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