1 /* 2 ********************************************************************** 3 * Copyright (C) 1997-2010, 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 "5.2" 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 * !! Note: Several comments in this file are machine-read by the 144 * genpname tool. These comments describe the correspondence between 145 * icu enum constants and UCD entities. Do not delete them. Update 146 * these comments as needed. 147 * 148 * Any comment of the form "/ *[name]* /" (spaces added) is such 149 * a comment. 150 * 151 * The U_JG_* and U_GC_*_MASK constants are matched by their symbolic 152 * name, which must match PropertyValueAliases.txt. 153 */ 154 155 /** 156 * Selection constants for Unicode properties. 157 * These constants are used in functions like u_hasBinaryProperty to select 158 * one of the Unicode properties. 159 * 160 * The properties APIs are intended to reflect Unicode properties as defined 161 * in the Unicode Character Database (UCD) and Unicode Technical Reports (UTR). 162 * For details about the properties see http://www.unicode.org/ucd/ . 163 * For names of Unicode properties see the UCD file PropertyAliases.txt. 164 * 165 * Important: If ICU is built with UCD files from Unicode versions below, e.g., 3.2, 166 * then properties marked with "new in Unicode 3.2" are not or not fully available. 167 * Check u_getUnicodeVersion to be sure. 168 * 169 * @see u_hasBinaryProperty 170 * @see u_getIntPropertyValue 171 * @see u_getUnicodeVersion 172 * @stable ICU 2.1 173 */ 174 typedef enum UProperty { 175 /* See note !!. Comments of the form "Binary property Dash", 176 "Enumerated property Script", "Double property Numeric_Value", 177 and "String property Age" are read by genpname. */ 178 179 /* Note: Place UCHAR_ALPHABETIC before UCHAR_BINARY_START so that 180 debuggers display UCHAR_ALPHABETIC as the symbolic name for 0, 181 rather than UCHAR_BINARY_START. Likewise for other *_START 182 identifiers. */ 183 184 /** Binary property Alphabetic. Same as u_isUAlphabetic, different from u_isalpha. 185 Lu+Ll+Lt+Lm+Lo+Nl+Other_Alphabetic @stable ICU 2.1 */ 186 UCHAR_ALPHABETIC=0, 187 /** First constant for binary Unicode properties. @stable ICU 2.1 */ 188 UCHAR_BINARY_START=UCHAR_ALPHABETIC, 189 /** Binary property ASCII_Hex_Digit. 0-9 A-F a-f @stable ICU 2.1 */ 190 UCHAR_ASCII_HEX_DIGIT=1, 191 /** Binary property Bidi_Control. 192 Format controls which have specific functions 193 in the Bidi Algorithm. @stable ICU 2.1 */ 194 UCHAR_BIDI_CONTROL=2, 195 /** Binary property Bidi_Mirrored. 196 Characters that may change display in RTL text. 197 Same as u_isMirrored. 198 See Bidi Algorithm, UTR 9. @stable ICU 2.1 */ 199 UCHAR_BIDI_MIRRORED=3, 200 /** Binary property Dash. Variations of dashes. @stable ICU 2.1 */ 201 UCHAR_DASH=4, 202 /** Binary property Default_Ignorable_Code_Point (new in Unicode 3.2). 203 Ignorable in most processing. 204 <2060..206F, FFF0..FFFB, E0000..E0FFF>+Other_Default_Ignorable_Code_Point+(Cf+Cc+Cs-White_Space) @stable ICU 2.1 */ 205 UCHAR_DEFAULT_IGNORABLE_CODE_POINT=5, 206 /** Binary property Deprecated (new in Unicode 3.2). 207 The usage of deprecated characters is strongly discouraged. @stable ICU 2.1 */ 208 UCHAR_DEPRECATED=6, 209 /** Binary property Diacritic. Characters that linguistically modify 210 the meaning of another character to which they apply. @stable ICU 2.1 */ 211 UCHAR_DIACRITIC=7, 212 /** Binary property Extender. 213 Extend the value or shape of a preceding alphabetic character, 214 e.g., length and iteration marks. @stable ICU 2.1 */ 215 UCHAR_EXTENDER=8, 216 /** Binary property Full_Composition_Exclusion. 217 CompositionExclusions.txt+Singleton Decompositions+ 218 Non-Starter Decompositions. @stable ICU 2.1 */ 219 UCHAR_FULL_COMPOSITION_EXCLUSION=9, 220 /** Binary property Grapheme_Base (new in Unicode 3.2). 221 For programmatic determination of grapheme cluster boundaries. 222 [0..10FFFF]-Cc-Cf-Cs-Co-Cn-Zl-Zp-Grapheme_Link-Grapheme_Extend-CGJ @stable ICU 2.1 */ 223 UCHAR_GRAPHEME_BASE=10, 224 /** Binary property Grapheme_Extend (new in Unicode 3.2). 225 For programmatic determination of grapheme cluster boundaries. 226 Me+Mn+Mc+Other_Grapheme_Extend-Grapheme_Link-CGJ @stable ICU 2.1 */ 227 UCHAR_GRAPHEME_EXTEND=11, 228 /** Binary property Grapheme_Link (new in Unicode 3.2). 229 For programmatic determination of grapheme cluster boundaries. @stable ICU 2.1 */ 230 UCHAR_GRAPHEME_LINK=12, 231 /** Binary property Hex_Digit. 232 Characters commonly used for hexadecimal numbers. @stable ICU 2.1 */ 233 UCHAR_HEX_DIGIT=13, 234 /** Binary property Hyphen. Dashes used to mark connections 235 between pieces of words, plus the Katakana middle dot. @stable ICU 2.1 */ 236 UCHAR_HYPHEN=14, 237 /** Binary property ID_Continue. 238 Characters that can continue an identifier. 239 DerivedCoreProperties.txt also says "NOTE: Cf characters should be filtered out." 240 ID_Start+Mn+Mc+Nd+Pc @stable ICU 2.1 */ 241 UCHAR_ID_CONTINUE=15, 242 /** Binary property ID_Start. 243 Characters that can start an identifier. 244 Lu+Ll+Lt+Lm+Lo+Nl @stable ICU 2.1 */ 245 UCHAR_ID_START=16, 246 /** Binary property Ideographic. 247 CJKV ideographs. @stable ICU 2.1 */ 248 UCHAR_IDEOGRAPHIC=17, 249 /** Binary property IDS_Binary_Operator (new in Unicode 3.2). 250 For programmatic determination of 251 Ideographic Description Sequences. @stable ICU 2.1 */ 252 UCHAR_IDS_BINARY_OPERATOR=18, 253 /** Binary property IDS_Trinary_Operator (new in Unicode 3.2). 254 For programmatic determination of 255 Ideographic Description Sequences. @stable ICU 2.1 */ 256 UCHAR_IDS_TRINARY_OPERATOR=19, 257 /** Binary property Join_Control. 258 Format controls for cursive joining and ligation. @stable ICU 2.1 */ 259 UCHAR_JOIN_CONTROL=20, 260 /** Binary property Logical_Order_Exception (new in Unicode 3.2). 261 Characters that do not use logical order and 262 require special handling in most processing. @stable ICU 2.1 */ 263 UCHAR_LOGICAL_ORDER_EXCEPTION=21, 264 /** Binary property Lowercase. Same as u_isULowercase, different from u_islower. 265 Ll+Other_Lowercase @stable ICU 2.1 */ 266 UCHAR_LOWERCASE=22, 267 /** Binary property Math. Sm+Other_Math @stable ICU 2.1 */ 268 UCHAR_MATH=23, 269 /** Binary property Noncharacter_Code_Point. 270 Code points that are explicitly defined as illegal 271 for the encoding of characters. @stable ICU 2.1 */ 272 UCHAR_NONCHARACTER_CODE_POINT=24, 273 /** Binary property Quotation_Mark. @stable ICU 2.1 */ 274 UCHAR_QUOTATION_MARK=25, 275 /** Binary property Radical (new in Unicode 3.2). 276 For programmatic determination of 277 Ideographic Description Sequences. @stable ICU 2.1 */ 278 UCHAR_RADICAL=26, 279 /** Binary property Soft_Dotted (new in Unicode 3.2). 280 Characters with a "soft dot", like i or j. 281 An accent placed on these characters causes 282 the dot to disappear. @stable ICU 2.1 */ 283 UCHAR_SOFT_DOTTED=27, 284 /** Binary property Terminal_Punctuation. 285 Punctuation characters that generally mark 286 the end of textual units. @stable ICU 2.1 */ 287 UCHAR_TERMINAL_PUNCTUATION=28, 288 /** Binary property Unified_Ideograph (new in Unicode 3.2). 289 For programmatic determination of 290 Ideographic Description Sequences. @stable ICU 2.1 */ 291 UCHAR_UNIFIED_IDEOGRAPH=29, 292 /** Binary property Uppercase. Same as u_isUUppercase, different from u_isupper. 293 Lu+Other_Uppercase @stable ICU 2.1 */ 294 UCHAR_UPPERCASE=30, 295 /** Binary property White_Space. 296 Same as u_isUWhiteSpace, different from u_isspace and u_isWhitespace. 297 Space characters+TAB+CR+LF-ZWSP-ZWNBSP @stable ICU 2.1 */ 298 UCHAR_WHITE_SPACE=31, 299 /** Binary property XID_Continue. 300 ID_Continue modified to allow closure under 301 normalization forms NFKC and NFKD. @stable ICU 2.1 */ 302 UCHAR_XID_CONTINUE=32, 303 /** Binary property XID_Start. ID_Start modified to allow 304 closure under normalization forms NFKC and NFKD. @stable ICU 2.1 */ 305 UCHAR_XID_START=33, 306 /** Binary property Case_Sensitive. Either the source of a case 307 mapping or _in_ the target of a case mapping. Not the same as 308 the general category Cased_Letter. @stable ICU 2.6 */ 309 UCHAR_CASE_SENSITIVE=34, 310 /** Binary property STerm (new in Unicode 4.0.1). 311 Sentence Terminal. Used in UAX #29: Text Boundaries 312 (http://www.unicode.org/reports/tr29/) 313 @stable ICU 3.0 */ 314 UCHAR_S_TERM=35, 315 /** Binary property Variation_Selector (new in Unicode 4.0.1). 316 Indicates all those characters that qualify as Variation Selectors. 317 For details on the behavior of these characters, 318 see StandardizedVariants.html and 15.6 Variation Selectors. 319 @stable ICU 3.0 */ 320 UCHAR_VARIATION_SELECTOR=36, 321 /** Binary property NFD_Inert. 322 ICU-specific property for characters that are inert under NFD, 323 i.e., they do not interact with adjacent characters. 324 See the documentation for the Normalizer2 class and the 325 Normalizer2::isInert() method. 326 @stable ICU 3.0 */ 327 UCHAR_NFD_INERT=37, 328 /** Binary property NFKD_Inert. 329 ICU-specific property for characters that are inert under NFKD, 330 i.e., they do not interact with adjacent characters. 331 See the documentation for the Normalizer2 class and the 332 Normalizer2::isInert() method. 333 @stable ICU 3.0 */ 334 UCHAR_NFKD_INERT=38, 335 /** Binary property NFC_Inert. 336 ICU-specific property for characters that are inert under NFC, 337 i.e., they do not interact with adjacent characters. 338 See the documentation for the Normalizer2 class and the 339 Normalizer2::isInert() method. 340 @stable ICU 3.0 */ 341 UCHAR_NFC_INERT=39, 342 /** Binary property NFKC_Inert. 343 ICU-specific property for characters that are inert under NFKC, 344 i.e., they do not interact with adjacent characters. 345 See the documentation for the Normalizer2 class and the 346 Normalizer2::isInert() method. 347 @stable ICU 3.0 */ 348 UCHAR_NFKC_INERT=40, 349 /** Binary Property Segment_Starter. 350 ICU-specific property for characters that are starters in terms of 351 Unicode normalization and combining character sequences. 352 They have ccc=0 and do not occur in non-initial position of the 353 canonical decomposition of any character 354 (like a-umlaut in NFD and a Jamo T in an NFD(Hangul LVT)). 355 ICU uses this property for segmenting a string for generating a set of 356 canonically equivalent strings, e.g. for canonical closure while 357 processing collation tailoring rules. 358 @stable ICU 3.0 */ 359 UCHAR_SEGMENT_STARTER=41, 360 /** Binary property Pattern_Syntax (new in Unicode 4.1). 361 See UAX #31 Identifier and Pattern Syntax 362 (http://www.unicode.org/reports/tr31/) 363 @stable ICU 3.4 */ 364 UCHAR_PATTERN_SYNTAX=42, 365 /** Binary property Pattern_White_Space (new in Unicode 4.1). 366 See UAX #31 Identifier and Pattern Syntax 367 (http://www.unicode.org/reports/tr31/) 368 @stable ICU 3.4 */ 369 UCHAR_PATTERN_WHITE_SPACE=43, 370 /** Binary property alnum (a C/POSIX character class). 371 Implemented according to the UTS #18 Annex C Standard Recommendation. 372 See the uchar.h file documentation. 373 @stable ICU 3.4 */ 374 UCHAR_POSIX_ALNUM=44, 375 /** Binary property blank (a C/POSIX character class). 376 Implemented according to the UTS #18 Annex C Standard Recommendation. 377 See the uchar.h file documentation. 378 @stable ICU 3.4 */ 379 UCHAR_POSIX_BLANK=45, 380 /** Binary property graph (a C/POSIX character class). 381 Implemented according to the UTS #18 Annex C Standard Recommendation. 382 See the uchar.h file documentation. 383 @stable ICU 3.4 */ 384 UCHAR_POSIX_GRAPH=46, 385 /** Binary property print (a C/POSIX character class). 386 Implemented according to the UTS #18 Annex C Standard Recommendation. 387 See the uchar.h file documentation. 388 @stable ICU 3.4 */ 389 UCHAR_POSIX_PRINT=47, 390 /** Binary property xdigit (a C/POSIX character class). 391 Implemented according to the UTS #18 Annex C Standard Recommendation. 392 See the uchar.h file documentation. 393 @stable ICU 3.4 */ 394 UCHAR_POSIX_XDIGIT=48, 395 /** Binary property Cased. For Lowercase, Uppercase and Titlecase characters. @draft ICU 4.4 */ 396 UCHAR_CASED=49, 397 /** Binary property Case_Ignorable. Used in context-sensitive case mappings. @draft ICU 4.4 */ 398 UCHAR_CASE_IGNORABLE=50, 399 /** Binary property Changes_When_Lowercased. @draft ICU 4.4 */ 400 UCHAR_CHANGES_WHEN_LOWERCASED=51, 401 /** Binary property Changes_When_Uppercased. @draft ICU 4.4 */ 402 UCHAR_CHANGES_WHEN_UPPERCASED=52, 403 /** Binary property Changes_When_Titlecased. @draft ICU 4.4 */ 404 UCHAR_CHANGES_WHEN_TITLECASED=53, 405 /** Binary property Changes_When_Casefolded. @draft ICU 4.4 */ 406 UCHAR_CHANGES_WHEN_CASEFOLDED=54, 407 /** Binary property Changes_When_Casemapped. @draft ICU 4.4 */ 408 UCHAR_CHANGES_WHEN_CASEMAPPED=55, 409 /** Binary property Changes_When_NFKC_Casefolded. @draft ICU 4.4 */ 410 UCHAR_CHANGES_WHEN_NFKC_CASEFOLDED=56, 411 /** One more than the last constant for binary Unicode properties. @stable ICU 2.1 */ 412 UCHAR_BINARY_LIMIT=57, 413 414 /** Enumerated property Bidi_Class. 415 Same as u_charDirection, returns UCharDirection values. @stable ICU 2.2 */ 416 UCHAR_BIDI_CLASS=0x1000, 417 /** First constant for enumerated/integer Unicode properties. @stable ICU 2.2 */ 418 UCHAR_INT_START=UCHAR_BIDI_CLASS, 419 /** Enumerated property Block. 420 Same as ublock_getCode, returns UBlockCode values. @stable ICU 2.2 */ 421 UCHAR_BLOCK=0x1001, 422 /** Enumerated property Canonical_Combining_Class. 423 Same as u_getCombiningClass, returns 8-bit numeric values. @stable ICU 2.2 */ 424 UCHAR_CANONICAL_COMBINING_CLASS=0x1002, 425 /** Enumerated property Decomposition_Type. 426 Returns UDecompositionType values. @stable ICU 2.2 */ 427 UCHAR_DECOMPOSITION_TYPE=0x1003, 428 /** Enumerated property East_Asian_Width. 429 See http://www.unicode.org/reports/tr11/ 430 Returns UEastAsianWidth values. @stable ICU 2.2 */ 431 UCHAR_EAST_ASIAN_WIDTH=0x1004, 432 /** Enumerated property General_Category. 433 Same as u_charType, returns UCharCategory values. @stable ICU 2.2 */ 434 UCHAR_GENERAL_CATEGORY=0x1005, 435 /** Enumerated property Joining_Group. 436 Returns UJoiningGroup values. @stable ICU 2.2 */ 437 UCHAR_JOINING_GROUP=0x1006, 438 /** Enumerated property Joining_Type. 439 Returns UJoiningType values. @stable ICU 2.2 */ 440 UCHAR_JOINING_TYPE=0x1007, 441 /** Enumerated property Line_Break. 442 Returns ULineBreak values. @stable ICU 2.2 */ 443 UCHAR_LINE_BREAK=0x1008, 444 /** Enumerated property Numeric_Type. 445 Returns UNumericType values. @stable ICU 2.2 */ 446 UCHAR_NUMERIC_TYPE=0x1009, 447 /** Enumerated property Script. 448 Same as uscript_getScript, returns UScriptCode values. @stable ICU 2.2 */ 449 UCHAR_SCRIPT=0x100A, 450 /** Enumerated property Hangul_Syllable_Type, new in Unicode 4. 451 Returns UHangulSyllableType values. @stable ICU 2.6 */ 452 UCHAR_HANGUL_SYLLABLE_TYPE=0x100B, 453 /** Enumerated property NFD_Quick_Check. 454 Returns UNormalizationCheckResult values. @stable ICU 3.0 */ 455 UCHAR_NFD_QUICK_CHECK=0x100C, 456 /** Enumerated property NFKD_Quick_Check. 457 Returns UNormalizationCheckResult values. @stable ICU 3.0 */ 458 UCHAR_NFKD_QUICK_CHECK=0x100D, 459 /** Enumerated property NFC_Quick_Check. 460 Returns UNormalizationCheckResult values. @stable ICU 3.0 */ 461 UCHAR_NFC_QUICK_CHECK=0x100E, 462 /** Enumerated property NFKC_Quick_Check. 463 Returns UNormalizationCheckResult values. @stable ICU 3.0 */ 464 UCHAR_NFKC_QUICK_CHECK=0x100F, 465 /** Enumerated property Lead_Canonical_Combining_Class. 466 ICU-specific property for the ccc of the first code point 467 of the decomposition, or lccc(c)=ccc(NFD(c)[0]). 468 Useful for checking for canonically ordered text; 469 see UNORM_FCD and http://www.unicode.org/notes/tn5/#FCD . 470 Returns 8-bit numeric values like UCHAR_CANONICAL_COMBINING_CLASS. @stable ICU 3.0 */ 471 UCHAR_LEAD_CANONICAL_COMBINING_CLASS=0x1010, 472 /** Enumerated property Trail_Canonical_Combining_Class. 473 ICU-specific property for the ccc of the last code point 474 of the decomposition, or tccc(c)=ccc(NFD(c)[last]). 475 Useful for checking for canonically ordered text; 476 see UNORM_FCD and http://www.unicode.org/notes/tn5/#FCD . 477 Returns 8-bit numeric values like UCHAR_CANONICAL_COMBINING_CLASS. @stable ICU 3.0 */ 478 UCHAR_TRAIL_CANONICAL_COMBINING_CLASS=0x1011, 479 /** Enumerated property Grapheme_Cluster_Break (new in Unicode 4.1). 480 Used in UAX #29: Text Boundaries 481 (http://www.unicode.org/reports/tr29/) 482 Returns UGraphemeClusterBreak values. @stable ICU 3.4 */ 483 UCHAR_GRAPHEME_CLUSTER_BREAK=0x1012, 484 /** Enumerated property Sentence_Break (new in Unicode 4.1). 485 Used in UAX #29: Text Boundaries 486 (http://www.unicode.org/reports/tr29/) 487 Returns USentenceBreak values. @stable ICU 3.4 */ 488 UCHAR_SENTENCE_BREAK=0x1013, 489 /** Enumerated property Word_Break (new in Unicode 4.1). 490 Used in UAX #29: Text Boundaries 491 (http://www.unicode.org/reports/tr29/) 492 Returns UWordBreakValues values. @stable ICU 3.4 */ 493 UCHAR_WORD_BREAK=0x1014, 494 /** One more than the last constant for enumerated/integer Unicode properties. @stable ICU 2.2 */ 495 UCHAR_INT_LIMIT=0x1015, 496 497 /** Bitmask property General_Category_Mask. 498 This is the General_Category property returned as a bit mask. 499 When used in u_getIntPropertyValue(c), same as U_MASK(u_charType(c)), 500 returns bit masks for UCharCategory values where exactly one bit is set. 501 When used with u_getPropertyValueName() and u_getPropertyValueEnum(), 502 a multi-bit mask is used for sets of categories like "Letters". 503 Mask values should be cast to uint32_t. 504 @stable ICU 2.4 */ 505 UCHAR_GENERAL_CATEGORY_MASK=0x2000, 506 /** First constant for bit-mask Unicode properties. @stable ICU 2.4 */ 507 UCHAR_MASK_START=UCHAR_GENERAL_CATEGORY_MASK, 508 /** One more than the last constant for bit-mask Unicode properties. @stable ICU 2.4 */ 509 UCHAR_MASK_LIMIT=0x2001, 510 511 /** Double property Numeric_Value. 512 Corresponds to u_getNumericValue. @stable ICU 2.4 */ 513 UCHAR_NUMERIC_VALUE=0x3000, 514 /** First constant for double Unicode properties. @stable ICU 2.4 */ 515 UCHAR_DOUBLE_START=UCHAR_NUMERIC_VALUE, 516 /** One more than the last constant for double Unicode properties. @stable ICU 2.4 */ 517 UCHAR_DOUBLE_LIMIT=0x3001, 518 519 /** String property Age. 520 Corresponds to u_charAge. @stable ICU 2.4 */ 521 UCHAR_AGE=0x4000, 522 /** First constant for string Unicode properties. @stable ICU 2.4 */ 523 UCHAR_STRING_START=UCHAR_AGE, 524 /** String property Bidi_Mirroring_Glyph. 525 Corresponds to u_charMirror. @stable ICU 2.4 */ 526 UCHAR_BIDI_MIRRORING_GLYPH=0x4001, 527 /** String property Case_Folding. 528 Corresponds to u_strFoldCase in ustring.h. @stable ICU 2.4 */ 529 UCHAR_CASE_FOLDING=0x4002, 530 /** String property ISO_Comment. 531 Corresponds to u_getISOComment. @stable ICU 2.4 */ 532 UCHAR_ISO_COMMENT=0x4003, 533 /** String property Lowercase_Mapping. 534 Corresponds to u_strToLower in ustring.h. @stable ICU 2.4 */ 535 UCHAR_LOWERCASE_MAPPING=0x4004, 536 /** String property Name. 537 Corresponds to u_charName. @stable ICU 2.4 */ 538 UCHAR_NAME=0x4005, 539 /** String property Simple_Case_Folding. 540 Corresponds to u_foldCase. @stable ICU 2.4 */ 541 UCHAR_SIMPLE_CASE_FOLDING=0x4006, 542 /** String property Simple_Lowercase_Mapping. 543 Corresponds to u_tolower. @stable ICU 2.4 */ 544 UCHAR_SIMPLE_LOWERCASE_MAPPING=0x4007, 545 /** String property Simple_Titlecase_Mapping. 546 Corresponds to u_totitle. @stable ICU 2.4 */ 547 UCHAR_SIMPLE_TITLECASE_MAPPING=0x4008, 548 /** String property Simple_Uppercase_Mapping. 549 Corresponds to u_toupper. @stable ICU 2.4 */ 550 UCHAR_SIMPLE_UPPERCASE_MAPPING=0x4009, 551 /** String property Titlecase_Mapping. 552 Corresponds to u_strToTitle in ustring.h. @stable ICU 2.4 */ 553 UCHAR_TITLECASE_MAPPING=0x400A, 554 /** String property Unicode_1_Name. 555 Corresponds to u_charName. @stable ICU 2.4 */ 556 UCHAR_UNICODE_1_NAME=0x400B, 557 /** String property Uppercase_Mapping. 558 Corresponds to u_strToUpper in ustring.h. @stable ICU 2.4 */ 559 UCHAR_UPPERCASE_MAPPING=0x400C, 560 /** One more than the last constant for string Unicode properties. @stable ICU 2.4 */ 561 UCHAR_STRING_LIMIT=0x400D, 562 563 /** Represents a nonexistent or invalid property or property value. @stable ICU 2.4 */ 564 UCHAR_INVALID_CODE = -1 565 } UProperty; 566 567 /** 568 * Data for enumerated Unicode general category types. 569 * See http://www.unicode.org/Public/UNIDATA/UnicodeData.html . 570 * @stable ICU 2.0 571 */ 572 typedef enum UCharCategory 573 { 574 /** See note !!. Comments of the form "Cn" are read by genpname. */ 575 576 /** Non-category for unassigned and non-character code points. @stable ICU 2.0 */ 577 U_UNASSIGNED = 0, 578 /** Cn "Other, Not Assigned (no characters in [UnicodeData.txt] have this property)" (same as U_UNASSIGNED!) @stable ICU 2.0 */ 579 U_GENERAL_OTHER_TYPES = 0, 580 /** Lu @stable ICU 2.0 */ 581 U_UPPERCASE_LETTER = 1, 582 /** Ll @stable ICU 2.0 */ 583 U_LOWERCASE_LETTER = 2, 584 /** Lt @stable ICU 2.0 */ 585 U_TITLECASE_LETTER = 3, 586 /** Lm @stable ICU 2.0 */ 587 U_MODIFIER_LETTER = 4, 588 /** Lo @stable ICU 2.0 */ 589 U_OTHER_LETTER = 5, 590 /** Mn @stable ICU 2.0 */ 591 U_NON_SPACING_MARK = 6, 592 /** Me @stable ICU 2.0 */ 593 U_ENCLOSING_MARK = 7, 594 /** Mc @stable ICU 2.0 */ 595 U_COMBINING_SPACING_MARK = 8, 596 /** Nd @stable ICU 2.0 */ 597 U_DECIMAL_DIGIT_NUMBER = 9, 598 /** Nl @stable ICU 2.0 */ 599 U_LETTER_NUMBER = 10, 600 /** No @stable ICU 2.0 */ 601 U_OTHER_NUMBER = 11, 602 /** Zs @stable ICU 2.0 */ 603 U_SPACE_SEPARATOR = 12, 604 /** Zl @stable ICU 2.0 */ 605 U_LINE_SEPARATOR = 13, 606 /** Zp @stable ICU 2.0 */ 607 U_PARAGRAPH_SEPARATOR = 14, 608 /** Cc @stable ICU 2.0 */ 609 U_CONTROL_CHAR = 15, 610 /** Cf @stable ICU 2.0 */ 611 U_FORMAT_CHAR = 16, 612 /** Co @stable ICU 2.0 */ 613 U_PRIVATE_USE_CHAR = 17, 614 /** Cs @stable ICU 2.0 */ 615 U_SURROGATE = 18, 616 /** Pd @stable ICU 2.0 */ 617 U_DASH_PUNCTUATION = 19, 618 /** Ps @stable ICU 2.0 */ 619 U_START_PUNCTUATION = 20, 620 /** Pe @stable ICU 2.0 */ 621 U_END_PUNCTUATION = 21, 622 /** Pc @stable ICU 2.0 */ 623 U_CONNECTOR_PUNCTUATION = 22, 624 /** Po @stable ICU 2.0 */ 625 U_OTHER_PUNCTUATION = 23, 626 /** Sm @stable ICU 2.0 */ 627 U_MATH_SYMBOL = 24, 628 /** Sc @stable ICU 2.0 */ 629 U_CURRENCY_SYMBOL = 25, 630 /** Sk @stable ICU 2.0 */ 631 U_MODIFIER_SYMBOL = 26, 632 /** So @stable ICU 2.0 */ 633 U_OTHER_SYMBOL = 27, 634 /** Pi @stable ICU 2.0 */ 635 U_INITIAL_PUNCTUATION = 28, 636 /** Pf @stable ICU 2.0 */ 637 U_FINAL_PUNCTUATION = 29, 638 /** One higher than the last enum UCharCategory constant. @stable ICU 2.0 */ 639 U_CHAR_CATEGORY_COUNT 640 } UCharCategory; 641 642 /** 643 * U_GC_XX_MASK constants are bit flags corresponding to Unicode 644 * general category values. 645 * For each category, the nth bit is set if the numeric value of the 646 * corresponding UCharCategory constant is n. 647 * 648 * There are also some U_GC_Y_MASK constants for groups of general categories 649 * like L for all letter categories. 650 * 651 * @see u_charType 652 * @see U_GET_GC_MASK 653 * @see UCharCategory 654 * @stable ICU 2.1 655 */ 656 #define U_GC_CN_MASK U_MASK(U_GENERAL_OTHER_TYPES) 657 658 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 659 #define U_GC_LU_MASK U_MASK(U_UPPERCASE_LETTER) 660 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 661 #define U_GC_LL_MASK U_MASK(U_LOWERCASE_LETTER) 662 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 663 #define U_GC_LT_MASK U_MASK(U_TITLECASE_LETTER) 664 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 665 #define U_GC_LM_MASK U_MASK(U_MODIFIER_LETTER) 666 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 667 #define U_GC_LO_MASK U_MASK(U_OTHER_LETTER) 668 669 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 670 #define U_GC_MN_MASK U_MASK(U_NON_SPACING_MARK) 671 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 672 #define U_GC_ME_MASK U_MASK(U_ENCLOSING_MARK) 673 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 674 #define U_GC_MC_MASK U_MASK(U_COMBINING_SPACING_MARK) 675 676 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 677 #define U_GC_ND_MASK U_MASK(U_DECIMAL_DIGIT_NUMBER) 678 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 679 #define U_GC_NL_MASK U_MASK(U_LETTER_NUMBER) 680 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 681 #define U_GC_NO_MASK U_MASK(U_OTHER_NUMBER) 682 683 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 684 #define U_GC_ZS_MASK U_MASK(U_SPACE_SEPARATOR) 685 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 686 #define U_GC_ZL_MASK U_MASK(U_LINE_SEPARATOR) 687 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 688 #define U_GC_ZP_MASK U_MASK(U_PARAGRAPH_SEPARATOR) 689 690 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 691 #define U_GC_CC_MASK U_MASK(U_CONTROL_CHAR) 692 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 693 #define U_GC_CF_MASK U_MASK(U_FORMAT_CHAR) 694 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 695 #define U_GC_CO_MASK U_MASK(U_PRIVATE_USE_CHAR) 696 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 697 #define U_GC_CS_MASK U_MASK(U_SURROGATE) 698 699 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 700 #define U_GC_PD_MASK U_MASK(U_DASH_PUNCTUATION) 701 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 702 #define U_GC_PS_MASK U_MASK(U_START_PUNCTUATION) 703 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 704 #define U_GC_PE_MASK U_MASK(U_END_PUNCTUATION) 705 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 706 #define U_GC_PC_MASK U_MASK(U_CONNECTOR_PUNCTUATION) 707 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 708 #define U_GC_PO_MASK U_MASK(U_OTHER_PUNCTUATION) 709 710 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 711 #define U_GC_SM_MASK U_MASK(U_MATH_SYMBOL) 712 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 713 #define U_GC_SC_MASK U_MASK(U_CURRENCY_SYMBOL) 714 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 715 #define U_GC_SK_MASK U_MASK(U_MODIFIER_SYMBOL) 716 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 717 #define U_GC_SO_MASK U_MASK(U_OTHER_SYMBOL) 718 719 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 720 #define U_GC_PI_MASK U_MASK(U_INITIAL_PUNCTUATION) 721 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 722 #define U_GC_PF_MASK U_MASK(U_FINAL_PUNCTUATION) 723 724 725 /** Mask constant for multiple UCharCategory bits (L Letters). @stable ICU 2.1 */ 726 #define U_GC_L_MASK \ 727 (U_GC_LU_MASK|U_GC_LL_MASK|U_GC_LT_MASK|U_GC_LM_MASK|U_GC_LO_MASK) 728 729 /** Mask constant for multiple UCharCategory bits (LC Cased Letters). @stable ICU 2.1 */ 730 #define U_GC_LC_MASK \ 731 (U_GC_LU_MASK|U_GC_LL_MASK|U_GC_LT_MASK) 732 733 /** Mask constant for multiple UCharCategory bits (M Marks). @stable ICU 2.1 */ 734 #define U_GC_M_MASK (U_GC_MN_MASK|U_GC_ME_MASK|U_GC_MC_MASK) 735 736 /** Mask constant for multiple UCharCategory bits (N Numbers). @stable ICU 2.1 */ 737 #define U_GC_N_MASK (U_GC_ND_MASK|U_GC_NL_MASK|U_GC_NO_MASK) 738 739 /** Mask constant for multiple UCharCategory bits (Z Separators). @stable ICU 2.1 */ 740 #define U_GC_Z_MASK (U_GC_ZS_MASK|U_GC_ZL_MASK|U_GC_ZP_MASK) 741 742 /** Mask constant for multiple UCharCategory bits (C Others). @stable ICU 2.1 */ 743 #define U_GC_C_MASK \ 744 (U_GC_CN_MASK|U_GC_CC_MASK|U_GC_CF_MASK|U_GC_CO_MASK|U_GC_CS_MASK) 745 746 /** Mask constant for multiple UCharCategory bits (P Punctuation). @stable ICU 2.1 */ 747 #define U_GC_P_MASK \ 748 (U_GC_PD_MASK|U_GC_PS_MASK|U_GC_PE_MASK|U_GC_PC_MASK|U_GC_PO_MASK| \ 749 U_GC_PI_MASK|U_GC_PF_MASK) 750 751 /** Mask constant for multiple UCharCategory bits (S Symbols). @stable ICU 2.1 */ 752 #define U_GC_S_MASK (U_GC_SM_MASK|U_GC_SC_MASK|U_GC_SK_MASK|U_GC_SO_MASK) 753 754 /** 755 * This specifies the language directional property of a character set. 756 * @stable ICU 2.0 757 */ 758 typedef enum UCharDirection { 759 /** See note !!. Comments of the form "EN" are read by genpname. */ 760 761 /** L @stable ICU 2.0 */ 762 U_LEFT_TO_RIGHT = 0, 763 /** R @stable ICU 2.0 */ 764 U_RIGHT_TO_LEFT = 1, 765 /** EN @stable ICU 2.0 */ 766 U_EUROPEAN_NUMBER = 2, 767 /** ES @stable ICU 2.0 */ 768 U_EUROPEAN_NUMBER_SEPARATOR = 3, 769 /** ET @stable ICU 2.0 */ 770 U_EUROPEAN_NUMBER_TERMINATOR = 4, 771 /** AN @stable ICU 2.0 */ 772 U_ARABIC_NUMBER = 5, 773 /** CS @stable ICU 2.0 */ 774 U_COMMON_NUMBER_SEPARATOR = 6, 775 /** B @stable ICU 2.0 */ 776 U_BLOCK_SEPARATOR = 7, 777 /** S @stable ICU 2.0 */ 778 U_SEGMENT_SEPARATOR = 8, 779 /** WS @stable ICU 2.0 */ 780 U_WHITE_SPACE_NEUTRAL = 9, 781 /** ON @stable ICU 2.0 */ 782 U_OTHER_NEUTRAL = 10, 783 /** LRE @stable ICU 2.0 */ 784 U_LEFT_TO_RIGHT_EMBEDDING = 11, 785 /** LRO @stable ICU 2.0 */ 786 U_LEFT_TO_RIGHT_OVERRIDE = 12, 787 /** AL @stable ICU 2.0 */ 788 U_RIGHT_TO_LEFT_ARABIC = 13, 789 /** RLE @stable ICU 2.0 */ 790 U_RIGHT_TO_LEFT_EMBEDDING = 14, 791 /** RLO @stable ICU 2.0 */ 792 U_RIGHT_TO_LEFT_OVERRIDE = 15, 793 /** PDF @stable ICU 2.0 */ 794 U_POP_DIRECTIONAL_FORMAT = 16, 795 /** NSM @stable ICU 2.0 */ 796 U_DIR_NON_SPACING_MARK = 17, 797 /** BN @stable ICU 2.0 */ 798 U_BOUNDARY_NEUTRAL = 18, 799 /** @stable ICU 2.0 */ 800 U_CHAR_DIRECTION_COUNT 801 } UCharDirection; 802 803 /** 804 * Constants for Unicode blocks, see the Unicode Data file Blocks.txt 805 * @stable ICU 2.0 806 */ 807 enum UBlockCode { 808 809 /** New No_Block value in Unicode 4. @stable ICU 2.6 */ 810 UBLOCK_NO_BLOCK = 0, /*[none]*/ /* Special range indicating No_Block */ 811 812 /** @stable ICU 2.0 */ 813 UBLOCK_BASIC_LATIN = 1, /*[0000]*/ /*See note !!*/ 814 815 /** @stable ICU 2.0 */ 816 UBLOCK_LATIN_1_SUPPLEMENT=2, /*[0080]*/ 817 818 /** @stable ICU 2.0 */ 819 UBLOCK_LATIN_EXTENDED_A =3, /*[0100]*/ 820 821 /** @stable ICU 2.0 */ 822 UBLOCK_LATIN_EXTENDED_B =4, /*[0180]*/ 823 824 /** @stable ICU 2.0 */ 825 UBLOCK_IPA_EXTENSIONS =5, /*[0250]*/ 826 827 /** @stable ICU 2.0 */ 828 UBLOCK_SPACING_MODIFIER_LETTERS =6, /*[02B0]*/ 829 830 /** @stable ICU 2.0 */ 831 UBLOCK_COMBINING_DIACRITICAL_MARKS =7, /*[0300]*/ 832 833 /** 834 * Unicode 3.2 renames this block to "Greek and Coptic". 835 * @stable ICU 2.0 836 */ 837 UBLOCK_GREEK =8, /*[0370]*/ 838 839 /** @stable ICU 2.0 */ 840 UBLOCK_CYRILLIC =9, /*[0400]*/ 841 842 /** @stable ICU 2.0 */ 843 UBLOCK_ARMENIAN =10, /*[0530]*/ 844 845 /** @stable ICU 2.0 */ 846 UBLOCK_HEBREW =11, /*[0590]*/ 847 848 /** @stable ICU 2.0 */ 849 UBLOCK_ARABIC =12, /*[0600]*/ 850 851 /** @stable ICU 2.0 */ 852 UBLOCK_SYRIAC =13, /*[0700]*/ 853 854 /** @stable ICU 2.0 */ 855 UBLOCK_THAANA =14, /*[0780]*/ 856 857 /** @stable ICU 2.0 */ 858 UBLOCK_DEVANAGARI =15, /*[0900]*/ 859 860 /** @stable ICU 2.0 */ 861 UBLOCK_BENGALI =16, /*[0980]*/ 862 863 /** @stable ICU 2.0 */ 864 UBLOCK_GURMUKHI =17, /*[0A00]*/ 865 866 /** @stable ICU 2.0 */ 867 UBLOCK_GUJARATI =18, /*[0A80]*/ 868 869 /** @stable ICU 2.0 */ 870 UBLOCK_ORIYA =19, /*[0B00]*/ 871 872 /** @stable ICU 2.0 */ 873 UBLOCK_TAMIL =20, /*[0B80]*/ 874 875 /** @stable ICU 2.0 */ 876 UBLOCK_TELUGU =21, /*[0C00]*/ 877 878 /** @stable ICU 2.0 */ 879 UBLOCK_KANNADA =22, /*[0C80]*/ 880 881 /** @stable ICU 2.0 */ 882 UBLOCK_MALAYALAM =23, /*[0D00]*/ 883 884 /** @stable ICU 2.0 */ 885 UBLOCK_SINHALA =24, /*[0D80]*/ 886 887 /** @stable ICU 2.0 */ 888 UBLOCK_THAI =25, /*[0E00]*/ 889 890 /** @stable ICU 2.0 */ 891 UBLOCK_LAO =26, /*[0E80]*/ 892 893 /** @stable ICU 2.0 */ 894 UBLOCK_TIBETAN =27, /*[0F00]*/ 895 896 /** @stable ICU 2.0 */ 897 UBLOCK_MYANMAR =28, /*[1000]*/ 898 899 /** @stable ICU 2.0 */ 900 UBLOCK_GEORGIAN =29, /*[10A0]*/ 901 902 /** @stable ICU 2.0 */ 903 UBLOCK_HANGUL_JAMO =30, /*[1100]*/ 904 905 /** @stable ICU 2.0 */ 906 UBLOCK_ETHIOPIC =31, /*[1200]*/ 907 908 /** @stable ICU 2.0 */ 909 UBLOCK_CHEROKEE =32, /*[13A0]*/ 910 911 /** @stable ICU 2.0 */ 912 UBLOCK_UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS =33, /*[1400]*/ 913 914 /** @stable ICU 2.0 */ 915 UBLOCK_OGHAM =34, /*[1680]*/ 916 917 /** @stable ICU 2.0 */ 918 UBLOCK_RUNIC =35, /*[16A0]*/ 919 920 /** @stable ICU 2.0 */ 921 UBLOCK_KHMER =36, /*[1780]*/ 922 923 /** @stable ICU 2.0 */ 924 UBLOCK_MONGOLIAN =37, /*[1800]*/ 925 926 /** @stable ICU 2.0 */ 927 UBLOCK_LATIN_EXTENDED_ADDITIONAL =38, /*[1E00]*/ 928 929 /** @stable ICU 2.0 */ 930 UBLOCK_GREEK_EXTENDED =39, /*[1F00]*/ 931 932 /** @stable ICU 2.0 */ 933 UBLOCK_GENERAL_PUNCTUATION =40, /*[2000]*/ 934 935 /** @stable ICU 2.0 */ 936 UBLOCK_SUPERSCRIPTS_AND_SUBSCRIPTS =41, /*[2070]*/ 937 938 /** @stable ICU 2.0 */ 939 UBLOCK_CURRENCY_SYMBOLS =42, /*[20A0]*/ 940 941 /** 942 * Unicode 3.2 renames this block to "Combining Diacritical Marks for Symbols". 943 * @stable ICU 2.0 944 */ 945 UBLOCK_COMBINING_MARKS_FOR_SYMBOLS =43, /*[20D0]*/ 946 947 /** @stable ICU 2.0 */ 948 UBLOCK_LETTERLIKE_SYMBOLS =44, /*[2100]*/ 949 950 /** @stable ICU 2.0 */ 951 UBLOCK_NUMBER_FORMS =45, /*[2150]*/ 952 953 /** @stable ICU 2.0 */ 954 UBLOCK_ARROWS =46, /*[2190]*/ 955 956 /** @stable ICU 2.0 */ 957 UBLOCK_MATHEMATICAL_OPERATORS =47, /*[2200]*/ 958 959 /** @stable ICU 2.0 */ 960 UBLOCK_MISCELLANEOUS_TECHNICAL =48, /*[2300]*/ 961 962 /** @stable ICU 2.0 */ 963 UBLOCK_CONTROL_PICTURES =49, /*[2400]*/ 964 965 /** @stable ICU 2.0 */ 966 UBLOCK_OPTICAL_CHARACTER_RECOGNITION =50, /*[2440]*/ 967 968 /** @stable ICU 2.0 */ 969 UBLOCK_ENCLOSED_ALPHANUMERICS =51, /*[2460]*/ 970 971 /** @stable ICU 2.0 */ 972 UBLOCK_BOX_DRAWING =52, /*[2500]*/ 973 974 /** @stable ICU 2.0 */ 975 UBLOCK_BLOCK_ELEMENTS =53, /*[2580]*/ 976 977 /** @stable ICU 2.0 */ 978 UBLOCK_GEOMETRIC_SHAPES =54, /*[25A0]*/ 979 980 /** @stable ICU 2.0 */ 981 UBLOCK_MISCELLANEOUS_SYMBOLS =55, /*[2600]*/ 982 983 /** @stable ICU 2.0 */ 984 UBLOCK_DINGBATS =56, /*[2700]*/ 985 986 /** @stable ICU 2.0 */ 987 UBLOCK_BRAILLE_PATTERNS =57, /*[2800]*/ 988 989 /** @stable ICU 2.0 */ 990 UBLOCK_CJK_RADICALS_SUPPLEMENT =58, /*[2E80]*/ 991 992 /** @stable ICU 2.0 */ 993 UBLOCK_KANGXI_RADICALS =59, /*[2F00]*/ 994 995 /** @stable ICU 2.0 */ 996 UBLOCK_IDEOGRAPHIC_DESCRIPTION_CHARACTERS =60, /*[2FF0]*/ 997 998 /** @stable ICU 2.0 */ 999 UBLOCK_CJK_SYMBOLS_AND_PUNCTUATION =61, /*[3000]*/ 1000 1001 /** @stable ICU 2.0 */ 1002 UBLOCK_HIRAGANA =62, /*[3040]*/ 1003 1004 /** @stable ICU 2.0 */ 1005 UBLOCK_KATAKANA =63, /*[30A0]*/ 1006 1007 /** @stable ICU 2.0 */ 1008 UBLOCK_BOPOMOFO =64, /*[3100]*/ 1009 1010 /** @stable ICU 2.0 */ 1011 UBLOCK_HANGUL_COMPATIBILITY_JAMO =65, /*[3130]*/ 1012 1013 /** @stable ICU 2.0 */ 1014 UBLOCK_KANBUN =66, /*[3190]*/ 1015 1016 /** @stable ICU 2.0 */ 1017 UBLOCK_BOPOMOFO_EXTENDED =67, /*[31A0]*/ 1018 1019 /** @stable ICU 2.0 */ 1020 UBLOCK_ENCLOSED_CJK_LETTERS_AND_MONTHS =68, /*[3200]*/ 1021 1022 /** @stable ICU 2.0 */ 1023 UBLOCK_CJK_COMPATIBILITY =69, /*[3300]*/ 1024 1025 /** @stable ICU 2.0 */ 1026 UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_A =70, /*[3400]*/ 1027 1028 /** @stable ICU 2.0 */ 1029 UBLOCK_CJK_UNIFIED_IDEOGRAPHS =71, /*[4E00]*/ 1030 1031 /** @stable ICU 2.0 */ 1032 UBLOCK_YI_SYLLABLES =72, /*[A000]*/ 1033 1034 /** @stable ICU 2.0 */ 1035 UBLOCK_YI_RADICALS =73, /*[A490]*/ 1036 1037 /** @stable ICU 2.0 */ 1038 UBLOCK_HANGUL_SYLLABLES =74, /*[AC00]*/ 1039 1040 /** @stable ICU 2.0 */ 1041 UBLOCK_HIGH_SURROGATES =75, /*[D800]*/ 1042 1043 /** @stable ICU 2.0 */ 1044 UBLOCK_HIGH_PRIVATE_USE_SURROGATES =76, /*[DB80]*/ 1045 1046 /** @stable ICU 2.0 */ 1047 UBLOCK_LOW_SURROGATES =77, /*[DC00]*/ 1048 1049 /** 1050 * Same as UBLOCK_PRIVATE_USE_AREA. 1051 * Until Unicode 3.1.1, the corresponding block name was "Private Use", 1052 * and multiple code point ranges had this block. 1053 * Unicode 3.2 renames the block for the BMP PUA to "Private Use Area" and 1054 * adds separate blocks for the supplementary PUAs. 1055 * 1056 * @stable ICU 2.0 1057 */ 1058 UBLOCK_PRIVATE_USE = 78, 1059 /** 1060 * Same as UBLOCK_PRIVATE_USE. 1061 * Until Unicode 3.1.1, the corresponding block name was "Private Use", 1062 * and multiple code point ranges had this block. 1063 * Unicode 3.2 renames the block for the BMP PUA to "Private Use Area" and 1064 * adds separate blocks for the supplementary PUAs. 1065 * 1066 * @stable ICU 2.0 1067 */ 1068 UBLOCK_PRIVATE_USE_AREA =UBLOCK_PRIVATE_USE, /*[E000]*/ 1069 1070 /** @stable ICU 2.0 */ 1071 UBLOCK_CJK_COMPATIBILITY_IDEOGRAPHS =79, /*[F900]*/ 1072 1073 /** @stable ICU 2.0 */ 1074 UBLOCK_ALPHABETIC_PRESENTATION_FORMS =80, /*[FB00]*/ 1075 1076 /** @stable ICU 2.0 */ 1077 UBLOCK_ARABIC_PRESENTATION_FORMS_A =81, /*[FB50]*/ 1078 1079 /** @stable ICU 2.0 */ 1080 UBLOCK_COMBINING_HALF_MARKS =82, /*[FE20]*/ 1081 1082 /** @stable ICU 2.0 */ 1083 UBLOCK_CJK_COMPATIBILITY_FORMS =83, /*[FE30]*/ 1084 1085 /** @stable ICU 2.0 */ 1086 UBLOCK_SMALL_FORM_VARIANTS =84, /*[FE50]*/ 1087 1088 /** @stable ICU 2.0 */ 1089 UBLOCK_ARABIC_PRESENTATION_FORMS_B =85, /*[FE70]*/ 1090 1091 /** @stable ICU 2.0 */ 1092 UBLOCK_SPECIALS =86, /*[FFF0]*/ 1093 1094 /** @stable ICU 2.0 */ 1095 UBLOCK_HALFWIDTH_AND_FULLWIDTH_FORMS =87, /*[FF00]*/ 1096 1097 /* New blocks in Unicode 3.1 */ 1098 1099 /** @stable ICU 2.0 */ 1100 UBLOCK_OLD_ITALIC = 88 , /*[10300]*/ 1101 /** @stable ICU 2.0 */ 1102 UBLOCK_GOTHIC = 89 , /*[10330]*/ 1103 /** @stable ICU 2.0 */ 1104 UBLOCK_DESERET = 90 , /*[10400]*/ 1105 /** @stable ICU 2.0 */ 1106 UBLOCK_BYZANTINE_MUSICAL_SYMBOLS = 91 , /*[1D000]*/ 1107 /** @stable ICU 2.0 */ 1108 UBLOCK_MUSICAL_SYMBOLS = 92 , /*[1D100]*/ 1109 /** @stable ICU 2.0 */ 1110 UBLOCK_MATHEMATICAL_ALPHANUMERIC_SYMBOLS = 93 , /*[1D400]*/ 1111 /** @stable ICU 2.0 */ 1112 UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_B = 94 , /*[20000]*/ 1113 /** @stable ICU 2.0 */ 1114 UBLOCK_CJK_COMPATIBILITY_IDEOGRAPHS_SUPPLEMENT = 95 , /*[2F800]*/ 1115 /** @stable ICU 2.0 */ 1116 UBLOCK_TAGS = 96, /*[E0000]*/ 1117 1118 /* New blocks in Unicode 3.2 */ 1119 1120 /** 1121 * Unicode 4.0.1 renames the "Cyrillic Supplementary" block to "Cyrillic Supplement". 1122 * @stable ICU 2.2 1123 */ 1124 UBLOCK_CYRILLIC_SUPPLEMENTARY = 97, 1125 /** @stable ICU 3.0 */ 1126 UBLOCK_CYRILLIC_SUPPLEMENT = UBLOCK_CYRILLIC_SUPPLEMENTARY, /*[0500]*/ 1127 /** @stable ICU 2.2 */ 1128 UBLOCK_TAGALOG = 98, /*[1700]*/ 1129 /** @stable ICU 2.2 */ 1130 UBLOCK_HANUNOO = 99, /*[1720]*/ 1131 /** @stable ICU 2.2 */ 1132 UBLOCK_BUHID = 100, /*[1740]*/ 1133 /** @stable ICU 2.2 */ 1134 UBLOCK_TAGBANWA = 101, /*[1760]*/ 1135 /** @stable ICU 2.2 */ 1136 UBLOCK_MISCELLANEOUS_MATHEMATICAL_SYMBOLS_A = 102, /*[27C0]*/ 1137 /** @stable ICU 2.2 */ 1138 UBLOCK_SUPPLEMENTAL_ARROWS_A = 103, /*[27F0]*/ 1139 /** @stable ICU 2.2 */ 1140 UBLOCK_SUPPLEMENTAL_ARROWS_B = 104, /*[2900]*/ 1141 /** @stable ICU 2.2 */ 1142 UBLOCK_MISCELLANEOUS_MATHEMATICAL_SYMBOLS_B = 105, /*[2980]*/ 1143 /** @stable ICU 2.2 */ 1144 UBLOCK_SUPPLEMENTAL_MATHEMATICAL_OPERATORS = 106, /*[2A00]*/ 1145 /** @stable ICU 2.2 */ 1146 UBLOCK_KATAKANA_PHONETIC_EXTENSIONS = 107, /*[31F0]*/ 1147 /** @stable ICU 2.2 */ 1148 UBLOCK_VARIATION_SELECTORS = 108, /*[FE00]*/ 1149 /** @stable ICU 2.2 */ 1150 UBLOCK_SUPPLEMENTARY_PRIVATE_USE_AREA_A = 109, /*[F0000]*/ 1151 /** @stable ICU 2.2 */ 1152 UBLOCK_SUPPLEMENTARY_PRIVATE_USE_AREA_B = 110, /*[100000]*/ 1153 1154 /* New blocks in Unicode 4 */ 1155 1156 /** @stable ICU 2.6 */ 1157 UBLOCK_LIMBU = 111, /*[1900]*/ 1158 /** @stable ICU 2.6 */ 1159 UBLOCK_TAI_LE = 112, /*[1950]*/ 1160 /** @stable ICU 2.6 */ 1161 UBLOCK_KHMER_SYMBOLS = 113, /*[19E0]*/ 1162 /** @stable ICU 2.6 */ 1163 UBLOCK_PHONETIC_EXTENSIONS = 114, /*[1D00]*/ 1164 /** @stable ICU 2.6 */ 1165 UBLOCK_MISCELLANEOUS_SYMBOLS_AND_ARROWS = 115, /*[2B00]*/ 1166 /** @stable ICU 2.6 */ 1167 UBLOCK_YIJING_HEXAGRAM_SYMBOLS = 116, /*[4DC0]*/ 1168 /** @stable ICU 2.6 */ 1169 UBLOCK_LINEAR_B_SYLLABARY = 117, /*[10000]*/ 1170 /** @stable ICU 2.6 */ 1171 UBLOCK_LINEAR_B_IDEOGRAMS = 118, /*[10080]*/ 1172 /** @stable ICU 2.6 */ 1173 UBLOCK_AEGEAN_NUMBERS = 119, /*[10100]*/ 1174 /** @stable ICU 2.6 */ 1175 UBLOCK_UGARITIC = 120, /*[10380]*/ 1176 /** @stable ICU 2.6 */ 1177 UBLOCK_SHAVIAN = 121, /*[10450]*/ 1178 /** @stable ICU 2.6 */ 1179 UBLOCK_OSMANYA = 122, /*[10480]*/ 1180 /** @stable ICU 2.6 */ 1181 UBLOCK_CYPRIOT_SYLLABARY = 123, /*[10800]*/ 1182 /** @stable ICU 2.6 */ 1183 UBLOCK_TAI_XUAN_JING_SYMBOLS = 124, /*[1D300]*/ 1184 /** @stable ICU 2.6 */ 1185 UBLOCK_VARIATION_SELECTORS_SUPPLEMENT = 125, /*[E0100]*/ 1186 1187 /* New blocks in Unicode 4.1 */ 1188 1189 /** @stable ICU 3.4 */ 1190 UBLOCK_ANCIENT_GREEK_MUSICAL_NOTATION = 126, /*[1D200]*/ 1191 /** @stable ICU 3.4 */ 1192 UBLOCK_ANCIENT_GREEK_NUMBERS = 127, /*[10140]*/ 1193 /** @stable ICU 3.4 */ 1194 UBLOCK_ARABIC_SUPPLEMENT = 128, /*[0750]*/ 1195 /** @stable ICU 3.4 */ 1196 UBLOCK_BUGINESE = 129, /*[1A00]*/ 1197 /** @stable ICU 3.4 */ 1198 UBLOCK_CJK_STROKES = 130, /*[31C0]*/ 1199 /** @stable ICU 3.4 */ 1200 UBLOCK_COMBINING_DIACRITICAL_MARKS_SUPPLEMENT = 131, /*[1DC0]*/ 1201 /** @stable ICU 3.4 */ 1202 UBLOCK_COPTIC = 132, /*[2C80]*/ 1203 /** @stable ICU 3.4 */ 1204 UBLOCK_ETHIOPIC_EXTENDED = 133, /*[2D80]*/ 1205 /** @stable ICU 3.4 */ 1206 UBLOCK_ETHIOPIC_SUPPLEMENT = 134, /*[1380]*/ 1207 /** @stable ICU 3.4 */ 1208 UBLOCK_GEORGIAN_SUPPLEMENT = 135, /*[2D00]*/ 1209 /** @stable ICU 3.4 */ 1210 UBLOCK_GLAGOLITIC = 136, /*[2C00]*/ 1211 /** @stable ICU 3.4 */ 1212 UBLOCK_KHAROSHTHI = 137, /*[10A00]*/ 1213 /** @stable ICU 3.4 */ 1214 UBLOCK_MODIFIER_TONE_LETTERS = 138, /*[A700]*/ 1215 /** @stable ICU 3.4 */ 1216 UBLOCK_NEW_TAI_LUE = 139, /*[1980]*/ 1217 /** @stable ICU 3.4 */ 1218 UBLOCK_OLD_PERSIAN = 140, /*[103A0]*/ 1219 /** @stable ICU 3.4 */ 1220 UBLOCK_PHONETIC_EXTENSIONS_SUPPLEMENT = 141, /*[1D80]*/ 1221 /** @stable ICU 3.4 */ 1222 UBLOCK_SUPPLEMENTAL_PUNCTUATION = 142, /*[2E00]*/ 1223 /** @stable ICU 3.4 */ 1224 UBLOCK_SYLOTI_NAGRI = 143, /*[A800]*/ 1225 /** @stable ICU 3.4 */ 1226 UBLOCK_TIFINAGH = 144, /*[2D30]*/ 1227 /** @stable ICU 3.4 */ 1228 UBLOCK_VERTICAL_FORMS = 145, /*[FE10]*/ 1229 1230 /* New blocks in Unicode 5.0 */ 1231 1232 /** @stable ICU 3.6 */ 1233 UBLOCK_NKO = 146, /*[07C0]*/ 1234 /** @stable ICU 3.6 */ 1235 UBLOCK_BALINESE = 147, /*[1B00]*/ 1236 /** @stable ICU 3.6 */ 1237 UBLOCK_LATIN_EXTENDED_C = 148, /*[2C60]*/ 1238 /** @stable ICU 3.6 */ 1239 UBLOCK_LATIN_EXTENDED_D = 149, /*[A720]*/ 1240 /** @stable ICU 3.6 */ 1241 UBLOCK_PHAGS_PA = 150, /*[A840]*/ 1242 /** @stable ICU 3.6 */ 1243 UBLOCK_PHOENICIAN = 151, /*[10900]*/ 1244 /** @stable ICU 3.6 */ 1245 UBLOCK_CUNEIFORM = 152, /*[12000]*/ 1246 /** @stable ICU 3.6 */ 1247 UBLOCK_CUNEIFORM_NUMBERS_AND_PUNCTUATION = 153, /*[12400]*/ 1248 /** @stable ICU 3.6 */ 1249 UBLOCK_COUNTING_ROD_NUMERALS = 154, /*[1D360]*/ 1250 1251 /* New blocks in Unicode 5.1 */ 1252 1253 /** @stable ICU 4.0 */ 1254 UBLOCK_SUNDANESE = 155, /*[1B80]*/ 1255 /** @stable ICU 4.0 */ 1256 UBLOCK_LEPCHA = 156, /*[1C00]*/ 1257 /** @stable ICU 4.0 */ 1258 UBLOCK_OL_CHIKI = 157, /*[1C50]*/ 1259 /** @stable ICU 4.0 */ 1260 UBLOCK_CYRILLIC_EXTENDED_A = 158, /*[2DE0]*/ 1261 /** @stable ICU 4.0 */ 1262 UBLOCK_VAI = 159, /*[A500]*/ 1263 /** @stable ICU 4.0 */ 1264 UBLOCK_CYRILLIC_EXTENDED_B = 160, /*[A640]*/ 1265 /** @stable ICU 4.0 */ 1266 UBLOCK_SAURASHTRA = 161, /*[A880]*/ 1267 /** @stable ICU 4.0 */ 1268 UBLOCK_KAYAH_LI = 162, /*[A900]*/ 1269 /** @stable ICU 4.0 */ 1270 UBLOCK_REJANG = 163, /*[A930]*/ 1271 /** @stable ICU 4.0 */ 1272 UBLOCK_CHAM = 164, /*[AA00]*/ 1273 /** @stable ICU 4.0 */ 1274 UBLOCK_ANCIENT_SYMBOLS = 165, /*[10190]*/ 1275 /** @stable ICU 4.0 */ 1276 UBLOCK_PHAISTOS_DISC = 166, /*[101D0]*/ 1277 /** @stable ICU 4.0 */ 1278 UBLOCK_LYCIAN = 167, /*[10280]*/ 1279 /** @stable ICU 4.0 */ 1280 UBLOCK_CARIAN = 168, /*[102A0]*/ 1281 /** @stable ICU 4.0 */ 1282 UBLOCK_LYDIAN = 169, /*[10920]*/ 1283 /** @stable ICU 4.0 */ 1284 UBLOCK_MAHJONG_TILES = 170, /*[1F000]*/ 1285 /** @stable ICU 4.0 */ 1286 UBLOCK_DOMINO_TILES = 171, /*[1F030]*/ 1287 1288 /* New blocks in Unicode 5.2 */ 1289 1290 /** @draft ICU 4.4 */ 1291 UBLOCK_SAMARITAN = 172, /*[0800]*/ 1292 /** @draft ICU 4.4 */ 1293 UBLOCK_UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS_EXTENDED = 173, /*[18B0]*/ 1294 /** @draft ICU 4.4 */ 1295 UBLOCK_TAI_THAM = 174, /*[1A20]*/ 1296 /** @draft ICU 4.4 */ 1297 UBLOCK_VEDIC_EXTENSIONS = 175, /*[1CD0]*/ 1298 /** @draft ICU 4.4 */ 1299 UBLOCK_LISU = 176, /*[A4D0]*/ 1300 /** @draft ICU 4.4 */ 1301 UBLOCK_BAMUM = 177, /*[A6A0]*/ 1302 /** @draft ICU 4.4 */ 1303 UBLOCK_COMMON_INDIC_NUMBER_FORMS = 178, /*[A830]*/ 1304 /** @draft ICU 4.4 */ 1305 UBLOCK_DEVANAGARI_EXTENDED = 179, /*[A8E0]*/ 1306 /** @draft ICU 4.4 */ 1307 UBLOCK_HANGUL_JAMO_EXTENDED_A = 180, /*[A960]*/ 1308 /** @draft ICU 4.4 */ 1309 UBLOCK_JAVANESE = 181, /*[A980]*/ 1310 /** @draft ICU 4.4 */ 1311 UBLOCK_MYANMAR_EXTENDED_A = 182, /*[AA60]*/ 1312 /** @draft ICU 4.4 */ 1313 UBLOCK_TAI_VIET = 183, /*[AA80]*/ 1314 /** @draft ICU 4.4 */ 1315 UBLOCK_MEETEI_MAYEK = 184, /*[ABC0]*/ 1316 /** @draft ICU 4.4 */ 1317 UBLOCK_HANGUL_JAMO_EXTENDED_B = 185, /*[D7B0]*/ 1318 /** @draft ICU 4.4 */ 1319 UBLOCK_IMPERIAL_ARAMAIC = 186, /*[10840]*/ 1320 /** @draft ICU 4.4 */ 1321 UBLOCK_OLD_SOUTH_ARABIAN = 187, /*[10A60]*/ 1322 /** @draft ICU 4.4 */ 1323 UBLOCK_AVESTAN = 188, /*[10B00]*/ 1324 /** @draft ICU 4.4 */ 1325 UBLOCK_INSCRIPTIONAL_PARTHIAN = 189, /*[10B40]*/ 1326 /** @draft ICU 4.4 */ 1327 UBLOCK_INSCRIPTIONAL_PAHLAVI = 190, /*[10B60]*/ 1328 /** @draft ICU 4.4 */ 1329 UBLOCK_OLD_TURKIC = 191, /*[10C00]*/ 1330 /** @draft ICU 4.4 */ 1331 UBLOCK_RUMI_NUMERAL_SYMBOLS = 192, /*[10E60]*/ 1332 /** @draft ICU 4.4 */ 1333 UBLOCK_KAITHI = 193, /*[11080]*/ 1334 /** @draft ICU 4.4 */ 1335 UBLOCK_EGYPTIAN_HIEROGLYPHS = 194, /*[13000]*/ 1336 /** @draft ICU 4.4 */ 1337 UBLOCK_ENCLOSED_ALPHANUMERIC_SUPPLEMENT = 195, /*[1F100]*/ 1338 /** @draft ICU 4.4 */ 1339 UBLOCK_ENCLOSED_IDEOGRAPHIC_SUPPLEMENT = 196, /*[1F200]*/ 1340 /** @draft ICU 4.4 */ 1341 UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_C = 197, /*[2A700]*/ 1342 1343 /** @stable ICU 2.0 */ 1344 UBLOCK_COUNT = 198, 1345 1346 /** @stable ICU 2.0 */ 1347 UBLOCK_INVALID_CODE=-1 1348 }; 1349 1350 /** @stable ICU 2.0 */ 1351 typedef enum UBlockCode UBlockCode; 1352 1353 /** 1354 * East Asian Width constants. 1355 * 1356 * @see UCHAR_EAST_ASIAN_WIDTH 1357 * @see u_getIntPropertyValue 1358 * @stable ICU 2.2 1359 */ 1360 typedef enum UEastAsianWidth { 1361 U_EA_NEUTRAL, /*[N]*/ /*See note !!*/ 1362 U_EA_AMBIGUOUS, /*[A]*/ 1363 U_EA_HALFWIDTH, /*[H]*/ 1364 U_EA_FULLWIDTH, /*[F]*/ 1365 U_EA_NARROW, /*[Na]*/ 1366 U_EA_WIDE, /*[W]*/ 1367 U_EA_COUNT 1368 } UEastAsianWidth; 1369 /* 1370 * Implementation note: 1371 * Keep UEastAsianWidth constant values in sync with names list in genprops/props2.c. 1372 */ 1373 1374 /** 1375 * Selector constants for u_charName(). 1376 * u_charName() returns the "modern" name of a 1377 * Unicode character; or the name that was defined in 1378 * Unicode version 1.0, before the Unicode standard merged 1379 * with ISO-10646; or an "extended" name that gives each 1380 * Unicode code point a unique name. 1381 * 1382 * @see u_charName 1383 * @stable ICU 2.0 1384 */ 1385 typedef enum UCharNameChoice { 1386 U_UNICODE_CHAR_NAME, 1387 U_UNICODE_10_CHAR_NAME, 1388 U_EXTENDED_CHAR_NAME, 1389 U_CHAR_NAME_ALIAS, /**< Corrected name from NameAliases.txt. @draft ICU 4.4 */ 1390 U_CHAR_NAME_CHOICE_COUNT 1391 } UCharNameChoice; 1392 1393 /** 1394 * Selector constants for u_getPropertyName() and 1395 * u_getPropertyValueName(). These selectors are used to choose which 1396 * name is returned for a given property or value. All properties and 1397 * values have a long name. Most have a short name, but some do not. 1398 * Unicode allows for additional names, beyond the long and short 1399 * name, which would be indicated by U_LONG_PROPERTY_NAME + i, where 1400 * i=1, 2,... 1401 * 1402 * @see u_getPropertyName() 1403 * @see u_getPropertyValueName() 1404 * @stable ICU 2.4 1405 */ 1406 typedef enum UPropertyNameChoice { 1407 U_SHORT_PROPERTY_NAME, 1408 U_LONG_PROPERTY_NAME, 1409 U_PROPERTY_NAME_CHOICE_COUNT 1410 } UPropertyNameChoice; 1411 1412 /** 1413 * Decomposition Type constants. 1414 * 1415 * @see UCHAR_DECOMPOSITION_TYPE 1416 * @stable ICU 2.2 1417 */ 1418 typedef enum UDecompositionType { 1419 U_DT_NONE, /*[none]*/ /*See note !!*/ 1420 U_DT_CANONICAL, /*[can]*/ 1421 U_DT_COMPAT, /*[com]*/ 1422 U_DT_CIRCLE, /*[enc]*/ 1423 U_DT_FINAL, /*[fin]*/ 1424 U_DT_FONT, /*[font]*/ 1425 U_DT_FRACTION, /*[fra]*/ 1426 U_DT_INITIAL, /*[init]*/ 1427 U_DT_ISOLATED, /*[iso]*/ 1428 U_DT_MEDIAL, /*[med]*/ 1429 U_DT_NARROW, /*[nar]*/ 1430 U_DT_NOBREAK, /*[nb]*/ 1431 U_DT_SMALL, /*[sml]*/ 1432 U_DT_SQUARE, /*[sqr]*/ 1433 U_DT_SUB, /*[sub]*/ 1434 U_DT_SUPER, /*[sup]*/ 1435 U_DT_VERTICAL, /*[vert]*/ 1436 U_DT_WIDE, /*[wide]*/ 1437 U_DT_COUNT /* 18 */ 1438 } UDecompositionType; 1439 1440 /** 1441 * Joining Type constants. 1442 * 1443 * @see UCHAR_JOINING_TYPE 1444 * @stable ICU 2.2 1445 */ 1446 typedef enum UJoiningType { 1447 U_JT_NON_JOINING, /*[U]*/ /*See note !!*/ 1448 U_JT_JOIN_CAUSING, /*[C]*/ 1449 U_JT_DUAL_JOINING, /*[D]*/ 1450 U_JT_LEFT_JOINING, /*[L]*/ 1451 U_JT_RIGHT_JOINING, /*[R]*/ 1452 U_JT_TRANSPARENT, /*[T]*/ 1453 U_JT_COUNT /* 6 */ 1454 } UJoiningType; 1455 1456 /** 1457 * Joining Group constants. 1458 * 1459 * @see UCHAR_JOINING_GROUP 1460 * @stable ICU 2.2 1461 */ 1462 typedef enum UJoiningGroup { 1463 U_JG_NO_JOINING_GROUP, 1464 U_JG_AIN, 1465 U_JG_ALAPH, 1466 U_JG_ALEF, 1467 U_JG_BEH, 1468 U_JG_BETH, 1469 U_JG_DAL, 1470 U_JG_DALATH_RISH, 1471 U_JG_E, 1472 U_JG_FEH, 1473 U_JG_FINAL_SEMKATH, 1474 U_JG_GAF, 1475 U_JG_GAMAL, 1476 U_JG_HAH, 1477 U_JG_HAMZA_ON_HEH_GOAL, 1478 U_JG_HE, 1479 U_JG_HEH, 1480 U_JG_HEH_GOAL, 1481 U_JG_HETH, 1482 U_JG_KAF, 1483 U_JG_KAPH, 1484 U_JG_KNOTTED_HEH, 1485 U_JG_LAM, 1486 U_JG_LAMADH, 1487 U_JG_MEEM, 1488 U_JG_MIM, 1489 U_JG_NOON, 1490 U_JG_NUN, 1491 U_JG_PE, 1492 U_JG_QAF, 1493 U_JG_QAPH, 1494 U_JG_REH, 1495 U_JG_REVERSED_PE, 1496 U_JG_SAD, 1497 U_JG_SADHE, 1498 U_JG_SEEN, 1499 U_JG_SEMKATH, 1500 U_JG_SHIN, 1501 U_JG_SWASH_KAF, 1502 U_JG_SYRIAC_WAW, 1503 U_JG_TAH, 1504 U_JG_TAW, 1505 U_JG_TEH_MARBUTA, 1506 U_JG_TETH, 1507 U_JG_WAW, 1508 U_JG_YEH, 1509 U_JG_YEH_BARREE, 1510 U_JG_YEH_WITH_TAIL, 1511 U_JG_YUDH, 1512 U_JG_YUDH_HE, 1513 U_JG_ZAIN, 1514 U_JG_FE, /**< @stable ICU 2.6 */ 1515 U_JG_KHAPH, /**< @stable ICU 2.6 */ 1516 U_JG_ZHAIN, /**< @stable ICU 2.6 */ 1517 U_JG_BURUSHASKI_YEH_BARREE, /**< @stable ICU 4.0 */ 1518 U_JG_FARSI_YEH, /**< @draft ICU 4.4 */ 1519 U_JG_NYA, /**< @draft ICU 4.4 */ 1520 U_JG_COUNT 1521 } UJoiningGroup; 1522 1523 /** 1524 * Grapheme Cluster Break constants. 1525 * 1526 * @see UCHAR_GRAPHEME_CLUSTER_BREAK 1527 * @stable ICU 3.4 1528 */ 1529 typedef enum UGraphemeClusterBreak { 1530 U_GCB_OTHER = 0, /*[XX]*/ /*See note !!*/ 1531 U_GCB_CONTROL = 1, /*[CN]*/ 1532 U_GCB_CR = 2, /*[CR]*/ 1533 U_GCB_EXTEND = 3, /*[EX]*/ 1534 U_GCB_L = 4, /*[L]*/ 1535 U_GCB_LF = 5, /*[LF]*/ 1536 U_GCB_LV = 6, /*[LV]*/ 1537 U_GCB_LVT = 7, /*[LVT]*/ 1538 U_GCB_T = 8, /*[T]*/ 1539 U_GCB_V = 9, /*[V]*/ 1540 U_GCB_SPACING_MARK = 10, /*[SM]*/ /* from here on: new in Unicode 5.1/ICU 4.0 */ 1541 U_GCB_PREPEND = 11, /*[PP]*/ 1542 U_GCB_COUNT = 12 1543 } UGraphemeClusterBreak; 1544 1545 /** 1546 * Word Break constants. 1547 * (UWordBreak is a pre-existing enum type in ubrk.h for word break status tags.) 1548 * 1549 * @see UCHAR_WORD_BREAK 1550 * @stable ICU 3.4 1551 */ 1552 typedef enum UWordBreakValues { 1553 U_WB_OTHER = 0, /*[XX]*/ /*See note !!*/ 1554 U_WB_ALETTER = 1, /*[LE]*/ 1555 U_WB_FORMAT = 2, /*[FO]*/ 1556 U_WB_KATAKANA = 3, /*[KA]*/ 1557 U_WB_MIDLETTER = 4, /*[ML]*/ 1558 U_WB_MIDNUM = 5, /*[MN]*/ 1559 U_WB_NUMERIC = 6, /*[NU]*/ 1560 U_WB_EXTENDNUMLET = 7, /*[EX]*/ 1561 U_WB_CR = 8, /*[CR]*/ /* from here on: new in Unicode 5.1/ICU 4.0 */ 1562 U_WB_EXTEND = 9, /*[Extend]*/ 1563 U_WB_LF = 10, /*[LF]*/ 1564 U_WB_MIDNUMLET =11, /*[MB]*/ 1565 U_WB_NEWLINE =12, /*[NL]*/ 1566 U_WB_COUNT = 13 1567 } UWordBreakValues; 1568 1569 /** 1570 * Sentence Break constants. 1571 * 1572 * @see UCHAR_SENTENCE_BREAK 1573 * @stable ICU 3.4 1574 */ 1575 typedef enum USentenceBreak { 1576 U_SB_OTHER = 0, /*[XX]*/ /*See note !!*/ 1577 U_SB_ATERM = 1, /*[AT]*/ 1578 U_SB_CLOSE = 2, /*[CL]*/ 1579 U_SB_FORMAT = 3, /*[FO]*/ 1580 U_SB_LOWER = 4, /*[LO]*/ 1581 U_SB_NUMERIC = 5, /*[NU]*/ 1582 U_SB_OLETTER = 6, /*[LE]*/ 1583 U_SB_SEP = 7, /*[SE]*/ 1584 U_SB_SP = 8, /*[SP]*/ 1585 U_SB_STERM = 9, /*[ST]*/ 1586 U_SB_UPPER = 10, /*[UP]*/ 1587 U_SB_CR = 11, /*[CR]*/ /* from here on: new in Unicode 5.1/ICU 4.0 */ 1588 U_SB_EXTEND = 12, /*[EX]*/ 1589 U_SB_LF = 13, /*[LF]*/ 1590 U_SB_SCONTINUE = 14, /*[SC]*/ 1591 U_SB_COUNT = 15 1592 } USentenceBreak; 1593 1594 /** 1595 * Line Break constants. 1596 * 1597 * @see UCHAR_LINE_BREAK 1598 * @stable ICU 2.2 1599 */ 1600 typedef enum ULineBreak { 1601 U_LB_UNKNOWN = 0, /*[XX]*/ /*See note !!*/ 1602 U_LB_AMBIGUOUS = 1, /*[AI]*/ 1603 U_LB_ALPHABETIC = 2, /*[AL]*/ 1604 U_LB_BREAK_BOTH = 3, /*[B2]*/ 1605 U_LB_BREAK_AFTER = 4, /*[BA]*/ 1606 U_LB_BREAK_BEFORE = 5, /*[BB]*/ 1607 U_LB_MANDATORY_BREAK = 6, /*[BK]*/ 1608 U_LB_CONTINGENT_BREAK = 7, /*[CB]*/ 1609 U_LB_CLOSE_PUNCTUATION = 8, /*[CL]*/ 1610 U_LB_COMBINING_MARK = 9, /*[CM]*/ 1611 U_LB_CARRIAGE_RETURN = 10, /*[CR]*/ 1612 U_LB_EXCLAMATION = 11, /*[EX]*/ 1613 U_LB_GLUE = 12, /*[GL]*/ 1614 U_LB_HYPHEN = 13, /*[HY]*/ 1615 U_LB_IDEOGRAPHIC = 14, /*[ID]*/ 1616 U_LB_INSEPERABLE = 15, 1617 /** Renamed from the misspelled "inseperable" in Unicode 4.0.1/ICU 3.0 @stable ICU 3.0 */ 1618 U_LB_INSEPARABLE=U_LB_INSEPERABLE,/*[IN]*/ 1619 U_LB_INFIX_NUMERIC = 16, /*[IS]*/ 1620 U_LB_LINE_FEED = 17, /*[LF]*/ 1621 U_LB_NONSTARTER = 18, /*[NS]*/ 1622 U_LB_NUMERIC = 19, /*[NU]*/ 1623 U_LB_OPEN_PUNCTUATION = 20, /*[OP]*/ 1624 U_LB_POSTFIX_NUMERIC = 21, /*[PO]*/ 1625 U_LB_PREFIX_NUMERIC = 22, /*[PR]*/ 1626 U_LB_QUOTATION = 23, /*[QU]*/ 1627 U_LB_COMPLEX_CONTEXT = 24, /*[SA]*/ 1628 U_LB_SURROGATE = 25, /*[SG]*/ 1629 U_LB_SPACE = 26, /*[SP]*/ 1630 U_LB_BREAK_SYMBOLS = 27, /*[SY]*/ 1631 U_LB_ZWSPACE = 28, /*[ZW]*/ 1632 U_LB_NEXT_LINE = 29, /*[NL]*/ /* from here on: new in Unicode 4/ICU 2.6 */ 1633 U_LB_WORD_JOINER = 30, /*[WJ]*/ 1634 U_LB_H2 = 31, /*[H2]*/ /* from here on: new in Unicode 4.1/ICU 3.4 */ 1635 U_LB_H3 = 32, /*[H3]*/ 1636 U_LB_JL = 33, /*[JL]*/ 1637 U_LB_JT = 34, /*[JT]*/ 1638 U_LB_JV = 35, /*[JV]*/ 1639 U_LB_CLOSE_PARENTHESIS = 36, /*[CP]*/ /* new in Unicode 5.2/ICU 4.4 */ 1640 U_LB_COUNT = 37 1641 } ULineBreak; 1642 1643 /** 1644 * Numeric Type constants. 1645 * 1646 * @see UCHAR_NUMERIC_TYPE 1647 * @stable ICU 2.2 1648 */ 1649 typedef enum UNumericType { 1650 U_NT_NONE, /*[None]*/ /*See note !!*/ 1651 U_NT_DECIMAL, /*[de]*/ 1652 U_NT_DIGIT, /*[di]*/ 1653 U_NT_NUMERIC, /*[nu]*/ 1654 U_NT_COUNT 1655 } UNumericType; 1656 1657 /** 1658 * Hangul Syllable Type constants. 1659 * 1660 * @see UCHAR_HANGUL_SYLLABLE_TYPE 1661 * @stable ICU 2.6 1662 */ 1663 typedef enum UHangulSyllableType { 1664 U_HST_NOT_APPLICABLE, /*[NA]*/ /*See note !!*/ 1665 U_HST_LEADING_JAMO, /*[L]*/ 1666 U_HST_VOWEL_JAMO, /*[V]*/ 1667 U_HST_TRAILING_JAMO, /*[T]*/ 1668 U_HST_LV_SYLLABLE, /*[LV]*/ 1669 U_HST_LVT_SYLLABLE, /*[LVT]*/ 1670 U_HST_COUNT 1671 } UHangulSyllableType; 1672 1673 /** 1674 * Check a binary Unicode property for a code point. 1675 * 1676 * Unicode, especially in version 3.2, defines many more properties than the 1677 * original set in UnicodeData.txt. 1678 * 1679 * The properties APIs are intended to reflect Unicode properties as defined 1680 * in the Unicode Character Database (UCD) and Unicode Technical Reports (UTR). 1681 * For details about the properties see http://www.unicode.org/ucd/ . 1682 * For names of Unicode properties see the UCD file PropertyAliases.txt. 1683 * 1684 * Important: If ICU is built with UCD files from Unicode versions below 3.2, 1685 * then properties marked with "new in Unicode 3.2" are not or not fully available. 1686 * 1687 * @param c Code point to test. 1688 * @param which UProperty selector constant, identifies which binary property to check. 1689 * Must be UCHAR_BINARY_START<=which<UCHAR_BINARY_LIMIT. 1690 * @return TRUE or FALSE according to the binary Unicode property value for c. 1691 * Also FALSE if 'which' is out of bounds or if the Unicode version 1692 * does not have data for the property at all, or not for this code point. 1693 * 1694 * @see UProperty 1695 * @see u_getIntPropertyValue 1696 * @see u_getUnicodeVersion 1697 * @stable ICU 2.1 1698 */ 1699 U_STABLE UBool U_EXPORT2 1700 u_hasBinaryProperty(UChar32 c, UProperty which); 1701 1702 /** 1703 * Check if a code point has the Alphabetic Unicode property. 1704 * Same as u_hasBinaryProperty(c, UCHAR_ALPHABETIC). 1705 * This is different from u_isalpha! 1706 * @param c Code point to test 1707 * @return true if the code point has the Alphabetic Unicode property, false otherwise 1708 * 1709 * @see UCHAR_ALPHABETIC 1710 * @see u_isalpha 1711 * @see u_hasBinaryProperty 1712 * @stable ICU 2.1 1713 */ 1714 U_STABLE UBool U_EXPORT2 1715 u_isUAlphabetic(UChar32 c); 1716 1717 /** 1718 * Check if a code point has the Lowercase Unicode property. 1719 * Same as u_hasBinaryProperty(c, UCHAR_LOWERCASE). 1720 * This is different from u_islower! 1721 * @param c Code point to test 1722 * @return true if the code point has the Lowercase Unicode property, false otherwise 1723 * 1724 * @see UCHAR_LOWERCASE 1725 * @see u_islower 1726 * @see u_hasBinaryProperty 1727 * @stable ICU 2.1 1728 */ 1729 U_STABLE UBool U_EXPORT2 1730 u_isULowercase(UChar32 c); 1731 1732 /** 1733 * Check if a code point has the Uppercase Unicode property. 1734 * Same as u_hasBinaryProperty(c, UCHAR_UPPERCASE). 1735 * This is different from u_isupper! 1736 * @param c Code point to test 1737 * @return true if the code point has the Uppercase Unicode property, false otherwise 1738 * 1739 * @see UCHAR_UPPERCASE 1740 * @see u_isupper 1741 * @see u_hasBinaryProperty 1742 * @stable ICU 2.1 1743 */ 1744 U_STABLE UBool U_EXPORT2 1745 u_isUUppercase(UChar32 c); 1746 1747 /** 1748 * Check if a code point has the White_Space Unicode property. 1749 * Same as u_hasBinaryProperty(c, UCHAR_WHITE_SPACE). 1750 * This is different from both u_isspace and u_isWhitespace! 1751 * 1752 * Note: There are several ICU whitespace functions; please see the uchar.h 1753 * file documentation for a detailed comparison. 1754 * 1755 * @param c Code point to test 1756 * @return true if the code point has the White_Space Unicode property, false otherwise. 1757 * 1758 * @see UCHAR_WHITE_SPACE 1759 * @see u_isWhitespace 1760 * @see u_isspace 1761 * @see u_isJavaSpaceChar 1762 * @see u_hasBinaryProperty 1763 * @stable ICU 2.1 1764 */ 1765 U_STABLE UBool U_EXPORT2 1766 u_isUWhiteSpace(UChar32 c); 1767 1768 /** 1769 * Get the property value for an enumerated or integer Unicode property for a code point. 1770 * Also returns binary and mask property values. 1771 * 1772 * Unicode, especially in version 3.2, defines many more properties than the 1773 * original set in UnicodeData.txt. 1774 * 1775 * The properties APIs are intended to reflect Unicode properties as defined 1776 * in the Unicode Character Database (UCD) and Unicode Technical Reports (UTR). 1777 * For details about the properties see http://www.unicode.org/ . 1778 * For names of Unicode properties see the UCD file PropertyAliases.txt. 1779 * 1780 * Sample usage: 1781 * UEastAsianWidth ea=(UEastAsianWidth)u_getIntPropertyValue(c, UCHAR_EAST_ASIAN_WIDTH); 1782 * UBool b=(UBool)u_getIntPropertyValue(c, UCHAR_IDEOGRAPHIC); 1783 * 1784 * @param c Code point to test. 1785 * @param which UProperty selector constant, identifies which property to check. 1786 * Must be UCHAR_BINARY_START<=which<UCHAR_BINARY_LIMIT 1787 * or UCHAR_INT_START<=which<UCHAR_INT_LIMIT 1788 * or UCHAR_MASK_START<=which<UCHAR_MASK_LIMIT. 1789 * @return Numeric value that is directly the property value or, 1790 * for enumerated properties, corresponds to the numeric value of the enumerated 1791 * constant of the respective property value enumeration type 1792 * (cast to enum type if necessary). 1793 * Returns 0 or 1 (for FALSE/TRUE) for binary Unicode properties. 1794 * Returns a bit-mask for mask properties. 1795 * Returns 0 if 'which' is out of bounds or if the Unicode version 1796 * does not have data for the property at all, or not for this code point. 1797 * 1798 * @see UProperty 1799 * @see u_hasBinaryProperty 1800 * @see u_getIntPropertyMinValue 1801 * @see u_getIntPropertyMaxValue 1802 * @see u_getUnicodeVersion 1803 * @stable ICU 2.2 1804 */ 1805 U_STABLE int32_t U_EXPORT2 1806 u_getIntPropertyValue(UChar32 c, UProperty which); 1807 1808 /** 1809 * Get the minimum value for an enumerated/integer/binary Unicode property. 1810 * Can be used together with u_getIntPropertyMaxValue 1811 * to allocate arrays of UnicodeSet or similar. 1812 * 1813 * @param which UProperty selector constant, identifies which binary property to check. 1814 * Must be UCHAR_BINARY_START<=which<UCHAR_BINARY_LIMIT 1815 * or UCHAR_INT_START<=which<UCHAR_INT_LIMIT. 1816 * @return Minimum value returned by u_getIntPropertyValue for a Unicode property. 1817 * 0 if the property selector is out of range. 1818 * 1819 * @see UProperty 1820 * @see u_hasBinaryProperty 1821 * @see u_getUnicodeVersion 1822 * @see u_getIntPropertyMaxValue 1823 * @see u_getIntPropertyValue 1824 * @stable ICU 2.2 1825 */ 1826 U_STABLE int32_t U_EXPORT2 1827 u_getIntPropertyMinValue(UProperty which); 1828 1829 /** 1830 * Get the maximum value for an enumerated/integer/binary Unicode property. 1831 * Can be used together with u_getIntPropertyMinValue 1832 * to allocate arrays of UnicodeSet or similar. 1833 * 1834 * Examples for min/max values (for Unicode 3.2): 1835 * 1836 * - UCHAR_BIDI_CLASS: 0/18 (U_LEFT_TO_RIGHT/U_BOUNDARY_NEUTRAL) 1837 * - UCHAR_SCRIPT: 0/45 (USCRIPT_COMMON/USCRIPT_TAGBANWA) 1838 * - UCHAR_IDEOGRAPHIC: 0/1 (FALSE/TRUE) 1839 * 1840 * For undefined UProperty constant values, min/max values will be 0/-1. 1841 * 1842 * @param which UProperty selector constant, identifies which binary property to check. 1843 * Must be UCHAR_BINARY_START<=which<UCHAR_BINARY_LIMIT 1844 * or UCHAR_INT_START<=which<UCHAR_INT_LIMIT. 1845 * @return Maximum value returned by u_getIntPropertyValue for a Unicode property. 1846 * <=0 if the property selector is out of range. 1847 * 1848 * @see UProperty 1849 * @see u_hasBinaryProperty 1850 * @see u_getUnicodeVersion 1851 * @see u_getIntPropertyMaxValue 1852 * @see u_getIntPropertyValue 1853 * @stable ICU 2.2 1854 */ 1855 U_STABLE int32_t U_EXPORT2 1856 u_getIntPropertyMaxValue(UProperty which); 1857 1858 /** 1859 * Get the numeric value for a Unicode code point as defined in the 1860 * Unicode Character Database. 1861 * 1862 * A "double" return type is necessary because 1863 * some numeric values are fractions, negative, or too large for int32_t. 1864 * 1865 * For characters without any numeric values in the Unicode Character Database, 1866 * this function will return U_NO_NUMERIC_VALUE. 1867 * 1868 * Similar to java.lang.Character.getNumericValue(), but u_getNumericValue() 1869 * also supports negative values, large values, and fractions, 1870 * while Java's getNumericValue() returns values 10..35 for ASCII letters. 1871 * 1872 * @param c Code point to get the numeric value for. 1873 * @return Numeric value of c, or U_NO_NUMERIC_VALUE if none is defined. 1874 * 1875 * @see U_NO_NUMERIC_VALUE 1876 * @stable ICU 2.2 1877 */ 1878 U_STABLE double U_EXPORT2 1879 u_getNumericValue(UChar32 c); 1880 1881 /** 1882 * Special value that is returned by u_getNumericValue when 1883 * no numeric value is defined for a code point. 1884 * 1885 * @see u_getNumericValue 1886 * @stable ICU 2.2 1887 */ 1888 #define U_NO_NUMERIC_VALUE ((double)-123456789.) 1889 1890 /** 1891 * Determines whether the specified code point has the general category "Ll" 1892 * (lowercase letter). 1893 * 1894 * Same as java.lang.Character.isLowerCase(). 1895 * 1896 * This misses some characters that are also lowercase but 1897 * have a different general category value. 1898 * In order to include those, use UCHAR_LOWERCASE. 1899 * 1900 * In addition to being equivalent to a Java function, this also serves 1901 * as a C/POSIX migration function. 1902 * See the comments about C/POSIX character classification functions in the 1903 * documentation at the top of this header file. 1904 * 1905 * @param c the code point to be tested 1906 * @return TRUE if the code point is an Ll lowercase letter 1907 * 1908 * @see UCHAR_LOWERCASE 1909 * @see u_isupper 1910 * @see u_istitle 1911 * @stable ICU 2.0 1912 */ 1913 U_STABLE UBool U_EXPORT2 1914 u_islower(UChar32 c); 1915 1916 /** 1917 * Determines whether the specified code point has the general category "Lu" 1918 * (uppercase letter). 1919 * 1920 * Same as java.lang.Character.isUpperCase(). 1921 * 1922 * This misses some characters that are also uppercase but 1923 * have a different general category value. 1924 * In order to include those, use UCHAR_UPPERCASE. 1925 * 1926 * In addition to being equivalent to a Java function, this also serves 1927 * as a C/POSIX migration function. 1928 * See the comments about C/POSIX character classification functions in the 1929 * documentation at the top of this header file. 1930 * 1931 * @param c the code point to be tested 1932 * @return TRUE if the code point is an Lu uppercase letter 1933 * 1934 * @see UCHAR_UPPERCASE 1935 * @see u_islower 1936 * @see u_istitle 1937 * @see u_tolower 1938 * @stable ICU 2.0 1939 */ 1940 U_STABLE UBool U_EXPORT2 1941 u_isupper(UChar32 c); 1942 1943 /** 1944 * Determines whether the specified code point is a titlecase letter. 1945 * True for general category "Lt" (titlecase letter). 1946 * 1947 * Same as java.lang.Character.isTitleCase(). 1948 * 1949 * @param c the code point to be tested 1950 * @return TRUE if the code point is an Lt titlecase letter 1951 * 1952 * @see u_isupper 1953 * @see u_islower 1954 * @see u_totitle 1955 * @stable ICU 2.0 1956 */ 1957 U_STABLE UBool U_EXPORT2 1958 u_istitle(UChar32 c); 1959 1960 /** 1961 * Determines whether the specified code point is a digit character according to Java. 1962 * True for characters with general category "Nd" (decimal digit numbers). 1963 * Beginning with Unicode 4, this is the same as 1964 * testing for the Numeric_Type of Decimal. 1965 * 1966 * Same as java.lang.Character.isDigit(). 1967 * 1968 * In addition to being equivalent to a Java function, this also serves 1969 * as a C/POSIX migration function. 1970 * See the comments about C/POSIX character classification functions in the 1971 * documentation at the top of this header file. 1972 * 1973 * @param c the code point to be tested 1974 * @return TRUE if the code point is a digit character according to Character.isDigit() 1975 * 1976 * @stable ICU 2.0 1977 */ 1978 U_STABLE UBool U_EXPORT2 1979 u_isdigit(UChar32 c); 1980 1981 /** 1982 * Determines whether the specified code point is a letter character. 1983 * True for general categories "L" (letters). 1984 * 1985 * Same as java.lang.Character.isLetter(). 1986 * 1987 * In addition to being equivalent to a Java function, this also serves 1988 * as a C/POSIX migration function. 1989 * See the comments about C/POSIX character classification functions in the 1990 * documentation at the top of this header file. 1991 * 1992 * @param c the code point to be tested 1993 * @return TRUE if the code point is a letter character 1994 * 1995 * @see u_isdigit 1996 * @see u_isalnum 1997 * @stable ICU 2.0 1998 */ 1999 U_STABLE UBool U_EXPORT2 2000 u_isalpha(UChar32 c); 2001 2002 /** 2003 * Determines whether the specified code point is an alphanumeric character 2004 * (letter or digit) according to Java. 2005 * True for characters with general categories 2006 * "L" (letters) and "Nd" (decimal digit numbers). 2007 * 2008 * Same as java.lang.Character.isLetterOrDigit(). 2009 * 2010 * In addition to being equivalent to a Java function, this also serves 2011 * as a C/POSIX migration function. 2012 * See the comments about C/POSIX character classification functions in the 2013 * documentation at the top of this header file. 2014 * 2015 * @param c the code point to be tested 2016 * @return TRUE if the code point is an alphanumeric character according to Character.isLetterOrDigit() 2017 * 2018 * @stable ICU 2.0 2019 */ 2020 U_STABLE UBool U_EXPORT2 2021 u_isalnum(UChar32 c); 2022 2023 /** 2024 * Determines whether the specified code point is a hexadecimal digit. 2025 * This is equivalent to u_digit(c, 16)>=0. 2026 * True for characters with general category "Nd" (decimal digit numbers) 2027 * as well as Latin letters a-f and A-F in both ASCII and Fullwidth ASCII. 2028 * (That is, for letters with code points 2029 * 0041..0046, 0061..0066, FF21..FF26, FF41..FF46.) 2030 * 2031 * In order to narrow the definition of hexadecimal digits to only ASCII 2032 * characters, use (c<=0x7f && u_isxdigit(c)). 2033 * 2034 * This is a C/POSIX migration function. 2035 * See the comments about C/POSIX character classification functions in the 2036 * documentation at the top of this header file. 2037 * 2038 * @param c the code point to be tested 2039 * @return TRUE if the code point is a hexadecimal digit 2040 * 2041 * @stable ICU 2.6 2042 */ 2043 U_STABLE UBool U_EXPORT2 2044 u_isxdigit(UChar32 c); 2045 2046 /** 2047 * Determines whether the specified code point is a punctuation character. 2048 * True for characters with general categories "P" (punctuation). 2049 * 2050 * This is a C/POSIX migration function. 2051 * See the comments about C/POSIX character classification functions in the 2052 * documentation at the top of this header file. 2053 * 2054 * @param c the code point to be tested 2055 * @return TRUE if the code point is a punctuation character 2056 * 2057 * @stable ICU 2.6 2058 */ 2059 U_STABLE UBool U_EXPORT2 2060 u_ispunct(UChar32 c); 2061 2062 /** 2063 * Determines whether the specified code point is a "graphic" character 2064 * (printable, excluding spaces). 2065 * TRUE for all characters except those with general categories 2066 * "Cc" (control codes), "Cf" (format controls), "Cs" (surrogates), 2067 * "Cn" (unassigned), and "Z" (separators). 2068 * 2069 * This is a C/POSIX migration function. 2070 * See the comments about C/POSIX character classification functions in the 2071 * documentation at the top of this header file. 2072 * 2073 * @param c the code point to be tested 2074 * @return TRUE if the code point is a "graphic" character 2075 * 2076 * @stable ICU 2.6 2077 */ 2078 U_STABLE UBool U_EXPORT2 2079 u_isgraph(UChar32 c); 2080 2081 /** 2082 * Determines whether the specified code point is a "blank" or "horizontal space", 2083 * a character that visibly separates words on a line. 2084 * The following are equivalent definitions: 2085 * 2086 * TRUE for Unicode White_Space characters except for "vertical space controls" 2087 * where "vertical space controls" are the following characters: 2088 * U+000A (LF) U+000B (VT) U+000C (FF) U+000D (CR) U+0085 (NEL) U+2028 (LS) U+2029 (PS) 2089 * 2090 * same as 2091 * 2092 * TRUE for U+0009 (TAB) and characters with general category "Zs" (space separators) 2093 * except Zero Width Space (ZWSP, U+200B). 2094 * 2095 * Note: There are several ICU whitespace functions; please see the uchar.h 2096 * file documentation for a detailed comparison. 2097 * 2098 * This is a C/POSIX migration function. 2099 * See the comments about C/POSIX character classification functions in the 2100 * documentation at the top of this header file. 2101 * 2102 * @param c the code point to be tested 2103 * @return TRUE if the code point is a "blank" 2104 * 2105 * @stable ICU 2.6 2106 */ 2107 U_STABLE UBool U_EXPORT2 2108 u_isblank(UChar32 c); 2109 2110 /** 2111 * Determines whether the specified code point is "defined", 2112 * which usually means that it is assigned a character. 2113 * True for general categories other than "Cn" (other, not assigned), 2114 * i.e., true for all code points mentioned in UnicodeData.txt. 2115 * 2116 * Note that non-character code points (e.g., U+FDD0) are not "defined" 2117 * (they are Cn), but surrogate code points are "defined" (Cs). 2118 * 2119 * Same as java.lang.Character.isDefined(). 2120 * 2121 * @param c the code point to be tested 2122 * @return TRUE if the code point is assigned a character 2123 * 2124 * @see u_isdigit 2125 * @see u_isalpha 2126 * @see u_isalnum 2127 * @see u_isupper 2128 * @see u_islower 2129 * @see u_istitle 2130 * @stable ICU 2.0 2131 */ 2132 U_STABLE UBool U_EXPORT2 2133 u_isdefined(UChar32 c); 2134 2135 /** 2136 * Determines if the specified character is a space character or not. 2137 * 2138 * Note: There are several ICU whitespace functions; please see the uchar.h 2139 * file documentation for a detailed comparison. 2140 * 2141 * This is a C/POSIX migration function. 2142 * See the comments about C/POSIX character classification functions in the 2143 * documentation at the top of this header file. 2144 * 2145 * @param c the character to be tested 2146 * @return true if the character is a space character; false otherwise. 2147 * 2148 * @see u_isJavaSpaceChar 2149 * @see u_isWhitespace 2150 * @see u_isUWhiteSpace 2151 * @stable ICU 2.0 2152 */ 2153 U_STABLE UBool U_EXPORT2 2154 u_isspace(UChar32 c); 2155 2156 /** 2157 * Determine if the specified code point is a space character according to Java. 2158 * True for characters with general categories "Z" (separators), 2159 * which does not include control codes (e.g., TAB or Line Feed). 2160 * 2161 * Same as java.lang.Character.isSpaceChar(). 2162 * 2163 * Note: There are several ICU whitespace functions; please see the uchar.h 2164 * file documentation for a detailed comparison. 2165 * 2166 * @param c the code point to be tested 2167 * @return TRUE if the code point is a space character according to Character.isSpaceChar() 2168 * 2169 * @see u_isspace 2170 * @see u_isWhitespace 2171 * @see u_isUWhiteSpace 2172 * @stable ICU 2.6 2173 */ 2174 U_STABLE UBool U_EXPORT2 2175 u_isJavaSpaceChar(UChar32 c); 2176 2177 /** 2178 * Determines if the specified code point is a whitespace character according to Java/ICU. 2179 * A character is considered to be a Java whitespace character if and only 2180 * if it satisfies one of the following criteria: 2181 * 2182 * - It is a Unicode Separator character (categories "Z" = "Zs" or "Zl" or "Zp"), but is not 2183 * also a non-breaking space (U+00A0 NBSP or U+2007 Figure Space or U+202F Narrow NBSP). 2184 * - It is U+0009 HORIZONTAL TABULATION. 2185 * - It is U+000A LINE FEED. 2186 * - It is U+000B VERTICAL TABULATION. 2187 * - It is U+000C FORM FEED. 2188 * - It is U+000D CARRIAGE RETURN. 2189 * - It is U+001C FILE SEPARATOR. 2190 * - It is U+001D GROUP SEPARATOR. 2191 * - It is U+001E RECORD SEPARATOR. 2192 * - It is U+001F UNIT SEPARATOR. 2193 * 2194 * This API tries to sync with the semantics of Java's 2195 * java.lang.Character.isWhitespace(), but it may not return 2196 * the exact same results because of the Unicode version 2197 * difference. 2198 * 2199 * Note: Unicode 4.0.1 changed U+200B ZERO WIDTH SPACE from a Space Separator (Zs) 2200 * to a Format Control (Cf). Since then, isWhitespace(0x200b) returns false. 2201 * See http://www.unicode.org/versions/Unicode4.0.1/ 2202 * 2203 * Note: There are several ICU whitespace functions; please see the uchar.h 2204 * file documentation for a detailed comparison. 2205 * 2206 * @param c the code point to be tested 2207 * @return TRUE if the code point is a whitespace character according to Java/ICU 2208 * 2209 * @see u_isspace 2210 * @see u_isJavaSpaceChar 2211 * @see u_isUWhiteSpace 2212 * @stable ICU 2.0 2213 */ 2214 U_STABLE UBool U_EXPORT2 2215 u_isWhitespace(UChar32 c); 2216 2217 /** 2218 * Determines whether the specified code point is a control character 2219 * (as defined by this function). 2220 * A control character is one of the following: 2221 * - ISO 8-bit control character (U+0000..U+001f and U+007f..U+009f) 2222 * - U_CONTROL_CHAR (Cc) 2223 * - U_FORMAT_CHAR (Cf) 2224 * - U_LINE_SEPARATOR (Zl) 2225 * - U_PARAGRAPH_SEPARATOR (Zp) 2226 * 2227 * This is a C/POSIX migration function. 2228 * See the comments about C/POSIX character classification functions in the 2229 * documentation at the top of this header file. 2230 * 2231 * @param c the code point to be tested 2232 * @return TRUE if the code point is a control character 2233 * 2234 * @see UCHAR_DEFAULT_IGNORABLE_CODE_POINT 2235 * @see u_isprint 2236 * @stable ICU 2.0 2237 */ 2238 U_STABLE UBool U_EXPORT2 2239 u_iscntrl(UChar32 c); 2240 2241 /** 2242 * Determines whether the specified code point is an ISO control code. 2243 * True for U+0000..U+001f and U+007f..U+009f (general category "Cc"). 2244 * 2245 * Same as java.lang.Character.isISOControl(). 2246 * 2247 * @param c the code point to be tested 2248 * @return TRUE if the code point is an ISO control code 2249 * 2250 * @see u_iscntrl 2251 * @stable ICU 2.6 2252 */ 2253 U_STABLE UBool U_EXPORT2 2254 u_isISOControl(UChar32 c); 2255 2256 /** 2257 * Determines whether the specified code point is a printable character. 2258 * True for general categories <em>other</em> than "C" (controls). 2259 * 2260 * This is a C/POSIX migration function. 2261 * See the comments about C/POSIX character classification functions in the 2262 * documentation at the top of this header file. 2263 * 2264 * @param c the code point to be tested 2265 * @return TRUE if the code point is a printable character 2266 * 2267 * @see UCHAR_DEFAULT_IGNORABLE_CODE_POINT 2268 * @see u_iscntrl 2269 * @stable ICU 2.0 2270 */ 2271 U_STABLE UBool U_EXPORT2 2272 u_isprint(UChar32 c); 2273 2274 /** 2275 * Determines whether the specified code point is a base character. 2276 * True for general categories "L" (letters), "N" (numbers), 2277 * "Mc" (spacing combining marks), and "Me" (enclosing marks). 2278 * 2279 * Note that this is different from the Unicode definition in 2280 * chapter 3.5, conformance clause D13, 2281 * which defines base characters to be all characters (not Cn) 2282 * that do not graphically combine with preceding characters (M) 2283 * and that are neither control (Cc) or format (Cf) characters. 2284 * 2285 * @param c the code point to be tested 2286 * @return TRUE if the code point is a base character according to this function 2287 * 2288 * @see u_isalpha 2289 * @see u_isdigit 2290 * @stable ICU 2.0 2291 */ 2292 U_STABLE UBool U_EXPORT2 2293 u_isbase(UChar32 c); 2294 2295 /** 2296 * Returns the bidirectional category value for the code point, 2297 * which is used in the Unicode bidirectional algorithm 2298 * (UAX #9 http://www.unicode.org/reports/tr9/). 2299 * Note that some <em>unassigned</em> code points have bidi values 2300 * of R or AL because they are in blocks that are reserved 2301 * for Right-To-Left scripts. 2302 * 2303 * Same as java.lang.Character.getDirectionality() 2304 * 2305 * @param c the code point to be tested 2306 * @return the bidirectional category (UCharDirection) value 2307 * 2308 * @see UCharDirection 2309 * @stable ICU 2.0 2310 */ 2311 U_STABLE UCharDirection U_EXPORT2 2312 u_charDirection(UChar32 c); 2313 2314 /** 2315 * Determines whether the code point has the Bidi_Mirrored property. 2316 * This property is set for characters that are commonly used in 2317 * Right-To-Left contexts and need to be displayed with a "mirrored" 2318 * glyph. 2319 * 2320 * Same as java.lang.Character.isMirrored(). 2321 * Same as UCHAR_BIDI_MIRRORED 2322 * 2323 * @param c the code point to be tested 2324 * @return TRUE if the character has the Bidi_Mirrored property 2325 * 2326 * @see UCHAR_BIDI_MIRRORED 2327 * @stable ICU 2.0 2328 */ 2329 U_STABLE UBool U_EXPORT2 2330 u_isMirrored(UChar32 c); 2331 2332 /** 2333 * Maps the specified character to a "mirror-image" character. 2334 * For characters with the Bidi_Mirrored property, implementations 2335 * sometimes need a "poor man's" mapping to another Unicode 2336 * character (code point) such that the default glyph may serve 2337 * as the mirror-image of the default glyph of the specified 2338 * character. This is useful for text conversion to and from 2339 * codepages with visual order, and for displays without glyph 2340 * selecetion capabilities. 2341 * 2342 * @param c the code point to be mapped 2343 * @return another Unicode code point that may serve as a mirror-image 2344 * substitute, or c itself if there is no such mapping or c 2345 * does not have the Bidi_Mirrored property 2346 * 2347 * @see UCHAR_BIDI_MIRRORED 2348 * @see u_isMirrored 2349 * @stable ICU 2.0 2350 */ 2351 U_STABLE UChar32 U_EXPORT2 2352 u_charMirror(UChar32 c); 2353 2354 /** 2355 * Returns the general category value for the code point. 2356 * 2357 * Same as java.lang.Character.getType(). 2358 * 2359 * @param c the code point to be tested 2360 * @return the general category (UCharCategory) value 2361 * 2362 * @see UCharCategory 2363 * @stable ICU 2.0 2364 */ 2365 U_STABLE int8_t U_EXPORT2 2366 u_charType(UChar32 c); 2367 2368 /** 2369 * Get a single-bit bit set for the general category of a character. 2370 * This bit set can be compared bitwise with U_GC_SM_MASK, U_GC_L_MASK, etc. 2371 * Same as U_MASK(u_charType(c)). 2372 * 2373 * @param c the code point to be tested 2374 * @return a single-bit mask corresponding to the general category (UCharCategory) value 2375 * 2376 * @see u_charType 2377 * @see UCharCategory 2378 * @see U_GC_CN_MASK 2379 * @stable ICU 2.1 2380 */ 2381 #define U_GET_GC_MASK(c) U_MASK(u_charType(c)) 2382 2383 /** 2384 * Callback from u_enumCharTypes(), is called for each contiguous range 2385 * of code points c (where start<=c<limit) 2386 * with the same Unicode general category ("character type"). 2387 * 2388 * The callback function can stop the enumeration by returning FALSE. 2389 * 2390 * @param context an opaque pointer, as passed into utrie_enum() 2391 * @param start the first code point in a contiguous range with value 2392 * @param limit one past the last code point in a contiguous range with value 2393 * @param type the general category for all code points in [start..limit[ 2394 * @return FALSE to stop the enumeration 2395 * 2396 * @stable ICU 2.1 2397 * @see UCharCategory 2398 * @see u_enumCharTypes 2399 */ 2400 typedef UBool U_CALLCONV 2401 UCharEnumTypeRange(const void *context, UChar32 start, UChar32 limit, UCharCategory type); 2402 2403 /** 2404 * Enumerate efficiently all code points with their Unicode general categories. 2405 * 2406 * This is useful for building data structures (e.g., UnicodeSet's), 2407 * for enumerating all assigned code points (type!=U_UNASSIGNED), etc. 2408 * 2409 * For each contiguous range of code points with a given general category ("character type"), 2410 * the UCharEnumTypeRange function is called. 2411 * Adjacent ranges have different types. 2412 * The Unicode Standard guarantees that the numeric value of the type is 0..31. 2413 * 2414 * @param enumRange a pointer to a function that is called for each contiguous range 2415 * of code points with the same general category 2416 * @param context an opaque pointer that is passed on to the callback function 2417 * 2418 * @stable ICU 2.1 2419 * @see UCharCategory 2420 * @see UCharEnumTypeRange 2421 */ 2422 U_STABLE void U_EXPORT2 2423 u_enumCharTypes(UCharEnumTypeRange *enumRange, const void *context); 2424 2425 #if !UCONFIG_NO_NORMALIZATION 2426 2427 /** 2428 * Returns the combining class of the code point as specified in UnicodeData.txt. 2429 * 2430 * @param c the code point of the character 2431 * @return the combining class of the character 2432 * @stable ICU 2.0 2433 */ 2434 U_STABLE uint8_t U_EXPORT2 2435 u_getCombiningClass(UChar32 c); 2436 2437 #endif 2438 2439 /** 2440 * Returns the decimal digit value of a decimal digit character. 2441 * Such characters have the general category "Nd" (decimal digit numbers) 2442 * and a Numeric_Type of Decimal. 2443 * 2444 * Unlike ICU releases before 2.6, no digit values are returned for any 2445 * Han characters because Han number characters are often used with a special 2446 * Chinese-style number format (with characters for powers of 10 in between) 2447 * instead of in decimal-positional notation. 2448 * Unicode 4 explicitly assigns Han number characters the Numeric_Type 2449 * Numeric instead of Decimal. 2450 * See Jitterbug 1483 for more details. 2451 * 2452 * Use u_getIntPropertyValue(c, UCHAR_NUMERIC_TYPE) and u_getNumericValue() 2453 * for complete numeric Unicode properties. 2454 * 2455 * @param c the code point for which to get the decimal digit value 2456 * @return the decimal digit value of c, 2457 * or -1 if c is not a decimal digit character 2458 * 2459 * @see u_getNumericValue 2460 * @stable ICU 2.0 2461 */ 2462 U_STABLE int32_t U_EXPORT2 2463 u_charDigitValue(UChar32 c); 2464 2465 /** 2466 * Returns the Unicode allocation block that contains the character. 2467 * 2468 * @param c the code point to be tested 2469 * @return the block value (UBlockCode) for c 2470 * 2471 * @see UBlockCode 2472 * @stable ICU 2.0 2473 */ 2474 U_STABLE UBlockCode U_EXPORT2 2475 ublock_getCode(UChar32 c); 2476 2477 /** 2478 * Retrieve the name of a Unicode character. 2479 * Depending on <code>nameChoice</code>, the character name written 2480 * into the buffer is the "modern" name or the name that was defined 2481 * in Unicode version 1.0. 2482 * The name contains only "invariant" characters 2483 * like A-Z, 0-9, space, and '-'. 2484 * Unicode 1.0 names are only retrieved if they are different from the modern 2485 * names and if the data file contains the data for them. gennames may or may 2486 * not be called with a command line option to include 1.0 names in unames.dat. 2487 * 2488 * @param code The character (code point) for which to get the name. 2489 * It must be <code>0<=code<=0x10ffff</code>. 2490 * @param nameChoice Selector for which name to get. 2491 * @param buffer Destination address for copying the name. 2492 * The name will always be zero-terminated. 2493 * If there is no name, then the buffer will be set to the empty string. 2494 * @param bufferLength <code>==sizeof(buffer)</code> 2495 * @param pErrorCode Pointer to a UErrorCode variable; 2496 * check for <code>U_SUCCESS()</code> after <code>u_charName()</code> 2497 * returns. 2498 * @return The length of the name, or 0 if there is no name for this character. 2499 * If the bufferLength is less than or equal to the length, then the buffer 2500 * contains the truncated name and the returned length indicates the full 2501 * length of the name. 2502 * The length does not include the zero-termination. 2503 * 2504 * @see UCharNameChoice 2505 * @see u_charFromName 2506 * @see u_enumCharNames 2507 * @stable ICU 2.0 2508 */ 2509 U_STABLE int32_t U_EXPORT2 2510 u_charName(UChar32 code, UCharNameChoice nameChoice, 2511 char *buffer, int32_t bufferLength, 2512 UErrorCode *pErrorCode); 2513 2514 /** 2515 * Get the ISO 10646 comment for a character. 2516 * The ISO 10646 comment is an informative field in the Unicode Character 2517 * Database (UnicodeData.txt field 11) and is from the ISO 10646 names list. 2518 * 2519 * Note: Unicode 5.2 removes all ISO comment data, resulting in empty strings 2520 * returned for all characters. 2521 * 2522 * @param c The character (code point) for which to get the ISO comment. 2523 * It must be <code>0<=c<=0x10ffff</code>. 2524 * @param dest Destination address for copying the comment. 2525 * The comment will be zero-terminated if possible. 2526 * If there is no comment, then the buffer will be set to the empty string. 2527 * @param destCapacity <code>==sizeof(dest)</code> 2528 * @param pErrorCode Pointer to a UErrorCode variable; 2529 * check for <code>U_SUCCESS()</code> after <code>u_getISOComment()</code> 2530 * returns. 2531 * @return The length of the comment, or 0 if there is no comment for this character. 2532 * If the destCapacity is less than or equal to the length, then the buffer 2533 * contains the truncated name and the returned length indicates the full 2534 * length of the name. 2535 * The length does not include the zero-termination. 2536 * 2537 * @stable ICU 2.2 2538 */ 2539 U_STABLE int32_t U_EXPORT2 2540 u_getISOComment(UChar32 c, 2541 char *dest, int32_t destCapacity, 2542 UErrorCode *pErrorCode); 2543 2544 /** 2545 * Find a Unicode character by its name and return its code point value. 2546 * The name is matched exactly and completely. 2547 * If the name does not correspond to a code point, <i>pErrorCode</i> 2548 * is set to <code>U_INVALID_CHAR_FOUND</code>. 2549 * A Unicode 1.0 name is matched only if it differs from the modern name. 2550 * Unicode names are all uppercase. Extended names are lowercase followed 2551 * by an uppercase hexadecimal number, and within angle brackets. 2552 * 2553 * @param nameChoice Selector for which name to match. 2554 * @param name The name to match. 2555 * @param pErrorCode Pointer to a UErrorCode variable 2556 * @return The Unicode value of the code point with the given name, 2557 * or an undefined value if there is no such code point. 2558 * 2559 * @see UCharNameChoice 2560 * @see u_charName 2561 * @see u_enumCharNames 2562 * @stable ICU 1.7 2563 */ 2564 U_STABLE UChar32 U_EXPORT2 2565 u_charFromName(UCharNameChoice nameChoice, 2566 const char *name, 2567 UErrorCode *pErrorCode); 2568 2569 /** 2570 * Type of a callback function for u_enumCharNames() that gets called 2571 * for each Unicode character with the code point value and 2572 * the character name. 2573 * If such a function returns FALSE, then the enumeration is stopped. 2574 * 2575 * @param context The context pointer that was passed to u_enumCharNames(). 2576 * @param code The Unicode code point for the character with this name. 2577 * @param nameChoice Selector for which kind of names is enumerated. 2578 * @param name The character's name, zero-terminated. 2579 * @param length The length of the name. 2580 * @return TRUE if the enumeration should continue, FALSE to stop it. 2581 * 2582 * @see UCharNameChoice 2583 * @see u_enumCharNames 2584 * @stable ICU 1.7 2585 */ 2586 typedef UBool U_CALLCONV UEnumCharNamesFn(void *context, 2587 UChar32 code, 2588 UCharNameChoice nameChoice, 2589 const char *name, 2590 int32_t length); 2591 2592 /** 2593 * Enumerate all assigned Unicode characters between the start and limit 2594 * code points (start inclusive, limit exclusive) and call a function 2595 * for each, passing the code point value and the character name. 2596 * For Unicode 1.0 names, only those are enumerated that differ from the 2597 * modern names. 2598 * 2599 * @param start The first code point in the enumeration range. 2600 * @param limit One more than the last code point in the enumeration range 2601 * (the first one after the range). 2602 * @param fn The function that is to be called for each character name. 2603 * @param context An arbitrary pointer that is passed to the function. 2604 * @param nameChoice Selector for which kind of names to enumerate. 2605 * @param pErrorCode Pointer to a UErrorCode variable 2606 * 2607 * @see UCharNameChoice 2608 * @see UEnumCharNamesFn 2609 * @see u_charName 2610 * @see u_charFromName 2611 * @stable ICU 1.7 2612 */ 2613 U_STABLE void U_EXPORT2 2614 u_enumCharNames(UChar32 start, UChar32 limit, 2615 UEnumCharNamesFn *fn, 2616 void *context, 2617 UCharNameChoice nameChoice, 2618 UErrorCode *pErrorCode); 2619 2620 /** 2621 * Return the Unicode name for a given property, as given in the 2622 * Unicode database file PropertyAliases.txt. 2623 * 2624 * In addition, this function maps the property 2625 * UCHAR_GENERAL_CATEGORY_MASK to the synthetic names "gcm" / 2626 * "General_Category_Mask". These names are not in 2627 * PropertyAliases.txt. 2628 * 2629 * @param property UProperty selector other than UCHAR_INVALID_CODE. 2630 * If out of range, NULL is returned. 2631 * 2632 * @param nameChoice selector for which name to get. If out of range, 2633 * NULL is returned. All properties have a long name. Most 2634 * have a short name, but some do not. Unicode allows for 2635 * additional names; if present these will be returned by 2636 * U_LONG_PROPERTY_NAME + i, where i=1, 2,... 2637 * 2638 * @return a pointer to the name, or NULL if either the 2639 * property or the nameChoice is out of range. If a given 2640 * nameChoice returns NULL, then all larger values of 2641 * nameChoice will return NULL, with one exception: if NULL is 2642 * returned for U_SHORT_PROPERTY_NAME, then 2643 * U_LONG_PROPERTY_NAME (and higher) may still return a 2644 * non-NULL value. The returned pointer is valid until 2645 * u_cleanup() is called. 2646 * 2647 * @see UProperty 2648 * @see UPropertyNameChoice 2649 * @stable ICU 2.4 2650 */ 2651 U_STABLE const char* U_EXPORT2 2652 u_getPropertyName(UProperty property, 2653 UPropertyNameChoice nameChoice); 2654 2655 /** 2656 * Return the UProperty enum for a given property name, as specified 2657 * in the Unicode database file PropertyAliases.txt. Short, long, and 2658 * any other variants are recognized. 2659 * 2660 * In addition, this function maps the synthetic names "gcm" / 2661 * "General_Category_Mask" to the property 2662 * UCHAR_GENERAL_CATEGORY_MASK. These names are not in 2663 * PropertyAliases.txt. 2664 * 2665 * @param alias the property name to be matched. The name is compared 2666 * using "loose matching" as described in PropertyAliases.txt. 2667 * 2668 * @return a UProperty enum, or UCHAR_INVALID_CODE if the given name 2669 * does not match any property. 2670 * 2671 * @see UProperty 2672 * @stable ICU 2.4 2673 */ 2674 U_STABLE UProperty U_EXPORT2 2675 u_getPropertyEnum(const char* alias); 2676 2677 /** 2678 * Return the Unicode name for a given property value, as given in the 2679 * Unicode database file PropertyValueAliases.txt. 2680 * 2681 * Note: Some of the names in PropertyValueAliases.txt can only be 2682 * retrieved using UCHAR_GENERAL_CATEGORY_MASK, not 2683 * UCHAR_GENERAL_CATEGORY. These include: "C" / "Other", "L" / 2684 * "Letter", "LC" / "Cased_Letter", "M" / "Mark", "N" / "Number", "P" 2685 * / "Punctuation", "S" / "Symbol", and "Z" / "Separator". 2686 * 2687 * @param property UProperty selector constant. 2688 * Must be UCHAR_BINARY_START<=which<UCHAR_BINARY_LIMIT 2689 * or UCHAR_INT_START<=which<UCHAR_INT_LIMIT 2690 * or UCHAR_MASK_START<=which<UCHAR_MASK_LIMIT. 2691 * If out of range, NULL is returned. 2692 * 2693 * @param value selector for a value for the given property. If out 2694 * of range, NULL is returned. In general, valid values range 2695 * from 0 up to some maximum. There are a few exceptions: 2696 * (1.) UCHAR_BLOCK values begin at the non-zero value 2697 * UBLOCK_BASIC_LATIN. (2.) UCHAR_CANONICAL_COMBINING_CLASS 2698 * values are not contiguous and range from 0..240. (3.) 2699 * UCHAR_GENERAL_CATEGORY_MASK values are not values of 2700 * UCharCategory, but rather mask values produced by 2701 * U_GET_GC_MASK(). This allows grouped categories such as 2702 * [:L:] to be represented. Mask values range 2703 * non-contiguously from 1..U_GC_P_MASK. 2704 * 2705 * @param nameChoice selector for which name to get. If out of range, 2706 * NULL is returned. All values have a long name. Most have 2707 * a short name, but some do not. Unicode allows for 2708 * additional names; if present these will be returned by 2709 * U_LONG_PROPERTY_NAME + i, where i=1, 2,... 2710 2711 * @return a pointer to the name, or NULL if either the 2712 * property or the nameChoice is out of range. If a given 2713 * nameChoice returns NULL, then all larger values of 2714 * nameChoice will return NULL, with one exception: if NULL is 2715 * returned for U_SHORT_PROPERTY_NAME, then 2716 * U_LONG_PROPERTY_NAME (and higher) may still return a 2717 * non-NULL value. The returned pointer is valid until 2718 * u_cleanup() is called. 2719 * 2720 * @see UProperty 2721 * @see UPropertyNameChoice 2722 * @stable ICU 2.4 2723 */ 2724 U_STABLE const char* U_EXPORT2 2725 u_getPropertyValueName(UProperty property, 2726 int32_t value, 2727 UPropertyNameChoice nameChoice); 2728 2729 /** 2730 * Return the property value integer for a given value name, as 2731 * specified in the Unicode database file PropertyValueAliases.txt. 2732 * Short, long, and any other variants are recognized. 2733 * 2734 * Note: Some of the names in PropertyValueAliases.txt will only be 2735 * recognized with UCHAR_GENERAL_CATEGORY_MASK, not 2736 * UCHAR_GENERAL_CATEGORY. These include: "C" / "Other", "L" / 2737 * "Letter", "LC" / "Cased_Letter", "M" / "Mark", "N" / "Number", "P" 2738 * / "Punctuation", "S" / "Symbol", and "Z" / "Separator". 2739 * 2740 * @param property UProperty selector constant. 2741 * Must be UCHAR_BINARY_START<=which<UCHAR_BINARY_LIMIT 2742 * or UCHAR_INT_START<=which<UCHAR_INT_LIMIT 2743 * or UCHAR_MASK_START<=which<UCHAR_MASK_LIMIT. 2744 * If out of range, UCHAR_INVALID_CODE is returned. 2745 * 2746 * @param alias the value name to be matched. The name is compared 2747 * using "loose matching" as described in 2748 * PropertyValueAliases.txt. 2749 * 2750 * @return a value integer or UCHAR_INVALID_CODE if the given name 2751 * does not match any value of the given property, or if the 2752 * property is invalid. Note: UCHAR_GENERAL_CATEGORY_MASK values 2753 * are not values of UCharCategory, but rather mask values 2754 * produced by U_GET_GC_MASK(). This allows grouped 2755 * categories such as [:L:] to be represented. 2756 * 2757 * @see UProperty 2758 * @stable ICU 2.4 2759 */ 2760 U_STABLE int32_t U_EXPORT2 2761 u_getPropertyValueEnum(UProperty property, 2762 const char* alias); 2763 2764 /** 2765 * Determines if the specified character is permissible as the 2766 * first character in an identifier according to Unicode 2767 * (The Unicode Standard, Version 3.0, chapter 5.16 Identifiers). 2768 * True for characters with general categories "L" (letters) and "Nl" (letter numbers). 2769 * 2770 * Same as java.lang.Character.isUnicodeIdentifierStart(). 2771 * Same as UCHAR_ID_START 2772 * 2773 * @param c the code point to be tested 2774 * @return TRUE if the code point may start an identifier 2775 * 2776 * @see UCHAR_ID_START 2777 * @see u_isalpha 2778 * @see u_isIDPart 2779 * @stable ICU 2.0 2780 */ 2781 U_STABLE UBool U_EXPORT2 2782 u_isIDStart(UChar32 c); 2783 2784 /** 2785 * Determines if the specified character is permissible 2786 * in an identifier according to Java. 2787 * True for characters with general categories "L" (letters), 2788 * "Nl" (letter numbers), "Nd" (decimal digits), 2789 * "Mc" and "Mn" (combining marks), "Pc" (connecting punctuation), and 2790 * u_isIDIgnorable(c). 2791 * 2792 * Same as java.lang.Character.isUnicodeIdentifierPart(). 2793 * Almost the same as Unicode's ID_Continue (UCHAR_ID_CONTINUE) 2794 * except that Unicode recommends to ignore Cf which is less than 2795 * u_isIDIgnorable(c). 2796 * 2797 * @param c the code point to be tested 2798 * @return TRUE if the code point may occur in an identifier according to Java 2799 * 2800 * @see UCHAR_ID_CONTINUE 2801 * @see u_isIDStart 2802 * @see u_isIDIgnorable 2803 * @stable ICU 2.0 2804 */ 2805 U_STABLE UBool U_EXPORT2 2806 u_isIDPart(UChar32 c); 2807 2808 /** 2809 * Determines if the specified character should be regarded 2810 * as an ignorable character in an identifier, 2811 * according to Java. 2812 * True for characters with general category "Cf" (format controls) as well as 2813 * non-whitespace ISO controls 2814 * (U+0000..U+0008, U+000E..U+001B, U+007F..U+009F). 2815 * 2816 * Same as java.lang.Character.isIdentifierIgnorable(). 2817 * 2818 * Note that Unicode just recommends to ignore Cf (format controls). 2819 * 2820 * @param c the code point to be tested 2821 * @return TRUE if the code point is ignorable in identifiers according to Java 2822 * 2823 * @see UCHAR_DEFAULT_IGNORABLE_CODE_POINT 2824 * @see u_isIDStart 2825 * @see u_isIDPart 2826 * @stable ICU 2.0 2827 */ 2828 U_STABLE UBool U_EXPORT2 2829 u_isIDIgnorable(UChar32 c); 2830 2831 /** 2832 * Determines if the specified character is permissible as the 2833 * first character in a Java identifier. 2834 * In addition to u_isIDStart(c), true for characters with 2835 * general categories "Sc" (currency symbols) and "Pc" (connecting punctuation). 2836 * 2837 * Same as java.lang.Character.isJavaIdentifierStart(). 2838 * 2839 * @param c the code point to be tested 2840 * @return TRUE if the code point may start a Java identifier 2841 * 2842 * @see u_isJavaIDPart 2843 * @see u_isalpha 2844 * @see u_isIDStart 2845 * @stable ICU 2.0 2846 */ 2847 U_STABLE UBool U_EXPORT2 2848 u_isJavaIDStart(UChar32 c); 2849 2850 /** 2851 * Determines if the specified character is permissible 2852 * in a Java identifier. 2853 * In addition to u_isIDPart(c), true for characters with 2854 * general category "Sc" (currency symbols). 2855 * 2856 * Same as java.lang.Character.isJavaIdentifierPart(). 2857 * 2858 * @param c the code point to be tested 2859 * @return TRUE if the code point may occur in a Java identifier 2860 * 2861 * @see u_isIDIgnorable 2862 * @see u_isJavaIDStart 2863 * @see u_isalpha 2864 * @see u_isdigit 2865 * @see u_isIDPart 2866 * @stable ICU 2.0 2867 */ 2868 U_STABLE UBool U_EXPORT2 2869 u_isJavaIDPart(UChar32 c); 2870 2871 /** 2872 * The given character is mapped to its lowercase equivalent according to 2873 * UnicodeData.txt; if the character has no lowercase equivalent, the character 2874 * itself is returned. 2875 * 2876 * Same as java.lang.Character.toLowerCase(). 2877 * 2878 * This function only returns the simple, single-code point case mapping. 2879 * Full case mappings should be used whenever possible because they produce 2880 * better results by working on whole strings. 2881 * They take into account the string context and the language and can map 2882 * to a result string with a different length as appropriate. 2883 * Full case mappings are applied by the string case mapping functions, 2884 * see ustring.h and the UnicodeString class. 2885 * See also the User Guide chapter on C/POSIX migration: 2886 * http://icu-project.org/userguide/posix.html#case_mappings 2887 * 2888 * @param c the code point to be mapped 2889 * @return the Simple_Lowercase_Mapping of the code point, if any; 2890 * otherwise the code point itself. 2891 * @stable ICU 2.0 2892 */ 2893 U_STABLE UChar32 U_EXPORT2 2894 u_tolower(UChar32 c); 2895 2896 /** 2897 * The given character is mapped to its uppercase equivalent according to UnicodeData.txt; 2898 * if the character has no uppercase equivalent, the character itself is 2899 * returned. 2900 * 2901 * Same as java.lang.Character.toUpperCase(). 2902 * 2903 * This function only returns the simple, single-code point case mapping. 2904 * Full case mappings should be used whenever possible because they produce 2905 * better results by working on whole strings. 2906 * They take into account the string context and the language and can map 2907 * to a result string with a different length as appropriate. 2908 * Full case mappings are applied by the string case mapping functions, 2909 * see ustring.h and the UnicodeString class. 2910 * See also the User Guide chapter on C/POSIX migration: 2911 * http://icu-project.org/userguide/posix.html#case_mappings 2912 * 2913 * @param c the code point to be mapped 2914 * @return the Simple_Uppercase_Mapping of the code point, if any; 2915 * otherwise the code point itself. 2916 * @stable ICU 2.0 2917 */ 2918 U_STABLE UChar32 U_EXPORT2 2919 u_toupper(UChar32 c); 2920 2921 /** 2922 * The given character is mapped to its titlecase equivalent 2923 * according to UnicodeData.txt; 2924 * if none is defined, the character itself is returned. 2925 * 2926 * Same as java.lang.Character.toTitleCase(). 2927 * 2928 * This function only returns the simple, single-code point case mapping. 2929 * Full case mappings should be used whenever possible because they produce 2930 * better results by working on whole strings. 2931 * They take into account the string context and the language and can map 2932 * to a result string with a different length as appropriate. 2933 * Full case mappings are applied by the string case mapping functions, 2934 * see ustring.h and the UnicodeString class. 2935 * See also the User Guide chapter on C/POSIX migration: 2936 * http://icu-project.org/userguide/posix.html#case_mappings 2937 * 2938 * @param c the code point to be mapped 2939 * @return the Simple_Titlecase_Mapping of the code point, if any; 2940 * otherwise the code point itself. 2941 * @stable ICU 2.0 2942 */ 2943 U_STABLE UChar32 U_EXPORT2 2944 u_totitle(UChar32 c); 2945 2946 /** Option value for case folding: use default mappings defined in CaseFolding.txt. @stable ICU 2.0 */ 2947 #define U_FOLD_CASE_DEFAULT 0 2948 2949 /** 2950 * Option value for case folding: 2951 * 2952 * Use the modified set of mappings provided in CaseFolding.txt to handle dotted I 2953 * and dotless i appropriately for Turkic languages (tr, az). 2954 * 2955 * Before Unicode 3.2, CaseFolding.txt contains mappings marked with 'I' that 2956 * are to be included for default mappings and 2957 * excluded for the Turkic-specific mappings. 2958 * 2959 * Unicode 3.2 CaseFolding.txt instead contains mappings marked with 'T' that 2960 * are to be excluded for default mappings and 2961 * included for the Turkic-specific mappings. 2962 * 2963 * @stable ICU 2.0 2964 */ 2965 #define U_FOLD_CASE_EXCLUDE_SPECIAL_I 1 2966 2967 /** 2968 * The given character is mapped to its case folding equivalent according to 2969 * UnicodeData.txt and CaseFolding.txt; 2970 * if the character has no case folding equivalent, the character 2971 * itself is returned. 2972 * 2973 * This function only returns the simple, single-code point case mapping. 2974 * Full case mappings should be used whenever possible because they produce 2975 * better results by working on whole strings. 2976 * They take into account the string context and the language and can map 2977 * to a result string with a different length as appropriate. 2978 * Full case mappings are applied by the string case mapping functions, 2979 * see ustring.h and the UnicodeString class. 2980 * See also the User Guide chapter on C/POSIX migration: 2981 * http://icu-project.org/userguide/posix.html#case_mappings 2982 * 2983 * @param c the code point to be mapped 2984 * @param options Either U_FOLD_CASE_DEFAULT or U_FOLD_CASE_EXCLUDE_SPECIAL_I 2985 * @return the Simple_Case_Folding of the code point, if any; 2986 * otherwise the code point itself. 2987 * @stable ICU 2.0 2988 */ 2989 U_STABLE UChar32 U_EXPORT2 2990 u_foldCase(UChar32 c, uint32_t options); 2991 2992 /** 2993 * Returns the decimal digit value of the code point in the 2994 * specified radix. 2995 * 2996 * If the radix is not in the range <code>2<=radix<=36</code> or if the 2997 * value of <code>c</code> is not a valid digit in the specified 2998 * radix, <code>-1</code> is returned. A character is a valid digit 2999 * if at least one of the following is true: 3000 * <ul> 3001 * <li>The character has a decimal digit value. 3002 * Such characters have the general category "Nd" (decimal digit numbers) 3003 * and a Numeric_Type of Decimal. 3004 * In this case the value is the character's decimal digit value.</li> 3005 * <li>The character is one of the uppercase Latin letters 3006 * <code>'A'</code> through <code>'Z'</code>. 3007 * In this case the value is <code>c-'A'+10</code>.</li> 3008 * <li>The character is one of the lowercase Latin letters 3009 * <code>'a'</code> through <code>'z'</code>. 3010 * In this case the value is <code>ch-'a'+10</code>.</li> 3011 * <li>Latin letters from both the ASCII range (0061..007A, 0041..005A) 3012 * as well as from the Fullwidth ASCII range (FF41..FF5A, FF21..FF3A) 3013 * are recognized.</li> 3014 * </ul> 3015 * 3016 * Same as java.lang.Character.digit(). 3017 * 3018 * @param ch the code point to be tested. 3019 * @param radix the radix. 3020 * @return the numeric value represented by the character in the 3021 * specified radix, 3022 * or -1 if there is no value or if the value exceeds the radix. 3023 * 3024 * @see UCHAR_NUMERIC_TYPE 3025 * @see u_forDigit 3026 * @see u_charDigitValue 3027 * @see u_isdigit 3028 * @stable ICU 2.0 3029 */ 3030 U_STABLE int32_t U_EXPORT2 3031 u_digit(UChar32 ch, int8_t radix); 3032 3033 /** 3034 * Determines the character representation for a specific digit in 3035 * the specified radix. If the value of <code>radix</code> is not a 3036 * valid radix, or the value of <code>digit</code> is not a valid 3037 * digit in the specified radix, the null character 3038 * (<code>U+0000</code>) is returned. 3039 * <p> 3040 * The <code>radix</code> argument is valid if it is greater than or 3041 * equal to 2 and less than or equal to 36. 3042 * The <code>digit</code> argument is valid if 3043 * <code>0 <= digit < radix</code>. 3044 * <p> 3045 * If the digit is less than 10, then 3046 * <code>'0' + digit</code> is returned. Otherwise, the value 3047 * <code>'a' + digit - 10</code> is returned. 3048 * 3049 * Same as java.lang.Character.forDigit(). 3050 * 3051 * @param digit the number to convert to a character. 3052 * @param radix the radix. 3053 * @return the <code>char</code> representation of the specified digit 3054 * in the specified radix. 3055 * 3056 * @see u_digit 3057 * @see u_charDigitValue 3058 * @see u_isdigit 3059 * @stable ICU 2.0 3060 */ 3061 U_STABLE UChar32 U_EXPORT2 3062 u_forDigit(int32_t digit, int8_t radix); 3063 3064 /** 3065 * Get the "age" of the code point. 3066 * The "age" is the Unicode version when the code point was first 3067 * designated (as a non-character or for Private Use) 3068 * or assigned a character. 3069 * This can be useful to avoid emitting code points to receiving 3070 * processes that do not accept newer characters. 3071 * The data is from the UCD file DerivedAge.txt. 3072 * 3073 * @param c The code point. 3074 * @param versionArray The Unicode version number array, to be filled in. 3075 * 3076 * @stable ICU 2.1 3077 */ 3078 U_STABLE void U_EXPORT2 3079 u_charAge(UChar32 c, UVersionInfo versionArray); 3080 3081 /** 3082 * Gets the Unicode version information. 3083 * The version array is filled in with the version information 3084 * for the Unicode standard that is currently used by ICU. 3085 * For example, Unicode version 3.1.1 is represented as an array with 3086 * the values { 3, 1, 1, 0 }. 3087 * 3088 * @param versionArray an output array that will be filled in with 3089 * the Unicode version number 3090 * @stable ICU 2.0 3091 */ 3092 U_STABLE void U_EXPORT2 3093 u_getUnicodeVersion(UVersionInfo versionArray); 3094 3095 #if !UCONFIG_NO_NORMALIZATION 3096 /** 3097 * Get the FC_NFKC_Closure property string for a character. 3098 * See Unicode Standard Annex #15 for details, search for "FC_NFKC_Closure" 3099 * or for "FNC": http://www.unicode.org/reports/tr15/ 3100 * 3101 * @param c The character (code point) for which to get the FC_NFKC_Closure string. 3102 * It must be <code>0<=c<=0x10ffff</code>. 3103 * @param dest Destination address for copying the string. 3104 * The string will be zero-terminated if possible. 3105 * If there is no FC_NFKC_Closure string, 3106 * then the buffer will be set to the empty string. 3107 * @param destCapacity <code>==sizeof(dest)</code> 3108 * @param pErrorCode Pointer to a UErrorCode variable. 3109 * @return The length of the string, or 0 if there is no FC_NFKC_Closure string for this character. 3110 * If the destCapacity is less than or equal to the length, then the buffer 3111 * contains the truncated name and the returned length indicates the full 3112 * length of the name. 3113 * The length does not include the zero-termination. 3114 * 3115 * @stable ICU 2.2 3116 */ 3117 U_STABLE int32_t U_EXPORT2 3118 u_getFC_NFKC_Closure(UChar32 c, UChar *dest, int32_t destCapacity, UErrorCode *pErrorCode); 3119 3120 #endif 3121 3122 3123 U_CDECL_END 3124 3125 #endif /*_UCHAR*/ 3126 /*eof*/ 3127