EIC code displayed by LXR |
|
|
|
|||
File indexing completed on 2026-09-13 09:27:45
0001 // © 2016 and later: Unicode, Inc. and others. 0002 // License & terms of use: http://www.unicode.org/copyright.html 0003 /* 0004 ********************************************************************** 0005 * Copyright (C) 1997-2016, International Business Machines 0006 * Corporation and others. All Rights Reserved. 0007 ********************************************************************** 0008 * 0009 * File UCHAR.H 0010 * 0011 * Modification History: 0012 * 0013 * Date Name Description 0014 * 04/02/97 aliu Creation. 0015 * 03/29/99 helena Updated for C APIs. 0016 * 4/15/99 Madhu Updated for C Implementation and Javadoc 0017 * 5/20/99 Madhu Added the function u_getVersion() 0018 * 8/19/1999 srl Upgraded scripts to Unicode 3.0 0019 * 8/27/1999 schererm UCharDirection constants: U_... 0020 * 11/11/1999 weiv added u_isalnum(), cleaned comments 0021 * 01/11/2000 helena Renamed u_getVersion to u_getUnicodeVersion(). 0022 ****************************************************************************** 0023 */ 0024 0025 #ifndef UCHAR_H 0026 #define UCHAR_H 0027 0028 #include <stdbool.h> 0029 #include "unicode/utypes.h" 0030 #include "unicode/stringoptions.h" 0031 #include "unicode/ucpmap.h" 0032 0033 #if !defined(USET_DEFINED) && !defined(U_IN_DOXYGEN) 0034 0035 #define USET_DEFINED 0036 0037 /** 0038 * USet is the C API type corresponding to C++ class UnicodeSet. 0039 * It is forward-declared here to avoid including unicode/uset.h file if related 0040 * APIs are not used. 0041 * 0042 * @see ucnv_getUnicodeSet 0043 * @stable ICU 2.4 0044 */ 0045 typedef struct USet USet; 0046 0047 #endif 0048 0049 0050 U_CDECL_BEGIN 0051 0052 /*==========================================================================*/ 0053 /* Unicode version number */ 0054 /*==========================================================================*/ 0055 /** 0056 * Unicode version number, default for the current ICU version. 0057 * The actual Unicode Character Database (UCD) data is stored in uprops.icu 0058 * and may be generated from UCD files from a different Unicode version. 0059 * Call u_getUnicodeVersion to get the actual Unicode version of the data. 0060 * 0061 * @see u_getUnicodeVersion 0062 * @stable ICU 2.0 0063 */ 0064 #define U_UNICODE_VERSION "16.0" 0065 0066 /** 0067 * \file 0068 * \brief C API: Unicode Properties 0069 * 0070 * This C API provides low-level access to the Unicode Character Database. 0071 * In addition to raw property values, some convenience functions calculate 0072 * derived properties, for example for Java-style programming. 0073 * 0074 * Unicode assigns each code point (not just assigned character) values for 0075 * many properties. 0076 * Most of them are simple boolean flags, or constants from a small enumerated list. 0077 * For some properties, values are strings or other relatively more complex types. 0078 * 0079 * For more information see 0080 * "About the Unicode Character Database" (http://www.unicode.org/ucd/) 0081 * and the ICU User Guide chapter on Properties (https://unicode-org.github.io/icu/userguide/strings/properties). 0082 * 0083 * Many properties are accessible via generic functions that take a UProperty selector. 0084 * - u_hasBinaryProperty() returns a binary value (true/false) per property and code point. 0085 * - u_getIntPropertyValue() returns an integer value per property and code point. 0086 * For each supported enumerated or catalog property, there is 0087 * an enum type for all of the property's values, and 0088 * u_getIntPropertyValue() returns the numeric values of those constants. 0089 * - u_getBinaryPropertySet() returns a set for each ICU-supported binary property with 0090 * all code points for which the property is true. 0091 * - u_getIntPropertyMap() returns a map for each 0092 * ICU-supported enumerated/catalog/int-valued property which 0093 * maps all Unicode code points to their values for that property. 0094 * 0095 * Many functions are designed to match java.lang.Character functions. 0096 * See the individual function documentation, 0097 * and see the JDK 1.4 java.lang.Character documentation 0098 * at http://java.sun.com/j2se/1.4/docs/api/java/lang/Character.html 0099 * 0100 * There are also functions that provide easy migration from C/POSIX functions 0101 * like isblank(). Their use is generally discouraged because the C/POSIX 0102 * standards do not define their semantics beyond the ASCII range, which means 0103 * that different implementations exhibit very different behavior. 0104 * Instead, Unicode properties should be used directly. 0105 * 0106 * There are also only a few, broad C/POSIX character classes, and they tend 0107 * to be used for conflicting purposes. For example, the "isalpha()" class 0108 * is sometimes used to determine word boundaries, while a more sophisticated 0109 * approach would at least distinguish initial letters from continuation 0110 * characters (the latter including combining marks). 0111 * (In ICU, BreakIterator is the most sophisticated API for word boundaries.) 0112 * Another example: There is no "istitle()" class for titlecase characters. 0113 * 0114 * ICU 3.4 and later provides API access for all twelve C/POSIX character classes. 0115 * ICU implements them according to the Standard Recommendations in 0116 * Annex C: Compatibility Properties of UTS #18 Unicode Regular Expressions 0117 * (http://www.unicode.org/reports/tr18/#Compatibility_Properties). 0118 * 0119 * API access for C/POSIX character classes is as follows: 0120 * - alpha: u_isUAlphabetic(c) or u_hasBinaryProperty(c, UCHAR_ALPHABETIC) 0121 * - lower: u_isULowercase(c) or u_hasBinaryProperty(c, UCHAR_LOWERCASE) 0122 * - upper: u_isUUppercase(c) or u_hasBinaryProperty(c, UCHAR_UPPERCASE) 0123 * - punct: u_ispunct(c) 0124 * - digit: u_isdigit(c) or u_charType(c)==U_DECIMAL_DIGIT_NUMBER 0125 * - xdigit: u_isxdigit(c) or u_hasBinaryProperty(c, UCHAR_POSIX_XDIGIT) 0126 * - alnum: u_hasBinaryProperty(c, UCHAR_POSIX_ALNUM) 0127 * - space: u_isUWhiteSpace(c) or u_hasBinaryProperty(c, UCHAR_WHITE_SPACE) 0128 * - blank: u_isblank(c) or u_hasBinaryProperty(c, UCHAR_POSIX_BLANK) 0129 * - cntrl: u_charType(c)==U_CONTROL_CHAR 0130 * - graph: u_hasBinaryProperty(c, UCHAR_POSIX_GRAPH) 0131 * - print: u_hasBinaryProperty(c, UCHAR_POSIX_PRINT) 0132 * 0133 * Note: Some of the u_isxyz() functions in uchar.h predate, and do not match, 0134 * the Standard Recommendations in UTS #18. Instead, they match Java 0135 * functions according to their API documentation. 0136 * 0137 * \htmlonly 0138 * The C/POSIX character classes are also available in UnicodeSet patterns, 0139 * using patterns like [:graph:] or \p{graph}. 0140 * \endhtmlonly 0141 * 0142 * Note: There are several ICU whitespace functions. 0143 * Comparison: 0144 * - u_isUWhiteSpace=UCHAR_WHITE_SPACE: Unicode White_Space property; 0145 * most of general categories "Z" (separators) + most whitespace ISO controls 0146 * (including no-break spaces, but excluding IS1..IS4) 0147 * - u_isWhitespace: Java isWhitespace; Z + whitespace ISO controls but excluding no-break spaces 0148 * - u_isJavaSpaceChar: Java isSpaceChar; just Z (including no-break spaces) 0149 * - u_isspace: Z + whitespace ISO controls (including no-break spaces) 0150 * - u_isblank: "horizontal spaces" = TAB + Zs 0151 */ 0152 0153 /** 0154 * Constants. 0155 */ 0156 0157 /** The lowest Unicode code point value. Code points are non-negative. @stable ICU 2.0 */ 0158 #define UCHAR_MIN_VALUE 0 0159 0160 /** 0161 * The highest Unicode code point value (scalar value) according to 0162 * The Unicode Standard. This is a 21-bit value (20.1 bits, rounded up). 0163 * For a single character, UChar32 is a simple type that can hold any code point value. 0164 * 0165 * @see UChar32 0166 * @stable ICU 2.0 0167 */ 0168 #define UCHAR_MAX_VALUE 0x10ffff 0169 0170 /** 0171 * Get a single-bit bit set (a flag) from a bit number 0..31. 0172 * @stable ICU 2.1 0173 */ 0174 #define U_MASK(x) ((uint32_t)1<<(x)) 0175 0176 /** 0177 * Selection constants for Unicode properties. 0178 * These constants are used in functions like u_hasBinaryProperty to select 0179 * one of the Unicode properties. 0180 * 0181 * The properties APIs are intended to reflect Unicode properties as defined 0182 * in the Unicode Character Database (UCD) and Unicode Technical Reports (UTR). 0183 * 0184 * For details about the properties see 0185 * UAX #44: Unicode Character Database (http://www.unicode.org/reports/tr44/). 0186 * 0187 * Important: If ICU is built with UCD files from Unicode versions below, e.g., 3.2, 0188 * then properties marked with "new in Unicode 3.2" are not or not fully available. 0189 * Check u_getUnicodeVersion to be sure. 0190 * 0191 * @see u_hasBinaryProperty 0192 * @see u_getIntPropertyValue 0193 * @see u_getUnicodeVersion 0194 * @stable ICU 2.1 0195 */ 0196 typedef enum UProperty { 0197 /* 0198 * Note: UProperty constants are parsed by preparseucd.py. 0199 * It matches lines like 0200 * UCHAR_<Unicode property name>=<integer>, 0201 */ 0202 0203 /* Note: Place UCHAR_ALPHABETIC before UCHAR_BINARY_START so that 0204 debuggers display UCHAR_ALPHABETIC as the symbolic name for 0, 0205 rather than UCHAR_BINARY_START. Likewise for other *_START 0206 identifiers. */ 0207 0208 /** Binary property Alphabetic. Same as u_isUAlphabetic, different from u_isalpha. 0209 Lu+Ll+Lt+Lm+Lo+Nl+Other_Alphabetic @stable ICU 2.1 */ 0210 UCHAR_ALPHABETIC=0, 0211 /** First constant for binary Unicode properties. @stable ICU 2.1 */ 0212 UCHAR_BINARY_START=UCHAR_ALPHABETIC, 0213 /** Binary property ASCII_Hex_Digit. 0-9 A-F a-f @stable ICU 2.1 */ 0214 UCHAR_ASCII_HEX_DIGIT=1, 0215 /** Binary property Bidi_Control. 0216 Format controls which have specific functions 0217 in the Bidi Algorithm. @stable ICU 2.1 */ 0218 UCHAR_BIDI_CONTROL=2, 0219 /** Binary property Bidi_Mirrored. 0220 Characters that may change display in RTL text. 0221 Same as u_isMirrored. 0222 See Bidi Algorithm, UTR 9. @stable ICU 2.1 */ 0223 UCHAR_BIDI_MIRRORED=3, 0224 /** Binary property Dash. Variations of dashes. @stable ICU 2.1 */ 0225 UCHAR_DASH=4, 0226 /** Binary property Default_Ignorable_Code_Point (new in Unicode 3.2). 0227 Ignorable in most processing. 0228 <2060..206F, FFF0..FFFB, E0000..E0FFF>+Other_Default_Ignorable_Code_Point+(Cf+Cc+Cs-White_Space) @stable ICU 2.1 */ 0229 UCHAR_DEFAULT_IGNORABLE_CODE_POINT=5, 0230 /** Binary property Deprecated (new in Unicode 3.2). 0231 The usage of deprecated characters is strongly discouraged. @stable ICU 2.1 */ 0232 UCHAR_DEPRECATED=6, 0233 /** Binary property Diacritic. Characters that linguistically modify 0234 the meaning of another character to which they apply. @stable ICU 2.1 */ 0235 UCHAR_DIACRITIC=7, 0236 /** Binary property Extender. 0237 Extend the value or shape of a preceding alphabetic character, 0238 e.g., length and iteration marks. @stable ICU 2.1 */ 0239 UCHAR_EXTENDER=8, 0240 /** Binary property Full_Composition_Exclusion. 0241 CompositionExclusions.txt+Singleton Decompositions+ 0242 Non-Starter Decompositions. @stable ICU 2.1 */ 0243 UCHAR_FULL_COMPOSITION_EXCLUSION=9, 0244 /** Binary property Grapheme_Base (new in Unicode 3.2). 0245 For programmatic determination of grapheme cluster boundaries. 0246 [0..10FFFF]-Cc-Cf-Cs-Co-Cn-Zl-Zp-Grapheme_Link-Grapheme_Extend-CGJ @stable ICU 2.1 */ 0247 UCHAR_GRAPHEME_BASE=10, 0248 /** Binary property Grapheme_Extend (new in Unicode 3.2). 0249 For programmatic determination of grapheme cluster boundaries. 0250 Me+Mn+Mc+Other_Grapheme_Extend-Grapheme_Link-CGJ @stable ICU 2.1 */ 0251 UCHAR_GRAPHEME_EXTEND=11, 0252 /** Binary property Grapheme_Link (new in Unicode 3.2). 0253 For programmatic determination of grapheme cluster boundaries. @stable ICU 2.1 */ 0254 UCHAR_GRAPHEME_LINK=12, 0255 /** Binary property Hex_Digit. 0256 Characters commonly used for hexadecimal numbers. @stable ICU 2.1 */ 0257 UCHAR_HEX_DIGIT=13, 0258 /** Binary property Hyphen. Dashes used to mark connections 0259 between pieces of words, plus the Katakana middle dot. @stable ICU 2.1 */ 0260 UCHAR_HYPHEN=14, 0261 /** Binary property ID_Continue. 0262 Characters that can continue an identifier. 0263 DerivedCoreProperties.txt also says "NOTE: Cf characters should be filtered out." 0264 ID_Start+Mn+Mc+Nd+Pc @stable ICU 2.1 */ 0265 UCHAR_ID_CONTINUE=15, 0266 /** Binary property ID_Start. 0267 Characters that can start an identifier. 0268 Lu+Ll+Lt+Lm+Lo+Nl @stable ICU 2.1 */ 0269 UCHAR_ID_START=16, 0270 /** Binary property Ideographic. 0271 CJKV ideographs. @stable ICU 2.1 */ 0272 UCHAR_IDEOGRAPHIC=17, 0273 /** Binary property IDS_Binary_Operator (new in Unicode 3.2). 0274 For programmatic determination of 0275 Ideographic Description Sequences. @stable ICU 2.1 */ 0276 UCHAR_IDS_BINARY_OPERATOR=18, 0277 /** Binary property IDS_Trinary_Operator (new in Unicode 3.2). 0278 For programmatic determination of 0279 Ideographic Description Sequences. @stable ICU 2.1 */ 0280 UCHAR_IDS_TRINARY_OPERATOR=19, 0281 /** Binary property Join_Control. 0282 Format controls for cursive joining and ligation. @stable ICU 2.1 */ 0283 UCHAR_JOIN_CONTROL=20, 0284 /** Binary property Logical_Order_Exception (new in Unicode 3.2). 0285 Characters that do not use logical order and 0286 require special handling in most processing. @stable ICU 2.1 */ 0287 UCHAR_LOGICAL_ORDER_EXCEPTION=21, 0288 /** Binary property Lowercase. Same as u_isULowercase, different from u_islower. 0289 Ll+Other_Lowercase @stable ICU 2.1 */ 0290 UCHAR_LOWERCASE=22, 0291 /** Binary property Math. Sm+Other_Math @stable ICU 2.1 */ 0292 UCHAR_MATH=23, 0293 /** Binary property Noncharacter_Code_Point. 0294 Code points that are explicitly defined as illegal 0295 for the encoding of characters. @stable ICU 2.1 */ 0296 UCHAR_NONCHARACTER_CODE_POINT=24, 0297 /** Binary property Quotation_Mark. @stable ICU 2.1 */ 0298 UCHAR_QUOTATION_MARK=25, 0299 /** Binary property Radical (new in Unicode 3.2). 0300 For programmatic determination of 0301 Ideographic Description Sequences. @stable ICU 2.1 */ 0302 UCHAR_RADICAL=26, 0303 /** Binary property Soft_Dotted (new in Unicode 3.2). 0304 Characters with a "soft dot", like i or j. 0305 An accent placed on these characters causes 0306 the dot to disappear. @stable ICU 2.1 */ 0307 UCHAR_SOFT_DOTTED=27, 0308 /** Binary property Terminal_Punctuation. 0309 Punctuation characters that generally mark 0310 the end of textual units. @stable ICU 2.1 */ 0311 UCHAR_TERMINAL_PUNCTUATION=28, 0312 /** Binary property Unified_Ideograph (new in Unicode 3.2). 0313 For programmatic determination of 0314 Ideographic Description Sequences. @stable ICU 2.1 */ 0315 UCHAR_UNIFIED_IDEOGRAPH=29, 0316 /** Binary property Uppercase. Same as u_isUUppercase, different from u_isupper. 0317 Lu+Other_Uppercase @stable ICU 2.1 */ 0318 UCHAR_UPPERCASE=30, 0319 /** Binary property White_Space. 0320 Same as u_isUWhiteSpace, different from u_isspace and u_isWhitespace. 0321 Space characters+TAB+CR+LF-ZWSP-ZWNBSP @stable ICU 2.1 */ 0322 UCHAR_WHITE_SPACE=31, 0323 /** Binary property XID_Continue. 0324 ID_Continue modified to allow closure under 0325 normalization forms NFKC and NFKD. @stable ICU 2.1 */ 0326 UCHAR_XID_CONTINUE=32, 0327 /** Binary property XID_Start. ID_Start modified to allow 0328 closure under normalization forms NFKC and NFKD. @stable ICU 2.1 */ 0329 UCHAR_XID_START=33, 0330 /** Binary property Case_Sensitive. Either the source of a case 0331 mapping or _in_ the target of a case mapping. Not the same as 0332 the general category Cased_Letter. @stable ICU 2.6 */ 0333 UCHAR_CASE_SENSITIVE=34, 0334 /** Binary property STerm (new in Unicode 4.0.1). 0335 Sentence Terminal. Used in UAX #29: Text Boundaries 0336 (http://www.unicode.org/reports/tr29/) 0337 @stable ICU 3.0 */ 0338 UCHAR_S_TERM=35, 0339 /** Binary property Variation_Selector (new in Unicode 4.0.1). 0340 Indicates all those characters that qualify as Variation Selectors. 0341 For details on the behavior of these characters, 0342 see StandardizedVariants.html and 15.6 Variation Selectors. 0343 @stable ICU 3.0 */ 0344 UCHAR_VARIATION_SELECTOR=36, 0345 /** Binary property NFD_Inert. 0346 ICU-specific property for characters that are inert under NFD, 0347 i.e., they do not interact with adjacent characters. 0348 See the documentation for the Normalizer2 class and the 0349 Normalizer2::isInert() method. 0350 @stable ICU 3.0 */ 0351 UCHAR_NFD_INERT=37, 0352 /** Binary property NFKD_Inert. 0353 ICU-specific property for characters that are inert under NFKD, 0354 i.e., they do not interact with adjacent characters. 0355 See the documentation for the Normalizer2 class and the 0356 Normalizer2::isInert() method. 0357 @stable ICU 3.0 */ 0358 UCHAR_NFKD_INERT=38, 0359 /** Binary property NFC_Inert. 0360 ICU-specific property for characters that are inert under NFC, 0361 i.e., they do not interact with adjacent characters. 0362 See the documentation for the Normalizer2 class and the 0363 Normalizer2::isInert() method. 0364 @stable ICU 3.0 */ 0365 UCHAR_NFC_INERT=39, 0366 /** Binary property NFKC_Inert. 0367 ICU-specific property for characters that are inert under NFKC, 0368 i.e., they do not interact with adjacent characters. 0369 See the documentation for the Normalizer2 class and the 0370 Normalizer2::isInert() method. 0371 @stable ICU 3.0 */ 0372 UCHAR_NFKC_INERT=40, 0373 /** Binary Property Segment_Starter. 0374 ICU-specific property for characters that are starters in terms of 0375 Unicode normalization and combining character sequences. 0376 They have ccc=0 and do not occur in non-initial position of the 0377 canonical decomposition of any character 0378 (like a-umlaut in NFD and a Jamo T in an NFD(Hangul LVT)). 0379 ICU uses this property for segmenting a string for generating a set of 0380 canonically equivalent strings, e.g. for canonical closure while 0381 processing collation tailoring rules. 0382 @stable ICU 3.0 */ 0383 UCHAR_SEGMENT_STARTER=41, 0384 /** Binary property Pattern_Syntax (new in Unicode 4.1). 0385 See UAX #31 Identifier and Pattern Syntax 0386 (http://www.unicode.org/reports/tr31/) 0387 @stable ICU 3.4 */ 0388 UCHAR_PATTERN_SYNTAX=42, 0389 /** Binary property Pattern_White_Space (new in Unicode 4.1). 0390 See UAX #31 Identifier and Pattern Syntax 0391 (http://www.unicode.org/reports/tr31/) 0392 @stable ICU 3.4 */ 0393 UCHAR_PATTERN_WHITE_SPACE=43, 0394 /** Binary property alnum (a C/POSIX character class). 0395 Implemented according to the UTS #18 Annex C Standard Recommendation. 0396 See the uchar.h file documentation. 0397 @stable ICU 3.4 */ 0398 UCHAR_POSIX_ALNUM=44, 0399 /** Binary property blank (a C/POSIX character class). 0400 Implemented according to the UTS #18 Annex C Standard Recommendation. 0401 See the uchar.h file documentation. 0402 @stable ICU 3.4 */ 0403 UCHAR_POSIX_BLANK=45, 0404 /** Binary property graph (a C/POSIX character class). 0405 Implemented according to the UTS #18 Annex C Standard Recommendation. 0406 See the uchar.h file documentation. 0407 @stable ICU 3.4 */ 0408 UCHAR_POSIX_GRAPH=46, 0409 /** Binary property print (a C/POSIX character class). 0410 Implemented according to the UTS #18 Annex C Standard Recommendation. 0411 See the uchar.h file documentation. 0412 @stable ICU 3.4 */ 0413 UCHAR_POSIX_PRINT=47, 0414 /** Binary property xdigit (a C/POSIX character class). 0415 Implemented according to the UTS #18 Annex C Standard Recommendation. 0416 See the uchar.h file documentation. 0417 @stable ICU 3.4 */ 0418 UCHAR_POSIX_XDIGIT=48, 0419 /** Binary property Cased. For Lowercase, Uppercase and Titlecase characters. @stable ICU 4.4 */ 0420 UCHAR_CASED=49, 0421 /** Binary property Case_Ignorable. Used in context-sensitive case mappings. @stable ICU 4.4 */ 0422 UCHAR_CASE_IGNORABLE=50, 0423 /** Binary property Changes_When_Lowercased. @stable ICU 4.4 */ 0424 UCHAR_CHANGES_WHEN_LOWERCASED=51, 0425 /** Binary property Changes_When_Uppercased. @stable ICU 4.4 */ 0426 UCHAR_CHANGES_WHEN_UPPERCASED=52, 0427 /** Binary property Changes_When_Titlecased. @stable ICU 4.4 */ 0428 UCHAR_CHANGES_WHEN_TITLECASED=53, 0429 /** Binary property Changes_When_Casefolded. @stable ICU 4.4 */ 0430 UCHAR_CHANGES_WHEN_CASEFOLDED=54, 0431 /** Binary property Changes_When_Casemapped. @stable ICU 4.4 */ 0432 UCHAR_CHANGES_WHEN_CASEMAPPED=55, 0433 /** Binary property Changes_When_NFKC_Casefolded. @stable ICU 4.4 */ 0434 UCHAR_CHANGES_WHEN_NFKC_CASEFOLDED=56, 0435 /** 0436 * Binary property Emoji. 0437 * See http://www.unicode.org/reports/tr51/#Emoji_Properties 0438 * 0439 * @stable ICU 57 0440 */ 0441 UCHAR_EMOJI=57, 0442 /** 0443 * Binary property Emoji_Presentation. 0444 * See http://www.unicode.org/reports/tr51/#Emoji_Properties 0445 * 0446 * @stable ICU 57 0447 */ 0448 UCHAR_EMOJI_PRESENTATION=58, 0449 /** 0450 * Binary property Emoji_Modifier. 0451 * See http://www.unicode.org/reports/tr51/#Emoji_Properties 0452 * 0453 * @stable ICU 57 0454 */ 0455 UCHAR_EMOJI_MODIFIER=59, 0456 /** 0457 * Binary property Emoji_Modifier_Base. 0458 * See http://www.unicode.org/reports/tr51/#Emoji_Properties 0459 * 0460 * @stable ICU 57 0461 */ 0462 UCHAR_EMOJI_MODIFIER_BASE=60, 0463 /** 0464 * Binary property Emoji_Component. 0465 * See http://www.unicode.org/reports/tr51/#Emoji_Properties 0466 * 0467 * @stable ICU 60 0468 */ 0469 UCHAR_EMOJI_COMPONENT=61, 0470 /** 0471 * Binary property Regional_Indicator. 0472 * @stable ICU 60 0473 */ 0474 UCHAR_REGIONAL_INDICATOR=62, 0475 /** 0476 * Binary property Prepended_Concatenation_Mark. 0477 * @stable ICU 60 0478 */ 0479 UCHAR_PREPENDED_CONCATENATION_MARK=63, 0480 /** 0481 * Binary property Extended_Pictographic. 0482 * See http://www.unicode.org/reports/tr51/#Emoji_Properties 0483 * 0484 * @stable ICU 62 0485 */ 0486 UCHAR_EXTENDED_PICTOGRAPHIC=64, 0487 /** 0488 * Binary property of strings Basic_Emoji. 0489 * See https://www.unicode.org/reports/tr51/#Emoji_Sets 0490 * 0491 * @stable ICU 70 0492 */ 0493 UCHAR_BASIC_EMOJI=65, 0494 /** 0495 * Binary property of strings Emoji_Keycap_Sequence. 0496 * See https://www.unicode.org/reports/tr51/#Emoji_Sets 0497 * 0498 * @stable ICU 70 0499 */ 0500 UCHAR_EMOJI_KEYCAP_SEQUENCE=66, 0501 /** 0502 * Binary property of strings RGI_Emoji_Modifier_Sequence. 0503 * See https://www.unicode.org/reports/tr51/#Emoji_Sets 0504 * 0505 * @stable ICU 70 0506 */ 0507 UCHAR_RGI_EMOJI_MODIFIER_SEQUENCE=67, 0508 /** 0509 * Binary property of strings RGI_Emoji_Flag_Sequence. 0510 * See https://www.unicode.org/reports/tr51/#Emoji_Sets 0511 * 0512 * @stable ICU 70 0513 */ 0514 UCHAR_RGI_EMOJI_FLAG_SEQUENCE=68, 0515 /** 0516 * Binary property of strings RGI_Emoji_Tag_Sequence. 0517 * See https://www.unicode.org/reports/tr51/#Emoji_Sets 0518 * 0519 * @stable ICU 70 0520 */ 0521 UCHAR_RGI_EMOJI_TAG_SEQUENCE=69, 0522 /** 0523 * Binary property of strings RGI_Emoji_ZWJ_Sequence. 0524 * See https://www.unicode.org/reports/tr51/#Emoji_Sets 0525 * 0526 * @stable ICU 70 0527 */ 0528 UCHAR_RGI_EMOJI_ZWJ_SEQUENCE=70, 0529 /** 0530 * Binary property of strings RGI_Emoji. 0531 * See https://www.unicode.org/reports/tr51/#Emoji_Sets 0532 * 0533 * @stable ICU 70 0534 */ 0535 UCHAR_RGI_EMOJI=71, 0536 /** 0537 * Binary property IDS_Unary_Operator. 0538 * For programmatic determination of Ideographic Description Sequences. 0539 * 0540 * @stable ICU 74 0541 */ 0542 UCHAR_IDS_UNARY_OPERATOR=72, 0543 /** 0544 * Binary property ID_Compat_Math_Start. 0545 * Used in mathematical identifier profile in UAX #31. 0546 * @stable ICU 74 0547 */ 0548 UCHAR_ID_COMPAT_MATH_START=73, 0549 /** 0550 * Binary property ID_Compat_Math_Continue. 0551 * Used in mathematical identifier profile in UAX #31. 0552 * @stable ICU 74 0553 */ 0554 UCHAR_ID_COMPAT_MATH_CONTINUE=74, 0555 #ifndef U_HIDE_DRAFT_API 0556 /** 0557 * Binary property Modifier_Combining_Mark. 0558 * Used by the AMTRA algorithm in UAX #53. 0559 * @draft ICU 76 0560 */ 0561 UCHAR_MODIFIER_COMBINING_MARK=75, 0562 #endif // U_HIDE_DRAFT_API 0563 #ifndef U_HIDE_DEPRECATED_API 0564 /** 0565 * One more than the last constant for binary Unicode properties. 0566 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. 0567 */ 0568 UCHAR_BINARY_LIMIT=76, 0569 #endif // U_HIDE_DEPRECATED_API 0570 0571 /** Enumerated property Bidi_Class. 0572 Same as u_charDirection, returns UCharDirection values. @stable ICU 2.2 */ 0573 UCHAR_BIDI_CLASS=0x1000, 0574 /** First constant for enumerated/integer Unicode properties. @stable ICU 2.2 */ 0575 UCHAR_INT_START=UCHAR_BIDI_CLASS, 0576 /** Enumerated property Block. 0577 Same as ublock_getCode, returns UBlockCode values. @stable ICU 2.2 */ 0578 UCHAR_BLOCK=0x1001, 0579 /** Enumerated property Canonical_Combining_Class. 0580 Same as u_getCombiningClass, returns 8-bit numeric values. @stable ICU 2.2 */ 0581 UCHAR_CANONICAL_COMBINING_CLASS=0x1002, 0582 /** Enumerated property Decomposition_Type. 0583 Returns UDecompositionType values. @stable ICU 2.2 */ 0584 UCHAR_DECOMPOSITION_TYPE=0x1003, 0585 /** Enumerated property East_Asian_Width. 0586 See http://www.unicode.org/reports/tr11/ 0587 Returns UEastAsianWidth values. @stable ICU 2.2 */ 0588 UCHAR_EAST_ASIAN_WIDTH=0x1004, 0589 /** Enumerated property General_Category. 0590 Same as u_charType, returns UCharCategory values. @stable ICU 2.2 */ 0591 UCHAR_GENERAL_CATEGORY=0x1005, 0592 /** Enumerated property Joining_Group. 0593 Returns UJoiningGroup values. @stable ICU 2.2 */ 0594 UCHAR_JOINING_GROUP=0x1006, 0595 /** Enumerated property Joining_Type. 0596 Returns UJoiningType values. @stable ICU 2.2 */ 0597 UCHAR_JOINING_TYPE=0x1007, 0598 /** Enumerated property Line_Break. 0599 Returns ULineBreak values. @stable ICU 2.2 */ 0600 UCHAR_LINE_BREAK=0x1008, 0601 /** Enumerated property Numeric_Type. 0602 Returns UNumericType values. @stable ICU 2.2 */ 0603 UCHAR_NUMERIC_TYPE=0x1009, 0604 /** Enumerated property Script. 0605 Same as uscript_getScript, returns UScriptCode values. @stable ICU 2.2 */ 0606 UCHAR_SCRIPT=0x100A, 0607 /** Enumerated property Hangul_Syllable_Type, new in Unicode 4. 0608 Returns UHangulSyllableType values. @stable ICU 2.6 */ 0609 UCHAR_HANGUL_SYLLABLE_TYPE=0x100B, 0610 /** Enumerated property NFD_Quick_Check. 0611 Returns UNormalizationCheckResult values. @stable ICU 3.0 */ 0612 UCHAR_NFD_QUICK_CHECK=0x100C, 0613 /** Enumerated property NFKD_Quick_Check. 0614 Returns UNormalizationCheckResult values. @stable ICU 3.0 */ 0615 UCHAR_NFKD_QUICK_CHECK=0x100D, 0616 /** Enumerated property NFC_Quick_Check. 0617 Returns UNormalizationCheckResult values. @stable ICU 3.0 */ 0618 UCHAR_NFC_QUICK_CHECK=0x100E, 0619 /** Enumerated property NFKC_Quick_Check. 0620 Returns UNormalizationCheckResult values. @stable ICU 3.0 */ 0621 UCHAR_NFKC_QUICK_CHECK=0x100F, 0622 /** Enumerated property Lead_Canonical_Combining_Class. 0623 ICU-specific property for the ccc of the first code point 0624 of the decomposition, or lccc(c)=ccc(NFD(c)[0]). 0625 Useful for checking for canonically ordered text; 0626 see UNORM_FCD and http://www.unicode.org/notes/tn5/#FCD . 0627 Returns 8-bit numeric values like UCHAR_CANONICAL_COMBINING_CLASS. @stable ICU 3.0 */ 0628 UCHAR_LEAD_CANONICAL_COMBINING_CLASS=0x1010, 0629 /** Enumerated property Trail_Canonical_Combining_Class. 0630 ICU-specific property for the ccc of the last code point 0631 of the decomposition, or tccc(c)=ccc(NFD(c)[last]). 0632 Useful for checking for canonically ordered text; 0633 see UNORM_FCD and http://www.unicode.org/notes/tn5/#FCD . 0634 Returns 8-bit numeric values like UCHAR_CANONICAL_COMBINING_CLASS. @stable ICU 3.0 */ 0635 UCHAR_TRAIL_CANONICAL_COMBINING_CLASS=0x1011, 0636 /** Enumerated property Grapheme_Cluster_Break (new in Unicode 4.1). 0637 Used in UAX #29: Text Boundaries 0638 (http://www.unicode.org/reports/tr29/) 0639 Returns UGraphemeClusterBreak values. @stable ICU 3.4 */ 0640 UCHAR_GRAPHEME_CLUSTER_BREAK=0x1012, 0641 /** Enumerated property Sentence_Break (new in Unicode 4.1). 0642 Used in UAX #29: Text Boundaries 0643 (http://www.unicode.org/reports/tr29/) 0644 Returns USentenceBreak values. @stable ICU 3.4 */ 0645 UCHAR_SENTENCE_BREAK=0x1013, 0646 /** Enumerated property Word_Break (new in Unicode 4.1). 0647 Used in UAX #29: Text Boundaries 0648 (http://www.unicode.org/reports/tr29/) 0649 Returns UWordBreakValues values. @stable ICU 3.4 */ 0650 UCHAR_WORD_BREAK=0x1014, 0651 /** Enumerated property Bidi_Paired_Bracket_Type (new in Unicode 6.3). 0652 Used in UAX #9: Unicode Bidirectional Algorithm 0653 (http://www.unicode.org/reports/tr9/) 0654 Returns UBidiPairedBracketType values. @stable ICU 52 */ 0655 UCHAR_BIDI_PAIRED_BRACKET_TYPE=0x1015, 0656 /** 0657 * Enumerated property Indic_Positional_Category. 0658 * New in Unicode 6.0 as provisional property Indic_Matra_Category; 0659 * renamed and changed to informative in Unicode 8.0. 0660 * See http://www.unicode.org/reports/tr44/#IndicPositionalCategory.txt 0661 * @stable ICU 63 0662 */ 0663 UCHAR_INDIC_POSITIONAL_CATEGORY=0x1016, 0664 /** 0665 * Enumerated property Indic_Syllabic_Category. 0666 * New in Unicode 6.0 as provisional; informative since Unicode 8.0. 0667 * See http://www.unicode.org/reports/tr44/#IndicSyllabicCategory.txt 0668 * @stable ICU 63 0669 */ 0670 UCHAR_INDIC_SYLLABIC_CATEGORY=0x1017, 0671 /** 0672 * Enumerated property Vertical_Orientation. 0673 * Used for UAX #50 Unicode Vertical Text Layout (https://www.unicode.org/reports/tr50/). 0674 * New as a UCD property in Unicode 10.0. 0675 * @stable ICU 63 0676 */ 0677 UCHAR_VERTICAL_ORIENTATION=0x1018, 0678 #ifndef U_HIDE_DRAFT_API 0679 /** 0680 * Enumerated property Identifier_Status. 0681 * Used for UTS #39 General Security Profile for Identifiers 0682 * (https://www.unicode.org/reports/tr39/#General_Security_Profile). 0683 * @draft ICU 75 0684 */ 0685 UCHAR_IDENTIFIER_STATUS=0x1019, 0686 /** 0687 * Enumerated property Indic_Conjunct_Break. 0688 * Used in the grapheme cluster break algorithm in UAX #29. 0689 * @draft ICU 76 0690 */ 0691 UCHAR_INDIC_CONJUNCT_BREAK=0x101A, 0692 #endif // U_HIDE_DRAFT_API 0693 #ifndef U_HIDE_DEPRECATED_API 0694 /** 0695 * One more than the last constant for enumerated/integer Unicode properties. 0696 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. 0697 */ 0698 UCHAR_INT_LIMIT=0x101B, 0699 #endif // U_HIDE_DEPRECATED_API 0700 0701 /** Bitmask property General_Category_Mask. 0702 This is the General_Category property returned as a bit mask. 0703 When used in u_getIntPropertyValue(c), same as U_MASK(u_charType(c)), 0704 returns bit masks for UCharCategory values where exactly one bit is set. 0705 When used with u_getPropertyValueName() and u_getPropertyValueEnum(), 0706 a multi-bit mask is used for sets of categories like "Letters". 0707 Mask values should be cast to uint32_t. 0708 @stable ICU 2.4 */ 0709 UCHAR_GENERAL_CATEGORY_MASK=0x2000, 0710 /** First constant for bit-mask Unicode properties. @stable ICU 2.4 */ 0711 UCHAR_MASK_START=UCHAR_GENERAL_CATEGORY_MASK, 0712 #ifndef U_HIDE_DEPRECATED_API 0713 /** 0714 * One more than the last constant for bit-mask Unicode properties. 0715 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. 0716 */ 0717 UCHAR_MASK_LIMIT=0x2001, 0718 #endif // U_HIDE_DEPRECATED_API 0719 0720 /** Double property Numeric_Value. 0721 Corresponds to u_getNumericValue. @stable ICU 2.4 */ 0722 UCHAR_NUMERIC_VALUE=0x3000, 0723 /** First constant for double Unicode properties. @stable ICU 2.4 */ 0724 UCHAR_DOUBLE_START=UCHAR_NUMERIC_VALUE, 0725 #ifndef U_HIDE_DEPRECATED_API 0726 /** 0727 * One more than the last constant for double Unicode properties. 0728 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. 0729 */ 0730 UCHAR_DOUBLE_LIMIT=0x3001, 0731 #endif // U_HIDE_DEPRECATED_API 0732 0733 /** String property Age. 0734 Corresponds to u_charAge. @stable ICU 2.4 */ 0735 UCHAR_AGE=0x4000, 0736 /** First constant for string Unicode properties. @stable ICU 2.4 */ 0737 UCHAR_STRING_START=UCHAR_AGE, 0738 /** String property Bidi_Mirroring_Glyph. 0739 Corresponds to u_charMirror. @stable ICU 2.4 */ 0740 UCHAR_BIDI_MIRRORING_GLYPH=0x4001, 0741 /** String property Case_Folding. 0742 Corresponds to u_strFoldCase in ustring.h. @stable ICU 2.4 */ 0743 UCHAR_CASE_FOLDING=0x4002, 0744 #ifndef U_HIDE_DEPRECATED_API 0745 /** Deprecated string property ISO_Comment. 0746 Corresponds to u_getISOComment. @deprecated ICU 49 */ 0747 UCHAR_ISO_COMMENT=0x4003, 0748 #endif /* U_HIDE_DEPRECATED_API */ 0749 /** String property Lowercase_Mapping. 0750 Corresponds to u_strToLower in ustring.h. @stable ICU 2.4 */ 0751 UCHAR_LOWERCASE_MAPPING=0x4004, 0752 /** String property Name. 0753 Corresponds to u_charName. @stable ICU 2.4 */ 0754 UCHAR_NAME=0x4005, 0755 /** String property Simple_Case_Folding. 0756 Corresponds to u_foldCase. @stable ICU 2.4 */ 0757 UCHAR_SIMPLE_CASE_FOLDING=0x4006, 0758 /** String property Simple_Lowercase_Mapping. 0759 Corresponds to u_tolower. @stable ICU 2.4 */ 0760 UCHAR_SIMPLE_LOWERCASE_MAPPING=0x4007, 0761 /** String property Simple_Titlecase_Mapping. 0762 Corresponds to u_totitle. @stable ICU 2.4 */ 0763 UCHAR_SIMPLE_TITLECASE_MAPPING=0x4008, 0764 /** String property Simple_Uppercase_Mapping. 0765 Corresponds to u_toupper. @stable ICU 2.4 */ 0766 UCHAR_SIMPLE_UPPERCASE_MAPPING=0x4009, 0767 /** String property Titlecase_Mapping. 0768 Corresponds to u_strToTitle in ustring.h. @stable ICU 2.4 */ 0769 UCHAR_TITLECASE_MAPPING=0x400A, 0770 #ifndef U_HIDE_DEPRECATED_API 0771 /** String property Unicode_1_Name. 0772 This property is of little practical value. 0773 Beginning with ICU 49, ICU APIs return an empty string for this property. 0774 Corresponds to u_charName(U_UNICODE_10_CHAR_NAME). @deprecated ICU 49 */ 0775 UCHAR_UNICODE_1_NAME=0x400B, 0776 #endif /* U_HIDE_DEPRECATED_API */ 0777 /** String property Uppercase_Mapping. 0778 Corresponds to u_strToUpper in ustring.h. @stable ICU 2.4 */ 0779 UCHAR_UPPERCASE_MAPPING=0x400C, 0780 /** String property Bidi_Paired_Bracket (new in Unicode 6.3). 0781 Corresponds to u_getBidiPairedBracket. @stable ICU 52 */ 0782 UCHAR_BIDI_PAIRED_BRACKET=0x400D, 0783 #ifndef U_HIDE_DEPRECATED_API 0784 /** 0785 * One more than the last constant for string Unicode properties. 0786 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. 0787 */ 0788 UCHAR_STRING_LIMIT=0x400E, 0789 #endif // U_HIDE_DEPRECATED_API 0790 0791 /** Miscellaneous property Script_Extensions (new in Unicode 6.0). 0792 Some characters are commonly used in multiple scripts. 0793 For more information, see UAX #24: http://www.unicode.org/reports/tr24/. 0794 Corresponds to uscript_hasScript and uscript_getScriptExtensions in uscript.h. 0795 @stable ICU 4.6 */ 0796 UCHAR_SCRIPT_EXTENSIONS=0x7000, 0797 /** First constant for Unicode properties with unusual value types. @stable ICU 4.6 */ 0798 UCHAR_OTHER_PROPERTY_START=UCHAR_SCRIPT_EXTENSIONS, 0799 #ifndef U_HIDE_DRAFT_API 0800 /** 0801 * Miscellaneous property Identifier_Type. 0802 * Used for UTS #39 General Security Profile for Identifiers 0803 * (https://www.unicode.org/reports/tr39/#General_Security_Profile). 0804 * 0805 * Corresponds to u_hasIDType() and u_getIDTypes(). 0806 * 0807 * Each code point maps to a <i>set</i> of UIdentifierType values. 0808 * 0809 * @see u_hasIDType 0810 * @see u_getIDTypes 0811 * @draft ICU 75 0812 */ 0813 UCHAR_IDENTIFIER_TYPE=0x7001, 0814 #endif // U_HIDE_DRAFT_API 0815 #ifndef U_HIDE_DEPRECATED_API 0816 /** 0817 * One more than the last constant for Unicode properties with unusual value types. 0818 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. 0819 */ 0820 UCHAR_OTHER_PROPERTY_LIMIT=0x7002, 0821 #endif // U_HIDE_DEPRECATED_API 0822 0823 /** Represents a nonexistent or invalid property or property value. @stable ICU 2.4 */ 0824 UCHAR_INVALID_CODE = -1 0825 } UProperty; 0826 0827 /** 0828 * Data for enumerated Unicode general category types. 0829 * See http://www.unicode.org/Public/UNIDATA/UnicodeData.html . 0830 * @stable ICU 2.0 0831 */ 0832 typedef enum UCharCategory 0833 { 0834 /* 0835 * Note: UCharCategory constants and their API comments are parsed by preparseucd.py. 0836 * It matches pairs of lines like 0837 * / ** <Unicode 2-letter General_Category value> comment... * / 0838 * U_<[A-Z_]+> = <integer>, 0839 */ 0840 0841 /** Non-category for unassigned and non-character code points. @stable ICU 2.0 */ 0842 U_UNASSIGNED = 0, 0843 /** Cn "Other, Not Assigned (no characters in [UnicodeData.txt] have this property)" (same as U_UNASSIGNED!) @stable ICU 2.0 */ 0844 U_GENERAL_OTHER_TYPES = 0, 0845 /** Lu @stable ICU 2.0 */ 0846 U_UPPERCASE_LETTER = 1, 0847 /** Ll @stable ICU 2.0 */ 0848 U_LOWERCASE_LETTER = 2, 0849 /** Lt @stable ICU 2.0 */ 0850 U_TITLECASE_LETTER = 3, 0851 /** Lm @stable ICU 2.0 */ 0852 U_MODIFIER_LETTER = 4, 0853 /** Lo @stable ICU 2.0 */ 0854 U_OTHER_LETTER = 5, 0855 /** Mn @stable ICU 2.0 */ 0856 U_NON_SPACING_MARK = 6, 0857 /** Me @stable ICU 2.0 */ 0858 U_ENCLOSING_MARK = 7, 0859 /** Mc @stable ICU 2.0 */ 0860 U_COMBINING_SPACING_MARK = 8, 0861 /** Nd @stable ICU 2.0 */ 0862 U_DECIMAL_DIGIT_NUMBER = 9, 0863 /** Nl @stable ICU 2.0 */ 0864 U_LETTER_NUMBER = 10, 0865 /** No @stable ICU 2.0 */ 0866 U_OTHER_NUMBER = 11, 0867 /** Zs @stable ICU 2.0 */ 0868 U_SPACE_SEPARATOR = 12, 0869 /** Zl @stable ICU 2.0 */ 0870 U_LINE_SEPARATOR = 13, 0871 /** Zp @stable ICU 2.0 */ 0872 U_PARAGRAPH_SEPARATOR = 14, 0873 /** Cc @stable ICU 2.0 */ 0874 U_CONTROL_CHAR = 15, 0875 /** Cf @stable ICU 2.0 */ 0876 U_FORMAT_CHAR = 16, 0877 /** Co @stable ICU 2.0 */ 0878 U_PRIVATE_USE_CHAR = 17, 0879 /** Cs @stable ICU 2.0 */ 0880 U_SURROGATE = 18, 0881 /** Pd @stable ICU 2.0 */ 0882 U_DASH_PUNCTUATION = 19, 0883 /** Ps @stable ICU 2.0 */ 0884 U_START_PUNCTUATION = 20, 0885 /** Pe @stable ICU 2.0 */ 0886 U_END_PUNCTUATION = 21, 0887 /** Pc @stable ICU 2.0 */ 0888 U_CONNECTOR_PUNCTUATION = 22, 0889 /** Po @stable ICU 2.0 */ 0890 U_OTHER_PUNCTUATION = 23, 0891 /** Sm @stable ICU 2.0 */ 0892 U_MATH_SYMBOL = 24, 0893 /** Sc @stable ICU 2.0 */ 0894 U_CURRENCY_SYMBOL = 25, 0895 /** Sk @stable ICU 2.0 */ 0896 U_MODIFIER_SYMBOL = 26, 0897 /** So @stable ICU 2.0 */ 0898 U_OTHER_SYMBOL = 27, 0899 /** Pi @stable ICU 2.0 */ 0900 U_INITIAL_PUNCTUATION = 28, 0901 /** Pf @stable ICU 2.0 */ 0902 U_FINAL_PUNCTUATION = 29, 0903 /** 0904 * One higher than the last enum UCharCategory constant. 0905 * This numeric value is stable (will not change), see 0906 * http://www.unicode.org/policies/stability_policy.html#Property_Value 0907 * 0908 * @stable ICU 2.0 0909 */ 0910 U_CHAR_CATEGORY_COUNT 0911 } UCharCategory; 0912 0913 /** 0914 * U_GC_XX_MASK constants are bit flags corresponding to Unicode 0915 * general category values. 0916 * For each category, the nth bit is set if the numeric value of the 0917 * corresponding UCharCategory constant is n. 0918 * 0919 * There are also some U_GC_Y_MASK constants for groups of general categories 0920 * like L for all letter categories. 0921 * 0922 * @see u_charType 0923 * @see U_GET_GC_MASK 0924 * @see UCharCategory 0925 * @stable ICU 2.1 0926 */ 0927 #define U_GC_CN_MASK U_MASK(U_GENERAL_OTHER_TYPES) 0928 0929 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 0930 #define U_GC_LU_MASK U_MASK(U_UPPERCASE_LETTER) 0931 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 0932 #define U_GC_LL_MASK U_MASK(U_LOWERCASE_LETTER) 0933 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 0934 #define U_GC_LT_MASK U_MASK(U_TITLECASE_LETTER) 0935 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 0936 #define U_GC_LM_MASK U_MASK(U_MODIFIER_LETTER) 0937 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 0938 #define U_GC_LO_MASK U_MASK(U_OTHER_LETTER) 0939 0940 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 0941 #define U_GC_MN_MASK U_MASK(U_NON_SPACING_MARK) 0942 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 0943 #define U_GC_ME_MASK U_MASK(U_ENCLOSING_MARK) 0944 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 0945 #define U_GC_MC_MASK U_MASK(U_COMBINING_SPACING_MARK) 0946 0947 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 0948 #define U_GC_ND_MASK U_MASK(U_DECIMAL_DIGIT_NUMBER) 0949 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 0950 #define U_GC_NL_MASK U_MASK(U_LETTER_NUMBER) 0951 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 0952 #define U_GC_NO_MASK U_MASK(U_OTHER_NUMBER) 0953 0954 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 0955 #define U_GC_ZS_MASK U_MASK(U_SPACE_SEPARATOR) 0956 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 0957 #define U_GC_ZL_MASK U_MASK(U_LINE_SEPARATOR) 0958 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 0959 #define U_GC_ZP_MASK U_MASK(U_PARAGRAPH_SEPARATOR) 0960 0961 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 0962 #define U_GC_CC_MASK U_MASK(U_CONTROL_CHAR) 0963 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 0964 #define U_GC_CF_MASK U_MASK(U_FORMAT_CHAR) 0965 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 0966 #define U_GC_CO_MASK U_MASK(U_PRIVATE_USE_CHAR) 0967 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 0968 #define U_GC_CS_MASK U_MASK(U_SURROGATE) 0969 0970 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 0971 #define U_GC_PD_MASK U_MASK(U_DASH_PUNCTUATION) 0972 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 0973 #define U_GC_PS_MASK U_MASK(U_START_PUNCTUATION) 0974 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 0975 #define U_GC_PE_MASK U_MASK(U_END_PUNCTUATION) 0976 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 0977 #define U_GC_PC_MASK U_MASK(U_CONNECTOR_PUNCTUATION) 0978 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 0979 #define U_GC_PO_MASK U_MASK(U_OTHER_PUNCTUATION) 0980 0981 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 0982 #define U_GC_SM_MASK U_MASK(U_MATH_SYMBOL) 0983 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 0984 #define U_GC_SC_MASK U_MASK(U_CURRENCY_SYMBOL) 0985 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 0986 #define U_GC_SK_MASK U_MASK(U_MODIFIER_SYMBOL) 0987 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 0988 #define U_GC_SO_MASK U_MASK(U_OTHER_SYMBOL) 0989 0990 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 0991 #define U_GC_PI_MASK U_MASK(U_INITIAL_PUNCTUATION) 0992 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 0993 #define U_GC_PF_MASK U_MASK(U_FINAL_PUNCTUATION) 0994 0995 0996 /** Mask constant for multiple UCharCategory bits (L Letters). @stable ICU 2.1 */ 0997 #define U_GC_L_MASK \ 0998 (U_GC_LU_MASK|U_GC_LL_MASK|U_GC_LT_MASK|U_GC_LM_MASK|U_GC_LO_MASK) 0999 1000 /** Mask constant for multiple UCharCategory bits (LC Cased Letters). @stable ICU 2.1 */ 1001 #define U_GC_LC_MASK \ 1002 (U_GC_LU_MASK|U_GC_LL_MASK|U_GC_LT_MASK) 1003 1004 /** Mask constant for multiple UCharCategory bits (M Marks). @stable ICU 2.1 */ 1005 #define U_GC_M_MASK (U_GC_MN_MASK|U_GC_ME_MASK|U_GC_MC_MASK) 1006 1007 /** Mask constant for multiple UCharCategory bits (N Numbers). @stable ICU 2.1 */ 1008 #define U_GC_N_MASK (U_GC_ND_MASK|U_GC_NL_MASK|U_GC_NO_MASK) 1009 1010 /** Mask constant for multiple UCharCategory bits (Z Separators). @stable ICU 2.1 */ 1011 #define U_GC_Z_MASK (U_GC_ZS_MASK|U_GC_ZL_MASK|U_GC_ZP_MASK) 1012 1013 /** Mask constant for multiple UCharCategory bits (C Others). @stable ICU 2.1 */ 1014 #define U_GC_C_MASK \ 1015 (U_GC_CN_MASK|U_GC_CC_MASK|U_GC_CF_MASK|U_GC_CO_MASK|U_GC_CS_MASK) 1016 1017 /** Mask constant for multiple UCharCategory bits (P Punctuation). @stable ICU 2.1 */ 1018 #define U_GC_P_MASK \ 1019 (U_GC_PD_MASK|U_GC_PS_MASK|U_GC_PE_MASK|U_GC_PC_MASK|U_GC_PO_MASK| \ 1020 U_GC_PI_MASK|U_GC_PF_MASK) 1021 1022 /** Mask constant for multiple UCharCategory bits (S Symbols). @stable ICU 2.1 */ 1023 #define U_GC_S_MASK (U_GC_SM_MASK|U_GC_SC_MASK|U_GC_SK_MASK|U_GC_SO_MASK) 1024 1025 /** 1026 * This specifies the language directional property of a character set. 1027 * @stable ICU 2.0 1028 */ 1029 typedef enum UCharDirection { 1030 /* 1031 * Note: UCharDirection constants and their API comments are parsed by preparseucd.py. 1032 * It matches pairs of lines like 1033 * / ** <Unicode 1..3-letter Bidi_Class value> comment... * / 1034 * U_<[A-Z_]+> = <integer>, 1035 */ 1036 1037 /** L @stable ICU 2.0 */ 1038 U_LEFT_TO_RIGHT = 0, 1039 /** R @stable ICU 2.0 */ 1040 U_RIGHT_TO_LEFT = 1, 1041 /** EN @stable ICU 2.0 */ 1042 U_EUROPEAN_NUMBER = 2, 1043 /** ES @stable ICU 2.0 */ 1044 U_EUROPEAN_NUMBER_SEPARATOR = 3, 1045 /** ET @stable ICU 2.0 */ 1046 U_EUROPEAN_NUMBER_TERMINATOR = 4, 1047 /** AN @stable ICU 2.0 */ 1048 U_ARABIC_NUMBER = 5, 1049 /** CS @stable ICU 2.0 */ 1050 U_COMMON_NUMBER_SEPARATOR = 6, 1051 /** B @stable ICU 2.0 */ 1052 U_BLOCK_SEPARATOR = 7, 1053 /** S @stable ICU 2.0 */ 1054 U_SEGMENT_SEPARATOR = 8, 1055 /** WS @stable ICU 2.0 */ 1056 U_WHITE_SPACE_NEUTRAL = 9, 1057 /** ON @stable ICU 2.0 */ 1058 U_OTHER_NEUTRAL = 10, 1059 /** LRE @stable ICU 2.0 */ 1060 U_LEFT_TO_RIGHT_EMBEDDING = 11, 1061 /** LRO @stable ICU 2.0 */ 1062 U_LEFT_TO_RIGHT_OVERRIDE = 12, 1063 /** AL @stable ICU 2.0 */ 1064 U_RIGHT_TO_LEFT_ARABIC = 13, 1065 /** RLE @stable ICU 2.0 */ 1066 U_RIGHT_TO_LEFT_EMBEDDING = 14, 1067 /** RLO @stable ICU 2.0 */ 1068 U_RIGHT_TO_LEFT_OVERRIDE = 15, 1069 /** PDF @stable ICU 2.0 */ 1070 U_POP_DIRECTIONAL_FORMAT = 16, 1071 /** NSM @stable ICU 2.0 */ 1072 U_DIR_NON_SPACING_MARK = 17, 1073 /** BN @stable ICU 2.0 */ 1074 U_BOUNDARY_NEUTRAL = 18, 1075 /** FSI @stable ICU 52 */ 1076 U_FIRST_STRONG_ISOLATE = 19, 1077 /** LRI @stable ICU 52 */ 1078 U_LEFT_TO_RIGHT_ISOLATE = 20, 1079 /** RLI @stable ICU 52 */ 1080 U_RIGHT_TO_LEFT_ISOLATE = 21, 1081 /** PDI @stable ICU 52 */ 1082 U_POP_DIRECTIONAL_ISOLATE = 22, 1083 #ifndef U_HIDE_DEPRECATED_API 1084 /** 1085 * One more than the highest UCharDirection value. 1086 * The highest value is available via u_getIntPropertyMaxValue(UCHAR_BIDI_CLASS). 1087 * 1088 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. 1089 */ 1090 U_CHAR_DIRECTION_COUNT 1091 #endif // U_HIDE_DEPRECATED_API 1092 } UCharDirection; 1093 1094 /** 1095 * Bidi Paired Bracket Type constants. 1096 * 1097 * @see UCHAR_BIDI_PAIRED_BRACKET_TYPE 1098 * @stable ICU 52 1099 */ 1100 typedef enum UBidiPairedBracketType { 1101 /* 1102 * Note: UBidiPairedBracketType constants are parsed by preparseucd.py. 1103 * It matches lines like 1104 * U_BPT_<Unicode Bidi_Paired_Bracket_Type value name> 1105 */ 1106 1107 /** Not a paired bracket. @stable ICU 52 */ 1108 U_BPT_NONE, 1109 /** Open paired bracket. @stable ICU 52 */ 1110 U_BPT_OPEN, 1111 /** Close paired bracket. @stable ICU 52 */ 1112 U_BPT_CLOSE, 1113 #ifndef U_HIDE_DEPRECATED_API 1114 /** 1115 * One more than the highest normal UBidiPairedBracketType value. 1116 * The highest value is available via u_getIntPropertyMaxValue(UCHAR_BIDI_PAIRED_BRACKET_TYPE). 1117 * 1118 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. 1119 */ 1120 U_BPT_COUNT /* 3 */ 1121 #endif // U_HIDE_DEPRECATED_API 1122 } UBidiPairedBracketType; 1123 1124 /** 1125 * Constants for Unicode blocks, see the Unicode Data file Blocks.txt 1126 * @stable ICU 2.0 1127 */ 1128 enum UBlockCode { 1129 /* 1130 * Note: UBlockCode constants are parsed by preparseucd.py. 1131 * It matches lines like 1132 * UBLOCK_<Unicode Block value name> = <integer>, 1133 */ 1134 1135 /** New No_Block value in Unicode 4. @stable ICU 2.6 */ 1136 UBLOCK_NO_BLOCK = 0, /*[none]*/ /* Special range indicating No_Block */ 1137 1138 /** @stable ICU 2.0 */ 1139 UBLOCK_BASIC_LATIN = 1, /*[0000]*/ 1140 1141 /** @stable ICU 2.0 */ 1142 UBLOCK_LATIN_1_SUPPLEMENT=2, /*[0080]*/ 1143 1144 /** @stable ICU 2.0 */ 1145 UBLOCK_LATIN_EXTENDED_A =3, /*[0100]*/ 1146 1147 /** @stable ICU 2.0 */ 1148 UBLOCK_LATIN_EXTENDED_B =4, /*[0180]*/ 1149 1150 /** @stable ICU 2.0 */ 1151 UBLOCK_IPA_EXTENSIONS =5, /*[0250]*/ 1152 1153 /** @stable ICU 2.0 */ 1154 UBLOCK_SPACING_MODIFIER_LETTERS =6, /*[02B0]*/ 1155 1156 /** @stable ICU 2.0 */ 1157 UBLOCK_COMBINING_DIACRITICAL_MARKS =7, /*[0300]*/ 1158 1159 /** 1160 * Unicode 3.2 renames this block to "Greek and Coptic". 1161 * @stable ICU 2.0 1162 */ 1163 UBLOCK_GREEK =8, /*[0370]*/ 1164 1165 /** @stable ICU 2.0 */ 1166 UBLOCK_CYRILLIC =9, /*[0400]*/ 1167 1168 /** @stable ICU 2.0 */ 1169 UBLOCK_ARMENIAN =10, /*[0530]*/ 1170 1171 /** @stable ICU 2.0 */ 1172 UBLOCK_HEBREW =11, /*[0590]*/ 1173 1174 /** @stable ICU 2.0 */ 1175 UBLOCK_ARABIC =12, /*[0600]*/ 1176 1177 /** @stable ICU 2.0 */ 1178 UBLOCK_SYRIAC =13, /*[0700]*/ 1179 1180 /** @stable ICU 2.0 */ 1181 UBLOCK_THAANA =14, /*[0780]*/ 1182 1183 /** @stable ICU 2.0 */ 1184 UBLOCK_DEVANAGARI =15, /*[0900]*/ 1185 1186 /** @stable ICU 2.0 */ 1187 UBLOCK_BENGALI =16, /*[0980]*/ 1188 1189 /** @stable ICU 2.0 */ 1190 UBLOCK_GURMUKHI =17, /*[0A00]*/ 1191 1192 /** @stable ICU 2.0 */ 1193 UBLOCK_GUJARATI =18, /*[0A80]*/ 1194 1195 /** @stable ICU 2.0 */ 1196 UBLOCK_ORIYA =19, /*[0B00]*/ 1197 1198 /** @stable ICU 2.0 */ 1199 UBLOCK_TAMIL =20, /*[0B80]*/ 1200 1201 /** @stable ICU 2.0 */ 1202 UBLOCK_TELUGU =21, /*[0C00]*/ 1203 1204 /** @stable ICU 2.0 */ 1205 UBLOCK_KANNADA =22, /*[0C80]*/ 1206 1207 /** @stable ICU 2.0 */ 1208 UBLOCK_MALAYALAM =23, /*[0D00]*/ 1209 1210 /** @stable ICU 2.0 */ 1211 UBLOCK_SINHALA =24, /*[0D80]*/ 1212 1213 /** @stable ICU 2.0 */ 1214 UBLOCK_THAI =25, /*[0E00]*/ 1215 1216 /** @stable ICU 2.0 */ 1217 UBLOCK_LAO =26, /*[0E80]*/ 1218 1219 /** @stable ICU 2.0 */ 1220 UBLOCK_TIBETAN =27, /*[0F00]*/ 1221 1222 /** @stable ICU 2.0 */ 1223 UBLOCK_MYANMAR =28, /*[1000]*/ 1224 1225 /** @stable ICU 2.0 */ 1226 UBLOCK_GEORGIAN =29, /*[10A0]*/ 1227 1228 /** @stable ICU 2.0 */ 1229 UBLOCK_HANGUL_JAMO =30, /*[1100]*/ 1230 1231 /** @stable ICU 2.0 */ 1232 UBLOCK_ETHIOPIC =31, /*[1200]*/ 1233 1234 /** @stable ICU 2.0 */ 1235 UBLOCK_CHEROKEE =32, /*[13A0]*/ 1236 1237 /** @stable ICU 2.0 */ 1238 UBLOCK_UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS =33, /*[1400]*/ 1239 1240 /** @stable ICU 2.0 */ 1241 UBLOCK_OGHAM =34, /*[1680]*/ 1242 1243 /** @stable ICU 2.0 */ 1244 UBLOCK_RUNIC =35, /*[16A0]*/ 1245 1246 /** @stable ICU 2.0 */ 1247 UBLOCK_KHMER =36, /*[1780]*/ 1248 1249 /** @stable ICU 2.0 */ 1250 UBLOCK_MONGOLIAN =37, /*[1800]*/ 1251 1252 /** @stable ICU 2.0 */ 1253 UBLOCK_LATIN_EXTENDED_ADDITIONAL =38, /*[1E00]*/ 1254 1255 /** @stable ICU 2.0 */ 1256 UBLOCK_GREEK_EXTENDED =39, /*[1F00]*/ 1257 1258 /** @stable ICU 2.0 */ 1259 UBLOCK_GENERAL_PUNCTUATION =40, /*[2000]*/ 1260 1261 /** @stable ICU 2.0 */ 1262 UBLOCK_SUPERSCRIPTS_AND_SUBSCRIPTS =41, /*[2070]*/ 1263 1264 /** @stable ICU 2.0 */ 1265 UBLOCK_CURRENCY_SYMBOLS =42, /*[20A0]*/ 1266 1267 /** 1268 * Unicode 3.2 renames this block to "Combining Diacritical Marks for Symbols". 1269 * @stable ICU 2.0 1270 */ 1271 UBLOCK_COMBINING_MARKS_FOR_SYMBOLS =43, /*[20D0]*/ 1272 1273 /** @stable ICU 2.0 */ 1274 UBLOCK_LETTERLIKE_SYMBOLS =44, /*[2100]*/ 1275 1276 /** @stable ICU 2.0 */ 1277 UBLOCK_NUMBER_FORMS =45, /*[2150]*/ 1278 1279 /** @stable ICU 2.0 */ 1280 UBLOCK_ARROWS =46, /*[2190]*/ 1281 1282 /** @stable ICU 2.0 */ 1283 UBLOCK_MATHEMATICAL_OPERATORS =47, /*[2200]*/ 1284 1285 /** @stable ICU 2.0 */ 1286 UBLOCK_MISCELLANEOUS_TECHNICAL =48, /*[2300]*/ 1287 1288 /** @stable ICU 2.0 */ 1289 UBLOCK_CONTROL_PICTURES =49, /*[2400]*/ 1290 1291 /** @stable ICU 2.0 */ 1292 UBLOCK_OPTICAL_CHARACTER_RECOGNITION =50, /*[2440]*/ 1293 1294 /** @stable ICU 2.0 */ 1295 UBLOCK_ENCLOSED_ALPHANUMERICS =51, /*[2460]*/ 1296 1297 /** @stable ICU 2.0 */ 1298 UBLOCK_BOX_DRAWING =52, /*[2500]*/ 1299 1300 /** @stable ICU 2.0 */ 1301 UBLOCK_BLOCK_ELEMENTS =53, /*[2580]*/ 1302 1303 /** @stable ICU 2.0 */ 1304 UBLOCK_GEOMETRIC_SHAPES =54, /*[25A0]*/ 1305 1306 /** @stable ICU 2.0 */ 1307 UBLOCK_MISCELLANEOUS_SYMBOLS =55, /*[2600]*/ 1308 1309 /** @stable ICU 2.0 */ 1310 UBLOCK_DINGBATS =56, /*[2700]*/ 1311 1312 /** @stable ICU 2.0 */ 1313 UBLOCK_BRAILLE_PATTERNS =57, /*[2800]*/ 1314 1315 /** @stable ICU 2.0 */ 1316 UBLOCK_CJK_RADICALS_SUPPLEMENT =58, /*[2E80]*/ 1317 1318 /** @stable ICU 2.0 */ 1319 UBLOCK_KANGXI_RADICALS =59, /*[2F00]*/ 1320 1321 /** @stable ICU 2.0 */ 1322 UBLOCK_IDEOGRAPHIC_DESCRIPTION_CHARACTERS =60, /*[2FF0]*/ 1323 1324 /** @stable ICU 2.0 */ 1325 UBLOCK_CJK_SYMBOLS_AND_PUNCTUATION =61, /*[3000]*/ 1326 1327 /** @stable ICU 2.0 */ 1328 UBLOCK_HIRAGANA =62, /*[3040]*/ 1329 1330 /** @stable ICU 2.0 */ 1331 UBLOCK_KATAKANA =63, /*[30A0]*/ 1332 1333 /** @stable ICU 2.0 */ 1334 UBLOCK_BOPOMOFO =64, /*[3100]*/ 1335 1336 /** @stable ICU 2.0 */ 1337 UBLOCK_HANGUL_COMPATIBILITY_JAMO =65, /*[3130]*/ 1338 1339 /** @stable ICU 2.0 */ 1340 UBLOCK_KANBUN =66, /*[3190]*/ 1341 1342 /** @stable ICU 2.0 */ 1343 UBLOCK_BOPOMOFO_EXTENDED =67, /*[31A0]*/ 1344 1345 /** @stable ICU 2.0 */ 1346 UBLOCK_ENCLOSED_CJK_LETTERS_AND_MONTHS =68, /*[3200]*/ 1347 1348 /** @stable ICU 2.0 */ 1349 UBLOCK_CJK_COMPATIBILITY =69, /*[3300]*/ 1350 1351 /** @stable ICU 2.0 */ 1352 UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_A =70, /*[3400]*/ 1353 1354 /** @stable ICU 2.0 */ 1355 UBLOCK_CJK_UNIFIED_IDEOGRAPHS =71, /*[4E00]*/ 1356 1357 /** @stable ICU 2.0 */ 1358 UBLOCK_YI_SYLLABLES =72, /*[A000]*/ 1359 1360 /** @stable ICU 2.0 */ 1361 UBLOCK_YI_RADICALS =73, /*[A490]*/ 1362 1363 /** @stable ICU 2.0 */ 1364 UBLOCK_HANGUL_SYLLABLES =74, /*[AC00]*/ 1365 1366 /** @stable ICU 2.0 */ 1367 UBLOCK_HIGH_SURROGATES =75, /*[D800]*/ 1368 1369 /** @stable ICU 2.0 */ 1370 UBLOCK_HIGH_PRIVATE_USE_SURROGATES =76, /*[DB80]*/ 1371 1372 /** @stable ICU 2.0 */ 1373 UBLOCK_LOW_SURROGATES =77, /*[DC00]*/ 1374 1375 /** 1376 * Same as UBLOCK_PRIVATE_USE. 1377 * Until Unicode 3.1.1, the corresponding block name was "Private Use", 1378 * and multiple code point ranges had this block. 1379 * Unicode 3.2 renames the block for the BMP PUA to "Private Use Area" and 1380 * adds separate blocks for the supplementary PUAs. 1381 * 1382 * @stable ICU 2.0 1383 */ 1384 UBLOCK_PRIVATE_USE_AREA =78, /*[E000]*/ 1385 /** 1386 * Same as UBLOCK_PRIVATE_USE_AREA. 1387 * Until Unicode 3.1.1, the corresponding block name was "Private Use", 1388 * and multiple code point ranges had this block. 1389 * Unicode 3.2 renames the block for the BMP PUA to "Private Use Area" and 1390 * adds separate blocks for the supplementary PUAs. 1391 * 1392 * @stable ICU 2.0 1393 */ 1394 UBLOCK_PRIVATE_USE = UBLOCK_PRIVATE_USE_AREA, 1395 1396 /** @stable ICU 2.0 */ 1397 UBLOCK_CJK_COMPATIBILITY_IDEOGRAPHS =79, /*[F900]*/ 1398 1399 /** @stable ICU 2.0 */ 1400 UBLOCK_ALPHABETIC_PRESENTATION_FORMS =80, /*[FB00]*/ 1401 1402 /** @stable ICU 2.0 */ 1403 UBLOCK_ARABIC_PRESENTATION_FORMS_A =81, /*[FB50]*/ 1404 1405 /** @stable ICU 2.0 */ 1406 UBLOCK_COMBINING_HALF_MARKS =82, /*[FE20]*/ 1407 1408 /** @stable ICU 2.0 */ 1409 UBLOCK_CJK_COMPATIBILITY_FORMS =83, /*[FE30]*/ 1410 1411 /** @stable ICU 2.0 */ 1412 UBLOCK_SMALL_FORM_VARIANTS =84, /*[FE50]*/ 1413 1414 /** @stable ICU 2.0 */ 1415 UBLOCK_ARABIC_PRESENTATION_FORMS_B =85, /*[FE70]*/ 1416 1417 /** @stable ICU 2.0 */ 1418 UBLOCK_SPECIALS =86, /*[FFF0]*/ 1419 1420 /** @stable ICU 2.0 */ 1421 UBLOCK_HALFWIDTH_AND_FULLWIDTH_FORMS =87, /*[FF00]*/ 1422 1423 /* New blocks in Unicode 3.1 */ 1424 1425 /** @stable ICU 2.0 */ 1426 UBLOCK_OLD_ITALIC = 88, /*[10300]*/ 1427 /** @stable ICU 2.0 */ 1428 UBLOCK_GOTHIC = 89, /*[10330]*/ 1429 /** @stable ICU 2.0 */ 1430 UBLOCK_DESERET = 90, /*[10400]*/ 1431 /** @stable ICU 2.0 */ 1432 UBLOCK_BYZANTINE_MUSICAL_SYMBOLS = 91, /*[1D000]*/ 1433 /** @stable ICU 2.0 */ 1434 UBLOCK_MUSICAL_SYMBOLS = 92, /*[1D100]*/ 1435 /** @stable ICU 2.0 */ 1436 UBLOCK_MATHEMATICAL_ALPHANUMERIC_SYMBOLS = 93, /*[1D400]*/ 1437 /** @stable ICU 2.0 */ 1438 UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_B = 94, /*[20000]*/ 1439 /** @stable ICU 2.0 */ 1440 UBLOCK_CJK_COMPATIBILITY_IDEOGRAPHS_SUPPLEMENT = 95, /*[2F800]*/ 1441 /** @stable ICU 2.0 */ 1442 UBLOCK_TAGS = 96, /*[E0000]*/ 1443 1444 /* New blocks in Unicode 3.2 */ 1445 1446 /** @stable ICU 3.0 */ 1447 UBLOCK_CYRILLIC_SUPPLEMENT = 97, /*[0500]*/ 1448 /** 1449 * Unicode 4.0.1 renames the "Cyrillic Supplementary" block to "Cyrillic Supplement". 1450 * @stable ICU 2.2 1451 */ 1452 UBLOCK_CYRILLIC_SUPPLEMENTARY = UBLOCK_CYRILLIC_SUPPLEMENT, 1453 /** @stable ICU 2.2 */ 1454 UBLOCK_TAGALOG = 98, /*[1700]*/ 1455 /** @stable ICU 2.2 */ 1456 UBLOCK_HANUNOO = 99, /*[1720]*/ 1457 /** @stable ICU 2.2 */ 1458 UBLOCK_BUHID = 100, /*[1740]*/ 1459 /** @stable ICU 2.2 */ 1460 UBLOCK_TAGBANWA = 101, /*[1760]*/ 1461 /** @stable ICU 2.2 */ 1462 UBLOCK_MISCELLANEOUS_MATHEMATICAL_SYMBOLS_A = 102, /*[27C0]*/ 1463 /** @stable ICU 2.2 */ 1464 UBLOCK_SUPPLEMENTAL_ARROWS_A = 103, /*[27F0]*/ 1465 /** @stable ICU 2.2 */ 1466 UBLOCK_SUPPLEMENTAL_ARROWS_B = 104, /*[2900]*/ 1467 /** @stable ICU 2.2 */ 1468 UBLOCK_MISCELLANEOUS_MATHEMATICAL_SYMBOLS_B = 105, /*[2980]*/ 1469 /** @stable ICU 2.2 */ 1470 UBLOCK_SUPPLEMENTAL_MATHEMATICAL_OPERATORS = 106, /*[2A00]*/ 1471 /** @stable ICU 2.2 */ 1472 UBLOCK_KATAKANA_PHONETIC_EXTENSIONS = 107, /*[31F0]*/ 1473 /** @stable ICU 2.2 */ 1474 UBLOCK_VARIATION_SELECTORS = 108, /*[FE00]*/ 1475 /** @stable ICU 2.2 */ 1476 UBLOCK_SUPPLEMENTARY_PRIVATE_USE_AREA_A = 109, /*[F0000]*/ 1477 /** @stable ICU 2.2 */ 1478 UBLOCK_SUPPLEMENTARY_PRIVATE_USE_AREA_B = 110, /*[100000]*/ 1479 1480 /* New blocks in Unicode 4 */ 1481 1482 /** @stable ICU 2.6 */ 1483 UBLOCK_LIMBU = 111, /*[1900]*/ 1484 /** @stable ICU 2.6 */ 1485 UBLOCK_TAI_LE = 112, /*[1950]*/ 1486 /** @stable ICU 2.6 */ 1487 UBLOCK_KHMER_SYMBOLS = 113, /*[19E0]*/ 1488 /** @stable ICU 2.6 */ 1489 UBLOCK_PHONETIC_EXTENSIONS = 114, /*[1D00]*/ 1490 /** @stable ICU 2.6 */ 1491 UBLOCK_MISCELLANEOUS_SYMBOLS_AND_ARROWS = 115, /*[2B00]*/ 1492 /** @stable ICU 2.6 */ 1493 UBLOCK_YIJING_HEXAGRAM_SYMBOLS = 116, /*[4DC0]*/ 1494 /** @stable ICU 2.6 */ 1495 UBLOCK_LINEAR_B_SYLLABARY = 117, /*[10000]*/ 1496 /** @stable ICU 2.6 */ 1497 UBLOCK_LINEAR_B_IDEOGRAMS = 118, /*[10080]*/ 1498 /** @stable ICU 2.6 */ 1499 UBLOCK_AEGEAN_NUMBERS = 119, /*[10100]*/ 1500 /** @stable ICU 2.6 */ 1501 UBLOCK_UGARITIC = 120, /*[10380]*/ 1502 /** @stable ICU 2.6 */ 1503 UBLOCK_SHAVIAN = 121, /*[10450]*/ 1504 /** @stable ICU 2.6 */ 1505 UBLOCK_OSMANYA = 122, /*[10480]*/ 1506 /** @stable ICU 2.6 */ 1507 UBLOCK_CYPRIOT_SYLLABARY = 123, /*[10800]*/ 1508 /** @stable ICU 2.6 */ 1509 UBLOCK_TAI_XUAN_JING_SYMBOLS = 124, /*[1D300]*/ 1510 /** @stable ICU 2.6 */ 1511 UBLOCK_VARIATION_SELECTORS_SUPPLEMENT = 125, /*[E0100]*/ 1512 1513 /* New blocks in Unicode 4.1 */ 1514 1515 /** @stable ICU 3.4 */ 1516 UBLOCK_ANCIENT_GREEK_MUSICAL_NOTATION = 126, /*[1D200]*/ 1517 /** @stable ICU 3.4 */ 1518 UBLOCK_ANCIENT_GREEK_NUMBERS = 127, /*[10140]*/ 1519 /** @stable ICU 3.4 */ 1520 UBLOCK_ARABIC_SUPPLEMENT = 128, /*[0750]*/ 1521 /** @stable ICU 3.4 */ 1522 UBLOCK_BUGINESE = 129, /*[1A00]*/ 1523 /** @stable ICU 3.4 */ 1524 UBLOCK_CJK_STROKES = 130, /*[31C0]*/ 1525 /** @stable ICU 3.4 */ 1526 UBLOCK_COMBINING_DIACRITICAL_MARKS_SUPPLEMENT = 131, /*[1DC0]*/ 1527 /** @stable ICU 3.4 */ 1528 UBLOCK_COPTIC = 132, /*[2C80]*/ 1529 /** @stable ICU 3.4 */ 1530 UBLOCK_ETHIOPIC_EXTENDED = 133, /*[2D80]*/ 1531 /** @stable ICU 3.4 */ 1532 UBLOCK_ETHIOPIC_SUPPLEMENT = 134, /*[1380]*/ 1533 /** @stable ICU 3.4 */ 1534 UBLOCK_GEORGIAN_SUPPLEMENT = 135, /*[2D00]*/ 1535 /** @stable ICU 3.4 */ 1536 UBLOCK_GLAGOLITIC = 136, /*[2C00]*/ 1537 /** @stable ICU 3.4 */ 1538 UBLOCK_KHAROSHTHI = 137, /*[10A00]*/ 1539 /** @stable ICU 3.4 */ 1540 UBLOCK_MODIFIER_TONE_LETTERS = 138, /*[A700]*/ 1541 /** @stable ICU 3.4 */ 1542 UBLOCK_NEW_TAI_LUE = 139, /*[1980]*/ 1543 /** @stable ICU 3.4 */ 1544 UBLOCK_OLD_PERSIAN = 140, /*[103A0]*/ 1545 /** @stable ICU 3.4 */ 1546 UBLOCK_PHONETIC_EXTENSIONS_SUPPLEMENT = 141, /*[1D80]*/ 1547 /** @stable ICU 3.4 */ 1548 UBLOCK_SUPPLEMENTAL_PUNCTUATION = 142, /*[2E00]*/ 1549 /** @stable ICU 3.4 */ 1550 UBLOCK_SYLOTI_NAGRI = 143, /*[A800]*/ 1551 /** @stable ICU 3.4 */ 1552 UBLOCK_TIFINAGH = 144, /*[2D30]*/ 1553 /** @stable ICU 3.4 */ 1554 UBLOCK_VERTICAL_FORMS = 145, /*[FE10]*/ 1555 1556 /* New blocks in Unicode 5.0 */ 1557 1558 /** @stable ICU 3.6 */ 1559 UBLOCK_NKO = 146, /*[07C0]*/ 1560 /** @stable ICU 3.6 */ 1561 UBLOCK_BALINESE = 147, /*[1B00]*/ 1562 /** @stable ICU 3.6 */ 1563 UBLOCK_LATIN_EXTENDED_C = 148, /*[2C60]*/ 1564 /** @stable ICU 3.6 */ 1565 UBLOCK_LATIN_EXTENDED_D = 149, /*[A720]*/ 1566 /** @stable ICU 3.6 */ 1567 UBLOCK_PHAGS_PA = 150, /*[A840]*/ 1568 /** @stable ICU 3.6 */ 1569 UBLOCK_PHOENICIAN = 151, /*[10900]*/ 1570 /** @stable ICU 3.6 */ 1571 UBLOCK_CUNEIFORM = 152, /*[12000]*/ 1572 /** @stable ICU 3.6 */ 1573 UBLOCK_CUNEIFORM_NUMBERS_AND_PUNCTUATION = 153, /*[12400]*/ 1574 /** @stable ICU 3.6 */ 1575 UBLOCK_COUNTING_ROD_NUMERALS = 154, /*[1D360]*/ 1576 1577 /* New blocks in Unicode 5.1 */ 1578 1579 /** @stable ICU 4.0 */ 1580 UBLOCK_SUNDANESE = 155, /*[1B80]*/ 1581 /** @stable ICU 4.0 */ 1582 UBLOCK_LEPCHA = 156, /*[1C00]*/ 1583 /** @stable ICU 4.0 */ 1584 UBLOCK_OL_CHIKI = 157, /*[1C50]*/ 1585 /** @stable ICU 4.0 */ 1586 UBLOCK_CYRILLIC_EXTENDED_A = 158, /*[2DE0]*/ 1587 /** @stable ICU 4.0 */ 1588 UBLOCK_VAI = 159, /*[A500]*/ 1589 /** @stable ICU 4.0 */ 1590 UBLOCK_CYRILLIC_EXTENDED_B = 160, /*[A640]*/ 1591 /** @stable ICU 4.0 */ 1592 UBLOCK_SAURASHTRA = 161, /*[A880]*/ 1593 /** @stable ICU 4.0 */ 1594 UBLOCK_KAYAH_LI = 162, /*[A900]*/ 1595 /** @stable ICU 4.0 */ 1596 UBLOCK_REJANG = 163, /*[A930]*/ 1597 /** @stable ICU 4.0 */ 1598 UBLOCK_CHAM = 164, /*[AA00]*/ 1599 /** @stable ICU 4.0 */ 1600 UBLOCK_ANCIENT_SYMBOLS = 165, /*[10190]*/ 1601 /** @stable ICU 4.0 */ 1602 UBLOCK_PHAISTOS_DISC = 166, /*[101D0]*/ 1603 /** @stable ICU 4.0 */ 1604 UBLOCK_LYCIAN = 167, /*[10280]*/ 1605 /** @stable ICU 4.0 */ 1606 UBLOCK_CARIAN = 168, /*[102A0]*/ 1607 /** @stable ICU 4.0 */ 1608 UBLOCK_LYDIAN = 169, /*[10920]*/ 1609 /** @stable ICU 4.0 */ 1610 UBLOCK_MAHJONG_TILES = 170, /*[1F000]*/ 1611 /** @stable ICU 4.0 */ 1612 UBLOCK_DOMINO_TILES = 171, /*[1F030]*/ 1613 1614 /* New blocks in Unicode 5.2 */ 1615 1616 /** @stable ICU 4.4 */ 1617 UBLOCK_SAMARITAN = 172, /*[0800]*/ 1618 /** @stable ICU 4.4 */ 1619 UBLOCK_UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS_EXTENDED = 173, /*[18B0]*/ 1620 /** @stable ICU 4.4 */ 1621 UBLOCK_TAI_THAM = 174, /*[1A20]*/ 1622 /** @stable ICU 4.4 */ 1623 UBLOCK_VEDIC_EXTENSIONS = 175, /*[1CD0]*/ 1624 /** @stable ICU 4.4 */ 1625 UBLOCK_LISU = 176, /*[A4D0]*/ 1626 /** @stable ICU 4.4 */ 1627 UBLOCK_BAMUM = 177, /*[A6A0]*/ 1628 /** @stable ICU 4.4 */ 1629 UBLOCK_COMMON_INDIC_NUMBER_FORMS = 178, /*[A830]*/ 1630 /** @stable ICU 4.4 */ 1631 UBLOCK_DEVANAGARI_EXTENDED = 179, /*[A8E0]*/ 1632 /** @stable ICU 4.4 */ 1633 UBLOCK_HANGUL_JAMO_EXTENDED_A = 180, /*[A960]*/ 1634 /** @stable ICU 4.4 */ 1635 UBLOCK_JAVANESE = 181, /*[A980]*/ 1636 /** @stable ICU 4.4 */ 1637 UBLOCK_MYANMAR_EXTENDED_A = 182, /*[AA60]*/ 1638 /** @stable ICU 4.4 */ 1639 UBLOCK_TAI_VIET = 183, /*[AA80]*/ 1640 /** @stable ICU 4.4 */ 1641 UBLOCK_MEETEI_MAYEK = 184, /*[ABC0]*/ 1642 /** @stable ICU 4.4 */ 1643 UBLOCK_HANGUL_JAMO_EXTENDED_B = 185, /*[D7B0]*/ 1644 /** @stable ICU 4.4 */ 1645 UBLOCK_IMPERIAL_ARAMAIC = 186, /*[10840]*/ 1646 /** @stable ICU 4.4 */ 1647 UBLOCK_OLD_SOUTH_ARABIAN = 187, /*[10A60]*/ 1648 /** @stable ICU 4.4 */ 1649 UBLOCK_AVESTAN = 188, /*[10B00]*/ 1650 /** @stable ICU 4.4 */ 1651 UBLOCK_INSCRIPTIONAL_PARTHIAN = 189, /*[10B40]*/ 1652 /** @stable ICU 4.4 */ 1653 UBLOCK_INSCRIPTIONAL_PAHLAVI = 190, /*[10B60]*/ 1654 /** @stable ICU 4.4 */ 1655 UBLOCK_OLD_TURKIC = 191, /*[10C00]*/ 1656 /** @stable ICU 4.4 */ 1657 UBLOCK_RUMI_NUMERAL_SYMBOLS = 192, /*[10E60]*/ 1658 /** @stable ICU 4.4 */ 1659 UBLOCK_KAITHI = 193, /*[11080]*/ 1660 /** @stable ICU 4.4 */ 1661 UBLOCK_EGYPTIAN_HIEROGLYPHS = 194, /*[13000]*/ 1662 /** @stable ICU 4.4 */ 1663 UBLOCK_ENCLOSED_ALPHANUMERIC_SUPPLEMENT = 195, /*[1F100]*/ 1664 /** @stable ICU 4.4 */ 1665 UBLOCK_ENCLOSED_IDEOGRAPHIC_SUPPLEMENT = 196, /*[1F200]*/ 1666 /** @stable ICU 4.4 */ 1667 UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_C = 197, /*[2A700]*/ 1668 1669 /* New blocks in Unicode 6.0 */ 1670 1671 /** @stable ICU 4.6 */ 1672 UBLOCK_MANDAIC = 198, /*[0840]*/ 1673 /** @stable ICU 4.6 */ 1674 UBLOCK_BATAK = 199, /*[1BC0]*/ 1675 /** @stable ICU 4.6 */ 1676 UBLOCK_ETHIOPIC_EXTENDED_A = 200, /*[AB00]*/ 1677 /** @stable ICU 4.6 */ 1678 UBLOCK_BRAHMI = 201, /*[11000]*/ 1679 /** @stable ICU 4.6 */ 1680 UBLOCK_BAMUM_SUPPLEMENT = 202, /*[16800]*/ 1681 /** @stable ICU 4.6 */ 1682 UBLOCK_KANA_SUPPLEMENT = 203, /*[1B000]*/ 1683 /** @stable ICU 4.6 */ 1684 UBLOCK_PLAYING_CARDS = 204, /*[1F0A0]*/ 1685 /** @stable ICU 4.6 */ 1686 UBLOCK_MISCELLANEOUS_SYMBOLS_AND_PICTOGRAPHS = 205, /*[1F300]*/ 1687 /** @stable ICU 4.6 */ 1688 UBLOCK_EMOTICONS = 206, /*[1F600]*/ 1689 /** @stable ICU 4.6 */ 1690 UBLOCK_TRANSPORT_AND_MAP_SYMBOLS = 207, /*[1F680]*/ 1691 /** @stable ICU 4.6 */ 1692 UBLOCK_ALCHEMICAL_SYMBOLS = 208, /*[1F700]*/ 1693 /** @stable ICU 4.6 */ 1694 UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_D = 209, /*[2B740]*/ 1695 1696 /* New blocks in Unicode 6.1 */ 1697 1698 /** @stable ICU 49 */ 1699 UBLOCK_ARABIC_EXTENDED_A = 210, /*[08A0]*/ 1700 /** @stable ICU 49 */ 1701 UBLOCK_ARABIC_MATHEMATICAL_ALPHABETIC_SYMBOLS = 211, /*[1EE00]*/ 1702 /** @stable ICU 49 */ 1703 UBLOCK_CHAKMA = 212, /*[11100]*/ 1704 /** @stable ICU 49 */ 1705 UBLOCK_MEETEI_MAYEK_EXTENSIONS = 213, /*[AAE0]*/ 1706 /** @stable ICU 49 */ 1707 UBLOCK_MEROITIC_CURSIVE = 214, /*[109A0]*/ 1708 /** @stable ICU 49 */ 1709 UBLOCK_MEROITIC_HIEROGLYPHS = 215, /*[10980]*/ 1710 /** @stable ICU 49 */ 1711 UBLOCK_MIAO = 216, /*[16F00]*/ 1712 /** @stable ICU 49 */ 1713 UBLOCK_SHARADA = 217, /*[11180]*/ 1714 /** @stable ICU 49 */ 1715 UBLOCK_SORA_SOMPENG = 218, /*[110D0]*/ 1716 /** @stable ICU 49 */ 1717 UBLOCK_SUNDANESE_SUPPLEMENT = 219, /*[1CC0]*/ 1718 /** @stable ICU 49 */ 1719 UBLOCK_TAKRI = 220, /*[11680]*/ 1720 1721 /* New blocks in Unicode 7.0 */ 1722 1723 /** @stable ICU 54 */ 1724 UBLOCK_BASSA_VAH = 221, /*[16AD0]*/ 1725 /** @stable ICU 54 */ 1726 UBLOCK_CAUCASIAN_ALBANIAN = 222, /*[10530]*/ 1727 /** @stable ICU 54 */ 1728 UBLOCK_COPTIC_EPACT_NUMBERS = 223, /*[102E0]*/ 1729 /** @stable ICU 54 */ 1730 UBLOCK_COMBINING_DIACRITICAL_MARKS_EXTENDED = 224, /*[1AB0]*/ 1731 /** @stable ICU 54 */ 1732 UBLOCK_DUPLOYAN = 225, /*[1BC00]*/ 1733 /** @stable ICU 54 */ 1734 UBLOCK_ELBASAN = 226, /*[10500]*/ 1735 /** @stable ICU 54 */ 1736 UBLOCK_GEOMETRIC_SHAPES_EXTENDED = 227, /*[1F780]*/ 1737 /** @stable ICU 54 */ 1738 UBLOCK_GRANTHA = 228, /*[11300]*/ 1739 /** @stable ICU 54 */ 1740 UBLOCK_KHOJKI = 229, /*[11200]*/ 1741 /** @stable ICU 54 */ 1742 UBLOCK_KHUDAWADI = 230, /*[112B0]*/ 1743 /** @stable ICU 54 */ 1744 UBLOCK_LATIN_EXTENDED_E = 231, /*[AB30]*/ 1745 /** @stable ICU 54 */ 1746 UBLOCK_LINEAR_A = 232, /*[10600]*/ 1747 /** @stable ICU 54 */ 1748 UBLOCK_MAHAJANI = 233, /*[11150]*/ 1749 /** @stable ICU 54 */ 1750 UBLOCK_MANICHAEAN = 234, /*[10AC0]*/ 1751 /** @stable ICU 54 */ 1752 UBLOCK_MENDE_KIKAKUI = 235, /*[1E800]*/ 1753 /** @stable ICU 54 */ 1754 UBLOCK_MODI = 236, /*[11600]*/ 1755 /** @stable ICU 54 */ 1756 UBLOCK_MRO = 237, /*[16A40]*/ 1757 /** @stable ICU 54 */ 1758 UBLOCK_MYANMAR_EXTENDED_B = 238, /*[A9E0]*/ 1759 /** @stable ICU 54 */ 1760 UBLOCK_NABATAEAN = 239, /*[10880]*/ 1761 /** @stable ICU 54 */ 1762 UBLOCK_OLD_NORTH_ARABIAN = 240, /*[10A80]*/ 1763 /** @stable ICU 54 */ 1764 UBLOCK_OLD_PERMIC = 241, /*[10350]*/ 1765 /** @stable ICU 54 */ 1766 UBLOCK_ORNAMENTAL_DINGBATS = 242, /*[1F650]*/ 1767 /** @stable ICU 54 */ 1768 UBLOCK_PAHAWH_HMONG = 243, /*[16B00]*/ 1769 /** @stable ICU 54 */ 1770 UBLOCK_PALMYRENE = 244, /*[10860]*/ 1771 /** @stable ICU 54 */ 1772 UBLOCK_PAU_CIN_HAU = 245, /*[11AC0]*/ 1773 /** @stable ICU 54 */ 1774 UBLOCK_PSALTER_PAHLAVI = 246, /*[10B80]*/ 1775 /** @stable ICU 54 */ 1776 UBLOCK_SHORTHAND_FORMAT_CONTROLS = 247, /*[1BCA0]*/ 1777 /** @stable ICU 54 */ 1778 UBLOCK_SIDDHAM = 248, /*[11580]*/ 1779 /** @stable ICU 54 */ 1780 UBLOCK_SINHALA_ARCHAIC_NUMBERS = 249, /*[111E0]*/ 1781 /** @stable ICU 54 */ 1782 UBLOCK_SUPPLEMENTAL_ARROWS_C = 250, /*[1F800]*/ 1783 /** @stable ICU 54 */ 1784 UBLOCK_TIRHUTA = 251, /*[11480]*/ 1785 /** @stable ICU 54 */ 1786 UBLOCK_WARANG_CITI = 252, /*[118A0]*/ 1787 1788 /* New blocks in Unicode 8.0 */ 1789 1790 /** @stable ICU 56 */ 1791 UBLOCK_AHOM = 253, /*[11700]*/ 1792 /** @stable ICU 56 */ 1793 UBLOCK_ANATOLIAN_HIEROGLYPHS = 254, /*[14400]*/ 1794 /** @stable ICU 56 */ 1795 UBLOCK_CHEROKEE_SUPPLEMENT = 255, /*[AB70]*/ 1796 /** @stable ICU 56 */ 1797 UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_E = 256, /*[2B820]*/ 1798 /** @stable ICU 56 */ 1799 UBLOCK_EARLY_DYNASTIC_CUNEIFORM = 257, /*[12480]*/ 1800 /** @stable ICU 56 */ 1801 UBLOCK_HATRAN = 258, /*[108E0]*/ 1802 /** @stable ICU 56 */ 1803 UBLOCK_MULTANI = 259, /*[11280]*/ 1804 /** @stable ICU 56 */ 1805 UBLOCK_OLD_HUNGARIAN = 260, /*[10C80]*/ 1806 /** @stable ICU 56 */ 1807 UBLOCK_SUPPLEMENTAL_SYMBOLS_AND_PICTOGRAPHS = 261, /*[1F900]*/ 1808 /** @stable ICU 56 */ 1809 UBLOCK_SUTTON_SIGNWRITING = 262, /*[1D800]*/ 1810 1811 /* New blocks in Unicode 9.0 */ 1812 1813 /** @stable ICU 58 */ 1814 UBLOCK_ADLAM = 263, /*[1E900]*/ 1815 /** @stable ICU 58 */ 1816 UBLOCK_BHAIKSUKI = 264, /*[11C00]*/ 1817 /** @stable ICU 58 */ 1818 UBLOCK_CYRILLIC_EXTENDED_C = 265, /*[1C80]*/ 1819 /** @stable ICU 58 */ 1820 UBLOCK_GLAGOLITIC_SUPPLEMENT = 266, /*[1E000]*/ 1821 /** @stable ICU 58 */ 1822 UBLOCK_IDEOGRAPHIC_SYMBOLS_AND_PUNCTUATION = 267, /*[16FE0]*/ 1823 /** @stable ICU 58 */ 1824 UBLOCK_MARCHEN = 268, /*[11C70]*/ 1825 /** @stable ICU 58 */ 1826 UBLOCK_MONGOLIAN_SUPPLEMENT = 269, /*[11660]*/ 1827 /** @stable ICU 58 */ 1828 UBLOCK_NEWA = 270, /*[11400]*/ 1829 /** @stable ICU 58 */ 1830 UBLOCK_OSAGE = 271, /*[104B0]*/ 1831 /** @stable ICU 58 */ 1832 UBLOCK_TANGUT = 272, /*[17000]*/ 1833 /** @stable ICU 58 */ 1834 UBLOCK_TANGUT_COMPONENTS = 273, /*[18800]*/ 1835 1836 // New blocks in Unicode 10.0 1837 1838 /** @stable ICU 60 */ 1839 UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_F = 274, /*[2CEB0]*/ 1840 /** @stable ICU 60 */ 1841 UBLOCK_KANA_EXTENDED_A = 275, /*[1B100]*/ 1842 /** @stable ICU 60 */ 1843 UBLOCK_MASARAM_GONDI = 276, /*[11D00]*/ 1844 /** @stable ICU 60 */ 1845 UBLOCK_NUSHU = 277, /*[1B170]*/ 1846 /** @stable ICU 60 */ 1847 UBLOCK_SOYOMBO = 278, /*[11A50]*/ 1848 /** @stable ICU 60 */ 1849 UBLOCK_SYRIAC_SUPPLEMENT = 279, /*[0860]*/ 1850 /** @stable ICU 60 */ 1851 UBLOCK_ZANABAZAR_SQUARE = 280, /*[11A00]*/ 1852 1853 // New blocks in Unicode 11.0 1854 1855 /** @stable ICU 62 */ 1856 UBLOCK_CHESS_SYMBOLS = 281, /*[1FA00]*/ 1857 /** @stable ICU 62 */ 1858 UBLOCK_DOGRA = 282, /*[11800]*/ 1859 /** @stable ICU 62 */ 1860 UBLOCK_GEORGIAN_EXTENDED = 283, /*[1C90]*/ 1861 /** @stable ICU 62 */ 1862 UBLOCK_GUNJALA_GONDI = 284, /*[11D60]*/ 1863 /** @stable ICU 62 */ 1864 UBLOCK_HANIFI_ROHINGYA = 285, /*[10D00]*/ 1865 /** @stable ICU 62 */ 1866 UBLOCK_INDIC_SIYAQ_NUMBERS = 286, /*[1EC70]*/ 1867 /** @stable ICU 62 */ 1868 UBLOCK_MAKASAR = 287, /*[11EE0]*/ 1869 /** @stable ICU 62 */ 1870 UBLOCK_MAYAN_NUMERALS = 288, /*[1D2E0]*/ 1871 /** @stable ICU 62 */ 1872 UBLOCK_MEDEFAIDRIN = 289, /*[16E40]*/ 1873 /** @stable ICU 62 */ 1874 UBLOCK_OLD_SOGDIAN = 290, /*[10F00]*/ 1875 /** @stable ICU 62 */ 1876 UBLOCK_SOGDIAN = 291, /*[10F30]*/ 1877 1878 // New blocks in Unicode 12.0 1879 1880 /** @stable ICU 64 */ 1881 UBLOCK_EGYPTIAN_HIEROGLYPH_FORMAT_CONTROLS = 292, /*[13430]*/ 1882 /** @stable ICU 64 */ 1883 UBLOCK_ELYMAIC = 293, /*[10FE0]*/ 1884 /** @stable ICU 64 */ 1885 UBLOCK_NANDINAGARI = 294, /*[119A0]*/ 1886 /** @stable ICU 64 */ 1887 UBLOCK_NYIAKENG_PUACHUE_HMONG = 295, /*[1E100]*/ 1888 /** @stable ICU 64 */ 1889 UBLOCK_OTTOMAN_SIYAQ_NUMBERS = 296, /*[1ED00]*/ 1890 /** @stable ICU 64 */ 1891 UBLOCK_SMALL_KANA_EXTENSION = 297, /*[1B130]*/ 1892 /** @stable ICU 64 */ 1893 UBLOCK_SYMBOLS_AND_PICTOGRAPHS_EXTENDED_A = 298, /*[1FA70]*/ 1894 /** @stable ICU 64 */ 1895 UBLOCK_TAMIL_SUPPLEMENT = 299, /*[11FC0]*/ 1896 /** @stable ICU 64 */ 1897 UBLOCK_WANCHO = 300, /*[1E2C0]*/ 1898 1899 // New blocks in Unicode 13.0 1900 1901 /** @stable ICU 66 */ 1902 UBLOCK_CHORASMIAN = 301, /*[10FB0]*/ 1903 /** @stable ICU 66 */ 1904 UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_G = 302, /*[30000]*/ 1905 /** @stable ICU 66 */ 1906 UBLOCK_DIVES_AKURU = 303, /*[11900]*/ 1907 /** @stable ICU 66 */ 1908 UBLOCK_KHITAN_SMALL_SCRIPT = 304, /*[18B00]*/ 1909 /** @stable ICU 66 */ 1910 UBLOCK_LISU_SUPPLEMENT = 305, /*[11FB0]*/ 1911 /** @stable ICU 66 */ 1912 UBLOCK_SYMBOLS_FOR_LEGACY_COMPUTING = 306, /*[1FB00]*/ 1913 /** @stable ICU 66 */ 1914 UBLOCK_TANGUT_SUPPLEMENT = 307, /*[18D00]*/ 1915 /** @stable ICU 66 */ 1916 UBLOCK_YEZIDI = 308, /*[10E80]*/ 1917 1918 // New blocks in Unicode 14.0 1919 1920 /** @stable ICU 70 */ 1921 UBLOCK_ARABIC_EXTENDED_B = 309, /*[0870]*/ 1922 /** @stable ICU 70 */ 1923 UBLOCK_CYPRO_MINOAN = 310, /*[12F90]*/ 1924 /** @stable ICU 70 */ 1925 UBLOCK_ETHIOPIC_EXTENDED_B = 311, /*[1E7E0]*/ 1926 /** @stable ICU 70 */ 1927 UBLOCK_KANA_EXTENDED_B = 312, /*[1AFF0]*/ 1928 /** @stable ICU 70 */ 1929 UBLOCK_LATIN_EXTENDED_F = 313, /*[10780]*/ 1930 /** @stable ICU 70 */ 1931 UBLOCK_LATIN_EXTENDED_G = 314, /*[1DF00]*/ 1932 /** @stable ICU 70 */ 1933 UBLOCK_OLD_UYGHUR = 315, /*[10F70]*/ 1934 /** @stable ICU 70 */ 1935 UBLOCK_TANGSA = 316, /*[16A70]*/ 1936 /** @stable ICU 70 */ 1937 UBLOCK_TOTO = 317, /*[1E290]*/ 1938 /** @stable ICU 70 */ 1939 UBLOCK_UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS_EXTENDED_A = 318, /*[11AB0]*/ 1940 /** @stable ICU 70 */ 1941 UBLOCK_VITHKUQI = 319, /*[10570]*/ 1942 /** @stable ICU 70 */ 1943 UBLOCK_ZNAMENNY_MUSICAL_NOTATION = 320, /*[1CF00]*/ 1944 1945 // New blocks in Unicode 15.0 1946 1947 /** @stable ICU 72 */ 1948 UBLOCK_ARABIC_EXTENDED_C = 321, /*[10EC0]*/ 1949 /** @stable ICU 72 */ 1950 UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_H = 322, /*[31350]*/ 1951 /** @stable ICU 72 */ 1952 UBLOCK_CYRILLIC_EXTENDED_D = 323, /*[1E030]*/ 1953 /** @stable ICU 72 */ 1954 UBLOCK_DEVANAGARI_EXTENDED_A = 324, /*[11B00]*/ 1955 /** @stable ICU 72 */ 1956 UBLOCK_KAKTOVIK_NUMERALS = 325, /*[1D2C0]*/ 1957 /** @stable ICU 72 */ 1958 UBLOCK_KAWI = 326, /*[11F00]*/ 1959 /** @stable ICU 72 */ 1960 UBLOCK_NAG_MUNDARI = 327, /*[1E4D0]*/ 1961 1962 // New block in Unicode 15.1 1963 1964 /** @stable ICU 74 */ 1965 UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_I = 328, /*[2EBF0]*/ 1966 1967 // New blocks in Unicode 16.0 1968 1969 /** @stable ICU 76 */ 1970 UBLOCK_EGYPTIAN_HIEROGLYPHS_EXTENDED_A = 329, /*[13460]*/ 1971 /** @stable ICU 76 */ 1972 UBLOCK_GARAY = 330, /*[10D40]*/ 1973 /** @stable ICU 76 */ 1974 UBLOCK_GURUNG_KHEMA = 331, /*[16100]*/ 1975 /** @stable ICU 76 */ 1976 UBLOCK_KIRAT_RAI = 332, /*[16D40]*/ 1977 /** @stable ICU 76 */ 1978 UBLOCK_MYANMAR_EXTENDED_C = 333, /*[116D0]*/ 1979 /** @stable ICU 76 */ 1980 UBLOCK_OL_ONAL = 334, /*[1E5D0]*/ 1981 /** @stable ICU 76 */ 1982 UBLOCK_SUNUWAR = 335, /*[11BC0]*/ 1983 /** @stable ICU 76 */ 1984 UBLOCK_SYMBOLS_FOR_LEGACY_COMPUTING_SUPPLEMENT = 336, /*[1CC00]*/ 1985 /** @stable ICU 76 */ 1986 UBLOCK_TODHRI = 337, /*[105C0]*/ 1987 /** @stable ICU 76 */ 1988 UBLOCK_TULU_TIGALARI = 338, /*[11380]*/ 1989 1990 #ifndef U_HIDE_DEPRECATED_API 1991 /** 1992 * One more than the highest normal UBlockCode value. 1993 * The highest value is available via u_getIntPropertyMaxValue(UCHAR_BLOCK). 1994 * 1995 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. 1996 */ 1997 UBLOCK_COUNT = 339, 1998 #endif // U_HIDE_DEPRECATED_API 1999 2000 /** @stable ICU 2.0 */ 2001 UBLOCK_INVALID_CODE=-1 2002 }; 2003 2004 /** @stable ICU 2.0 */ 2005 typedef enum UBlockCode UBlockCode; 2006 2007 /** 2008 * East Asian Width constants. 2009 * 2010 * @see UCHAR_EAST_ASIAN_WIDTH 2011 * @see u_getIntPropertyValue 2012 * @stable ICU 2.2 2013 */ 2014 typedef enum UEastAsianWidth { 2015 /* 2016 * Note: UEastAsianWidth constants are parsed by preparseucd.py. 2017 * It matches lines like 2018 * U_EA_<Unicode East_Asian_Width value name> 2019 */ 2020 2021 U_EA_NEUTRAL, /*[N]*/ 2022 U_EA_AMBIGUOUS, /*[A]*/ 2023 U_EA_HALFWIDTH, /*[H]*/ 2024 U_EA_FULLWIDTH, /*[F]*/ 2025 U_EA_NARROW, /*[Na]*/ 2026 U_EA_WIDE, /*[W]*/ 2027 #ifndef U_HIDE_DEPRECATED_API 2028 /** 2029 * One more than the highest normal UEastAsianWidth value. 2030 * The highest value is available via u_getIntPropertyMaxValue(UCHAR_EAST_ASIAN_WIDTH). 2031 * 2032 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. 2033 */ 2034 U_EA_COUNT 2035 #endif // U_HIDE_DEPRECATED_API 2036 } UEastAsianWidth; 2037 2038 /** 2039 * Selector constants for u_charName(). 2040 * u_charName() returns the "modern" name of a 2041 * Unicode character; or the name that was defined in 2042 * Unicode version 1.0, before the Unicode standard merged 2043 * with ISO-10646; or an "extended" name that gives each 2044 * Unicode code point a unique name. 2045 * 2046 * @see u_charName 2047 * @stable ICU 2.0 2048 */ 2049 typedef enum UCharNameChoice { 2050 /** Unicode character name (Name property). @stable ICU 2.0 */ 2051 U_UNICODE_CHAR_NAME, 2052 #ifndef U_HIDE_DEPRECATED_API 2053 /** 2054 * The Unicode_1_Name property value which is of little practical value. 2055 * Beginning with ICU 49, ICU APIs return an empty string for this name choice. 2056 * @deprecated ICU 49 2057 */ 2058 U_UNICODE_10_CHAR_NAME, 2059 #endif /* U_HIDE_DEPRECATED_API */ 2060 /** Standard or synthetic character name. @stable ICU 2.0 */ 2061 U_EXTENDED_CHAR_NAME = U_UNICODE_CHAR_NAME+2, 2062 /** Corrected name from NameAliases.txt. @stable ICU 4.4 */ 2063 U_CHAR_NAME_ALIAS, 2064 #ifndef U_HIDE_DEPRECATED_API 2065 /** 2066 * One more than the highest normal UCharNameChoice value. 2067 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. 2068 */ 2069 U_CHAR_NAME_CHOICE_COUNT 2070 #endif // U_HIDE_DEPRECATED_API 2071 } UCharNameChoice; 2072 2073 /** 2074 * Selector constants for u_getPropertyName() and 2075 * u_getPropertyValueName(). These selectors are used to choose which 2076 * name is returned for a given property or value. All properties and 2077 * values have a long name. Most have a short name, but some do not. 2078 * Unicode allows for additional names, beyond the long and short 2079 * name, which would be indicated by U_LONG_PROPERTY_NAME + i, where 2080 * i=1, 2,... 2081 * 2082 * @see u_getPropertyName() 2083 * @see u_getPropertyValueName() 2084 * @stable ICU 2.4 2085 */ 2086 typedef enum UPropertyNameChoice { 2087 U_SHORT_PROPERTY_NAME, 2088 U_LONG_PROPERTY_NAME, 2089 #ifndef U_HIDE_DEPRECATED_API 2090 /** 2091 * One more than the highest normal UPropertyNameChoice value. 2092 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. 2093 */ 2094 U_PROPERTY_NAME_CHOICE_COUNT 2095 #endif // U_HIDE_DEPRECATED_API 2096 } UPropertyNameChoice; 2097 2098 /** 2099 * Decomposition Type constants. 2100 * 2101 * @see UCHAR_DECOMPOSITION_TYPE 2102 * @stable ICU 2.2 2103 */ 2104 typedef enum UDecompositionType { 2105 /* 2106 * Note: UDecompositionType constants are parsed by preparseucd.py. 2107 * It matches lines like 2108 * U_DT_<Unicode Decomposition_Type value name> 2109 */ 2110 2111 U_DT_NONE, /*[none]*/ 2112 U_DT_CANONICAL, /*[can]*/ 2113 U_DT_COMPAT, /*[com]*/ 2114 U_DT_CIRCLE, /*[enc]*/ 2115 U_DT_FINAL, /*[fin]*/ 2116 U_DT_FONT, /*[font]*/ 2117 U_DT_FRACTION, /*[fra]*/ 2118 U_DT_INITIAL, /*[init]*/ 2119 U_DT_ISOLATED, /*[iso]*/ 2120 U_DT_MEDIAL, /*[med]*/ 2121 U_DT_NARROW, /*[nar]*/ 2122 U_DT_NOBREAK, /*[nb]*/ 2123 U_DT_SMALL, /*[sml]*/ 2124 U_DT_SQUARE, /*[sqr]*/ 2125 U_DT_SUB, /*[sub]*/ 2126 U_DT_SUPER, /*[sup]*/ 2127 U_DT_VERTICAL, /*[vert]*/ 2128 U_DT_WIDE, /*[wide]*/ 2129 #ifndef U_HIDE_DEPRECATED_API 2130 /** 2131 * One more than the highest normal UDecompositionType value. 2132 * The highest value is available via u_getIntPropertyMaxValue(UCHAR_DECOMPOSITION_TYPE). 2133 * 2134 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. 2135 */ 2136 U_DT_COUNT /* 18 */ 2137 #endif // U_HIDE_DEPRECATED_API 2138 } UDecompositionType; 2139 2140 /** 2141 * Joining Type constants. 2142 * 2143 * @see UCHAR_JOINING_TYPE 2144 * @stable ICU 2.2 2145 */ 2146 typedef enum UJoiningType { 2147 /* 2148 * Note: UJoiningType constants are parsed by preparseucd.py. 2149 * It matches lines like 2150 * U_JT_<Unicode Joining_Type value name> 2151 */ 2152 2153 U_JT_NON_JOINING, /*[U]*/ 2154 U_JT_JOIN_CAUSING, /*[C]*/ 2155 U_JT_DUAL_JOINING, /*[D]*/ 2156 U_JT_LEFT_JOINING, /*[L]*/ 2157 U_JT_RIGHT_JOINING, /*[R]*/ 2158 U_JT_TRANSPARENT, /*[T]*/ 2159 #ifndef U_HIDE_DEPRECATED_API 2160 /** 2161 * One more than the highest normal UJoiningType value. 2162 * The highest value is available via u_getIntPropertyMaxValue(UCHAR_JOINING_TYPE). 2163 * 2164 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. 2165 */ 2166 U_JT_COUNT /* 6 */ 2167 #endif // U_HIDE_DEPRECATED_API 2168 } UJoiningType; 2169 2170 /** 2171 * Joining Group constants. 2172 * 2173 * @see UCHAR_JOINING_GROUP 2174 * @stable ICU 2.2 2175 */ 2176 typedef enum UJoiningGroup { 2177 /* 2178 * Note: UJoiningGroup constants are parsed by preparseucd.py. 2179 * It matches lines like 2180 * U_JG_<Unicode Joining_Group value name> 2181 */ 2182 2183 U_JG_NO_JOINING_GROUP, 2184 U_JG_AIN, 2185 U_JG_ALAPH, 2186 U_JG_ALEF, 2187 U_JG_BEH, 2188 U_JG_BETH, 2189 U_JG_DAL, 2190 U_JG_DALATH_RISH, 2191 U_JG_E, 2192 U_JG_FEH, 2193 U_JG_FINAL_SEMKATH, 2194 U_JG_GAF, 2195 U_JG_GAMAL, 2196 U_JG_HAH, 2197 U_JG_TEH_MARBUTA_GOAL, /**< @stable ICU 4.6 */ 2198 U_JG_HAMZA_ON_HEH_GOAL=U_JG_TEH_MARBUTA_GOAL, 2199 U_JG_HE, 2200 U_JG_HEH, 2201 U_JG_HEH_GOAL, 2202 U_JG_HETH, 2203 U_JG_KAF, 2204 U_JG_KAPH, 2205 U_JG_KNOTTED_HEH, 2206 U_JG_LAM, 2207 U_JG_LAMADH, 2208 U_JG_MEEM, 2209 U_JG_MIM, 2210 U_JG_NOON, 2211 U_JG_NUN, 2212 U_JG_PE, 2213 U_JG_QAF, 2214 U_JG_QAPH, 2215 U_JG_REH, 2216 U_JG_REVERSED_PE, 2217 U_JG_SAD, 2218 U_JG_SADHE, 2219 U_JG_SEEN, 2220 U_JG_SEMKATH, 2221 U_JG_SHIN, 2222 U_JG_SWASH_KAF, 2223 U_JG_SYRIAC_WAW, 2224 U_JG_TAH, 2225 U_JG_TAW, 2226 U_JG_TEH_MARBUTA, 2227 U_JG_TETH, 2228 U_JG_WAW, 2229 U_JG_YEH, 2230 U_JG_YEH_BARREE, 2231 U_JG_YEH_WITH_TAIL, 2232 U_JG_YUDH, 2233 U_JG_YUDH_HE, 2234 U_JG_ZAIN, 2235 U_JG_FE, /**< @stable ICU 2.6 */ 2236 U_JG_KHAPH, /**< @stable ICU 2.6 */ 2237 U_JG_ZHAIN, /**< @stable ICU 2.6 */ 2238 U_JG_BURUSHASKI_YEH_BARREE, /**< @stable ICU 4.0 */ 2239 U_JG_FARSI_YEH, /**< @stable ICU 4.4 */ 2240 U_JG_NYA, /**< @stable ICU 4.4 */ 2241 U_JG_ROHINGYA_YEH, /**< @stable ICU 49 */ 2242 U_JG_MANICHAEAN_ALEPH, /**< @stable ICU 54 */ 2243 U_JG_MANICHAEAN_AYIN, /**< @stable ICU 54 */ 2244 U_JG_MANICHAEAN_BETH, /**< @stable ICU 54 */ 2245 U_JG_MANICHAEAN_DALETH, /**< @stable ICU 54 */ 2246 U_JG_MANICHAEAN_DHAMEDH, /**< @stable ICU 54 */ 2247 U_JG_MANICHAEAN_FIVE, /**< @stable ICU 54 */ 2248 U_JG_MANICHAEAN_GIMEL, /**< @stable ICU 54 */ 2249 U_JG_MANICHAEAN_HETH, /**< @stable ICU 54 */ 2250 U_JG_MANICHAEAN_HUNDRED, /**< @stable ICU 54 */ 2251 U_JG_MANICHAEAN_KAPH, /**< @stable ICU 54 */ 2252 U_JG_MANICHAEAN_LAMEDH, /**< @stable ICU 54 */ 2253 U_JG_MANICHAEAN_MEM, /**< @stable ICU 54 */ 2254 U_JG_MANICHAEAN_NUN, /**< @stable ICU 54 */ 2255 U_JG_MANICHAEAN_ONE, /**< @stable ICU 54 */ 2256 U_JG_MANICHAEAN_PE, /**< @stable ICU 54 */ 2257 U_JG_MANICHAEAN_QOPH, /**< @stable ICU 54 */ 2258 U_JG_MANICHAEAN_RESH, /**< @stable ICU 54 */ 2259 U_JG_MANICHAEAN_SADHE, /**< @stable ICU 54 */ 2260 U_JG_MANICHAEAN_SAMEKH, /**< @stable ICU 54 */ 2261 U_JG_MANICHAEAN_TAW, /**< @stable ICU 54 */ 2262 U_JG_MANICHAEAN_TEN, /**< @stable ICU 54 */ 2263 U_JG_MANICHAEAN_TETH, /**< @stable ICU 54 */ 2264 U_JG_MANICHAEAN_THAMEDH, /**< @stable ICU 54 */ 2265 U_JG_MANICHAEAN_TWENTY, /**< @stable ICU 54 */ 2266 U_JG_MANICHAEAN_WAW, /**< @stable ICU 54 */ 2267 U_JG_MANICHAEAN_YODH, /**< @stable ICU 54 */ 2268 U_JG_MANICHAEAN_ZAYIN, /**< @stable ICU 54 */ 2269 U_JG_STRAIGHT_WAW, /**< @stable ICU 54 */ 2270 U_JG_AFRICAN_FEH, /**< @stable ICU 58 */ 2271 U_JG_AFRICAN_NOON, /**< @stable ICU 58 */ 2272 U_JG_AFRICAN_QAF, /**< @stable ICU 58 */ 2273 2274 U_JG_MALAYALAM_BHA, /**< @stable ICU 60 */ 2275 U_JG_MALAYALAM_JA, /**< @stable ICU 60 */ 2276 U_JG_MALAYALAM_LLA, /**< @stable ICU 60 */ 2277 U_JG_MALAYALAM_LLLA, /**< @stable ICU 60 */ 2278 U_JG_MALAYALAM_NGA, /**< @stable ICU 60 */ 2279 U_JG_MALAYALAM_NNA, /**< @stable ICU 60 */ 2280 U_JG_MALAYALAM_NNNA, /**< @stable ICU 60 */ 2281 U_JG_MALAYALAM_NYA, /**< @stable ICU 60 */ 2282 U_JG_MALAYALAM_RA, /**< @stable ICU 60 */ 2283 U_JG_MALAYALAM_SSA, /**< @stable ICU 60 */ 2284 U_JG_MALAYALAM_TTA, /**< @stable ICU 60 */ 2285 2286 U_JG_HANIFI_ROHINGYA_KINNA_YA, /**< @stable ICU 62 */ 2287 U_JG_HANIFI_ROHINGYA_PA, /**< @stable ICU 62 */ 2288 2289 U_JG_THIN_YEH, /**< @stable ICU 70 */ 2290 U_JG_VERTICAL_TAIL, /**< @stable ICU 70 */ 2291 2292 U_JG_KASHMIRI_YEH, /**< @stable ICU 76 */ 2293 2294 #ifndef U_HIDE_DEPRECATED_API 2295 /** 2296 * One more than the highest normal UJoiningGroup value. 2297 * The highest value is available via u_getIntPropertyMaxValue(UCHAR_JOINING_GROUP). 2298 * 2299 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. 2300 */ 2301 U_JG_COUNT 2302 #endif // U_HIDE_DEPRECATED_API 2303 } UJoiningGroup; 2304 2305 /** 2306 * Grapheme Cluster Break constants. 2307 * 2308 * @see UCHAR_GRAPHEME_CLUSTER_BREAK 2309 * @stable ICU 3.4 2310 */ 2311 typedef enum UGraphemeClusterBreak { 2312 /* 2313 * Note: UGraphemeClusterBreak constants are parsed by preparseucd.py. 2314 * It matches lines like 2315 * U_GCB_<Unicode Grapheme_Cluster_Break value name> 2316 */ 2317 2318 U_GCB_OTHER = 0, /*[XX]*/ 2319 U_GCB_CONTROL = 1, /*[CN]*/ 2320 U_GCB_CR = 2, /*[CR]*/ 2321 U_GCB_EXTEND = 3, /*[EX]*/ 2322 U_GCB_L = 4, /*[L]*/ 2323 U_GCB_LF = 5, /*[LF]*/ 2324 U_GCB_LV = 6, /*[LV]*/ 2325 U_GCB_LVT = 7, /*[LVT]*/ 2326 U_GCB_T = 8, /*[T]*/ 2327 U_GCB_V = 9, /*[V]*/ 2328 /** @stable ICU 4.0 */ 2329 U_GCB_SPACING_MARK = 10, /*[SM]*/ /* from here on: new in Unicode 5.1/ICU 4.0 */ 2330 /** @stable ICU 4.0 */ 2331 U_GCB_PREPEND = 11, /*[PP]*/ 2332 /** @stable ICU 50 */ 2333 U_GCB_REGIONAL_INDICATOR = 12, /*[RI]*/ /* new in Unicode 6.2/ICU 50 */ 2334 /** @stable ICU 58 */ 2335 U_GCB_E_BASE = 13, /*[EB]*/ /* from here on: new in Unicode 9.0/ICU 58 */ 2336 /** @stable ICU 58 */ 2337 U_GCB_E_BASE_GAZ = 14, /*[EBG]*/ 2338 /** @stable ICU 58 */ 2339 U_GCB_E_MODIFIER = 15, /*[EM]*/ 2340 /** @stable ICU 58 */ 2341 U_GCB_GLUE_AFTER_ZWJ = 16, /*[GAZ]*/ 2342 /** @stable ICU 58 */ 2343 U_GCB_ZWJ = 17, /*[ZWJ]*/ 2344 2345 #ifndef U_HIDE_DEPRECATED_API 2346 /** 2347 * One more than the highest normal UGraphemeClusterBreak value. 2348 * The highest value is available via u_getIntPropertyMaxValue(UCHAR_GRAPHEME_CLUSTER_BREAK). 2349 * 2350 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. 2351 */ 2352 U_GCB_COUNT = 18 2353 #endif // U_HIDE_DEPRECATED_API 2354 } UGraphemeClusterBreak; 2355 2356 /** 2357 * Word Break constants. 2358 * (UWordBreak is a pre-existing enum type in ubrk.h for word break status tags.) 2359 * 2360 * @see UCHAR_WORD_BREAK 2361 * @stable ICU 3.4 2362 */ 2363 typedef enum UWordBreakValues { 2364 /* 2365 * Note: UWordBreakValues constants are parsed by preparseucd.py. 2366 * It matches lines like 2367 * U_WB_<Unicode Word_Break value name> 2368 */ 2369 2370 U_WB_OTHER = 0, /*[XX]*/ 2371 U_WB_ALETTER = 1, /*[LE]*/ 2372 U_WB_FORMAT = 2, /*[FO]*/ 2373 U_WB_KATAKANA = 3, /*[KA]*/ 2374 U_WB_MIDLETTER = 4, /*[ML]*/ 2375 U_WB_MIDNUM = 5, /*[MN]*/ 2376 U_WB_NUMERIC = 6, /*[NU]*/ 2377 U_WB_EXTENDNUMLET = 7, /*[EX]*/ 2378 /** @stable ICU 4.0 */ 2379 U_WB_CR = 8, /*[CR]*/ /* from here on: new in Unicode 5.1/ICU 4.0 */ 2380 /** @stable ICU 4.0 */ 2381 U_WB_EXTEND = 9, /*[Extend]*/ 2382 /** @stable ICU 4.0 */ 2383 U_WB_LF = 10, /*[LF]*/ 2384 /** @stable ICU 4.0 */ 2385 U_WB_MIDNUMLET =11, /*[MB]*/ 2386 /** @stable ICU 4.0 */ 2387 U_WB_NEWLINE =12, /*[NL]*/ 2388 /** @stable ICU 50 */ 2389 U_WB_REGIONAL_INDICATOR = 13, /*[RI]*/ /* new in Unicode 6.2/ICU 50 */ 2390 /** @stable ICU 52 */ 2391 U_WB_HEBREW_LETTER = 14, /*[HL]*/ /* from here on: new in Unicode 6.3/ICU 52 */ 2392 /** @stable ICU 52 */ 2393 U_WB_SINGLE_QUOTE = 15, /*[SQ]*/ 2394 /** @stable ICU 52 */ 2395 U_WB_DOUBLE_QUOTE = 16, /*[DQ]*/ 2396 /** @stable ICU 58 */ 2397 U_WB_E_BASE = 17, /*[EB]*/ /* from here on: new in Unicode 9.0/ICU 58 */ 2398 /** @stable ICU 58 */ 2399 U_WB_E_BASE_GAZ = 18, /*[EBG]*/ 2400 /** @stable ICU 58 */ 2401 U_WB_E_MODIFIER = 19, /*[EM]*/ 2402 /** @stable ICU 58 */ 2403 U_WB_GLUE_AFTER_ZWJ = 20, /*[GAZ]*/ 2404 /** @stable ICU 58 */ 2405 U_WB_ZWJ = 21, /*[ZWJ]*/ 2406 /** @stable ICU 62 */ 2407 U_WB_WSEGSPACE = 22, /*[WSEGSPACE]*/ 2408 2409 #ifndef U_HIDE_DEPRECATED_API 2410 /** 2411 * One more than the highest normal UWordBreakValues value. 2412 * The highest value is available via u_getIntPropertyMaxValue(UCHAR_WORD_BREAK). 2413 * 2414 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. 2415 */ 2416 U_WB_COUNT = 23 2417 #endif // U_HIDE_DEPRECATED_API 2418 } UWordBreakValues; 2419 2420 /** 2421 * Sentence Break constants. 2422 * 2423 * @see UCHAR_SENTENCE_BREAK 2424 * @stable ICU 3.4 2425 */ 2426 typedef enum USentenceBreak { 2427 /* 2428 * Note: USentenceBreak constants are parsed by preparseucd.py. 2429 * It matches lines like 2430 * U_SB_<Unicode Sentence_Break value name> 2431 */ 2432 2433 U_SB_OTHER = 0, /*[XX]*/ 2434 U_SB_ATERM = 1, /*[AT]*/ 2435 U_SB_CLOSE = 2, /*[CL]*/ 2436 U_SB_FORMAT = 3, /*[FO]*/ 2437 U_SB_LOWER = 4, /*[LO]*/ 2438 U_SB_NUMERIC = 5, /*[NU]*/ 2439 U_SB_OLETTER = 6, /*[LE]*/ 2440 U_SB_SEP = 7, /*[SE]*/ 2441 U_SB_SP = 8, /*[SP]*/ 2442 U_SB_STERM = 9, /*[ST]*/ 2443 U_SB_UPPER = 10, /*[UP]*/ 2444 U_SB_CR = 11, /*[CR]*/ /* from here on: new in Unicode 5.1/ICU 4.0 */ 2445 U_SB_EXTEND = 12, /*[EX]*/ 2446 U_SB_LF = 13, /*[LF]*/ 2447 U_SB_SCONTINUE = 14, /*[SC]*/ 2448 #ifndef U_HIDE_DEPRECATED_API 2449 /** 2450 * One more than the highest normal USentenceBreak value. 2451 * The highest value is available via u_getIntPropertyMaxValue(UCHAR_SENTENCE_BREAK). 2452 * 2453 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. 2454 */ 2455 U_SB_COUNT = 15 2456 #endif // U_HIDE_DEPRECATED_API 2457 } USentenceBreak; 2458 2459 /** 2460 * Line Break constants. 2461 * 2462 * @see UCHAR_LINE_BREAK 2463 * @stable ICU 2.2 2464 */ 2465 typedef enum ULineBreak { 2466 /* 2467 * Note: ULineBreak constants are parsed by preparseucd.py. 2468 * It matches lines like 2469 * U_LB_<Unicode Line_Break value name> 2470 */ 2471 2472 U_LB_UNKNOWN = 0, /*[XX]*/ 2473 U_LB_AMBIGUOUS = 1, /*[AI]*/ 2474 U_LB_ALPHABETIC = 2, /*[AL]*/ 2475 U_LB_BREAK_BOTH = 3, /*[B2]*/ 2476 U_LB_BREAK_AFTER = 4, /*[BA]*/ 2477 U_LB_BREAK_BEFORE = 5, /*[BB]*/ 2478 U_LB_MANDATORY_BREAK = 6, /*[BK]*/ 2479 U_LB_CONTINGENT_BREAK = 7, /*[CB]*/ 2480 U_LB_CLOSE_PUNCTUATION = 8, /*[CL]*/ 2481 U_LB_COMBINING_MARK = 9, /*[CM]*/ 2482 U_LB_CARRIAGE_RETURN = 10, /*[CR]*/ 2483 U_LB_EXCLAMATION = 11, /*[EX]*/ 2484 U_LB_GLUE = 12, /*[GL]*/ 2485 U_LB_HYPHEN = 13, /*[HY]*/ 2486 U_LB_IDEOGRAPHIC = 14, /*[ID]*/ 2487 /** Renamed from the misspelled "inseperable" in Unicode 4.0.1/ICU 3.0 @stable ICU 3.0 */ 2488 U_LB_INSEPARABLE = 15, /*[IN]*/ 2489 U_LB_INSEPERABLE = U_LB_INSEPARABLE, 2490 U_LB_INFIX_NUMERIC = 16, /*[IS]*/ 2491 U_LB_LINE_FEED = 17, /*[LF]*/ 2492 U_LB_NONSTARTER = 18, /*[NS]*/ 2493 U_LB_NUMERIC = 19, /*[NU]*/ 2494 U_LB_OPEN_PUNCTUATION = 20, /*[OP]*/ 2495 U_LB_POSTFIX_NUMERIC = 21, /*[PO]*/ 2496 U_LB_PREFIX_NUMERIC = 22, /*[PR]*/ 2497 U_LB_QUOTATION = 23, /*[QU]*/ 2498 U_LB_COMPLEX_CONTEXT = 24, /*[SA]*/ 2499 U_LB_SURROGATE = 25, /*[SG]*/ 2500 U_LB_SPACE = 26, /*[SP]*/ 2501 U_LB_BREAK_SYMBOLS = 27, /*[SY]*/ 2502 U_LB_ZWSPACE = 28, /*[ZW]*/ 2503 /** @stable ICU 2.6 */ 2504 U_LB_NEXT_LINE = 29, /*[NL]*/ /* from here on: new in Unicode 4/ICU 2.6 */ 2505 /** @stable ICU 2.6 */ 2506 U_LB_WORD_JOINER = 30, /*[WJ]*/ 2507 /** @stable ICU 3.4 */ 2508 U_LB_H2 = 31, /*[H2]*/ /* from here on: new in Unicode 4.1/ICU 3.4 */ 2509 /** @stable ICU 3.4 */ 2510 U_LB_H3 = 32, /*[H3]*/ 2511 /** @stable ICU 3.4 */ 2512 U_LB_JL = 33, /*[JL]*/ 2513 /** @stable ICU 3.4 */ 2514 U_LB_JT = 34, /*[JT]*/ 2515 /** @stable ICU 3.4 */ 2516 U_LB_JV = 35, /*[JV]*/ 2517 /** @stable ICU 4.4 */ 2518 U_LB_CLOSE_PARENTHESIS = 36, /*[CP]*/ /* new in Unicode 5.2/ICU 4.4 */ 2519 /** @stable ICU 49 */ 2520 U_LB_CONDITIONAL_JAPANESE_STARTER = 37,/*[CJ]*/ /* new in Unicode 6.1/ICU 49 */ 2521 /** @stable ICU 49 */ 2522 U_LB_HEBREW_LETTER = 38, /*[HL]*/ /* new in Unicode 6.1/ICU 49 */ 2523 /** @stable ICU 50 */ 2524 U_LB_REGIONAL_INDICATOR = 39,/*[RI]*/ /* new in Unicode 6.2/ICU 50 */ 2525 /** @stable ICU 58 */ 2526 U_LB_E_BASE = 40, /*[EB]*/ /* from here on: new in Unicode 9.0/ICU 58 */ 2527 /** @stable ICU 58 */ 2528 U_LB_E_MODIFIER = 41, /*[EM]*/ 2529 /** @stable ICU 58 */ 2530 U_LB_ZWJ = 42, /*[ZWJ]*/ 2531 /** @stable ICU 74 */ 2532 U_LB_AKSARA = 43, /*[AK]*/ 2533 /** @stable ICU 74 */ 2534 U_LB_AKSARA_PREBASE = 44, /*[AP]*/ 2535 /** @stable ICU 74 */ 2536 U_LB_AKSARA_START = 45, /*[AS]*/ 2537 /** @stable ICU 74 */ 2538 U_LB_VIRAMA_FINAL = 46, /*[VF]*/ 2539 /** @stable ICU 74 */ 2540 U_LB_VIRAMA = 47, /*[VI]*/ 2541 #ifndef U_HIDE_DEPRECATED_API 2542 /** 2543 * One more than the highest normal ULineBreak value. 2544 * The highest value is available via u_getIntPropertyMaxValue(UCHAR_LINE_BREAK). 2545 * 2546 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. 2547 */ 2548 U_LB_COUNT = 48 2549 #endif // U_HIDE_DEPRECATED_API 2550 } ULineBreak; 2551 2552 /** 2553 * Numeric Type constants. 2554 * 2555 * @see UCHAR_NUMERIC_TYPE 2556 * @stable ICU 2.2 2557 */ 2558 typedef enum UNumericType { 2559 /* 2560 * Note: UNumericType constants are parsed by preparseucd.py. 2561 * It matches lines like 2562 * U_NT_<Unicode Numeric_Type value name> 2563 */ 2564 2565 U_NT_NONE, /*[None]*/ 2566 U_NT_DECIMAL, /*[de]*/ 2567 U_NT_DIGIT, /*[di]*/ 2568 U_NT_NUMERIC, /*[nu]*/ 2569 #ifndef U_HIDE_DEPRECATED_API 2570 /** 2571 * One more than the highest normal UNumericType value. 2572 * The highest value is available via u_getIntPropertyMaxValue(UCHAR_NUMERIC_TYPE). 2573 * 2574 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. 2575 */ 2576 U_NT_COUNT 2577 #endif // U_HIDE_DEPRECATED_API 2578 } UNumericType; 2579 2580 /** 2581 * Hangul Syllable Type constants. 2582 * 2583 * @see UCHAR_HANGUL_SYLLABLE_TYPE 2584 * @stable ICU 2.6 2585 */ 2586 typedef enum UHangulSyllableType { 2587 /* 2588 * Note: UHangulSyllableType constants are parsed by preparseucd.py. 2589 * It matches lines like 2590 * U_HST_<Unicode Hangul_Syllable_Type value name> 2591 */ 2592 2593 U_HST_NOT_APPLICABLE, /*[NA]*/ 2594 U_HST_LEADING_JAMO, /*[L]*/ 2595 U_HST_VOWEL_JAMO, /*[V]*/ 2596 U_HST_TRAILING_JAMO, /*[T]*/ 2597 U_HST_LV_SYLLABLE, /*[LV]*/ 2598 U_HST_LVT_SYLLABLE, /*[LVT]*/ 2599 #ifndef U_HIDE_DEPRECATED_API 2600 /** 2601 * One more than the highest normal UHangulSyllableType value. 2602 * The highest value is available via u_getIntPropertyMaxValue(UCHAR_HANGUL_SYLLABLE_TYPE). 2603 * 2604 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. 2605 */ 2606 U_HST_COUNT 2607 #endif // U_HIDE_DEPRECATED_API 2608 } UHangulSyllableType; 2609 2610 /** 2611 * Indic Positional Category constants. 2612 * 2613 * @see UCHAR_INDIC_POSITIONAL_CATEGORY 2614 * @stable ICU 63 2615 */ 2616 typedef enum UIndicPositionalCategory { 2617 /* 2618 * Note: UIndicPositionalCategory constants are parsed by preparseucd.py. 2619 * It matches lines like 2620 * U_INPC_<Unicode Indic_Positional_Category value name> 2621 */ 2622 2623 /** @stable ICU 63 */ 2624 U_INPC_NA, 2625 /** @stable ICU 63 */ 2626 U_INPC_BOTTOM, 2627 /** @stable ICU 63 */ 2628 U_INPC_BOTTOM_AND_LEFT, 2629 /** @stable ICU 63 */ 2630 U_INPC_BOTTOM_AND_RIGHT, 2631 /** @stable ICU 63 */ 2632 U_INPC_LEFT, 2633 /** @stable ICU 63 */ 2634 U_INPC_LEFT_AND_RIGHT, 2635 /** @stable ICU 63 */ 2636 U_INPC_OVERSTRUCK, 2637 /** @stable ICU 63 */ 2638 U_INPC_RIGHT, 2639 /** @stable ICU 63 */ 2640 U_INPC_TOP, 2641 /** @stable ICU 63 */ 2642 U_INPC_TOP_AND_BOTTOM, 2643 /** @stable ICU 63 */ 2644 U_INPC_TOP_AND_BOTTOM_AND_RIGHT, 2645 /** @stable ICU 63 */ 2646 U_INPC_TOP_AND_LEFT, 2647 /** @stable ICU 63 */ 2648 U_INPC_TOP_AND_LEFT_AND_RIGHT, 2649 /** @stable ICU 63 */ 2650 U_INPC_TOP_AND_RIGHT, 2651 /** @stable ICU 63 */ 2652 U_INPC_VISUAL_ORDER_LEFT, 2653 /** @stable ICU 66 */ 2654 U_INPC_TOP_AND_BOTTOM_AND_LEFT, 2655 } UIndicPositionalCategory; 2656 2657 /** 2658 * Indic Syllabic Category constants. 2659 * 2660 * @see UCHAR_INDIC_SYLLABIC_CATEGORY 2661 * @stable ICU 63 2662 */ 2663 typedef enum UIndicSyllabicCategory { 2664 /* 2665 * Note: UIndicSyllabicCategory constants are parsed by preparseucd.py. 2666 * It matches lines like 2667 * U_INSC_<Unicode Indic_Syllabic_Category value name> 2668 */ 2669 2670 /** @stable ICU 63 */ 2671 U_INSC_OTHER, 2672 /** @stable ICU 63 */ 2673 U_INSC_AVAGRAHA, 2674 /** @stable ICU 63 */ 2675 U_INSC_BINDU, 2676 /** @stable ICU 63 */ 2677 U_INSC_BRAHMI_JOINING_NUMBER, 2678 /** @stable ICU 63 */ 2679 U_INSC_CANTILLATION_MARK, 2680 /** @stable ICU 63 */ 2681 U_INSC_CONSONANT, 2682 /** @stable ICU 63 */ 2683 U_INSC_CONSONANT_DEAD, 2684 /** @stable ICU 63 */ 2685 U_INSC_CONSONANT_FINAL, 2686 /** @stable ICU 63 */ 2687 U_INSC_CONSONANT_HEAD_LETTER, 2688 /** @stable ICU 63 */ 2689 U_INSC_CONSONANT_INITIAL_POSTFIXED, 2690 /** @stable ICU 63 */ 2691 U_INSC_CONSONANT_KILLER, 2692 /** @stable ICU 63 */ 2693 U_INSC_CONSONANT_MEDIAL, 2694 /** @stable ICU 63 */ 2695 U_INSC_CONSONANT_PLACEHOLDER, 2696 /** @stable ICU 63 */ 2697 U_INSC_CONSONANT_PRECEDING_REPHA, 2698 /** @stable ICU 63 */ 2699 U_INSC_CONSONANT_PREFIXED, 2700 /** @stable ICU 63 */ 2701 U_INSC_CONSONANT_SUBJOINED, 2702 /** @stable ICU 63 */ 2703 U_INSC_CONSONANT_SUCCEEDING_REPHA, 2704 /** @stable ICU 63 */ 2705 U_INSC_CONSONANT_WITH_STACKER, 2706 /** @stable ICU 63 */ 2707 U_INSC_GEMINATION_MARK, 2708 /** @stable ICU 63 */ 2709 U_INSC_INVISIBLE_STACKER, 2710 /** @stable ICU 63 */ 2711 U_INSC_JOINER, 2712 /** @stable ICU 63 */ 2713 U_INSC_MODIFYING_LETTER, 2714 /** @stable ICU 63 */ 2715 U_INSC_NON_JOINER, 2716 /** @stable ICU 63 */ 2717 U_INSC_NUKTA, 2718 /** @stable ICU 63 */ 2719 U_INSC_NUMBER, 2720 /** @stable ICU 63 */ 2721 U_INSC_NUMBER_JOINER, 2722 /** @stable ICU 63 */ 2723 U_INSC_PURE_KILLER, 2724 /** @stable ICU 63 */ 2725 U_INSC_REGISTER_SHIFTER, 2726 /** @stable ICU 63 */ 2727 U_INSC_SYLLABLE_MODIFIER, 2728 /** @stable ICU 63 */ 2729 U_INSC_TONE_LETTER, 2730 /** @stable ICU 63 */ 2731 U_INSC_TONE_MARK, 2732 /** @stable ICU 63 */ 2733 U_INSC_VIRAMA, 2734 /** @stable ICU 63 */ 2735 U_INSC_VISARGA, 2736 /** @stable ICU 63 */ 2737 U_INSC_VOWEL, 2738 /** @stable ICU 63 */ 2739 U_INSC_VOWEL_DEPENDENT, 2740 /** @stable ICU 63 */ 2741 U_INSC_VOWEL_INDEPENDENT, 2742 /** @stable ICU 76 */ 2743 U_INSC_REORDERING_KILLER, 2744 } UIndicSyllabicCategory; 2745 2746 #ifndef U_HIDE_DRAFT_API 2747 /** 2748 * Indic Conjunct Break constants. 2749 * 2750 * @see UCHAR_INDIC_CONJUNCT_BREAK 2751 * @draft ICU 76 2752 */ 2753 typedef enum UIndicConjunctBreak { 2754 /* 2755 * Note: UIndicConjunctBreak constants are parsed by preparseucd.py. 2756 * It matches lines like 2757 * U_INCB_<Unicode Indic_Conjunct_Break value name> 2758 */ 2759 2760 /** @draft ICU 76 */ 2761 U_INCB_NONE, 2762 /** @draft ICU 76 */ 2763 U_INCB_CONSONANT, 2764 /** @draft ICU 76 */ 2765 U_INCB_EXTEND, 2766 /** @draft ICU 76 */ 2767 U_INCB_LINKER, 2768 } UIndicConjunctBreak; 2769 #endif // U_HIDE_DRAFT_API 2770 2771 /** 2772 * Vertical Orientation constants. 2773 * 2774 * @see UCHAR_VERTICAL_ORIENTATION 2775 * @stable ICU 63 2776 */ 2777 typedef enum UVerticalOrientation { 2778 /* 2779 * Note: UVerticalOrientation constants are parsed by preparseucd.py. 2780 * It matches lines like 2781 * U_VO_<Unicode Vertical_Orientation value name> 2782 */ 2783 2784 /** @stable ICU 63 */ 2785 U_VO_ROTATED, 2786 /** @stable ICU 63 */ 2787 U_VO_TRANSFORMED_ROTATED, 2788 /** @stable ICU 63 */ 2789 U_VO_TRANSFORMED_UPRIGHT, 2790 /** @stable ICU 63 */ 2791 U_VO_UPRIGHT, 2792 } UVerticalOrientation; 2793 2794 #ifndef U_HIDE_DRAFT_API 2795 /** 2796 * Identifier Status constants. 2797 * See https://www.unicode.org/reports/tr39/#Identifier_Status_and_Type. 2798 * 2799 * @see UCHAR_IDENTIFIER_STATUS 2800 * @draft ICU 75 2801 */ 2802 typedef enum UIdentifierStatus { 2803 /* 2804 * Note: UIdentifierStatus constants are parsed by preparseucd.py. 2805 * It matches lines like 2806 * U_ID_STATUS_<Unicode Identifier_Status value name> 2807 */ 2808 2809 /** @draft ICU 75 */ 2810 U_ID_STATUS_RESTRICTED, 2811 /** @draft ICU 75 */ 2812 U_ID_STATUS_ALLOWED, 2813 } UIdentifierStatus; 2814 2815 /** 2816 * Identifier Type constants. 2817 * See https://www.unicode.org/reports/tr39/#Identifier_Status_and_Type. 2818 * 2819 * @see UCHAR_IDENTIFIER_TYPE 2820 * @draft ICU 75 2821 */ 2822 typedef enum UIdentifierType { 2823 /* 2824 * Note: UIdentifierType constants are parsed by preparseucd.py. 2825 * It matches lines like 2826 * U_ID_TYPE_<Unicode Identifier_Type value name> 2827 */ 2828 2829 /** @draft ICU 75 */ 2830 U_ID_TYPE_NOT_CHARACTER, 2831 /** @draft ICU 75 */ 2832 U_ID_TYPE_DEPRECATED, 2833 /** @draft ICU 75 */ 2834 U_ID_TYPE_DEFAULT_IGNORABLE, 2835 /** @draft ICU 75 */ 2836 U_ID_TYPE_NOT_NFKC, 2837 /** @draft ICU 75 */ 2838 U_ID_TYPE_NOT_XID, 2839 /** @draft ICU 75 */ 2840 U_ID_TYPE_EXCLUSION, 2841 /** @draft ICU 75 */ 2842 U_ID_TYPE_OBSOLETE, 2843 /** @draft ICU 75 */ 2844 U_ID_TYPE_TECHNICAL, 2845 /** @draft ICU 75 */ 2846 U_ID_TYPE_UNCOMMON_USE, 2847 /** @draft ICU 75 */ 2848 U_ID_TYPE_LIMITED_USE, 2849 /** @draft ICU 75 */ 2850 U_ID_TYPE_INCLUSION, 2851 /** @draft ICU 75 */ 2852 U_ID_TYPE_RECOMMENDED, 2853 } UIdentifierType; 2854 #endif // U_HIDE_DRAFT_API 2855 2856 /** 2857 * Check a binary Unicode property for a code point. 2858 * 2859 * Unicode, especially in version 3.2, defines many more properties than the 2860 * original set in UnicodeData.txt. 2861 * 2862 * The properties APIs are intended to reflect Unicode properties as defined 2863 * in the Unicode Character Database (UCD) and Unicode Technical Reports (UTR). 2864 * For details about the properties see http://www.unicode.org/ucd/ . 2865 * For names of Unicode properties see the UCD file PropertyAliases.txt. 2866 * 2867 * Important: If ICU is built with UCD files from Unicode versions below 3.2, 2868 * then properties marked with "new in Unicode 3.2" are not or not fully available. 2869 * 2870 * @param c Code point to test. 2871 * @param which UProperty selector constant, identifies which binary property to check. 2872 * Must be UCHAR_BINARY_START<=which<UCHAR_BINARY_LIMIT. 2873 * @return true or false according to the binary Unicode property value for c. 2874 * Also false if 'which' is out of bounds or if the Unicode version 2875 * does not have data for the property at all. 2876 * 2877 * @see UProperty 2878 * @see u_getBinaryPropertySet 2879 * @see u_getIntPropertyValue 2880 * @see u_getUnicodeVersion 2881 * @stable ICU 2.1 2882 */ 2883 U_CAPI UBool U_EXPORT2 2884 u_hasBinaryProperty(UChar32 c, UProperty which); 2885 2886 /** 2887 * Returns true if the property is true for the string. 2888 * Same as u_hasBinaryProperty(single code point, which) 2889 * if the string contains exactly one code point. 2890 * 2891 * Most properties apply only to single code points. 2892 * <a href="https://www.unicode.org/reports/tr51/#Emoji_Sets">UTS #51 Unicode Emoji</a> 2893 * defines several properties of strings. 2894 * 2895 * @param s String to test. 2896 * @param length Length of the string, or negative if NUL-terminated. 2897 * @param which UProperty selector constant, identifies which binary property to check. 2898 * Must be UCHAR_BINARY_START<=which<UCHAR_BINARY_LIMIT. 2899 * @return true or false according to the binary Unicode property value for the string. 2900 * Also false if 'which' is out of bounds or if the Unicode version 2901 * does not have data for the property at all. 2902 * 2903 * @see UProperty 2904 * @see u_hasBinaryProperty 2905 * @see u_getBinaryPropertySet 2906 * @see u_getIntPropertyValue 2907 * @see u_getUnicodeVersion 2908 * @stable ICU 70 2909 */ 2910 U_CAPI UBool U_EXPORT2 2911 u_stringHasBinaryProperty(const UChar *s, int32_t length, UProperty which); 2912 2913 /** 2914 * Returns a frozen USet for a binary property. 2915 * The library retains ownership over the returned object. 2916 * Sets an error code if the property number is not one for a binary property. 2917 * 2918 * The returned set contains all code points for which the property is true. 2919 * 2920 * @param property UCHAR_BINARY_START..UCHAR_BINARY_LIMIT-1 2921 * @param pErrorCode an in/out ICU UErrorCode 2922 * @return the property as a set 2923 * @see UProperty 2924 * @see u_hasBinaryProperty 2925 * @see Unicode::fromUSet 2926 * @stable ICU 63 2927 */ 2928 U_CAPI const USet * U_EXPORT2 2929 u_getBinaryPropertySet(UProperty property, UErrorCode *pErrorCode); 2930 2931 /** 2932 * Check if a code point has the Alphabetic Unicode property. 2933 * Same as u_hasBinaryProperty(c, UCHAR_ALPHABETIC). 2934 * This is different from u_isalpha! 2935 * @param c Code point to test 2936 * @return true if the code point has the Alphabetic Unicode property, false otherwise 2937 * 2938 * @see UCHAR_ALPHABETIC 2939 * @see u_isalpha 2940 * @see u_hasBinaryProperty 2941 * @stable ICU 2.1 2942 */ 2943 U_CAPI UBool U_EXPORT2 2944 u_isUAlphabetic(UChar32 c); 2945 2946 /** 2947 * Check if a code point has the Lowercase Unicode property. 2948 * Same as u_hasBinaryProperty(c, UCHAR_LOWERCASE). 2949 * This is different from u_islower! 2950 * @param c Code point to test 2951 * @return true if the code point has the Lowercase Unicode property, false otherwise 2952 * 2953 * @see UCHAR_LOWERCASE 2954 * @see u_islower 2955 * @see u_hasBinaryProperty 2956 * @stable ICU 2.1 2957 */ 2958 U_CAPI UBool U_EXPORT2 2959 u_isULowercase(UChar32 c); 2960 2961 /** 2962 * Check if a code point has the Uppercase Unicode property. 2963 * Same as u_hasBinaryProperty(c, UCHAR_UPPERCASE). 2964 * This is different from u_isupper! 2965 * @param c Code point to test 2966 * @return true if the code point has the Uppercase Unicode property, false otherwise 2967 * 2968 * @see UCHAR_UPPERCASE 2969 * @see u_isupper 2970 * @see u_hasBinaryProperty 2971 * @stable ICU 2.1 2972 */ 2973 U_CAPI UBool U_EXPORT2 2974 u_isUUppercase(UChar32 c); 2975 2976 /** 2977 * Check if a code point has the White_Space Unicode property. 2978 * Same as u_hasBinaryProperty(c, UCHAR_WHITE_SPACE). 2979 * This is different from both u_isspace and u_isWhitespace! 2980 * 2981 * Note: There are several ICU whitespace functions; please see the uchar.h 2982 * file documentation for a detailed comparison. 2983 * 2984 * @param c Code point to test 2985 * @return true if the code point has the White_Space Unicode property, false otherwise. 2986 * 2987 * @see UCHAR_WHITE_SPACE 2988 * @see u_isWhitespace 2989 * @see u_isspace 2990 * @see u_isJavaSpaceChar 2991 * @see u_hasBinaryProperty 2992 * @stable ICU 2.1 2993 */ 2994 U_CAPI UBool U_EXPORT2 2995 u_isUWhiteSpace(UChar32 c); 2996 2997 /** 2998 * Get the property value for an enumerated or integer Unicode property for a code point. 2999 * Also returns binary and mask property values. 3000 * 3001 * Unicode, especially in version 3.2, defines many more properties than the 3002 * original set in UnicodeData.txt. 3003 * 3004 * The properties APIs are intended to reflect Unicode properties as defined 3005 * in the Unicode Character Database (UCD) and Unicode Technical Reports (UTR). 3006 * For details about the properties see http://www.unicode.org/ . 3007 * For names of Unicode properties see the UCD file PropertyAliases.txt. 3008 * 3009 * Sample usage: 3010 * UEastAsianWidth ea=(UEastAsianWidth)u_getIntPropertyValue(c, UCHAR_EAST_ASIAN_WIDTH); 3011 * UBool b=(UBool)u_getIntPropertyValue(c, UCHAR_IDEOGRAPHIC); 3012 * 3013 * @param c Code point to test. 3014 * @param which UProperty selector constant, identifies which property to check. 3015 * Must be UCHAR_BINARY_START<=which<UCHAR_BINARY_LIMIT 3016 * or UCHAR_INT_START<=which<UCHAR_INT_LIMIT 3017 * or UCHAR_MASK_START<=which<UCHAR_MASK_LIMIT. 3018 * @return Numeric value that is directly the property value or, 3019 * for enumerated properties, corresponds to the numeric value of the enumerated 3020 * constant of the respective property value enumeration type 3021 * (cast to enum type if necessary). 3022 * Returns 0 or 1 (for false/true) for binary Unicode properties. 3023 * Returns a bit-mask for mask properties. 3024 * Returns 0 if 'which' is out of bounds or if the Unicode version 3025 * does not have data for the property at all, or not for this code point. 3026 * 3027 * @see UProperty 3028 * @see u_hasBinaryProperty 3029 * @see u_getIntPropertyMinValue 3030 * @see u_getIntPropertyMaxValue 3031 * @see u_getIntPropertyMap 3032 * @see u_getUnicodeVersion 3033 * @stable ICU 2.2 3034 */ 3035 U_CAPI int32_t U_EXPORT2 3036 u_getIntPropertyValue(UChar32 c, UProperty which); 3037 3038 /** 3039 * Get the minimum value for an enumerated/integer/binary Unicode property. 3040 * Can be used together with u_getIntPropertyMaxValue 3041 * to allocate arrays of UnicodeSet or similar. 3042 * 3043 * @param which UProperty selector constant, identifies which binary property to check. 3044 * Must be UCHAR_BINARY_START<=which<UCHAR_BINARY_LIMIT 3045 * or UCHAR_INT_START<=which<UCHAR_INT_LIMIT. 3046 * @return Minimum value returned by u_getIntPropertyValue for a Unicode property. 3047 * 0 if the property selector is out of range. 3048 * 3049 * @see UProperty 3050 * @see u_hasBinaryProperty 3051 * @see u_getUnicodeVersion 3052 * @see u_getIntPropertyMaxValue 3053 * @see u_getIntPropertyValue 3054 * @stable ICU 2.2 3055 */ 3056 U_CAPI int32_t U_EXPORT2 3057 u_getIntPropertyMinValue(UProperty which); 3058 3059 /** 3060 * Get the maximum value for an enumerated/integer/binary Unicode property. 3061 * Can be used together with u_getIntPropertyMinValue 3062 * to allocate arrays of UnicodeSet or similar. 3063 * 3064 * Examples for min/max values (for Unicode 3.2): 3065 * 3066 * - UCHAR_BIDI_CLASS: 0/18 (U_LEFT_TO_RIGHT/U_BOUNDARY_NEUTRAL) 3067 * - UCHAR_SCRIPT: 0/45 (USCRIPT_COMMON/USCRIPT_TAGBANWA) 3068 * - UCHAR_IDEOGRAPHIC: 0/1 (false/true) 3069 * 3070 * For undefined UProperty constant values, min/max values will be 0/-1. 3071 * 3072 * @param which UProperty selector constant, identifies which binary property to check. 3073 * Must be UCHAR_BINARY_START<=which<UCHAR_BINARY_LIMIT 3074 * or UCHAR_INT_START<=which<UCHAR_INT_LIMIT. 3075 * @return Maximum value returned by u_getIntPropertyValue for a Unicode property. 3076 * <=0 if the property selector is out of range. 3077 * 3078 * @see UProperty 3079 * @see u_hasBinaryProperty 3080 * @see u_getUnicodeVersion 3081 * @see u_getIntPropertyMaxValue 3082 * @see u_getIntPropertyValue 3083 * @stable ICU 2.2 3084 */ 3085 U_CAPI int32_t U_EXPORT2 3086 u_getIntPropertyMaxValue(UProperty which); 3087 3088 /** 3089 * Returns an immutable UCPMap for an enumerated/catalog/int-valued property. 3090 * The library retains ownership over the returned object. 3091 * Sets an error code if the property number is not one for an "int property". 3092 * 3093 * The returned object maps all Unicode code points to their values for that property. 3094 * For documentation of the integer values see u_getIntPropertyValue(). 3095 * 3096 * @param property UCHAR_INT_START..UCHAR_INT_LIMIT-1 3097 * @param pErrorCode an in/out ICU UErrorCode 3098 * @return the property as a map 3099 * @see UProperty 3100 * @see u_getIntPropertyValue 3101 * @stable ICU 63 3102 */ 3103 U_CAPI const UCPMap * U_EXPORT2 3104 u_getIntPropertyMap(UProperty property, UErrorCode *pErrorCode); 3105 3106 /** 3107 * Get the numeric value for a Unicode code point as defined in the 3108 * Unicode Character Database. 3109 * 3110 * A "double" return type is necessary because 3111 * some numeric values are fractions, negative, or too large for int32_t. 3112 * 3113 * For characters without any numeric values in the Unicode Character Database, 3114 * this function will return U_NO_NUMERIC_VALUE. 3115 * Note: This is different from the Unicode Standard which specifies NaN as the default value. 3116 * (NaN is not available on all platforms.) 3117 * 3118 * Similar to java.lang.Character.getNumericValue(), but u_getNumericValue() 3119 * also supports negative values, large values, and fractions, 3120 * while Java's getNumericValue() returns values 10..35 for ASCII letters. 3121 * 3122 * @param c Code point to get the numeric value for. 3123 * @return Numeric value of c, or U_NO_NUMERIC_VALUE if none is defined. 3124 * 3125 * @see U_NO_NUMERIC_VALUE 3126 * @stable ICU 2.2 3127 */ 3128 U_CAPI double U_EXPORT2 3129 u_getNumericValue(UChar32 c); 3130 3131 /** 3132 * Special value that is returned by u_getNumericValue when 3133 * no numeric value is defined for a code point. 3134 * 3135 * @see u_getNumericValue 3136 * @stable ICU 2.2 3137 */ 3138 #define U_NO_NUMERIC_VALUE ((double)-123456789.) 3139 3140 /** 3141 * Determines whether the specified code point has the general category "Ll" 3142 * (lowercase letter). 3143 * 3144 * Same as java.lang.Character.isLowerCase(). 3145 * 3146 * This misses some characters that are also lowercase but 3147 * have a different general category value. 3148 * In order to include those, use UCHAR_LOWERCASE. 3149 * 3150 * In addition to being equivalent to a Java function, this also serves 3151 * as a C/POSIX migration function. 3152 * See the comments about C/POSIX character classification functions in the 3153 * documentation at the top of this header file. 3154 * 3155 * @param c the code point to be tested 3156 * @return true if the code point is an Ll lowercase letter 3157 * 3158 * @see UCHAR_LOWERCASE 3159 * @see u_isupper 3160 * @see u_istitle 3161 * @stable ICU 2.0 3162 */ 3163 U_CAPI UBool U_EXPORT2 3164 u_islower(UChar32 c); 3165 3166 /** 3167 * Determines whether the specified code point has the general category "Lu" 3168 * (uppercase letter). 3169 * 3170 * Same as java.lang.Character.isUpperCase(). 3171 * 3172 * This misses some characters that are also uppercase but 3173 * have a different general category value. 3174 * In order to include those, use UCHAR_UPPERCASE. 3175 * 3176 * In addition to being equivalent to a Java function, this also serves 3177 * as a C/POSIX migration function. 3178 * See the comments about C/POSIX character classification functions in the 3179 * documentation at the top of this header file. 3180 * 3181 * @param c the code point to be tested 3182 * @return true if the code point is an Lu uppercase letter 3183 * 3184 * @see UCHAR_UPPERCASE 3185 * @see u_islower 3186 * @see u_istitle 3187 * @see u_tolower 3188 * @stable ICU 2.0 3189 */ 3190 U_CAPI UBool U_EXPORT2 3191 u_isupper(UChar32 c); 3192 3193 /** 3194 * Determines whether the specified code point is a titlecase letter. 3195 * True for general category "Lt" (titlecase letter). 3196 * 3197 * Same as java.lang.Character.isTitleCase(). 3198 * 3199 * @param c the code point to be tested 3200 * @return true if the code point is an Lt titlecase letter 3201 * 3202 * @see u_isupper 3203 * @see u_islower 3204 * @see u_totitle 3205 * @stable ICU 2.0 3206 */ 3207 U_CAPI UBool U_EXPORT2 3208 u_istitle(UChar32 c); 3209 3210 /** 3211 * Determines whether the specified code point is a digit character according to Java. 3212 * True for characters with general category "Nd" (decimal digit numbers). 3213 * Beginning with Unicode 4, this is the same as 3214 * testing for the Numeric_Type of Decimal. 3215 * 3216 * Same as java.lang.Character.isDigit(). 3217 * 3218 * In addition to being equivalent to a Java function, this also serves 3219 * as a C/POSIX migration function. 3220 * See the comments about C/POSIX character classification functions in the 3221 * documentation at the top of this header file. 3222 * 3223 * @param c the code point to be tested 3224 * @return true if the code point is a digit character according to Character.isDigit() 3225 * 3226 * @stable ICU 2.0 3227 */ 3228 U_CAPI UBool U_EXPORT2 3229 u_isdigit(UChar32 c); 3230 3231 /** 3232 * Determines whether the specified code point is a letter character. 3233 * True for general categories "L" (letters). 3234 * 3235 * Same as java.lang.Character.isLetter(). 3236 * 3237 * In addition to being equivalent to a Java function, this also serves 3238 * as a C/POSIX migration function. 3239 * See the comments about C/POSIX character classification functions in the 3240 * documentation at the top of this header file. 3241 * 3242 * @param c the code point to be tested 3243 * @return true if the code point is a letter character 3244 * 3245 * @see u_isdigit 3246 * @see u_isalnum 3247 * @stable ICU 2.0 3248 */ 3249 U_CAPI UBool U_EXPORT2 3250 u_isalpha(UChar32 c); 3251 3252 /** 3253 * Determines whether the specified code point is an alphanumeric character 3254 * (letter or digit) according to Java. 3255 * True for characters with general categories 3256 * "L" (letters) and "Nd" (decimal digit numbers). 3257 * 3258 * Same as java.lang.Character.isLetterOrDigit(). 3259 * 3260 * In addition to being equivalent to a Java function, this also serves 3261 * as a C/POSIX migration function. 3262 * See the comments about C/POSIX character classification functions in the 3263 * documentation at the top of this header file. 3264 * 3265 * @param c the code point to be tested 3266 * @return true if the code point is an alphanumeric character according to Character.isLetterOrDigit() 3267 * 3268 * @stable ICU 2.0 3269 */ 3270 U_CAPI UBool U_EXPORT2 3271 u_isalnum(UChar32 c); 3272 3273 /** 3274 * Determines whether the specified code point is a hexadecimal digit. 3275 * This is equivalent to u_digit(c, 16)>=0. 3276 * True for characters with general category "Nd" (decimal digit numbers) 3277 * as well as Latin letters a-f and A-F in both ASCII and Fullwidth ASCII. 3278 * (That is, for letters with code points 3279 * 0041..0046, 0061..0066, FF21..FF26, FF41..FF46.) 3280 * 3281 * In order to narrow the definition of hexadecimal digits to only ASCII 3282 * characters, use (c<=0x7f && u_isxdigit(c)). 3283 * 3284 * This is a C/POSIX migration function. 3285 * See the comments about C/POSIX character classification functions in the 3286 * documentation at the top of this header file. 3287 * 3288 * @param c the code point to be tested 3289 * @return true if the code point is a hexadecimal digit 3290 * 3291 * @stable ICU 2.6 3292 */ 3293 U_CAPI UBool U_EXPORT2 3294 u_isxdigit(UChar32 c); 3295 3296 /** 3297 * Determines whether the specified code point is a punctuation character. 3298 * True for characters with general categories "P" (punctuation). 3299 * 3300 * This is a C/POSIX migration function. 3301 * See the comments about C/POSIX character classification functions in the 3302 * documentation at the top of this header file. 3303 * 3304 * @param c the code point to be tested 3305 * @return true if the code point is a punctuation character 3306 * 3307 * @stable ICU 2.6 3308 */ 3309 U_CAPI UBool U_EXPORT2 3310 u_ispunct(UChar32 c); 3311 3312 /** 3313 * Determines whether the specified code point is a "graphic" character 3314 * (printable, excluding spaces). 3315 * true for all characters except those with general categories 3316 * "Cc" (control codes), "Cf" (format controls), "Cs" (surrogates), 3317 * "Cn" (unassigned), and "Z" (separators). 3318 * 3319 * This is a C/POSIX migration function. 3320 * See the comments about C/POSIX character classification functions in the 3321 * documentation at the top of this header file. 3322 * 3323 * @param c the code point to be tested 3324 * @return true if the code point is a "graphic" character 3325 * 3326 * @stable ICU 2.6 3327 */ 3328 U_CAPI UBool U_EXPORT2 3329 u_isgraph(UChar32 c); 3330 3331 /** 3332 * Determines whether the specified code point is a "blank" or "horizontal space", 3333 * a character that visibly separates words on a line. 3334 * The following are equivalent definitions: 3335 * 3336 * true for Unicode White_Space characters except for "vertical space controls" 3337 * where "vertical space controls" are the following characters: 3338 * U+000A (LF) U+000B (VT) U+000C (FF) U+000D (CR) U+0085 (NEL) U+2028 (LS) U+2029 (PS) 3339 * 3340 * same as 3341 * 3342 * true for U+0009 (TAB) and characters with general category "Zs" (space separators). 3343 * 3344 * Note: There are several ICU whitespace functions; please see the uchar.h 3345 * file documentation for a detailed comparison. 3346 * 3347 * This is a C/POSIX migration function. 3348 * See the comments about C/POSIX character classification functions in the 3349 * documentation at the top of this header file. 3350 * 3351 * @param c the code point to be tested 3352 * @return true if the code point is a "blank" 3353 * 3354 * @stable ICU 2.6 3355 */ 3356 U_CAPI UBool U_EXPORT2 3357 u_isblank(UChar32 c); 3358 3359 /** 3360 * Determines whether the specified code point is "defined", 3361 * which usually means that it is assigned a character. 3362 * True for general categories other than "Cn" (other, not assigned), 3363 * i.e., true for all code points mentioned in UnicodeData.txt. 3364 * 3365 * Note that non-character code points (e.g., U+FDD0) are not "defined" 3366 * (they are Cn), but surrogate code points are "defined" (Cs). 3367 * 3368 * Same as java.lang.Character.isDefined(). 3369 * 3370 * @param c the code point to be tested 3371 * @return true if the code point is assigned a character 3372 * 3373 * @see u_isdigit 3374 * @see u_isalpha 3375 * @see u_isalnum 3376 * @see u_isupper 3377 * @see u_islower 3378 * @see u_istitle 3379 * @stable ICU 2.0 3380 */ 3381 U_CAPI UBool U_EXPORT2 3382 u_isdefined(UChar32 c); 3383 3384 /** 3385 * Determines if the specified character is a space character or not. 3386 * 3387 * Note: There are several ICU whitespace functions; please see the uchar.h 3388 * file documentation for a detailed comparison. 3389 * 3390 * This is a C/POSIX migration function. 3391 * See the comments about C/POSIX character classification functions in the 3392 * documentation at the top of this header file. 3393 * 3394 * @param c the character to be tested 3395 * @return true if the character is a space character; false otherwise. 3396 * 3397 * @see u_isJavaSpaceChar 3398 * @see u_isWhitespace 3399 * @see u_isUWhiteSpace 3400 * @stable ICU 2.0 3401 */ 3402 U_CAPI UBool U_EXPORT2 3403 u_isspace(UChar32 c); 3404 3405 /** 3406 * Determine if the specified code point is a space character according to Java. 3407 * True for characters with general categories "Z" (separators), 3408 * which does not include control codes (e.g., TAB or Line Feed). 3409 * 3410 * Same as java.lang.Character.isSpaceChar(). 3411 * 3412 * Note: There are several ICU whitespace functions; please see the uchar.h 3413 * file documentation for a detailed comparison. 3414 * 3415 * @param c the code point to be tested 3416 * @return true if the code point is a space character according to Character.isSpaceChar() 3417 * 3418 * @see u_isspace 3419 * @see u_isWhitespace 3420 * @see u_isUWhiteSpace 3421 * @stable ICU 2.6 3422 */ 3423 U_CAPI UBool U_EXPORT2 3424 u_isJavaSpaceChar(UChar32 c); 3425 3426 /** 3427 * Determines if the specified code point is a whitespace character according to Java/ICU. 3428 * A character is considered to be a Java whitespace character if and only 3429 * if it satisfies one of the following criteria: 3430 * 3431 * - It is a Unicode Separator character (categories "Z" = "Zs" or "Zl" or "Zp"), but is not 3432 * also a non-breaking space (U+00A0 NBSP or U+2007 Figure Space or U+202F Narrow NBSP). 3433 * - It is U+0009 HORIZONTAL TABULATION. 3434 * - It is U+000A LINE FEED. 3435 * - It is U+000B VERTICAL TABULATION. 3436 * - It is U+000C FORM FEED. 3437 * - It is U+000D CARRIAGE RETURN. 3438 * - It is U+001C FILE SEPARATOR. 3439 * - It is U+001D GROUP SEPARATOR. 3440 * - It is U+001E RECORD SEPARATOR. 3441 * - It is U+001F UNIT SEPARATOR. 3442 * 3443 * This API tries to sync with the semantics of Java's 3444 * java.lang.Character.isWhitespace(), but it may not return 3445 * the exact same results because of the Unicode version 3446 * difference. 3447 * 3448 * Note: Unicode 4.0.1 changed U+200B ZERO WIDTH SPACE from a Space Separator (Zs) 3449 * to a Format Control (Cf). Since then, isWhitespace(0x200b) returns false. 3450 * See http://www.unicode.org/versions/Unicode4.0.1/ 3451 * 3452 * Note: There are several ICU whitespace functions; please see the uchar.h 3453 * file documentation for a detailed comparison. 3454 * 3455 * @param c the code point to be tested 3456 * @return true if the code point is a whitespace character according to Java/ICU 3457 * 3458 * @see u_isspace 3459 * @see u_isJavaSpaceChar 3460 * @see u_isUWhiteSpace 3461 * @stable ICU 2.0 3462 */ 3463 U_CAPI UBool U_EXPORT2 3464 u_isWhitespace(UChar32 c); 3465 3466 /** 3467 * Determines whether the specified code point is a control character 3468 * (as defined by this function). 3469 * A control character is one of the following: 3470 * - ISO 8-bit control character (U+0000..U+001f and U+007f..U+009f) 3471 * - U_CONTROL_CHAR (Cc) 3472 * - U_FORMAT_CHAR (Cf) 3473 * - U_LINE_SEPARATOR (Zl) 3474 * - U_PARAGRAPH_SEPARATOR (Zp) 3475 * 3476 * This is a C/POSIX migration function. 3477 * See the comments about C/POSIX character classification functions in the 3478 * documentation at the top of this header file. 3479 * 3480 * @param c the code point to be tested 3481 * @return true if the code point is a control character 3482 * 3483 * @see UCHAR_DEFAULT_IGNORABLE_CODE_POINT 3484 * @see u_isprint 3485 * @stable ICU 2.0 3486 */ 3487 U_CAPI UBool U_EXPORT2 3488 u_iscntrl(UChar32 c); 3489 3490 /** 3491 * Determines whether the specified code point is an ISO control code. 3492 * True for U+0000..U+001f and U+007f..U+009f (general category "Cc"). 3493 * 3494 * Same as java.lang.Character.isISOControl(). 3495 * 3496 * @param c the code point to be tested 3497 * @return true if the code point is an ISO control code 3498 * 3499 * @see u_iscntrl 3500 * @stable ICU 2.6 3501 */ 3502 U_CAPI UBool U_EXPORT2 3503 u_isISOControl(UChar32 c); 3504 3505 /** 3506 * Determines whether the specified code point is a printable character. 3507 * True for general categories <em>other</em> than "C" (controls). 3508 * 3509 * This is a C/POSIX migration function. 3510 * See the comments about C/POSIX character classification functions in the 3511 * documentation at the top of this header file. 3512 * 3513 * @param c the code point to be tested 3514 * @return true if the code point is a printable character 3515 * 3516 * @see UCHAR_DEFAULT_IGNORABLE_CODE_POINT 3517 * @see u_iscntrl 3518 * @stable ICU 2.0 3519 */ 3520 U_CAPI UBool U_EXPORT2 3521 u_isprint(UChar32 c); 3522 3523 /** 3524 * Non-standard: Determines whether the specified code point is a base character. 3525 * True for general categories "L" (letters), "N" (numbers), 3526 * "Mc" (spacing combining marks), and "Me" (enclosing marks). 3527 * 3528 * Note that this is different from the Unicode Standard definition in 3529 * chapter 3.6, conformance clause D51 “Base character”, 3530 * which defines base characters as the code points with general categories 3531 * Letter (L), Number (N), Punctuation (P), Symbol (S), or Space Separator (Zs). 3532 * 3533 * @param c the code point to be tested 3534 * @return true if the code point is a base character according to this function 3535 * 3536 * @see u_isalpha 3537 * @see u_isdigit 3538 * @stable ICU 2.0 3539 */ 3540 U_CAPI UBool U_EXPORT2 3541 u_isbase(UChar32 c); 3542 3543 /** 3544 * Returns the bidirectional category value for the code point, 3545 * which is used in the Unicode bidirectional algorithm 3546 * (UAX #9 http://www.unicode.org/reports/tr9/). 3547 * Note that some <em>unassigned</em> code points have bidi values 3548 * of R or AL because they are in blocks that are reserved 3549 * for Right-To-Left scripts. 3550 * 3551 * Same as java.lang.Character.getDirectionality() 3552 * 3553 * @param c the code point to be tested 3554 * @return the bidirectional category (UCharDirection) value 3555 * 3556 * @see UCharDirection 3557 * @stable ICU 2.0 3558 */ 3559 U_CAPI UCharDirection U_EXPORT2 3560 u_charDirection(UChar32 c); 3561 3562 /** 3563 * Determines whether the code point has the Bidi_Mirrored property. 3564 * This property is set for characters that are commonly used in 3565 * Right-To-Left contexts and need to be displayed with a "mirrored" 3566 * glyph. 3567 * 3568 * Same as java.lang.Character.isMirrored(). 3569 * Same as UCHAR_BIDI_MIRRORED 3570 * 3571 * @param c the code point to be tested 3572 * @return true if the character has the Bidi_Mirrored property 3573 * 3574 * @see UCHAR_BIDI_MIRRORED 3575 * @stable ICU 2.0 3576 */ 3577 U_CAPI UBool U_EXPORT2 3578 u_isMirrored(UChar32 c); 3579 3580 /** 3581 * Maps the specified character to a "mirror-image" character. 3582 * For characters with the Bidi_Mirrored property, implementations 3583 * sometimes need a "poor man's" mapping to another Unicode 3584 * character (code point) such that the default glyph may serve 3585 * as the mirror-image of the default glyph of the specified 3586 * character. This is useful for text conversion to and from 3587 * codepages with visual order, and for displays without glyph 3588 * selection capabilities. 3589 * 3590 * @param c the code point to be mapped 3591 * @return another Unicode code point that may serve as a mirror-image 3592 * substitute, or c itself if there is no such mapping or c 3593 * does not have the Bidi_Mirrored property 3594 * 3595 * @see UCHAR_BIDI_MIRRORED 3596 * @see u_isMirrored 3597 * @stable ICU 2.0 3598 */ 3599 U_CAPI UChar32 U_EXPORT2 3600 u_charMirror(UChar32 c); 3601 3602 /** 3603 * Maps the specified character to its paired bracket character. 3604 * For Bidi_Paired_Bracket_Type!=None, this is the same as u_charMirror(). 3605 * Otherwise c itself is returned. 3606 * See http://www.unicode.org/reports/tr9/ 3607 * 3608 * @param c the code point to be mapped 3609 * @return the paired bracket code point, 3610 * or c itself if there is no such mapping 3611 * (Bidi_Paired_Bracket_Type=None) 3612 * 3613 * @see UCHAR_BIDI_PAIRED_BRACKET 3614 * @see UCHAR_BIDI_PAIRED_BRACKET_TYPE 3615 * @see u_charMirror 3616 * @stable ICU 52 3617 */ 3618 U_CAPI UChar32 U_EXPORT2 3619 u_getBidiPairedBracket(UChar32 c); 3620 3621 /** 3622 * Returns the general category value for the code point. 3623 * 3624 * Same as java.lang.Character.getType(). 3625 * 3626 * @param c the code point to be tested 3627 * @return the general category (UCharCategory) value 3628 * 3629 * @see UCharCategory 3630 * @stable ICU 2.0 3631 */ 3632 U_CAPI int8_t U_EXPORT2 3633 u_charType(UChar32 c); 3634 3635 /** 3636 * Get a single-bit bit set for the general category of a character. 3637 * This bit set can be compared bitwise with U_GC_SM_MASK, U_GC_L_MASK, etc. 3638 * Same as U_MASK(u_charType(c)). 3639 * 3640 * @param c the code point to be tested 3641 * @return a single-bit mask corresponding to the general category (UCharCategory) value 3642 * 3643 * @see u_charType 3644 * @see UCharCategory 3645 * @see U_GC_CN_MASK 3646 * @stable ICU 2.1 3647 */ 3648 #define U_GET_GC_MASK(c) U_MASK(u_charType(c)) 3649 3650 /** 3651 * Callback from u_enumCharTypes(), is called for each contiguous range 3652 * of code points c (where start<=c<limit) 3653 * with the same Unicode general category ("character type"). 3654 * 3655 * The callback function can stop the enumeration by returning false. 3656 * 3657 * @param context an opaque pointer, as passed into utrie_enum() 3658 * @param start the first code point in a contiguous range with value 3659 * @param limit one past the last code point in a contiguous range with value 3660 * @param type the general category for all code points in [start..limit[ 3661 * @return false to stop the enumeration 3662 * 3663 * @stable ICU 2.1 3664 * @see UCharCategory 3665 * @see u_enumCharTypes 3666 */ 3667 typedef UBool U_CALLCONV 3668 UCharEnumTypeRange(const void *context, UChar32 start, UChar32 limit, UCharCategory type); 3669 3670 /** 3671 * Enumerate efficiently all code points with their Unicode general categories. 3672 * 3673 * This is useful for building data structures (e.g., UnicodeSet's), 3674 * for enumerating all assigned code points (type!=U_UNASSIGNED), etc. 3675 * 3676 * For each contiguous range of code points with a given general category ("character type"), 3677 * the UCharEnumTypeRange function is called. 3678 * Adjacent ranges have different types. 3679 * The Unicode Standard guarantees that the numeric value of the type is 0..31. 3680 * 3681 * @param enumRange a pointer to a function that is called for each contiguous range 3682 * of code points with the same general category 3683 * @param context an opaque pointer that is passed on to the callback function 3684 * 3685 * @stable ICU 2.1 3686 * @see UCharCategory 3687 * @see UCharEnumTypeRange 3688 */ 3689 U_CAPI void U_EXPORT2 3690 u_enumCharTypes(UCharEnumTypeRange *enumRange, const void *context); 3691 3692 #if !UCONFIG_NO_NORMALIZATION 3693 3694 /** 3695 * Returns the combining class of the code point as specified in UnicodeData.txt. 3696 * 3697 * @param c the code point of the character 3698 * @return the combining class of the character 3699 * @stable ICU 2.0 3700 */ 3701 U_CAPI uint8_t U_EXPORT2 3702 u_getCombiningClass(UChar32 c); 3703 3704 #endif 3705 3706 /** 3707 * Returns the decimal digit value of a decimal digit character. 3708 * Such characters have the general category "Nd" (decimal digit numbers) 3709 * and a Numeric_Type of Decimal. 3710 * 3711 * Unlike ICU releases before 2.6, no digit values are returned for any 3712 * Han characters because Han number characters are often used with a special 3713 * Chinese-style number format (with characters for powers of 10 in between) 3714 * instead of in decimal-positional notation. 3715 * Unicode 4 explicitly assigns Han number characters the Numeric_Type 3716 * Numeric instead of Decimal. 3717 * See Jitterbug 1483 for more details. 3718 * 3719 * Use u_getIntPropertyValue(c, UCHAR_NUMERIC_TYPE) and u_getNumericValue() 3720 * for complete numeric Unicode properties. 3721 * 3722 * @param c the code point for which to get the decimal digit value 3723 * @return the decimal digit value of c, 3724 * or -1 if c is not a decimal digit character 3725 * 3726 * @see u_getNumericValue 3727 * @stable ICU 2.0 3728 */ 3729 U_CAPI int32_t U_EXPORT2 3730 u_charDigitValue(UChar32 c); 3731 3732 /** 3733 * Returns the Unicode allocation block that contains the character. 3734 * 3735 * @param c the code point to be tested 3736 * @return the block value (UBlockCode) for c 3737 * 3738 * @see UBlockCode 3739 * @stable ICU 2.0 3740 */ 3741 U_CAPI UBlockCode U_EXPORT2 3742 ublock_getCode(UChar32 c); 3743 3744 /** 3745 * Retrieve the name of a Unicode character. 3746 * Depending on <code>nameChoice</code>, the character name written 3747 * into the buffer is the "modern" name or the name that was defined 3748 * in Unicode version 1.0. 3749 * The name contains only "invariant" characters 3750 * like A-Z, 0-9, space, and '-'. 3751 * Unicode 1.0 names are only retrieved if they are different from the modern 3752 * names and if the data file contains the data for them. gennames may or may 3753 * not be called with a command line option to include 1.0 names in unames.dat. 3754 * 3755 * @param code The character (code point) for which to get the name. 3756 * It must be <code>0<=code<=0x10ffff</code>. 3757 * @param nameChoice Selector for which name to get. 3758 * @param buffer Destination address for copying the name. 3759 * The name will always be zero-terminated. 3760 * If there is no name, then the buffer will be set to the empty string. 3761 * @param bufferLength <code>==sizeof(buffer)</code> 3762 * @param pErrorCode Pointer to a UErrorCode variable; 3763 * check for <code>U_SUCCESS()</code> after <code>u_charName()</code> 3764 * returns. 3765 * @return The length of the name, or 0 if there is no name for this character. 3766 * If the bufferLength is less than or equal to the length, then the buffer 3767 * contains the truncated name and the returned length indicates the full 3768 * length of the name. 3769 * The length does not include the zero-termination. 3770 * 3771 * @see UCharNameChoice 3772 * @see u_charFromName 3773 * @see u_enumCharNames 3774 * @stable ICU 2.0 3775 */ 3776 U_CAPI int32_t U_EXPORT2 3777 u_charName(UChar32 code, UCharNameChoice nameChoice, 3778 char *buffer, int32_t bufferLength, 3779 UErrorCode *pErrorCode); 3780 3781 #ifndef U_HIDE_DEPRECATED_API 3782 /** 3783 * Returns an empty string. 3784 * Used to return the ISO 10646 comment for a character. 3785 * The Unicode ISO_Comment property is deprecated and has no values. 3786 * 3787 * @param c The character (code point) for which to get the ISO comment. 3788 * It must be <code>0<=c<=0x10ffff</code>. 3789 * @param dest Destination address for copying the comment. 3790 * The comment will be zero-terminated if possible. 3791 * If there is no comment, then the buffer will be set to the empty string. 3792 * @param destCapacity <code>==sizeof(dest)</code> 3793 * @param pErrorCode Pointer to a UErrorCode variable; 3794 * check for <code>U_SUCCESS()</code> after <code>u_getISOComment()</code> 3795 * returns. 3796 * @return 0 3797 * 3798 * @deprecated ICU 49 3799 */ 3800 U_DEPRECATED int32_t U_EXPORT2 3801 u_getISOComment(UChar32 c, 3802 char *dest, int32_t destCapacity, 3803 UErrorCode *pErrorCode); 3804 #endif /* U_HIDE_DEPRECATED_API */ 3805 3806 /** 3807 * Find a Unicode character by its name and return its code point value. 3808 * The name is matched exactly and completely. 3809 * If the name does not correspond to a code point, <i>pErrorCode</i> 3810 * is set to <code>U_INVALID_CHAR_FOUND</code>. 3811 * A Unicode 1.0 name is matched only if it differs from the modern name. 3812 * Unicode names are all uppercase. Extended names are lowercase followed 3813 * by an uppercase hexadecimal number, and within angle brackets. 3814 * 3815 * @param nameChoice Selector for which name to match. 3816 * @param name The name to match. 3817 * @param pErrorCode Pointer to a UErrorCode variable 3818 * @return The Unicode value of the code point with the given name, 3819 * or an undefined value if there is no such code point. 3820 * 3821 * @see UCharNameChoice 3822 * @see u_charName 3823 * @see u_enumCharNames 3824 * @stable ICU 1.7 3825 */ 3826 U_CAPI UChar32 U_EXPORT2 3827 u_charFromName(UCharNameChoice nameChoice, 3828 const char *name, 3829 UErrorCode *pErrorCode); 3830 3831 /** 3832 * Type of a callback function for u_enumCharNames() that gets called 3833 * for each Unicode character with the code point value and 3834 * the character name. 3835 * If such a function returns false, then the enumeration is stopped. 3836 * 3837 * @param context The context pointer that was passed to u_enumCharNames(). 3838 * @param code The Unicode code point for the character with this name. 3839 * @param nameChoice Selector for which kind of names is enumerated. 3840 * @param name The character's name, zero-terminated. 3841 * @param length The length of the name. 3842 * @return true if the enumeration should continue, false to stop it. 3843 * 3844 * @see UCharNameChoice 3845 * @see u_enumCharNames 3846 * @stable ICU 1.7 3847 */ 3848 typedef UBool U_CALLCONV UEnumCharNamesFn(void *context, 3849 UChar32 code, 3850 UCharNameChoice nameChoice, 3851 const char *name, 3852 int32_t length); 3853 3854 /** 3855 * Enumerate all assigned Unicode characters between the start and limit 3856 * code points (start inclusive, limit exclusive) and call a function 3857 * for each, passing the code point value and the character name. 3858 * For Unicode 1.0 names, only those are enumerated that differ from the 3859 * modern names. 3860 * 3861 * @param start The first code point in the enumeration range. 3862 * @param limit One more than the last code point in the enumeration range 3863 * (the first one after the range). 3864 * @param fn The function that is to be called for each character name. 3865 * @param context An arbitrary pointer that is passed to the function. 3866 * @param nameChoice Selector for which kind of names to enumerate. 3867 * @param pErrorCode Pointer to a UErrorCode variable 3868 * 3869 * @see UCharNameChoice 3870 * @see UEnumCharNamesFn 3871 * @see u_charName 3872 * @see u_charFromName 3873 * @stable ICU 1.7 3874 */ 3875 U_CAPI void U_EXPORT2 3876 u_enumCharNames(UChar32 start, UChar32 limit, 3877 UEnumCharNamesFn *fn, 3878 void *context, 3879 UCharNameChoice nameChoice, 3880 UErrorCode *pErrorCode); 3881 3882 /** 3883 * Return the Unicode name for a given property, as given in the 3884 * Unicode database file PropertyAliases.txt. 3885 * 3886 * In addition, this function maps the property 3887 * UCHAR_GENERAL_CATEGORY_MASK to the synthetic names "gcm" / 3888 * "General_Category_Mask". These names are not in 3889 * PropertyAliases.txt. 3890 * 3891 * @param property UProperty selector other than UCHAR_INVALID_CODE. 3892 * If out of range, NULL is returned. 3893 * 3894 * @param nameChoice selector for which name to get. If out of range, 3895 * NULL is returned. All properties have a long name. Most 3896 * have a short name, but some do not. Unicode allows for 3897 * additional names; if present these will be returned by 3898 * U_LONG_PROPERTY_NAME + i, where i=1, 2,... 3899 * 3900 * @return a pointer to the name, or NULL if either the 3901 * property or the nameChoice is out of range. If a given 3902 * nameChoice returns NULL, then all larger values of 3903 * nameChoice will return NULL, with one exception: if NULL is 3904 * returned for U_SHORT_PROPERTY_NAME, then 3905 * U_LONG_PROPERTY_NAME (and higher) may still return a 3906 * non-NULL value. The returned pointer is valid until 3907 * u_cleanup() is called. 3908 * 3909 * @see UProperty 3910 * @see UPropertyNameChoice 3911 * @stable ICU 2.4 3912 */ 3913 U_CAPI const char* U_EXPORT2 3914 u_getPropertyName(UProperty property, 3915 UPropertyNameChoice nameChoice); 3916 3917 /** 3918 * Return the UProperty enum for a given property name, as specified 3919 * in the Unicode database file PropertyAliases.txt. Short, long, and 3920 * any other variants are recognized. 3921 * 3922 * In addition, this function maps the synthetic names "gcm" / 3923 * "General_Category_Mask" to the property 3924 * UCHAR_GENERAL_CATEGORY_MASK. These names are not in 3925 * PropertyAliases.txt. 3926 * 3927 * @param alias the property name to be matched. The name is compared 3928 * using "loose matching" as described in PropertyAliases.txt. 3929 * 3930 * @return a UProperty enum, or UCHAR_INVALID_CODE if the given name 3931 * does not match any property. 3932 * 3933 * @see UProperty 3934 * @stable ICU 2.4 3935 */ 3936 U_CAPI UProperty U_EXPORT2 3937 u_getPropertyEnum(const char* alias); 3938 3939 /** 3940 * Return the Unicode name for a given property value, as given in the 3941 * Unicode database file PropertyValueAliases.txt. 3942 * 3943 * Note: Some of the names in PropertyValueAliases.txt can only be 3944 * retrieved using UCHAR_GENERAL_CATEGORY_MASK, not 3945 * UCHAR_GENERAL_CATEGORY. These include: "C" / "Other", "L" / 3946 * "Letter", "LC" / "Cased_Letter", "M" / "Mark", "N" / "Number", "P" 3947 * / "Punctuation", "S" / "Symbol", and "Z" / "Separator". 3948 * 3949 * @param property UProperty selector constant. 3950 * Must be UCHAR_BINARY_START<=which<UCHAR_BINARY_LIMIT 3951 * or UCHAR_INT_START<=which<UCHAR_INT_LIMIT 3952 * or UCHAR_MASK_START<=which<UCHAR_MASK_LIMIT. 3953 * If out of range, NULL is returned. 3954 * 3955 * @param value selector for a value for the given property. If out 3956 * of range, NULL is returned. In general, valid values range 3957 * from 0 up to some maximum. There are a few exceptions: 3958 * (1.) UCHAR_BLOCK values begin at the non-zero value 3959 * UBLOCK_BASIC_LATIN. (2.) UCHAR_CANONICAL_COMBINING_CLASS 3960 * values are not contiguous and range from 0..240. (3.) 3961 * UCHAR_GENERAL_CATEGORY_MASK values are not values of 3962 * UCharCategory, but rather mask values produced by 3963 * U_GET_GC_MASK(). This allows grouped categories such as 3964 * [:L:] to be represented. Mask values range 3965 * non-contiguously from 1..U_GC_P_MASK. 3966 * 3967 * @param nameChoice selector for which name to get. If out of range, 3968 * NULL is returned. All values have a long name. Most have 3969 * a short name, but some do not. Unicode allows for 3970 * additional names; if present these will be returned by 3971 * U_LONG_PROPERTY_NAME + i, where i=1, 2,... 3972 3973 * @return a pointer to the name, or NULL if either the 3974 * property or the nameChoice is out of range. If a given 3975 * nameChoice returns NULL, then all larger values of 3976 * nameChoice will return NULL, with one exception: if NULL is 3977 * returned for U_SHORT_PROPERTY_NAME, then 3978 * U_LONG_PROPERTY_NAME (and higher) may still return a 3979 * non-NULL value. The returned pointer is valid until 3980 * u_cleanup() is called. 3981 * 3982 * @see UProperty 3983 * @see UPropertyNameChoice 3984 * @stable ICU 2.4 3985 */ 3986 U_CAPI const char* U_EXPORT2 3987 u_getPropertyValueName(UProperty property, 3988 int32_t value, 3989 UPropertyNameChoice nameChoice); 3990 3991 /** 3992 * Return the property value integer for a given value name, as 3993 * specified in the Unicode database file PropertyValueAliases.txt. 3994 * Short, long, and any other variants are recognized. 3995 * 3996 * Note: Some of the names in PropertyValueAliases.txt will only be 3997 * recognized with UCHAR_GENERAL_CATEGORY_MASK, not 3998 * UCHAR_GENERAL_CATEGORY. These include: "C" / "Other", "L" / 3999 * "Letter", "LC" / "Cased_Letter", "M" / "Mark", "N" / "Number", "P" 4000 * / "Punctuation", "S" / "Symbol", and "Z" / "Separator". 4001 * 4002 * @param property UProperty selector constant. 4003 * Must be UCHAR_BINARY_START<=which<UCHAR_BINARY_LIMIT 4004 * or UCHAR_INT_START<=which<UCHAR_INT_LIMIT 4005 * or UCHAR_MASK_START<=which<UCHAR_MASK_LIMIT. 4006 * If out of range, UCHAR_INVALID_CODE is returned. 4007 * 4008 * @param alias the value name to be matched. The name is compared 4009 * using "loose matching" as described in 4010 * PropertyValueAliases.txt. 4011 * 4012 * @return a value integer or UCHAR_INVALID_CODE if the given name 4013 * does not match any value of the given property, or if the 4014 * property is invalid. Note: UCHAR_GENERAL_CATEGORY_MASK values 4015 * are not values of UCharCategory, but rather mask values 4016 * produced by U_GET_GC_MASK(). This allows grouped 4017 * categories such as [:L:] to be represented. 4018 * 4019 * @see UProperty 4020 * @stable ICU 2.4 4021 */ 4022 U_CAPI int32_t U_EXPORT2 4023 u_getPropertyValueEnum(UProperty property, 4024 const char* alias); 4025 4026 /** 4027 * Determines if the specified character is permissible as the first character in an identifier 4028 * according to UAX #31 Unicode Identifier and Pattern Syntax. 4029 * 4030 * Same as Unicode ID_Start (UCHAR_ID_START). 4031 * 4032 * @param c the code point to be tested 4033 * @return true if the code point may start an identifier 4034 * 4035 * @see UCHAR_ID_START 4036 * @see u_isalpha 4037 * @see u_isIDPart 4038 * @stable ICU 2.0 4039 */ 4040 U_CAPI UBool U_EXPORT2 4041 u_isIDStart(UChar32 c); 4042 4043 /** 4044 * Determines if the specified character is permissible as a non-initial character of an identifier 4045 * according to UAX #31 Unicode Identifier and Pattern Syntax. 4046 * 4047 * Same as Unicode ID_Continue (UCHAR_ID_CONTINUE). 4048 * 4049 * @param c the code point to be tested 4050 * @return true if the code point may occur as a non-initial character of an identifier 4051 * 4052 * @see UCHAR_ID_CONTINUE 4053 * @see u_isIDStart 4054 * @see u_isIDIgnorable 4055 * @stable ICU 2.0 4056 */ 4057 U_CAPI UBool U_EXPORT2 4058 u_isIDPart(UChar32 c); 4059 4060 #ifndef U_HIDE_DRAFT_API 4061 /** 4062 * Does the set of Identifier_Type values code point c contain the given type? 4063 * 4064 * Used for UTS #39 General Security Profile for Identifiers 4065 * (https://www.unicode.org/reports/tr39/#General_Security_Profile). 4066 * 4067 * Each code point maps to a <i>set</i> of UIdentifierType values. 4068 * 4069 * @param c code point 4070 * @param type Identifier_Type to check 4071 * @return true if type is in Identifier_Type(c) 4072 * @draft ICU 75 4073 */ 4074 U_CAPI bool U_EXPORT2 4075 u_hasIDType(UChar32 c, UIdentifierType type); 4076 4077 /** 4078 * Writes code point c's Identifier_Type as a list of UIdentifierType values 4079 * to the output types array and returns the number of types. 4080 * 4081 * Used for UTS #39 General Security Profile for Identifiers 4082 * (https://www.unicode.org/reports/tr39/#General_Security_Profile). 4083 * 4084 * Each code point maps to a <i>set</i> of UIdentifierType values. 4085 * There is always at least one type. 4086 * The order of output values is undefined. 4087 * Each type is output at most once; 4088 * there cannot be more output values than UIdentifierType constants. 4089 * In addition, only some of the types can be combined with others, 4090 * and usually only a small number of types occur together. 4091 * Future versions might add additional types. 4092 * See UTS #39 and its data files for details. 4093 * 4094 * If there are more than capacity types to be written, then 4095 * U_BUFFER_OVERFLOW_ERROR is set and the number of types is returned. 4096 * (Usual ICU buffer handling behavior.) 4097 * 4098 * @param c code point 4099 * @param types output array 4100 * @param capacity capacity of the array 4101 * @param pErrorCode Standard ICU error code. Its input value must 4102 * pass the U_SUCCESS() test, or else the function returns 4103 * immediately. Check for U_FAILURE() on output or use with 4104 * function chaining. (See User Guide for details.) 4105 * @return number of values in c's Identifier_Type, 4106 * written to types unless U_BUFFER_OVERFLOW_ERROR indicates insufficient capacity 4107 * @draft ICU 75 4108 */ 4109 U_CAPI int32_t U_EXPORT2 4110 u_getIDTypes(UChar32 c, UIdentifierType *types, int32_t capacity, UErrorCode *pErrorCode); 4111 #endif // U_HIDE_DRAFT_API 4112 4113 /** 4114 * Determines if the specified character should be regarded 4115 * as an ignorable character in an identifier, 4116 * according to Java. 4117 * True for characters with general category "Cf" (format controls) as well as 4118 * non-whitespace ISO controls 4119 * (U+0000..U+0008, U+000E..U+001B, U+007F..U+009F). 4120 * 4121 * Same as java.lang.Character.isIdentifierIgnorable(). 4122 * 4123 * Note that Unicode just recommends to ignore Cf (format controls). 4124 * 4125 * @param c the code point to be tested 4126 * @return true if the code point is ignorable in identifiers according to Java 4127 * 4128 * @see UCHAR_DEFAULT_IGNORABLE_CODE_POINT 4129 * @see u_isIDStart 4130 * @see u_isIDPart 4131 * @stable ICU 2.0 4132 */ 4133 U_CAPI UBool U_EXPORT2 4134 u_isIDIgnorable(UChar32 c); 4135 4136 /** 4137 * Determines if the specified character is permissible as the 4138 * first character in a Java identifier. 4139 * In addition to u_isIDStart(c), true for characters with 4140 * general categories "Sc" (currency symbols) and "Pc" (connecting punctuation). 4141 * 4142 * Same as java.lang.Character.isJavaIdentifierStart(). 4143 * 4144 * @param c the code point to be tested 4145 * @return true if the code point may start a Java identifier 4146 * 4147 * @see u_isJavaIDPart 4148 * @see u_isalpha 4149 * @see u_isIDStart 4150 * @stable ICU 2.0 4151 */ 4152 U_CAPI UBool U_EXPORT2 4153 u_isJavaIDStart(UChar32 c); 4154 4155 /** 4156 * Determines if the specified character is permissible 4157 * in a Java identifier. 4158 * In addition to u_isIDPart(c), true for characters with 4159 * general category "Sc" (currency symbols). 4160 * 4161 * Same as java.lang.Character.isJavaIdentifierPart(). 4162 * 4163 * @param c the code point to be tested 4164 * @return true if the code point may occur in a Java identifier 4165 * 4166 * @see u_isIDIgnorable 4167 * @see u_isJavaIDStart 4168 * @see u_isalpha 4169 * @see u_isdigit 4170 * @see u_isIDPart 4171 * @stable ICU 2.0 4172 */ 4173 U_CAPI UBool U_EXPORT2 4174 u_isJavaIDPart(UChar32 c); 4175 4176 /** 4177 * The given character is mapped to its lowercase equivalent according to 4178 * UnicodeData.txt; if the character has no lowercase equivalent, the character 4179 * itself is returned. 4180 * 4181 * Same as java.lang.Character.toLowerCase(). 4182 * 4183 * This function only returns the simple, single-code point case mapping. 4184 * Full case mappings should be used whenever possible because they produce 4185 * better results by working on whole strings. 4186 * They take into account the string context and the language and can map 4187 * to a result string with a different length as appropriate. 4188 * Full case mappings are applied by the string case mapping functions, 4189 * see ustring.h and the UnicodeString class. 4190 * See also the User Guide chapter on C/POSIX migration: 4191 * https://unicode-org.github.io/icu/userguide/icu/posix#case-mappings 4192 * 4193 * @param c the code point to be mapped 4194 * @return the Simple_Lowercase_Mapping of the code point, if any; 4195 * otherwise the code point itself. 4196 * @stable ICU 2.0 4197 */ 4198 U_CAPI UChar32 U_EXPORT2 4199 u_tolower(UChar32 c); 4200 4201 /** 4202 * The given character is mapped to its uppercase equivalent according to UnicodeData.txt; 4203 * if the character has no uppercase equivalent, the character itself is 4204 * returned. 4205 * 4206 * Same as java.lang.Character.toUpperCase(). 4207 * 4208 * This function only returns the simple, single-code point case mapping. 4209 * Full case mappings should be used whenever possible because they produce 4210 * better results by working on whole strings. 4211 * They take into account the string context and the language and can map 4212 * to a result string with a different length as appropriate. 4213 * Full case mappings are applied by the string case mapping functions, 4214 * see ustring.h and the UnicodeString class. 4215 * See also the User Guide chapter on C/POSIX migration: 4216 * https://unicode-org.github.io/icu/userguide/icu/posix#case-mappings 4217 * 4218 * @param c the code point to be mapped 4219 * @return the Simple_Uppercase_Mapping of the code point, if any; 4220 * otherwise the code point itself. 4221 * @stable ICU 2.0 4222 */ 4223 U_CAPI UChar32 U_EXPORT2 4224 u_toupper(UChar32 c); 4225 4226 /** 4227 * The given character is mapped to its titlecase equivalent 4228 * according to UnicodeData.txt; 4229 * if none is defined, the character itself is returned. 4230 * 4231 * Same as java.lang.Character.toTitleCase(). 4232 * 4233 * This function only returns the simple, single-code point case mapping. 4234 * Full case mappings should be used whenever possible because they produce 4235 * better results by working on whole strings. 4236 * They take into account the string context and the language and can map 4237 * to a result string with a different length as appropriate. 4238 * Full case mappings are applied by the string case mapping functions, 4239 * see ustring.h and the UnicodeString class. 4240 * See also the User Guide chapter on C/POSIX migration: 4241 * https://unicode-org.github.io/icu/userguide/icu/posix#case-mappings 4242 * 4243 * @param c the code point to be mapped 4244 * @return the Simple_Titlecase_Mapping of the code point, if any; 4245 * otherwise the code point itself. 4246 * @stable ICU 2.0 4247 */ 4248 U_CAPI UChar32 U_EXPORT2 4249 u_totitle(UChar32 c); 4250 4251 /** 4252 * The given character is mapped to its case folding equivalent according to 4253 * UnicodeData.txt and CaseFolding.txt; 4254 * if the character has no case folding equivalent, the character 4255 * itself is returned. 4256 * 4257 * This function only returns the simple, single-code point case mapping. 4258 * Full case mappings should be used whenever possible because they produce 4259 * better results by working on whole strings. 4260 * They take into account the string context and the language and can map 4261 * to a result string with a different length as appropriate. 4262 * Full case mappings are applied by the string case mapping functions, 4263 * see ustring.h and the UnicodeString class. 4264 * See also the User Guide chapter on C/POSIX migration: 4265 * https://unicode-org.github.io/icu/userguide/icu/posix#case-mappings 4266 * 4267 * @param c the code point to be mapped 4268 * @param options Either U_FOLD_CASE_DEFAULT or U_FOLD_CASE_EXCLUDE_SPECIAL_I 4269 * @return the Simple_Case_Folding of the code point, if any; 4270 * otherwise the code point itself. 4271 * @stable ICU 2.0 4272 */ 4273 U_CAPI UChar32 U_EXPORT2 4274 u_foldCase(UChar32 c, uint32_t options); 4275 4276 /** 4277 * Returns the decimal digit value of the code point in the 4278 * specified radix. 4279 * 4280 * If the radix is not in the range <code>2<=radix<=36</code> or if the 4281 * value of <code>c</code> is not a valid digit in the specified 4282 * radix, <code>-1</code> is returned. A character is a valid digit 4283 * if at least one of the following is true: 4284 * <ul> 4285 * <li>The character has a decimal digit value. 4286 * Such characters have the general category "Nd" (decimal digit numbers) 4287 * and a Numeric_Type of Decimal. 4288 * In this case the value is the character's decimal digit value.</li> 4289 * <li>The character is one of the uppercase Latin letters 4290 * <code>'A'</code> through <code>'Z'</code>. 4291 * In this case the value is <code>c-'A'+10</code>.</li> 4292 * <li>The character is one of the lowercase Latin letters 4293 * <code>'a'</code> through <code>'z'</code>. 4294 * In this case the value is <code>ch-'a'+10</code>.</li> 4295 * <li>Latin letters from both the ASCII range (0061..007A, 0041..005A) 4296 * as well as from the Fullwidth ASCII range (FF41..FF5A, FF21..FF3A) 4297 * are recognized.</li> 4298 * </ul> 4299 * 4300 * Same as java.lang.Character.digit(). 4301 * 4302 * @param ch the code point to be tested. 4303 * @param radix the radix. 4304 * @return the numeric value represented by the character in the 4305 * specified radix, 4306 * or -1 if there is no value or if the value exceeds the radix. 4307 * 4308 * @see UCHAR_NUMERIC_TYPE 4309 * @see u_forDigit 4310 * @see u_charDigitValue 4311 * @see u_isdigit 4312 * @stable ICU 2.0 4313 */ 4314 U_CAPI int32_t U_EXPORT2 4315 u_digit(UChar32 ch, int8_t radix); 4316 4317 /** 4318 * Determines the character representation for a specific digit in 4319 * the specified radix. If the value of <code>radix</code> is not a 4320 * valid radix, or the value of <code>digit</code> is not a valid 4321 * digit in the specified radix, the null character 4322 * (<code>U+0000</code>) is returned. 4323 * <p> 4324 * The <code>radix</code> argument is valid if it is greater than or 4325 * equal to 2 and less than or equal to 36. 4326 * The <code>digit</code> argument is valid if 4327 * <code>0 <= digit < radix</code>. 4328 * <p> 4329 * If the digit is less than 10, then 4330 * <code>'0' + digit</code> is returned. Otherwise, the value 4331 * <code>'a' + digit - 10</code> is returned. 4332 * 4333 * Same as java.lang.Character.forDigit(). 4334 * 4335 * @param digit the number to convert to a character. 4336 * @param radix the radix. 4337 * @return the <code>char</code> representation of the specified digit 4338 * in the specified radix. 4339 * 4340 * @see u_digit 4341 * @see u_charDigitValue 4342 * @see u_isdigit 4343 * @stable ICU 2.0 4344 */ 4345 U_CAPI UChar32 U_EXPORT2 4346 u_forDigit(int32_t digit, int8_t radix); 4347 4348 /** 4349 * Get the "age" of the code point. 4350 * The "age" is the Unicode version when the code point was first 4351 * designated (as a non-character or for Private Use) 4352 * or assigned a character. 4353 * This can be useful to avoid emitting code points to receiving 4354 * processes that do not accept newer characters. 4355 * The data is from the UCD file DerivedAge.txt. 4356 * 4357 * @param c The code point. 4358 * @param versionArray The Unicode version number array, to be filled in. 4359 * 4360 * @stable ICU 2.1 4361 */ 4362 U_CAPI void U_EXPORT2 4363 u_charAge(UChar32 c, UVersionInfo versionArray); 4364 4365 /** 4366 * Gets the Unicode version information. 4367 * The version array is filled in with the version information 4368 * for the Unicode standard that is currently used by ICU. 4369 * For example, Unicode version 3.1.1 is represented as an array with 4370 * the values { 3, 1, 1, 0 }. 4371 * 4372 * @param versionArray an output array that will be filled in with 4373 * the Unicode version number 4374 * @stable ICU 2.0 4375 */ 4376 U_CAPI void U_EXPORT2 4377 u_getUnicodeVersion(UVersionInfo versionArray); 4378 4379 #if !UCONFIG_NO_NORMALIZATION 4380 /** 4381 * Get the FC_NFKC_Closure property string for a character. 4382 * See Unicode Standard Annex #15 for details, search for "FC_NFKC_Closure" 4383 * or for "FNC": http://www.unicode.org/reports/tr15/ 4384 * 4385 * @param c The character (code point) for which to get the FC_NFKC_Closure string. 4386 * It must be <code>0<=c<=0x10ffff</code>. 4387 * @param dest Destination address for copying the string. 4388 * The string will be zero-terminated if possible. 4389 * If there is no FC_NFKC_Closure string, 4390 * then the buffer will be set to the empty string. 4391 * @param destCapacity <code>==sizeof(dest)</code> 4392 * @param pErrorCode Pointer to a UErrorCode variable. 4393 * @return The length of the string, or 0 if there is no FC_NFKC_Closure string for this character. 4394 * If the destCapacity is less than or equal to the length, then the buffer 4395 * contains the truncated name and the returned length indicates the full 4396 * length of the name. 4397 * The length does not include the zero-termination. 4398 * 4399 * @stable ICU 2.2 4400 */ 4401 U_CAPI int32_t U_EXPORT2 4402 u_getFC_NFKC_Closure(UChar32 c, UChar *dest, int32_t destCapacity, UErrorCode *pErrorCode); 4403 4404 #endif 4405 4406 4407 U_CDECL_END 4408 4409 #endif /*_UCHAR*/ 4410 /*eof*/
| [ Source navigation ] | [ Diff markup ] | [ Identifier search ] | [ general search ] |
|
This page was automatically generated by the 2.3.7 LXR engine. The LXR team |
|