. 538 * For programmatic determination of Ideographic Description Sequences. 539 * 540 * @stable ICU 74 541 */ 542 UCHAR_IDS_UNARY_OPERATOR=72, 543 /** 544 * Binary property ID_Compat_Math_Start. 545 * Used in mathematical identifier profile in UAX #31. 546 * @stable ICU 74 547 */ 548 UCHAR_ID_COMPAT_MATH_START=73, 549 /** 550 * Binary property ID_Compat_Math_Continue. 551 * Used in mathematical identifier profile in UAX #31. 552 * @stable ICU 74 553 */ 554 UCHAR_ID_COMPAT_MATH_CONTINUE=74, 555 /** 556 * Binary property Modifier_Combining_Mark. 557 * Used by the AMTRA algorithm in UAX #53. 558 * @stable ICU 76 559 */ 560 UCHAR_MODIFIER_COMBINING_MARK=75, 561 #ifndef U_HIDE_DEPRECATED_API 562 /** 563 * One more than the last constant for binary Unicode properties. 564 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. 565 */ 566 UCHAR_BINARY_LIMIT=76, 567 #endif // U_HIDE_DEPRECATED_API 568 569 /** Enumerated property Bidi_Class. 570 Same as u_charDirection, returns UCharDirection values. @stable ICU 2.2 */ 571 UCHAR_BIDI_CLASS=0x1000, 572 /** First constant for enumerated/integer Unicode properties. @stable ICU 2.2 */ 573 UCHAR_INT_START=UCHAR_BIDI_CLASS, 574 /** Enumerated property Block. 575 Same as ublock_getCode, returns UBlockCode values. @stable ICU 2.2 */ 576 UCHAR_BLOCK=0x1001, 577 /** Enumerated property Canonical_Combining_Class. 578 Same as u_getCombiningClass, returns 8-bit numeric values. @stable ICU 2.2 */ 579 UCHAR_CANONICAL_COMBINING_CLASS=0x1002, 580 /** Enumerated property Decomposition_Type. 581 Returns UDecompositionType values. @stable ICU 2.2 */ 582 UCHAR_DECOMPOSITION_TYPE=0x1003, 583 /** Enumerated property East_Asian_Width. 584 See http://www.unicode.org/reports/tr11/ 585 Returns UEastAsianWidth values. @stable ICU 2.2 */ 586 UCHAR_EAST_ASIAN_WIDTH=0x1004, 587 /** Enumerated property General_Category. 588 Same as u_charType, returns UCharCategory values. @stable ICU 2.2 */ 589 UCHAR_GENERAL_CATEGORY=0x1005, 590 /** Enumerated property Joining_Group. 591 Returns UJoiningGroup values. @stable ICU 2.2 */ 592 UCHAR_JOINING_GROUP=0x1006, 593 /** Enumerated property Joining_Type. 594 Returns UJoiningType values. @stable ICU 2.2 */ 595 UCHAR_JOINING_TYPE=0x1007, 596 /** Enumerated property Line_Break. 597 Returns ULineBreak values. @stable ICU 2.2 */ 598 UCHAR_LINE_BREAK=0x1008, 599 /** Enumerated property Numeric_Type. 600 Returns UNumericType values. @stable ICU 2.2 */ 601 UCHAR_NUMERIC_TYPE=0x1009, 602 /** Enumerated property Script. 603 Same as uscript_getScript, returns UScriptCode values. @stable ICU 2.2 */ 604 UCHAR_SCRIPT=0x100A, 605 /** Enumerated property Hangul_Syllable_Type, new in Unicode 4. 606 Returns UHangulSyllableType values. @stable ICU 2.6 */ 607 UCHAR_HANGUL_SYLLABLE_TYPE=0x100B, 608 /** Enumerated property NFD_Quick_Check. 609 Returns UNormalizationCheckResult values. @stable ICU 3.0 */ 610 UCHAR_NFD_QUICK_CHECK=0x100C, 611 /** Enumerated property NFKD_Quick_Check. 612 Returns UNormalizationCheckResult values. @stable ICU 3.0 */ 613 UCHAR_NFKD_QUICK_CHECK=0x100D, 614 /** Enumerated property NFC_Quick_Check. 615 Returns UNormalizationCheckResult values. @stable ICU 3.0 */ 616 UCHAR_NFC_QUICK_CHECK=0x100E, 617 /** Enumerated property NFKC_Quick_Check. 618 Returns UNormalizationCheckResult values. @stable ICU 3.0 */ 619 UCHAR_NFKC_QUICK_CHECK=0x100F, 620 /** Enumerated property Lead_Canonical_Combining_Class. 621 ICU-specific property for the ccc of the first code point 622 of the decomposition, or lccc(c)=ccc(NFD(c)[0]). 623 Useful for checking for canonically ordered text; 624 see UNORM_FCD and http://www.unicode.org/notes/tn5/#FCD . 625 Returns 8-bit numeric values like UCHAR_CANONICAL_COMBINING_CLASS. @stable ICU 3.0 */ 626 UCHAR_LEAD_CANONICAL_COMBINING_CLASS=0x1010, 627 /** Enumerated property Trail_Canonical_Combining_Class. 628 ICU-specific property for the ccc of the last code point 629 of the decomposition, or tccc(c)=ccc(NFD(c)[last]). 630 Useful for checking for canonically ordered text; 631 see UNORM_FCD and http://www.unicode.org/notes/tn5/#FCD . 632 Returns 8-bit numeric values like UCHAR_CANONICAL_COMBINING_CLASS. @stable ICU 3.0 */ 633 UCHAR_TRAIL_CANONICAL_COMBINING_CLASS=0x1011, 634 /** Enumerated property Grapheme_Cluster_Break (new in Unicode 4.1). 635 Used in UAX #29: Text Boundaries 636 (http://www.unicode.org/reports/tr29/) 637 Returns UGraphemeClusterBreak values. @stable ICU 3.4 */ 638 UCHAR_GRAPHEME_CLUSTER_BREAK=0x1012, 639 /** Enumerated property Sentence_Break (new in Unicode 4.1). 640 Used in UAX #29: Text Boundaries 641 (http://www.unicode.org/reports/tr29/) 642 Returns USentenceBreak values. @stable ICU 3.4 */ 643 UCHAR_SENTENCE_BREAK=0x1013, 644 /** Enumerated property Word_Break (new in Unicode 4.1). 645 Used in UAX #29: Text Boundaries 646 (http://www.unicode.org/reports/tr29/) 647 Returns UWordBreakValues values. @stable ICU 3.4 */ 648 UCHAR_WORD_BREAK=0x1014, 649 /** Enumerated property Bidi_Paired_Bracket_Type (new in Unicode 6.3). 650 Used in UAX #9: Unicode Bidirectional Algorithm 651 (http://www.unicode.org/reports/tr9/) 652 Returns UBidiPairedBracketType values. @stable ICU 52 */ 653 UCHAR_BIDI_PAIRED_BRACKET_TYPE=0x1015, 654 /** 655 * Enumerated property Indic_Positional_Category. 656 * New in Unicode 6.0 as provisional property Indic_Matra_Category; 657 * renamed and changed to informative in Unicode 8.0. 658 * See http://www.unicode.org/reports/tr44/#IndicPositionalCategory.txt 659 * @stable ICU 63 660 */ 661 UCHAR_INDIC_POSITIONAL_CATEGORY=0x1016, 662 /** 663 * Enumerated property Indic_Syllabic_Category. 664 * New in Unicode 6.0 as provisional; informative since Unicode 8.0. 665 * See http://www.unicode.org/reports/tr44/#IndicSyllabicCategory.txt 666 * @stable ICU 63 667 */ 668 UCHAR_INDIC_SYLLABIC_CATEGORY=0x1017, 669 /** 670 * Enumerated property Vertical_Orientation. 671 * Used for UAX #50 Unicode Vertical Text Layout (https://www.unicode.org/reports/tr50/). 672 * New as a UCD property in Unicode 10.0. 673 * @stable ICU 63 674 */ 675 UCHAR_VERTICAL_ORIENTATION=0x1018, 676 /** 677 * Enumerated property Identifier_Status. 678 * Used for UTS #39 General Security Profile for Identifiers 679 * (https://www.unicode.org/reports/tr39/#General_Security_Profile). 680 * @stable ICU 75 681 */ 682 UCHAR_IDENTIFIER_STATUS=0x1019, 683 /** 684 * Enumerated property Indic_Conjunct_Break. 685 * Used in the grapheme cluster break algorithm in UAX #29. 686 * @stable ICU 76 687 */ 688 UCHAR_INDIC_CONJUNCT_BREAK=0x101A, 689 #ifndef U_HIDE_DEPRECATED_API 690 /** 691 * One more than the last constant for enumerated/integer Unicode properties. 692 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. 693 */ 694 UCHAR_INT_LIMIT=0x101B, 695 #endif // U_HIDE_DEPRECATED_API 696 697 /** Bitmask property General_Category_Mask. 698 This is the General_Category property returned as a bit mask. 699 When used in u_getIntPropertyValue(c), same as U_MASK(u_charType(c)), 700 returns bit masks for UCharCategory values where exactly one bit is set. 701 When used with u_getPropertyValueName() and u_getPropertyValueEnum(), 702 a multi-bit mask is used for sets of categories like "Letters". 703 Mask values should be cast to uint32_t. 704 @stable ICU 2.4 */ 705 UCHAR_GENERAL_CATEGORY_MASK=0x2000, 706 /** First constant for bit-mask Unicode properties. @stable ICU 2.4 */ 707 UCHAR_MASK_START=UCHAR_GENERAL_CATEGORY_MASK, 708 #ifndef U_HIDE_DEPRECATED_API 709 /** 710 * One more than the last constant for bit-mask Unicode properties. 711 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. 712 */ 713 UCHAR_MASK_LIMIT=0x2001, 714 #endif // U_HIDE_DEPRECATED_API 715 716 /** Double property Numeric_Value. 717 Corresponds to u_getNumericValue. @stable ICU 2.4 */ 718 UCHAR_NUMERIC_VALUE=0x3000, 719 /** First constant for double Unicode properties. @stable ICU 2.4 */ 720 UCHAR_DOUBLE_START=UCHAR_NUMERIC_VALUE, 721 #ifndef U_HIDE_DEPRECATED_API 722 /** 723 * One more than the last constant for double Unicode properties. 724 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. 725 */ 726 UCHAR_DOUBLE_LIMIT=0x3001, 727 #endif // U_HIDE_DEPRECATED_API 728 729 /** String property Age. 730 Corresponds to u_charAge. @stable ICU 2.4 */ 731 UCHAR_AGE=0x4000, 732 /** First constant for string Unicode properties. @stable ICU 2.4 */ 733 UCHAR_STRING_START=UCHAR_AGE, 734 /** String property Bidi_Mirroring_Glyph. 735 Corresponds to u_charMirror. @stable ICU 2.4 */ 736 UCHAR_BIDI_MIRRORING_GLYPH=0x4001, 737 /** String property Case_Folding. 738 Corresponds to u_strFoldCase in ustring.h. @stable ICU 2.4 */ 739 UCHAR_CASE_FOLDING=0x4002, 740 #ifndef U_HIDE_DEPRECATED_API 741 /** Deprecated string property ISO_Comment. 742 Corresponds to u_getISOComment. @deprecated ICU 49 */ 743 UCHAR_ISO_COMMENT=0x4003, 744 #endif /* U_HIDE_DEPRECATED_API */ 745 /** String property Lowercase_Mapping. 746 Corresponds to u_strToLower in ustring.h. @stable ICU 2.4 */ 747 UCHAR_LOWERCASE_MAPPING=0x4004, 748 /** String property Name. 749 Corresponds to u_charName. @stable ICU 2.4 */ 750 UCHAR_NAME=0x4005, 751 /** String property Simple_Case_Folding. 752 Corresponds to u_foldCase. @stable ICU 2.4 */ 753 UCHAR_SIMPLE_CASE_FOLDING=0x4006, 754 /** String property Simple_Lowercase_Mapping. 755 Corresponds to u_tolower. @stable ICU 2.4 */ 756 UCHAR_SIMPLE_LOWERCASE_MAPPING=0x4007, 757 /** String property Simple_Titlecase_Mapping. 758 Corresponds to u_totitle. @stable ICU 2.4 */ 759 UCHAR_SIMPLE_TITLECASE_MAPPING=0x4008, 760 /** String property Simple_Uppercase_Mapping. 761 Corresponds to u_toupper. @stable ICU 2.4 */ 762 UCHAR_SIMPLE_UPPERCASE_MAPPING=0x4009, 763 /** String property Titlecase_Mapping. 764 Corresponds to u_strToTitle in ustring.h. @stable ICU 2.4 */ 765 UCHAR_TITLECASE_MAPPING=0x400A, 766 #ifndef U_HIDE_DEPRECATED_API 767 /** String property Unicode_1_Name. 768 This property is of little practical value. 769 Beginning with ICU 49, ICU APIs return an empty string for this property. 770 Corresponds to u_charName(U_UNICODE_10_CHAR_NAME). @deprecated ICU 49 */ 771 UCHAR_UNICODE_1_NAME=0x400B, 772 #endif /* U_HIDE_DEPRECATED_API */ 773 /** String property Uppercase_Mapping. 774 Corresponds to u_strToUpper in ustring.h. @stable ICU 2.4 */ 775 UCHAR_UPPERCASE_MAPPING=0x400C, 776 /** String property Bidi_Paired_Bracket (new in Unicode 6.3). 777 Corresponds to u_getBidiPairedBracket. @stable ICU 52 */ 778 UCHAR_BIDI_PAIRED_BRACKET=0x400D, 779 #ifndef U_HIDE_DEPRECATED_API 780 /** 781 * One more than the last constant for string Unicode properties. 782 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. 783 */ 784 UCHAR_STRING_LIMIT=0x400E, 785 #endif // U_HIDE_DEPRECATED_API 786 787 /** Miscellaneous property Script_Extensions (new in Unicode 6.0). 788 Some characters are commonly used in multiple scripts. 789 For more information, see UAX #24: http://www.unicode.org/reports/tr24/. 790 Corresponds to uscript_hasScript and uscript_getScriptExtensions in uscript.h. 791 @stable ICU 4.6 */ 792 UCHAR_SCRIPT_EXTENSIONS=0x7000, 793 /** First constant for Unicode properties with unusual value types. @stable ICU 4.6 */ 794 UCHAR_OTHER_PROPERTY_START=UCHAR_SCRIPT_EXTENSIONS, 795 /** 796 * Miscellaneous property Identifier_Type. 797 * Used for UTS #39 General Security Profile for Identifiers 798 * (https://www.unicode.org/reports/tr39/#General_Security_Profile). 799 * 800 * Corresponds to u_hasIDType() and u_getIDTypes(). 801 * 802 * Each code point maps to a <i>set</i> of UIdentifierType values. 803 * 804 * @see u_hasIDType 805 * @see u_getIDTypes 806 * @stable ICU 75 807 */ 808 UCHAR_IDENTIFIER_TYPE=0x7001, 809 #ifndef U_HIDE_DEPRECATED_API 810 /** 811 * One more than the last constant for Unicode properties with unusual value types. 812 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. 813 */ 814 UCHAR_OTHER_PROPERTY_LIMIT=0x7002, 815 #endif // U_HIDE_DEPRECATED_API 816 817 /** Represents a nonexistent or invalid property or property value. @stable ICU 2.4 */ 818 UCHAR_INVALID_CODE = -1 819 } UProperty; 820 821 /** 822 * Data for enumerated Unicode general category types. 823 * See http://www.unicode.org/Public/UNIDATA/UnicodeData.html . 824 * @stable ICU 2.0 825 */ 826 typedef enum UCharCategory 827 { 828 /* 829 * Note: UCharCategory constants and their API comments are parsed by preparseucd.py. 830 * It matches pairs of lines like 831 * / ** <Unicode 2-letter General_Category value> comment... * / 832 * U_<[A-Z_]+> = <integer>, 833 */ 834 835 /** Non-category for unassigned and non-character code points. @stable ICU 2.0 */ 836 U_UNASSIGNED = 0, 837 /** Cn "Other, Not Assigned (no characters in [UnicodeData.txt] have this property)" (same as U_UNASSIGNED!) @stable ICU 2.0 */ 838 U_GENERAL_OTHER_TYPES = 0, 839 /** Lu @stable ICU 2.0 */ 840 U_UPPERCASE_LETTER = 1, 841 /** Ll @stable ICU 2.0 */ 842 U_LOWERCASE_LETTER = 2, 843 /** Lt @stable ICU 2.0 */ 844 U_TITLECASE_LETTER = 3, 845 /** Lm @stable ICU 2.0 */ 846 U_MODIFIER_LETTER = 4, 847 /** Lo @stable ICU 2.0 */ 848 U_OTHER_LETTER = 5, 849 /** Mn @stable ICU 2.0 */ 850 U_NON_SPACING_MARK = 6, 851 /** Me @stable ICU 2.0 */ 852 U_ENCLOSING_MARK = 7, 853 /** Mc @stable ICU 2.0 */ 854 U_COMBINING_SPACING_MARK = 8, 855 /** Nd @stable ICU 2.0 */ 856 U_DECIMAL_DIGIT_NUMBER = 9, 857 /** Nl @stable ICU 2.0 */ 858 U_LETTER_NUMBER = 10, 859 /** No @stable ICU 2.0 */ 860 U_OTHER_NUMBER = 11, 861 /** Zs @stable ICU 2.0 */ 862 U_SPACE_SEPARATOR = 12, 863 /** Zl @stable ICU 2.0 */ 864 U_LINE_SEPARATOR = 13, 865 /** Zp @stable ICU 2.0 */ 866 U_PARAGRAPH_SEPARATOR = 14, 867 /** Cc @stable ICU 2.0 */ 868 U_CONTROL_CHAR = 15, 869 /** Cf @stable ICU 2.0 */ 870 U_FORMAT_CHAR = 16, 871 /** Co @stable ICU 2.0 */ 872 U_PRIVATE_USE_CHAR = 17, 873 /** Cs @stable ICU 2.0 */ 874 U_SURROGATE = 18, 875 /** Pd @stable ICU 2.0 */ 876 U_DASH_PUNCTUATION = 19, 877 /** Ps @stable ICU 2.0 */ 878 U_START_PUNCTUATION = 20, 879 /** Pe @stable ICU 2.0 */ 880 U_END_PUNCTUATION = 21, 881 /** Pc @stable ICU 2.0 */ 882 U_CONNECTOR_PUNCTUATION = 22, 883 /** Po @stable ICU 2.0 */ 884 U_OTHER_PUNCTUATION = 23, 885 /** Sm @stable ICU 2.0 */ 886 U_MATH_SYMBOL = 24, 887 /** Sc @stable ICU 2.0 */ 888 U_CURRENCY_SYMBOL = 25, 889 /** Sk @stable ICU 2.0 */ 890 U_MODIFIER_SYMBOL = 26, 891 /** So @stable ICU 2.0 */ 892 U_OTHER_SYMBOL = 27, 893 /** Pi @stable ICU 2.0 */ 894 U_INITIAL_PUNCTUATION = 28, 895 /** Pf @stable ICU 2.0 */ 896 U_FINAL_PUNCTUATION = 29, 897 /** 898 * One higher than the last enum UCharCategory constant. 899 * This numeric value is stable (will not change), see 900 * http://www.unicode.org/policies/stability_policy.html#Property_Value 901 * 902 * @stable ICU 2.0 903 */ 904 U_CHAR_CATEGORY_COUNT 905 } UCharCategory; 906 907 /** 908 * U_GC_XX_MASK constants are bit flags corresponding to Unicode 909 * general category values. 910 * For each category, the nth bit is set if the numeric value of the 911 * corresponding UCharCategory constant is n. 912 * 913 * There are also some U_GC_Y_MASK constants for groups of general categories 914 * like L for all letter categories. 915 * 916 * @see u_charType 917 * @see U_GET_GC_MASK 918 * @see UCharCategory 919 * @stable ICU 2.1 920 */ 921 #define U_GC_CN_MASK U_MASK(U_GENERAL_OTHER_TYPES) 922 923 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 924 #define U_GC_LU_MASK U_MASK(U_UPPERCASE_LETTER) 925 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 926 #define U_GC_LL_MASK U_MASK(U_LOWERCASE_LETTER) 927 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 928 #define U_GC_LT_MASK U_MASK(U_TITLECASE_LETTER) 929 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 930 #define U_GC_LM_MASK U_MASK(U_MODIFIER_LETTER) 931 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 932 #define U_GC_LO_MASK U_MASK(U_OTHER_LETTER) 933 934 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 935 #define U_GC_MN_MASK U_MASK(U_NON_SPACING_MARK) 936 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 937 #define U_GC_ME_MASK U_MASK(U_ENCLOSING_MARK) 938 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 939 #define U_GC_MC_MASK U_MASK(U_COMBINING_SPACING_MARK) 940 941 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 942 #define U_GC_ND_MASK U_MASK(U_DECIMAL_DIGIT_NUMBER) 943 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 944 #define U_GC_NL_MASK U_MASK(U_LETTER_NUMBER) 945 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 946 #define U_GC_NO_MASK U_MASK(U_OTHER_NUMBER) 947 948 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 949 #define U_GC_ZS_MASK U_MASK(U_SPACE_SEPARATOR) 950 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 951 #define U_GC_ZL_MASK U_MASK(U_LINE_SEPARATOR) 952 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 953 #define U_GC_ZP_MASK U_MASK(U_PARAGRAPH_SEPARATOR) 954 955 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 956 #define U_GC_CC_MASK U_MASK(U_CONTROL_CHAR) 957 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 958 #define U_GC_CF_MASK U_MASK(U_FORMAT_CHAR) 959 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 960 #define U_GC_CO_MASK U_MASK(U_PRIVATE_USE_CHAR) 961 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 962 #define U_GC_CS_MASK U_MASK(U_SURROGATE) 963 964 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 965 #define U_GC_PD_MASK U_MASK(U_DASH_PUNCTUATION) 966 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 967 #define U_GC_PS_MASK U_MASK(U_START_PUNCTUATION) 968 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 969 #define U_GC_PE_MASK U_MASK(U_END_PUNCTUATION) 970 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 971 #define U_GC_PC_MASK U_MASK(U_CONNECTOR_PUNCTUATION) 972 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 973 #define U_GC_PO_MASK U_MASK(U_OTHER_PUNCTUATION) 974 975 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 976 #define U_GC_SM_MASK U_MASK(U_MATH_SYMBOL) 977 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 978 #define U_GC_SC_MASK U_MASK(U_CURRENCY_SYMBOL) 979 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 980 #define U_GC_SK_MASK U_MASK(U_MODIFIER_SYMBOL) 981 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 982 #define U_GC_SO_MASK U_MASK(U_OTHER_SYMBOL) 983 984 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 985 #define U_GC_PI_MASK U_MASK(U_INITIAL_PUNCTUATION) 986 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 987 #define U_GC_PF_MASK U_MASK(U_FINAL_PUNCTUATION) 988 989 990 /** Mask constant for multiple UCharCategory bits (L Letters). @stable ICU 2.1 */ 991 #define U_GC_L_MASK \ 992 (U_GC_LU_MASK|U_GC_LL_MASK|U_GC_LT_MASK|U_GC_LM_MASK|U_GC_LO_MASK) 993 994 /** Mask constant for multiple UCharCategory bits (LC Cased Letters). @stable ICU 2.1 */ 995 #define U_GC_LC_MASK \ 996 (U_GC_LU_MASK|U_GC_LL_MASK|U_GC_LT_MASK) 997 998 /** Mask constant for multiple UCharCategory bits (M Marks). @stable ICU 2.1 */ 999 #define U_GC_M_MASK (U_GC_MN_MASK|U_GC_ME_MASK|U_GC_MC_MASK) 1000 1001 /** Mask constant for multiple UCharCategory bits (N Numbers). @stable ICU 2.1 */ 1002 #define U_GC_N_MASK (U_GC_ND_MASK|U_GC_NL_MASK|U_GC_NO_MASK) 1003 1004 /** Mask constant for multiple UCharCategory bits (Z Separators). @stable ICU 2.1 */ 1005 #define U_GC_Z_MASK (U_GC_ZS_MASK|U_GC_ZL_MASK|U_GC_ZP_MASK) 1006 1007 /** Mask constant for multiple UCharCategory bits (C Others). @stable ICU 2.1 */ 1008 #define U_GC_C_MASK \ 1009 (U_GC_CN_MASK|U_GC_CC_MASK|U_GC_CF_MASK|U_GC_CO_MASK|U_GC_CS_MASK) 1010 1011 /** Mask constant for multiple UCharCategory bits (P Punctuation). @stable ICU 2.1 */ 1012 #define U_GC_P_MASK \ 1013 (U_GC_PD_MASK|U_GC_PS_MASK|U_GC_PE_MASK|U_GC_PC_MASK|U_GC_PO_MASK| \ 1014 U_GC_PI_MASK|U_GC_PF_MASK) 1015 1016 /** Mask constant for multiple UCharCategory bits (S Symbols). @stable ICU 2.1 */ 1017 #define U_GC_S_MASK (U_GC_SM_MASK|U_GC_SC_MASK|U_GC_SK_MASK|U_GC_SO_MASK) 1018 1019 /** 1020 * This specifies the language directional property of a character set. 1021 * @stable ICU 2.0 1022 */ 1023 typedef enum UCharDirection { 1024 /* 1025 * Note: UCharDirection constants and their API comments are parsed by preparseucd.py. 1026 * It matches pairs of lines like 1027 * / ** <Unicode 1..3-letter Bidi_Class value> comment... * / 1028 * U_<[A-Z_]+> = <integer>, 1029 */ 1030 1031 /** L @stable ICU 2.0 */ 1032 U_LEFT_TO_RIGHT = 0, 1033 /** R @stable ICU 2.0 */ 1034 U_RIGHT_TO_LEFT = 1, 1035 /** EN @stable ICU 2.0 */ 1036 U_EUROPEAN_NUMBER = 2, 1037 /** ES @stable ICU 2.0 */ 1038 U_EUROPEAN_NUMBER_SEPARATOR = 3, 1039 /** ET @stable ICU 2.0 */ 1040 U_EUROPEAN_NUMBER_TERMINATOR = 4, 1041 /** AN @stable ICU 2.0 */ 1042 U_ARABIC_NUMBER = 5, 1043 /** CS @stable ICU 2.0 */ 1044 U_COMMON_NUMBER_SEPARATOR = 6, 1045 /** B @stable ICU 2.0 */ 1046 U_BLOCK_SEPARATOR = 7, 1047 /** S @stable ICU 2.0 */ 1048 U_SEGMENT_SEPARATOR = 8, 1049 /** WS @stable ICU 2.0 */ 1050 U_WHITE_SPACE_NEUTRAL = 9, 1051 /** ON @stable ICU 2.0 */ 1052 U_OTHER_NEUTRAL = 10, 1053 /** LRE @stable ICU 2.0 */ 1054 U_LEFT_TO_RIGHT_EMBEDDING = 11, 1055 /** LRO @stable ICU 2.0 */ 1056 U_LEFT_TO_RIGHT_OVERRIDE = 12, 1057 /** AL @stable ICU 2.0 */ 1058 U_RIGHT_TO_LEFT_ARABIC = 13, 1059 /** RLE @stable ICU 2.0 */ 1060 U_RIGHT_TO_LEFT_EMBEDDING = 14, 1061 /** RLO @stable ICU 2.0 */ 1062 U_RIGHT_TO_LEFT_OVERRIDE = 15, 1063 /** PDF @stable ICU 2.0 */ 1064 U_POP_DIRECTIONAL_FORMAT = 16, 1065 /** NSM @stable ICU 2.0 */ 1066 U_DIR_NON_SPACING_MARK = 17, 1067 /** BN @stable ICU 2.0 */ 1068 U_BOUNDARY_NEUTRAL = 18, 1069 /** FSI @stable ICU 52 */ 1070 U_FIRST_STRONG_ISOLATE = 19, 1071 /** LRI @stable ICU 52 */ 1072 U_LEFT_TO_RIGHT_ISOLATE = 20, 1073 /** RLI @stable ICU 52 */ 1074 U_RIGHT_TO_LEFT_ISOLATE = 21, 1075 /** PDI @stable ICU 52 */ 1076 U_POP_DIRECTIONAL_ISOLATE = 22, 1077 #ifndef U_HIDE_DEPRECATED_API 1078 /** 1079 * One more than the highest UCharDirection value. 1080 * The highest value is available via u_getIntPropertyMaxValue(UCHAR_BIDI_CLASS). 1081 * 1082 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. 1083 */ 1084 U_CHAR_DIRECTION_COUNT 1085 #endif // U_HIDE_DEPRECATED_API 1086 } UCharDirection; 1087 1088 /** 1089 * Bidi Paired Bracket Type constants. 1090 * 1091 * @see UCHAR_BIDI_PAIRED_BRACKET_TYPE 1092 * @stable ICU 52 1093 */ 1094 typedef enum UBidiPairedBracketType { 1095 /* 1096 * Note: UBidiPairedBracketType constants are parsed by preparseucd.py. 1097 * It matches lines like 1098 * U_BPT_<Unicode Bidi_Paired_Bracket_Type value name> 1099 */ 1100 1101 /** Not a paired bracket. @stable ICU 52 */ 1102 U_BPT_NONE, 1103 /** Open paired bracket. @stable ICU 52 */ 1104 U_BPT_OPEN, 1105 /** Close paired bracket. @stable ICU 52 */ 1106 U_BPT_CLOSE, 1107 #ifndef U_HIDE_DEPRECATED_API 1108 /** 1109 * One more than the highest normal UBidiPairedBracketType value. 1110 * The highest value is available via u_getIntPropertyMaxValue(UCHAR_BIDI_PAIRED_BRACKET_TYPE). 1111 * 1112 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. 1113 */ 1114 U_BPT_COUNT /* 3 */ 1115 #endif // U_HIDE_DEPRECATED_API 1116 } UBidiPairedBracketType; 1117 1118 /** 1119 * Constants for Unicode blocks, see the Unicode Data file Blocks.txt 1120 * @stable ICU 2.0 1121 */ 1122 enum UBlockCode { 1123 /* 1124 * Note: UBlockCode constants are parsed by preparseucd.py. 1125 * It matches lines like 1126 * UBLOCK_<Unicode Block value name> = <integer>, 1127 */ 1128 1129 /** New No_Block value in Unicode 4. @stable ICU 2.6 */ 1130 UBLOCK_NO_BLOCK = 0, /*[none]*/ /* Special range indicating No_Block */ 1131 1132 /** @stable ICU 2.0 */ 1133 UBLOCK_BASIC_LATIN = 1, /*[0000]*/ 1134 1135 /** @stable ICU 2.0 */ 1136 UBLOCK_LATIN_1_SUPPLEMENT=2, /*[0080]*/ 1137 1138 /** @stable ICU 2.0 */ 1139 UBLOCK_LATIN_EXTENDED_A =3, /*[0100]*/ 1140 1141 /** @stable ICU 2.0 */ 1142 UBLOCK_LATIN_EXTENDED_B =4, /*[0180]*/ 1143 1144 /** @stable ICU 2.0 */ 1145 UBLOCK_IPA_EXTENSIONS =5, /*[0250]*/ 1146 1147 /** @stable ICU 2.0 */ 1148 UBLOCK_SPACING_MODIFIER_LETTERS =6, /*[02B0]*/ 1149 1150 /** @stable ICU 2.0 */ 1151 UBLOCK_COMBINING_DIACRITICAL_MARKS =7, /*[0300]*/ 1152 1153 /** 1154 * Unicode 3.2 renames this block to "Greek and Coptic". 1155 * @stable ICU 2.0 1156 */ 1157 UBLOCK_GREEK =8, /*[0370]*/ 1158 1159 /** @stable ICU 2.0 */ 1160 UBLOCK_CYRILLIC =9, /*[0400]*/ 1161 1162 /** @stable ICU 2.0 */ 1163 UBLOCK_ARMENIAN =10, /*[0530]*/ 1164 1165 /** @stable ICU 2.0 */ 1166 UBLOCK_HEBREW =11, /*[0590]*/ 1167 1168 /** @stable ICU 2.0 */ 1169 UBLOCK_ARABIC =12, /*[0600]*/ 1170 1171 /** @stable ICU 2.0 */ 1172 UBLOCK_SYRIAC =13, /*[0700]*/ 1173 1174 /** @stable ICU 2.0 */ 1175 UBLOCK_THAANA =14, /*[0780]*/ 1176 1177 /** @stable ICU 2.0 */ 1178 UBLOCK_DEVANAGARI =15, /*[0900]*/ 1179 1180 /** @stable ICU 2.0 */ 1181 UBLOCK_BENGALI =16, /*[0980]*/ 1182 1183 /** @stable ICU 2.0 */ 1184 UBLOCK_GURMUKHI =17, /*[0A00]*/ 1185 1186 /** @stable ICU 2.0 */ 1187 UBLOCK_GUJARATI =18, /*[0A80]*/ 1188 1189 /** @stable ICU 2.0 */ 1190 UBLOCK_ORIYA =19, /*[0B00]*/ 1191 1192 /** @stable ICU 2.0 */ 1193 UBLOCK_TAMIL =20, /*[0B80]*/ 1194 1195 /** @stable ICU 2.0 */ 1196 UBLOCK_TELUGU =21, /*[0C00]*/ 1197 1198 /** @stable ICU 2.0 */ 1199 UBLOCK_KANNADA =22, /*[0C80]*/ 1200 1201 /** @stable ICU 2.0 */ 1202 UBLOCK_MALAYALAM =23, /*[0D00]*/ 1203 1204 /** @stable ICU 2.0 */ 1205 UBLOCK_SINHALA =24, /*[0D80]*/ 1206 1207 /** @stable ICU 2.0 */ 1208 UBLOCK_THAI =25, /*[0E00]*/ 1209 1210 /** @stable ICU 2.0 */ 1211 UBLOCK_LAO =26, /*[0E80]*/ 1212 1213 /** @stable ICU 2.0 */ 1214 UBLOCK_TIBETAN =27, /*[0F00]*/ 1215 1216 /** @stable ICU 2.0 */ 1217 UBLOCK_MYANMAR =28, /*[1000]*/ 1218 1219 /** @stable ICU 2.0 */ 1220 UBLOCK_GEORGIAN =29, /*[10A0]*/ 1221 1222 /** @stable ICU 2.0 */ 1223 UBLOCK_HANGUL_JAMO =30, /*[1100]*/ 1224 1225 /** @stable ICU 2.0 */ 1226 UBLOCK_ETHIOPIC =31, /*[1200]*/ 1227 1228 /** @stable ICU 2.0 */ 1229 UBLOCK_CHEROKEE =32, /*[13A0]*/ 1230 1231 /** @stable ICU 2.0 */ 1232 UBLOCK_UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS =33, /*[1400]*/ 1233 1234 /** @stable ICU 2.0 */ 1235 UBLOCK_OGHAM =34, /*[1680]*/ 1236 1237 /** @stable ICU 2.0 */ 1238 UBLOCK_RUNIC =35, /*[16A0]*/ 1239 1240 /** @stable ICU 2.0 */ 1241 UBLOCK_KHMER =36, /*[1780]*/ 1242 1243 /** @stable ICU 2.0 */ 1244 UBLOCK_MONGOLIAN =37, /*[1800]*/ 1245 1246 /** @stable ICU 2.0 */ 1247 UBLOCK_LATIN_EXTENDED_ADDITIONAL =38, /*[1E00]*/ 1248 1249 /** @stable ICU 2.0 */ 1250 UBLOCK_GREEK_EXTENDED =39, /*[1F00]*/ 1251 1252 /** @stable ICU 2.0 */ 1253 UBLOCK_GENERAL_PUNCTUATION =40, /*[2000]*/ 1254 1255 /** @stable ICU 2.0 */ 1256 UBLOCK_SUPERSCRIPTS_AND_SUBSCRIPTS =41, /*[2070]*/ 1257 1258 /** @stable ICU 2.0 */ 1259 UBLOCK_CURRENCY_SYMBOLS =42, /*[20A0]*/ 1260 1261 /** 1262 * Unicode 3.2 renames this block to "Combining Diacritical Marks for Symbols". 1263 * @stable ICU 2.0 1264 */ 1265 UBLOCK_COMBINING_MARKS_FOR_SYMBOLS =43, /*[20D0]*/ 1266 1267 /** @stable ICU 2.0 */ 1268 UBLOCK_LETTERLIKE_SYMBOLS =44, /*[2100]*/ 1269 1270 /** @stable ICU 2.0 */ 1271 UBLOCK_NUMBER_FORMS =45, /*[2150]*/ 1272 1273 /** @stable ICU 2.0 */ 1274 UBLOCK_ARROWS =46, /*[2190]*/ 1275 1276 /** @stable ICU 2.0 */ 1277 UBLOCK_MATHEMATICAL_OPERATORS =47, /*[2200]*/ 1278 1279 /** @stable ICU 2.0 */ 1280 UBLOCK_MISCELLANEOUS_TECHNICAL =48, /*[2300]*/ 1281 1282 /** @stable ICU 2.0 */ 1283 UBLOCK_CONTROL_PICTURES =49, /*[2400]*/ 1284 1285 /** @stable ICU 2.0 */ 1286 UBLOCK_OPTICAL_CHARACTER_RECOGNITION =50, /*[2440]*/ 1287 1288 /** @stable ICU 2.0 */ 1289 UBLOCK_ENCLOSED_ALPHANUMERICS =51, /*[2460]*/ 1290 1291 /** @stable ICU 2.0 */ 1292 UBLOCK_BOX_DRAWING =52, /*[2500]*/ 1293 1294 /** @stable ICU 2.0 */ 1295 UBLOCK_BLOCK_ELEMENTS =53, /*[2580]*/ 1296 1297 /** @stable ICU 2.0 */ 1298 UBLOCK_GEOMETRIC_SHAPES =54, /*[25A0]*/ 1299 1300 /** @stable ICU 2.0 */ 1301 UBLOCK_MISCELLANEOUS_SYMBOLS =55, /*[2600]*/ 1302 1303 /** @stable ICU 2.0 */ 1304 UBLOCK_DINGBATS =56, /*[2700]*/ 1305 1306 /** @stable ICU 2.0 */ 1307 UBLOCK_BRAILLE_PATTERNS =57, /*[2800]*/ 1308 1309 /** @stable ICU 2.0 */ 1310 UBLOCK_CJK_RADICALS_SUPPLEMENT =58, /*[2E80]*/ 1311 1312 /** @stable ICU 2.0 */ 1313 UBLOCK_KANGXI_RADICALS =59, /*[2F00]*/ 1314 1315 /** @stable ICU 2.0 */ 1316 UBLOCK_IDEOGRAPHIC_DESCRIPTION_CHARACTERS =60, /*[2FF0]*/ 1317 1318 /** @stable ICU 2.0 */ 1319 UBLOCK_CJK_SYMBOLS_AND_PUNCTUATION =61, /*[3000]*/ 1320 1321 /** @stable ICU 2.0 */ 1322 UBLOCK_HIRAGANA =62, /*[3040]*/ 1323 1324 /** @stable ICU 2.0 */ 1325 UBLOCK_KATAKANA =63, /*[30A0]*/ 1326 1327 /** @stable ICU 2.0 */ 1328 UBLOCK_BOPOMOFO =64, /*[3100]*/ 1329 1330 /** @stable ICU 2.0 */ 1331 UBLOCK_HANGUL_COMPATIBILITY_JAMO =65, /*[3130]*/ 1332 1333 /** @stable ICU 2.0 */ 1334 UBLOCK_KANBUN =66, /*[3190]*/ 1335 1336 /** @stable ICU 2.0 */ 1337 UBLOCK_BOPOMOFO_EXTENDED =67, /*[31A0]*/ 1338 1339 /** @stable ICU 2.0 */ 1340 UBLOCK_ENCLOSED_CJK_LETTERS_AND_MONTHS =68, /*[3200]*/ 1341 1342 /** @stable ICU 2.0 */ 1343 UBLOCK_CJK_COMPATIBILITY =69, /*[3300]*/ 1344 1345 /** @stable ICU 2.0 */ 1346 UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_A =70, /*[3400]*/ 1347 1348 /** @stable ICU 2.0 */ 1349 UBLOCK_CJK_UNIFIED_IDEOGRAPHS =71, /*[4E00]*/ 1350 1351 /** @stable ICU 2.0 */ 1352 UBLOCK_YI_SYLLABLES =72, /*[A000]*/ 1353 1354 /** @stable ICU 2.0 */ 1355 UBLOCK_YI_RADICALS =73, /*[A490]*/ 1356 1357 /** @stable ICU 2.0 */ 1358 UBLOCK_HANGUL_SYLLABLES =74, /*[AC00]*/ 1359 1360 /** @stable ICU 2.0 */ 1361 UBLOCK_HIGH_SURROGATES =75, /*[D800]*/ 1362 1363 /** @stable ICU 2.0 */ 1364 UBLOCK_HIGH_PRIVATE_USE_SURROGATES =76, /*[DB80]*/ 1365 1366 /** @stable ICU 2.0 */ 1367 UBLOCK_LOW_SURROGATES =77, /*[DC00]*/ 1368 1369 /** 1370 * Same as UBLOCK_PRIVATE_USE. 1371 * Until Unicode 3.1.1, the corresponding block name was "Private Use", 1372 * and multiple code point ranges had this block. 1373 * Unicode 3.2 renames the block for the BMP PUA to "Private Use Area" and 1374 * adds separate blocks for the supplementary PUAs. 1375 * 1376 * @stable ICU 2.0 1377 */ 1378 UBLOCK_PRIVATE_USE_AREA =78, /*[E000]*/ 1379 /** 1380 * Same as UBLOCK_PRIVATE_USE_AREA. 1381 * Until Unicode 3.1.1, the corresponding block name was "Private Use", 1382 * and multiple code point ranges had this block. 1383 * Unicode 3.2 renames the block for the BMP PUA to "Private Use Area" and 1384 * adds separate blocks for the supplementary PUAs. 1385 * 1386 * @stable ICU 2.0 1387 */ 1388 UBLOCK_PRIVATE_USE = UBLOCK_PRIVATE_USE_AREA, 1389 1390 /** @stable ICU 2.0 */ 1391 UBLOCK_CJK_COMPATIBILITY_IDEOGRAPHS =79, /*[F900]*/ 1392 1393 /** @stable ICU 2.0 */ 1394 UBLOCK_ALPHABETIC_PRESENTATION_FORMS =80, /*[FB00]*/ 1395 1396 /** @stable ICU 2.0 */ 1397 UBLOCK_ARABIC_PRESENTATION_FORMS_A =81, /*[FB50]*/ 1398 1399 /** @stable ICU 2.0 */ 1400 UBLOCK_COMBINING_HALF_MARKS =82, /*[FE20]*/ 1401 1402 /** @stable ICU 2.0 */ 1403 UBLOCK_CJK_COMPATIBILITY_FORMS =83, /*[FE30]*/ 1404 1405 /** @stable ICU 2.0 */ 1406 UBLOCK_SMALL_FORM_VARIANTS =84, /*[FE50]*/ 1407 1408 /** @stable ICU 2.0 */ 1409 UBLOCK_ARABIC_PRESENTATION_FORMS_B =85, /*[FE70]*/ 1410 1411 /** @stable ICU 2.0 */ 1412 UBLOCK_SPECIALS =86, /*[FFF0]*/ 1413 1414 /** @stable ICU 2.0 */ 1415 UBLOCK_HALFWIDTH_AND_FULLWIDTH_FORMS =87, /*[FF00]*/ 1416 1417 /* New blocks in Unicode 3.1 */ 1418 1419 /** @stable ICU 2.0 */ 1420 UBLOCK_OLD_ITALIC = 88, /*[10300]*/ 1421 /** @stable ICU 2.0 */ 1422 UBLOCK_GOTHIC = 89, /*[10330]*/ 1423 /** @stable ICU 2.0 */ 1424 UBLOCK_DESERET = 90, /*[10400]*/ 1425 /** @stable ICU 2.0 */ 1426 UBLOCK_BYZANTINE_MUSICAL_SYMBOLS = 91, /*[1D000]*/ 1427 /** @stable ICU 2.0 */ 1428 UBLOCK_MUSICAL_SYMBOLS = 92, /*[1D100]*/ 1429 /** @stable ICU 2.0 */ 1430 UBLOCK_MATHEMATICAL_ALPHANUMERIC_SYMBOLS = 93, /*[1D400]*/ 1431 /** @stable ICU 2.0 */ 1432 UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_B = 94, /*[20000]*/ 1433 /** @stable ICU 2.0 */ 1434 UBLOCK_CJK_COMPATIBILITY_IDEOGRAPHS_SUPPLEMENT = 95, /*[2F800]*/ 1435 /** @stable ICU 2.0 */ 1436 UBLOCK_TAGS = 96, /*[E0000]*/ 1437 1438 /* New blocks in Unicode 3.2 */ 1439 1440 /** @stable ICU 3.0 */ 1441 UBLOCK_CYRILLIC_SUPPLEMENT = 97, /*[0500]*/ 1442 /** 1443 * Unicode 4.0.1 renames the "Cyrillic Supplementary" block to "Cyrillic Supplement". 1444 * @stable ICU 2.2 1445 */ 1446 UBLOCK_CYRILLIC_SUPPLEMENTARY = UBLOCK_CYRILLIC_SUPPLEMENT, 1447 /** @stable ICU 2.2 */ 1448 UBLOCK_TAGALOG = 98, /*[1700]*/ 1449 /** @stable ICU 2.2 */ 1450 UBLOCK_HANUNOO = 99, /*[1720]*/ 1451 /** @stable ICU 2.2 */ 1452 UBLOCK_BUHID = 100, /*[1740]*/ 1453 /** @stable ICU 2.2 */ 1454 UBLOCK_TAGBANWA = 101, /*[1760]*/ 1455 /** @stable ICU 2.2 */ 1456 UBLOCK_MISCELLANEOUS_MATHEMATICAL_SYMBOLS_A = 102, /*[27C0]*/ 1457 /** @stable ICU 2.2 */ 1458 UBLOCK_SUPPLEMENTAL_ARROWS_A = 103, /*[27F0]*/ 1459 /** @stable ICU 2.2 */ 1460 UBLOCK_SUPPLEMENTAL_ARROWS_B = 104, /*[2900]*/ 1461 /** @stable ICU 2.2 */ 1462 UBLOCK_MISCELLANEOUS_MATHEMATICAL_SYMBOLS_B = 105, /*[2980]*/ 1463 /** @stable ICU 2.2 */ 1464 UBLOCK_SUPPLEMENTAL_MATHEMATICAL_OPERATORS = 106, /*[2A00]*/ 1465 /** @stable ICU 2.2 */ 1466 UBLOCK_KATAKANA_PHONETIC_EXTENSIONS = 107, /*[31F0]*/ 1467 /** @stable ICU 2.2 */ 1468 UBLOCK_VARIATION_SELECTORS = 108, /*[FE00]*/ 1469 /** @stable ICU 2.2 */ 1470 UBLOCK_SUPPLEMENTARY_PRIVATE_USE_AREA_A = 109, /*[F0000]*/ 1471 /** @stable ICU 2.2 */ 1472 UBLOCK_SUPPLEMENTARY_PRIVATE_USE_AREA_B = 110, /*[100000]*/ 1473 1474 /* New blocks in Unicode 4 */ 1475 1476 /** @stable ICU 2.6 */ 1477 UBLOCK_LIMBU = 111, /*[1900]*/ 1478 /** @stable ICU 2.6 */ 1479 UBLOCK_TAI_LE = 112, /*[1950]*/ 1480 /** @stable ICU 2.6 */ 1481 UBLOCK_KHMER_SYMBOLS = 113, /*[19E0]*/ 1482 /** @stable ICU 2.6 */ 1483 UBLOCK_PHONETIC_EXTENSIONS = 114, /*[1D00]*/ 1484 /** @stable ICU 2.6 */ 1485 UBLOCK_MISCELLANEOUS_SYMBOLS_AND_ARROWS = 115, /*[2B00]*/ 1486 /** @stable ICU 2.6 */ 1487 UBLOCK_YIJING_HEXAGRAM_SYMBOLS = 116, /*[4DC0]*/ 1488 /** @stable ICU 2.6 */ 1489 UBLOCK_LINEAR_B_SYLLABARY = 117, /*[10000]*/ 1490 /** @stable ICU 2.6 */ 1491 UBLOCK_LINEAR_B_IDEOGRAMS = 118, /*[10080]*/ 1492 /** @stable ICU 2.6 */ 1493 UBLOCK_AEGEAN_NUMBERS = 119, /*[10100]*/ 1494 /** @stable ICU 2.6 */ 1495 UBLOCK_UGARITIC = 120, /*[10380]*/ 1496 /** @stable ICU 2.6 */ 1497 UBLOCK_SHAVIAN = 121, /*[10450]*/ 1498 /** @stable ICU 2.6 */ 1499 UBLOCK_OSMANYA = 122, /*[10480]*/ 1500 /** @stable ICU 2.6 */ 1501 UBLOCK_CYPRIOT_SYLLABARY = 123, /*[10800]*/ 1502 /** @stable ICU 2.6 */ 1503 UBLOCK_TAI_XUAN_JING_SYMBOLS = 124, /*[1D300]*/ 1504 /** @stable ICU 2.6 */ 1505 UBLOCK_VARIATION_SELECTORS_SUPPLEMENT = 125, /*[E0100]*/ 1506 1507 /* New blocks in Unicode 4.1 */ 1508 1509 /** @stable ICU 3.4 */ 1510 UBLOCK_ANCIENT_GREEK_MUSICAL_NOTATION = 126, /*[1D200]*/ 1511 /** @stable ICU 3.4 */ 1512 UBLOCK_ANCIENT_GREEK_NUMBERS = 127, /*[10140]*/ 1513 /** @stable ICU 3.4 */ 1514 UBLOCK_ARABIC_SUPPLEMENT = 128, /*[0750]*/ 1515 /** @stable ICU 3.4 */ 1516 UBLOCK_BUGINESE = 129, /*[1A00]*/ 1517 /** @stable ICU 3.4 */ 1518 UBLOCK_CJK_STROKES = 130, /*[31C0]*/ 1519 /** @stable ICU 3.4 */ 1520 UBLOCK_COMBINING_DIACRITICAL_MARKS_SUPPLEMENT = 131, /*[1DC0]*/ 1521 /** @stable ICU 3.4 */ 1522 UBLOCK_COPTIC = 132, /*[2C80]*/ 1523 /** @stable ICU 3.4 */ 1524 UBLOCK_ETHIOPIC_EXTENDED = 133, /*[2D80]*/ 1525 /** @stable ICU 3.4 */ 1526 UBLOCK_ETHIOPIC_SUPPLEMENT = 134, /*[1380]*/ 1527 /** @stable ICU 3.4 */ 1528 UBLOCK_GEORGIAN_SUPPLEMENT = 135, /*[2D00]*/ 1529 /** @stable ICU 3.4 */ 1530 UBLOCK_GLAGOLITIC = 136, /*[2C00]*/ 1531 /** @stable ICU 3.4 */ 1532 UBLOCK_KHAROSHTHI = 137, /*[10A00]*/ 1533 /** @stable ICU 3.4 */ 1534 UBLOCK_MODIFIER_TONE_LETTERS = 138, /*[A700]*/ 1535 /** @stable ICU 3.4 */ 1536 UBLOCK_NEW_TAI_LUE = 139, /*[1980]*/ 1537 /** @stable ICU 3.4 */ 1538 UBLOCK_OLD_PERSIAN = 140, /*[103A0]*/ 1539 /** @stable ICU 3.4 */ 1540 UBLOCK_PHONETIC_EXTENSIONS_SUPPLEMENT = 141, /*[1D80]*/ 1541 /** @stable ICU 3.4 */ 1542 UBLOCK_SUPPLEMENTAL_PUNCTUATION = 142, /*[2E00]*/ 1543 /** @stable ICU 3.4 */ 1544 UBLOCK_SYLOTI_NAGRI = 143, /*[A800]*/ 1545 /** @stable ICU 3.4 */ 1546 UBLOCK_TIFINAGH = 144, /*[2D30]*/ 1547 /** @stable ICU 3.4 */ 1548 UBLOCK_VERTICAL_FORMS = 145, /*[FE10]*/ 1549 1550 /* New blocks in Unicode 5.0 */ 1551 1552 /** @stable ICU 3.6 */ 1553 UBLOCK_NKO = 146, /*[07C0]*/ 1554 /** @stable ICU 3.6 */ 1555 UBLOCK_BALINESE = 147, /*[1B00]*/ 1556 /** @stable ICU 3.6 */ 1557 UBLOCK_LATIN_EXTENDED_C = 148, /*[2C60]*/ 1558 /** @stable ICU 3.6 */ 1559 UBLOCK_LATIN_EXTENDED_D = 149, /*[A720]*/ 1560 /** @stable ICU 3.6 */ 1561 UBLOCK_PHAGS_PA = 150, /*[A840]*/ 1562 /** @stable ICU 3.6 */ 1563 UBLOCK_PHOENICIAN = 151, /*[10900]*/ 1564 /** @stable ICU 3.6 */ 1565 UBLOCK_CUNEIFORM = 152, /*[12000]*/ 1566 /** @stable ICU 3.6 */ 1567 UBLOCK_CUNEIFORM_NUMBERS_AND_PUNCTUATION = 153, /*[12400]*/ 1568 /** @stable ICU 3.6 */ 1569 UBLOCK_COUNTING_ROD_NUMERALS = 154, /*[1D360]*/ 1570 1571 /* New blocks in Unicode 5.1 */ 1572 1573 /** @stable ICU 4.0 */ 1574 UBLOCK_SUNDANESE = 155, /*[1B80]*/ 1575 /** @stable ICU 4.0 */ 1576 UBLOCK_LEPCHA = 156, /*[1C00]*/ 1577 /** @stable ICU 4.0 */ 1578 UBLOCK_OL_CHIKI = 157, /*[1C50]*/ 1579 /** @stable ICU 4.0 */ 1580 UBLOCK_CYRILLIC_EXTENDED_A = 158, /*[2DE0]*/ 1581 /** @stable ICU 4.0 */ 1582 UBLOCK_VAI = 159, /*[A500]*/ 1583 /** @stable ICU 4.0 */ 1584 UBLOCK_CYRILLIC_EXTENDED_B = 160, /*[A640]*/ 1585 /** @stable ICU 4.0 */ 1586 UBLOCK_SAURASHTRA = 161, /*[A880]*/ 1587 /** @stable ICU 4.0 */ 1588 UBLOCK_KAYAH_LI = 162, /*[A900]*/ 1589 /** @stable ICU 4.0 */ 1590 UBLOCK_REJANG = 163, /*[A930]*/ 1591 /** @stable ICU 4.0 */ 1592 UBLOCK_CHAM = 164, /*[AA00]*/ 1593 /** @stable ICU 4.0 */ 1594 UBLOCK_ANCIENT_SYMBOLS = 165, /*[10190]*/ 1595 /** @stable ICU 4.0 */ 1596 UBLOCK_PHAISTOS_DISC = 166, /*[101D0]*/ 1597 /** @stable ICU 4.0 */ 1598 UBLOCK_LYCIAN = 167, /*[10280]*/ 1599 /** @stable ICU 4.0 */ 1600 UBLOCK_CARIAN = 168, /*[102A0]*/ 1601 /** @stable ICU 4.0 */ 1602 UBLOCK_LYDIAN = 169, /*[10920]*/ 1603 /** @stable ICU 4.0 */ 1604 UBLOCK_MAHJONG_TILES = 170, /*[1F000]*/ 1605 /** @stable ICU 4.0 */ 1606 UBLOCK_DOMINO_TILES = 171, /*[1F030]*/ 1607 1608 /* New blocks in Unicode 5.2 */ 1609 1610 /** @stable ICU 4.4 */ 1611 UBLOCK_SAMARITAN = 172, /*[0800]*/ 1612 /** @stable ICU 4.4 */ 1613 UBLOCK_UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS_EXTENDED = 173, /*[18B0]*/ 1614 /** @stable ICU 4.4 */ 1615 UBLOCK_TAI_THAM = 174, /*[1A20]*/ 1616 /** @stable ICU 4.4 */ 1617 UBLOCK_VEDIC_EXTENSIONS = 175, /*[1CD0]*/ 1618 /** @stable ICU 4.4 */ 1619 UBLOCK_LISU = 176, /*[A4D0]*/ 1620 /** @stable ICU 4.4 */ 1621 UBLOCK_BAMUM = 177, /*[A6A0]*/ 1622 /** @stable ICU 4.4 */ 1623 UBLOCK_COMMON_INDIC_NUMBER_FORMS = 178, /*[A830]*/ 1624 /** @stable ICU 4.4 */ 1625 UBLOCK_DEVANAGARI_EXTENDED = 179, /*[A8E0]*/ 1626 /** @stable ICU 4.4 */ 1627 UBLOCK_HANGUL_JAMO_EXTENDED_A = 180, /*[A960]*/ 1628 /** @stable ICU 4.4 */ 1629 UBLOCK_JAVANESE = 181, /*[A980]*/ 1630 /** @stable ICU 4.4 */ 1631 UBLOCK_MYANMAR_EXTENDED_A = 182, /*[AA60]*/ 1632 /** @stable ICU 4.4 */ 1633 UBLOCK_TAI_VIET = 183, /*[AA80]*/ 1634 /** @stable ICU 4.4 */ 1635 UBLOCK_MEETEI_MAYEK = 184, /*[ABC0]*/ 1636 /** @stable ICU 4.4 */ 1637 UBLOCK_HANGUL_JAMO_EXTENDED_B = 185, /*[D7B0]*/ 1638 /** @stable ICU 4.4 */ 1639 UBLOCK_IMPERIAL_ARAMAIC = 186, /*[10840]*/ 1640 /** @stable ICU 4.4 */ 1641 UBLOCK_OLD_SOUTH_ARABIAN = 187, /*[10A60]*/ 1642 /** @stable ICU 4.4 */ 1643 UBLOCK_AVESTAN = 188, /*[10B00]*/ 1644 /** @stable ICU 4.4 */ 1645 UBLOCK_INSCRIPTIONAL_PARTHIAN = 189, /*[10B40]*/ 1646 /** @stable ICU 4.4 */ 1647 UBLOCK_INSCRIPTIONAL_PAHLAVI = 190, /*[10B60]*/ 1648 /** @stable ICU 4.4 */ 1649 UBLOCK_OLD_TURKIC = 191, /*[10C00]*/ 1650 /** @stable ICU 4.4 */ 1651 UBLOCK_RUMI_NUMERAL_SYMBOLS = 192, /*[10E60]*/ 1652 /** @stable ICU 4.4 */ 1653 UBLOCK_KAITHI = 193, /*[11080]*/ 1654 /** @stable ICU 4.4 */ 1655 UBLOCK_EGYPTIAN_HIEROGLYPHS = 194, /*[13000]*/ 1656 /** @stable ICU 4.4 */ 1657 UBLOCK_ENCLOSED_ALPHANUMERIC_SUPPLEMENT = 195, /*[1F100]*/ 1658 /** @stable ICU 4.4 */ 1659 UBLOCK_ENCLOSED_IDEOGRAPHIC_SUPPLEMENT = 196, /*[1F200]*/ 1660 /** @stable ICU 4.4 */ 1661 UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_C = 197, /*[2A700]*/ 1662 1663 /* New blocks in Unicode 6.0 */ 1664 1665 /** @stable ICU 4.6 */ 1666 UBLOCK_MANDAIC = 198, /*[0840]*/ 1667 /** @stable ICU 4.6 */ 1668 UBLOCK_BATAK = 199, /*[1BC0]*/ 1669 /** @stable ICU 4.6 */ 1670 UBLOCK_ETHIOPIC_EXTENDED_A = 200, /*[AB00]*/ 1671 /** @stable ICU 4.6 */ 1672 UBLOCK_BRAHMI = 201, /*[11000]*/ 1673 /** @stable ICU 4.6 */ 1674 UBLOCK_BAMUM_SUPPLEMENT = 202, /*[16800]*/ 1675 /** @stable ICU 4.6 */ 1676 UBLOCK_KANA_SUPPLEMENT = 203, /*[1B000]*/ 1677 /** @stable ICU 4.6 */ 1678 UBLOCK_PLAYING_CARDS = 204, /*[1F0A0]*/ 1679 /** @stable ICU 4.6 */ 1680 UBLOCK_MISCELLANEOUS_SYMBOLS_AND_PICTOGRAPHS = 205, /*[1F300]*/ 1681 /** @stable ICU 4.6 */ 1682 UBLOCK_EMOTICONS = 206, /*[1F600]*/ 1683 /** @stable ICU 4.6 */ 1684 UBLOCK_TRANSPORT_AND_MAP_SYMBOLS = 207, /*[1F680]*/ 1685 /** @stable ICU 4.6 */ 1686 UBLOCK_ALCHEMICAL_SYMBOLS = 208, /*[1F700]*/ 1687 /** @stable ICU 4.6 */ 1688 UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_D = 209, /*[2B740]*/ 1689 1690 /* New blocks in Unicode 6.1 */ 1691 1692 /** @stable ICU 49 */ 1693 UBLOCK_ARABIC_EXTENDED_A = 210, /*[08A0]*/ 1694 /** @stable ICU 49 */ 1695 UBLOCK_ARABIC_MATHEMATICAL_ALPHABETIC_SYMBOLS = 211, /*[1EE00]*/ 1696 /** @stable ICU 49 */ 1697 UBLOCK_CHAKMA = 212, /*[11100]*/ 1698 /** @stable ICU 49 */ 1699 UBLOCK_MEETEI_MAYEK_EXTENSIONS = 213, /*[AAE0]*/ 1700 /** @stable ICU 49 */ 1701 UBLOCK_MEROITIC_CURSIVE = 214, /*[109A0]*/ 1702 /** @stable ICU 49 */ 1703 UBLOCK_MEROITIC_HIEROGLYPHS = 215, /*[10980]*/ 1704 /** @stable ICU 49 */ 1705 UBLOCK_MIAO = 216, /*[16F00]*/ 1706 /** @stable ICU 49 */ 1707 UBLOCK_SHARADA = 217, /*[11180]*/ 1708 /** @stable ICU 49 */ 1709 UBLOCK_SORA_SOMPENG = 218, /*[110D0]*/ 1710 /** @stable ICU 49 */ 1711 UBLOCK_SUNDANESE_SUPPLEMENT = 219, /*[1CC0]*/ 1712 /** @stable ICU 49 */ 1713 UBLOCK_TAKRI = 220, /*[11680]*/ 1714 1715 /* New blocks in Unicode 7.0 */ 1716 1717 /** @stable ICU 54 */ 1718 UBLOCK_BASSA_VAH = 221, /*[16AD0]*/ 1719 /** @stable ICU 54 */ 1720 UBLOCK_CAUCASIAN_ALBANIAN = 222, /*[10530]*/ 1721 /** @stable ICU 54 */ 1722 UBLOCK_COPTIC_EPACT_NUMBERS = 223, /*[102E0]*/ 1723 /** @stable ICU 54 */ 1724 UBLOCK_COMBINING_DIACRITICAL_MARKS_EXTENDED = 224, /*[1AB0]*/ 1725 /** @stable ICU 54 */ 1726 UBLOCK_DUPLOYAN = 225, /*[1BC00]*/ 1727 /** @stable ICU 54 */ 1728 UBLOCK_ELBASAN = 226, /*[10500]*/ 1729 /** @stable ICU 54 */ 1730 UBLOCK_GEOMETRIC_SHAPES_EXTENDED = 227, /*[1F780]*/ 1731 /** @stable ICU 54 */ 1732 UBLOCK_GRANTHA = 228, /*[11300]*/ 1733 /** @stable ICU 54 */ 1734 UBLOCK_KHOJKI = 229, /*[11200]*/ 1735 /** @stable ICU 54 */ 1736 UBLOCK_KHUDAWADI = 230, /*[112B0]*/ 1737 /** @stable ICU 54 */ 1738 UBLOCK_LATIN_EXTENDED_E = 231, /*[AB30]*/ 1739 /** @stable ICU 54 */ 1740 UBLOCK_LINEAR_A = 232, /*[10600]*/ 1741 /** @stable ICU 54 */ 1742 UBLOCK_MAHAJANI = 233, /*[11150]*/ 1743 /** @stable ICU 54 */ 1744 UBLOCK_MANICHAEAN = 234, /*[10AC0]*/ 1745 /** @stable ICU 54 */ 1746 UBLOCK_MENDE_KIKAKUI = 235, /*[1E800]*/ 1747 /** @stable ICU 54 */ 1748 UBLOCK_MODI = 236, /*[11600]*/ 1749 /** @stable ICU 54 */ 1750 UBLOCK_MRO = 237, /*[16A40]*/ 1751 /** @stable ICU 54 */ 1752 UBLOCK_MYANMAR_EXTENDED_B = 238, /*[A9E0]*/ 1753 /** @stable ICU 54 */ 1754 UBLOCK_NABATAEAN = 239, /*[10880]*/ 1755 /** @stable ICU 54 */ 1756 UBLOCK_OLD_NORTH_ARABIAN = 240, /*[10A80]*/ 1757 /** @stable ICU 54 */ 1758 UBLOCK_OLD_PERMIC = 241, /*[10350]*/ 1759 /** @stable ICU 54 */ 1760 UBLOCK_ORNAMENTAL_DINGBATS = 242, /*[1F650]*/ 1761 /** @stable ICU 54 */ 1762 UBLOCK_PAHAWH_HMONG = 243, /*[16B00]*/ 1763 /** @stable ICU 54 */ 1764 UBLOCK_PALMYRENE = 244, /*[10860]*/ 1765 /** @stable ICU 54 */ 1766 UBLOCK_PAU_CIN_HAU = 245, /*[11AC0]*/ 1767 /** @stable ICU 54 */ 1768 UBLOCK_PSALTER_PAHLAVI = 246, /*[10B80]*/ 1769 /** @stable ICU 54 */ 1770 UBLOCK_SHORTHAND_FORMAT_CONTROLS = 247, /*[1BCA0]*/ 1771 /** @stable ICU 54 */ 1772 UBLOCK_SIDDHAM = 248, /*[11580]*/ 1773 /** @stable ICU 54 */ 1774 UBLOCK_SINHALA_ARCHAIC_NUMBERS = 249, /*[111E0]*/ 1775 /** @stable ICU 54 */ 1776 UBLOCK_SUPPLEMENTAL_ARROWS_C = 250, /*[1F800]*/ 1777 /** @stable ICU 54 */ 1778 UBLOCK_TIRHUTA = 251, /*[11480]*/ 1779 /** @stable ICU 54 */ 1780 UBLOCK_WARANG_CITI = 252, /*[118A0]*/ 1781 1782 /* New blocks in Unicode 8.0 */ 1783 1784 /** @stable ICU 56 */ 1785 UBLOCK_AHOM = 253, /*[11700]*/ 1786 /** @stable ICU 56 */ 1787 UBLOCK_ANATOLIAN_HIEROGLYPHS = 254, /*[14400]*/ 1788 /** @stable ICU 56 */ 1789 UBLOCK_CHEROKEE_SUPPLEMENT = 255, /*[AB70]*/ 1790 /** @stable ICU 56 */ 1791 UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_E = 256, /*[2B820]*/ 1792 /** @stable ICU 56 */ 1793 UBLOCK_EARLY_DYNASTIC_CUNEIFORM = 257, /*[12480]*/ 1794 /** @stable ICU 56 */ 1795 UBLOCK_HATRAN = 258, /*[108E0]*/ 1796 /** @stable ICU 56 */ 1797 UBLOCK_MULTANI = 259, /*[11280]*/ 1798 /** @stable ICU 56 */ 1799 UBLOCK_OLD_HUNGARIAN = 260, /*[10C80]*/ 1800 /** @stable ICU 56 */ 1801 UBLOCK_SUPPLEMENTAL_SYMBOLS_AND_PICTOGRAPHS = 261, /*[1F900]*/ 1802 /** @stable ICU 56 */ 1803 UBLOCK_SUTTON_SIGNWRITING = 262, /*[1D800]*/ 1804 1805 /* New blocks in Unicode 9.0 */ 1806 1807 /** @stable ICU 58 */ 1808 UBLOCK_ADLAM = 263, /*[1E900]*/ 1809 /** @stable ICU 58 */ 1810 UBLOCK_BHAIKSUKI = 264, /*[11C00]*/ 1811 /** @stable ICU 58 */ 1812 UBLOCK_CYRILLIC_EXTENDED_C = 265, /*[1C80]*/ 1813 /** @stable ICU 58 */ 1814 UBLOCK_GLAGOLITIC_SUPPLEMENT = 266, /*[1E000]*/ 1815 /** @stable ICU 58 */ 1816 UBLOCK_IDEOGRAPHIC_SYMBOLS_AND_PUNCTUATION = 267, /*[16FE0]*/ 1817 /** @stable ICU 58 */ 1818 UBLOCK_MARCHEN = 268, /*[11C70]*/ 1819 /** @stable ICU 58 */ 1820 UBLOCK_MONGOLIAN_SUPPLEMENT = 269, /*[11660]*/ 1821 /** @stable ICU 58 */ 1822 UBLOCK_NEWA = 270, /*[11400]*/ 1823 /** @stable ICU 58 */ 1824 UBLOCK_OSAGE = 271, /*[104B0]*/ 1825 /** @stable ICU 58 */ 1826 UBLOCK_TANGUT = 272, /*[17000]*/ 1827 /** @stable ICU 58 */ 1828 UBLOCK_TANGUT_COMPONENTS = 273, /*[18800]*/ 1829 1830 // New blocks in Unicode 10.0 1831 1832 /** @stable ICU 60 */ 1833 UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_F = 274, /*[2CEB0]*/ 1834 /** @stable ICU 60 */ 1835 UBLOCK_KANA_EXTENDED_A = 275, /*[1B100]*/ 1836 /** @stable ICU 60 */ 1837 UBLOCK_MASARAM_GONDI = 276, /*[11D00]*/ 1838 /** @stable ICU 60 */ 1839 UBLOCK_NUSHU = 277, /*[1B170]*/ 1840 /** @stable ICU 60 */ 1841 UBLOCK_SOYOMBO = 278, /*[11A50]*/ 1842 /** @stable ICU 60 */ 1843 UBLOCK_SYRIAC_SUPPLEMENT = 279, /*[0860]*/ 1844 /** @stable ICU 60 */ 1845 UBLOCK_ZANABAZAR_SQUARE = 280, /*[11A00]*/ 1846 1847 // New blocks in Unicode 11.0 1848 1849 /** @stable ICU 62 */ 1850 UBLOCK_CHESS_SYMBOLS = 281, /*[1FA00]*/ 1851 /** @stable ICU 62 */ 1852 UBLOCK_DOGRA = 282, /*[11800]*/ 1853 /** @stable ICU 62 */ 1854 UBLOCK_GEORGIAN_EXTENDED = 283, /*[1C90]*/ 1855 /** @stable ICU 62 */ 1856 UBLOCK_GUNJALA_GONDI = 284, /*[11D60]*/ 1857 /** @stable ICU 62 */ 1858 UBLOCK_HANIFI_ROHINGYA = 285, /*[10D00]*/ 1859 /** @stable ICU 62 */ 1860 UBLOCK_INDIC_SIYAQ_NUMBERS = 286, /*[1EC70]*/ 1861 /** @stable ICU 62 */ 1862 UBLOCK_MAKASAR = 287, /*[11EE0]*/ 1863 /** @stable ICU 62 */ 1864 UBLOCK_MAYAN_NUMERALS = 288, /*[1D2E0]*/ 1865 /** @stable ICU 62 */ 1866 UBLOCK_MEDEFAIDRIN = 289, /*[16E40]*/ 1867 /** @stable ICU 62 */ 1868 UBLOCK_OLD_SOGDIAN = 290, /*[10F00]*/ 1869 /** @stable ICU 62 */ 1870 UBLOCK_SOGDIAN = 291, /*[10F30]*/ 1871 1872 // New blocks in Unicode 12.0 1873 1874 /** @stable ICU 64 */ 1875 UBLOCK_EGYPTIAN_HIEROGLYPH_FORMAT_CONTROLS = 292, /*[13430]*/ 1876 /** @stable ICU 64 */ 1877 UBLOCK_ELYMAIC = 293, /*[10FE0]*/ 1878 /** @stable ICU 64 */ 1879 UBLOCK_NANDINAGARI = 294, /*[119A0]*/ 1880 /** @stable ICU 64 */ 1881 UBLOCK_NYIAKENG_PUACHUE_HMONG = 295, /*[1E100]*/ 1882 /** @stable ICU 64 */ 1883 UBLOCK_OTTOMAN_SIYAQ_NUMBERS = 296, /*[1ED00]*/ 1884 /** @stable ICU 64 */ 1885 UBLOCK_SMALL_KANA_EXTENSION = 297, /*[1B130]*/ 1886 /** @stable ICU 64 */ 1887 UBLOCK_SYMBOLS_AND_PICTOGRAPHS_EXTENDED_A = 298, /*[1FA70]*/ 1888 /** @stable ICU 64 */ 1889 UBLOCK_TAMIL_SUPPLEMENT = 299, /*[11FC0]*/ 1890 /** @stable ICU 64 */ 1891 UBLOCK_WANCHO = 300, /*[1E2C0]*/ 1892 1893 // New blocks in Unicode 13.0 1894 1895 /** @stable ICU 66 */ 1896 UBLOCK_CHORASMIAN = 301, /*[10FB0]*/ 1897 /** @stable ICU 66 */ 1898 UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_G = 302, /*[30000]*/ 1899 /** @stable ICU 66 */ 1900 UBLOCK_DIVES_AKURU = 303, /*[11900]*/ 1901 /** @stable ICU 66 */ 1902 UBLOCK_KHITAN_SMALL_SCRIPT = 304, /*[18B00]*/ 1903 /** @stable ICU 66 */ 1904 UBLOCK_LISU_SUPPLEMENT = 305, /*[11FB0]*/ 1905 /** @stable ICU 66 */ 1906 UBLOCK_SYMBOLS_FOR_LEGACY_COMPUTING = 306, /*[1FB00]*/ 1907 /** @stable ICU 66 */ 1908 UBLOCK_TANGUT_SUPPLEMENT = 307, /*[18D00]*/ 1909 /** @stable ICU 66 */ 1910 UBLOCK_YEZIDI = 308, /*[10E80]*/ 1911 1912 // New blocks in Unicode 14.0 1913 1914 /** @stable ICU 70 */ 1915 UBLOCK_ARABIC_EXTENDED_B = 309, /*[0870]*/ 1916 /** @stable ICU 70 */ 1917 UBLOCK_CYPRO_MINOAN = 310, /*[12F90]*/ 1918 /** @stable ICU 70 */ 1919 UBLOCK_ETHIOPIC_EXTENDED_B = 311, /*[1E7E0]*/ 1920 /** @stable ICU 70 */ 1921 UBLOCK_KANA_EXTENDED_B = 312, /*[1AFF0]*/ 1922 /** @stable ICU 70 */ 1923 UBLOCK_LATIN_EXTENDED_F = 313, /*[10780]*/ 1924 /** @stable ICU 70 */ 1925 UBLOCK_LATIN_EXTENDED_G = 314, /*[1DF00]*/ 1926 /** @stable ICU 70 */ 1927 UBLOCK_OLD_UYGHUR = 315, /*[10F70]*/ 1928 /** @stable ICU 70 */ 1929 UBLOCK_TANGSA = 316, /*[16A70]*/ 1930 /** @stable ICU 70 */ 1931 UBLOCK_TOTO = 317, /*[1E290]*/ 1932 /** @stable ICU 70 */ 1933 UBLOCK_UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS_EXTENDED_A = 318, /*[11AB0]*/ 1934 /** @stable ICU 70 */ 1935 UBLOCK_VITHKUQI = 319, /*[10570]*/ 1936 /** @stable ICU 70 */ 1937 UBLOCK_ZNAMENNY_MUSICAL_NOTATION = 320, /*[1CF00]*/ 1938 1939 // New blocks in Unicode 15.0 1940 1941 /** @stable ICU 72 */ 1942 UBLOCK_ARABIC_EXTENDED_C = 321, /*[10EC0]*/ 1943 /** @stable ICU 72 */ 1944 UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_H = 322, /*[31350]*/ 1945 /** @stable ICU 72 */ 1946 UBLOCK_CYRILLIC_EXTENDED_D = 323, /*[1E030]*/ 1947 /** @stable ICU 72 */ 1948 UBLOCK_DEVANAGARI_EXTENDED_A = 324, /*[11B00]*/ 1949 /** @stable ICU 72 */ 1950 UBLOCK_KAKTOVIK_NUMERALS = 325, /*[1D2C0]*/ 1951 /** @stable ICU 72 */ 1952 UBLOCK_KAWI = 326, /*[11F00]*/ 1953 /** @stable ICU 72 */ 1954 UBLOCK_NAG_MUNDARI = 327, /*[1E4D0]*/ 1955 1956 // New block in Unicode 15.1 1957 1958 /** @stable ICU 74 */ 1959 UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_I = 328, /*[2EBF0]*/ 1960 1961 // New blocks in Unicode 16.0 1962 1963 /** @stable ICU 76 */ 1964 UBLOCK_EGYPTIAN_HIEROGLYPHS_EXTENDED_A = 329, /*[13460]*/ 1965 /** @stable ICU 76 */ 1966 UBLOCK_GARAY = 330, /*[10D40]*/ 1967 /** @stable ICU 76 */ 1968 UBLOCK_GURUNG_KHEMA = 331, /*[16100]*/ 1969 /** @stable ICU 76 */ 1970 UBLOCK_KIRAT_RAI = 332, /*[16D40]*/ 1971 /** @stable ICU 76 */ 1972 UBLOCK_MYANMAR_EXTENDED_C = 333, /*[116D0]*/ 1973 /** @stable ICU 76 */ 1974 UBLOCK_OL_ONAL = 334, /*[1E5D0]*/ 1975 /** @stable ICU 76 */ 1976 UBLOCK_SUNUWAR = 335, /*[11BC0]*/ 1977 /** @stable ICU 76 */ 1978 UBLOCK_SYMBOLS_FOR_LEGACY_COMPUTING_SUPPLEMENT = 336, /*[1CC00]*/ 1979 /** @stable ICU 76 */ 1980 UBLOCK_TODHRI = 337, /*[105C0]*/ 1981 /** @stable ICU 76 */ 1982 UBLOCK_TULU_TIGALARI = 338, /*[11380]*/ 1983 1984 // New blocks in Unicode 17.0.0 1985 1986 /** @stable ICU 78 */ 1987 UBLOCK_BERIA_ERFE = 339, /*[16EA0]*/ 1988 /** @stable ICU 78 */ 1989 UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_J = 340, /*[323B0]*/ 1990 /** @stable ICU 78 */ 1991 UBLOCK_MISCELLANEOUS_SYMBOLS_SUPPLEMENT = 341, /*[1CEC0]*/ 1992 /** @stable ICU 78 */ 1993 UBLOCK_SHARADA_SUPPLEMENT = 342, /*[11B60]*/ 1994 /** @stable ICU 78 */ 1995 UBLOCK_SIDETIC = 343, /*[10940]*/ 1996 /** @stable ICU 78 */ 1997 UBLOCK_TAI_YO = 344, /*[1E6C0]*/ 1998 /** @stable ICU 78 */ 1999 UBLOCK_TANGUT_COMPONENTS_SUPPLEMENT = 345, /*[18D80]*/ 2000 /** @stable ICU 78 */ 2001 UBLOCK_TOLONG_SIKI = 346, /*[11DB0]*/ 2002 2003 #ifndef U_HIDE_DEPRECATED_API 2004 /** 2005 * One more than the highest normal UBlockCode value. 2006 * The highest value is available via u_getIntPropertyMaxValue(UCHAR_BLOCK). 2007 * 2008 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. 2009 */ 2010 UBLOCK_COUNT = 347, 2011 #endif // U_HIDE_DEPRECATED_API 2012 2013 /** @stable ICU 2.0 */ 2014 UBLOCK_INVALID_CODE=-1 2015 }; 2016 2017 /** @stable ICU 2.0 */ 2018 typedef enum UBlockCode UBlockCode; 2019 2020 /** 2021 * East Asian Width constants. 2022 * 2023 * @see UCHAR_EAST_ASIAN_WIDTH 2024 * @see u_getIntPropertyValue 2025 * @stable ICU 2.2 2026 */ 2027 typedef enum UEastAsianWidth { 2028 /* 2029 * Note: UEastAsianWidth constants are parsed by preparseucd.py. 2030 * It matches lines like 2031 * U_EA_<Unicode East_Asian_Width value name> 2032 */ 2033 2034 U_EA_NEUTRAL, /*[N]*/ 2035 U_EA_AMBIGUOUS, /*[A]*/ 2036 U_EA_HALFWIDTH, /*[H]*/ 2037 U_EA_FULLWIDTH, /*[F]*/ 2038 U_EA_NARROW, /*[Na]*/ 2039 U_EA_WIDE, /*[W]*/ 2040 #ifndef U_HIDE_DEPRECATED_API 2041 /** 2042 * One more than the highest normal UEastAsianWidth value. 2043 * The highest value is available via u_getIntPropertyMaxValue(UCHAR_EAST_ASIAN_WIDTH). 2044 * 2045 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. 2046 */ 2047 U_EA_COUNT 2048 #endif // U_HIDE_DEPRECATED_API 2049 } UEastAsianWidth; 2050 2051 /** 2052 * Selector constants for u_charName(). 2053 * u_charName() returns the "modern" name of a 2054 * Unicode character; or the name that was defined in 2055 * Unicode version 1.0, before the Unicode standard merged 2056 * with ISO-10646; or an "extended" name that gives each 2057 * Unicode code point a unique name. 2058 * 2059 * @see u_charName 2060 * @stable ICU 2.0 2061 */ 2062 typedef enum UCharNameChoice { 2063 /** Unicode character name (Name property). @stable ICU 2.0 */ 2064 U_UNICODE_CHAR_NAME, 2065 #ifndef U_HIDE_DEPRECATED_API 2066 /** 2067 * The Unicode_1_Name property value which is of little practical value. 2068 * Beginning with ICU 49, ICU APIs return an empty string for this name choice. 2069 * @deprecated ICU 49 2070 */ 2071 U_UNICODE_10_CHAR_NAME, 2072 #endif /* U_HIDE_DEPRECATED_API */ 2073 /** Standard or synthetic character name. @stable ICU 2.0 */ 2074 U_EXTENDED_CHAR_NAME = U_UNICODE_CHAR_NAME+2, 2075 /** Corrected name from NameAliases.txt. @stable ICU 4.4 */ 2076 U_CHAR_NAME_ALIAS, 2077 #ifndef U_HIDE_DEPRECATED_API 2078 /** 2079 * One more than the highest normal UCharNameChoice value. 2080 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. 2081 */ 2082 U_CHAR_NAME_CHOICE_COUNT 2083 #endif // U_HIDE_DEPRECATED_API 2084 } UCharNameChoice; 2085 2086 /** 2087 * Selector constants for u_getPropertyName() and 2088 * u_getPropertyValueName(). These selectors are used to choose which 2089 * name is returned for a given property or value. All properties and 2090 * values have a long name. Most have a short name, but some do not. 2091 * Unicode allows for additional names, beyond the long and short 2092 * name, which would be indicated by U_LONG_PROPERTY_NAME + i, where 2093 * i=1, 2,... 2094 * 2095 * @see u_getPropertyName() 2096 * @see u_getPropertyValueName() 2097 * @stable ICU 2.4 2098 */ 2099 typedef enum UPropertyNameChoice { 2100 U_SHORT_PROPERTY_NAME, 2101 U_LONG_PROPERTY_NAME, 2102 #ifndef U_HIDE_DEPRECATED_API 2103 /** 2104 * One more than the highest normal UPropertyNameChoice value. 2105 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. 2106 */ 2107 U_PROPERTY_NAME_CHOICE_COUNT 2108 #endif // U_HIDE_DEPRECATED_API 2109 } UPropertyNameChoice; 2110 2111 /** 2112 * Decomposition Type constants. 2113 * 2114 * @see UCHAR_DECOMPOSITION_TYPE 2115 * @stable ICU 2.2 2116 */ 2117 typedef enum UDecompositionType { 2118 /* 2119 * Note: UDecompositionType constants are parsed by preparseucd.py. 2120 * It matches lines like 2121 * U_DT_<Unicode Decomposition_Type value name> 2122 */ 2123 2124 U_DT_NONE, /*[none]*/ 2125 U_DT_CANONICAL, /*[can]*/ 2126 U_DT_COMPAT, /*[com]*/ 2127 U_DT_CIRCLE, /*[enc]*/ 2128 U_DT_FINAL, /*[fin]*/ 2129 U_DT_FONT, /*[font]*/ 2130 U_DT_FRACTION, /*[fra]*/ 2131 U_DT_INITIAL, /*[init]*/ 2132 U_DT_ISOLATED, /*[iso]*/ 2133 U_DT_MEDIAL, /*[med]*/ 2134 U_DT_NARROW, /*[nar]*/ 2135 U_DT_NOBREAK, /*[nb]*/ 2136 U_DT_SMALL, /*[sml]*/ 2137 U_DT_SQUARE, /*[sqr]*/ 2138 U_DT_SUB, /*[sub]*/ 2139 U_DT_SUPER, /*[sup]*/ 2140 U_DT_VERTICAL, /*[vert]*/ 2141 U_DT_WIDE, /*[wide]*/ 2142 #ifndef U_HIDE_DEPRECATED_API 2143 /** 2144 * One more than the highest normal UDecompositionType value. 2145 * The highest value is available via u_getIntPropertyMaxValue(UCHAR_DECOMPOSITION_TYPE). 2146 * 2147 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. 2148 */ 2149 U_DT_COUNT /* 18 */ 2150 #endif // U_HIDE_DEPRECATED_API 2151 } UDecompositionType; 2152 2153 /** 2154 * Joining Type constants. 2155 * 2156 * @see UCHAR_JOINING_TYPE 2157 * @stable ICU 2.2 2158 */ 2159 typedef enum UJoiningType { 2160 /* 2161 * Note: UJoiningType constants are parsed by preparseucd.py. 2162 * It matches lines like 2163 * U_JT_<Unicode Joining_Type value name> 2164 */ 2165 2166 U_JT_NON_JOINING, /*[U]*/ 2167 U_JT_JOIN_CAUSING, /*[C]*/ 2168 U_JT_DUAL_JOINING, /*[D]*/ 2169 U_JT_LEFT_JOINING, /*[L]*/ 2170 U_JT_RIGHT_JOINING, /*[R]*/ 2171 U_JT_TRANSPARENT, /*[T]*/ 2172 #ifndef U_HIDE_DEPRECATED_API 2173 /** 2174 * One more than the highest normal UJoiningType value. 2175 * The highest value is available via u_getIntPropertyMaxValue(UCHAR_JOINING_TYPE). 2176 * 2177 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. 2178 */ 2179 U_JT_COUNT /* 6 */ 2180 #endif // U_HIDE_DEPRECATED_API 2181 } UJoiningType; 2182 2183 /** 2184 * Joining Group constants. 2185 * 2186 * @see UCHAR_JOINING_GROUP 2187 * @stable ICU 2.2 2188 */ 2189 typedef enum UJoiningGroup { 2190 /* 2191 * Note: UJoiningGroup constants are parsed by preparseucd.py. 2192 * It matches lines like 2193 * U_JG_<Unicode Joining_Group value name> 2194 */ 2195 2196 U_JG_NO_JOINING_GROUP, 2197 U_JG_AIN, 2198 U_JG_ALAPH, 2199 U_JG_ALEF, 2200 U_JG_BEH, 2201 U_JG_BETH, 2202 U_JG_DAL, 2203 U_JG_DALATH_RISH, 2204 U_JG_E, 2205 U_JG_FEH, 2206 U_JG_FINAL_SEMKATH, 2207 U_JG_GAF, 2208 U_JG_GAMAL, 2209 U_JG_HAH, 2210 U_JG_TEH_MARBUTA_GOAL, /**< @stable ICU 4.6 */ 2211 U_JG_HAMZA_ON_HEH_GOAL=U_JG_TEH_MARBUTA_GOAL, 2212 U_JG_HE, 2213 U_JG_HEH, 2214 U_JG_HEH_GOAL, 2215 U_JG_HETH, 2216 U_JG_KAF, 2217 U_JG_KAPH, 2218 U_JG_KNOTTED_HEH, 2219 U_JG_LAM, 2220 U_JG_LAMADH, 2221 U_JG_MEEM, 2222 U_JG_MIM, 2223 U_JG_NOON, 2224 U_JG_NUN, 2225 U_JG_PE, 2226 U_JG_QAF, 2227 U_JG_QAPH, 2228 U_JG_REH, 2229 U_JG_REVERSED_PE, 2230 U_JG_SAD, 2231 U_JG_SADHE, 2232 U_JG_SEEN, 2233 U_JG_SEMKATH, 2234 U_JG_SHIN, 2235 U_JG_SWASH_KAF, 2236 U_JG_SYRIAC_WAW, 2237 U_JG_TAH, 2238 U_JG_TAW, 2239 U_JG_TEH_MARBUTA, 2240 U_JG_TETH, 2241 U_JG_WAW, 2242 U_JG_YEH, 2243 U_JG_YEH_BARREE, 2244 U_JG_YEH_WITH_TAIL, 2245 U_JG_YUDH, 2246 U_JG_YUDH_HE, 2247 U_JG_ZAIN, 2248 U_JG_FE, /**< @stable ICU 2.6 */ 2249 U_JG_KHAPH, /**< @stable ICU 2.6 */ 2250 U_JG_ZHAIN, /**< @stable ICU 2.6 */ 2251 U_JG_BURUSHASKI_YEH_BARREE, /**< @stable ICU 4.0 */ 2252 U_JG_FARSI_YEH, /**< @stable ICU 4.4 */ 2253 U_JG_NYA, /**< @stable ICU 4.4 */ 2254 U_JG_ROHINGYA_YEH, /**< @stable ICU 49 */ 2255 U_JG_MANICHAEAN_ALEPH, /**< @stable ICU 54 */ 2256 U_JG_MANICHAEAN_AYIN, /**< @stable ICU 54 */ 2257 U_JG_MANICHAEAN_BETH, /**< @stable ICU 54 */ 2258 U_JG_MANICHAEAN_DALETH, /**< @stable ICU 54 */ 2259 U_JG_MANICHAEAN_DHAMEDH, /**< @stable ICU 54 */ 2260 U_JG_MANICHAEAN_FIVE, /**< @stable ICU 54 */ 2261 U_JG_MANICHAEAN_GIMEL, /**< @stable ICU 54 */ 2262 U_JG_MANICHAEAN_HETH, /**< @stable ICU 54 */ 2263 U_JG_MANICHAEAN_HUNDRED, /**< @stable ICU 54 */ 2264 U_JG_MANICHAEAN_KAPH, /**< @stable ICU 54 */ 2265 U_JG_MANICHAEAN_LAMEDH, /**< @stable ICU 54 */ 2266 U_JG_MANICHAEAN_MEM, /**< @stable ICU 54 */ 2267 U_JG_MANICHAEAN_NUN, /**< @stable ICU 54 */ 2268 U_JG_MANICHAEAN_ONE, /**< @stable ICU 54 */ 2269 U_JG_MANICHAEAN_PE, /**< @stable ICU 54 */ 2270 U_JG_MANICHAEAN_QOPH, /**< @stable ICU 54 */ 2271 U_JG_MANICHAEAN_RESH, /**< @stable ICU 54 */ 2272 U_JG_MANICHAEAN_SADHE, /**< @stable ICU 54 */ 2273 U_JG_MANICHAEAN_SAMEKH, /**< @stable ICU 54 */ 2274 U_JG_MANICHAEAN_TAW, /**< @stable ICU 54 */ 2275 U_JG_MANICHAEAN_TEN, /**< @stable ICU 54 */ 2276 U_JG_MANICHAEAN_TETH, /**< @stable ICU 54 */ 2277 U_JG_MANICHAEAN_THAMEDH, /**< @stable ICU 54 */ 2278 U_JG_MANICHAEAN_TWENTY, /**< @stable ICU 54 */ 2279 U_JG_MANICHAEAN_WAW, /**< @stable ICU 54 */ 2280 U_JG_MANICHAEAN_YODH, /**< @stable ICU 54 */ 2281 U_JG_MANICHAEAN_ZAYIN, /**< @stable ICU 54 */ 2282 U_JG_STRAIGHT_WAW, /**< @stable ICU 54 */ 2283 U_JG_AFRICAN_FEH, /**< @stable ICU 58 */ 2284 U_JG_AFRICAN_NOON, /**< @stable ICU 58 */ 2285 U_JG_AFRICAN_QAF, /**< @stable ICU 58 */ 2286 2287 U_JG_MALAYALAM_BHA, /**< @stable ICU 60 */ 2288 U_JG_MALAYALAM_JA, /**< @stable ICU 60 */ 2289 U_JG_MALAYALAM_LLA, /**< @stable ICU 60 */ 2290 U_JG_MALAYALAM_LLLA, /**< @stable ICU 60 */ 2291 U_JG_MALAYALAM_NGA, /**< @stable ICU 60 */ 2292 U_JG_MALAYALAM_NNA, /**< @stable ICU 60 */ 2293 U_JG_MALAYALAM_NNNA, /**< @stable ICU 60 */ 2294 U_JG_MALAYALAM_NYA, /**< @stable ICU 60 */ 2295 U_JG_MALAYALAM_RA, /**< @stable ICU 60 */ 2296 U_JG_MALAYALAM_SSA, /**< @stable ICU 60 */ 2297 U_JG_MALAYALAM_TTA, /**< @stable ICU 60 */ 2298 2299 U_JG_HANIFI_ROHINGYA_KINNA_YA, /**< @stable ICU 62 */ 2300 U_JG_HANIFI_ROHINGYA_PA, /**< @stable ICU 62 */ 2301 2302 U_JG_THIN_YEH, /**< @stable ICU 70 */ 2303 U_JG_VERTICAL_TAIL, /**< @stable ICU 70 */ 2304 2305 U_JG_KASHMIRI_YEH, /**< @stable ICU 76 */ 2306 2307 U_JG_THIN_NOON, /**< @stable ICU 78 */ 2308 2309 #ifndef U_HIDE_DEPRECATED_API 2310 /** 2311 * One more than the highest normal UJoiningGroup value. 2312 * The highest value is available via u_getIntPropertyMaxValue(UCHAR_JOINING_GROUP). 2313 * 2314 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. 2315 */ 2316 U_JG_COUNT 2317 #endif // U_HIDE_DEPRECATED_API 2318 } UJoiningGroup; 2319 2320 /** 2321 * Grapheme Cluster Break constants. 2322 * 2323 * @see UCHAR_GRAPHEME_CLUSTER_BREAK 2324 * @stable ICU 3.4 2325 */ 2326 typedef enum UGraphemeClusterBreak { 2327 /* 2328 * Note: UGraphemeClusterBreak constants are parsed by preparseucd.py. 2329 * It matches lines like 2330 * U_GCB_<Unicode Grapheme_Cluster_Break value name> 2331 */ 2332 2333 U_GCB_OTHER = 0, /*[XX]*/ 2334 U_GCB_CONTROL = 1, /*[CN]*/ 2335 U_GCB_CR = 2, /*[CR]*/ 2336 U_GCB_EXTEND = 3, /*[EX]*/ 2337 U_GCB_L = 4, /*[L]*/ 2338 U_GCB_LF = 5, /*[LF]*/ 2339 U_GCB_LV = 6, /*[LV]*/ 2340 U_GCB_LVT = 7, /*[LVT]*/ 2341 U_GCB_T = 8, /*[T]*/ 2342 U_GCB_V = 9, /*[V]*/ 2343 /** @stable ICU 4.0 */ 2344 U_GCB_SPACING_MARK = 10, /*[SM]*/ /* from here on: new in Unicode 5.1/ICU 4.0 */ 2345 /** @stable ICU 4.0 */ 2346 U_GCB_PREPEND = 11, /*[PP]*/ 2347 /** @stable ICU 50 */ 2348 U_GCB_REGIONAL_INDICATOR = 12, /*[RI]*/ /* new in Unicode 6.2/ICU 50 */ 2349 /** @stable ICU 58 */ 2350 U_GCB_E_BASE = 13, /*[EB]*/ /* from here on: new in Unicode 9.0/ICU 58 */ 2351 /** @stable ICU 58 */ 2352 U_GCB_E_BASE_GAZ = 14, /*[EBG]*/ 2353 /** @stable ICU 58 */ 2354 U_GCB_E_MODIFIER = 15, /*[EM]*/ 2355 /** @stable ICU 58 */ 2356 U_GCB_GLUE_AFTER_ZWJ = 16, /*[GAZ]*/ 2357 /** @stable ICU 58 */ 2358 U_GCB_ZWJ = 17, /*[ZWJ]*/ 2359 2360 #ifndef U_HIDE_DEPRECATED_API 2361 /** 2362 * One more than the highest normal UGraphemeClusterBreak value. 2363 * The highest value is available via u_getIntPropertyMaxValue(UCHAR_GRAPHEME_CLUSTER_BREAK). 2364 * 2365 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. 2366 */ 2367 U_GCB_COUNT = 18 2368 #endif // U_HIDE_DEPRECATED_API 2369 } UGraphemeClusterBreak; 2370 2371 /** 2372 * Word Break constants. 2373 * (UWordBreak is a pre-existing enum type in ubrk.h for word break status tags.) 2374 * 2375 * @see UCHAR_WORD_BREAK 2376 * @stable ICU 3.4 2377 */ 2378 typedef enum UWordBreakValues { 2379 /* 2380 * Note: UWordBreakValues constants are parsed by preparseucd.py. 2381 * It matches lines like 2382 * U_WB_<Unicode Word_Break value name> 2383 */ 2384 2385 U_WB_OTHER = 0, /*[XX]*/ 2386 U_WB_ALETTER = 1, /*[LE]*/ 2387 U_WB_FORMAT = 2, /*[FO]*/ 2388 U_WB_KATAKANA = 3, /*[KA]*/ 2389 U_WB_MIDLETTER = 4, /*[ML]*/ 2390 U_WB_MIDNUM = 5, /*[MN]*/ 2391 U_WB_NUMERIC = 6, /*[NU]*/ 2392 U_WB_EXTENDNUMLET = 7, /*[EX]*/ 2393 /** @stable ICU 4.0 */ 2394 U_WB_CR = 8, /*[CR]*/ /* from here on: new in Unicode 5.1/ICU 4.0 */ 2395 /** @stable ICU 4.0 */ 2396 U_WB_EXTEND = 9, /*[Extend]*/ 2397 /** @stable ICU 4.0 */ 2398 U_WB_LF = 10, /*[LF]*/ 2399 /** @stable ICU 4.0 */ 2400 U_WB_MIDNUMLET =11, /*[MB]*/ 2401 /** @stable ICU 4.0 */ 2402 U_WB_NEWLINE =12, /*[NL]*/ 2403 /** @stable ICU 50 */ 2404 U_WB_REGIONAL_INDICATOR = 13, /*[RI]*/ /* new in Unicode 6.2/ICU 50 */ 2405 /** @stable ICU 52 */ 2406 U_WB_HEBREW_LETTER = 14, /*[HL]*/ /* from here on: new in Unicode 6.3/ICU 52 */ 2407 /** @stable ICU 52 */ 2408 U_WB_SINGLE_QUOTE = 15, /*[SQ]*/ 2409 /** @stable ICU 52 */ 2410 U_WB_DOUBLE_QUOTE = 16, /*[DQ]*/ 2411 /** @stable ICU 58 */ 2412 U_WB_E_BASE = 17, /*[EB]*/ /* from here on: new in Unicode 9.0/ICU 58 */ 2413 /** @stable ICU 58 */ 2414 U_WB_E_BASE_GAZ = 18, /*[EBG]*/ 2415 /** @stable ICU 58 */ 2416 U_WB_E_MODIFIER = 19, /*[EM]*/ 2417 /** @stable ICU 58 */ 2418 U_WB_GLUE_AFTER_ZWJ = 20, /*[GAZ]*/ 2419 /** @stable ICU 58 */ 2420 U_WB_ZWJ = 21, /*[ZWJ]*/ 2421 /** @stable ICU 62 */ 2422 U_WB_WSEGSPACE = 22, /*[WSEGSPACE]*/ 2423 2424 #ifndef U_HIDE_DEPRECATED_API 2425 /** 2426 * One more than the highest normal UWordBreakValues value. 2427 * The highest value is available via u_getIntPropertyMaxValue(UCHAR_WORD_BREAK). 2428 * 2429 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. 2430 */ 2431 U_WB_COUNT = 23 2432 #endif // U_HIDE_DEPRECATED_API 2433 } UWordBreakValues; 2434 2435 /** 2436 * Sentence Break constants. 2437 * 2438 * @see UCHAR_SENTENCE_BREAK 2439 * @stable ICU 3.4 2440 */ 2441 typedef enum USentenceBreak { 2442 /* 2443 * Note: USentenceBreak constants are parsed by preparseucd.py. 2444 * It matches lines like 2445 * U_SB_<Unicode Sentence_Break value name> 2446 */ 2447 2448 U_SB_OTHER = 0, /*[XX]*/ 2449 U_SB_ATERM = 1, /*[AT]*/ 2450 U_SB_CLOSE = 2, /*[CL]*/ 2451 U_SB_FORMAT = 3, /*[FO]*/ 2452 U_SB_LOWER = 4, /*[LO]*/ 2453 U_SB_NUMERIC = 5, /*[NU]*/ 2454 U_SB_OLETTER = 6, /*[LE]*/ 2455 U_SB_SEP = 7, /*[SE]*/ 2456 U_SB_SP = 8, /*[SP]*/ 2457 U_SB_STERM = 9, /*[ST]*/ 2458 U_SB_UPPER = 10, /*[UP]*/ 2459 U_SB_CR = 11, /*[CR]*/ /* from here on: new in Unicode 5.1/ICU 4.0 */ 2460 U_SB_EXTEND = 12, /*[EX]*/ 2461 U_SB_LF = 13, /*[LF]*/ 2462 U_SB_SCONTINUE = 14, /*[SC]*/ 2463 #ifndef U_HIDE_DEPRECATED_API 2464 /** 2465 * One more than the highest normal USentenceBreak value. 2466 * The highest value is available via u_getIntPropertyMaxValue(UCHAR_SENTENCE_BREAK). 2467 * 2468 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. 2469 */ 2470 U_SB_COUNT = 15 2471 #endif // U_HIDE_DEPRECATED_API 2472 } USentenceBreak; 2473 2474 /** 2475 * Line Break constants. 2476 * 2477 * @see UCHAR_LINE_BREAK 2478 * @stable ICU 2.2 2479 */ 2480 typedef enum ULineBreak { 2481 /* 2482 * Note: ULineBreak constants are parsed by preparseucd.py. 2483 * It matches lines like 2484 * U_LB_<Unicode Line_Break value name> 2485 */ 2486 2487 U_LB_UNKNOWN = 0, /*[XX]*/ 2488 U_LB_AMBIGUOUS = 1, /*[AI]*/ 2489 U_LB_ALPHABETIC = 2, /*[AL]*/ 2490 U_LB_BREAK_BOTH = 3, /*[B2]*/ 2491 U_LB_BREAK_AFTER = 4, /*[BA]*/ 2492 U_LB_BREAK_BEFORE = 5, /*[BB]*/ 2493 U_LB_MANDATORY_BREAK = 6, /*[BK]*/ 2494 U_LB_CONTINGENT_BREAK = 7, /*[CB]*/ 2495 U_LB_CLOSE_PUNCTUATION = 8, /*[CL]*/ 2496 U_LB_COMBINING_MARK = 9, /*[CM]*/ 2497 U_LB_CARRIAGE_RETURN = 10, /*[CR]*/ 2498 U_LB_EXCLAMATION = 11, /*[EX]*/ 2499 U_LB_GLUE = 12, /*[GL]*/ 2500 U_LB_HYPHEN = 13, /*[HY]*/ 2501 U_LB_IDEOGRAPHIC = 14, /*[ID]*/ 2502 /** Renamed from the misspelled "inseperable" in Unicode 4.0.1/ICU 3.0 @stable ICU 3.0 */ 2503 U_LB_INSEPARABLE = 15, /*[IN]*/ 2504 U_LB_INSEPERABLE = U_LB_INSEPARABLE, 2505 U_LB_INFIX_NUMERIC = 16, /*[IS]*/ 2506 U_LB_LINE_FEED = 17, /*[LF]*/ 2507 U_LB_NONSTARTER = 18, /*[NS]*/ 2508 U_LB_NUMERIC = 19, /*[NU]*/ 2509 U_LB_OPEN_PUNCTUATION = 20, /*[OP]*/ 2510 U_LB_POSTFIX_NUMERIC = 21, /*[PO]*/ 2511 U_LB_PREFIX_NUMERIC = 22, /*[PR]*/ 2512 U_LB_QUOTATION = 23, /*[QU]*/ 2513 U_LB_COMPLEX_CONTEXT = 24, /*[SA]*/ 2514 U_LB_SURROGATE = 25, /*[SG]*/ 2515 U_LB_SPACE = 26, /*[SP]*/ 2516 U_LB_BREAK_SYMBOLS = 27, /*[SY]*/ 2517 U_LB_ZWSPACE = 28, /*[ZW]*/ 2518 /** @stable ICU 2.6 */ 2519 U_LB_NEXT_LINE = 29, /*[NL]*/ /* from here on: new in Unicode 4/ICU 2.6 */ 2520 /** @stable ICU 2.6 */ 2521 U_LB_WORD_JOINER = 30, /*[WJ]*/ 2522 /** @stable ICU 3.4 */ 2523 U_LB_H2 = 31, /*[H2]*/ /* from here on: new in Unicode 4.1/ICU 3.4 */ 2524 /** @stable ICU 3.4 */ 2525 U_LB_H3 = 32, /*[H3]*/ 2526 /** @stable ICU 3.4 */ 2527 U_LB_JL = 33, /*[JL]*/ 2528 /** @stable ICU 3.4 */ 2529 U_LB_JT = 34, /*[JT]*/ 2530 /** @stable ICU 3.4 */ 2531 U_LB_JV = 35, /*[JV]*/ 2532 /** @stable ICU 4.4 */ 2533 U_LB_CLOSE_PARENTHESIS = 36, /*[CP]*/ /* new in Unicode 5.2/ICU 4.4 */ 2534 /** @stable ICU 49 */ 2535 U_LB_CONDITIONAL_JAPANESE_STARTER = 37,/*[CJ]*/ /* new in Unicode 6.1/ICU 49 */ 2536 /** @stable ICU 49 */ 2537 U_LB_HEBREW_LETTER = 38, /*[HL]*/ /* new in Unicode 6.1/ICU 49 */ 2538 /** @stable ICU 50 */ 2539 U_LB_REGIONAL_INDICATOR = 39,/*[RI]*/ /* new in Unicode 6.2/ICU 50 */ 2540 /** @stable ICU 58 */ 2541 U_LB_E_BASE = 40, /*[EB]*/ /* from here on: new in Unicode 9.0/ICU 58 */ 2542 /** @stable ICU 58 */ 2543 U_LB_E_MODIFIER = 41, /*[EM]*/ 2544 /** @stable ICU 58 */ 2545 U_LB_ZWJ = 42, /*[ZWJ]*/ 2546 /** @stable ICU 74 */ 2547 U_LB_AKSARA = 43, /*[AK]*/ 2548 /** @stable ICU 74 */ 2549 U_LB_AKSARA_PREBASE = 44, /*[AP]*/ 2550 /** @stable ICU 74 */ 2551 U_LB_AKSARA_START = 45, /*[AS]*/ 2552 /** @stable ICU 74 */ 2553 U_LB_VIRAMA_FINAL = 46, /*[VF]*/ 2554 /** @stable ICU 74 */ 2555 U_LB_VIRAMA = 47, /*[VI]*/ 2556 /** @stable ICU 78 */ 2557 U_LB_UNAMBIGUOUS_HYPHEN = 48,/*[HH]*/ 2558 #ifndef U_HIDE_DEPRECATED_API 2559 /** 2560 * One more than the highest normal ULineBreak value. 2561 * The highest value is available via u_getIntPropertyMaxValue(UCHAR_LINE_BREAK). 2562 * 2563 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. 2564 */ 2565 U_LB_COUNT = 49 2566 #endif // U_HIDE_DEPRECATED_API 2567 } ULineBreak; 2568 2569 /** 2570 * Numeric Type constants. 2571 * 2572 * @see UCHAR_NUMERIC_TYPE 2573 * @stable ICU 2.2 2574 */ 2575 typedef enum UNumericType { 2576 /* 2577 * Note: UNumericType constants are parsed by preparseucd.py. 2578 * It matches lines like 2579 * U_NT_<Unicode Numeric_Type value name> 2580 */ 2581 2582 U_NT_NONE, /*[None]*/ 2583 U_NT_DECIMAL, /*[de]*/ 2584 U_NT_DIGIT, /*[di]*/ 2585 U_NT_NUMERIC, /*[nu]*/ 2586 #ifndef U_HIDE_DEPRECATED_API 2587 /** 2588 * One more than the highest normal UNumericType value. 2589 * The highest value is available via u_getIntPropertyMaxValue(UCHAR_NUMERIC_TYPE). 2590 * 2591 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. 2592 */ 2593 U_NT_COUNT 2594 #endif // U_HIDE_DEPRECATED_API 2595 } UNumericType; 2596 2597 /** 2598 * Hangul Syllable Type constants. 2599 * 2600 * @see UCHAR_HANGUL_SYLLABLE_TYPE 2601 * @stable ICU 2.6 2602 */ 2603 typedef enum UHangulSyllableType { 2604 /* 2605 * Note: UHangulSyllableType constants are parsed by preparseucd.py. 2606 * It matches lines like 2607 * U_HST_<Unicode Hangul_Syllable_Type value name> 2608 */ 2609 2610 U_HST_NOT_APPLICABLE, /*[NA]*/ 2611 U_HST_LEADING_JAMO, /*[L]*/ 2612 U_HST_VOWEL_JAMO, /*[V]*/ 2613 U_HST_TRAILING_JAMO, /*[T]*/ 2614 U_HST_LV_SYLLABLE, /*[LV]*/ 2615 U_HST_LVT_SYLLABLE, /*[LVT]*/ 2616 #ifndef U_HIDE_DEPRECATED_API 2617 /** 2618 * One more than the highest normal UHangulSyllableType value. 2619 * The highest value is available via u_getIntPropertyMaxValue(UCHAR_HANGUL_SYLLABLE_TYPE). 2620 * 2621 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. 2622 */ 2623 U_HST_COUNT 2624 #endif // U_HIDE_DEPRECATED_API 2625 } UHangulSyllableType; 2626 2627 /** 2628 * Indic Positional Category constants. 2629 * 2630 * @see UCHAR_INDIC_POSITIONAL_CATEGORY 2631 * @stable ICU 63 2632 */ 2633 typedef enum UIndicPositionalCategory { 2634 /* 2635 * Note: UIndicPositionalCategory constants are parsed by preparseucd.py. 2636 * It matches lines like 2637 * U_INPC_<Unicode Indic_Positional_Category value name> 2638 */ 2639 2640 /** @stable ICU 63 */ 2641 U_INPC_NA, 2642 /** @stable ICU 63 */ 2643 U_INPC_BOTTOM, 2644 /** @stable ICU 63 */ 2645 U_INPC_BOTTOM_AND_LEFT, 2646 /** @stable ICU 63 */ 2647 U_INPC_BOTTOM_AND_RIGHT, 2648 /** @stable ICU 63 */ 2649 U_INPC_LEFT, 2650 /** @stable ICU 63 */ 2651 U_INPC_LEFT_AND_RIGHT, 2652 /** @stable ICU 63 */ 2653 U_INPC_OVERSTRUCK, 2654 /** @stable ICU 63 */ 2655 U_INPC_RIGHT, 2656 /** @stable ICU 63 */ 2657 U_INPC_TOP, 2658 /** @stable ICU 63 */ 2659 U_INPC_TOP_AND_BOTTOM, 2660 /** @stable ICU 63 */ 2661 U_INPC_TOP_AND_BOTTOM_AND_RIGHT, 2662 /** @stable ICU 63 */ 2663 U_INPC_TOP_AND_LEFT, 2664 /** @stable ICU 63 */ 2665 U_INPC_TOP_AND_LEFT_AND_RIGHT, 2666 /** @stable ICU 63 */ 2667 U_INPC_TOP_AND_RIGHT, 2668 /** @stable ICU 63 */ 2669 U_INPC_VISUAL_ORDER_LEFT, 2670 /** @stable ICU 66 */ 2671 U_INPC_TOP_AND_BOTTOM_AND_LEFT, 2672 } UIndicPositionalCategory; 2673 2674 /** 2675 * Indic Syllabic Category constants. 2676 * 2677 * @see UCHAR_INDIC_SYLLABIC_CATEGORY 2678 * @stable ICU 63 2679 */ 2680 typedef enum UIndicSyllabicCategory { 2681 /* 2682 * Note: UIndicSyllabicCategory constants are parsed by preparseucd.py. 2683 * It matches lines like 2684 * U_INSC_<Unicode Indic_Syllabic_Category value name> 2685 */ 2686 2687 /** @stable ICU 63 */ 2688 U_INSC_OTHER, 2689 /** @stable ICU 63 */ 2690 U_INSC_AVAGRAHA, 2691 /** @stable ICU 63 */ 2692 U_INSC_BINDU, 2693 /** @stable ICU 63 */ 2694 U_INSC_BRAHMI_JOINING_NUMBER, 2695 /** @stable ICU 63 */ 2696 U_INSC_CANTILLATION_MARK, 2697 /** @stable ICU 63 */ 2698 U_INSC_CONSONANT, 2699 /** @stable ICU 63 */ 2700 U_INSC_CONSONANT_DEAD, 2701 /** @stable ICU 63 */ 2702 U_INSC_CONSONANT_FINAL, 2703 /** @stable ICU 63 */ 2704 U_INSC_CONSONANT_HEAD_LETTER, 2705 /** @stable ICU 63 */ 2706 U_INSC_CONSONANT_INITIAL_POSTFIXED, 2707 /** @stable ICU 63 */ 2708 U_INSC_CONSONANT_KILLER, 2709 /** @stable ICU 63 */ 2710 U_INSC_CONSONANT_MEDIAL, 2711 /** @stable ICU 63 */ 2712 U_INSC_CONSONANT_PLACEHOLDER, 2713 /** @stable ICU 63 */ 2714 U_INSC_CONSONANT_PRECEDING_REPHA, 2715 /** @stable ICU 63 */ 2716 U_INSC_CONSONANT_PREFIXED, 2717 /** @stable ICU 63 */ 2718 U_INSC_CONSONANT_SUBJOINED, 2719 /** @stable ICU 63 */ 2720 U_INSC_CONSONANT_SUCCEEDING_REPHA, 2721 /** @stable ICU 63 */ 2722 U_INSC_CONSONANT_WITH_STACKER, 2723 /** @stable ICU 63 */ 2724 U_INSC_GEMINATION_MARK, 2725 /** @stable ICU 63 */ 2726 U_INSC_INVISIBLE_STACKER, 2727 /** @stable ICU 63 */ 2728 U_INSC_JOINER, 2729 /** @stable ICU 63 */ 2730 U_INSC_MODIFYING_LETTER, 2731 /** @stable ICU 63 */ 2732 U_INSC_NON_JOINER, 2733 /** @stable ICU 63 */ 2734 U_INSC_NUKTA, 2735 /** @stable ICU 63 */ 2736 U_INSC_NUMBER, 2737 /** @stable ICU 63 */ 2738 U_INSC_NUMBER_JOINER, 2739 /** @stable ICU 63 */ 2740 U_INSC_PURE_KILLER, 2741 /** @stable ICU 63 */ 2742 U_INSC_REGISTER_SHIFTER, 2743 /** @stable ICU 63 */ 2744 U_INSC_SYLLABLE_MODIFIER, 2745 /** @stable ICU 63 */ 2746 U_INSC_TONE_LETTER, 2747 /** @stable ICU 63 */ 2748 U_INSC_TONE_MARK, 2749 /** @stable ICU 63 */ 2750 U_INSC_VIRAMA, 2751 /** @stable ICU 63 */ 2752 U_INSC_VISARGA, 2753 /** @stable ICU 63 */ 2754 U_INSC_VOWEL, 2755 /** @stable ICU 63 */ 2756 U_INSC_VOWEL_DEPENDENT, 2757 /** @stable ICU 63 */ 2758 U_INSC_VOWEL_INDEPENDENT, 2759 /** @stable ICU 76 */ 2760 U_INSC_REORDERING_KILLER, 2761 } UIndicSyllabicCategory; 2762 2763 /** 2764 * Indic Conjunct Break constants. 2765 * 2766 * @see UCHAR_INDIC_CONJUNCT_BREAK 2767 * @stable ICU 76 2768 */ 2769 typedef enum UIndicConjunctBreak { 2770 /* 2771 * Note: UIndicConjunctBreak constants are parsed by preparseucd.py. 2772 * It matches lines like 2773 * U_INCB_<Unicode Indic_Conjunct_Break value name> 2774 */ 2775 2776 /** @stable ICU 76 */ 2777 U_INCB_NONE, 2778 /** @stable ICU 76 */ 2779 U_INCB_CONSONANT, 2780 /** @stable ICU 76 */ 2781 U_INCB_EXTEND, 2782 /** @stable ICU 76 */ 2783 U_INCB_LINKER, 2784 } UIndicConjunctBreak; 2785 2786 /** 2787 * Vertical Orientation constants. 2788 * 2789 * @see UCHAR_VERTICAL_ORIENTATION 2790 * @stable ICU 63 2791 */ 2792 typedef enum UVerticalOrientation { 2793 /* 2794 * Note: UVerticalOrientation constants are parsed by preparseucd.py. 2795 * It matches lines like 2796 * U_VO_<Unicode Vertical_Orientation value name> 2797 */ 2798 2799 /** @stable ICU 63 */ 2800 U_VO_ROTATED, 2801 /** @stable ICU 63 */ 2802 U_VO_TRANSFORMED_ROTATED, 2803 /** @stable ICU 63 */ 2804 U_VO_TRANSFORMED_UPRIGHT, 2805 /** @stable ICU 63 */ 2806 U_VO_UPRIGHT, 2807 } UVerticalOrientation; 2808 2809 /** 2810 * Identifier Status constants. 2811 * See https://www.unicode.org/reports/tr39/#Identifier_Status_and_Type. 2812 * 2813 * @see UCHAR_IDENTIFIER_STATUS 2814 * @stable ICU 75 2815 */ 2816 typedef enum UIdentifierStatus { 2817 /* 2818 * Note: UIdentifierStatus constants are parsed by preparseucd.py. 2819 * It matches lines like 2820 * U_ID_STATUS_<Unicode Identifier_Status value name> 2821 */ 2822 2823 /** @stable ICU 75 */ 2824 U_ID_STATUS_RESTRICTED, 2825 /** @stable ICU 75 */ 2826 U_ID_STATUS_ALLOWED, 2827 } UIdentifierStatus; 2828 2829 /** 2830 * Identifier Type constants. 2831 * See https://www.unicode.org/reports/tr39/#Identifier_Status_and_Type. 2832 * 2833 * @see UCHAR_IDENTIFIER_TYPE 2834 * @stable ICU 75 2835 */ 2836 typedef enum UIdentifierType { 2837 /* 2838 * Note: UIdentifierType constants are parsed by preparseucd.py. 2839 * It matches lines like 2840 * U_ID_TYPE_<Unicode Identifier_Type value name> 2841 */ 2842 2843 /** @stable ICU 75 */ 2844 U_ID_TYPE_NOT_CHARACTER, 2845 /** @stable ICU 75 */ 2846 U_ID_TYPE_DEPRECATED, 2847 /** @stable ICU 75 */ 2848 U_ID_TYPE_DEFAULT_IGNORABLE, 2849 /** @stable ICU 75 */ 2850 U_ID_TYPE_NOT_NFKC, 2851 /** @stable ICU 75 */ 2852 U_ID_TYPE_NOT_XID, 2853 /** @stable ICU 75 */ 2854 U_ID_TYPE_EXCLUSION, 2855 /** @stable ICU 75 */ 2856 U_ID_TYPE_OBSOLETE, 2857 /** @stable ICU 75 */ 2858 U_ID_TYPE_TECHNICAL, 2859 /** @stable ICU 75 */ 2860 U_ID_TYPE_UNCOMMON_USE, 2861 /** @stable ICU 75 */ 2862 U_ID_TYPE_LIMITED_USE, 2863 /** @stable ICU 75 */ 2864 U_ID_TYPE_INCLUSION, 2865 /** @stable ICU 75 */ 2866 U_ID_TYPE_RECOMMENDED, 2867 } UIdentifierType; 2868 2869 /** 2870 * Check a binary Unicode property for a code point. 2871 * 2872 * Unicode, especially in version 3.2, defines many more properties than the 2873 * original set in UnicodeData.txt. 2874 * 2875 * The properties APIs are intended to reflect Unicode properties as defined 2876 * in the Unicode Character Database (UCD) and Unicode Technical Reports (UTR). 2877 * For details about the properties see http://www.unicode.org/ucd/ . 2878 * For names of Unicode properties see the UCD file PropertyAliases.txt. 2879 * 2880 * Important: If ICU is built with UCD files from Unicode versions below 3.2, 2881 * then properties marked with "new in Unicode 3.2" are not or not fully available. 2882 * 2883 * @param c Code point to test. 2884 * @param which UProperty selector constant, identifies which binary property to check. 2885 * Must be UCHAR_BINARY_START<=which<UCHAR_BINARY_LIMIT. 2886 * @return true or false according to the binary Unicode property value for c. 2887 * Also false if 'which' is out of bounds or if the Unicode version 2888 * does not have data for the property at all. 2889 * 2890 * @see UProperty 2891 * @see u_getBinaryPropertySet 2892 * @see u_getIntPropertyValue 2893 * @see u_getUnicodeVersion 2894 * @stable ICU 2.1 2895 */ 2896 U_CAPI UBool U_EXPORT2 2897 u_hasBinaryProperty(UChar32 c, UProperty which); 2898 2899 /** 2900 * Returns true if the property is true for the string. 2901 * Same as u_hasBinaryProperty(single code point, which) 2902 * if the string contains exactly one code point. 2903 * 2904 * Most properties apply only to single code points. 2905 * <a href="https://www.unicode.org/reports/tr51/#Emoji_Sets">UTS #51 Unicode Emoji</a> 2906 * defines several properties of strings. 2907 * 2908 * @param s String to test. 2909 * @param length Length of the string, or negative if NUL-terminated. 2910 * @param which UProperty selector constant, identifies which binary property to check. 2911 * Must be UCHAR_BINARY_START<=which<UCHAR_BINARY_LIMIT. 2912 * @return true or false according to the binary Unicode property value for the string. 2913 * Also false if 'which' is out of bounds or if the Unicode version 2914 * does not have data for the property at all. 2915 * 2916 * @see UProperty 2917 * @see u_hasBinaryProperty 2918 * @see u_getBinaryPropertySet 2919 * @see u_getIntPropertyValue 2920 * @see u_getUnicodeVersion 2921 * @stable ICU 70 2922 */ 2923 U_CAPI UBool U_EXPORT2 2924 u_stringHasBinaryProperty(const UChar *s, int32_t length, UProperty which); 2925 2926 /** 2927 * Returns a frozen USet for a binary property. 2928 * The library retains ownership over the returned object. 2929 * Sets an error code if the property number is not one for a binary property. 2930 * 2931 * The returned set contains all code points for which the property is true. 2932 * 2933 * @param property UCHAR_BINARY_START..UCHAR_BINARY_LIMIT-1 2934 * @param pErrorCode an in/out ICU UErrorCode 2935 * @return the property as a set 2936 * @see UProperty 2937 * @see u_hasBinaryProperty 2938 * @see UnicodeSet::fromUSet 2939 * @stable ICU 63 2940 */ 2941 U_CAPI const USet * U_EXPORT2 2942 u_getBinaryPropertySet(UProperty property, UErrorCode *pErrorCode); 2943 2944 /** 2945 * Check if a code point has the Alphabetic Unicode property. 2946 * Same as u_hasBinaryProperty(c, UCHAR_ALPHABETIC). 2947 * This is different from u_isalpha! 2948 * @param c Code point to test 2949 * @return true if the code point has the Alphabetic Unicode property, false otherwise 2950 * 2951 * @see UCHAR_ALPHABETIC 2952 * @see u_isalpha 2953 * @see u_hasBinaryProperty 2954 * @stable ICU 2.1 2955 */ 2956 U_CAPI UBool U_EXPORT2 2957 u_isUAlphabetic(UChar32 c); 2958 2959 /** 2960 * Check if a code point has the Lowercase Unicode property. 2961 * Same as u_hasBinaryProperty(c, UCHAR_LOWERCASE). 2962 * This is different from u_islower! 2963 * @param c Code point to test 2964 * @return true if the code point has the Lowercase Unicode property, false otherwise 2965 * 2966 * @see UCHAR_LOWERCASE 2967 * @see u_islower 2968 * @see u_hasBinaryProperty 2969 * @stable ICU 2.1 2970 */ 2971 U_CAPI UBool U_EXPORT2 2972 u_isULowercase(UChar32 c); 2973 2974 /** 2975 * Check if a code point has the Uppercase Unicode property. 2976 * Same as u_hasBinaryProperty(c, UCHAR_UPPERCASE). 2977 * This is different from u_isupper! 2978 * @param c Code point to test 2979 * @return true if the code point has the Uppercase Unicode property, false otherwise 2980 * 2981 * @see UCHAR_UPPERCASE 2982 * @see u_isupper 2983 * @see u_hasBinaryProperty 2984 * @stable ICU 2.1 2985 */ 2986 U_CAPI UBool U_EXPORT2 2987 u_isUUppercase(UChar32 c); 2988 2989 /** 2990 * Check if a code point has the White_Space Unicode property. 2991 * Same as u_hasBinaryProperty(c, UCHAR_WHITE_SPACE). 2992 * This is different from both u_isspace and u_isWhitespace! 2993 * 2994 * Note: There are several ICU whitespace functions; please see the uchar.h 2995 * file documentation for a detailed comparison. 2996 * 2997 * @param c Code point to test 2998 * @return true if the code point has the White_Space Unicode property, false otherwise. 2999 * 3000 * @see UCHAR_WHITE_SPACE 3001 * @see u_isWhitespace 3002 * @see u_isspace 3003 * @see u_isJavaSpaceChar 3004 * @see u_hasBinaryProperty 3005 * @stable ICU 2.1 3006 */ 3007 U_CAPI UBool U_EXPORT2 3008 u_isUWhiteSpace(UChar32 c); 3009 3010 /** 3011 * Get the property value for an enumerated or integer Unicode property for a code point. 3012 * Also returns binary and mask property values. 3013 * 3014 * Unicode, especially in version 3.2, defines many more properties than the 3015 * original set in UnicodeData.txt. 3016 * 3017 * The properties APIs are intended to reflect Unicode properties as defined 3018 * in the Unicode Character Database (UCD) and Unicode Technical Reports (UTR). 3019 * For details about the properties see http://www.unicode.org/ . 3020 * For names of Unicode properties see the UCD file PropertyAliases.txt. 3021 * 3022 * Sample usage: 3023 * UEastAsianWidth ea=(UEastAsianWidth)u_getIntPropertyValue(c, UCHAR_EAST_ASIAN_WIDTH); 3024 * UBool b=(UBool)u_getIntPropertyValue(c, UCHAR_IDEOGRAPHIC); 3025 * 3026 * @param c Code point to test. 3027 * @param which UProperty selector constant, identifies which property to check. 3028 * Must be UCHAR_BINARY_START<=which<UCHAR_BINARY_LIMIT 3029 * or UCHAR_INT_START<=which<UCHAR_INT_LIMIT 3030 * or UCHAR_MASK_START<=which<UCHAR_MASK_LIMIT. 3031 * @return Numeric value that is directly the property value or, 3032 * for enumerated properties, corresponds to the numeric value of the enumerated 3033 * constant of the respective property value enumeration type 3034 * (cast to enum type if necessary). 3035 * Returns 0 or 1 (for false/true) for binary Unicode properties. 3036 * Returns a bit-mask for mask properties. 3037 * Returns 0 if 'which' is out of bounds or if the Unicode version 3038 * does not have data for the property at all, or not for this code point. 3039 * 3040 * @see UProperty 3041 * @see u_hasBinaryProperty 3042 * @see u_getIntPropertyMinValue 3043 * @see u_getIntPropertyMaxValue 3044 * @see u_getIntPropertyMap 3045 * @see u_getUnicodeVersion 3046 * @stable ICU 2.2 3047 */ 3048 U_CAPI int32_t U_EXPORT2 3049 u_getIntPropertyValue(UChar32 c, UProperty which); 3050 3051 /** 3052 * Get the minimum value for an enumerated/integer/binary Unicode property. 3053 * Can be used together with u_getIntPropertyMaxValue 3054 * to allocate arrays of UnicodeSet or similar. 3055 * 3056 * @param which UProperty selector constant, identifies which binary property to check. 3057 * Must be UCHAR_BINARY_START<=which<UCHAR_BINARY_LIMIT 3058 * or UCHAR_INT_START<=which<UCHAR_INT_LIMIT. 3059 * @return Minimum value returned by u_getIntPropertyValue for a Unicode property. 3060 * 0 if the property selector is out of range. 3061 * 3062 * @see UProperty 3063 * @see u_hasBinaryProperty 3064 * @see u_getUnicodeVersion 3065 * @see u_getIntPropertyMaxValue 3066 * @see u_getIntPropertyValue 3067 * @stable ICU 2.2 3068 */ 3069 U_CAPI int32_t U_EXPORT2 3070 u_getIntPropertyMinValue(UProperty which); 3071 3072 /** 3073 * Get the maximum value for an enumerated/integer/binary Unicode property. 3074 * Can be used together with u_getIntPropertyMinValue 3075 * to allocate arrays of UnicodeSet or similar. 3076 * 3077 * Examples for min/max values (for Unicode 3.2): 3078 * 3079 * - UCHAR_BIDI_CLASS: 0/18 (U_LEFT_TO_RIGHT/U_BOUNDARY_NEUTRAL) 3080 * - UCHAR_SCRIPT: 0/45 (USCRIPT_COMMON/USCRIPT_TAGBANWA) 3081 * - UCHAR_IDEOGRAPHIC: 0/1 (false/true) 3082 * 3083 * For undefined UProperty constant values, min/max values will be 0/-1. 3084 * 3085 * @param which UProperty selector constant, identifies which binary property to check. 3086 * Must be UCHAR_BINARY_START<=which<UCHAR_BINARY_LIMIT 3087 * or UCHAR_INT_START<=which<UCHAR_INT_LIMIT. 3088 * @return Maximum value returned by u_getIntPropertyValue for a Unicode property. 3089 * <=0 if the property selector is out of range. 3090 * 3091 * @see UProperty 3092 * @see u_hasBinaryProperty 3093 * @see u_getUnicodeVersion 3094 * @see u_getIntPropertyMaxValue 3095 * @see u_getIntPropertyValue 3096 * @stable ICU 2.2 3097 */ 3098 U_CAPI int32_t U_EXPORT2 3099 u_getIntPropertyMaxValue(UProperty which); 3100 3101 /** 3102 * Returns an immutable UCPMap for an enumerated/catalog/int-valued property. 3103 * The library retains ownership over the returned object. 3104 * Sets an error code if the property number is not one for an "int property". 3105 * 3106 * The returned object maps all Unicode code points to their values for that property. 3107 * For documentation of the integer values see u_getIntPropertyValue(). 3108 * 3109 * @param property UCHAR_INT_START..UCHAR_INT_LIMIT-1 3110 * @param pErrorCode an in/out ICU UErrorCode 3111 * @return the property as a map 3112 * @see UProperty 3113 * @see u_getIntPropertyValue 3114 * @stable ICU 63 3115 */ 3116 U_CAPI const UCPMap * U_EXPORT2 3117 u_getIntPropertyMap(UProperty property, UErrorCode *pErrorCode); 3118 3119 /** 3120 * Get the numeric value for a Unicode code point as defined in the 3121 * Unicode Character Database. 3122 * 3123 * A "double" return type is necessary because 3124 * some numeric values are fractions, negative, or too large for int32_t. 3125 * 3126 * For characters without any numeric values in the Unicode Character Database, 3127 * this function will return U_NO_NUMERIC_VALUE. 3128 * Note: This is different from the Unicode Standard which specifies NaN as the default value. 3129 * (NaN is not available on all platforms.) 3130 * 3131 * Similar to java.lang.Character.getNumericValue(), but u_getNumericValue() 3132 * also supports negative values, large values, and fractions, 3133 * while Java's getNumericValue() returns values 10..35 for ASCII letters. 3134 * 3135 * @param c Code point to get the numeric value for. 3136 * @return Numeric value of c, or U_NO_NUMERIC_VALUE if none is defined. 3137 * 3138 * @see U_NO_NUMERIC_VALUE 3139 * @stable ICU 2.2 3140 */ 3141 U_CAPI double U_EXPORT2 3142 u_getNumericValue(UChar32 c); 3143 3144 /** 3145 * Special value that is returned by u_getNumericValue when 3146 * no numeric value is defined for a code point. 3147 * 3148 * @see u_getNumericValue 3149 * @stable ICU 2.2 3150 */ 3151 #define U_NO_NUMERIC_VALUE ((double)-123456789.) 3152 3153 /** 3154 * Determines whether the specified code point has the general category "Ll" 3155 * (lowercase letter). 3156 * 3157 * Same as java.lang.Character.isLowerCase(). 3158 * 3159 * This misses some characters that are also lowercase but 3160 * have a different general category value. 3161 * In order to include those, use UCHAR_LOWERCASE. 3162 * 3163 * In addition to being equivalent to a Java function, this also serves 3164 * as a C/POSIX migration function. 3165 * See the comments about C/POSIX character classification functions in the 3166 * documentation at the top of this header file. 3167 * 3168 * @param c the code point to be tested 3169 * @return true if the code point is an Ll lowercase letter 3170 * 3171 * @see UCHAR_LOWERCASE 3172 * @see u_isupper 3173 * @see u_istitle 3174 * @stable ICU 2.0 3175 */ 3176 U_CAPI UBool U_EXPORT2 3177 u_islower(UChar32 c); 3178 3179 /** 3180 * Determines whether the specified code point has the general category "Lu" 3181 * (uppercase letter). 3182 * 3183 * Same as java.lang.Character.isUpperCase(). 3184 * 3185 * This misses some characters that are also uppercase but 3186 * have a different general category value. 3187 * In order to include those, use UCHAR_UPPERCASE. 3188 * 3189 * In addition to being equivalent to a Java function, this also serves 3190 * as a C/POSIX migration function. 3191 * See the comments about C/POSIX character classification functions in the 3192 * documentation at the top of this header file. 3193 * 3194 * @param c the code point to be tested 3195 * @return true if the code point is an Lu uppercase letter 3196 * 3197 * @see UCHAR_UPPERCASE 3198 * @see u_islower 3199 * @see u_istitle 3200 * @see u_tolower 3201 * @stable ICU 2.0 3202 */ 3203 U_CAPI UBool U_EXPORT2 3204 u_isupper(UChar32 c); 3205 3206 /** 3207 * Determines whether the specified code point is a titlecase letter. 3208 * True for general category "Lt" (titlecase letter). 3209 * 3210 * Same as java.lang.Character.isTitleCase(). 3211 * 3212 * @param c the code point to be tested 3213 * @return true if the code point is an Lt titlecase letter 3214 * 3215 * @see u_isupper 3216 * @see u_islower 3217 * @see u_totitle 3218 * @stable ICU 2.0 3219 */ 3220 U_CAPI UBool U_EXPORT2 3221 u_istitle(UChar32 c); 3222 3223 /** 3224 * Determines whether the specified code point is a digit character according to Java. 3225 * True for characters with general category "Nd" (decimal digit numbers). 3226 * Beginning with Unicode 4, this is the same as 3227 * testing for the Numeric_Type of Decimal. 3228 * 3229 * Same as java.lang.Character.isDigit(). 3230 * 3231 * In addition to being equivalent to a Java function, this also serves 3232 * as a C/POSIX migration function. 3233 * See the comments about C/POSIX character classification functions in the 3234 * documentation at the top of this header file. 3235 * 3236 * @param c the code point to be tested 3237 * @return true if the code point is a digit character according to Character.isDigit() 3238 * 3239 * @stable ICU 2.0 3240 */ 3241 U_CAPI UBool U_EXPORT2 3242 u_isdigit(UChar32 c); 3243 3244 /** 3245 * Determines whether the specified code point is a letter character. 3246 * True for general categories "L" (letters). 3247 * 3248 * Same as java.lang.Character.isLetter(). 3249 * 3250 * In addition to being equivalent to a Java function, this also serves 3251 * as a C/POSIX migration function. 3252 * See the comments about C/POSIX character classification functions in the 3253 * documentation at the top of this header file. 3254 * 3255 * @param c the code point to be tested 3256 * @return true if the code point is a letter character 3257 * 3258 * @see u_isdigit 3259 * @see u_isalnum 3260 * @stable ICU 2.0 3261 */ 3262 U_CAPI UBool U_EXPORT2 3263 u_isalpha(UChar32 c); 3264 3265 /** 3266 * Determines whether the specified code point is an alphanumeric character 3267 * (letter or digit) according to Java. 3268 * True for characters with general categories 3269 * "L" (letters) and "Nd" (decimal digit numbers). 3270 * 3271 * Same as java.lang.Character.isLetterOrDigit(). 3272 * 3273 * In addition to being equivalent to a Java function, this also serves 3274 * as a C/POSIX migration function. 3275 * See the comments about C/POSIX character classification functions in the 3276 * documentation at the top of this header file. 3277 * 3278 * @param c the code point to be tested 3279 * @return true if the code point is an alphanumeric character according to Character.isLetterOrDigit() 3280 * 3281 * @stable ICU 2.0 3282 */ 3283 U_CAPI UBool U_EXPORT2 3284 u_isalnum(UChar32 c); 3285 3286 /** 3287 * Determines whether the specified code point is a hexadecimal digit. 3288 * This is equivalent to u_digit(c, 16)>=0. 3289 * True for characters with general category "Nd" (decimal digit numbers) 3290 * as well as Latin letters a-f and A-F in both ASCII and Fullwidth ASCII. 3291 * (That is, for letters with code points 3292 * 0041..0046, 0061..0066, FF21..FF26, FF41..FF46.) 3293 * 3294 * In order to narrow the definition of hexadecimal digits to only ASCII 3295 * characters, use (c<=0x7f && u_isxdigit(c)). 3296 * 3297 * This is a C/POSIX migration function. 3298 * See the comments about C/POSIX character classification functions in the 3299 * documentation at the top of this header file. 3300 * 3301 * @param c the code point to be tested 3302 * @return true if the code point is a hexadecimal digit 3303 * 3304 * @stable ICU 2.6 3305 */ 3306 U_CAPI UBool U_EXPORT2 3307 u_isxdigit(UChar32 c); 3308 3309 /** 3310 * Determines whether the specified code point is a punctuation character. 3311 * True for characters with general categories "P" (punctuation). 3312 * 3313 * This is a C/POSIX migration function. 3314 * See the comments about C/POSIX character classification functions in the 3315 * documentation at the top of this header file. 3316 * 3317 * @param c the code point to be tested 3318 * @return true if the code point is a punctuation character 3319 * 3320 * @stable ICU 2.6 3321 */ 3322 U_CAPI UBool U_EXPORT2 3323 u_ispunct(UChar32 c); 3324 3325 /** 3326 * Determines whether the specified code point is a "graphic" character 3327 * (printable, excluding spaces). 3328 * true for all characters except those with general categories 3329 * "Cc" (control codes), "Cf" (format controls), "Cs" (surrogates), 3330 * "Cn" (unassigned), and "Z" (separators). 3331 * 3332 * This is a C/POSIX migration function. 3333 * See the comments about C/POSIX character classification functions in the 3334 * documentation at the top of this header file. 3335 * 3336 * @param c the code point to be tested 3337 * @return true if the code point is a "graphic" character 3338 * 3339 * @stable ICU 2.6 3340 */ 3341 U_CAPI UBool U_EXPORT2 3342 u_isgraph(UChar32 c); 3343 3344 /** 3345 * Determines whether the specified code point is a "blank" or "horizontal space", 3346 * a character that visibly separates words on a line. 3347 * The following are equivalent definitions: 3348 * 3349 * true for Unicode White_Space characters except for "vertical space controls" 3350 * where "vertical space controls" are the following characters: 3351 * U+000A (LF) U+000B (VT) U+000C (FF) U+000D (CR) U+0085 (NEL) U+2028 (LS) U+2029 (PS) 3352 * 3353 * same as 3354 * 3355 * true for U+0009 (TAB) and characters with general category "Zs" (space separators). 3356 * 3357 * Note: There are several ICU whitespace functions; please see the uchar.h 3358 * file documentation for a detailed comparison. 3359 * 3360 * This is a C/POSIX migration function. 3361 * See the comments about C/POSIX character classification functions in the 3362 * documentation at the top of this header file. 3363 * 3364 * @param c the code point to be tested 3365 * @return true if the code point is a "blank" 3366 * 3367 * @stable ICU 2.6 3368 */ 3369 U_CAPI UBool U_EXPORT2 3370 u_isblank(UChar32 c); 3371 3372 /** 3373 * Determines whether the specified code point is "defined", 3374 * which usually means that it is assigned a character. 3375 * True for general categories other than "Cn" (other, not assigned), 3376 * i.e., true for all code points mentioned in UnicodeData.txt. 3377 * 3378 * Note that non-character code points (e.g., U+FDD0) are not "defined" 3379 * (they are Cn), but surrogate code points are "defined" (Cs). 3380 * 3381 * Same as java.lang.Character.isDefined(). 3382 * 3383 * @param c the code point to be tested 3384 * @return true if the code point is assigned a character 3385 * 3386 * @see u_isdigit 3387 * @see u_isalpha 3388 * @see u_isalnum 3389 * @see u_isupper 3390 * @see u_islower 3391 * @see u_istitle 3392 * @stable ICU 2.0 3393 */ 3394 U_CAPI UBool U_EXPORT2 3395 u_isdefined(UChar32 c); 3396 3397 /** 3398 * Determines if the specified character is a space character or not. 3399 * 3400 * Note: There are several ICU whitespace functions; please see the uchar.h 3401 * file documentation for a detailed comparison. 3402 * 3403 * This is a C/POSIX migration function. 3404 * See the comments about C/POSIX character classification functions in the 3405 * documentation at the top of this header file. 3406 * 3407 * @param c the character to be tested 3408 * @return true if the character is a space character; false otherwise. 3409 * 3410 * @see u_isJavaSpaceChar 3411 * @see u_isWhitespace 3412 * @see u_isUWhiteSpace 3413 * @stable ICU 2.0 3414 */ 3415 U_CAPI UBool U_EXPORT2 3416 u_isspace(UChar32 c); 3417 3418 /** 3419 * Determine if the specified code point is a space character according to Java. 3420 * True for characters with general categories "Z" (separators), 3421 * which does not include control codes (e.g., TAB or Line Feed). 3422 * 3423 * Same as java.lang.Character.isSpaceChar(). 3424 * 3425 * Note: There are several ICU whitespace functions; please see the uchar.h 3426 * file documentation for a detailed comparison. 3427 * 3428 * @param c the code point to be tested 3429 * @return true if the code point is a space character according to Character.isSpaceChar() 3430 * 3431 * @see u_isspace 3432 * @see u_isWhitespace 3433 * @see u_isUWhiteSpace 3434 * @stable ICU 2.6 3435 */ 3436 U_CAPI UBool U_EXPORT2 3437 u_isJavaSpaceChar(UChar32 c); 3438 3439 /** 3440 * Determines if the specified code point is a whitespace character according to Java/ICU. 3441 * A character is considered to be a Java whitespace character if and only 3442 * if it satisfies one of the following criteria: 3443 * 3444 * - It is a Unicode Separator character (categories "Z" = "Zs" or "Zl" or "Zp"), but is not 3445 * also a non-breaking space (U+00A0 NBSP or U+2007 Figure Space or U+202F Narrow NBSP). 3446 * - It is U+0009 HORIZONTAL TABULATION. 3447 * - It is U+000A LINE FEED. 3448 * - It is U+000B VERTICAL TABULATION. 3449 * - It is U+000C FORM FEED. 3450 * - It is U+000D CARRIAGE RETURN. 3451 * - It is U+001C FILE SEPARATOR. 3452 * - It is U+001D GROUP SEPARATOR. 3453 * - It is U+001E RECORD SEPARATOR. 3454 * - It is U+001F UNIT SEPARATOR. 3455 * 3456 * This API tries to sync with the semantics of Java's 3457 * java.lang.Character.isWhitespace(), but it may not return 3458 * the exact same results because of the Unicode version 3459 * difference. 3460 * 3461 * Note: Unicode 4.0.1 changed U+200B ZERO WIDTH SPACE from a Space Separator (Zs) 3462 * to a Format Control (Cf). Since then, isWhitespace(0x200b) returns false. 3463 * See http://www.unicode.org/versions/Unicode4.0.1/ 3464 * 3465 * Note: There are several ICU whitespace functions; please see the uchar.h 3466 * file documentation for a detailed comparison. 3467 * 3468 * @param c the code point to be tested 3469 * @return true if the code point is a whitespace character according to Java/ICU 3470 * 3471 * @see u_isspace 3472 * @see u_isJavaSpaceChar 3473 * @see u_isUWhiteSpace 3474 * @stable ICU 2.0 3475 */ 3476 U_CAPI UBool U_EXPORT2 3477 u_isWhitespace(UChar32 c); 3478 3479 /** 3480 * Determines whether the specified code point is a control character 3481 * (as defined by this function). 3482 * A control character is one of the following: 3483 * - ISO 8-bit control character (U+0000..U+001f and U+007f..U+009f) 3484 * - U_CONTROL_CHAR (Cc) 3485 * - U_FORMAT_CHAR (Cf) 3486 * - U_LINE_SEPARATOR (Zl) 3487 * - U_PARAGRAPH_SEPARATOR (Zp) 3488 * 3489 * This is a C/POSIX migration function. 3490 * See the comments about C/POSIX character classification functions in the 3491 * documentation at the top of this header file. 3492 * 3493 * @param c the code point to be tested 3494 * @return true if the code point is a control character 3495 * 3496 * @see UCHAR_DEFAULT_IGNORABLE_CODE_POINT 3497 * @see u_isprint 3498 * @stable ICU 2.0 3499 */ 3500 U_CAPI UBool U_EXPORT2 3501 u_iscntrl(UChar32 c); 3502 3503 /** 3504 * Determines whether the specified code point is an ISO control code. 3505 * True for U+0000..U+001f and U+007f..U+009f (general category "Cc"). 3506 * 3507 * Same as java.lang.Character.isISOControl(). 3508 * 3509 * @param c the code point to be tested 3510 * @return true if the code point is an ISO control code 3511 * 3512 * @see u_iscntrl 3513 * @stable ICU 2.6 3514 */ 3515 U_CAPI UBool U_EXPORT2 3516 u_isISOControl(UChar32 c); 3517 3518 /** 3519 * Determines whether the specified code point is a printable character. 3520 * True for general categories <em>other</em> than "C" (controls). 3521 * 3522 * This is a C/POSIX migration function. 3523 * See the comments about C/POSIX character classification functions in the 3524 * documentation at the top of this header file. 3525 * 3526 * @param c the code point to be tested 3527 * @return true if the code point is a printable character 3528 * 3529 * @see UCHAR_DEFAULT_IGNORABLE_CODE_POINT 3530 * @see u_iscntrl 3531 * @stable ICU 2.0 3532 */ 3533 U_CAPI UBool U_EXPORT2 3534 u_isprint(UChar32 c); 3535 3536 /** 3537 * Non-standard: Determines whether the specified code point is a base character. 3538 * True for general categories "L" (letters), "N" (numbers), 3539 * "Mc" (spacing combining marks), and "Me" (enclosing marks). 3540 * 3541 * Note that this is different from the Unicode Standard definition in 3542 * chapter 3.6, conformance clause D51 “Base character”, 3543 * which defines base characters as the code points with general categories 3544 * Letter (L), Number (N), Punctuation (P), Symbol (S), or Space Separator (Zs). 3545 * 3546 * @param c the code point to be tested 3547 * @return true if the code point is a base character according to this function 3548 * 3549 * @see u_isalpha 3550 * @see u_isdigit 3551 * @stable ICU 2.0 3552 */ 3553 U_CAPI UBool U_EXPORT2 3554 u_isbase(UChar32 c); 3555 3556 /** 3557 * Returns the bidirectional category value for the code point, 3558 * which is used in the Unicode bidirectional algorithm 3559 * (UAX #9 http://www.unicode.org/reports/tr9/). 3560 * Note that some <em>unassigned</em> code points have bidi values 3561 * of R or AL because they are in blocks that are reserved 3562 * for Right-To-Left scripts. 3563 * 3564 * Same as java.lang.Character.getDirectionality() 3565 * 3566 * @param c the code point to be tested 3567 * @return the bidirectional category (UCharDirection) value 3568 * 3569 * @see UCharDirection 3570 * @stable ICU 2.0 3571 */ 3572 U_CAPI UCharDirection U_EXPORT2 3573 u_charDirection(UChar32 c); 3574 3575 /** 3576 * Determines whether the code point has the Bidi_Mirrored property. 3577 * This property is set for characters that are commonly used in 3578 * Right-To-Left contexts and need to be displayed with a "mirrored" 3579 * glyph. 3580 * 3581 * Same as java.lang.Character.isMirrored(). 3582 * Same as UCHAR_BIDI_MIRRORED 3583 * 3584 * @param c the code point to be tested 3585 * @return true if the character has the Bidi_Mirrored property 3586 * 3587 * @see UCHAR_BIDI_MIRRORED 3588 * @stable ICU 2.0 3589 */ 3590 U_CAPI UBool U_EXPORT2 3591 u_isMirrored(UChar32 c); 3592 3593 /** 3594 * Maps the specified character to a "mirror-image" character. 3595 * For characters with the Bidi_Mirrored property, implementations 3596 * sometimes need a "poor man's" mapping to another Unicode 3597 * character (code point) such that the default glyph may serve 3598 * as the mirror-image of the default glyph of the specified 3599 * character. This is useful for text conversion to and from 3600 * codepages with visual order, and for displays without glyph 3601 * selection capabilities. 3602 * 3603 * @param c the code point to be mapped 3604 * @return another Unicode code point that may serve as a mirror-image 3605 * substitute, or c itself if there is no such mapping or c 3606 * does not have the Bidi_Mirrored property 3607 * 3608 * @see UCHAR_BIDI_MIRRORED 3609 * @see u_isMirrored 3610 * @stable ICU 2.0 3611 */ 3612 U_CAPI UChar32 U_EXPORT2 3613 u_charMirror(UChar32 c); 3614 3615 /** 3616 * Maps the specified character to its paired bracket character. 3617 * For Bidi_Paired_Bracket_Type!=None, this is the same as u_charMirror(). 3618 * Otherwise c itself is returned. 3619 * See http://www.unicode.org/reports/tr9/ 3620 * 3621 * @param c the code point to be mapped 3622 * @return the paired bracket code point, 3623 * or c itself if there is no such mapping 3624 * (Bidi_Paired_Bracket_Type=None) 3625 * 3626 * @see UCHAR_BIDI_PAIRED_BRACKET 3627 * @see UCHAR_BIDI_PAIRED_BRACKET_TYPE 3628 * @see u_charMirror 3629 * @stable ICU 52 3630 */ 3631 U_CAPI UChar32 U_EXPORT2 3632 u_getBidiPairedBracket(UChar32 c); 3633 3634 /** 3635 * Returns the general category value for the code point. 3636 * 3637 * Same as java.lang.Character.getType(). 3638 * 3639 * @param c the code point to be tested 3640 * @return the general category (UCharCategory) value 3641 * 3642 * @see UCharCategory 3643 * @stable ICU 2.0 3644 */ 3645 U_CAPI int8_t U_EXPORT2 3646 u_charType(UChar32 c); 3647 3648 /** 3649 * Get a single-bit bit set for the general category of a character. 3650 * This bit set can be compared bitwise with U_GC_SM_MASK, U_GC_L_MASK, etc. 3651 * Same as U_MASK(u_charType(c)). 3652 * 3653 * @param c the code point to be tested 3654 * @return a single-bit mask corresponding to the general category (UCharCategory) value 3655 * 3656 * @see u_charType 3657 * @see UCharCategory 3658 * @see U_GC_CN_MASK 3659 * @stable ICU 2.1 3660 */ 3661 #define U_GET_GC_MASK(c) U_MASK(u_charType(c)) 3662 3663 /** 3664 * Callback from u_enumCharTypes(), is called for each contiguous range 3665 * of code points c (where start<=c<limit) 3666 * with the same Unicode general category ("character type"). 3667 * 3668 * The callback function can stop the enumeration by returning false. 3669 * 3670 * @param context an opaque pointer, as passed into utrie_enum() 3671 * @param start the first code point in a contiguous range with value 3672 * @param limit one past the last code point in a contiguous range with value 3673 * @param type the general category for all code points in [start..limit[ 3674 * @return false to stop the enumeration 3675 * 3676 * @stable ICU 2.1 3677 * @see UCharCategory 3678 * @see u_enumCharTypes 3679 */ 3680 typedef UBool U_CALLCONV 3681 UCharEnumTypeRange(const void *context, UChar32 start, UChar32 limit, UCharCategory type); 3682 3683 /** 3684 * Enumerate efficiently all code points with their Unicode general categories. 3685 * 3686 * This is useful for building data structures (e.g., UnicodeSet's), 3687 * for enumerating all assigned code points (type!=U_UNASSIGNED), etc. 3688 * 3689 * For each contiguous range of code points with a given general category ("character type"), 3690 * the UCharEnumTypeRange function is called. 3691 * Adjacent ranges have different types. 3692 * The Unicode Standard guarantees that the numeric value of the type is 0..31. 3693 * 3694 * @param enumRange a pointer to a function that is called for each contiguous range 3695 * of code points with the same general category 3696 * @param context an opaque pointer that is passed on to the callback function 3697 * 3698 * @stable ICU 2.1 3699 * @see UCharCategory 3700 * @see UCharEnumTypeRange 3701 */ 3702 U_CAPI void U_EXPORT2 3703 u_enumCharTypes(UCharEnumTypeRange *enumRange, const void *context); 3704 3705 #if !UCONFIG_NO_NORMALIZATION 3706 3707 /** 3708 * Returns the combining class of the code point as specified in UnicodeData.txt. 3709 * 3710 * @param c the code point of the character 3711 * @return the combining class of the character 3712 * @stable ICU 2.0 3713 */ 3714 U_CAPI uint8_t U_EXPORT2 3715 u_getCombiningClass(UChar32 c); 3716 3717 #endif 3718 3719 /** 3720 * Returns the decimal digit value of a decimal digit character. 3721 * Such characters have the general category "Nd" (decimal digit numbers) 3722 * and a Numeric_Type of Decimal. 3723 * 3724 * Unlike ICU releases before 2.6, no digit values are returned for any 3725 * Han characters because Han number characters are often used with a special 3726 * Chinese-style number format (with characters for powers of 10 in between) 3727 * instead of in decimal-positional notation. 3728 * Unicode 4 explicitly assigns Han number characters the Numeric_Type 3729 * Numeric instead of Decimal. 3730 * See Jitterbug 1483 for more details. 3731 * 3732 * Use u_getIntPropertyValue(c, UCHAR_NUMERIC_TYPE) and u_getNumericValue() 3733 * for complete numeric Unicode properties. 3734 * 3735 * @param c the code point for which to get the decimal digit value 3736 * @return the decimal digit value of c, 3737 * or -1 if c is not a decimal digit character 3738 * 3739 * @see u_getNumericValue 3740 * @stable ICU 2.0 3741 */ 3742 U_CAPI int32_t U_EXPORT2 3743 u_charDigitValue(UChar32 c); 3744 3745 /** 3746 * Returns the Unicode allocation block that contains the character. 3747 * 3748 * @param c the code point to be tested 3749 * @return the block value (UBlockCode) for c 3750 * 3751 * @see UBlockCode 3752 * @stable ICU 2.0 3753 */ 3754 U_CAPI UBlockCode U_EXPORT2 3755 ublock_getCode(UChar32 c); 3756 3757 /** 3758 * Retrieve the name of a Unicode character. 3759 * Depending on <code>nameChoice</code>, the character name written 3760 * into the buffer is the "modern" name or the name that was defined 3761 * in Unicode version 1.0. 3762 * The name contains only "invariant" characters 3763 * like A-Z, 0-9, space, and '-'. 3764 * Unicode 1.0 names are only retrieved if they are different from the modern 3765 * names and if the data file contains the data for them. gennames may or may 3766 * not be called with a command line option to include 1.0 names in unames.dat. 3767 * 3768 * @param code The character (code point) for which to get the name. 3769 * It must be <code>0<=code<=0x10ffff</code>. 3770 * @param nameChoice Selector for which name to get. 3771 * @param buffer Destination address for copying the name. 3772 * The name will always be zero-terminated. 3773 * If there is no name, then the buffer will be set to the empty string. 3774 * @param bufferLength <code>==sizeof(buffer)</code> 3775 * @param pErrorCode Pointer to a UErrorCode variable; 3776 * check for <code>U_SUCCESS()</code> after <code>u_charName()</code> 3777 * returns. 3778 * @return The length of the name, or 0 if there is no name for this character. 3779 * If the bufferLength is less than or equal to the length, then the buffer 3780 * contains the truncated name and the returned length indicates the full 3781 * length of the name. 3782 * The length does not include the zero-termination. 3783 * 3784 * @see UCharNameChoice 3785 * @see u_charFromName 3786 * @see u_enumCharNames 3787 * @stable ICU 2.0 3788 */ 3789 U_CAPI int32_t U_EXPORT2 3790 u_charName(UChar32 code, UCharNameChoice nameChoice, 3791 char *buffer, int32_t bufferLength, 3792 UErrorCode *pErrorCode); 3793 3794 #ifndef U_HIDE_DEPRECATED_API 3795 /** 3796 * Returns an empty string. 3797 * Used to return the ISO 10646 comment for a character. 3798 * The Unicode ISO_Comment property is deprecated and has no values. 3799 * 3800 * @param c The character (code point) for which to get the ISO comment. 3801 * It must be <code>0<=c<=0x10ffff</code>. 3802 * @param dest Destination address for copying the comment. 3803 * The comment will be zero-terminated if possible. 3804 * If there is no comment, then the buffer will be set to the empty string. 3805 * @param destCapacity <code>==sizeof(dest)</code> 3806 * @param pErrorCode Pointer to a UErrorCode variable; 3807 * check for <code>U_SUCCESS()</code> after <code>u_getISOComment()</code> 3808 * returns. 3809 * @return 0 3810 * 3811 * @deprecated ICU 49 3812 */ 3813 U_DEPRECATED int32_t U_EXPORT2 3814 u_getISOComment(UChar32 c, 3815 char *dest, int32_t destCapacity, 3816 UErrorCode *pErrorCode); 3817 #endif /* U_HIDE_DEPRECATED_API */ 3818 3819 /** 3820 * Find a Unicode character by its name and return its code point value. 3821 * The name is matched exactly and completely. 3822 * If the name does not correspond to a code point, <i>pErrorCode</i> 3823 * is set to <code>U_INVALID_CHAR_FOUND</code>. 3824 * A Unicode 1.0 name is matched only if it differs from the modern name. 3825 * Unicode names are all uppercase. Extended names are lowercase followed 3826 * by an uppercase hexadecimal number, and within angle brackets. 3827 * 3828 * @param nameChoice Selector for which name to match. 3829 * @param name The name to match. 3830 * @param pErrorCode Pointer to a UErrorCode variable 3831 * @return The Unicode value of the code point with the given name, 3832 * or an undefined value if there is no such code point. 3833 * 3834 * @see UCharNameChoice 3835 * @see u_charName 3836 * @see u_enumCharNames 3837 * @stable ICU 1.7 3838 */ 3839 U_CAPI UChar32 U_EXPORT2 3840 u_charFromName(UCharNameChoice nameChoice, 3841 const char *name, 3842 UErrorCode *pErrorCode); 3843 3844 /** 3845 * Type of a callback function for u_enumCharNames() that gets called 3846 * for each Unicode character with the code point value and 3847 * the character name. 3848 * If such a function returns false, then the enumeration is stopped. 3849 * 3850 * @param context The context pointer that was passed to u_enumCharNames(). 3851 * @param code The Unicode code point for the character with this name. 3852 * @param nameChoice Selector for which kind of names is enumerated. 3853 * @param name The character's name, zero-terminated. 3854 * @param length The length of the name. 3855 * @return true if the enumeration should continue, false to stop it. 3856 * 3857 * @see UCharNameChoice 3858 * @see u_enumCharNames 3859 * @stable ICU 1.7 3860 */ 3861 typedef UBool U_CALLCONV UEnumCharNamesFn(void *context, 3862 UChar32 code, 3863 UCharNameChoice nameChoice, 3864 const char *name, 3865 int32_t length); 3866 3867 /** 3868 * Enumerate all assigned Unicode characters between the start and limit 3869 * code points (start inclusive, limit exclusive) and call a function 3870 * for each, passing the code point value and the character name. 3871 * For Unicode 1.0 names, only those are enumerated that differ from the 3872 * modern names. 3873 * 3874 * @param start The first code point in the enumeration range. 3875 * @param limit One more than the last code point in the enumeration range 3876 * (the first one after the range). 3877 * @param fn The function that is to be called for each character name. 3878 * @param context An arbitrary pointer that is passed to the function. 3879 * @param nameChoice Selector for which kind of names to enumerate. 3880 * @param pErrorCode Pointer to a UErrorCode variable 3881 * 3882 * @see UCharNameChoice 3883 * @see UEnumCharNamesFn 3884 * @see u_charName 3885 * @see u_charFromName 3886 * @stable ICU 1.7 3887 */ 3888 U_CAPI void U_EXPORT2 3889 u_enumCharNames(UChar32 start, UChar32 limit, 3890 UEnumCharNamesFn *fn, 3891 void *context, 3892 UCharNameChoice nameChoice, 3893 UErrorCode *pErrorCode); 3894 3895 /** 3896 * Return the Unicode name for a given property, as given in the 3897 * Unicode database file PropertyAliases.txt. 3898 * 3899 * In addition, this function maps the property 3900 * UCHAR_GENERAL_CATEGORY_MASK to the synthetic names "gcm" / 3901 * "General_Category_Mask". These names are not in 3902 * PropertyAliases.txt. 3903 * 3904 * @param property UProperty selector other than UCHAR_INVALID_CODE. 3905 * If out of range, NULL is returned. 3906 * 3907 * @param nameChoice selector for which name to get. If out of range, 3908 * NULL is returned. All properties have a long name. Most 3909 * have a short name, but some do not. Unicode allows for 3910 * additional names; if present these will be returned by 3911 * U_LONG_PROPERTY_NAME + i, where i=1, 2,... 3912 * 3913 * @return a pointer to the name, or NULL if either the 3914 * property or the nameChoice is out of range. If a given 3915 * nameChoice returns NULL, then all larger values of 3916 * nameChoice will return NULL, with one exception: if NULL is 3917 * returned for U_SHORT_PROPERTY_NAME, then 3918 * U_LONG_PROPERTY_NAME (and higher) may still return a 3919 * non-NULL value. The returned pointer is valid until 3920 * u_cleanup() is called. 3921 * 3922 * @see UProperty 3923 * @see UPropertyNameChoice 3924 * @stable ICU 2.4 3925 */ 3926 U_CAPI const char* U_EXPORT2 3927 u_getPropertyName(UProperty property, 3928 UPropertyNameChoice nameChoice); 3929 3930 /** 3931 * Return the UProperty enum for a given property name, as specified 3932 * in the Unicode database file PropertyAliases.txt. Short, long, and 3933 * any other variants are recognized. 3934 * 3935 * In addition, this function maps the synthetic names "gcm" / 3936 * "General_Category_Mask" to the property 3937 * UCHAR_GENERAL_CATEGORY_MASK. These names are not in 3938 * PropertyAliases.txt. 3939 * 3940 * @param alias the property name to be matched. The name is compared 3941 * using "loose matching" as described in PropertyAliases.txt. 3942 * 3943 * @return a UProperty enum, or UCHAR_INVALID_CODE if the given name 3944 * does not match any property. 3945 * 3946 * @see UProperty 3947 * @stable ICU 2.4 3948 */ 3949 U_CAPI UProperty U_EXPORT2 3950 u_getPropertyEnum(const char* alias); 3951 3952 /** 3953 * Return the Unicode name for a given property value, as given in the 3954 * Unicode database file PropertyValueAliases.txt. 3955 * 3956 * Note: Some of the names in PropertyValueAliases.txt can only be 3957 * retrieved using UCHAR_GENERAL_CATEGORY_MASK, not 3958 * UCHAR_GENERAL_CATEGORY. These include: "C" / "Other", "L" / 3959 * "Letter", "LC" / "Cased_Letter", "M" / "Mark", "N" / "Number", "P" 3960 * / "Punctuation", "S" / "Symbol", and "Z" / "Separator". 3961 * 3962 * @param property UProperty selector constant. 3963 * Must be UCHAR_BINARY_START<=which<UCHAR_BINARY_LIMIT 3964 * or UCHAR_INT_START<=which<UCHAR_INT_LIMIT 3965 * or UCHAR_MASK_START<=which<UCHAR_MASK_LIMIT. 3966 * If out of range, NULL is returned. 3967 * 3968 * @param value selector for a value for the given property. If out 3969 * of range, NULL is returned. In general, valid values range 3970 * from 0 up to some maximum. There are a few exceptions: 3971 * (1.) UCHAR_BLOCK values begin at the non-zero value 3972 * UBLOCK_BASIC_LATIN. (2.) UCHAR_CANONICAL_COMBINING_CLASS 3973 * values are not contiguous and range from 0..240. (3.) 3974 * UCHAR_GENERAL_CATEGORY_MASK values are not values of 3975 * UCharCategory, but rather mask values produced by 3976 * U_GET_GC_MASK(). This allows grouped categories such as 3977 * [:L:] to be represented. Mask values range 3978 * non-contiguously from 1..U_GC_P_MASK. 3979 * 3980 * @param nameChoice selector for which name to get. If out of range, 3981 * NULL is returned. All values have a long name. Most have 3982 * a short name, but some do not. Unicode allows for 3983 * additional names; if present these will be returned by 3984 * U_LONG_PROPERTY_NAME + i, where i=1, 2,... 3985 3986 * @return a pointer to the name, or NULL if either the 3987 * property or the nameChoice is out of range. If a given 3988 * nameChoice returns NULL, then all larger values of 3989 * nameChoice will return NULL, with one exception: if NULL is 3990 * returned for U_SHORT_PROPERTY_NAME, then 3991 * U_LONG_PROPERTY_NAME (and higher) may still return a 3992 * non-NULL value. The returned pointer is valid until 3993 * u_cleanup() is called. 3994 * 3995 * @see UProperty 3996 * @see UPropertyNameChoice 3997 * @stable ICU 2.4 3998 */ 3999 U_CAPI const char* U_EXPORT2 4000 u_getPropertyValueName(UProperty property, 4001 int32_t value, 4002 UPropertyNameChoice nameChoice); 4003 4004 /** 4005 * Return the property value integer for a given value name, as 4006 * specified in the Unicode database file PropertyValueAliases.txt. 4007 * Short, long, and any other variants are recognized. 4008 * 4009 * Note: Some of the names in PropertyValueAliases.txt will only be 4010 * recognized with UCHAR_GENERAL_CATEGORY_MASK, not 4011 * UCHAR_GENERAL_CATEGORY. These include: "C" / "Other", "L" / 4012 * "Letter", "LC" / "Cased_Letter", "M" / "Mark", "N" / "Number", "P" 4013 * / "Punctuation", "S" / "Symbol", and "Z" / "Separator". 4014 * 4015 * @param property UProperty selector constant. 4016 * Must be UCHAR_BINARY_START<=which<UCHAR_BINARY_LIMIT 4017 * or UCHAR_INT_START<=which<UCHAR_INT_LIMIT 4018 * or UCHAR_MASK_START<=which<UCHAR_MASK_LIMIT. 4019 * If out of range, UCHAR_INVALID_CODE is returned. 4020 * 4021 * @param alias the value name to be matched. The name is compared 4022 * using "loose matching" as described in 4023 * PropertyValueAliases.txt. 4024 * 4025 * @return a value integer or UCHAR_INVALID_CODE if the given name 4026 * does not match any value of the given property, or if the 4027 * property is invalid. Note: UCHAR_GENERAL_CATEGORY_MASK values 4028 * are not values of UCharCategory, but rather mask values 4029 * produced by U_GET_GC_MASK(). This allows grouped 4030 * categories such as [:L:] to be represented. 4031 * 4032 * @see UProperty 4033 * @stable ICU 2.4 4034 */ 4035 U_CAPI int32_t U_EXPORT2 4036 u_getPropertyValueEnum(UProperty property, 4037 const char* alias); 4038 4039 /** 4040 * Determines if the specified character is permissible as the first character in an identifier 4041 * according to UAX #31 Unicode Identifier and Pattern Syntax. 4042 * 4043 * Same as Unicode ID_Start (UCHAR_ID_START). 4044 * 4045 * @param c the code point to be tested 4046 * @return true if the code point may start an identifier 4047 * 4048 * @see UCHAR_ID_START 4049 * @see u_isalpha 4050 * @see u_isIDPart 4051 * @stable ICU 2.0 4052 */ 4053 U_CAPI UBool U_EXPORT2 4054 u_isIDStart(UChar32 c); 4055 4056 /** 4057 * Determines if the specified character is permissible as a non-initial character of an identifier 4058 * according to UAX #31 Unicode Identifier and Pattern Syntax. 4059 * 4060 * Same as Unicode ID_Continue (UCHAR_ID_CONTINUE). 4061 * 4062 * @param c the code point to be tested 4063 * @return true if the code point may occur as a non-initial character of an identifier 4064 * 4065 * @see UCHAR_ID_CONTINUE 4066 * @see u_isIDStart 4067 * @see u_isIDIgnorable 4068 * @stable ICU 2.0 4069 */ 4070 U_CAPI UBool U_EXPORT2 4071 u_isIDPart(UChar32 c); 4072 4073 /** 4074 * Does the set of Identifier_Type values code point c contain the given type? 4075 * 4076 * Used for UTS #39 General Security Profile for Identifiers 4077 * (https://www.unicode.org/reports/tr39/#General_Security_Profile). 4078 * 4079 * Each code point maps to a <i>set</i> of UIdentifierType values. 4080 * 4081 * @param c code point 4082 * @param type Identifier_Type to check 4083 * @return true if type is in Identifier_Type(c) 4084 * @stable ICU 75 4085 */ 4086 U_CAPI bool U_EXPORT2 4087 u_hasIDType(UChar32 c, UIdentifierType type); 4088 4089 /** 4090 * Writes code point c's Identifier_Type as a list of UIdentifierType values 4091 * to the output types array and returns the number of types. 4092 * 4093 * Used for UTS #39 General Security Profile for Identifiers 4094 * (https://www.unicode.org/reports/tr39/#General_Security_Profile). 4095 * 4096 * Each code point maps to a <i>set</i> of UIdentifierType values. 4097 * There is always at least one type. 4098 * The order of output values is undefined. 4099 * Each type is output at most once; 4100 * there cannot be more output values than UIdentifierType constants. 4101 * In addition, only some of the types can be combined with others, 4102 * and usually only a small number of types occur together. 4103 * Future versions might add additional types. 4104 * See UTS #39 and its data files for details. 4105 * 4106 * If there are more than capacity types to be written, then 4107 * U_BUFFER_OVERFLOW_ERROR is set and the number of types is returned. 4108 * (Usual ICU buffer handling behavior.) 4109 * 4110 * @param c code point 4111 * @param types output array 4112 * @param capacity capacity of the array 4113 * @param pErrorCode Standard ICU error code. Its input value must 4114 * pass the U_SUCCESS() test, or else the function returns 4115 * immediately. Check for U_FAILURE() on output or use with 4116 * function chaining. (See User Guide for details.) 4117 * @return number of values in c's Identifier_Type, 4118 * written to types unless U_BUFFER_OVERFLOW_ERROR indicates insufficient capacity 4119 * @stable ICU 75 4120 */ 4121 U_CAPI int32_t U_EXPORT2 4122 u_getIDTypes(UChar32 c, UIdentifierType *types, int32_t capacity, UErrorCode *pErrorCode); 4123 4124 /** 4125 * Determines if the specified character should be regarded 4126 * as an ignorable character in an identifier, 4127 * according to Java. 4128 * True for characters with general category "Cf" (format controls) as well as 4129 * non-whitespace ISO controls 4130 * (U+0000..U+0008, U+000E..U+001B, U+007F..U+009F). 4131 * 4132 * Same as java.lang.Character.isIdentifierIgnorable(). 4133 * 4134 * Note that Unicode just recommends to ignore Cf (format controls). 4135 * 4136 * @param c the code point to be tested 4137 * @return true if the code point is ignorable in identifiers according to Java 4138 * 4139 * @see UCHAR_DEFAULT_IGNORABLE_CODE_POINT 4140 * @see u_isIDStart 4141 * @see u_isIDPart 4142 * @stable ICU 2.0 4143 */ 4144 U_CAPI UBool U_EXPORT2 4145 u_isIDIgnorable(UChar32 c); 4146 4147 /** 4148 * Determines if the specified character is permissible as the 4149 * first character in a Java identifier. 4150 * In addition to u_isIDStart(c), true for characters with 4151 * general categories "Sc" (currency symbols) and "Pc" (connecting punctuation). 4152 * 4153 * Same as java.lang.Character.isJavaIdentifierStart(). 4154 * 4155 * @param c the code point to be tested 4156 * @return true if the code point may start a Java identifier 4157 * 4158 * @see u_isJavaIDPart 4159 * @see u_isalpha 4160 * @see u_isIDStart 4161 * @stable ICU 2.0 4162 */ 4163 U_CAPI UBool U_EXPORT2 4164 u_isJavaIDStart(UChar32 c); 4165 4166 /** 4167 * Determines if the specified character is permissible 4168 * in a Java identifier. 4169 * In addition to u_isIDPart(c), true for characters with 4170 * general category "Sc" (currency symbols). 4171 * 4172 * Same as java.lang.Character.isJavaIdentifierPart(). 4173 * 4174 * @param c the code point to be tested 4175 * @return true if the code point may occur in a Java identifier 4176 * 4177 * @see u_isIDIgnorable 4178 * @see u_isJavaIDStart 4179 * @see u_isalpha 4180 * @see u_isdigit 4181 * @see u_isIDPart 4182 * @stable ICU 2.0 4183 */ 4184 U_CAPI UBool U_EXPORT2 4185 u_isJavaIDPart(UChar32 c); 4186 4187 /** 4188 * The given character is mapped to its lowercase equivalent according to 4189 * UnicodeData.txt; if the character has no lowercase equivalent, the character 4190 * itself is returned. 4191 * 4192 * Same as java.lang.Character.toLowerCase(). 4193 * 4194 * This function only returns the simple, single-code point case mapping. 4195 * Full case mappings should be used whenever possible because they produce 4196 * better results by working on whole strings. 4197 * They take into account the string context and the language and can map 4198 * to a result string with a different length as appropriate. 4199 * Full case mappings are applied by the string case mapping functions, 4200 * see ustring.h and the UnicodeString class. 4201 * See also the User Guide chapter on C/POSIX migration: 4202 * https://unicode-org.github.io/icu/userguide/icu/posix#case-mappings 4203 * 4204 * @param c the code point to be mapped 4205 * @return the Simple_Lowercase_Mapping of the code point, if any; 4206 * otherwise the code point itself. 4207 * @stable ICU 2.0 4208 */ 4209 U_CAPI UChar32 U_EXPORT2 4210 u_tolower(UChar32 c); 4211 4212 /** 4213 * The given character is mapped to its uppercase equivalent according to UnicodeData.txt; 4214 * if the character has no uppercase equivalent, the character itself is 4215 * returned. 4216 * 4217 * Same as java.lang.Character.toUpperCase(). 4218 * 4219 * This function only returns the simple, single-code point case mapping. 4220 * Full case mappings should be used whenever possible because they produce 4221 * better results by working on whole strings. 4222 * They take into account the string context and the language and can map 4223 * to a result string with a different length as appropriate. 4224 * Full case mappings are applied by the string case mapping functions, 4225 * see ustring.h and the UnicodeString class. 4226 * See also the User Guide chapter on C/POSIX migration: 4227 * https://unicode-org.github.io/icu/userguide/icu/posix#case-mappings 4228 * 4229 * @param c the code point to be mapped 4230 * @return the Simple_Uppercase_Mapping of the code point, if any; 4231 * otherwise the code point itself. 4232 * @stable ICU 2.0 4233 */ 4234 U_CAPI UChar32 U_EXPORT2 4235 u_toupper(UChar32 c); 4236 4237 /** 4238 * The given character is mapped to its titlecase equivalent 4239 * according to UnicodeData.txt; 4240 * if none is defined, the character itself is returned. 4241 * 4242 * Same as java.lang.Character.toTitleCase(). 4243 * 4244 * This function only returns the simple, single-code point case mapping. 4245 * Full case mappings should be used whenever possible because they produce 4246 * better results by working on whole strings. 4247 * They take into account the string context and the language and can map 4248 * to a result string with a different length as appropriate. 4249 * Full case mappings are applied by the string case mapping functions, 4250 * see ustring.h and the UnicodeString class. 4251 * See also the User Guide chapter on C/POSIX migration: 4252 * https://unicode-org.github.io/icu/userguide/icu/posix#case-mappings 4253 * 4254 * @param c the code point to be mapped 4255 * @return the Simple_Titlecase_Mapping of the code point, if any; 4256 * otherwise the code point itself. 4257 * @stable ICU 2.0 4258 */ 4259 U_CAPI UChar32 U_EXPORT2 4260 u_totitle(UChar32 c); 4261 4262 /** 4263 * The given character is mapped to its case folding equivalent according to 4264 * UnicodeData.txt and CaseFolding.txt; 4265 * if the character has no case folding equivalent, the character 4266 * itself is returned. 4267 * 4268 * This function only returns the simple, single-code point case mapping. 4269 * Full case mappings should be used whenever possible because they produce 4270 * better results by working on whole strings. 4271 * They take into account the string context and the language and can map 4272 * to a result string with a different length as appropriate. 4273 * Full case mappings are applied by the string case mapping functions, 4274 * see ustring.h and the UnicodeString class. 4275 * See also the User Guide chapter on C/POSIX migration: 4276 * https://unicode-org.github.io/icu/userguide/icu/posix#case-mappings 4277 * 4278 * @param c the code point to be mapped 4279 * @param options Either U_FOLD_CASE_DEFAULT or U_FOLD_CASE_EXCLUDE_SPECIAL_I 4280 * @return the Simple_Case_Folding of the code point, if any; 4281 * otherwise the code point itself. 4282 * @stable ICU 2.0 4283 */ 4284 U_CAPI UChar32 U_EXPORT2 4285 u_foldCase(UChar32 c, uint32_t options); 4286 4287 /** 4288 * Returns the decimal digit value of the code point in the 4289 * specified radix. 4290 * 4291 * If the radix is not in the range <code>2<=radix<=36</code> or if the 4292 * value of <code>c</code> is not a valid digit in the specified 4293 * radix, <code>-1</code> is returned. A character is a valid digit 4294 * if at least one of the following is true: 4295 * <ul> 4296 * <li>The character has a decimal digit value. 4297 * Such characters have the general category "Nd" (decimal digit numbers) 4298 * and a Numeric_Type of Decimal. 4299 * In this case the value is the character's decimal digit value.</li> 4300 * <li>The character is one of the uppercase Latin letters 4301 * <code>'A'</code> through <code>'Z'</code>. 4302 * In this case the value is <code>c-'A'+10</code>.</li> 4303 * <li>The character is one of the lowercase Latin letters 4304 * <code>'a'</code> through <code>'z'</code>. 4305 * In this case the value is <code>ch-'a'+10</code>.</li> 4306 * <li>Latin letters from both the ASCII range (0061..007A, 0041..005A) 4307 * as well as from the Fullwidth ASCII range (FF41..FF5A, FF21..FF3A) 4308 * are recognized.</li> 4309 * </ul> 4310 * 4311 * Same as java.lang.Character.digit(). 4312 * 4313 * @param ch the code point to be tested. 4314 * @param radix the radix. 4315 * @return the numeric value represented by the character in the 4316 * specified radix, 4317 * or -1 if there is no value or if the value exceeds the radix. 4318 * 4319 * @see UCHAR_NUMERIC_TYPE 4320 * @see u_forDigit 4321 * @see u_charDigitValue 4322 * @see u_isdigit 4323 * @stable ICU 2.0 4324 */ 4325 U_CAPI int32_t U_EXPORT2 4326 u_digit(UChar32 ch, int8_t radix); 4327 4328 /** 4329 * Determines the character representation for a specific digit in 4330 * the specified radix. If the value of <code>radix</code> is not a 4331 * valid radix, or the value of <code>digit</code> is not a valid 4332 * digit in the specified radix, the null character 4333 * (<code>U+0000</code>) is returned. 4334 * <p> 4335 * The <code>radix</code> argument is valid if it is greater than or 4336 * equal to 2 and less than or equal to 36. 4337 * The <code>digit</code> argument is valid if 4338 * <code>0 <= digit < radix</code>. 4339 * <p> 4340 * If the digit is less than 10, then 4341 * <code>'0' + digit</code> is returned. Otherwise, the value 4342 * <code>'a' + digit - 10</code> is returned. 4343 * 4344 * Same as java.lang.Character.forDigit(). 4345 * 4346 * @param digit the number to convert to a character. 4347 * @param radix the radix. 4348 * @return the <code>char</code> representation of the specified digit 4349 * in the specified radix. 4350 * 4351 * @see u_digit 4352 * @see u_charDigitValue 4353 * @see u_isdigit 4354 * @stable ICU 2.0 4355 */ 4356 U_CAPI UChar32 U_EXPORT2 4357 u_forDigit(int32_t digit, int8_t radix); 4358 4359 /** 4360 * Get the "age" of the code point. 4361 * The "age" is the Unicode version when the code point was first 4362 * designated (as a non-character or for Private Use) 4363 * or assigned a character. 4364 * This can be useful to avoid emitting code points to receiving 4365 * processes that do not accept newer characters. 4366 * The data is from the UCD file DerivedAge.txt. 4367 * 4368 * @param c The code point. 4369 * @param versionArray The Unicode version number array, to be filled in. 4370 * 4371 * @stable ICU 2.1 4372 */ 4373 U_CAPI void U_EXPORT2 4374 u_charAge(UChar32 c, UVersionInfo versionArray); 4375 4376 /** 4377 * Gets the Unicode version information. 4378 * The version array is filled in with the version information 4379 * for the Unicode standard that is currently used by ICU. 4380 * For example, Unicode version 3.1.1 is represented as an array with 4381 * the values { 3, 1, 1, 0 }. 4382 * 4383 * @param versionArray an output array that will be filled in with 4384 * the Unicode version number 4385 * @stable ICU 2.0 4386 */ 4387 U_CAPI void U_EXPORT2 4388 u_getUnicodeVersion(UVersionInfo versionArray); 4389 4390 #if !UCONFIG_NO_NORMALIZATION 4391 /** 4392 * Get the FC_NFKC_Closure property string for a character. 4393 * See Unicode Standard Annex #15 for details, search for "FC_NFKC_Closure" 4394 * or for "FNC": http://www.unicode.org/reports/tr15/ 4395 * 4396 * @param c The character (code point) for which to get the FC_NFKC_Closure string. 4397 * It must be <code>0<=c<=0x10ffff</code>. 4398 * @param dest Destination address for copying the string. 4399 * The string will be zero-terminated if possible. 4400 * If there is no FC_NFKC_Closure string, 4401 * then the buffer will be set to the empty string. 4402 * @param destCapacity <code>==sizeof(dest)</code> 4403 * @param pErrorCode Pointer to a UErrorCode variable. 4404 * @return The length of the string, or 0 if there is no FC_NFKC_Closure string for this character. 4405 * If the destCapacity is less than or equal to the length, then the buffer 4406 * contains the truncated name and the returned length indicates the full 4407 * length of the name. 4408 * The length does not include the zero-termination. 4409 * 4410 * @stable ICU 2.2 4411 */ 4412 U_CAPI int32_t U_EXPORT2 4413 u_getFC_NFKC_Closure(UChar32 c, UChar *dest, int32_t destCapacity, UErrorCode *pErrorCode); 4414 4415 #endif 4416 4417 4418 U_CDECL_END 4419 4420 #endif /*_UCHAR*/ 4421 /*eof*/