Where Online Learning is simpler!
The C and C++ Include Header Files
/usr/include/unicode/uchar.h
$ cat -n /usr/include/unicode/uchar.h 1 // © 2016 and later: Unicode, Inc. and others. 2 // License & terms of use: http://www.unicode.org/copyright.html 3 /* 4 ********************************************************************** 5 * Copyright (C) 1997-2016, International Business Machines 6 * Corporation and others. All Rights Reserved. 7 ********************************************************************** 8 * 9 * File UCHAR.H 10 * 11 * Modification History: 12 * 13 * Date Name Description 14 * 04/02/97 aliu Creation. 15 * 03/29/99 helena Updated for C APIs. 16 * 4/15/99 Madhu Updated for C Implementation and Javadoc 17 * 5/20/99 Madhu Added the function u_getVersion() 18 * 8/19/1999 srl Upgraded scripts to Unicode 3.0 19 * 8/27/1999 schererm UCharDirection constants: U_... 20 * 11/11/1999 weiv added u_isalnum(), cleaned comments 21 * 01/11/2000 helena Renamed u_getVersion to u_getUnicodeVersion(). 22 ****************************************************************************** 23 */ 24 25 #ifndef UCHAR_H 26 #define UCHAR_H 27 28 #include "unicode/utypes.h" 29 #include "unicode/stringoptions.h" 30 #include "unicode/ucpmap.h" 31 32 #if !defined(USET_DEFINED) && !defined(U_IN_DOXYGEN) 33 34 #define USET_DEFINED 35 36 /** 37 * USet is the C API type corresponding to C++ class UnicodeSet. 38 * It is forward-declared here to avoid including unicode/uset.h file if related 39 * APIs are not used. 40 * 41 * @see ucnv_getUnicodeSet 42 * @stable ICU 2.4 43 */ 44 typedef struct USet USet; 45 46 #endif 47 48 49 U_CDECL_BEGIN 50 51 /*==========================================================================*/ 52 /* Unicode version number */ 53 /*==========================================================================*/ 54 /** 55 * Unicode version number, default for the current ICU version. 56 * The actual Unicode Character Database (UCD) data is stored in uprops.dat 57 * and may be generated from UCD files from a different Unicode version. 58 * Call u_getUnicodeVersion to get the actual Unicode version of the data. 59 * 60 * @see u_getUnicodeVersion 61 * @stable ICU 2.0 62 */ 63 #define U_UNICODE_VERSION "15.1" 64 65 /** 66 * \file 67 * \brief C API: Unicode Properties 68 * 69 * This C API provides low-level access to the Unicode Character Database. 70 * In addition to raw property values, some convenience functions calculate 71 * derived properties, for example for Java-style programming. 72 * 73 * Unicode assigns each code point (not just assigned character) values for 74 * many properties. 75 * Most of them are simple boolean flags, or constants from a small enumerated list. 76 * For some properties, values are strings or other relatively more complex types. 77 * 78 * For more information see 79 * "About the Unicode Character Database" (http://www.unicode.org/ucd/) 80 * and the ICU User Guide chapter on Properties (https://unicode-org.github.io/icu/userguide/strings/properties). 81 * 82 * Many properties are accessible via generic functions that take a UProperty selector. 83 * - u_hasBinaryProperty() returns a binary value (true/false) per property and code point. 84 * - u_getIntPropertyValue() returns an integer value per property and code point. 85 * For each supported enumerated or catalog property, there is 86 * an enum type for all of the property's values, and 87 * u_getIntPropertyValue() returns the numeric values of those constants. 88 * - u_getBinaryPropertySet() returns a set for each ICU-supported binary property with 89 * all code points for which the property is true. 90 * - u_getIntPropertyMap() returns a map for each 91 * ICU-supported enumerated/catalog/int-valued property which 92 * maps all Unicode code points to their values for that property. 93 * 94 * Many functions are designed to match java.lang.Character functions. 95 * See the individual function documentation, 96 * and see the JDK 1.4 java.lang.Character documentation 97 * at http://java.sun.com/j2se/1.4/docs/api/java/lang/Character.html 98 * 99 * There are also functions that provide easy migration from C/POSIX functions 100 * like isblank(). Their use is generally discouraged because the C/POSIX 101 * standards do not define their semantics beyond the ASCII range, which means 102 * that different implementations exhibit very different behavior. 103 * Instead, Unicode properties should be used directly. 104 * 105 * There are also only a few, broad C/POSIX character classes, and they tend 106 * to be used for conflicting purposes. For example, the "isalpha()" class 107 * is sometimes used to determine word boundaries, while a more sophisticated 108 * approach would at least distinguish initial letters from continuation 109 * characters (the latter including combining marks). 110 * (In ICU, BreakIterator is the most sophisticated API for word boundaries.) 111 * Another example: There is no "istitle()" class for titlecase characters. 112 * 113 * ICU 3.4 and later provides API access for all twelve C/POSIX character classes. 114 * ICU implements them according to the Standard Recommendations in 115 * Annex C: Compatibility Properties of UTS #18 Unicode Regular Expressions 116 * (http://www.unicode.org/reports/tr18/#Compatibility_Properties). 117 * 118 * API access for C/POSIX character classes is as follows: 119 * - alpha: u_isUAlphabetic(c) or u_hasBinaryProperty(c, UCHAR_ALPHABETIC) 120 * - lower: u_isULowercase(c) or u_hasBinaryProperty(c, UCHAR_LOWERCASE) 121 * - upper: u_isUUppercase(c) or u_hasBinaryProperty(c, UCHAR_UPPERCASE) 122 * - punct: u_ispunct(c) 123 * - digit: u_isdigit(c) or u_charType(c)==U_DECIMAL_DIGIT_NUMBER 124 * - xdigit: u_isxdigit(c) or u_hasBinaryProperty(c, UCHAR_POSIX_XDIGIT) 125 * - alnum: u_hasBinaryProperty(c, UCHAR_POSIX_ALNUM) 126 * - space: u_isUWhiteSpace(c) or u_hasBinaryProperty(c, UCHAR_WHITE_SPACE) 127 * - blank: u_isblank(c) or u_hasBinaryProperty(c, UCHAR_POSIX_BLANK) 128 * - cntrl: u_charType(c)==U_CONTROL_CHAR 129 * - graph: u_hasBinaryProperty(c, UCHAR_POSIX_GRAPH) 130 * - print: u_hasBinaryProperty(c, UCHAR_POSIX_PRINT) 131 * 132 * Note: Some of the u_isxyz() functions in uchar.h predate, and do not match, 133 * the Standard Recommendations in UTS #18. Instead, they match Java 134 * functions according to their API documentation. 135 * 136 * \htmlonly 137 * The C/POSIX character classes are also available in UnicodeSet patterns, 138 * using patterns like [:graph:] or \p{graph}. 139 * \endhtmlonly 140 * 141 * Note: There are several ICU whitespace functions. 142 * Comparison: 143 * - u_isUWhiteSpace=UCHAR_WHITE_SPACE: Unicode White_Space property; 144 * most of general categories "Z" (separators) + most whitespace ISO controls 145 * (including no-break spaces, but excluding IS1..IS4) 146 * - u_isWhitespace: Java isWhitespace; Z + whitespace ISO controls but excluding no-break spaces 147 * - u_isJavaSpaceChar: Java isSpaceChar; just Z (including no-break spaces) 148 * - u_isspace: Z + whitespace ISO controls (including no-break spaces) 149 * - u_isblank: "horizontal spaces" = TAB + Zs 150 */ 151 152 /** 153 * Constants. 154 */ 155 156 /** The lowest Unicode code point value. Code points are non-negative. @stable ICU 2.0 */ 157 #define UCHAR_MIN_VALUE 0 158 159 /** 160 * The highest Unicode code point value (scalar value) according to 161 * The Unicode Standard. This is a 21-bit value (20.1 bits, rounded up). 162 * For a single character, UChar32 is a simple type that can hold any code point value. 163 * 164 * @see UChar32 165 * @stable ICU 2.0 166 */ 167 #define UCHAR_MAX_VALUE 0x10ffff 168 169 /** 170 * Get a single-bit bit set (a flag) from a bit number 0..31. 171 * @stable ICU 2.1 172 */ 173 #define U_MASK(x) ((uint32_t)1<<(x)) 174 175 /** 176 * Selection constants for Unicode properties. 177 * These constants are used in functions like u_hasBinaryProperty to select 178 * one of the Unicode properties. 179 * 180 * The properties APIs are intended to reflect Unicode properties as defined 181 * in the Unicode Character Database (UCD) and Unicode Technical Reports (UTR). 182 * 183 * For details about the properties see 184 * UAX #44: Unicode Character Database (http://www.unicode.org/reports/tr44/). 185 * 186 * Important: If ICU is built with UCD files from Unicode versions below, e.g., 3.2, 187 * then properties marked with "new in Unicode 3.2" are not or not fully available. 188 * Check u_getUnicodeVersion to be sure. 189 * 190 * @see u_hasBinaryProperty 191 * @see u_getIntPropertyValue 192 * @see u_getUnicodeVersion 193 * @stable ICU 2.1 194 */ 195 typedef enum UProperty { 196 /* 197 * Note: UProperty constants are parsed by preparseucd.py. 198 * It matches lines like 199 * UCHAR_<Unicode property name>=<integer>, 200 */ 201 202 /* Note: Place UCHAR_ALPHABETIC before UCHAR_BINARY_START so that 203 debuggers display UCHAR_ALPHABETIC as the symbolic name for 0, 204 rather than UCHAR_BINARY_START. Likewise for other *_START 205 identifiers. */ 206 207 /** Binary property Alphabetic. Same as u_isUAlphabetic, different from u_isalpha. 208 Lu+Ll+Lt+Lm+Lo+Nl+Other_Alphabetic @stable ICU 2.1 */ 209 UCHAR_ALPHABETIC=0, 210 /** First constant for binary Unicode properties. @stable ICU 2.1 */ 211 UCHAR_BINARY_START=UCHAR_ALPHABETIC, 212 /** Binary property ASCII_Hex_Digit. 0-9 A-F a-f @stable ICU 2.1 */ 213 UCHAR_ASCII_HEX_DIGIT=1, 214 /** Binary property Bidi_Control. 215 Format controls which have specific functions 216 in the Bidi Algorithm. @stable ICU 2.1 */ 217 UCHAR_BIDI_CONTROL=2, 218 /** Binary property Bidi_Mirrored. 219 Characters that may change display in RTL text. 220 Same as u_isMirrored. 221 See Bidi Algorithm, UTR 9. @stable ICU 2.1 */ 222 UCHAR_BIDI_MIRRORED=3, 223 /** Binary property Dash. Variations of dashes. @stable ICU 2.1 */ 224 UCHAR_DASH=4, 225 /** Binary property Default_Ignorable_Code_Point (new in Unicode 3.2). 226 Ignorable in most processing. 227 <2060..206F, FFF0..FFFB, E0000..E0FFF>+Other_Default_Ignorable_Code_Point+(Cf+Cc+Cs-White_Space) @stable ICU 2.1 */ 228 UCHAR_DEFAULT_IGNORABLE_CODE_POINT=5, 229 /** Binary property Deprecated (new in Unicode 3.2). 230 The usage of deprecated characters is strongly discouraged. @stable ICU 2.1 */ 231 UCHAR_DEPRECATED=6, 232 /** Binary property Diacritic. Characters that linguistically modify 233 the meaning of another character to which they apply. @stable ICU 2.1 */ 234 UCHAR_DIACRITIC=7, 235 /** Binary property Extender. 236 Extend the value or shape of a preceding alphabetic character, 237 e.g., length and iteration marks. @stable ICU 2.1 */ 238 UCHAR_EXTENDER=8, 239 /** Binary property Full_Composition_Exclusion. 240 CompositionExclusions.txt+Singleton Decompositions+ 241 Non-Starter Decompositions. @stable ICU 2.1 */ 242 UCHAR_FULL_COMPOSITION_EXCLUSION=9, 243 /** Binary property Grapheme_Base (new in Unicode 3.2). 244 For programmatic determination of grapheme cluster boundaries. 245 [0..10FFFF]-Cc-Cf-Cs-Co-Cn-Zl-Zp-Grapheme_Link-Grapheme_Extend-CGJ @stable ICU 2.1 */ 246 UCHAR_GRAPHEME_BASE=10, 247 /** Binary property Grapheme_Extend (new in Unicode 3.2). 248 For programmatic determination of grapheme cluster boundaries. 249 Me+Mn+Mc+Other_Grapheme_Extend-Grapheme_Link-CGJ @stable ICU 2.1 */ 250 UCHAR_GRAPHEME_EXTEND=11, 251 /** Binary property Grapheme_Link (new in Unicode 3.2). 252 For programmatic determination of grapheme cluster boundaries. @stable ICU 2.1 */ 253 UCHAR_GRAPHEME_LINK=12, 254 /** Binary property Hex_Digit. 255 Characters commonly used for hexadecimal numbers. @stable ICU 2.1 */ 256 UCHAR_HEX_DIGIT=13, 257 /** Binary property Hyphen. Dashes used to mark connections 258 between pieces of words, plus the Katakana middle dot. @stable ICU 2.1 */ 259 UCHAR_HYPHEN=14, 260 /** Binary property ID_Continue. 261 Characters that can continue an identifier. 262 DerivedCoreProperties.txt also says "NOTE: Cf characters should be filtered out." 263 ID_Start+Mn+Mc+Nd+Pc @stable ICU 2.1 */ 264 UCHAR_ID_CONTINUE=15, 265 /** Binary property ID_Start. 266 Characters that can start an identifier. 267 Lu+Ll+Lt+Lm+Lo+Nl @stable ICU 2.1 */ 268 UCHAR_ID_START=16, 269 /** Binary property Ideographic. 270 CJKV ideographs. @stable ICU 2.1 */ 271 UCHAR_IDEOGRAPHIC=17, 272 /** Binary property IDS_Binary_Operator (new in Unicode 3.2). 273 For programmatic determination of 274 Ideographic Description Sequences. @stable ICU 2.1 */ 275 UCHAR_IDS_BINARY_OPERATOR=18, 276 /** Binary property IDS_Trinary_Operator (new in Unicode 3.2). 277 For programmatic determination of 278 Ideographic Description Sequences. @stable ICU 2.1 */ 279 UCHAR_IDS_TRINARY_OPERATOR=19, 280 /** Binary property Join_Control. 281 Format controls for cursive joining and ligation. @stable ICU 2.1 */ 282 UCHAR_JOIN_CONTROL=20, 283 /** Binary property Logical_Order_Exception (new in Unicode 3.2). 284 Characters that do not use logical order and 285 require special handling in most processing. @stable ICU 2.1 */ 286 UCHAR_LOGICAL_ORDER_EXCEPTION=21, 287 /** Binary property Lowercase. Same as u_isULowercase, different from u_islower. 288 Ll+Other_Lowercase @stable ICU 2.1 */ 289 UCHAR_LOWERCASE=22, 290 /** Binary property Math. Sm+Other_Math @stable ICU 2.1 */ 291 UCHAR_MATH=23, 292 /** Binary property Noncharacter_Code_Point. 293 Code points that are explicitly defined as illegal 294 for the encoding of characters. @stable ICU 2.1 */ 295 UCHAR_NONCHARACTER_CODE_POINT=24, 296 /** Binary property Quotation_Mark. @stable ICU 2.1 */ 297 UCHAR_QUOTATION_MARK=25, 298 /** Binary property Radical (new in Unicode 3.2). 299 For programmatic determination of 300 Ideographic Description Sequences. @stable ICU 2.1 */ 301 UCHAR_RADICAL=26, 302 /** Binary property Soft_Dotted (new in Unicode 3.2). 303 Characters with a "soft dot", like i or j. 304 An accent placed on these characters causes 305 the dot to disappear. @stable ICU 2.1 */ 306 UCHAR_SOFT_DOTTED=27, 307 /** Binary property Terminal_Punctuation. 308 Punctuation characters that generally mark 309 the end of textual units. @stable ICU 2.1 */ 310 UCHAR_TERMINAL_PUNCTUATION=28, 311 /** Binary property Unified_Ideograph (new in Unicode 3.2). 312 For programmatic determination of 313 Ideographic Description Sequences. @stable ICU 2.1 */ 314 UCHAR_UNIFIED_IDEOGRAPH=29, 315 /** Binary property Uppercase. Same as u_isUUppercase, different from u_isupper. 316 Lu+Other_Uppercase @stable ICU 2.1 */ 317 UCHAR_UPPERCASE=30, 318 /** Binary property White_Space. 319 Same as u_isUWhiteSpace, different from u_isspace and u_isWhitespace. 320 Space characters+TAB+CR+LF-ZWSP-ZWNBSP @stable ICU 2.1 */ 321 UCHAR_WHITE_SPACE=31, 322 /** Binary property XID_Continue. 323 ID_Continue modified to allow closure under 324 normalization forms NFKC and NFKD. @stable ICU 2.1 */ 325 UCHAR_XID_CONTINUE=32, 326 /** Binary property XID_Start. ID_Start modified to allow 327 closure under normalization forms NFKC and NFKD. @stable ICU 2.1 */ 328 UCHAR_XID_START=33, 329 /** Binary property Case_Sensitive. Either the source of a case 330 mapping or _in_ the target of a case mapping. Not the same as 331 the general category Cased_Letter. @stable ICU 2.6 */ 332 UCHAR_CASE_SENSITIVE=34, 333 /** Binary property STerm (new in Unicode 4.0.1). 334 Sentence Terminal. Used in UAX #29: Text Boundaries 335 (http://www.unicode.org/reports/tr29/) 336 @stable ICU 3.0 */ 337 UCHAR_S_TERM=35, 338 /** Binary property Variation_Selector (new in Unicode 4.0.1). 339 Indicates all those characters that qualify as Variation Selectors. 340 For details on the behavior of these characters, 341 see StandardizedVariants.html and 15.6 Variation Selectors. 342 @stable ICU 3.0 */ 343 UCHAR_VARIATION_SELECTOR=36, 344 /** Binary property NFD_Inert. 345 ICU-specific property for characters that are inert under NFD, 346 i.e., they do not interact with adjacent characters. 347 See the documentation for the Normalizer2 class and the 348 Normalizer2::isInert() method. 349 @stable ICU 3.0 */ 350 UCHAR_NFD_INERT=37, 351 /** Binary property NFKD_Inert. 352 ICU-specific property for characters that are inert under NFKD, 353 i.e., they do not interact with adjacent characters. 354 See the documentation for the Normalizer2 class and the 355 Normalizer2::isInert() method. 356 @stable ICU 3.0 */ 357 UCHAR_NFKD_INERT=38, 358 /** Binary property NFC_Inert. 359 ICU-specific property for characters that are inert under NFC, 360 i.e., they do not interact with adjacent characters. 361 See the documentation for the Normalizer2 class and the 362 Normalizer2::isInert() method. 363 @stable ICU 3.0 */ 364 UCHAR_NFC_INERT=39, 365 /** Binary property NFKC_Inert. 366 ICU-specific property for characters that are inert under NFKC, 367 i.e., they do not interact with adjacent characters. 368 See the documentation for the Normalizer2 class and the 369 Normalizer2::isInert() method. 370 @stable ICU 3.0 */ 371 UCHAR_NFKC_INERT=40, 372 /** Binary Property Segment_Starter. 373 ICU-specific property for characters that are starters in terms of 374 Unicode normalization and combining character sequences. 375 They have ccc=0 and do not occur in non-initial position of the 376 canonical decomposition of any character 377 (like a-umlaut in NFD and a Jamo T in an NFD(Hangul LVT)). 378 ICU uses this property for segmenting a string for generating a set of 379 canonically equivalent strings, e.g. for canonical closure while 380 processing collation tailoring rules. 381 @stable ICU 3.0 */ 382 UCHAR_SEGMENT_STARTER=41, 383 /** Binary property Pattern_Syntax (new in Unicode 4.1). 384 See UAX #31 Identifier and Pattern Syntax 385 (http://www.unicode.org/reports/tr31/) 386 @stable ICU 3.4 */ 387 UCHAR_PATTERN_SYNTAX=42, 388 /** Binary property Pattern_White_Space (new in Unicode 4.1). 389 See UAX #31 Identifier and Pattern Syntax 390 (http://www.unicode.org/reports/tr31/) 391 @stable ICU 3.4 */ 392 UCHAR_PATTERN_WHITE_SPACE=43, 393 /** Binary property alnum (a C/POSIX character class). 394 Implemented according to the UTS #18 Annex C Standard Recommendation. 395 See the uchar.h file documentation. 396 @stable ICU 3.4 */ 397 UCHAR_POSIX_ALNUM=44, 398 /** Binary property blank (a C/POSIX character class). 399 Implemented according to the UTS #18 Annex C Standard Recommendation. 400 See the uchar.h file documentation. 401 @stable ICU 3.4 */ 402 UCHAR_POSIX_BLANK=45, 403 /** Binary property graph (a C/POSIX character class). 404 Implemented according to the UTS #18 Annex C Standard Recommendation. 405 See the uchar.h file documentation. 406 @stable ICU 3.4 */ 407 UCHAR_POSIX_GRAPH=46, 408 /** Binary property print (a C/POSIX character class). 409 Implemented according to the UTS #18 Annex C Standard Recommendation. 410 See the uchar.h file documentation. 411 @stable ICU 3.4 */ 412 UCHAR_POSIX_PRINT=47, 413 /** Binary property xdigit (a C/POSIX character class). 414 Implemented according to the UTS #18 Annex C Standard Recommendation. 415 See the uchar.h file documentation. 416 @stable ICU 3.4 */ 417 UCHAR_POSIX_XDIGIT=48, 418 /** Binary property Cased. For Lowercase, Uppercase and Titlecase characters. @stable ICU 4.4 */ 419 UCHAR_CASED=49, 420 /** Binary property Case_Ignorable. Used in context-sensitive case mappings. @stable ICU 4.4 */ 421 UCHAR_CASE_IGNORABLE=50, 422 /** Binary property Changes_When_Lowercased. @stable ICU 4.4 */ 423 UCHAR_CHANGES_WHEN_LOWERCASED=51, 424 /** Binary property Changes_When_Uppercased. @stable ICU 4.4 */ 425 UCHAR_CHANGES_WHEN_UPPERCASED=52, 426 /** Binary property Changes_When_Titlecased. @stable ICU 4.4 */ 427 UCHAR_CHANGES_WHEN_TITLECASED=53, 428 /** Binary property Changes_When_Casefolded. @stable ICU 4.4 */ 429 UCHAR_CHANGES_WHEN_CASEFOLDED=54, 430 /** Binary property Changes_When_Casemapped. @stable ICU 4.4 */ 431 UCHAR_CHANGES_WHEN_CASEMAPPED=55, 432 /** Binary property Changes_When_NFKC_Casefolded. @stable ICU 4.4 */ 433 UCHAR_CHANGES_WHEN_NFKC_CASEFOLDED=56, 434 /** 435 * Binary property Emoji. 436 * See http://www.unicode.org/reports/tr51/#Emoji_Properties 437 * 438 * @stable ICU 57 439 */ 440 UCHAR_EMOJI=57, 441 /** 442 * Binary property Emoji_Presentation. 443 * See http://www.unicode.org/reports/tr51/#Emoji_Properties 444 * 445 * @stable ICU 57 446 */ 447 UCHAR_EMOJI_PRESENTATION=58, 448 /** 449 * Binary property Emoji_Modifier. 450 * See http://www.unicode.org/reports/tr51/#Emoji_Properties 451 * 452 * @stable ICU 57 453 */ 454 UCHAR_EMOJI_MODIFIER=59, 455 /** 456 * Binary property Emoji_Modifier_Base. 457 * See http://www.unicode.org/reports/tr51/#Emoji_Properties 458 * 459 * @stable ICU 57 460 */ 461 UCHAR_EMOJI_MODIFIER_BASE=60, 462 /** 463 * Binary property Emoji_Component. 464 * See http://www.unicode.org/reports/tr51/#Emoji_Properties 465 * 466 * @stable ICU 60 467 */ 468 UCHAR_EMOJI_COMPONENT=61, 469 /** 470 * Binary property Regional_Indicator. 471 * @stable ICU 60 472 */ 473 UCHAR_REGIONAL_INDICATOR=62, 474 /** 475 * Binary property Prepended_Concatenation_Mark. 476 * @stable ICU 60 477 */ 478 UCHAR_PREPENDED_CONCATENATION_MARK=63, 479 /** 480 * Binary property Extended_Pictographic. 481 * See http://www.unicode.org/reports/tr51/#Emoji_Properties 482 * 483 * @stable ICU 62 484 */ 485 UCHAR_EXTENDED_PICTOGRAPHIC=64, 486 /** 487 * Binary property of strings Basic_Emoji. 488 * See https://www.unicode.org/reports/tr51/#Emoji_Sets 489 * 490 * @stable ICU 70 491 */ 492 UCHAR_BASIC_EMOJI=65, 493 /** 494 * Binary property of strings Emoji_Keycap_Sequence. 495 * See https://www.unicode.org/reports/tr51/#Emoji_Sets 496 * 497 * @stable ICU 70 498 */ 499 UCHAR_EMOJI_KEYCAP_SEQUENCE=66, 500 /** 501 * Binary property of strings RGI_Emoji_Modifier_Sequence. 502 * See https://www.unicode.org/reports/tr51/#Emoji_Sets 503 * 504 * @stable ICU 70 505 */ 506 UCHAR_RGI_EMOJI_MODIFIER_SEQUENCE=67, 507 /** 508 * Binary property of strings RGI_Emoji_Flag_Sequence. 509 * See https://www.unicode.org/reports/tr51/#Emoji_Sets 510 * 511 * @stable ICU 70 512 */ 513 UCHAR_RGI_EMOJI_FLAG_SEQUENCE=68, 514 /** 515 * Binary property of strings RGI_Emoji_Tag_Sequence. 516 * See https://www.unicode.org/reports/tr51/#Emoji_Sets 517 * 518 * @stable ICU 70 519 */ 520 UCHAR_RGI_EMOJI_TAG_SEQUENCE=69, 521 /** 522 * Binary property of strings RGI_Emoji_ZWJ_Sequence. 523 * See https://www.unicode.org/reports/tr51/#Emoji_Sets 524 * 525 * @stable ICU 70 526 */ 527 UCHAR_RGI_EMOJI_ZWJ_SEQUENCE=70, 528 /** 529 * Binary property of strings RGI_Emoji. 530 * See https://www.unicode.org/reports/tr51/#Emoji_Sets 531 * 532 * @stable ICU 70 533 */ 534 UCHAR_RGI_EMOJI=71, 535 #ifndef U_HIDE_DRAFT_API 536 /** 537 * Binary property IDS_Unary_Operator. 538 * For programmatic determination of Ideographic Description Sequences. 539 * 540 * @draft 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 * @draft 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 * @draft ICU 74 553 */ 554 UCHAR_ID_COMPAT_MATH_CONTINUE=74, 555 #endif // U_HIDE_DRAFT_API 556 #ifndef U_HIDE_DEPRECATED_API 557 /** 558 * One more than the last constant for binary Unicode properties. 559 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. 560 */ 561 UCHAR_BINARY_LIMIT=75, 562 #endif // U_HIDE_DEPRECATED_API 563 564 /** Enumerated property Bidi_Class. 565 Same as u_charDirection, returns UCharDirection values. @stable ICU 2.2 */ 566 UCHAR_BIDI_CLASS=0x1000, 567 /** First constant for enumerated/integer Unicode properties. @stable ICU 2.2 */ 568 UCHAR_INT_START=UCHAR_BIDI_CLASS, 569 /** Enumerated property Block. 570 Same as ublock_getCode, returns UBlockCode values. @stable ICU 2.2 */ 571 UCHAR_BLOCK=0x1001, 572 /** Enumerated property Canonical_Combining_Class. 573 Same as u_getCombiningClass, returns 8-bit numeric values. @stable ICU 2.2 */ 574 UCHAR_CANONICAL_COMBINING_CLASS=0x1002, 575 /** Enumerated property Decomposition_Type. 576 Returns UDecompositionType values. @stable ICU 2.2 */ 577 UCHAR_DECOMPOSITION_TYPE=0x1003, 578 /** Enumerated property East_Asian_Width. 579 See http://www.unicode.org/reports/tr11/ 580 Returns UEastAsianWidth values. @stable ICU 2.2 */ 581 UCHAR_EAST_ASIAN_WIDTH=0x1004, 582 /** Enumerated property General_Category. 583 Same as u_charType, returns UCharCategory values. @stable ICU 2.2 */ 584 UCHAR_GENERAL_CATEGORY=0x1005, 585 /** Enumerated property Joining_Group. 586 Returns UJoiningGroup values. @stable ICU 2.2 */ 587 UCHAR_JOINING_GROUP=0x1006, 588 /** Enumerated property Joining_Type. 589 Returns UJoiningType values. @stable ICU 2.2 */ 590 UCHAR_JOINING_TYPE=0x1007, 591 /** Enumerated property Line_Break. 592 Returns ULineBreak values. @stable ICU 2.2 */ 593 UCHAR_LINE_BREAK=0x1008, 594 /** Enumerated property Numeric_Type. 595 Returns UNumericType values. @stable ICU 2.2 */ 596 UCHAR_NUMERIC_TYPE=0x1009, 597 /** Enumerated property Script. 598 Same as uscript_getScript, returns UScriptCode values. @stable ICU 2.2 */ 599 UCHAR_SCRIPT=0x100A, 600 /** Enumerated property Hangul_Syllable_Type, new in Unicode 4. 601 Returns UHangulSyllableType values. @stable ICU 2.6 */ 602 UCHAR_HANGUL_SYLLABLE_TYPE=0x100B, 603 /** Enumerated property NFD_Quick_Check. 604 Returns UNormalizationCheckResult values. @stable ICU 3.0 */ 605 UCHAR_NFD_QUICK_CHECK=0x100C, 606 /** Enumerated property NFKD_Quick_Check. 607 Returns UNormalizationCheckResult values. @stable ICU 3.0 */ 608 UCHAR_NFKD_QUICK_CHECK=0x100D, 609 /** Enumerated property NFC_Quick_Check. 610 Returns UNormalizationCheckResult values. @stable ICU 3.0 */ 611 UCHAR_NFC_QUICK_CHECK=0x100E, 612 /** Enumerated property NFKC_Quick_Check. 613 Returns UNormalizationCheckResult values. @stable ICU 3.0 */ 614 UCHAR_NFKC_QUICK_CHECK=0x100F, 615 /** Enumerated property Lead_Canonical_Combining_Class. 616 ICU-specific property for the ccc of the first code point 617 of the decomposition, or lccc(c)=ccc(NFD(c)[0]). 618 Useful for checking for canonically ordered text; 619 see UNORM_FCD and http://www.unicode.org/notes/tn5/#FCD . 620 Returns 8-bit numeric values like UCHAR_CANONICAL_COMBINING_CLASS. @stable ICU 3.0 */ 621 UCHAR_LEAD_CANONICAL_COMBINING_CLASS=0x1010, 622 /** Enumerated property Trail_Canonical_Combining_Class. 623 ICU-specific property for the ccc of the last code point 624 of the decomposition, or tccc(c)=ccc(NFD(c)[last]). 625 Useful for checking for canonically ordered text; 626 see UNORM_FCD and http://www.unicode.org/notes/tn5/#FCD . 627 Returns 8-bit numeric values like UCHAR_CANONICAL_COMBINING_CLASS. @stable ICU 3.0 */ 628 UCHAR_TRAIL_CANONICAL_COMBINING_CLASS=0x1011, 629 /** Enumerated property Grapheme_Cluster_Break (new in Unicode 4.1). 630 Used in UAX #29: Text Boundaries 631 (http://www.unicode.org/reports/tr29/) 632 Returns UGraphemeClusterBreak values. @stable ICU 3.4 */ 633 UCHAR_GRAPHEME_CLUSTER_BREAK=0x1012, 634 /** Enumerated property Sentence_Break (new in Unicode 4.1). 635 Used in UAX #29: Text Boundaries 636 (http://www.unicode.org/reports/tr29/) 637 Returns USentenceBreak values. @stable ICU 3.4 */ 638 UCHAR_SENTENCE_BREAK=0x1013, 639 /** Enumerated property Word_Break (new in Unicode 4.1). 640 Used in UAX #29: Text Boundaries 641 (http://www.unicode.org/reports/tr29/) 642 Returns UWordBreakValues values. @stable ICU 3.4 */ 643 UCHAR_WORD_BREAK=0x1014, 644 /** Enumerated property Bidi_Paired_Bracket_Type (new in Unicode 6.3). 645 Used in UAX #9: Unicode Bidirectional Algorithm 646 (http://www.unicode.org/reports/tr9/) 647 Returns UBidiPairedBracketType values. @stable ICU 52 */ 648 UCHAR_BIDI_PAIRED_BRACKET_TYPE=0x1015, 649 /** 650 * Enumerated property Indic_Positional_Category. 651 * New in Unicode 6.0 as provisional property Indic_Matra_Category; 652 * renamed and changed to informative in Unicode 8.0. 653 * See http://www.unicode.org/reports/tr44/#IndicPositionalCategory.txt 654 * @stable ICU 63 655 */ 656 UCHAR_INDIC_POSITIONAL_CATEGORY=0x1016, 657 /** 658 * Enumerated property Indic_Syllabic_Category. 659 * New in Unicode 6.0 as provisional; informative since Unicode 8.0. 660 * See http://www.unicode.org/reports/tr44/#IndicSyllabicCategory.txt 661 * @stable ICU 63 662 */ 663 UCHAR_INDIC_SYLLABIC_CATEGORY=0x1017, 664 /** 665 * Enumerated property Vertical_Orientation. 666 * Used for UAX #50 Unicode Vertical Text Layout (https://www.unicode.org/reports/tr50/). 667 * New as a UCD property in Unicode 10.0. 668 * @stable ICU 63 669 */ 670 UCHAR_VERTICAL_ORIENTATION=0x1018, 671 #ifndef U_HIDE_DEPRECATED_API 672 /** 673 * One more than the last constant for enumerated/integer Unicode properties. 674 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. 675 */ 676 UCHAR_INT_LIMIT=0x1019, 677 #endif // U_HIDE_DEPRECATED_API 678 679 /** Bitmask property General_Category_Mask. 680 This is the General_Category property returned as a bit mask. 681 When used in u_getIntPropertyValue(c), same as U_MASK(u_charType(c)), 682 returns bit masks for UCharCategory values where exactly one bit is set. 683 When used with u_getPropertyValueName() and u_getPropertyValueEnum(), 684 a multi-bit mask is used for sets of categories like "Letters". 685 Mask values should be cast to uint32_t. 686 @stable ICU 2.4 */ 687 UCHAR_GENERAL_CATEGORY_MASK=0x2000, 688 /** First constant for bit-mask Unicode properties. @stable ICU 2.4 */ 689 UCHAR_MASK_START=UCHAR_GENERAL_CATEGORY_MASK, 690 #ifndef U_HIDE_DEPRECATED_API 691 /** 692 * One more than the last constant for bit-mask Unicode properties. 693 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. 694 */ 695 UCHAR_MASK_LIMIT=0x2001, 696 #endif // U_HIDE_DEPRECATED_API 697 698 /** Double property Numeric_Value. 699 Corresponds to u_getNumericValue. @stable ICU 2.4 */ 700 UCHAR_NUMERIC_VALUE=0x3000, 701 /** First constant for double Unicode properties. @stable ICU 2.4 */ 702 UCHAR_DOUBLE_START=UCHAR_NUMERIC_VALUE, 703 #ifndef U_HIDE_DEPRECATED_API 704 /** 705 * One more than the last constant for double Unicode properties. 706 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. 707 */ 708 UCHAR_DOUBLE_LIMIT=0x3001, 709 #endif // U_HIDE_DEPRECATED_API 710 711 /** String property Age. 712 Corresponds to u_charAge. @stable ICU 2.4 */ 713 UCHAR_AGE=0x4000, 714 /** First constant for string Unicode properties. @stable ICU 2.4 */ 715 UCHAR_STRING_START=UCHAR_AGE, 716 /** String property Bidi_Mirroring_Glyph. 717 Corresponds to u_charMirror. @stable ICU 2.4 */ 718 UCHAR_BIDI_MIRRORING_GLYPH=0x4001, 719 /** String property Case_Folding. 720 Corresponds to u_strFoldCase in ustring.h. @stable ICU 2.4 */ 721 UCHAR_CASE_FOLDING=0x4002, 722 #ifndef U_HIDE_DEPRECATED_API 723 /** Deprecated string property ISO_Comment. 724 Corresponds to u_getISOComment. @deprecated ICU 49 */ 725 UCHAR_ISO_COMMENT=0x4003, 726 #endif /* U_HIDE_DEPRECATED_API */ 727 /** String property Lowercase_Mapping. 728 Corresponds to u_strToLower in ustring.h. @stable ICU 2.4 */ 729 UCHAR_LOWERCASE_MAPPING=0x4004, 730 /** String property Name. 731 Corresponds to u_charName. @stable ICU 2.4 */ 732 UCHAR_NAME=0x4005, 733 /** String property Simple_Case_Folding. 734 Corresponds to u_foldCase. @stable ICU 2.4 */ 735 UCHAR_SIMPLE_CASE_FOLDING=0x4006, 736 /** String property Simple_Lowercase_Mapping. 737 Corresponds to u_tolower. @stable ICU 2.4 */ 738 UCHAR_SIMPLE_LOWERCASE_MAPPING=0x4007, 739 /** String property Simple_Titlecase_Mapping. 740 Corresponds to u_totitle. @stable ICU 2.4 */ 741 UCHAR_SIMPLE_TITLECASE_MAPPING=0x4008, 742 /** String property Simple_Uppercase_Mapping. 743 Corresponds to u_toupper. @stable ICU 2.4 */ 744 UCHAR_SIMPLE_UPPERCASE_MAPPING=0x4009, 745 /** String property Titlecase_Mapping. 746 Corresponds to u_strToTitle in ustring.h. @stable ICU 2.4 */ 747 UCHAR_TITLECASE_MAPPING=0x400A, 748 #ifndef U_HIDE_DEPRECATED_API 749 /** String property Unicode_1_Name. 750 This property is of little practical value. 751 Beginning with ICU 49, ICU APIs return an empty string for this property. 752 Corresponds to u_charName(U_UNICODE_10_CHAR_NAME). @deprecated ICU 49 */ 753 UCHAR_UNICODE_1_NAME=0x400B, 754 #endif /* U_HIDE_DEPRECATED_API */ 755 /** String property Uppercase_Mapping. 756 Corresponds to u_strToUpper in ustring.h. @stable ICU 2.4 */ 757 UCHAR_UPPERCASE_MAPPING=0x400C, 758 /** String property Bidi_Paired_Bracket (new in Unicode 6.3). 759 Corresponds to u_getBidiPairedBracket. @stable ICU 52 */ 760 UCHAR_BIDI_PAIRED_BRACKET=0x400D, 761 #ifndef U_HIDE_DEPRECATED_API 762 /** 763 * One more than the last constant for string Unicode properties. 764 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. 765 */ 766 UCHAR_STRING_LIMIT=0x400E, 767 #endif // U_HIDE_DEPRECATED_API 768 769 /** Miscellaneous property Script_Extensions (new in Unicode 6.0). 770 Some characters are commonly used in multiple scripts. 771 For more information, see UAX #24: http://www.unicode.org/reports/tr24/. 772 Corresponds to uscript_hasScript and uscript_getScriptExtensions in uscript.h. 773 @stable ICU 4.6 */ 774 UCHAR_SCRIPT_EXTENSIONS=0x7000, 775 /** First constant for Unicode properties with unusual value types. @stable ICU 4.6 */ 776 UCHAR_OTHER_PROPERTY_START=UCHAR_SCRIPT_EXTENSIONS, 777 #ifndef U_HIDE_DEPRECATED_API 778 /** 779 * One more than the last constant for Unicode properties with unusual value types. 780 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. 781 */ 782 UCHAR_OTHER_PROPERTY_LIMIT=0x7001, 783 #endif // U_HIDE_DEPRECATED_API 784 785 /** Represents a nonexistent or invalid property or property value. @stable ICU 2.4 */ 786 UCHAR_INVALID_CODE = -1 787 } UProperty; 788 789 /** 790 * Data for enumerated Unicode general category types. 791 * See http://www.unicode.org/Public/UNIDATA/UnicodeData.html . 792 * @stable ICU 2.0 793 */ 794 typedef enum UCharCategory 795 { 796 /* 797 * Note: UCharCategory constants and their API comments are parsed by preparseucd.py. 798 * It matches pairs of lines like 799 * / ** <Unicode 2-letter General_Category value> comment... * / 800 * U_<[A-Z_]+> = <integer>, 801 */ 802 803 /** Non-category for unassigned and non-character code points. @stable ICU 2.0 */ 804 U_UNASSIGNED = 0, 805 /** Cn "Other, Not Assigned (no characters in [UnicodeData.txt] have this property)" (same as U_UNASSIGNED!) @stable ICU 2.0 */ 806 U_GENERAL_OTHER_TYPES = 0, 807 /** Lu @stable ICU 2.0 */ 808 U_UPPERCASE_LETTER = 1, 809 /** Ll @stable ICU 2.0 */ 810 U_LOWERCASE_LETTER = 2, 811 /** Lt @stable ICU 2.0 */ 812 U_TITLECASE_LETTER = 3, 813 /** Lm @stable ICU 2.0 */ 814 U_MODIFIER_LETTER = 4, 815 /** Lo @stable ICU 2.0 */ 816 U_OTHER_LETTER = 5, 817 /** Mn @stable ICU 2.0 */ 818 U_NON_SPACING_MARK = 6, 819 /** Me @stable ICU 2.0 */ 820 U_ENCLOSING_MARK = 7, 821 /** Mc @stable ICU 2.0 */ 822 U_COMBINING_SPACING_MARK = 8, 823 /** Nd @stable ICU 2.0 */ 824 U_DECIMAL_DIGIT_NUMBER = 9, 825 /** Nl @stable ICU 2.0 */ 826 U_LETTER_NUMBER = 10, 827 /** No @stable ICU 2.0 */ 828 U_OTHER_NUMBER = 11, 829 /** Zs @stable ICU 2.0 */ 830 U_SPACE_SEPARATOR = 12, 831 /** Zl @stable ICU 2.0 */ 832 U_LINE_SEPARATOR = 13, 833 /** Zp @stable ICU 2.0 */ 834 U_PARAGRAPH_SEPARATOR = 14, 835 /** Cc @stable ICU 2.0 */ 836 U_CONTROL_CHAR = 15, 837 /** Cf @stable ICU 2.0 */ 838 U_FORMAT_CHAR = 16, 839 /** Co @stable ICU 2.0 */ 840 U_PRIVATE_USE_CHAR = 17, 841 /** Cs @stable ICU 2.0 */ 842 U_SURROGATE = 18, 843 /** Pd @stable ICU 2.0 */ 844 U_DASH_PUNCTUATION = 19, 845 /** Ps @stable ICU 2.0 */ 846 U_START_PUNCTUATION = 20, 847 /** Pe @stable ICU 2.0 */ 848 U_END_PUNCTUATION = 21, 849 /** Pc @stable ICU 2.0 */ 850 U_CONNECTOR_PUNCTUATION = 22, 851 /** Po @stable ICU 2.0 */ 852 U_OTHER_PUNCTUATION = 23, 853 /** Sm @stable ICU 2.0 */ 854 U_MATH_SYMBOL = 24, 855 /** Sc @stable ICU 2.0 */ 856 U_CURRENCY_SYMBOL = 25, 857 /** Sk @stable ICU 2.0 */ 858 U_MODIFIER_SYMBOL = 26, 859 /** So @stable ICU 2.0 */ 860 U_OTHER_SYMBOL = 27, 861 /** Pi @stable ICU 2.0 */ 862 U_INITIAL_PUNCTUATION = 28, 863 /** Pf @stable ICU 2.0 */ 864 U_FINAL_PUNCTUATION = 29, 865 /** 866 * One higher than the last enum UCharCategory constant. 867 * This numeric value is stable (will not change), see 868 * http://www.unicode.org/policies/stability_policy.html#Property_Value 869 * 870 * @stable ICU 2.0 871 */ 872 U_CHAR_CATEGORY_COUNT 873 } UCharCategory; 874 875 /** 876 * U_GC_XX_MASK constants are bit flags corresponding to Unicode 877 * general category values. 878 * For each category, the nth bit is set if the numeric value of the 879 * corresponding UCharCategory constant is n. 880 * 881 * There are also some U_GC_Y_MASK constants for groups of general categories 882 * like L for all letter categories. 883 * 884 * @see u_charType 885 * @see U_GET_GC_MASK 886 * @see UCharCategory 887 * @stable ICU 2.1 888 */ 889 #define U_GC_CN_MASK U_MASK(U_GENERAL_OTHER_TYPES) 890 891 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 892 #define U_GC_LU_MASK U_MASK(U_UPPERCASE_LETTER) 893 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 894 #define U_GC_LL_MASK U_MASK(U_LOWERCASE_LETTER) 895 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 896 #define U_GC_LT_MASK U_MASK(U_TITLECASE_LETTER) 897 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 898 #define U_GC_LM_MASK U_MASK(U_MODIFIER_LETTER) 899 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 900 #define U_GC_LO_MASK U_MASK(U_OTHER_LETTER) 901 902 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 903 #define U_GC_MN_MASK U_MASK(U_NON_SPACING_MARK) 904 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 905 #define U_GC_ME_MASK U_MASK(U_ENCLOSING_MARK) 906 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 907 #define U_GC_MC_MASK U_MASK(U_COMBINING_SPACING_MARK) 908 909 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 910 #define U_GC_ND_MASK U_MASK(U_DECIMAL_DIGIT_NUMBER) 911 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 912 #define U_GC_NL_MASK U_MASK(U_LETTER_NUMBER) 913 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 914 #define U_GC_NO_MASK U_MASK(U_OTHER_NUMBER) 915 916 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 917 #define U_GC_ZS_MASK U_MASK(U_SPACE_SEPARATOR) 918 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 919 #define U_GC_ZL_MASK U_MASK(U_LINE_SEPARATOR) 920 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 921 #define U_GC_ZP_MASK U_MASK(U_PARAGRAPH_SEPARATOR) 922 923 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 924 #define U_GC_CC_MASK U_MASK(U_CONTROL_CHAR) 925 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 926 #define U_GC_CF_MASK U_MASK(U_FORMAT_CHAR) 927 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 928 #define U_GC_CO_MASK U_MASK(U_PRIVATE_USE_CHAR) 929 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 930 #define U_GC_CS_MASK U_MASK(U_SURROGATE) 931 932 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 933 #define U_GC_PD_MASK U_MASK(U_DASH_PUNCTUATION) 934 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 935 #define U_GC_PS_MASK U_MASK(U_START_PUNCTUATION) 936 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 937 #define U_GC_PE_MASK U_MASK(U_END_PUNCTUATION) 938 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 939 #define U_GC_PC_MASK U_MASK(U_CONNECTOR_PUNCTUATION) 940 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 941 #define U_GC_PO_MASK U_MASK(U_OTHER_PUNCTUATION) 942 943 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 944 #define U_GC_SM_MASK U_MASK(U_MATH_SYMBOL) 945 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 946 #define U_GC_SC_MASK U_MASK(U_CURRENCY_SYMBOL) 947 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 948 #define U_GC_SK_MASK U_MASK(U_MODIFIER_SYMBOL) 949 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 950 #define U_GC_SO_MASK U_MASK(U_OTHER_SYMBOL) 951 952 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 953 #define U_GC_PI_MASK U_MASK(U_INITIAL_PUNCTUATION) 954 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 955 #define U_GC_PF_MASK U_MASK(U_FINAL_PUNCTUATION) 956 957 958 /** Mask constant for multiple UCharCategory bits (L Letters). @stable ICU 2.1 */ 959 #define U_GC_L_MASK \ 960 (U_GC_LU_MASK|U_GC_LL_MASK|U_GC_LT_MASK|U_GC_LM_MASK|U_GC_LO_MASK) 961 962 /** Mask constant for multiple UCharCategory bits (LC Cased Letters). @stable ICU 2.1 */ 963 #define U_GC_LC_MASK \ 964 (U_GC_LU_MASK|U_GC_LL_MASK|U_GC_LT_MASK) 965 966 /** Mask constant for multiple UCharCategory bits (M Marks). @stable ICU 2.1 */ 967 #define U_GC_M_MASK (U_GC_MN_MASK|U_GC_ME_MASK|U_GC_MC_MASK) 968 969 /** Mask constant for multiple UCharCategory bits (N Numbers). @stable ICU 2.1 */ 970 #define U_GC_N_MASK (U_GC_ND_MASK|U_GC_NL_MASK|U_GC_NO_MASK) 971 972 /** Mask constant for multiple UCharCategory bits (Z Separators). @stable ICU 2.1 */ 973 #define U_GC_Z_MASK (U_GC_ZS_MASK|U_GC_ZL_MASK|U_GC_ZP_MASK) 974 975 /** Mask constant for multiple UCharCategory bits (C Others). @stable ICU 2.1 */ 976 #define U_GC_C_MASK \ 977 (U_GC_CN_MASK|U_GC_CC_MASK|U_GC_CF_MASK|U_GC_CO_MASK|U_GC_CS_MASK) 978 979 /** Mask constant for multiple UCharCategory bits (P Punctuation). @stable ICU 2.1 */ 980 #define U_GC_P_MASK \ 981 (U_GC_PD_MASK|U_GC_PS_MASK|U_GC_PE_MASK|U_GC_PC_MASK|U_GC_PO_MASK| \ 982 U_GC_PI_MASK|U_GC_PF_MASK) 983 984 /** Mask constant for multiple UCharCategory bits (S Symbols). @stable ICU 2.1 */ 985 #define U_GC_S_MASK (U_GC_SM_MASK|U_GC_SC_MASK|U_GC_SK_MASK|U_GC_SO_MASK) 986 987 /** 988 * This specifies the language directional property of a character set. 989 * @stable ICU 2.0 990 */ 991 typedef enum UCharDirection { 992 /* 993 * Note: UCharDirection constants and their API comments are parsed by preparseucd.py. 994 * It matches pairs of lines like 995 * / ** <Unicode 1..3-letter Bidi_Class value> comment... * / 996 * U_<[A-Z_]+> = <integer>, 997 */ 998 999 /** L @stable ICU 2.0 */ 1000 U_LEFT_TO_RIGHT = 0, 1001 /** R @stable ICU 2.0 */ 1002 U_RIGHT_TO_LEFT = 1, 1003 /** EN @stable ICU 2.0 */ 1004 U_EUROPEAN_NUMBER = 2, 1005 /** ES @stable ICU 2.0 */ 1006 U_EUROPEAN_NUMBER_SEPARATOR = 3, 1007 /** ET @stable ICU 2.0 */ 1008 U_EUROPEAN_NUMBER_TERMINATOR = 4, 1009 /** AN @stable ICU 2.0 */ 1010 U_ARABIC_NUMBER = 5, 1011 /** CS @stable ICU 2.0 */ 1012 U_COMMON_NUMBER_SEPARATOR = 6, 1013 /** B @stable ICU 2.0 */ 1014 U_BLOCK_SEPARATOR = 7, 1015 /** S @stable ICU 2.0 */ 1016 U_SEGMENT_SEPARATOR = 8, 1017 /** WS @stable ICU 2.0 */ 1018 U_WHITE_SPACE_NEUTRAL = 9, 1019 /** ON @stable ICU 2.0 */ 1020 U_OTHER_NEUTRAL = 10, 1021 /** LRE @stable ICU 2.0 */ 1022 U_LEFT_TO_RIGHT_EMBEDDING = 11, 1023 /** LRO @stable ICU 2.0 */ 1024 U_LEFT_TO_RIGHT_OVERRIDE = 12, 1025 /** AL @stable ICU 2.0 */ 1026 U_RIGHT_TO_LEFT_ARABIC = 13, 1027 /** RLE @stable ICU 2.0 */ 1028 U_RIGHT_TO_LEFT_EMBEDDING = 14, 1029 /** RLO @stable ICU 2.0 */ 1030 U_RIGHT_TO_LEFT_OVERRIDE = 15, 1031 /** PDF @stable ICU 2.0 */ 1032 U_POP_DIRECTIONAL_FORMAT = 16, 1033 /** NSM @stable ICU 2.0 */ 1034 U_DIR_NON_SPACING_MARK = 17, 1035 /** BN @stable ICU 2.0 */ 1036 U_BOUNDARY_NEUTRAL = 18, 1037 /** FSI @stable ICU 52 */ 1038 U_FIRST_STRONG_ISOLATE = 19, 1039 /** LRI @stable ICU 52 */ 1040 U_LEFT_TO_RIGHT_ISOLATE = 20, 1041 /** RLI @stable ICU 52 */ 1042 U_RIGHT_TO_LEFT_ISOLATE = 21, 1043 /** PDI @stable ICU 52 */ 1044 U_POP_DIRECTIONAL_ISOLATE = 22, 1045 #ifndef U_HIDE_DEPRECATED_API 1046 /** 1047 * One more than the highest UCharDirection value. 1048 * The highest value is available via u_getIntPropertyMaxValue(UCHAR_BIDI_CLASS). 1049 * 1050 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. 1051 */ 1052 U_CHAR_DIRECTION_COUNT 1053 #endif // U_HIDE_DEPRECATED_API 1054 } UCharDirection; 1055 1056 /** 1057 * Bidi Paired Bracket Type constants. 1058 * 1059 * @see UCHAR_BIDI_PAIRED_BRACKET_TYPE 1060 * @stable ICU 52 1061 */ 1062 typedef enum UBidiPairedBracketType { 1063 /* 1064 * Note: UBidiPairedBracketType constants are parsed by preparseucd.py. 1065 * It matches lines like 1066 * U_BPT_<Unicode Bidi_Paired_Bracket_Type value name> 1067 */ 1068 1069 /** Not a paired bracket. @stable ICU 52 */ 1070 U_BPT_NONE, 1071 /** Open paired bracket. @stable ICU 52 */ 1072 U_BPT_OPEN, 1073 /** Close paired bracket. @stable ICU 52 */ 1074 U_BPT_CLOSE, 1075 #ifndef U_HIDE_DEPRECATED_API 1076 /** 1077 * One more than the highest normal UBidiPairedBracketType value. 1078 * The highest value is available via u_getIntPropertyMaxValue(UCHAR_BIDI_PAIRED_BRACKET_TYPE). 1079 * 1080 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. 1081 */ 1082 U_BPT_COUNT /* 3 */ 1083 #endif // U_HIDE_DEPRECATED_API 1084 } UBidiPairedBracketType; 1085 1086 /** 1087 * Constants for Unicode blocks, see the Unicode Data file Blocks.txt 1088 * @stable ICU 2.0 1089 */ 1090 enum UBlockCode { 1091 /* 1092 * Note: UBlockCode constants are parsed by preparseucd.py. 1093 * It matches lines like 1094 * UBLOCK_<Unicode Block value name> = <integer>, 1095 */ 1096 1097 /** New No_Block value in Unicode 4. @stable ICU 2.6 */ 1098 UBLOCK_NO_BLOCK = 0, /*[none]*/ /* Special range indicating No_Block */ 1099 1100 /** @stable ICU 2.0 */ 1101 UBLOCK_BASIC_LATIN = 1, /*[0000]*/ 1102 1103 /** @stable ICU 2.0 */ 1104 UBLOCK_LATIN_1_SUPPLEMENT=2, /*[0080]*/ 1105 1106 /** @stable ICU 2.0 */ 1107 UBLOCK_LATIN_EXTENDED_A =3, /*[0100]*/ 1108 1109 /** @stable ICU 2.0 */ 1110 UBLOCK_LATIN_EXTENDED_B =4, /*[0180]*/ 1111 1112 /** @stable ICU 2.0 */ 1113 UBLOCK_IPA_EXTENSIONS =5, /*[0250]*/ 1114 1115 /** @stable ICU 2.0 */ 1116 UBLOCK_SPACING_MODIFIER_LETTERS =6, /*[02B0]*/ 1117 1118 /** @stable ICU 2.0 */ 1119 UBLOCK_COMBINING_DIACRITICAL_MARKS =7, /*[0300]*/ 1120 1121 /** 1122 * Unicode 3.2 renames this block to "Greek and Coptic". 1123 * @stable ICU 2.0 1124 */ 1125 UBLOCK_GREEK =8, /*[0370]*/ 1126 1127 /** @stable ICU 2.0 */ 1128 UBLOCK_CYRILLIC =9, /*[0400]*/ 1129 1130 /** @stable ICU 2.0 */ 1131 UBLOCK_ARMENIAN =10, /*[0530]*/ 1132 1133 /** @stable ICU 2.0 */ 1134 UBLOCK_HEBREW =11, /*[0590]*/ 1135 1136 /** @stable ICU 2.0 */ 1137 UBLOCK_ARABIC =12, /*[0600]*/ 1138 1139 /** @stable ICU 2.0 */ 1140 UBLOCK_SYRIAC =13, /*[0700]*/ 1141 1142 /** @stable ICU 2.0 */ 1143 UBLOCK_THAANA =14, /*[0780]*/ 1144 1145 /** @stable ICU 2.0 */ 1146 UBLOCK_DEVANAGARI =15, /*[0900]*/ 1147 1148 /** @stable ICU 2.0 */ 1149 UBLOCK_BENGALI =16, /*[0980]*/ 1150 1151 /** @stable ICU 2.0 */ 1152 UBLOCK_GURMUKHI =17, /*[0A00]*/ 1153 1154 /** @stable ICU 2.0 */ 1155 UBLOCK_GUJARATI =18, /*[0A80]*/ 1156 1157 /** @stable ICU 2.0 */ 1158 UBLOCK_ORIYA =19, /*[0B00]*/ 1159 1160 /** @stable ICU 2.0 */ 1161 UBLOCK_TAMIL =20, /*[0B80]*/ 1162 1163 /** @stable ICU 2.0 */ 1164 UBLOCK_TELUGU =21, /*[0C00]*/ 1165 1166 /** @stable ICU 2.0 */ 1167 UBLOCK_KANNADA =22, /*[0C80]*/ 1168 1169 /** @stable ICU 2.0 */ 1170 UBLOCK_MALAYALAM =23, /*[0D00]*/ 1171 1172 /** @stable ICU 2.0 */ 1173 UBLOCK_SINHALA =24, /*[0D80]*/ 1174 1175 /** @stable ICU 2.0 */ 1176 UBLOCK_THAI =25, /*[0E00]*/ 1177 1178 /** @stable ICU 2.0 */ 1179 UBLOCK_LAO =26, /*[0E80]*/ 1180 1181 /** @stable ICU 2.0 */ 1182 UBLOCK_TIBETAN =27, /*[0F00]*/ 1183 1184 /** @stable ICU 2.0 */ 1185 UBLOCK_MYANMAR =28, /*[1000]*/ 1186 1187 /** @stable ICU 2.0 */ 1188 UBLOCK_GEORGIAN =29, /*[10A0]*/ 1189 1190 /** @stable ICU 2.0 */ 1191 UBLOCK_HANGUL_JAMO =30, /*[1100]*/ 1192 1193 /** @stable ICU 2.0 */ 1194 UBLOCK_ETHIOPIC =31, /*[1200]*/ 1195 1196 /** @stable ICU 2.0 */ 1197 UBLOCK_CHEROKEE =32, /*[13A0]*/ 1198 1199 /** @stable ICU 2.0 */ 1200 UBLOCK_UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS =33, /*[1400]*/ 1201 1202 /** @stable ICU 2.0 */ 1203 UBLOCK_OGHAM =34, /*[1680]*/ 1204 1205 /** @stable ICU 2.0 */ 1206 UBLOCK_RUNIC =35, /*[16A0]*/ 1207 1208 /** @stable ICU 2.0 */ 1209 UBLOCK_KHMER =36, /*[1780]*/ 1210 1211 /** @stable ICU 2.0 */ 1212 UBLOCK_MONGOLIAN =37, /*[1800]*/ 1213 1214 /** @stable ICU 2.0 */ 1215 UBLOCK_LATIN_EXTENDED_ADDITIONAL =38, /*[1E00]*/ 1216 1217 /** @stable ICU 2.0 */ 1218 UBLOCK_GREEK_EXTENDED =39, /*[1F00]*/ 1219 1220 /** @stable ICU 2.0 */ 1221 UBLOCK_GENERAL_PUNCTUATION =40, /*[2000]*/ 1222 1223 /** @stable ICU 2.0 */ 1224 UBLOCK_SUPERSCRIPTS_AND_SUBSCRIPTS =41, /*[2070]*/ 1225 1226 /** @stable ICU 2.0 */ 1227 UBLOCK_CURRENCY_SYMBOLS =42, /*[20A0]*/ 1228 1229 /** 1230 * Unicode 3.2 renames this block to "Combining Diacritical Marks for Symbols". 1231 * @stable ICU 2.0 1232 */ 1233 UBLOCK_COMBINING_MARKS_FOR_SYMBOLS =43, /*[20D0]*/ 1234 1235 /** @stable ICU 2.0 */ 1236 UBLOCK_LETTERLIKE_SYMBOLS =44, /*[2100]*/ 1237 1238 /** @stable ICU 2.0 */ 1239 UBLOCK_NUMBER_FORMS =45, /*[2150]*/ 1240 1241 /** @stable ICU 2.0 */ 1242 UBLOCK_ARROWS =46, /*[2190]*/ 1243 1244 /** @stable ICU 2.0 */ 1245 UBLOCK_MATHEMATICAL_OPERATORS =47, /*[2200]*/ 1246 1247 /** @stable ICU 2.0 */ 1248 UBLOCK_MISCELLANEOUS_TECHNICAL =48, /*[2300]*/ 1249 1250 /** @stable ICU 2.0 */ 1251 UBLOCK_CONTROL_PICTURES =49, /*[2400]*/ 1252 1253 /** @stable ICU 2.0 */ 1254 UBLOCK_OPTICAL_CHARACTER_RECOGNITION =50, /*[2440]*/ 1255 1256 /** @stable ICU 2.0 */ 1257 UBLOCK_ENCLOSED_ALPHANUMERICS =51, /*[2460]*/ 1258 1259 /** @stable ICU 2.0 */ 1260 UBLOCK_BOX_DRAWING =52, /*[2500]*/ 1261 1262 /** @stable ICU 2.0 */ 1263 UBLOCK_BLOCK_ELEMENTS =53, /*[2580]*/ 1264 1265 /** @stable ICU 2.0 */ 1266 UBLOCK_GEOMETRIC_SHAPES =54, /*[25A0]*/ 1267 1268 /** @stable ICU 2.0 */ 1269 UBLOCK_MISCELLANEOUS_SYMBOLS =55, /*[2600]*/ 1270 1271 /** @stable ICU 2.0 */ 1272 UBLOCK_DINGBATS =56, /*[2700]*/ 1273 1274 /** @stable ICU 2.0 */ 1275 UBLOCK_BRAILLE_PATTERNS =57, /*[2800]*/ 1276 1277 /** @stable ICU 2.0 */ 1278 UBLOCK_CJK_RADICALS_SUPPLEMENT =58, /*[2E80]*/ 1279 1280 /** @stable ICU 2.0 */ 1281 UBLOCK_KANGXI_RADICALS =59, /*[2F00]*/ 1282 1283 /** @stable ICU 2.0 */ 1284 UBLOCK_IDEOGRAPHIC_DESCRIPTION_CHARACTERS =60, /*[2FF0]*/ 1285 1286 /** @stable ICU 2.0 */ 1287 UBLOCK_CJK_SYMBOLS_AND_PUNCTUATION =61, /*[3000]*/ 1288 1289 /** @stable ICU 2.0 */ 1290 UBLOCK_HIRAGANA =62, /*[3040]*/ 1291 1292 /** @stable ICU 2.0 */ 1293 UBLOCK_KATAKANA =63, /*[30A0]*/ 1294 1295 /** @stable ICU 2.0 */ 1296 UBLOCK_BOPOMOFO =64, /*[3100]*/ 1297 1298 /** @stable ICU 2.0 */ 1299 UBLOCK_HANGUL_COMPATIBILITY_JAMO =65, /*[3130]*/ 1300 1301 /** @stable ICU 2.0 */ 1302 UBLOCK_KANBUN =66, /*[3190]*/ 1303 1304 /** @stable ICU 2.0 */ 1305 UBLOCK_BOPOMOFO_EXTENDED =67, /*[31A0]*/ 1306 1307 /** @stable ICU 2.0 */ 1308 UBLOCK_ENCLOSED_CJK_LETTERS_AND_MONTHS =68, /*[3200]*/ 1309 1310 /** @stable ICU 2.0 */ 1311 UBLOCK_CJK_COMPATIBILITY =69, /*[3300]*/ 1312 1313 /** @stable ICU 2.0 */ 1314 UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_A =70, /*[3400]*/ 1315 1316 /** @stable ICU 2.0 */ 1317 UBLOCK_CJK_UNIFIED_IDEOGRAPHS =71, /*[4E00]*/ 1318 1319 /** @stable ICU 2.0 */ 1320 UBLOCK_YI_SYLLABLES =72, /*[A000]*/ 1321 1322 /** @stable ICU 2.0 */ 1323 UBLOCK_YI_RADICALS =73, /*[A490]*/ 1324 1325 /** @stable ICU 2.0 */ 1326 UBLOCK_HANGUL_SYLLABLES =74, /*[AC00]*/ 1327 1328 /** @stable ICU 2.0 */ 1329 UBLOCK_HIGH_SURROGATES =75, /*[D800]*/ 1330 1331 /** @stable ICU 2.0 */ 1332 UBLOCK_HIGH_PRIVATE_USE_SURROGATES =76, /*[DB80]*/ 1333 1334 /** @stable ICU 2.0 */ 1335 UBLOCK_LOW_SURROGATES =77, /*[DC00]*/ 1336 1337 /** 1338 * Same as UBLOCK_PRIVATE_USE. 1339 * Until Unicode 3.1.1, the corresponding block name was "Private Use", 1340 * and multiple code point ranges had this block. 1341 * Unicode 3.2 renames the block for the BMP PUA to "Private Use Area" and 1342 * adds separate blocks for the supplementary PUAs. 1343 * 1344 * @stable ICU 2.0 1345 */ 1346 UBLOCK_PRIVATE_USE_AREA =78, /*[E000]*/ 1347 /** 1348 * Same as UBLOCK_PRIVATE_USE_AREA. 1349 * Until Unicode 3.1.1, the corresponding block name was "Private Use", 1350 * and multiple code point ranges had this block. 1351 * Unicode 3.2 renames the block for the BMP PUA to "Private Use Area" and 1352 * adds separate blocks for the supplementary PUAs. 1353 * 1354 * @stable ICU 2.0 1355 */ 1356 UBLOCK_PRIVATE_USE = UBLOCK_PRIVATE_USE_AREA, 1357 1358 /** @stable ICU 2.0 */ 1359 UBLOCK_CJK_COMPATIBILITY_IDEOGRAPHS =79, /*[F900]*/ 1360 1361 /** @stable ICU 2.0 */ 1362 UBLOCK_ALPHABETIC_PRESENTATION_FORMS =80, /*[FB00]*/ 1363 1364 /** @stable ICU 2.0 */ 1365 UBLOCK_ARABIC_PRESENTATION_FORMS_A =81, /*[FB50]*/ 1366 1367 /** @stable ICU 2.0 */ 1368 UBLOCK_COMBINING_HALF_MARKS =82, /*[FE20]*/ 1369 1370 /** @stable ICU 2.0 */ 1371 UBLOCK_CJK_COMPATIBILITY_FORMS =83, /*[FE30]*/ 1372 1373 /** @stable ICU 2.0 */ 1374 UBLOCK_SMALL_FORM_VARIANTS =84, /*[FE50]*/ 1375 1376 /** @stable ICU 2.0 */ 1377 UBLOCK_ARABIC_PRESENTATION_FORMS_B =85, /*[FE70]*/ 1378 1379 /** @stable ICU 2.0 */ 1380 UBLOCK_SPECIALS =86, /*[FFF0]*/ 1381 1382 /** @stable ICU 2.0 */ 1383 UBLOCK_HALFWIDTH_AND_FULLWIDTH_FORMS =87, /*[FF00]*/ 1384 1385 /* New blocks in Unicode 3.1 */ 1386 1387 /** @stable ICU 2.0 */ 1388 UBLOCK_OLD_ITALIC = 88, /*[10300]*/ 1389 /** @stable ICU 2.0 */ 1390 UBLOCK_GOTHIC = 89, /*[10330]*/ 1391 /** @stable ICU 2.0 */ 1392 UBLOCK_DESERET = 90, /*[10400]*/ 1393 /** @stable ICU 2.0 */ 1394 UBLOCK_BYZANTINE_MUSICAL_SYMBOLS = 91, /*[1D000]*/ 1395 /** @stable ICU 2.0 */ 1396 UBLOCK_MUSICAL_SYMBOLS = 92, /*[1D100]*/ 1397 /** @stable ICU 2.0 */ 1398 UBLOCK_MATHEMATICAL_ALPHANUMERIC_SYMBOLS = 93, /*[1D400]*/ 1399 /** @stable ICU 2.0 */ 1400 UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_B = 94, /*[20000]*/ 1401 /** @stable ICU 2.0 */ 1402 UBLOCK_CJK_COMPATIBILITY_IDEOGRAPHS_SUPPLEMENT = 95, /*[2F800]*/ 1403 /** @stable ICU 2.0 */ 1404 UBLOCK_TAGS = 96, /*[E0000]*/ 1405 1406 /* New blocks in Unicode 3.2 */ 1407 1408 /** @stable ICU 3.0 */ 1409 UBLOCK_CYRILLIC_SUPPLEMENT = 97, /*[0500]*/ 1410 /** 1411 * Unicode 4.0.1 renames the "Cyrillic Supplementary" block to "Cyrillic Supplement". 1412 * @stable ICU 2.2 1413 */ 1414 UBLOCK_CYRILLIC_SUPPLEMENTARY = UBLOCK_CYRILLIC_SUPPLEMENT, 1415 /** @stable ICU 2.2 */ 1416 UBLOCK_TAGALOG = 98, /*[1700]*/ 1417 /** @stable ICU 2.2 */ 1418 UBLOCK_HANUNOO = 99, /*[1720]*/ 1419 /** @stable ICU 2.2 */ 1420 UBLOCK_BUHID = 100, /*[1740]*/ 1421 /** @stable ICU 2.2 */ 1422 UBLOCK_TAGBANWA = 101, /*[1760]*/ 1423 /** @stable ICU 2.2 */ 1424 UBLOCK_MISCELLANEOUS_MATHEMATICAL_SYMBOLS_A = 102, /*[27C0]*/ 1425 /** @stable ICU 2.2 */ 1426 UBLOCK_SUPPLEMENTAL_ARROWS_A = 103, /*[27F0]*/ 1427 /** @stable ICU 2.2 */ 1428 UBLOCK_SUPPLEMENTAL_ARROWS_B = 104, /*[2900]*/ 1429 /** @stable ICU 2.2 */ 1430 UBLOCK_MISCELLANEOUS_MATHEMATICAL_SYMBOLS_B = 105, /*[2980]*/ 1431 /** @stable ICU 2.2 */ 1432 UBLOCK_SUPPLEMENTAL_MATHEMATICAL_OPERATORS = 106, /*[2A00]*/ 1433 /** @stable ICU 2.2 */ 1434 UBLOCK_KATAKANA_PHONETIC_EXTENSIONS = 107, /*[31F0]*/ 1435 /** @stable ICU 2.2 */ 1436 UBLOCK_VARIATION_SELECTORS = 108, /*[FE00]*/ 1437 /** @stable ICU 2.2 */ 1438 UBLOCK_SUPPLEMENTARY_PRIVATE_USE_AREA_A = 109, /*[F0000]*/ 1439 /** @stable ICU 2.2 */ 1440 UBLOCK_SUPPLEMENTARY_PRIVATE_USE_AREA_B = 110, /*[100000]*/ 1441 1442 /* New blocks in Unicode 4 */ 1443 1444 /** @stable ICU 2.6 */ 1445 UBLOCK_LIMBU = 111, /*[1900]*/ 1446 /** @stable ICU 2.6 */ 1447 UBLOCK_TAI_LE = 112, /*[1950]*/ 1448 /** @stable ICU 2.6 */ 1449 UBLOCK_KHMER_SYMBOLS = 113, /*[19E0]*/ 1450 /** @stable ICU 2.6 */ 1451 UBLOCK_PHONETIC_EXTENSIONS = 114, /*[1D00]*/ 1452 /** @stable ICU 2.6 */ 1453 UBLOCK_MISCELLANEOUS_SYMBOLS_AND_ARROWS = 115, /*[2B00]*/ 1454 /** @stable ICU 2.6 */ 1455 UBLOCK_YIJING_HEXAGRAM_SYMBOLS = 116, /*[4DC0]*/ 1456 /** @stable ICU 2.6 */ 1457 UBLOCK_LINEAR_B_SYLLABARY = 117, /*[10000]*/ 1458 /** @stable ICU 2.6 */ 1459 UBLOCK_LINEAR_B_IDEOGRAMS = 118, /*[10080]*/ 1460 /** @stable ICU 2.6 */ 1461 UBLOCK_AEGEAN_NUMBERS = 119, /*[10100]*/ 1462 /** @stable ICU 2.6 */ 1463 UBLOCK_UGARITIC = 120, /*[10380]*/ 1464 /** @stable ICU 2.6 */ 1465 UBLOCK_SHAVIAN = 121, /*[10450]*/ 1466 /** @stable ICU 2.6 */ 1467 UBLOCK_OSMANYA = 122, /*[10480]*/ 1468 /** @stable ICU 2.6 */ 1469 UBLOCK_CYPRIOT_SYLLABARY = 123, /*[10800]*/ 1470 /** @stable ICU 2.6 */ 1471 UBLOCK_TAI_XUAN_JING_SYMBOLS = 124, /*[1D300]*/ 1472 /** @stable ICU 2.6 */ 1473 UBLOCK_VARIATION_SELECTORS_SUPPLEMENT = 125, /*[E0100]*/ 1474 1475 /* New blocks in Unicode 4.1 */ 1476 1477 /** @stable ICU 3.4 */ 1478 UBLOCK_ANCIENT_GREEK_MUSICAL_NOTATION = 126, /*[1D200]*/ 1479 /** @stable ICU 3.4 */ 1480 UBLOCK_ANCIENT_GREEK_NUMBERS = 127, /*[10140]*/ 1481 /** @stable ICU 3.4 */ 1482 UBLOCK_ARABIC_SUPPLEMENT = 128, /*[0750]*/ 1483 /** @stable ICU 3.4 */ 1484 UBLOCK_BUGINESE = 129, /*[1A00]*/ 1485 /** @stable ICU 3.4 */ 1486 UBLOCK_CJK_STROKES = 130, /*[31C0]*/ 1487 /** @stable ICU 3.4 */ 1488 UBLOCK_COMBINING_DIACRITICAL_MARKS_SUPPLEMENT = 131, /*[1DC0]*/ 1489 /** @stable ICU 3.4 */ 1490 UBLOCK_COPTIC = 132, /*[2C80]*/ 1491 /** @stable ICU 3.4 */ 1492 UBLOCK_ETHIOPIC_EXTENDED = 133, /*[2D80]*/ 1493 /** @stable ICU 3.4 */ 1494 UBLOCK_ETHIOPIC_SUPPLEMENT = 134, /*[1380]*/ 1495 /** @stable ICU 3.4 */ 1496 UBLOCK_GEORGIAN_SUPPLEMENT = 135, /*[2D00]*/ 1497 /** @stable ICU 3.4 */ 1498 UBLOCK_GLAGOLITIC = 136, /*[2C00]*/ 1499 /** @stable ICU 3.4 */ 1500 UBLOCK_KHAROSHTHI = 137, /*[10A00]*/ 1501 /** @stable ICU 3.4 */ 1502 UBLOCK_MODIFIER_TONE_LETTERS = 138, /*[A700]*/ 1503 /** @stable ICU 3.4 */ 1504 UBLOCK_NEW_TAI_LUE = 139, /*[1980]*/ 1505 /** @stable ICU 3.4 */ 1506 UBLOCK_OLD_PERSIAN = 140, /*[103A0]*/ 1507 /** @stable ICU 3.4 */ 1508 UBLOCK_PHONETIC_EXTENSIONS_SUPPLEMENT = 141, /*[1D80]*/ 1509 /** @stable ICU 3.4 */ 1510 UBLOCK_SUPPLEMENTAL_PUNCTUATION = 142, /*[2E00]*/ 1511 /** @stable ICU 3.4 */ 1512 UBLOCK_SYLOTI_NAGRI = 143, /*[A800]*/ 1513 /** @stable ICU 3.4 */ 1514 UBLOCK_TIFINAGH = 144, /*[2D30]*/ 1515 /** @stable ICU 3.4 */ 1516 UBLOCK_VERTICAL_FORMS = 145, /*[FE10]*/ 1517 1518 /* New blocks in Unicode 5.0 */ 1519 1520 /** @stable ICU 3.6 */ 1521 UBLOCK_NKO = 146, /*[07C0]*/ 1522 /** @stable ICU 3.6 */ 1523 UBLOCK_BALINESE = 147, /*[1B00]*/ 1524 /** @stable ICU 3.6 */ 1525 UBLOCK_LATIN_EXTENDED_C = 148, /*[2C60]*/ 1526 /** @stable ICU 3.6 */ 1527 UBLOCK_LATIN_EXTENDED_D = 149, /*[A720]*/ 1528 /** @stable ICU 3.6 */ 1529 UBLOCK_PHAGS_PA = 150, /*[A840]*/ 1530 /** @stable ICU 3.6 */ 1531 UBLOCK_PHOENICIAN = 151, /*[10900]*/ 1532 /** @stable ICU 3.6 */ 1533 UBLOCK_CUNEIFORM = 152, /*[12000]*/ 1534 /** @stable ICU 3.6 */ 1535 UBLOCK_CUNEIFORM_NUMBERS_AND_PUNCTUATION = 153, /*[12400]*/ 1536 /** @stable ICU 3.6 */ 1537 UBLOCK_COUNTING_ROD_NUMERALS = 154, /*[1D360]*/ 1538 1539 /* New blocks in Unicode 5.1 */ 1540 1541 /** @stable ICU 4.0 */ 1542 UBLOCK_SUNDANESE = 155, /*[1B80]*/ 1543 /** @stable ICU 4.0 */ 1544 UBLOCK_LEPCHA = 156, /*[1C00]*/ 1545 /** @stable ICU 4.0 */ 1546 UBLOCK_OL_CHIKI = 157, /*[1C50]*/ 1547 /** @stable ICU 4.0 */ 1548 UBLOCK_CYRILLIC_EXTENDED_A = 158, /*[2DE0]*/ 1549 /** @stable ICU 4.0 */ 1550 UBLOCK_VAI = 159, /*[A500]*/ 1551 /** @stable ICU 4.0 */ 1552 UBLOCK_CYRILLIC_EXTENDED_B = 160, /*[A640]*/ 1553 /** @stable ICU 4.0 */ 1554 UBLOCK_SAURASHTRA = 161, /*[A880]*/ 1555 /** @stable ICU 4.0 */ 1556 UBLOCK_KAYAH_LI = 162, /*[A900]*/ 1557 /** @stable ICU 4.0 */ 1558 UBLOCK_REJANG = 163, /*[A930]*/ 1559 /** @stable ICU 4.0 */ 1560 UBLOCK_CHAM = 164, /*[AA00]*/ 1561 /** @stable ICU 4.0 */ 1562 UBLOCK_ANCIENT_SYMBOLS = 165, /*[10190]*/ 1563 /** @stable ICU 4.0 */ 1564 UBLOCK_PHAISTOS_DISC = 166, /*[101D0]*/ 1565 /** @stable ICU 4.0 */ 1566 UBLOCK_LYCIAN = 167, /*[10280]*/ 1567 /** @stable ICU 4.0 */ 1568 UBLOCK_CARIAN = 168, /*[102A0]*/ 1569 /** @stable ICU 4.0 */ 1570 UBLOCK_LYDIAN = 169, /*[10920]*/ 1571 /** @stable ICU 4.0 */ 1572 UBLOCK_MAHJONG_TILES = 170, /*[1F000]*/ 1573 /** @stable ICU 4.0 */ 1574 UBLOCK_DOMINO_TILES = 171, /*[1F030]*/ 1575 1576 /* New blocks in Unicode 5.2 */ 1577 1578 /** @stable ICU 4.4 */ 1579 UBLOCK_SAMARITAN = 172, /*[0800]*/ 1580 /** @stable ICU 4.4 */ 1581 UBLOCK_UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS_EXTENDED = 173, /*[18B0]*/ 1582 /** @stable ICU 4.4 */ 1583 UBLOCK_TAI_THAM = 174, /*[1A20]*/ 1584 /** @stable ICU 4.4 */ 1585 UBLOCK_VEDIC_EXTENSIONS = 175, /*[1CD0]*/ 1586 /** @stable ICU 4.4 */ 1587 UBLOCK_LISU = 176, /*[A4D0]*/ 1588 /** @stable ICU 4.4 */ 1589 UBLOCK_BAMUM = 177, /*[A6A0]*/ 1590 /** @stable ICU 4.4 */ 1591 UBLOCK_COMMON_INDIC_NUMBER_FORMS = 178, /*[A830]*/ 1592 /** @stable ICU 4.4 */ 1593 UBLOCK_DEVANAGARI_EXTENDED = 179, /*[A8E0]*/ 1594 /** @stable ICU 4.4 */ 1595 UBLOCK_HANGUL_JAMO_EXTENDED_A = 180, /*[A960]*/ 1596 /** @stable ICU 4.4 */ 1597 UBLOCK_JAVANESE = 181, /*[A980]*/ 1598 /** @stable ICU 4.4 */ 1599 UBLOCK_MYANMAR_EXTENDED_A = 182, /*[AA60]*/ 1600 /** @stable ICU 4.4 */ 1601 UBLOCK_TAI_VIET = 183, /*[AA80]*/ 1602 /** @stable ICU 4.4 */ 1603 UBLOCK_MEETEI_MAYEK = 184, /*[ABC0]*/ 1604 /** @stable ICU 4.4 */ 1605 UBLOCK_HANGUL_JAMO_EXTENDED_B = 185, /*[D7B0]*/ 1606 /** @stable ICU 4.4 */ 1607 UBLOCK_IMPERIAL_ARAMAIC = 186, /*[10840]*/ 1608 /** @stable ICU 4.4 */ 1609 UBLOCK_OLD_SOUTH_ARABIAN = 187, /*[10A60]*/ 1610 /** @stable ICU 4.4 */ 1611 UBLOCK_AVESTAN = 188, /*[10B00]*/ 1612 /** @stable ICU 4.4 */ 1613 UBLOCK_INSCRIPTIONAL_PARTHIAN = 189, /*[10B40]*/ 1614 /** @stable ICU 4.4 */ 1615 UBLOCK_INSCRIPTIONAL_PAHLAVI = 190, /*[10B60]*/ 1616 /** @stable ICU 4.4 */ 1617 UBLOCK_OLD_TURKIC = 191, /*[10C00]*/ 1618 /** @stable ICU 4.4 */ 1619 UBLOCK_RUMI_NUMERAL_SYMBOLS = 192, /*[10E60]*/ 1620 /** @stable ICU 4.4 */ 1621 UBLOCK_KAITHI = 193, /*[11080]*/ 1622 /** @stable ICU 4.4 */ 1623 UBLOCK_EGYPTIAN_HIEROGLYPHS = 194, /*[13000]*/ 1624 /** @stable ICU 4.4 */ 1625 UBLOCK_ENCLOSED_ALPHANUMERIC_SUPPLEMENT = 195, /*[1F100]*/ 1626 /** @stable ICU 4.4 */ 1627 UBLOCK_ENCLOSED_IDEOGRAPHIC_SUPPLEMENT = 196, /*[1F200]*/ 1628 /** @stable ICU 4.4 */ 1629 UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_C = 197, /*[2A700]*/ 1630 1631 /* New blocks in Unicode 6.0 */ 1632 1633 /** @stable ICU 4.6 */ 1634 UBLOCK_MANDAIC = 198, /*[0840]*/ 1635 /** @stable ICU 4.6 */ 1636 UBLOCK_BATAK = 199, /*[1BC0]*/ 1637 /** @stable ICU 4.6 */ 1638 UBLOCK_ETHIOPIC_EXTENDED_A = 200, /*[AB00]*/ 1639 /** @stable ICU 4.6 */ 1640 UBLOCK_BRAHMI = 201, /*[11000]*/ 1641 /** @stable ICU 4.6 */ 1642 UBLOCK_BAMUM_SUPPLEMENT = 202, /*[16800]*/ 1643 /** @stable ICU 4.6 */ 1644 UBLOCK_KANA_SUPPLEMENT = 203, /*[1B000]*/ 1645 /** @stable ICU 4.6 */ 1646 UBLOCK_PLAYING_CARDS = 204, /*[1F0A0]*/ 1647 /** @stable ICU 4.6 */ 1648 UBLOCK_MISCELLANEOUS_SYMBOLS_AND_PICTOGRAPHS = 205, /*[1F300]*/ 1649 /** @stable ICU 4.6 */ 1650 UBLOCK_EMOTICONS = 206, /*[1F600]*/ 1651 /** @stable ICU 4.6 */ 1652 UBLOCK_TRANSPORT_AND_MAP_SYMBOLS = 207, /*[1F680]*/ 1653 /** @stable ICU 4.6 */ 1654 UBLOCK_ALCHEMICAL_SYMBOLS = 208, /*[1F700]*/ 1655 /** @stable ICU 4.6 */ 1656 UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_D = 209, /*[2B740]*/ 1657 1658 /* New blocks in Unicode 6.1 */ 1659 1660 /** @stable ICU 49 */ 1661 UBLOCK_ARABIC_EXTENDED_A = 210, /*[08A0]*/ 1662 /** @stable ICU 49 */ 1663 UBLOCK_ARABIC_MATHEMATICAL_ALPHABETIC_SYMBOLS = 211, /*[1EE00]*/ 1664 /** @stable ICU 49 */ 1665 UBLOCK_CHAKMA = 212, /*[11100]*/ 1666 /** @stable ICU 49 */ 1667 UBLOCK_MEETEI_MAYEK_EXTENSIONS = 213, /*[AAE0]*/ 1668 /** @stable ICU 49 */ 1669 UBLOCK_MEROITIC_CURSIVE = 214, /*[109A0]*/ 1670 /** @stable ICU 49 */ 1671 UBLOCK_MEROITIC_HIEROGLYPHS = 215, /*[10980]*/ 1672 /** @stable ICU 49 */ 1673 UBLOCK_MIAO = 216, /*[16F00]*/ 1674 /** @stable ICU 49 */ 1675 UBLOCK_SHARADA = 217, /*[11180]*/ 1676 /** @stable ICU 49 */ 1677 UBLOCK_SORA_SOMPENG = 218, /*[110D0]*/ 1678 /** @stable ICU 49 */ 1679 UBLOCK_SUNDANESE_SUPPLEMENT = 219, /*[1CC0]*/ 1680 /** @stable ICU 49 */ 1681 UBLOCK_TAKRI = 220, /*[11680]*/ 1682 1683 /* New blocks in Unicode 7.0 */ 1684 1685 /** @stable ICU 54 */ 1686 UBLOCK_BASSA_VAH = 221, /*[16AD0]*/ 1687 /** @stable ICU 54 */ 1688 UBLOCK_CAUCASIAN_ALBANIAN = 222, /*[10530]*/ 1689 /** @stable ICU 54 */ 1690 UBLOCK_COPTIC_EPACT_NUMBERS = 223, /*[102E0]*/ 1691 /** @stable ICU 54 */ 1692 UBLOCK_COMBINING_DIACRITICAL_MARKS_EXTENDED = 224, /*[1AB0]*/ 1693 /** @stable ICU 54 */ 1694 UBLOCK_DUPLOYAN = 225, /*[1BC00]*/ 1695 /** @stable ICU 54 */ 1696 UBLOCK_ELBASAN = 226, /*[10500]*/ 1697 /** @stable ICU 54 */ 1698 UBLOCK_GEOMETRIC_SHAPES_EXTENDED = 227, /*[1F780]*/ 1699 /** @stable ICU 54 */ 1700 UBLOCK_GRANTHA = 228, /*[11300]*/ 1701 /** @stable ICU 54 */ 1702 UBLOCK_KHOJKI = 229, /*[11200]*/ 1703 /** @stable ICU 54 */ 1704 UBLOCK_KHUDAWADI = 230, /*[112B0]*/ 1705 /** @stable ICU 54 */ 1706 UBLOCK_LATIN_EXTENDED_E = 231, /*[AB30]*/ 1707 /** @stable ICU 54 */ 1708 UBLOCK_LINEAR_A = 232, /*[10600]*/ 1709 /** @stable ICU 54 */ 1710 UBLOCK_MAHAJANI = 233, /*[11150]*/ 1711 /** @stable ICU 54 */ 1712 UBLOCK_MANICHAEAN = 234, /*[10AC0]*/ 1713 /** @stable ICU 54 */ 1714 UBLOCK_MENDE_KIKAKUI = 235, /*[1E800]*/ 1715 /** @stable ICU 54 */ 1716 UBLOCK_MODI = 236, /*[11600]*/ 1717 /** @stable ICU 54 */ 1718 UBLOCK_MRO = 237, /*[16A40]*/ 1719 /** @stable ICU 54 */ 1720 UBLOCK_MYANMAR_EXTENDED_B = 238, /*[A9E0]*/ 1721 /** @stable ICU 54 */ 1722 UBLOCK_NABATAEAN = 239, /*[10880]*/ 1723 /** @stable ICU 54 */ 1724 UBLOCK_OLD_NORTH_ARABIAN = 240, /*[10A80]*/ 1725 /** @stable ICU 54 */ 1726 UBLOCK_OLD_PERMIC = 241, /*[10350]*/ 1727 /** @stable ICU 54 */ 1728 UBLOCK_ORNAMENTAL_DINGBATS = 242, /*[1F650]*/ 1729 /** @stable ICU 54 */ 1730 UBLOCK_PAHAWH_HMONG = 243, /*[16B00]*/ 1731 /** @stable ICU 54 */ 1732 UBLOCK_PALMYRENE = 244, /*[10860]*/ 1733 /** @stable ICU 54 */ 1734 UBLOCK_PAU_CIN_HAU = 245, /*[11AC0]*/ 1735 /** @stable ICU 54 */ 1736 UBLOCK_PSALTER_PAHLAVI = 246, /*[10B80]*/ 1737 /** @stable ICU 54 */ 1738 UBLOCK_SHORTHAND_FORMAT_CONTROLS = 247, /*[1BCA0]*/ 1739 /** @stable ICU 54 */ 1740 UBLOCK_SIDDHAM = 248, /*[11580]*/ 1741 /** @stable ICU 54 */ 1742 UBLOCK_SINHALA_ARCHAIC_NUMBERS = 249, /*[111E0]*/ 1743 /** @stable ICU 54 */ 1744 UBLOCK_SUPPLEMENTAL_ARROWS_C = 250, /*[1F800]*/ 1745 /** @stable ICU 54 */ 1746 UBLOCK_TIRHUTA = 251, /*[11480]*/ 1747 /** @stable ICU 54 */ 1748 UBLOCK_WARANG_CITI = 252, /*[118A0]*/ 1749 1750 /* New blocks in Unicode 8.0 */ 1751 1752 /** @stable ICU 56 */ 1753 UBLOCK_AHOM = 253, /*[11700]*/ 1754 /** @stable ICU 56 */ 1755 UBLOCK_ANATOLIAN_HIEROGLYPHS = 254, /*[14400]*/ 1756 /** @stable ICU 56 */ 1757 UBLOCK_CHEROKEE_SUPPLEMENT = 255, /*[AB70]*/ 1758 /** @stable ICU 56 */ 1759 UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_E = 256, /*[2B820]*/ 1760 /** @stable ICU 56 */ 1761 UBLOCK_EARLY_DYNASTIC_CUNEIFORM = 257, /*[12480]*/ 1762 /** @stable ICU 56 */ 1763 UBLOCK_HATRAN = 258, /*[108E0]*/ 1764 /** @stable ICU 56 */ 1765 UBLOCK_MULTANI = 259, /*[11280]*/ 1766 /** @stable ICU 56 */ 1767 UBLOCK_OLD_HUNGARIAN = 260, /*[10C80]*/ 1768 /** @stable ICU 56 */ 1769 UBLOCK_SUPPLEMENTAL_SYMBOLS_AND_PICTOGRAPHS = 261, /*[1F900]*/ 1770 /** @stable ICU 56 */ 1771 UBLOCK_SUTTON_SIGNWRITING = 262, /*[1D800]*/ 1772 1773 /* New blocks in Unicode 9.0 */ 1774 1775 /** @stable ICU 58 */ 1776 UBLOCK_ADLAM = 263, /*[1E900]*/ 1777 /** @stable ICU 58 */ 1778 UBLOCK_BHAIKSUKI = 264, /*[11C00]*/ 1779 /** @stable ICU 58 */ 1780 UBLOCK_CYRILLIC_EXTENDED_C = 265, /*[1C80]*/ 1781 /** @stable ICU 58 */ 1782 UBLOCK_GLAGOLITIC_SUPPLEMENT = 266, /*[1E000]*/ 1783 /** @stable ICU 58 */ 1784 UBLOCK_IDEOGRAPHIC_SYMBOLS_AND_PUNCTUATION = 267, /*[16FE0]*/ 1785 /** @stable ICU 58 */ 1786 UBLOCK_MARCHEN = 268, /*[11C70]*/ 1787 /** @stable ICU 58 */ 1788 UBLOCK_MONGOLIAN_SUPPLEMENT = 269, /*[11660]*/ 1789 /** @stable ICU 58 */ 1790 UBLOCK_NEWA = 270, /*[11400]*/ 1791 /** @stable ICU 58 */ 1792 UBLOCK_OSAGE = 271, /*[104B0]*/ 1793 /** @stable ICU 58 */ 1794 UBLOCK_TANGUT = 272, /*[17000]*/ 1795 /** @stable ICU 58 */ 1796 UBLOCK_TANGUT_COMPONENTS = 273, /*[18800]*/ 1797 1798 // New blocks in Unicode 10.0 1799 1800 /** @stable ICU 60 */ 1801 UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_F = 274, /*[2CEB0]*/ 1802 /** @stable ICU 60 */ 1803 UBLOCK_KANA_EXTENDED_A = 275, /*[1B100]*/ 1804 /** @stable ICU 60 */ 1805 UBLOCK_MASARAM_GONDI = 276, /*[11D00]*/ 1806 /** @stable ICU 60 */ 1807 UBLOCK_NUSHU = 277, /*[1B170]*/ 1808 /** @stable ICU 60 */ 1809 UBLOCK_SOYOMBO = 278, /*[11A50]*/ 1810 /** @stable ICU 60 */ 1811 UBLOCK_SYRIAC_SUPPLEMENT = 279, /*[0860]*/ 1812 /** @stable ICU 60 */ 1813 UBLOCK_ZANABAZAR_SQUARE = 280, /*[11A00]*/ 1814 1815 // New blocks in Unicode 11.0 1816 1817 /** @stable ICU 62 */ 1818 UBLOCK_CHESS_SYMBOLS = 281, /*[1FA00]*/ 1819 /** @stable ICU 62 */ 1820 UBLOCK_DOGRA = 282, /*[11800]*/ 1821 /** @stable ICU 62 */ 1822 UBLOCK_GEORGIAN_EXTENDED = 283, /*[1C90]*/ 1823 /** @stable ICU 62 */ 1824 UBLOCK_GUNJALA_GONDI = 284, /*[11D60]*/ 1825 /** @stable ICU 62 */ 1826 UBLOCK_HANIFI_ROHINGYA = 285, /*[10D00]*/ 1827 /** @stable ICU 62 */ 1828 UBLOCK_INDIC_SIYAQ_NUMBERS = 286, /*[1EC70]*/ 1829 /** @stable ICU 62 */ 1830 UBLOCK_MAKASAR = 287, /*[11EE0]*/ 1831 /** @stable ICU 62 */ 1832 UBLOCK_MAYAN_NUMERALS = 288, /*[1D2E0]*/ 1833 /** @stable ICU 62 */ 1834 UBLOCK_MEDEFAIDRIN = 289, /*[16E40]*/ 1835 /** @stable ICU 62 */ 1836 UBLOCK_OLD_SOGDIAN = 290, /*[10F00]*/ 1837 /** @stable ICU 62 */ 1838 UBLOCK_SOGDIAN = 291, /*[10F30]*/ 1839 1840 // New blocks in Unicode 12.0 1841 1842 /** @stable ICU 64 */ 1843 UBLOCK_EGYPTIAN_HIEROGLYPH_FORMAT_CONTROLS = 292, /*[13430]*/ 1844 /** @stable ICU 64 */ 1845 UBLOCK_ELYMAIC = 293, /*[10FE0]*/ 1846 /** @stable ICU 64 */ 1847 UBLOCK_NANDINAGARI = 294, /*[119A0]*/ 1848 /** @stable ICU 64 */ 1849 UBLOCK_NYIAKENG_PUACHUE_HMONG = 295, /*[1E100]*/ 1850 /** @stable ICU 64 */ 1851 UBLOCK_OTTOMAN_SIYAQ_NUMBERS = 296, /*[1ED00]*/ 1852 /** @stable ICU 64 */ 1853 UBLOCK_SMALL_KANA_EXTENSION = 297, /*[1B130]*/ 1854 /** @stable ICU 64 */ 1855 UBLOCK_SYMBOLS_AND_PICTOGRAPHS_EXTENDED_A = 298, /*[1FA70]*/ 1856 /** @stable ICU 64 */ 1857 UBLOCK_TAMIL_SUPPLEMENT = 299, /*[11FC0]*/ 1858 /** @stable ICU 64 */ 1859 UBLOCK_WANCHO = 300, /*[1E2C0]*/ 1860 1861 // New blocks in Unicode 13.0 1862 1863 /** @stable ICU 66 */ 1864 UBLOCK_CHORASMIAN = 301, /*[10FB0]*/ 1865 /** @stable ICU 66 */ 1866 UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_G = 302, /*[30000]*/ 1867 /** @stable ICU 66 */ 1868 UBLOCK_DIVES_AKURU = 303, /*[11900]*/ 1869 /** @stable ICU 66 */ 1870 UBLOCK_KHITAN_SMALL_SCRIPT = 304, /*[18B00]*/ 1871 /** @stable ICU 66 */ 1872 UBLOCK_LISU_SUPPLEMENT = 305, /*[11FB0]*/ 1873 /** @stable ICU 66 */ 1874 UBLOCK_SYMBOLS_FOR_LEGACY_COMPUTING = 306, /*[1FB00]*/ 1875 /** @stable ICU 66 */ 1876 UBLOCK_TANGUT_SUPPLEMENT = 307, /*[18D00]*/ 1877 /** @stable ICU 66 */ 1878 UBLOCK_YEZIDI = 308, /*[10E80]*/ 1879 1880 // New blocks in Unicode 14.0 1881 1882 /** @stable ICU 70 */ 1883 UBLOCK_ARABIC_EXTENDED_B = 309, /*[0870]*/ 1884 /** @stable ICU 70 */ 1885 UBLOCK_CYPRO_MINOAN = 310, /*[12F90]*/ 1886 /** @stable ICU 70 */ 1887 UBLOCK_ETHIOPIC_EXTENDED_B = 311, /*[1E7E0]*/ 1888 /** @stable ICU 70 */ 1889 UBLOCK_KANA_EXTENDED_B = 312, /*[1AFF0]*/ 1890 /** @stable ICU 70 */ 1891 UBLOCK_LATIN_EXTENDED_F = 313, /*[10780]*/ 1892 /** @stable ICU 70 */ 1893 UBLOCK_LATIN_EXTENDED_G = 314, /*[1DF00]*/ 1894 /** @stable ICU 70 */ 1895 UBLOCK_OLD_UYGHUR = 315, /*[10F70]*/ 1896 /** @stable ICU 70 */ 1897 UBLOCK_TANGSA = 316, /*[16A70]*/ 1898 /** @stable ICU 70 */ 1899 UBLOCK_TOTO = 317, /*[1E290]*/ 1900 /** @stable ICU 70 */ 1901 UBLOCK_UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS_EXTENDED_A = 318, /*[11AB0]*/ 1902 /** @stable ICU 70 */ 1903 UBLOCK_VITHKUQI = 319, /*[10570]*/ 1904 /** @stable ICU 70 */ 1905 UBLOCK_ZNAMENNY_MUSICAL_NOTATION = 320, /*[1CF00]*/ 1906 1907 // New blocks in Unicode 15.0 1908 1909 /** @stable ICU 72 */ 1910 UBLOCK_ARABIC_EXTENDED_C = 321, /*[10EC0]*/ 1911 /** @stable ICU 72 */ 1912 UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_H = 322, /*[31350]*/ 1913 /** @stable ICU 72 */ 1914 UBLOCK_CYRILLIC_EXTENDED_D = 323, /*[1E030]*/ 1915 /** @stable ICU 72 */ 1916 UBLOCK_DEVANAGARI_EXTENDED_A = 324, /*[11B00]*/ 1917 /** @stable ICU 72 */ 1918 UBLOCK_KAKTOVIK_NUMERALS = 325, /*[1D2C0]*/ 1919 /** @stable ICU 72 */ 1920 UBLOCK_KAWI = 326, /*[11F00]*/ 1921 /** @stable ICU 72 */ 1922 UBLOCK_NAG_MUNDARI = 327, /*[1E4D0]*/ 1923 1924 // New block in Unicode 15.1 1925 1926 /** @stable ICU 74 */ 1927 UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_I = 328, /*[2EBF0]*/ 1928 1929 #ifndef U_HIDE_DEPRECATED_API 1930 /** 1931 * One more than the highest normal UBlockCode value. 1932 * The highest value is available via u_getIntPropertyMaxValue(UCHAR_BLOCK). 1933 * 1934 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. 1935 */ 1936 UBLOCK_COUNT = 329, 1937 #endif // U_HIDE_DEPRECATED_API 1938 1939 /** @stable ICU 2.0 */ 1940 UBLOCK_INVALID_CODE=-1 1941 }; 1942 1943 /** @stable ICU 2.0 */ 1944 typedef enum UBlockCode UBlockCode; 1945 1946 /** 1947 * East Asian Width constants. 1948 * 1949 * @see UCHAR_EAST_ASIAN_WIDTH 1950 * @see u_getIntPropertyValue 1951 * @stable ICU 2.2 1952 */ 1953 typedef enum UEastAsianWidth { 1954 /* 1955 * Note: UEastAsianWidth constants are parsed by preparseucd.py. 1956 * It matches lines like 1957 * U_EA_<Unicode East_Asian_Width value name> 1958 */ 1959 1960 U_EA_NEUTRAL, /*[N]*/ 1961 U_EA_AMBIGUOUS, /*[A]*/ 1962 U_EA_HALFWIDTH, /*[H]*/ 1963 U_EA_FULLWIDTH, /*[F]*/ 1964 U_EA_NARROW, /*[Na]*/ 1965 U_EA_WIDE, /*[W]*/ 1966 #ifndef U_HIDE_DEPRECATED_API 1967 /** 1968 * One more than the highest normal UEastAsianWidth value. 1969 * The highest value is available via u_getIntPropertyMaxValue(UCHAR_EAST_ASIAN_WIDTH). 1970 * 1971 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. 1972 */ 1973 U_EA_COUNT 1974 #endif // U_HIDE_DEPRECATED_API 1975 } UEastAsianWidth; 1976 1977 /** 1978 * Selector constants for u_charName(). 1979 * u_charName() returns the "modern" name of a 1980 * Unicode character; or the name that was defined in 1981 * Unicode version 1.0, before the Unicode standard merged 1982 * with ISO-10646; or an "extended" name that gives each 1983 * Unicode code point a unique name. 1984 * 1985 * @see u_charName 1986 * @stable ICU 2.0 1987 */ 1988 typedef enum UCharNameChoice { 1989 /** Unicode character name (Name property). @stable ICU 2.0 */ 1990 U_UNICODE_CHAR_NAME, 1991 #ifndef U_HIDE_DEPRECATED_API 1992 /** 1993 * The Unicode_1_Name property value which is of little practical value. 1994 * Beginning with ICU 49, ICU APIs return an empty string for this name choice. 1995 * @deprecated ICU 49 1996 */ 1997 U_UNICODE_10_CHAR_NAME, 1998 #endif /* U_HIDE_DEPRECATED_API */ 1999 /** Standard or synthetic character name. @stable ICU 2.0 */ 2000 U_EXTENDED_CHAR_NAME = U_UNICODE_CHAR_NAME+2, 2001 /** Corrected name from NameAliases.txt. @stable ICU 4.4 */ 2002 U_CHAR_NAME_ALIAS, 2003 #ifndef U_HIDE_DEPRECATED_API 2004 /** 2005 * One more than the highest normal UCharNameChoice value. 2006 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. 2007 */ 2008 U_CHAR_NAME_CHOICE_COUNT 2009 #endif // U_HIDE_DEPRECATED_API 2010 } UCharNameChoice; 2011 2012 /** 2013 * Selector constants for u_getPropertyName() and 2014 * u_getPropertyValueName(). These selectors are used to choose which 2015 * name is returned for a given property or value. All properties and 2016 * values have a long name. Most have a short name, but some do not. 2017 * Unicode allows for additional names, beyond the long and short 2018 * name, which would be indicated by U_LONG_PROPERTY_NAME + i, where 2019 * i=1, 2,... 2020 * 2021 * @see u_getPropertyName() 2022 * @see u_getPropertyValueName() 2023 * @stable ICU 2.4 2024 */ 2025 typedef enum UPropertyNameChoice { 2026 U_SHORT_PROPERTY_NAME, 2027 U_LONG_PROPERTY_NAME, 2028 #ifndef U_HIDE_DEPRECATED_API 2029 /** 2030 * One more than the highest normal UPropertyNameChoice value. 2031 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. 2032 */ 2033 U_PROPERTY_NAME_CHOICE_COUNT 2034 #endif // U_HIDE_DEPRECATED_API 2035 } UPropertyNameChoice; 2036 2037 /** 2038 * Decomposition Type constants. 2039 * 2040 * @see UCHAR_DECOMPOSITION_TYPE 2041 * @stable ICU 2.2 2042 */ 2043 typedef enum UDecompositionType { 2044 /* 2045 * Note: UDecompositionType constants are parsed by preparseucd.py. 2046 * It matches lines like 2047 * U_DT_<Unicode Decomposition_Type value name> 2048 */ 2049 2050 U_DT_NONE, /*[none]*/ 2051 U_DT_CANONICAL, /*[can]*/ 2052 U_DT_COMPAT, /*[com]*/ 2053 U_DT_CIRCLE, /*[enc]*/ 2054 U_DT_FINAL, /*[fin]*/ 2055 U_DT_FONT, /*[font]*/ 2056 U_DT_FRACTION, /*[fra]*/ 2057 U_DT_INITIAL, /*[init]*/ 2058 U_DT_ISOLATED, /*[iso]*/ 2059 U_DT_MEDIAL, /*[med]*/ 2060 U_DT_NARROW, /*[nar]*/ 2061 U_DT_NOBREAK, /*[nb]*/ 2062 U_DT_SMALL, /*[sml]*/ 2063 U_DT_SQUARE, /*[sqr]*/ 2064 U_DT_SUB, /*[sub]*/ 2065 U_DT_SUPER, /*[sup]*/ 2066 U_DT_VERTICAL, /*[vert]*/ 2067 U_DT_WIDE, /*[wide]*/ 2068 #ifndef U_HIDE_DEPRECATED_API 2069 /** 2070 * One more than the highest normal UDecompositionType value. 2071 * The highest value is available via u_getIntPropertyMaxValue(UCHAR_DECOMPOSITION_TYPE). 2072 * 2073 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. 2074 */ 2075 U_DT_COUNT /* 18 */ 2076 #endif // U_HIDE_DEPRECATED_API 2077 } UDecompositionType; 2078 2079 /** 2080 * Joining Type constants. 2081 * 2082 * @see UCHAR_JOINING_TYPE 2083 * @stable ICU 2.2 2084 */ 2085 typedef enum UJoiningType { 2086 /* 2087 * Note: UJoiningType constants are parsed by preparseucd.py. 2088 * It matches lines like 2089 * U_JT_<Unicode Joining_Type value name> 2090 */ 2091 2092 U_JT_NON_JOINING, /*[U]*/ 2093 U_JT_JOIN_CAUSING, /*[C]*/ 2094 U_JT_DUAL_JOINING, /*[D]*/ 2095 U_JT_LEFT_JOINING, /*[L]*/ 2096 U_JT_RIGHT_JOINING, /*[R]*/ 2097 U_JT_TRANSPARENT, /*[T]*/ 2098 #ifndef U_HIDE_DEPRECATED_API 2099 /** 2100 * One more than the highest normal UJoiningType value. 2101 * The highest value is available via u_getIntPropertyMaxValue(UCHAR_JOINING_TYPE). 2102 * 2103 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. 2104 */ 2105 U_JT_COUNT /* 6 */ 2106 #endif // U_HIDE_DEPRECATED_API 2107 } UJoiningType; 2108 2109 /** 2110 * Joining Group constants. 2111 * 2112 * @see UCHAR_JOINING_GROUP 2113 * @stable ICU 2.2 2114 */ 2115 typedef enum UJoiningGroup { 2116 /* 2117 * Note: UJoiningGroup constants are parsed by preparseucd.py. 2118 * It matches lines like 2119 * U_JG_<Unicode Joining_Group value name> 2120 */ 2121 2122 U_JG_NO_JOINING_GROUP, 2123 U_JG_AIN, 2124 U_JG_ALAPH, 2125 U_JG_ALEF, 2126 U_JG_BEH, 2127 U_JG_BETH, 2128 U_JG_DAL, 2129 U_JG_DALATH_RISH, 2130 U_JG_E, 2131 U_JG_FEH, 2132 U_JG_FINAL_SEMKATH, 2133 U_JG_GAF, 2134 U_JG_GAMAL, 2135 U_JG_HAH, 2136 U_JG_TEH_MARBUTA_GOAL, /**< @stable ICU 4.6 */ 2137 U_JG_HAMZA_ON_HEH_GOAL=U_JG_TEH_MARBUTA_GOAL, 2138 U_JG_HE, 2139 U_JG_HEH, 2140 U_JG_HEH_GOAL, 2141 U_JG_HETH, 2142 U_JG_KAF, 2143 U_JG_KAPH, 2144 U_JG_KNOTTED_HEH, 2145 U_JG_LAM, 2146 U_JG_LAMADH, 2147 U_JG_MEEM, 2148 U_JG_MIM, 2149 U_JG_NOON, 2150 U_JG_NUN, 2151 U_JG_PE, 2152 U_JG_QAF, 2153 U_JG_QAPH, 2154 U_JG_REH, 2155 U_JG_REVERSED_PE, 2156 U_JG_SAD, 2157 U_JG_SADHE, 2158 U_JG_SEEN, 2159 U_JG_SEMKATH, 2160 U_JG_SHIN, 2161 U_JG_SWASH_KAF, 2162 U_JG_SYRIAC_WAW, 2163 U_JG_TAH, 2164 U_JG_TAW, 2165 U_JG_TEH_MARBUTA, 2166 U_JG_TETH, 2167 U_JG_WAW, 2168 U_JG_YEH, 2169 U_JG_YEH_BARREE, 2170 U_JG_YEH_WITH_TAIL, 2171 U_JG_YUDH, 2172 U_JG_YUDH_HE, 2173 U_JG_ZAIN, 2174 U_JG_FE, /**< @stable ICU 2.6 */ 2175 U_JG_KHAPH, /**< @stable ICU 2.6 */ 2176 U_JG_ZHAIN, /**< @stable ICU 2.6 */ 2177 U_JG_BURUSHASKI_YEH_BARREE, /**< @stable ICU 4.0 */ 2178 U_JG_FARSI_YEH, /**< @stable ICU 4.4 */ 2179 U_JG_NYA, /**< @stable ICU 4.4 */ 2180 U_JG_ROHINGYA_YEH, /**< @stable ICU 49 */ 2181 U_JG_MANICHAEAN_ALEPH, /**< @stable ICU 54 */ 2182 U_JG_MANICHAEAN_AYIN, /**< @stable ICU 54 */ 2183 U_JG_MANICHAEAN_BETH, /**< @stable ICU 54 */ 2184 U_JG_MANICHAEAN_DALETH, /**< @stable ICU 54 */ 2185 U_JG_MANICHAEAN_DHAMEDH, /**< @stable ICU 54 */ 2186 U_JG_MANICHAEAN_FIVE, /**< @stable ICU 54 */ 2187 U_JG_MANICHAEAN_GIMEL, /**< @stable ICU 54 */ 2188 U_JG_MANICHAEAN_HETH, /**< @stable ICU 54 */ 2189 U_JG_MANICHAEAN_HUNDRED, /**< @stable ICU 54 */ 2190 U_JG_MANICHAEAN_KAPH, /**< @stable ICU 54 */ 2191 U_JG_MANICHAEAN_LAMEDH, /**< @stable ICU 54 */ 2192 U_JG_MANICHAEAN_MEM, /**< @stable ICU 54 */ 2193 U_JG_MANICHAEAN_NUN, /**< @stable ICU 54 */ 2194 U_JG_MANICHAEAN_ONE, /**< @stable ICU 54 */ 2195 U_JG_MANICHAEAN_PE, /**< @stable ICU 54 */ 2196 U_JG_MANICHAEAN_QOPH, /**< @stable ICU 54 */ 2197 U_JG_MANICHAEAN_RESH, /**< @stable ICU 54 */ 2198 U_JG_MANICHAEAN_SADHE, /**< @stable ICU 54 */ 2199 U_JG_MANICHAEAN_SAMEKH, /**< @stable ICU 54 */ 2200 U_JG_MANICHAEAN_TAW, /**< @stable ICU 54 */ 2201 U_JG_MANICHAEAN_TEN, /**< @stable ICU 54 */ 2202 U_JG_MANICHAEAN_TETH, /**< @stable ICU 54 */ 2203 U_JG_MANICHAEAN_THAMEDH, /**< @stable ICU 54 */ 2204 U_JG_MANICHAEAN_TWENTY, /**< @stable ICU 54 */ 2205 U_JG_MANICHAEAN_WAW, /**< @stable ICU 54 */ 2206 U_JG_MANICHAEAN_YODH, /**< @stable ICU 54 */ 2207 U_JG_MANICHAEAN_ZAYIN, /**< @stable ICU 54 */ 2208 U_JG_STRAIGHT_WAW, /**< @stable ICU 54 */ 2209 U_JG_AFRICAN_FEH, /**< @stable ICU 58 */ 2210 U_JG_AFRICAN_NOON, /**< @stable ICU 58 */ 2211 U_JG_AFRICAN_QAF, /**< @stable ICU 58 */ 2212 2213 U_JG_MALAYALAM_BHA, /**< @stable ICU 60 */ 2214 U_JG_MALAYALAM_JA, /**< @stable ICU 60 */ 2215 U_JG_MALAYALAM_LLA, /**< @stable ICU 60 */ 2216 U_JG_MALAYALAM_LLLA, /**< @stable ICU 60 */ 2217 U_JG_MALAYALAM_NGA, /**< @stable ICU 60 */ 2218 U_JG_MALAYALAM_NNA, /**< @stable ICU 60 */ 2219 U_JG_MALAYALAM_NNNA, /**< @stable ICU 60 */ 2220 U_JG_MALAYALAM_NYA, /**< @stable ICU 60 */ 2221 U_JG_MALAYALAM_RA, /**< @stable ICU 60 */ 2222 U_JG_MALAYALAM_SSA, /**< @stable ICU 60 */ 2223 U_JG_MALAYALAM_TTA, /**< @stable ICU 60 */ 2224 2225 U_JG_HANIFI_ROHINGYA_KINNA_YA, /**< @stable ICU 62 */ 2226 U_JG_HANIFI_ROHINGYA_PA, /**< @stable ICU 62 */ 2227 2228 U_JG_THIN_YEH, /**< @stable ICU 70 */ 2229 U_JG_VERTICAL_TAIL, /**< @stable ICU 70 */ 2230 2231 #ifndef U_HIDE_DEPRECATED_API 2232 /** 2233 * One more than the highest normal UJoiningGroup value. 2234 * The highest value is available via u_getIntPropertyMaxValue(UCHAR_JOINING_GROUP). 2235 * 2236 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. 2237 */ 2238 U_JG_COUNT 2239 #endif // U_HIDE_DEPRECATED_API 2240 } UJoiningGroup; 2241 2242 /** 2243 * Grapheme Cluster Break constants. 2244 * 2245 * @see UCHAR_GRAPHEME_CLUSTER_BREAK 2246 * @stable ICU 3.4 2247 */ 2248 typedef enum UGraphemeClusterBreak { 2249 /* 2250 * Note: UGraphemeClusterBreak constants are parsed by preparseucd.py. 2251 * It matches lines like 2252 * U_GCB_<Unicode Grapheme_Cluster_Break value name> 2253 */ 2254 2255 U_GCB_OTHER = 0, /*[XX]*/ 2256 U_GCB_CONTROL = 1, /*[CN]*/ 2257 U_GCB_CR = 2, /*[CR]*/ 2258 U_GCB_EXTEND = 3, /*[EX]*/ 2259 U_GCB_L = 4, /*[L]*/ 2260 U_GCB_LF = 5, /*[LF]*/ 2261 U_GCB_LV = 6, /*[LV]*/ 2262 U_GCB_LVT = 7, /*[LVT]*/ 2263 U_GCB_T = 8, /*[T]*/ 2264 U_GCB_V = 9, /*[V]*/ 2265 /** @stable ICU 4.0 */ 2266 U_GCB_SPACING_MARK = 10, /*[SM]*/ /* from here on: new in Unicode 5.1/ICU 4.0 */ 2267 /** @stable ICU 4.0 */ 2268 U_GCB_PREPEND = 11, /*[PP]*/ 2269 /** @stable ICU 50 */ 2270 U_GCB_REGIONAL_INDICATOR = 12, /*[RI]*/ /* new in Unicode 6.2/ICU 50 */ 2271 /** @stable ICU 58 */ 2272 U_GCB_E_BASE = 13, /*[EB]*/ /* from here on: new in Unicode 9.0/ICU 58 */ 2273 /** @stable ICU 58 */ 2274 U_GCB_E_BASE_GAZ = 14, /*[EBG]*/ 2275 /** @stable ICU 58 */ 2276 U_GCB_E_MODIFIER = 15, /*[EM]*/ 2277 /** @stable ICU 58 */ 2278 U_GCB_GLUE_AFTER_ZWJ = 16, /*[GAZ]*/ 2279 /** @stable ICU 58 */ 2280 U_GCB_ZWJ = 17, /*[ZWJ]*/ 2281 2282 #ifndef U_HIDE_DEPRECATED_API 2283 /** 2284 * One more than the highest normal UGraphemeClusterBreak value. 2285 * The highest value is available via u_getIntPropertyMaxValue(UCHAR_GRAPHEME_CLUSTER_BREAK). 2286 * 2287 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. 2288 */ 2289 U_GCB_COUNT = 18 2290 #endif // U_HIDE_DEPRECATED_API 2291 } UGraphemeClusterBreak; 2292 2293 /** 2294 * Word Break constants. 2295 * (UWordBreak is a pre-existing enum type in ubrk.h for word break status tags.) 2296 * 2297 * @see UCHAR_WORD_BREAK 2298 * @stable ICU 3.4 2299 */ 2300 typedef enum UWordBreakValues { 2301 /* 2302 * Note: UWordBreakValues constants are parsed by preparseucd.py. 2303 * It matches lines like 2304 * U_WB_<Unicode Word_Break value name> 2305 */ 2306 2307 U_WB_OTHER = 0, /*[XX]*/ 2308 U_WB_ALETTER = 1, /*[LE]*/ 2309 U_WB_FORMAT = 2, /*[FO]*/ 2310 U_WB_KATAKANA = 3, /*[KA]*/ 2311 U_WB_MIDLETTER = 4, /*[ML]*/ 2312 U_WB_MIDNUM = 5, /*[MN]*/ 2313 U_WB_NUMERIC = 6, /*[NU]*/ 2314 U_WB_EXTENDNUMLET = 7, /*[EX]*/ 2315 /** @stable ICU 4.0 */ 2316 U_WB_CR = 8, /*[CR]*/ /* from here on: new in Unicode 5.1/ICU 4.0 */ 2317 /** @stable ICU 4.0 */ 2318 U_WB_EXTEND = 9, /*[Extend]*/ 2319 /** @stable ICU 4.0 */ 2320 U_WB_LF = 10, /*[LF]*/ 2321 /** @stable ICU 4.0 */ 2322 U_WB_MIDNUMLET =11, /*[MB]*/ 2323 /** @stable ICU 4.0 */ 2324 U_WB_NEWLINE =12, /*[NL]*/ 2325 /** @stable ICU 50 */ 2326 U_WB_REGIONAL_INDICATOR = 13, /*[RI]*/ /* new in Unicode 6.2/ICU 50 */ 2327 /** @stable ICU 52 */ 2328 U_WB_HEBREW_LETTER = 14, /*[HL]*/ /* from here on: new in Unicode 6.3/ICU 52 */ 2329 /** @stable ICU 52 */ 2330 U_WB_SINGLE_QUOTE = 15, /*[SQ]*/ 2331 /** @stable ICU 52 */ 2332 U_WB_DOUBLE_QUOTE = 16, /*[DQ]*/ 2333 /** @stable ICU 58 */ 2334 U_WB_E_BASE = 17, /*[EB]*/ /* from here on: new in Unicode 9.0/ICU 58 */ 2335 /** @stable ICU 58 */ 2336 U_WB_E_BASE_GAZ = 18, /*[EBG]*/ 2337 /** @stable ICU 58 */ 2338 U_WB_E_MODIFIER = 19, /*[EM]*/ 2339 /** @stable ICU 58 */ 2340 U_WB_GLUE_AFTER_ZWJ = 20, /*[GAZ]*/ 2341 /** @stable ICU 58 */ 2342 U_WB_ZWJ = 21, /*[ZWJ]*/ 2343 /** @stable ICU 62 */ 2344 U_WB_WSEGSPACE = 22, /*[WSEGSPACE]*/ 2345 2346 #ifndef U_HIDE_DEPRECATED_API 2347 /** 2348 * One more than the highest normal UWordBreakValues value. 2349 * The highest value is available via u_getIntPropertyMaxValue(UCHAR_WORD_BREAK). 2350 * 2351 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. 2352 */ 2353 U_WB_COUNT = 23 2354 #endif // U_HIDE_DEPRECATED_API 2355 } UWordBreakValues; 2356 2357 /** 2358 * Sentence Break constants. 2359 * 2360 * @see UCHAR_SENTENCE_BREAK 2361 * @stable ICU 3.4 2362 */ 2363 typedef enum USentenceBreak { 2364 /* 2365 * Note: USentenceBreak constants are parsed by preparseucd.py. 2366 * It matches lines like 2367 * U_SB_<Unicode Sentence_Break value name> 2368 */ 2369 2370 U_SB_OTHER = 0, /*[XX]*/ 2371 U_SB_ATERM = 1, /*[AT]*/ 2372 U_SB_CLOSE = 2, /*[CL]*/ 2373 U_SB_FORMAT = 3, /*[FO]*/ 2374 U_SB_LOWER = 4, /*[LO]*/ 2375 U_SB_NUMERIC = 5, /*[NU]*/ 2376 U_SB_OLETTER = 6, /*[LE]*/ 2377 U_SB_SEP = 7, /*[SE]*/ 2378 U_SB_SP = 8, /*[SP]*/ 2379 U_SB_STERM = 9, /*[ST]*/ 2380 U_SB_UPPER = 10, /*[UP]*/ 2381 U_SB_CR = 11, /*[CR]*/ /* from here on: new in Unicode 5.1/ICU 4.0 */ 2382 U_SB_EXTEND = 12, /*[EX]*/ 2383 U_SB_LF = 13, /*[LF]*/ 2384 U_SB_SCONTINUE = 14, /*[SC]*/ 2385 #ifndef U_HIDE_DEPRECATED_API 2386 /** 2387 * One more than the highest normal USentenceBreak value. 2388 * The highest value is available via u_getIntPropertyMaxValue(UCHAR_SENTENCE_BREAK). 2389 * 2390 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. 2391 */ 2392 U_SB_COUNT = 15 2393 #endif // U_HIDE_DEPRECATED_API 2394 } USentenceBreak; 2395 2396 /** 2397 * Line Break constants. 2398 * 2399 * @see UCHAR_LINE_BREAK 2400 * @stable ICU 2.2 2401 */ 2402 typedef enum ULineBreak { 2403 /* 2404 * Note: ULineBreak constants are parsed by preparseucd.py. 2405 * It matches lines like 2406 * U_LB_<Unicode Line_Break value name> 2407 */ 2408 2409 U_LB_UNKNOWN = 0, /*[XX]*/ 2410 U_LB_AMBIGUOUS = 1, /*[AI]*/ 2411 U_LB_ALPHABETIC = 2, /*[AL]*/ 2412 U_LB_BREAK_BOTH = 3, /*[B2]*/ 2413 U_LB_BREAK_AFTER = 4, /*[BA]*/ 2414 U_LB_BREAK_BEFORE = 5, /*[BB]*/ 2415 U_LB_MANDATORY_BREAK = 6, /*[BK]*/ 2416 U_LB_CONTINGENT_BREAK = 7, /*[CB]*/ 2417 U_LB_CLOSE_PUNCTUATION = 8, /*[CL]*/ 2418 U_LB_COMBINING_MARK = 9, /*[CM]*/ 2419 U_LB_CARRIAGE_RETURN = 10, /*[CR]*/ 2420 U_LB_EXCLAMATION = 11, /*[EX]*/ 2421 U_LB_GLUE = 12, /*[GL]*/ 2422 U_LB_HYPHEN = 13, /*[HY]*/ 2423 U_LB_IDEOGRAPHIC = 14, /*[ID]*/ 2424 /** Renamed from the misspelled "inseperable" in Unicode 4.0.1/ICU 3.0 @stable ICU 3.0 */ 2425 U_LB_INSEPARABLE = 15, /*[IN]*/ 2426 U_LB_INSEPERABLE = U_LB_INSEPARABLE, 2427 U_LB_INFIX_NUMERIC = 16, /*[IS]*/ 2428 U_LB_LINE_FEED = 17, /*[LF]*/ 2429 U_LB_NONSTARTER = 18, /*[NS]*/ 2430 U_LB_NUMERIC = 19, /*[NU]*/ 2431 U_LB_OPEN_PUNCTUATION = 20, /*[OP]*/ 2432 U_LB_POSTFIX_NUMERIC = 21, /*[PO]*/ 2433 U_LB_PREFIX_NUMERIC = 22, /*[PR]*/ 2434 U_LB_QUOTATION = 23, /*[QU]*/ 2435 U_LB_COMPLEX_CONTEXT = 24, /*[SA]*/ 2436 U_LB_SURROGATE = 25, /*[SG]*/ 2437 U_LB_SPACE = 26, /*[SP]*/ 2438 U_LB_BREAK_SYMBOLS = 27, /*[SY]*/ 2439 U_LB_ZWSPACE = 28, /*[ZW]*/ 2440 /** @stable ICU 2.6 */ 2441 U_LB_NEXT_LINE = 29, /*[NL]*/ /* from here on: new in Unicode 4/ICU 2.6 */ 2442 /** @stable ICU 2.6 */ 2443 U_LB_WORD_JOINER = 30, /*[WJ]*/ 2444 /** @stable ICU 3.4 */ 2445 U_LB_H2 = 31, /*[H2]*/ /* from here on: new in Unicode 4.1/ICU 3.4 */ 2446 /** @stable ICU 3.4 */ 2447 U_LB_H3 = 32, /*[H3]*/ 2448 /** @stable ICU 3.4 */ 2449 U_LB_JL = 33, /*[JL]*/ 2450 /** @stable ICU 3.4 */ 2451 U_LB_JT = 34, /*[JT]*/ 2452 /** @stable ICU 3.4 */ 2453 U_LB_JV = 35, /*[JV]*/ 2454 /** @stable ICU 4.4 */ 2455 U_LB_CLOSE_PARENTHESIS = 36, /*[CP]*/ /* new in Unicode 5.2/ICU 4.4 */ 2456 /** @stable ICU 49 */ 2457 U_LB_CONDITIONAL_JAPANESE_STARTER = 37,/*[CJ]*/ /* new in Unicode 6.1/ICU 49 */ 2458 /** @stable ICU 49 */ 2459 U_LB_HEBREW_LETTER = 38, /*[HL]*/ /* new in Unicode 6.1/ICU 49 */ 2460 /** @stable ICU 50 */ 2461 U_LB_REGIONAL_INDICATOR = 39,/*[RI]*/ /* new in Unicode 6.2/ICU 50 */ 2462 /** @stable ICU 58 */ 2463 U_LB_E_BASE = 40, /*[EB]*/ /* from here on: new in Unicode 9.0/ICU 58 */ 2464 /** @stable ICU 58 */ 2465 U_LB_E_MODIFIER = 41, /*[EM]*/ 2466 /** @stable ICU 58 */ 2467 U_LB_ZWJ = 42, /*[ZWJ]*/ 2468 /** @stable ICU 74 */ 2469 U_LB_AKSARA = 43, /*[AK]*/ 2470 /** @stable ICU 74 */ 2471 U_LB_AKSARA_PREBASE = 44, /*[AP]*/ 2472 /** @stable ICU 74 */ 2473 U_LB_AKSARA_START = 45, /*[AS]*/ 2474 /** @stable ICU 74 */ 2475 U_LB_VIRAMA_FINAL = 46, /*[VF]*/ 2476 /** @stable ICU 74 */ 2477 U_LB_VIRAMA = 47, /*[VI]*/ 2478 #ifndef U_HIDE_DEPRECATED_API 2479 /** 2480 * One more than the highest normal ULineBreak value. 2481 * The highest value is available via u_getIntPropertyMaxValue(UCHAR_LINE_BREAK). 2482 * 2483 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. 2484 */ 2485 U_LB_COUNT = 48 2486 #endif // U_HIDE_DEPRECATED_API 2487 } ULineBreak; 2488 2489 /** 2490 * Numeric Type constants. 2491 * 2492 * @see UCHAR_NUMERIC_TYPE 2493 * @stable ICU 2.2 2494 */ 2495 typedef enum UNumericType { 2496 /* 2497 * Note: UNumericType constants are parsed by preparseucd.py. 2498 * It matches lines like 2499 * U_NT_<Unicode Numeric_Type value name> 2500 */ 2501 2502 U_NT_NONE, /*[None]*/ 2503 U_NT_DECIMAL, /*[de]*/ 2504 U_NT_DIGIT, /*[di]*/ 2505 U_NT_NUMERIC, /*[nu]*/ 2506 #ifndef U_HIDE_DEPRECATED_API 2507 /** 2508 * One more than the highest normal UNumericType value. 2509 * The highest value is available via u_getIntPropertyMaxValue(UCHAR_NUMERIC_TYPE). 2510 * 2511 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. 2512 */ 2513 U_NT_COUNT 2514 #endif // U_HIDE_DEPRECATED_API 2515 } UNumericType; 2516 2517 /** 2518 * Hangul Syllable Type constants. 2519 * 2520 * @see UCHAR_HANGUL_SYLLABLE_TYPE 2521 * @stable ICU 2.6 2522 */ 2523 typedef enum UHangulSyllableType { 2524 /* 2525 * Note: UHangulSyllableType constants are parsed by preparseucd.py. 2526 * It matches lines like 2527 * U_HST_<Unicode Hangul_Syllable_Type value name> 2528 */ 2529 2530 U_HST_NOT_APPLICABLE, /*[NA]*/ 2531 U_HST_LEADING_JAMO, /*[L]*/ 2532 U_HST_VOWEL_JAMO, /*[V]*/ 2533 U_HST_TRAILING_JAMO, /*[T]*/ 2534 U_HST_LV_SYLLABLE, /*[LV]*/ 2535 U_HST_LVT_SYLLABLE, /*[LVT]*/ 2536 #ifndef U_HIDE_DEPRECATED_API 2537 /** 2538 * One more than the highest normal UHangulSyllableType value. 2539 * The highest value is available via u_getIntPropertyMaxValue(UCHAR_HANGUL_SYLLABLE_TYPE). 2540 * 2541 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. 2542 */ 2543 U_HST_COUNT 2544 #endif // U_HIDE_DEPRECATED_API 2545 } UHangulSyllableType; 2546 2547 /** 2548 * Indic Positional Category constants. 2549 * 2550 * @see UCHAR_INDIC_POSITIONAL_CATEGORY 2551 * @stable ICU 63 2552 */ 2553 typedef enum UIndicPositionalCategory { 2554 /* 2555 * Note: UIndicPositionalCategory constants are parsed by preparseucd.py. 2556 * It matches lines like 2557 * U_INPC_<Unicode Indic_Positional_Category value name> 2558 */ 2559 2560 /** @stable ICU 63 */ 2561 U_INPC_NA, 2562 /** @stable ICU 63 */ 2563 U_INPC_BOTTOM, 2564 /** @stable ICU 63 */ 2565 U_INPC_BOTTOM_AND_LEFT, 2566 /** @stable ICU 63 */ 2567 U_INPC_BOTTOM_AND_RIGHT, 2568 /** @stable ICU 63 */ 2569 U_INPC_LEFT, 2570 /** @stable ICU 63 */ 2571 U_INPC_LEFT_AND_RIGHT, 2572 /** @stable ICU 63 */ 2573 U_INPC_OVERSTRUCK, 2574 /** @stable ICU 63 */ 2575 U_INPC_RIGHT, 2576 /** @stable ICU 63 */ 2577 U_INPC_TOP, 2578 /** @stable ICU 63 */ 2579 U_INPC_TOP_AND_BOTTOM, 2580 /** @stable ICU 63 */ 2581 U_INPC_TOP_AND_BOTTOM_AND_RIGHT, 2582 /** @stable ICU 63 */ 2583 U_INPC_TOP_AND_LEFT, 2584 /** @stable ICU 63 */ 2585 U_INPC_TOP_AND_LEFT_AND_RIGHT, 2586 /** @stable ICU 63 */ 2587 U_INPC_TOP_AND_RIGHT, 2588 /** @stable ICU 63 */ 2589 U_INPC_VISUAL_ORDER_LEFT, 2590 /** @stable ICU 66 */ 2591 U_INPC_TOP_AND_BOTTOM_AND_LEFT, 2592 } UIndicPositionalCategory; 2593 2594 /** 2595 * Indic Syllabic Category constants. 2596 * 2597 * @see UCHAR_INDIC_SYLLABIC_CATEGORY 2598 * @stable ICU 63 2599 */ 2600 typedef enum UIndicSyllabicCategory { 2601 /* 2602 * Note: UIndicSyllabicCategory constants are parsed by preparseucd.py. 2603 * It matches lines like 2604 * U_INSC_<Unicode Indic_Syllabic_Category value name> 2605 */ 2606 2607 /** @stable ICU 63 */ 2608 U_INSC_OTHER, 2609 /** @stable ICU 63 */ 2610 U_INSC_AVAGRAHA, 2611 /** @stable ICU 63 */ 2612 U_INSC_BINDU, 2613 /** @stable ICU 63 */ 2614 U_INSC_BRAHMI_JOINING_NUMBER, 2615 /** @stable ICU 63 */ 2616 U_INSC_CANTILLATION_MARK, 2617 /** @stable ICU 63 */ 2618 U_INSC_CONSONANT, 2619 /** @stable ICU 63 */ 2620 U_INSC_CONSONANT_DEAD, 2621 /** @stable ICU 63 */ 2622 U_INSC_CONSONANT_FINAL, 2623 /** @stable ICU 63 */ 2624 U_INSC_CONSONANT_HEAD_LETTER, 2625 /** @stable ICU 63 */ 2626 U_INSC_CONSONANT_INITIAL_POSTFIXED, 2627 /** @stable ICU 63 */ 2628 U_INSC_CONSONANT_KILLER, 2629 /** @stable ICU 63 */ 2630 U_INSC_CONSONANT_MEDIAL, 2631 /** @stable ICU 63 */ 2632 U_INSC_CONSONANT_PLACEHOLDER, 2633 /** @stable ICU 63 */ 2634 U_INSC_CONSONANT_PRECEDING_REPHA, 2635 /** @stable ICU 63 */ 2636 U_INSC_CONSONANT_PREFIXED, 2637 /** @stable ICU 63 */ 2638 U_INSC_CONSONANT_SUBJOINED, 2639 /** @stable ICU 63 */ 2640 U_INSC_CONSONANT_SUCCEEDING_REPHA, 2641 /** @stable ICU 63 */ 2642 U_INSC_CONSONANT_WITH_STACKER, 2643 /** @stable ICU 63 */ 2644 U_INSC_GEMINATION_MARK, 2645 /** @stable ICU 63 */ 2646 U_INSC_INVISIBLE_STACKER, 2647 /** @stable ICU 63 */ 2648 U_INSC_JOINER, 2649 /** @stable ICU 63 */ 2650 U_INSC_MODIFYING_LETTER, 2651 /** @stable ICU 63 */ 2652 U_INSC_NON_JOINER, 2653 /** @stable ICU 63 */ 2654 U_INSC_NUKTA, 2655 /** @stable ICU 63 */ 2656 U_INSC_NUMBER, 2657 /** @stable ICU 63 */ 2658 U_INSC_NUMBER_JOINER, 2659 /** @stable ICU 63 */ 2660 U_INSC_PURE_KILLER, 2661 /** @stable ICU 63 */ 2662 U_INSC_REGISTER_SHIFTER, 2663 /** @stable ICU 63 */ 2664 U_INSC_SYLLABLE_MODIFIER, 2665 /** @stable ICU 63 */ 2666 U_INSC_TONE_LETTER, 2667 /** @stable ICU 63 */ 2668 U_INSC_TONE_MARK, 2669 /** @stable ICU 63 */ 2670 U_INSC_VIRAMA, 2671 /** @stable ICU 63 */ 2672 U_INSC_VISARGA, 2673 /** @stable ICU 63 */ 2674 U_INSC_VOWEL, 2675 /** @stable ICU 63 */ 2676 U_INSC_VOWEL_DEPENDENT, 2677 /** @stable ICU 63 */ 2678 U_INSC_VOWEL_INDEPENDENT, 2679 } UIndicSyllabicCategory; 2680 2681 /** 2682 * Vertical Orientation constants. 2683 * 2684 * @see UCHAR_VERTICAL_ORIENTATION 2685 * @stable ICU 63 2686 */ 2687 typedef enum UVerticalOrientation { 2688 /* 2689 * Note: UVerticalOrientation constants are parsed by preparseucd.py. 2690 * It matches lines like 2691 * U_VO_<Unicode Vertical_Orientation value name> 2692 */ 2693 2694 /** @stable ICU 63 */ 2695 U_VO_ROTATED, 2696 /** @stable ICU 63 */ 2697 U_VO_TRANSFORMED_ROTATED, 2698 /** @stable ICU 63 */ 2699 U_VO_TRANSFORMED_UPRIGHT, 2700 /** @stable ICU 63 */ 2701 U_VO_UPRIGHT, 2702 } UVerticalOrientation; 2703 2704 /** 2705 * Check a binary Unicode property for a code point. 2706 * 2707 * Unicode, especially in version 3.2, defines many more properties than the 2708 * original set in UnicodeData.txt. 2709 * 2710 * The properties APIs are intended to reflect Unicode properties as defined 2711 * in the Unicode Character Database (UCD) and Unicode Technical Reports (UTR). 2712 * For details about the properties see http://www.unicode.org/ucd/ . 2713 * For names of Unicode properties see the UCD file PropertyAliases.txt. 2714 * 2715 * Important: If ICU is built with UCD files from Unicode versions below 3.2, 2716 * then properties marked with "new in Unicode 3.2" are not or not fully available. 2717 * 2718 * @param c Code point to test. 2719 * @param which UProperty selector constant, identifies which binary property to check. 2720 * Must be UCHAR_BINARY_START<=which<UCHAR_BINARY_LIMIT. 2721 * @return true or false according to the binary Unicode property value for c. 2722 * Also false if 'which' is out of bounds or if the Unicode version 2723 * does not have data for the property at all. 2724 * 2725 * @see UProperty 2726 * @see u_getBinaryPropertySet 2727 * @see u_getIntPropertyValue 2728 * @see u_getUnicodeVersion 2729 * @stable ICU 2.1 2730 */ 2731 U_CAPI UBool U_EXPORT2 2732 u_hasBinaryProperty(UChar32 c, UProperty which); 2733 2734 /** 2735 * Returns true if the property is true for the string. 2736 * Same as u_hasBinaryProperty(single code point, which) 2737 * if the string contains exactly one code point. 2738 * 2739 * Most properties apply only to single code points. 2740 * <a href="https://www.unicode.org/reports/tr51/#Emoji_Sets">UTS #51 Unicode Emoji</a> 2741 * defines several properties of strings. 2742 * 2743 * @param s String to test. 2744 * @param length Length of the string, or negative if NUL-terminated. 2745 * @param which UProperty selector constant, identifies which binary property to check. 2746 * Must be UCHAR_BINARY_START<=which<UCHAR_BINARY_LIMIT. 2747 * @return true or false according to the binary Unicode property value for the string. 2748 * Also false if 'which' is out of bounds or if the Unicode version 2749 * does not have data for the property at all. 2750 * 2751 * @see UProperty 2752 * @see u_hasBinaryProperty 2753 * @see u_getBinaryPropertySet 2754 * @see u_getIntPropertyValue 2755 * @see u_getUnicodeVersion 2756 * @stable ICU 70 2757 */ 2758 U_CAPI UBool U_EXPORT2 2759 u_stringHasBinaryProperty(const UChar *s, int32_t length, UProperty which); 2760 2761 /** 2762 * Returns a frozen USet for a binary property. 2763 * The library retains ownership over the returned object. 2764 * Sets an error code if the property number is not one for a binary property. 2765 * 2766 * The returned set contains all code points for which the property is true. 2767 * 2768 * @param property UCHAR_BINARY_START..UCHAR_BINARY_LIMIT-1 2769 * @param pErrorCode an in/out ICU UErrorCode 2770 * @return the property as a set 2771 * @see UProperty 2772 * @see u_hasBinaryProperty 2773 * @see Unicode::fromUSet 2774 * @stable ICU 63 2775 */ 2776 U_CAPI const USet * U_EXPORT2 2777 u_getBinaryPropertySet(UProperty property, UErrorCode *pErrorCode); 2778 2779 /** 2780 * Check if a code point has the Alphabetic Unicode property. 2781 * Same as u_hasBinaryProperty(c, UCHAR_ALPHABETIC). 2782 * This is different from u_isalpha! 2783 * @param c Code point to test 2784 * @return true if the code point has the Alphabetic Unicode property, false otherwise 2785 * 2786 * @see UCHAR_ALPHABETIC 2787 * @see u_isalpha 2788 * @see u_hasBinaryProperty 2789 * @stable ICU 2.1 2790 */ 2791 U_CAPI UBool U_EXPORT2 2792 u_isUAlphabetic(UChar32 c); 2793 2794 /** 2795 * Check if a code point has the Lowercase Unicode property. 2796 * Same as u_hasBinaryProperty(c, UCHAR_LOWERCASE). 2797 * This is different from u_islower! 2798 * @param c Code point to test 2799 * @return true if the code point has the Lowercase Unicode property, false otherwise 2800 * 2801 * @see UCHAR_LOWERCASE 2802 * @see u_islower 2803 * @see u_hasBinaryProperty 2804 * @stable ICU 2.1 2805 */ 2806 U_CAPI UBool U_EXPORT2 2807 u_isULowercase(UChar32 c); 2808 2809 /** 2810 * Check if a code point has the Uppercase Unicode property. 2811 * Same as u_hasBinaryProperty(c, UCHAR_UPPERCASE). 2812 * This is different from u_isupper! 2813 * @param c Code point to test 2814 * @return true if the code point has the Uppercase Unicode property, false otherwise 2815 * 2816 * @see UCHAR_UPPERCASE 2817 * @see u_isupper 2818 * @see u_hasBinaryProperty 2819 * @stable ICU 2.1 2820 */ 2821 U_CAPI UBool U_EXPORT2 2822 u_isUUppercase(UChar32 c); 2823 2824 /** 2825 * Check if a code point has the White_Space Unicode property. 2826 * Same as u_hasBinaryProperty(c, UCHAR_WHITE_SPACE). 2827 * This is different from both u_isspace and u_isWhitespace! 2828 * 2829 * Note: There are several ICU whitespace functions; please see the uchar.h 2830 * file documentation for a detailed comparison. 2831 * 2832 * @param c Code point to test 2833 * @return true if the code point has the White_Space Unicode property, false otherwise. 2834 * 2835 * @see UCHAR_WHITE_SPACE 2836 * @see u_isWhitespace 2837 * @see u_isspace 2838 * @see u_isJavaSpaceChar 2839 * @see u_hasBinaryProperty 2840 * @stable ICU 2.1 2841 */ 2842 U_CAPI UBool U_EXPORT2 2843 u_isUWhiteSpace(UChar32 c); 2844 2845 /** 2846 * Get the property value for an enumerated or integer Unicode property for a code point. 2847 * Also returns binary and mask property values. 2848 * 2849 * Unicode, especially in version 3.2, defines many more properties than the 2850 * original set in UnicodeData.txt. 2851 * 2852 * The properties APIs are intended to reflect Unicode properties as defined 2853 * in the Unicode Character Database (UCD) and Unicode Technical Reports (UTR). 2854 * For details about the properties see http://www.unicode.org/ . 2855 * For names of Unicode properties see the UCD file PropertyAliases.txt. 2856 * 2857 * Sample usage: 2858 * UEastAsianWidth ea=(UEastAsianWidth)u_getIntPropertyValue(c, UCHAR_EAST_ASIAN_WIDTH); 2859 * UBool b=(UBool)u_getIntPropertyValue(c, UCHAR_IDEOGRAPHIC); 2860 * 2861 * @param c Code point to test. 2862 * @param which UProperty selector constant, identifies which property to check. 2863 * Must be UCHAR_BINARY_START<=which<UCHAR_BINARY_LIMIT 2864 * or UCHAR_INT_START<=which<UCHAR_INT_LIMIT 2865 * or UCHAR_MASK_START<=which<UCHAR_MASK_LIMIT. 2866 * @return Numeric value that is directly the property value or, 2867 * for enumerated properties, corresponds to the numeric value of the enumerated 2868 * constant of the respective property value enumeration type 2869 * (cast to enum type if necessary). 2870 * Returns 0 or 1 (for false/true) for binary Unicode properties. 2871 * Returns a bit-mask for mask properties. 2872 * Returns 0 if 'which' is out of bounds or if the Unicode version 2873 * does not have data for the property at all, or not for this code point. 2874 * 2875 * @see UProperty 2876 * @see u_hasBinaryProperty 2877 * @see u_getIntPropertyMinValue 2878 * @see u_getIntPropertyMaxValue 2879 * @see u_getIntPropertyMap 2880 * @see u_getUnicodeVersion 2881 * @stable ICU 2.2 2882 */ 2883 U_CAPI int32_t U_EXPORT2 2884 u_getIntPropertyValue(UChar32 c, UProperty which); 2885 2886 /** 2887 * Get the minimum value for an enumerated/integer/binary Unicode property. 2888 * Can be used together with u_getIntPropertyMaxValue 2889 * to allocate arrays of UnicodeSet or similar. 2890 * 2891 * @param which UProperty selector constant, identifies which binary property to check. 2892 * Must be UCHAR_BINARY_START<=which<UCHAR_BINARY_LIMIT 2893 * or UCHAR_INT_START<=which<UCHAR_INT_LIMIT. 2894 * @return Minimum value returned by u_getIntPropertyValue for a Unicode property. 2895 * 0 if the property selector is out of range. 2896 * 2897 * @see UProperty 2898 * @see u_hasBinaryProperty 2899 * @see u_getUnicodeVersion 2900 * @see u_getIntPropertyMaxValue 2901 * @see u_getIntPropertyValue 2902 * @stable ICU 2.2 2903 */ 2904 U_CAPI int32_t U_EXPORT2 2905 u_getIntPropertyMinValue(UProperty which); 2906 2907 /** 2908 * Get the maximum value for an enumerated/integer/binary Unicode property. 2909 * Can be used together with u_getIntPropertyMinValue 2910 * to allocate arrays of UnicodeSet or similar. 2911 * 2912 * Examples for min/max values (for Unicode 3.2): 2913 * 2914 * - UCHAR_BIDI_CLASS: 0/18 (U_LEFT_TO_RIGHT/U_BOUNDARY_NEUTRAL) 2915 * - UCHAR_SCRIPT: 0/45 (USCRIPT_COMMON/USCRIPT_TAGBANWA) 2916 * - UCHAR_IDEOGRAPHIC: 0/1 (false/true) 2917 * 2918 * For undefined UProperty constant values, min/max values will be 0/-1. 2919 * 2920 * @param which UProperty selector constant, identifies which binary property to check. 2921 * Must be UCHAR_BINARY_START<=which<UCHAR_BINARY_LIMIT 2922 * or UCHAR_INT_START<=which<UCHAR_INT_LIMIT. 2923 * @return Maximum value returned by u_getIntPropertyValue for a Unicode property. 2924 * <=0 if the property selector is out of range. 2925 * 2926 * @see UProperty 2927 * @see u_hasBinaryProperty 2928 * @see u_getUnicodeVersion 2929 * @see u_getIntPropertyMaxValue 2930 * @see u_getIntPropertyValue 2931 * @stable ICU 2.2 2932 */ 2933 U_CAPI int32_t U_EXPORT2 2934 u_getIntPropertyMaxValue(UProperty which); 2935 2936 /** 2937 * Returns an immutable UCPMap for an enumerated/catalog/int-valued property. 2938 * The library retains ownership over the returned object. 2939 * Sets an error code if the property number is not one for an "int property". 2940 * 2941 * The returned object maps all Unicode code points to their values for that property. 2942 * For documentation of the integer values see u_getIntPropertyValue(). 2943 * 2944 * @param property UCHAR_INT_START..UCHAR_INT_LIMIT-1 2945 * @param pErrorCode an in/out ICU UErrorCode 2946 * @return the property as a map 2947 * @see UProperty 2948 * @see u_getIntPropertyValue 2949 * @stable ICU 63 2950 */ 2951 U_CAPI const UCPMap * U_EXPORT2 2952 u_getIntPropertyMap(UProperty property, UErrorCode *pErrorCode); 2953 2954 /** 2955 * Get the numeric value for a Unicode code point as defined in the 2956 * Unicode Character Database. 2957 * 2958 * A "double" return type is necessary because 2959 * some numeric values are fractions, negative, or too large for int32_t. 2960 * 2961 * For characters without any numeric values in the Unicode Character Database, 2962 * this function will return U_NO_NUMERIC_VALUE. 2963 * Note: This is different from the Unicode Standard which specifies NaN as the default value. 2964 * (NaN is not available on all platforms.) 2965 * 2966 * Similar to java.lang.Character.getNumericValue(), but u_getNumericValue() 2967 * also supports negative values, large values, and fractions, 2968 * while Java's getNumericValue() returns values 10..35 for ASCII letters. 2969 * 2970 * @param c Code point to get the numeric value for. 2971 * @return Numeric value of c, or U_NO_NUMERIC_VALUE if none is defined. 2972 * 2973 * @see U_NO_NUMERIC_VALUE 2974 * @stable ICU 2.2 2975 */ 2976 U_CAPI double U_EXPORT2 2977 u_getNumericValue(UChar32 c); 2978 2979 /** 2980 * Special value that is returned by u_getNumericValue when 2981 * no numeric value is defined for a code point. 2982 * 2983 * @see u_getNumericValue 2984 * @stable ICU 2.2 2985 */ 2986 #define U_NO_NUMERIC_VALUE ((double)-123456789.) 2987 2988 /** 2989 * Determines whether the specified code point has the general category "Ll" 2990 * (lowercase letter). 2991 * 2992 * Same as java.lang.Character.isLowerCase(). 2993 * 2994 * This misses some characters that are also lowercase but 2995 * have a different general category value. 2996 * In order to include those, use UCHAR_LOWERCASE. 2997 * 2998 * In addition to being equivalent to a Java function, this also serves 2999 * as a C/POSIX migration function. 3000 * See the comments about C/POSIX character classification functions in the 3001 * documentation at the top of this header file. 3002 * 3003 * @param c the code point to be tested 3004 * @return true if the code point is an Ll lowercase letter 3005 * 3006 * @see UCHAR_LOWERCASE 3007 * @see u_isupper 3008 * @see u_istitle 3009 * @stable ICU 2.0 3010 */ 3011 U_CAPI UBool U_EXPORT2 3012 u_islower(UChar32 c); 3013 3014 /** 3015 * Determines whether the specified code point has the general category "Lu" 3016 * (uppercase letter). 3017 * 3018 * Same as java.lang.Character.isUpperCase(). 3019 * 3020 * This misses some characters that are also uppercase but 3021 * have a different general category value. 3022 * In order to include those, use UCHAR_UPPERCASE. 3023 * 3024 * In addition to being equivalent to a Java function, this also serves 3025 * as a C/POSIX migration function. 3026 * See the comments about C/POSIX character classification functions in the 3027 * documentation at the top of this header file. 3028 * 3029 * @param c the code point to be tested 3030 * @return true if the code point is an Lu uppercase letter 3031 * 3032 * @see UCHAR_UPPERCASE 3033 * @see u_islower 3034 * @see u_istitle 3035 * @see u_tolower 3036 * @stable ICU 2.0 3037 */ 3038 U_CAPI UBool U_EXPORT2 3039 u_isupper(UChar32 c); 3040 3041 /** 3042 * Determines whether the specified code point is a titlecase letter. 3043 * True for general category "Lt" (titlecase letter). 3044 * 3045 * Same as java.lang.Character.isTitleCase(). 3046 * 3047 * @param c the code point to be tested 3048 * @return true if the code point is an Lt titlecase letter 3049 * 3050 * @see u_isupper 3051 * @see u_islower 3052 * @see u_totitle 3053 * @stable ICU 2.0 3054 */ 3055 U_CAPI UBool U_EXPORT2 3056 u_istitle(UChar32 c); 3057 3058 /** 3059 * Determines whether the specified code point is a digit character according to Java. 3060 * True for characters with general category "Nd" (decimal digit numbers). 3061 * Beginning with Unicode 4, this is the same as 3062 * testing for the Numeric_Type of Decimal. 3063 * 3064 * Same as java.lang.Character.isDigit(). 3065 * 3066 * In addition to being equivalent to a Java function, this also serves 3067 * as a C/POSIX migration function. 3068 * See the comments about C/POSIX character classification functions in the 3069 * documentation at the top of this header file. 3070 * 3071 * @param c the code point to be tested 3072 * @return true if the code point is a digit character according to Character.isDigit() 3073 * 3074 * @stable ICU 2.0 3075 */ 3076 U_CAPI UBool U_EXPORT2 3077 u_isdigit(UChar32 c); 3078 3079 /** 3080 * Determines whether the specified code point is a letter character. 3081 * True for general categories "L" (letters). 3082 * 3083 * Same as java.lang.Character.isLetter(). 3084 * 3085 * In addition to being equivalent to a Java function, this also serves 3086 * as a C/POSIX migration function. 3087 * See the comments about C/POSIX character classification functions in the 3088 * documentation at the top of this header file. 3089 * 3090 * @param c the code point to be tested 3091 * @return true if the code point is a letter character 3092 * 3093 * @see u_isdigit 3094 * @see u_isalnum 3095 * @stable ICU 2.0 3096 */ 3097 U_CAPI UBool U_EXPORT2 3098 u_isalpha(UChar32 c); 3099 3100 /** 3101 * Determines whether the specified code point is an alphanumeric character 3102 * (letter or digit) according to Java. 3103 * True for characters with general categories 3104 * "L" (letters) and "Nd" (decimal digit numbers). 3105 * 3106 * Same as java.lang.Character.isLetterOrDigit(). 3107 * 3108 * In addition to being equivalent to a Java function, this also serves 3109 * as a C/POSIX migration function. 3110 * See the comments about C/POSIX character classification functions in the 3111 * documentation at the top of this header file. 3112 * 3113 * @param c the code point to be tested 3114 * @return true if the code point is an alphanumeric character according to Character.isLetterOrDigit() 3115 * 3116 * @stable ICU 2.0 3117 */ 3118 U_CAPI UBool U_EXPORT2 3119 u_isalnum(UChar32 c); 3120 3121 /** 3122 * Determines whether the specified code point is a hexadecimal digit. 3123 * This is equivalent to u_digit(c, 16)>=0. 3124 * True for characters with general category "Nd" (decimal digit numbers) 3125 * as well as Latin letters a-f and A-F in both ASCII and Fullwidth ASCII. 3126 * (That is, for letters with code points 3127 * 0041..0046, 0061..0066, FF21..FF26, FF41..FF46.) 3128 * 3129 * In order to narrow the definition of hexadecimal digits to only ASCII 3130 * characters, use (c<=0x7f && u_isxdigit(c)). 3131 * 3132 * This is a C/POSIX migration function. 3133 * See the comments about C/POSIX character classification functions in the 3134 * documentation at the top of this header file. 3135 * 3136 * @param c the code point to be tested 3137 * @return true if the code point is a hexadecimal digit 3138 * 3139 * @stable ICU 2.6 3140 */ 3141 U_CAPI UBool U_EXPORT2 3142 u_isxdigit(UChar32 c); 3143 3144 /** 3145 * Determines whether the specified code point is a punctuation character. 3146 * True for characters with general categories "P" (punctuation). 3147 * 3148 * This is a C/POSIX migration function. 3149 * See the comments about C/POSIX character classification functions in the 3150 * documentation at the top of this header file. 3151 * 3152 * @param c the code point to be tested 3153 * @return true if the code point is a punctuation character 3154 * 3155 * @stable ICU 2.6 3156 */ 3157 U_CAPI UBool U_EXPORT2 3158 u_ispunct(UChar32 c); 3159 3160 /** 3161 * Determines whether the specified code point is a "graphic" character 3162 * (printable, excluding spaces). 3163 * true for all characters except those with general categories 3164 * "Cc" (control codes), "Cf" (format controls), "Cs" (surrogates), 3165 * "Cn" (unassigned), and "Z" (separators). 3166 * 3167 * This is a C/POSIX migration function. 3168 * See the comments about C/POSIX character classification functions in the 3169 * documentation at the top of this header file. 3170 * 3171 * @param c the code point to be tested 3172 * @return true if the code point is a "graphic" character 3173 * 3174 * @stable ICU 2.6 3175 */ 3176 U_CAPI UBool U_EXPORT2 3177 u_isgraph(UChar32 c); 3178 3179 /** 3180 * Determines whether the specified code point is a "blank" or "horizontal space", 3181 * a character that visibly separates words on a line. 3182 * The following are equivalent definitions: 3183 * 3184 * true for Unicode White_Space characters except for "vertical space controls" 3185 * where "vertical space controls" are the following characters: 3186 * U+000A (LF) U+000B (VT) U+000C (FF) U+000D (CR) U+0085 (NEL) U+2028 (LS) U+2029 (PS) 3187 * 3188 * same as 3189 * 3190 * true for U+0009 (TAB) and characters with general category "Zs" (space separators). 3191 * 3192 * Note: There are several ICU whitespace functions; please see the uchar.h 3193 * file documentation for a detailed comparison. 3194 * 3195 * This is a C/POSIX migration function. 3196 * See the comments about C/POSIX character classification functions in the 3197 * documentation at the top of this header file. 3198 * 3199 * @param c the code point to be tested 3200 * @return true if the code point is a "blank" 3201 * 3202 * @stable ICU 2.6 3203 */ 3204 U_CAPI UBool U_EXPORT2 3205 u_isblank(UChar32 c); 3206 3207 /** 3208 * Determines whether the specified code point is "defined", 3209 * which usually means that it is assigned a character. 3210 * True for general categories other than "Cn" (other, not assigned), 3211 * i.e., true for all code points mentioned in UnicodeData.txt. 3212 * 3213 * Note that non-character code points (e.g., U+FDD0) are not "defined" 3214 * (they are Cn), but surrogate code points are "defined" (Cs). 3215 * 3216 * Same as java.lang.Character.isDefined(). 3217 * 3218 * @param c the code point to be tested 3219 * @return true if the code point is assigned a character 3220 * 3221 * @see u_isdigit 3222 * @see u_isalpha 3223 * @see u_isalnum 3224 * @see u_isupper 3225 * @see u_islower 3226 * @see u_istitle 3227 * @stable ICU 2.0 3228 */ 3229 U_CAPI UBool U_EXPORT2 3230 u_isdefined(UChar32 c); 3231 3232 /** 3233 * Determines if the specified character is a space character or not. 3234 * 3235 * Note: There are several ICU whitespace functions; please see the uchar.h 3236 * file documentation for a detailed comparison. 3237 * 3238 * This is a C/POSIX migration function. 3239 * See the comments about C/POSIX character classification functions in the 3240 * documentation at the top of this header file. 3241 * 3242 * @param c the character to be tested 3243 * @return true if the character is a space character; false otherwise. 3244 * 3245 * @see u_isJavaSpaceChar 3246 * @see u_isWhitespace 3247 * @see u_isUWhiteSpace 3248 * @stable ICU 2.0 3249 */ 3250 U_CAPI UBool U_EXPORT2 3251 u_isspace(UChar32 c); 3252 3253 /** 3254 * Determine if the specified code point is a space character according to Java. 3255 * True for characters with general categories "Z" (separators), 3256 * which does not include control codes (e.g., TAB or Line Feed). 3257 * 3258 * Same as java.lang.Character.isSpaceChar(). 3259 * 3260 * Note: There are several ICU whitespace functions; please see the uchar.h 3261 * file documentation for a detailed comparison. 3262 * 3263 * @param c the code point to be tested 3264 * @return true if the code point is a space character according to Character.isSpaceChar() 3265 * 3266 * @see u_isspace 3267 * @see u_isWhitespace 3268 * @see u_isUWhiteSpace 3269 * @stable ICU 2.6 3270 */ 3271 U_CAPI UBool U_EXPORT2 3272 u_isJavaSpaceChar(UChar32 c); 3273 3274 /** 3275 * Determines if the specified code point is a whitespace character according to Java/ICU. 3276 * A character is considered to be a Java whitespace character if and only 3277 * if it satisfies one of the following criteria: 3278 * 3279 * - It is a Unicode Separator character (categories "Z" = "Zs" or "Zl" or "Zp"), but is not 3280 * also a non-breaking space (U+00A0 NBSP or U+2007 Figure Space or U+202F Narrow NBSP). 3281 * - It is U+0009 HORIZONTAL TABULATION. 3282 * - It is U+000A LINE FEED. 3283 * - It is U+000B VERTICAL TABULATION. 3284 * - It is U+000C FORM FEED. 3285 * - It is U+000D CARRIAGE RETURN. 3286 * - It is U+001C FILE SEPARATOR. 3287 * - It is U+001D GROUP SEPARATOR. 3288 * - It is U+001E RECORD SEPARATOR. 3289 * - It is U+001F UNIT SEPARATOR. 3290 * 3291 * This API tries to sync with the semantics of Java's 3292 * java.lang.Character.isWhitespace(), but it may not return 3293 * the exact same results because of the Unicode version 3294 * difference. 3295 * 3296 * Note: Unicode 4.0.1 changed U+200B ZERO WIDTH SPACE from a Space Separator (Zs) 3297 * to a Format Control (Cf). Since then, isWhitespace(0x200b) returns false. 3298 * See http://www.unicode.org/versions/Unicode4.0.1/ 3299 * 3300 * Note: There are several ICU whitespace functions; please see the uchar.h 3301 * file documentation for a detailed comparison. 3302 * 3303 * @param c the code point to be tested 3304 * @return true if the code point is a whitespace character according to Java/ICU 3305 * 3306 * @see u_isspace 3307 * @see u_isJavaSpaceChar 3308 * @see u_isUWhiteSpace 3309 * @stable ICU 2.0 3310 */ 3311 U_CAPI UBool U_EXPORT2 3312 u_isWhitespace(UChar32 c); 3313 3314 /** 3315 * Determines whether the specified code point is a control character 3316 * (as defined by this function). 3317 * A control character is one of the following: 3318 * - ISO 8-bit control character (U+0000..U+001f and U+007f..U+009f) 3319 * - U_CONTROL_CHAR (Cc) 3320 * - U_FORMAT_CHAR (Cf) 3321 * - U_LINE_SEPARATOR (Zl) 3322 * - U_PARAGRAPH_SEPARATOR (Zp) 3323 * 3324 * This is a C/POSIX migration function. 3325 * See the comments about C/POSIX character classification functions in the 3326 * documentation at the top of this header file. 3327 * 3328 * @param c the code point to be tested 3329 * @return true if the code point is a control character 3330 * 3331 * @see UCHAR_DEFAULT_IGNORABLE_CODE_POINT 3332 * @see u_isprint 3333 * @stable ICU 2.0 3334 */ 3335 U_CAPI UBool U_EXPORT2 3336 u_iscntrl(UChar32 c); 3337 3338 /** 3339 * Determines whether the specified code point is an ISO control code. 3340 * True for U+0000..U+001f and U+007f..U+009f (general category "Cc"). 3341 * 3342 * Same as java.lang.Character.isISOControl(). 3343 * 3344 * @param c the code point to be tested 3345 * @return true if the code point is an ISO control code 3346 * 3347 * @see u_iscntrl 3348 * @stable ICU 2.6 3349 */ 3350 U_CAPI UBool U_EXPORT2 3351 u_isISOControl(UChar32 c); 3352 3353 /** 3354 * Determines whether the specified code point is a printable character. 3355 * True for general categories <em>other</em> than "C" (controls). 3356 * 3357 * This is a C/POSIX migration function. 3358 * See the comments about C/POSIX character classification functions in the 3359 * documentation at the top of this header file. 3360 * 3361 * @param c the code point to be tested 3362 * @return true if the code point is a printable character 3363 * 3364 * @see UCHAR_DEFAULT_IGNORABLE_CODE_POINT 3365 * @see u_iscntrl 3366 * @stable ICU 2.0 3367 */ 3368 U_CAPI UBool U_EXPORT2 3369 u_isprint(UChar32 c); 3370 3371 /** 3372 * Non-standard: Determines whether the specified code point is a base character. 3373 * True for general categories "L" (letters), "N" (numbers), 3374 * "Mc" (spacing combining marks), and "Me" (enclosing marks). 3375 * 3376 * Note that this is different from the Unicode Standard definition in 3377 * chapter 3.6, conformance clause D51 “Base character”, 3378 * which defines base characters as the code points with general categories 3379 * Letter (L), Number (N), Punctuation (P), Symbol (S), or Space Separator (Zs). 3380 * 3381 * @param c the code point to be tested 3382 * @return true if the code point is a base character according to this function 3383 * 3384 * @see u_isalpha 3385 * @see u_isdigit 3386 * @stable ICU 2.0 3387 */ 3388 U_CAPI UBool U_EXPORT2 3389 u_isbase(UChar32 c); 3390 3391 /** 3392 * Returns the bidirectional category value for the code point, 3393 * which is used in the Unicode bidirectional algorithm 3394 * (UAX #9 http://www.unicode.org/reports/tr9/). 3395 * Note that some <em>unassigned</em> code points have bidi values 3396 * of R or AL because they are in blocks that are reserved 3397 * for Right-To-Left scripts. 3398 * 3399 * Same as java.lang.Character.getDirectionality() 3400 * 3401 * @param c the code point to be tested 3402 * @return the bidirectional category (UCharDirection) value 3403 * 3404 * @see UCharDirection 3405 * @stable ICU 2.0 3406 */ 3407 U_CAPI UCharDirection U_EXPORT2 3408 u_charDirection(UChar32 c); 3409 3410 /** 3411 * Determines whether the code point has the Bidi_Mirrored property. 3412 * This property is set for characters that are commonly used in 3413 * Right-To-Left contexts and need to be displayed with a "mirrored" 3414 * glyph. 3415 * 3416 * Same as java.lang.Character.isMirrored(). 3417 * Same as UCHAR_BIDI_MIRRORED 3418 * 3419 * @param c the code point to be tested 3420 * @return true if the character has the Bidi_Mirrored property 3421 * 3422 * @see UCHAR_BIDI_MIRRORED 3423 * @stable ICU 2.0 3424 */ 3425 U_CAPI UBool U_EXPORT2 3426 u_isMirrored(UChar32 c); 3427 3428 /** 3429 * Maps the specified character to a "mirror-image" character. 3430 * For characters with the Bidi_Mirrored property, implementations 3431 * sometimes need a "poor man's" mapping to another Unicode 3432 * character (code point) such that the default glyph may serve 3433 * as the mirror-image of the default glyph of the specified 3434 * character. This is useful for text conversion to and from 3435 * codepages with visual order, and for displays without glyph 3436 * selection capabilities. 3437 * 3438 * @param c the code point to be mapped 3439 * @return another Unicode code point that may serve as a mirror-image 3440 * substitute, or c itself if there is no such mapping or c 3441 * does not have the Bidi_Mirrored property 3442 * 3443 * @see UCHAR_BIDI_MIRRORED 3444 * @see u_isMirrored 3445 * @stable ICU 2.0 3446 */ 3447 U_CAPI UChar32 U_EXPORT2 3448 u_charMirror(UChar32 c); 3449 3450 /** 3451 * Maps the specified character to its paired bracket character. 3452 * For Bidi_Paired_Bracket_Type!=None, this is the same as u_charMirror(). 3453 * Otherwise c itself is returned. 3454 * See http://www.unicode.org/reports/tr9/ 3455 * 3456 * @param c the code point to be mapped 3457 * @return the paired bracket code point, 3458 * or c itself if there is no such mapping 3459 * (Bidi_Paired_Bracket_Type=None) 3460 * 3461 * @see UCHAR_BIDI_PAIRED_BRACKET 3462 * @see UCHAR_BIDI_PAIRED_BRACKET_TYPE 3463 * @see u_charMirror 3464 * @stable ICU 52 3465 */ 3466 U_CAPI UChar32 U_EXPORT2 3467 u_getBidiPairedBracket(UChar32 c); 3468 3469 /** 3470 * Returns the general category value for the code point. 3471 * 3472 * Same as java.lang.Character.getType(). 3473 * 3474 * @param c the code point to be tested 3475 * @return the general category (UCharCategory) value 3476 * 3477 * @see UCharCategory 3478 * @stable ICU 2.0 3479 */ 3480 U_CAPI int8_t U_EXPORT2 3481 u_charType(UChar32 c); 3482 3483 /** 3484 * Get a single-bit bit set for the general category of a character. 3485 * This bit set can be compared bitwise with U_GC_SM_MASK, U_GC_L_MASK, etc. 3486 * Same as U_MASK(u_charType(c)). 3487 * 3488 * @param c the code point to be tested 3489 * @return a single-bit mask corresponding to the general category (UCharCategory) value 3490 * 3491 * @see u_charType 3492 * @see UCharCategory 3493 * @see U_GC_CN_MASK 3494 * @stable ICU 2.1 3495 */ 3496 #define U_GET_GC_MASK(c) U_MASK(u_charType(c)) 3497 3498 /** 3499 * Callback from u_enumCharTypes(), is called for each contiguous range 3500 * of code points c (where start<=c<limit) 3501 * with the same Unicode general category ("character type"). 3502 * 3503 * The callback function can stop the enumeration by returning false. 3504 * 3505 * @param context an opaque pointer, as passed into utrie_enum() 3506 * @param start the first code point in a contiguous range with value 3507 * @param limit one past the last code point in a contiguous range with value 3508 * @param type the general category for all code points in [start..limit[ 3509 * @return false to stop the enumeration 3510 * 3511 * @stable ICU 2.1 3512 * @see UCharCategory 3513 * @see u_enumCharTypes 3514 */ 3515 typedef UBool U_CALLCONV 3516 UCharEnumTypeRange(const void *context, UChar32 start, UChar32 limit, UCharCategory type); 3517 3518 /** 3519 * Enumerate efficiently all code points with their Unicode general categories. 3520 * 3521 * This is useful for building data structures (e.g., UnicodeSet's), 3522 * for enumerating all assigned code points (type!=U_UNASSIGNED), etc. 3523 * 3524 * For each contiguous range of code points with a given general category ("character type"), 3525 * the UCharEnumTypeRange function is called. 3526 * Adjacent ranges have different types. 3527 * The Unicode Standard guarantees that the numeric value of the type is 0..31. 3528 * 3529 * @param enumRange a pointer to a function that is called for each contiguous range 3530 * of code points with the same general category 3531 * @param context an opaque pointer that is passed on to the callback function 3532 * 3533 * @stable ICU 2.1 3534 * @see UCharCategory 3535 * @see UCharEnumTypeRange 3536 */ 3537 U_CAPI void U_EXPORT2 3538 u_enumCharTypes(UCharEnumTypeRange *enumRange, const void *context); 3539 3540 #if !UCONFIG_NO_NORMALIZATION 3541 3542 /** 3543 * Returns the combining class of the code point as specified in UnicodeData.txt. 3544 * 3545 * @param c the code point of the character 3546 * @return the combining class of the character 3547 * @stable ICU 2.0 3548 */ 3549 U_CAPI uint8_t U_EXPORT2 3550 u_getCombiningClass(UChar32 c); 3551 3552 #endif 3553 3554 /** 3555 * Returns the decimal digit value of a decimal digit character. 3556 * Such characters have the general category "Nd" (decimal digit numbers) 3557 * and a Numeric_Type of Decimal. 3558 * 3559 * Unlike ICU releases before 2.6, no digit values are returned for any 3560 * Han characters because Han number characters are often used with a special 3561 * Chinese-style number format (with characters for powers of 10 in between) 3562 * instead of in decimal-positional notation. 3563 * Unicode 4 explicitly assigns Han number characters the Numeric_Type 3564 * Numeric instead of Decimal. 3565 * See Jitterbug 1483 for more details. 3566 * 3567 * Use u_getIntPropertyValue(c, UCHAR_NUMERIC_TYPE) and u_getNumericValue() 3568 * for complete numeric Unicode properties. 3569 * 3570 * @param c the code point for which to get the decimal digit value 3571 * @return the decimal digit value of c, 3572 * or -1 if c is not a decimal digit character 3573 * 3574 * @see u_getNumericValue 3575 * @stable ICU 2.0 3576 */ 3577 U_CAPI int32_t U_EXPORT2 3578 u_charDigitValue(UChar32 c); 3579 3580 /** 3581 * Returns the Unicode allocation block that contains the character. 3582 * 3583 * @param c the code point to be tested 3584 * @return the block value (UBlockCode) for c 3585 * 3586 * @see UBlockCode 3587 * @stable ICU 2.0 3588 */ 3589 U_CAPI UBlockCode U_EXPORT2 3590 ublock_getCode(UChar32 c); 3591 3592 /** 3593 * Retrieve the name of a Unicode character. 3594 * Depending on <code>nameChoice</code>, the character name written 3595 * into the buffer is the "modern" name or the name that was defined 3596 * in Unicode version 1.0. 3597 * The name contains only "invariant" characters 3598 * like A-Z, 0-9, space, and '-'. 3599 * Unicode 1.0 names are only retrieved if they are different from the modern 3600 * names and if the data file contains the data for them. gennames may or may 3601 * not be called with a command line option to include 1.0 names in unames.dat. 3602 * 3603 * @param code The character (code point) for which to get the name. 3604 * It must be <code>0<=code<=0x10ffff</code>. 3605 * @param nameChoice Selector for which name to get. 3606 * @param buffer Destination address for copying the name. 3607 * The name will always be zero-terminated. 3608 * If there is no name, then the buffer will be set to the empty string. 3609 * @param bufferLength <code>==sizeof(buffer)</code> 3610 * @param pErrorCode Pointer to a UErrorCode variable; 3611 * check for <code>U_SUCCESS()</code> after <code>u_charName()</code> 3612 * returns. 3613 * @return The length of the name, or 0 if there is no name for this character. 3614 * If the bufferLength is less than or equal to the length, then the buffer 3615 * contains the truncated name and the returned length indicates the full 3616 * length of the name. 3617 * The length does not include the zero-termination. 3618 * 3619 * @see UCharNameChoice 3620 * @see u_charFromName 3621 * @see u_enumCharNames 3622 * @stable ICU 2.0 3623 */ 3624 U_CAPI int32_t U_EXPORT2 3625 u_charName(UChar32 code, UCharNameChoice nameChoice, 3626 char *buffer, int32_t bufferLength, 3627 UErrorCode *pErrorCode); 3628 3629 #ifndef U_HIDE_DEPRECATED_API 3630 /** 3631 * Returns an empty string. 3632 * Used to return the ISO 10646 comment for a character. 3633 * The Unicode ISO_Comment property is deprecated and has no values. 3634 * 3635 * @param c The character (code point) for which to get the ISO comment. 3636 * It must be <code>0<=c<=0x10ffff</code>. 3637 * @param dest Destination address for copying the comment. 3638 * The comment will be zero-terminated if possible. 3639 * If there is no comment, then the buffer will be set to the empty string. 3640 * @param destCapacity <code>==sizeof(dest)</code> 3641 * @param pErrorCode Pointer to a UErrorCode variable; 3642 * check for <code>U_SUCCESS()</code> after <code>u_getISOComment()</code> 3643 * returns. 3644 * @return 0 3645 * 3646 * @deprecated ICU 49 3647 */ 3648 U_DEPRECATED int32_t U_EXPORT2 3649 u_getISOComment(UChar32 c, 3650 char *dest, int32_t destCapacity, 3651 UErrorCode *pErrorCode); 3652 #endif /* U_HIDE_DEPRECATED_API */ 3653 3654 /** 3655 * Find a Unicode character by its name and return its code point value. 3656 * The name is matched exactly and completely. 3657 * If the name does not correspond to a code point, <i>pErrorCode</i> 3658 * is set to <code>U_INVALID_CHAR_FOUND</code>. 3659 * A Unicode 1.0 name is matched only if it differs from the modern name. 3660 * Unicode names are all uppercase. Extended names are lowercase followed 3661 * by an uppercase hexadecimal number, and within angle brackets. 3662 * 3663 * @param nameChoice Selector for which name to match. 3664 * @param name The name to match. 3665 * @param pErrorCode Pointer to a UErrorCode variable 3666 * @return The Unicode value of the code point with the given name, 3667 * or an undefined value if there is no such code point. 3668 * 3669 * @see UCharNameChoice 3670 * @see u_charName 3671 * @see u_enumCharNames 3672 * @stable ICU 1.7 3673 */ 3674 U_CAPI UChar32 U_EXPORT2 3675 u_charFromName(UCharNameChoice nameChoice, 3676 const char *name, 3677 UErrorCode *pErrorCode); 3678 3679 /** 3680 * Type of a callback function for u_enumCharNames() that gets called 3681 * for each Unicode character with the code point value and 3682 * the character name. 3683 * If such a function returns false, then the enumeration is stopped. 3684 * 3685 * @param context The context pointer that was passed to u_enumCharNames(). 3686 * @param code The Unicode code point for the character with this name. 3687 * @param nameChoice Selector for which kind of names is enumerated. 3688 * @param name The character's name, zero-terminated. 3689 * @param length The length of the name. 3690 * @return true if the enumeration should continue, false to stop it. 3691 * 3692 * @see UCharNameChoice 3693 * @see u_enumCharNames 3694 * @stable ICU 1.7 3695 */ 3696 typedef UBool U_CALLCONV UEnumCharNamesFn(void *context, 3697 UChar32 code, 3698 UCharNameChoice nameChoice, 3699 const char *name, 3700 int32_t length); 3701 3702 /** 3703 * Enumerate all assigned Unicode characters between the start and limit 3704 * code points (start inclusive, limit exclusive) and call a function 3705 * for each, passing the code point value and the character name. 3706 * For Unicode 1.0 names, only those are enumerated that differ from the 3707 * modern names. 3708 * 3709 * @param start The first code point in the enumeration range. 3710 * @param limit One more than the last code point in the enumeration range 3711 * (the first one after the range). 3712 * @param fn The function that is to be called for each character name. 3713 * @param context An arbitrary pointer that is passed to the function. 3714 * @param nameChoice Selector for which kind of names to enumerate. 3715 * @param pErrorCode Pointer to a UErrorCode variable 3716 * 3717 * @see UCharNameChoice 3718 * @see UEnumCharNamesFn 3719 * @see u_charName 3720 * @see u_charFromName 3721 * @stable ICU 1.7 3722 */ 3723 U_CAPI void U_EXPORT2 3724 u_enumCharNames(UChar32 start, UChar32 limit, 3725 UEnumCharNamesFn *fn, 3726 void *context, 3727 UCharNameChoice nameChoice, 3728 UErrorCode *pErrorCode); 3729 3730 /** 3731 * Return the Unicode name for a given property, as given in the 3732 * Unicode database file PropertyAliases.txt. 3733 * 3734 * In addition, this function maps the property 3735 * UCHAR_GENERAL_CATEGORY_MASK to the synthetic names "gcm" / 3736 * "General_Category_Mask". These names are not in 3737 * PropertyAliases.txt. 3738 * 3739 * @param property UProperty selector other than UCHAR_INVALID_CODE. 3740 * If out of range, NULL is returned. 3741 * 3742 * @param nameChoice selector for which name to get. If out of range, 3743 * NULL is returned. All properties have a long name. Most 3744 * have a short name, but some do not. Unicode allows for 3745 * additional names; if present these will be returned by 3746 * U_LONG_PROPERTY_NAME + i, where i=1, 2,... 3747 * 3748 * @return a pointer to the name, or NULL if either the 3749 * property or the nameChoice is out of range. If a given 3750 * nameChoice returns NULL, then all larger values of 3751 * nameChoice will return NULL, with one exception: if NULL is 3752 * returned for U_SHORT_PROPERTY_NAME, then 3753 * U_LONG_PROPERTY_NAME (and higher) may still return a 3754 * non-NULL value. The returned pointer is valid until 3755 * u_cleanup() is called. 3756 * 3757 * @see UProperty 3758 * @see UPropertyNameChoice 3759 * @stable ICU 2.4 3760 */ 3761 U_CAPI const char* U_EXPORT2 3762 u_getPropertyName(UProperty property, 3763 UPropertyNameChoice nameChoice); 3764 3765 /** 3766 * Return the UProperty enum for a given property name, as specified 3767 * in the Unicode database file PropertyAliases.txt. Short, long, and 3768 * any other variants are recognized. 3769 * 3770 * In addition, this function maps the synthetic names "gcm" / 3771 * "General_Category_Mask" to the property 3772 * UCHAR_GENERAL_CATEGORY_MASK. These names are not in 3773 * PropertyAliases.txt. 3774 * 3775 * @param alias the property name to be matched. The name is compared 3776 * using "loose matching" as described in PropertyAliases.txt. 3777 * 3778 * @return a UProperty enum, or UCHAR_INVALID_CODE if the given name 3779 * does not match any property. 3780 * 3781 * @see UProperty 3782 * @stable ICU 2.4 3783 */ 3784 U_CAPI UProperty U_EXPORT2 3785 u_getPropertyEnum(const char* alias); 3786 3787 /** 3788 * Return the Unicode name for a given property value, as given in the 3789 * Unicode database file PropertyValueAliases.txt. 3790 * 3791 * Note: Some of the names in PropertyValueAliases.txt can only be 3792 * retrieved using UCHAR_GENERAL_CATEGORY_MASK, not 3793 * UCHAR_GENERAL_CATEGORY. These include: "C" / "Other", "L" / 3794 * "Letter", "LC" / "Cased_Letter", "M" / "Mark", "N" / "Number", "P" 3795 * / "Punctuation", "S" / "Symbol", and "Z" / "Separator". 3796 * 3797 * @param property UProperty selector constant. 3798 * Must be UCHAR_BINARY_START<=which<UCHAR_BINARY_LIMIT 3799 * or UCHAR_INT_START<=which<UCHAR_INT_LIMIT 3800 * or UCHAR_MASK_START<=which<UCHAR_MASK_LIMIT. 3801 * If out of range, NULL is returned. 3802 * 3803 * @param value selector for a value for the given property. If out 3804 * of range, NULL is returned. In general, valid values range 3805 * from 0 up to some maximum. There are a few exceptions: 3806 * (1.) UCHAR_BLOCK values begin at the non-zero value 3807 * UBLOCK_BASIC_LATIN. (2.) UCHAR_CANONICAL_COMBINING_CLASS 3808 * values are not contiguous and range from 0..240. (3.) 3809 * UCHAR_GENERAL_CATEGORY_MASK values are not values of 3810 * UCharCategory, but rather mask values produced by 3811 * U_GET_GC_MASK(). This allows grouped categories such as 3812 * [:L:] to be represented. Mask values range 3813 * non-contiguously from 1..U_GC_P_MASK. 3814 * 3815 * @param nameChoice selector for which name to get. If out of range, 3816 * NULL is returned. All values have a long name. Most have 3817 * a short name, but some do not. Unicode allows for 3818 * additional names; if present these will be returned by 3819 * U_LONG_PROPERTY_NAME + i, where i=1, 2,... 3820 3821 * @return a pointer to the name, or NULL if either the 3822 * property or the nameChoice is out of range. If a given 3823 * nameChoice returns NULL, then all larger values of 3824 * nameChoice will return NULL, with one exception: if NULL is 3825 * returned for U_SHORT_PROPERTY_NAME, then 3826 * U_LONG_PROPERTY_NAME (and higher) may still return a 3827 * non-NULL value. The returned pointer is valid until 3828 * u_cleanup() is called. 3829 * 3830 * @see UProperty 3831 * @see UPropertyNameChoice 3832 * @stable ICU 2.4 3833 */ 3834 U_CAPI const char* U_EXPORT2 3835 u_getPropertyValueName(UProperty property, 3836 int32_t value, 3837 UPropertyNameChoice nameChoice); 3838 3839 /** 3840 * Return the property value integer for a given value name, as 3841 * specified in the Unicode database file PropertyValueAliases.txt. 3842 * Short, long, and any other variants are recognized. 3843 * 3844 * Note: Some of the names in PropertyValueAliases.txt will only be 3845 * recognized with UCHAR_GENERAL_CATEGORY_MASK, not 3846 * UCHAR_GENERAL_CATEGORY. These include: "C" / "Other", "L" / 3847 * "Letter", "LC" / "Cased_Letter", "M" / "Mark", "N" / "Number", "P" 3848 * / "Punctuation", "S" / "Symbol", and "Z" / "Separator". 3849 * 3850 * @param property UProperty selector constant. 3851 * Must be UCHAR_BINARY_START<=which<UCHAR_BINARY_LIMIT 3852 * or UCHAR_INT_START<=which<UCHAR_INT_LIMIT 3853 * or UCHAR_MASK_START<=which<UCHAR_MASK_LIMIT. 3854 * If out of range, UCHAR_INVALID_CODE is returned. 3855 * 3856 * @param alias the value name to be matched. The name is compared 3857 * using "loose matching" as described in 3858 * PropertyValueAliases.txt. 3859 * 3860 * @return a value integer or UCHAR_INVALID_CODE if the given name 3861 * does not match any value of the given property, or if the 3862 * property is invalid. Note: UCHAR_GENERAL_CATEGORY_MASK values 3863 * are not values of UCharCategory, but rather mask values 3864 * produced by U_GET_GC_MASK(). This allows grouped 3865 * categories such as [:L:] to be represented. 3866 * 3867 * @see UProperty 3868 * @stable ICU 2.4 3869 */ 3870 U_CAPI int32_t U_EXPORT2 3871 u_getPropertyValueEnum(UProperty property, 3872 const char* alias); 3873 3874 /** 3875 * Determines if the specified character is permissible as the first character in an identifier 3876 * according to UAX #31 Unicode Identifier and Pattern Syntax. 3877 * 3878 * Same as Unicode ID_Start (UCHAR_ID_START). 3879 * 3880 * @param c the code point to be tested 3881 * @return true if the code point may start an identifier 3882 * 3883 * @see UCHAR_ID_START 3884 * @see u_isalpha 3885 * @see u_isIDPart 3886 * @stable ICU 2.0 3887 */ 3888 U_CAPI UBool U_EXPORT2 3889 u_isIDStart(UChar32 c); 3890 3891 /** 3892 * Determines if the specified character is permissible as a non-initial character of an identifier 3893 * according to UAX #31 Unicode Identifier and Pattern Syntax. 3894 * 3895 * Same as Unicode ID_Continue (UCHAR_ID_CONTINUE). 3896 * 3897 * @param c the code point to be tested 3898 * @return true if the code point may occur as a non-initial character of an identifier 3899 * 3900 * @see UCHAR_ID_CONTINUE 3901 * @see u_isIDStart 3902 * @see u_isIDIgnorable 3903 * @stable ICU 2.0 3904 */ 3905 U_CAPI UBool U_EXPORT2 3906 u_isIDPart(UChar32 c); 3907 3908 /** 3909 * Determines if the specified character should be regarded 3910 * as an ignorable character in an identifier, 3911 * according to Java. 3912 * True for characters with general category "Cf" (format controls) as well as 3913 * non-whitespace ISO controls 3914 * (U+0000..U+0008, U+000E..U+001B, U+007F..U+009F). 3915 * 3916 * Same as java.lang.Character.isIdentifierIgnorable(). 3917 * 3918 * Note that Unicode just recommends to ignore Cf (format controls). 3919 * 3920 * @param c the code point to be tested 3921 * @return true if the code point is ignorable in identifiers according to Java 3922 * 3923 * @see UCHAR_DEFAULT_IGNORABLE_CODE_POINT 3924 * @see u_isIDStart 3925 * @see u_isIDPart 3926 * @stable ICU 2.0 3927 */ 3928 U_CAPI UBool U_EXPORT2 3929 u_isIDIgnorable(UChar32 c); 3930 3931 /** 3932 * Determines if the specified character is permissible as the 3933 * first character in a Java identifier. 3934 * In addition to u_isIDStart(c), true for characters with 3935 * general categories "Sc" (currency symbols) and "Pc" (connecting punctuation). 3936 * 3937 * Same as java.lang.Character.isJavaIdentifierStart(). 3938 * 3939 * @param c the code point to be tested 3940 * @return true if the code point may start a Java identifier 3941 * 3942 * @see u_isJavaIDPart 3943 * @see u_isalpha 3944 * @see u_isIDStart 3945 * @stable ICU 2.0 3946 */ 3947 U_CAPI UBool U_EXPORT2 3948 u_isJavaIDStart(UChar32 c); 3949 3950 /** 3951 * Determines if the specified character is permissible 3952 * in a Java identifier. 3953 * In addition to u_isIDPart(c), true for characters with 3954 * general category "Sc" (currency symbols). 3955 * 3956 * Same as java.lang.Character.isJavaIdentifierPart(). 3957 * 3958 * @param c the code point to be tested 3959 * @return true if the code point may occur in a Java identifier 3960 * 3961 * @see u_isIDIgnorable 3962 * @see u_isJavaIDStart 3963 * @see u_isalpha 3964 * @see u_isdigit 3965 * @see u_isIDPart 3966 * @stable ICU 2.0 3967 */ 3968 U_CAPI UBool U_EXPORT2 3969 u_isJavaIDPart(UChar32 c); 3970 3971 /** 3972 * The given character is mapped to its lowercase equivalent according to 3973 * UnicodeData.txt; if the character has no lowercase equivalent, the character 3974 * itself is returned. 3975 * 3976 * Same as java.lang.Character.toLowerCase(). 3977 * 3978 * This function only returns the simple, single-code point case mapping. 3979 * Full case mappings should be used whenever possible because they produce 3980 * better results by working on whole strings. 3981 * They take into account the string context and the language and can map 3982 * to a result string with a different length as appropriate. 3983 * Full case mappings are applied by the string case mapping functions, 3984 * see ustring.h and the UnicodeString class. 3985 * See also the User Guide chapter on C/POSIX migration: 3986 * https://unicode-org.github.io/icu/userguide/icu/posix#case-mappings 3987 * 3988 * @param c the code point to be mapped 3989 * @return the Simple_Lowercase_Mapping of the code point, if any; 3990 * otherwise the code point itself. 3991 * @stable ICU 2.0 3992 */ 3993 U_CAPI UChar32 U_EXPORT2 3994 u_tolower(UChar32 c); 3995 3996 /** 3997 * The given character is mapped to its uppercase equivalent according to UnicodeData.txt; 3998 * if the character has no uppercase equivalent, the character itself is 3999 * returned. 4000 * 4001 * Same as java.lang.Character.toUpperCase(). 4002 * 4003 * This function only returns the simple, single-code point case mapping. 4004 * Full case mappings should be used whenever possible because they produce 4005 * better results by working on whole strings. 4006 * They take into account the string context and the language and can map 4007 * to a result string with a different length as appropriate. 4008 * Full case mappings are applied by the string case mapping functions, 4009 * see ustring.h and the UnicodeString class. 4010 * See also the User Guide chapter on C/POSIX migration: 4011 * https://unicode-org.github.io/icu/userguide/icu/posix#case-mappings 4012 * 4013 * @param c the code point to be mapped 4014 * @return the Simple_Uppercase_Mapping of the code point, if any; 4015 * otherwise the code point itself. 4016 * @stable ICU 2.0 4017 */ 4018 U_CAPI UChar32 U_EXPORT2 4019 u_toupper(UChar32 c); 4020 4021 /** 4022 * The given character is mapped to its titlecase equivalent 4023 * according to UnicodeData.txt; 4024 * if none is defined, the character itself is returned. 4025 * 4026 * Same as java.lang.Character.toTitleCase(). 4027 * 4028 * This function only returns the simple, single-code point case mapping. 4029 * Full case mappings should be used whenever possible because they produce 4030 * better results by working on whole strings. 4031 * They take into account the string context and the language and can map 4032 * to a result string with a different length as appropriate. 4033 * Full case mappings are applied by the string case mapping functions, 4034 * see ustring.h and the UnicodeString class. 4035 * See also the User Guide chapter on C/POSIX migration: 4036 * https://unicode-org.github.io/icu/userguide/icu/posix#case-mappings 4037 * 4038 * @param c the code point to be mapped 4039 * @return the Simple_Titlecase_Mapping of the code point, if any; 4040 * otherwise the code point itself. 4041 * @stable ICU 2.0 4042 */ 4043 U_CAPI UChar32 U_EXPORT2 4044 u_totitle(UChar32 c); 4045 4046 /** 4047 * The given character is mapped to its case folding equivalent according to 4048 * UnicodeData.txt and CaseFolding.txt; 4049 * if the character has no case folding equivalent, the character 4050 * itself is returned. 4051 * 4052 * This function only returns the simple, single-code point case mapping. 4053 * Full case mappings should be used whenever possible because they produce 4054 * better results by working on whole strings. 4055 * They take into account the string context and the language and can map 4056 * to a result string with a different length as appropriate. 4057 * Full case mappings are applied by the string case mapping functions, 4058 * see ustring.h and the UnicodeString class. 4059 * See also the User Guide chapter on C/POSIX migration: 4060 * https://unicode-org.github.io/icu/userguide/icu/posix#case-mappings 4061 * 4062 * @param c the code point to be mapped 4063 * @param options Either U_FOLD_CASE_DEFAULT or U_FOLD_CASE_EXCLUDE_SPECIAL_I 4064 * @return the Simple_Case_Folding of the code point, if any; 4065 * otherwise the code point itself. 4066 * @stable ICU 2.0 4067 */ 4068 U_CAPI UChar32 U_EXPORT2 4069 u_foldCase(UChar32 c, uint32_t options); 4070 4071 /** 4072 * Returns the decimal digit value of the code point in the 4073 * specified radix. 4074 * 4075 * If the radix is not in the range <code>2<=radix<=36</code> or if the 4076 * value of <code>c</code> is not a valid digit in the specified 4077 * radix, <code>-1</code> is returned. A character is a valid digit 4078 * if at least one of the following is true: 4079 * <ul> 4080 * <li>The character has a decimal digit value. 4081 * Such characters have the general category "Nd" (decimal digit numbers) 4082 * and a Numeric_Type of Decimal. 4083 * In this case the value is the character's decimal digit value.</li> 4084 * <li>The character is one of the uppercase Latin letters 4085 * <code>'A'</code> through <code>'Z'</code>. 4086 * In this case the value is <code>c-'A'+10</code>.</li> 4087 * <li>The character is one of the lowercase Latin letters 4088 * <code>'a'</code> through <code>'z'</code>. 4089 * In this case the value is <code>ch-'a'+10</code>.</li> 4090 * <li>Latin letters from both the ASCII range (0061..007A, 0041..005A) 4091 * as well as from the Fullwidth ASCII range (FF41..FF5A, FF21..FF3A) 4092 * are recognized.</li> 4093 * </ul> 4094 * 4095 * Same as java.lang.Character.digit(). 4096 * 4097 * @param ch the code point to be tested. 4098 * @param radix the radix. 4099 * @return the numeric value represented by the character in the 4100 * specified radix, 4101 * or -1 if there is no value or if the value exceeds the radix. 4102 * 4103 * @see UCHAR_NUMERIC_TYPE 4104 * @see u_forDigit 4105 * @see u_charDigitValue 4106 * @see u_isdigit 4107 * @stable ICU 2.0 4108 */ 4109 U_CAPI int32_t U_EXPORT2 4110 u_digit(UChar32 ch, int8_t radix); 4111 4112 /** 4113 * Determines the character representation for a specific digit in 4114 * the specified radix. If the value of <code>radix</code> is not a 4115 * valid radix, or the value of <code>digit</code> is not a valid 4116 * digit in the specified radix, the null character 4117 * (<code>U+0000</code>) is returned. 4118 * <p> 4119 * The <code>radix</code> argument is valid if it is greater than or 4120 * equal to 2 and less than or equal to 36. 4121 * The <code>digit</code> argument is valid if 4122 * <code>0 <= digit < radix</code>. 4123 * <p> 4124 * If the digit is less than 10, then 4125 * <code>'0' + digit</code> is returned. Otherwise, the value 4126 * <code>'a' + digit - 10</code> is returned. 4127 * 4128 * Same as java.lang.Character.forDigit(). 4129 * 4130 * @param digit the number to convert to a character. 4131 * @param radix the radix. 4132 * @return the <code>char</code> representation of the specified digit 4133 * in the specified radix. 4134 * 4135 * @see u_digit 4136 * @see u_charDigitValue 4137 * @see u_isdigit 4138 * @stable ICU 2.0 4139 */ 4140 U_CAPI UChar32 U_EXPORT2 4141 u_forDigit(int32_t digit, int8_t radix); 4142 4143 /** 4144 * Get the "age" of the code point. 4145 * The "age" is the Unicode version when the code point was first 4146 * designated (as a non-character or for Private Use) 4147 * or assigned a character. 4148 * This can be useful to avoid emitting code points to receiving 4149 * processes that do not accept newer characters. 4150 * The data is from the UCD file DerivedAge.txt. 4151 * 4152 * @param c The code point. 4153 * @param versionArray The Unicode version number array, to be filled in. 4154 * 4155 * @stable ICU 2.1 4156 */ 4157 U_CAPI void U_EXPORT2 4158 u_charAge(UChar32 c, UVersionInfo versionArray); 4159 4160 /** 4161 * Gets the Unicode version information. 4162 * The version array is filled in with the version information 4163 * for the Unicode standard that is currently used by ICU. 4164 * For example, Unicode version 3.1.1 is represented as an array with 4165 * the values { 3, 1, 1, 0 }. 4166 * 4167 * @param versionArray an output array that will be filled in with 4168 * the Unicode version number 4169 * @stable ICU 2.0 4170 */ 4171 U_CAPI void U_EXPORT2 4172 u_getUnicodeVersion(UVersionInfo versionArray); 4173 4174 #if !UCONFIG_NO_NORMALIZATION 4175 /** 4176 * Get the FC_NFKC_Closure property string for a character. 4177 * See Unicode Standard Annex #15 for details, search for "FC_NFKC_Closure" 4178 * or for "FNC": http://www.unicode.org/reports/tr15/ 4179 * 4180 * @param c The character (code point) for which to get the FC_NFKC_Closure string. 4181 * It must be <code>0<=c<=0x10ffff</code>. 4182 * @param dest Destination address for copying the string. 4183 * The string will be zero-terminated if possible. 4184 * If there is no FC_NFKC_Closure string, 4185 * then the buffer will be set to the empty string. 4186 * @param destCapacity <code>==sizeof(dest)</code> 4187 * @param pErrorCode Pointer to a UErrorCode variable. 4188 * @return The length of the string, or 0 if there is no FC_NFKC_Closure string for this character. 4189 * If the destCapacity is less than or equal to the length, then the buffer 4190 * contains the truncated name and the returned length indicates the full 4191 * length of the name. 4192 * The length does not include the zero-termination. 4193 * 4194 * @stable ICU 2.2 4195 */ 4196 U_CAPI int32_t U_EXPORT2 4197 u_getFC_NFKC_Closure(UChar32 c, UChar *dest, int32_t destCapacity, UErrorCode *pErrorCode); 4198 4199 #endif 4200 4201 4202 U_CDECL_END 4203 4204 #endif /*_UCHAR*/ 4205 /*eof*/
Contact us
|
About us
|
Term of use
|
Copyright © 2000-2025 MyWebUniversity.com ™
