1 /* 2 ********************************************************************** 3 * Copyright (C) 1997-2013, 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 28 U_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 "6.3" 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 */ 161 typedef 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 */ 586 typedef 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 */ 777 typedef 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 */ 841 typedef 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 */ 862 enum 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 /** @stable ICU 2.0 */ 1456 UBLOCK_COUNT = 221, 1457 1458 /** @stable ICU 2.0 */ 1459 UBLOCK_INVALID_CODE=-1 1460 }; 1461 1462 /** @stable ICU 2.0 */ 1463 typedef enum UBlockCode UBlockCode; 1464 1465 /** 1466 * East Asian Width constants. 1467 * 1468 * @see UCHAR_EAST_ASIAN_WIDTH 1469 * @see u_getIntPropertyValue 1470 * @stable ICU 2.2 1471 */ 1472 typedef enum UEastAsianWidth { 1473 /* 1474 * Note: UEastAsianWidth constants are parsed by preparseucd.py. 1475 * It matches lines like 1476 * U_EA_<Unicode East_Asian_Width value name> 1477 */ 1478 1479 U_EA_NEUTRAL, /*[N]*/ 1480 U_EA_AMBIGUOUS, /*[A]*/ 1481 U_EA_HALFWIDTH, /*[H]*/ 1482 U_EA_FULLWIDTH, /*[F]*/ 1483 U_EA_NARROW, /*[Na]*/ 1484 U_EA_WIDE, /*[W]*/ 1485 U_EA_COUNT 1486 } UEastAsianWidth; 1487 1488 /** 1489 * Selector constants for u_charName(). 1490 * u_charName() returns the "modern" name of a 1491 * Unicode character; or the name that was defined in 1492 * Unicode version 1.0, before the Unicode standard merged 1493 * with ISO-10646; or an "extended" name that gives each 1494 * Unicode code point a unique name. 1495 * 1496 * @see u_charName 1497 * @stable ICU 2.0 1498 */ 1499 typedef enum UCharNameChoice { 1500 /** Unicode character name (Name property). @stable ICU 2.0 */ 1501 U_UNICODE_CHAR_NAME, 1502 #ifndef U_HIDE_DEPRECATED_API 1503 /** 1504 * The Unicode_1_Name property value which is of little practical value. 1505 * Beginning with ICU 49, ICU APIs return an empty string for this name choice. 1506 * @deprecated ICU 49 1507 */ 1508 U_UNICODE_10_CHAR_NAME, 1509 #endif /* U_HIDE_DEPRECATED_API */ 1510 /** Standard or synthetic character name. @stable ICU 2.0 */ 1511 U_EXTENDED_CHAR_NAME = U_UNICODE_CHAR_NAME+2, 1512 /** Corrected name from NameAliases.txt. @stable ICU 4.4 */ 1513 U_CHAR_NAME_ALIAS, 1514 /** @stable ICU 2.0 */ 1515 U_CHAR_NAME_CHOICE_COUNT 1516 } UCharNameChoice; 1517 1518 /** 1519 * Selector constants for u_getPropertyName() and 1520 * u_getPropertyValueName(). These selectors are used to choose which 1521 * name is returned for a given property or value. All properties and 1522 * values have a long name. Most have a short name, but some do not. 1523 * Unicode allows for additional names, beyond the long and short 1524 * name, which would be indicated by U_LONG_PROPERTY_NAME + i, where 1525 * i=1, 2,... 1526 * 1527 * @see u_getPropertyName() 1528 * @see u_getPropertyValueName() 1529 * @stable ICU 2.4 1530 */ 1531 typedef enum UPropertyNameChoice { 1532 U_SHORT_PROPERTY_NAME, 1533 U_LONG_PROPERTY_NAME, 1534 U_PROPERTY_NAME_CHOICE_COUNT 1535 } UPropertyNameChoice; 1536 1537 /** 1538 * Decomposition Type constants. 1539 * 1540 * @see UCHAR_DECOMPOSITION_TYPE 1541 * @stable ICU 2.2 1542 */ 1543 typedef enum UDecompositionType { 1544 /* 1545 * Note: UDecompositionType constants are parsed by preparseucd.py. 1546 * It matches lines like 1547 * U_DT_<Unicode Decomposition_Type value name> 1548 */ 1549 1550 U_DT_NONE, /*[none]*/ 1551 U_DT_CANONICAL, /*[can]*/ 1552 U_DT_COMPAT, /*[com]*/ 1553 U_DT_CIRCLE, /*[enc]*/ 1554 U_DT_FINAL, /*[fin]*/ 1555 U_DT_FONT, /*[font]*/ 1556 U_DT_FRACTION, /*[fra]*/ 1557 U_DT_INITIAL, /*[init]*/ 1558 U_DT_ISOLATED, /*[iso]*/ 1559 U_DT_MEDIAL, /*[med]*/ 1560 U_DT_NARROW, /*[nar]*/ 1561 U_DT_NOBREAK, /*[nb]*/ 1562 U_DT_SMALL, /*[sml]*/ 1563 U_DT_SQUARE, /*[sqr]*/ 1564 U_DT_SUB, /*[sub]*/ 1565 U_DT_SUPER, /*[sup]*/ 1566 U_DT_VERTICAL, /*[vert]*/ 1567 U_DT_WIDE, /*[wide]*/ 1568 U_DT_COUNT /* 18 */ 1569 } UDecompositionType; 1570 1571 /** 1572 * Joining Type constants. 1573 * 1574 * @see UCHAR_JOINING_TYPE 1575 * @stable ICU 2.2 1576 */ 1577 typedef enum UJoiningType { 1578 /* 1579 * Note: UJoiningType constants are parsed by preparseucd.py. 1580 * It matches lines like 1581 * U_JT_<Unicode Joining_Type value name> 1582 */ 1583 1584 U_JT_NON_JOINING, /*[U]*/ 1585 U_JT_JOIN_CAUSING, /*[C]*/ 1586 U_JT_DUAL_JOINING, /*[D]*/ 1587 U_JT_LEFT_JOINING, /*[L]*/ 1588 U_JT_RIGHT_JOINING, /*[R]*/ 1589 U_JT_TRANSPARENT, /*[T]*/ 1590 U_JT_COUNT /* 6 */ 1591 } UJoiningType; 1592 1593 /** 1594 * Joining Group constants. 1595 * 1596 * @see UCHAR_JOINING_GROUP 1597 * @stable ICU 2.2 1598 */ 1599 typedef enum UJoiningGroup { 1600 /* 1601 * Note: UJoiningGroup constants are parsed by preparseucd.py. 1602 * It matches lines like 1603 * U_JG_<Unicode Joining_Group value name> 1604 */ 1605 1606 U_JG_NO_JOINING_GROUP, 1607 U_JG_AIN, 1608 U_JG_ALAPH, 1609 U_JG_ALEF, 1610 U_JG_BEH, 1611 U_JG_BETH, 1612 U_JG_DAL, 1613 U_JG_DALATH_RISH, 1614 U_JG_E, 1615 U_JG_FEH, 1616 U_JG_FINAL_SEMKATH, 1617 U_JG_GAF, 1618 U_JG_GAMAL, 1619 U_JG_HAH, 1620 U_JG_TEH_MARBUTA_GOAL, /**< @stable ICU 4.6 */ 1621 U_JG_HAMZA_ON_HEH_GOAL=U_JG_TEH_MARBUTA_GOAL, 1622 U_JG_HE, 1623 U_JG_HEH, 1624 U_JG_HEH_GOAL, 1625 U_JG_HETH, 1626 U_JG_KAF, 1627 U_JG_KAPH, 1628 U_JG_KNOTTED_HEH, 1629 U_JG_LAM, 1630 U_JG_LAMADH, 1631 U_JG_MEEM, 1632 U_JG_MIM, 1633 U_JG_NOON, 1634 U_JG_NUN, 1635 U_JG_PE, 1636 U_JG_QAF, 1637 U_JG_QAPH, 1638 U_JG_REH, 1639 U_JG_REVERSED_PE, 1640 U_JG_SAD, 1641 U_JG_SADHE, 1642 U_JG_SEEN, 1643 U_JG_SEMKATH, 1644 U_JG_SHIN, 1645 U_JG_SWASH_KAF, 1646 U_JG_SYRIAC_WAW, 1647 U_JG_TAH, 1648 U_JG_TAW, 1649 U_JG_TEH_MARBUTA, 1650 U_JG_TETH, 1651 U_JG_WAW, 1652 U_JG_YEH, 1653 U_JG_YEH_BARREE, 1654 U_JG_YEH_WITH_TAIL, 1655 U_JG_YUDH, 1656 U_JG_YUDH_HE, 1657 U_JG_ZAIN, 1658 U_JG_FE, /**< @stable ICU 2.6 */ 1659 U_JG_KHAPH, /**< @stable ICU 2.6 */ 1660 U_JG_ZHAIN, /**< @stable ICU 2.6 */ 1661 U_JG_BURUSHASKI_YEH_BARREE, /**< @stable ICU 4.0 */ 1662 U_JG_FARSI_YEH, /**< @stable ICU 4.4 */ 1663 U_JG_NYA, /**< @stable ICU 4.4 */ 1664 U_JG_ROHINGYA_YEH, /**< @stable ICU 49 */ 1665 U_JG_COUNT 1666 } UJoiningGroup; 1667 1668 /** 1669 * Grapheme Cluster Break constants. 1670 * 1671 * @see UCHAR_GRAPHEME_CLUSTER_BREAK 1672 * @stable ICU 3.4 1673 */ 1674 typedef enum UGraphemeClusterBreak { 1675 /* 1676 * Note: UGraphemeClusterBreak constants are parsed by preparseucd.py. 1677 * It matches lines like 1678 * U_GCB_<Unicode Grapheme_Cluster_Break value name> 1679 */ 1680 1681 U_GCB_OTHER = 0, /*[XX]*/ 1682 U_GCB_CONTROL = 1, /*[CN]*/ 1683 U_GCB_CR = 2, /*[CR]*/ 1684 U_GCB_EXTEND = 3, /*[EX]*/ 1685 U_GCB_L = 4, /*[L]*/ 1686 U_GCB_LF = 5, /*[LF]*/ 1687 U_GCB_LV = 6, /*[LV]*/ 1688 U_GCB_LVT = 7, /*[LVT]*/ 1689 U_GCB_T = 8, /*[T]*/ 1690 U_GCB_V = 9, /*[V]*/ 1691 U_GCB_SPACING_MARK = 10, /*[SM]*/ /* from here on: new in Unicode 5.1/ICU 4.0 */ 1692 U_GCB_PREPEND = 11, /*[PP]*/ 1693 U_GCB_REGIONAL_INDICATOR = 12, /*[RI]*/ /* new in Unicode 6.2/ICU 50 */ 1694 U_GCB_COUNT = 13 1695 } UGraphemeClusterBreak; 1696 1697 /** 1698 * Word Break constants. 1699 * (UWordBreak is a pre-existing enum type in ubrk.h for word break status tags.) 1700 * 1701 * @see UCHAR_WORD_BREAK 1702 * @stable ICU 3.4 1703 */ 1704 typedef enum UWordBreakValues { 1705 /* 1706 * Note: UWordBreakValues constants are parsed by preparseucd.py. 1707 * It matches lines like 1708 * U_WB_<Unicode Word_Break value name> 1709 */ 1710 1711 U_WB_OTHER = 0, /*[XX]*/ 1712 U_WB_ALETTER = 1, /*[LE]*/ 1713 U_WB_FORMAT = 2, /*[FO]*/ 1714 U_WB_KATAKANA = 3, /*[KA]*/ 1715 U_WB_MIDLETTER = 4, /*[ML]*/ 1716 U_WB_MIDNUM = 5, /*[MN]*/ 1717 U_WB_NUMERIC = 6, /*[NU]*/ 1718 U_WB_EXTENDNUMLET = 7, /*[EX]*/ 1719 U_WB_CR = 8, /*[CR]*/ /* from here on: new in Unicode 5.1/ICU 4.0 */ 1720 U_WB_EXTEND = 9, /*[Extend]*/ 1721 U_WB_LF = 10, /*[LF]*/ 1722 U_WB_MIDNUMLET =11, /*[MB]*/ 1723 U_WB_NEWLINE =12, /*[NL]*/ 1724 U_WB_REGIONAL_INDICATOR = 13, /*[RI]*/ /* new in Unicode 6.2/ICU 50 */ 1725 U_WB_HEBREW_LETTER = 14, /*[HL]*/ /* from here on: new in Unicode 6.3/ICU 52 */ 1726 U_WB_SINGLE_QUOTE = 15, /*[SQ]*/ 1727 U_WB_DOUBLE_QUOTE = 16, /*[DQ]*/ 1728 U_WB_COUNT = 17 1729 } UWordBreakValues; 1730 1731 /** 1732 * Sentence Break constants. 1733 * 1734 * @see UCHAR_SENTENCE_BREAK 1735 * @stable ICU 3.4 1736 */ 1737 typedef enum USentenceBreak { 1738 /* 1739 * Note: USentenceBreak constants are parsed by preparseucd.py. 1740 * It matches lines like 1741 * U_SB_<Unicode Sentence_Break value name> 1742 */ 1743 1744 U_SB_OTHER = 0, /*[XX]*/ 1745 U_SB_ATERM = 1, /*[AT]*/ 1746 U_SB_CLOSE = 2, /*[CL]*/ 1747 U_SB_FORMAT = 3, /*[FO]*/ 1748 U_SB_LOWER = 4, /*[LO]*/ 1749 U_SB_NUMERIC = 5, /*[NU]*/ 1750 U_SB_OLETTER = 6, /*[LE]*/ 1751 U_SB_SEP = 7, /*[SE]*/ 1752 U_SB_SP = 8, /*[SP]*/ 1753 U_SB_STERM = 9, /*[ST]*/ 1754 U_SB_UPPER = 10, /*[UP]*/ 1755 U_SB_CR = 11, /*[CR]*/ /* from here on: new in Unicode 5.1/ICU 4.0 */ 1756 U_SB_EXTEND = 12, /*[EX]*/ 1757 U_SB_LF = 13, /*[LF]*/ 1758 U_SB_SCONTINUE = 14, /*[SC]*/ 1759 U_SB_COUNT = 15 1760 } USentenceBreak; 1761 1762 /** 1763 * Line Break constants. 1764 * 1765 * @see UCHAR_LINE_BREAK 1766 * @stable ICU 2.2 1767 */ 1768 typedef enum ULineBreak { 1769 /* 1770 * Note: ULineBreak constants are parsed by preparseucd.py. 1771 * It matches lines like 1772 * U_LB_<Unicode Line_Break value name> 1773 */ 1774 1775 U_LB_UNKNOWN = 0, /*[XX]*/ 1776 U_LB_AMBIGUOUS = 1, /*[AI]*/ 1777 U_LB_ALPHABETIC = 2, /*[AL]*/ 1778 U_LB_BREAK_BOTH = 3, /*[B2]*/ 1779 U_LB_BREAK_AFTER = 4, /*[BA]*/ 1780 U_LB_BREAK_BEFORE = 5, /*[BB]*/ 1781 U_LB_MANDATORY_BREAK = 6, /*[BK]*/ 1782 U_LB_CONTINGENT_BREAK = 7, /*[CB]*/ 1783 U_LB_CLOSE_PUNCTUATION = 8, /*[CL]*/ 1784 U_LB_COMBINING_MARK = 9, /*[CM]*/ 1785 U_LB_CARRIAGE_RETURN = 10, /*[CR]*/ 1786 U_LB_EXCLAMATION = 11, /*[EX]*/ 1787 U_LB_GLUE = 12, /*[GL]*/ 1788 U_LB_HYPHEN = 13, /*[HY]*/ 1789 U_LB_IDEOGRAPHIC = 14, /*[ID]*/ 1790 /** Renamed from the misspelled "inseperable" in Unicode 4.0.1/ICU 3.0 @stable ICU 3.0 */ 1791 U_LB_INSEPARABLE = 15, /*[IN]*/ 1792 U_LB_INSEPERABLE = U_LB_INSEPARABLE, 1793 U_LB_INFIX_NUMERIC = 16, /*[IS]*/ 1794 U_LB_LINE_FEED = 17, /*[LF]*/ 1795 U_LB_NONSTARTER = 18, /*[NS]*/ 1796 U_LB_NUMERIC = 19, /*[NU]*/ 1797 U_LB_OPEN_PUNCTUATION = 20, /*[OP]*/ 1798 U_LB_POSTFIX_NUMERIC = 21, /*[PO]*/ 1799 U_LB_PREFIX_NUMERIC = 22, /*[PR]*/ 1800 U_LB_QUOTATION = 23, /*[QU]*/ 1801 U_LB_COMPLEX_CONTEXT = 24, /*[SA]*/ 1802 U_LB_SURROGATE = 25, /*[SG]*/ 1803 U_LB_SPACE = 26, /*[SP]*/ 1804 U_LB_BREAK_SYMBOLS = 27, /*[SY]*/ 1805 U_LB_ZWSPACE = 28, /*[ZW]*/ 1806 U_LB_NEXT_LINE = 29, /*[NL]*/ /* from here on: new in Unicode 4/ICU 2.6 */ 1807 U_LB_WORD_JOINER = 30, /*[WJ]*/ 1808 U_LB_H2 = 31, /*[H2]*/ /* from here on: new in Unicode 4.1/ICU 3.4 */ 1809 U_LB_H3 = 32, /*[H3]*/ 1810 U_LB_JL = 33, /*[JL]*/ 1811 U_LB_JT = 34, /*[JT]*/ 1812 U_LB_JV = 35, /*[JV]*/ 1813 U_LB_CLOSE_PARENTHESIS = 36, /*[CP]*/ /* new in Unicode 5.2/ICU 4.4 */ 1814 U_LB_CONDITIONAL_JAPANESE_STARTER = 37,/*[CJ]*/ /* new in Unicode 6.1/ICU 49 */ 1815 U_LB_HEBREW_LETTER = 38, /*[HL]*/ /* new in Unicode 6.1/ICU 49 */ 1816 U_LB_REGIONAL_INDICATOR = 39,/*[RI]*/ /* new in Unicode 6.2/ICU 50 */ 1817 U_LB_COUNT = 40 1818 } ULineBreak; 1819 1820 /** 1821 * Numeric Type constants. 1822 * 1823 * @see UCHAR_NUMERIC_TYPE 1824 * @stable ICU 2.2 1825 */ 1826 typedef enum UNumericType { 1827 /* 1828 * Note: UNumericType constants are parsed by preparseucd.py. 1829 * It matches lines like 1830 * U_NT_<Unicode Numeric_Type value name> 1831 */ 1832 1833 U_NT_NONE, /*[None]*/ 1834 U_NT_DECIMAL, /*[de]*/ 1835 U_NT_DIGIT, /*[di]*/ 1836 U_NT_NUMERIC, /*[nu]*/ 1837 U_NT_COUNT 1838 } UNumericType; 1839 1840 /** 1841 * Hangul Syllable Type constants. 1842 * 1843 * @see UCHAR_HANGUL_SYLLABLE_TYPE 1844 * @stable ICU 2.6 1845 */ 1846 typedef enum UHangulSyllableType { 1847 /* 1848 * Note: UHangulSyllableType constants are parsed by preparseucd.py. 1849 * It matches lines like 1850 * U_HST_<Unicode Hangul_Syllable_Type value name> 1851 */ 1852 1853 U_HST_NOT_APPLICABLE, /*[NA]*/ 1854 U_HST_LEADING_JAMO, /*[L]*/ 1855 U_HST_VOWEL_JAMO, /*[V]*/ 1856 U_HST_TRAILING_JAMO, /*[T]*/ 1857 U_HST_LV_SYLLABLE, /*[LV]*/ 1858 U_HST_LVT_SYLLABLE, /*[LVT]*/ 1859 U_HST_COUNT 1860 } UHangulSyllableType; 1861 1862 /** 1863 * Check a binary Unicode property for a code point. 1864 * 1865 * Unicode, especially in version 3.2, defines many more properties than the 1866 * original set in UnicodeData.txt. 1867 * 1868 * The properties APIs are intended to reflect Unicode properties as defined 1869 * in the Unicode Character Database (UCD) and Unicode Technical Reports (UTR). 1870 * For details about the properties see http://www.unicode.org/ucd/ . 1871 * For names of Unicode properties see the UCD file PropertyAliases.txt. 1872 * 1873 * Important: If ICU is built with UCD files from Unicode versions below 3.2, 1874 * then properties marked with "new in Unicode 3.2" are not or not fully available. 1875 * 1876 * @param c Code point to test. 1877 * @param which UProperty selector constant, identifies which binary property to check. 1878 * Must be UCHAR_BINARY_START<=which<UCHAR_BINARY_LIMIT. 1879 * @return TRUE or FALSE according to the binary Unicode property value for c. 1880 * Also FALSE if 'which' is out of bounds or if the Unicode version 1881 * does not have data for the property at all, or not for this code point. 1882 * 1883 * @see UProperty 1884 * @see u_getIntPropertyValue 1885 * @see u_getUnicodeVersion 1886 * @stable ICU 2.1 1887 */ 1888 U_STABLE UBool U_EXPORT2 1889 u_hasBinaryProperty(UChar32 c, UProperty which); 1890 1891 /** 1892 * Check if a code point has the Alphabetic Unicode property. 1893 * Same as u_hasBinaryProperty(c, UCHAR_ALPHABETIC). 1894 * This is different from u_isalpha! 1895 * @param c Code point to test 1896 * @return true if the code point has the Alphabetic Unicode property, false otherwise 1897 * 1898 * @see UCHAR_ALPHABETIC 1899 * @see u_isalpha 1900 * @see u_hasBinaryProperty 1901 * @stable ICU 2.1 1902 */ 1903 U_STABLE UBool U_EXPORT2 1904 u_isUAlphabetic(UChar32 c); 1905 1906 /** 1907 * Check if a code point has the Lowercase Unicode property. 1908 * Same as u_hasBinaryProperty(c, UCHAR_LOWERCASE). 1909 * This is different from u_islower! 1910 * @param c Code point to test 1911 * @return true if the code point has the Lowercase Unicode property, false otherwise 1912 * 1913 * @see UCHAR_LOWERCASE 1914 * @see u_islower 1915 * @see u_hasBinaryProperty 1916 * @stable ICU 2.1 1917 */ 1918 U_STABLE UBool U_EXPORT2 1919 u_isULowercase(UChar32 c); 1920 1921 /** 1922 * Check if a code point has the Uppercase Unicode property. 1923 * Same as u_hasBinaryProperty(c, UCHAR_UPPERCASE). 1924 * This is different from u_isupper! 1925 * @param c Code point to test 1926 * @return true if the code point has the Uppercase Unicode property, false otherwise 1927 * 1928 * @see UCHAR_UPPERCASE 1929 * @see u_isupper 1930 * @see u_hasBinaryProperty 1931 * @stable ICU 2.1 1932 */ 1933 U_STABLE UBool U_EXPORT2 1934 u_isUUppercase(UChar32 c); 1935 1936 /** 1937 * Check if a code point has the White_Space Unicode property. 1938 * Same as u_hasBinaryProperty(c, UCHAR_WHITE_SPACE). 1939 * This is different from both u_isspace and u_isWhitespace! 1940 * 1941 * Note: There are several ICU whitespace functions; please see the uchar.h 1942 * file documentation for a detailed comparison. 1943 * 1944 * @param c Code point to test 1945 * @return true if the code point has the White_Space Unicode property, false otherwise. 1946 * 1947 * @see UCHAR_WHITE_SPACE 1948 * @see u_isWhitespace 1949 * @see u_isspace 1950 * @see u_isJavaSpaceChar 1951 * @see u_hasBinaryProperty 1952 * @stable ICU 2.1 1953 */ 1954 U_STABLE UBool U_EXPORT2 1955 u_isUWhiteSpace(UChar32 c); 1956 1957 /** 1958 * Get the property value for an enumerated or integer Unicode property for a code point. 1959 * Also returns binary and mask property values. 1960 * 1961 * Unicode, especially in version 3.2, defines many more properties than the 1962 * original set in UnicodeData.txt. 1963 * 1964 * The properties APIs are intended to reflect Unicode properties as defined 1965 * in the Unicode Character Database (UCD) and Unicode Technical Reports (UTR). 1966 * For details about the properties see http://www.unicode.org/ . 1967 * For names of Unicode properties see the UCD file PropertyAliases.txt. 1968 * 1969 * Sample usage: 1970 * UEastAsianWidth ea=(UEastAsianWidth)u_getIntPropertyValue(c, UCHAR_EAST_ASIAN_WIDTH); 1971 * UBool b=(UBool)u_getIntPropertyValue(c, UCHAR_IDEOGRAPHIC); 1972 * 1973 * @param c Code point to test. 1974 * @param which UProperty selector constant, identifies which property to check. 1975 * Must be UCHAR_BINARY_START<=which<UCHAR_BINARY_LIMIT 1976 * or UCHAR_INT_START<=which<UCHAR_INT_LIMIT 1977 * or UCHAR_MASK_START<=which<UCHAR_MASK_LIMIT. 1978 * @return Numeric value that is directly the property value or, 1979 * for enumerated properties, corresponds to the numeric value of the enumerated 1980 * constant of the respective property value enumeration type 1981 * (cast to enum type if necessary). 1982 * Returns 0 or 1 (for FALSE/TRUE) for binary Unicode properties. 1983 * Returns a bit-mask for mask properties. 1984 * Returns 0 if 'which' is out of bounds or if the Unicode version 1985 * does not have data for the property at all, or not for this code point. 1986 * 1987 * @see UProperty 1988 * @see u_hasBinaryProperty 1989 * @see u_getIntPropertyMinValue 1990 * @see u_getIntPropertyMaxValue 1991 * @see u_getUnicodeVersion 1992 * @stable ICU 2.2 1993 */ 1994 U_STABLE int32_t U_EXPORT2 1995 u_getIntPropertyValue(UChar32 c, UProperty which); 1996 1997 /** 1998 * Get the minimum value for an enumerated/integer/binary Unicode property. 1999 * Can be used together with u_getIntPropertyMaxValue 2000 * to allocate arrays of UnicodeSet or similar. 2001 * 2002 * @param which UProperty selector constant, identifies which binary property to check. 2003 * Must be UCHAR_BINARY_START<=which<UCHAR_BINARY_LIMIT 2004 * or UCHAR_INT_START<=which<UCHAR_INT_LIMIT. 2005 * @return Minimum value returned by u_getIntPropertyValue for a Unicode property. 2006 * 0 if the property selector is out of range. 2007 * 2008 * @see UProperty 2009 * @see u_hasBinaryProperty 2010 * @see u_getUnicodeVersion 2011 * @see u_getIntPropertyMaxValue 2012 * @see u_getIntPropertyValue 2013 * @stable ICU 2.2 2014 */ 2015 U_STABLE int32_t U_EXPORT2 2016 u_getIntPropertyMinValue(UProperty which); 2017 2018 /** 2019 * Get the maximum value for an enumerated/integer/binary Unicode property. 2020 * Can be used together with u_getIntPropertyMinValue 2021 * to allocate arrays of UnicodeSet or similar. 2022 * 2023 * Examples for min/max values (for Unicode 3.2): 2024 * 2025 * - UCHAR_BIDI_CLASS: 0/18 (U_LEFT_TO_RIGHT/U_BOUNDARY_NEUTRAL) 2026 * - UCHAR_SCRIPT: 0/45 (USCRIPT_COMMON/USCRIPT_TAGBANWA) 2027 * - UCHAR_IDEOGRAPHIC: 0/1 (FALSE/TRUE) 2028 * 2029 * For undefined UProperty constant values, min/max values will be 0/-1. 2030 * 2031 * @param which UProperty selector constant, identifies which binary property to check. 2032 * Must be UCHAR_BINARY_START<=which<UCHAR_BINARY_LIMIT 2033 * or UCHAR_INT_START<=which<UCHAR_INT_LIMIT. 2034 * @return Maximum value returned by u_getIntPropertyValue for a Unicode property. 2035 * <=0 if the property selector is out of range. 2036 * 2037 * @see UProperty 2038 * @see u_hasBinaryProperty 2039 * @see u_getUnicodeVersion 2040 * @see u_getIntPropertyMaxValue 2041 * @see u_getIntPropertyValue 2042 * @stable ICU 2.2 2043 */ 2044 U_STABLE int32_t U_EXPORT2 2045 u_getIntPropertyMaxValue(UProperty which); 2046 2047 /** 2048 * Get the numeric value for a Unicode code point as defined in the 2049 * Unicode Character Database. 2050 * 2051 * A "double" return type is necessary because 2052 * some numeric values are fractions, negative, or too large for int32_t. 2053 * 2054 * For characters without any numeric values in the Unicode Character Database, 2055 * this function will return U_NO_NUMERIC_VALUE. 2056 * Note: This is different from the Unicode Standard which specifies NaN as the default value. 2057 * (NaN is not available on all platforms.) 2058 * 2059 * Similar to java.lang.Character.getNumericValue(), but u_getNumericValue() 2060 * also supports negative values, large values, and fractions, 2061 * while Java's getNumericValue() returns values 10..35 for ASCII letters. 2062 * 2063 * @param c Code point to get the numeric value for. 2064 * @return Numeric value of c, or U_NO_NUMERIC_VALUE if none is defined. 2065 * 2066 * @see U_NO_NUMERIC_VALUE 2067 * @stable ICU 2.2 2068 */ 2069 U_STABLE double U_EXPORT2 2070 u_getNumericValue(UChar32 c); 2071 2072 /** 2073 * Special value that is returned by u_getNumericValue when 2074 * no numeric value is defined for a code point. 2075 * 2076 * @see u_getNumericValue 2077 * @stable ICU 2.2 2078 */ 2079 #define U_NO_NUMERIC_VALUE ((double)-123456789.) 2080 2081 /** 2082 * Determines whether the specified code point has the general category "Ll" 2083 * (lowercase letter). 2084 * 2085 * Same as java.lang.Character.isLowerCase(). 2086 * 2087 * This misses some characters that are also lowercase but 2088 * have a different general category value. 2089 * In order to include those, use UCHAR_LOWERCASE. 2090 * 2091 * In addition to being equivalent to a Java function, this also serves 2092 * as a C/POSIX migration function. 2093 * See the comments about C/POSIX character classification functions in the 2094 * documentation at the top of this header file. 2095 * 2096 * @param c the code point to be tested 2097 * @return TRUE if the code point is an Ll lowercase letter 2098 * 2099 * @see UCHAR_LOWERCASE 2100 * @see u_isupper 2101 * @see u_istitle 2102 * @stable ICU 2.0 2103 */ 2104 U_STABLE UBool U_EXPORT2 2105 u_islower(UChar32 c); 2106 2107 /** 2108 * Determines whether the specified code point has the general category "Lu" 2109 * (uppercase letter). 2110 * 2111 * Same as java.lang.Character.isUpperCase(). 2112 * 2113 * This misses some characters that are also uppercase but 2114 * have a different general category value. 2115 * In order to include those, use UCHAR_UPPERCASE. 2116 * 2117 * In addition to being equivalent to a Java function, this also serves 2118 * as a C/POSIX migration function. 2119 * See the comments about C/POSIX character classification functions in the 2120 * documentation at the top of this header file. 2121 * 2122 * @param c the code point to be tested 2123 * @return TRUE if the code point is an Lu uppercase letter 2124 * 2125 * @see UCHAR_UPPERCASE 2126 * @see u_islower 2127 * @see u_istitle 2128 * @see u_tolower 2129 * @stable ICU 2.0 2130 */ 2131 U_STABLE UBool U_EXPORT2 2132 u_isupper(UChar32 c); 2133 2134 /** 2135 * Determines whether the specified code point is a titlecase letter. 2136 * True for general category "Lt" (titlecase letter). 2137 * 2138 * Same as java.lang.Character.isTitleCase(). 2139 * 2140 * @param c the code point to be tested 2141 * @return TRUE if the code point is an Lt titlecase letter 2142 * 2143 * @see u_isupper 2144 * @see u_islower 2145 * @see u_totitle 2146 * @stable ICU 2.0 2147 */ 2148 U_STABLE UBool U_EXPORT2 2149 u_istitle(UChar32 c); 2150 2151 /** 2152 * Determines whether the specified code point is a digit character according to Java. 2153 * True for characters with general category "Nd" (decimal digit numbers). 2154 * Beginning with Unicode 4, this is the same as 2155 * testing for the Numeric_Type of Decimal. 2156 * 2157 * Same as java.lang.Character.isDigit(). 2158 * 2159 * In addition to being equivalent to a Java function, this also serves 2160 * as a C/POSIX migration function. 2161 * See the comments about C/POSIX character classification functions in the 2162 * documentation at the top of this header file. 2163 * 2164 * @param c the code point to be tested 2165 * @return TRUE if the code point is a digit character according to Character.isDigit() 2166 * 2167 * @stable ICU 2.0 2168 */ 2169 U_STABLE UBool U_EXPORT2 2170 u_isdigit(UChar32 c); 2171 2172 /** 2173 * Determines whether the specified code point is a letter character. 2174 * True for general categories "L" (letters). 2175 * 2176 * Same as java.lang.Character.isLetter(). 2177 * 2178 * In addition to being equivalent to a Java function, this also serves 2179 * as a C/POSIX migration function. 2180 * See the comments about C/POSIX character classification functions in the 2181 * documentation at the top of this header file. 2182 * 2183 * @param c the code point to be tested 2184 * @return TRUE if the code point is a letter character 2185 * 2186 * @see u_isdigit 2187 * @see u_isalnum 2188 * @stable ICU 2.0 2189 */ 2190 U_STABLE UBool U_EXPORT2 2191 u_isalpha(UChar32 c); 2192 2193 /** 2194 * Determines whether the specified code point is an alphanumeric character 2195 * (letter or digit) according to Java. 2196 * True for characters with general categories 2197 * "L" (letters) and "Nd" (decimal digit numbers). 2198 * 2199 * Same as java.lang.Character.isLetterOrDigit(). 2200 * 2201 * In addition to being equivalent to a Java function, this also serves 2202 * as a C/POSIX migration function. 2203 * See the comments about C/POSIX character classification functions in the 2204 * documentation at the top of this header file. 2205 * 2206 * @param c the code point to be tested 2207 * @return TRUE if the code point is an alphanumeric character according to Character.isLetterOrDigit() 2208 * 2209 * @stable ICU 2.0 2210 */ 2211 U_STABLE UBool U_EXPORT2 2212 u_isalnum(UChar32 c); 2213 2214 /** 2215 * Determines whether the specified code point is a hexadecimal digit. 2216 * This is equivalent to u_digit(c, 16)>=0. 2217 * True for characters with general category "Nd" (decimal digit numbers) 2218 * as well as Latin letters a-f and A-F in both ASCII and Fullwidth ASCII. 2219 * (That is, for letters with code points 2220 * 0041..0046, 0061..0066, FF21..FF26, FF41..FF46.) 2221 * 2222 * In order to narrow the definition of hexadecimal digits to only ASCII 2223 * characters, use (c<=0x7f && u_isxdigit(c)). 2224 * 2225 * This is a C/POSIX migration function. 2226 * See the comments about C/POSIX character classification functions in the 2227 * documentation at the top of this header file. 2228 * 2229 * @param c the code point to be tested 2230 * @return TRUE if the code point is a hexadecimal digit 2231 * 2232 * @stable ICU 2.6 2233 */ 2234 U_STABLE UBool U_EXPORT2 2235 u_isxdigit(UChar32 c); 2236 2237 /** 2238 * Determines whether the specified code point is a punctuation character. 2239 * True for characters with general categories "P" (punctuation). 2240 * 2241 * This is a C/POSIX migration function. 2242 * See the comments about C/POSIX character classification functions in the 2243 * documentation at the top of this header file. 2244 * 2245 * @param c the code point to be tested 2246 * @return TRUE if the code point is a punctuation character 2247 * 2248 * @stable ICU 2.6 2249 */ 2250 U_STABLE UBool U_EXPORT2 2251 u_ispunct(UChar32 c); 2252 2253 /** 2254 * Determines whether the specified code point is a "graphic" character 2255 * (printable, excluding spaces). 2256 * TRUE for all characters except those with general categories 2257 * "Cc" (control codes), "Cf" (format controls), "Cs" (surrogates), 2258 * "Cn" (unassigned), and "Z" (separators). 2259 * 2260 * This is a C/POSIX migration function. 2261 * See the comments about C/POSIX character classification functions in the 2262 * documentation at the top of this header file. 2263 * 2264 * @param c the code point to be tested 2265 * @return TRUE if the code point is a "graphic" character 2266 * 2267 * @stable ICU 2.6 2268 */ 2269 U_STABLE UBool U_EXPORT2 2270 u_isgraph(UChar32 c); 2271 2272 /** 2273 * Determines whether the specified code point is a "blank" or "horizontal space", 2274 * a character that visibly separates words on a line. 2275 * The following are equivalent definitions: 2276 * 2277 * TRUE for Unicode White_Space characters except for "vertical space controls" 2278 * where "vertical space controls" are the following characters: 2279 * U+000A (LF) U+000B (VT) U+000C (FF) U+000D (CR) U+0085 (NEL) U+2028 (LS) U+2029 (PS) 2280 * 2281 * same as 2282 * 2283 * TRUE for U+0009 (TAB) and characters with general category "Zs" (space separators) 2284 * except Zero Width Space (ZWSP, U+200B). 2285 * 2286 * Note: There are several ICU whitespace functions; please see the uchar.h 2287 * file documentation for a detailed comparison. 2288 * 2289 * This is a C/POSIX migration function. 2290 * See the comments about C/POSIX character classification functions in the 2291 * documentation at the top of this header file. 2292 * 2293 * @param c the code point to be tested 2294 * @return TRUE if the code point is a "blank" 2295 * 2296 * @stable ICU 2.6 2297 */ 2298 U_STABLE UBool U_EXPORT2 2299 u_isblank(UChar32 c); 2300 2301 /** 2302 * Determines whether the specified code point is "defined", 2303 * which usually means that it is assigned a character. 2304 * True for general categories other than "Cn" (other, not assigned), 2305 * i.e., true for all code points mentioned in UnicodeData.txt. 2306 * 2307 * Note that non-character code points (e.g., U+FDD0) are not "defined" 2308 * (they are Cn), but surrogate code points are "defined" (Cs). 2309 * 2310 * Same as java.lang.Character.isDefined(). 2311 * 2312 * @param c the code point to be tested 2313 * @return TRUE if the code point is assigned a character 2314 * 2315 * @see u_isdigit 2316 * @see u_isalpha 2317 * @see u_isalnum 2318 * @see u_isupper 2319 * @see u_islower 2320 * @see u_istitle 2321 * @stable ICU 2.0 2322 */ 2323 U_STABLE UBool U_EXPORT2 2324 u_isdefined(UChar32 c); 2325 2326 /** 2327 * Determines if the specified character is a space character or not. 2328 * 2329 * Note: There are several ICU whitespace functions; please see the uchar.h 2330 * file documentation for a detailed comparison. 2331 * 2332 * This is a C/POSIX migration function. 2333 * See the comments about C/POSIX character classification functions in the 2334 * documentation at the top of this header file. 2335 * 2336 * @param c the character to be tested 2337 * @return true if the character is a space character; false otherwise. 2338 * 2339 * @see u_isJavaSpaceChar 2340 * @see u_isWhitespace 2341 * @see u_isUWhiteSpace 2342 * @stable ICU 2.0 2343 */ 2344 U_STABLE UBool U_EXPORT2 2345 u_isspace(UChar32 c); 2346 2347 /** 2348 * Determine if the specified code point is a space character according to Java. 2349 * True for characters with general categories "Z" (separators), 2350 * which does not include control codes (e.g., TAB or Line Feed). 2351 * 2352 * Same as java.lang.Character.isSpaceChar(). 2353 * 2354 * Note: There are several ICU whitespace functions; please see the uchar.h 2355 * file documentation for a detailed comparison. 2356 * 2357 * @param c the code point to be tested 2358 * @return TRUE if the code point is a space character according to Character.isSpaceChar() 2359 * 2360 * @see u_isspace 2361 * @see u_isWhitespace 2362 * @see u_isUWhiteSpace 2363 * @stable ICU 2.6 2364 */ 2365 U_STABLE UBool U_EXPORT2 2366 u_isJavaSpaceChar(UChar32 c); 2367 2368 /** 2369 * Determines if the specified code point is a whitespace character according to Java/ICU. 2370 * A character is considered to be a Java whitespace character if and only 2371 * if it satisfies one of the following criteria: 2372 * 2373 * - It is a Unicode Separator character (categories "Z" = "Zs" or "Zl" or "Zp"), but is not 2374 * also a non-breaking space (U+00A0 NBSP or U+2007 Figure Space or U+202F Narrow NBSP). 2375 * - It is U+0009 HORIZONTAL TABULATION. 2376 * - It is U+000A LINE FEED. 2377 * - It is U+000B VERTICAL TABULATION. 2378 * - It is U+000C FORM FEED. 2379 * - It is U+000D CARRIAGE RETURN. 2380 * - It is U+001C FILE SEPARATOR. 2381 * - It is U+001D GROUP SEPARATOR. 2382 * - It is U+001E RECORD SEPARATOR. 2383 * - It is U+001F UNIT SEPARATOR. 2384 * 2385 * This API tries to sync with the semantics of Java's 2386 * java.lang.Character.isWhitespace(), but it may not return 2387 * the exact same results because of the Unicode version 2388 * difference. 2389 * 2390 * Note: Unicode 4.0.1 changed U+200B ZERO WIDTH SPACE from a Space Separator (Zs) 2391 * to a Format Control (Cf). Since then, isWhitespace(0x200b) returns false. 2392 * See http://www.unicode.org/versions/Unicode4.0.1/ 2393 * 2394 * Note: There are several ICU whitespace functions; please see the uchar.h 2395 * file documentation for a detailed comparison. 2396 * 2397 * @param c the code point to be tested 2398 * @return TRUE if the code point is a whitespace character according to Java/ICU 2399 * 2400 * @see u_isspace 2401 * @see u_isJavaSpaceChar 2402 * @see u_isUWhiteSpace 2403 * @stable ICU 2.0 2404 */ 2405 U_STABLE UBool U_EXPORT2 2406 u_isWhitespace(UChar32 c); 2407 2408 /** 2409 * Determines whether the specified code point is a control character 2410 * (as defined by this function). 2411 * A control character is one of the following: 2412 * - ISO 8-bit control character (U+0000..U+001f and U+007f..U+009f) 2413 * - U_CONTROL_CHAR (Cc) 2414 * - U_FORMAT_CHAR (Cf) 2415 * - U_LINE_SEPARATOR (Zl) 2416 * - U_PARAGRAPH_SEPARATOR (Zp) 2417 * 2418 * This is a C/POSIX migration function. 2419 * See the comments about C/POSIX character classification functions in the 2420 * documentation at the top of this header file. 2421 * 2422 * @param c the code point to be tested 2423 * @return TRUE if the code point is a control character 2424 * 2425 * @see UCHAR_DEFAULT_IGNORABLE_CODE_POINT 2426 * @see u_isprint 2427 * @stable ICU 2.0 2428 */ 2429 U_STABLE UBool U_EXPORT2 2430 u_iscntrl(UChar32 c); 2431 2432 /** 2433 * Determines whether the specified code point is an ISO control code. 2434 * True for U+0000..U+001f and U+007f..U+009f (general category "Cc"). 2435 * 2436 * Same as java.lang.Character.isISOControl(). 2437 * 2438 * @param c the code point to be tested 2439 * @return TRUE if the code point is an ISO control code 2440 * 2441 * @see u_iscntrl 2442 * @stable ICU 2.6 2443 */ 2444 U_STABLE UBool U_EXPORT2 2445 u_isISOControl(UChar32 c); 2446 2447 /** 2448 * Determines whether the specified code point is a printable character. 2449 * True for general categories <em>other</em> than "C" (controls). 2450 * 2451 * This is a C/POSIX migration function. 2452 * See the comments about C/POSIX character classification functions in the 2453 * documentation at the top of this header file. 2454 * 2455 * @param c the code point to be tested 2456 * @return TRUE if the code point is a printable character 2457 * 2458 * @see UCHAR_DEFAULT_IGNORABLE_CODE_POINT 2459 * @see u_iscntrl 2460 * @stable ICU 2.0 2461 */ 2462 U_STABLE UBool U_EXPORT2 2463 u_isprint(UChar32 c); 2464 2465 /** 2466 * Determines whether the specified code point is a base character. 2467 * True for general categories "L" (letters), "N" (numbers), 2468 * "Mc" (spacing combining marks), and "Me" (enclosing marks). 2469 * 2470 * Note that this is different from the Unicode definition in 2471 * chapter 3.5, conformance clause D13, 2472 * which defines base characters to be all characters (not Cn) 2473 * that do not graphically combine with preceding characters (M) 2474 * and that are neither control (Cc) or format (Cf) characters. 2475 * 2476 * @param c the code point to be tested 2477 * @return TRUE if the code point is a base character according to this function 2478 * 2479 * @see u_isalpha 2480 * @see u_isdigit 2481 * @stable ICU 2.0 2482 */ 2483 U_STABLE UBool U_EXPORT2 2484 u_isbase(UChar32 c); 2485 2486 /** 2487 * Returns the bidirectional category value for the code point, 2488 * which is used in the Unicode bidirectional algorithm 2489 * (UAX #9 http://www.unicode.org/reports/tr9/). 2490 * Note that some <em>unassigned</em> code points have bidi values 2491 * of R or AL because they are in blocks that are reserved 2492 * for Right-To-Left scripts. 2493 * 2494 * Same as java.lang.Character.getDirectionality() 2495 * 2496 * @param c the code point to be tested 2497 * @return the bidirectional category (UCharDirection) value 2498 * 2499 * @see UCharDirection 2500 * @stable ICU 2.0 2501 */ 2502 U_STABLE UCharDirection U_EXPORT2 2503 u_charDirection(UChar32 c); 2504 2505 /** 2506 * Determines whether the code point has the Bidi_Mirrored property. 2507 * This property is set for characters that are commonly used in 2508 * Right-To-Left contexts and need to be displayed with a "mirrored" 2509 * glyph. 2510 * 2511 * Same as java.lang.Character.isMirrored(). 2512 * Same as UCHAR_BIDI_MIRRORED 2513 * 2514 * @param c the code point to be tested 2515 * @return TRUE if the character has the Bidi_Mirrored property 2516 * 2517 * @see UCHAR_BIDI_MIRRORED 2518 * @stable ICU 2.0 2519 */ 2520 U_STABLE UBool U_EXPORT2 2521 u_isMirrored(UChar32 c); 2522 2523 /** 2524 * Maps the specified character to a "mirror-image" character. 2525 * For characters with the Bidi_Mirrored property, implementations 2526 * sometimes need a "poor man's" mapping to another Unicode 2527 * character (code point) such that the default glyph may serve 2528 * as the mirror-image of the default glyph of the specified 2529 * character. This is useful for text conversion to and from 2530 * codepages with visual order, and for displays without glyph 2531 * selection capabilities. 2532 * 2533 * @param c the code point to be mapped 2534 * @return another Unicode code point that may serve as a mirror-image 2535 * substitute, or c itself if there is no such mapping or c 2536 * does not have the Bidi_Mirrored property 2537 * 2538 * @see UCHAR_BIDI_MIRRORED 2539 * @see u_isMirrored 2540 * @stable ICU 2.0 2541 */ 2542 U_STABLE UChar32 U_EXPORT2 2543 u_charMirror(UChar32 c); 2544 2545 /** 2546 * Maps the specified character to its paired bracket character. 2547 * For Bidi_Paired_Bracket_Type!=None, this is the same as u_charMirror(). 2548 * Otherwise c itself is returned. 2549 * See http://www.unicode.org/reports/tr9/ 2550 * 2551 * @param c the code point to be mapped 2552 * @return the paired bracket code point, 2553 * or c itself if there is no such mapping 2554 * (Bidi_Paired_Bracket_Type=None) 2555 * 2556 * @see UCHAR_BIDI_PAIRED_BRACKET 2557 * @see UCHAR_BIDI_PAIRED_BRACKET_TYPE 2558 * @see u_charMirror 2559 * @stable ICU 52 2560 */ 2561 U_STABLE UChar32 U_EXPORT2 2562 u_getBidiPairedBracket(UChar32 c); 2563 2564 /** 2565 * Returns the general category value for the code point. 2566 * 2567 * Same as java.lang.Character.getType(). 2568 * 2569 * @param c the code point to be tested 2570 * @return the general category (UCharCategory) value 2571 * 2572 * @see UCharCategory 2573 * @stable ICU 2.0 2574 */ 2575 U_STABLE int8_t U_EXPORT2 2576 u_charType(UChar32 c); 2577 2578 /** 2579 * Get a single-bit bit set for the general category of a character. 2580 * This bit set can be compared bitwise with U_GC_SM_MASK, U_GC_L_MASK, etc. 2581 * Same as U_MASK(u_charType(c)). 2582 * 2583 * @param c the code point to be tested 2584 * @return a single-bit mask corresponding to the general category (UCharCategory) value 2585 * 2586 * @see u_charType 2587 * @see UCharCategory 2588 * @see U_GC_CN_MASK 2589 * @stable ICU 2.1 2590 */ 2591 #define U_GET_GC_MASK(c) U_MASK(u_charType(c)) 2592 2593 /** 2594 * Callback from u_enumCharTypes(), is called for each contiguous range 2595 * of code points c (where start<=c<limit) 2596 * with the same Unicode general category ("character type"). 2597 * 2598 * The callback function can stop the enumeration by returning FALSE. 2599 * 2600 * @param context an opaque pointer, as passed into utrie_enum() 2601 * @param start the first code point in a contiguous range with value 2602 * @param limit one past the last code point in a contiguous range with value 2603 * @param type the general category for all code points in [start..limit[ 2604 * @return FALSE to stop the enumeration 2605 * 2606 * @stable ICU 2.1 2607 * @see UCharCategory 2608 * @see u_enumCharTypes 2609 */ 2610 typedef UBool U_CALLCONV 2611 UCharEnumTypeRange(const void *context, UChar32 start, UChar32 limit, UCharCategory type); 2612 2613 /** 2614 * Enumerate efficiently all code points with their Unicode general categories. 2615 * 2616 * This is useful for building data structures (e.g., UnicodeSet's), 2617 * for enumerating all assigned code points (type!=U_UNASSIGNED), etc. 2618 * 2619 * For each contiguous range of code points with a given general category ("character type"), 2620 * the UCharEnumTypeRange function is called. 2621 * Adjacent ranges have different types. 2622 * The Unicode Standard guarantees that the numeric value of the type is 0..31. 2623 * 2624 * @param enumRange a pointer to a function that is called for each contiguous range 2625 * of code points with the same general category 2626 * @param context an opaque pointer that is passed on to the callback function 2627 * 2628 * @stable ICU 2.1 2629 * @see UCharCategory 2630 * @see UCharEnumTypeRange 2631 */ 2632 U_STABLE void U_EXPORT2 2633 u_enumCharTypes(UCharEnumTypeRange *enumRange, const void *context); 2634 2635 #if !UCONFIG_NO_NORMALIZATION 2636 2637 /** 2638 * Returns the combining class of the code point as specified in UnicodeData.txt. 2639 * 2640 * @param c the code point of the character 2641 * @return the combining class of the character 2642 * @stable ICU 2.0 2643 */ 2644 U_STABLE uint8_t U_EXPORT2 2645 u_getCombiningClass(UChar32 c); 2646 2647 #endif 2648 2649 /** 2650 * Returns the decimal digit value of a decimal digit character. 2651 * Such characters have the general category "Nd" (decimal digit numbers) 2652 * and a Numeric_Type of Decimal. 2653 * 2654 * Unlike ICU releases before 2.6, no digit values are returned for any 2655 * Han characters because Han number characters are often used with a special 2656 * Chinese-style number format (with characters for powers of 10 in between) 2657 * instead of in decimal-positional notation. 2658 * Unicode 4 explicitly assigns Han number characters the Numeric_Type 2659 * Numeric instead of Decimal. 2660 * See Jitterbug 1483 for more details. 2661 * 2662 * Use u_getIntPropertyValue(c, UCHAR_NUMERIC_TYPE) and u_getNumericValue() 2663 * for complete numeric Unicode properties. 2664 * 2665 * @param c the code point for which to get the decimal digit value 2666 * @return the decimal digit value of c, 2667 * or -1 if c is not a decimal digit character 2668 * 2669 * @see u_getNumericValue 2670 * @stable ICU 2.0 2671 */ 2672 U_STABLE int32_t U_EXPORT2 2673 u_charDigitValue(UChar32 c); 2674 2675 /** 2676 * Returns the Unicode allocation block that contains the character. 2677 * 2678 * @param c the code point to be tested 2679 * @return the block value (UBlockCode) for c 2680 * 2681 * @see UBlockCode 2682 * @stable ICU 2.0 2683 */ 2684 U_STABLE UBlockCode U_EXPORT2 2685 ublock_getCode(UChar32 c); 2686 2687 /** 2688 * Retrieve the name of a Unicode character. 2689 * Depending on <code>nameChoice</code>, the character name written 2690 * into the buffer is the "modern" name or the name that was defined 2691 * in Unicode version 1.0. 2692 * The name contains only "invariant" characters 2693 * like A-Z, 0-9, space, and '-'. 2694 * Unicode 1.0 names are only retrieved if they are different from the modern 2695 * names and if the data file contains the data for them. gennames may or may 2696 * not be called with a command line option to include 1.0 names in unames.dat. 2697 * 2698 * @param code The character (code point) for which to get the name. 2699 * It must be <code>0<=code<=0x10ffff</code>. 2700 * @param nameChoice Selector for which name to get. 2701 * @param buffer Destination address for copying the name. 2702 * The name will always be zero-terminated. 2703 * If there is no name, then the buffer will be set to the empty string. 2704 * @param bufferLength <code>==sizeof(buffer)</code> 2705 * @param pErrorCode Pointer to a UErrorCode variable; 2706 * check for <code>U_SUCCESS()</code> after <code>u_charName()</code> 2707 * returns. 2708 * @return The length of the name, or 0 if there is no name for this character. 2709 * If the bufferLength is less than or equal to the length, then the buffer 2710 * contains the truncated name and the returned length indicates the full 2711 * length of the name. 2712 * The length does not include the zero-termination. 2713 * 2714 * @see UCharNameChoice 2715 * @see u_charFromName 2716 * @see u_enumCharNames 2717 * @stable ICU 2.0 2718 */ 2719 U_STABLE int32_t U_EXPORT2 2720 u_charName(UChar32 code, UCharNameChoice nameChoice, 2721 char *buffer, int32_t bufferLength, 2722 UErrorCode *pErrorCode); 2723 2724 #ifndef U_HIDE_DEPRECATED_API 2725 /** 2726 * Returns an empty string. 2727 * Used to return the ISO 10646 comment for a character. 2728 * The Unicode ISO_Comment property is deprecated and has no values. 2729 * 2730 * @param c The character (code point) for which to get the ISO comment. 2731 * It must be <code>0<=c<=0x10ffff</code>. 2732 * @param dest Destination address for copying the comment. 2733 * The comment will be zero-terminated if possible. 2734 * If there is no comment, then the buffer will be set to the empty string. 2735 * @param destCapacity <code>==sizeof(dest)</code> 2736 * @param pErrorCode Pointer to a UErrorCode variable; 2737 * check for <code>U_SUCCESS()</code> after <code>u_getISOComment()</code> 2738 * returns. 2739 * @return 0 2740 * 2741 * @deprecated ICU 49 2742 */ 2743 U_STABLE int32_t U_EXPORT2 2744 u_getISOComment(UChar32 c, 2745 char *dest, int32_t destCapacity, 2746 UErrorCode *pErrorCode); 2747 #endif /* U_HIDE_DEPRECATED_API */ 2748 2749 /** 2750 * Find a Unicode character by its name and return its code point value. 2751 * The name is matched exactly and completely. 2752 * If the name does not correspond to a code point, <i>pErrorCode</i> 2753 * is set to <code>U_INVALID_CHAR_FOUND</code>. 2754 * A Unicode 1.0 name is matched only if it differs from the modern name. 2755 * Unicode names are all uppercase. Extended names are lowercase followed 2756 * by an uppercase hexadecimal number, and within angle brackets. 2757 * 2758 * @param nameChoice Selector for which name to match. 2759 * @param name The name to match. 2760 * @param pErrorCode Pointer to a UErrorCode variable 2761 * @return The Unicode value of the code point with the given name, 2762 * or an undefined value if there is no such code point. 2763 * 2764 * @see UCharNameChoice 2765 * @see u_charName 2766 * @see u_enumCharNames 2767 * @stable ICU 1.7 2768 */ 2769 U_STABLE UChar32 U_EXPORT2 2770 u_charFromName(UCharNameChoice nameChoice, 2771 const char *name, 2772 UErrorCode *pErrorCode); 2773 2774 /** 2775 * Type of a callback function for u_enumCharNames() that gets called 2776 * for each Unicode character with the code point value and 2777 * the character name. 2778 * If such a function returns FALSE, then the enumeration is stopped. 2779 * 2780 * @param context The context pointer that was passed to u_enumCharNames(). 2781 * @param code The Unicode code point for the character with this name. 2782 * @param nameChoice Selector for which kind of names is enumerated. 2783 * @param name The character's name, zero-terminated. 2784 * @param length The length of the name. 2785 * @return TRUE if the enumeration should continue, FALSE to stop it. 2786 * 2787 * @see UCharNameChoice 2788 * @see u_enumCharNames 2789 * @stable ICU 1.7 2790 */ 2791 typedef UBool U_CALLCONV UEnumCharNamesFn(void *context, 2792 UChar32 code, 2793 UCharNameChoice nameChoice, 2794 const char *name, 2795 int32_t length); 2796 2797 /** 2798 * Enumerate all assigned Unicode characters between the start and limit 2799 * code points (start inclusive, limit exclusive) and call a function 2800 * for each, passing the code point value and the character name. 2801 * For Unicode 1.0 names, only those are enumerated that differ from the 2802 * modern names. 2803 * 2804 * @param start The first code point in the enumeration range. 2805 * @param limit One more than the last code point in the enumeration range 2806 * (the first one after the range). 2807 * @param fn The function that is to be called for each character name. 2808 * @param context An arbitrary pointer that is passed to the function. 2809 * @param nameChoice Selector for which kind of names to enumerate. 2810 * @param pErrorCode Pointer to a UErrorCode variable 2811 * 2812 * @see UCharNameChoice 2813 * @see UEnumCharNamesFn 2814 * @see u_charName 2815 * @see u_charFromName 2816 * @stable ICU 1.7 2817 */ 2818 U_STABLE void U_EXPORT2 2819 u_enumCharNames(UChar32 start, UChar32 limit, 2820 UEnumCharNamesFn *fn, 2821 void *context, 2822 UCharNameChoice nameChoice, 2823 UErrorCode *pErrorCode); 2824 2825 /** 2826 * Return the Unicode name for a given property, as given in the 2827 * Unicode database file PropertyAliases.txt. 2828 * 2829 * In addition, this function maps the property 2830 * UCHAR_GENERAL_CATEGORY_MASK to the synthetic names "gcm" / 2831 * "General_Category_Mask". These names are not in 2832 * PropertyAliases.txt. 2833 * 2834 * @param property UProperty selector other than UCHAR_INVALID_CODE. 2835 * If out of range, NULL is returned. 2836 * 2837 * @param nameChoice selector for which name to get. If out of range, 2838 * NULL is returned. All properties have a long name. Most 2839 * have a short name, but some do not. Unicode allows for 2840 * additional names; if present these will be returned by 2841 * U_LONG_PROPERTY_NAME + i, where i=1, 2,... 2842 * 2843 * @return a pointer to the name, or NULL if either the 2844 * property or the nameChoice is out of range. If a given 2845 * nameChoice returns NULL, then all larger values of 2846 * nameChoice will return NULL, with one exception: if NULL is 2847 * returned for U_SHORT_PROPERTY_NAME, then 2848 * U_LONG_PROPERTY_NAME (and higher) may still return a 2849 * non-NULL value. The returned pointer is valid until 2850 * u_cleanup() is called. 2851 * 2852 * @see UProperty 2853 * @see UPropertyNameChoice 2854 * @stable ICU 2.4 2855 */ 2856 U_STABLE const char* U_EXPORT2 2857 u_getPropertyName(UProperty property, 2858 UPropertyNameChoice nameChoice); 2859 2860 /** 2861 * Return the UProperty enum for a given property name, as specified 2862 * in the Unicode database file PropertyAliases.txt. Short, long, and 2863 * any other variants are recognized. 2864 * 2865 * In addition, this function maps the synthetic names "gcm" / 2866 * "General_Category_Mask" to the property 2867 * UCHAR_GENERAL_CATEGORY_MASK. These names are not in 2868 * PropertyAliases.txt. 2869 * 2870 * @param alias the property name to be matched. The name is compared 2871 * using "loose matching" as described in PropertyAliases.txt. 2872 * 2873 * @return a UProperty enum, or UCHAR_INVALID_CODE if the given name 2874 * does not match any property. 2875 * 2876 * @see UProperty 2877 * @stable ICU 2.4 2878 */ 2879 U_STABLE UProperty U_EXPORT2 2880 u_getPropertyEnum(const char* alias); 2881 2882 /** 2883 * Return the Unicode name for a given property value, as given in the 2884 * Unicode database file PropertyValueAliases.txt. 2885 * 2886 * Note: Some of the names in PropertyValueAliases.txt can only be 2887 * retrieved using UCHAR_GENERAL_CATEGORY_MASK, not 2888 * UCHAR_GENERAL_CATEGORY. These include: "C" / "Other", "L" / 2889 * "Letter", "LC" / "Cased_Letter", "M" / "Mark", "N" / "Number", "P" 2890 * / "Punctuation", "S" / "Symbol", and "Z" / "Separator". 2891 * 2892 * @param property UProperty selector constant. 2893 * Must be UCHAR_BINARY_START<=which<UCHAR_BINARY_LIMIT 2894 * or UCHAR_INT_START<=which<UCHAR_INT_LIMIT 2895 * or UCHAR_MASK_START<=which<UCHAR_MASK_LIMIT. 2896 * If out of range, NULL is returned. 2897 * 2898 * @param value selector for a value for the given property. If out 2899 * of range, NULL is returned. In general, valid values range 2900 * from 0 up to some maximum. There are a few exceptions: 2901 * (1.) UCHAR_BLOCK values begin at the non-zero value 2902 * UBLOCK_BASIC_LATIN. (2.) UCHAR_CANONICAL_COMBINING_CLASS 2903 * values are not contiguous and range from 0..240. (3.) 2904 * UCHAR_GENERAL_CATEGORY_MASK values are not values of 2905 * UCharCategory, but rather mask values produced by 2906 * U_GET_GC_MASK(). This allows grouped categories such as 2907 * [:L:] to be represented. Mask values range 2908 * non-contiguously from 1..U_GC_P_MASK. 2909 * 2910 * @param nameChoice selector for which name to get. If out of range, 2911 * NULL is returned. All values have a long name. Most have 2912 * a short name, but some do not. Unicode allows for 2913 * additional names; if present these will be returned by 2914 * U_LONG_PROPERTY_NAME + i, where i=1, 2,... 2915 2916 * @return a pointer to the name, or NULL if either the 2917 * property or the nameChoice is out of range. If a given 2918 * nameChoice returns NULL, then all larger values of 2919 * nameChoice will return NULL, with one exception: if NULL is 2920 * returned for U_SHORT_PROPERTY_NAME, then 2921 * U_LONG_PROPERTY_NAME (and higher) may still return a 2922 * non-NULL value. The returned pointer is valid until 2923 * u_cleanup() is called. 2924 * 2925 * @see UProperty 2926 * @see UPropertyNameChoice 2927 * @stable ICU 2.4 2928 */ 2929 U_STABLE const char* U_EXPORT2 2930 u_getPropertyValueName(UProperty property, 2931 int32_t value, 2932 UPropertyNameChoice nameChoice); 2933 2934 /** 2935 * Return the property value integer for a given value name, as 2936 * specified in the Unicode database file PropertyValueAliases.txt. 2937 * Short, long, and any other variants are recognized. 2938 * 2939 * Note: Some of the names in PropertyValueAliases.txt will only be 2940 * recognized with UCHAR_GENERAL_CATEGORY_MASK, not 2941 * UCHAR_GENERAL_CATEGORY. These include: "C" / "Other", "L" / 2942 * "Letter", "LC" / "Cased_Letter", "M" / "Mark", "N" / "Number", "P" 2943 * / "Punctuation", "S" / "Symbol", and "Z" / "Separator". 2944 * 2945 * @param property UProperty selector constant. 2946 * Must be UCHAR_BINARY_START<=which<UCHAR_BINARY_LIMIT 2947 * or UCHAR_INT_START<=which<UCHAR_INT_LIMIT 2948 * or UCHAR_MASK_START<=which<UCHAR_MASK_LIMIT. 2949 * If out of range, UCHAR_INVALID_CODE is returned. 2950 * 2951 * @param alias the value name to be matched. The name is compared 2952 * using "loose matching" as described in 2953 * PropertyValueAliases.txt. 2954 * 2955 * @return a value integer or UCHAR_INVALID_CODE if the given name 2956 * does not match any value of the given property, or if the 2957 * property is invalid. Note: UCHAR_GENERAL_CATEGORY_MASK values 2958 * are not values of UCharCategory, but rather mask values 2959 * produced by U_GET_GC_MASK(). This allows grouped 2960 * categories such as [:L:] to be represented. 2961 * 2962 * @see UProperty 2963 * @stable ICU 2.4 2964 */ 2965 U_STABLE int32_t U_EXPORT2 2966 u_getPropertyValueEnum(UProperty property, 2967 const char* alias); 2968 2969 /** 2970 * Determines if the specified character is permissible as the 2971 * first character in an identifier according to Unicode 2972 * (The Unicode Standard, Version 3.0, chapter 5.16 Identifiers). 2973 * True for characters with general categories "L" (letters) and "Nl" (letter numbers). 2974 * 2975 * Same as java.lang.Character.isUnicodeIdentifierStart(). 2976 * Same as UCHAR_ID_START 2977 * 2978 * @param c the code point to be tested 2979 * @return TRUE if the code point may start an identifier 2980 * 2981 * @see UCHAR_ID_START 2982 * @see u_isalpha 2983 * @see u_isIDPart 2984 * @stable ICU 2.0 2985 */ 2986 U_STABLE UBool U_EXPORT2 2987 u_isIDStart(UChar32 c); 2988 2989 /** 2990 * Determines if the specified character is permissible 2991 * in an identifier according to Java. 2992 * True for characters with general categories "L" (letters), 2993 * "Nl" (letter numbers), "Nd" (decimal digits), 2994 * "Mc" and "Mn" (combining marks), "Pc" (connecting punctuation), and 2995 * u_isIDIgnorable(c). 2996 * 2997 * Same as java.lang.Character.isUnicodeIdentifierPart(). 2998 * Almost the same as Unicode's ID_Continue (UCHAR_ID_CONTINUE) 2999 * except that Unicode recommends to ignore Cf which is less than 3000 * u_isIDIgnorable(c). 3001 * 3002 * @param c the code point to be tested 3003 * @return TRUE if the code point may occur in an identifier according to Java 3004 * 3005 * @see UCHAR_ID_CONTINUE 3006 * @see u_isIDStart 3007 * @see u_isIDIgnorable 3008 * @stable ICU 2.0 3009 */ 3010 U_STABLE UBool U_EXPORT2 3011 u_isIDPart(UChar32 c); 3012 3013 /** 3014 * Determines if the specified character should be regarded 3015 * as an ignorable character in an identifier, 3016 * according to Java. 3017 * True for characters with general category "Cf" (format controls) as well as 3018 * non-whitespace ISO controls 3019 * (U+0000..U+0008, U+000E..U+001B, U+007F..U+009F). 3020 * 3021 * Same as java.lang.Character.isIdentifierIgnorable(). 3022 * 3023 * Note that Unicode just recommends to ignore Cf (format controls). 3024 * 3025 * @param c the code point to be tested 3026 * @return TRUE if the code point is ignorable in identifiers according to Java 3027 * 3028 * @see UCHAR_DEFAULT_IGNORABLE_CODE_POINT 3029 * @see u_isIDStart 3030 * @see u_isIDPart 3031 * @stable ICU 2.0 3032 */ 3033 U_STABLE UBool U_EXPORT2 3034 u_isIDIgnorable(UChar32 c); 3035 3036 /** 3037 * Determines if the specified character is permissible as the 3038 * first character in a Java identifier. 3039 * In addition to u_isIDStart(c), true for characters with 3040 * general categories "Sc" (currency symbols) and "Pc" (connecting punctuation). 3041 * 3042 * Same as java.lang.Character.isJavaIdentifierStart(). 3043 * 3044 * @param c the code point to be tested 3045 * @return TRUE if the code point may start a Java identifier 3046 * 3047 * @see u_isJavaIDPart 3048 * @see u_isalpha 3049 * @see u_isIDStart 3050 * @stable ICU 2.0 3051 */ 3052 U_STABLE UBool U_EXPORT2 3053 u_isJavaIDStart(UChar32 c); 3054 3055 /** 3056 * Determines if the specified character is permissible 3057 * in a Java identifier. 3058 * In addition to u_isIDPart(c), true for characters with 3059 * general category "Sc" (currency symbols). 3060 * 3061 * Same as java.lang.Character.isJavaIdentifierPart(). 3062 * 3063 * @param c the code point to be tested 3064 * @return TRUE if the code point may occur in a Java identifier 3065 * 3066 * @see u_isIDIgnorable 3067 * @see u_isJavaIDStart 3068 * @see u_isalpha 3069 * @see u_isdigit 3070 * @see u_isIDPart 3071 * @stable ICU 2.0 3072 */ 3073 U_STABLE UBool U_EXPORT2 3074 u_isJavaIDPart(UChar32 c); 3075 3076 /** 3077 * The given character is mapped to its lowercase equivalent according to 3078 * UnicodeData.txt; if the character has no lowercase equivalent, the character 3079 * itself is returned. 3080 * 3081 * Same as java.lang.Character.toLowerCase(). 3082 * 3083 * This function only returns the simple, single-code point case mapping. 3084 * Full case mappings should be used whenever possible because they produce 3085 * better results by working on whole strings. 3086 * They take into account the string context and the language and can map 3087 * to a result string with a different length as appropriate. 3088 * Full case mappings are applied by the string case mapping functions, 3089 * see ustring.h and the UnicodeString class. 3090 * See also the User Guide chapter on C/POSIX migration: 3091 * http://icu-project.org/userguide/posix.html#case_mappings 3092 * 3093 * @param c the code point to be mapped 3094 * @return the Simple_Lowercase_Mapping of the code point, if any; 3095 * otherwise the code point itself. 3096 * @stable ICU 2.0 3097 */ 3098 U_STABLE UChar32 U_EXPORT2 3099 u_tolower(UChar32 c); 3100 3101 /** 3102 * The given character is mapped to its uppercase equivalent according to UnicodeData.txt; 3103 * if the character has no uppercase equivalent, the character itself is 3104 * returned. 3105 * 3106 * Same as java.lang.Character.toUpperCase(). 3107 * 3108 * This function only returns the simple, single-code point case mapping. 3109 * Full case mappings should be used whenever possible because they produce 3110 * better results by working on whole strings. 3111 * They take into account the string context and the language and can map 3112 * to a result string with a different length as appropriate. 3113 * Full case mappings are applied by the string case mapping functions, 3114 * see ustring.h and the UnicodeString class. 3115 * See also the User Guide chapter on C/POSIX migration: 3116 * http://icu-project.org/userguide/posix.html#case_mappings 3117 * 3118 * @param c the code point to be mapped 3119 * @return the Simple_Uppercase_Mapping of the code point, if any; 3120 * otherwise the code point itself. 3121 * @stable ICU 2.0 3122 */ 3123 U_STABLE UChar32 U_EXPORT2 3124 u_toupper(UChar32 c); 3125 3126 /** 3127 * The given character is mapped to its titlecase equivalent 3128 * according to UnicodeData.txt; 3129 * if none is defined, the character itself is returned. 3130 * 3131 * Same as java.lang.Character.toTitleCase(). 3132 * 3133 * This function only returns the simple, single-code point case mapping. 3134 * Full case mappings should be used whenever possible because they produce 3135 * better results by working on whole strings. 3136 * They take into account the string context and the language and can map 3137 * to a result string with a different length as appropriate. 3138 * Full case mappings are applied by the string case mapping functions, 3139 * see ustring.h and the UnicodeString class. 3140 * See also the User Guide chapter on C/POSIX migration: 3141 * http://icu-project.org/userguide/posix.html#case_mappings 3142 * 3143 * @param c the code point to be mapped 3144 * @return the Simple_Titlecase_Mapping of the code point, if any; 3145 * otherwise the code point itself. 3146 * @stable ICU 2.0 3147 */ 3148 U_STABLE UChar32 U_EXPORT2 3149 u_totitle(UChar32 c); 3150 3151 /** Option value for case folding: use default mappings defined in CaseFolding.txt. @stable ICU 2.0 */ 3152 #define U_FOLD_CASE_DEFAULT 0 3153 3154 /** 3155 * Option value for case folding: 3156 * 3157 * Use the modified set of mappings provided in CaseFolding.txt to handle dotted I 3158 * and dotless i appropriately for Turkic languages (tr, az). 3159 * 3160 * Before Unicode 3.2, CaseFolding.txt contains mappings marked with 'I' that 3161 * are to be included for default mappings and 3162 * excluded for the Turkic-specific mappings. 3163 * 3164 * Unicode 3.2 CaseFolding.txt instead contains mappings marked with 'T' that 3165 * are to be excluded for default mappings and 3166 * included for the Turkic-specific mappings. 3167 * 3168 * @stable ICU 2.0 3169 */ 3170 #define U_FOLD_CASE_EXCLUDE_SPECIAL_I 1 3171 3172 /** 3173 * The given character is mapped to its case folding equivalent according to 3174 * UnicodeData.txt and CaseFolding.txt; 3175 * if the character has no case folding equivalent, the character 3176 * itself is returned. 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 * @param options Either U_FOLD_CASE_DEFAULT or U_FOLD_CASE_EXCLUDE_SPECIAL_I 3190 * @return the Simple_Case_Folding of the code point, if any; 3191 * otherwise the code point itself. 3192 * @stable ICU 2.0 3193 */ 3194 U_STABLE UChar32 U_EXPORT2 3195 u_foldCase(UChar32 c, uint32_t options); 3196 3197 /** 3198 * Returns the decimal digit value of the code point in the 3199 * specified radix. 3200 * 3201 * If the radix is not in the range <code>2<=radix<=36</code> or if the 3202 * value of <code>c</code> is not a valid digit in the specified 3203 * radix, <code>-1</code> is returned. A character is a valid digit 3204 * if at least one of the following is true: 3205 * <ul> 3206 * <li>The character has a decimal digit value. 3207 * Such characters have the general category "Nd" (decimal digit numbers) 3208 * and a Numeric_Type of Decimal. 3209 * In this case the value is the character's decimal digit value.</li> 3210 * <li>The character is one of the uppercase Latin letters 3211 * <code>'A'</code> through <code>'Z'</code>. 3212 * In this case the value is <code>c-'A'+10</code>.</li> 3213 * <li>The character is one of the lowercase Latin letters 3214 * <code>'a'</code> through <code>'z'</code>. 3215 * In this case the value is <code>ch-'a'+10</code>.</li> 3216 * <li>Latin letters from both the ASCII range (0061..007A, 0041..005A) 3217 * as well as from the Fullwidth ASCII range (FF41..FF5A, FF21..FF3A) 3218 * are recognized.</li> 3219 * </ul> 3220 * 3221 * Same as java.lang.Character.digit(). 3222 * 3223 * @param ch the code point to be tested. 3224 * @param radix the radix. 3225 * @return the numeric value represented by the character in the 3226 * specified radix, 3227 * or -1 if there is no value or if the value exceeds the radix. 3228 * 3229 * @see UCHAR_NUMERIC_TYPE 3230 * @see u_forDigit 3231 * @see u_charDigitValue 3232 * @see u_isdigit 3233 * @stable ICU 2.0 3234 */ 3235 U_STABLE int32_t U_EXPORT2 3236 u_digit(UChar32 ch, int8_t radix); 3237 3238 /** 3239 * Determines the character representation for a specific digit in 3240 * the specified radix. If the value of <code>radix</code> is not a 3241 * valid radix, or the value of <code>digit</code> is not a valid 3242 * digit in the specified radix, the null character 3243 * (<code>U+0000</code>) is returned. 3244 * <p> 3245 * The <code>radix</code> argument is valid if it is greater than or 3246 * equal to 2 and less than or equal to 36. 3247 * The <code>digit</code> argument is valid if 3248 * <code>0 <= digit < radix</code>. 3249 * <p> 3250 * If the digit is less than 10, then 3251 * <code>'0' + digit</code> is returned. Otherwise, the value 3252 * <code>'a' + digit - 10</code> is returned. 3253 * 3254 * Same as java.lang.Character.forDigit(). 3255 * 3256 * @param digit the number to convert to a character. 3257 * @param radix the radix. 3258 * @return the <code>char</code> representation of the specified digit 3259 * in the specified radix. 3260 * 3261 * @see u_digit 3262 * @see u_charDigitValue 3263 * @see u_isdigit 3264 * @stable ICU 2.0 3265 */ 3266 U_STABLE UChar32 U_EXPORT2 3267 u_forDigit(int32_t digit, int8_t radix); 3268 3269 /** 3270 * Get the "age" of the code point. 3271 * The "age" is the Unicode version when the code point was first 3272 * designated (as a non-character or for Private Use) 3273 * or assigned a character. 3274 * This can be useful to avoid emitting code points to receiving 3275 * processes that do not accept newer characters. 3276 * The data is from the UCD file DerivedAge.txt. 3277 * 3278 * @param c The code point. 3279 * @param versionArray The Unicode version number array, to be filled in. 3280 * 3281 * @stable ICU 2.1 3282 */ 3283 U_STABLE void U_EXPORT2 3284 u_charAge(UChar32 c, UVersionInfo versionArray); 3285 3286 /** 3287 * Gets the Unicode version information. 3288 * The version array is filled in with the version information 3289 * for the Unicode standard that is currently used by ICU. 3290 * For example, Unicode version 3.1.1 is represented as an array with 3291 * the values { 3, 1, 1, 0 }. 3292 * 3293 * @param versionArray an output array that will be filled in with 3294 * the Unicode version number 3295 * @stable ICU 2.0 3296 */ 3297 U_STABLE void U_EXPORT2 3298 u_getUnicodeVersion(UVersionInfo versionArray); 3299 3300 #if !UCONFIG_NO_NORMALIZATION 3301 /** 3302 * Get the FC_NFKC_Closure property string for a character. 3303 * See Unicode Standard Annex #15 for details, search for "FC_NFKC_Closure" 3304 * or for "FNC": http://www.unicode.org/reports/tr15/ 3305 * 3306 * @param c The character (code point) for which to get the FC_NFKC_Closure string. 3307 * It must be <code>0<=c<=0x10ffff</code>. 3308 * @param dest Destination address for copying the string. 3309 * The string will be zero-terminated if possible. 3310 * If there is no FC_NFKC_Closure string, 3311 * then the buffer will be set to the empty string. 3312 * @param destCapacity <code>==sizeof(dest)</code> 3313 * @param pErrorCode Pointer to a UErrorCode variable. 3314 * @return The length of the string, or 0 if there is no FC_NFKC_Closure string for this character. 3315 * If the destCapacity is less than or equal to the length, then the buffer 3316 * contains the truncated name and the returned length indicates the full 3317 * length of the name. 3318 * The length does not include the zero-termination. 3319 * 3320 * @stable ICU 2.2 3321 */ 3322 U_STABLE int32_t U_EXPORT2 3323 u_getFC_NFKC_Closure(UChar32 c, UChar *dest, int32_t destCapacity, UErrorCode *pErrorCode); 3324 3325 #endif 3326 3327 3328 U_CDECL_END 3329 3330 #endif /*_UCHAR*/ 3331 /*eof*/ 3332