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