1/* 2********************************************************************** 3* Copyright (C) 1997-2014, International Business Machines 4* Corporation and others. All Rights Reserved. 5********************************************************************** 6* 7* File UCHAR.H 8* 9* Modification History: 10* 11* Date Name Description 12* 04/02/97 aliu Creation. 13* 03/29/99 helena Updated for C APIs. 14* 4/15/99 Madhu Updated for C Implementation and Javadoc 15* 5/20/99 Madhu Added the function u_getVersion() 16* 8/19/1999 srl Upgraded scripts to Unicode 3.0 17* 8/27/1999 schererm UCharDirection constants: U_... 18* 11/11/1999 weiv added u_isalnum(), cleaned comments 19* 01/11/2000 helena Renamed u_getVersion to u_getUnicodeVersion(). 20****************************************************************************** 21*/ 22 23#ifndef UCHAR_H 24#define UCHAR_H 25 26#include "unicode/utypes.h" 27 28U_CDECL_BEGIN 29 30/*==========================================================================*/ 31/* Unicode version number */ 32/*==========================================================================*/ 33/** 34 * Unicode version number, default for the current ICU version. 35 * The actual Unicode Character Database (UCD) data is stored in uprops.dat 36 * and may be generated from UCD files from a different Unicode version. 37 * Call u_getUnicodeVersion to get the actual Unicode version of the data. 38 * 39 * @see u_getUnicodeVersion 40 * @stable ICU 2.0 41 */ 42#define U_UNICODE_VERSION "7.0" 43 44/** 45 * \file 46 * \brief C API: Unicode Properties 47 * 48 * This C API provides low-level access to the Unicode Character Database. 49 * In addition to raw property values, some convenience functions calculate 50 * derived properties, for example for Java-style programming. 51 * 52 * Unicode assigns each code point (not just assigned character) values for 53 * many properties. 54 * Most of them are simple boolean flags, or constants from a small enumerated list. 55 * For some properties, values are strings or other relatively more complex types. 56 * 57 * For more information see 58 * "About the Unicode Character Database" (http://www.unicode.org/ucd/) 59 * and the ICU User Guide chapter on Properties (http://icu-project.org/userguide/properties.html). 60 * 61 * Many functions are designed to match java.lang.Character functions. 62 * See the individual function documentation, 63 * and see the JDK 1.4 java.lang.Character documentation 64 * at http://java.sun.com/j2se/1.4/docs/api/java/lang/Character.html 65 * 66 * There are also functions that provide easy migration from C/POSIX functions 67 * like isblank(). Their use is generally discouraged because the C/POSIX 68 * standards do not define their semantics beyond the ASCII range, which means 69 * that different implementations exhibit very different behavior. 70 * Instead, Unicode properties should be used directly. 71 * 72 * There are also only a few, broad C/POSIX character classes, and they tend 73 * to be used for conflicting purposes. For example, the "isalpha()" class 74 * is sometimes used to determine word boundaries, while a more sophisticated 75 * approach would at least distinguish initial letters from continuation 76 * characters (the latter including combining marks). 77 * (In ICU, BreakIterator is the most sophisticated API for word boundaries.) 78 * Another example: There is no "istitle()" class for titlecase characters. 79 * 80 * ICU 3.4 and later provides API access for all twelve C/POSIX character classes. 81 * ICU implements them according to the Standard Recommendations in 82 * Annex C: Compatibility Properties of UTS #18 Unicode Regular Expressions 83 * (http://www.unicode.org/reports/tr18/#Compatibility_Properties). 84 * 85 * API access for C/POSIX character classes is as follows: 86 * - alpha: u_isUAlphabetic(c) or u_hasBinaryProperty(c, UCHAR_ALPHABETIC) 87 * - lower: u_isULowercase(c) or u_hasBinaryProperty(c, UCHAR_LOWERCASE) 88 * - upper: u_isUUppercase(c) or u_hasBinaryProperty(c, UCHAR_UPPERCASE) 89 * - punct: u_ispunct(c) 90 * - digit: u_isdigit(c) or u_charType(c)==U_DECIMAL_DIGIT_NUMBER 91 * - xdigit: u_isxdigit(c) or u_hasBinaryProperty(c, UCHAR_POSIX_XDIGIT) 92 * - alnum: u_hasBinaryProperty(c, UCHAR_POSIX_ALNUM) 93 * - space: u_isUWhiteSpace(c) or u_hasBinaryProperty(c, UCHAR_WHITE_SPACE) 94 * - blank: u_isblank(c) or u_hasBinaryProperty(c, UCHAR_POSIX_BLANK) 95 * - cntrl: u_charType(c)==U_CONTROL_CHAR 96 * - graph: u_hasBinaryProperty(c, UCHAR_POSIX_GRAPH) 97 * - print: u_hasBinaryProperty(c, UCHAR_POSIX_PRINT) 98 * 99 * Note: Some of the u_isxyz() functions in uchar.h predate, and do not match, 100 * the Standard Recommendations in UTS #18. Instead, they match Java 101 * functions according to their API documentation. 102 * 103 * \htmlonly 104 * The C/POSIX character classes are also available in UnicodeSet patterns, 105 * using patterns like [:graph:] or \p{graph}. 106 * \endhtmlonly 107 * 108 * Note: There are several ICU whitespace functions. 109 * Comparison: 110 * - u_isUWhiteSpace=UCHAR_WHITE_SPACE: Unicode White_Space property; 111 * most of general categories "Z" (separators) + most whitespace ISO controls 112 * (including no-break spaces, but excluding IS1..IS4 and ZWSP) 113 * - u_isWhitespace: Java isWhitespace; Z + whitespace ISO controls but excluding no-break spaces 114 * - u_isJavaSpaceChar: Java isSpaceChar; just Z (including no-break spaces) 115 * - u_isspace: Z + whitespace ISO controls (including no-break spaces) 116 * - u_isblank: "horizontal spaces" = TAB + Zs - ZWSP 117 */ 118 119/** 120 * Constants. 121 */ 122 123/** The lowest Unicode code point value. Code points are non-negative. @stable ICU 2.0 */ 124#define UCHAR_MIN_VALUE 0 125 126/** 127 * The highest Unicode code point value (scalar value) according to 128 * The Unicode Standard. This is a 21-bit value (20.1 bits, rounded up). 129 * For a single character, UChar32 is a simple type that can hold any code point value. 130 * 131 * @see UChar32 132 * @stable ICU 2.0 133 */ 134#define UCHAR_MAX_VALUE 0x10ffff 135 136/** 137 * Get a single-bit bit set (a flag) from a bit number 0..31. 138 * @stable ICU 2.1 139 */ 140#define U_MASK(x) ((uint32_t)1<<(x)) 141 142/** 143 * Selection constants for Unicode properties. 144 * These constants are used in functions like u_hasBinaryProperty to select 145 * one of the Unicode properties. 146 * 147 * The properties APIs are intended to reflect Unicode properties as defined 148 * in the Unicode Character Database (UCD) and Unicode Technical Reports (UTR). 149 * For details about the properties see http://www.unicode.org/ucd/ . 150 * For names of Unicode properties see the UCD file PropertyAliases.txt. 151 * 152 * Important: If ICU is built with UCD files from Unicode versions below, e.g., 3.2, 153 * then properties marked with "new in Unicode 3.2" are not or not fully available. 154 * Check u_getUnicodeVersion to be sure. 155 * 156 * @see u_hasBinaryProperty 157 * @see u_getIntPropertyValue 158 * @see u_getUnicodeVersion 159 * @stable ICU 2.1 160 */ 161typedef enum UProperty { 162 /* 163 * Note: UProperty constants are parsed by preparseucd.py. 164 * It matches lines like 165 * UCHAR_<Unicode property name>=<integer>, 166 */ 167 168 /* Note: Place UCHAR_ALPHABETIC before UCHAR_BINARY_START so that 169 debuggers display UCHAR_ALPHABETIC as the symbolic name for 0, 170 rather than UCHAR_BINARY_START. Likewise for other *_START 171 identifiers. */ 172 173 /** Binary property Alphabetic. Same as u_isUAlphabetic, different from u_isalpha. 174 Lu+Ll+Lt+Lm+Lo+Nl+Other_Alphabetic @stable ICU 2.1 */ 175 UCHAR_ALPHABETIC=0, 176 /** First constant for binary Unicode properties. @stable ICU 2.1 */ 177 UCHAR_BINARY_START=UCHAR_ALPHABETIC, 178 /** Binary property ASCII_Hex_Digit. 0-9 A-F a-f @stable ICU 2.1 */ 179 UCHAR_ASCII_HEX_DIGIT=1, 180 /** Binary property Bidi_Control. 181 Format controls which have specific functions 182 in the Bidi Algorithm. @stable ICU 2.1 */ 183 UCHAR_BIDI_CONTROL=2, 184 /** Binary property Bidi_Mirrored. 185 Characters that may change display in RTL text. 186 Same as u_isMirrored. 187 See Bidi Algorithm, UTR 9. @stable ICU 2.1 */ 188 UCHAR_BIDI_MIRRORED=3, 189 /** Binary property Dash. Variations of dashes. @stable ICU 2.1 */ 190 UCHAR_DASH=4, 191 /** Binary property Default_Ignorable_Code_Point (new in Unicode 3.2). 192 Ignorable in most processing. 193 <2060..206F, FFF0..FFFB, E0000..E0FFF>+Other_Default_Ignorable_Code_Point+(Cf+Cc+Cs-White_Space) @stable ICU 2.1 */ 194 UCHAR_DEFAULT_IGNORABLE_CODE_POINT=5, 195 /** Binary property Deprecated (new in Unicode 3.2). 196 The usage of deprecated characters is strongly discouraged. @stable ICU 2.1 */ 197 UCHAR_DEPRECATED=6, 198 /** Binary property Diacritic. Characters that linguistically modify 199 the meaning of another character to which they apply. @stable ICU 2.1 */ 200 UCHAR_DIACRITIC=7, 201 /** Binary property Extender. 202 Extend the value or shape of a preceding alphabetic character, 203 e.g., length and iteration marks. @stable ICU 2.1 */ 204 UCHAR_EXTENDER=8, 205 /** Binary property Full_Composition_Exclusion. 206 CompositionExclusions.txt+Singleton Decompositions+ 207 Non-Starter Decompositions. @stable ICU 2.1 */ 208 UCHAR_FULL_COMPOSITION_EXCLUSION=9, 209 /** Binary property Grapheme_Base (new in Unicode 3.2). 210 For programmatic determination of grapheme cluster boundaries. 211 [0..10FFFF]-Cc-Cf-Cs-Co-Cn-Zl-Zp-Grapheme_Link-Grapheme_Extend-CGJ @stable ICU 2.1 */ 212 UCHAR_GRAPHEME_BASE=10, 213 /** Binary property Grapheme_Extend (new in Unicode 3.2). 214 For programmatic determination of grapheme cluster boundaries. 215 Me+Mn+Mc+Other_Grapheme_Extend-Grapheme_Link-CGJ @stable ICU 2.1 */ 216 UCHAR_GRAPHEME_EXTEND=11, 217 /** Binary property Grapheme_Link (new in Unicode 3.2). 218 For programmatic determination of grapheme cluster boundaries. @stable ICU 2.1 */ 219 UCHAR_GRAPHEME_LINK=12, 220 /** Binary property Hex_Digit. 221 Characters commonly used for hexadecimal numbers. @stable ICU 2.1 */ 222 UCHAR_HEX_DIGIT=13, 223 /** Binary property Hyphen. Dashes used to mark connections 224 between pieces of words, plus the Katakana middle dot. @stable ICU 2.1 */ 225 UCHAR_HYPHEN=14, 226 /** Binary property ID_Continue. 227 Characters that can continue an identifier. 228 DerivedCoreProperties.txt also says "NOTE: Cf characters should be filtered out." 229 ID_Start+Mn+Mc+Nd+Pc @stable ICU 2.1 */ 230 UCHAR_ID_CONTINUE=15, 231 /** Binary property ID_Start. 232 Characters that can start an identifier. 233 Lu+Ll+Lt+Lm+Lo+Nl @stable ICU 2.1 */ 234 UCHAR_ID_START=16, 235 /** Binary property Ideographic. 236 CJKV ideographs. @stable ICU 2.1 */ 237 UCHAR_IDEOGRAPHIC=17, 238 /** Binary property IDS_Binary_Operator (new in Unicode 3.2). 239 For programmatic determination of 240 Ideographic Description Sequences. @stable ICU 2.1 */ 241 UCHAR_IDS_BINARY_OPERATOR=18, 242 /** Binary property IDS_Trinary_Operator (new in Unicode 3.2). 243 For programmatic determination of 244 Ideographic Description Sequences. @stable ICU 2.1 */ 245 UCHAR_IDS_TRINARY_OPERATOR=19, 246 /** Binary property Join_Control. 247 Format controls for cursive joining and ligation. @stable ICU 2.1 */ 248 UCHAR_JOIN_CONTROL=20, 249 /** Binary property Logical_Order_Exception (new in Unicode 3.2). 250 Characters that do not use logical order and 251 require special handling in most processing. @stable ICU 2.1 */ 252 UCHAR_LOGICAL_ORDER_EXCEPTION=21, 253 /** Binary property Lowercase. Same as u_isULowercase, different from u_islower. 254 Ll+Other_Lowercase @stable ICU 2.1 */ 255 UCHAR_LOWERCASE=22, 256 /** Binary property Math. Sm+Other_Math @stable ICU 2.1 */ 257 UCHAR_MATH=23, 258 /** Binary property Noncharacter_Code_Point. 259 Code points that are explicitly defined as illegal 260 for the encoding of characters. @stable ICU 2.1 */ 261 UCHAR_NONCHARACTER_CODE_POINT=24, 262 /** Binary property Quotation_Mark. @stable ICU 2.1 */ 263 UCHAR_QUOTATION_MARK=25, 264 /** Binary property Radical (new in Unicode 3.2). 265 For programmatic determination of 266 Ideographic Description Sequences. @stable ICU 2.1 */ 267 UCHAR_RADICAL=26, 268 /** Binary property Soft_Dotted (new in Unicode 3.2). 269 Characters with a "soft dot", like i or j. 270 An accent placed on these characters causes 271 the dot to disappear. @stable ICU 2.1 */ 272 UCHAR_SOFT_DOTTED=27, 273 /** Binary property Terminal_Punctuation. 274 Punctuation characters that generally mark 275 the end of textual units. @stable ICU 2.1 */ 276 UCHAR_TERMINAL_PUNCTUATION=28, 277 /** Binary property Unified_Ideograph (new in Unicode 3.2). 278 For programmatic determination of 279 Ideographic Description Sequences. @stable ICU 2.1 */ 280 UCHAR_UNIFIED_IDEOGRAPH=29, 281 /** Binary property Uppercase. Same as u_isUUppercase, different from u_isupper. 282 Lu+Other_Uppercase @stable ICU 2.1 */ 283 UCHAR_UPPERCASE=30, 284 /** Binary property White_Space. 285 Same as u_isUWhiteSpace, different from u_isspace and u_isWhitespace. 286 Space characters+TAB+CR+LF-ZWSP-ZWNBSP @stable ICU 2.1 */ 287 UCHAR_WHITE_SPACE=31, 288 /** Binary property XID_Continue. 289 ID_Continue modified to allow closure under 290 normalization forms NFKC and NFKD. @stable ICU 2.1 */ 291 UCHAR_XID_CONTINUE=32, 292 /** Binary property XID_Start. ID_Start modified to allow 293 closure under normalization forms NFKC and NFKD. @stable ICU 2.1 */ 294 UCHAR_XID_START=33, 295 /** Binary property Case_Sensitive. Either the source of a case 296 mapping or _in_ the target of a case mapping. Not the same as 297 the general category Cased_Letter. @stable ICU 2.6 */ 298 UCHAR_CASE_SENSITIVE=34, 299 /** Binary property STerm (new in Unicode 4.0.1). 300 Sentence Terminal. Used in UAX #29: Text Boundaries 301 (http://www.unicode.org/reports/tr29/) 302 @stable ICU 3.0 */ 303 UCHAR_S_TERM=35, 304 /** Binary property Variation_Selector (new in Unicode 4.0.1). 305 Indicates all those characters that qualify as Variation Selectors. 306 For details on the behavior of these characters, 307 see StandardizedVariants.html and 15.6 Variation Selectors. 308 @stable ICU 3.0 */ 309 UCHAR_VARIATION_SELECTOR=36, 310 /** Binary property NFD_Inert. 311 ICU-specific property for characters that are inert under NFD, 312 i.e., they do not interact with adjacent characters. 313 See the documentation for the Normalizer2 class and the 314 Normalizer2::isInert() method. 315 @stable ICU 3.0 */ 316 UCHAR_NFD_INERT=37, 317 /** Binary property NFKD_Inert. 318 ICU-specific property for characters that are inert under NFKD, 319 i.e., they do not interact with adjacent characters. 320 See the documentation for the Normalizer2 class and the 321 Normalizer2::isInert() method. 322 @stable ICU 3.0 */ 323 UCHAR_NFKD_INERT=38, 324 /** Binary property NFC_Inert. 325 ICU-specific property for characters that are inert under NFC, 326 i.e., they do not interact with adjacent characters. 327 See the documentation for the Normalizer2 class and the 328 Normalizer2::isInert() method. 329 @stable ICU 3.0 */ 330 UCHAR_NFC_INERT=39, 331 /** Binary property NFKC_Inert. 332 ICU-specific property for characters that are inert under NFKC, 333 i.e., they do not interact with adjacent characters. 334 See the documentation for the Normalizer2 class and the 335 Normalizer2::isInert() method. 336 @stable ICU 3.0 */ 337 UCHAR_NFKC_INERT=40, 338 /** Binary Property Segment_Starter. 339 ICU-specific property for characters that are starters in terms of 340 Unicode normalization and combining character sequences. 341 They have ccc=0 and do not occur in non-initial position of the 342 canonical decomposition of any character 343 (like a-umlaut in NFD and a Jamo T in an NFD(Hangul LVT)). 344 ICU uses this property for segmenting a string for generating a set of 345 canonically equivalent strings, e.g. for canonical closure while 346 processing collation tailoring rules. 347 @stable ICU 3.0 */ 348 UCHAR_SEGMENT_STARTER=41, 349 /** Binary property Pattern_Syntax (new in Unicode 4.1). 350 See UAX #31 Identifier and Pattern Syntax 351 (http://www.unicode.org/reports/tr31/) 352 @stable ICU 3.4 */ 353 UCHAR_PATTERN_SYNTAX=42, 354 /** Binary property Pattern_White_Space (new in Unicode 4.1). 355 See UAX #31 Identifier and Pattern Syntax 356 (http://www.unicode.org/reports/tr31/) 357 @stable ICU 3.4 */ 358 UCHAR_PATTERN_WHITE_SPACE=43, 359 /** Binary property alnum (a C/POSIX character class). 360 Implemented according to the UTS #18 Annex C Standard Recommendation. 361 See the uchar.h file documentation. 362 @stable ICU 3.4 */ 363 UCHAR_POSIX_ALNUM=44, 364 /** Binary property blank (a C/POSIX character class). 365 Implemented according to the UTS #18 Annex C Standard Recommendation. 366 See the uchar.h file documentation. 367 @stable ICU 3.4 */ 368 UCHAR_POSIX_BLANK=45, 369 /** Binary property graph (a C/POSIX character class). 370 Implemented according to the UTS #18 Annex C Standard Recommendation. 371 See the uchar.h file documentation. 372 @stable ICU 3.4 */ 373 UCHAR_POSIX_GRAPH=46, 374 /** Binary property print (a C/POSIX character class). 375 Implemented according to the UTS #18 Annex C Standard Recommendation. 376 See the uchar.h file documentation. 377 @stable ICU 3.4 */ 378 UCHAR_POSIX_PRINT=47, 379 /** Binary property xdigit (a C/POSIX character class). 380 Implemented according to the UTS #18 Annex C Standard Recommendation. 381 See the uchar.h file documentation. 382 @stable ICU 3.4 */ 383 UCHAR_POSIX_XDIGIT=48, 384 /** Binary property Cased. For Lowercase, Uppercase and Titlecase characters. @stable ICU 4.4 */ 385 UCHAR_CASED=49, 386 /** Binary property Case_Ignorable. Used in context-sensitive case mappings. @stable ICU 4.4 */ 387 UCHAR_CASE_IGNORABLE=50, 388 /** Binary property Changes_When_Lowercased. @stable ICU 4.4 */ 389 UCHAR_CHANGES_WHEN_LOWERCASED=51, 390 /** Binary property Changes_When_Uppercased. @stable ICU 4.4 */ 391 UCHAR_CHANGES_WHEN_UPPERCASED=52, 392 /** Binary property Changes_When_Titlecased. @stable ICU 4.4 */ 393 UCHAR_CHANGES_WHEN_TITLECASED=53, 394 /** Binary property Changes_When_Casefolded. @stable ICU 4.4 */ 395 UCHAR_CHANGES_WHEN_CASEFOLDED=54, 396 /** Binary property Changes_When_Casemapped. @stable ICU 4.4 */ 397 UCHAR_CHANGES_WHEN_CASEMAPPED=55, 398 /** Binary property Changes_When_NFKC_Casefolded. @stable ICU 4.4 */ 399 UCHAR_CHANGES_WHEN_NFKC_CASEFOLDED=56, 400 /** One more than the last constant for binary Unicode properties. @stable ICU 2.1 */ 401 UCHAR_BINARY_LIMIT=57, 402 403 /** Enumerated property Bidi_Class. 404 Same as u_charDirection, returns UCharDirection values. @stable ICU 2.2 */ 405 UCHAR_BIDI_CLASS=0x1000, 406 /** First constant for enumerated/integer Unicode properties. @stable ICU 2.2 */ 407 UCHAR_INT_START=UCHAR_BIDI_CLASS, 408 /** Enumerated property Block. 409 Same as ublock_getCode, returns UBlockCode values. @stable ICU 2.2 */ 410 UCHAR_BLOCK=0x1001, 411 /** Enumerated property Canonical_Combining_Class. 412 Same as u_getCombiningClass, returns 8-bit numeric values. @stable ICU 2.2 */ 413 UCHAR_CANONICAL_COMBINING_CLASS=0x1002, 414 /** Enumerated property Decomposition_Type. 415 Returns UDecompositionType values. @stable ICU 2.2 */ 416 UCHAR_DECOMPOSITION_TYPE=0x1003, 417 /** Enumerated property East_Asian_Width. 418 See http://www.unicode.org/reports/tr11/ 419 Returns UEastAsianWidth values. @stable ICU 2.2 */ 420 UCHAR_EAST_ASIAN_WIDTH=0x1004, 421 /** Enumerated property General_Category. 422 Same as u_charType, returns UCharCategory values. @stable ICU 2.2 */ 423 UCHAR_GENERAL_CATEGORY=0x1005, 424 /** Enumerated property Joining_Group. 425 Returns UJoiningGroup values. @stable ICU 2.2 */ 426 UCHAR_JOINING_GROUP=0x1006, 427 /** Enumerated property Joining_Type. 428 Returns UJoiningType values. @stable ICU 2.2 */ 429 UCHAR_JOINING_TYPE=0x1007, 430 /** Enumerated property Line_Break. 431 Returns ULineBreak values. @stable ICU 2.2 */ 432 UCHAR_LINE_BREAK=0x1008, 433 /** Enumerated property Numeric_Type. 434 Returns UNumericType values. @stable ICU 2.2 */ 435 UCHAR_NUMERIC_TYPE=0x1009, 436 /** Enumerated property Script. 437 Same as uscript_getScript, returns UScriptCode values. @stable ICU 2.2 */ 438 UCHAR_SCRIPT=0x100A, 439 /** Enumerated property Hangul_Syllable_Type, new in Unicode 4. 440 Returns UHangulSyllableType values. @stable ICU 2.6 */ 441 UCHAR_HANGUL_SYLLABLE_TYPE=0x100B, 442 /** Enumerated property NFD_Quick_Check. 443 Returns UNormalizationCheckResult values. @stable ICU 3.0 */ 444 UCHAR_NFD_QUICK_CHECK=0x100C, 445 /** Enumerated property NFKD_Quick_Check. 446 Returns UNormalizationCheckResult values. @stable ICU 3.0 */ 447 UCHAR_NFKD_QUICK_CHECK=0x100D, 448 /** Enumerated property NFC_Quick_Check. 449 Returns UNormalizationCheckResult values. @stable ICU 3.0 */ 450 UCHAR_NFC_QUICK_CHECK=0x100E, 451 /** Enumerated property NFKC_Quick_Check. 452 Returns UNormalizationCheckResult values. @stable ICU 3.0 */ 453 UCHAR_NFKC_QUICK_CHECK=0x100F, 454 /** Enumerated property Lead_Canonical_Combining_Class. 455 ICU-specific property for the ccc of the first code point 456 of the decomposition, or lccc(c)=ccc(NFD(c)[0]). 457 Useful for checking for canonically ordered text; 458 see UNORM_FCD and http://www.unicode.org/notes/tn5/#FCD . 459 Returns 8-bit numeric values like UCHAR_CANONICAL_COMBINING_CLASS. @stable ICU 3.0 */ 460 UCHAR_LEAD_CANONICAL_COMBINING_CLASS=0x1010, 461 /** Enumerated property Trail_Canonical_Combining_Class. 462 ICU-specific property for the ccc of the last code point 463 of the decomposition, or tccc(c)=ccc(NFD(c)[last]). 464 Useful for checking for canonically ordered text; 465 see UNORM_FCD and http://www.unicode.org/notes/tn5/#FCD . 466 Returns 8-bit numeric values like UCHAR_CANONICAL_COMBINING_CLASS. @stable ICU 3.0 */ 467 UCHAR_TRAIL_CANONICAL_COMBINING_CLASS=0x1011, 468 /** Enumerated property Grapheme_Cluster_Break (new in Unicode 4.1). 469 Used in UAX #29: Text Boundaries 470 (http://www.unicode.org/reports/tr29/) 471 Returns UGraphemeClusterBreak values. @stable ICU 3.4 */ 472 UCHAR_GRAPHEME_CLUSTER_BREAK=0x1012, 473 /** Enumerated property Sentence_Break (new in Unicode 4.1). 474 Used in UAX #29: Text Boundaries 475 (http://www.unicode.org/reports/tr29/) 476 Returns USentenceBreak values. @stable ICU 3.4 */ 477 UCHAR_SENTENCE_BREAK=0x1013, 478 /** Enumerated property Word_Break (new in Unicode 4.1). 479 Used in UAX #29: Text Boundaries 480 (http://www.unicode.org/reports/tr29/) 481 Returns UWordBreakValues values. @stable ICU 3.4 */ 482 UCHAR_WORD_BREAK=0x1014, 483 /** Enumerated property Bidi_Paired_Bracket_Type (new in Unicode 6.3). 484 Used in UAX #9: Unicode Bidirectional Algorithm 485 (http://www.unicode.org/reports/tr9/) 486 Returns UBidiPairedBracketType values. @stable ICU 52 */ 487 UCHAR_BIDI_PAIRED_BRACKET_TYPE=0x1015, 488 /** One more than the last constant for enumerated/integer Unicode properties. @stable ICU 2.2 */ 489 UCHAR_INT_LIMIT=0x1016, 490 491 /** Bitmask property General_Category_Mask. 492 This is the General_Category property returned as a bit mask. 493 When used in u_getIntPropertyValue(c), same as U_MASK(u_charType(c)), 494 returns bit masks for UCharCategory values where exactly one bit is set. 495 When used with u_getPropertyValueName() and u_getPropertyValueEnum(), 496 a multi-bit mask is used for sets of categories like "Letters". 497 Mask values should be cast to uint32_t. 498 @stable ICU 2.4 */ 499 UCHAR_GENERAL_CATEGORY_MASK=0x2000, 500 /** First constant for bit-mask Unicode properties. @stable ICU 2.4 */ 501 UCHAR_MASK_START=UCHAR_GENERAL_CATEGORY_MASK, 502 /** One more than the last constant for bit-mask Unicode properties. @stable ICU 2.4 */ 503 UCHAR_MASK_LIMIT=0x2001, 504 505 /** Double property Numeric_Value. 506 Corresponds to u_getNumericValue. @stable ICU 2.4 */ 507 UCHAR_NUMERIC_VALUE=0x3000, 508 /** First constant for double Unicode properties. @stable ICU 2.4 */ 509 UCHAR_DOUBLE_START=UCHAR_NUMERIC_VALUE, 510 /** One more than the last constant for double Unicode properties. @stable ICU 2.4 */ 511 UCHAR_DOUBLE_LIMIT=0x3001, 512 513 /** String property Age. 514 Corresponds to u_charAge. @stable ICU 2.4 */ 515 UCHAR_AGE=0x4000, 516 /** First constant for string Unicode properties. @stable ICU 2.4 */ 517 UCHAR_STRING_START=UCHAR_AGE, 518 /** String property Bidi_Mirroring_Glyph. 519 Corresponds to u_charMirror. @stable ICU 2.4 */ 520 UCHAR_BIDI_MIRRORING_GLYPH=0x4001, 521 /** String property Case_Folding. 522 Corresponds to u_strFoldCase in ustring.h. @stable ICU 2.4 */ 523 UCHAR_CASE_FOLDING=0x4002, 524#ifndef U_HIDE_DEPRECATED_API 525 /** Deprecated string property ISO_Comment. 526 Corresponds to u_getISOComment. @deprecated ICU 49 */ 527 UCHAR_ISO_COMMENT=0x4003, 528#endif /* U_HIDE_DEPRECATED_API */ 529 /** String property Lowercase_Mapping. 530 Corresponds to u_strToLower in ustring.h. @stable ICU 2.4 */ 531 UCHAR_LOWERCASE_MAPPING=0x4004, 532 /** String property Name. 533 Corresponds to u_charName. @stable ICU 2.4 */ 534 UCHAR_NAME=0x4005, 535 /** String property Simple_Case_Folding. 536 Corresponds to u_foldCase. @stable ICU 2.4 */ 537 UCHAR_SIMPLE_CASE_FOLDING=0x4006, 538 /** String property Simple_Lowercase_Mapping. 539 Corresponds to u_tolower. @stable ICU 2.4 */ 540 UCHAR_SIMPLE_LOWERCASE_MAPPING=0x4007, 541 /** String property Simple_Titlecase_Mapping. 542 Corresponds to u_totitle. @stable ICU 2.4 */ 543 UCHAR_SIMPLE_TITLECASE_MAPPING=0x4008, 544 /** String property Simple_Uppercase_Mapping. 545 Corresponds to u_toupper. @stable ICU 2.4 */ 546 UCHAR_SIMPLE_UPPERCASE_MAPPING=0x4009, 547 /** String property Titlecase_Mapping. 548 Corresponds to u_strToTitle in ustring.h. @stable ICU 2.4 */ 549 UCHAR_TITLECASE_MAPPING=0x400A, 550#ifndef U_HIDE_DEPRECATED_API 551 /** String property Unicode_1_Name. 552 This property is of little practical value. 553 Beginning with ICU 49, ICU APIs return an empty string for this property. 554 Corresponds to u_charName(U_UNICODE_10_CHAR_NAME). @deprecated ICU 49 */ 555 UCHAR_UNICODE_1_NAME=0x400B, 556#endif /* U_HIDE_DEPRECATED_API */ 557 /** String property Uppercase_Mapping. 558 Corresponds to u_strToUpper in ustring.h. @stable ICU 2.4 */ 559 UCHAR_UPPERCASE_MAPPING=0x400C, 560 /** String property Bidi_Paired_Bracket (new in Unicode 6.3). 561 Corresponds to u_getBidiPairedBracket. @stable ICU 52 */ 562 UCHAR_BIDI_PAIRED_BRACKET=0x400D, 563 /** One more than the last constant for string Unicode properties. @stable ICU 2.4 */ 564 UCHAR_STRING_LIMIT=0x400E, 565 566 /** Miscellaneous property Script_Extensions (new in Unicode 6.0). 567 Some characters are commonly used in multiple scripts. 568 For more information, see UAX #24: http://www.unicode.org/reports/tr24/. 569 Corresponds to uscript_hasScript and uscript_getScriptExtensions in uscript.h. 570 @stable ICU 4.6 */ 571 UCHAR_SCRIPT_EXTENSIONS=0x7000, 572 /** First constant for Unicode properties with unusual value types. @stable ICU 4.6 */ 573 UCHAR_OTHER_PROPERTY_START=UCHAR_SCRIPT_EXTENSIONS, 574 /** One more than the last constant for Unicode properties with unusual value types. 575 * @stable ICU 4.6 */ 576 UCHAR_OTHER_PROPERTY_LIMIT=0x7001, 577 /** Represents a nonexistent or invalid property or property value. @stable ICU 2.4 */ 578 UCHAR_INVALID_CODE = -1 579} UProperty; 580 581/** 582 * Data for enumerated Unicode general category types. 583 * See http://www.unicode.org/Public/UNIDATA/UnicodeData.html . 584 * @stable ICU 2.0 585 */ 586typedef enum UCharCategory 587{ 588 /* 589 * Note: UCharCategory constants and their API comments are parsed by preparseucd.py. 590 * It matches pairs of lines like 591 * / ** <Unicode 2-letter General_Category value> comment... * / 592 * U_<[A-Z_]+> = <integer>, 593 */ 594 595 /** Non-category for unassigned and non-character code points. @stable ICU 2.0 */ 596 U_UNASSIGNED = 0, 597 /** Cn "Other, Not Assigned (no characters in [UnicodeData.txt] have this property)" (same as U_UNASSIGNED!) @stable ICU 2.0 */ 598 U_GENERAL_OTHER_TYPES = 0, 599 /** Lu @stable ICU 2.0 */ 600 U_UPPERCASE_LETTER = 1, 601 /** Ll @stable ICU 2.0 */ 602 U_LOWERCASE_LETTER = 2, 603 /** Lt @stable ICU 2.0 */ 604 U_TITLECASE_LETTER = 3, 605 /** Lm @stable ICU 2.0 */ 606 U_MODIFIER_LETTER = 4, 607 /** Lo @stable ICU 2.0 */ 608 U_OTHER_LETTER = 5, 609 /** Mn @stable ICU 2.0 */ 610 U_NON_SPACING_MARK = 6, 611 /** Me @stable ICU 2.0 */ 612 U_ENCLOSING_MARK = 7, 613 /** Mc @stable ICU 2.0 */ 614 U_COMBINING_SPACING_MARK = 8, 615 /** Nd @stable ICU 2.0 */ 616 U_DECIMAL_DIGIT_NUMBER = 9, 617 /** Nl @stable ICU 2.0 */ 618 U_LETTER_NUMBER = 10, 619 /** No @stable ICU 2.0 */ 620 U_OTHER_NUMBER = 11, 621 /** Zs @stable ICU 2.0 */ 622 U_SPACE_SEPARATOR = 12, 623 /** Zl @stable ICU 2.0 */ 624 U_LINE_SEPARATOR = 13, 625 /** Zp @stable ICU 2.0 */ 626 U_PARAGRAPH_SEPARATOR = 14, 627 /** Cc @stable ICU 2.0 */ 628 U_CONTROL_CHAR = 15, 629 /** Cf @stable ICU 2.0 */ 630 U_FORMAT_CHAR = 16, 631 /** Co @stable ICU 2.0 */ 632 U_PRIVATE_USE_CHAR = 17, 633 /** Cs @stable ICU 2.0 */ 634 U_SURROGATE = 18, 635 /** Pd @stable ICU 2.0 */ 636 U_DASH_PUNCTUATION = 19, 637 /** Ps @stable ICU 2.0 */ 638 U_START_PUNCTUATION = 20, 639 /** Pe @stable ICU 2.0 */ 640 U_END_PUNCTUATION = 21, 641 /** Pc @stable ICU 2.0 */ 642 U_CONNECTOR_PUNCTUATION = 22, 643 /** Po @stable ICU 2.0 */ 644 U_OTHER_PUNCTUATION = 23, 645 /** Sm @stable ICU 2.0 */ 646 U_MATH_SYMBOL = 24, 647 /** Sc @stable ICU 2.0 */ 648 U_CURRENCY_SYMBOL = 25, 649 /** Sk @stable ICU 2.0 */ 650 U_MODIFIER_SYMBOL = 26, 651 /** So @stable ICU 2.0 */ 652 U_OTHER_SYMBOL = 27, 653 /** Pi @stable ICU 2.0 */ 654 U_INITIAL_PUNCTUATION = 28, 655 /** Pf @stable ICU 2.0 */ 656 U_FINAL_PUNCTUATION = 29, 657 /** One higher than the last enum UCharCategory constant. @stable ICU 2.0 */ 658 U_CHAR_CATEGORY_COUNT 659} UCharCategory; 660 661/** 662 * U_GC_XX_MASK constants are bit flags corresponding to Unicode 663 * general category values. 664 * For each category, the nth bit is set if the numeric value of the 665 * corresponding UCharCategory constant is n. 666 * 667 * There are also some U_GC_Y_MASK constants for groups of general categories 668 * like L for all letter categories. 669 * 670 * @see u_charType 671 * @see U_GET_GC_MASK 672 * @see UCharCategory 673 * @stable ICU 2.1 674 */ 675#define U_GC_CN_MASK U_MASK(U_GENERAL_OTHER_TYPES) 676 677/** Mask constant for a UCharCategory. @stable ICU 2.1 */ 678#define U_GC_LU_MASK U_MASK(U_UPPERCASE_LETTER) 679/** Mask constant for a UCharCategory. @stable ICU 2.1 */ 680#define U_GC_LL_MASK U_MASK(U_LOWERCASE_LETTER) 681/** Mask constant for a UCharCategory. @stable ICU 2.1 */ 682#define U_GC_LT_MASK U_MASK(U_TITLECASE_LETTER) 683/** Mask constant for a UCharCategory. @stable ICU 2.1 */ 684#define U_GC_LM_MASK U_MASK(U_MODIFIER_LETTER) 685/** Mask constant for a UCharCategory. @stable ICU 2.1 */ 686#define U_GC_LO_MASK U_MASK(U_OTHER_LETTER) 687 688/** Mask constant for a UCharCategory. @stable ICU 2.1 */ 689#define U_GC_MN_MASK U_MASK(U_NON_SPACING_MARK) 690/** Mask constant for a UCharCategory. @stable ICU 2.1 */ 691#define U_GC_ME_MASK U_MASK(U_ENCLOSING_MARK) 692/** Mask constant for a UCharCategory. @stable ICU 2.1 */ 693#define U_GC_MC_MASK U_MASK(U_COMBINING_SPACING_MARK) 694 695/** Mask constant for a UCharCategory. @stable ICU 2.1 */ 696#define U_GC_ND_MASK U_MASK(U_DECIMAL_DIGIT_NUMBER) 697/** Mask constant for a UCharCategory. @stable ICU 2.1 */ 698#define U_GC_NL_MASK U_MASK(U_LETTER_NUMBER) 699/** Mask constant for a UCharCategory. @stable ICU 2.1 */ 700#define U_GC_NO_MASK U_MASK(U_OTHER_NUMBER) 701 702/** Mask constant for a UCharCategory. @stable ICU 2.1 */ 703#define U_GC_ZS_MASK U_MASK(U_SPACE_SEPARATOR) 704/** Mask constant for a UCharCategory. @stable ICU 2.1 */ 705#define U_GC_ZL_MASK U_MASK(U_LINE_SEPARATOR) 706/** Mask constant for a UCharCategory. @stable ICU 2.1 */ 707#define U_GC_ZP_MASK U_MASK(U_PARAGRAPH_SEPARATOR) 708 709/** Mask constant for a UCharCategory. @stable ICU 2.1 */ 710#define U_GC_CC_MASK U_MASK(U_CONTROL_CHAR) 711/** Mask constant for a UCharCategory. @stable ICU 2.1 */ 712#define U_GC_CF_MASK U_MASK(U_FORMAT_CHAR) 713/** Mask constant for a UCharCategory. @stable ICU 2.1 */ 714#define U_GC_CO_MASK U_MASK(U_PRIVATE_USE_CHAR) 715/** Mask constant for a UCharCategory. @stable ICU 2.1 */ 716#define U_GC_CS_MASK U_MASK(U_SURROGATE) 717 718/** Mask constant for a UCharCategory. @stable ICU 2.1 */ 719#define U_GC_PD_MASK U_MASK(U_DASH_PUNCTUATION) 720/** Mask constant for a UCharCategory. @stable ICU 2.1 */ 721#define U_GC_PS_MASK U_MASK(U_START_PUNCTUATION) 722/** Mask constant for a UCharCategory. @stable ICU 2.1 */ 723#define U_GC_PE_MASK U_MASK(U_END_PUNCTUATION) 724/** Mask constant for a UCharCategory. @stable ICU 2.1 */ 725#define U_GC_PC_MASK U_MASK(U_CONNECTOR_PUNCTUATION) 726/** Mask constant for a UCharCategory. @stable ICU 2.1 */ 727#define U_GC_PO_MASK U_MASK(U_OTHER_PUNCTUATION) 728 729/** Mask constant for a UCharCategory. @stable ICU 2.1 */ 730#define U_GC_SM_MASK U_MASK(U_MATH_SYMBOL) 731/** Mask constant for a UCharCategory. @stable ICU 2.1 */ 732#define U_GC_SC_MASK U_MASK(U_CURRENCY_SYMBOL) 733/** Mask constant for a UCharCategory. @stable ICU 2.1 */ 734#define U_GC_SK_MASK U_MASK(U_MODIFIER_SYMBOL) 735/** Mask constant for a UCharCategory. @stable ICU 2.1 */ 736#define U_GC_SO_MASK U_MASK(U_OTHER_SYMBOL) 737 738/** Mask constant for a UCharCategory. @stable ICU 2.1 */ 739#define U_GC_PI_MASK U_MASK(U_INITIAL_PUNCTUATION) 740/** Mask constant for a UCharCategory. @stable ICU 2.1 */ 741#define U_GC_PF_MASK U_MASK(U_FINAL_PUNCTUATION) 742 743 744/** Mask constant for multiple UCharCategory bits (L Letters). @stable ICU 2.1 */ 745#define U_GC_L_MASK \ 746 (U_GC_LU_MASK|U_GC_LL_MASK|U_GC_LT_MASK|U_GC_LM_MASK|U_GC_LO_MASK) 747 748/** Mask constant for multiple UCharCategory bits (LC Cased Letters). @stable ICU 2.1 */ 749#define U_GC_LC_MASK \ 750 (U_GC_LU_MASK|U_GC_LL_MASK|U_GC_LT_MASK) 751 752/** Mask constant for multiple UCharCategory bits (M Marks). @stable ICU 2.1 */ 753#define U_GC_M_MASK (U_GC_MN_MASK|U_GC_ME_MASK|U_GC_MC_MASK) 754 755/** Mask constant for multiple UCharCategory bits (N Numbers). @stable ICU 2.1 */ 756#define U_GC_N_MASK (U_GC_ND_MASK|U_GC_NL_MASK|U_GC_NO_MASK) 757 758/** Mask constant for multiple UCharCategory bits (Z Separators). @stable ICU 2.1 */ 759#define U_GC_Z_MASK (U_GC_ZS_MASK|U_GC_ZL_MASK|U_GC_ZP_MASK) 760 761/** Mask constant for multiple UCharCategory bits (C Others). @stable ICU 2.1 */ 762#define U_GC_C_MASK \ 763 (U_GC_CN_MASK|U_GC_CC_MASK|U_GC_CF_MASK|U_GC_CO_MASK|U_GC_CS_MASK) 764 765/** Mask constant for multiple UCharCategory bits (P Punctuation). @stable ICU 2.1 */ 766#define U_GC_P_MASK \ 767 (U_GC_PD_MASK|U_GC_PS_MASK|U_GC_PE_MASK|U_GC_PC_MASK|U_GC_PO_MASK| \ 768 U_GC_PI_MASK|U_GC_PF_MASK) 769 770/** Mask constant for multiple UCharCategory bits (S Symbols). @stable ICU 2.1 */ 771#define U_GC_S_MASK (U_GC_SM_MASK|U_GC_SC_MASK|U_GC_SK_MASK|U_GC_SO_MASK) 772 773/** 774 * This specifies the language directional property of a character set. 775 * @stable ICU 2.0 776 */ 777typedef enum UCharDirection { 778 /* 779 * Note: UCharDirection constants and their API comments are parsed by preparseucd.py. 780 * It matches pairs of lines like 781 * / ** <Unicode 1..3-letter Bidi_Class value> comment... * / 782 * U_<[A-Z_]+> = <integer>, 783 */ 784 785 /** L @stable ICU 2.0 */ 786 U_LEFT_TO_RIGHT = 0, 787 /** R @stable ICU 2.0 */ 788 U_RIGHT_TO_LEFT = 1, 789 /** EN @stable ICU 2.0 */ 790 U_EUROPEAN_NUMBER = 2, 791 /** ES @stable ICU 2.0 */ 792 U_EUROPEAN_NUMBER_SEPARATOR = 3, 793 /** ET @stable ICU 2.0 */ 794 U_EUROPEAN_NUMBER_TERMINATOR = 4, 795 /** AN @stable ICU 2.0 */ 796 U_ARABIC_NUMBER = 5, 797 /** CS @stable ICU 2.0 */ 798 U_COMMON_NUMBER_SEPARATOR = 6, 799 /** B @stable ICU 2.0 */ 800 U_BLOCK_SEPARATOR = 7, 801 /** S @stable ICU 2.0 */ 802 U_SEGMENT_SEPARATOR = 8, 803 /** WS @stable ICU 2.0 */ 804 U_WHITE_SPACE_NEUTRAL = 9, 805 /** ON @stable ICU 2.0 */ 806 U_OTHER_NEUTRAL = 10, 807 /** LRE @stable ICU 2.0 */ 808 U_LEFT_TO_RIGHT_EMBEDDING = 11, 809 /** LRO @stable ICU 2.0 */ 810 U_LEFT_TO_RIGHT_OVERRIDE = 12, 811 /** AL @stable ICU 2.0 */ 812 U_RIGHT_TO_LEFT_ARABIC = 13, 813 /** RLE @stable ICU 2.0 */ 814 U_RIGHT_TO_LEFT_EMBEDDING = 14, 815 /** RLO @stable ICU 2.0 */ 816 U_RIGHT_TO_LEFT_OVERRIDE = 15, 817 /** PDF @stable ICU 2.0 */ 818 U_POP_DIRECTIONAL_FORMAT = 16, 819 /** NSM @stable ICU 2.0 */ 820 U_DIR_NON_SPACING_MARK = 17, 821 /** BN @stable ICU 2.0 */ 822 U_BOUNDARY_NEUTRAL = 18, 823 /** FSI @stable ICU 52 */ 824 U_FIRST_STRONG_ISOLATE = 19, 825 /** LRI @stable ICU 52 */ 826 U_LEFT_TO_RIGHT_ISOLATE = 20, 827 /** RLI @stable ICU 52 */ 828 U_RIGHT_TO_LEFT_ISOLATE = 21, 829 /** PDI @stable ICU 52 */ 830 U_POP_DIRECTIONAL_ISOLATE = 22, 831 /** @stable ICU 2.0 */ 832 U_CHAR_DIRECTION_COUNT 833} UCharDirection; 834 835/** 836 * Bidi Paired Bracket Type constants. 837 * 838 * @see UCHAR_BIDI_PAIRED_BRACKET_TYPE 839 * @stable ICU 52 840 */ 841typedef enum UBidiPairedBracketType { 842 /* 843 * Note: UBidiPairedBracketType constants are parsed by preparseucd.py. 844 * It matches lines like 845 * U_BPT_<Unicode Bidi_Paired_Bracket_Type value name> 846 */ 847 848 /** Not a paired bracket. @stable ICU 52 */ 849 U_BPT_NONE, 850 /** Open paired bracket. @stable ICU 52 */ 851 U_BPT_OPEN, 852 /** Close paired bracket. @stable ICU 52 */ 853 U_BPT_CLOSE, 854 /** @stable ICU 52 */ 855 U_BPT_COUNT /* 3 */ 856} UBidiPairedBracketType; 857 858/** 859 * Constants for Unicode blocks, see the Unicode Data file Blocks.txt 860 * @stable ICU 2.0 861 */ 862enum UBlockCode { 863 /* 864 * Note: UBlockCode constants are parsed by preparseucd.py. 865 * It matches lines like 866 * UBLOCK_<Unicode Block value name> = <integer>, 867 */ 868 869 /** New No_Block value in Unicode 4. @stable ICU 2.6 */ 870 UBLOCK_NO_BLOCK = 0, /*[none]*/ /* Special range indicating No_Block */ 871 872 /** @stable ICU 2.0 */ 873 UBLOCK_BASIC_LATIN = 1, /*[0000]*/ 874 875 /** @stable ICU 2.0 */ 876 UBLOCK_LATIN_1_SUPPLEMENT=2, /*[0080]*/ 877 878 /** @stable ICU 2.0 */ 879 UBLOCK_LATIN_EXTENDED_A =3, /*[0100]*/ 880 881 /** @stable ICU 2.0 */ 882 UBLOCK_LATIN_EXTENDED_B =4, /*[0180]*/ 883 884 /** @stable ICU 2.0 */ 885 UBLOCK_IPA_EXTENSIONS =5, /*[0250]*/ 886 887 /** @stable ICU 2.0 */ 888 UBLOCK_SPACING_MODIFIER_LETTERS =6, /*[02B0]*/ 889 890 /** @stable ICU 2.0 */ 891 UBLOCK_COMBINING_DIACRITICAL_MARKS =7, /*[0300]*/ 892 893 /** 894 * Unicode 3.2 renames this block to "Greek and Coptic". 895 * @stable ICU 2.0 896 */ 897 UBLOCK_GREEK =8, /*[0370]*/ 898 899 /** @stable ICU 2.0 */ 900 UBLOCK_CYRILLIC =9, /*[0400]*/ 901 902 /** @stable ICU 2.0 */ 903 UBLOCK_ARMENIAN =10, /*[0530]*/ 904 905 /** @stable ICU 2.0 */ 906 UBLOCK_HEBREW =11, /*[0590]*/ 907 908 /** @stable ICU 2.0 */ 909 UBLOCK_ARABIC =12, /*[0600]*/ 910 911 /** @stable ICU 2.0 */ 912 UBLOCK_SYRIAC =13, /*[0700]*/ 913 914 /** @stable ICU 2.0 */ 915 UBLOCK_THAANA =14, /*[0780]*/ 916 917 /** @stable ICU 2.0 */ 918 UBLOCK_DEVANAGARI =15, /*[0900]*/ 919 920 /** @stable ICU 2.0 */ 921 UBLOCK_BENGALI =16, /*[0980]*/ 922 923 /** @stable ICU 2.0 */ 924 UBLOCK_GURMUKHI =17, /*[0A00]*/ 925 926 /** @stable ICU 2.0 */ 927 UBLOCK_GUJARATI =18, /*[0A80]*/ 928 929 /** @stable ICU 2.0 */ 930 UBLOCK_ORIYA =19, /*[0B00]*/ 931 932 /** @stable ICU 2.0 */ 933 UBLOCK_TAMIL =20, /*[0B80]*/ 934 935 /** @stable ICU 2.0 */ 936 UBLOCK_TELUGU =21, /*[0C00]*/ 937 938 /** @stable ICU 2.0 */ 939 UBLOCK_KANNADA =22, /*[0C80]*/ 940 941 /** @stable ICU 2.0 */ 942 UBLOCK_MALAYALAM =23, /*[0D00]*/ 943 944 /** @stable ICU 2.0 */ 945 UBLOCK_SINHALA =24, /*[0D80]*/ 946 947 /** @stable ICU 2.0 */ 948 UBLOCK_THAI =25, /*[0E00]*/ 949 950 /** @stable ICU 2.0 */ 951 UBLOCK_LAO =26, /*[0E80]*/ 952 953 /** @stable ICU 2.0 */ 954 UBLOCK_TIBETAN =27, /*[0F00]*/ 955 956 /** @stable ICU 2.0 */ 957 UBLOCK_MYANMAR =28, /*[1000]*/ 958 959 /** @stable ICU 2.0 */ 960 UBLOCK_GEORGIAN =29, /*[10A0]*/ 961 962 /** @stable ICU 2.0 */ 963 UBLOCK_HANGUL_JAMO =30, /*[1100]*/ 964 965 /** @stable ICU 2.0 */ 966 UBLOCK_ETHIOPIC =31, /*[1200]*/ 967 968 /** @stable ICU 2.0 */ 969 UBLOCK_CHEROKEE =32, /*[13A0]*/ 970 971 /** @stable ICU 2.0 */ 972 UBLOCK_UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS =33, /*[1400]*/ 973 974 /** @stable ICU 2.0 */ 975 UBLOCK_OGHAM =34, /*[1680]*/ 976 977 /** @stable ICU 2.0 */ 978 UBLOCK_RUNIC =35, /*[16A0]*/ 979 980 /** @stable ICU 2.0 */ 981 UBLOCK_KHMER =36, /*[1780]*/ 982 983 /** @stable ICU 2.0 */ 984 UBLOCK_MONGOLIAN =37, /*[1800]*/ 985 986 /** @stable ICU 2.0 */ 987 UBLOCK_LATIN_EXTENDED_ADDITIONAL =38, /*[1E00]*/ 988 989 /** @stable ICU 2.0 */ 990 UBLOCK_GREEK_EXTENDED =39, /*[1F00]*/ 991 992 /** @stable ICU 2.0 */ 993 UBLOCK_GENERAL_PUNCTUATION =40, /*[2000]*/ 994 995 /** @stable ICU 2.0 */ 996 UBLOCK_SUPERSCRIPTS_AND_SUBSCRIPTS =41, /*[2070]*/ 997 998 /** @stable ICU 2.0 */ 999 UBLOCK_CURRENCY_SYMBOLS =42, /*[20A0]*/ 1000 1001 /** 1002 * Unicode 3.2 renames this block to "Combining Diacritical Marks for Symbols". 1003 * @stable ICU 2.0 1004 */ 1005 UBLOCK_COMBINING_MARKS_FOR_SYMBOLS =43, /*[20D0]*/ 1006 1007 /** @stable ICU 2.0 */ 1008 UBLOCK_LETTERLIKE_SYMBOLS =44, /*[2100]*/ 1009 1010 /** @stable ICU 2.0 */ 1011 UBLOCK_NUMBER_FORMS =45, /*[2150]*/ 1012 1013 /** @stable ICU 2.0 */ 1014 UBLOCK_ARROWS =46, /*[2190]*/ 1015 1016 /** @stable ICU 2.0 */ 1017 UBLOCK_MATHEMATICAL_OPERATORS =47, /*[2200]*/ 1018 1019 /** @stable ICU 2.0 */ 1020 UBLOCK_MISCELLANEOUS_TECHNICAL =48, /*[2300]*/ 1021 1022 /** @stable ICU 2.0 */ 1023 UBLOCK_CONTROL_PICTURES =49, /*[2400]*/ 1024 1025 /** @stable ICU 2.0 */ 1026 UBLOCK_OPTICAL_CHARACTER_RECOGNITION =50, /*[2440]*/ 1027 1028 /** @stable ICU 2.0 */ 1029 UBLOCK_ENCLOSED_ALPHANUMERICS =51, /*[2460]*/ 1030 1031 /** @stable ICU 2.0 */ 1032 UBLOCK_BOX_DRAWING =52, /*[2500]*/ 1033 1034 /** @stable ICU 2.0 */ 1035 UBLOCK_BLOCK_ELEMENTS =53, /*[2580]*/ 1036 1037 /** @stable ICU 2.0 */ 1038 UBLOCK_GEOMETRIC_SHAPES =54, /*[25A0]*/ 1039 1040 /** @stable ICU 2.0 */ 1041 UBLOCK_MISCELLANEOUS_SYMBOLS =55, /*[2600]*/ 1042 1043 /** @stable ICU 2.0 */ 1044 UBLOCK_DINGBATS =56, /*[2700]*/ 1045 1046 /** @stable ICU 2.0 */ 1047 UBLOCK_BRAILLE_PATTERNS =57, /*[2800]*/ 1048 1049 /** @stable ICU 2.0 */ 1050 UBLOCK_CJK_RADICALS_SUPPLEMENT =58, /*[2E80]*/ 1051 1052 /** @stable ICU 2.0 */ 1053 UBLOCK_KANGXI_RADICALS =59, /*[2F00]*/ 1054 1055 /** @stable ICU 2.0 */ 1056 UBLOCK_IDEOGRAPHIC_DESCRIPTION_CHARACTERS =60, /*[2FF0]*/ 1057 1058 /** @stable ICU 2.0 */ 1059 UBLOCK_CJK_SYMBOLS_AND_PUNCTUATION =61, /*[3000]*/ 1060 1061 /** @stable ICU 2.0 */ 1062 UBLOCK_HIRAGANA =62, /*[3040]*/ 1063 1064 /** @stable ICU 2.0 */ 1065 UBLOCK_KATAKANA =63, /*[30A0]*/ 1066 1067 /** @stable ICU 2.0 */ 1068 UBLOCK_BOPOMOFO =64, /*[3100]*/ 1069 1070 /** @stable ICU 2.0 */ 1071 UBLOCK_HANGUL_COMPATIBILITY_JAMO =65, /*[3130]*/ 1072 1073 /** @stable ICU 2.0 */ 1074 UBLOCK_KANBUN =66, /*[3190]*/ 1075 1076 /** @stable ICU 2.0 */ 1077 UBLOCK_BOPOMOFO_EXTENDED =67, /*[31A0]*/ 1078 1079 /** @stable ICU 2.0 */ 1080 UBLOCK_ENCLOSED_CJK_LETTERS_AND_MONTHS =68, /*[3200]*/ 1081 1082 /** @stable ICU 2.0 */ 1083 UBLOCK_CJK_COMPATIBILITY =69, /*[3300]*/ 1084 1085 /** @stable ICU 2.0 */ 1086 UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_A =70, /*[3400]*/ 1087 1088 /** @stable ICU 2.0 */ 1089 UBLOCK_CJK_UNIFIED_IDEOGRAPHS =71, /*[4E00]*/ 1090 1091 /** @stable ICU 2.0 */ 1092 UBLOCK_YI_SYLLABLES =72, /*[A000]*/ 1093 1094 /** @stable ICU 2.0 */ 1095 UBLOCK_YI_RADICALS =73, /*[A490]*/ 1096 1097 /** @stable ICU 2.0 */ 1098 UBLOCK_HANGUL_SYLLABLES =74, /*[AC00]*/ 1099 1100 /** @stable ICU 2.0 */ 1101 UBLOCK_HIGH_SURROGATES =75, /*[D800]*/ 1102 1103 /** @stable ICU 2.0 */ 1104 UBLOCK_HIGH_PRIVATE_USE_SURROGATES =76, /*[DB80]*/ 1105 1106 /** @stable ICU 2.0 */ 1107 UBLOCK_LOW_SURROGATES =77, /*[DC00]*/ 1108 1109 /** 1110 * Same as UBLOCK_PRIVATE_USE. 1111 * Until Unicode 3.1.1, the corresponding block name was "Private Use", 1112 * and multiple code point ranges had this block. 1113 * Unicode 3.2 renames the block for the BMP PUA to "Private Use Area" and 1114 * adds separate blocks for the supplementary PUAs. 1115 * 1116 * @stable ICU 2.0 1117 */ 1118 UBLOCK_PRIVATE_USE_AREA =78, /*[E000]*/ 1119 /** 1120 * Same as UBLOCK_PRIVATE_USE_AREA. 1121 * Until Unicode 3.1.1, the corresponding block name was "Private Use", 1122 * and multiple code point ranges had this block. 1123 * Unicode 3.2 renames the block for the BMP PUA to "Private Use Area" and 1124 * adds separate blocks for the supplementary PUAs. 1125 * 1126 * @stable ICU 2.0 1127 */ 1128 UBLOCK_PRIVATE_USE = UBLOCK_PRIVATE_USE_AREA, 1129 1130 /** @stable ICU 2.0 */ 1131 UBLOCK_CJK_COMPATIBILITY_IDEOGRAPHS =79, /*[F900]*/ 1132 1133 /** @stable ICU 2.0 */ 1134 UBLOCK_ALPHABETIC_PRESENTATION_FORMS =80, /*[FB00]*/ 1135 1136 /** @stable ICU 2.0 */ 1137 UBLOCK_ARABIC_PRESENTATION_FORMS_A =81, /*[FB50]*/ 1138 1139 /** @stable ICU 2.0 */ 1140 UBLOCK_COMBINING_HALF_MARKS =82, /*[FE20]*/ 1141 1142 /** @stable ICU 2.0 */ 1143 UBLOCK_CJK_COMPATIBILITY_FORMS =83, /*[FE30]*/ 1144 1145 /** @stable ICU 2.0 */ 1146 UBLOCK_SMALL_FORM_VARIANTS =84, /*[FE50]*/ 1147 1148 /** @stable ICU 2.0 */ 1149 UBLOCK_ARABIC_PRESENTATION_FORMS_B =85, /*[FE70]*/ 1150 1151 /** @stable ICU 2.0 */ 1152 UBLOCK_SPECIALS =86, /*[FFF0]*/ 1153 1154 /** @stable ICU 2.0 */ 1155 UBLOCK_HALFWIDTH_AND_FULLWIDTH_FORMS =87, /*[FF00]*/ 1156 1157 /* New blocks in Unicode 3.1 */ 1158 1159 /** @stable ICU 2.0 */ 1160 UBLOCK_OLD_ITALIC = 88, /*[10300]*/ 1161 /** @stable ICU 2.0 */ 1162 UBLOCK_GOTHIC = 89, /*[10330]*/ 1163 /** @stable ICU 2.0 */ 1164 UBLOCK_DESERET = 90, /*[10400]*/ 1165 /** @stable ICU 2.0 */ 1166 UBLOCK_BYZANTINE_MUSICAL_SYMBOLS = 91, /*[1D000]*/ 1167 /** @stable ICU 2.0 */ 1168 UBLOCK_MUSICAL_SYMBOLS = 92, /*[1D100]*/ 1169 /** @stable ICU 2.0 */ 1170 UBLOCK_MATHEMATICAL_ALPHANUMERIC_SYMBOLS = 93, /*[1D400]*/ 1171 /** @stable ICU 2.0 */ 1172 UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_B = 94, /*[20000]*/ 1173 /** @stable ICU 2.0 */ 1174 UBLOCK_CJK_COMPATIBILITY_IDEOGRAPHS_SUPPLEMENT = 95, /*[2F800]*/ 1175 /** @stable ICU 2.0 */ 1176 UBLOCK_TAGS = 96, /*[E0000]*/ 1177 1178 /* New blocks in Unicode 3.2 */ 1179 1180 /** @stable ICU 3.0 */ 1181 UBLOCK_CYRILLIC_SUPPLEMENT = 97, /*[0500]*/ 1182 /** 1183 * Unicode 4.0.1 renames the "Cyrillic Supplementary" block to "Cyrillic Supplement". 1184 * @stable ICU 2.2 1185 */ 1186 UBLOCK_CYRILLIC_SUPPLEMENTARY = UBLOCK_CYRILLIC_SUPPLEMENT, 1187 /** @stable ICU 2.2 */ 1188 UBLOCK_TAGALOG = 98, /*[1700]*/ 1189 /** @stable ICU 2.2 */ 1190 UBLOCK_HANUNOO = 99, /*[1720]*/ 1191 /** @stable ICU 2.2 */ 1192 UBLOCK_BUHID = 100, /*[1740]*/ 1193 /** @stable ICU 2.2 */ 1194 UBLOCK_TAGBANWA = 101, /*[1760]*/ 1195 /** @stable ICU 2.2 */ 1196 UBLOCK_MISCELLANEOUS_MATHEMATICAL_SYMBOLS_A = 102, /*[27C0]*/ 1197 /** @stable ICU 2.2 */ 1198 UBLOCK_SUPPLEMENTAL_ARROWS_A = 103, /*[27F0]*/ 1199 /** @stable ICU 2.2 */ 1200 UBLOCK_SUPPLEMENTAL_ARROWS_B = 104, /*[2900]*/ 1201 /** @stable ICU 2.2 */ 1202 UBLOCK_MISCELLANEOUS_MATHEMATICAL_SYMBOLS_B = 105, /*[2980]*/ 1203 /** @stable ICU 2.2 */ 1204 UBLOCK_SUPPLEMENTAL_MATHEMATICAL_OPERATORS = 106, /*[2A00]*/ 1205 /** @stable ICU 2.2 */ 1206 UBLOCK_KATAKANA_PHONETIC_EXTENSIONS = 107, /*[31F0]*/ 1207 /** @stable ICU 2.2 */ 1208 UBLOCK_VARIATION_SELECTORS = 108, /*[FE00]*/ 1209 /** @stable ICU 2.2 */ 1210 UBLOCK_SUPPLEMENTARY_PRIVATE_USE_AREA_A = 109, /*[F0000]*/ 1211 /** @stable ICU 2.2 */ 1212 UBLOCK_SUPPLEMENTARY_PRIVATE_USE_AREA_B = 110, /*[100000]*/ 1213 1214 /* New blocks in Unicode 4 */ 1215 1216 /** @stable ICU 2.6 */ 1217 UBLOCK_LIMBU = 111, /*[1900]*/ 1218 /** @stable ICU 2.6 */ 1219 UBLOCK_TAI_LE = 112, /*[1950]*/ 1220 /** @stable ICU 2.6 */ 1221 UBLOCK_KHMER_SYMBOLS = 113, /*[19E0]*/ 1222 /** @stable ICU 2.6 */ 1223 UBLOCK_PHONETIC_EXTENSIONS = 114, /*[1D00]*/ 1224 /** @stable ICU 2.6 */ 1225 UBLOCK_MISCELLANEOUS_SYMBOLS_AND_ARROWS = 115, /*[2B00]*/ 1226 /** @stable ICU 2.6 */ 1227 UBLOCK_YIJING_HEXAGRAM_SYMBOLS = 116, /*[4DC0]*/ 1228 /** @stable ICU 2.6 */ 1229 UBLOCK_LINEAR_B_SYLLABARY = 117, /*[10000]*/ 1230 /** @stable ICU 2.6 */ 1231 UBLOCK_LINEAR_B_IDEOGRAMS = 118, /*[10080]*/ 1232 /** @stable ICU 2.6 */ 1233 UBLOCK_AEGEAN_NUMBERS = 119, /*[10100]*/ 1234 /** @stable ICU 2.6 */ 1235 UBLOCK_UGARITIC = 120, /*[10380]*/ 1236 /** @stable ICU 2.6 */ 1237 UBLOCK_SHAVIAN = 121, /*[10450]*/ 1238 /** @stable ICU 2.6 */ 1239 UBLOCK_OSMANYA = 122, /*[10480]*/ 1240 /** @stable ICU 2.6 */ 1241 UBLOCK_CYPRIOT_SYLLABARY = 123, /*[10800]*/ 1242 /** @stable ICU 2.6 */ 1243 UBLOCK_TAI_XUAN_JING_SYMBOLS = 124, /*[1D300]*/ 1244 /** @stable ICU 2.6 */ 1245 UBLOCK_VARIATION_SELECTORS_SUPPLEMENT = 125, /*[E0100]*/ 1246 1247 /* New blocks in Unicode 4.1 */ 1248 1249 /** @stable ICU 3.4 */ 1250 UBLOCK_ANCIENT_GREEK_MUSICAL_NOTATION = 126, /*[1D200]*/ 1251 /** @stable ICU 3.4 */ 1252 UBLOCK_ANCIENT_GREEK_NUMBERS = 127, /*[10140]*/ 1253 /** @stable ICU 3.4 */ 1254 UBLOCK_ARABIC_SUPPLEMENT = 128, /*[0750]*/ 1255 /** @stable ICU 3.4 */ 1256 UBLOCK_BUGINESE = 129, /*[1A00]*/ 1257 /** @stable ICU 3.4 */ 1258 UBLOCK_CJK_STROKES = 130, /*[31C0]*/ 1259 /** @stable ICU 3.4 */ 1260 UBLOCK_COMBINING_DIACRITICAL_MARKS_SUPPLEMENT = 131, /*[1DC0]*/ 1261 /** @stable ICU 3.4 */ 1262 UBLOCK_COPTIC = 132, /*[2C80]*/ 1263 /** @stable ICU 3.4 */ 1264 UBLOCK_ETHIOPIC_EXTENDED = 133, /*[2D80]*/ 1265 /** @stable ICU 3.4 */ 1266 UBLOCK_ETHIOPIC_SUPPLEMENT = 134, /*[1380]*/ 1267 /** @stable ICU 3.4 */ 1268 UBLOCK_GEORGIAN_SUPPLEMENT = 135, /*[2D00]*/ 1269 /** @stable ICU 3.4 */ 1270 UBLOCK_GLAGOLITIC = 136, /*[2C00]*/ 1271 /** @stable ICU 3.4 */ 1272 UBLOCK_KHAROSHTHI = 137, /*[10A00]*/ 1273 /** @stable ICU 3.4 */ 1274 UBLOCK_MODIFIER_TONE_LETTERS = 138, /*[A700]*/ 1275 /** @stable ICU 3.4 */ 1276 UBLOCK_NEW_TAI_LUE = 139, /*[1980]*/ 1277 /** @stable ICU 3.4 */ 1278 UBLOCK_OLD_PERSIAN = 140, /*[103A0]*/ 1279 /** @stable ICU 3.4 */ 1280 UBLOCK_PHONETIC_EXTENSIONS_SUPPLEMENT = 141, /*[1D80]*/ 1281 /** @stable ICU 3.4 */ 1282 UBLOCK_SUPPLEMENTAL_PUNCTUATION = 142, /*[2E00]*/ 1283 /** @stable ICU 3.4 */ 1284 UBLOCK_SYLOTI_NAGRI = 143, /*[A800]*/ 1285 /** @stable ICU 3.4 */ 1286 UBLOCK_TIFINAGH = 144, /*[2D30]*/ 1287 /** @stable ICU 3.4 */ 1288 UBLOCK_VERTICAL_FORMS = 145, /*[FE10]*/ 1289 1290 /* New blocks in Unicode 5.0 */ 1291 1292 /** @stable ICU 3.6 */ 1293 UBLOCK_NKO = 146, /*[07C0]*/ 1294 /** @stable ICU 3.6 */ 1295 UBLOCK_BALINESE = 147, /*[1B00]*/ 1296 /** @stable ICU 3.6 */ 1297 UBLOCK_LATIN_EXTENDED_C = 148, /*[2C60]*/ 1298 /** @stable ICU 3.6 */ 1299 UBLOCK_LATIN_EXTENDED_D = 149, /*[A720]*/ 1300 /** @stable ICU 3.6 */ 1301 UBLOCK_PHAGS_PA = 150, /*[A840]*/ 1302 /** @stable ICU 3.6 */ 1303 UBLOCK_PHOENICIAN = 151, /*[10900]*/ 1304 /** @stable ICU 3.6 */ 1305 UBLOCK_CUNEIFORM = 152, /*[12000]*/ 1306 /** @stable ICU 3.6 */ 1307 UBLOCK_CUNEIFORM_NUMBERS_AND_PUNCTUATION = 153, /*[12400]*/ 1308 /** @stable ICU 3.6 */ 1309 UBLOCK_COUNTING_ROD_NUMERALS = 154, /*[1D360]*/ 1310 1311 /* New blocks in Unicode 5.1 */ 1312 1313 /** @stable ICU 4.0 */ 1314 UBLOCK_SUNDANESE = 155, /*[1B80]*/ 1315 /** @stable ICU 4.0 */ 1316 UBLOCK_LEPCHA = 156, /*[1C00]*/ 1317 /** @stable ICU 4.0 */ 1318 UBLOCK_OL_CHIKI = 157, /*[1C50]*/ 1319 /** @stable ICU 4.0 */ 1320 UBLOCK_CYRILLIC_EXTENDED_A = 158, /*[2DE0]*/ 1321 /** @stable ICU 4.0 */ 1322 UBLOCK_VAI = 159, /*[A500]*/ 1323 /** @stable ICU 4.0 */ 1324 UBLOCK_CYRILLIC_EXTENDED_B = 160, /*[A640]*/ 1325 /** @stable ICU 4.0 */ 1326 UBLOCK_SAURASHTRA = 161, /*[A880]*/ 1327 /** @stable ICU 4.0 */ 1328 UBLOCK_KAYAH_LI = 162, /*[A900]*/ 1329 /** @stable ICU 4.0 */ 1330 UBLOCK_REJANG = 163, /*[A930]*/ 1331 /** @stable ICU 4.0 */ 1332 UBLOCK_CHAM = 164, /*[AA00]*/ 1333 /** @stable ICU 4.0 */ 1334 UBLOCK_ANCIENT_SYMBOLS = 165, /*[10190]*/ 1335 /** @stable ICU 4.0 */ 1336 UBLOCK_PHAISTOS_DISC = 166, /*[101D0]*/ 1337 /** @stable ICU 4.0 */ 1338 UBLOCK_LYCIAN = 167, /*[10280]*/ 1339 /** @stable ICU 4.0 */ 1340 UBLOCK_CARIAN = 168, /*[102A0]*/ 1341 /** @stable ICU 4.0 */ 1342 UBLOCK_LYDIAN = 169, /*[10920]*/ 1343 /** @stable ICU 4.0 */ 1344 UBLOCK_MAHJONG_TILES = 170, /*[1F000]*/ 1345 /** @stable ICU 4.0 */ 1346 UBLOCK_DOMINO_TILES = 171, /*[1F030]*/ 1347 1348 /* New blocks in Unicode 5.2 */ 1349 1350 /** @stable ICU 4.4 */ 1351 UBLOCK_SAMARITAN = 172, /*[0800]*/ 1352 /** @stable ICU 4.4 */ 1353 UBLOCK_UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS_EXTENDED = 173, /*[18B0]*/ 1354 /** @stable ICU 4.4 */ 1355 UBLOCK_TAI_THAM = 174, /*[1A20]*/ 1356 /** @stable ICU 4.4 */ 1357 UBLOCK_VEDIC_EXTENSIONS = 175, /*[1CD0]*/ 1358 /** @stable ICU 4.4 */ 1359 UBLOCK_LISU = 176, /*[A4D0]*/ 1360 /** @stable ICU 4.4 */ 1361 UBLOCK_BAMUM = 177, /*[A6A0]*/ 1362 /** @stable ICU 4.4 */ 1363 UBLOCK_COMMON_INDIC_NUMBER_FORMS = 178, /*[A830]*/ 1364 /** @stable ICU 4.4 */ 1365 UBLOCK_DEVANAGARI_EXTENDED = 179, /*[A8E0]*/ 1366 /** @stable ICU 4.4 */ 1367 UBLOCK_HANGUL_JAMO_EXTENDED_A = 180, /*[A960]*/ 1368 /** @stable ICU 4.4 */ 1369 UBLOCK_JAVANESE = 181, /*[A980]*/ 1370 /** @stable ICU 4.4 */ 1371 UBLOCK_MYANMAR_EXTENDED_A = 182, /*[AA60]*/ 1372 /** @stable ICU 4.4 */ 1373 UBLOCK_TAI_VIET = 183, /*[AA80]*/ 1374 /** @stable ICU 4.4 */ 1375 UBLOCK_MEETEI_MAYEK = 184, /*[ABC0]*/ 1376 /** @stable ICU 4.4 */ 1377 UBLOCK_HANGUL_JAMO_EXTENDED_B = 185, /*[D7B0]*/ 1378 /** @stable ICU 4.4 */ 1379 UBLOCK_IMPERIAL_ARAMAIC = 186, /*[10840]*/ 1380 /** @stable ICU 4.4 */ 1381 UBLOCK_OLD_SOUTH_ARABIAN = 187, /*[10A60]*/ 1382 /** @stable ICU 4.4 */ 1383 UBLOCK_AVESTAN = 188, /*[10B00]*/ 1384 /** @stable ICU 4.4 */ 1385 UBLOCK_INSCRIPTIONAL_PARTHIAN = 189, /*[10B40]*/ 1386 /** @stable ICU 4.4 */ 1387 UBLOCK_INSCRIPTIONAL_PAHLAVI = 190, /*[10B60]*/ 1388 /** @stable ICU 4.4 */ 1389 UBLOCK_OLD_TURKIC = 191, /*[10C00]*/ 1390 /** @stable ICU 4.4 */ 1391 UBLOCK_RUMI_NUMERAL_SYMBOLS = 192, /*[10E60]*/ 1392 /** @stable ICU 4.4 */ 1393 UBLOCK_KAITHI = 193, /*[11080]*/ 1394 /** @stable ICU 4.4 */ 1395 UBLOCK_EGYPTIAN_HIEROGLYPHS = 194, /*[13000]*/ 1396 /** @stable ICU 4.4 */ 1397 UBLOCK_ENCLOSED_ALPHANUMERIC_SUPPLEMENT = 195, /*[1F100]*/ 1398 /** @stable ICU 4.4 */ 1399 UBLOCK_ENCLOSED_IDEOGRAPHIC_SUPPLEMENT = 196, /*[1F200]*/ 1400 /** @stable ICU 4.4 */ 1401 UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_C = 197, /*[2A700]*/ 1402 1403 /* New blocks in Unicode 6.0 */ 1404 1405 /** @stable ICU 4.6 */ 1406 UBLOCK_MANDAIC = 198, /*[0840]*/ 1407 /** @stable ICU 4.6 */ 1408 UBLOCK_BATAK = 199, /*[1BC0]*/ 1409 /** @stable ICU 4.6 */ 1410 UBLOCK_ETHIOPIC_EXTENDED_A = 200, /*[AB00]*/ 1411 /** @stable ICU 4.6 */ 1412 UBLOCK_BRAHMI = 201, /*[11000]*/ 1413 /** @stable ICU 4.6 */ 1414 UBLOCK_BAMUM_SUPPLEMENT = 202, /*[16800]*/ 1415 /** @stable ICU 4.6 */ 1416 UBLOCK_KANA_SUPPLEMENT = 203, /*[1B000]*/ 1417 /** @stable ICU 4.6 */ 1418 UBLOCK_PLAYING_CARDS = 204, /*[1F0A0]*/ 1419 /** @stable ICU 4.6 */ 1420 UBLOCK_MISCELLANEOUS_SYMBOLS_AND_PICTOGRAPHS = 205, /*[1F300]*/ 1421 /** @stable ICU 4.6 */ 1422 UBLOCK_EMOTICONS = 206, /*[1F600]*/ 1423 /** @stable ICU 4.6 */ 1424 UBLOCK_TRANSPORT_AND_MAP_SYMBOLS = 207, /*[1F680]*/ 1425 /** @stable ICU 4.6 */ 1426 UBLOCK_ALCHEMICAL_SYMBOLS = 208, /*[1F700]*/ 1427 /** @stable ICU 4.6 */ 1428 UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_D = 209, /*[2B740]*/ 1429 1430 /* New blocks in Unicode 6.1 */ 1431 1432 /** @stable ICU 49 */ 1433 UBLOCK_ARABIC_EXTENDED_A = 210, /*[08A0]*/ 1434 /** @stable ICU 49 */ 1435 UBLOCK_ARABIC_MATHEMATICAL_ALPHABETIC_SYMBOLS = 211, /*[1EE00]*/ 1436 /** @stable ICU 49 */ 1437 UBLOCK_CHAKMA = 212, /*[11100]*/ 1438 /** @stable ICU 49 */ 1439 UBLOCK_MEETEI_MAYEK_EXTENSIONS = 213, /*[AAE0]*/ 1440 /** @stable ICU 49 */ 1441 UBLOCK_MEROITIC_CURSIVE = 214, /*[109A0]*/ 1442 /** @stable ICU 49 */ 1443 UBLOCK_MEROITIC_HIEROGLYPHS = 215, /*[10980]*/ 1444 /** @stable ICU 49 */ 1445 UBLOCK_MIAO = 216, /*[16F00]*/ 1446 /** @stable ICU 49 */ 1447 UBLOCK_SHARADA = 217, /*[11180]*/ 1448 /** @stable ICU 49 */ 1449 UBLOCK_SORA_SOMPENG = 218, /*[110D0]*/ 1450 /** @stable ICU 49 */ 1451 UBLOCK_SUNDANESE_SUPPLEMENT = 219, /*[1CC0]*/ 1452 /** @stable ICU 49 */ 1453 UBLOCK_TAKRI = 220, /*[11680]*/ 1454 1455 /* New blocks in Unicode 7.0 */ 1456 1457 /** @stable ICU 54 */ 1458 UBLOCK_BASSA_VAH = 221, /*[16AD0]*/ 1459 /** @stable ICU 54 */ 1460 UBLOCK_CAUCASIAN_ALBANIAN = 222, /*[10530]*/ 1461 /** @stable ICU 54 */ 1462 UBLOCK_COPTIC_EPACT_NUMBERS = 223, /*[102E0]*/ 1463 /** @stable ICU 54 */ 1464 UBLOCK_COMBINING_DIACRITICAL_MARKS_EXTENDED = 224, /*[1AB0]*/ 1465 /** @stable ICU 54 */ 1466 UBLOCK_DUPLOYAN = 225, /*[1BC00]*/ 1467 /** @stable ICU 54 */ 1468 UBLOCK_ELBASAN = 226, /*[10500]*/ 1469 /** @stable ICU 54 */ 1470 UBLOCK_GEOMETRIC_SHAPES_EXTENDED = 227, /*[1F780]*/ 1471 /** @stable ICU 54 */ 1472 UBLOCK_GRANTHA = 228, /*[11300]*/ 1473 /** @stable ICU 54 */ 1474 UBLOCK_KHOJKI = 229, /*[11200]*/ 1475 /** @stable ICU 54 */ 1476 UBLOCK_KHUDAWADI = 230, /*[112B0]*/ 1477 /** @stable ICU 54 */ 1478 UBLOCK_LATIN_EXTENDED_E = 231, /*[AB30]*/ 1479 /** @stable ICU 54 */ 1480 UBLOCK_LINEAR_A = 232, /*[10600]*/ 1481 /** @stable ICU 54 */ 1482 UBLOCK_MAHAJANI = 233, /*[11150]*/ 1483 /** @stable ICU 54 */ 1484 UBLOCK_MANICHAEAN = 234, /*[10AC0]*/ 1485 /** @stable ICU 54 */ 1486 UBLOCK_MENDE_KIKAKUI = 235, /*[1E800]*/ 1487 /** @stable ICU 54 */ 1488 UBLOCK_MODI = 236, /*[11600]*/ 1489 /** @stable ICU 54 */ 1490 UBLOCK_MRO = 237, /*[16A40]*/ 1491 /** @stable ICU 54 */ 1492 UBLOCK_MYANMAR_EXTENDED_B = 238, /*[A9E0]*/ 1493 /** @stable ICU 54 */ 1494 UBLOCK_NABATAEAN = 239, /*[10880]*/ 1495 /** @stable ICU 54 */ 1496 UBLOCK_OLD_NORTH_ARABIAN = 240, /*[10A80]*/ 1497 /** @stable ICU 54 */ 1498 UBLOCK_OLD_PERMIC = 241, /*[10350]*/ 1499 /** @stable ICU 54 */ 1500 UBLOCK_ORNAMENTAL_DINGBATS = 242, /*[1F650]*/ 1501 /** @stable ICU 54 */ 1502 UBLOCK_PAHAWH_HMONG = 243, /*[16B00]*/ 1503 /** @stable ICU 54 */ 1504 UBLOCK_PALMYRENE = 244, /*[10860]*/ 1505 /** @stable ICU 54 */ 1506 UBLOCK_PAU_CIN_HAU = 245, /*[11AC0]*/ 1507 /** @stable ICU 54 */ 1508 UBLOCK_PSALTER_PAHLAVI = 246, /*[10B80]*/ 1509 /** @stable ICU 54 */ 1510 UBLOCK_SHORTHAND_FORMAT_CONTROLS = 247, /*[1BCA0]*/ 1511 /** @stable ICU 54 */ 1512 UBLOCK_SIDDHAM = 248, /*[11580]*/ 1513 /** @stable ICU 54 */ 1514 UBLOCK_SINHALA_ARCHAIC_NUMBERS = 249, /*[111E0]*/ 1515 /** @stable ICU 54 */ 1516 UBLOCK_SUPPLEMENTAL_ARROWS_C = 250, /*[1F800]*/ 1517 /** @stable ICU 54 */ 1518 UBLOCK_TIRHUTA = 251, /*[11480]*/ 1519 /** @stable ICU 54 */ 1520 UBLOCK_WARANG_CITI = 252, /*[118A0]*/ 1521 1522 /** @stable ICU 2.0 */ 1523 UBLOCK_COUNT = 253, 1524 1525 /** @stable ICU 2.0 */ 1526 UBLOCK_INVALID_CODE=-1 1527}; 1528 1529/** @stable ICU 2.0 */ 1530typedef enum UBlockCode UBlockCode; 1531 1532/** 1533 * East Asian Width constants. 1534 * 1535 * @see UCHAR_EAST_ASIAN_WIDTH 1536 * @see u_getIntPropertyValue 1537 * @stable ICU 2.2 1538 */ 1539typedef enum UEastAsianWidth { 1540 /* 1541 * Note: UEastAsianWidth constants are parsed by preparseucd.py. 1542 * It matches lines like 1543 * U_EA_<Unicode East_Asian_Width value name> 1544 */ 1545 1546 U_EA_NEUTRAL, /*[N]*/ 1547 U_EA_AMBIGUOUS, /*[A]*/ 1548 U_EA_HALFWIDTH, /*[H]*/ 1549 U_EA_FULLWIDTH, /*[F]*/ 1550 U_EA_NARROW, /*[Na]*/ 1551 U_EA_WIDE, /*[W]*/ 1552 U_EA_COUNT 1553} UEastAsianWidth; 1554 1555/** 1556 * Selector constants for u_charName(). 1557 * u_charName() returns the "modern" name of a 1558 * Unicode character; or the name that was defined in 1559 * Unicode version 1.0, before the Unicode standard merged 1560 * with ISO-10646; or an "extended" name that gives each 1561 * Unicode code point a unique name. 1562 * 1563 * @see u_charName 1564 * @stable ICU 2.0 1565 */ 1566typedef enum UCharNameChoice { 1567 /** Unicode character name (Name property). @stable ICU 2.0 */ 1568 U_UNICODE_CHAR_NAME, 1569#ifndef U_HIDE_DEPRECATED_API 1570 /** 1571 * The Unicode_1_Name property value which is of little practical value. 1572 * Beginning with ICU 49, ICU APIs return an empty string for this name choice. 1573 * @deprecated ICU 49 1574 */ 1575 U_UNICODE_10_CHAR_NAME, 1576#endif /* U_HIDE_DEPRECATED_API */ 1577 /** Standard or synthetic character name. @stable ICU 2.0 */ 1578 U_EXTENDED_CHAR_NAME = U_UNICODE_CHAR_NAME+2, 1579 /** Corrected name from NameAliases.txt. @stable ICU 4.4 */ 1580 U_CHAR_NAME_ALIAS, 1581 /** @stable ICU 2.0 */ 1582 U_CHAR_NAME_CHOICE_COUNT 1583} UCharNameChoice; 1584 1585/** 1586 * Selector constants for u_getPropertyName() and 1587 * u_getPropertyValueName(). These selectors are used to choose which 1588 * name is returned for a given property or value. All properties and 1589 * values have a long name. Most have a short name, but some do not. 1590 * Unicode allows for additional names, beyond the long and short 1591 * name, which would be indicated by U_LONG_PROPERTY_NAME + i, where 1592 * i=1, 2,... 1593 * 1594 * @see u_getPropertyName() 1595 * @see u_getPropertyValueName() 1596 * @stable ICU 2.4 1597 */ 1598typedef enum UPropertyNameChoice { 1599 U_SHORT_PROPERTY_NAME, 1600 U_LONG_PROPERTY_NAME, 1601 U_PROPERTY_NAME_CHOICE_COUNT 1602} UPropertyNameChoice; 1603 1604/** 1605 * Decomposition Type constants. 1606 * 1607 * @see UCHAR_DECOMPOSITION_TYPE 1608 * @stable ICU 2.2 1609 */ 1610typedef enum UDecompositionType { 1611 /* 1612 * Note: UDecompositionType constants are parsed by preparseucd.py. 1613 * It matches lines like 1614 * U_DT_<Unicode Decomposition_Type value name> 1615 */ 1616 1617 U_DT_NONE, /*[none]*/ 1618 U_DT_CANONICAL, /*[can]*/ 1619 U_DT_COMPAT, /*[com]*/ 1620 U_DT_CIRCLE, /*[enc]*/ 1621 U_DT_FINAL, /*[fin]*/ 1622 U_DT_FONT, /*[font]*/ 1623 U_DT_FRACTION, /*[fra]*/ 1624 U_DT_INITIAL, /*[init]*/ 1625 U_DT_ISOLATED, /*[iso]*/ 1626 U_DT_MEDIAL, /*[med]*/ 1627 U_DT_NARROW, /*[nar]*/ 1628 U_DT_NOBREAK, /*[nb]*/ 1629 U_DT_SMALL, /*[sml]*/ 1630 U_DT_SQUARE, /*[sqr]*/ 1631 U_DT_SUB, /*[sub]*/ 1632 U_DT_SUPER, /*[sup]*/ 1633 U_DT_VERTICAL, /*[vert]*/ 1634 U_DT_WIDE, /*[wide]*/ 1635 U_DT_COUNT /* 18 */ 1636} UDecompositionType; 1637 1638/** 1639 * Joining Type constants. 1640 * 1641 * @see UCHAR_JOINING_TYPE 1642 * @stable ICU 2.2 1643 */ 1644typedef enum UJoiningType { 1645 /* 1646 * Note: UJoiningType constants are parsed by preparseucd.py. 1647 * It matches lines like 1648 * U_JT_<Unicode Joining_Type value name> 1649 */ 1650 1651 U_JT_NON_JOINING, /*[U]*/ 1652 U_JT_JOIN_CAUSING, /*[C]*/ 1653 U_JT_DUAL_JOINING, /*[D]*/ 1654 U_JT_LEFT_JOINING, /*[L]*/ 1655 U_JT_RIGHT_JOINING, /*[R]*/ 1656 U_JT_TRANSPARENT, /*[T]*/ 1657 U_JT_COUNT /* 6 */ 1658} UJoiningType; 1659 1660/** 1661 * Joining Group constants. 1662 * 1663 * @see UCHAR_JOINING_GROUP 1664 * @stable ICU 2.2 1665 */ 1666typedef enum UJoiningGroup { 1667 /* 1668 * Note: UJoiningGroup constants are parsed by preparseucd.py. 1669 * It matches lines like 1670 * U_JG_<Unicode Joining_Group value name> 1671 */ 1672 1673 U_JG_NO_JOINING_GROUP, 1674 U_JG_AIN, 1675 U_JG_ALAPH, 1676 U_JG_ALEF, 1677 U_JG_BEH, 1678 U_JG_BETH, 1679 U_JG_DAL, 1680 U_JG_DALATH_RISH, 1681 U_JG_E, 1682 U_JG_FEH, 1683 U_JG_FINAL_SEMKATH, 1684 U_JG_GAF, 1685 U_JG_GAMAL, 1686 U_JG_HAH, 1687 U_JG_TEH_MARBUTA_GOAL, /**< @stable ICU 4.6 */ 1688 U_JG_HAMZA_ON_HEH_GOAL=U_JG_TEH_MARBUTA_GOAL, 1689 U_JG_HE, 1690 U_JG_HEH, 1691 U_JG_HEH_GOAL, 1692 U_JG_HETH, 1693 U_JG_KAF, 1694 U_JG_KAPH, 1695 U_JG_KNOTTED_HEH, 1696 U_JG_LAM, 1697 U_JG_LAMADH, 1698 U_JG_MEEM, 1699 U_JG_MIM, 1700 U_JG_NOON, 1701 U_JG_NUN, 1702 U_JG_PE, 1703 U_JG_QAF, 1704 U_JG_QAPH, 1705 U_JG_REH, 1706 U_JG_REVERSED_PE, 1707 U_JG_SAD, 1708 U_JG_SADHE, 1709 U_JG_SEEN, 1710 U_JG_SEMKATH, 1711 U_JG_SHIN, 1712 U_JG_SWASH_KAF, 1713 U_JG_SYRIAC_WAW, 1714 U_JG_TAH, 1715 U_JG_TAW, 1716 U_JG_TEH_MARBUTA, 1717 U_JG_TETH, 1718 U_JG_WAW, 1719 U_JG_YEH, 1720 U_JG_YEH_BARREE, 1721 U_JG_YEH_WITH_TAIL, 1722 U_JG_YUDH, 1723 U_JG_YUDH_HE, 1724 U_JG_ZAIN, 1725 U_JG_FE, /**< @stable ICU 2.6 */ 1726 U_JG_KHAPH, /**< @stable ICU 2.6 */ 1727 U_JG_ZHAIN, /**< @stable ICU 2.6 */ 1728 U_JG_BURUSHASKI_YEH_BARREE, /**< @stable ICU 4.0 */ 1729 U_JG_FARSI_YEH, /**< @stable ICU 4.4 */ 1730 U_JG_NYA, /**< @stable ICU 4.4 */ 1731 U_JG_ROHINGYA_YEH, /**< @stable ICU 49 */ 1732 U_JG_MANICHAEAN_ALEPH, /**< @stable ICU 54 */ 1733 U_JG_MANICHAEAN_AYIN, /**< @stable ICU 54 */ 1734 U_JG_MANICHAEAN_BETH, /**< @stable ICU 54 */ 1735 U_JG_MANICHAEAN_DALETH, /**< @stable ICU 54 */ 1736 U_JG_MANICHAEAN_DHAMEDH, /**< @stable ICU 54 */ 1737 U_JG_MANICHAEAN_FIVE, /**< @stable ICU 54 */ 1738 U_JG_MANICHAEAN_GIMEL, /**< @stable ICU 54 */ 1739 U_JG_MANICHAEAN_HETH, /**< @stable ICU 54 */ 1740 U_JG_MANICHAEAN_HUNDRED, /**< @stable ICU 54 */ 1741 U_JG_MANICHAEAN_KAPH, /**< @stable ICU 54 */ 1742 U_JG_MANICHAEAN_LAMEDH, /**< @stable ICU 54 */ 1743 U_JG_MANICHAEAN_MEM, /**< @stable ICU 54 */ 1744 U_JG_MANICHAEAN_NUN, /**< @stable ICU 54 */ 1745 U_JG_MANICHAEAN_ONE, /**< @stable ICU 54 */ 1746 U_JG_MANICHAEAN_PE, /**< @stable ICU 54 */ 1747 U_JG_MANICHAEAN_QOPH, /**< @stable ICU 54 */ 1748 U_JG_MANICHAEAN_RESH, /**< @stable ICU 54 */ 1749 U_JG_MANICHAEAN_SADHE, /**< @stable ICU 54 */ 1750 U_JG_MANICHAEAN_SAMEKH, /**< @stable ICU 54 */ 1751 U_JG_MANICHAEAN_TAW, /**< @stable ICU 54 */ 1752 U_JG_MANICHAEAN_TEN, /**< @stable ICU 54 */ 1753 U_JG_MANICHAEAN_TETH, /**< @stable ICU 54 */ 1754 U_JG_MANICHAEAN_THAMEDH, /**< @stable ICU 54 */ 1755 U_JG_MANICHAEAN_TWENTY, /**< @stable ICU 54 */ 1756 U_JG_MANICHAEAN_WAW, /**< @stable ICU 54 */ 1757 U_JG_MANICHAEAN_YODH, /**< @stable ICU 54 */ 1758 U_JG_MANICHAEAN_ZAYIN, /**< @stable ICU 54 */ 1759 U_JG_STRAIGHT_WAW, /**< @stable ICU 54 */ 1760 U_JG_COUNT 1761} UJoiningGroup; 1762 1763/** 1764 * Grapheme Cluster Break constants. 1765 * 1766 * @see UCHAR_GRAPHEME_CLUSTER_BREAK 1767 * @stable ICU 3.4 1768 */ 1769typedef enum UGraphemeClusterBreak { 1770 /* 1771 * Note: UGraphemeClusterBreak constants are parsed by preparseucd.py. 1772 * It matches lines like 1773 * U_GCB_<Unicode Grapheme_Cluster_Break value name> 1774 */ 1775 1776 U_GCB_OTHER = 0, /*[XX]*/ 1777 U_GCB_CONTROL = 1, /*[CN]*/ 1778 U_GCB_CR = 2, /*[CR]*/ 1779 U_GCB_EXTEND = 3, /*[EX]*/ 1780 U_GCB_L = 4, /*[L]*/ 1781 U_GCB_LF = 5, /*[LF]*/ 1782 U_GCB_LV = 6, /*[LV]*/ 1783 U_GCB_LVT = 7, /*[LVT]*/ 1784 U_GCB_T = 8, /*[T]*/ 1785 U_GCB_V = 9, /*[V]*/ 1786 U_GCB_SPACING_MARK = 10, /*[SM]*/ /* from here on: new in Unicode 5.1/ICU 4.0 */ 1787 U_GCB_PREPEND = 11, /*[PP]*/ 1788 U_GCB_REGIONAL_INDICATOR = 12, /*[RI]*/ /* new in Unicode 6.2/ICU 50 */ 1789 U_GCB_COUNT = 13 1790} UGraphemeClusterBreak; 1791 1792/** 1793 * Word Break constants. 1794 * (UWordBreak is a pre-existing enum type in ubrk.h for word break status tags.) 1795 * 1796 * @see UCHAR_WORD_BREAK 1797 * @stable ICU 3.4 1798 */ 1799typedef enum UWordBreakValues { 1800 /* 1801 * Note: UWordBreakValues constants are parsed by preparseucd.py. 1802 * It matches lines like 1803 * U_WB_<Unicode Word_Break value name> 1804 */ 1805 1806 U_WB_OTHER = 0, /*[XX]*/ 1807 U_WB_ALETTER = 1, /*[LE]*/ 1808 U_WB_FORMAT = 2, /*[FO]*/ 1809 U_WB_KATAKANA = 3, /*[KA]*/ 1810 U_WB_MIDLETTER = 4, /*[ML]*/ 1811 U_WB_MIDNUM = 5, /*[MN]*/ 1812 U_WB_NUMERIC = 6, /*[NU]*/ 1813 U_WB_EXTENDNUMLET = 7, /*[EX]*/ 1814 U_WB_CR = 8, /*[CR]*/ /* from here on: new in Unicode 5.1/ICU 4.0 */ 1815 U_WB_EXTEND = 9, /*[Extend]*/ 1816 U_WB_LF = 10, /*[LF]*/ 1817 U_WB_MIDNUMLET =11, /*[MB]*/ 1818 U_WB_NEWLINE =12, /*[NL]*/ 1819 U_WB_REGIONAL_INDICATOR = 13, /*[RI]*/ /* new in Unicode 6.2/ICU 50 */ 1820 U_WB_HEBREW_LETTER = 14, /*[HL]*/ /* from here on: new in Unicode 6.3/ICU 52 */ 1821 U_WB_SINGLE_QUOTE = 15, /*[SQ]*/ 1822 U_WB_DOUBLE_QUOTE = 16, /*[DQ]*/ 1823 U_WB_COUNT = 17 1824} UWordBreakValues; 1825 1826/** 1827 * Sentence Break constants. 1828 * 1829 * @see UCHAR_SENTENCE_BREAK 1830 * @stable ICU 3.4 1831 */ 1832typedef enum USentenceBreak { 1833 /* 1834 * Note: USentenceBreak constants are parsed by preparseucd.py. 1835 * It matches lines like 1836 * U_SB_<Unicode Sentence_Break value name> 1837 */ 1838 1839 U_SB_OTHER = 0, /*[XX]*/ 1840 U_SB_ATERM = 1, /*[AT]*/ 1841 U_SB_CLOSE = 2, /*[CL]*/ 1842 U_SB_FORMAT = 3, /*[FO]*/ 1843 U_SB_LOWER = 4, /*[LO]*/ 1844 U_SB_NUMERIC = 5, /*[NU]*/ 1845 U_SB_OLETTER = 6, /*[LE]*/ 1846 U_SB_SEP = 7, /*[SE]*/ 1847 U_SB_SP = 8, /*[SP]*/ 1848 U_SB_STERM = 9, /*[ST]*/ 1849 U_SB_UPPER = 10, /*[UP]*/ 1850 U_SB_CR = 11, /*[CR]*/ /* from here on: new in Unicode 5.1/ICU 4.0 */ 1851 U_SB_EXTEND = 12, /*[EX]*/ 1852 U_SB_LF = 13, /*[LF]*/ 1853 U_SB_SCONTINUE = 14, /*[SC]*/ 1854 U_SB_COUNT = 15 1855} USentenceBreak; 1856 1857/** 1858 * Line Break constants. 1859 * 1860 * @see UCHAR_LINE_BREAK 1861 * @stable ICU 2.2 1862 */ 1863typedef enum ULineBreak { 1864 /* 1865 * Note: ULineBreak constants are parsed by preparseucd.py. 1866 * It matches lines like 1867 * U_LB_<Unicode Line_Break value name> 1868 */ 1869 1870 U_LB_UNKNOWN = 0, /*[XX]*/ 1871 U_LB_AMBIGUOUS = 1, /*[AI]*/ 1872 U_LB_ALPHABETIC = 2, /*[AL]*/ 1873 U_LB_BREAK_BOTH = 3, /*[B2]*/ 1874 U_LB_BREAK_AFTER = 4, /*[BA]*/ 1875 U_LB_BREAK_BEFORE = 5, /*[BB]*/ 1876 U_LB_MANDATORY_BREAK = 6, /*[BK]*/ 1877 U_LB_CONTINGENT_BREAK = 7, /*[CB]*/ 1878 U_LB_CLOSE_PUNCTUATION = 8, /*[CL]*/ 1879 U_LB_COMBINING_MARK = 9, /*[CM]*/ 1880 U_LB_CARRIAGE_RETURN = 10, /*[CR]*/ 1881 U_LB_EXCLAMATION = 11, /*[EX]*/ 1882 U_LB_GLUE = 12, /*[GL]*/ 1883 U_LB_HYPHEN = 13, /*[HY]*/ 1884 U_LB_IDEOGRAPHIC = 14, /*[ID]*/ 1885 /** Renamed from the misspelled "inseperable" in Unicode 4.0.1/ICU 3.0 @stable ICU 3.0 */ 1886 U_LB_INSEPARABLE = 15, /*[IN]*/ 1887 U_LB_INSEPERABLE = U_LB_INSEPARABLE, 1888 U_LB_INFIX_NUMERIC = 16, /*[IS]*/ 1889 U_LB_LINE_FEED = 17, /*[LF]*/ 1890 U_LB_NONSTARTER = 18, /*[NS]*/ 1891 U_LB_NUMERIC = 19, /*[NU]*/ 1892 U_LB_OPEN_PUNCTUATION = 20, /*[OP]*/ 1893 U_LB_POSTFIX_NUMERIC = 21, /*[PO]*/ 1894 U_LB_PREFIX_NUMERIC = 22, /*[PR]*/ 1895 U_LB_QUOTATION = 23, /*[QU]*/ 1896 U_LB_COMPLEX_CONTEXT = 24, /*[SA]*/ 1897 U_LB_SURROGATE = 25, /*[SG]*/ 1898 U_LB_SPACE = 26, /*[SP]*/ 1899 U_LB_BREAK_SYMBOLS = 27, /*[SY]*/ 1900 U_LB_ZWSPACE = 28, /*[ZW]*/ 1901 U_LB_NEXT_LINE = 29, /*[NL]*/ /* from here on: new in Unicode 4/ICU 2.6 */ 1902 U_LB_WORD_JOINER = 30, /*[WJ]*/ 1903 U_LB_H2 = 31, /*[H2]*/ /* from here on: new in Unicode 4.1/ICU 3.4 */ 1904 U_LB_H3 = 32, /*[H3]*/ 1905 U_LB_JL = 33, /*[JL]*/ 1906 U_LB_JT = 34, /*[JT]*/ 1907 U_LB_JV = 35, /*[JV]*/ 1908 U_LB_CLOSE_PARENTHESIS = 36, /*[CP]*/ /* new in Unicode 5.2/ICU 4.4 */ 1909 U_LB_CONDITIONAL_JAPANESE_STARTER = 37,/*[CJ]*/ /* new in Unicode 6.1/ICU 49 */ 1910 U_LB_HEBREW_LETTER = 38, /*[HL]*/ /* new in Unicode 6.1/ICU 49 */ 1911 U_LB_REGIONAL_INDICATOR = 39,/*[RI]*/ /* new in Unicode 6.2/ICU 50 */ 1912 U_LB_COUNT = 40 1913} ULineBreak; 1914 1915/** 1916 * Numeric Type constants. 1917 * 1918 * @see UCHAR_NUMERIC_TYPE 1919 * @stable ICU 2.2 1920 */ 1921typedef enum UNumericType { 1922 /* 1923 * Note: UNumericType constants are parsed by preparseucd.py. 1924 * It matches lines like 1925 * U_NT_<Unicode Numeric_Type value name> 1926 */ 1927 1928 U_NT_NONE, /*[None]*/ 1929 U_NT_DECIMAL, /*[de]*/ 1930 U_NT_DIGIT, /*[di]*/ 1931 U_NT_NUMERIC, /*[nu]*/ 1932 U_NT_COUNT 1933} UNumericType; 1934 1935/** 1936 * Hangul Syllable Type constants. 1937 * 1938 * @see UCHAR_HANGUL_SYLLABLE_TYPE 1939 * @stable ICU 2.6 1940 */ 1941typedef enum UHangulSyllableType { 1942 /* 1943 * Note: UHangulSyllableType constants are parsed by preparseucd.py. 1944 * It matches lines like 1945 * U_HST_<Unicode Hangul_Syllable_Type value name> 1946 */ 1947 1948 U_HST_NOT_APPLICABLE, /*[NA]*/ 1949 U_HST_LEADING_JAMO, /*[L]*/ 1950 U_HST_VOWEL_JAMO, /*[V]*/ 1951 U_HST_TRAILING_JAMO, /*[T]*/ 1952 U_HST_LV_SYLLABLE, /*[LV]*/ 1953 U_HST_LVT_SYLLABLE, /*[LVT]*/ 1954 U_HST_COUNT 1955} UHangulSyllableType; 1956 1957/** 1958 * Check a binary Unicode property for a code point. 1959 * 1960 * Unicode, especially in version 3.2, defines many more properties than the 1961 * original set in UnicodeData.txt. 1962 * 1963 * The properties APIs are intended to reflect Unicode properties as defined 1964 * in the Unicode Character Database (UCD) and Unicode Technical Reports (UTR). 1965 * For details about the properties see http://www.unicode.org/ucd/ . 1966 * For names of Unicode properties see the UCD file PropertyAliases.txt. 1967 * 1968 * Important: If ICU is built with UCD files from Unicode versions below 3.2, 1969 * then properties marked with "new in Unicode 3.2" are not or not fully available. 1970 * 1971 * @param c Code point to test. 1972 * @param which UProperty selector constant, identifies which binary property to check. 1973 * Must be UCHAR_BINARY_START<=which<UCHAR_BINARY_LIMIT. 1974 * @return TRUE or FALSE according to the binary Unicode property value for c. 1975 * Also FALSE if 'which' is out of bounds or if the Unicode version 1976 * does not have data for the property at all, or not for this code point. 1977 * 1978 * @see UProperty 1979 * @see u_getIntPropertyValue 1980 * @see u_getUnicodeVersion 1981 * @stable ICU 2.1 1982 */ 1983U_STABLE UBool U_EXPORT2 1984u_hasBinaryProperty(UChar32 c, UProperty which); 1985 1986/** 1987 * Check if a code point has the Alphabetic Unicode property. 1988 * Same as u_hasBinaryProperty(c, UCHAR_ALPHABETIC). 1989 * This is different from u_isalpha! 1990 * @param c Code point to test 1991 * @return true if the code point has the Alphabetic Unicode property, false otherwise 1992 * 1993 * @see UCHAR_ALPHABETIC 1994 * @see u_isalpha 1995 * @see u_hasBinaryProperty 1996 * @stable ICU 2.1 1997 */ 1998U_STABLE UBool U_EXPORT2 1999u_isUAlphabetic(UChar32 c); 2000 2001/** 2002 * Check if a code point has the Lowercase Unicode property. 2003 * Same as u_hasBinaryProperty(c, UCHAR_LOWERCASE). 2004 * This is different from u_islower! 2005 * @param c Code point to test 2006 * @return true if the code point has the Lowercase Unicode property, false otherwise 2007 * 2008 * @see UCHAR_LOWERCASE 2009 * @see u_islower 2010 * @see u_hasBinaryProperty 2011 * @stable ICU 2.1 2012 */ 2013U_STABLE UBool U_EXPORT2 2014u_isULowercase(UChar32 c); 2015 2016/** 2017 * Check if a code point has the Uppercase Unicode property. 2018 * Same as u_hasBinaryProperty(c, UCHAR_UPPERCASE). 2019 * This is different from u_isupper! 2020 * @param c Code point to test 2021 * @return true if the code point has the Uppercase Unicode property, false otherwise 2022 * 2023 * @see UCHAR_UPPERCASE 2024 * @see u_isupper 2025 * @see u_hasBinaryProperty 2026 * @stable ICU 2.1 2027 */ 2028U_STABLE UBool U_EXPORT2 2029u_isUUppercase(UChar32 c); 2030 2031/** 2032 * Check if a code point has the White_Space Unicode property. 2033 * Same as u_hasBinaryProperty(c, UCHAR_WHITE_SPACE). 2034 * This is different from both u_isspace and u_isWhitespace! 2035 * 2036 * Note: There are several ICU whitespace functions; please see the uchar.h 2037 * file documentation for a detailed comparison. 2038 * 2039 * @param c Code point to test 2040 * @return true if the code point has the White_Space Unicode property, false otherwise. 2041 * 2042 * @see UCHAR_WHITE_SPACE 2043 * @see u_isWhitespace 2044 * @see u_isspace 2045 * @see u_isJavaSpaceChar 2046 * @see u_hasBinaryProperty 2047 * @stable ICU 2.1 2048 */ 2049U_STABLE UBool U_EXPORT2 2050u_isUWhiteSpace(UChar32 c); 2051 2052/** 2053 * Get the property value for an enumerated or integer Unicode property for a code point. 2054 * Also returns binary and mask property values. 2055 * 2056 * Unicode, especially in version 3.2, defines many more properties than the 2057 * original set in UnicodeData.txt. 2058 * 2059 * The properties APIs are intended to reflect Unicode properties as defined 2060 * in the Unicode Character Database (UCD) and Unicode Technical Reports (UTR). 2061 * For details about the properties see http://www.unicode.org/ . 2062 * For names of Unicode properties see the UCD file PropertyAliases.txt. 2063 * 2064 * Sample usage: 2065 * UEastAsianWidth ea=(UEastAsianWidth)u_getIntPropertyValue(c, UCHAR_EAST_ASIAN_WIDTH); 2066 * UBool b=(UBool)u_getIntPropertyValue(c, UCHAR_IDEOGRAPHIC); 2067 * 2068 * @param c Code point to test. 2069 * @param which UProperty selector constant, identifies which property to check. 2070 * Must be UCHAR_BINARY_START<=which<UCHAR_BINARY_LIMIT 2071 * or UCHAR_INT_START<=which<UCHAR_INT_LIMIT 2072 * or UCHAR_MASK_START<=which<UCHAR_MASK_LIMIT. 2073 * @return Numeric value that is directly the property value or, 2074 * for enumerated properties, corresponds to the numeric value of the enumerated 2075 * constant of the respective property value enumeration type 2076 * (cast to enum type if necessary). 2077 * Returns 0 or 1 (for FALSE/TRUE) for binary Unicode properties. 2078 * Returns a bit-mask for mask properties. 2079 * Returns 0 if 'which' is out of bounds or if the Unicode version 2080 * does not have data for the property at all, or not for this code point. 2081 * 2082 * @see UProperty 2083 * @see u_hasBinaryProperty 2084 * @see u_getIntPropertyMinValue 2085 * @see u_getIntPropertyMaxValue 2086 * @see u_getUnicodeVersion 2087 * @stable ICU 2.2 2088 */ 2089U_STABLE int32_t U_EXPORT2 2090u_getIntPropertyValue(UChar32 c, UProperty which); 2091 2092/** 2093 * Get the minimum value for an enumerated/integer/binary Unicode property. 2094 * Can be used together with u_getIntPropertyMaxValue 2095 * to allocate arrays of UnicodeSet or similar. 2096 * 2097 * @param which UProperty selector constant, identifies which binary property to check. 2098 * Must be UCHAR_BINARY_START<=which<UCHAR_BINARY_LIMIT 2099 * or UCHAR_INT_START<=which<UCHAR_INT_LIMIT. 2100 * @return Minimum value returned by u_getIntPropertyValue for a Unicode property. 2101 * 0 if the property selector is out of range. 2102 * 2103 * @see UProperty 2104 * @see u_hasBinaryProperty 2105 * @see u_getUnicodeVersion 2106 * @see u_getIntPropertyMaxValue 2107 * @see u_getIntPropertyValue 2108 * @stable ICU 2.2 2109 */ 2110U_STABLE int32_t U_EXPORT2 2111u_getIntPropertyMinValue(UProperty which); 2112 2113/** 2114 * Get the maximum value for an enumerated/integer/binary Unicode property. 2115 * Can be used together with u_getIntPropertyMinValue 2116 * to allocate arrays of UnicodeSet or similar. 2117 * 2118 * Examples for min/max values (for Unicode 3.2): 2119 * 2120 * - UCHAR_BIDI_CLASS: 0/18 (U_LEFT_TO_RIGHT/U_BOUNDARY_NEUTRAL) 2121 * - UCHAR_SCRIPT: 0/45 (USCRIPT_COMMON/USCRIPT_TAGBANWA) 2122 * - UCHAR_IDEOGRAPHIC: 0/1 (FALSE/TRUE) 2123 * 2124 * For undefined UProperty constant values, min/max values will be 0/-1. 2125 * 2126 * @param which UProperty selector constant, identifies which binary property to check. 2127 * Must be UCHAR_BINARY_START<=which<UCHAR_BINARY_LIMIT 2128 * or UCHAR_INT_START<=which<UCHAR_INT_LIMIT. 2129 * @return Maximum value returned by u_getIntPropertyValue for a Unicode property. 2130 * <=0 if the property selector is out of range. 2131 * 2132 * @see UProperty 2133 * @see u_hasBinaryProperty 2134 * @see u_getUnicodeVersion 2135 * @see u_getIntPropertyMaxValue 2136 * @see u_getIntPropertyValue 2137 * @stable ICU 2.2 2138 */ 2139U_STABLE int32_t U_EXPORT2 2140u_getIntPropertyMaxValue(UProperty which); 2141 2142/** 2143 * Get the numeric value for a Unicode code point as defined in the 2144 * Unicode Character Database. 2145 * 2146 * A "double" return type is necessary because 2147 * some numeric values are fractions, negative, or too large for int32_t. 2148 * 2149 * For characters without any numeric values in the Unicode Character Database, 2150 * this function will return U_NO_NUMERIC_VALUE. 2151 * Note: This is different from the Unicode Standard which specifies NaN as the default value. 2152 * (NaN is not available on all platforms.) 2153 * 2154 * Similar to java.lang.Character.getNumericValue(), but u_getNumericValue() 2155 * also supports negative values, large values, and fractions, 2156 * while Java's getNumericValue() returns values 10..35 for ASCII letters. 2157 * 2158 * @param c Code point to get the numeric value for. 2159 * @return Numeric value of c, or U_NO_NUMERIC_VALUE if none is defined. 2160 * 2161 * @see U_NO_NUMERIC_VALUE 2162 * @stable ICU 2.2 2163 */ 2164U_STABLE double U_EXPORT2 2165u_getNumericValue(UChar32 c); 2166 2167/** 2168 * Special value that is returned by u_getNumericValue when 2169 * no numeric value is defined for a code point. 2170 * 2171 * @see u_getNumericValue 2172 * @stable ICU 2.2 2173 */ 2174#define U_NO_NUMERIC_VALUE ((double)-123456789.) 2175 2176/** 2177 * Determines whether the specified code point has the general category "Ll" 2178 * (lowercase letter). 2179 * 2180 * Same as java.lang.Character.isLowerCase(). 2181 * 2182 * This misses some characters that are also lowercase but 2183 * have a different general category value. 2184 * In order to include those, use UCHAR_LOWERCASE. 2185 * 2186 * In addition to being equivalent to a Java function, this also serves 2187 * as a C/POSIX migration function. 2188 * See the comments about C/POSIX character classification functions in the 2189 * documentation at the top of this header file. 2190 * 2191 * @param c the code point to be tested 2192 * @return TRUE if the code point is an Ll lowercase letter 2193 * 2194 * @see UCHAR_LOWERCASE 2195 * @see u_isupper 2196 * @see u_istitle 2197 * @stable ICU 2.0 2198 */ 2199U_STABLE UBool U_EXPORT2 2200u_islower(UChar32 c); 2201 2202/** 2203 * Determines whether the specified code point has the general category "Lu" 2204 * (uppercase letter). 2205 * 2206 * Same as java.lang.Character.isUpperCase(). 2207 * 2208 * This misses some characters that are also uppercase but 2209 * have a different general category value. 2210 * In order to include those, use UCHAR_UPPERCASE. 2211 * 2212 * In addition to being equivalent to a Java function, this also serves 2213 * as a C/POSIX migration function. 2214 * See the comments about C/POSIX character classification functions in the 2215 * documentation at the top of this header file. 2216 * 2217 * @param c the code point to be tested 2218 * @return TRUE if the code point is an Lu uppercase letter 2219 * 2220 * @see UCHAR_UPPERCASE 2221 * @see u_islower 2222 * @see u_istitle 2223 * @see u_tolower 2224 * @stable ICU 2.0 2225 */ 2226U_STABLE UBool U_EXPORT2 2227u_isupper(UChar32 c); 2228 2229/** 2230 * Determines whether the specified code point is a titlecase letter. 2231 * True for general category "Lt" (titlecase letter). 2232 * 2233 * Same as java.lang.Character.isTitleCase(). 2234 * 2235 * @param c the code point to be tested 2236 * @return TRUE if the code point is an Lt titlecase letter 2237 * 2238 * @see u_isupper 2239 * @see u_islower 2240 * @see u_totitle 2241 * @stable ICU 2.0 2242 */ 2243U_STABLE UBool U_EXPORT2 2244u_istitle(UChar32 c); 2245 2246/** 2247 * Determines whether the specified code point is a digit character according to Java. 2248 * True for characters with general category "Nd" (decimal digit numbers). 2249 * Beginning with Unicode 4, this is the same as 2250 * testing for the Numeric_Type of Decimal. 2251 * 2252 * Same as java.lang.Character.isDigit(). 2253 * 2254 * In addition to being equivalent to a Java function, this also serves 2255 * as a C/POSIX migration function. 2256 * See the comments about C/POSIX character classification functions in the 2257 * documentation at the top of this header file. 2258 * 2259 * @param c the code point to be tested 2260 * @return TRUE if the code point is a digit character according to Character.isDigit() 2261 * 2262 * @stable ICU 2.0 2263 */ 2264U_STABLE UBool U_EXPORT2 2265u_isdigit(UChar32 c); 2266 2267/** 2268 * Determines whether the specified code point is a letter character. 2269 * True for general categories "L" (letters). 2270 * 2271 * Same as java.lang.Character.isLetter(). 2272 * 2273 * In addition to being equivalent to a Java function, this also serves 2274 * as a C/POSIX migration function. 2275 * See the comments about C/POSIX character classification functions in the 2276 * documentation at the top of this header file. 2277 * 2278 * @param c the code point to be tested 2279 * @return TRUE if the code point is a letter character 2280 * 2281 * @see u_isdigit 2282 * @see u_isalnum 2283 * @stable ICU 2.0 2284 */ 2285U_STABLE UBool U_EXPORT2 2286u_isalpha(UChar32 c); 2287 2288/** 2289 * Determines whether the specified code point is an alphanumeric character 2290 * (letter or digit) according to Java. 2291 * True for characters with general categories 2292 * "L" (letters) and "Nd" (decimal digit numbers). 2293 * 2294 * Same as java.lang.Character.isLetterOrDigit(). 2295 * 2296 * In addition to being equivalent to a Java function, this also serves 2297 * as a C/POSIX migration function. 2298 * See the comments about C/POSIX character classification functions in the 2299 * documentation at the top of this header file. 2300 * 2301 * @param c the code point to be tested 2302 * @return TRUE if the code point is an alphanumeric character according to Character.isLetterOrDigit() 2303 * 2304 * @stable ICU 2.0 2305 */ 2306U_STABLE UBool U_EXPORT2 2307u_isalnum(UChar32 c); 2308 2309/** 2310 * Determines whether the specified code point is a hexadecimal digit. 2311 * This is equivalent to u_digit(c, 16)>=0. 2312 * True for characters with general category "Nd" (decimal digit numbers) 2313 * as well as Latin letters a-f and A-F in both ASCII and Fullwidth ASCII. 2314 * (That is, for letters with code points 2315 * 0041..0046, 0061..0066, FF21..FF26, FF41..FF46.) 2316 * 2317 * In order to narrow the definition of hexadecimal digits to only ASCII 2318 * characters, use (c<=0x7f && u_isxdigit(c)). 2319 * 2320 * This is a C/POSIX migration function. 2321 * See the comments about C/POSIX character classification functions in the 2322 * documentation at the top of this header file. 2323 * 2324 * @param c the code point to be tested 2325 * @return TRUE if the code point is a hexadecimal digit 2326 * 2327 * @stable ICU 2.6 2328 */ 2329U_STABLE UBool U_EXPORT2 2330u_isxdigit(UChar32 c); 2331 2332/** 2333 * Determines whether the specified code point is a punctuation character. 2334 * True for characters with general categories "P" (punctuation). 2335 * 2336 * This is a C/POSIX migration function. 2337 * See the comments about C/POSIX character classification functions in the 2338 * documentation at the top of this header file. 2339 * 2340 * @param c the code point to be tested 2341 * @return TRUE if the code point is a punctuation character 2342 * 2343 * @stable ICU 2.6 2344 */ 2345U_STABLE UBool U_EXPORT2 2346u_ispunct(UChar32 c); 2347 2348/** 2349 * Determines whether the specified code point is a "graphic" character 2350 * (printable, excluding spaces). 2351 * TRUE for all characters except those with general categories 2352 * "Cc" (control codes), "Cf" (format controls), "Cs" (surrogates), 2353 * "Cn" (unassigned), and "Z" (separators). 2354 * 2355 * This is a C/POSIX migration function. 2356 * See the comments about C/POSIX character classification functions in the 2357 * documentation at the top of this header file. 2358 * 2359 * @param c the code point to be tested 2360 * @return TRUE if the code point is a "graphic" character 2361 * 2362 * @stable ICU 2.6 2363 */ 2364U_STABLE UBool U_EXPORT2 2365u_isgraph(UChar32 c); 2366 2367/** 2368 * Determines whether the specified code point is a "blank" or "horizontal space", 2369 * a character that visibly separates words on a line. 2370 * The following are equivalent definitions: 2371 * 2372 * TRUE for Unicode White_Space characters except for "vertical space controls" 2373 * where "vertical space controls" are the following characters: 2374 * U+000A (LF) U+000B (VT) U+000C (FF) U+000D (CR) U+0085 (NEL) U+2028 (LS) U+2029 (PS) 2375 * 2376 * same as 2377 * 2378 * TRUE for U+0009 (TAB) and characters with general category "Zs" (space separators) 2379 * except Zero Width Space (ZWSP, U+200B). 2380 * 2381 * Note: There are several ICU whitespace functions; please see the uchar.h 2382 * file documentation for a detailed comparison. 2383 * 2384 * This is a C/POSIX migration function. 2385 * See the comments about C/POSIX character classification functions in the 2386 * documentation at the top of this header file. 2387 * 2388 * @param c the code point to be tested 2389 * @return TRUE if the code point is a "blank" 2390 * 2391 * @stable ICU 2.6 2392 */ 2393U_STABLE UBool U_EXPORT2 2394u_isblank(UChar32 c); 2395 2396/** 2397 * Determines whether the specified code point is "defined", 2398 * which usually means that it is assigned a character. 2399 * True for general categories other than "Cn" (other, not assigned), 2400 * i.e., true for all code points mentioned in UnicodeData.txt. 2401 * 2402 * Note that non-character code points (e.g., U+FDD0) are not "defined" 2403 * (they are Cn), but surrogate code points are "defined" (Cs). 2404 * 2405 * Same as java.lang.Character.isDefined(). 2406 * 2407 * @param c the code point to be tested 2408 * @return TRUE if the code point is assigned a character 2409 * 2410 * @see u_isdigit 2411 * @see u_isalpha 2412 * @see u_isalnum 2413 * @see u_isupper 2414 * @see u_islower 2415 * @see u_istitle 2416 * @stable ICU 2.0 2417 */ 2418U_STABLE UBool U_EXPORT2 2419u_isdefined(UChar32 c); 2420 2421/** 2422 * Determines if the specified character is a space character or not. 2423 * 2424 * Note: There are several ICU whitespace functions; please see the uchar.h 2425 * file documentation for a detailed comparison. 2426 * 2427 * This is a C/POSIX migration function. 2428 * See the comments about C/POSIX character classification functions in the 2429 * documentation at the top of this header file. 2430 * 2431 * @param c the character to be tested 2432 * @return true if the character is a space character; false otherwise. 2433 * 2434 * @see u_isJavaSpaceChar 2435 * @see u_isWhitespace 2436 * @see u_isUWhiteSpace 2437 * @stable ICU 2.0 2438 */ 2439U_STABLE UBool U_EXPORT2 2440u_isspace(UChar32 c); 2441 2442/** 2443 * Determine if the specified code point is a space character according to Java. 2444 * True for characters with general categories "Z" (separators), 2445 * which does not include control codes (e.g., TAB or Line Feed). 2446 * 2447 * Same as java.lang.Character.isSpaceChar(). 2448 * 2449 * Note: There are several ICU whitespace functions; please see the uchar.h 2450 * file documentation for a detailed comparison. 2451 * 2452 * @param c the code point to be tested 2453 * @return TRUE if the code point is a space character according to Character.isSpaceChar() 2454 * 2455 * @see u_isspace 2456 * @see u_isWhitespace 2457 * @see u_isUWhiteSpace 2458 * @stable ICU 2.6 2459 */ 2460U_STABLE UBool U_EXPORT2 2461u_isJavaSpaceChar(UChar32 c); 2462 2463/** 2464 * Determines if the specified code point is a whitespace character according to Java/ICU. 2465 * A character is considered to be a Java whitespace character if and only 2466 * if it satisfies one of the following criteria: 2467 * 2468 * - It is a Unicode Separator character (categories "Z" = "Zs" or "Zl" or "Zp"), but is not 2469 * also a non-breaking space (U+00A0 NBSP or U+2007 Figure Space or U+202F Narrow NBSP). 2470 * - It is U+0009 HORIZONTAL TABULATION. 2471 * - It is U+000A LINE FEED. 2472 * - It is U+000B VERTICAL TABULATION. 2473 * - It is U+000C FORM FEED. 2474 * - It is U+000D CARRIAGE RETURN. 2475 * - It is U+001C FILE SEPARATOR. 2476 * - It is U+001D GROUP SEPARATOR. 2477 * - It is U+001E RECORD SEPARATOR. 2478 * - It is U+001F UNIT SEPARATOR. 2479 * 2480 * This API tries to sync with the semantics of Java's 2481 * java.lang.Character.isWhitespace(), but it may not return 2482 * the exact same results because of the Unicode version 2483 * difference. 2484 * 2485 * Note: Unicode 4.0.1 changed U+200B ZERO WIDTH SPACE from a Space Separator (Zs) 2486 * to a Format Control (Cf). Since then, isWhitespace(0x200b) returns false. 2487 * See http://www.unicode.org/versions/Unicode4.0.1/ 2488 * 2489 * Note: There are several ICU whitespace functions; please see the uchar.h 2490 * file documentation for a detailed comparison. 2491 * 2492 * @param c the code point to be tested 2493 * @return TRUE if the code point is a whitespace character according to Java/ICU 2494 * 2495 * @see u_isspace 2496 * @see u_isJavaSpaceChar 2497 * @see u_isUWhiteSpace 2498 * @stable ICU 2.0 2499 */ 2500U_STABLE UBool U_EXPORT2 2501u_isWhitespace(UChar32 c); 2502 2503/** 2504 * Determines whether the specified code point is a control character 2505 * (as defined by this function). 2506 * A control character is one of the following: 2507 * - ISO 8-bit control character (U+0000..U+001f and U+007f..U+009f) 2508 * - U_CONTROL_CHAR (Cc) 2509 * - U_FORMAT_CHAR (Cf) 2510 * - U_LINE_SEPARATOR (Zl) 2511 * - U_PARAGRAPH_SEPARATOR (Zp) 2512 * 2513 * This is a C/POSIX migration function. 2514 * See the comments about C/POSIX character classification functions in the 2515 * documentation at the top of this header file. 2516 * 2517 * @param c the code point to be tested 2518 * @return TRUE if the code point is a control character 2519 * 2520 * @see UCHAR_DEFAULT_IGNORABLE_CODE_POINT 2521 * @see u_isprint 2522 * @stable ICU 2.0 2523 */ 2524U_STABLE UBool U_EXPORT2 2525u_iscntrl(UChar32 c); 2526 2527/** 2528 * Determines whether the specified code point is an ISO control code. 2529 * True for U+0000..U+001f and U+007f..U+009f (general category "Cc"). 2530 * 2531 * Same as java.lang.Character.isISOControl(). 2532 * 2533 * @param c the code point to be tested 2534 * @return TRUE if the code point is an ISO control code 2535 * 2536 * @see u_iscntrl 2537 * @stable ICU 2.6 2538 */ 2539U_STABLE UBool U_EXPORT2 2540u_isISOControl(UChar32 c); 2541 2542/** 2543 * Determines whether the specified code point is a printable character. 2544 * True for general categories <em>other</em> than "C" (controls). 2545 * 2546 * This is a C/POSIX migration function. 2547 * See the comments about C/POSIX character classification functions in the 2548 * documentation at the top of this header file. 2549 * 2550 * @param c the code point to be tested 2551 * @return TRUE if the code point is a printable character 2552 * 2553 * @see UCHAR_DEFAULT_IGNORABLE_CODE_POINT 2554 * @see u_iscntrl 2555 * @stable ICU 2.0 2556 */ 2557U_STABLE UBool U_EXPORT2 2558u_isprint(UChar32 c); 2559 2560/** 2561 * Determines whether the specified code point is a base character. 2562 * True for general categories "L" (letters), "N" (numbers), 2563 * "Mc" (spacing combining marks), and "Me" (enclosing marks). 2564 * 2565 * Note that this is different from the Unicode definition in 2566 * chapter 3.5, conformance clause D13, 2567 * which defines base characters to be all characters (not Cn) 2568 * that do not graphically combine with preceding characters (M) 2569 * and that are neither control (Cc) or format (Cf) characters. 2570 * 2571 * @param c the code point to be tested 2572 * @return TRUE if the code point is a base character according to this function 2573 * 2574 * @see u_isalpha 2575 * @see u_isdigit 2576 * @stable ICU 2.0 2577 */ 2578U_STABLE UBool U_EXPORT2 2579u_isbase(UChar32 c); 2580 2581/** 2582 * Returns the bidirectional category value for the code point, 2583 * which is used in the Unicode bidirectional algorithm 2584 * (UAX #9 http://www.unicode.org/reports/tr9/). 2585 * Note that some <em>unassigned</em> code points have bidi values 2586 * of R or AL because they are in blocks that are reserved 2587 * for Right-To-Left scripts. 2588 * 2589 * Same as java.lang.Character.getDirectionality() 2590 * 2591 * @param c the code point to be tested 2592 * @return the bidirectional category (UCharDirection) value 2593 * 2594 * @see UCharDirection 2595 * @stable ICU 2.0 2596 */ 2597U_STABLE UCharDirection U_EXPORT2 2598u_charDirection(UChar32 c); 2599 2600/** 2601 * Determines whether the code point has the Bidi_Mirrored property. 2602 * This property is set for characters that are commonly used in 2603 * Right-To-Left contexts and need to be displayed with a "mirrored" 2604 * glyph. 2605 * 2606 * Same as java.lang.Character.isMirrored(). 2607 * Same as UCHAR_BIDI_MIRRORED 2608 * 2609 * @param c the code point to be tested 2610 * @return TRUE if the character has the Bidi_Mirrored property 2611 * 2612 * @see UCHAR_BIDI_MIRRORED 2613 * @stable ICU 2.0 2614 */ 2615U_STABLE UBool U_EXPORT2 2616u_isMirrored(UChar32 c); 2617 2618/** 2619 * Maps the specified character to a "mirror-image" character. 2620 * For characters with the Bidi_Mirrored property, implementations 2621 * sometimes need a "poor man's" mapping to another Unicode 2622 * character (code point) such that the default glyph may serve 2623 * as the mirror-image of the default glyph of the specified 2624 * character. This is useful for text conversion to and from 2625 * codepages with visual order, and for displays without glyph 2626 * selection capabilities. 2627 * 2628 * @param c the code point to be mapped 2629 * @return another Unicode code point that may serve as a mirror-image 2630 * substitute, or c itself if there is no such mapping or c 2631 * does not have the Bidi_Mirrored property 2632 * 2633 * @see UCHAR_BIDI_MIRRORED 2634 * @see u_isMirrored 2635 * @stable ICU 2.0 2636 */ 2637U_STABLE UChar32 U_EXPORT2 2638u_charMirror(UChar32 c); 2639 2640/** 2641 * Maps the specified character to its paired bracket character. 2642 * For Bidi_Paired_Bracket_Type!=None, this is the same as u_charMirror(). 2643 * Otherwise c itself is returned. 2644 * See http://www.unicode.org/reports/tr9/ 2645 * 2646 * @param c the code point to be mapped 2647 * @return the paired bracket code point, 2648 * or c itself if there is no such mapping 2649 * (Bidi_Paired_Bracket_Type=None) 2650 * 2651 * @see UCHAR_BIDI_PAIRED_BRACKET 2652 * @see UCHAR_BIDI_PAIRED_BRACKET_TYPE 2653 * @see u_charMirror 2654 * @stable ICU 52 2655 */ 2656U_STABLE UChar32 U_EXPORT2 2657u_getBidiPairedBracket(UChar32 c); 2658 2659/** 2660 * Returns the general category value for the code point. 2661 * 2662 * Same as java.lang.Character.getType(). 2663 * 2664 * @param c the code point to be tested 2665 * @return the general category (UCharCategory) value 2666 * 2667 * @see UCharCategory 2668 * @stable ICU 2.0 2669 */ 2670U_STABLE int8_t U_EXPORT2 2671u_charType(UChar32 c); 2672 2673/** 2674 * Get a single-bit bit set for the general category of a character. 2675 * This bit set can be compared bitwise with U_GC_SM_MASK, U_GC_L_MASK, etc. 2676 * Same as U_MASK(u_charType(c)). 2677 * 2678 * @param c the code point to be tested 2679 * @return a single-bit mask corresponding to the general category (UCharCategory) value 2680 * 2681 * @see u_charType 2682 * @see UCharCategory 2683 * @see U_GC_CN_MASK 2684 * @stable ICU 2.1 2685 */ 2686#define U_GET_GC_MASK(c) U_MASK(u_charType(c)) 2687 2688/** 2689 * Callback from u_enumCharTypes(), is called for each contiguous range 2690 * of code points c (where start<=c<limit) 2691 * with the same Unicode general category ("character type"). 2692 * 2693 * The callback function can stop the enumeration by returning FALSE. 2694 * 2695 * @param context an opaque pointer, as passed into utrie_enum() 2696 * @param start the first code point in a contiguous range with value 2697 * @param limit one past the last code point in a contiguous range with value 2698 * @param type the general category for all code points in [start..limit[ 2699 * @return FALSE to stop the enumeration 2700 * 2701 * @stable ICU 2.1 2702 * @see UCharCategory 2703 * @see u_enumCharTypes 2704 */ 2705typedef UBool U_CALLCONV 2706UCharEnumTypeRange(const void *context, UChar32 start, UChar32 limit, UCharCategory type); 2707 2708/** 2709 * Enumerate efficiently all code points with their Unicode general categories. 2710 * 2711 * This is useful for building data structures (e.g., UnicodeSet's), 2712 * for enumerating all assigned code points (type!=U_UNASSIGNED), etc. 2713 * 2714 * For each contiguous range of code points with a given general category ("character type"), 2715 * the UCharEnumTypeRange function is called. 2716 * Adjacent ranges have different types. 2717 * The Unicode Standard guarantees that the numeric value of the type is 0..31. 2718 * 2719 * @param enumRange a pointer to a function that is called for each contiguous range 2720 * of code points with the same general category 2721 * @param context an opaque pointer that is passed on to the callback function 2722 * 2723 * @stable ICU 2.1 2724 * @see UCharCategory 2725 * @see UCharEnumTypeRange 2726 */ 2727U_STABLE void U_EXPORT2 2728u_enumCharTypes(UCharEnumTypeRange *enumRange, const void *context); 2729 2730#if !UCONFIG_NO_NORMALIZATION 2731 2732/** 2733 * Returns the combining class of the code point as specified in UnicodeData.txt. 2734 * 2735 * @param c the code point of the character 2736 * @return the combining class of the character 2737 * @stable ICU 2.0 2738 */ 2739U_STABLE uint8_t U_EXPORT2 2740u_getCombiningClass(UChar32 c); 2741 2742#endif 2743 2744/** 2745 * Returns the decimal digit value of a decimal digit character. 2746 * Such characters have the general category "Nd" (decimal digit numbers) 2747 * and a Numeric_Type of Decimal. 2748 * 2749 * Unlike ICU releases before 2.6, no digit values are returned for any 2750 * Han characters because Han number characters are often used with a special 2751 * Chinese-style number format (with characters for powers of 10 in between) 2752 * instead of in decimal-positional notation. 2753 * Unicode 4 explicitly assigns Han number characters the Numeric_Type 2754 * Numeric instead of Decimal. 2755 * See Jitterbug 1483 for more details. 2756 * 2757 * Use u_getIntPropertyValue(c, UCHAR_NUMERIC_TYPE) and u_getNumericValue() 2758 * for complete numeric Unicode properties. 2759 * 2760 * @param c the code point for which to get the decimal digit value 2761 * @return the decimal digit value of c, 2762 * or -1 if c is not a decimal digit character 2763 * 2764 * @see u_getNumericValue 2765 * @stable ICU 2.0 2766 */ 2767U_STABLE int32_t U_EXPORT2 2768u_charDigitValue(UChar32 c); 2769 2770/** 2771 * Returns the Unicode allocation block that contains the character. 2772 * 2773 * @param c the code point to be tested 2774 * @return the block value (UBlockCode) for c 2775 * 2776 * @see UBlockCode 2777 * @stable ICU 2.0 2778 */ 2779U_STABLE UBlockCode U_EXPORT2 2780ublock_getCode(UChar32 c); 2781 2782/** 2783 * Retrieve the name of a Unicode character. 2784 * Depending on <code>nameChoice</code>, the character name written 2785 * into the buffer is the "modern" name or the name that was defined 2786 * in Unicode version 1.0. 2787 * The name contains only "invariant" characters 2788 * like A-Z, 0-9, space, and '-'. 2789 * Unicode 1.0 names are only retrieved if they are different from the modern 2790 * names and if the data file contains the data for them. gennames may or may 2791 * not be called with a command line option to include 1.0 names in unames.dat. 2792 * 2793 * @param code The character (code point) for which to get the name. 2794 * It must be <code>0<=code<=0x10ffff</code>. 2795 * @param nameChoice Selector for which name to get. 2796 * @param buffer Destination address for copying the name. 2797 * The name will always be zero-terminated. 2798 * If there is no name, then the buffer will be set to the empty string. 2799 * @param bufferLength <code>==sizeof(buffer)</code> 2800 * @param pErrorCode Pointer to a UErrorCode variable; 2801 * check for <code>U_SUCCESS()</code> after <code>u_charName()</code> 2802 * returns. 2803 * @return The length of the name, or 0 if there is no name for this character. 2804 * If the bufferLength is less than or equal to the length, then the buffer 2805 * contains the truncated name and the returned length indicates the full 2806 * length of the name. 2807 * The length does not include the zero-termination. 2808 * 2809 * @see UCharNameChoice 2810 * @see u_charFromName 2811 * @see u_enumCharNames 2812 * @stable ICU 2.0 2813 */ 2814U_STABLE int32_t U_EXPORT2 2815u_charName(UChar32 code, UCharNameChoice nameChoice, 2816 char *buffer, int32_t bufferLength, 2817 UErrorCode *pErrorCode); 2818 2819#ifndef U_HIDE_DEPRECATED_API 2820/** 2821 * Returns an empty string. 2822 * Used to return the ISO 10646 comment for a character. 2823 * The Unicode ISO_Comment property is deprecated and has no values. 2824 * 2825 * @param c The character (code point) for which to get the ISO comment. 2826 * It must be <code>0<=c<=0x10ffff</code>. 2827 * @param dest Destination address for copying the comment. 2828 * The comment will be zero-terminated if possible. 2829 * If there is no comment, then the buffer will be set to the empty string. 2830 * @param destCapacity <code>==sizeof(dest)</code> 2831 * @param pErrorCode Pointer to a UErrorCode variable; 2832 * check for <code>U_SUCCESS()</code> after <code>u_getISOComment()</code> 2833 * returns. 2834 * @return 0 2835 * 2836 * @deprecated ICU 49 2837 */ 2838U_DEPRECATED int32_t U_EXPORT2 2839u_getISOComment(UChar32 c, 2840 char *dest, int32_t destCapacity, 2841 UErrorCode *pErrorCode); 2842#endif /* U_HIDE_DEPRECATED_API */ 2843 2844/** 2845 * Find a Unicode character by its name and return its code point value. 2846 * The name is matched exactly and completely. 2847 * If the name does not correspond to a code point, <i>pErrorCode</i> 2848 * is set to <code>U_INVALID_CHAR_FOUND</code>. 2849 * A Unicode 1.0 name is matched only if it differs from the modern name. 2850 * Unicode names are all uppercase. Extended names are lowercase followed 2851 * by an uppercase hexadecimal number, and within angle brackets. 2852 * 2853 * @param nameChoice Selector for which name to match. 2854 * @param name The name to match. 2855 * @param pErrorCode Pointer to a UErrorCode variable 2856 * @return The Unicode value of the code point with the given name, 2857 * or an undefined value if there is no such code point. 2858 * 2859 * @see UCharNameChoice 2860 * @see u_charName 2861 * @see u_enumCharNames 2862 * @stable ICU 1.7 2863 */ 2864U_STABLE UChar32 U_EXPORT2 2865u_charFromName(UCharNameChoice nameChoice, 2866 const char *name, 2867 UErrorCode *pErrorCode); 2868 2869/** 2870 * Type of a callback function for u_enumCharNames() that gets called 2871 * for each Unicode character with the code point value and 2872 * the character name. 2873 * If such a function returns FALSE, then the enumeration is stopped. 2874 * 2875 * @param context The context pointer that was passed to u_enumCharNames(). 2876 * @param code The Unicode code point for the character with this name. 2877 * @param nameChoice Selector for which kind of names is enumerated. 2878 * @param name The character's name, zero-terminated. 2879 * @param length The length of the name. 2880 * @return TRUE if the enumeration should continue, FALSE to stop it. 2881 * 2882 * @see UCharNameChoice 2883 * @see u_enumCharNames 2884 * @stable ICU 1.7 2885 */ 2886typedef UBool U_CALLCONV UEnumCharNamesFn(void *context, 2887 UChar32 code, 2888 UCharNameChoice nameChoice, 2889 const char *name, 2890 int32_t length); 2891 2892/** 2893 * Enumerate all assigned Unicode characters between the start and limit 2894 * code points (start inclusive, limit exclusive) and call a function 2895 * for each, passing the code point value and the character name. 2896 * For Unicode 1.0 names, only those are enumerated that differ from the 2897 * modern names. 2898 * 2899 * @param start The first code point in the enumeration range. 2900 * @param limit One more than the last code point in the enumeration range 2901 * (the first one after the range). 2902 * @param fn The function that is to be called for each character name. 2903 * @param context An arbitrary pointer that is passed to the function. 2904 * @param nameChoice Selector for which kind of names to enumerate. 2905 * @param pErrorCode Pointer to a UErrorCode variable 2906 * 2907 * @see UCharNameChoice 2908 * @see UEnumCharNamesFn 2909 * @see u_charName 2910 * @see u_charFromName 2911 * @stable ICU 1.7 2912 */ 2913U_STABLE void U_EXPORT2 2914u_enumCharNames(UChar32 start, UChar32 limit, 2915 UEnumCharNamesFn *fn, 2916 void *context, 2917 UCharNameChoice nameChoice, 2918 UErrorCode *pErrorCode); 2919 2920/** 2921 * Return the Unicode name for a given property, as given in the 2922 * Unicode database file PropertyAliases.txt. 2923 * 2924 * In addition, this function maps the property 2925 * UCHAR_GENERAL_CATEGORY_MASK to the synthetic names "gcm" / 2926 * "General_Category_Mask". These names are not in 2927 * PropertyAliases.txt. 2928 * 2929 * @param property UProperty selector other than UCHAR_INVALID_CODE. 2930 * If out of range, NULL is returned. 2931 * 2932 * @param nameChoice selector for which name to get. If out of range, 2933 * NULL is returned. All properties have a long name. Most 2934 * have a short name, but some do not. Unicode allows for 2935 * additional names; if present these will be returned by 2936 * U_LONG_PROPERTY_NAME + i, where i=1, 2,... 2937 * 2938 * @return a pointer to the name, or NULL if either the 2939 * property or the nameChoice is out of range. If a given 2940 * nameChoice returns NULL, then all larger values of 2941 * nameChoice will return NULL, with one exception: if NULL is 2942 * returned for U_SHORT_PROPERTY_NAME, then 2943 * U_LONG_PROPERTY_NAME (and higher) may still return a 2944 * non-NULL value. The returned pointer is valid until 2945 * u_cleanup() is called. 2946 * 2947 * @see UProperty 2948 * @see UPropertyNameChoice 2949 * @stable ICU 2.4 2950 */ 2951U_STABLE const char* U_EXPORT2 2952u_getPropertyName(UProperty property, 2953 UPropertyNameChoice nameChoice); 2954 2955/** 2956 * Return the UProperty enum for a given property name, as specified 2957 * in the Unicode database file PropertyAliases.txt. Short, long, and 2958 * any other variants are recognized. 2959 * 2960 * In addition, this function maps the synthetic names "gcm" / 2961 * "General_Category_Mask" to the property 2962 * UCHAR_GENERAL_CATEGORY_MASK. These names are not in 2963 * PropertyAliases.txt. 2964 * 2965 * @param alias the property name to be matched. The name is compared 2966 * using "loose matching" as described in PropertyAliases.txt. 2967 * 2968 * @return a UProperty enum, or UCHAR_INVALID_CODE if the given name 2969 * does not match any property. 2970 * 2971 * @see UProperty 2972 * @stable ICU 2.4 2973 */ 2974U_STABLE UProperty U_EXPORT2 2975u_getPropertyEnum(const char* alias); 2976 2977/** 2978 * Return the Unicode name for a given property value, as given in the 2979 * Unicode database file PropertyValueAliases.txt. 2980 * 2981 * Note: Some of the names in PropertyValueAliases.txt can only be 2982 * retrieved using UCHAR_GENERAL_CATEGORY_MASK, not 2983 * UCHAR_GENERAL_CATEGORY. These include: "C" / "Other", "L" / 2984 * "Letter", "LC" / "Cased_Letter", "M" / "Mark", "N" / "Number", "P" 2985 * / "Punctuation", "S" / "Symbol", and "Z" / "Separator". 2986 * 2987 * @param property UProperty selector constant. 2988 * Must be UCHAR_BINARY_START<=which<UCHAR_BINARY_LIMIT 2989 * or UCHAR_INT_START<=which<UCHAR_INT_LIMIT 2990 * or UCHAR_MASK_START<=which<UCHAR_MASK_LIMIT. 2991 * If out of range, NULL is returned. 2992 * 2993 * @param value selector for a value for the given property. If out 2994 * of range, NULL is returned. In general, valid values range 2995 * from 0 up to some maximum. There are a few exceptions: 2996 * (1.) UCHAR_BLOCK values begin at the non-zero value 2997 * UBLOCK_BASIC_LATIN. (2.) UCHAR_CANONICAL_COMBINING_CLASS 2998 * values are not contiguous and range from 0..240. (3.) 2999 * UCHAR_GENERAL_CATEGORY_MASK values are not values of 3000 * UCharCategory, but rather mask values produced by 3001 * U_GET_GC_MASK(). This allows grouped categories such as 3002 * [:L:] to be represented. Mask values range 3003 * non-contiguously from 1..U_GC_P_MASK. 3004 * 3005 * @param nameChoice selector for which name to get. If out of range, 3006 * NULL is returned. All values have a long name. Most have 3007 * a short name, but some do not. Unicode allows for 3008 * additional names; if present these will be returned by 3009 * U_LONG_PROPERTY_NAME + i, where i=1, 2,... 3010 3011 * @return a pointer to the name, or NULL if either the 3012 * property or the nameChoice is out of range. If a given 3013 * nameChoice returns NULL, then all larger values of 3014 * nameChoice will return NULL, with one exception: if NULL is 3015 * returned for U_SHORT_PROPERTY_NAME, then 3016 * U_LONG_PROPERTY_NAME (and higher) may still return a 3017 * non-NULL value. The returned pointer is valid until 3018 * u_cleanup() is called. 3019 * 3020 * @see UProperty 3021 * @see UPropertyNameChoice 3022 * @stable ICU 2.4 3023 */ 3024U_STABLE const char* U_EXPORT2 3025u_getPropertyValueName(UProperty property, 3026 int32_t value, 3027 UPropertyNameChoice nameChoice); 3028 3029/** 3030 * Return the property value integer for a given value name, as 3031 * specified in the Unicode database file PropertyValueAliases.txt. 3032 * Short, long, and any other variants are recognized. 3033 * 3034 * Note: Some of the names in PropertyValueAliases.txt will only be 3035 * recognized with UCHAR_GENERAL_CATEGORY_MASK, not 3036 * UCHAR_GENERAL_CATEGORY. These include: "C" / "Other", "L" / 3037 * "Letter", "LC" / "Cased_Letter", "M" / "Mark", "N" / "Number", "P" 3038 * / "Punctuation", "S" / "Symbol", and "Z" / "Separator". 3039 * 3040 * @param property UProperty selector constant. 3041 * Must be UCHAR_BINARY_START<=which<UCHAR_BINARY_LIMIT 3042 * or UCHAR_INT_START<=which<UCHAR_INT_LIMIT 3043 * or UCHAR_MASK_START<=which<UCHAR_MASK_LIMIT. 3044 * If out of range, UCHAR_INVALID_CODE is returned. 3045 * 3046 * @param alias the value name to be matched. The name is compared 3047 * using "loose matching" as described in 3048 * PropertyValueAliases.txt. 3049 * 3050 * @return a value integer or UCHAR_INVALID_CODE if the given name 3051 * does not match any value of the given property, or if the 3052 * property is invalid. Note: UCHAR_GENERAL_CATEGORY_MASK values 3053 * are not values of UCharCategory, but rather mask values 3054 * produced by U_GET_GC_MASK(). This allows grouped 3055 * categories such as [:L:] to be represented. 3056 * 3057 * @see UProperty 3058 * @stable ICU 2.4 3059 */ 3060U_STABLE int32_t U_EXPORT2 3061u_getPropertyValueEnum(UProperty property, 3062 const char* alias); 3063 3064/** 3065 * Determines if the specified character is permissible as the 3066 * first character in an identifier according to Unicode 3067 * (The Unicode Standard, Version 3.0, chapter 5.16 Identifiers). 3068 * True for characters with general categories "L" (letters) and "Nl" (letter numbers). 3069 * 3070 * Same as java.lang.Character.isUnicodeIdentifierStart(). 3071 * Same as UCHAR_ID_START 3072 * 3073 * @param c the code point to be tested 3074 * @return TRUE if the code point may start an identifier 3075 * 3076 * @see UCHAR_ID_START 3077 * @see u_isalpha 3078 * @see u_isIDPart 3079 * @stable ICU 2.0 3080 */ 3081U_STABLE UBool U_EXPORT2 3082u_isIDStart(UChar32 c); 3083 3084/** 3085 * Determines if the specified character is permissible 3086 * in an identifier according to Java. 3087 * True for characters with general categories "L" (letters), 3088 * "Nl" (letter numbers), "Nd" (decimal digits), 3089 * "Mc" and "Mn" (combining marks), "Pc" (connecting punctuation), and 3090 * u_isIDIgnorable(c). 3091 * 3092 * Same as java.lang.Character.isUnicodeIdentifierPart(). 3093 * Almost the same as Unicode's ID_Continue (UCHAR_ID_CONTINUE) 3094 * except that Unicode recommends to ignore Cf which is less than 3095 * u_isIDIgnorable(c). 3096 * 3097 * @param c the code point to be tested 3098 * @return TRUE if the code point may occur in an identifier according to Java 3099 * 3100 * @see UCHAR_ID_CONTINUE 3101 * @see u_isIDStart 3102 * @see u_isIDIgnorable 3103 * @stable ICU 2.0 3104 */ 3105U_STABLE UBool U_EXPORT2 3106u_isIDPart(UChar32 c); 3107 3108/** 3109 * Determines if the specified character should be regarded 3110 * as an ignorable character in an identifier, 3111 * according to Java. 3112 * True for characters with general category "Cf" (format controls) as well as 3113 * non-whitespace ISO controls 3114 * (U+0000..U+0008, U+000E..U+001B, U+007F..U+009F). 3115 * 3116 * Same as java.lang.Character.isIdentifierIgnorable(). 3117 * 3118 * Note that Unicode just recommends to ignore Cf (format controls). 3119 * 3120 * @param c the code point to be tested 3121 * @return TRUE if the code point is ignorable in identifiers according to Java 3122 * 3123 * @see UCHAR_DEFAULT_IGNORABLE_CODE_POINT 3124 * @see u_isIDStart 3125 * @see u_isIDPart 3126 * @stable ICU 2.0 3127 */ 3128U_STABLE UBool U_EXPORT2 3129u_isIDIgnorable(UChar32 c); 3130 3131/** 3132 * Determines if the specified character is permissible as the 3133 * first character in a Java identifier. 3134 * In addition to u_isIDStart(c), true for characters with 3135 * general categories "Sc" (currency symbols) and "Pc" (connecting punctuation). 3136 * 3137 * Same as java.lang.Character.isJavaIdentifierStart(). 3138 * 3139 * @param c the code point to be tested 3140 * @return TRUE if the code point may start a Java identifier 3141 * 3142 * @see u_isJavaIDPart 3143 * @see u_isalpha 3144 * @see u_isIDStart 3145 * @stable ICU 2.0 3146 */ 3147U_STABLE UBool U_EXPORT2 3148u_isJavaIDStart(UChar32 c); 3149 3150/** 3151 * Determines if the specified character is permissible 3152 * in a Java identifier. 3153 * In addition to u_isIDPart(c), true for characters with 3154 * general category "Sc" (currency symbols). 3155 * 3156 * Same as java.lang.Character.isJavaIdentifierPart(). 3157 * 3158 * @param c the code point to be tested 3159 * @return TRUE if the code point may occur in a Java identifier 3160 * 3161 * @see u_isIDIgnorable 3162 * @see u_isJavaIDStart 3163 * @see u_isalpha 3164 * @see u_isdigit 3165 * @see u_isIDPart 3166 * @stable ICU 2.0 3167 */ 3168U_STABLE UBool U_EXPORT2 3169u_isJavaIDPart(UChar32 c); 3170 3171/** 3172 * The given character is mapped to its lowercase equivalent according to 3173 * UnicodeData.txt; if the character has no lowercase equivalent, the character 3174 * itself is returned. 3175 * 3176 * Same as java.lang.Character.toLowerCase(). 3177 * 3178 * This function only returns the simple, single-code point case mapping. 3179 * Full case mappings should be used whenever possible because they produce 3180 * better results by working on whole strings. 3181 * They take into account the string context and the language and can map 3182 * to a result string with a different length as appropriate. 3183 * Full case mappings are applied by the string case mapping functions, 3184 * see ustring.h and the UnicodeString class. 3185 * See also the User Guide chapter on C/POSIX migration: 3186 * http://icu-project.org/userguide/posix.html#case_mappings 3187 * 3188 * @param c the code point to be mapped 3189 * @return the Simple_Lowercase_Mapping of the code point, if any; 3190 * otherwise the code point itself. 3191 * @stable ICU 2.0 3192 */ 3193U_STABLE UChar32 U_EXPORT2 3194u_tolower(UChar32 c); 3195 3196/** 3197 * The given character is mapped to its uppercase equivalent according to UnicodeData.txt; 3198 * if the character has no uppercase equivalent, the character itself is 3199 * returned. 3200 * 3201 * Same as java.lang.Character.toUpperCase(). 3202 * 3203 * This function only returns the simple, single-code point case mapping. 3204 * Full case mappings should be used whenever possible because they produce 3205 * better results by working on whole strings. 3206 * They take into account the string context and the language and can map 3207 * to a result string with a different length as appropriate. 3208 * Full case mappings are applied by the string case mapping functions, 3209 * see ustring.h and the UnicodeString class. 3210 * See also the User Guide chapter on C/POSIX migration: 3211 * http://icu-project.org/userguide/posix.html#case_mappings 3212 * 3213 * @param c the code point to be mapped 3214 * @return the Simple_Uppercase_Mapping of the code point, if any; 3215 * otherwise the code point itself. 3216 * @stable ICU 2.0 3217 */ 3218U_STABLE UChar32 U_EXPORT2 3219u_toupper(UChar32 c); 3220 3221/** 3222 * The given character is mapped to its titlecase equivalent 3223 * according to UnicodeData.txt; 3224 * if none is defined, the character itself is returned. 3225 * 3226 * Same as java.lang.Character.toTitleCase(). 3227 * 3228 * This function only returns the simple, single-code point case mapping. 3229 * Full case mappings should be used whenever possible because they produce 3230 * better results by working on whole strings. 3231 * They take into account the string context and the language and can map 3232 * to a result string with a different length as appropriate. 3233 * Full case mappings are applied by the string case mapping functions, 3234 * see ustring.h and the UnicodeString class. 3235 * See also the User Guide chapter on C/POSIX migration: 3236 * http://icu-project.org/userguide/posix.html#case_mappings 3237 * 3238 * @param c the code point to be mapped 3239 * @return the Simple_Titlecase_Mapping of the code point, if any; 3240 * otherwise the code point itself. 3241 * @stable ICU 2.0 3242 */ 3243U_STABLE UChar32 U_EXPORT2 3244u_totitle(UChar32 c); 3245 3246/** Option value for case folding: use default mappings defined in CaseFolding.txt. @stable ICU 2.0 */ 3247#define U_FOLD_CASE_DEFAULT 0 3248 3249/** 3250 * Option value for case folding: 3251 * 3252 * Use the modified set of mappings provided in CaseFolding.txt to handle dotted I 3253 * and dotless i appropriately for Turkic languages (tr, az). 3254 * 3255 * Before Unicode 3.2, CaseFolding.txt contains mappings marked with 'I' that 3256 * are to be included for default mappings and 3257 * excluded for the Turkic-specific mappings. 3258 * 3259 * Unicode 3.2 CaseFolding.txt instead contains mappings marked with 'T' that 3260 * are to be excluded for default mappings and 3261 * included for the Turkic-specific mappings. 3262 * 3263 * @stable ICU 2.0 3264 */ 3265#define U_FOLD_CASE_EXCLUDE_SPECIAL_I 1 3266 3267/** 3268 * The given character is mapped to its case folding equivalent according to 3269 * UnicodeData.txt and CaseFolding.txt; 3270 * if the character has no case folding equivalent, the character 3271 * itself is returned. 3272 * 3273 * This function only returns the simple, single-code point case mapping. 3274 * Full case mappings should be used whenever possible because they produce 3275 * better results by working on whole strings. 3276 * They take into account the string context and the language and can map 3277 * to a result string with a different length as appropriate. 3278 * Full case mappings are applied by the string case mapping functions, 3279 * see ustring.h and the UnicodeString class. 3280 * See also the User Guide chapter on C/POSIX migration: 3281 * http://icu-project.org/userguide/posix.html#case_mappings 3282 * 3283 * @param c the code point to be mapped 3284 * @param options Either U_FOLD_CASE_DEFAULT or U_FOLD_CASE_EXCLUDE_SPECIAL_I 3285 * @return the Simple_Case_Folding of the code point, if any; 3286 * otherwise the code point itself. 3287 * @stable ICU 2.0 3288 */ 3289U_STABLE UChar32 U_EXPORT2 3290u_foldCase(UChar32 c, uint32_t options); 3291 3292/** 3293 * Returns the decimal digit value of the code point in the 3294 * specified radix. 3295 * 3296 * If the radix is not in the range <code>2<=radix<=36</code> or if the 3297 * value of <code>c</code> is not a valid digit in the specified 3298 * radix, <code>-1</code> is returned. A character is a valid digit 3299 * if at least one of the following is true: 3300 * <ul> 3301 * <li>The character has a decimal digit value. 3302 * Such characters have the general category "Nd" (decimal digit numbers) 3303 * and a Numeric_Type of Decimal. 3304 * In this case the value is the character's decimal digit value.</li> 3305 * <li>The character is one of the uppercase Latin letters 3306 * <code>'A'</code> through <code>'Z'</code>. 3307 * In this case the value is <code>c-'A'+10</code>.</li> 3308 * <li>The character is one of the lowercase Latin letters 3309 * <code>'a'</code> through <code>'z'</code>. 3310 * In this case the value is <code>ch-'a'+10</code>.</li> 3311 * <li>Latin letters from both the ASCII range (0061..007A, 0041..005A) 3312 * as well as from the Fullwidth ASCII range (FF41..FF5A, FF21..FF3A) 3313 * are recognized.</li> 3314 * </ul> 3315 * 3316 * Same as java.lang.Character.digit(). 3317 * 3318 * @param ch the code point to be tested. 3319 * @param radix the radix. 3320 * @return the numeric value represented by the character in the 3321 * specified radix, 3322 * or -1 if there is no value or if the value exceeds the radix. 3323 * 3324 * @see UCHAR_NUMERIC_TYPE 3325 * @see u_forDigit 3326 * @see u_charDigitValue 3327 * @see u_isdigit 3328 * @stable ICU 2.0 3329 */ 3330U_STABLE int32_t U_EXPORT2 3331u_digit(UChar32 ch, int8_t radix); 3332 3333/** 3334 * Determines the character representation for a specific digit in 3335 * the specified radix. If the value of <code>radix</code> is not a 3336 * valid radix, or the value of <code>digit</code> is not a valid 3337 * digit in the specified radix, the null character 3338 * (<code>U+0000</code>) is returned. 3339 * <p> 3340 * The <code>radix</code> argument is valid if it is greater than or 3341 * equal to 2 and less than or equal to 36. 3342 * The <code>digit</code> argument is valid if 3343 * <code>0 <= digit < radix</code>. 3344 * <p> 3345 * If the digit is less than 10, then 3346 * <code>'0' + digit</code> is returned. Otherwise, the value 3347 * <code>'a' + digit - 10</code> is returned. 3348 * 3349 * Same as java.lang.Character.forDigit(). 3350 * 3351 * @param digit the number to convert to a character. 3352 * @param radix the radix. 3353 * @return the <code>char</code> representation of the specified digit 3354 * in the specified radix. 3355 * 3356 * @see u_digit 3357 * @see u_charDigitValue 3358 * @see u_isdigit 3359 * @stable ICU 2.0 3360 */ 3361U_STABLE UChar32 U_EXPORT2 3362u_forDigit(int32_t digit, int8_t radix); 3363 3364/** 3365 * Get the "age" of the code point. 3366 * The "age" is the Unicode version when the code point was first 3367 * designated (as a non-character or for Private Use) 3368 * or assigned a character. 3369 * This can be useful to avoid emitting code points to receiving 3370 * processes that do not accept newer characters. 3371 * The data is from the UCD file DerivedAge.txt. 3372 * 3373 * @param c The code point. 3374 * @param versionArray The Unicode version number array, to be filled in. 3375 * 3376 * @stable ICU 2.1 3377 */ 3378U_STABLE void U_EXPORT2 3379u_charAge(UChar32 c, UVersionInfo versionArray); 3380 3381/** 3382 * Gets the Unicode version information. 3383 * The version array is filled in with the version information 3384 * for the Unicode standard that is currently used by ICU. 3385 * For example, Unicode version 3.1.1 is represented as an array with 3386 * the values { 3, 1, 1, 0 }. 3387 * 3388 * @param versionArray an output array that will be filled in with 3389 * the Unicode version number 3390 * @stable ICU 2.0 3391 */ 3392U_STABLE void U_EXPORT2 3393u_getUnicodeVersion(UVersionInfo versionArray); 3394 3395#if !UCONFIG_NO_NORMALIZATION 3396/** 3397 * Get the FC_NFKC_Closure property string for a character. 3398 * See Unicode Standard Annex #15 for details, search for "FC_NFKC_Closure" 3399 * or for "FNC": http://www.unicode.org/reports/tr15/ 3400 * 3401 * @param c The character (code point) for which to get the FC_NFKC_Closure string. 3402 * It must be <code>0<=c<=0x10ffff</code>. 3403 * @param dest Destination address for copying the string. 3404 * The string will be zero-terminated if possible. 3405 * If there is no FC_NFKC_Closure string, 3406 * then the buffer will be set to the empty string. 3407 * @param destCapacity <code>==sizeof(dest)</code> 3408 * @param pErrorCode Pointer to a UErrorCode variable. 3409 * @return The length of the string, or 0 if there is no FC_NFKC_Closure string for this character. 3410 * If the destCapacity is less than or equal to the length, then the buffer 3411 * contains the truncated name and the returned length indicates the full 3412 * length of the name. 3413 * The length does not include the zero-termination. 3414 * 3415 * @stable ICU 2.2 3416 */ 3417U_STABLE int32_t U_EXPORT2 3418u_getFC_NFKC_Closure(UChar32 c, UChar *dest, int32_t destCapacity, UErrorCode *pErrorCode); 3419 3420#endif 3421 3422 3423U_CDECL_END 3424 3425#endif /*_UCHAR*/ 3426/*eof*/ 3427