1.1 --- /dev/null Thu Jan 01 00:00:00 1970 +0000
1.2 +++ b/intl/icu/source/common/unicode/uchar.h Wed Dec 31 06:09:35 2014 +0100
1.3 @@ -0,0 +1,3331 @@
1.4 +/*
1.5 +**********************************************************************
1.6 +* Copyright (C) 1997-2013, International Business Machines
1.7 +* Corporation and others. All Rights Reserved.
1.8 +**********************************************************************
1.9 +*
1.10 +* File UCHAR.H
1.11 +*
1.12 +* Modification History:
1.13 +*
1.14 +* Date Name Description
1.15 +* 04/02/97 aliu Creation.
1.16 +* 03/29/99 helena Updated for C APIs.
1.17 +* 4/15/99 Madhu Updated for C Implementation and Javadoc
1.18 +* 5/20/99 Madhu Added the function u_getVersion()
1.19 +* 8/19/1999 srl Upgraded scripts to Unicode 3.0
1.20 +* 8/27/1999 schererm UCharDirection constants: U_...
1.21 +* 11/11/1999 weiv added u_isalnum(), cleaned comments
1.22 +* 01/11/2000 helena Renamed u_getVersion to u_getUnicodeVersion().
1.23 +******************************************************************************
1.24 +*/
1.25 +
1.26 +#ifndef UCHAR_H
1.27 +#define UCHAR_H
1.28 +
1.29 +#include "unicode/utypes.h"
1.30 +
1.31 +U_CDECL_BEGIN
1.32 +
1.33 +/*==========================================================================*/
1.34 +/* Unicode version number */
1.35 +/*==========================================================================*/
1.36 +/**
1.37 + * Unicode version number, default for the current ICU version.
1.38 + * The actual Unicode Character Database (UCD) data is stored in uprops.dat
1.39 + * and may be generated from UCD files from a different Unicode version.
1.40 + * Call u_getUnicodeVersion to get the actual Unicode version of the data.
1.41 + *
1.42 + * @see u_getUnicodeVersion
1.43 + * @stable ICU 2.0
1.44 + */
1.45 +#define U_UNICODE_VERSION "6.3"
1.46 +
1.47 +/**
1.48 + * \file
1.49 + * \brief C API: Unicode Properties
1.50 + *
1.51 + * This C API provides low-level access to the Unicode Character Database.
1.52 + * In addition to raw property values, some convenience functions calculate
1.53 + * derived properties, for example for Java-style programming.
1.54 + *
1.55 + * Unicode assigns each code point (not just assigned character) values for
1.56 + * many properties.
1.57 + * Most of them are simple boolean flags, or constants from a small enumerated list.
1.58 + * For some properties, values are strings or other relatively more complex types.
1.59 + *
1.60 + * For more information see
1.61 + * "About the Unicode Character Database" (http://www.unicode.org/ucd/)
1.62 + * and the ICU User Guide chapter on Properties (http://icu-project.org/userguide/properties.html).
1.63 + *
1.64 + * Many functions are designed to match java.lang.Character functions.
1.65 + * See the individual function documentation,
1.66 + * and see the JDK 1.4 java.lang.Character documentation
1.67 + * at http://java.sun.com/j2se/1.4/docs/api/java/lang/Character.html
1.68 + *
1.69 + * There are also functions that provide easy migration from C/POSIX functions
1.70 + * like isblank(). Their use is generally discouraged because the C/POSIX
1.71 + * standards do not define their semantics beyond the ASCII range, which means
1.72 + * that different implementations exhibit very different behavior.
1.73 + * Instead, Unicode properties should be used directly.
1.74 + *
1.75 + * There are also only a few, broad C/POSIX character classes, and they tend
1.76 + * to be used for conflicting purposes. For example, the "isalpha()" class
1.77 + * is sometimes used to determine word boundaries, while a more sophisticated
1.78 + * approach would at least distinguish initial letters from continuation
1.79 + * characters (the latter including combining marks).
1.80 + * (In ICU, BreakIterator is the most sophisticated API for word boundaries.)
1.81 + * Another example: There is no "istitle()" class for titlecase characters.
1.82 + *
1.83 + * ICU 3.4 and later provides API access for all twelve C/POSIX character classes.
1.84 + * ICU implements them according to the Standard Recommendations in
1.85 + * Annex C: Compatibility Properties of UTS #18 Unicode Regular Expressions
1.86 + * (http://www.unicode.org/reports/tr18/#Compatibility_Properties).
1.87 + *
1.88 + * API access for C/POSIX character classes is as follows:
1.89 + * - alpha: u_isUAlphabetic(c) or u_hasBinaryProperty(c, UCHAR_ALPHABETIC)
1.90 + * - lower: u_isULowercase(c) or u_hasBinaryProperty(c, UCHAR_LOWERCASE)
1.91 + * - upper: u_isUUppercase(c) or u_hasBinaryProperty(c, UCHAR_UPPERCASE)
1.92 + * - punct: u_ispunct(c)
1.93 + * - digit: u_isdigit(c) or u_charType(c)==U_DECIMAL_DIGIT_NUMBER
1.94 + * - xdigit: u_isxdigit(c) or u_hasBinaryProperty(c, UCHAR_POSIX_XDIGIT)
1.95 + * - alnum: u_hasBinaryProperty(c, UCHAR_POSIX_ALNUM)
1.96 + * - space: u_isUWhiteSpace(c) or u_hasBinaryProperty(c, UCHAR_WHITE_SPACE)
1.97 + * - blank: u_isblank(c) or u_hasBinaryProperty(c, UCHAR_POSIX_BLANK)
1.98 + * - cntrl: u_charType(c)==U_CONTROL_CHAR
1.99 + * - graph: u_hasBinaryProperty(c, UCHAR_POSIX_GRAPH)
1.100 + * - print: u_hasBinaryProperty(c, UCHAR_POSIX_PRINT)
1.101 + *
1.102 + * Note: Some of the u_isxyz() functions in uchar.h predate, and do not match,
1.103 + * the Standard Recommendations in UTS #18. Instead, they match Java
1.104 + * functions according to their API documentation.
1.105 + *
1.106 + * \htmlonly
1.107 + * The C/POSIX character classes are also available in UnicodeSet patterns,
1.108 + * using patterns like [:graph:] or \p{graph}.
1.109 + * \endhtmlonly
1.110 + *
1.111 + * Note: There are several ICU whitespace functions.
1.112 + * Comparison:
1.113 + * - u_isUWhiteSpace=UCHAR_WHITE_SPACE: Unicode White_Space property;
1.114 + * most of general categories "Z" (separators) + most whitespace ISO controls
1.115 + * (including no-break spaces, but excluding IS1..IS4 and ZWSP)
1.116 + * - u_isWhitespace: Java isWhitespace; Z + whitespace ISO controls but excluding no-break spaces
1.117 + * - u_isJavaSpaceChar: Java isSpaceChar; just Z (including no-break spaces)
1.118 + * - u_isspace: Z + whitespace ISO controls (including no-break spaces)
1.119 + * - u_isblank: "horizontal spaces" = TAB + Zs - ZWSP
1.120 + */
1.121 +
1.122 +/**
1.123 + * Constants.
1.124 + */
1.125 +
1.126 +/** The lowest Unicode code point value. Code points are non-negative. @stable ICU 2.0 */
1.127 +#define UCHAR_MIN_VALUE 0
1.128 +
1.129 +/**
1.130 + * The highest Unicode code point value (scalar value) according to
1.131 + * The Unicode Standard. This is a 21-bit value (20.1 bits, rounded up).
1.132 + * For a single character, UChar32 is a simple type that can hold any code point value.
1.133 + *
1.134 + * @see UChar32
1.135 + * @stable ICU 2.0
1.136 + */
1.137 +#define UCHAR_MAX_VALUE 0x10ffff
1.138 +
1.139 +/**
1.140 + * Get a single-bit bit set (a flag) from a bit number 0..31.
1.141 + * @stable ICU 2.1
1.142 + */
1.143 +#define U_MASK(x) ((uint32_t)1<<(x))
1.144 +
1.145 +/**
1.146 + * Selection constants for Unicode properties.
1.147 + * These constants are used in functions like u_hasBinaryProperty to select
1.148 + * one of the Unicode properties.
1.149 + *
1.150 + * The properties APIs are intended to reflect Unicode properties as defined
1.151 + * in the Unicode Character Database (UCD) and Unicode Technical Reports (UTR).
1.152 + * For details about the properties see http://www.unicode.org/ucd/ .
1.153 + * For names of Unicode properties see the UCD file PropertyAliases.txt.
1.154 + *
1.155 + * Important: If ICU is built with UCD files from Unicode versions below, e.g., 3.2,
1.156 + * then properties marked with "new in Unicode 3.2" are not or not fully available.
1.157 + * Check u_getUnicodeVersion to be sure.
1.158 + *
1.159 + * @see u_hasBinaryProperty
1.160 + * @see u_getIntPropertyValue
1.161 + * @see u_getUnicodeVersion
1.162 + * @stable ICU 2.1
1.163 + */
1.164 +typedef enum UProperty {
1.165 + /*
1.166 + * Note: UProperty constants are parsed by preparseucd.py.
1.167 + * It matches lines like
1.168 + * UCHAR_<Unicode property name>=<integer>,
1.169 + */
1.170 +
1.171 + /* Note: Place UCHAR_ALPHABETIC before UCHAR_BINARY_START so that
1.172 + debuggers display UCHAR_ALPHABETIC as the symbolic name for 0,
1.173 + rather than UCHAR_BINARY_START. Likewise for other *_START
1.174 + identifiers. */
1.175 +
1.176 + /** Binary property Alphabetic. Same as u_isUAlphabetic, different from u_isalpha.
1.177 + Lu+Ll+Lt+Lm+Lo+Nl+Other_Alphabetic @stable ICU 2.1 */
1.178 + UCHAR_ALPHABETIC=0,
1.179 + /** First constant for binary Unicode properties. @stable ICU 2.1 */
1.180 + UCHAR_BINARY_START=UCHAR_ALPHABETIC,
1.181 + /** Binary property ASCII_Hex_Digit. 0-9 A-F a-f @stable ICU 2.1 */
1.182 + UCHAR_ASCII_HEX_DIGIT=1,
1.183 + /** Binary property Bidi_Control.
1.184 + Format controls which have specific functions
1.185 + in the Bidi Algorithm. @stable ICU 2.1 */
1.186 + UCHAR_BIDI_CONTROL=2,
1.187 + /** Binary property Bidi_Mirrored.
1.188 + Characters that may change display in RTL text.
1.189 + Same as u_isMirrored.
1.190 + See Bidi Algorithm, UTR 9. @stable ICU 2.1 */
1.191 + UCHAR_BIDI_MIRRORED=3,
1.192 + /** Binary property Dash. Variations of dashes. @stable ICU 2.1 */
1.193 + UCHAR_DASH=4,
1.194 + /** Binary property Default_Ignorable_Code_Point (new in Unicode 3.2).
1.195 + Ignorable in most processing.
1.196 + <2060..206F, FFF0..FFFB, E0000..E0FFF>+Other_Default_Ignorable_Code_Point+(Cf+Cc+Cs-White_Space) @stable ICU 2.1 */
1.197 + UCHAR_DEFAULT_IGNORABLE_CODE_POINT=5,
1.198 + /** Binary property Deprecated (new in Unicode 3.2).
1.199 + The usage of deprecated characters is strongly discouraged. @stable ICU 2.1 */
1.200 + UCHAR_DEPRECATED=6,
1.201 + /** Binary property Diacritic. Characters that linguistically modify
1.202 + the meaning of another character to which they apply. @stable ICU 2.1 */
1.203 + UCHAR_DIACRITIC=7,
1.204 + /** Binary property Extender.
1.205 + Extend the value or shape of a preceding alphabetic character,
1.206 + e.g., length and iteration marks. @stable ICU 2.1 */
1.207 + UCHAR_EXTENDER=8,
1.208 + /** Binary property Full_Composition_Exclusion.
1.209 + CompositionExclusions.txt+Singleton Decompositions+
1.210 + Non-Starter Decompositions. @stable ICU 2.1 */
1.211 + UCHAR_FULL_COMPOSITION_EXCLUSION=9,
1.212 + /** Binary property Grapheme_Base (new in Unicode 3.2).
1.213 + For programmatic determination of grapheme cluster boundaries.
1.214 + [0..10FFFF]-Cc-Cf-Cs-Co-Cn-Zl-Zp-Grapheme_Link-Grapheme_Extend-CGJ @stable ICU 2.1 */
1.215 + UCHAR_GRAPHEME_BASE=10,
1.216 + /** Binary property Grapheme_Extend (new in Unicode 3.2).
1.217 + For programmatic determination of grapheme cluster boundaries.
1.218 + Me+Mn+Mc+Other_Grapheme_Extend-Grapheme_Link-CGJ @stable ICU 2.1 */
1.219 + UCHAR_GRAPHEME_EXTEND=11,
1.220 + /** Binary property Grapheme_Link (new in Unicode 3.2).
1.221 + For programmatic determination of grapheme cluster boundaries. @stable ICU 2.1 */
1.222 + UCHAR_GRAPHEME_LINK=12,
1.223 + /** Binary property Hex_Digit.
1.224 + Characters commonly used for hexadecimal numbers. @stable ICU 2.1 */
1.225 + UCHAR_HEX_DIGIT=13,
1.226 + /** Binary property Hyphen. Dashes used to mark connections
1.227 + between pieces of words, plus the Katakana middle dot. @stable ICU 2.1 */
1.228 + UCHAR_HYPHEN=14,
1.229 + /** Binary property ID_Continue.
1.230 + Characters that can continue an identifier.
1.231 + DerivedCoreProperties.txt also says "NOTE: Cf characters should be filtered out."
1.232 + ID_Start+Mn+Mc+Nd+Pc @stable ICU 2.1 */
1.233 + UCHAR_ID_CONTINUE=15,
1.234 + /** Binary property ID_Start.
1.235 + Characters that can start an identifier.
1.236 + Lu+Ll+Lt+Lm+Lo+Nl @stable ICU 2.1 */
1.237 + UCHAR_ID_START=16,
1.238 + /** Binary property Ideographic.
1.239 + CJKV ideographs. @stable ICU 2.1 */
1.240 + UCHAR_IDEOGRAPHIC=17,
1.241 + /** Binary property IDS_Binary_Operator (new in Unicode 3.2).
1.242 + For programmatic determination of
1.243 + Ideographic Description Sequences. @stable ICU 2.1 */
1.244 + UCHAR_IDS_BINARY_OPERATOR=18,
1.245 + /** Binary property IDS_Trinary_Operator (new in Unicode 3.2).
1.246 + For programmatic determination of
1.247 + Ideographic Description Sequences. @stable ICU 2.1 */
1.248 + UCHAR_IDS_TRINARY_OPERATOR=19,
1.249 + /** Binary property Join_Control.
1.250 + Format controls for cursive joining and ligation. @stable ICU 2.1 */
1.251 + UCHAR_JOIN_CONTROL=20,
1.252 + /** Binary property Logical_Order_Exception (new in Unicode 3.2).
1.253 + Characters that do not use logical order and
1.254 + require special handling in most processing. @stable ICU 2.1 */
1.255 + UCHAR_LOGICAL_ORDER_EXCEPTION=21,
1.256 + /** Binary property Lowercase. Same as u_isULowercase, different from u_islower.
1.257 + Ll+Other_Lowercase @stable ICU 2.1 */
1.258 + UCHAR_LOWERCASE=22,
1.259 + /** Binary property Math. Sm+Other_Math @stable ICU 2.1 */
1.260 + UCHAR_MATH=23,
1.261 + /** Binary property Noncharacter_Code_Point.
1.262 + Code points that are explicitly defined as illegal
1.263 + for the encoding of characters. @stable ICU 2.1 */
1.264 + UCHAR_NONCHARACTER_CODE_POINT=24,
1.265 + /** Binary property Quotation_Mark. @stable ICU 2.1 */
1.266 + UCHAR_QUOTATION_MARK=25,
1.267 + /** Binary property Radical (new in Unicode 3.2).
1.268 + For programmatic determination of
1.269 + Ideographic Description Sequences. @stable ICU 2.1 */
1.270 + UCHAR_RADICAL=26,
1.271 + /** Binary property Soft_Dotted (new in Unicode 3.2).
1.272 + Characters with a "soft dot", like i or j.
1.273 + An accent placed on these characters causes
1.274 + the dot to disappear. @stable ICU 2.1 */
1.275 + UCHAR_SOFT_DOTTED=27,
1.276 + /** Binary property Terminal_Punctuation.
1.277 + Punctuation characters that generally mark
1.278 + the end of textual units. @stable ICU 2.1 */
1.279 + UCHAR_TERMINAL_PUNCTUATION=28,
1.280 + /** Binary property Unified_Ideograph (new in Unicode 3.2).
1.281 + For programmatic determination of
1.282 + Ideographic Description Sequences. @stable ICU 2.1 */
1.283 + UCHAR_UNIFIED_IDEOGRAPH=29,
1.284 + /** Binary property Uppercase. Same as u_isUUppercase, different from u_isupper.
1.285 + Lu+Other_Uppercase @stable ICU 2.1 */
1.286 + UCHAR_UPPERCASE=30,
1.287 + /** Binary property White_Space.
1.288 + Same as u_isUWhiteSpace, different from u_isspace and u_isWhitespace.
1.289 + Space characters+TAB+CR+LF-ZWSP-ZWNBSP @stable ICU 2.1 */
1.290 + UCHAR_WHITE_SPACE=31,
1.291 + /** Binary property XID_Continue.
1.292 + ID_Continue modified to allow closure under
1.293 + normalization forms NFKC and NFKD. @stable ICU 2.1 */
1.294 + UCHAR_XID_CONTINUE=32,
1.295 + /** Binary property XID_Start. ID_Start modified to allow
1.296 + closure under normalization forms NFKC and NFKD. @stable ICU 2.1 */
1.297 + UCHAR_XID_START=33,
1.298 + /** Binary property Case_Sensitive. Either the source of a case
1.299 + mapping or _in_ the target of a case mapping. Not the same as
1.300 + the general category Cased_Letter. @stable ICU 2.6 */
1.301 + UCHAR_CASE_SENSITIVE=34,
1.302 + /** Binary property STerm (new in Unicode 4.0.1).
1.303 + Sentence Terminal. Used in UAX #29: Text Boundaries
1.304 + (http://www.unicode.org/reports/tr29/)
1.305 + @stable ICU 3.0 */
1.306 + UCHAR_S_TERM=35,
1.307 + /** Binary property Variation_Selector (new in Unicode 4.0.1).
1.308 + Indicates all those characters that qualify as Variation Selectors.
1.309 + For details on the behavior of these characters,
1.310 + see StandardizedVariants.html and 15.6 Variation Selectors.
1.311 + @stable ICU 3.0 */
1.312 + UCHAR_VARIATION_SELECTOR=36,
1.313 + /** Binary property NFD_Inert.
1.314 + ICU-specific property for characters that are inert under NFD,
1.315 + i.e., they do not interact with adjacent characters.
1.316 + See the documentation for the Normalizer2 class and the
1.317 + Normalizer2::isInert() method.
1.318 + @stable ICU 3.0 */
1.319 + UCHAR_NFD_INERT=37,
1.320 + /** Binary property NFKD_Inert.
1.321 + ICU-specific property for characters that are inert under NFKD,
1.322 + i.e., they do not interact with adjacent characters.
1.323 + See the documentation for the Normalizer2 class and the
1.324 + Normalizer2::isInert() method.
1.325 + @stable ICU 3.0 */
1.326 + UCHAR_NFKD_INERT=38,
1.327 + /** Binary property NFC_Inert.
1.328 + ICU-specific property for characters that are inert under NFC,
1.329 + i.e., they do not interact with adjacent characters.
1.330 + See the documentation for the Normalizer2 class and the
1.331 + Normalizer2::isInert() method.
1.332 + @stable ICU 3.0 */
1.333 + UCHAR_NFC_INERT=39,
1.334 + /** Binary property NFKC_Inert.
1.335 + ICU-specific property for characters that are inert under NFKC,
1.336 + i.e., they do not interact with adjacent characters.
1.337 + See the documentation for the Normalizer2 class and the
1.338 + Normalizer2::isInert() method.
1.339 + @stable ICU 3.0 */
1.340 + UCHAR_NFKC_INERT=40,
1.341 + /** Binary Property Segment_Starter.
1.342 + ICU-specific property for characters that are starters in terms of
1.343 + Unicode normalization and combining character sequences.
1.344 + They have ccc=0 and do not occur in non-initial position of the
1.345 + canonical decomposition of any character
1.346 + (like a-umlaut in NFD and a Jamo T in an NFD(Hangul LVT)).
1.347 + ICU uses this property for segmenting a string for generating a set of
1.348 + canonically equivalent strings, e.g. for canonical closure while
1.349 + processing collation tailoring rules.
1.350 + @stable ICU 3.0 */
1.351 + UCHAR_SEGMENT_STARTER=41,
1.352 + /** Binary property Pattern_Syntax (new in Unicode 4.1).
1.353 + See UAX #31 Identifier and Pattern Syntax
1.354 + (http://www.unicode.org/reports/tr31/)
1.355 + @stable ICU 3.4 */
1.356 + UCHAR_PATTERN_SYNTAX=42,
1.357 + /** Binary property Pattern_White_Space (new in Unicode 4.1).
1.358 + See UAX #31 Identifier and Pattern Syntax
1.359 + (http://www.unicode.org/reports/tr31/)
1.360 + @stable ICU 3.4 */
1.361 + UCHAR_PATTERN_WHITE_SPACE=43,
1.362 + /** Binary property alnum (a C/POSIX character class).
1.363 + Implemented according to the UTS #18 Annex C Standard Recommendation.
1.364 + See the uchar.h file documentation.
1.365 + @stable ICU 3.4 */
1.366 + UCHAR_POSIX_ALNUM=44,
1.367 + /** Binary property blank (a C/POSIX character class).
1.368 + Implemented according to the UTS #18 Annex C Standard Recommendation.
1.369 + See the uchar.h file documentation.
1.370 + @stable ICU 3.4 */
1.371 + UCHAR_POSIX_BLANK=45,
1.372 + /** Binary property graph (a C/POSIX character class).
1.373 + Implemented according to the UTS #18 Annex C Standard Recommendation.
1.374 + See the uchar.h file documentation.
1.375 + @stable ICU 3.4 */
1.376 + UCHAR_POSIX_GRAPH=46,
1.377 + /** Binary property print (a C/POSIX character class).
1.378 + Implemented according to the UTS #18 Annex C Standard Recommendation.
1.379 + See the uchar.h file documentation.
1.380 + @stable ICU 3.4 */
1.381 + UCHAR_POSIX_PRINT=47,
1.382 + /** Binary property xdigit (a C/POSIX character class).
1.383 + Implemented according to the UTS #18 Annex C Standard Recommendation.
1.384 + See the uchar.h file documentation.
1.385 + @stable ICU 3.4 */
1.386 + UCHAR_POSIX_XDIGIT=48,
1.387 + /** Binary property Cased. For Lowercase, Uppercase and Titlecase characters. @stable ICU 4.4 */
1.388 + UCHAR_CASED=49,
1.389 + /** Binary property Case_Ignorable. Used in context-sensitive case mappings. @stable ICU 4.4 */
1.390 + UCHAR_CASE_IGNORABLE=50,
1.391 + /** Binary property Changes_When_Lowercased. @stable ICU 4.4 */
1.392 + UCHAR_CHANGES_WHEN_LOWERCASED=51,
1.393 + /** Binary property Changes_When_Uppercased. @stable ICU 4.4 */
1.394 + UCHAR_CHANGES_WHEN_UPPERCASED=52,
1.395 + /** Binary property Changes_When_Titlecased. @stable ICU 4.4 */
1.396 + UCHAR_CHANGES_WHEN_TITLECASED=53,
1.397 + /** Binary property Changes_When_Casefolded. @stable ICU 4.4 */
1.398 + UCHAR_CHANGES_WHEN_CASEFOLDED=54,
1.399 + /** Binary property Changes_When_Casemapped. @stable ICU 4.4 */
1.400 + UCHAR_CHANGES_WHEN_CASEMAPPED=55,
1.401 + /** Binary property Changes_When_NFKC_Casefolded. @stable ICU 4.4 */
1.402 + UCHAR_CHANGES_WHEN_NFKC_CASEFOLDED=56,
1.403 + /** One more than the last constant for binary Unicode properties. @stable ICU 2.1 */
1.404 + UCHAR_BINARY_LIMIT=57,
1.405 +
1.406 + /** Enumerated property Bidi_Class.
1.407 + Same as u_charDirection, returns UCharDirection values. @stable ICU 2.2 */
1.408 + UCHAR_BIDI_CLASS=0x1000,
1.409 + /** First constant for enumerated/integer Unicode properties. @stable ICU 2.2 */
1.410 + UCHAR_INT_START=UCHAR_BIDI_CLASS,
1.411 + /** Enumerated property Block.
1.412 + Same as ublock_getCode, returns UBlockCode values. @stable ICU 2.2 */
1.413 + UCHAR_BLOCK=0x1001,
1.414 + /** Enumerated property Canonical_Combining_Class.
1.415 + Same as u_getCombiningClass, returns 8-bit numeric values. @stable ICU 2.2 */
1.416 + UCHAR_CANONICAL_COMBINING_CLASS=0x1002,
1.417 + /** Enumerated property Decomposition_Type.
1.418 + Returns UDecompositionType values. @stable ICU 2.2 */
1.419 + UCHAR_DECOMPOSITION_TYPE=0x1003,
1.420 + /** Enumerated property East_Asian_Width.
1.421 + See http://www.unicode.org/reports/tr11/
1.422 + Returns UEastAsianWidth values. @stable ICU 2.2 */
1.423 + UCHAR_EAST_ASIAN_WIDTH=0x1004,
1.424 + /** Enumerated property General_Category.
1.425 + Same as u_charType, returns UCharCategory values. @stable ICU 2.2 */
1.426 + UCHAR_GENERAL_CATEGORY=0x1005,
1.427 + /** Enumerated property Joining_Group.
1.428 + Returns UJoiningGroup values. @stable ICU 2.2 */
1.429 + UCHAR_JOINING_GROUP=0x1006,
1.430 + /** Enumerated property Joining_Type.
1.431 + Returns UJoiningType values. @stable ICU 2.2 */
1.432 + UCHAR_JOINING_TYPE=0x1007,
1.433 + /** Enumerated property Line_Break.
1.434 + Returns ULineBreak values. @stable ICU 2.2 */
1.435 + UCHAR_LINE_BREAK=0x1008,
1.436 + /** Enumerated property Numeric_Type.
1.437 + Returns UNumericType values. @stable ICU 2.2 */
1.438 + UCHAR_NUMERIC_TYPE=0x1009,
1.439 + /** Enumerated property Script.
1.440 + Same as uscript_getScript, returns UScriptCode values. @stable ICU 2.2 */
1.441 + UCHAR_SCRIPT=0x100A,
1.442 + /** Enumerated property Hangul_Syllable_Type, new in Unicode 4.
1.443 + Returns UHangulSyllableType values. @stable ICU 2.6 */
1.444 + UCHAR_HANGUL_SYLLABLE_TYPE=0x100B,
1.445 + /** Enumerated property NFD_Quick_Check.
1.446 + Returns UNormalizationCheckResult values. @stable ICU 3.0 */
1.447 + UCHAR_NFD_QUICK_CHECK=0x100C,
1.448 + /** Enumerated property NFKD_Quick_Check.
1.449 + Returns UNormalizationCheckResult values. @stable ICU 3.0 */
1.450 + UCHAR_NFKD_QUICK_CHECK=0x100D,
1.451 + /** Enumerated property NFC_Quick_Check.
1.452 + Returns UNormalizationCheckResult values. @stable ICU 3.0 */
1.453 + UCHAR_NFC_QUICK_CHECK=0x100E,
1.454 + /** Enumerated property NFKC_Quick_Check.
1.455 + Returns UNormalizationCheckResult values. @stable ICU 3.0 */
1.456 + UCHAR_NFKC_QUICK_CHECK=0x100F,
1.457 + /** Enumerated property Lead_Canonical_Combining_Class.
1.458 + ICU-specific property for the ccc of the first code point
1.459 + of the decomposition, or lccc(c)=ccc(NFD(c)[0]).
1.460 + Useful for checking for canonically ordered text;
1.461 + see UNORM_FCD and http://www.unicode.org/notes/tn5/#FCD .
1.462 + Returns 8-bit numeric values like UCHAR_CANONICAL_COMBINING_CLASS. @stable ICU 3.0 */
1.463 + UCHAR_LEAD_CANONICAL_COMBINING_CLASS=0x1010,
1.464 + /** Enumerated property Trail_Canonical_Combining_Class.
1.465 + ICU-specific property for the ccc of the last code point
1.466 + of the decomposition, or tccc(c)=ccc(NFD(c)[last]).
1.467 + Useful for checking for canonically ordered text;
1.468 + see UNORM_FCD and http://www.unicode.org/notes/tn5/#FCD .
1.469 + Returns 8-bit numeric values like UCHAR_CANONICAL_COMBINING_CLASS. @stable ICU 3.0 */
1.470 + UCHAR_TRAIL_CANONICAL_COMBINING_CLASS=0x1011,
1.471 + /** Enumerated property Grapheme_Cluster_Break (new in Unicode 4.1).
1.472 + Used in UAX #29: Text Boundaries
1.473 + (http://www.unicode.org/reports/tr29/)
1.474 + Returns UGraphemeClusterBreak values. @stable ICU 3.4 */
1.475 + UCHAR_GRAPHEME_CLUSTER_BREAK=0x1012,
1.476 + /** Enumerated property Sentence_Break (new in Unicode 4.1).
1.477 + Used in UAX #29: Text Boundaries
1.478 + (http://www.unicode.org/reports/tr29/)
1.479 + Returns USentenceBreak values. @stable ICU 3.4 */
1.480 + UCHAR_SENTENCE_BREAK=0x1013,
1.481 + /** Enumerated property Word_Break (new in Unicode 4.1).
1.482 + Used in UAX #29: Text Boundaries
1.483 + (http://www.unicode.org/reports/tr29/)
1.484 + Returns UWordBreakValues values. @stable ICU 3.4 */
1.485 + UCHAR_WORD_BREAK=0x1014,
1.486 + /** Enumerated property Bidi_Paired_Bracket_Type (new in Unicode 6.3).
1.487 + Used in UAX #9: Unicode Bidirectional Algorithm
1.488 + (http://www.unicode.org/reports/tr9/)
1.489 + Returns UBidiPairedBracketType values. @stable ICU 52 */
1.490 + UCHAR_BIDI_PAIRED_BRACKET_TYPE=0x1015,
1.491 + /** One more than the last constant for enumerated/integer Unicode properties. @stable ICU 2.2 */
1.492 + UCHAR_INT_LIMIT=0x1016,
1.493 +
1.494 + /** Bitmask property General_Category_Mask.
1.495 + This is the General_Category property returned as a bit mask.
1.496 + When used in u_getIntPropertyValue(c), same as U_MASK(u_charType(c)),
1.497 + returns bit masks for UCharCategory values where exactly one bit is set.
1.498 + When used with u_getPropertyValueName() and u_getPropertyValueEnum(),
1.499 + a multi-bit mask is used for sets of categories like "Letters".
1.500 + Mask values should be cast to uint32_t.
1.501 + @stable ICU 2.4 */
1.502 + UCHAR_GENERAL_CATEGORY_MASK=0x2000,
1.503 + /** First constant for bit-mask Unicode properties. @stable ICU 2.4 */
1.504 + UCHAR_MASK_START=UCHAR_GENERAL_CATEGORY_MASK,
1.505 + /** One more than the last constant for bit-mask Unicode properties. @stable ICU 2.4 */
1.506 + UCHAR_MASK_LIMIT=0x2001,
1.507 +
1.508 + /** Double property Numeric_Value.
1.509 + Corresponds to u_getNumericValue. @stable ICU 2.4 */
1.510 + UCHAR_NUMERIC_VALUE=0x3000,
1.511 + /** First constant for double Unicode properties. @stable ICU 2.4 */
1.512 + UCHAR_DOUBLE_START=UCHAR_NUMERIC_VALUE,
1.513 + /** One more than the last constant for double Unicode properties. @stable ICU 2.4 */
1.514 + UCHAR_DOUBLE_LIMIT=0x3001,
1.515 +
1.516 + /** String property Age.
1.517 + Corresponds to u_charAge. @stable ICU 2.4 */
1.518 + UCHAR_AGE=0x4000,
1.519 + /** First constant for string Unicode properties. @stable ICU 2.4 */
1.520 + UCHAR_STRING_START=UCHAR_AGE,
1.521 + /** String property Bidi_Mirroring_Glyph.
1.522 + Corresponds to u_charMirror. @stable ICU 2.4 */
1.523 + UCHAR_BIDI_MIRRORING_GLYPH=0x4001,
1.524 + /** String property Case_Folding.
1.525 + Corresponds to u_strFoldCase in ustring.h. @stable ICU 2.4 */
1.526 + UCHAR_CASE_FOLDING=0x4002,
1.527 +#ifndef U_HIDE_DEPRECATED_API
1.528 + /** Deprecated string property ISO_Comment.
1.529 + Corresponds to u_getISOComment. @deprecated ICU 49 */
1.530 + UCHAR_ISO_COMMENT=0x4003,
1.531 +#endif /* U_HIDE_DEPRECATED_API */
1.532 + /** String property Lowercase_Mapping.
1.533 + Corresponds to u_strToLower in ustring.h. @stable ICU 2.4 */
1.534 + UCHAR_LOWERCASE_MAPPING=0x4004,
1.535 + /** String property Name.
1.536 + Corresponds to u_charName. @stable ICU 2.4 */
1.537 + UCHAR_NAME=0x4005,
1.538 + /** String property Simple_Case_Folding.
1.539 + Corresponds to u_foldCase. @stable ICU 2.4 */
1.540 + UCHAR_SIMPLE_CASE_FOLDING=0x4006,
1.541 + /** String property Simple_Lowercase_Mapping.
1.542 + Corresponds to u_tolower. @stable ICU 2.4 */
1.543 + UCHAR_SIMPLE_LOWERCASE_MAPPING=0x4007,
1.544 + /** String property Simple_Titlecase_Mapping.
1.545 + Corresponds to u_totitle. @stable ICU 2.4 */
1.546 + UCHAR_SIMPLE_TITLECASE_MAPPING=0x4008,
1.547 + /** String property Simple_Uppercase_Mapping.
1.548 + Corresponds to u_toupper. @stable ICU 2.4 */
1.549 + UCHAR_SIMPLE_UPPERCASE_MAPPING=0x4009,
1.550 + /** String property Titlecase_Mapping.
1.551 + Corresponds to u_strToTitle in ustring.h. @stable ICU 2.4 */
1.552 + UCHAR_TITLECASE_MAPPING=0x400A,
1.553 +#ifndef U_HIDE_DEPRECATED_API
1.554 + /** String property Unicode_1_Name.
1.555 + This property is of little practical value.
1.556 + Beginning with ICU 49, ICU APIs return an empty string for this property.
1.557 + Corresponds to u_charName(U_UNICODE_10_CHAR_NAME). @deprecated ICU 49 */
1.558 + UCHAR_UNICODE_1_NAME=0x400B,
1.559 +#endif /* U_HIDE_DEPRECATED_API */
1.560 + /** String property Uppercase_Mapping.
1.561 + Corresponds to u_strToUpper in ustring.h. @stable ICU 2.4 */
1.562 + UCHAR_UPPERCASE_MAPPING=0x400C,
1.563 + /** String property Bidi_Paired_Bracket (new in Unicode 6.3).
1.564 + Corresponds to u_getBidiPairedBracket. @stable ICU 52 */
1.565 + UCHAR_BIDI_PAIRED_BRACKET=0x400D,
1.566 + /** One more than the last constant for string Unicode properties. @stable ICU 2.4 */
1.567 + UCHAR_STRING_LIMIT=0x400E,
1.568 +
1.569 + /** Miscellaneous property Script_Extensions (new in Unicode 6.0).
1.570 + Some characters are commonly used in multiple scripts.
1.571 + For more information, see UAX #24: http://www.unicode.org/reports/tr24/.
1.572 + Corresponds to uscript_hasScript and uscript_getScriptExtensions in uscript.h.
1.573 + @stable ICU 4.6 */
1.574 + UCHAR_SCRIPT_EXTENSIONS=0x7000,
1.575 + /** First constant for Unicode properties with unusual value types. @stable ICU 4.6 */
1.576 + UCHAR_OTHER_PROPERTY_START=UCHAR_SCRIPT_EXTENSIONS,
1.577 + /** One more than the last constant for Unicode properties with unusual value types.
1.578 + * @stable ICU 4.6 */
1.579 + UCHAR_OTHER_PROPERTY_LIMIT=0x7001,
1.580 + /** Represents a nonexistent or invalid property or property value. @stable ICU 2.4 */
1.581 + UCHAR_INVALID_CODE = -1
1.582 +} UProperty;
1.583 +
1.584 +/**
1.585 + * Data for enumerated Unicode general category types.
1.586 + * See http://www.unicode.org/Public/UNIDATA/UnicodeData.html .
1.587 + * @stable ICU 2.0
1.588 + */
1.589 +typedef enum UCharCategory
1.590 +{
1.591 + /*
1.592 + * Note: UCharCategory constants and their API comments are parsed by preparseucd.py.
1.593 + * It matches pairs of lines like
1.594 + * / ** <Unicode 2-letter General_Category value> comment... * /
1.595 + * U_<[A-Z_]+> = <integer>,
1.596 + */
1.597 +
1.598 + /** Non-category for unassigned and non-character code points. @stable ICU 2.0 */
1.599 + U_UNASSIGNED = 0,
1.600 + /** Cn "Other, Not Assigned (no characters in [UnicodeData.txt] have this property)" (same as U_UNASSIGNED!) @stable ICU 2.0 */
1.601 + U_GENERAL_OTHER_TYPES = 0,
1.602 + /** Lu @stable ICU 2.0 */
1.603 + U_UPPERCASE_LETTER = 1,
1.604 + /** Ll @stable ICU 2.0 */
1.605 + U_LOWERCASE_LETTER = 2,
1.606 + /** Lt @stable ICU 2.0 */
1.607 + U_TITLECASE_LETTER = 3,
1.608 + /** Lm @stable ICU 2.0 */
1.609 + U_MODIFIER_LETTER = 4,
1.610 + /** Lo @stable ICU 2.0 */
1.611 + U_OTHER_LETTER = 5,
1.612 + /** Mn @stable ICU 2.0 */
1.613 + U_NON_SPACING_MARK = 6,
1.614 + /** Me @stable ICU 2.0 */
1.615 + U_ENCLOSING_MARK = 7,
1.616 + /** Mc @stable ICU 2.0 */
1.617 + U_COMBINING_SPACING_MARK = 8,
1.618 + /** Nd @stable ICU 2.0 */
1.619 + U_DECIMAL_DIGIT_NUMBER = 9,
1.620 + /** Nl @stable ICU 2.0 */
1.621 + U_LETTER_NUMBER = 10,
1.622 + /** No @stable ICU 2.0 */
1.623 + U_OTHER_NUMBER = 11,
1.624 + /** Zs @stable ICU 2.0 */
1.625 + U_SPACE_SEPARATOR = 12,
1.626 + /** Zl @stable ICU 2.0 */
1.627 + U_LINE_SEPARATOR = 13,
1.628 + /** Zp @stable ICU 2.0 */
1.629 + U_PARAGRAPH_SEPARATOR = 14,
1.630 + /** Cc @stable ICU 2.0 */
1.631 + U_CONTROL_CHAR = 15,
1.632 + /** Cf @stable ICU 2.0 */
1.633 + U_FORMAT_CHAR = 16,
1.634 + /** Co @stable ICU 2.0 */
1.635 + U_PRIVATE_USE_CHAR = 17,
1.636 + /** Cs @stable ICU 2.0 */
1.637 + U_SURROGATE = 18,
1.638 + /** Pd @stable ICU 2.0 */
1.639 + U_DASH_PUNCTUATION = 19,
1.640 + /** Ps @stable ICU 2.0 */
1.641 + U_START_PUNCTUATION = 20,
1.642 + /** Pe @stable ICU 2.0 */
1.643 + U_END_PUNCTUATION = 21,
1.644 + /** Pc @stable ICU 2.0 */
1.645 + U_CONNECTOR_PUNCTUATION = 22,
1.646 + /** Po @stable ICU 2.0 */
1.647 + U_OTHER_PUNCTUATION = 23,
1.648 + /** Sm @stable ICU 2.0 */
1.649 + U_MATH_SYMBOL = 24,
1.650 + /** Sc @stable ICU 2.0 */
1.651 + U_CURRENCY_SYMBOL = 25,
1.652 + /** Sk @stable ICU 2.0 */
1.653 + U_MODIFIER_SYMBOL = 26,
1.654 + /** So @stable ICU 2.0 */
1.655 + U_OTHER_SYMBOL = 27,
1.656 + /** Pi @stable ICU 2.0 */
1.657 + U_INITIAL_PUNCTUATION = 28,
1.658 + /** Pf @stable ICU 2.0 */
1.659 + U_FINAL_PUNCTUATION = 29,
1.660 + /** One higher than the last enum UCharCategory constant. @stable ICU 2.0 */
1.661 + U_CHAR_CATEGORY_COUNT
1.662 +} UCharCategory;
1.663 +
1.664 +/**
1.665 + * U_GC_XX_MASK constants are bit flags corresponding to Unicode
1.666 + * general category values.
1.667 + * For each category, the nth bit is set if the numeric value of the
1.668 + * corresponding UCharCategory constant is n.
1.669 + *
1.670 + * There are also some U_GC_Y_MASK constants for groups of general categories
1.671 + * like L for all letter categories.
1.672 + *
1.673 + * @see u_charType
1.674 + * @see U_GET_GC_MASK
1.675 + * @see UCharCategory
1.676 + * @stable ICU 2.1
1.677 + */
1.678 +#define U_GC_CN_MASK U_MASK(U_GENERAL_OTHER_TYPES)
1.679 +
1.680 +/** Mask constant for a UCharCategory. @stable ICU 2.1 */
1.681 +#define U_GC_LU_MASK U_MASK(U_UPPERCASE_LETTER)
1.682 +/** Mask constant for a UCharCategory. @stable ICU 2.1 */
1.683 +#define U_GC_LL_MASK U_MASK(U_LOWERCASE_LETTER)
1.684 +/** Mask constant for a UCharCategory. @stable ICU 2.1 */
1.685 +#define U_GC_LT_MASK U_MASK(U_TITLECASE_LETTER)
1.686 +/** Mask constant for a UCharCategory. @stable ICU 2.1 */
1.687 +#define U_GC_LM_MASK U_MASK(U_MODIFIER_LETTER)
1.688 +/** Mask constant for a UCharCategory. @stable ICU 2.1 */
1.689 +#define U_GC_LO_MASK U_MASK(U_OTHER_LETTER)
1.690 +
1.691 +/** Mask constant for a UCharCategory. @stable ICU 2.1 */
1.692 +#define U_GC_MN_MASK U_MASK(U_NON_SPACING_MARK)
1.693 +/** Mask constant for a UCharCategory. @stable ICU 2.1 */
1.694 +#define U_GC_ME_MASK U_MASK(U_ENCLOSING_MARK)
1.695 +/** Mask constant for a UCharCategory. @stable ICU 2.1 */
1.696 +#define U_GC_MC_MASK U_MASK(U_COMBINING_SPACING_MARK)
1.697 +
1.698 +/** Mask constant for a UCharCategory. @stable ICU 2.1 */
1.699 +#define U_GC_ND_MASK U_MASK(U_DECIMAL_DIGIT_NUMBER)
1.700 +/** Mask constant for a UCharCategory. @stable ICU 2.1 */
1.701 +#define U_GC_NL_MASK U_MASK(U_LETTER_NUMBER)
1.702 +/** Mask constant for a UCharCategory. @stable ICU 2.1 */
1.703 +#define U_GC_NO_MASK U_MASK(U_OTHER_NUMBER)
1.704 +
1.705 +/** Mask constant for a UCharCategory. @stable ICU 2.1 */
1.706 +#define U_GC_ZS_MASK U_MASK(U_SPACE_SEPARATOR)
1.707 +/** Mask constant for a UCharCategory. @stable ICU 2.1 */
1.708 +#define U_GC_ZL_MASK U_MASK(U_LINE_SEPARATOR)
1.709 +/** Mask constant for a UCharCategory. @stable ICU 2.1 */
1.710 +#define U_GC_ZP_MASK U_MASK(U_PARAGRAPH_SEPARATOR)
1.711 +
1.712 +/** Mask constant for a UCharCategory. @stable ICU 2.1 */
1.713 +#define U_GC_CC_MASK U_MASK(U_CONTROL_CHAR)
1.714 +/** Mask constant for a UCharCategory. @stable ICU 2.1 */
1.715 +#define U_GC_CF_MASK U_MASK(U_FORMAT_CHAR)
1.716 +/** Mask constant for a UCharCategory. @stable ICU 2.1 */
1.717 +#define U_GC_CO_MASK U_MASK(U_PRIVATE_USE_CHAR)
1.718 +/** Mask constant for a UCharCategory. @stable ICU 2.1 */
1.719 +#define U_GC_CS_MASK U_MASK(U_SURROGATE)
1.720 +
1.721 +/** Mask constant for a UCharCategory. @stable ICU 2.1 */
1.722 +#define U_GC_PD_MASK U_MASK(U_DASH_PUNCTUATION)
1.723 +/** Mask constant for a UCharCategory. @stable ICU 2.1 */
1.724 +#define U_GC_PS_MASK U_MASK(U_START_PUNCTUATION)
1.725 +/** Mask constant for a UCharCategory. @stable ICU 2.1 */
1.726 +#define U_GC_PE_MASK U_MASK(U_END_PUNCTUATION)
1.727 +/** Mask constant for a UCharCategory. @stable ICU 2.1 */
1.728 +#define U_GC_PC_MASK U_MASK(U_CONNECTOR_PUNCTUATION)
1.729 +/** Mask constant for a UCharCategory. @stable ICU 2.1 */
1.730 +#define U_GC_PO_MASK U_MASK(U_OTHER_PUNCTUATION)
1.731 +
1.732 +/** Mask constant for a UCharCategory. @stable ICU 2.1 */
1.733 +#define U_GC_SM_MASK U_MASK(U_MATH_SYMBOL)
1.734 +/** Mask constant for a UCharCategory. @stable ICU 2.1 */
1.735 +#define U_GC_SC_MASK U_MASK(U_CURRENCY_SYMBOL)
1.736 +/** Mask constant for a UCharCategory. @stable ICU 2.1 */
1.737 +#define U_GC_SK_MASK U_MASK(U_MODIFIER_SYMBOL)
1.738 +/** Mask constant for a UCharCategory. @stable ICU 2.1 */
1.739 +#define U_GC_SO_MASK U_MASK(U_OTHER_SYMBOL)
1.740 +
1.741 +/** Mask constant for a UCharCategory. @stable ICU 2.1 */
1.742 +#define U_GC_PI_MASK U_MASK(U_INITIAL_PUNCTUATION)
1.743 +/** Mask constant for a UCharCategory. @stable ICU 2.1 */
1.744 +#define U_GC_PF_MASK U_MASK(U_FINAL_PUNCTUATION)
1.745 +
1.746 +
1.747 +/** Mask constant for multiple UCharCategory bits (L Letters). @stable ICU 2.1 */
1.748 +#define U_GC_L_MASK \
1.749 + (U_GC_LU_MASK|U_GC_LL_MASK|U_GC_LT_MASK|U_GC_LM_MASK|U_GC_LO_MASK)
1.750 +
1.751 +/** Mask constant for multiple UCharCategory bits (LC Cased Letters). @stable ICU 2.1 */
1.752 +#define U_GC_LC_MASK \
1.753 + (U_GC_LU_MASK|U_GC_LL_MASK|U_GC_LT_MASK)
1.754 +
1.755 +/** Mask constant for multiple UCharCategory bits (M Marks). @stable ICU 2.1 */
1.756 +#define U_GC_M_MASK (U_GC_MN_MASK|U_GC_ME_MASK|U_GC_MC_MASK)
1.757 +
1.758 +/** Mask constant for multiple UCharCategory bits (N Numbers). @stable ICU 2.1 */
1.759 +#define U_GC_N_MASK (U_GC_ND_MASK|U_GC_NL_MASK|U_GC_NO_MASK)
1.760 +
1.761 +/** Mask constant for multiple UCharCategory bits (Z Separators). @stable ICU 2.1 */
1.762 +#define U_GC_Z_MASK (U_GC_ZS_MASK|U_GC_ZL_MASK|U_GC_ZP_MASK)
1.763 +
1.764 +/** Mask constant for multiple UCharCategory bits (C Others). @stable ICU 2.1 */
1.765 +#define U_GC_C_MASK \
1.766 + (U_GC_CN_MASK|U_GC_CC_MASK|U_GC_CF_MASK|U_GC_CO_MASK|U_GC_CS_MASK)
1.767 +
1.768 +/** Mask constant for multiple UCharCategory bits (P Punctuation). @stable ICU 2.1 */
1.769 +#define U_GC_P_MASK \
1.770 + (U_GC_PD_MASK|U_GC_PS_MASK|U_GC_PE_MASK|U_GC_PC_MASK|U_GC_PO_MASK| \
1.771 + U_GC_PI_MASK|U_GC_PF_MASK)
1.772 +
1.773 +/** Mask constant for multiple UCharCategory bits (S Symbols). @stable ICU 2.1 */
1.774 +#define U_GC_S_MASK (U_GC_SM_MASK|U_GC_SC_MASK|U_GC_SK_MASK|U_GC_SO_MASK)
1.775 +
1.776 +/**
1.777 + * This specifies the language directional property of a character set.
1.778 + * @stable ICU 2.0
1.779 + */
1.780 +typedef enum UCharDirection {
1.781 + /*
1.782 + * Note: UCharDirection constants and their API comments are parsed by preparseucd.py.
1.783 + * It matches pairs of lines like
1.784 + * / ** <Unicode 1..3-letter Bidi_Class value> comment... * /
1.785 + * U_<[A-Z_]+> = <integer>,
1.786 + */
1.787 +
1.788 + /** L @stable ICU 2.0 */
1.789 + U_LEFT_TO_RIGHT = 0,
1.790 + /** R @stable ICU 2.0 */
1.791 + U_RIGHT_TO_LEFT = 1,
1.792 + /** EN @stable ICU 2.0 */
1.793 + U_EUROPEAN_NUMBER = 2,
1.794 + /** ES @stable ICU 2.0 */
1.795 + U_EUROPEAN_NUMBER_SEPARATOR = 3,
1.796 + /** ET @stable ICU 2.0 */
1.797 + U_EUROPEAN_NUMBER_TERMINATOR = 4,
1.798 + /** AN @stable ICU 2.0 */
1.799 + U_ARABIC_NUMBER = 5,
1.800 + /** CS @stable ICU 2.0 */
1.801 + U_COMMON_NUMBER_SEPARATOR = 6,
1.802 + /** B @stable ICU 2.0 */
1.803 + U_BLOCK_SEPARATOR = 7,
1.804 + /** S @stable ICU 2.0 */
1.805 + U_SEGMENT_SEPARATOR = 8,
1.806 + /** WS @stable ICU 2.0 */
1.807 + U_WHITE_SPACE_NEUTRAL = 9,
1.808 + /** ON @stable ICU 2.0 */
1.809 + U_OTHER_NEUTRAL = 10,
1.810 + /** LRE @stable ICU 2.0 */
1.811 + U_LEFT_TO_RIGHT_EMBEDDING = 11,
1.812 + /** LRO @stable ICU 2.0 */
1.813 + U_LEFT_TO_RIGHT_OVERRIDE = 12,
1.814 + /** AL @stable ICU 2.0 */
1.815 + U_RIGHT_TO_LEFT_ARABIC = 13,
1.816 + /** RLE @stable ICU 2.0 */
1.817 + U_RIGHT_TO_LEFT_EMBEDDING = 14,
1.818 + /** RLO @stable ICU 2.0 */
1.819 + U_RIGHT_TO_LEFT_OVERRIDE = 15,
1.820 + /** PDF @stable ICU 2.0 */
1.821 + U_POP_DIRECTIONAL_FORMAT = 16,
1.822 + /** NSM @stable ICU 2.0 */
1.823 + U_DIR_NON_SPACING_MARK = 17,
1.824 + /** BN @stable ICU 2.0 */
1.825 + U_BOUNDARY_NEUTRAL = 18,
1.826 + /** FSI @stable ICU 52 */
1.827 + U_FIRST_STRONG_ISOLATE = 19,
1.828 + /** LRI @stable ICU 52 */
1.829 + U_LEFT_TO_RIGHT_ISOLATE = 20,
1.830 + /** RLI @stable ICU 52 */
1.831 + U_RIGHT_TO_LEFT_ISOLATE = 21,
1.832 + /** PDI @stable ICU 52 */
1.833 + U_POP_DIRECTIONAL_ISOLATE = 22,
1.834 + /** @stable ICU 2.0 */
1.835 + U_CHAR_DIRECTION_COUNT
1.836 +} UCharDirection;
1.837 +
1.838 +/**
1.839 + * Bidi Paired Bracket Type constants.
1.840 + *
1.841 + * @see UCHAR_BIDI_PAIRED_BRACKET_TYPE
1.842 + * @stable ICU 52
1.843 + */
1.844 +typedef enum UBidiPairedBracketType {
1.845 + /*
1.846 + * Note: UBidiPairedBracketType constants are parsed by preparseucd.py.
1.847 + * It matches lines like
1.848 + * U_BPT_<Unicode Bidi_Paired_Bracket_Type value name>
1.849 + */
1.850 +
1.851 + /** Not a paired bracket. @stable ICU 52 */
1.852 + U_BPT_NONE,
1.853 + /** Open paired bracket. @stable ICU 52 */
1.854 + U_BPT_OPEN,
1.855 + /** Close paired bracket. @stable ICU 52 */
1.856 + U_BPT_CLOSE,
1.857 + /** @stable ICU 52 */
1.858 + U_BPT_COUNT /* 3 */
1.859 +} UBidiPairedBracketType;
1.860 +
1.861 +/**
1.862 + * Constants for Unicode blocks, see the Unicode Data file Blocks.txt
1.863 + * @stable ICU 2.0
1.864 + */
1.865 +enum UBlockCode {
1.866 + /*
1.867 + * Note: UBlockCode constants are parsed by preparseucd.py.
1.868 + * It matches lines like
1.869 + * UBLOCK_<Unicode Block value name> = <integer>,
1.870 + */
1.871 +
1.872 + /** New No_Block value in Unicode 4. @stable ICU 2.6 */
1.873 + UBLOCK_NO_BLOCK = 0, /*[none]*/ /* Special range indicating No_Block */
1.874 +
1.875 + /** @stable ICU 2.0 */
1.876 + UBLOCK_BASIC_LATIN = 1, /*[0000]*/
1.877 +
1.878 + /** @stable ICU 2.0 */
1.879 + UBLOCK_LATIN_1_SUPPLEMENT=2, /*[0080]*/
1.880 +
1.881 + /** @stable ICU 2.0 */
1.882 + UBLOCK_LATIN_EXTENDED_A =3, /*[0100]*/
1.883 +
1.884 + /** @stable ICU 2.0 */
1.885 + UBLOCK_LATIN_EXTENDED_B =4, /*[0180]*/
1.886 +
1.887 + /** @stable ICU 2.0 */
1.888 + UBLOCK_IPA_EXTENSIONS =5, /*[0250]*/
1.889 +
1.890 + /** @stable ICU 2.0 */
1.891 + UBLOCK_SPACING_MODIFIER_LETTERS =6, /*[02B0]*/
1.892 +
1.893 + /** @stable ICU 2.0 */
1.894 + UBLOCK_COMBINING_DIACRITICAL_MARKS =7, /*[0300]*/
1.895 +
1.896 + /**
1.897 + * Unicode 3.2 renames this block to "Greek and Coptic".
1.898 + * @stable ICU 2.0
1.899 + */
1.900 + UBLOCK_GREEK =8, /*[0370]*/
1.901 +
1.902 + /** @stable ICU 2.0 */
1.903 + UBLOCK_CYRILLIC =9, /*[0400]*/
1.904 +
1.905 + /** @stable ICU 2.0 */
1.906 + UBLOCK_ARMENIAN =10, /*[0530]*/
1.907 +
1.908 + /** @stable ICU 2.0 */
1.909 + UBLOCK_HEBREW =11, /*[0590]*/
1.910 +
1.911 + /** @stable ICU 2.0 */
1.912 + UBLOCK_ARABIC =12, /*[0600]*/
1.913 +
1.914 + /** @stable ICU 2.0 */
1.915 + UBLOCK_SYRIAC =13, /*[0700]*/
1.916 +
1.917 + /** @stable ICU 2.0 */
1.918 + UBLOCK_THAANA =14, /*[0780]*/
1.919 +
1.920 + /** @stable ICU 2.0 */
1.921 + UBLOCK_DEVANAGARI =15, /*[0900]*/
1.922 +
1.923 + /** @stable ICU 2.0 */
1.924 + UBLOCK_BENGALI =16, /*[0980]*/
1.925 +
1.926 + /** @stable ICU 2.0 */
1.927 + UBLOCK_GURMUKHI =17, /*[0A00]*/
1.928 +
1.929 + /** @stable ICU 2.0 */
1.930 + UBLOCK_GUJARATI =18, /*[0A80]*/
1.931 +
1.932 + /** @stable ICU 2.0 */
1.933 + UBLOCK_ORIYA =19, /*[0B00]*/
1.934 +
1.935 + /** @stable ICU 2.0 */
1.936 + UBLOCK_TAMIL =20, /*[0B80]*/
1.937 +
1.938 + /** @stable ICU 2.0 */
1.939 + UBLOCK_TELUGU =21, /*[0C00]*/
1.940 +
1.941 + /** @stable ICU 2.0 */
1.942 + UBLOCK_KANNADA =22, /*[0C80]*/
1.943 +
1.944 + /** @stable ICU 2.0 */
1.945 + UBLOCK_MALAYALAM =23, /*[0D00]*/
1.946 +
1.947 + /** @stable ICU 2.0 */
1.948 + UBLOCK_SINHALA =24, /*[0D80]*/
1.949 +
1.950 + /** @stable ICU 2.0 */
1.951 + UBLOCK_THAI =25, /*[0E00]*/
1.952 +
1.953 + /** @stable ICU 2.0 */
1.954 + UBLOCK_LAO =26, /*[0E80]*/
1.955 +
1.956 + /** @stable ICU 2.0 */
1.957 + UBLOCK_TIBETAN =27, /*[0F00]*/
1.958 +
1.959 + /** @stable ICU 2.0 */
1.960 + UBLOCK_MYANMAR =28, /*[1000]*/
1.961 +
1.962 + /** @stable ICU 2.0 */
1.963 + UBLOCK_GEORGIAN =29, /*[10A0]*/
1.964 +
1.965 + /** @stable ICU 2.0 */
1.966 + UBLOCK_HANGUL_JAMO =30, /*[1100]*/
1.967 +
1.968 + /** @stable ICU 2.0 */
1.969 + UBLOCK_ETHIOPIC =31, /*[1200]*/
1.970 +
1.971 + /** @stable ICU 2.0 */
1.972 + UBLOCK_CHEROKEE =32, /*[13A0]*/
1.973 +
1.974 + /** @stable ICU 2.0 */
1.975 + UBLOCK_UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS =33, /*[1400]*/
1.976 +
1.977 + /** @stable ICU 2.0 */
1.978 + UBLOCK_OGHAM =34, /*[1680]*/
1.979 +
1.980 + /** @stable ICU 2.0 */
1.981 + UBLOCK_RUNIC =35, /*[16A0]*/
1.982 +
1.983 + /** @stable ICU 2.0 */
1.984 + UBLOCK_KHMER =36, /*[1780]*/
1.985 +
1.986 + /** @stable ICU 2.0 */
1.987 + UBLOCK_MONGOLIAN =37, /*[1800]*/
1.988 +
1.989 + /** @stable ICU 2.0 */
1.990 + UBLOCK_LATIN_EXTENDED_ADDITIONAL =38, /*[1E00]*/
1.991 +
1.992 + /** @stable ICU 2.0 */
1.993 + UBLOCK_GREEK_EXTENDED =39, /*[1F00]*/
1.994 +
1.995 + /** @stable ICU 2.0 */
1.996 + UBLOCK_GENERAL_PUNCTUATION =40, /*[2000]*/
1.997 +
1.998 + /** @stable ICU 2.0 */
1.999 + UBLOCK_SUPERSCRIPTS_AND_SUBSCRIPTS =41, /*[2070]*/
1.1000 +
1.1001 + /** @stable ICU 2.0 */
1.1002 + UBLOCK_CURRENCY_SYMBOLS =42, /*[20A0]*/
1.1003 +
1.1004 + /**
1.1005 + * Unicode 3.2 renames this block to "Combining Diacritical Marks for Symbols".
1.1006 + * @stable ICU 2.0
1.1007 + */
1.1008 + UBLOCK_COMBINING_MARKS_FOR_SYMBOLS =43, /*[20D0]*/
1.1009 +
1.1010 + /** @stable ICU 2.0 */
1.1011 + UBLOCK_LETTERLIKE_SYMBOLS =44, /*[2100]*/
1.1012 +
1.1013 + /** @stable ICU 2.0 */
1.1014 + UBLOCK_NUMBER_FORMS =45, /*[2150]*/
1.1015 +
1.1016 + /** @stable ICU 2.0 */
1.1017 + UBLOCK_ARROWS =46, /*[2190]*/
1.1018 +
1.1019 + /** @stable ICU 2.0 */
1.1020 + UBLOCK_MATHEMATICAL_OPERATORS =47, /*[2200]*/
1.1021 +
1.1022 + /** @stable ICU 2.0 */
1.1023 + UBLOCK_MISCELLANEOUS_TECHNICAL =48, /*[2300]*/
1.1024 +
1.1025 + /** @stable ICU 2.0 */
1.1026 + UBLOCK_CONTROL_PICTURES =49, /*[2400]*/
1.1027 +
1.1028 + /** @stable ICU 2.0 */
1.1029 + UBLOCK_OPTICAL_CHARACTER_RECOGNITION =50, /*[2440]*/
1.1030 +
1.1031 + /** @stable ICU 2.0 */
1.1032 + UBLOCK_ENCLOSED_ALPHANUMERICS =51, /*[2460]*/
1.1033 +
1.1034 + /** @stable ICU 2.0 */
1.1035 + UBLOCK_BOX_DRAWING =52, /*[2500]*/
1.1036 +
1.1037 + /** @stable ICU 2.0 */
1.1038 + UBLOCK_BLOCK_ELEMENTS =53, /*[2580]*/
1.1039 +
1.1040 + /** @stable ICU 2.0 */
1.1041 + UBLOCK_GEOMETRIC_SHAPES =54, /*[25A0]*/
1.1042 +
1.1043 + /** @stable ICU 2.0 */
1.1044 + UBLOCK_MISCELLANEOUS_SYMBOLS =55, /*[2600]*/
1.1045 +
1.1046 + /** @stable ICU 2.0 */
1.1047 + UBLOCK_DINGBATS =56, /*[2700]*/
1.1048 +
1.1049 + /** @stable ICU 2.0 */
1.1050 + UBLOCK_BRAILLE_PATTERNS =57, /*[2800]*/
1.1051 +
1.1052 + /** @stable ICU 2.0 */
1.1053 + UBLOCK_CJK_RADICALS_SUPPLEMENT =58, /*[2E80]*/
1.1054 +
1.1055 + /** @stable ICU 2.0 */
1.1056 + UBLOCK_KANGXI_RADICALS =59, /*[2F00]*/
1.1057 +
1.1058 + /** @stable ICU 2.0 */
1.1059 + UBLOCK_IDEOGRAPHIC_DESCRIPTION_CHARACTERS =60, /*[2FF0]*/
1.1060 +
1.1061 + /** @stable ICU 2.0 */
1.1062 + UBLOCK_CJK_SYMBOLS_AND_PUNCTUATION =61, /*[3000]*/
1.1063 +
1.1064 + /** @stable ICU 2.0 */
1.1065 + UBLOCK_HIRAGANA =62, /*[3040]*/
1.1066 +
1.1067 + /** @stable ICU 2.0 */
1.1068 + UBLOCK_KATAKANA =63, /*[30A0]*/
1.1069 +
1.1070 + /** @stable ICU 2.0 */
1.1071 + UBLOCK_BOPOMOFO =64, /*[3100]*/
1.1072 +
1.1073 + /** @stable ICU 2.0 */
1.1074 + UBLOCK_HANGUL_COMPATIBILITY_JAMO =65, /*[3130]*/
1.1075 +
1.1076 + /** @stable ICU 2.0 */
1.1077 + UBLOCK_KANBUN =66, /*[3190]*/
1.1078 +
1.1079 + /** @stable ICU 2.0 */
1.1080 + UBLOCK_BOPOMOFO_EXTENDED =67, /*[31A0]*/
1.1081 +
1.1082 + /** @stable ICU 2.0 */
1.1083 + UBLOCK_ENCLOSED_CJK_LETTERS_AND_MONTHS =68, /*[3200]*/
1.1084 +
1.1085 + /** @stable ICU 2.0 */
1.1086 + UBLOCK_CJK_COMPATIBILITY =69, /*[3300]*/
1.1087 +
1.1088 + /** @stable ICU 2.0 */
1.1089 + UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_A =70, /*[3400]*/
1.1090 +
1.1091 + /** @stable ICU 2.0 */
1.1092 + UBLOCK_CJK_UNIFIED_IDEOGRAPHS =71, /*[4E00]*/
1.1093 +
1.1094 + /** @stable ICU 2.0 */
1.1095 + UBLOCK_YI_SYLLABLES =72, /*[A000]*/
1.1096 +
1.1097 + /** @stable ICU 2.0 */
1.1098 + UBLOCK_YI_RADICALS =73, /*[A490]*/
1.1099 +
1.1100 + /** @stable ICU 2.0 */
1.1101 + UBLOCK_HANGUL_SYLLABLES =74, /*[AC00]*/
1.1102 +
1.1103 + /** @stable ICU 2.0 */
1.1104 + UBLOCK_HIGH_SURROGATES =75, /*[D800]*/
1.1105 +
1.1106 + /** @stable ICU 2.0 */
1.1107 + UBLOCK_HIGH_PRIVATE_USE_SURROGATES =76, /*[DB80]*/
1.1108 +
1.1109 + /** @stable ICU 2.0 */
1.1110 + UBLOCK_LOW_SURROGATES =77, /*[DC00]*/
1.1111 +
1.1112 + /**
1.1113 + * Same as UBLOCK_PRIVATE_USE.
1.1114 + * Until Unicode 3.1.1, the corresponding block name was "Private Use",
1.1115 + * and multiple code point ranges had this block.
1.1116 + * Unicode 3.2 renames the block for the BMP PUA to "Private Use Area" and
1.1117 + * adds separate blocks for the supplementary PUAs.
1.1118 + *
1.1119 + * @stable ICU 2.0
1.1120 + */
1.1121 + UBLOCK_PRIVATE_USE_AREA =78, /*[E000]*/
1.1122 + /**
1.1123 + * Same as UBLOCK_PRIVATE_USE_AREA.
1.1124 + * Until Unicode 3.1.1, the corresponding block name was "Private Use",
1.1125 + * and multiple code point ranges had this block.
1.1126 + * Unicode 3.2 renames the block for the BMP PUA to "Private Use Area" and
1.1127 + * adds separate blocks for the supplementary PUAs.
1.1128 + *
1.1129 + * @stable ICU 2.0
1.1130 + */
1.1131 + UBLOCK_PRIVATE_USE = UBLOCK_PRIVATE_USE_AREA,
1.1132 +
1.1133 + /** @stable ICU 2.0 */
1.1134 + UBLOCK_CJK_COMPATIBILITY_IDEOGRAPHS =79, /*[F900]*/
1.1135 +
1.1136 + /** @stable ICU 2.0 */
1.1137 + UBLOCK_ALPHABETIC_PRESENTATION_FORMS =80, /*[FB00]*/
1.1138 +
1.1139 + /** @stable ICU 2.0 */
1.1140 + UBLOCK_ARABIC_PRESENTATION_FORMS_A =81, /*[FB50]*/
1.1141 +
1.1142 + /** @stable ICU 2.0 */
1.1143 + UBLOCK_COMBINING_HALF_MARKS =82, /*[FE20]*/
1.1144 +
1.1145 + /** @stable ICU 2.0 */
1.1146 + UBLOCK_CJK_COMPATIBILITY_FORMS =83, /*[FE30]*/
1.1147 +
1.1148 + /** @stable ICU 2.0 */
1.1149 + UBLOCK_SMALL_FORM_VARIANTS =84, /*[FE50]*/
1.1150 +
1.1151 + /** @stable ICU 2.0 */
1.1152 + UBLOCK_ARABIC_PRESENTATION_FORMS_B =85, /*[FE70]*/
1.1153 +
1.1154 + /** @stable ICU 2.0 */
1.1155 + UBLOCK_SPECIALS =86, /*[FFF0]*/
1.1156 +
1.1157 + /** @stable ICU 2.0 */
1.1158 + UBLOCK_HALFWIDTH_AND_FULLWIDTH_FORMS =87, /*[FF00]*/
1.1159 +
1.1160 + /* New blocks in Unicode 3.1 */
1.1161 +
1.1162 + /** @stable ICU 2.0 */
1.1163 + UBLOCK_OLD_ITALIC = 88, /*[10300]*/
1.1164 + /** @stable ICU 2.0 */
1.1165 + UBLOCK_GOTHIC = 89, /*[10330]*/
1.1166 + /** @stable ICU 2.0 */
1.1167 + UBLOCK_DESERET = 90, /*[10400]*/
1.1168 + /** @stable ICU 2.0 */
1.1169 + UBLOCK_BYZANTINE_MUSICAL_SYMBOLS = 91, /*[1D000]*/
1.1170 + /** @stable ICU 2.0 */
1.1171 + UBLOCK_MUSICAL_SYMBOLS = 92, /*[1D100]*/
1.1172 + /** @stable ICU 2.0 */
1.1173 + UBLOCK_MATHEMATICAL_ALPHANUMERIC_SYMBOLS = 93, /*[1D400]*/
1.1174 + /** @stable ICU 2.0 */
1.1175 + UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_B = 94, /*[20000]*/
1.1176 + /** @stable ICU 2.0 */
1.1177 + UBLOCK_CJK_COMPATIBILITY_IDEOGRAPHS_SUPPLEMENT = 95, /*[2F800]*/
1.1178 + /** @stable ICU 2.0 */
1.1179 + UBLOCK_TAGS = 96, /*[E0000]*/
1.1180 +
1.1181 + /* New blocks in Unicode 3.2 */
1.1182 +
1.1183 + /** @stable ICU 3.0 */
1.1184 + UBLOCK_CYRILLIC_SUPPLEMENT = 97, /*[0500]*/
1.1185 + /**
1.1186 + * Unicode 4.0.1 renames the "Cyrillic Supplementary" block to "Cyrillic Supplement".
1.1187 + * @stable ICU 2.2
1.1188 + */
1.1189 + UBLOCK_CYRILLIC_SUPPLEMENTARY = UBLOCK_CYRILLIC_SUPPLEMENT,
1.1190 + /** @stable ICU 2.2 */
1.1191 + UBLOCK_TAGALOG = 98, /*[1700]*/
1.1192 + /** @stable ICU 2.2 */
1.1193 + UBLOCK_HANUNOO = 99, /*[1720]*/
1.1194 + /** @stable ICU 2.2 */
1.1195 + UBLOCK_BUHID = 100, /*[1740]*/
1.1196 + /** @stable ICU 2.2 */
1.1197 + UBLOCK_TAGBANWA = 101, /*[1760]*/
1.1198 + /** @stable ICU 2.2 */
1.1199 + UBLOCK_MISCELLANEOUS_MATHEMATICAL_SYMBOLS_A = 102, /*[27C0]*/
1.1200 + /** @stable ICU 2.2 */
1.1201 + UBLOCK_SUPPLEMENTAL_ARROWS_A = 103, /*[27F0]*/
1.1202 + /** @stable ICU 2.2 */
1.1203 + UBLOCK_SUPPLEMENTAL_ARROWS_B = 104, /*[2900]*/
1.1204 + /** @stable ICU 2.2 */
1.1205 + UBLOCK_MISCELLANEOUS_MATHEMATICAL_SYMBOLS_B = 105, /*[2980]*/
1.1206 + /** @stable ICU 2.2 */
1.1207 + UBLOCK_SUPPLEMENTAL_MATHEMATICAL_OPERATORS = 106, /*[2A00]*/
1.1208 + /** @stable ICU 2.2 */
1.1209 + UBLOCK_KATAKANA_PHONETIC_EXTENSIONS = 107, /*[31F0]*/
1.1210 + /** @stable ICU 2.2 */
1.1211 + UBLOCK_VARIATION_SELECTORS = 108, /*[FE00]*/
1.1212 + /** @stable ICU 2.2 */
1.1213 + UBLOCK_SUPPLEMENTARY_PRIVATE_USE_AREA_A = 109, /*[F0000]*/
1.1214 + /** @stable ICU 2.2 */
1.1215 + UBLOCK_SUPPLEMENTARY_PRIVATE_USE_AREA_B = 110, /*[100000]*/
1.1216 +
1.1217 + /* New blocks in Unicode 4 */
1.1218 +
1.1219 + /** @stable ICU 2.6 */
1.1220 + UBLOCK_LIMBU = 111, /*[1900]*/
1.1221 + /** @stable ICU 2.6 */
1.1222 + UBLOCK_TAI_LE = 112, /*[1950]*/
1.1223 + /** @stable ICU 2.6 */
1.1224 + UBLOCK_KHMER_SYMBOLS = 113, /*[19E0]*/
1.1225 + /** @stable ICU 2.6 */
1.1226 + UBLOCK_PHONETIC_EXTENSIONS = 114, /*[1D00]*/
1.1227 + /** @stable ICU 2.6 */
1.1228 + UBLOCK_MISCELLANEOUS_SYMBOLS_AND_ARROWS = 115, /*[2B00]*/
1.1229 + /** @stable ICU 2.6 */
1.1230 + UBLOCK_YIJING_HEXAGRAM_SYMBOLS = 116, /*[4DC0]*/
1.1231 + /** @stable ICU 2.6 */
1.1232 + UBLOCK_LINEAR_B_SYLLABARY = 117, /*[10000]*/
1.1233 + /** @stable ICU 2.6 */
1.1234 + UBLOCK_LINEAR_B_IDEOGRAMS = 118, /*[10080]*/
1.1235 + /** @stable ICU 2.6 */
1.1236 + UBLOCK_AEGEAN_NUMBERS = 119, /*[10100]*/
1.1237 + /** @stable ICU 2.6 */
1.1238 + UBLOCK_UGARITIC = 120, /*[10380]*/
1.1239 + /** @stable ICU 2.6 */
1.1240 + UBLOCK_SHAVIAN = 121, /*[10450]*/
1.1241 + /** @stable ICU 2.6 */
1.1242 + UBLOCK_OSMANYA = 122, /*[10480]*/
1.1243 + /** @stable ICU 2.6 */
1.1244 + UBLOCK_CYPRIOT_SYLLABARY = 123, /*[10800]*/
1.1245 + /** @stable ICU 2.6 */
1.1246 + UBLOCK_TAI_XUAN_JING_SYMBOLS = 124, /*[1D300]*/
1.1247 + /** @stable ICU 2.6 */
1.1248 + UBLOCK_VARIATION_SELECTORS_SUPPLEMENT = 125, /*[E0100]*/
1.1249 +
1.1250 + /* New blocks in Unicode 4.1 */
1.1251 +
1.1252 + /** @stable ICU 3.4 */
1.1253 + UBLOCK_ANCIENT_GREEK_MUSICAL_NOTATION = 126, /*[1D200]*/
1.1254 + /** @stable ICU 3.4 */
1.1255 + UBLOCK_ANCIENT_GREEK_NUMBERS = 127, /*[10140]*/
1.1256 + /** @stable ICU 3.4 */
1.1257 + UBLOCK_ARABIC_SUPPLEMENT = 128, /*[0750]*/
1.1258 + /** @stable ICU 3.4 */
1.1259 + UBLOCK_BUGINESE = 129, /*[1A00]*/
1.1260 + /** @stable ICU 3.4 */
1.1261 + UBLOCK_CJK_STROKES = 130, /*[31C0]*/
1.1262 + /** @stable ICU 3.4 */
1.1263 + UBLOCK_COMBINING_DIACRITICAL_MARKS_SUPPLEMENT = 131, /*[1DC0]*/
1.1264 + /** @stable ICU 3.4 */
1.1265 + UBLOCK_COPTIC = 132, /*[2C80]*/
1.1266 + /** @stable ICU 3.4 */
1.1267 + UBLOCK_ETHIOPIC_EXTENDED = 133, /*[2D80]*/
1.1268 + /** @stable ICU 3.4 */
1.1269 + UBLOCK_ETHIOPIC_SUPPLEMENT = 134, /*[1380]*/
1.1270 + /** @stable ICU 3.4 */
1.1271 + UBLOCK_GEORGIAN_SUPPLEMENT = 135, /*[2D00]*/
1.1272 + /** @stable ICU 3.4 */
1.1273 + UBLOCK_GLAGOLITIC = 136, /*[2C00]*/
1.1274 + /** @stable ICU 3.4 */
1.1275 + UBLOCK_KHAROSHTHI = 137, /*[10A00]*/
1.1276 + /** @stable ICU 3.4 */
1.1277 + UBLOCK_MODIFIER_TONE_LETTERS = 138, /*[A700]*/
1.1278 + /** @stable ICU 3.4 */
1.1279 + UBLOCK_NEW_TAI_LUE = 139, /*[1980]*/
1.1280 + /** @stable ICU 3.4 */
1.1281 + UBLOCK_OLD_PERSIAN = 140, /*[103A0]*/
1.1282 + /** @stable ICU 3.4 */
1.1283 + UBLOCK_PHONETIC_EXTENSIONS_SUPPLEMENT = 141, /*[1D80]*/
1.1284 + /** @stable ICU 3.4 */
1.1285 + UBLOCK_SUPPLEMENTAL_PUNCTUATION = 142, /*[2E00]*/
1.1286 + /** @stable ICU 3.4 */
1.1287 + UBLOCK_SYLOTI_NAGRI = 143, /*[A800]*/
1.1288 + /** @stable ICU 3.4 */
1.1289 + UBLOCK_TIFINAGH = 144, /*[2D30]*/
1.1290 + /** @stable ICU 3.4 */
1.1291 + UBLOCK_VERTICAL_FORMS = 145, /*[FE10]*/
1.1292 +
1.1293 + /* New blocks in Unicode 5.0 */
1.1294 +
1.1295 + /** @stable ICU 3.6 */
1.1296 + UBLOCK_NKO = 146, /*[07C0]*/
1.1297 + /** @stable ICU 3.6 */
1.1298 + UBLOCK_BALINESE = 147, /*[1B00]*/
1.1299 + /** @stable ICU 3.6 */
1.1300 + UBLOCK_LATIN_EXTENDED_C = 148, /*[2C60]*/
1.1301 + /** @stable ICU 3.6 */
1.1302 + UBLOCK_LATIN_EXTENDED_D = 149, /*[A720]*/
1.1303 + /** @stable ICU 3.6 */
1.1304 + UBLOCK_PHAGS_PA = 150, /*[A840]*/
1.1305 + /** @stable ICU 3.6 */
1.1306 + UBLOCK_PHOENICIAN = 151, /*[10900]*/
1.1307 + /** @stable ICU 3.6 */
1.1308 + UBLOCK_CUNEIFORM = 152, /*[12000]*/
1.1309 + /** @stable ICU 3.6 */
1.1310 + UBLOCK_CUNEIFORM_NUMBERS_AND_PUNCTUATION = 153, /*[12400]*/
1.1311 + /** @stable ICU 3.6 */
1.1312 + UBLOCK_COUNTING_ROD_NUMERALS = 154, /*[1D360]*/
1.1313 +
1.1314 + /* New blocks in Unicode 5.1 */
1.1315 +
1.1316 + /** @stable ICU 4.0 */
1.1317 + UBLOCK_SUNDANESE = 155, /*[1B80]*/
1.1318 + /** @stable ICU 4.0 */
1.1319 + UBLOCK_LEPCHA = 156, /*[1C00]*/
1.1320 + /** @stable ICU 4.0 */
1.1321 + UBLOCK_OL_CHIKI = 157, /*[1C50]*/
1.1322 + /** @stable ICU 4.0 */
1.1323 + UBLOCK_CYRILLIC_EXTENDED_A = 158, /*[2DE0]*/
1.1324 + /** @stable ICU 4.0 */
1.1325 + UBLOCK_VAI = 159, /*[A500]*/
1.1326 + /** @stable ICU 4.0 */
1.1327 + UBLOCK_CYRILLIC_EXTENDED_B = 160, /*[A640]*/
1.1328 + /** @stable ICU 4.0 */
1.1329 + UBLOCK_SAURASHTRA = 161, /*[A880]*/
1.1330 + /** @stable ICU 4.0 */
1.1331 + UBLOCK_KAYAH_LI = 162, /*[A900]*/
1.1332 + /** @stable ICU 4.0 */
1.1333 + UBLOCK_REJANG = 163, /*[A930]*/
1.1334 + /** @stable ICU 4.0 */
1.1335 + UBLOCK_CHAM = 164, /*[AA00]*/
1.1336 + /** @stable ICU 4.0 */
1.1337 + UBLOCK_ANCIENT_SYMBOLS = 165, /*[10190]*/
1.1338 + /** @stable ICU 4.0 */
1.1339 + UBLOCK_PHAISTOS_DISC = 166, /*[101D0]*/
1.1340 + /** @stable ICU 4.0 */
1.1341 + UBLOCK_LYCIAN = 167, /*[10280]*/
1.1342 + /** @stable ICU 4.0 */
1.1343 + UBLOCK_CARIAN = 168, /*[102A0]*/
1.1344 + /** @stable ICU 4.0 */
1.1345 + UBLOCK_LYDIAN = 169, /*[10920]*/
1.1346 + /** @stable ICU 4.0 */
1.1347 + UBLOCK_MAHJONG_TILES = 170, /*[1F000]*/
1.1348 + /** @stable ICU 4.0 */
1.1349 + UBLOCK_DOMINO_TILES = 171, /*[1F030]*/
1.1350 +
1.1351 + /* New blocks in Unicode 5.2 */
1.1352 +
1.1353 + /** @stable ICU 4.4 */
1.1354 + UBLOCK_SAMARITAN = 172, /*[0800]*/
1.1355 + /** @stable ICU 4.4 */
1.1356 + UBLOCK_UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS_EXTENDED = 173, /*[18B0]*/
1.1357 + /** @stable ICU 4.4 */
1.1358 + UBLOCK_TAI_THAM = 174, /*[1A20]*/
1.1359 + /** @stable ICU 4.4 */
1.1360 + UBLOCK_VEDIC_EXTENSIONS = 175, /*[1CD0]*/
1.1361 + /** @stable ICU 4.4 */
1.1362 + UBLOCK_LISU = 176, /*[A4D0]*/
1.1363 + /** @stable ICU 4.4 */
1.1364 + UBLOCK_BAMUM = 177, /*[A6A0]*/
1.1365 + /** @stable ICU 4.4 */
1.1366 + UBLOCK_COMMON_INDIC_NUMBER_FORMS = 178, /*[A830]*/
1.1367 + /** @stable ICU 4.4 */
1.1368 + UBLOCK_DEVANAGARI_EXTENDED = 179, /*[A8E0]*/
1.1369 + /** @stable ICU 4.4 */
1.1370 + UBLOCK_HANGUL_JAMO_EXTENDED_A = 180, /*[A960]*/
1.1371 + /** @stable ICU 4.4 */
1.1372 + UBLOCK_JAVANESE = 181, /*[A980]*/
1.1373 + /** @stable ICU 4.4 */
1.1374 + UBLOCK_MYANMAR_EXTENDED_A = 182, /*[AA60]*/
1.1375 + /** @stable ICU 4.4 */
1.1376 + UBLOCK_TAI_VIET = 183, /*[AA80]*/
1.1377 + /** @stable ICU 4.4 */
1.1378 + UBLOCK_MEETEI_MAYEK = 184, /*[ABC0]*/
1.1379 + /** @stable ICU 4.4 */
1.1380 + UBLOCK_HANGUL_JAMO_EXTENDED_B = 185, /*[D7B0]*/
1.1381 + /** @stable ICU 4.4 */
1.1382 + UBLOCK_IMPERIAL_ARAMAIC = 186, /*[10840]*/
1.1383 + /** @stable ICU 4.4 */
1.1384 + UBLOCK_OLD_SOUTH_ARABIAN = 187, /*[10A60]*/
1.1385 + /** @stable ICU 4.4 */
1.1386 + UBLOCK_AVESTAN = 188, /*[10B00]*/
1.1387 + /** @stable ICU 4.4 */
1.1388 + UBLOCK_INSCRIPTIONAL_PARTHIAN = 189, /*[10B40]*/
1.1389 + /** @stable ICU 4.4 */
1.1390 + UBLOCK_INSCRIPTIONAL_PAHLAVI = 190, /*[10B60]*/
1.1391 + /** @stable ICU 4.4 */
1.1392 + UBLOCK_OLD_TURKIC = 191, /*[10C00]*/
1.1393 + /** @stable ICU 4.4 */
1.1394 + UBLOCK_RUMI_NUMERAL_SYMBOLS = 192, /*[10E60]*/
1.1395 + /** @stable ICU 4.4 */
1.1396 + UBLOCK_KAITHI = 193, /*[11080]*/
1.1397 + /** @stable ICU 4.4 */
1.1398 + UBLOCK_EGYPTIAN_HIEROGLYPHS = 194, /*[13000]*/
1.1399 + /** @stable ICU 4.4 */
1.1400 + UBLOCK_ENCLOSED_ALPHANUMERIC_SUPPLEMENT = 195, /*[1F100]*/
1.1401 + /** @stable ICU 4.4 */
1.1402 + UBLOCK_ENCLOSED_IDEOGRAPHIC_SUPPLEMENT = 196, /*[1F200]*/
1.1403 + /** @stable ICU 4.4 */
1.1404 + UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_C = 197, /*[2A700]*/
1.1405 +
1.1406 + /* New blocks in Unicode 6.0 */
1.1407 +
1.1408 + /** @stable ICU 4.6 */
1.1409 + UBLOCK_MANDAIC = 198, /*[0840]*/
1.1410 + /** @stable ICU 4.6 */
1.1411 + UBLOCK_BATAK = 199, /*[1BC0]*/
1.1412 + /** @stable ICU 4.6 */
1.1413 + UBLOCK_ETHIOPIC_EXTENDED_A = 200, /*[AB00]*/
1.1414 + /** @stable ICU 4.6 */
1.1415 + UBLOCK_BRAHMI = 201, /*[11000]*/
1.1416 + /** @stable ICU 4.6 */
1.1417 + UBLOCK_BAMUM_SUPPLEMENT = 202, /*[16800]*/
1.1418 + /** @stable ICU 4.6 */
1.1419 + UBLOCK_KANA_SUPPLEMENT = 203, /*[1B000]*/
1.1420 + /** @stable ICU 4.6 */
1.1421 + UBLOCK_PLAYING_CARDS = 204, /*[1F0A0]*/
1.1422 + /** @stable ICU 4.6 */
1.1423 + UBLOCK_MISCELLANEOUS_SYMBOLS_AND_PICTOGRAPHS = 205, /*[1F300]*/
1.1424 + /** @stable ICU 4.6 */
1.1425 + UBLOCK_EMOTICONS = 206, /*[1F600]*/
1.1426 + /** @stable ICU 4.6 */
1.1427 + UBLOCK_TRANSPORT_AND_MAP_SYMBOLS = 207, /*[1F680]*/
1.1428 + /** @stable ICU 4.6 */
1.1429 + UBLOCK_ALCHEMICAL_SYMBOLS = 208, /*[1F700]*/
1.1430 + /** @stable ICU 4.6 */
1.1431 + UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_D = 209, /*[2B740]*/
1.1432 +
1.1433 + /* New blocks in Unicode 6.1 */
1.1434 +
1.1435 + /** @stable ICU 49 */
1.1436 + UBLOCK_ARABIC_EXTENDED_A = 210, /*[08A0]*/
1.1437 + /** @stable ICU 49 */
1.1438 + UBLOCK_ARABIC_MATHEMATICAL_ALPHABETIC_SYMBOLS = 211, /*[1EE00]*/
1.1439 + /** @stable ICU 49 */
1.1440 + UBLOCK_CHAKMA = 212, /*[11100]*/
1.1441 + /** @stable ICU 49 */
1.1442 + UBLOCK_MEETEI_MAYEK_EXTENSIONS = 213, /*[AAE0]*/
1.1443 + /** @stable ICU 49 */
1.1444 + UBLOCK_MEROITIC_CURSIVE = 214, /*[109A0]*/
1.1445 + /** @stable ICU 49 */
1.1446 + UBLOCK_MEROITIC_HIEROGLYPHS = 215, /*[10980]*/
1.1447 + /** @stable ICU 49 */
1.1448 + UBLOCK_MIAO = 216, /*[16F00]*/
1.1449 + /** @stable ICU 49 */
1.1450 + UBLOCK_SHARADA = 217, /*[11180]*/
1.1451 + /** @stable ICU 49 */
1.1452 + UBLOCK_SORA_SOMPENG = 218, /*[110D0]*/
1.1453 + /** @stable ICU 49 */
1.1454 + UBLOCK_SUNDANESE_SUPPLEMENT = 219, /*[1CC0]*/
1.1455 + /** @stable ICU 49 */
1.1456 + UBLOCK_TAKRI = 220, /*[11680]*/
1.1457 +
1.1458 + /** @stable ICU 2.0 */
1.1459 + UBLOCK_COUNT = 221,
1.1460 +
1.1461 + /** @stable ICU 2.0 */
1.1462 + UBLOCK_INVALID_CODE=-1
1.1463 +};
1.1464 +
1.1465 +/** @stable ICU 2.0 */
1.1466 +typedef enum UBlockCode UBlockCode;
1.1467 +
1.1468 +/**
1.1469 + * East Asian Width constants.
1.1470 + *
1.1471 + * @see UCHAR_EAST_ASIAN_WIDTH
1.1472 + * @see u_getIntPropertyValue
1.1473 + * @stable ICU 2.2
1.1474 + */
1.1475 +typedef enum UEastAsianWidth {
1.1476 + /*
1.1477 + * Note: UEastAsianWidth constants are parsed by preparseucd.py.
1.1478 + * It matches lines like
1.1479 + * U_EA_<Unicode East_Asian_Width value name>
1.1480 + */
1.1481 +
1.1482 + U_EA_NEUTRAL, /*[N]*/
1.1483 + U_EA_AMBIGUOUS, /*[A]*/
1.1484 + U_EA_HALFWIDTH, /*[H]*/
1.1485 + U_EA_FULLWIDTH, /*[F]*/
1.1486 + U_EA_NARROW, /*[Na]*/
1.1487 + U_EA_WIDE, /*[W]*/
1.1488 + U_EA_COUNT
1.1489 +} UEastAsianWidth;
1.1490 +
1.1491 +/**
1.1492 + * Selector constants for u_charName().
1.1493 + * u_charName() returns the "modern" name of a
1.1494 + * Unicode character; or the name that was defined in
1.1495 + * Unicode version 1.0, before the Unicode standard merged
1.1496 + * with ISO-10646; or an "extended" name that gives each
1.1497 + * Unicode code point a unique name.
1.1498 + *
1.1499 + * @see u_charName
1.1500 + * @stable ICU 2.0
1.1501 + */
1.1502 +typedef enum UCharNameChoice {
1.1503 + /** Unicode character name (Name property). @stable ICU 2.0 */
1.1504 + U_UNICODE_CHAR_NAME,
1.1505 +#ifndef U_HIDE_DEPRECATED_API
1.1506 + /**
1.1507 + * The Unicode_1_Name property value which is of little practical value.
1.1508 + * Beginning with ICU 49, ICU APIs return an empty string for this name choice.
1.1509 + * @deprecated ICU 49
1.1510 + */
1.1511 + U_UNICODE_10_CHAR_NAME,
1.1512 +#endif /* U_HIDE_DEPRECATED_API */
1.1513 + /** Standard or synthetic character name. @stable ICU 2.0 */
1.1514 + U_EXTENDED_CHAR_NAME = U_UNICODE_CHAR_NAME+2,
1.1515 + /** Corrected name from NameAliases.txt. @stable ICU 4.4 */
1.1516 + U_CHAR_NAME_ALIAS,
1.1517 + /** @stable ICU 2.0 */
1.1518 + U_CHAR_NAME_CHOICE_COUNT
1.1519 +} UCharNameChoice;
1.1520 +
1.1521 +/**
1.1522 + * Selector constants for u_getPropertyName() and
1.1523 + * u_getPropertyValueName(). These selectors are used to choose which
1.1524 + * name is returned for a given property or value. All properties and
1.1525 + * values have a long name. Most have a short name, but some do not.
1.1526 + * Unicode allows for additional names, beyond the long and short
1.1527 + * name, which would be indicated by U_LONG_PROPERTY_NAME + i, where
1.1528 + * i=1, 2,...
1.1529 + *
1.1530 + * @see u_getPropertyName()
1.1531 + * @see u_getPropertyValueName()
1.1532 + * @stable ICU 2.4
1.1533 + */
1.1534 +typedef enum UPropertyNameChoice {
1.1535 + U_SHORT_PROPERTY_NAME,
1.1536 + U_LONG_PROPERTY_NAME,
1.1537 + U_PROPERTY_NAME_CHOICE_COUNT
1.1538 +} UPropertyNameChoice;
1.1539 +
1.1540 +/**
1.1541 + * Decomposition Type constants.
1.1542 + *
1.1543 + * @see UCHAR_DECOMPOSITION_TYPE
1.1544 + * @stable ICU 2.2
1.1545 + */
1.1546 +typedef enum UDecompositionType {
1.1547 + /*
1.1548 + * Note: UDecompositionType constants are parsed by preparseucd.py.
1.1549 + * It matches lines like
1.1550 + * U_DT_<Unicode Decomposition_Type value name>
1.1551 + */
1.1552 +
1.1553 + U_DT_NONE, /*[none]*/
1.1554 + U_DT_CANONICAL, /*[can]*/
1.1555 + U_DT_COMPAT, /*[com]*/
1.1556 + U_DT_CIRCLE, /*[enc]*/
1.1557 + U_DT_FINAL, /*[fin]*/
1.1558 + U_DT_FONT, /*[font]*/
1.1559 + U_DT_FRACTION, /*[fra]*/
1.1560 + U_DT_INITIAL, /*[init]*/
1.1561 + U_DT_ISOLATED, /*[iso]*/
1.1562 + U_DT_MEDIAL, /*[med]*/
1.1563 + U_DT_NARROW, /*[nar]*/
1.1564 + U_DT_NOBREAK, /*[nb]*/
1.1565 + U_DT_SMALL, /*[sml]*/
1.1566 + U_DT_SQUARE, /*[sqr]*/
1.1567 + U_DT_SUB, /*[sub]*/
1.1568 + U_DT_SUPER, /*[sup]*/
1.1569 + U_DT_VERTICAL, /*[vert]*/
1.1570 + U_DT_WIDE, /*[wide]*/
1.1571 + U_DT_COUNT /* 18 */
1.1572 +} UDecompositionType;
1.1573 +
1.1574 +/**
1.1575 + * Joining Type constants.
1.1576 + *
1.1577 + * @see UCHAR_JOINING_TYPE
1.1578 + * @stable ICU 2.2
1.1579 + */
1.1580 +typedef enum UJoiningType {
1.1581 + /*
1.1582 + * Note: UJoiningType constants are parsed by preparseucd.py.
1.1583 + * It matches lines like
1.1584 + * U_JT_<Unicode Joining_Type value name>
1.1585 + */
1.1586 +
1.1587 + U_JT_NON_JOINING, /*[U]*/
1.1588 + U_JT_JOIN_CAUSING, /*[C]*/
1.1589 + U_JT_DUAL_JOINING, /*[D]*/
1.1590 + U_JT_LEFT_JOINING, /*[L]*/
1.1591 + U_JT_RIGHT_JOINING, /*[R]*/
1.1592 + U_JT_TRANSPARENT, /*[T]*/
1.1593 + U_JT_COUNT /* 6 */
1.1594 +} UJoiningType;
1.1595 +
1.1596 +/**
1.1597 + * Joining Group constants.
1.1598 + *
1.1599 + * @see UCHAR_JOINING_GROUP
1.1600 + * @stable ICU 2.2
1.1601 + */
1.1602 +typedef enum UJoiningGroup {
1.1603 + /*
1.1604 + * Note: UJoiningGroup constants are parsed by preparseucd.py.
1.1605 + * It matches lines like
1.1606 + * U_JG_<Unicode Joining_Group value name>
1.1607 + */
1.1608 +
1.1609 + U_JG_NO_JOINING_GROUP,
1.1610 + U_JG_AIN,
1.1611 + U_JG_ALAPH,
1.1612 + U_JG_ALEF,
1.1613 + U_JG_BEH,
1.1614 + U_JG_BETH,
1.1615 + U_JG_DAL,
1.1616 + U_JG_DALATH_RISH,
1.1617 + U_JG_E,
1.1618 + U_JG_FEH,
1.1619 + U_JG_FINAL_SEMKATH,
1.1620 + U_JG_GAF,
1.1621 + U_JG_GAMAL,
1.1622 + U_JG_HAH,
1.1623 + U_JG_TEH_MARBUTA_GOAL, /**< @stable ICU 4.6 */
1.1624 + U_JG_HAMZA_ON_HEH_GOAL=U_JG_TEH_MARBUTA_GOAL,
1.1625 + U_JG_HE,
1.1626 + U_JG_HEH,
1.1627 + U_JG_HEH_GOAL,
1.1628 + U_JG_HETH,
1.1629 + U_JG_KAF,
1.1630 + U_JG_KAPH,
1.1631 + U_JG_KNOTTED_HEH,
1.1632 + U_JG_LAM,
1.1633 + U_JG_LAMADH,
1.1634 + U_JG_MEEM,
1.1635 + U_JG_MIM,
1.1636 + U_JG_NOON,
1.1637 + U_JG_NUN,
1.1638 + U_JG_PE,
1.1639 + U_JG_QAF,
1.1640 + U_JG_QAPH,
1.1641 + U_JG_REH,
1.1642 + U_JG_REVERSED_PE,
1.1643 + U_JG_SAD,
1.1644 + U_JG_SADHE,
1.1645 + U_JG_SEEN,
1.1646 + U_JG_SEMKATH,
1.1647 + U_JG_SHIN,
1.1648 + U_JG_SWASH_KAF,
1.1649 + U_JG_SYRIAC_WAW,
1.1650 + U_JG_TAH,
1.1651 + U_JG_TAW,
1.1652 + U_JG_TEH_MARBUTA,
1.1653 + U_JG_TETH,
1.1654 + U_JG_WAW,
1.1655 + U_JG_YEH,
1.1656 + U_JG_YEH_BARREE,
1.1657 + U_JG_YEH_WITH_TAIL,
1.1658 + U_JG_YUDH,
1.1659 + U_JG_YUDH_HE,
1.1660 + U_JG_ZAIN,
1.1661 + U_JG_FE, /**< @stable ICU 2.6 */
1.1662 + U_JG_KHAPH, /**< @stable ICU 2.6 */
1.1663 + U_JG_ZHAIN, /**< @stable ICU 2.6 */
1.1664 + U_JG_BURUSHASKI_YEH_BARREE, /**< @stable ICU 4.0 */
1.1665 + U_JG_FARSI_YEH, /**< @stable ICU 4.4 */
1.1666 + U_JG_NYA, /**< @stable ICU 4.4 */
1.1667 + U_JG_ROHINGYA_YEH, /**< @stable ICU 49 */
1.1668 + U_JG_COUNT
1.1669 +} UJoiningGroup;
1.1670 +
1.1671 +/**
1.1672 + * Grapheme Cluster Break constants.
1.1673 + *
1.1674 + * @see UCHAR_GRAPHEME_CLUSTER_BREAK
1.1675 + * @stable ICU 3.4
1.1676 + */
1.1677 +typedef enum UGraphemeClusterBreak {
1.1678 + /*
1.1679 + * Note: UGraphemeClusterBreak constants are parsed by preparseucd.py.
1.1680 + * It matches lines like
1.1681 + * U_GCB_<Unicode Grapheme_Cluster_Break value name>
1.1682 + */
1.1683 +
1.1684 + U_GCB_OTHER = 0, /*[XX]*/
1.1685 + U_GCB_CONTROL = 1, /*[CN]*/
1.1686 + U_GCB_CR = 2, /*[CR]*/
1.1687 + U_GCB_EXTEND = 3, /*[EX]*/
1.1688 + U_GCB_L = 4, /*[L]*/
1.1689 + U_GCB_LF = 5, /*[LF]*/
1.1690 + U_GCB_LV = 6, /*[LV]*/
1.1691 + U_GCB_LVT = 7, /*[LVT]*/
1.1692 + U_GCB_T = 8, /*[T]*/
1.1693 + U_GCB_V = 9, /*[V]*/
1.1694 + U_GCB_SPACING_MARK = 10, /*[SM]*/ /* from here on: new in Unicode 5.1/ICU 4.0 */
1.1695 + U_GCB_PREPEND = 11, /*[PP]*/
1.1696 + U_GCB_REGIONAL_INDICATOR = 12, /*[RI]*/ /* new in Unicode 6.2/ICU 50 */
1.1697 + U_GCB_COUNT = 13
1.1698 +} UGraphemeClusterBreak;
1.1699 +
1.1700 +/**
1.1701 + * Word Break constants.
1.1702 + * (UWordBreak is a pre-existing enum type in ubrk.h for word break status tags.)
1.1703 + *
1.1704 + * @see UCHAR_WORD_BREAK
1.1705 + * @stable ICU 3.4
1.1706 + */
1.1707 +typedef enum UWordBreakValues {
1.1708 + /*
1.1709 + * Note: UWordBreakValues constants are parsed by preparseucd.py.
1.1710 + * It matches lines like
1.1711 + * U_WB_<Unicode Word_Break value name>
1.1712 + */
1.1713 +
1.1714 + U_WB_OTHER = 0, /*[XX]*/
1.1715 + U_WB_ALETTER = 1, /*[LE]*/
1.1716 + U_WB_FORMAT = 2, /*[FO]*/
1.1717 + U_WB_KATAKANA = 3, /*[KA]*/
1.1718 + U_WB_MIDLETTER = 4, /*[ML]*/
1.1719 + U_WB_MIDNUM = 5, /*[MN]*/
1.1720 + U_WB_NUMERIC = 6, /*[NU]*/
1.1721 + U_WB_EXTENDNUMLET = 7, /*[EX]*/
1.1722 + U_WB_CR = 8, /*[CR]*/ /* from here on: new in Unicode 5.1/ICU 4.0 */
1.1723 + U_WB_EXTEND = 9, /*[Extend]*/
1.1724 + U_WB_LF = 10, /*[LF]*/
1.1725 + U_WB_MIDNUMLET =11, /*[MB]*/
1.1726 + U_WB_NEWLINE =12, /*[NL]*/
1.1727 + U_WB_REGIONAL_INDICATOR = 13, /*[RI]*/ /* new in Unicode 6.2/ICU 50 */
1.1728 + U_WB_HEBREW_LETTER = 14, /*[HL]*/ /* from here on: new in Unicode 6.3/ICU 52 */
1.1729 + U_WB_SINGLE_QUOTE = 15, /*[SQ]*/
1.1730 + U_WB_DOUBLE_QUOTE = 16, /*[DQ]*/
1.1731 + U_WB_COUNT = 17
1.1732 +} UWordBreakValues;
1.1733 +
1.1734 +/**
1.1735 + * Sentence Break constants.
1.1736 + *
1.1737 + * @see UCHAR_SENTENCE_BREAK
1.1738 + * @stable ICU 3.4
1.1739 + */
1.1740 +typedef enum USentenceBreak {
1.1741 + /*
1.1742 + * Note: USentenceBreak constants are parsed by preparseucd.py.
1.1743 + * It matches lines like
1.1744 + * U_SB_<Unicode Sentence_Break value name>
1.1745 + */
1.1746 +
1.1747 + U_SB_OTHER = 0, /*[XX]*/
1.1748 + U_SB_ATERM = 1, /*[AT]*/
1.1749 + U_SB_CLOSE = 2, /*[CL]*/
1.1750 + U_SB_FORMAT = 3, /*[FO]*/
1.1751 + U_SB_LOWER = 4, /*[LO]*/
1.1752 + U_SB_NUMERIC = 5, /*[NU]*/
1.1753 + U_SB_OLETTER = 6, /*[LE]*/
1.1754 + U_SB_SEP = 7, /*[SE]*/
1.1755 + U_SB_SP = 8, /*[SP]*/
1.1756 + U_SB_STERM = 9, /*[ST]*/
1.1757 + U_SB_UPPER = 10, /*[UP]*/
1.1758 + U_SB_CR = 11, /*[CR]*/ /* from here on: new in Unicode 5.1/ICU 4.0 */
1.1759 + U_SB_EXTEND = 12, /*[EX]*/
1.1760 + U_SB_LF = 13, /*[LF]*/
1.1761 + U_SB_SCONTINUE = 14, /*[SC]*/
1.1762 + U_SB_COUNT = 15
1.1763 +} USentenceBreak;
1.1764 +
1.1765 +/**
1.1766 + * Line Break constants.
1.1767 + *
1.1768 + * @see UCHAR_LINE_BREAK
1.1769 + * @stable ICU 2.2
1.1770 + */
1.1771 +typedef enum ULineBreak {
1.1772 + /*
1.1773 + * Note: ULineBreak constants are parsed by preparseucd.py.
1.1774 + * It matches lines like
1.1775 + * U_LB_<Unicode Line_Break value name>
1.1776 + */
1.1777 +
1.1778 + U_LB_UNKNOWN = 0, /*[XX]*/
1.1779 + U_LB_AMBIGUOUS = 1, /*[AI]*/
1.1780 + U_LB_ALPHABETIC = 2, /*[AL]*/
1.1781 + U_LB_BREAK_BOTH = 3, /*[B2]*/
1.1782 + U_LB_BREAK_AFTER = 4, /*[BA]*/
1.1783 + U_LB_BREAK_BEFORE = 5, /*[BB]*/
1.1784 + U_LB_MANDATORY_BREAK = 6, /*[BK]*/
1.1785 + U_LB_CONTINGENT_BREAK = 7, /*[CB]*/
1.1786 + U_LB_CLOSE_PUNCTUATION = 8, /*[CL]*/
1.1787 + U_LB_COMBINING_MARK = 9, /*[CM]*/
1.1788 + U_LB_CARRIAGE_RETURN = 10, /*[CR]*/
1.1789 + U_LB_EXCLAMATION = 11, /*[EX]*/
1.1790 + U_LB_GLUE = 12, /*[GL]*/
1.1791 + U_LB_HYPHEN = 13, /*[HY]*/
1.1792 + U_LB_IDEOGRAPHIC = 14, /*[ID]*/
1.1793 + /** Renamed from the misspelled "inseperable" in Unicode 4.0.1/ICU 3.0 @stable ICU 3.0 */
1.1794 + U_LB_INSEPARABLE = 15, /*[IN]*/
1.1795 + U_LB_INSEPERABLE = U_LB_INSEPARABLE,
1.1796 + U_LB_INFIX_NUMERIC = 16, /*[IS]*/
1.1797 + U_LB_LINE_FEED = 17, /*[LF]*/
1.1798 + U_LB_NONSTARTER = 18, /*[NS]*/
1.1799 + U_LB_NUMERIC = 19, /*[NU]*/
1.1800 + U_LB_OPEN_PUNCTUATION = 20, /*[OP]*/
1.1801 + U_LB_POSTFIX_NUMERIC = 21, /*[PO]*/
1.1802 + U_LB_PREFIX_NUMERIC = 22, /*[PR]*/
1.1803 + U_LB_QUOTATION = 23, /*[QU]*/
1.1804 + U_LB_COMPLEX_CONTEXT = 24, /*[SA]*/
1.1805 + U_LB_SURROGATE = 25, /*[SG]*/
1.1806 + U_LB_SPACE = 26, /*[SP]*/
1.1807 + U_LB_BREAK_SYMBOLS = 27, /*[SY]*/
1.1808 + U_LB_ZWSPACE = 28, /*[ZW]*/
1.1809 + U_LB_NEXT_LINE = 29, /*[NL]*/ /* from here on: new in Unicode 4/ICU 2.6 */
1.1810 + U_LB_WORD_JOINER = 30, /*[WJ]*/
1.1811 + U_LB_H2 = 31, /*[H2]*/ /* from here on: new in Unicode 4.1/ICU 3.4 */
1.1812 + U_LB_H3 = 32, /*[H3]*/
1.1813 + U_LB_JL = 33, /*[JL]*/
1.1814 + U_LB_JT = 34, /*[JT]*/
1.1815 + U_LB_JV = 35, /*[JV]*/
1.1816 + U_LB_CLOSE_PARENTHESIS = 36, /*[CP]*/ /* new in Unicode 5.2/ICU 4.4 */
1.1817 + U_LB_CONDITIONAL_JAPANESE_STARTER = 37,/*[CJ]*/ /* new in Unicode 6.1/ICU 49 */
1.1818 + U_LB_HEBREW_LETTER = 38, /*[HL]*/ /* new in Unicode 6.1/ICU 49 */
1.1819 + U_LB_REGIONAL_INDICATOR = 39,/*[RI]*/ /* new in Unicode 6.2/ICU 50 */
1.1820 + U_LB_COUNT = 40
1.1821 +} ULineBreak;
1.1822 +
1.1823 +/**
1.1824 + * Numeric Type constants.
1.1825 + *
1.1826 + * @see UCHAR_NUMERIC_TYPE
1.1827 + * @stable ICU 2.2
1.1828 + */
1.1829 +typedef enum UNumericType {
1.1830 + /*
1.1831 + * Note: UNumericType constants are parsed by preparseucd.py.
1.1832 + * It matches lines like
1.1833 + * U_NT_<Unicode Numeric_Type value name>
1.1834 + */
1.1835 +
1.1836 + U_NT_NONE, /*[None]*/
1.1837 + U_NT_DECIMAL, /*[de]*/
1.1838 + U_NT_DIGIT, /*[di]*/
1.1839 + U_NT_NUMERIC, /*[nu]*/
1.1840 + U_NT_COUNT
1.1841 +} UNumericType;
1.1842 +
1.1843 +/**
1.1844 + * Hangul Syllable Type constants.
1.1845 + *
1.1846 + * @see UCHAR_HANGUL_SYLLABLE_TYPE
1.1847 + * @stable ICU 2.6
1.1848 + */
1.1849 +typedef enum UHangulSyllableType {
1.1850 + /*
1.1851 + * Note: UHangulSyllableType constants are parsed by preparseucd.py.
1.1852 + * It matches lines like
1.1853 + * U_HST_<Unicode Hangul_Syllable_Type value name>
1.1854 + */
1.1855 +
1.1856 + U_HST_NOT_APPLICABLE, /*[NA]*/
1.1857 + U_HST_LEADING_JAMO, /*[L]*/
1.1858 + U_HST_VOWEL_JAMO, /*[V]*/
1.1859 + U_HST_TRAILING_JAMO, /*[T]*/
1.1860 + U_HST_LV_SYLLABLE, /*[LV]*/
1.1861 + U_HST_LVT_SYLLABLE, /*[LVT]*/
1.1862 + U_HST_COUNT
1.1863 +} UHangulSyllableType;
1.1864 +
1.1865 +/**
1.1866 + * Check a binary Unicode property for a code point.
1.1867 + *
1.1868 + * Unicode, especially in version 3.2, defines many more properties than the
1.1869 + * original set in UnicodeData.txt.
1.1870 + *
1.1871 + * The properties APIs are intended to reflect Unicode properties as defined
1.1872 + * in the Unicode Character Database (UCD) and Unicode Technical Reports (UTR).
1.1873 + * For details about the properties see http://www.unicode.org/ucd/ .
1.1874 + * For names of Unicode properties see the UCD file PropertyAliases.txt.
1.1875 + *
1.1876 + * Important: If ICU is built with UCD files from Unicode versions below 3.2,
1.1877 + * then properties marked with "new in Unicode 3.2" are not or not fully available.
1.1878 + *
1.1879 + * @param c Code point to test.
1.1880 + * @param which UProperty selector constant, identifies which binary property to check.
1.1881 + * Must be UCHAR_BINARY_START<=which<UCHAR_BINARY_LIMIT.
1.1882 + * @return TRUE or FALSE according to the binary Unicode property value for c.
1.1883 + * Also FALSE if 'which' is out of bounds or if the Unicode version
1.1884 + * does not have data for the property at all, or not for this code point.
1.1885 + *
1.1886 + * @see UProperty
1.1887 + * @see u_getIntPropertyValue
1.1888 + * @see u_getUnicodeVersion
1.1889 + * @stable ICU 2.1
1.1890 + */
1.1891 +U_STABLE UBool U_EXPORT2
1.1892 +u_hasBinaryProperty(UChar32 c, UProperty which);
1.1893 +
1.1894 +/**
1.1895 + * Check if a code point has the Alphabetic Unicode property.
1.1896 + * Same as u_hasBinaryProperty(c, UCHAR_ALPHABETIC).
1.1897 + * This is different from u_isalpha!
1.1898 + * @param c Code point to test
1.1899 + * @return true if the code point has the Alphabetic Unicode property, false otherwise
1.1900 + *
1.1901 + * @see UCHAR_ALPHABETIC
1.1902 + * @see u_isalpha
1.1903 + * @see u_hasBinaryProperty
1.1904 + * @stable ICU 2.1
1.1905 + */
1.1906 +U_STABLE UBool U_EXPORT2
1.1907 +u_isUAlphabetic(UChar32 c);
1.1908 +
1.1909 +/**
1.1910 + * Check if a code point has the Lowercase Unicode property.
1.1911 + * Same as u_hasBinaryProperty(c, UCHAR_LOWERCASE).
1.1912 + * This is different from u_islower!
1.1913 + * @param c Code point to test
1.1914 + * @return true if the code point has the Lowercase Unicode property, false otherwise
1.1915 + *
1.1916 + * @see UCHAR_LOWERCASE
1.1917 + * @see u_islower
1.1918 + * @see u_hasBinaryProperty
1.1919 + * @stable ICU 2.1
1.1920 + */
1.1921 +U_STABLE UBool U_EXPORT2
1.1922 +u_isULowercase(UChar32 c);
1.1923 +
1.1924 +/**
1.1925 + * Check if a code point has the Uppercase Unicode property.
1.1926 + * Same as u_hasBinaryProperty(c, UCHAR_UPPERCASE).
1.1927 + * This is different from u_isupper!
1.1928 + * @param c Code point to test
1.1929 + * @return true if the code point has the Uppercase Unicode property, false otherwise
1.1930 + *
1.1931 + * @see UCHAR_UPPERCASE
1.1932 + * @see u_isupper
1.1933 + * @see u_hasBinaryProperty
1.1934 + * @stable ICU 2.1
1.1935 + */
1.1936 +U_STABLE UBool U_EXPORT2
1.1937 +u_isUUppercase(UChar32 c);
1.1938 +
1.1939 +/**
1.1940 + * Check if a code point has the White_Space Unicode property.
1.1941 + * Same as u_hasBinaryProperty(c, UCHAR_WHITE_SPACE).
1.1942 + * This is different from both u_isspace and u_isWhitespace!
1.1943 + *
1.1944 + * Note: There are several ICU whitespace functions; please see the uchar.h
1.1945 + * file documentation for a detailed comparison.
1.1946 + *
1.1947 + * @param c Code point to test
1.1948 + * @return true if the code point has the White_Space Unicode property, false otherwise.
1.1949 + *
1.1950 + * @see UCHAR_WHITE_SPACE
1.1951 + * @see u_isWhitespace
1.1952 + * @see u_isspace
1.1953 + * @see u_isJavaSpaceChar
1.1954 + * @see u_hasBinaryProperty
1.1955 + * @stable ICU 2.1
1.1956 + */
1.1957 +U_STABLE UBool U_EXPORT2
1.1958 +u_isUWhiteSpace(UChar32 c);
1.1959 +
1.1960 +/**
1.1961 + * Get the property value for an enumerated or integer Unicode property for a code point.
1.1962 + * Also returns binary and mask property values.
1.1963 + *
1.1964 + * Unicode, especially in version 3.2, defines many more properties than the
1.1965 + * original set in UnicodeData.txt.
1.1966 + *
1.1967 + * The properties APIs are intended to reflect Unicode properties as defined
1.1968 + * in the Unicode Character Database (UCD) and Unicode Technical Reports (UTR).
1.1969 + * For details about the properties see http://www.unicode.org/ .
1.1970 + * For names of Unicode properties see the UCD file PropertyAliases.txt.
1.1971 + *
1.1972 + * Sample usage:
1.1973 + * UEastAsianWidth ea=(UEastAsianWidth)u_getIntPropertyValue(c, UCHAR_EAST_ASIAN_WIDTH);
1.1974 + * UBool b=(UBool)u_getIntPropertyValue(c, UCHAR_IDEOGRAPHIC);
1.1975 + *
1.1976 + * @param c Code point to test.
1.1977 + * @param which UProperty selector constant, identifies which property to check.
1.1978 + * Must be UCHAR_BINARY_START<=which<UCHAR_BINARY_LIMIT
1.1979 + * or UCHAR_INT_START<=which<UCHAR_INT_LIMIT
1.1980 + * or UCHAR_MASK_START<=which<UCHAR_MASK_LIMIT.
1.1981 + * @return Numeric value that is directly the property value or,
1.1982 + * for enumerated properties, corresponds to the numeric value of the enumerated
1.1983 + * constant of the respective property value enumeration type
1.1984 + * (cast to enum type if necessary).
1.1985 + * Returns 0 or 1 (for FALSE/TRUE) for binary Unicode properties.
1.1986 + * Returns a bit-mask for mask properties.
1.1987 + * Returns 0 if 'which' is out of bounds or if the Unicode version
1.1988 + * does not have data for the property at all, or not for this code point.
1.1989 + *
1.1990 + * @see UProperty
1.1991 + * @see u_hasBinaryProperty
1.1992 + * @see u_getIntPropertyMinValue
1.1993 + * @see u_getIntPropertyMaxValue
1.1994 + * @see u_getUnicodeVersion
1.1995 + * @stable ICU 2.2
1.1996 + */
1.1997 +U_STABLE int32_t U_EXPORT2
1.1998 +u_getIntPropertyValue(UChar32 c, UProperty which);
1.1999 +
1.2000 +/**
1.2001 + * Get the minimum value for an enumerated/integer/binary Unicode property.
1.2002 + * Can be used together with u_getIntPropertyMaxValue
1.2003 + * to allocate arrays of UnicodeSet or similar.
1.2004 + *
1.2005 + * @param which UProperty selector constant, identifies which binary property to check.
1.2006 + * Must be UCHAR_BINARY_START<=which<UCHAR_BINARY_LIMIT
1.2007 + * or UCHAR_INT_START<=which<UCHAR_INT_LIMIT.
1.2008 + * @return Minimum value returned by u_getIntPropertyValue for a Unicode property.
1.2009 + * 0 if the property selector is out of range.
1.2010 + *
1.2011 + * @see UProperty
1.2012 + * @see u_hasBinaryProperty
1.2013 + * @see u_getUnicodeVersion
1.2014 + * @see u_getIntPropertyMaxValue
1.2015 + * @see u_getIntPropertyValue
1.2016 + * @stable ICU 2.2
1.2017 + */
1.2018 +U_STABLE int32_t U_EXPORT2
1.2019 +u_getIntPropertyMinValue(UProperty which);
1.2020 +
1.2021 +/**
1.2022 + * Get the maximum value for an enumerated/integer/binary Unicode property.
1.2023 + * Can be used together with u_getIntPropertyMinValue
1.2024 + * to allocate arrays of UnicodeSet or similar.
1.2025 + *
1.2026 + * Examples for min/max values (for Unicode 3.2):
1.2027 + *
1.2028 + * - UCHAR_BIDI_CLASS: 0/18 (U_LEFT_TO_RIGHT/U_BOUNDARY_NEUTRAL)
1.2029 + * - UCHAR_SCRIPT: 0/45 (USCRIPT_COMMON/USCRIPT_TAGBANWA)
1.2030 + * - UCHAR_IDEOGRAPHIC: 0/1 (FALSE/TRUE)
1.2031 + *
1.2032 + * For undefined UProperty constant values, min/max values will be 0/-1.
1.2033 + *
1.2034 + * @param which UProperty selector constant, identifies which binary property to check.
1.2035 + * Must be UCHAR_BINARY_START<=which<UCHAR_BINARY_LIMIT
1.2036 + * or UCHAR_INT_START<=which<UCHAR_INT_LIMIT.
1.2037 + * @return Maximum value returned by u_getIntPropertyValue for a Unicode property.
1.2038 + * <=0 if the property selector is out of range.
1.2039 + *
1.2040 + * @see UProperty
1.2041 + * @see u_hasBinaryProperty
1.2042 + * @see u_getUnicodeVersion
1.2043 + * @see u_getIntPropertyMaxValue
1.2044 + * @see u_getIntPropertyValue
1.2045 + * @stable ICU 2.2
1.2046 + */
1.2047 +U_STABLE int32_t U_EXPORT2
1.2048 +u_getIntPropertyMaxValue(UProperty which);
1.2049 +
1.2050 +/**
1.2051 + * Get the numeric value for a Unicode code point as defined in the
1.2052 + * Unicode Character Database.
1.2053 + *
1.2054 + * A "double" return type is necessary because
1.2055 + * some numeric values are fractions, negative, or too large for int32_t.
1.2056 + *
1.2057 + * For characters without any numeric values in the Unicode Character Database,
1.2058 + * this function will return U_NO_NUMERIC_VALUE.
1.2059 + * Note: This is different from the Unicode Standard which specifies NaN as the default value.
1.2060 + * (NaN is not available on all platforms.)
1.2061 + *
1.2062 + * Similar to java.lang.Character.getNumericValue(), but u_getNumericValue()
1.2063 + * also supports negative values, large values, and fractions,
1.2064 + * while Java's getNumericValue() returns values 10..35 for ASCII letters.
1.2065 + *
1.2066 + * @param c Code point to get the numeric value for.
1.2067 + * @return Numeric value of c, or U_NO_NUMERIC_VALUE if none is defined.
1.2068 + *
1.2069 + * @see U_NO_NUMERIC_VALUE
1.2070 + * @stable ICU 2.2
1.2071 + */
1.2072 +U_STABLE double U_EXPORT2
1.2073 +u_getNumericValue(UChar32 c);
1.2074 +
1.2075 +/**
1.2076 + * Special value that is returned by u_getNumericValue when
1.2077 + * no numeric value is defined for a code point.
1.2078 + *
1.2079 + * @see u_getNumericValue
1.2080 + * @stable ICU 2.2
1.2081 + */
1.2082 +#define U_NO_NUMERIC_VALUE ((double)-123456789.)
1.2083 +
1.2084 +/**
1.2085 + * Determines whether the specified code point has the general category "Ll"
1.2086 + * (lowercase letter).
1.2087 + *
1.2088 + * Same as java.lang.Character.isLowerCase().
1.2089 + *
1.2090 + * This misses some characters that are also lowercase but
1.2091 + * have a different general category value.
1.2092 + * In order to include those, use UCHAR_LOWERCASE.
1.2093 + *
1.2094 + * In addition to being equivalent to a Java function, this also serves
1.2095 + * as a C/POSIX migration function.
1.2096 + * See the comments about C/POSIX character classification functions in the
1.2097 + * documentation at the top of this header file.
1.2098 + *
1.2099 + * @param c the code point to be tested
1.2100 + * @return TRUE if the code point is an Ll lowercase letter
1.2101 + *
1.2102 + * @see UCHAR_LOWERCASE
1.2103 + * @see u_isupper
1.2104 + * @see u_istitle
1.2105 + * @stable ICU 2.0
1.2106 + */
1.2107 +U_STABLE UBool U_EXPORT2
1.2108 +u_islower(UChar32 c);
1.2109 +
1.2110 +/**
1.2111 + * Determines whether the specified code point has the general category "Lu"
1.2112 + * (uppercase letter).
1.2113 + *
1.2114 + * Same as java.lang.Character.isUpperCase().
1.2115 + *
1.2116 + * This misses some characters that are also uppercase but
1.2117 + * have a different general category value.
1.2118 + * In order to include those, use UCHAR_UPPERCASE.
1.2119 + *
1.2120 + * In addition to being equivalent to a Java function, this also serves
1.2121 + * as a C/POSIX migration function.
1.2122 + * See the comments about C/POSIX character classification functions in the
1.2123 + * documentation at the top of this header file.
1.2124 + *
1.2125 + * @param c the code point to be tested
1.2126 + * @return TRUE if the code point is an Lu uppercase letter
1.2127 + *
1.2128 + * @see UCHAR_UPPERCASE
1.2129 + * @see u_islower
1.2130 + * @see u_istitle
1.2131 + * @see u_tolower
1.2132 + * @stable ICU 2.0
1.2133 + */
1.2134 +U_STABLE UBool U_EXPORT2
1.2135 +u_isupper(UChar32 c);
1.2136 +
1.2137 +/**
1.2138 + * Determines whether the specified code point is a titlecase letter.
1.2139 + * True for general category "Lt" (titlecase letter).
1.2140 + *
1.2141 + * Same as java.lang.Character.isTitleCase().
1.2142 + *
1.2143 + * @param c the code point to be tested
1.2144 + * @return TRUE if the code point is an Lt titlecase letter
1.2145 + *
1.2146 + * @see u_isupper
1.2147 + * @see u_islower
1.2148 + * @see u_totitle
1.2149 + * @stable ICU 2.0
1.2150 + */
1.2151 +U_STABLE UBool U_EXPORT2
1.2152 +u_istitle(UChar32 c);
1.2153 +
1.2154 +/**
1.2155 + * Determines whether the specified code point is a digit character according to Java.
1.2156 + * True for characters with general category "Nd" (decimal digit numbers).
1.2157 + * Beginning with Unicode 4, this is the same as
1.2158 + * testing for the Numeric_Type of Decimal.
1.2159 + *
1.2160 + * Same as java.lang.Character.isDigit().
1.2161 + *
1.2162 + * In addition to being equivalent to a Java function, this also serves
1.2163 + * as a C/POSIX migration function.
1.2164 + * See the comments about C/POSIX character classification functions in the
1.2165 + * documentation at the top of this header file.
1.2166 + *
1.2167 + * @param c the code point to be tested
1.2168 + * @return TRUE if the code point is a digit character according to Character.isDigit()
1.2169 + *
1.2170 + * @stable ICU 2.0
1.2171 + */
1.2172 +U_STABLE UBool U_EXPORT2
1.2173 +u_isdigit(UChar32 c);
1.2174 +
1.2175 +/**
1.2176 + * Determines whether the specified code point is a letter character.
1.2177 + * True for general categories "L" (letters).
1.2178 + *
1.2179 + * Same as java.lang.Character.isLetter().
1.2180 + *
1.2181 + * In addition to being equivalent to a Java function, this also serves
1.2182 + * as a C/POSIX migration function.
1.2183 + * See the comments about C/POSIX character classification functions in the
1.2184 + * documentation at the top of this header file.
1.2185 + *
1.2186 + * @param c the code point to be tested
1.2187 + * @return TRUE if the code point is a letter character
1.2188 + *
1.2189 + * @see u_isdigit
1.2190 + * @see u_isalnum
1.2191 + * @stable ICU 2.0
1.2192 + */
1.2193 +U_STABLE UBool U_EXPORT2
1.2194 +u_isalpha(UChar32 c);
1.2195 +
1.2196 +/**
1.2197 + * Determines whether the specified code point is an alphanumeric character
1.2198 + * (letter or digit) according to Java.
1.2199 + * True for characters with general categories
1.2200 + * "L" (letters) and "Nd" (decimal digit numbers).
1.2201 + *
1.2202 + * Same as java.lang.Character.isLetterOrDigit().
1.2203 + *
1.2204 + * In addition to being equivalent to a Java function, this also serves
1.2205 + * as a C/POSIX migration function.
1.2206 + * See the comments about C/POSIX character classification functions in the
1.2207 + * documentation at the top of this header file.
1.2208 + *
1.2209 + * @param c the code point to be tested
1.2210 + * @return TRUE if the code point is an alphanumeric character according to Character.isLetterOrDigit()
1.2211 + *
1.2212 + * @stable ICU 2.0
1.2213 + */
1.2214 +U_STABLE UBool U_EXPORT2
1.2215 +u_isalnum(UChar32 c);
1.2216 +
1.2217 +/**
1.2218 + * Determines whether the specified code point is a hexadecimal digit.
1.2219 + * This is equivalent to u_digit(c, 16)>=0.
1.2220 + * True for characters with general category "Nd" (decimal digit numbers)
1.2221 + * as well as Latin letters a-f and A-F in both ASCII and Fullwidth ASCII.
1.2222 + * (That is, for letters with code points
1.2223 + * 0041..0046, 0061..0066, FF21..FF26, FF41..FF46.)
1.2224 + *
1.2225 + * In order to narrow the definition of hexadecimal digits to only ASCII
1.2226 + * characters, use (c<=0x7f && u_isxdigit(c)).
1.2227 + *
1.2228 + * This is a C/POSIX migration function.
1.2229 + * See the comments about C/POSIX character classification functions in the
1.2230 + * documentation at the top of this header file.
1.2231 + *
1.2232 + * @param c the code point to be tested
1.2233 + * @return TRUE if the code point is a hexadecimal digit
1.2234 + *
1.2235 + * @stable ICU 2.6
1.2236 + */
1.2237 +U_STABLE UBool U_EXPORT2
1.2238 +u_isxdigit(UChar32 c);
1.2239 +
1.2240 +/**
1.2241 + * Determines whether the specified code point is a punctuation character.
1.2242 + * True for characters with general categories "P" (punctuation).
1.2243 + *
1.2244 + * This is a C/POSIX migration function.
1.2245 + * See the comments about C/POSIX character classification functions in the
1.2246 + * documentation at the top of this header file.
1.2247 + *
1.2248 + * @param c the code point to be tested
1.2249 + * @return TRUE if the code point is a punctuation character
1.2250 + *
1.2251 + * @stable ICU 2.6
1.2252 + */
1.2253 +U_STABLE UBool U_EXPORT2
1.2254 +u_ispunct(UChar32 c);
1.2255 +
1.2256 +/**
1.2257 + * Determines whether the specified code point is a "graphic" character
1.2258 + * (printable, excluding spaces).
1.2259 + * TRUE for all characters except those with general categories
1.2260 + * "Cc" (control codes), "Cf" (format controls), "Cs" (surrogates),
1.2261 + * "Cn" (unassigned), and "Z" (separators).
1.2262 + *
1.2263 + * This is a C/POSIX migration function.
1.2264 + * See the comments about C/POSIX character classification functions in the
1.2265 + * documentation at the top of this header file.
1.2266 + *
1.2267 + * @param c the code point to be tested
1.2268 + * @return TRUE if the code point is a "graphic" character
1.2269 + *
1.2270 + * @stable ICU 2.6
1.2271 + */
1.2272 +U_STABLE UBool U_EXPORT2
1.2273 +u_isgraph(UChar32 c);
1.2274 +
1.2275 +/**
1.2276 + * Determines whether the specified code point is a "blank" or "horizontal space",
1.2277 + * a character that visibly separates words on a line.
1.2278 + * The following are equivalent definitions:
1.2279 + *
1.2280 + * TRUE for Unicode White_Space characters except for "vertical space controls"
1.2281 + * where "vertical space controls" are the following characters:
1.2282 + * U+000A (LF) U+000B (VT) U+000C (FF) U+000D (CR) U+0085 (NEL) U+2028 (LS) U+2029 (PS)
1.2283 + *
1.2284 + * same as
1.2285 + *
1.2286 + * TRUE for U+0009 (TAB) and characters with general category "Zs" (space separators)
1.2287 + * except Zero Width Space (ZWSP, U+200B).
1.2288 + *
1.2289 + * Note: There are several ICU whitespace functions; please see the uchar.h
1.2290 + * file documentation for a detailed comparison.
1.2291 + *
1.2292 + * This is a C/POSIX migration function.
1.2293 + * See the comments about C/POSIX character classification functions in the
1.2294 + * documentation at the top of this header file.
1.2295 + *
1.2296 + * @param c the code point to be tested
1.2297 + * @return TRUE if the code point is a "blank"
1.2298 + *
1.2299 + * @stable ICU 2.6
1.2300 + */
1.2301 +U_STABLE UBool U_EXPORT2
1.2302 +u_isblank(UChar32 c);
1.2303 +
1.2304 +/**
1.2305 + * Determines whether the specified code point is "defined",
1.2306 + * which usually means that it is assigned a character.
1.2307 + * True for general categories other than "Cn" (other, not assigned),
1.2308 + * i.e., true for all code points mentioned in UnicodeData.txt.
1.2309 + *
1.2310 + * Note that non-character code points (e.g., U+FDD0) are not "defined"
1.2311 + * (they are Cn), but surrogate code points are "defined" (Cs).
1.2312 + *
1.2313 + * Same as java.lang.Character.isDefined().
1.2314 + *
1.2315 + * @param c the code point to be tested
1.2316 + * @return TRUE if the code point is assigned a character
1.2317 + *
1.2318 + * @see u_isdigit
1.2319 + * @see u_isalpha
1.2320 + * @see u_isalnum
1.2321 + * @see u_isupper
1.2322 + * @see u_islower
1.2323 + * @see u_istitle
1.2324 + * @stable ICU 2.0
1.2325 + */
1.2326 +U_STABLE UBool U_EXPORT2
1.2327 +u_isdefined(UChar32 c);
1.2328 +
1.2329 +/**
1.2330 + * Determines if the specified character is a space character or not.
1.2331 + *
1.2332 + * Note: There are several ICU whitespace functions; please see the uchar.h
1.2333 + * file documentation for a detailed comparison.
1.2334 + *
1.2335 + * This is a C/POSIX migration function.
1.2336 + * See the comments about C/POSIX character classification functions in the
1.2337 + * documentation at the top of this header file.
1.2338 + *
1.2339 + * @param c the character to be tested
1.2340 + * @return true if the character is a space character; false otherwise.
1.2341 + *
1.2342 + * @see u_isJavaSpaceChar
1.2343 + * @see u_isWhitespace
1.2344 + * @see u_isUWhiteSpace
1.2345 + * @stable ICU 2.0
1.2346 + */
1.2347 +U_STABLE UBool U_EXPORT2
1.2348 +u_isspace(UChar32 c);
1.2349 +
1.2350 +/**
1.2351 + * Determine if the specified code point is a space character according to Java.
1.2352 + * True for characters with general categories "Z" (separators),
1.2353 + * which does not include control codes (e.g., TAB or Line Feed).
1.2354 + *
1.2355 + * Same as java.lang.Character.isSpaceChar().
1.2356 + *
1.2357 + * Note: There are several ICU whitespace functions; please see the uchar.h
1.2358 + * file documentation for a detailed comparison.
1.2359 + *
1.2360 + * @param c the code point to be tested
1.2361 + * @return TRUE if the code point is a space character according to Character.isSpaceChar()
1.2362 + *
1.2363 + * @see u_isspace
1.2364 + * @see u_isWhitespace
1.2365 + * @see u_isUWhiteSpace
1.2366 + * @stable ICU 2.6
1.2367 + */
1.2368 +U_STABLE UBool U_EXPORT2
1.2369 +u_isJavaSpaceChar(UChar32 c);
1.2370 +
1.2371 +/**
1.2372 + * Determines if the specified code point is a whitespace character according to Java/ICU.
1.2373 + * A character is considered to be a Java whitespace character if and only
1.2374 + * if it satisfies one of the following criteria:
1.2375 + *
1.2376 + * - It is a Unicode Separator character (categories "Z" = "Zs" or "Zl" or "Zp"), but is not
1.2377 + * also a non-breaking space (U+00A0 NBSP or U+2007 Figure Space or U+202F Narrow NBSP).
1.2378 + * - It is U+0009 HORIZONTAL TABULATION.
1.2379 + * - It is U+000A LINE FEED.
1.2380 + * - It is U+000B VERTICAL TABULATION.
1.2381 + * - It is U+000C FORM FEED.
1.2382 + * - It is U+000D CARRIAGE RETURN.
1.2383 + * - It is U+001C FILE SEPARATOR.
1.2384 + * - It is U+001D GROUP SEPARATOR.
1.2385 + * - It is U+001E RECORD SEPARATOR.
1.2386 + * - It is U+001F UNIT SEPARATOR.
1.2387 + *
1.2388 + * This API tries to sync with the semantics of Java's
1.2389 + * java.lang.Character.isWhitespace(), but it may not return
1.2390 + * the exact same results because of the Unicode version
1.2391 + * difference.
1.2392 + *
1.2393 + * Note: Unicode 4.0.1 changed U+200B ZERO WIDTH SPACE from a Space Separator (Zs)
1.2394 + * to a Format Control (Cf). Since then, isWhitespace(0x200b) returns false.
1.2395 + * See http://www.unicode.org/versions/Unicode4.0.1/
1.2396 + *
1.2397 + * Note: There are several ICU whitespace functions; please see the uchar.h
1.2398 + * file documentation for a detailed comparison.
1.2399 + *
1.2400 + * @param c the code point to be tested
1.2401 + * @return TRUE if the code point is a whitespace character according to Java/ICU
1.2402 + *
1.2403 + * @see u_isspace
1.2404 + * @see u_isJavaSpaceChar
1.2405 + * @see u_isUWhiteSpace
1.2406 + * @stable ICU 2.0
1.2407 + */
1.2408 +U_STABLE UBool U_EXPORT2
1.2409 +u_isWhitespace(UChar32 c);
1.2410 +
1.2411 +/**
1.2412 + * Determines whether the specified code point is a control character
1.2413 + * (as defined by this function).
1.2414 + * A control character is one of the following:
1.2415 + * - ISO 8-bit control character (U+0000..U+001f and U+007f..U+009f)
1.2416 + * - U_CONTROL_CHAR (Cc)
1.2417 + * - U_FORMAT_CHAR (Cf)
1.2418 + * - U_LINE_SEPARATOR (Zl)
1.2419 + * - U_PARAGRAPH_SEPARATOR (Zp)
1.2420 + *
1.2421 + * This is a C/POSIX migration function.
1.2422 + * See the comments about C/POSIX character classification functions in the
1.2423 + * documentation at the top of this header file.
1.2424 + *
1.2425 + * @param c the code point to be tested
1.2426 + * @return TRUE if the code point is a control character
1.2427 + *
1.2428 + * @see UCHAR_DEFAULT_IGNORABLE_CODE_POINT
1.2429 + * @see u_isprint
1.2430 + * @stable ICU 2.0
1.2431 + */
1.2432 +U_STABLE UBool U_EXPORT2
1.2433 +u_iscntrl(UChar32 c);
1.2434 +
1.2435 +/**
1.2436 + * Determines whether the specified code point is an ISO control code.
1.2437 + * True for U+0000..U+001f and U+007f..U+009f (general category "Cc").
1.2438 + *
1.2439 + * Same as java.lang.Character.isISOControl().
1.2440 + *
1.2441 + * @param c the code point to be tested
1.2442 + * @return TRUE if the code point is an ISO control code
1.2443 + *
1.2444 + * @see u_iscntrl
1.2445 + * @stable ICU 2.6
1.2446 + */
1.2447 +U_STABLE UBool U_EXPORT2
1.2448 +u_isISOControl(UChar32 c);
1.2449 +
1.2450 +/**
1.2451 + * Determines whether the specified code point is a printable character.
1.2452 + * True for general categories <em>other</em> than "C" (controls).
1.2453 + *
1.2454 + * This is a C/POSIX migration function.
1.2455 + * See the comments about C/POSIX character classification functions in the
1.2456 + * documentation at the top of this header file.
1.2457 + *
1.2458 + * @param c the code point to be tested
1.2459 + * @return TRUE if the code point is a printable character
1.2460 + *
1.2461 + * @see UCHAR_DEFAULT_IGNORABLE_CODE_POINT
1.2462 + * @see u_iscntrl
1.2463 + * @stable ICU 2.0
1.2464 + */
1.2465 +U_STABLE UBool U_EXPORT2
1.2466 +u_isprint(UChar32 c);
1.2467 +
1.2468 +/**
1.2469 + * Determines whether the specified code point is a base character.
1.2470 + * True for general categories "L" (letters), "N" (numbers),
1.2471 + * "Mc" (spacing combining marks), and "Me" (enclosing marks).
1.2472 + *
1.2473 + * Note that this is different from the Unicode definition in
1.2474 + * chapter 3.5, conformance clause D13,
1.2475 + * which defines base characters to be all characters (not Cn)
1.2476 + * that do not graphically combine with preceding characters (M)
1.2477 + * and that are neither control (Cc) or format (Cf) characters.
1.2478 + *
1.2479 + * @param c the code point to be tested
1.2480 + * @return TRUE if the code point is a base character according to this function
1.2481 + *
1.2482 + * @see u_isalpha
1.2483 + * @see u_isdigit
1.2484 + * @stable ICU 2.0
1.2485 + */
1.2486 +U_STABLE UBool U_EXPORT2
1.2487 +u_isbase(UChar32 c);
1.2488 +
1.2489 +/**
1.2490 + * Returns the bidirectional category value for the code point,
1.2491 + * which is used in the Unicode bidirectional algorithm
1.2492 + * (UAX #9 http://www.unicode.org/reports/tr9/).
1.2493 + * Note that some <em>unassigned</em> code points have bidi values
1.2494 + * of R or AL because they are in blocks that are reserved
1.2495 + * for Right-To-Left scripts.
1.2496 + *
1.2497 + * Same as java.lang.Character.getDirectionality()
1.2498 + *
1.2499 + * @param c the code point to be tested
1.2500 + * @return the bidirectional category (UCharDirection) value
1.2501 + *
1.2502 + * @see UCharDirection
1.2503 + * @stable ICU 2.0
1.2504 + */
1.2505 +U_STABLE UCharDirection U_EXPORT2
1.2506 +u_charDirection(UChar32 c);
1.2507 +
1.2508 +/**
1.2509 + * Determines whether the code point has the Bidi_Mirrored property.
1.2510 + * This property is set for characters that are commonly used in
1.2511 + * Right-To-Left contexts and need to be displayed with a "mirrored"
1.2512 + * glyph.
1.2513 + *
1.2514 + * Same as java.lang.Character.isMirrored().
1.2515 + * Same as UCHAR_BIDI_MIRRORED
1.2516 + *
1.2517 + * @param c the code point to be tested
1.2518 + * @return TRUE if the character has the Bidi_Mirrored property
1.2519 + *
1.2520 + * @see UCHAR_BIDI_MIRRORED
1.2521 + * @stable ICU 2.0
1.2522 + */
1.2523 +U_STABLE UBool U_EXPORT2
1.2524 +u_isMirrored(UChar32 c);
1.2525 +
1.2526 +/**
1.2527 + * Maps the specified character to a "mirror-image" character.
1.2528 + * For characters with the Bidi_Mirrored property, implementations
1.2529 + * sometimes need a "poor man's" mapping to another Unicode
1.2530 + * character (code point) such that the default glyph may serve
1.2531 + * as the mirror-image of the default glyph of the specified
1.2532 + * character. This is useful for text conversion to and from
1.2533 + * codepages with visual order, and for displays without glyph
1.2534 + * selection capabilities.
1.2535 + *
1.2536 + * @param c the code point to be mapped
1.2537 + * @return another Unicode code point that may serve as a mirror-image
1.2538 + * substitute, or c itself if there is no such mapping or c
1.2539 + * does not have the Bidi_Mirrored property
1.2540 + *
1.2541 + * @see UCHAR_BIDI_MIRRORED
1.2542 + * @see u_isMirrored
1.2543 + * @stable ICU 2.0
1.2544 + */
1.2545 +U_STABLE UChar32 U_EXPORT2
1.2546 +u_charMirror(UChar32 c);
1.2547 +
1.2548 +/**
1.2549 + * Maps the specified character to its paired bracket character.
1.2550 + * For Bidi_Paired_Bracket_Type!=None, this is the same as u_charMirror().
1.2551 + * Otherwise c itself is returned.
1.2552 + * See http://www.unicode.org/reports/tr9/
1.2553 + *
1.2554 + * @param c the code point to be mapped
1.2555 + * @return the paired bracket code point,
1.2556 + * or c itself if there is no such mapping
1.2557 + * (Bidi_Paired_Bracket_Type=None)
1.2558 + *
1.2559 + * @see UCHAR_BIDI_PAIRED_BRACKET
1.2560 + * @see UCHAR_BIDI_PAIRED_BRACKET_TYPE
1.2561 + * @see u_charMirror
1.2562 + * @stable ICU 52
1.2563 + */
1.2564 +U_STABLE UChar32 U_EXPORT2
1.2565 +u_getBidiPairedBracket(UChar32 c);
1.2566 +
1.2567 +/**
1.2568 + * Returns the general category value for the code point.
1.2569 + *
1.2570 + * Same as java.lang.Character.getType().
1.2571 + *
1.2572 + * @param c the code point to be tested
1.2573 + * @return the general category (UCharCategory) value
1.2574 + *
1.2575 + * @see UCharCategory
1.2576 + * @stable ICU 2.0
1.2577 + */
1.2578 +U_STABLE int8_t U_EXPORT2
1.2579 +u_charType(UChar32 c);
1.2580 +
1.2581 +/**
1.2582 + * Get a single-bit bit set for the general category of a character.
1.2583 + * This bit set can be compared bitwise with U_GC_SM_MASK, U_GC_L_MASK, etc.
1.2584 + * Same as U_MASK(u_charType(c)).
1.2585 + *
1.2586 + * @param c the code point to be tested
1.2587 + * @return a single-bit mask corresponding to the general category (UCharCategory) value
1.2588 + *
1.2589 + * @see u_charType
1.2590 + * @see UCharCategory
1.2591 + * @see U_GC_CN_MASK
1.2592 + * @stable ICU 2.1
1.2593 + */
1.2594 +#define U_GET_GC_MASK(c) U_MASK(u_charType(c))
1.2595 +
1.2596 +/**
1.2597 + * Callback from u_enumCharTypes(), is called for each contiguous range
1.2598 + * of code points c (where start<=c<limit)
1.2599 + * with the same Unicode general category ("character type").
1.2600 + *
1.2601 + * The callback function can stop the enumeration by returning FALSE.
1.2602 + *
1.2603 + * @param context an opaque pointer, as passed into utrie_enum()
1.2604 + * @param start the first code point in a contiguous range with value
1.2605 + * @param limit one past the last code point in a contiguous range with value
1.2606 + * @param type the general category for all code points in [start..limit[
1.2607 + * @return FALSE to stop the enumeration
1.2608 + *
1.2609 + * @stable ICU 2.1
1.2610 + * @see UCharCategory
1.2611 + * @see u_enumCharTypes
1.2612 + */
1.2613 +typedef UBool U_CALLCONV
1.2614 +UCharEnumTypeRange(const void *context, UChar32 start, UChar32 limit, UCharCategory type);
1.2615 +
1.2616 +/**
1.2617 + * Enumerate efficiently all code points with their Unicode general categories.
1.2618 + *
1.2619 + * This is useful for building data structures (e.g., UnicodeSet's),
1.2620 + * for enumerating all assigned code points (type!=U_UNASSIGNED), etc.
1.2621 + *
1.2622 + * For each contiguous range of code points with a given general category ("character type"),
1.2623 + * the UCharEnumTypeRange function is called.
1.2624 + * Adjacent ranges have different types.
1.2625 + * The Unicode Standard guarantees that the numeric value of the type is 0..31.
1.2626 + *
1.2627 + * @param enumRange a pointer to a function that is called for each contiguous range
1.2628 + * of code points with the same general category
1.2629 + * @param context an opaque pointer that is passed on to the callback function
1.2630 + *
1.2631 + * @stable ICU 2.1
1.2632 + * @see UCharCategory
1.2633 + * @see UCharEnumTypeRange
1.2634 + */
1.2635 +U_STABLE void U_EXPORT2
1.2636 +u_enumCharTypes(UCharEnumTypeRange *enumRange, const void *context);
1.2637 +
1.2638 +#if !UCONFIG_NO_NORMALIZATION
1.2639 +
1.2640 +/**
1.2641 + * Returns the combining class of the code point as specified in UnicodeData.txt.
1.2642 + *
1.2643 + * @param c the code point of the character
1.2644 + * @return the combining class of the character
1.2645 + * @stable ICU 2.0
1.2646 + */
1.2647 +U_STABLE uint8_t U_EXPORT2
1.2648 +u_getCombiningClass(UChar32 c);
1.2649 +
1.2650 +#endif
1.2651 +
1.2652 +/**
1.2653 + * Returns the decimal digit value of a decimal digit character.
1.2654 + * Such characters have the general category "Nd" (decimal digit numbers)
1.2655 + * and a Numeric_Type of Decimal.
1.2656 + *
1.2657 + * Unlike ICU releases before 2.6, no digit values are returned for any
1.2658 + * Han characters because Han number characters are often used with a special
1.2659 + * Chinese-style number format (with characters for powers of 10 in between)
1.2660 + * instead of in decimal-positional notation.
1.2661 + * Unicode 4 explicitly assigns Han number characters the Numeric_Type
1.2662 + * Numeric instead of Decimal.
1.2663 + * See Jitterbug 1483 for more details.
1.2664 + *
1.2665 + * Use u_getIntPropertyValue(c, UCHAR_NUMERIC_TYPE) and u_getNumericValue()
1.2666 + * for complete numeric Unicode properties.
1.2667 + *
1.2668 + * @param c the code point for which to get the decimal digit value
1.2669 + * @return the decimal digit value of c,
1.2670 + * or -1 if c is not a decimal digit character
1.2671 + *
1.2672 + * @see u_getNumericValue
1.2673 + * @stable ICU 2.0
1.2674 + */
1.2675 +U_STABLE int32_t U_EXPORT2
1.2676 +u_charDigitValue(UChar32 c);
1.2677 +
1.2678 +/**
1.2679 + * Returns the Unicode allocation block that contains the character.
1.2680 + *
1.2681 + * @param c the code point to be tested
1.2682 + * @return the block value (UBlockCode) for c
1.2683 + *
1.2684 + * @see UBlockCode
1.2685 + * @stable ICU 2.0
1.2686 + */
1.2687 +U_STABLE UBlockCode U_EXPORT2
1.2688 +ublock_getCode(UChar32 c);
1.2689 +
1.2690 +/**
1.2691 + * Retrieve the name of a Unicode character.
1.2692 + * Depending on <code>nameChoice</code>, the character name written
1.2693 + * into the buffer is the "modern" name or the name that was defined
1.2694 + * in Unicode version 1.0.
1.2695 + * The name contains only "invariant" characters
1.2696 + * like A-Z, 0-9, space, and '-'.
1.2697 + * Unicode 1.0 names are only retrieved if they are different from the modern
1.2698 + * names and if the data file contains the data for them. gennames may or may
1.2699 + * not be called with a command line option to include 1.0 names in unames.dat.
1.2700 + *
1.2701 + * @param code The character (code point) for which to get the name.
1.2702 + * It must be <code>0<=code<=0x10ffff</code>.
1.2703 + * @param nameChoice Selector for which name to get.
1.2704 + * @param buffer Destination address for copying the name.
1.2705 + * The name will always be zero-terminated.
1.2706 + * If there is no name, then the buffer will be set to the empty string.
1.2707 + * @param bufferLength <code>==sizeof(buffer)</code>
1.2708 + * @param pErrorCode Pointer to a UErrorCode variable;
1.2709 + * check for <code>U_SUCCESS()</code> after <code>u_charName()</code>
1.2710 + * returns.
1.2711 + * @return The length of the name, or 0 if there is no name for this character.
1.2712 + * If the bufferLength is less than or equal to the length, then the buffer
1.2713 + * contains the truncated name and the returned length indicates the full
1.2714 + * length of the name.
1.2715 + * The length does not include the zero-termination.
1.2716 + *
1.2717 + * @see UCharNameChoice
1.2718 + * @see u_charFromName
1.2719 + * @see u_enumCharNames
1.2720 + * @stable ICU 2.0
1.2721 + */
1.2722 +U_STABLE int32_t U_EXPORT2
1.2723 +u_charName(UChar32 code, UCharNameChoice nameChoice,
1.2724 + char *buffer, int32_t bufferLength,
1.2725 + UErrorCode *pErrorCode);
1.2726 +
1.2727 +#ifndef U_HIDE_DEPRECATED_API
1.2728 +/**
1.2729 + * Returns an empty string.
1.2730 + * Used to return the ISO 10646 comment for a character.
1.2731 + * The Unicode ISO_Comment property is deprecated and has no values.
1.2732 + *
1.2733 + * @param c The character (code point) for which to get the ISO comment.
1.2734 + * It must be <code>0<=c<=0x10ffff</code>.
1.2735 + * @param dest Destination address for copying the comment.
1.2736 + * The comment will be zero-terminated if possible.
1.2737 + * If there is no comment, then the buffer will be set to the empty string.
1.2738 + * @param destCapacity <code>==sizeof(dest)</code>
1.2739 + * @param pErrorCode Pointer to a UErrorCode variable;
1.2740 + * check for <code>U_SUCCESS()</code> after <code>u_getISOComment()</code>
1.2741 + * returns.
1.2742 + * @return 0
1.2743 + *
1.2744 + * @deprecated ICU 49
1.2745 + */
1.2746 +U_STABLE int32_t U_EXPORT2
1.2747 +u_getISOComment(UChar32 c,
1.2748 + char *dest, int32_t destCapacity,
1.2749 + UErrorCode *pErrorCode);
1.2750 +#endif /* U_HIDE_DEPRECATED_API */
1.2751 +
1.2752 +/**
1.2753 + * Find a Unicode character by its name and return its code point value.
1.2754 + * The name is matched exactly and completely.
1.2755 + * If the name does not correspond to a code point, <i>pErrorCode</i>
1.2756 + * is set to <code>U_INVALID_CHAR_FOUND</code>.
1.2757 + * A Unicode 1.0 name is matched only if it differs from the modern name.
1.2758 + * Unicode names are all uppercase. Extended names are lowercase followed
1.2759 + * by an uppercase hexadecimal number, and within angle brackets.
1.2760 + *
1.2761 + * @param nameChoice Selector for which name to match.
1.2762 + * @param name The name to match.
1.2763 + * @param pErrorCode Pointer to a UErrorCode variable
1.2764 + * @return The Unicode value of the code point with the given name,
1.2765 + * or an undefined value if there is no such code point.
1.2766 + *
1.2767 + * @see UCharNameChoice
1.2768 + * @see u_charName
1.2769 + * @see u_enumCharNames
1.2770 + * @stable ICU 1.7
1.2771 + */
1.2772 +U_STABLE UChar32 U_EXPORT2
1.2773 +u_charFromName(UCharNameChoice nameChoice,
1.2774 + const char *name,
1.2775 + UErrorCode *pErrorCode);
1.2776 +
1.2777 +/**
1.2778 + * Type of a callback function for u_enumCharNames() that gets called
1.2779 + * for each Unicode character with the code point value and
1.2780 + * the character name.
1.2781 + * If such a function returns FALSE, then the enumeration is stopped.
1.2782 + *
1.2783 + * @param context The context pointer that was passed to u_enumCharNames().
1.2784 + * @param code The Unicode code point for the character with this name.
1.2785 + * @param nameChoice Selector for which kind of names is enumerated.
1.2786 + * @param name The character's name, zero-terminated.
1.2787 + * @param length The length of the name.
1.2788 + * @return TRUE if the enumeration should continue, FALSE to stop it.
1.2789 + *
1.2790 + * @see UCharNameChoice
1.2791 + * @see u_enumCharNames
1.2792 + * @stable ICU 1.7
1.2793 + */
1.2794 +typedef UBool U_CALLCONV UEnumCharNamesFn(void *context,
1.2795 + UChar32 code,
1.2796 + UCharNameChoice nameChoice,
1.2797 + const char *name,
1.2798 + int32_t length);
1.2799 +
1.2800 +/**
1.2801 + * Enumerate all assigned Unicode characters between the start and limit
1.2802 + * code points (start inclusive, limit exclusive) and call a function
1.2803 + * for each, passing the code point value and the character name.
1.2804 + * For Unicode 1.0 names, only those are enumerated that differ from the
1.2805 + * modern names.
1.2806 + *
1.2807 + * @param start The first code point in the enumeration range.
1.2808 + * @param limit One more than the last code point in the enumeration range
1.2809 + * (the first one after the range).
1.2810 + * @param fn The function that is to be called for each character name.
1.2811 + * @param context An arbitrary pointer that is passed to the function.
1.2812 + * @param nameChoice Selector for which kind of names to enumerate.
1.2813 + * @param pErrorCode Pointer to a UErrorCode variable
1.2814 + *
1.2815 + * @see UCharNameChoice
1.2816 + * @see UEnumCharNamesFn
1.2817 + * @see u_charName
1.2818 + * @see u_charFromName
1.2819 + * @stable ICU 1.7
1.2820 + */
1.2821 +U_STABLE void U_EXPORT2
1.2822 +u_enumCharNames(UChar32 start, UChar32 limit,
1.2823 + UEnumCharNamesFn *fn,
1.2824 + void *context,
1.2825 + UCharNameChoice nameChoice,
1.2826 + UErrorCode *pErrorCode);
1.2827 +
1.2828 +/**
1.2829 + * Return the Unicode name for a given property, as given in the
1.2830 + * Unicode database file PropertyAliases.txt.
1.2831 + *
1.2832 + * In addition, this function maps the property
1.2833 + * UCHAR_GENERAL_CATEGORY_MASK to the synthetic names "gcm" /
1.2834 + * "General_Category_Mask". These names are not in
1.2835 + * PropertyAliases.txt.
1.2836 + *
1.2837 + * @param property UProperty selector other than UCHAR_INVALID_CODE.
1.2838 + * If out of range, NULL is returned.
1.2839 + *
1.2840 + * @param nameChoice selector for which name to get. If out of range,
1.2841 + * NULL is returned. All properties have a long name. Most
1.2842 + * have a short name, but some do not. Unicode allows for
1.2843 + * additional names; if present these will be returned by
1.2844 + * U_LONG_PROPERTY_NAME + i, where i=1, 2,...
1.2845 + *
1.2846 + * @return a pointer to the name, or NULL if either the
1.2847 + * property or the nameChoice is out of range. If a given
1.2848 + * nameChoice returns NULL, then all larger values of
1.2849 + * nameChoice will return NULL, with one exception: if NULL is
1.2850 + * returned for U_SHORT_PROPERTY_NAME, then
1.2851 + * U_LONG_PROPERTY_NAME (and higher) may still return a
1.2852 + * non-NULL value. The returned pointer is valid until
1.2853 + * u_cleanup() is called.
1.2854 + *
1.2855 + * @see UProperty
1.2856 + * @see UPropertyNameChoice
1.2857 + * @stable ICU 2.4
1.2858 + */
1.2859 +U_STABLE const char* U_EXPORT2
1.2860 +u_getPropertyName(UProperty property,
1.2861 + UPropertyNameChoice nameChoice);
1.2862 +
1.2863 +/**
1.2864 + * Return the UProperty enum for a given property name, as specified
1.2865 + * in the Unicode database file PropertyAliases.txt. Short, long, and
1.2866 + * any other variants are recognized.
1.2867 + *
1.2868 + * In addition, this function maps the synthetic names "gcm" /
1.2869 + * "General_Category_Mask" to the property
1.2870 + * UCHAR_GENERAL_CATEGORY_MASK. These names are not in
1.2871 + * PropertyAliases.txt.
1.2872 + *
1.2873 + * @param alias the property name to be matched. The name is compared
1.2874 + * using "loose matching" as described in PropertyAliases.txt.
1.2875 + *
1.2876 + * @return a UProperty enum, or UCHAR_INVALID_CODE if the given name
1.2877 + * does not match any property.
1.2878 + *
1.2879 + * @see UProperty
1.2880 + * @stable ICU 2.4
1.2881 + */
1.2882 +U_STABLE UProperty U_EXPORT2
1.2883 +u_getPropertyEnum(const char* alias);
1.2884 +
1.2885 +/**
1.2886 + * Return the Unicode name for a given property value, as given in the
1.2887 + * Unicode database file PropertyValueAliases.txt.
1.2888 + *
1.2889 + * Note: Some of the names in PropertyValueAliases.txt can only be
1.2890 + * retrieved using UCHAR_GENERAL_CATEGORY_MASK, not
1.2891 + * UCHAR_GENERAL_CATEGORY. These include: "C" / "Other", "L" /
1.2892 + * "Letter", "LC" / "Cased_Letter", "M" / "Mark", "N" / "Number", "P"
1.2893 + * / "Punctuation", "S" / "Symbol", and "Z" / "Separator".
1.2894 + *
1.2895 + * @param property UProperty selector constant.
1.2896 + * Must be UCHAR_BINARY_START<=which<UCHAR_BINARY_LIMIT
1.2897 + * or UCHAR_INT_START<=which<UCHAR_INT_LIMIT
1.2898 + * or UCHAR_MASK_START<=which<UCHAR_MASK_LIMIT.
1.2899 + * If out of range, NULL is returned.
1.2900 + *
1.2901 + * @param value selector for a value for the given property. If out
1.2902 + * of range, NULL is returned. In general, valid values range
1.2903 + * from 0 up to some maximum. There are a few exceptions:
1.2904 + * (1.) UCHAR_BLOCK values begin at the non-zero value
1.2905 + * UBLOCK_BASIC_LATIN. (2.) UCHAR_CANONICAL_COMBINING_CLASS
1.2906 + * values are not contiguous and range from 0..240. (3.)
1.2907 + * UCHAR_GENERAL_CATEGORY_MASK values are not values of
1.2908 + * UCharCategory, but rather mask values produced by
1.2909 + * U_GET_GC_MASK(). This allows grouped categories such as
1.2910 + * [:L:] to be represented. Mask values range
1.2911 + * non-contiguously from 1..U_GC_P_MASK.
1.2912 + *
1.2913 + * @param nameChoice selector for which name to get. If out of range,
1.2914 + * NULL is returned. All values have a long name. Most have
1.2915 + * a short name, but some do not. Unicode allows for
1.2916 + * additional names; if present these will be returned by
1.2917 + * U_LONG_PROPERTY_NAME + i, where i=1, 2,...
1.2918 +
1.2919 + * @return a pointer to the name, or NULL if either the
1.2920 + * property or the nameChoice is out of range. If a given
1.2921 + * nameChoice returns NULL, then all larger values of
1.2922 + * nameChoice will return NULL, with one exception: if NULL is
1.2923 + * returned for U_SHORT_PROPERTY_NAME, then
1.2924 + * U_LONG_PROPERTY_NAME (and higher) may still return a
1.2925 + * non-NULL value. The returned pointer is valid until
1.2926 + * u_cleanup() is called.
1.2927 + *
1.2928 + * @see UProperty
1.2929 + * @see UPropertyNameChoice
1.2930 + * @stable ICU 2.4
1.2931 + */
1.2932 +U_STABLE const char* U_EXPORT2
1.2933 +u_getPropertyValueName(UProperty property,
1.2934 + int32_t value,
1.2935 + UPropertyNameChoice nameChoice);
1.2936 +
1.2937 +/**
1.2938 + * Return the property value integer for a given value name, as
1.2939 + * specified in the Unicode database file PropertyValueAliases.txt.
1.2940 + * Short, long, and any other variants are recognized.
1.2941 + *
1.2942 + * Note: Some of the names in PropertyValueAliases.txt will only be
1.2943 + * recognized with UCHAR_GENERAL_CATEGORY_MASK, not
1.2944 + * UCHAR_GENERAL_CATEGORY. These include: "C" / "Other", "L" /
1.2945 + * "Letter", "LC" / "Cased_Letter", "M" / "Mark", "N" / "Number", "P"
1.2946 + * / "Punctuation", "S" / "Symbol", and "Z" / "Separator".
1.2947 + *
1.2948 + * @param property UProperty selector constant.
1.2949 + * Must be UCHAR_BINARY_START<=which<UCHAR_BINARY_LIMIT
1.2950 + * or UCHAR_INT_START<=which<UCHAR_INT_LIMIT
1.2951 + * or UCHAR_MASK_START<=which<UCHAR_MASK_LIMIT.
1.2952 + * If out of range, UCHAR_INVALID_CODE is returned.
1.2953 + *
1.2954 + * @param alias the value name to be matched. The name is compared
1.2955 + * using "loose matching" as described in
1.2956 + * PropertyValueAliases.txt.
1.2957 + *
1.2958 + * @return a value integer or UCHAR_INVALID_CODE if the given name
1.2959 + * does not match any value of the given property, or if the
1.2960 + * property is invalid. Note: UCHAR_GENERAL_CATEGORY_MASK values
1.2961 + * are not values of UCharCategory, but rather mask values
1.2962 + * produced by U_GET_GC_MASK(). This allows grouped
1.2963 + * categories such as [:L:] to be represented.
1.2964 + *
1.2965 + * @see UProperty
1.2966 + * @stable ICU 2.4
1.2967 + */
1.2968 +U_STABLE int32_t U_EXPORT2
1.2969 +u_getPropertyValueEnum(UProperty property,
1.2970 + const char* alias);
1.2971 +
1.2972 +/**
1.2973 + * Determines if the specified character is permissible as the
1.2974 + * first character in an identifier according to Unicode
1.2975 + * (The Unicode Standard, Version 3.0, chapter 5.16 Identifiers).
1.2976 + * True for characters with general categories "L" (letters) and "Nl" (letter numbers).
1.2977 + *
1.2978 + * Same as java.lang.Character.isUnicodeIdentifierStart().
1.2979 + * Same as UCHAR_ID_START
1.2980 + *
1.2981 + * @param c the code point to be tested
1.2982 + * @return TRUE if the code point may start an identifier
1.2983 + *
1.2984 + * @see UCHAR_ID_START
1.2985 + * @see u_isalpha
1.2986 + * @see u_isIDPart
1.2987 + * @stable ICU 2.0
1.2988 + */
1.2989 +U_STABLE UBool U_EXPORT2
1.2990 +u_isIDStart(UChar32 c);
1.2991 +
1.2992 +/**
1.2993 + * Determines if the specified character is permissible
1.2994 + * in an identifier according to Java.
1.2995 + * True for characters with general categories "L" (letters),
1.2996 + * "Nl" (letter numbers), "Nd" (decimal digits),
1.2997 + * "Mc" and "Mn" (combining marks), "Pc" (connecting punctuation), and
1.2998 + * u_isIDIgnorable(c).
1.2999 + *
1.3000 + * Same as java.lang.Character.isUnicodeIdentifierPart().
1.3001 + * Almost the same as Unicode's ID_Continue (UCHAR_ID_CONTINUE)
1.3002 + * except that Unicode recommends to ignore Cf which is less than
1.3003 + * u_isIDIgnorable(c).
1.3004 + *
1.3005 + * @param c the code point to be tested
1.3006 + * @return TRUE if the code point may occur in an identifier according to Java
1.3007 + *
1.3008 + * @see UCHAR_ID_CONTINUE
1.3009 + * @see u_isIDStart
1.3010 + * @see u_isIDIgnorable
1.3011 + * @stable ICU 2.0
1.3012 + */
1.3013 +U_STABLE UBool U_EXPORT2
1.3014 +u_isIDPart(UChar32 c);
1.3015 +
1.3016 +/**
1.3017 + * Determines if the specified character should be regarded
1.3018 + * as an ignorable character in an identifier,
1.3019 + * according to Java.
1.3020 + * True for characters with general category "Cf" (format controls) as well as
1.3021 + * non-whitespace ISO controls
1.3022 + * (U+0000..U+0008, U+000E..U+001B, U+007F..U+009F).
1.3023 + *
1.3024 + * Same as java.lang.Character.isIdentifierIgnorable().
1.3025 + *
1.3026 + * Note that Unicode just recommends to ignore Cf (format controls).
1.3027 + *
1.3028 + * @param c the code point to be tested
1.3029 + * @return TRUE if the code point is ignorable in identifiers according to Java
1.3030 + *
1.3031 + * @see UCHAR_DEFAULT_IGNORABLE_CODE_POINT
1.3032 + * @see u_isIDStart
1.3033 + * @see u_isIDPart
1.3034 + * @stable ICU 2.0
1.3035 + */
1.3036 +U_STABLE UBool U_EXPORT2
1.3037 +u_isIDIgnorable(UChar32 c);
1.3038 +
1.3039 +/**
1.3040 + * Determines if the specified character is permissible as the
1.3041 + * first character in a Java identifier.
1.3042 + * In addition to u_isIDStart(c), true for characters with
1.3043 + * general categories "Sc" (currency symbols) and "Pc" (connecting punctuation).
1.3044 + *
1.3045 + * Same as java.lang.Character.isJavaIdentifierStart().
1.3046 + *
1.3047 + * @param c the code point to be tested
1.3048 + * @return TRUE if the code point may start a Java identifier
1.3049 + *
1.3050 + * @see u_isJavaIDPart
1.3051 + * @see u_isalpha
1.3052 + * @see u_isIDStart
1.3053 + * @stable ICU 2.0
1.3054 + */
1.3055 +U_STABLE UBool U_EXPORT2
1.3056 +u_isJavaIDStart(UChar32 c);
1.3057 +
1.3058 +/**
1.3059 + * Determines if the specified character is permissible
1.3060 + * in a Java identifier.
1.3061 + * In addition to u_isIDPart(c), true for characters with
1.3062 + * general category "Sc" (currency symbols).
1.3063 + *
1.3064 + * Same as java.lang.Character.isJavaIdentifierPart().
1.3065 + *
1.3066 + * @param c the code point to be tested
1.3067 + * @return TRUE if the code point may occur in a Java identifier
1.3068 + *
1.3069 + * @see u_isIDIgnorable
1.3070 + * @see u_isJavaIDStart
1.3071 + * @see u_isalpha
1.3072 + * @see u_isdigit
1.3073 + * @see u_isIDPart
1.3074 + * @stable ICU 2.0
1.3075 + */
1.3076 +U_STABLE UBool U_EXPORT2
1.3077 +u_isJavaIDPart(UChar32 c);
1.3078 +
1.3079 +/**
1.3080 + * The given character is mapped to its lowercase equivalent according to
1.3081 + * UnicodeData.txt; if the character has no lowercase equivalent, the character
1.3082 + * itself is returned.
1.3083 + *
1.3084 + * Same as java.lang.Character.toLowerCase().
1.3085 + *
1.3086 + * This function only returns the simple, single-code point case mapping.
1.3087 + * Full case mappings should be used whenever possible because they produce
1.3088 + * better results by working on whole strings.
1.3089 + * They take into account the string context and the language and can map
1.3090 + * to a result string with a different length as appropriate.
1.3091 + * Full case mappings are applied by the string case mapping functions,
1.3092 + * see ustring.h and the UnicodeString class.
1.3093 + * See also the User Guide chapter on C/POSIX migration:
1.3094 + * http://icu-project.org/userguide/posix.html#case_mappings
1.3095 + *
1.3096 + * @param c the code point to be mapped
1.3097 + * @return the Simple_Lowercase_Mapping of the code point, if any;
1.3098 + * otherwise the code point itself.
1.3099 + * @stable ICU 2.0
1.3100 + */
1.3101 +U_STABLE UChar32 U_EXPORT2
1.3102 +u_tolower(UChar32 c);
1.3103 +
1.3104 +/**
1.3105 + * The given character is mapped to its uppercase equivalent according to UnicodeData.txt;
1.3106 + * if the character has no uppercase equivalent, the character itself is
1.3107 + * returned.
1.3108 + *
1.3109 + * Same as java.lang.Character.toUpperCase().
1.3110 + *
1.3111 + * This function only returns the simple, single-code point case mapping.
1.3112 + * Full case mappings should be used whenever possible because they produce
1.3113 + * better results by working on whole strings.
1.3114 + * They take into account the string context and the language and can map
1.3115 + * to a result string with a different length as appropriate.
1.3116 + * Full case mappings are applied by the string case mapping functions,
1.3117 + * see ustring.h and the UnicodeString class.
1.3118 + * See also the User Guide chapter on C/POSIX migration:
1.3119 + * http://icu-project.org/userguide/posix.html#case_mappings
1.3120 + *
1.3121 + * @param c the code point to be mapped
1.3122 + * @return the Simple_Uppercase_Mapping of the code point, if any;
1.3123 + * otherwise the code point itself.
1.3124 + * @stable ICU 2.0
1.3125 + */
1.3126 +U_STABLE UChar32 U_EXPORT2
1.3127 +u_toupper(UChar32 c);
1.3128 +
1.3129 +/**
1.3130 + * The given character is mapped to its titlecase equivalent
1.3131 + * according to UnicodeData.txt;
1.3132 + * if none is defined, the character itself is returned.
1.3133 + *
1.3134 + * Same as java.lang.Character.toTitleCase().
1.3135 + *
1.3136 + * This function only returns the simple, single-code point case mapping.
1.3137 + * Full case mappings should be used whenever possible because they produce
1.3138 + * better results by working on whole strings.
1.3139 + * They take into account the string context and the language and can map
1.3140 + * to a result string with a different length as appropriate.
1.3141 + * Full case mappings are applied by the string case mapping functions,
1.3142 + * see ustring.h and the UnicodeString class.
1.3143 + * See also the User Guide chapter on C/POSIX migration:
1.3144 + * http://icu-project.org/userguide/posix.html#case_mappings
1.3145 + *
1.3146 + * @param c the code point to be mapped
1.3147 + * @return the Simple_Titlecase_Mapping of the code point, if any;
1.3148 + * otherwise the code point itself.
1.3149 + * @stable ICU 2.0
1.3150 + */
1.3151 +U_STABLE UChar32 U_EXPORT2
1.3152 +u_totitle(UChar32 c);
1.3153 +
1.3154 +/** Option value for case folding: use default mappings defined in CaseFolding.txt. @stable ICU 2.0 */
1.3155 +#define U_FOLD_CASE_DEFAULT 0
1.3156 +
1.3157 +/**
1.3158 + * Option value for case folding:
1.3159 + *
1.3160 + * Use the modified set of mappings provided in CaseFolding.txt to handle dotted I
1.3161 + * and dotless i appropriately for Turkic languages (tr, az).
1.3162 + *
1.3163 + * Before Unicode 3.2, CaseFolding.txt contains mappings marked with 'I' that
1.3164 + * are to be included for default mappings and
1.3165 + * excluded for the Turkic-specific mappings.
1.3166 + *
1.3167 + * Unicode 3.2 CaseFolding.txt instead contains mappings marked with 'T' that
1.3168 + * are to be excluded for default mappings and
1.3169 + * included for the Turkic-specific mappings.
1.3170 + *
1.3171 + * @stable ICU 2.0
1.3172 + */
1.3173 +#define U_FOLD_CASE_EXCLUDE_SPECIAL_I 1
1.3174 +
1.3175 +/**
1.3176 + * The given character is mapped to its case folding equivalent according to
1.3177 + * UnicodeData.txt and CaseFolding.txt;
1.3178 + * if the character has no case folding equivalent, the character
1.3179 + * itself is returned.
1.3180 + *
1.3181 + * This function only returns the simple, single-code point case mapping.
1.3182 + * Full case mappings should be used whenever possible because they produce
1.3183 + * better results by working on whole strings.
1.3184 + * They take into account the string context and the language and can map
1.3185 + * to a result string with a different length as appropriate.
1.3186 + * Full case mappings are applied by the string case mapping functions,
1.3187 + * see ustring.h and the UnicodeString class.
1.3188 + * See also the User Guide chapter on C/POSIX migration:
1.3189 + * http://icu-project.org/userguide/posix.html#case_mappings
1.3190 + *
1.3191 + * @param c the code point to be mapped
1.3192 + * @param options Either U_FOLD_CASE_DEFAULT or U_FOLD_CASE_EXCLUDE_SPECIAL_I
1.3193 + * @return the Simple_Case_Folding of the code point, if any;
1.3194 + * otherwise the code point itself.
1.3195 + * @stable ICU 2.0
1.3196 + */
1.3197 +U_STABLE UChar32 U_EXPORT2
1.3198 +u_foldCase(UChar32 c, uint32_t options);
1.3199 +
1.3200 +/**
1.3201 + * Returns the decimal digit value of the code point in the
1.3202 + * specified radix.
1.3203 + *
1.3204 + * If the radix is not in the range <code>2<=radix<=36</code> or if the
1.3205 + * value of <code>c</code> is not a valid digit in the specified
1.3206 + * radix, <code>-1</code> is returned. A character is a valid digit
1.3207 + * if at least one of the following is true:
1.3208 + * <ul>
1.3209 + * <li>The character has a decimal digit value.
1.3210 + * Such characters have the general category "Nd" (decimal digit numbers)
1.3211 + * and a Numeric_Type of Decimal.
1.3212 + * In this case the value is the character's decimal digit value.</li>
1.3213 + * <li>The character is one of the uppercase Latin letters
1.3214 + * <code>'A'</code> through <code>'Z'</code>.
1.3215 + * In this case the value is <code>c-'A'+10</code>.</li>
1.3216 + * <li>The character is one of the lowercase Latin letters
1.3217 + * <code>'a'</code> through <code>'z'</code>.
1.3218 + * In this case the value is <code>ch-'a'+10</code>.</li>
1.3219 + * <li>Latin letters from both the ASCII range (0061..007A, 0041..005A)
1.3220 + * as well as from the Fullwidth ASCII range (FF41..FF5A, FF21..FF3A)
1.3221 + * are recognized.</li>
1.3222 + * </ul>
1.3223 + *
1.3224 + * Same as java.lang.Character.digit().
1.3225 + *
1.3226 + * @param ch the code point to be tested.
1.3227 + * @param radix the radix.
1.3228 + * @return the numeric value represented by the character in the
1.3229 + * specified radix,
1.3230 + * or -1 if there is no value or if the value exceeds the radix.
1.3231 + *
1.3232 + * @see UCHAR_NUMERIC_TYPE
1.3233 + * @see u_forDigit
1.3234 + * @see u_charDigitValue
1.3235 + * @see u_isdigit
1.3236 + * @stable ICU 2.0
1.3237 + */
1.3238 +U_STABLE int32_t U_EXPORT2
1.3239 +u_digit(UChar32 ch, int8_t radix);
1.3240 +
1.3241 +/**
1.3242 + * Determines the character representation for a specific digit in
1.3243 + * the specified radix. If the value of <code>radix</code> is not a
1.3244 + * valid radix, or the value of <code>digit</code> is not a valid
1.3245 + * digit in the specified radix, the null character
1.3246 + * (<code>U+0000</code>) is returned.
1.3247 + * <p>
1.3248 + * The <code>radix</code> argument is valid if it is greater than or
1.3249 + * equal to 2 and less than or equal to 36.
1.3250 + * The <code>digit</code> argument is valid if
1.3251 + * <code>0 <= digit < radix</code>.
1.3252 + * <p>
1.3253 + * If the digit is less than 10, then
1.3254 + * <code>'0' + digit</code> is returned. Otherwise, the value
1.3255 + * <code>'a' + digit - 10</code> is returned.
1.3256 + *
1.3257 + * Same as java.lang.Character.forDigit().
1.3258 + *
1.3259 + * @param digit the number to convert to a character.
1.3260 + * @param radix the radix.
1.3261 + * @return the <code>char</code> representation of the specified digit
1.3262 + * in the specified radix.
1.3263 + *
1.3264 + * @see u_digit
1.3265 + * @see u_charDigitValue
1.3266 + * @see u_isdigit
1.3267 + * @stable ICU 2.0
1.3268 + */
1.3269 +U_STABLE UChar32 U_EXPORT2
1.3270 +u_forDigit(int32_t digit, int8_t radix);
1.3271 +
1.3272 +/**
1.3273 + * Get the "age" of the code point.
1.3274 + * The "age" is the Unicode version when the code point was first
1.3275 + * designated (as a non-character or for Private Use)
1.3276 + * or assigned a character.
1.3277 + * This can be useful to avoid emitting code points to receiving
1.3278 + * processes that do not accept newer characters.
1.3279 + * The data is from the UCD file DerivedAge.txt.
1.3280 + *
1.3281 + * @param c The code point.
1.3282 + * @param versionArray The Unicode version number array, to be filled in.
1.3283 + *
1.3284 + * @stable ICU 2.1
1.3285 + */
1.3286 +U_STABLE void U_EXPORT2
1.3287 +u_charAge(UChar32 c, UVersionInfo versionArray);
1.3288 +
1.3289 +/**
1.3290 + * Gets the Unicode version information.
1.3291 + * The version array is filled in with the version information
1.3292 + * for the Unicode standard that is currently used by ICU.
1.3293 + * For example, Unicode version 3.1.1 is represented as an array with
1.3294 + * the values { 3, 1, 1, 0 }.
1.3295 + *
1.3296 + * @param versionArray an output array that will be filled in with
1.3297 + * the Unicode version number
1.3298 + * @stable ICU 2.0
1.3299 + */
1.3300 +U_STABLE void U_EXPORT2
1.3301 +u_getUnicodeVersion(UVersionInfo versionArray);
1.3302 +
1.3303 +#if !UCONFIG_NO_NORMALIZATION
1.3304 +/**
1.3305 + * Get the FC_NFKC_Closure property string for a character.
1.3306 + * See Unicode Standard Annex #15 for details, search for "FC_NFKC_Closure"
1.3307 + * or for "FNC": http://www.unicode.org/reports/tr15/
1.3308 + *
1.3309 + * @param c The character (code point) for which to get the FC_NFKC_Closure string.
1.3310 + * It must be <code>0<=c<=0x10ffff</code>.
1.3311 + * @param dest Destination address for copying the string.
1.3312 + * The string will be zero-terminated if possible.
1.3313 + * If there is no FC_NFKC_Closure string,
1.3314 + * then the buffer will be set to the empty string.
1.3315 + * @param destCapacity <code>==sizeof(dest)</code>
1.3316 + * @param pErrorCode Pointer to a UErrorCode variable.
1.3317 + * @return The length of the string, or 0 if there is no FC_NFKC_Closure string for this character.
1.3318 + * If the destCapacity is less than or equal to the length, then the buffer
1.3319 + * contains the truncated name and the returned length indicates the full
1.3320 + * length of the name.
1.3321 + * The length does not include the zero-termination.
1.3322 + *
1.3323 + * @stable ICU 2.2
1.3324 + */
1.3325 +U_STABLE int32_t U_EXPORT2
1.3326 +u_getFC_NFKC_Closure(UChar32 c, UChar *dest, int32_t destCapacity, UErrorCode *pErrorCode);
1.3327 +
1.3328 +#endif
1.3329 +
1.3330 +
1.3331 +U_CDECL_END
1.3332 +
1.3333 +#endif /*_UCHAR*/
1.3334 +/*eof*/
