Mercurial > repos > rliterman > csp2

annotate CSP2/CSP2_env/env-d9b9114564458d9d-741b3de822f2aaca6c6caa4325c4afce/include/unicode/uchar.h @ 69:33d812a61356

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload commit 2e9511a184a1ca667c7be0c6321a36dc4e3d116d
author jpayne
date Tue, 18 Mar 2025 17:55:14 -0400
parents
children
rev   line source
jpayne@69 1 // © 2016 and later: Unicode, Inc. and others.
jpayne@69 2 // License & terms of use: http://www.unicode.org/copyright.html
jpayne@69 3 /*
jpayne@69 4 **********************************************************************
jpayne@69 5 * Copyright (C) 1997-2016, International Business Machines
jpayne@69 6 * Corporation and others. All Rights Reserved.
jpayne@69 7 **********************************************************************
jpayne@69 8 *
jpayne@69 9 * File UCHAR.H
jpayne@69 10 *
jpayne@69 11 * Modification History:
jpayne@69 12 *
jpayne@69 13 * Date Name Description
jpayne@69 14 * 04/02/97 aliu Creation.
jpayne@69 15 * 03/29/99 helena Updated for C APIs.
jpayne@69 16 * 4/15/99 Madhu Updated for C Implementation and Javadoc
jpayne@69 17 * 5/20/99 Madhu Added the function u_getVersion()
jpayne@69 18 * 8/19/1999 srl Upgraded scripts to Unicode 3.0
jpayne@69 19 * 8/27/1999 schererm UCharDirection constants: U_...
jpayne@69 20 * 11/11/1999 weiv added u_isalnum(), cleaned comments
jpayne@69 21 * 01/11/2000 helena Renamed u_getVersion to u_getUnicodeVersion().
jpayne@69 22 ******************************************************************************
jpayne@69 23 */
jpayne@69 24
jpayne@69 25 #ifndef UCHAR_H
jpayne@69 26 #define UCHAR_H
jpayne@69 27
jpayne@69 28 #include "unicode/utypes.h"
jpayne@69 29 #include "unicode/stringoptions.h"
jpayne@69 30 #include "unicode/ucpmap.h"
jpayne@69 31
jpayne@69 32 #if !defined(USET_DEFINED) && !defined(U_IN_DOXYGEN)
jpayne@69 33
jpayne@69 34 #define USET_DEFINED
jpayne@69 35
jpayne@69 36 /**
jpayne@69 37 * USet is the C API type corresponding to C++ class UnicodeSet.
jpayne@69 38 * It is forward-declared here to avoid including unicode/uset.h file if related
jpayne@69 39 * APIs are not used.
jpayne@69 40 *
jpayne@69 41 * @see ucnv_getUnicodeSet
jpayne@69 42 * @stable ICU 2.4
jpayne@69 43 */
jpayne@69 44 typedef struct USet USet;
jpayne@69 45
jpayne@69 46 #endif
jpayne@69 47
jpayne@69 48
jpayne@69 49 U_CDECL_BEGIN
jpayne@69 50
jpayne@69 51 /*==========================================================================*/
jpayne@69 52 /* Unicode version number */
jpayne@69 53 /*==========================================================================*/
jpayne@69 54 /**
jpayne@69 55 * Unicode version number, default for the current ICU version.
jpayne@69 56 * The actual Unicode Character Database (UCD) data is stored in uprops.dat
jpayne@69 57 * and may be generated from UCD files from a different Unicode version.
jpayne@69 58 * Call u_getUnicodeVersion to get the actual Unicode version of the data.
jpayne@69 59 *
jpayne@69 60 * @see u_getUnicodeVersion
jpayne@69 61 * @stable ICU 2.0
jpayne@69 62 */
jpayne@69 63 #define U_UNICODE_VERSION "13.0"
jpayne@69 64
jpayne@69 65 /**
jpayne@69 66 * \file
jpayne@69 67 * \brief C API: Unicode Properties
jpayne@69 68 *
jpayne@69 69 * This C API provides low-level access to the Unicode Character Database.
jpayne@69 70 * In addition to raw property values, some convenience functions calculate
jpayne@69 71 * derived properties, for example for Java-style programming.
jpayne@69 72 *
jpayne@69 73 * Unicode assigns each code point (not just assigned character) values for
jpayne@69 74 * many properties.
jpayne@69 75 * Most of them are simple boolean flags, or constants from a small enumerated list.
jpayne@69 76 * For some properties, values are strings or other relatively more complex types.
jpayne@69 77 *
jpayne@69 78 * For more information see
jpayne@69 79 * "About the Unicode Character Database" (http://www.unicode.org/ucd/)
jpayne@69 80 * and the ICU User Guide chapter on Properties (http://icu-project.org/userguide/properties.html).
jpayne@69 81 *
jpayne@69 82 * Many properties are accessible via generic functions that take a UProperty selector.
jpayne@69 83 * - u_hasBinaryProperty() returns a binary value (TRUE/FALSE) per property and code point.
jpayne@69 84 * - u_getIntPropertyValue() returns an integer value per property and code point.
jpayne@69 85 * For each supported enumerated or catalog property, there is
jpayne@69 86 * an enum type for all of the property's values, and
jpayne@69 87 * u_getIntPropertyValue() returns the numeric values of those constants.
jpayne@69 88 * - u_getBinaryPropertySet() returns a set for each ICU-supported binary property with
jpayne@69 89 * all code points for which the property is true.
jpayne@69 90 * - u_getIntPropertyMap() returns a map for each
jpayne@69 91 * ICU-supported enumerated/catalog/int-valued property which
jpayne@69 92 * maps all Unicode code points to their values for that property.
jpayne@69 93 *
jpayne@69 94 * Many functions are designed to match java.lang.Character functions.
jpayne@69 95 * See the individual function documentation,
jpayne@69 96 * and see the JDK 1.4 java.lang.Character documentation
jpayne@69 97 * at http://java.sun.com/j2se/1.4/docs/api/java/lang/Character.html
jpayne@69 98 *
jpayne@69 99 * There are also functions that provide easy migration from C/POSIX functions
jpayne@69 100 * like isblank(). Their use is generally discouraged because the C/POSIX
jpayne@69 101 * standards do not define their semantics beyond the ASCII range, which means
jpayne@69 102 * that different implementations exhibit very different behavior.
jpayne@69 103 * Instead, Unicode properties should be used directly.
jpayne@69 104 *
jpayne@69 105 * There are also only a few, broad C/POSIX character classes, and they tend
jpayne@69 106 * to be used for conflicting purposes. For example, the "isalpha()" class
jpayne@69 107 * is sometimes used to determine word boundaries, while a more sophisticated
jpayne@69 108 * approach would at least distinguish initial letters from continuation
jpayne@69 109 * characters (the latter including combining marks).
jpayne@69 110 * (In ICU, BreakIterator is the most sophisticated API for word boundaries.)
jpayne@69 111 * Another example: There is no "istitle()" class for titlecase characters.
jpayne@69 112 *
jpayne@69 113 * ICU 3.4 and later provides API access for all twelve C/POSIX character classes.
jpayne@69 114 * ICU implements them according to the Standard Recommendations in
jpayne@69 115 * Annex C: Compatibility Properties of UTS #18 Unicode Regular Expressions
jpayne@69 116 * (http://www.unicode.org/reports/tr18/#Compatibility_Properties).
jpayne@69 117 *
jpayne@69 118 * API access for C/POSIX character classes is as follows:
jpayne@69 119 * - alpha: u_isUAlphabetic(c) or u_hasBinaryProperty(c, UCHAR_ALPHABETIC)
jpayne@69 120 * - lower: u_isULowercase(c) or u_hasBinaryProperty(c, UCHAR_LOWERCASE)
jpayne@69 121 * - upper: u_isUUppercase(c) or u_hasBinaryProperty(c, UCHAR_UPPERCASE)
jpayne@69 122 * - punct: u_ispunct(c)
jpayne@69 123 * - digit: u_isdigit(c) or u_charType(c)==U_DECIMAL_DIGIT_NUMBER
jpayne@69 124 * - xdigit: u_isxdigit(c) or u_hasBinaryProperty(c, UCHAR_POSIX_XDIGIT)
jpayne@69 125 * - alnum: u_hasBinaryProperty(c, UCHAR_POSIX_ALNUM)
jpayne@69 126 * - space: u_isUWhiteSpace(c) or u_hasBinaryProperty(c, UCHAR_WHITE_SPACE)
jpayne@69 127 * - blank: u_isblank(c) or u_hasBinaryProperty(c, UCHAR_POSIX_BLANK)
jpayne@69 128 * - cntrl: u_charType(c)==U_CONTROL_CHAR
jpayne@69 129 * - graph: u_hasBinaryProperty(c, UCHAR_POSIX_GRAPH)
jpayne@69 130 * - print: u_hasBinaryProperty(c, UCHAR_POSIX_PRINT)
jpayne@69 131 *
jpayne@69 132 * Note: Some of the u_isxyz() functions in uchar.h predate, and do not match,
jpayne@69 133 * the Standard Recommendations in UTS #18. Instead, they match Java
jpayne@69 134 * functions according to their API documentation.
jpayne@69 135 *
jpayne@69 136 * \htmlonly
jpayne@69 137 * The C/POSIX character classes are also available in UnicodeSet patterns,
jpayne@69 138 * using patterns like [:graph:] or \p{graph}.
jpayne@69 139 * \endhtmlonly
jpayne@69 140 *
jpayne@69 141 * Note: There are several ICU whitespace functions.
jpayne@69 142 * Comparison:
jpayne@69 143 * - u_isUWhiteSpace=UCHAR_WHITE_SPACE: Unicode White_Space property;
jpayne@69 144 * most of general categories "Z" (separators) + most whitespace ISO controls
jpayne@69 145 * (including no-break spaces, but excluding IS1..IS4)
jpayne@69 146 * - u_isWhitespace: Java isWhitespace; Z + whitespace ISO controls but excluding no-break spaces
jpayne@69 147 * - u_isJavaSpaceChar: Java isSpaceChar; just Z (including no-break spaces)
jpayne@69 148 * - u_isspace: Z + whitespace ISO controls (including no-break spaces)
jpayne@69 149 * - u_isblank: "horizontal spaces" = TAB + Zs
jpayne@69 150 */
jpayne@69 151
jpayne@69 152 /**
jpayne@69 153 * Constants.
jpayne@69 154 */
jpayne@69 155
jpayne@69 156 /** The lowest Unicode code point value. Code points are non-negative. @stable ICU 2.0 */
jpayne@69 157 #define UCHAR_MIN_VALUE 0
jpayne@69 158
jpayne@69 159 /**
jpayne@69 160 * The highest Unicode code point value (scalar value) according to
jpayne@69 161 * The Unicode Standard. This is a 21-bit value (20.1 bits, rounded up).
jpayne@69 162 * For a single character, UChar32 is a simple type that can hold any code point value.
jpayne@69 163 *
jpayne@69 164 * @see UChar32
jpayne@69 165 * @stable ICU 2.0
jpayne@69 166 */
jpayne@69 167 #define UCHAR_MAX_VALUE 0x10ffff
jpayne@69 168
jpayne@69 169 /**
jpayne@69 170 * Get a single-bit bit set (a flag) from a bit number 0..31.
jpayne@69 171 * @stable ICU 2.1
jpayne@69 172 */
jpayne@69 173 #define U_MASK(x) ((uint32_t)1<<(x))
jpayne@69 174
jpayne@69 175 /**
jpayne@69 176 * Selection constants for Unicode properties.
jpayne@69 177 * These constants are used in functions like u_hasBinaryProperty to select
jpayne@69 178 * one of the Unicode properties.
jpayne@69 179 *
jpayne@69 180 * The properties APIs are intended to reflect Unicode properties as defined
jpayne@69 181 * in the Unicode Character Database (UCD) and Unicode Technical Reports (UTR).
jpayne@69 182 *
jpayne@69 183 * For details about the properties see
jpayne@69 184 * UAX #44: Unicode Character Database (http://www.unicode.org/reports/tr44/).
jpayne@69 185 *
jpayne@69 186 * Important: If ICU is built with UCD files from Unicode versions below, e.g., 3.2,
jpayne@69 187 * then properties marked with "new in Unicode 3.2" are not or not fully available.
jpayne@69 188 * Check u_getUnicodeVersion to be sure.
jpayne@69 189 *
jpayne@69 190 * @see u_hasBinaryProperty
jpayne@69 191 * @see u_getIntPropertyValue
jpayne@69 192 * @see u_getUnicodeVersion
jpayne@69 193 * @stable ICU 2.1
jpayne@69 194 */
jpayne@69 195 typedef enum UProperty {
jpayne@69 196 /*
jpayne@69 197 * Note: UProperty constants are parsed by preparseucd.py.
jpayne@69 198 * It matches lines like
jpayne@69 199 * UCHAR_<Unicode property name>=<integer>,
jpayne@69 200 */
jpayne@69 201
jpayne@69 202 /* Note: Place UCHAR_ALPHABETIC before UCHAR_BINARY_START so that
jpayne@69 203 debuggers display UCHAR_ALPHABETIC as the symbolic name for 0,
jpayne@69 204 rather than UCHAR_BINARY_START. Likewise for other *_START
jpayne@69 205 identifiers. */
jpayne@69 206
jpayne@69 207 /** Binary property Alphabetic. Same as u_isUAlphabetic, different from u_isalpha.
jpayne@69 208 Lu+Ll+Lt+Lm+Lo+Nl+Other_Alphabetic @stable ICU 2.1 */
jpayne@69 209 UCHAR_ALPHABETIC=0,
jpayne@69 210 /** First constant for binary Unicode properties. @stable ICU 2.1 */
jpayne@69 211 UCHAR_BINARY_START=UCHAR_ALPHABETIC,
jpayne@69 212 /** Binary property ASCII_Hex_Digit. 0-9 A-F a-f @stable ICU 2.1 */
jpayne@69 213 UCHAR_ASCII_HEX_DIGIT=1,
jpayne@69 214 /** Binary property Bidi_Control.
jpayne@69 215 Format controls which have specific functions
jpayne@69 216 in the Bidi Algorithm. @stable ICU 2.1 */
jpayne@69 217 UCHAR_BIDI_CONTROL=2,
jpayne@69 218 /** Binary property Bidi_Mirrored.
jpayne@69 219 Characters that may change display in RTL text.
jpayne@69 220 Same as u_isMirrored.
jpayne@69 221 See Bidi Algorithm, UTR 9. @stable ICU 2.1 */
jpayne@69 222 UCHAR_BIDI_MIRRORED=3,
jpayne@69 223 /** Binary property Dash. Variations of dashes. @stable ICU 2.1 */
jpayne@69 224 UCHAR_DASH=4,
jpayne@69 225 /** Binary property Default_Ignorable_Code_Point (new in Unicode 3.2).
jpayne@69 226 Ignorable in most processing.
jpayne@69 227 <2060..206F, FFF0..FFFB, E0000..E0FFF>+Other_Default_Ignorable_Code_Point+(Cf+Cc+Cs-White_Space) @stable ICU 2.1 */
jpayne@69 228 UCHAR_DEFAULT_IGNORABLE_CODE_POINT=5,
jpayne@69 229 /** Binary property Deprecated (new in Unicode 3.2).
jpayne@69 230 The usage of deprecated characters is strongly discouraged. @stable ICU 2.1 */
jpayne@69 231 UCHAR_DEPRECATED=6,
jpayne@69 232 /** Binary property Diacritic. Characters that linguistically modify
jpayne@69 233 the meaning of another character to which they apply. @stable ICU 2.1 */
jpayne@69 234 UCHAR_DIACRITIC=7,
jpayne@69 235 /** Binary property Extender.
jpayne@69 236 Extend the value or shape of a preceding alphabetic character,
jpayne@69 237 e.g., length and iteration marks. @stable ICU 2.1 */
jpayne@69 238 UCHAR_EXTENDER=8,
jpayne@69 239 /** Binary property Full_Composition_Exclusion.
jpayne@69 240 CompositionExclusions.txt+Singleton Decompositions+
jpayne@69 241 Non-Starter Decompositions. @stable ICU 2.1 */
jpayne@69 242 UCHAR_FULL_COMPOSITION_EXCLUSION=9,
jpayne@69 243 /** Binary property Grapheme_Base (new in Unicode 3.2).
jpayne@69 244 For programmatic determination of grapheme cluster boundaries.
jpayne@69 245 [0..10FFFF]-Cc-Cf-Cs-Co-Cn-Zl-Zp-Grapheme_Link-Grapheme_Extend-CGJ @stable ICU 2.1 */
jpayne@69 246 UCHAR_GRAPHEME_BASE=10,
jpayne@69 247 /** Binary property Grapheme_Extend (new in Unicode 3.2).
jpayne@69 248 For programmatic determination of grapheme cluster boundaries.
jpayne@69 249 Me+Mn+Mc+Other_Grapheme_Extend-Grapheme_Link-CGJ @stable ICU 2.1 */
jpayne@69 250 UCHAR_GRAPHEME_EXTEND=11,
jpayne@69 251 /** Binary property Grapheme_Link (new in Unicode 3.2).
jpayne@69 252 For programmatic determination of grapheme cluster boundaries. @stable ICU 2.1 */
jpayne@69 253 UCHAR_GRAPHEME_LINK=12,
jpayne@69 254 /** Binary property Hex_Digit.
jpayne@69 255 Characters commonly used for hexadecimal numbers. @stable ICU 2.1 */
jpayne@69 256 UCHAR_HEX_DIGIT=13,
jpayne@69 257 /** Binary property Hyphen. Dashes used to mark connections
jpayne@69 258 between pieces of words, plus the Katakana middle dot. @stable ICU 2.1 */
jpayne@69 259 UCHAR_HYPHEN=14,
jpayne@69 260 /** Binary property ID_Continue.
jpayne@69 261 Characters that can continue an identifier.
jpayne@69 262 DerivedCoreProperties.txt also says "NOTE: Cf characters should be filtered out."
jpayne@69 263 ID_Start+Mn+Mc+Nd+Pc @stable ICU 2.1 */
jpayne@69 264 UCHAR_ID_CONTINUE=15,
jpayne@69 265 /** Binary property ID_Start.
jpayne@69 266 Characters that can start an identifier.
jpayne@69 267 Lu+Ll+Lt+Lm+Lo+Nl @stable ICU 2.1 */
jpayne@69 268 UCHAR_ID_START=16,
jpayne@69 269 /** Binary property Ideographic.
jpayne@69 270 CJKV ideographs. @stable ICU 2.1 */
jpayne@69 271 UCHAR_IDEOGRAPHIC=17,
jpayne@69 272 /** Binary property IDS_Binary_Operator (new in Unicode 3.2).
jpayne@69 273 For programmatic determination of
jpayne@69 274 Ideographic Description Sequences. @stable ICU 2.1 */
jpayne@69 275 UCHAR_IDS_BINARY_OPERATOR=18,
jpayne@69 276 /** Binary property IDS_Trinary_Operator (new in Unicode 3.2).
jpayne@69 277 For programmatic determination of
jpayne@69 278 Ideographic Description Sequences. @stable ICU 2.1 */
jpayne@69 279 UCHAR_IDS_TRINARY_OPERATOR=19,
jpayne@69 280 /** Binary property Join_Control.
jpayne@69 281 Format controls for cursive joining and ligation. @stable ICU 2.1 */
jpayne@69 282 UCHAR_JOIN_CONTROL=20,
jpayne@69 283 /** Binary property Logical_Order_Exception (new in Unicode 3.2).
jpayne@69 284 Characters that do not use logical order and
jpayne@69 285 require special handling in most processing. @stable ICU 2.1 */
jpayne@69 286 UCHAR_LOGICAL_ORDER_EXCEPTION=21,
jpayne@69 287 /** Binary property Lowercase. Same as u_isULowercase, different from u_islower.
jpayne@69 288 Ll+Other_Lowercase @stable ICU 2.1 */
jpayne@69 289 UCHAR_LOWERCASE=22,
jpayne@69 290 /** Binary property Math. Sm+Other_Math @stable ICU 2.1 */
jpayne@69 291 UCHAR_MATH=23,
jpayne@69 292 /** Binary property Noncharacter_Code_Point.
jpayne@69 293 Code points that are explicitly defined as illegal
jpayne@69 294 for the encoding of characters. @stable ICU 2.1 */
jpayne@69 295 UCHAR_NONCHARACTER_CODE_POINT=24,
jpayne@69 296 /** Binary property Quotation_Mark. @stable ICU 2.1 */
jpayne@69 297 UCHAR_QUOTATION_MARK=25,
jpayne@69 298 /** Binary property Radical (new in Unicode 3.2).
jpayne@69 299 For programmatic determination of
jpayne@69 300 Ideographic Description Sequences. @stable ICU 2.1 */
jpayne@69 301 UCHAR_RADICAL=26,
jpayne@69 302 /** Binary property Soft_Dotted (new in Unicode 3.2).
jpayne@69 303 Characters with a "soft dot", like i or j.
jpayne@69 304 An accent placed on these characters causes
jpayne@69 305 the dot to disappear. @stable ICU 2.1 */
jpayne@69 306 UCHAR_SOFT_DOTTED=27,
jpayne@69 307 /** Binary property Terminal_Punctuation.
jpayne@69 308 Punctuation characters that generally mark
jpayne@69 309 the end of textual units. @stable ICU 2.1 */
jpayne@69 310 UCHAR_TERMINAL_PUNCTUATION=28,
jpayne@69 311 /** Binary property Unified_Ideograph (new in Unicode 3.2).
jpayne@69 312 For programmatic determination of
jpayne@69 313 Ideographic Description Sequences. @stable ICU 2.1 */
jpayne@69 314 UCHAR_UNIFIED_IDEOGRAPH=29,
jpayne@69 315 /** Binary property Uppercase. Same as u_isUUppercase, different from u_isupper.
jpayne@69 316 Lu+Other_Uppercase @stable ICU 2.1 */
jpayne@69 317 UCHAR_UPPERCASE=30,
jpayne@69 318 /** Binary property White_Space.
jpayne@69 319 Same as u_isUWhiteSpace, different from u_isspace and u_isWhitespace.
jpayne@69 320 Space characters+TAB+CR+LF-ZWSP-ZWNBSP @stable ICU 2.1 */
jpayne@69 321 UCHAR_WHITE_SPACE=31,
jpayne@69 322 /** Binary property XID_Continue.
jpayne@69 323 ID_Continue modified to allow closure under
jpayne@69 324 normalization forms NFKC and NFKD. @stable ICU 2.1 */
jpayne@69 325 UCHAR_XID_CONTINUE=32,
jpayne@69 326 /** Binary property XID_Start. ID_Start modified to allow
jpayne@69 327 closure under normalization forms NFKC and NFKD. @stable ICU 2.1 */
jpayne@69 328 UCHAR_XID_START=33,
jpayne@69 329 /** Binary property Case_Sensitive. Either the source of a case
jpayne@69 330 mapping or _in_ the target of a case mapping. Not the same as
jpayne@69 331 the general category Cased_Letter. @stable ICU 2.6 */
jpayne@69 332 UCHAR_CASE_SENSITIVE=34,
jpayne@69 333 /** Binary property STerm (new in Unicode 4.0.1).
jpayne@69 334 Sentence Terminal. Used in UAX #29: Text Boundaries
jpayne@69 335 (http://www.unicode.org/reports/tr29/)
jpayne@69 336 @stable ICU 3.0 */
jpayne@69 337 UCHAR_S_TERM=35,
jpayne@69 338 /** Binary property Variation_Selector (new in Unicode 4.0.1).
jpayne@69 339 Indicates all those characters that qualify as Variation Selectors.
jpayne@69 340 For details on the behavior of these characters,
jpayne@69 341 see StandardizedVariants.html and 15.6 Variation Selectors.
jpayne@69 342 @stable ICU 3.0 */
jpayne@69 343 UCHAR_VARIATION_SELECTOR=36,
jpayne@69 344 /** Binary property NFD_Inert.
jpayne@69 345 ICU-specific property for characters that are inert under NFD,
jpayne@69 346 i.e., they do not interact with adjacent characters.
jpayne@69 347 See the documentation for the Normalizer2 class and the
jpayne@69 348 Normalizer2::isInert() method.
jpayne@69 349 @stable ICU 3.0 */
jpayne@69 350 UCHAR_NFD_INERT=37,
jpayne@69 351 /** Binary property NFKD_Inert.
jpayne@69 352 ICU-specific property for characters that are inert under NFKD,
jpayne@69 353 i.e., they do not interact with adjacent characters.
jpayne@69 354 See the documentation for the Normalizer2 class and the
jpayne@69 355 Normalizer2::isInert() method.
jpayne@69 356 @stable ICU 3.0 */
jpayne@69 357 UCHAR_NFKD_INERT=38,
jpayne@69 358 /** Binary property NFC_Inert.
jpayne@69 359 ICU-specific property for characters that are inert under NFC,
jpayne@69 360 i.e., they do not interact with adjacent characters.
jpayne@69 361 See the documentation for the Normalizer2 class and the
jpayne@69 362 Normalizer2::isInert() method.
jpayne@69 363 @stable ICU 3.0 */
jpayne@69 364 UCHAR_NFC_INERT=39,
jpayne@69 365 /** Binary property NFKC_Inert.
jpayne@69 366 ICU-specific property for characters that are inert under NFKC,
jpayne@69 367 i.e., they do not interact with adjacent characters.
jpayne@69 368 See the documentation for the Normalizer2 class and the
jpayne@69 369 Normalizer2::isInert() method.
jpayne@69 370 @stable ICU 3.0 */
jpayne@69 371 UCHAR_NFKC_INERT=40,
jpayne@69 372 /** Binary Property Segment_Starter.
jpayne@69 373 ICU-specific property for characters that are starters in terms of
jpayne@69 374 Unicode normalization and combining character sequences.
jpayne@69 375 They have ccc=0 and do not occur in non-initial position of the
jpayne@69 376 canonical decomposition of any character
jpayne@69 377 (like a-umlaut in NFD and a Jamo T in an NFD(Hangul LVT)).
jpayne@69 378 ICU uses this property for segmenting a string for generating a set of
jpayne@69 379 canonically equivalent strings, e.g. for canonical closure while
jpayne@69 380 processing collation tailoring rules.
jpayne@69 381 @stable ICU 3.0 */
jpayne@69 382 UCHAR_SEGMENT_STARTER=41,
jpayne@69 383 /** Binary property Pattern_Syntax (new in Unicode 4.1).
jpayne@69 384 See UAX #31 Identifier and Pattern Syntax
jpayne@69 385 (http://www.unicode.org/reports/tr31/)
jpayne@69 386 @stable ICU 3.4 */
jpayne@69 387 UCHAR_PATTERN_SYNTAX=42,
jpayne@69 388 /** Binary property Pattern_White_Space (new in Unicode 4.1).
jpayne@69 389 See UAX #31 Identifier and Pattern Syntax
jpayne@69 390 (http://www.unicode.org/reports/tr31/)
jpayne@69 391 @stable ICU 3.4 */
jpayne@69 392 UCHAR_PATTERN_WHITE_SPACE=43,
jpayne@69 393 /** Binary property alnum (a C/POSIX character class).
jpayne@69 394 Implemented according to the UTS #18 Annex C Standard Recommendation.
jpayne@69 395 See the uchar.h file documentation.
jpayne@69 396 @stable ICU 3.4 */
jpayne@69 397 UCHAR_POSIX_ALNUM=44,
jpayne@69 398 /** Binary property blank (a C/POSIX character class).
jpayne@69 399 Implemented according to the UTS #18 Annex C Standard Recommendation.
jpayne@69 400 See the uchar.h file documentation.
jpayne@69 401 @stable ICU 3.4 */
jpayne@69 402 UCHAR_POSIX_BLANK=45,
jpayne@69 403 /** Binary property graph (a C/POSIX character class).
jpayne@69 404 Implemented according to the UTS #18 Annex C Standard Recommendation.
jpayne@69 405 See the uchar.h file documentation.
jpayne@69 406 @stable ICU 3.4 */
jpayne@69 407 UCHAR_POSIX_GRAPH=46,
jpayne@69 408 /** Binary property print (a C/POSIX character class).
jpayne@69 409 Implemented according to the UTS #18 Annex C Standard Recommendation.
jpayne@69 410 See the uchar.h file documentation.
jpayne@69 411 @stable ICU 3.4 */
jpayne@69 412 UCHAR_POSIX_PRINT=47,
jpayne@69 413 /** Binary property xdigit (a C/POSIX character class).
jpayne@69 414 Implemented according to the UTS #18 Annex C Standard Recommendation.
jpayne@69 415 See the uchar.h file documentation.
jpayne@69 416 @stable ICU 3.4 */
jpayne@69 417 UCHAR_POSIX_XDIGIT=48,
jpayne@69 418 /** Binary property Cased. For Lowercase, Uppercase and Titlecase characters. @stable ICU 4.4 */
jpayne@69 419 UCHAR_CASED=49,
jpayne@69 420 /** Binary property Case_Ignorable. Used in context-sensitive case mappings. @stable ICU 4.4 */
jpayne@69 421 UCHAR_CASE_IGNORABLE=50,
jpayne@69 422 /** Binary property Changes_When_Lowercased. @stable ICU 4.4 */
jpayne@69 423 UCHAR_CHANGES_WHEN_LOWERCASED=51,
jpayne@69 424 /** Binary property Changes_When_Uppercased. @stable ICU 4.4 */
jpayne@69 425 UCHAR_CHANGES_WHEN_UPPERCASED=52,
jpayne@69 426 /** Binary property Changes_When_Titlecased. @stable ICU 4.4 */
jpayne@69 427 UCHAR_CHANGES_WHEN_TITLECASED=53,
jpayne@69 428 /** Binary property Changes_When_Casefolded. @stable ICU 4.4 */
jpayne@69 429 UCHAR_CHANGES_WHEN_CASEFOLDED=54,
jpayne@69 430 /** Binary property Changes_When_Casemapped. @stable ICU 4.4 */
jpayne@69 431 UCHAR_CHANGES_WHEN_CASEMAPPED=55,
jpayne@69 432 /** Binary property Changes_When_NFKC_Casefolded. @stable ICU 4.4 */
jpayne@69 433 UCHAR_CHANGES_WHEN_NFKC_CASEFOLDED=56,
jpayne@69 434 /**
jpayne@69 435 * Binary property Emoji.
jpayne@69 436 * See http://www.unicode.org/reports/tr51/#Emoji_Properties
jpayne@69 437 *
jpayne@69 438 * @stable ICU 57
jpayne@69 439 */
jpayne@69 440 UCHAR_EMOJI=57,
jpayne@69 441 /**
jpayne@69 442 * Binary property Emoji_Presentation.
jpayne@69 443 * See http://www.unicode.org/reports/tr51/#Emoji_Properties
jpayne@69 444 *
jpayne@69 445 * @stable ICU 57
jpayne@69 446 */
jpayne@69 447 UCHAR_EMOJI_PRESENTATION=58,
jpayne@69 448 /**
jpayne@69 449 * Binary property Emoji_Modifier.
jpayne@69 450 * See http://www.unicode.org/reports/tr51/#Emoji_Properties
jpayne@69 451 *
jpayne@69 452 * @stable ICU 57
jpayne@69 453 */
jpayne@69 454 UCHAR_EMOJI_MODIFIER=59,
jpayne@69 455 /**
jpayne@69 456 * Binary property Emoji_Modifier_Base.
jpayne@69 457 * See http://www.unicode.org/reports/tr51/#Emoji_Properties
jpayne@69 458 *
jpayne@69 459 * @stable ICU 57
jpayne@69 460 */
jpayne@69 461 UCHAR_EMOJI_MODIFIER_BASE=60,
jpayne@69 462 /**
jpayne@69 463 * Binary property Emoji_Component.
jpayne@69 464 * See http://www.unicode.org/reports/tr51/#Emoji_Properties
jpayne@69 465 *
jpayne@69 466 * @stable ICU 60
jpayne@69 467 */
jpayne@69 468 UCHAR_EMOJI_COMPONENT=61,
jpayne@69 469 /**
jpayne@69 470 * Binary property Regional_Indicator.
jpayne@69 471 * @stable ICU 60
jpayne@69 472 */
jpayne@69 473 UCHAR_REGIONAL_INDICATOR=62,
jpayne@69 474 /**
jpayne@69 475 * Binary property Prepended_Concatenation_Mark.
jpayne@69 476 * @stable ICU 60
jpayne@69 477 */
jpayne@69 478 UCHAR_PREPENDED_CONCATENATION_MARK=63,
jpayne@69 479 /**
jpayne@69 480 * Binary property Extended_Pictographic.
jpayne@69 481 * See http://www.unicode.org/reports/tr51/#Emoji_Properties
jpayne@69 482 *
jpayne@69 483 * @stable ICU 62
jpayne@69 484 */
jpayne@69 485 UCHAR_EXTENDED_PICTOGRAPHIC=64,
jpayne@69 486 #ifndef U_HIDE_DEPRECATED_API
jpayne@69 487 /**
jpayne@69 488 * One more than the last constant for binary Unicode properties.
jpayne@69 489 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420.
jpayne@69 490 */
jpayne@69 491 UCHAR_BINARY_LIMIT,
jpayne@69 492 #endif // U_HIDE_DEPRECATED_API
jpayne@69 493
jpayne@69 494 /** Enumerated property Bidi_Class.
jpayne@69 495 Same as u_charDirection, returns UCharDirection values. @stable ICU 2.2 */
jpayne@69 496 UCHAR_BIDI_CLASS=0x1000,
jpayne@69 497 /** First constant for enumerated/integer Unicode properties. @stable ICU 2.2 */
jpayne@69 498 UCHAR_INT_START=UCHAR_BIDI_CLASS,
jpayne@69 499 /** Enumerated property Block.
jpayne@69 500 Same as ublock_getCode, returns UBlockCode values. @stable ICU 2.2 */
jpayne@69 501 UCHAR_BLOCK=0x1001,
jpayne@69 502 /** Enumerated property Canonical_Combining_Class.
jpayne@69 503 Same as u_getCombiningClass, returns 8-bit numeric values. @stable ICU 2.2 */
jpayne@69 504 UCHAR_CANONICAL_COMBINING_CLASS=0x1002,
jpayne@69 505 /** Enumerated property Decomposition_Type.
jpayne@69 506 Returns UDecompositionType values. @stable ICU 2.2 */
jpayne@69 507 UCHAR_DECOMPOSITION_TYPE=0x1003,
jpayne@69 508 /** Enumerated property East_Asian_Width.
jpayne@69 509 See http://www.unicode.org/reports/tr11/
jpayne@69 510 Returns UEastAsianWidth values. @stable ICU 2.2 */
jpayne@69 511 UCHAR_EAST_ASIAN_WIDTH=0x1004,
jpayne@69 512 /** Enumerated property General_Category.
jpayne@69 513 Same as u_charType, returns UCharCategory values. @stable ICU 2.2 */
jpayne@69 514 UCHAR_GENERAL_CATEGORY=0x1005,
jpayne@69 515 /** Enumerated property Joining_Group.
jpayne@69 516 Returns UJoiningGroup values. @stable ICU 2.2 */
jpayne@69 517 UCHAR_JOINING_GROUP=0x1006,
jpayne@69 518 /** Enumerated property Joining_Type.
jpayne@69 519 Returns UJoiningType values. @stable ICU 2.2 */
jpayne@69 520 UCHAR_JOINING_TYPE=0x1007,
jpayne@69 521 /** Enumerated property Line_Break.
jpayne@69 522 Returns ULineBreak values. @stable ICU 2.2 */
jpayne@69 523 UCHAR_LINE_BREAK=0x1008,
jpayne@69 524 /** Enumerated property Numeric_Type.
jpayne@69 525 Returns UNumericType values. @stable ICU 2.2 */
jpayne@69 526 UCHAR_NUMERIC_TYPE=0x1009,
jpayne@69 527 /** Enumerated property Script.
jpayne@69 528 Same as uscript_getScript, returns UScriptCode values. @stable ICU 2.2 */
jpayne@69 529 UCHAR_SCRIPT=0x100A,
jpayne@69 530 /** Enumerated property Hangul_Syllable_Type, new in Unicode 4.
jpayne@69 531 Returns UHangulSyllableType values. @stable ICU 2.6 */
jpayne@69 532 UCHAR_HANGUL_SYLLABLE_TYPE=0x100B,
jpayne@69 533 /** Enumerated property NFD_Quick_Check.
jpayne@69 534 Returns UNormalizationCheckResult values. @stable ICU 3.0 */
jpayne@69 535 UCHAR_NFD_QUICK_CHECK=0x100C,
jpayne@69 536 /** Enumerated property NFKD_Quick_Check.
jpayne@69 537 Returns UNormalizationCheckResult values. @stable ICU 3.0 */
jpayne@69 538 UCHAR_NFKD_QUICK_CHECK=0x100D,
jpayne@69 539 /** Enumerated property NFC_Quick_Check.
jpayne@69 540 Returns UNormalizationCheckResult values. @stable ICU 3.0 */
jpayne@69 541 UCHAR_NFC_QUICK_CHECK=0x100E,
jpayne@69 542 /** Enumerated property NFKC_Quick_Check.
jpayne@69 543 Returns UNormalizationCheckResult values. @stable ICU 3.0 */
jpayne@69 544 UCHAR_NFKC_QUICK_CHECK=0x100F,
jpayne@69 545 /** Enumerated property Lead_Canonical_Combining_Class.
jpayne@69 546 ICU-specific property for the ccc of the first code point
jpayne@69 547 of the decomposition, or lccc(c)=ccc(NFD(c)[0]).
jpayne@69 548 Useful for checking for canonically ordered text;
jpayne@69 549 see UNORM_FCD and http://www.unicode.org/notes/tn5/#FCD .
jpayne@69 550 Returns 8-bit numeric values like UCHAR_CANONICAL_COMBINING_CLASS. @stable ICU 3.0 */
jpayne@69 551 UCHAR_LEAD_CANONICAL_COMBINING_CLASS=0x1010,
jpayne@69 552 /** Enumerated property Trail_Canonical_Combining_Class.
jpayne@69 553 ICU-specific property for the ccc of the last code point
jpayne@69 554 of the decomposition, or tccc(c)=ccc(NFD(c)[last]).
jpayne@69 555 Useful for checking for canonically ordered text;
jpayne@69 556 see UNORM_FCD and http://www.unicode.org/notes/tn5/#FCD .
jpayne@69 557 Returns 8-bit numeric values like UCHAR_CANONICAL_COMBINING_CLASS. @stable ICU 3.0 */
jpayne@69 558 UCHAR_TRAIL_CANONICAL_COMBINING_CLASS=0x1011,
jpayne@69 559 /** Enumerated property Grapheme_Cluster_Break (new in Unicode 4.1).
jpayne@69 560 Used in UAX #29: Text Boundaries
jpayne@69 561 (http://www.unicode.org/reports/tr29/)
jpayne@69 562 Returns UGraphemeClusterBreak values. @stable ICU 3.4 */
jpayne@69 563 UCHAR_GRAPHEME_CLUSTER_BREAK=0x1012,
jpayne@69 564 /** Enumerated property Sentence_Break (new in Unicode 4.1).
jpayne@69 565 Used in UAX #29: Text Boundaries
jpayne@69 566 (http://www.unicode.org/reports/tr29/)
jpayne@69 567 Returns USentenceBreak values. @stable ICU 3.4 */
jpayne@69 568 UCHAR_SENTENCE_BREAK=0x1013,
jpayne@69 569 /** Enumerated property Word_Break (new in Unicode 4.1).
jpayne@69 570 Used in UAX #29: Text Boundaries
jpayne@69 571 (http://www.unicode.org/reports/tr29/)
jpayne@69 572 Returns UWordBreakValues values. @stable ICU 3.4 */
jpayne@69 573 UCHAR_WORD_BREAK=0x1014,
jpayne@69 574 /** Enumerated property Bidi_Paired_Bracket_Type (new in Unicode 6.3).
jpayne@69 575 Used in UAX #9: Unicode Bidirectional Algorithm
jpayne@69 576 (http://www.unicode.org/reports/tr9/)
jpayne@69 577 Returns UBidiPairedBracketType values. @stable ICU 52 */
jpayne@69 578 UCHAR_BIDI_PAIRED_BRACKET_TYPE=0x1015,
jpayne@69 579 /**
jpayne@69 580 * Enumerated property Indic_Positional_Category.
jpayne@69 581 * New in Unicode 6.0 as provisional property Indic_Matra_Category;
jpayne@69 582 * renamed and changed to informative in Unicode 8.0.
jpayne@69 583 * See http://www.unicode.org/reports/tr44/#IndicPositionalCategory.txt
jpayne@69 584 * @stable ICU 63
jpayne@69 585 */
jpayne@69 586 UCHAR_INDIC_POSITIONAL_CATEGORY=0x1016,
jpayne@69 587 /**
jpayne@69 588 * Enumerated property Indic_Syllabic_Category.
jpayne@69 589 * New in Unicode 6.0 as provisional; informative since Unicode 8.0.
jpayne@69 590 * See http://www.unicode.org/reports/tr44/#IndicSyllabicCategory.txt
jpayne@69 591 * @stable ICU 63
jpayne@69 592 */
jpayne@69 593 UCHAR_INDIC_SYLLABIC_CATEGORY=0x1017,
jpayne@69 594 /**
jpayne@69 595 * Enumerated property Vertical_Orientation.
jpayne@69 596 * Used for UAX #50 Unicode Vertical Text Layout (https://www.unicode.org/reports/tr50/).
jpayne@69 597 * New as a UCD property in Unicode 10.0.
jpayne@69 598 * @stable ICU 63
jpayne@69 599 */
jpayne@69 600 UCHAR_VERTICAL_ORIENTATION=0x1018,
jpayne@69 601 #ifndef U_HIDE_DEPRECATED_API
jpayne@69 602 /**
jpayne@69 603 * One more than the last constant for enumerated/integer Unicode properties.
jpayne@69 604 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420.
jpayne@69 605 */
jpayne@69 606 UCHAR_INT_LIMIT=0x1019,
jpayne@69 607 #endif // U_HIDE_DEPRECATED_API
jpayne@69 608
jpayne@69 609 /** Bitmask property General_Category_Mask.
jpayne@69 610 This is the General_Category property returned as a bit mask.
jpayne@69 611 When used in u_getIntPropertyValue(c), same as U_MASK(u_charType(c)),
jpayne@69 612 returns bit masks for UCharCategory values where exactly one bit is set.
jpayne@69 613 When used with u_getPropertyValueName() and u_getPropertyValueEnum(),
jpayne@69 614 a multi-bit mask is used for sets of categories like "Letters".
jpayne@69 615 Mask values should be cast to uint32_t.
jpayne@69 616 @stable ICU 2.4 */
jpayne@69 617 UCHAR_GENERAL_CATEGORY_MASK=0x2000,
jpayne@69 618 /** First constant for bit-mask Unicode properties. @stable ICU 2.4 */
jpayne@69 619 UCHAR_MASK_START=UCHAR_GENERAL_CATEGORY_MASK,
jpayne@69 620 #ifndef U_HIDE_DEPRECATED_API
jpayne@69 621 /**
jpayne@69 622 * One more than the last constant for bit-mask Unicode properties.
jpayne@69 623 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420.
jpayne@69 624 */
jpayne@69 625 UCHAR_MASK_LIMIT=0x2001,
jpayne@69 626 #endif // U_HIDE_DEPRECATED_API
jpayne@69 627
jpayne@69 628 /** Double property Numeric_Value.
jpayne@69 629 Corresponds to u_getNumericValue. @stable ICU 2.4 */
jpayne@69 630 UCHAR_NUMERIC_VALUE=0x3000,
jpayne@69 631 /** First constant for double Unicode properties. @stable ICU 2.4 */
jpayne@69 632 UCHAR_DOUBLE_START=UCHAR_NUMERIC_VALUE,
jpayne@69 633 #ifndef U_HIDE_DEPRECATED_API
jpayne@69 634 /**
jpayne@69 635 * One more than the last constant for double Unicode properties.
jpayne@69 636 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420.
jpayne@69 637 */
jpayne@69 638 UCHAR_DOUBLE_LIMIT=0x3001,
jpayne@69 639 #endif // U_HIDE_DEPRECATED_API
jpayne@69 640
jpayne@69 641 /** String property Age.
jpayne@69 642 Corresponds to u_charAge. @stable ICU 2.4 */
jpayne@69 643 UCHAR_AGE=0x4000,
jpayne@69 644 /** First constant for string Unicode properties. @stable ICU 2.4 */
jpayne@69 645 UCHAR_STRING_START=UCHAR_AGE,
jpayne@69 646 /** String property Bidi_Mirroring_Glyph.
jpayne@69 647 Corresponds to u_charMirror. @stable ICU 2.4 */
jpayne@69 648 UCHAR_BIDI_MIRRORING_GLYPH=0x4001,
jpayne@69 649 /** String property Case_Folding.
jpayne@69 650 Corresponds to u_strFoldCase in ustring.h. @stable ICU 2.4 */
jpayne@69 651 UCHAR_CASE_FOLDING=0x4002,
jpayne@69 652 #ifndef U_HIDE_DEPRECATED_API
jpayne@69 653 /** Deprecated string property ISO_Comment.
jpayne@69 654 Corresponds to u_getISOComment. @deprecated ICU 49 */
jpayne@69 655 UCHAR_ISO_COMMENT=0x4003,
jpayne@69 656 #endif /* U_HIDE_DEPRECATED_API */
jpayne@69 657 /** String property Lowercase_Mapping.
jpayne@69 658 Corresponds to u_strToLower in ustring.h. @stable ICU 2.4 */
jpayne@69 659 UCHAR_LOWERCASE_MAPPING=0x4004,
jpayne@69 660 /** String property Name.
jpayne@69 661 Corresponds to u_charName. @stable ICU 2.4 */
jpayne@69 662 UCHAR_NAME=0x4005,
jpayne@69 663 /** String property Simple_Case_Folding.
jpayne@69 664 Corresponds to u_foldCase. @stable ICU 2.4 */
jpayne@69 665 UCHAR_SIMPLE_CASE_FOLDING=0x4006,
jpayne@69 666 /** String property Simple_Lowercase_Mapping.
jpayne@69 667 Corresponds to u_tolower. @stable ICU 2.4 */
jpayne@69 668 UCHAR_SIMPLE_LOWERCASE_MAPPING=0x4007,
jpayne@69 669 /** String property Simple_Titlecase_Mapping.
jpayne@69 670 Corresponds to u_totitle. @stable ICU 2.4 */
jpayne@69 671 UCHAR_SIMPLE_TITLECASE_MAPPING=0x4008,
jpayne@69 672 /** String property Simple_Uppercase_Mapping.
jpayne@69 673 Corresponds to u_toupper. @stable ICU 2.4 */
jpayne@69 674 UCHAR_SIMPLE_UPPERCASE_MAPPING=0x4009,
jpayne@69 675 /** String property Titlecase_Mapping.
jpayne@69 676 Corresponds to u_strToTitle in ustring.h. @stable ICU 2.4 */
jpayne@69 677 UCHAR_TITLECASE_MAPPING=0x400A,
jpayne@69 678 #ifndef U_HIDE_DEPRECATED_API
jpayne@69 679 /** String property Unicode_1_Name.
jpayne@69 680 This property is of little practical value.
jpayne@69 681 Beginning with ICU 49, ICU APIs return an empty string for this property.
jpayne@69 682 Corresponds to u_charName(U_UNICODE_10_CHAR_NAME). @deprecated ICU 49 */
jpayne@69 683 UCHAR_UNICODE_1_NAME=0x400B,
jpayne@69 684 #endif /* U_HIDE_DEPRECATED_API */
jpayne@69 685 /** String property Uppercase_Mapping.
jpayne@69 686 Corresponds to u_strToUpper in ustring.h. @stable ICU 2.4 */
jpayne@69 687 UCHAR_UPPERCASE_MAPPING=0x400C,
jpayne@69 688 /** String property Bidi_Paired_Bracket (new in Unicode 6.3).
jpayne@69 689 Corresponds to u_getBidiPairedBracket. @stable ICU 52 */
jpayne@69 690 UCHAR_BIDI_PAIRED_BRACKET=0x400D,
jpayne@69 691 #ifndef U_HIDE_DEPRECATED_API
jpayne@69 692 /**
jpayne@69 693 * One more than the last constant for string Unicode properties.
jpayne@69 694 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420.
jpayne@69 695 */
jpayne@69 696 UCHAR_STRING_LIMIT=0x400E,
jpayne@69 697 #endif // U_HIDE_DEPRECATED_API
jpayne@69 698
jpayne@69 699 /** Miscellaneous property Script_Extensions (new in Unicode 6.0).
jpayne@69 700 Some characters are commonly used in multiple scripts.
jpayne@69 701 For more information, see UAX #24: http://www.unicode.org/reports/tr24/.
jpayne@69 702 Corresponds to uscript_hasScript and uscript_getScriptExtensions in uscript.h.
jpayne@69 703 @stable ICU 4.6 */
jpayne@69 704 UCHAR_SCRIPT_EXTENSIONS=0x7000,
jpayne@69 705 /** First constant for Unicode properties with unusual value types. @stable ICU 4.6 */
jpayne@69 706 UCHAR_OTHER_PROPERTY_START=UCHAR_SCRIPT_EXTENSIONS,
jpayne@69 707 #ifndef U_HIDE_DEPRECATED_API
jpayne@69 708 /**
jpayne@69 709 * One more than the last constant for Unicode properties with unusual value types.
jpayne@69 710 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420.
jpayne@69 711 */
jpayne@69 712 UCHAR_OTHER_PROPERTY_LIMIT=0x7001,
jpayne@69 713 #endif // U_HIDE_DEPRECATED_API
jpayne@69 714
jpayne@69 715 /** Represents a nonexistent or invalid property or property value. @stable ICU 2.4 */
jpayne@69 716 UCHAR_INVALID_CODE = -1
jpayne@69 717 } UProperty;
jpayne@69 718
jpayne@69 719 /**
jpayne@69 720 * Data for enumerated Unicode general category types.
jpayne@69 721 * See http://www.unicode.org/Public/UNIDATA/UnicodeData.html .
jpayne@69 722 * @stable ICU 2.0
jpayne@69 723 */
jpayne@69 724 typedef enum UCharCategory
jpayne@69 725 {
jpayne@69 726 /*
jpayne@69 727 * Note: UCharCategory constants and their API comments are parsed by preparseucd.py.
jpayne@69 728 * It matches pairs of lines like
jpayne@69 729 * / ** <Unicode 2-letter General_Category value> comment... * /
jpayne@69 730 * U_<[A-Z_]+> = <integer>,
jpayne@69 731 */
jpayne@69 732
jpayne@69 733 /** Non-category for unassigned and non-character code points. @stable ICU 2.0 */
jpayne@69 734 U_UNASSIGNED = 0,
jpayne@69 735 /** Cn "Other, Not Assigned (no characters in [UnicodeData.txt] have this property)" (same as U_UNASSIGNED!) @stable ICU 2.0 */
jpayne@69 736 U_GENERAL_OTHER_TYPES = 0,
jpayne@69 737 /** Lu @stable ICU 2.0 */
jpayne@69 738 U_UPPERCASE_LETTER = 1,
jpayne@69 739 /** Ll @stable ICU 2.0 */
jpayne@69 740 U_LOWERCASE_LETTER = 2,
jpayne@69 741 /** Lt @stable ICU 2.0 */
jpayne@69 742 U_TITLECASE_LETTER = 3,
jpayne@69 743 /** Lm @stable ICU 2.0 */
jpayne@69 744 U_MODIFIER_LETTER = 4,
jpayne@69 745 /** Lo @stable ICU 2.0 */
jpayne@69 746 U_OTHER_LETTER = 5,
jpayne@69 747 /** Mn @stable ICU 2.0 */
jpayne@69 748 U_NON_SPACING_MARK = 6,
jpayne@69 749 /** Me @stable ICU 2.0 */
jpayne@69 750 U_ENCLOSING_MARK = 7,
jpayne@69 751 /** Mc @stable ICU 2.0 */
jpayne@69 752 U_COMBINING_SPACING_MARK = 8,
jpayne@69 753 /** Nd @stable ICU 2.0 */
jpayne@69 754 U_DECIMAL_DIGIT_NUMBER = 9,
jpayne@69 755 /** Nl @stable ICU 2.0 */
jpayne@69 756 U_LETTER_NUMBER = 10,
jpayne@69 757 /** No @stable ICU 2.0 */
jpayne@69 758 U_OTHER_NUMBER = 11,
jpayne@69 759 /** Zs @stable ICU 2.0 */
jpayne@69 760 U_SPACE_SEPARATOR = 12,
jpayne@69 761 /** Zl @stable ICU 2.0 */
jpayne@69 762 U_LINE_SEPARATOR = 13,
jpayne@69 763 /** Zp @stable ICU 2.0 */
jpayne@69 764 U_PARAGRAPH_SEPARATOR = 14,
jpayne@69 765 /** Cc @stable ICU 2.0 */
jpayne@69 766 U_CONTROL_CHAR = 15,
jpayne@69 767 /** Cf @stable ICU 2.0 */
jpayne@69 768 U_FORMAT_CHAR = 16,
jpayne@69 769 /** Co @stable ICU 2.0 */
jpayne@69 770 U_PRIVATE_USE_CHAR = 17,
jpayne@69 771 /** Cs @stable ICU 2.0 */
jpayne@69 772 U_SURROGATE = 18,
jpayne@69 773 /** Pd @stable ICU 2.0 */
jpayne@69 774 U_DASH_PUNCTUATION = 19,
jpayne@69 775 /** Ps @stable ICU 2.0 */
jpayne@69 776 U_START_PUNCTUATION = 20,
jpayne@69 777 /** Pe @stable ICU 2.0 */
jpayne@69 778 U_END_PUNCTUATION = 21,
jpayne@69 779 /** Pc @stable ICU 2.0 */
jpayne@69 780 U_CONNECTOR_PUNCTUATION = 22,
jpayne@69 781 /** Po @stable ICU 2.0 */
jpayne@69 782 U_OTHER_PUNCTUATION = 23,
jpayne@69 783 /** Sm @stable ICU 2.0 */
jpayne@69 784 U_MATH_SYMBOL = 24,
jpayne@69 785 /** Sc @stable ICU 2.0 */
jpayne@69 786 U_CURRENCY_SYMBOL = 25,
jpayne@69 787 /** Sk @stable ICU 2.0 */
jpayne@69 788 U_MODIFIER_SYMBOL = 26,
jpayne@69 789 /** So @stable ICU 2.0 */
jpayne@69 790 U_OTHER_SYMBOL = 27,
jpayne@69 791 /** Pi @stable ICU 2.0 */
jpayne@69 792 U_INITIAL_PUNCTUATION = 28,
jpayne@69 793 /** Pf @stable ICU 2.0 */
jpayne@69 794 U_FINAL_PUNCTUATION = 29,
jpayne@69 795 /**
jpayne@69 796 * One higher than the last enum UCharCategory constant.
jpayne@69 797 * This numeric value is stable (will not change), see
jpayne@69 798 * http://www.unicode.org/policies/stability_policy.html#Property_Value
jpayne@69 799 *
jpayne@69 800 * @stable ICU 2.0
jpayne@69 801 */
jpayne@69 802 U_CHAR_CATEGORY_COUNT
jpayne@69 803 } UCharCategory;
jpayne@69 804
jpayne@69 805 /**
jpayne@69 806 * U_GC_XX_MASK constants are bit flags corresponding to Unicode
jpayne@69 807 * general category values.
jpayne@69 808 * For each category, the nth bit is set if the numeric value of the
jpayne@69 809 * corresponding UCharCategory constant is n.
jpayne@69 810 *
jpayne@69 811 * There are also some U_GC_Y_MASK constants for groups of general categories
jpayne@69 812 * like L for all letter categories.
jpayne@69 813 *
jpayne@69 814 * @see u_charType
jpayne@69 815 * @see U_GET_GC_MASK
jpayne@69 816 * @see UCharCategory
jpayne@69 817 * @stable ICU 2.1
jpayne@69 818 */
jpayne@69 819 #define U_GC_CN_MASK U_MASK(U_GENERAL_OTHER_TYPES)
jpayne@69 820
jpayne@69 821 /** Mask constant for a UCharCategory. @stable ICU 2.1 */
jpayne@69 822 #define U_GC_LU_MASK U_MASK(U_UPPERCASE_LETTER)
jpayne@69 823 /** Mask constant for a UCharCategory. @stable ICU 2.1 */
jpayne@69 824 #define U_GC_LL_MASK U_MASK(U_LOWERCASE_LETTER)
jpayne@69 825 /** Mask constant for a UCharCategory. @stable ICU 2.1 */
jpayne@69 826 #define U_GC_LT_MASK U_MASK(U_TITLECASE_LETTER)
jpayne@69 827 /** Mask constant for a UCharCategory. @stable ICU 2.1 */
jpayne@69 828 #define U_GC_LM_MASK U_MASK(U_MODIFIER_LETTER)
jpayne@69 829 /** Mask constant for a UCharCategory. @stable ICU 2.1 */
jpayne@69 830 #define U_GC_LO_MASK U_MASK(U_OTHER_LETTER)
jpayne@69 831
jpayne@69 832 /** Mask constant for a UCharCategory. @stable ICU 2.1 */
jpayne@69 833 #define U_GC_MN_MASK U_MASK(U_NON_SPACING_MARK)
jpayne@69 834 /** Mask constant for a UCharCategory. @stable ICU 2.1 */
jpayne@69 835 #define U_GC_ME_MASK U_MASK(U_ENCLOSING_MARK)
jpayne@69 836 /** Mask constant for a UCharCategory. @stable ICU 2.1 */
jpayne@69 837 #define U_GC_MC_MASK U_MASK(U_COMBINING_SPACING_MARK)
jpayne@69 838
jpayne@69 839 /** Mask constant for a UCharCategory. @stable ICU 2.1 */
jpayne@69 840 #define U_GC_ND_MASK U_MASK(U_DECIMAL_DIGIT_NUMBER)
jpayne@69 841 /** Mask constant for a UCharCategory. @stable ICU 2.1 */
jpayne@69 842 #define U_GC_NL_MASK U_MASK(U_LETTER_NUMBER)
jpayne@69 843 /** Mask constant for a UCharCategory. @stable ICU 2.1 */
jpayne@69 844 #define U_GC_NO_MASK U_MASK(U_OTHER_NUMBER)
jpayne@69 845
jpayne@69 846 /** Mask constant for a UCharCategory. @stable ICU 2.1 */
jpayne@69 847 #define U_GC_ZS_MASK U_MASK(U_SPACE_SEPARATOR)
jpayne@69 848 /** Mask constant for a UCharCategory. @stable ICU 2.1 */
jpayne@69 849 #define U_GC_ZL_MASK U_MASK(U_LINE_SEPARATOR)
jpayne@69 850 /** Mask constant for a UCharCategory. @stable ICU 2.1 */
jpayne@69 851 #define U_GC_ZP_MASK U_MASK(U_PARAGRAPH_SEPARATOR)
jpayne@69 852
jpayne@69 853 /** Mask constant for a UCharCategory. @stable ICU 2.1 */
jpayne@69 854 #define U_GC_CC_MASK U_MASK(U_CONTROL_CHAR)
jpayne@69 855 /** Mask constant for a UCharCategory. @stable ICU 2.1 */
jpayne@69 856 #define U_GC_CF_MASK U_MASK(U_FORMAT_CHAR)
jpayne@69 857 /** Mask constant for a UCharCategory. @stable ICU 2.1 */
jpayne@69 858 #define U_GC_CO_MASK U_MASK(U_PRIVATE_USE_CHAR)
jpayne@69 859 /** Mask constant for a UCharCategory. @stable ICU 2.1 */
jpayne@69 860 #define U_GC_CS_MASK U_MASK(U_SURROGATE)
jpayne@69 861
jpayne@69 862 /** Mask constant for a UCharCategory. @stable ICU 2.1 */
jpayne@69 863 #define U_GC_PD_MASK U_MASK(U_DASH_PUNCTUATION)
jpayne@69 864 /** Mask constant for a UCharCategory. @stable ICU 2.1 */
jpayne@69 865 #define U_GC_PS_MASK U_MASK(U_START_PUNCTUATION)
jpayne@69 866 /** Mask constant for a UCharCategory. @stable ICU 2.1 */
jpayne@69 867 #define U_GC_PE_MASK U_MASK(U_END_PUNCTUATION)
jpayne@69 868 /** Mask constant for a UCharCategory. @stable ICU 2.1 */
jpayne@69 869 #define U_GC_PC_MASK U_MASK(U_CONNECTOR_PUNCTUATION)
jpayne@69 870 /** Mask constant for a UCharCategory. @stable ICU 2.1 */
jpayne@69 871 #define U_GC_PO_MASK U_MASK(U_OTHER_PUNCTUATION)
jpayne@69 872
jpayne@69 873 /** Mask constant for a UCharCategory. @stable ICU 2.1 */
jpayne@69 874 #define U_GC_SM_MASK U_MASK(U_MATH_SYMBOL)
jpayne@69 875 /** Mask constant for a UCharCategory. @stable ICU 2.1 */
jpayne@69 876 #define U_GC_SC_MASK U_MASK(U_CURRENCY_SYMBOL)
jpayne@69 877 /** Mask constant for a UCharCategory. @stable ICU 2.1 */
jpayne@69 878 #define U_GC_SK_MASK U_MASK(U_MODIFIER_SYMBOL)
jpayne@69 879 /** Mask constant for a UCharCategory. @stable ICU 2.1 */
jpayne@69 880 #define U_GC_SO_MASK U_MASK(U_OTHER_SYMBOL)
jpayne@69 881
jpayne@69 882 /** Mask constant for a UCharCategory. @stable ICU 2.1 */
jpayne@69 883 #define U_GC_PI_MASK U_MASK(U_INITIAL_PUNCTUATION)
jpayne@69 884 /** Mask constant for a UCharCategory. @stable ICU 2.1 */
jpayne@69 885 #define U_GC_PF_MASK U_MASK(U_FINAL_PUNCTUATION)
jpayne@69 886
jpayne@69 887
jpayne@69 888 /** Mask constant for multiple UCharCategory bits (L Letters). @stable ICU 2.1 */
jpayne@69 889 #define U_GC_L_MASK \
jpayne@69 890 (U_GC_LU_MASK|U_GC_LL_MASK|U_GC_LT_MASK|U_GC_LM_MASK|U_GC_LO_MASK)
jpayne@69 891
jpayne@69 892 /** Mask constant for multiple UCharCategory bits (LC Cased Letters). @stable ICU 2.1 */
jpayne@69 893 #define U_GC_LC_MASK \
jpayne@69 894 (U_GC_LU_MASK|U_GC_LL_MASK|U_GC_LT_MASK)
jpayne@69 895
jpayne@69 896 /** Mask constant for multiple UCharCategory bits (M Marks). @stable ICU 2.1 */
jpayne@69 897 #define U_GC_M_MASK (U_GC_MN_MASK|U_GC_ME_MASK|U_GC_MC_MASK)
jpayne@69 898
jpayne@69 899 /** Mask constant for multiple UCharCategory bits (N Numbers). @stable ICU 2.1 */
jpayne@69 900 #define U_GC_N_MASK (U_GC_ND_MASK|U_GC_NL_MASK|U_GC_NO_MASK)
jpayne@69 901
jpayne@69 902 /** Mask constant for multiple UCharCategory bits (Z Separators). @stable ICU 2.1 */
jpayne@69 903 #define U_GC_Z_MASK (U_GC_ZS_MASK|U_GC_ZL_MASK|U_GC_ZP_MASK)
jpayne@69 904
jpayne@69 905 /** Mask constant for multiple UCharCategory bits (C Others). @stable ICU 2.1 */
jpayne@69 906 #define U_GC_C_MASK \
jpayne@69 907 (U_GC_CN_MASK|U_GC_CC_MASK|U_GC_CF_MASK|U_GC_CO_MASK|U_GC_CS_MASK)
jpayne@69 908
jpayne@69 909 /** Mask constant for multiple UCharCategory bits (P Punctuation). @stable ICU 2.1 */
jpayne@69 910 #define U_GC_P_MASK \
jpayne@69 911 (U_GC_PD_MASK|U_GC_PS_MASK|U_GC_PE_MASK|U_GC_PC_MASK|U_GC_PO_MASK| \
jpayne@69 912 U_GC_PI_MASK|U_GC_PF_MASK)
jpayne@69 913
jpayne@69 914 /** Mask constant for multiple UCharCategory bits (S Symbols). @stable ICU 2.1 */
jpayne@69 915 #define U_GC_S_MASK (U_GC_SM_MASK|U_GC_SC_MASK|U_GC_SK_MASK|U_GC_SO_MASK)
jpayne@69 916
jpayne@69 917 /**
jpayne@69 918 * This specifies the language directional property of a character set.
jpayne@69 919 * @stable ICU 2.0
jpayne@69 920 */
jpayne@69 921 typedef enum UCharDirection {
jpayne@69 922 /*
jpayne@69 923 * Note: UCharDirection constants and their API comments are parsed by preparseucd.py.
jpayne@69 924 * It matches pairs of lines like
jpayne@69 925 * / ** <Unicode 1..3-letter Bidi_Class value> comment... * /
jpayne@69 926 * U_<[A-Z_]+> = <integer>,
jpayne@69 927 */
jpayne@69 928
jpayne@69 929 /** L @stable ICU 2.0 */
jpayne@69 930 U_LEFT_TO_RIGHT = 0,
jpayne@69 931 /** R @stable ICU 2.0 */
jpayne@69 932 U_RIGHT_TO_LEFT = 1,
jpayne@69 933 /** EN @stable ICU 2.0 */
jpayne@69 934 U_EUROPEAN_NUMBER = 2,
jpayne@69 935 /** ES @stable ICU 2.0 */
jpayne@69 936 U_EUROPEAN_NUMBER_SEPARATOR = 3,
jpayne@69 937 /** ET @stable ICU 2.0 */
jpayne@69 938 U_EUROPEAN_NUMBER_TERMINATOR = 4,
jpayne@69 939 /** AN @stable ICU 2.0 */
jpayne@69 940 U_ARABIC_NUMBER = 5,
jpayne@69 941 /** CS @stable ICU 2.0 */
jpayne@69 942 U_COMMON_NUMBER_SEPARATOR = 6,
jpayne@69 943 /** B @stable ICU 2.0 */
jpayne@69 944 U_BLOCK_SEPARATOR = 7,
jpayne@69 945 /** S @stable ICU 2.0 */
jpayne@69 946 U_SEGMENT_SEPARATOR = 8,
jpayne@69 947 /** WS @stable ICU 2.0 */
jpayne@69 948 U_WHITE_SPACE_NEUTRAL = 9,
jpayne@69 949 /** ON @stable ICU 2.0 */
jpayne@69 950 U_OTHER_NEUTRAL = 10,
jpayne@69 951 /** LRE @stable ICU 2.0 */
jpayne@69 952 U_LEFT_TO_RIGHT_EMBEDDING = 11,
jpayne@69 953 /** LRO @stable ICU 2.0 */
jpayne@69 954 U_LEFT_TO_RIGHT_OVERRIDE = 12,
jpayne@69 955 /** AL @stable ICU 2.0 */
jpayne@69 956 U_RIGHT_TO_LEFT_ARABIC = 13,
jpayne@69 957 /** RLE @stable ICU 2.0 */
jpayne@69 958 U_RIGHT_TO_LEFT_EMBEDDING = 14,
jpayne@69 959 /** RLO @stable ICU 2.0 */
jpayne@69 960 U_RIGHT_TO_LEFT_OVERRIDE = 15,
jpayne@69 961 /** PDF @stable ICU 2.0 */
jpayne@69 962 U_POP_DIRECTIONAL_FORMAT = 16,
jpayne@69 963 /** NSM @stable ICU 2.0 */
jpayne@69 964 U_DIR_NON_SPACING_MARK = 17,
jpayne@69 965 /** BN @stable ICU 2.0 */
jpayne@69 966 U_BOUNDARY_NEUTRAL = 18,
jpayne@69 967 /** FSI @stable ICU 52 */
jpayne@69 968 U_FIRST_STRONG_ISOLATE = 19,
jpayne@69 969 /** LRI @stable ICU 52 */
jpayne@69 970 U_LEFT_TO_RIGHT_ISOLATE = 20,
jpayne@69 971 /** RLI @stable ICU 52 */
jpayne@69 972 U_RIGHT_TO_LEFT_ISOLATE = 21,
jpayne@69 973 /** PDI @stable ICU 52 */
jpayne@69 974 U_POP_DIRECTIONAL_ISOLATE = 22,
jpayne@69 975 #ifndef U_HIDE_DEPRECATED_API
jpayne@69 976 /**
jpayne@69 977 * One more than the highest UCharDirection value.
jpayne@69 978 * The highest value is available via u_getIntPropertyMaxValue(UCHAR_BIDI_CLASS).
jpayne@69 979 *
jpayne@69 980 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420.
jpayne@69 981 */
jpayne@69 982 U_CHAR_DIRECTION_COUNT
jpayne@69 983 #endif // U_HIDE_DEPRECATED_API
jpayne@69 984 } UCharDirection;
jpayne@69 985
jpayne@69 986 /**
jpayne@69 987 * Bidi Paired Bracket Type constants.
jpayne@69 988 *
jpayne@69 989 * @see UCHAR_BIDI_PAIRED_BRACKET_TYPE
jpayne@69 990 * @stable ICU 52
jpayne@69 991 */
jpayne@69 992 typedef enum UBidiPairedBracketType {
jpayne@69 993 /*
jpayne@69 994 * Note: UBidiPairedBracketType constants are parsed by preparseucd.py.
jpayne@69 995 * It matches lines like
jpayne@69 996 * U_BPT_<Unicode Bidi_Paired_Bracket_Type value name>
jpayne@69 997 */
jpayne@69 998
jpayne@69 999 /** Not a paired bracket. @stable ICU 52 */
jpayne@69 1000 U_BPT_NONE,
jpayne@69 1001 /** Open paired bracket. @stable ICU 52 */
jpayne@69 1002 U_BPT_OPEN,
jpayne@69 1003 /** Close paired bracket. @stable ICU 52 */
jpayne@69 1004 U_BPT_CLOSE,
jpayne@69 1005 #ifndef U_HIDE_DEPRECATED_API
jpayne@69 1006 /**
jpayne@69 1007 * One more than the highest normal UBidiPairedBracketType value.
jpayne@69 1008 * The highest value is available via u_getIntPropertyMaxValue(UCHAR_BIDI_PAIRED_BRACKET_TYPE).
jpayne@69 1009 *
jpayne@69 1010 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420.
jpayne@69 1011 */
jpayne@69 1012 U_BPT_COUNT /* 3 */
jpayne@69 1013 #endif // U_HIDE_DEPRECATED_API
jpayne@69 1014 } UBidiPairedBracketType;
jpayne@69 1015
jpayne@69 1016 /**
jpayne@69 1017 * Constants for Unicode blocks, see the Unicode Data file Blocks.txt
jpayne@69 1018 * @stable ICU 2.0
jpayne@69 1019 */
jpayne@69 1020 enum UBlockCode {
jpayne@69 1021 /*
jpayne@69 1022 * Note: UBlockCode constants are parsed by preparseucd.py.
jpayne@69 1023 * It matches lines like
jpayne@69 1024 * UBLOCK_<Unicode Block value name> = <integer>,
jpayne@69 1025 */
jpayne@69 1026
jpayne@69 1027 /** New No_Block value in Unicode 4. @stable ICU 2.6 */
jpayne@69 1028 UBLOCK_NO_BLOCK = 0, /*[none]*/ /* Special range indicating No_Block */
jpayne@69 1029
jpayne@69 1030 /** @stable ICU 2.0 */
jpayne@69 1031 UBLOCK_BASIC_LATIN = 1, /*[0000]*/
jpayne@69 1032
jpayne@69 1033 /** @stable ICU 2.0 */
jpayne@69 1034 UBLOCK_LATIN_1_SUPPLEMENT=2, /*[0080]*/
jpayne@69 1035
jpayne@69 1036 /** @stable ICU 2.0 */
jpayne@69 1037 UBLOCK_LATIN_EXTENDED_A =3, /*[0100]*/
jpayne@69 1038
jpayne@69 1039 /** @stable ICU 2.0 */
jpayne@69 1040 UBLOCK_LATIN_EXTENDED_B =4, /*[0180]*/
jpayne@69 1041
jpayne@69 1042 /** @stable ICU 2.0 */
jpayne@69 1043 UBLOCK_IPA_EXTENSIONS =5, /*[0250]*/
jpayne@69 1044
jpayne@69 1045 /** @stable ICU 2.0 */
jpayne@69 1046 UBLOCK_SPACING_MODIFIER_LETTERS =6, /*[02B0]*/
jpayne@69 1047
jpayne@69 1048 /** @stable ICU 2.0 */
jpayne@69 1049 UBLOCK_COMBINING_DIACRITICAL_MARKS =7, /*[0300]*/
jpayne@69 1050
jpayne@69 1051 /**
jpayne@69 1052 * Unicode 3.2 renames this block to "Greek and Coptic".
jpayne@69 1053 * @stable ICU 2.0
jpayne@69 1054 */
jpayne@69 1055 UBLOCK_GREEK =8, /*[0370]*/
jpayne@69 1056
jpayne@69 1057 /** @stable ICU 2.0 */
jpayne@69 1058 UBLOCK_CYRILLIC =9, /*[0400]*/
jpayne@69 1059
jpayne@69 1060 /** @stable ICU 2.0 */
jpayne@69 1061 UBLOCK_ARMENIAN =10, /*[0530]*/
jpayne@69 1062
jpayne@69 1063 /** @stable ICU 2.0 */
jpayne@69 1064 UBLOCK_HEBREW =11, /*[0590]*/
jpayne@69 1065
jpayne@69 1066 /** @stable ICU 2.0 */
jpayne@69 1067 UBLOCK_ARABIC =12, /*[0600]*/
jpayne@69 1068
jpayne@69 1069 /** @stable ICU 2.0 */
jpayne@69 1070 UBLOCK_SYRIAC =13, /*[0700]*/
jpayne@69 1071
jpayne@69 1072 /** @stable ICU 2.0 */
jpayne@69 1073 UBLOCK_THAANA =14, /*[0780]*/
jpayne@69 1074
jpayne@69 1075 /** @stable ICU 2.0 */
jpayne@69 1076 UBLOCK_DEVANAGARI =15, /*[0900]*/
jpayne@69 1077
jpayne@69 1078 /** @stable ICU 2.0 */
jpayne@69 1079 UBLOCK_BENGALI =16, /*[0980]*/
jpayne@69 1080
jpayne@69 1081 /** @stable ICU 2.0 */
jpayne@69 1082 UBLOCK_GURMUKHI =17, /*[0A00]*/
jpayne@69 1083
jpayne@69 1084 /** @stable ICU 2.0 */
jpayne@69 1085 UBLOCK_GUJARATI =18, /*[0A80]*/
jpayne@69 1086
jpayne@69 1087 /** @stable ICU 2.0 */
jpayne@69 1088 UBLOCK_ORIYA =19, /*[0B00]*/
jpayne@69 1089
jpayne@69 1090 /** @stable ICU 2.0 */
jpayne@69 1091 UBLOCK_TAMIL =20, /*[0B80]*/
jpayne@69 1092
jpayne@69 1093 /** @stable ICU 2.0 */
jpayne@69 1094 UBLOCK_TELUGU =21, /*[0C00]*/
jpayne@69 1095
jpayne@69 1096 /** @stable ICU 2.0 */
jpayne@69 1097 UBLOCK_KANNADA =22, /*[0C80]*/
jpayne@69 1098
jpayne@69 1099 /** @stable ICU 2.0 */
jpayne@69 1100 UBLOCK_MALAYALAM =23, /*[0D00]*/
jpayne@69 1101
jpayne@69 1102 /** @stable ICU 2.0 */
jpayne@69 1103 UBLOCK_SINHALA =24, /*[0D80]*/
jpayne@69 1104
jpayne@69 1105 /** @stable ICU 2.0 */
jpayne@69 1106 UBLOCK_THAI =25, /*[0E00]*/
jpayne@69 1107
jpayne@69 1108 /** @stable ICU 2.0 */
jpayne@69 1109 UBLOCK_LAO =26, /*[0E80]*/
jpayne@69 1110
jpayne@69 1111 /** @stable ICU 2.0 */
jpayne@69 1112 UBLOCK_TIBETAN =27, /*[0F00]*/
jpayne@69 1113
jpayne@69 1114 /** @stable ICU 2.0 */
jpayne@69 1115 UBLOCK_MYANMAR =28, /*[1000]*/
jpayne@69 1116
jpayne@69 1117 /** @stable ICU 2.0 */
jpayne@69 1118 UBLOCK_GEORGIAN =29, /*[10A0]*/
jpayne@69 1119
jpayne@69 1120 /** @stable ICU 2.0 */
jpayne@69 1121 UBLOCK_HANGUL_JAMO =30, /*[1100]*/
jpayne@69 1122
jpayne@69 1123 /** @stable ICU 2.0 */
jpayne@69 1124 UBLOCK_ETHIOPIC =31, /*[1200]*/
jpayne@69 1125
jpayne@69 1126 /** @stable ICU 2.0 */
jpayne@69 1127 UBLOCK_CHEROKEE =32, /*[13A0]*/
jpayne@69 1128
jpayne@69 1129 /** @stable ICU 2.0 */
jpayne@69 1130 UBLOCK_UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS =33, /*[1400]*/
jpayne@69 1131
jpayne@69 1132 /** @stable ICU 2.0 */
jpayne@69 1133 UBLOCK_OGHAM =34, /*[1680]*/
jpayne@69 1134
jpayne@69 1135 /** @stable ICU 2.0 */
jpayne@69 1136 UBLOCK_RUNIC =35, /*[16A0]*/
jpayne@69 1137
jpayne@69 1138 /** @stable ICU 2.0 */
jpayne@69 1139 UBLOCK_KHMER =36, /*[1780]*/
jpayne@69 1140
jpayne@69 1141 /** @stable ICU 2.0 */
jpayne@69 1142 UBLOCK_MONGOLIAN =37, /*[1800]*/
jpayne@69 1143
jpayne@69 1144 /** @stable ICU 2.0 */
jpayne@69 1145 UBLOCK_LATIN_EXTENDED_ADDITIONAL =38, /*[1E00]*/
jpayne@69 1146
jpayne@69 1147 /** @stable ICU 2.0 */
jpayne@69 1148 UBLOCK_GREEK_EXTENDED =39, /*[1F00]*/
jpayne@69 1149
jpayne@69 1150 /** @stable ICU 2.0 */
jpayne@69 1151 UBLOCK_GENERAL_PUNCTUATION =40, /*[2000]*/
jpayne@69 1152
jpayne@69 1153 /** @stable ICU 2.0 */
jpayne@69 1154 UBLOCK_SUPERSCRIPTS_AND_SUBSCRIPTS =41, /*[2070]*/
jpayne@69 1155
jpayne@69 1156 /** @stable ICU 2.0 */
jpayne@69 1157 UBLOCK_CURRENCY_SYMBOLS =42, /*[20A0]*/
jpayne@69 1158
jpayne@69 1159 /**
jpayne@69 1160 * Unicode 3.2 renames this block to "Combining Diacritical Marks for Symbols".
jpayne@69 1161 * @stable ICU 2.0
jpayne@69 1162 */
jpayne@69 1163 UBLOCK_COMBINING_MARKS_FOR_SYMBOLS =43, /*[20D0]*/
jpayne@69 1164
jpayne@69 1165 /** @stable ICU 2.0 */
jpayne@69 1166 UBLOCK_LETTERLIKE_SYMBOLS =44, /*[2100]*/
jpayne@69 1167
jpayne@69 1168 /** @stable ICU 2.0 */
jpayne@69 1169 UBLOCK_NUMBER_FORMS =45, /*[2150]*/
jpayne@69 1170
jpayne@69 1171 /** @stable ICU 2.0 */
jpayne@69 1172 UBLOCK_ARROWS =46, /*[2190]*/
jpayne@69 1173
jpayne@69 1174 /** @stable ICU 2.0 */
jpayne@69 1175 UBLOCK_MATHEMATICAL_OPERATORS =47, /*[2200]*/
jpayne@69 1176
jpayne@69 1177 /** @stable ICU 2.0 */
jpayne@69 1178 UBLOCK_MISCELLANEOUS_TECHNICAL =48, /*[2300]*/
jpayne@69 1179
jpayne@69 1180 /** @stable ICU 2.0 */
jpayne@69 1181 UBLOCK_CONTROL_PICTURES =49, /*[2400]*/
jpayne@69 1182
jpayne@69 1183 /** @stable ICU 2.0 */
jpayne@69 1184 UBLOCK_OPTICAL_CHARACTER_RECOGNITION =50, /*[2440]*/
jpayne@69 1185
jpayne@69 1186 /** @stable ICU 2.0 */
jpayne@69 1187 UBLOCK_ENCLOSED_ALPHANUMERICS =51, /*[2460]*/
jpayne@69 1188
jpayne@69 1189 /** @stable ICU 2.0 */
jpayne@69 1190 UBLOCK_BOX_DRAWING =52, /*[2500]*/
jpayne@69 1191
jpayne@69 1192 /** @stable ICU 2.0 */
jpayne@69 1193 UBLOCK_BLOCK_ELEMENTS =53, /*[2580]*/
jpayne@69 1194
jpayne@69 1195 /** @stable ICU 2.0 */
jpayne@69 1196 UBLOCK_GEOMETRIC_SHAPES =54, /*[25A0]*/
jpayne@69 1197
jpayne@69 1198 /** @stable ICU 2.0 */
jpayne@69 1199 UBLOCK_MISCELLANEOUS_SYMBOLS =55, /*[2600]*/
jpayne@69 1200
jpayne@69 1201 /** @stable ICU 2.0 */
jpayne@69 1202 UBLOCK_DINGBATS =56, /*[2700]*/
jpayne@69 1203
jpayne@69 1204 /** @stable ICU 2.0 */
jpayne@69 1205 UBLOCK_BRAILLE_PATTERNS =57, /*[2800]*/
jpayne@69 1206
jpayne@69 1207 /** @stable ICU 2.0 */
jpayne@69 1208 UBLOCK_CJK_RADICALS_SUPPLEMENT =58, /*[2E80]*/
jpayne@69 1209
jpayne@69 1210 /** @stable ICU 2.0 */
jpayne@69 1211 UBLOCK_KANGXI_RADICALS =59, /*[2F00]*/
jpayne@69 1212
jpayne@69 1213 /** @stable ICU 2.0 */
jpayne@69 1214 UBLOCK_IDEOGRAPHIC_DESCRIPTION_CHARACTERS =60, /*[2FF0]*/
jpayne@69 1215
jpayne@69 1216 /** @stable ICU 2.0 */
jpayne@69 1217 UBLOCK_CJK_SYMBOLS_AND_PUNCTUATION =61, /*[3000]*/
jpayne@69 1218
jpayne@69 1219 /** @stable ICU 2.0 */
jpayne@69 1220 UBLOCK_HIRAGANA =62, /*[3040]*/
jpayne@69 1221
jpayne@69 1222 /** @stable ICU 2.0 */
jpayne@69 1223 UBLOCK_KATAKANA =63, /*[30A0]*/
jpayne@69 1224
jpayne@69 1225 /** @stable ICU 2.0 */
jpayne@69 1226 UBLOCK_BOPOMOFO =64, /*[3100]*/
jpayne@69 1227
jpayne@69 1228 /** @stable ICU 2.0 */
jpayne@69 1229 UBLOCK_HANGUL_COMPATIBILITY_JAMO =65, /*[3130]*/
jpayne@69 1230
jpayne@69 1231 /** @stable ICU 2.0 */
jpayne@69 1232 UBLOCK_KANBUN =66, /*[3190]*/
jpayne@69 1233
jpayne@69 1234 /** @stable ICU 2.0 */
jpayne@69 1235 UBLOCK_BOPOMOFO_EXTENDED =67, /*[31A0]*/
jpayne@69 1236
jpayne@69 1237 /** @stable ICU 2.0 */
jpayne@69 1238 UBLOCK_ENCLOSED_CJK_LETTERS_AND_MONTHS =68, /*[3200]*/
jpayne@69 1239
jpayne@69 1240 /** @stable ICU 2.0 */
jpayne@69 1241 UBLOCK_CJK_COMPATIBILITY =69, /*[3300]*/
jpayne@69 1242
jpayne@69 1243 /** @stable ICU 2.0 */
jpayne@69 1244 UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_A =70, /*[3400]*/
jpayne@69 1245
jpayne@69 1246 /** @stable ICU 2.0 */
jpayne@69 1247 UBLOCK_CJK_UNIFIED_IDEOGRAPHS =71, /*[4E00]*/
jpayne@69 1248
jpayne@69 1249 /** @stable ICU 2.0 */
jpayne@69 1250 UBLOCK_YI_SYLLABLES =72, /*[A000]*/
jpayne@69 1251
jpayne@69 1252 /** @stable ICU 2.0 */
jpayne@69 1253 UBLOCK_YI_RADICALS =73, /*[A490]*/
jpayne@69 1254
jpayne@69 1255 /** @stable ICU 2.0 */
jpayne@69 1256 UBLOCK_HANGUL_SYLLABLES =74, /*[AC00]*/
jpayne@69 1257
jpayne@69 1258 /** @stable ICU 2.0 */
jpayne@69 1259 UBLOCK_HIGH_SURROGATES =75, /*[D800]*/
jpayne@69 1260
jpayne@69 1261 /** @stable ICU 2.0 */
jpayne@69 1262 UBLOCK_HIGH_PRIVATE_USE_SURROGATES =76, /*[DB80]*/
jpayne@69 1263
jpayne@69 1264 /** @stable ICU 2.0 */
jpayne@69 1265 UBLOCK_LOW_SURROGATES =77, /*[DC00]*/
jpayne@69 1266
jpayne@69 1267 /**
jpayne@69 1268 * Same as UBLOCK_PRIVATE_USE.
jpayne@69 1269 * Until Unicode 3.1.1, the corresponding block name was "Private Use",
jpayne@69 1270 * and multiple code point ranges had this block.
jpayne@69 1271 * Unicode 3.2 renames the block for the BMP PUA to "Private Use Area" and
jpayne@69 1272 * adds separate blocks for the supplementary PUAs.
jpayne@69 1273 *
jpayne@69 1274 * @stable ICU 2.0
jpayne@69 1275 */
jpayne@69 1276 UBLOCK_PRIVATE_USE_AREA =78, /*[E000]*/
jpayne@69 1277 /**
jpayne@69 1278 * Same as UBLOCK_PRIVATE_USE_AREA.
jpayne@69 1279 * Until Unicode 3.1.1, the corresponding block name was "Private Use",
jpayne@69 1280 * and multiple code point ranges had this block.
jpayne@69 1281 * Unicode 3.2 renames the block for the BMP PUA to "Private Use Area" and
jpayne@69 1282 * adds separate blocks for the supplementary PUAs.
jpayne@69 1283 *
jpayne@69 1284 * @stable ICU 2.0
jpayne@69 1285 */
jpayne@69 1286 UBLOCK_PRIVATE_USE = UBLOCK_PRIVATE_USE_AREA,
jpayne@69 1287
jpayne@69 1288 /** @stable ICU 2.0 */
jpayne@69 1289 UBLOCK_CJK_COMPATIBILITY_IDEOGRAPHS =79, /*[F900]*/
jpayne@69 1290
jpayne@69 1291 /** @stable ICU 2.0 */
jpayne@69 1292 UBLOCK_ALPHABETIC_PRESENTATION_FORMS =80, /*[FB00]*/
jpayne@69 1293
jpayne@69 1294 /** @stable ICU 2.0 */
jpayne@69 1295 UBLOCK_ARABIC_PRESENTATION_FORMS_A =81, /*[FB50]*/
jpayne@69 1296
jpayne@69 1297 /** @stable ICU 2.0 */
jpayne@69 1298 UBLOCK_COMBINING_HALF_MARKS =82, /*[FE20]*/
jpayne@69 1299
jpayne@69 1300 /** @stable ICU 2.0 */
jpayne@69 1301 UBLOCK_CJK_COMPATIBILITY_FORMS =83, /*[FE30]*/
jpayne@69 1302
jpayne@69 1303 /** @stable ICU 2.0 */
jpayne@69 1304 UBLOCK_SMALL_FORM_VARIANTS =84, /*[FE50]*/
jpayne@69 1305
jpayne@69 1306 /** @stable ICU 2.0 */
jpayne@69 1307 UBLOCK_ARABIC_PRESENTATION_FORMS_B =85, /*[FE70]*/
jpayne@69 1308
jpayne@69 1309 /** @stable ICU 2.0 */
jpayne@69 1310 UBLOCK_SPECIALS =86, /*[FFF0]*/
jpayne@69 1311
jpayne@69 1312 /** @stable ICU 2.0 */
jpayne@69 1313 UBLOCK_HALFWIDTH_AND_FULLWIDTH_FORMS =87, /*[FF00]*/
jpayne@69 1314
jpayne@69 1315 /* New blocks in Unicode 3.1 */
jpayne@69 1316
jpayne@69 1317 /** @stable ICU 2.0 */
jpayne@69 1318 UBLOCK_OLD_ITALIC = 88, /*[10300]*/
jpayne@69 1319 /** @stable ICU 2.0 */
jpayne@69 1320 UBLOCK_GOTHIC = 89, /*[10330]*/
jpayne@69 1321 /** @stable ICU 2.0 */
jpayne@69 1322 UBLOCK_DESERET = 90, /*[10400]*/
jpayne@69 1323 /** @stable ICU 2.0 */
jpayne@69 1324 UBLOCK_BYZANTINE_MUSICAL_SYMBOLS = 91, /*[1D000]*/
jpayne@69 1325 /** @stable ICU 2.0 */
jpayne@69 1326 UBLOCK_MUSICAL_SYMBOLS = 92, /*[1D100]*/
jpayne@69 1327 /** @stable ICU 2.0 */
jpayne@69 1328 UBLOCK_MATHEMATICAL_ALPHANUMERIC_SYMBOLS = 93, /*[1D400]*/
jpayne@69 1329 /** @stable ICU 2.0 */
jpayne@69 1330 UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_B = 94, /*[20000]*/
jpayne@69 1331 /** @stable ICU 2.0 */
jpayne@69 1332 UBLOCK_CJK_COMPATIBILITY_IDEOGRAPHS_SUPPLEMENT = 95, /*[2F800]*/
jpayne@69 1333 /** @stable ICU 2.0 */
jpayne@69 1334 UBLOCK_TAGS = 96, /*[E0000]*/
jpayne@69 1335
jpayne@69 1336 /* New blocks in Unicode 3.2 */
jpayne@69 1337
jpayne@69 1338 /** @stable ICU 3.0 */
jpayne@69 1339 UBLOCK_CYRILLIC_SUPPLEMENT = 97, /*[0500]*/
jpayne@69 1340 /**
jpayne@69 1341 * Unicode 4.0.1 renames the "Cyrillic Supplementary" block to "Cyrillic Supplement".
jpayne@69 1342 * @stable ICU 2.2
jpayne@69 1343 */
jpayne@69 1344 UBLOCK_CYRILLIC_SUPPLEMENTARY = UBLOCK_CYRILLIC_SUPPLEMENT,
jpayne@69 1345 /** @stable ICU 2.2 */
jpayne@69 1346 UBLOCK_TAGALOG = 98, /*[1700]*/
jpayne@69 1347 /** @stable ICU 2.2 */
jpayne@69 1348 UBLOCK_HANUNOO = 99, /*[1720]*/
jpayne@69 1349 /** @stable ICU 2.2 */
jpayne@69 1350 UBLOCK_BUHID = 100, /*[1740]*/
jpayne@69 1351 /** @stable ICU 2.2 */
jpayne@69 1352 UBLOCK_TAGBANWA = 101, /*[1760]*/
jpayne@69 1353 /** @stable ICU 2.2 */
jpayne@69 1354 UBLOCK_MISCELLANEOUS_MATHEMATICAL_SYMBOLS_A = 102, /*[27C0]*/
jpayne@69 1355 /** @stable ICU 2.2 */
jpayne@69 1356 UBLOCK_SUPPLEMENTAL_ARROWS_A = 103, /*[27F0]*/
jpayne@69 1357 /** @stable ICU 2.2 */
jpayne@69 1358 UBLOCK_SUPPLEMENTAL_ARROWS_B = 104, /*[2900]*/
jpayne@69 1359 /** @stable ICU 2.2 */
jpayne@69 1360 UBLOCK_MISCELLANEOUS_MATHEMATICAL_SYMBOLS_B = 105, /*[2980]*/
jpayne@69 1361 /** @stable ICU 2.2 */
jpayne@69 1362 UBLOCK_SUPPLEMENTAL_MATHEMATICAL_OPERATORS = 106, /*[2A00]*/
jpayne@69 1363 /** @stable ICU 2.2 */
jpayne@69 1364 UBLOCK_KATAKANA_PHONETIC_EXTENSIONS = 107, /*[31F0]*/
jpayne@69 1365 /** @stable ICU 2.2 */
jpayne@69 1366 UBLOCK_VARIATION_SELECTORS = 108, /*[FE00]*/
jpayne@69 1367 /** @stable ICU 2.2 */
jpayne@69 1368 UBLOCK_SUPPLEMENTARY_PRIVATE_USE_AREA_A = 109, /*[F0000]*/
jpayne@69 1369 /** @stable ICU 2.2 */
jpayne@69 1370 UBLOCK_SUPPLEMENTARY_PRIVATE_USE_AREA_B = 110, /*[100000]*/
jpayne@69 1371
jpayne@69 1372 /* New blocks in Unicode 4 */
jpayne@69 1373
jpayne@69 1374 /** @stable ICU 2.6 */
jpayne@69 1375 UBLOCK_LIMBU = 111, /*[1900]*/
jpayne@69 1376 /** @stable ICU 2.6 */
jpayne@69 1377 UBLOCK_TAI_LE = 112, /*[1950]*/
jpayne@69 1378 /** @stable ICU 2.6 */
jpayne@69 1379 UBLOCK_KHMER_SYMBOLS = 113, /*[19E0]*/
jpayne@69 1380 /** @stable ICU 2.6 */
jpayne@69 1381 UBLOCK_PHONETIC_EXTENSIONS = 114, /*[1D00]*/
jpayne@69 1382 /** @stable ICU 2.6 */
jpayne@69 1383 UBLOCK_MISCELLANEOUS_SYMBOLS_AND_ARROWS = 115, /*[2B00]*/
jpayne@69 1384 /** @stable ICU 2.6 */
jpayne@69 1385 UBLOCK_YIJING_HEXAGRAM_SYMBOLS = 116, /*[4DC0]*/
jpayne@69 1386 /** @stable ICU 2.6 */
jpayne@69 1387 UBLOCK_LINEAR_B_SYLLABARY = 117, /*[10000]*/
jpayne@69 1388 /** @stable ICU 2.6 */
jpayne@69 1389 UBLOCK_LINEAR_B_IDEOGRAMS = 118, /*[10080]*/
jpayne@69 1390 /** @stable ICU 2.6 */
jpayne@69 1391 UBLOCK_AEGEAN_NUMBERS = 119, /*[10100]*/
jpayne@69 1392 /** @stable ICU 2.6 */
jpayne@69 1393 UBLOCK_UGARITIC = 120, /*[10380]*/
jpayne@69 1394 /** @stable ICU 2.6 */
jpayne@69 1395 UBLOCK_SHAVIAN = 121, /*[10450]*/
jpayne@69 1396 /** @stable ICU 2.6 */
jpayne@69 1397 UBLOCK_OSMANYA = 122, /*[10480]*/
jpayne@69 1398 /** @stable ICU 2.6 */
jpayne@69 1399 UBLOCK_CYPRIOT_SYLLABARY = 123, /*[10800]*/
jpayne@69 1400 /** @stable ICU 2.6 */
jpayne@69 1401 UBLOCK_TAI_XUAN_JING_SYMBOLS = 124, /*[1D300]*/
jpayne@69 1402 /** @stable ICU 2.6 */
jpayne@69 1403 UBLOCK_VARIATION_SELECTORS_SUPPLEMENT = 125, /*[E0100]*/
jpayne@69 1404
jpayne@69 1405 /* New blocks in Unicode 4.1 */
jpayne@69 1406
jpayne@69 1407 /** @stable ICU 3.4 */
jpayne@69 1408 UBLOCK_ANCIENT_GREEK_MUSICAL_NOTATION = 126, /*[1D200]*/
jpayne@69 1409 /** @stable ICU 3.4 */
jpayne@69 1410 UBLOCK_ANCIENT_GREEK_NUMBERS = 127, /*[10140]*/
jpayne@69 1411 /** @stable ICU 3.4 */
jpayne@69 1412 UBLOCK_ARABIC_SUPPLEMENT = 128, /*[0750]*/
jpayne@69 1413 /** @stable ICU 3.4 */
jpayne@69 1414 UBLOCK_BUGINESE = 129, /*[1A00]*/
jpayne@69 1415 /** @stable ICU 3.4 */
jpayne@69 1416 UBLOCK_CJK_STROKES = 130, /*[31C0]*/
jpayne@69 1417 /** @stable ICU 3.4 */
jpayne@69 1418 UBLOCK_COMBINING_DIACRITICAL_MARKS_SUPPLEMENT = 131, /*[1DC0]*/
jpayne@69 1419 /** @stable ICU 3.4 */
jpayne@69 1420 UBLOCK_COPTIC = 132, /*[2C80]*/
jpayne@69 1421 /** @stable ICU 3.4 */
jpayne@69 1422 UBLOCK_ETHIOPIC_EXTENDED = 133, /*[2D80]*/
jpayne@69 1423 /** @stable ICU 3.4 */
jpayne@69 1424 UBLOCK_ETHIOPIC_SUPPLEMENT = 134, /*[1380]*/
jpayne@69 1425 /** @stable ICU 3.4 */
jpayne@69 1426 UBLOCK_GEORGIAN_SUPPLEMENT = 135, /*[2D00]*/
jpayne@69 1427 /** @stable ICU 3.4 */
jpayne@69 1428 UBLOCK_GLAGOLITIC = 136, /*[2C00]*/
jpayne@69 1429 /** @stable ICU 3.4 */
jpayne@69 1430 UBLOCK_KHAROSHTHI = 137, /*[10A00]*/
jpayne@69 1431 /** @stable ICU 3.4 */
jpayne@69 1432 UBLOCK_MODIFIER_TONE_LETTERS = 138, /*[A700]*/
jpayne@69 1433 /** @stable ICU 3.4 */
jpayne@69 1434 UBLOCK_NEW_TAI_LUE = 139, /*[1980]*/
jpayne@69 1435 /** @stable ICU 3.4 */
jpayne@69 1436 UBLOCK_OLD_PERSIAN = 140, /*[103A0]*/
jpayne@69 1437 /** @stable ICU 3.4 */
jpayne@69 1438 UBLOCK_PHONETIC_EXTENSIONS_SUPPLEMENT = 141, /*[1D80]*/
jpayne@69 1439 /** @stable ICU 3.4 */
jpayne@69 1440 UBLOCK_SUPPLEMENTAL_PUNCTUATION = 142, /*[2E00]*/
jpayne@69 1441 /** @stable ICU 3.4 */
jpayne@69 1442 UBLOCK_SYLOTI_NAGRI = 143, /*[A800]*/
jpayne@69 1443 /** @stable ICU 3.4 */
jpayne@69 1444 UBLOCK_TIFINAGH = 144, /*[2D30]*/
jpayne@69 1445 /** @stable ICU 3.4 */
jpayne@69 1446 UBLOCK_VERTICAL_FORMS = 145, /*[FE10]*/
jpayne@69 1447
jpayne@69 1448 /* New blocks in Unicode 5.0 */
jpayne@69 1449
jpayne@69 1450 /** @stable ICU 3.6 */
jpayne@69 1451 UBLOCK_NKO = 146, /*[07C0]*/
jpayne@69 1452 /** @stable ICU 3.6 */
jpayne@69 1453 UBLOCK_BALINESE = 147, /*[1B00]*/
jpayne@69 1454 /** @stable ICU 3.6 */
jpayne@69 1455 UBLOCK_LATIN_EXTENDED_C = 148, /*[2C60]*/
jpayne@69 1456 /** @stable ICU 3.6 */
jpayne@69 1457 UBLOCK_LATIN_EXTENDED_D = 149, /*[A720]*/
jpayne@69 1458 /** @stable ICU 3.6 */
jpayne@69 1459 UBLOCK_PHAGS_PA = 150, /*[A840]*/
jpayne@69 1460 /** @stable ICU 3.6 */
jpayne@69 1461 UBLOCK_PHOENICIAN = 151, /*[10900]*/
jpayne@69 1462 /** @stable ICU 3.6 */
jpayne@69 1463 UBLOCK_CUNEIFORM = 152, /*[12000]*/
jpayne@69 1464 /** @stable ICU 3.6 */
jpayne@69 1465 UBLOCK_CUNEIFORM_NUMBERS_AND_PUNCTUATION = 153, /*[12400]*/
jpayne@69 1466 /** @stable ICU 3.6 */
jpayne@69 1467 UBLOCK_COUNTING_ROD_NUMERALS = 154, /*[1D360]*/
jpayne@69 1468
jpayne@69 1469 /* New blocks in Unicode 5.1 */
jpayne@69 1470
jpayne@69 1471 /** @stable ICU 4.0 */
jpayne@69 1472 UBLOCK_SUNDANESE = 155, /*[1B80]*/
jpayne@69 1473 /** @stable ICU 4.0 */
jpayne@69 1474 UBLOCK_LEPCHA = 156, /*[1C00]*/
jpayne@69 1475 /** @stable ICU 4.0 */
jpayne@69 1476 UBLOCK_OL_CHIKI = 157, /*[1C50]*/
jpayne@69 1477 /** @stable ICU 4.0 */
jpayne@69 1478 UBLOCK_CYRILLIC_EXTENDED_A = 158, /*[2DE0]*/
jpayne@69 1479 /** @stable ICU 4.0 */
jpayne@69 1480 UBLOCK_VAI = 159, /*[A500]*/
jpayne@69 1481 /** @stable ICU 4.0 */
jpayne@69 1482 UBLOCK_CYRILLIC_EXTENDED_B = 160, /*[A640]*/
jpayne@69 1483 /** @stable ICU 4.0 */
jpayne@69 1484 UBLOCK_SAURASHTRA = 161, /*[A880]*/
jpayne@69 1485 /** @stable ICU 4.0 */
jpayne@69 1486 UBLOCK_KAYAH_LI = 162, /*[A900]*/
jpayne@69 1487 /** @stable ICU 4.0 */
jpayne@69 1488 UBLOCK_REJANG = 163, /*[A930]*/
jpayne@69 1489 /** @stable ICU 4.0 */
jpayne@69 1490 UBLOCK_CHAM = 164, /*[AA00]*/
jpayne@69 1491 /** @stable ICU 4.0 */
jpayne@69 1492 UBLOCK_ANCIENT_SYMBOLS = 165, /*[10190]*/
jpayne@69 1493 /** @stable ICU 4.0 */
jpayne@69 1494 UBLOCK_PHAISTOS_DISC = 166, /*[101D0]*/
jpayne@69 1495 /** @stable ICU 4.0 */
jpayne@69 1496 UBLOCK_LYCIAN = 167, /*[10280]*/
jpayne@69 1497 /** @stable ICU 4.0 */
jpayne@69 1498 UBLOCK_CARIAN = 168, /*[102A0]*/
jpayne@69 1499 /** @stable ICU 4.0 */
jpayne@69 1500 UBLOCK_LYDIAN = 169, /*[10920]*/
jpayne@69 1501 /** @stable ICU 4.0 */
jpayne@69 1502 UBLOCK_MAHJONG_TILES = 170, /*[1F000]*/
jpayne@69 1503 /** @stable ICU 4.0 */
jpayne@69 1504 UBLOCK_DOMINO_TILES = 171, /*[1F030]*/
jpayne@69 1505
jpayne@69 1506 /* New blocks in Unicode 5.2 */
jpayne@69 1507
jpayne@69 1508 /** @stable ICU 4.4 */
jpayne@69 1509 UBLOCK_SAMARITAN = 172, /*[0800]*/
jpayne@69 1510 /** @stable ICU 4.4 */
jpayne@69 1511 UBLOCK_UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS_EXTENDED = 173, /*[18B0]*/
jpayne@69 1512 /** @stable ICU 4.4 */
jpayne@69 1513 UBLOCK_TAI_THAM = 174, /*[1A20]*/
jpayne@69 1514 /** @stable ICU 4.4 */
jpayne@69 1515 UBLOCK_VEDIC_EXTENSIONS = 175, /*[1CD0]*/
jpayne@69 1516 /** @stable ICU 4.4 */
jpayne@69 1517 UBLOCK_LISU = 176, /*[A4D0]*/
jpayne@69 1518 /** @stable ICU 4.4 */
jpayne@69 1519 UBLOCK_BAMUM = 177, /*[A6A0]*/
jpayne@69 1520 /** @stable ICU 4.4 */
jpayne@69 1521 UBLOCK_COMMON_INDIC_NUMBER_FORMS = 178, /*[A830]*/
jpayne@69 1522 /** @stable ICU 4.4 */
jpayne@69 1523 UBLOCK_DEVANAGARI_EXTENDED = 179, /*[A8E0]*/
jpayne@69 1524 /** @stable ICU 4.4 */
jpayne@69 1525 UBLOCK_HANGUL_JAMO_EXTENDED_A = 180, /*[A960]*/
jpayne@69 1526 /** @stable ICU 4.4 */
jpayne@69 1527 UBLOCK_JAVANESE = 181, /*[A980]*/
jpayne@69 1528 /** @stable ICU 4.4 */
jpayne@69 1529 UBLOCK_MYANMAR_EXTENDED_A = 182, /*[AA60]*/
jpayne@69 1530 /** @stable ICU 4.4 */
jpayne@69 1531 UBLOCK_TAI_VIET = 183, /*[AA80]*/
jpayne@69 1532 /** @stable ICU 4.4 */
jpayne@69 1533 UBLOCK_MEETEI_MAYEK = 184, /*[ABC0]*/
jpayne@69 1534 /** @stable ICU 4.4 */
jpayne@69 1535 UBLOCK_HANGUL_JAMO_EXTENDED_B = 185, /*[D7B0]*/
jpayne@69 1536 /** @stable ICU 4.4 */
jpayne@69 1537 UBLOCK_IMPERIAL_ARAMAIC = 186, /*[10840]*/
jpayne@69 1538 /** @stable ICU 4.4 */
jpayne@69 1539 UBLOCK_OLD_SOUTH_ARABIAN = 187, /*[10A60]*/
jpayne@69 1540 /** @stable ICU 4.4 */
jpayne@69 1541 UBLOCK_AVESTAN = 188, /*[10B00]*/
jpayne@69 1542 /** @stable ICU 4.4 */
jpayne@69 1543 UBLOCK_INSCRIPTIONAL_PARTHIAN = 189, /*[10B40]*/
jpayne@69 1544 /** @stable ICU 4.4 */
jpayne@69 1545 UBLOCK_INSCRIPTIONAL_PAHLAVI = 190, /*[10B60]*/
jpayne@69 1546 /** @stable ICU 4.4 */
jpayne@69 1547 UBLOCK_OLD_TURKIC = 191, /*[10C00]*/
jpayne@69 1548 /** @stable ICU 4.4 */
jpayne@69 1549 UBLOCK_RUMI_NUMERAL_SYMBOLS = 192, /*[10E60]*/
jpayne@69 1550 /** @stable ICU 4.4 */
jpayne@69 1551 UBLOCK_KAITHI = 193, /*[11080]*/
jpayne@69 1552 /** @stable ICU 4.4 */
jpayne@69 1553 UBLOCK_EGYPTIAN_HIEROGLYPHS = 194, /*[13000]*/
jpayne@69 1554 /** @stable ICU 4.4 */
jpayne@69 1555 UBLOCK_ENCLOSED_ALPHANUMERIC_SUPPLEMENT = 195, /*[1F100]*/
jpayne@69 1556 /** @stable ICU 4.4 */
jpayne@69 1557 UBLOCK_ENCLOSED_IDEOGRAPHIC_SUPPLEMENT = 196, /*[1F200]*/
jpayne@69 1558 /** @stable ICU 4.4 */
jpayne@69 1559 UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_C = 197, /*[2A700]*/
jpayne@69 1560
jpayne@69 1561 /* New blocks in Unicode 6.0 */
jpayne@69 1562
jpayne@69 1563 /** @stable ICU 4.6 */
jpayne@69 1564 UBLOCK_MANDAIC = 198, /*[0840]*/
jpayne@69 1565 /** @stable ICU 4.6 */
jpayne@69 1566 UBLOCK_BATAK = 199, /*[1BC0]*/
jpayne@69 1567 /** @stable ICU 4.6 */
jpayne@69 1568 UBLOCK_ETHIOPIC_EXTENDED_A = 200, /*[AB00]*/
jpayne@69 1569 /** @stable ICU 4.6 */
jpayne@69 1570 UBLOCK_BRAHMI = 201, /*[11000]*/
jpayne@69 1571 /** @stable ICU 4.6 */
jpayne@69 1572 UBLOCK_BAMUM_SUPPLEMENT = 202, /*[16800]*/
jpayne@69 1573 /** @stable ICU 4.6 */
jpayne@69 1574 UBLOCK_KANA_SUPPLEMENT = 203, /*[1B000]*/
jpayne@69 1575 /** @stable ICU 4.6 */
jpayne@69 1576 UBLOCK_PLAYING_CARDS = 204, /*[1F0A0]*/
jpayne@69 1577 /** @stable ICU 4.6 */
jpayne@69 1578 UBLOCK_MISCELLANEOUS_SYMBOLS_AND_PICTOGRAPHS = 205, /*[1F300]*/
jpayne@69 1579 /** @stable ICU 4.6 */
jpayne@69 1580 UBLOCK_EMOTICONS = 206, /*[1F600]*/
jpayne@69 1581 /** @stable ICU 4.6 */
jpayne@69 1582 UBLOCK_TRANSPORT_AND_MAP_SYMBOLS = 207, /*[1F680]*/
jpayne@69 1583 /** @stable ICU 4.6 */
jpayne@69 1584 UBLOCK_ALCHEMICAL_SYMBOLS = 208, /*[1F700]*/
jpayne@69 1585 /** @stable ICU 4.6 */
jpayne@69 1586 UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_D = 209, /*[2B740]*/
jpayne@69 1587
jpayne@69 1588 /* New blocks in Unicode 6.1 */
jpayne@69 1589
jpayne@69 1590 /** @stable ICU 49 */
jpayne@69 1591 UBLOCK_ARABIC_EXTENDED_A = 210, /*[08A0]*/
jpayne@69 1592 /** @stable ICU 49 */
jpayne@69 1593 UBLOCK_ARABIC_MATHEMATICAL_ALPHABETIC_SYMBOLS = 211, /*[1EE00]*/
jpayne@69 1594 /** @stable ICU 49 */
jpayne@69 1595 UBLOCK_CHAKMA = 212, /*[11100]*/
jpayne@69 1596 /** @stable ICU 49 */
jpayne@69 1597 UBLOCK_MEETEI_MAYEK_EXTENSIONS = 213, /*[AAE0]*/
jpayne@69 1598 /** @stable ICU 49 */
jpayne@69 1599 UBLOCK_MEROITIC_CURSIVE = 214, /*[109A0]*/
jpayne@69 1600 /** @stable ICU 49 */
jpayne@69 1601 UBLOCK_MEROITIC_HIEROGLYPHS = 215, /*[10980]*/
jpayne@69 1602 /** @stable ICU 49 */
jpayne@69 1603 UBLOCK_MIAO = 216, /*[16F00]*/
jpayne@69 1604 /** @stable ICU 49 */
jpayne@69 1605 UBLOCK_SHARADA = 217, /*[11180]*/
jpayne@69 1606 /** @stable ICU 49 */
jpayne@69 1607 UBLOCK_SORA_SOMPENG = 218, /*[110D0]*/
jpayne@69 1608 /** @stable ICU 49 */
jpayne@69 1609 UBLOCK_SUNDANESE_SUPPLEMENT = 219, /*[1CC0]*/
jpayne@69 1610 /** @stable ICU 49 */
jpayne@69 1611 UBLOCK_TAKRI = 220, /*[11680]*/
jpayne@69 1612
jpayne@69 1613 /* New blocks in Unicode 7.0 */
jpayne@69 1614
jpayne@69 1615 /** @stable ICU 54 */
jpayne@69 1616 UBLOCK_BASSA_VAH = 221, /*[16AD0]*/
jpayne@69 1617 /** @stable ICU 54 */
jpayne@69 1618 UBLOCK_CAUCASIAN_ALBANIAN = 222, /*[10530]*/
jpayne@69 1619 /** @stable ICU 54 */
jpayne@69 1620 UBLOCK_COPTIC_EPACT_NUMBERS = 223, /*[102E0]*/
jpayne@69 1621 /** @stable ICU 54 */
jpayne@69 1622 UBLOCK_COMBINING_DIACRITICAL_MARKS_EXTENDED = 224, /*[1AB0]*/
jpayne@69 1623 /** @stable ICU 54 */
jpayne@69 1624 UBLOCK_DUPLOYAN = 225, /*[1BC00]*/
jpayne@69 1625 /** @stable ICU 54 */
jpayne@69 1626 UBLOCK_ELBASAN = 226, /*[10500]*/
jpayne@69 1627 /** @stable ICU 54 */
jpayne@69 1628 UBLOCK_GEOMETRIC_SHAPES_EXTENDED = 227, /*[1F780]*/
jpayne@69 1629 /** @stable ICU 54 */
jpayne@69 1630 UBLOCK_GRANTHA = 228, /*[11300]*/
jpayne@69 1631 /** @stable ICU 54 */
jpayne@69 1632 UBLOCK_KHOJKI = 229, /*[11200]*/
jpayne@69 1633 /** @stable ICU 54 */
jpayne@69 1634 UBLOCK_KHUDAWADI = 230, /*[112B0]*/
jpayne@69 1635 /** @stable ICU 54 */
jpayne@69 1636 UBLOCK_LATIN_EXTENDED_E = 231, /*[AB30]*/
jpayne@69 1637 /** @stable ICU 54 */
jpayne@69 1638 UBLOCK_LINEAR_A = 232, /*[10600]*/
jpayne@69 1639 /** @stable ICU 54 */
jpayne@69 1640 UBLOCK_MAHAJANI = 233, /*[11150]*/
jpayne@69 1641 /** @stable ICU 54 */
jpayne@69 1642 UBLOCK_MANICHAEAN = 234, /*[10AC0]*/
jpayne@69 1643 /** @stable ICU 54 */
jpayne@69 1644 UBLOCK_MENDE_KIKAKUI = 235, /*[1E800]*/
jpayne@69 1645 /** @stable ICU 54 */
jpayne@69 1646 UBLOCK_MODI = 236, /*[11600]*/
jpayne@69 1647 /** @stable ICU 54 */
jpayne@69 1648 UBLOCK_MRO = 237, /*[16A40]*/
jpayne@69 1649 /** @stable ICU 54 */
jpayne@69 1650 UBLOCK_MYANMAR_EXTENDED_B = 238, /*[A9E0]*/
jpayne@69 1651 /** @stable ICU 54 */
jpayne@69 1652 UBLOCK_NABATAEAN = 239, /*[10880]*/
jpayne@69 1653 /** @stable ICU 54 */
jpayne@69 1654 UBLOCK_OLD_NORTH_ARABIAN = 240, /*[10A80]*/
jpayne@69 1655 /** @stable ICU 54 */
jpayne@69 1656 UBLOCK_OLD_PERMIC = 241, /*[10350]*/
jpayne@69 1657 /** @stable ICU 54 */
jpayne@69 1658 UBLOCK_ORNAMENTAL_DINGBATS = 242, /*[1F650]*/
jpayne@69 1659 /** @stable ICU 54 */
jpayne@69 1660 UBLOCK_PAHAWH_HMONG = 243, /*[16B00]*/
jpayne@69 1661 /** @stable ICU 54 */
jpayne@69 1662 UBLOCK_PALMYRENE = 244, /*[10860]*/
jpayne@69 1663 /** @stable ICU 54 */
jpayne@69 1664 UBLOCK_PAU_CIN_HAU = 245, /*[11AC0]*/
jpayne@69 1665 /** @stable ICU 54 */
jpayne@69 1666 UBLOCK_PSALTER_PAHLAVI = 246, /*[10B80]*/
jpayne@69 1667 /** @stable ICU 54 */
jpayne@69 1668 UBLOCK_SHORTHAND_FORMAT_CONTROLS = 247, /*[1BCA0]*/
jpayne@69 1669 /** @stable ICU 54 */
jpayne@69 1670 UBLOCK_SIDDHAM = 248, /*[11580]*/
jpayne@69 1671 /** @stable ICU 54 */
jpayne@69 1672 UBLOCK_SINHALA_ARCHAIC_NUMBERS = 249, /*[111E0]*/
jpayne@69 1673 /** @stable ICU 54 */
jpayne@69 1674 UBLOCK_SUPPLEMENTAL_ARROWS_C = 250, /*[1F800]*/
jpayne@69 1675 /** @stable ICU 54 */
jpayne@69 1676 UBLOCK_TIRHUTA = 251, /*[11480]*/
jpayne@69 1677 /** @stable ICU 54 */
jpayne@69 1678 UBLOCK_WARANG_CITI = 252, /*[118A0]*/
jpayne@69 1679
jpayne@69 1680 /* New blocks in Unicode 8.0 */
jpayne@69 1681
jpayne@69 1682 /** @stable ICU 56 */
jpayne@69 1683 UBLOCK_AHOM = 253, /*[11700]*/
jpayne@69 1684 /** @stable ICU 56 */
jpayne@69 1685 UBLOCK_ANATOLIAN_HIEROGLYPHS = 254, /*[14400]*/
jpayne@69 1686 /** @stable ICU 56 */
jpayne@69 1687 UBLOCK_CHEROKEE_SUPPLEMENT = 255, /*[AB70]*/
jpayne@69 1688 /** @stable ICU 56 */
jpayne@69 1689 UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_E = 256, /*[2B820]*/
jpayne@69 1690 /** @stable ICU 56 */
jpayne@69 1691 UBLOCK_EARLY_DYNASTIC_CUNEIFORM = 257, /*[12480]*/
jpayne@69 1692 /** @stable ICU 56 */
jpayne@69 1693 UBLOCK_HATRAN = 258, /*[108E0]*/
jpayne@69 1694 /** @stable ICU 56 */
jpayne@69 1695 UBLOCK_MULTANI = 259, /*[11280]*/
jpayne@69 1696 /** @stable ICU 56 */
jpayne@69 1697 UBLOCK_OLD_HUNGARIAN = 260, /*[10C80]*/
jpayne@69 1698 /** @stable ICU 56 */
jpayne@69 1699 UBLOCK_SUPPLEMENTAL_SYMBOLS_AND_PICTOGRAPHS = 261, /*[1F900]*/
jpayne@69 1700 /** @stable ICU 56 */
jpayne@69 1701 UBLOCK_SUTTON_SIGNWRITING = 262, /*[1D800]*/
jpayne@69 1702
jpayne@69 1703 /* New blocks in Unicode 9.0 */
jpayne@69 1704
jpayne@69 1705 /** @stable ICU 58 */
jpayne@69 1706 UBLOCK_ADLAM = 263, /*[1E900]*/
jpayne@69 1707 /** @stable ICU 58 */
jpayne@69 1708 UBLOCK_BHAIKSUKI = 264, /*[11C00]*/
jpayne@69 1709 /** @stable ICU 58 */
jpayne@69 1710 UBLOCK_CYRILLIC_EXTENDED_C = 265, /*[1C80]*/
jpayne@69 1711 /** @stable ICU 58 */
jpayne@69 1712 UBLOCK_GLAGOLITIC_SUPPLEMENT = 266, /*[1E000]*/
jpayne@69 1713 /** @stable ICU 58 */
jpayne@69 1714 UBLOCK_IDEOGRAPHIC_SYMBOLS_AND_PUNCTUATION = 267, /*[16FE0]*/
jpayne@69 1715 /** @stable ICU 58 */
jpayne@69 1716 UBLOCK_MARCHEN = 268, /*[11C70]*/
jpayne@69 1717 /** @stable ICU 58 */
jpayne@69 1718 UBLOCK_MONGOLIAN_SUPPLEMENT = 269, /*[11660]*/
jpayne@69 1719 /** @stable ICU 58 */
jpayne@69 1720 UBLOCK_NEWA = 270, /*[11400]*/
jpayne@69 1721 /** @stable ICU 58 */
jpayne@69 1722 UBLOCK_OSAGE = 271, /*[104B0]*/
jpayne@69 1723 /** @stable ICU 58 */
jpayne@69 1724 UBLOCK_TANGUT = 272, /*[17000]*/
jpayne@69 1725 /** @stable ICU 58 */
jpayne@69 1726 UBLOCK_TANGUT_COMPONENTS = 273, /*[18800]*/
jpayne@69 1727
jpayne@69 1728 // New blocks in Unicode 10.0
jpayne@69 1729
jpayne@69 1730 /** @stable ICU 60 */
jpayne@69 1731 UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_F = 274, /*[2CEB0]*/
jpayne@69 1732 /** @stable ICU 60 */
jpayne@69 1733 UBLOCK_KANA_EXTENDED_A = 275, /*[1B100]*/
jpayne@69 1734 /** @stable ICU 60 */
jpayne@69 1735 UBLOCK_MASARAM_GONDI = 276, /*[11D00]*/
jpayne@69 1736 /** @stable ICU 60 */
jpayne@69 1737 UBLOCK_NUSHU = 277, /*[1B170]*/
jpayne@69 1738 /** @stable ICU 60 */
jpayne@69 1739 UBLOCK_SOYOMBO = 278, /*[11A50]*/
jpayne@69 1740 /** @stable ICU 60 */
jpayne@69 1741 UBLOCK_SYRIAC_SUPPLEMENT = 279, /*[0860]*/
jpayne@69 1742 /** @stable ICU 60 */
jpayne@69 1743 UBLOCK_ZANABAZAR_SQUARE = 280, /*[11A00]*/
jpayne@69 1744
jpayne@69 1745 // New blocks in Unicode 11.0
jpayne@69 1746
jpayne@69 1747 /** @stable ICU 62 */
jpayne@69 1748 UBLOCK_CHESS_SYMBOLS = 281, /*[1FA00]*/
jpayne@69 1749 /** @stable ICU 62 */
jpayne@69 1750 UBLOCK_DOGRA = 282, /*[11800]*/
jpayne@69 1751 /** @stable ICU 62 */
jpayne@69 1752 UBLOCK_GEORGIAN_EXTENDED = 283, /*[1C90]*/
jpayne@69 1753 /** @stable ICU 62 */
jpayne@69 1754 UBLOCK_GUNJALA_GONDI = 284, /*[11D60]*/
jpayne@69 1755 /** @stable ICU 62 */
jpayne@69 1756 UBLOCK_HANIFI_ROHINGYA = 285, /*[10D00]*/
jpayne@69 1757 /** @stable ICU 62 */
jpayne@69 1758 UBLOCK_INDIC_SIYAQ_NUMBERS = 286, /*[1EC70]*/
jpayne@69 1759 /** @stable ICU 62 */
jpayne@69 1760 UBLOCK_MAKASAR = 287, /*[11EE0]*/
jpayne@69 1761 /** @stable ICU 62 */
jpayne@69 1762 UBLOCK_MAYAN_NUMERALS = 288, /*[1D2E0]*/
jpayne@69 1763 /** @stable ICU 62 */
jpayne@69 1764 UBLOCK_MEDEFAIDRIN = 289, /*[16E40]*/
jpayne@69 1765 /** @stable ICU 62 */
jpayne@69 1766 UBLOCK_OLD_SOGDIAN = 290, /*[10F00]*/
jpayne@69 1767 /** @stable ICU 62 */
jpayne@69 1768 UBLOCK_SOGDIAN = 291, /*[10F30]*/
jpayne@69 1769
jpayne@69 1770 // New blocks in Unicode 12.0
jpayne@69 1771
jpayne@69 1772 /** @stable ICU 64 */
jpayne@69 1773 UBLOCK_EGYPTIAN_HIEROGLYPH_FORMAT_CONTROLS = 292, /*[13430]*/
jpayne@69 1774 /** @stable ICU 64 */
jpayne@69 1775 UBLOCK_ELYMAIC = 293, /*[10FE0]*/
jpayne@69 1776 /** @stable ICU 64 */
jpayne@69 1777 UBLOCK_NANDINAGARI = 294, /*[119A0]*/
jpayne@69 1778 /** @stable ICU 64 */
jpayne@69 1779 UBLOCK_NYIAKENG_PUACHUE_HMONG = 295, /*[1E100]*/
jpayne@69 1780 /** @stable ICU 64 */
jpayne@69 1781 UBLOCK_OTTOMAN_SIYAQ_NUMBERS = 296, /*[1ED00]*/
jpayne@69 1782 /** @stable ICU 64 */
jpayne@69 1783 UBLOCK_SMALL_KANA_EXTENSION = 297, /*[1B130]*/
jpayne@69 1784 /** @stable ICU 64 */
jpayne@69 1785 UBLOCK_SYMBOLS_AND_PICTOGRAPHS_EXTENDED_A = 298, /*[1FA70]*/
jpayne@69 1786 /** @stable ICU 64 */
jpayne@69 1787 UBLOCK_TAMIL_SUPPLEMENT = 299, /*[11FC0]*/
jpayne@69 1788 /** @stable ICU 64 */
jpayne@69 1789 UBLOCK_WANCHO = 300, /*[1E2C0]*/
jpayne@69 1790
jpayne@69 1791 // New blocks in Unicode 13.0
jpayne@69 1792
jpayne@69 1793 /** @stable ICU 66 */
jpayne@69 1794 UBLOCK_CHORASMIAN = 301, /*[10FB0]*/
jpayne@69 1795 /** @stable ICU 66 */
jpayne@69 1796 UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_G = 302, /*[30000]*/
jpayne@69 1797 /** @stable ICU 66 */
jpayne@69 1798 UBLOCK_DIVES_AKURU = 303, /*[11900]*/
jpayne@69 1799 /** @stable ICU 66 */
jpayne@69 1800 UBLOCK_KHITAN_SMALL_SCRIPT = 304, /*[18B00]*/
jpayne@69 1801 /** @stable ICU 66 */
jpayne@69 1802 UBLOCK_LISU_SUPPLEMENT = 305, /*[11FB0]*/
jpayne@69 1803 /** @stable ICU 66 */
jpayne@69 1804 UBLOCK_SYMBOLS_FOR_LEGACY_COMPUTING = 306, /*[1FB00]*/
jpayne@69 1805 /** @stable ICU 66 */
jpayne@69 1806 UBLOCK_TANGUT_SUPPLEMENT = 307, /*[18D00]*/
jpayne@69 1807 /** @stable ICU 66 */
jpayne@69 1808 UBLOCK_YEZIDI = 308, /*[10E80]*/
jpayne@69 1809
jpayne@69 1810 #ifndef U_HIDE_DEPRECATED_API
jpayne@69 1811 /**
jpayne@69 1812 * One more than the highest normal UBlockCode value.
jpayne@69 1813 * The highest value is available via u_getIntPropertyMaxValue(UCHAR_BLOCK).
jpayne@69 1814 *
jpayne@69 1815 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420.
jpayne@69 1816 */
jpayne@69 1817 UBLOCK_COUNT = 309,
jpayne@69 1818 #endif // U_HIDE_DEPRECATED_API
jpayne@69 1819
jpayne@69 1820 /** @stable ICU 2.0 */
jpayne@69 1821 UBLOCK_INVALID_CODE=-1
jpayne@69 1822 };
jpayne@69 1823
jpayne@69 1824 /** @stable ICU 2.0 */
jpayne@69 1825 typedef enum UBlockCode UBlockCode;
jpayne@69 1826
jpayne@69 1827 /**
jpayne@69 1828 * East Asian Width constants.
jpayne@69 1829 *
jpayne@69 1830 * @see UCHAR_EAST_ASIAN_WIDTH
jpayne@69 1831 * @see u_getIntPropertyValue
jpayne@69 1832 * @stable ICU 2.2
jpayne@69 1833 */
jpayne@69 1834 typedef enum UEastAsianWidth {
jpayne@69 1835 /*
jpayne@69 1836 * Note: UEastAsianWidth constants are parsed by preparseucd.py.
jpayne@69 1837 * It matches lines like
jpayne@69 1838 * U_EA_<Unicode East_Asian_Width value name>
jpayne@69 1839 */
jpayne@69 1840
jpayne@69 1841 U_EA_NEUTRAL, /*[N]*/
jpayne@69 1842 U_EA_AMBIGUOUS, /*[A]*/
jpayne@69 1843 U_EA_HALFWIDTH, /*[H]*/
jpayne@69 1844 U_EA_FULLWIDTH, /*[F]*/
jpayne@69 1845 U_EA_NARROW, /*[Na]*/
jpayne@69 1846 U_EA_WIDE, /*[W]*/
jpayne@69 1847 #ifndef U_HIDE_DEPRECATED_API
jpayne@69 1848 /**
jpayne@69 1849 * One more than the highest normal UEastAsianWidth value.
jpayne@69 1850 * The highest value is available via u_getIntPropertyMaxValue(UCHAR_EAST_ASIAN_WIDTH).
jpayne@69 1851 *
jpayne@69 1852 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420.
jpayne@69 1853 */
jpayne@69 1854 U_EA_COUNT
jpayne@69 1855 #endif // U_HIDE_DEPRECATED_API
jpayne@69 1856 } UEastAsianWidth;
jpayne@69 1857
jpayne@69 1858 /**
jpayne@69 1859 * Selector constants for u_charName().
jpayne@69 1860 * u_charName() returns the "modern" name of a
jpayne@69 1861 * Unicode character; or the name that was defined in
jpayne@69 1862 * Unicode version 1.0, before the Unicode standard merged
jpayne@69 1863 * with ISO-10646; or an "extended" name that gives each
jpayne@69 1864 * Unicode code point a unique name.
jpayne@69 1865 *
jpayne@69 1866 * @see u_charName
jpayne@69 1867 * @stable ICU 2.0
jpayne@69 1868 */
jpayne@69 1869 typedef enum UCharNameChoice {
jpayne@69 1870 /** Unicode character name (Name property). @stable ICU 2.0 */
jpayne@69 1871 U_UNICODE_CHAR_NAME,
jpayne@69 1872 #ifndef U_HIDE_DEPRECATED_API
jpayne@69 1873 /**
jpayne@69 1874 * The Unicode_1_Name property value which is of little practical value.
jpayne@69 1875 * Beginning with ICU 49, ICU APIs return an empty string for this name choice.
jpayne@69 1876 * @deprecated ICU 49
jpayne@69 1877 */
jpayne@69 1878 U_UNICODE_10_CHAR_NAME,
jpayne@69 1879 #endif /* U_HIDE_DEPRECATED_API */
jpayne@69 1880 /** Standard or synthetic character name. @stable ICU 2.0 */
jpayne@69 1881 U_EXTENDED_CHAR_NAME = U_UNICODE_CHAR_NAME+2,
jpayne@69 1882 /** Corrected name from NameAliases.txt. @stable ICU 4.4 */
jpayne@69 1883 U_CHAR_NAME_ALIAS,
jpayne@69 1884 #ifndef U_HIDE_DEPRECATED_API
jpayne@69 1885 /**
jpayne@69 1886 * One more than the highest normal UCharNameChoice value.
jpayne@69 1887 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420.
jpayne@69 1888 */
jpayne@69 1889 U_CHAR_NAME_CHOICE_COUNT
jpayne@69 1890 #endif // U_HIDE_DEPRECATED_API
jpayne@69 1891 } UCharNameChoice;
jpayne@69 1892
jpayne@69 1893 /**
jpayne@69 1894 * Selector constants for u_getPropertyName() and
jpayne@69 1895 * u_getPropertyValueName(). These selectors are used to choose which
jpayne@69 1896 * name is returned for a given property or value. All properties and
jpayne@69 1897 * values have a long name. Most have a short name, but some do not.
jpayne@69 1898 * Unicode allows for additional names, beyond the long and short
jpayne@69 1899 * name, which would be indicated by U_LONG_PROPERTY_NAME + i, where
jpayne@69 1900 * i=1, 2,...
jpayne@69 1901 *
jpayne@69 1902 * @see u_getPropertyName()
jpayne@69 1903 * @see u_getPropertyValueName()
jpayne@69 1904 * @stable ICU 2.4
jpayne@69 1905 */
jpayne@69 1906 typedef enum UPropertyNameChoice {
jpayne@69 1907 U_SHORT_PROPERTY_NAME,
jpayne@69 1908 U_LONG_PROPERTY_NAME,
jpayne@69 1909 #ifndef U_HIDE_DEPRECATED_API
jpayne@69 1910 /**
jpayne@69 1911 * One more than the highest normal UPropertyNameChoice value.
jpayne@69 1912 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420.
jpayne@69 1913 */
jpayne@69 1914 U_PROPERTY_NAME_CHOICE_COUNT
jpayne@69 1915 #endif // U_HIDE_DEPRECATED_API
jpayne@69 1916 } UPropertyNameChoice;
jpayne@69 1917
jpayne@69 1918 /**
jpayne@69 1919 * Decomposition Type constants.
jpayne@69 1920 *
jpayne@69 1921 * @see UCHAR_DECOMPOSITION_TYPE
jpayne@69 1922 * @stable ICU 2.2
jpayne@69 1923 */
jpayne@69 1924 typedef enum UDecompositionType {
jpayne@69 1925 /*
jpayne@69 1926 * Note: UDecompositionType constants are parsed by preparseucd.py.
jpayne@69 1927 * It matches lines like
jpayne@69 1928 * U_DT_<Unicode Decomposition_Type value name>
jpayne@69 1929 */
jpayne@69 1930
jpayne@69 1931 U_DT_NONE, /*[none]*/
jpayne@69 1932 U_DT_CANONICAL, /*[can]*/
jpayne@69 1933 U_DT_COMPAT, /*[com]*/
jpayne@69 1934 U_DT_CIRCLE, /*[enc]*/
jpayne@69 1935 U_DT_FINAL, /*[fin]*/
jpayne@69 1936 U_DT_FONT, /*[font]*/
jpayne@69 1937 U_DT_FRACTION, /*[fra]*/
jpayne@69 1938 U_DT_INITIAL, /*[init]*/
jpayne@69 1939 U_DT_ISOLATED, /*[iso]*/
jpayne@69 1940 U_DT_MEDIAL, /*[med]*/
jpayne@69 1941 U_DT_NARROW, /*[nar]*/
jpayne@69 1942 U_DT_NOBREAK, /*[nb]*/
jpayne@69 1943 U_DT_SMALL, /*[sml]*/
jpayne@69 1944 U_DT_SQUARE, /*[sqr]*/
jpayne@69 1945 U_DT_SUB, /*[sub]*/
jpayne@69 1946 U_DT_SUPER, /*[sup]*/
jpayne@69 1947 U_DT_VERTICAL, /*[vert]*/
jpayne@69 1948 U_DT_WIDE, /*[wide]*/
jpayne@69 1949 #ifndef U_HIDE_DEPRECATED_API
jpayne@69 1950 /**
jpayne@69 1951 * One more than the highest normal UDecompositionType value.
jpayne@69 1952 * The highest value is available via u_getIntPropertyMaxValue(UCHAR_DECOMPOSITION_TYPE).
jpayne@69 1953 *
jpayne@69 1954 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420.
jpayne@69 1955 */
jpayne@69 1956 U_DT_COUNT /* 18 */
jpayne@69 1957 #endif // U_HIDE_DEPRECATED_API
jpayne@69 1958 } UDecompositionType;
jpayne@69 1959
jpayne@69 1960 /**
jpayne@69 1961 * Joining Type constants.
jpayne@69 1962 *
jpayne@69 1963 * @see UCHAR_JOINING_TYPE
jpayne@69 1964 * @stable ICU 2.2
jpayne@69 1965 */
jpayne@69 1966 typedef enum UJoiningType {
jpayne@69 1967 /*
jpayne@69 1968 * Note: UJoiningType constants are parsed by preparseucd.py.
jpayne@69 1969 * It matches lines like
jpayne@69 1970 * U_JT_<Unicode Joining_Type value name>
jpayne@69 1971 */
jpayne@69 1972
jpayne@69 1973 U_JT_NON_JOINING, /*[U]*/
jpayne@69 1974 U_JT_JOIN_CAUSING, /*[C]*/
jpayne@69 1975 U_JT_DUAL_JOINING, /*[D]*/
jpayne@69 1976 U_JT_LEFT_JOINING, /*[L]*/
jpayne@69 1977 U_JT_RIGHT_JOINING, /*[R]*/
jpayne@69 1978 U_JT_TRANSPARENT, /*[T]*/
jpayne@69 1979 #ifndef U_HIDE_DEPRECATED_API
jpayne@69 1980 /**
jpayne@69 1981 * One more than the highest normal UJoiningType value.
jpayne@69 1982 * The highest value is available via u_getIntPropertyMaxValue(UCHAR_JOINING_TYPE).
jpayne@69 1983 *
jpayne@69 1984 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420.
jpayne@69 1985 */
jpayne@69 1986 U_JT_COUNT /* 6 */
jpayne@69 1987 #endif // U_HIDE_DEPRECATED_API
jpayne@69 1988 } UJoiningType;
jpayne@69 1989
jpayne@69 1990 /**
jpayne@69 1991 * Joining Group constants.
jpayne@69 1992 *
jpayne@69 1993 * @see UCHAR_JOINING_GROUP
jpayne@69 1994 * @stable ICU 2.2
jpayne@69 1995 */
jpayne@69 1996 typedef enum UJoiningGroup {
jpayne@69 1997 /*
jpayne@69 1998 * Note: UJoiningGroup constants are parsed by preparseucd.py.
jpayne@69 1999 * It matches lines like
jpayne@69 2000 * U_JG_<Unicode Joining_Group value name>
jpayne@69 2001 */
jpayne@69 2002
jpayne@69 2003 U_JG_NO_JOINING_GROUP,
jpayne@69 2004 U_JG_AIN,
jpayne@69 2005 U_JG_ALAPH,
jpayne@69 2006 U_JG_ALEF,
jpayne@69 2007 U_JG_BEH,
jpayne@69 2008 U_JG_BETH,
jpayne@69 2009 U_JG_DAL,
jpayne@69 2010 U_JG_DALATH_RISH,
jpayne@69 2011 U_JG_E,
jpayne@69 2012 U_JG_FEH,
jpayne@69 2013 U_JG_FINAL_SEMKATH,
jpayne@69 2014 U_JG_GAF,
jpayne@69 2015 U_JG_GAMAL,
jpayne@69 2016 U_JG_HAH,
jpayne@69 2017 U_JG_TEH_MARBUTA_GOAL, /**< @stable ICU 4.6 */
jpayne@69 2018 U_JG_HAMZA_ON_HEH_GOAL=U_JG_TEH_MARBUTA_GOAL,
jpayne@69 2019 U_JG_HE,
jpayne@69 2020 U_JG_HEH,
jpayne@69 2021 U_JG_HEH_GOAL,
jpayne@69 2022 U_JG_HETH,
jpayne@69 2023 U_JG_KAF,
jpayne@69 2024 U_JG_KAPH,
jpayne@69 2025 U_JG_KNOTTED_HEH,
jpayne@69 2026 U_JG_LAM,
jpayne@69 2027 U_JG_LAMADH,
jpayne@69 2028 U_JG_MEEM,
jpayne@69 2029 U_JG_MIM,
jpayne@69 2030 U_JG_NOON,
jpayne@69 2031 U_JG_NUN,
jpayne@69 2032 U_JG_PE,
jpayne@69 2033 U_JG_QAF,
jpayne@69 2034 U_JG_QAPH,
jpayne@69 2035 U_JG_REH,
jpayne@69 2036 U_JG_REVERSED_PE,
jpayne@69 2037 U_JG_SAD,
jpayne@69 2038 U_JG_SADHE,
jpayne@69 2039 U_JG_SEEN,
jpayne@69 2040 U_JG_SEMKATH,
jpayne@69 2041 U_JG_SHIN,
jpayne@69 2042 U_JG_SWASH_KAF,
jpayne@69 2043 U_JG_SYRIAC_WAW,
jpayne@69 2044 U_JG_TAH,
jpayne@69 2045 U_JG_TAW,
jpayne@69 2046 U_JG_TEH_MARBUTA,
jpayne@69 2047 U_JG_TETH,
jpayne@69 2048 U_JG_WAW,
jpayne@69 2049 U_JG_YEH,
jpayne@69 2050 U_JG_YEH_BARREE,
jpayne@69 2051 U_JG_YEH_WITH_TAIL,
jpayne@69 2052 U_JG_YUDH,
jpayne@69 2053 U_JG_YUDH_HE,
jpayne@69 2054 U_JG_ZAIN,
jpayne@69 2055 U_JG_FE, /**< @stable ICU 2.6 */
jpayne@69 2056 U_JG_KHAPH, /**< @stable ICU 2.6 */
jpayne@69 2057 U_JG_ZHAIN, /**< @stable ICU 2.6 */
jpayne@69 2058 U_JG_BURUSHASKI_YEH_BARREE, /**< @stable ICU 4.0 */
jpayne@69 2059 U_JG_FARSI_YEH, /**< @stable ICU 4.4 */
jpayne@69 2060 U_JG_NYA, /**< @stable ICU 4.4 */
jpayne@69 2061 U_JG_ROHINGYA_YEH, /**< @stable ICU 49 */
jpayne@69 2062 U_JG_MANICHAEAN_ALEPH, /**< @stable ICU 54 */
jpayne@69 2063 U_JG_MANICHAEAN_AYIN, /**< @stable ICU 54 */
jpayne@69 2064 U_JG_MANICHAEAN_BETH, /**< @stable ICU 54 */
jpayne@69 2065 U_JG_MANICHAEAN_DALETH, /**< @stable ICU 54 */
jpayne@69 2066 U_JG_MANICHAEAN_DHAMEDH, /**< @stable ICU 54 */
jpayne@69 2067 U_JG_MANICHAEAN_FIVE, /**< @stable ICU 54 */
jpayne@69 2068 U_JG_MANICHAEAN_GIMEL, /**< @stable ICU 54 */
jpayne@69 2069 U_JG_MANICHAEAN_HETH, /**< @stable ICU 54 */
jpayne@69 2070 U_JG_MANICHAEAN_HUNDRED, /**< @stable ICU 54 */
jpayne@69 2071 U_JG_MANICHAEAN_KAPH, /**< @stable ICU 54 */
jpayne@69 2072 U_JG_MANICHAEAN_LAMEDH, /**< @stable ICU 54 */
jpayne@69 2073 U_JG_MANICHAEAN_MEM, /**< @stable ICU 54 */
jpayne@69 2074 U_JG_MANICHAEAN_NUN, /**< @stable ICU 54 */
jpayne@69 2075 U_JG_MANICHAEAN_ONE, /**< @stable ICU 54 */
jpayne@69 2076 U_JG_MANICHAEAN_PE, /**< @stable ICU 54 */
jpayne@69 2077 U_JG_MANICHAEAN_QOPH, /**< @stable ICU 54 */
jpayne@69 2078 U_JG_MANICHAEAN_RESH, /**< @stable ICU 54 */
jpayne@69 2079 U_JG_MANICHAEAN_SADHE, /**< @stable ICU 54 */
jpayne@69 2080 U_JG_MANICHAEAN_SAMEKH, /**< @stable ICU 54 */
jpayne@69 2081 U_JG_MANICHAEAN_TAW, /**< @stable ICU 54 */
jpayne@69 2082 U_JG_MANICHAEAN_TEN, /**< @stable ICU 54 */
jpayne@69 2083 U_JG_MANICHAEAN_TETH, /**< @stable ICU 54 */
jpayne@69 2084 U_JG_MANICHAEAN_THAMEDH, /**< @stable ICU 54 */
jpayne@69 2085 U_JG_MANICHAEAN_TWENTY, /**< @stable ICU 54 */
jpayne@69 2086 U_JG_MANICHAEAN_WAW, /**< @stable ICU 54 */
jpayne@69 2087 U_JG_MANICHAEAN_YODH, /**< @stable ICU 54 */
jpayne@69 2088 U_JG_MANICHAEAN_ZAYIN, /**< @stable ICU 54 */
jpayne@69 2089 U_JG_STRAIGHT_WAW, /**< @stable ICU 54 */
jpayne@69 2090 U_JG_AFRICAN_FEH, /**< @stable ICU 58 */
jpayne@69 2091 U_JG_AFRICAN_NOON, /**< @stable ICU 58 */
jpayne@69 2092 U_JG_AFRICAN_QAF, /**< @stable ICU 58 */
jpayne@69 2093
jpayne@69 2094 U_JG_MALAYALAM_BHA, /**< @stable ICU 60 */
jpayne@69 2095 U_JG_MALAYALAM_JA, /**< @stable ICU 60 */
jpayne@69 2096 U_JG_MALAYALAM_LLA, /**< @stable ICU 60 */
jpayne@69 2097 U_JG_MALAYALAM_LLLA, /**< @stable ICU 60 */
jpayne@69 2098 U_JG_MALAYALAM_NGA, /**< @stable ICU 60 */
jpayne@69 2099 U_JG_MALAYALAM_NNA, /**< @stable ICU 60 */
jpayne@69 2100 U_JG_MALAYALAM_NNNA, /**< @stable ICU 60 */
jpayne@69 2101 U_JG_MALAYALAM_NYA, /**< @stable ICU 60 */
jpayne@69 2102 U_JG_MALAYALAM_RA, /**< @stable ICU 60 */
jpayne@69 2103 U_JG_MALAYALAM_SSA, /**< @stable ICU 60 */
jpayne@69 2104 U_JG_MALAYALAM_TTA, /**< @stable ICU 60 */
jpayne@69 2105
jpayne@69 2106 U_JG_HANIFI_ROHINGYA_KINNA_YA, /**< @stable ICU 62 */
jpayne@69 2107 U_JG_HANIFI_ROHINGYA_PA, /**< @stable ICU 62 */
jpayne@69 2108
jpayne@69 2109 #ifndef U_HIDE_DEPRECATED_API
jpayne@69 2110 /**
jpayne@69 2111 * One more than the highest normal UJoiningGroup value.
jpayne@69 2112 * The highest value is available via u_getIntPropertyMaxValue(UCHAR_JOINING_GROUP).
jpayne@69 2113 *
jpayne@69 2114 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420.
jpayne@69 2115 */
jpayne@69 2116 U_JG_COUNT
jpayne@69 2117 #endif // U_HIDE_DEPRECATED_API
jpayne@69 2118 } UJoiningGroup;
jpayne@69 2119
jpayne@69 2120 /**
jpayne@69 2121 * Grapheme Cluster Break constants.
jpayne@69 2122 *
jpayne@69 2123 * @see UCHAR_GRAPHEME_CLUSTER_BREAK
jpayne@69 2124 * @stable ICU 3.4
jpayne@69 2125 */
jpayne@69 2126 typedef enum UGraphemeClusterBreak {
jpayne@69 2127 /*
jpayne@69 2128 * Note: UGraphemeClusterBreak constants are parsed by preparseucd.py.
jpayne@69 2129 * It matches lines like
jpayne@69 2130 * U_GCB_<Unicode Grapheme_Cluster_Break value name>
jpayne@69 2131 */
jpayne@69 2132
jpayne@69 2133 U_GCB_OTHER = 0, /*[XX]*/
jpayne@69 2134 U_GCB_CONTROL = 1, /*[CN]*/
jpayne@69 2135 U_GCB_CR = 2, /*[CR]*/
jpayne@69 2136 U_GCB_EXTEND = 3, /*[EX]*/
jpayne@69 2137 U_GCB_L = 4, /*[L]*/
jpayne@69 2138 U_GCB_LF = 5, /*[LF]*/
jpayne@69 2139 U_GCB_LV = 6, /*[LV]*/
jpayne@69 2140 U_GCB_LVT = 7, /*[LVT]*/
jpayne@69 2141 U_GCB_T = 8, /*[T]*/
jpayne@69 2142 U_GCB_V = 9, /*[V]*/
jpayne@69 2143 /** @stable ICU 4.0 */
jpayne@69 2144 U_GCB_SPACING_MARK = 10, /*[SM]*/ /* from here on: new in Unicode 5.1/ICU 4.0 */
jpayne@69 2145 /** @stable ICU 4.0 */
jpayne@69 2146 U_GCB_PREPEND = 11, /*[PP]*/
jpayne@69 2147 /** @stable ICU 50 */
jpayne@69 2148 U_GCB_REGIONAL_INDICATOR = 12, /*[RI]*/ /* new in Unicode 6.2/ICU 50 */
jpayne@69 2149 /** @stable ICU 58 */
jpayne@69 2150 U_GCB_E_BASE = 13, /*[EB]*/ /* from here on: new in Unicode 9.0/ICU 58 */
jpayne@69 2151 /** @stable ICU 58 */
jpayne@69 2152 U_GCB_E_BASE_GAZ = 14, /*[EBG]*/
jpayne@69 2153 /** @stable ICU 58 */
jpayne@69 2154 U_GCB_E_MODIFIER = 15, /*[EM]*/
jpayne@69 2155 /** @stable ICU 58 */
jpayne@69 2156 U_GCB_GLUE_AFTER_ZWJ = 16, /*[GAZ]*/
jpayne@69 2157 /** @stable ICU 58 */
jpayne@69 2158 U_GCB_ZWJ = 17, /*[ZWJ]*/
jpayne@69 2159
jpayne@69 2160 #ifndef U_HIDE_DEPRECATED_API
jpayne@69 2161 /**
jpayne@69 2162 * One more than the highest normal UGraphemeClusterBreak value.
jpayne@69 2163 * The highest value is available via u_getIntPropertyMaxValue(UCHAR_GRAPHEME_CLUSTER_BREAK).
jpayne@69 2164 *
jpayne@69 2165 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420.
jpayne@69 2166 */
jpayne@69 2167 U_GCB_COUNT = 18
jpayne@69 2168 #endif // U_HIDE_DEPRECATED_API
jpayne@69 2169 } UGraphemeClusterBreak;
jpayne@69 2170
jpayne@69 2171 /**
jpayne@69 2172 * Word Break constants.
jpayne@69 2173 * (UWordBreak is a pre-existing enum type in ubrk.h for word break status tags.)
jpayne@69 2174 *
jpayne@69 2175 * @see UCHAR_WORD_BREAK
jpayne@69 2176 * @stable ICU 3.4
jpayne@69 2177 */
jpayne@69 2178 typedef enum UWordBreakValues {
jpayne@69 2179 /*
jpayne@69 2180 * Note: UWordBreakValues constants are parsed by preparseucd.py.
jpayne@69 2181 * It matches lines like
jpayne@69 2182 * U_WB_<Unicode Word_Break value name>
jpayne@69 2183 */
jpayne@69 2184
jpayne@69 2185 U_WB_OTHER = 0, /*[XX]*/
jpayne@69 2186 U_WB_ALETTER = 1, /*[LE]*/
jpayne@69 2187 U_WB_FORMAT = 2, /*[FO]*/
jpayne@69 2188 U_WB_KATAKANA = 3, /*[KA]*/
jpayne@69 2189 U_WB_MIDLETTER = 4, /*[ML]*/
jpayne@69 2190 U_WB_MIDNUM = 5, /*[MN]*/
jpayne@69 2191 U_WB_NUMERIC = 6, /*[NU]*/
jpayne@69 2192 U_WB_EXTENDNUMLET = 7, /*[EX]*/
jpayne@69 2193 /** @stable ICU 4.0 */
jpayne@69 2194 U_WB_CR = 8, /*[CR]*/ /* from here on: new in Unicode 5.1/ICU 4.0 */
jpayne@69 2195 /** @stable ICU 4.0 */
jpayne@69 2196 U_WB_EXTEND = 9, /*[Extend]*/
jpayne@69 2197 /** @stable ICU 4.0 */
jpayne@69 2198 U_WB_LF = 10, /*[LF]*/
jpayne@69 2199 /** @stable ICU 4.0 */
jpayne@69 2200 U_WB_MIDNUMLET =11, /*[MB]*/
jpayne@69 2201 /** @stable ICU 4.0 */
jpayne@69 2202 U_WB_NEWLINE =12, /*[NL]*/
jpayne@69 2203 /** @stable ICU 50 */
jpayne@69 2204 U_WB_REGIONAL_INDICATOR = 13, /*[RI]*/ /* new in Unicode 6.2/ICU 50 */
jpayne@69 2205 /** @stable ICU 52 */
jpayne@69 2206 U_WB_HEBREW_LETTER = 14, /*[HL]*/ /* from here on: new in Unicode 6.3/ICU 52 */
jpayne@69 2207 /** @stable ICU 52 */
jpayne@69 2208 U_WB_SINGLE_QUOTE = 15, /*[SQ]*/
jpayne@69 2209 /** @stable ICU 52 */
jpayne@69 2210 U_WB_DOUBLE_QUOTE = 16, /*[DQ]*/
jpayne@69 2211 /** @stable ICU 58 */
jpayne@69 2212 U_WB_E_BASE = 17, /*[EB]*/ /* from here on: new in Unicode 9.0/ICU 58 */
jpayne@69 2213 /** @stable ICU 58 */
jpayne@69 2214 U_WB_E_BASE_GAZ = 18, /*[EBG]*/
jpayne@69 2215 /** @stable ICU 58 */
jpayne@69 2216 U_WB_E_MODIFIER = 19, /*[EM]*/
jpayne@69 2217 /** @stable ICU 58 */
jpayne@69 2218 U_WB_GLUE_AFTER_ZWJ = 20, /*[GAZ]*/
jpayne@69 2219 /** @stable ICU 58 */
jpayne@69 2220 U_WB_ZWJ = 21, /*[ZWJ]*/
jpayne@69 2221 /** @stable ICU 62 */
jpayne@69 2222 U_WB_WSEGSPACE = 22, /*[WSEGSPACE]*/
jpayne@69 2223
jpayne@69 2224 #ifndef U_HIDE_DEPRECATED_API
jpayne@69 2225 /**
jpayne@69 2226 * One more than the highest normal UWordBreakValues value.
jpayne@69 2227 * The highest value is available via u_getIntPropertyMaxValue(UCHAR_WORD_BREAK).
jpayne@69 2228 *
jpayne@69 2229 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420.
jpayne@69 2230 */
jpayne@69 2231 U_WB_COUNT = 23
jpayne@69 2232 #endif // U_HIDE_DEPRECATED_API
jpayne@69 2233 } UWordBreakValues;
jpayne@69 2234
jpayne@69 2235 /**
jpayne@69 2236 * Sentence Break constants.
jpayne@69 2237 *
jpayne@69 2238 * @see UCHAR_SENTENCE_BREAK
jpayne@69 2239 * @stable ICU 3.4
jpayne@69 2240 */
jpayne@69 2241 typedef enum USentenceBreak {
jpayne@69 2242 /*
jpayne@69 2243 * Note: USentenceBreak constants are parsed by preparseucd.py.
jpayne@69 2244 * It matches lines like
jpayne@69 2245 * U_SB_<Unicode Sentence_Break value name>
jpayne@69 2246 */
jpayne@69 2247
jpayne@69 2248 U_SB_OTHER = 0, /*[XX]*/
jpayne@69 2249 U_SB_ATERM = 1, /*[AT]*/
jpayne@69 2250 U_SB_CLOSE = 2, /*[CL]*/
jpayne@69 2251 U_SB_FORMAT = 3, /*[FO]*/
jpayne@69 2252 U_SB_LOWER = 4, /*[LO]*/
jpayne@69 2253 U_SB_NUMERIC = 5, /*[NU]*/
jpayne@69 2254 U_SB_OLETTER = 6, /*[LE]*/
jpayne@69 2255 U_SB_SEP = 7, /*[SE]*/
jpayne@69 2256 U_SB_SP = 8, /*[SP]*/
jpayne@69 2257 U_SB_STERM = 9, /*[ST]*/
jpayne@69 2258 U_SB_UPPER = 10, /*[UP]*/
jpayne@69 2259 U_SB_CR = 11, /*[CR]*/ /* from here on: new in Unicode 5.1/ICU 4.0 */
jpayne@69 2260 U_SB_EXTEND = 12, /*[EX]*/
jpayne@69 2261 U_SB_LF = 13, /*[LF]*/
jpayne@69 2262 U_SB_SCONTINUE = 14, /*[SC]*/
jpayne@69 2263 #ifndef U_HIDE_DEPRECATED_API
jpayne@69 2264 /**
jpayne@69 2265 * One more than the highest normal USentenceBreak value.
jpayne@69 2266 * The highest value is available via u_getIntPropertyMaxValue(UCHAR_SENTENCE_BREAK).
jpayne@69 2267 *
jpayne@69 2268 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420.
jpayne@69 2269 */
jpayne@69 2270 U_SB_COUNT = 15
jpayne@69 2271 #endif // U_HIDE_DEPRECATED_API
jpayne@69 2272 } USentenceBreak;
jpayne@69 2273
jpayne@69 2274 /**
jpayne@69 2275 * Line Break constants.
jpayne@69 2276 *
jpayne@69 2277 * @see UCHAR_LINE_BREAK
jpayne@69 2278 * @stable ICU 2.2
jpayne@69 2279 */
jpayne@69 2280 typedef enum ULineBreak {
jpayne@69 2281 /*
jpayne@69 2282 * Note: ULineBreak constants are parsed by preparseucd.py.
jpayne@69 2283 * It matches lines like
jpayne@69 2284 * U_LB_<Unicode Line_Break value name>
jpayne@69 2285 */
jpayne@69 2286
jpayne@69 2287 U_LB_UNKNOWN = 0, /*[XX]*/
jpayne@69 2288 U_LB_AMBIGUOUS = 1, /*[AI]*/
jpayne@69 2289 U_LB_ALPHABETIC = 2, /*[AL]*/
jpayne@69 2290 U_LB_BREAK_BOTH = 3, /*[B2]*/
jpayne@69 2291 U_LB_BREAK_AFTER = 4, /*[BA]*/
jpayne@69 2292 U_LB_BREAK_BEFORE = 5, /*[BB]*/
jpayne@69 2293 U_LB_MANDATORY_BREAK = 6, /*[BK]*/
jpayne@69 2294 U_LB_CONTINGENT_BREAK = 7, /*[CB]*/
jpayne@69 2295 U_LB_CLOSE_PUNCTUATION = 8, /*[CL]*/
jpayne@69 2296 U_LB_COMBINING_MARK = 9, /*[CM]*/
jpayne@69 2297 U_LB_CARRIAGE_RETURN = 10, /*[CR]*/
jpayne@69 2298 U_LB_EXCLAMATION = 11, /*[EX]*/
jpayne@69 2299 U_LB_GLUE = 12, /*[GL]*/
jpayne@69 2300 U_LB_HYPHEN = 13, /*[HY]*/
jpayne@69 2301 U_LB_IDEOGRAPHIC = 14, /*[ID]*/
jpayne@69 2302 /** Renamed from the misspelled "inseperable" in Unicode 4.0.1/ICU 3.0 @stable ICU 3.0 */
jpayne@69 2303 U_LB_INSEPARABLE = 15, /*[IN]*/
jpayne@69 2304 U_LB_INSEPERABLE = U_LB_INSEPARABLE,
jpayne@69 2305 U_LB_INFIX_NUMERIC = 16, /*[IS]*/
jpayne@69 2306 U_LB_LINE_FEED = 17, /*[LF]*/
jpayne@69 2307 U_LB_NONSTARTER = 18, /*[NS]*/
jpayne@69 2308 U_LB_NUMERIC = 19, /*[NU]*/
jpayne@69 2309 U_LB_OPEN_PUNCTUATION = 20, /*[OP]*/
jpayne@69 2310 U_LB_POSTFIX_NUMERIC = 21, /*[PO]*/
jpayne@69 2311 U_LB_PREFIX_NUMERIC = 22, /*[PR]*/
jpayne@69 2312 U_LB_QUOTATION = 23, /*[QU]*/
jpayne@69 2313 U_LB_COMPLEX_CONTEXT = 24, /*[SA]*/
jpayne@69 2314 U_LB_SURROGATE = 25, /*[SG]*/
jpayne@69 2315 U_LB_SPACE = 26, /*[SP]*/
jpayne@69 2316 U_LB_BREAK_SYMBOLS = 27, /*[SY]*/
jpayne@69 2317 U_LB_ZWSPACE = 28, /*[ZW]*/
jpayne@69 2318 /** @stable ICU 2.6 */
jpayne@69 2319 U_LB_NEXT_LINE = 29, /*[NL]*/ /* from here on: new in Unicode 4/ICU 2.6 */
jpayne@69 2320 /** @stable ICU 2.6 */
jpayne@69 2321 U_LB_WORD_JOINER = 30, /*[WJ]*/
jpayne@69 2322 /** @stable ICU 3.4 */
jpayne@69 2323 U_LB_H2 = 31, /*[H2]*/ /* from here on: new in Unicode 4.1/ICU 3.4 */
jpayne@69 2324 /** @stable ICU 3.4 */
jpayne@69 2325 U_LB_H3 = 32, /*[H3]*/
jpayne@69 2326 /** @stable ICU 3.4 */
jpayne@69 2327 U_LB_JL = 33, /*[JL]*/
jpayne@69 2328 /** @stable ICU 3.4 */
jpayne@69 2329 U_LB_JT = 34, /*[JT]*/
jpayne@69 2330 /** @stable ICU 3.4 */
jpayne@69 2331 U_LB_JV = 35, /*[JV]*/
jpayne@69 2332 /** @stable ICU 4.4 */
jpayne@69 2333 U_LB_CLOSE_PARENTHESIS = 36, /*[CP]*/ /* new in Unicode 5.2/ICU 4.4 */
jpayne@69 2334 /** @stable ICU 49 */
jpayne@69 2335 U_LB_CONDITIONAL_JAPANESE_STARTER = 37,/*[CJ]*/ /* new in Unicode 6.1/ICU 49 */
jpayne@69 2336 /** @stable ICU 49 */
jpayne@69 2337 U_LB_HEBREW_LETTER = 38, /*[HL]*/ /* new in Unicode 6.1/ICU 49 */
jpayne@69 2338 /** @stable ICU 50 */
jpayne@69 2339 U_LB_REGIONAL_INDICATOR = 39,/*[RI]*/ /* new in Unicode 6.2/ICU 50 */
jpayne@69 2340 /** @stable ICU 58 */
jpayne@69 2341 U_LB_E_BASE = 40, /*[EB]*/ /* from here on: new in Unicode 9.0/ICU 58 */
jpayne@69 2342 /** @stable ICU 58 */
jpayne@69 2343 U_LB_E_MODIFIER = 41, /*[EM]*/
jpayne@69 2344 /** @stable ICU 58 */
jpayne@69 2345 U_LB_ZWJ = 42, /*[ZWJ]*/
jpayne@69 2346 #ifndef U_HIDE_DEPRECATED_API
jpayne@69 2347 /**
jpayne@69 2348 * One more than the highest normal ULineBreak value.
jpayne@69 2349 * The highest value is available via u_getIntPropertyMaxValue(UCHAR_LINE_BREAK).
jpayne@69 2350 *
jpayne@69 2351 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420.
jpayne@69 2352 */
jpayne@69 2353 U_LB_COUNT = 43
jpayne@69 2354 #endif // U_HIDE_DEPRECATED_API
jpayne@69 2355 } ULineBreak;
jpayne@69 2356
jpayne@69 2357 /**
jpayne@69 2358 * Numeric Type constants.
jpayne@69 2359 *
jpayne@69 2360 * @see UCHAR_NUMERIC_TYPE
jpayne@69 2361 * @stable ICU 2.2
jpayne@69 2362 */
jpayne@69 2363 typedef enum UNumericType {
jpayne@69 2364 /*
jpayne@69 2365 * Note: UNumericType constants are parsed by preparseucd.py.
jpayne@69 2366 * It matches lines like
jpayne@69 2367 * U_NT_<Unicode Numeric_Type value name>
jpayne@69 2368 */
jpayne@69 2369
jpayne@69 2370 U_NT_NONE, /*[None]*/
jpayne@69 2371 U_NT_DECIMAL, /*[de]*/
jpayne@69 2372 U_NT_DIGIT, /*[di]*/
jpayne@69 2373 U_NT_NUMERIC, /*[nu]*/
jpayne@69 2374 #ifndef U_HIDE_DEPRECATED_API
jpayne@69 2375 /**
jpayne@69 2376 * One more than the highest normal UNumericType value.
jpayne@69 2377 * The highest value is available via u_getIntPropertyMaxValue(UCHAR_NUMERIC_TYPE).
jpayne@69 2378 *
jpayne@69 2379 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420.
jpayne@69 2380 */
jpayne@69 2381 U_NT_COUNT
jpayne@69 2382 #endif // U_HIDE_DEPRECATED_API
jpayne@69 2383 } UNumericType;
jpayne@69 2384
jpayne@69 2385 /**
jpayne@69 2386 * Hangul Syllable Type constants.
jpayne@69 2387 *
jpayne@69 2388 * @see UCHAR_HANGUL_SYLLABLE_TYPE
jpayne@69 2389 * @stable ICU 2.6
jpayne@69 2390 */
jpayne@69 2391 typedef enum UHangulSyllableType {
jpayne@69 2392 /*
jpayne@69 2393 * Note: UHangulSyllableType constants are parsed by preparseucd.py.
jpayne@69 2394 * It matches lines like
jpayne@69 2395 * U_HST_<Unicode Hangul_Syllable_Type value name>
jpayne@69 2396 */
jpayne@69 2397
jpayne@69 2398 U_HST_NOT_APPLICABLE, /*[NA]*/
jpayne@69 2399 U_HST_LEADING_JAMO, /*[L]*/
jpayne@69 2400 U_HST_VOWEL_JAMO, /*[V]*/
jpayne@69 2401 U_HST_TRAILING_JAMO, /*[T]*/
jpayne@69 2402 U_HST_LV_SYLLABLE, /*[LV]*/
jpayne@69 2403 U_HST_LVT_SYLLABLE, /*[LVT]*/
jpayne@69 2404 #ifndef U_HIDE_DEPRECATED_API
jpayne@69 2405 /**
jpayne@69 2406 * One more than the highest normal UHangulSyllableType value.
jpayne@69 2407 * The highest value is available via u_getIntPropertyMaxValue(UCHAR_HANGUL_SYLLABLE_TYPE).
jpayne@69 2408 *
jpayne@69 2409 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420.
jpayne@69 2410 */
jpayne@69 2411 U_HST_COUNT
jpayne@69 2412 #endif // U_HIDE_DEPRECATED_API
jpayne@69 2413 } UHangulSyllableType;
jpayne@69 2414
jpayne@69 2415 /**
jpayne@69 2416 * Indic Positional Category constants.
jpayne@69 2417 *
jpayne@69 2418 * @see UCHAR_INDIC_POSITIONAL_CATEGORY
jpayne@69 2419 * @stable ICU 63
jpayne@69 2420 */
jpayne@69 2421 typedef enum UIndicPositionalCategory {
jpayne@69 2422 /*
jpayne@69 2423 * Note: UIndicPositionalCategory constants are parsed by preparseucd.py.
jpayne@69 2424 * It matches lines like
jpayne@69 2425 * U_INPC_<Unicode Indic_Positional_Category value name>
jpayne@69 2426 */
jpayne@69 2427
jpayne@69 2428 /** @stable ICU 63 */
jpayne@69 2429 U_INPC_NA,
jpayne@69 2430 /** @stable ICU 63 */
jpayne@69 2431 U_INPC_BOTTOM,
jpayne@69 2432 /** @stable ICU 63 */
jpayne@69 2433 U_INPC_BOTTOM_AND_LEFT,
jpayne@69 2434 /** @stable ICU 63 */
jpayne@69 2435 U_INPC_BOTTOM_AND_RIGHT,
jpayne@69 2436 /** @stable ICU 63 */
jpayne@69 2437 U_INPC_LEFT,
jpayne@69 2438 /** @stable ICU 63 */
jpayne@69 2439 U_INPC_LEFT_AND_RIGHT,
jpayne@69 2440 /** @stable ICU 63 */
jpayne@69 2441 U_INPC_OVERSTRUCK,
jpayne@69 2442 /** @stable ICU 63 */
jpayne@69 2443 U_INPC_RIGHT,
jpayne@69 2444 /** @stable ICU 63 */
jpayne@69 2445 U_INPC_TOP,
jpayne@69 2446 /** @stable ICU 63 */
jpayne@69 2447 U_INPC_TOP_AND_BOTTOM,
jpayne@69 2448 /** @stable ICU 63 */
jpayne@69 2449 U_INPC_TOP_AND_BOTTOM_AND_RIGHT,
jpayne@69 2450 /** @stable ICU 63 */
jpayne@69 2451 U_INPC_TOP_AND_LEFT,
jpayne@69 2452 /** @stable ICU 63 */
jpayne@69 2453 U_INPC_TOP_AND_LEFT_AND_RIGHT,
jpayne@69 2454 /** @stable ICU 63 */
jpayne@69 2455 U_INPC_TOP_AND_RIGHT,
jpayne@69 2456 /** @stable ICU 63 */
jpayne@69 2457 U_INPC_VISUAL_ORDER_LEFT,
jpayne@69 2458 /** @stable ICU 66 */
jpayne@69 2459 U_INPC_TOP_AND_BOTTOM_AND_LEFT,
jpayne@69 2460 } UIndicPositionalCategory;
jpayne@69 2461
jpayne@69 2462 /**
jpayne@69 2463 * Indic Syllabic Category constants.
jpayne@69 2464 *
jpayne@69 2465 * @see UCHAR_INDIC_SYLLABIC_CATEGORY
jpayne@69 2466 * @stable ICU 63
jpayne@69 2467 */
jpayne@69 2468 typedef enum UIndicSyllabicCategory {
jpayne@69 2469 /*
jpayne@69 2470 * Note: UIndicSyllabicCategory constants are parsed by preparseucd.py.
jpayne@69 2471 * It matches lines like
jpayne@69 2472 * U_INSC_<Unicode Indic_Syllabic_Category value name>
jpayne@69 2473 */
jpayne@69 2474
jpayne@69 2475 /** @stable ICU 63 */
jpayne@69 2476 U_INSC_OTHER,
jpayne@69 2477 /** @stable ICU 63 */
jpayne@69 2478 U_INSC_AVAGRAHA,
jpayne@69 2479 /** @stable ICU 63 */
jpayne@69 2480 U_INSC_BINDU,
jpayne@69 2481 /** @stable ICU 63 */
jpayne@69 2482 U_INSC_BRAHMI_JOINING_NUMBER,
jpayne@69 2483 /** @stable ICU 63 */
jpayne@69 2484 U_INSC_CANTILLATION_MARK,
jpayne@69 2485 /** @stable ICU 63 */
jpayne@69 2486 U_INSC_CONSONANT,
jpayne@69 2487 /** @stable ICU 63 */
jpayne@69 2488 U_INSC_CONSONANT_DEAD,
jpayne@69 2489 /** @stable ICU 63 */
jpayne@69 2490 U_INSC_CONSONANT_FINAL,
jpayne@69 2491 /** @stable ICU 63 */
jpayne@69 2492 U_INSC_CONSONANT_HEAD_LETTER,
jpayne@69 2493 /** @stable ICU 63 */
jpayne@69 2494 U_INSC_CONSONANT_INITIAL_POSTFIXED,
jpayne@69 2495 /** @stable ICU 63 */
jpayne@69 2496 U_INSC_CONSONANT_KILLER,
jpayne@69 2497 /** @stable ICU 63 */
jpayne@69 2498 U_INSC_CONSONANT_MEDIAL,
jpayne@69 2499 /** @stable ICU 63 */
jpayne@69 2500 U_INSC_CONSONANT_PLACEHOLDER,
jpayne@69 2501 /** @stable ICU 63 */
jpayne@69 2502 U_INSC_CONSONANT_PRECEDING_REPHA,
jpayne@69 2503 /** @stable ICU 63 */
jpayne@69 2504 U_INSC_CONSONANT_PREFIXED,
jpayne@69 2505 /** @stable ICU 63 */
jpayne@69 2506 U_INSC_CONSONANT_SUBJOINED,
jpayne@69 2507 /** @stable ICU 63 */
jpayne@69 2508 U_INSC_CONSONANT_SUCCEEDING_REPHA,
jpayne@69 2509 /** @stable ICU 63 */
jpayne@69 2510 U_INSC_CONSONANT_WITH_STACKER,
jpayne@69 2511 /** @stable ICU 63 */
jpayne@69 2512 U_INSC_GEMINATION_MARK,
jpayne@69 2513 /** @stable ICU 63 */
jpayne@69 2514 U_INSC_INVISIBLE_STACKER,
jpayne@69 2515 /** @stable ICU 63 */
jpayne@69 2516 U_INSC_JOINER,
jpayne@69 2517 /** @stable ICU 63 */
jpayne@69 2518 U_INSC_MODIFYING_LETTER,
jpayne@69 2519 /** @stable ICU 63 */
jpayne@69 2520 U_INSC_NON_JOINER,
jpayne@69 2521 /** @stable ICU 63 */
jpayne@69 2522 U_INSC_NUKTA,
jpayne@69 2523 /** @stable ICU 63 */
jpayne@69 2524 U_INSC_NUMBER,
jpayne@69 2525 /** @stable ICU 63 */
jpayne@69 2526 U_INSC_NUMBER_JOINER,
jpayne@69 2527 /** @stable ICU 63 */
jpayne@69 2528 U_INSC_PURE_KILLER,
jpayne@69 2529 /** @stable ICU 63 */
jpayne@69 2530 U_INSC_REGISTER_SHIFTER,
jpayne@69 2531 /** @stable ICU 63 */
jpayne@69 2532 U_INSC_SYLLABLE_MODIFIER,
jpayne@69 2533 /** @stable ICU 63 */
jpayne@69 2534 U_INSC_TONE_LETTER,
jpayne@69 2535 /** @stable ICU 63 */
jpayne@69 2536 U_INSC_TONE_MARK,
jpayne@69 2537 /** @stable ICU 63 */
jpayne@69 2538 U_INSC_VIRAMA,
jpayne@69 2539 /** @stable ICU 63 */
jpayne@69 2540 U_INSC_VISARGA,
jpayne@69 2541 /** @stable ICU 63 */
jpayne@69 2542 U_INSC_VOWEL,
jpayne@69 2543 /** @stable ICU 63 */
jpayne@69 2544 U_INSC_VOWEL_DEPENDENT,
jpayne@69 2545 /** @stable ICU 63 */
jpayne@69 2546 U_INSC_VOWEL_INDEPENDENT,
jpayne@69 2547 } UIndicSyllabicCategory;
jpayne@69 2548
jpayne@69 2549 /**
jpayne@69 2550 * Vertical Orientation constants.
jpayne@69 2551 *
jpayne@69 2552 * @see UCHAR_VERTICAL_ORIENTATION
jpayne@69 2553 * @stable ICU 63
jpayne@69 2554 */
jpayne@69 2555 typedef enum UVerticalOrientation {
jpayne@69 2556 /*
jpayne@69 2557 * Note: UVerticalOrientation constants are parsed by preparseucd.py.
jpayne@69 2558 * It matches lines like
jpayne@69 2559 * U_VO_<Unicode Vertical_Orientation value name>
jpayne@69 2560 */
jpayne@69 2561
jpayne@69 2562 /** @stable ICU 63 */
jpayne@69 2563 U_VO_ROTATED,
jpayne@69 2564 /** @stable ICU 63 */
jpayne@69 2565 U_VO_TRANSFORMED_ROTATED,
jpayne@69 2566 /** @stable ICU 63 */
jpayne@69 2567 U_VO_TRANSFORMED_UPRIGHT,
jpayne@69 2568 /** @stable ICU 63 */
jpayne@69 2569 U_VO_UPRIGHT,
jpayne@69 2570 } UVerticalOrientation;
jpayne@69 2571
jpayne@69 2572 /**
jpayne@69 2573 * Check a binary Unicode property for a code point.
jpayne@69 2574 *
jpayne@69 2575 * Unicode, especially in version 3.2, defines many more properties than the
jpayne@69 2576 * original set in UnicodeData.txt.
jpayne@69 2577 *
jpayne@69 2578 * The properties APIs are intended to reflect Unicode properties as defined
jpayne@69 2579 * in the Unicode Character Database (UCD) and Unicode Technical Reports (UTR).
jpayne@69 2580 * For details about the properties see http://www.unicode.org/ucd/ .
jpayne@69 2581 * For names of Unicode properties see the UCD file PropertyAliases.txt.
jpayne@69 2582 *
jpayne@69 2583 * Important: If ICU is built with UCD files from Unicode versions below 3.2,
jpayne@69 2584 * then properties marked with "new in Unicode 3.2" are not or not fully available.
jpayne@69 2585 *
jpayne@69 2586 * @param c Code point to test.
jpayne@69 2587 * @param which UProperty selector constant, identifies which binary property to check.
jpayne@69 2588 * Must be UCHAR_BINARY_START<=which<UCHAR_BINARY_LIMIT.
jpayne@69 2589 * @return TRUE or FALSE according to the binary Unicode property value for c.
jpayne@69 2590 * Also FALSE if 'which' is out of bounds or if the Unicode version
jpayne@69 2591 * does not have data for the property at all, or not for this code point.
jpayne@69 2592 *
jpayne@69 2593 * @see UProperty
jpayne@69 2594 * @see u_getBinaryPropertySet
jpayne@69 2595 * @see u_getIntPropertyValue
jpayne@69 2596 * @see u_getUnicodeVersion
jpayne@69 2597 * @stable ICU 2.1
jpayne@69 2598 */
jpayne@69 2599 U_STABLE UBool U_EXPORT2
jpayne@69 2600 u_hasBinaryProperty(UChar32 c, UProperty which);
jpayne@69 2601
jpayne@69 2602 /**
jpayne@69 2603 * Returns a frozen USet for a binary property.
jpayne@69 2604 * The library retains ownership over the returned object.
jpayne@69 2605 * Sets an error code if the property number is not one for a binary property.
jpayne@69 2606 *
jpayne@69 2607 * The returned set contains all code points for which the property is true.
jpayne@69 2608 *
jpayne@69 2609 * @param property UCHAR_BINARY_START..UCHAR_BINARY_LIMIT-1
jpayne@69 2610 * @param pErrorCode an in/out ICU UErrorCode
jpayne@69 2611 * @return the property as a set
jpayne@69 2612 * @see UProperty
jpayne@69 2613 * @see u_hasBinaryProperty
jpayne@69 2614 * @see Unicode::fromUSet
jpayne@69 2615 * @stable ICU 63
jpayne@69 2616 */
jpayne@69 2617 U_CAPI const USet * U_EXPORT2
jpayne@69 2618 u_getBinaryPropertySet(UProperty property, UErrorCode *pErrorCode);
jpayne@69 2619
jpayne@69 2620 /**
jpayne@69 2621 * Check if a code point has the Alphabetic Unicode property.
jpayne@69 2622 * Same as u_hasBinaryProperty(c, UCHAR_ALPHABETIC).
jpayne@69 2623 * This is different from u_isalpha!
jpayne@69 2624 * @param c Code point to test
jpayne@69 2625 * @return true if the code point has the Alphabetic Unicode property, false otherwise
jpayne@69 2626 *
jpayne@69 2627 * @see UCHAR_ALPHABETIC
jpayne@69 2628 * @see u_isalpha
jpayne@69 2629 * @see u_hasBinaryProperty
jpayne@69 2630 * @stable ICU 2.1
jpayne@69 2631 */
jpayne@69 2632 U_STABLE UBool U_EXPORT2
jpayne@69 2633 u_isUAlphabetic(UChar32 c);
jpayne@69 2634
jpayne@69 2635 /**
jpayne@69 2636 * Check if a code point has the Lowercase Unicode property.
jpayne@69 2637 * Same as u_hasBinaryProperty(c, UCHAR_LOWERCASE).
jpayne@69 2638 * This is different from u_islower!
jpayne@69 2639 * @param c Code point to test
jpayne@69 2640 * @return true if the code point has the Lowercase Unicode property, false otherwise
jpayne@69 2641 *
jpayne@69 2642 * @see UCHAR_LOWERCASE
jpayne@69 2643 * @see u_islower
jpayne@69 2644 * @see u_hasBinaryProperty
jpayne@69 2645 * @stable ICU 2.1
jpayne@69 2646 */
jpayne@69 2647 U_STABLE UBool U_EXPORT2
jpayne@69 2648 u_isULowercase(UChar32 c);
jpayne@69 2649
jpayne@69 2650 /**
jpayne@69 2651 * Check if a code point has the Uppercase Unicode property.
jpayne@69 2652 * Same as u_hasBinaryProperty(c, UCHAR_UPPERCASE).
jpayne@69 2653 * This is different from u_isupper!
jpayne@69 2654 * @param c Code point to test
jpayne@69 2655 * @return true if the code point has the Uppercase Unicode property, false otherwise
jpayne@69 2656 *
jpayne@69 2657 * @see UCHAR_UPPERCASE
jpayne@69 2658 * @see u_isupper
jpayne@69 2659 * @see u_hasBinaryProperty
jpayne@69 2660 * @stable ICU 2.1
jpayne@69 2661 */
jpayne@69 2662 U_STABLE UBool U_EXPORT2
jpayne@69 2663 u_isUUppercase(UChar32 c);
jpayne@69 2664
jpayne@69 2665 /**
jpayne@69 2666 * Check if a code point has the White_Space Unicode property.
jpayne@69 2667 * Same as u_hasBinaryProperty(c, UCHAR_WHITE_SPACE).
jpayne@69 2668 * This is different from both u_isspace and u_isWhitespace!
jpayne@69 2669 *
jpayne@69 2670 * Note: There are several ICU whitespace functions; please see the uchar.h
jpayne@69 2671 * file documentation for a detailed comparison.
jpayne@69 2672 *
jpayne@69 2673 * @param c Code point to test
jpayne@69 2674 * @return true if the code point has the White_Space Unicode property, false otherwise.
jpayne@69 2675 *
jpayne@69 2676 * @see UCHAR_WHITE_SPACE
jpayne@69 2677 * @see u_isWhitespace
jpayne@69 2678 * @see u_isspace
jpayne@69 2679 * @see u_isJavaSpaceChar
jpayne@69 2680 * @see u_hasBinaryProperty
jpayne@69 2681 * @stable ICU 2.1
jpayne@69 2682 */
jpayne@69 2683 U_STABLE UBool U_EXPORT2
jpayne@69 2684 u_isUWhiteSpace(UChar32 c);
jpayne@69 2685
jpayne@69 2686 /**
jpayne@69 2687 * Get the property value for an enumerated or integer Unicode property for a code point.
jpayne@69 2688 * Also returns binary and mask property values.
jpayne@69 2689 *
jpayne@69 2690 * Unicode, especially in version 3.2, defines many more properties than the
jpayne@69 2691 * original set in UnicodeData.txt.
jpayne@69 2692 *
jpayne@69 2693 * The properties APIs are intended to reflect Unicode properties as defined
jpayne@69 2694 * in the Unicode Character Database (UCD) and Unicode Technical Reports (UTR).
jpayne@69 2695 * For details about the properties see http://www.unicode.org/ .
jpayne@69 2696 * For names of Unicode properties see the UCD file PropertyAliases.txt.
jpayne@69 2697 *
jpayne@69 2698 * Sample usage:
jpayne@69 2699 * UEastAsianWidth ea=(UEastAsianWidth)u_getIntPropertyValue(c, UCHAR_EAST_ASIAN_WIDTH);
jpayne@69 2700 * UBool b=(UBool)u_getIntPropertyValue(c, UCHAR_IDEOGRAPHIC);
jpayne@69 2701 *
jpayne@69 2702 * @param c Code point to test.
jpayne@69 2703 * @param which UProperty selector constant, identifies which property to check.
jpayne@69 2704 * Must be UCHAR_BINARY_START<=which<UCHAR_BINARY_LIMIT
jpayne@69 2705 * or UCHAR_INT_START<=which<UCHAR_INT_LIMIT
jpayne@69 2706 * or UCHAR_MASK_START<=which<UCHAR_MASK_LIMIT.
jpayne@69 2707 * @return Numeric value that is directly the property value or,
jpayne@69 2708 * for enumerated properties, corresponds to the numeric value of the enumerated
jpayne@69 2709 * constant of the respective property value enumeration type
jpayne@69 2710 * (cast to enum type if necessary).
jpayne@69 2711 * Returns 0 or 1 (for FALSE/TRUE) for binary Unicode properties.
jpayne@69 2712 * Returns a bit-mask for mask properties.
jpayne@69 2713 * Returns 0 if 'which' is out of bounds or if the Unicode version
jpayne@69 2714 * does not have data for the property at all, or not for this code point.
jpayne@69 2715 *
jpayne@69 2716 * @see UProperty
jpayne@69 2717 * @see u_hasBinaryProperty
jpayne@69 2718 * @see u_getIntPropertyMinValue
jpayne@69 2719 * @see u_getIntPropertyMaxValue
jpayne@69 2720 * @see u_getIntPropertyMap
jpayne@69 2721 * @see u_getUnicodeVersion
jpayne@69 2722 * @stable ICU 2.2
jpayne@69 2723 */
jpayne@69 2724 U_STABLE int32_t U_EXPORT2
jpayne@69 2725 u_getIntPropertyValue(UChar32 c, UProperty which);
jpayne@69 2726
jpayne@69 2727 /**
jpayne@69 2728 * Get the minimum value for an enumerated/integer/binary Unicode property.
jpayne@69 2729 * Can be used together with u_getIntPropertyMaxValue
jpayne@69 2730 * to allocate arrays of UnicodeSet or similar.
jpayne@69 2731 *
jpayne@69 2732 * @param which UProperty selector constant, identifies which binary property to check.
jpayne@69 2733 * Must be UCHAR_BINARY_START<=which<UCHAR_BINARY_LIMIT
jpayne@69 2734 * or UCHAR_INT_START<=which<UCHAR_INT_LIMIT.
jpayne@69 2735 * @return Minimum value returned by u_getIntPropertyValue for a Unicode property.
jpayne@69 2736 * 0 if the property selector is out of range.
jpayne@69 2737 *
jpayne@69 2738 * @see UProperty
jpayne@69 2739 * @see u_hasBinaryProperty
jpayne@69 2740 * @see u_getUnicodeVersion
jpayne@69 2741 * @see u_getIntPropertyMaxValue
jpayne@69 2742 * @see u_getIntPropertyValue
jpayne@69 2743 * @stable ICU 2.2
jpayne@69 2744 */
jpayne@69 2745 U_STABLE int32_t U_EXPORT2
jpayne@69 2746 u_getIntPropertyMinValue(UProperty which);
jpayne@69 2747
jpayne@69 2748 /**
jpayne@69 2749 * Get the maximum value for an enumerated/integer/binary Unicode property.
jpayne@69 2750 * Can be used together with u_getIntPropertyMinValue
jpayne@69 2751 * to allocate arrays of UnicodeSet or similar.
jpayne@69 2752 *
jpayne@69 2753 * Examples for min/max values (for Unicode 3.2):
jpayne@69 2754 *
jpayne@69 2755 * - UCHAR_BIDI_CLASS: 0/18 (U_LEFT_TO_RIGHT/U_BOUNDARY_NEUTRAL)
jpayne@69 2756 * - UCHAR_SCRIPT: 0/45 (USCRIPT_COMMON/USCRIPT_TAGBANWA)
jpayne@69 2757 * - UCHAR_IDEOGRAPHIC: 0/1 (FALSE/TRUE)
jpayne@69 2758 *
jpayne@69 2759 * For undefined UProperty constant values, min/max values will be 0/-1.
jpayne@69 2760 *
jpayne@69 2761 * @param which UProperty selector constant, identifies which binary property to check.
jpayne@69 2762 * Must be UCHAR_BINARY_START<=which<UCHAR_BINARY_LIMIT
jpayne@69 2763 * or UCHAR_INT_START<=which<UCHAR_INT_LIMIT.
jpayne@69 2764 * @return Maximum value returned by u_getIntPropertyValue for a Unicode property.
jpayne@69 2765 * <=0 if the property selector is out of range.
jpayne@69 2766 *
jpayne@69 2767 * @see UProperty
jpayne@69 2768 * @see u_hasBinaryProperty
jpayne@69 2769 * @see u_getUnicodeVersion
jpayne@69 2770 * @see u_getIntPropertyMaxValue
jpayne@69 2771 * @see u_getIntPropertyValue
jpayne@69 2772 * @stable ICU 2.2
jpayne@69 2773 */
jpayne@69 2774 U_STABLE int32_t U_EXPORT2
jpayne@69 2775 u_getIntPropertyMaxValue(UProperty which);
jpayne@69 2776
jpayne@69 2777 /**
jpayne@69 2778 * Returns an immutable UCPMap for an enumerated/catalog/int-valued property.
jpayne@69 2779 * The library retains ownership over the returned object.
jpayne@69 2780 * Sets an error code if the property number is not one for an "int property".
jpayne@69 2781 *
jpayne@69 2782 * The returned object maps all Unicode code points to their values for that property.
jpayne@69 2783 * For documentation of the integer values see u_getIntPropertyValue().
jpayne@69 2784 *
jpayne@69 2785 * @param property UCHAR_INT_START..UCHAR_INT_LIMIT-1
jpayne@69 2786 * @param pErrorCode an in/out ICU UErrorCode
jpayne@69 2787 * @return the property as a map
jpayne@69 2788 * @see UProperty
jpayne@69 2789 * @see u_getIntPropertyValue
jpayne@69 2790 * @stable ICU 63
jpayne@69 2791 */
jpayne@69 2792 U_CAPI const UCPMap * U_EXPORT2
jpayne@69 2793 u_getIntPropertyMap(UProperty property, UErrorCode *pErrorCode);
jpayne@69 2794
jpayne@69 2795 /**
jpayne@69 2796 * Get the numeric value for a Unicode code point as defined in the
jpayne@69 2797 * Unicode Character Database.
jpayne@69 2798 *
jpayne@69 2799 * A "double" return type is necessary because
jpayne@69 2800 * some numeric values are fractions, negative, or too large for int32_t.
jpayne@69 2801 *
jpayne@69 2802 * For characters without any numeric values in the Unicode Character Database,
jpayne@69 2803 * this function will return U_NO_NUMERIC_VALUE.
jpayne@69 2804 * Note: This is different from the Unicode Standard which specifies NaN as the default value.
jpayne@69 2805 * (NaN is not available on all platforms.)
jpayne@69 2806 *
jpayne@69 2807 * Similar to java.lang.Character.getNumericValue(), but u_getNumericValue()
jpayne@69 2808 * also supports negative values, large values, and fractions,
jpayne@69 2809 * while Java's getNumericValue() returns values 10..35 for ASCII letters.
jpayne@69 2810 *
jpayne@69 2811 * @param c Code point to get the numeric value for.
jpayne@69 2812 * @return Numeric value of c, or U_NO_NUMERIC_VALUE if none is defined.
jpayne@69 2813 *
jpayne@69 2814 * @see U_NO_NUMERIC_VALUE
jpayne@69 2815 * @stable ICU 2.2
jpayne@69 2816 */
jpayne@69 2817 U_STABLE double U_EXPORT2
jpayne@69 2818 u_getNumericValue(UChar32 c);
jpayne@69 2819
jpayne@69 2820 /**
jpayne@69 2821 * Special value that is returned by u_getNumericValue when
jpayne@69 2822 * no numeric value is defined for a code point.
jpayne@69 2823 *
jpayne@69 2824 * @see u_getNumericValue
jpayne@69 2825 * @stable ICU 2.2
jpayne@69 2826 */
jpayne@69 2827 #define U_NO_NUMERIC_VALUE ((double)-123456789.)
jpayne@69 2828
jpayne@69 2829 /**
jpayne@69 2830 * Determines whether the specified code point has the general category "Ll"
jpayne@69 2831 * (lowercase letter).
jpayne@69 2832 *
jpayne@69 2833 * Same as java.lang.Character.isLowerCase().
jpayne@69 2834 *
jpayne@69 2835 * This misses some characters that are also lowercase but
jpayne@69 2836 * have a different general category value.
jpayne@69 2837 * In order to include those, use UCHAR_LOWERCASE.
jpayne@69 2838 *
jpayne@69 2839 * In addition to being equivalent to a Java function, this also serves
jpayne@69 2840 * as a C/POSIX migration function.
jpayne@69 2841 * See the comments about C/POSIX character classification functions in the
jpayne@69 2842 * documentation at the top of this header file.
jpayne@69 2843 *
jpayne@69 2844 * @param c the code point to be tested
jpayne@69 2845 * @return TRUE if the code point is an Ll lowercase letter
jpayne@69 2846 *
jpayne@69 2847 * @see UCHAR_LOWERCASE
jpayne@69 2848 * @see u_isupper
jpayne@69 2849 * @see u_istitle
jpayne@69 2850 * @stable ICU 2.0
jpayne@69 2851 */
jpayne@69 2852 U_STABLE UBool U_EXPORT2
jpayne@69 2853 u_islower(UChar32 c);
jpayne@69 2854
jpayne@69 2855 /**
jpayne@69 2856 * Determines whether the specified code point has the general category "Lu"
jpayne@69 2857 * (uppercase letter).
jpayne@69 2858 *
jpayne@69 2859 * Same as java.lang.Character.isUpperCase().
jpayne@69 2860 *
jpayne@69 2861 * This misses some characters that are also uppercase but
jpayne@69 2862 * have a different general category value.
jpayne@69 2863 * In order to include those, use UCHAR_UPPERCASE.
jpayne@69 2864 *
jpayne@69 2865 * In addition to being equivalent to a Java function, this also serves
jpayne@69 2866 * as a C/POSIX migration function.
jpayne@69 2867 * See the comments about C/POSIX character classification functions in the
jpayne@69 2868 * documentation at the top of this header file.
jpayne@69 2869 *
jpayne@69 2870 * @param c the code point to be tested
jpayne@69 2871 * @return TRUE if the code point is an Lu uppercase letter
jpayne@69 2872 *
jpayne@69 2873 * @see UCHAR_UPPERCASE
jpayne@69 2874 * @see u_islower
jpayne@69 2875 * @see u_istitle
jpayne@69 2876 * @see u_tolower
jpayne@69 2877 * @stable ICU 2.0
jpayne@69 2878 */
jpayne@69 2879 U_STABLE UBool U_EXPORT2
jpayne@69 2880 u_isupper(UChar32 c);
jpayne@69 2881
jpayne@69 2882 /**
jpayne@69 2883 * Determines whether the specified code point is a titlecase letter.
jpayne@69 2884 * True for general category "Lt" (titlecase letter).
jpayne@69 2885 *
jpayne@69 2886 * Same as java.lang.Character.isTitleCase().
jpayne@69 2887 *
jpayne@69 2888 * @param c the code point to be tested
jpayne@69 2889 * @return TRUE if the code point is an Lt titlecase letter
jpayne@69 2890 *
jpayne@69 2891 * @see u_isupper
jpayne@69 2892 * @see u_islower
jpayne@69 2893 * @see u_totitle
jpayne@69 2894 * @stable ICU 2.0
jpayne@69 2895 */
jpayne@69 2896 U_STABLE UBool U_EXPORT2
jpayne@69 2897 u_istitle(UChar32 c);
jpayne@69 2898
jpayne@69 2899 /**
jpayne@69 2900 * Determines whether the specified code point is a digit character according to Java.
jpayne@69 2901 * True for characters with general category "Nd" (decimal digit numbers).
jpayne@69 2902 * Beginning with Unicode 4, this is the same as
jpayne@69 2903 * testing for the Numeric_Type of Decimal.
jpayne@69 2904 *
jpayne@69 2905 * Same as java.lang.Character.isDigit().
jpayne@69 2906 *
jpayne@69 2907 * In addition to being equivalent to a Java function, this also serves
jpayne@69 2908 * as a C/POSIX migration function.
jpayne@69 2909 * See the comments about C/POSIX character classification functions in the
jpayne@69 2910 * documentation at the top of this header file.
jpayne@69 2911 *
jpayne@69 2912 * @param c the code point to be tested
jpayne@69 2913 * @return TRUE if the code point is a digit character according to Character.isDigit()
jpayne@69 2914 *
jpayne@69 2915 * @stable ICU 2.0
jpayne@69 2916 */
jpayne@69 2917 U_STABLE UBool U_EXPORT2
jpayne@69 2918 u_isdigit(UChar32 c);
jpayne@69 2919
jpayne@69 2920 /**
jpayne@69 2921 * Determines whether the specified code point is a letter character.
jpayne@69 2922 * True for general categories "L" (letters).
jpayne@69 2923 *
jpayne@69 2924 * Same as java.lang.Character.isLetter().
jpayne@69 2925 *
jpayne@69 2926 * In addition to being equivalent to a Java function, this also serves
jpayne@69 2927 * as a C/POSIX migration function.
jpayne@69 2928 * See the comments about C/POSIX character classification functions in the
jpayne@69 2929 * documentation at the top of this header file.
jpayne@69 2930 *
jpayne@69 2931 * @param c the code point to be tested
jpayne@69 2932 * @return TRUE if the code point is a letter character
jpayne@69 2933 *
jpayne@69 2934 * @see u_isdigit
jpayne@69 2935 * @see u_isalnum
jpayne@69 2936 * @stable ICU 2.0
jpayne@69 2937 */
jpayne@69 2938 U_STABLE UBool U_EXPORT2
jpayne@69 2939 u_isalpha(UChar32 c);
jpayne@69 2940
jpayne@69 2941 /**
jpayne@69 2942 * Determines whether the specified code point is an alphanumeric character
jpayne@69 2943 * (letter or digit) according to Java.
jpayne@69 2944 * True for characters with general categories
jpayne@69 2945 * "L" (letters) and "Nd" (decimal digit numbers).
jpayne@69 2946 *
jpayne@69 2947 * Same as java.lang.Character.isLetterOrDigit().
jpayne@69 2948 *
jpayne@69 2949 * In addition to being equivalent to a Java function, this also serves
jpayne@69 2950 * as a C/POSIX migration function.
jpayne@69 2951 * See the comments about C/POSIX character classification functions in the
jpayne@69 2952 * documentation at the top of this header file.
jpayne@69 2953 *
jpayne@69 2954 * @param c the code point to be tested
jpayne@69 2955 * @return TRUE if the code point is an alphanumeric character according to Character.isLetterOrDigit()
jpayne@69 2956 *
jpayne@69 2957 * @stable ICU 2.0
jpayne@69 2958 */
jpayne@69 2959 U_STABLE UBool U_EXPORT2
jpayne@69 2960 u_isalnum(UChar32 c);
jpayne@69 2961
jpayne@69 2962 /**
jpayne@69 2963 * Determines whether the specified code point is a hexadecimal digit.
jpayne@69 2964 * This is equivalent to u_digit(c, 16)>=0.
jpayne@69 2965 * True for characters with general category "Nd" (decimal digit numbers)
jpayne@69 2966 * as well as Latin letters a-f and A-F in both ASCII and Fullwidth ASCII.
jpayne@69 2967 * (That is, for letters with code points
jpayne@69 2968 * 0041..0046, 0061..0066, FF21..FF26, FF41..FF46.)
jpayne@69 2969 *
jpayne@69 2970 * In order to narrow the definition of hexadecimal digits to only ASCII
jpayne@69 2971 * characters, use (c<=0x7f && u_isxdigit(c)).
jpayne@69 2972 *
jpayne@69 2973 * This is a C/POSIX migration function.
jpayne@69 2974 * See the comments about C/POSIX character classification functions in the
jpayne@69 2975 * documentation at the top of this header file.
jpayne@69 2976 *
jpayne@69 2977 * @param c the code point to be tested
jpayne@69 2978 * @return TRUE if the code point is a hexadecimal digit
jpayne@69 2979 *
jpayne@69 2980 * @stable ICU 2.6
jpayne@69 2981 */
jpayne@69 2982 U_STABLE UBool U_EXPORT2
jpayne@69 2983 u_isxdigit(UChar32 c);
jpayne@69 2984
jpayne@69 2985 /**
jpayne@69 2986 * Determines whether the specified code point is a punctuation character.
jpayne@69 2987 * True for characters with general categories "P" (punctuation).
jpayne@69 2988 *
jpayne@69 2989 * This is a C/POSIX migration function.
jpayne@69 2990 * See the comments about C/POSIX character classification functions in the
jpayne@69 2991 * documentation at the top of this header file.
jpayne@69 2992 *
jpayne@69 2993 * @param c the code point to be tested
jpayne@69 2994 * @return TRUE if the code point is a punctuation character
jpayne@69 2995 *
jpayne@69 2996 * @stable ICU 2.6
jpayne@69 2997 */
jpayne@69 2998 U_STABLE UBool U_EXPORT2
jpayne@69 2999 u_ispunct(UChar32 c);
jpayne@69 3000
jpayne@69 3001 /**
jpayne@69 3002 * Determines whether the specified code point is a "graphic" character
jpayne@69 3003 * (printable, excluding spaces).
jpayne@69 3004 * TRUE for all characters except those with general categories
jpayne@69 3005 * "Cc" (control codes), "Cf" (format controls), "Cs" (surrogates),
jpayne@69 3006 * "Cn" (unassigned), and "Z" (separators).
jpayne@69 3007 *
jpayne@69 3008 * This is a C/POSIX migration function.
jpayne@69 3009 * See the comments about C/POSIX character classification functions in the
jpayne@69 3010 * documentation at the top of this header file.
jpayne@69 3011 *
jpayne@69 3012 * @param c the code point to be tested
jpayne@69 3013 * @return TRUE if the code point is a "graphic" character
jpayne@69 3014 *
jpayne@69 3015 * @stable ICU 2.6
jpayne@69 3016 */
jpayne@69 3017 U_STABLE UBool U_EXPORT2
jpayne@69 3018 u_isgraph(UChar32 c);
jpayne@69 3019
jpayne@69 3020 /**
jpayne@69 3021 * Determines whether the specified code point is a "blank" or "horizontal space",
jpayne@69 3022 * a character that visibly separates words on a line.
jpayne@69 3023 * The following are equivalent definitions:
jpayne@69 3024 *
jpayne@69 3025 * TRUE for Unicode White_Space characters except for "vertical space controls"
jpayne@69 3026 * where "vertical space controls" are the following characters:
jpayne@69 3027 * U+000A (LF) U+000B (VT) U+000C (FF) U+000D (CR) U+0085 (NEL) U+2028 (LS) U+2029 (PS)
jpayne@69 3028 *
jpayne@69 3029 * same as
jpayne@69 3030 *
jpayne@69 3031 * TRUE for U+0009 (TAB) and characters with general category "Zs" (space separators).
jpayne@69 3032 *
jpayne@69 3033 * Note: There are several ICU whitespace functions; please see the uchar.h
jpayne@69 3034 * file documentation for a detailed comparison.
jpayne@69 3035 *
jpayne@69 3036 * This is a C/POSIX migration function.
jpayne@69 3037 * See the comments about C/POSIX character classification functions in the
jpayne@69 3038 * documentation at the top of this header file.
jpayne@69 3039 *
jpayne@69 3040 * @param c the code point to be tested
jpayne@69 3041 * @return TRUE if the code point is a "blank"
jpayne@69 3042 *
jpayne@69 3043 * @stable ICU 2.6
jpayne@69 3044 */
jpayne@69 3045 U_STABLE UBool U_EXPORT2
jpayne@69 3046 u_isblank(UChar32 c);
jpayne@69 3047
jpayne@69 3048 /**
jpayne@69 3049 * Determines whether the specified code point is "defined",
jpayne@69 3050 * which usually means that it is assigned a character.
jpayne@69 3051 * True for general categories other than "Cn" (other, not assigned),
jpayne@69 3052 * i.e., true for all code points mentioned in UnicodeData.txt.
jpayne@69 3053 *
jpayne@69 3054 * Note that non-character code points (e.g., U+FDD0) are not "defined"
jpayne@69 3055 * (they are Cn), but surrogate code points are "defined" (Cs).
jpayne@69 3056 *
jpayne@69 3057 * Same as java.lang.Character.isDefined().
jpayne@69 3058 *
jpayne@69 3059 * @param c the code point to be tested
jpayne@69 3060 * @return TRUE if the code point is assigned a character
jpayne@69 3061 *
jpayne@69 3062 * @see u_isdigit
jpayne@69 3063 * @see u_isalpha
jpayne@69 3064 * @see u_isalnum
jpayne@69 3065 * @see u_isupper
jpayne@69 3066 * @see u_islower
jpayne@69 3067 * @see u_istitle
jpayne@69 3068 * @stable ICU 2.0
jpayne@69 3069 */
jpayne@69 3070 U_STABLE UBool U_EXPORT2
jpayne@69 3071 u_isdefined(UChar32 c);
jpayne@69 3072
jpayne@69 3073 /**
jpayne@69 3074 * Determines if the specified character is a space character or not.
jpayne@69 3075 *
jpayne@69 3076 * Note: There are several ICU whitespace functions; please see the uchar.h
jpayne@69 3077 * file documentation for a detailed comparison.
jpayne@69 3078 *
jpayne@69 3079 * This is a C/POSIX migration function.
jpayne@69 3080 * See the comments about C/POSIX character classification functions in the
jpayne@69 3081 * documentation at the top of this header file.
jpayne@69 3082 *
jpayne@69 3083 * @param c the character to be tested
jpayne@69 3084 * @return true if the character is a space character; false otherwise.
jpayne@69 3085 *
jpayne@69 3086 * @see u_isJavaSpaceChar
jpayne@69 3087 * @see u_isWhitespace
jpayne@69 3088 * @see u_isUWhiteSpace
jpayne@69 3089 * @stable ICU 2.0
jpayne@69 3090 */
jpayne@69 3091 U_STABLE UBool U_EXPORT2
jpayne@69 3092 u_isspace(UChar32 c);
jpayne@69 3093
jpayne@69 3094 /**
jpayne@69 3095 * Determine if the specified code point is a space character according to Java.
jpayne@69 3096 * True for characters with general categories "Z" (separators),
jpayne@69 3097 * which does not include control codes (e.g., TAB or Line Feed).
jpayne@69 3098 *
jpayne@69 3099 * Same as java.lang.Character.isSpaceChar().
jpayne@69 3100 *
jpayne@69 3101 * Note: There are several ICU whitespace functions; please see the uchar.h
jpayne@69 3102 * file documentation for a detailed comparison.
jpayne@69 3103 *
jpayne@69 3104 * @param c the code point to be tested
jpayne@69 3105 * @return TRUE if the code point is a space character according to Character.isSpaceChar()
jpayne@69 3106 *
jpayne@69 3107 * @see u_isspace
jpayne@69 3108 * @see u_isWhitespace
jpayne@69 3109 * @see u_isUWhiteSpace
jpayne@69 3110 * @stable ICU 2.6
jpayne@69 3111 */
jpayne@69 3112 U_STABLE UBool U_EXPORT2
jpayne@69 3113 u_isJavaSpaceChar(UChar32 c);
jpayne@69 3114
jpayne@69 3115 /**
jpayne@69 3116 * Determines if the specified code point is a whitespace character according to Java/ICU.
jpayne@69 3117 * A character is considered to be a Java whitespace character if and only
jpayne@69 3118 * if it satisfies one of the following criteria:
jpayne@69 3119 *
jpayne@69 3120 * - It is a Unicode Separator character (categories "Z" = "Zs" or "Zl" or "Zp"), but is not
jpayne@69 3121 * also a non-breaking space (U+00A0 NBSP or U+2007 Figure Space or U+202F Narrow NBSP).
jpayne@69 3122 * - It is U+0009 HORIZONTAL TABULATION.
jpayne@69 3123 * - It is U+000A LINE FEED.
jpayne@69 3124 * - It is U+000B VERTICAL TABULATION.
jpayne@69 3125 * - It is U+000C FORM FEED.
jpayne@69 3126 * - It is U+000D CARRIAGE RETURN.
jpayne@69 3127 * - It is U+001C FILE SEPARATOR.
jpayne@69 3128 * - It is U+001D GROUP SEPARATOR.
jpayne@69 3129 * - It is U+001E RECORD SEPARATOR.
jpayne@69 3130 * - It is U+001F UNIT SEPARATOR.
jpayne@69 3131 *
jpayne@69 3132 * This API tries to sync with the semantics of Java's
jpayne@69 3133 * java.lang.Character.isWhitespace(), but it may not return
jpayne@69 3134 * the exact same results because of the Unicode version
jpayne@69 3135 * difference.
jpayne@69 3136 *
jpayne@69 3137 * Note: Unicode 4.0.1 changed U+200B ZERO WIDTH SPACE from a Space Separator (Zs)
jpayne@69 3138 * to a Format Control (Cf). Since then, isWhitespace(0x200b) returns false.
jpayne@69 3139 * See http://www.unicode.org/versions/Unicode4.0.1/
jpayne@69 3140 *
jpayne@69 3141 * Note: There are several ICU whitespace functions; please see the uchar.h
jpayne@69 3142 * file documentation for a detailed comparison.
jpayne@69 3143 *
jpayne@69 3144 * @param c the code point to be tested
jpayne@69 3145 * @return TRUE if the code point is a whitespace character according to Java/ICU
jpayne@69 3146 *
jpayne@69 3147 * @see u_isspace
jpayne@69 3148 * @see u_isJavaSpaceChar
jpayne@69 3149 * @see u_isUWhiteSpace
jpayne@69 3150 * @stable ICU 2.0
jpayne@69 3151 */
jpayne@69 3152 U_STABLE UBool U_EXPORT2
jpayne@69 3153 u_isWhitespace(UChar32 c);
jpayne@69 3154
jpayne@69 3155 /**
jpayne@69 3156 * Determines whether the specified code point is a control character
jpayne@69 3157 * (as defined by this function).
jpayne@69 3158 * A control character is one of the following:
jpayne@69 3159 * - ISO 8-bit control character (U+0000..U+001f and U+007f..U+009f)
jpayne@69 3160 * - U_CONTROL_CHAR (Cc)
jpayne@69 3161 * - U_FORMAT_CHAR (Cf)
jpayne@69 3162 * - U_LINE_SEPARATOR (Zl)
jpayne@69 3163 * - U_PARAGRAPH_SEPARATOR (Zp)
jpayne@69 3164 *
jpayne@69 3165 * This is a C/POSIX migration function.
jpayne@69 3166 * See the comments about C/POSIX character classification functions in the
jpayne@69 3167 * documentation at the top of this header file.
jpayne@69 3168 *
jpayne@69 3169 * @param c the code point to be tested
jpayne@69 3170 * @return TRUE if the code point is a control character
jpayne@69 3171 *
jpayne@69 3172 * @see UCHAR_DEFAULT_IGNORABLE_CODE_POINT
jpayne@69 3173 * @see u_isprint
jpayne@69 3174 * @stable ICU 2.0
jpayne@69 3175 */
jpayne@69 3176 U_STABLE UBool U_EXPORT2
jpayne@69 3177 u_iscntrl(UChar32 c);
jpayne@69 3178
jpayne@69 3179 /**
jpayne@69 3180 * Determines whether the specified code point is an ISO control code.
jpayne@69 3181 * True for U+0000..U+001f and U+007f..U+009f (general category "Cc").
jpayne@69 3182 *
jpayne@69 3183 * Same as java.lang.Character.isISOControl().
jpayne@69 3184 *
jpayne@69 3185 * @param c the code point to be tested
jpayne@69 3186 * @return TRUE if the code point is an ISO control code
jpayne@69 3187 *
jpayne@69 3188 * @see u_iscntrl
jpayne@69 3189 * @stable ICU 2.6
jpayne@69 3190 */
jpayne@69 3191 U_STABLE UBool U_EXPORT2
jpayne@69 3192 u_isISOControl(UChar32 c);
jpayne@69 3193
jpayne@69 3194 /**
jpayne@69 3195 * Determines whether the specified code point is a printable character.
jpayne@69 3196 * True for general categories <em>other</em> than "C" (controls).
jpayne@69 3197 *
jpayne@69 3198 * This is a C/POSIX migration function.
jpayne@69 3199 * See the comments about C/POSIX character classification functions in the
jpayne@69 3200 * documentation at the top of this header file.
jpayne@69 3201 *
jpayne@69 3202 * @param c the code point to be tested
jpayne@69 3203 * @return TRUE if the code point is a printable character
jpayne@69 3204 *
jpayne@69 3205 * @see UCHAR_DEFAULT_IGNORABLE_CODE_POINT
jpayne@69 3206 * @see u_iscntrl
jpayne@69 3207 * @stable ICU 2.0
jpayne@69 3208 */
jpayne@69 3209 U_STABLE UBool U_EXPORT2
jpayne@69 3210 u_isprint(UChar32 c);
jpayne@69 3211
jpayne@69 3212 /**
jpayne@69 3213 * Non-standard: Determines whether the specified code point is a base character.
jpayne@69 3214 * True for general categories "L" (letters), "N" (numbers),
jpayne@69 3215 * "Mc" (spacing combining marks), and "Me" (enclosing marks).
jpayne@69 3216 *
jpayne@69 3217 * Note that this is different from the Unicode Standard definition in
jpayne@69 3218 * chapter 3.6, conformance clause D51 “Base character”,
jpayne@69 3219 * which defines base characters as the code points with general categories
jpayne@69 3220 * Letter (L), Number (N), Punctuation (P), Symbol (S), or Space Separator (Zs).
jpayne@69 3221 *
jpayne@69 3222 * @param c the code point to be tested
jpayne@69 3223 * @return TRUE if the code point is a base character according to this function
jpayne@69 3224 *
jpayne@69 3225 * @see u_isalpha
jpayne@69 3226 * @see u_isdigit
jpayne@69 3227 * @stable ICU 2.0
jpayne@69 3228 */
jpayne@69 3229 U_STABLE UBool U_EXPORT2
jpayne@69 3230 u_isbase(UChar32 c);
jpayne@69 3231
jpayne@69 3232 /**
jpayne@69 3233 * Returns the bidirectional category value for the code point,
jpayne@69 3234 * which is used in the Unicode bidirectional algorithm
jpayne@69 3235 * (UAX #9 http://www.unicode.org/reports/tr9/).
jpayne@69 3236 * Note that some <em>unassigned</em> code points have bidi values
jpayne@69 3237 * of R or AL because they are in blocks that are reserved
jpayne@69 3238 * for Right-To-Left scripts.
jpayne@69 3239 *
jpayne@69 3240 * Same as java.lang.Character.getDirectionality()
jpayne@69 3241 *
jpayne@69 3242 * @param c the code point to be tested
jpayne@69 3243 * @return the bidirectional category (UCharDirection) value
jpayne@69 3244 *
jpayne@69 3245 * @see UCharDirection
jpayne@69 3246 * @stable ICU 2.0
jpayne@69 3247 */
jpayne@69 3248 U_STABLE UCharDirection U_EXPORT2
jpayne@69 3249 u_charDirection(UChar32 c);
jpayne@69 3250
jpayne@69 3251 /**
jpayne@69 3252 * Determines whether the code point has the Bidi_Mirrored property.
jpayne@69 3253 * This property is set for characters that are commonly used in
jpayne@69 3254 * Right-To-Left contexts and need to be displayed with a "mirrored"
jpayne@69 3255 * glyph.
jpayne@69 3256 *
jpayne@69 3257 * Same as java.lang.Character.isMirrored().
jpayne@69 3258 * Same as UCHAR_BIDI_MIRRORED
jpayne@69 3259 *
jpayne@69 3260 * @param c the code point to be tested
jpayne@69 3261 * @return TRUE if the character has the Bidi_Mirrored property
jpayne@69 3262 *
jpayne@69 3263 * @see UCHAR_BIDI_MIRRORED
jpayne@69 3264 * @stable ICU 2.0
jpayne@69 3265 */
jpayne@69 3266 U_STABLE UBool U_EXPORT2
jpayne@69 3267 u_isMirrored(UChar32 c);
jpayne@69 3268
jpayne@69 3269 /**
jpayne@69 3270 * Maps the specified character to a "mirror-image" character.
jpayne@69 3271 * For characters with the Bidi_Mirrored property, implementations
jpayne@69 3272 * sometimes need a "poor man's" mapping to another Unicode
jpayne@69 3273 * character (code point) such that the default glyph may serve
jpayne@69 3274 * as the mirror-image of the default glyph of the specified
jpayne@69 3275 * character. This is useful for text conversion to and from
jpayne@69 3276 * codepages with visual order, and for displays without glyph
jpayne@69 3277 * selection capabilities.
jpayne@69 3278 *
jpayne@69 3279 * @param c the code point to be mapped
jpayne@69 3280 * @return another Unicode code point that may serve as a mirror-image
jpayne@69 3281 * substitute, or c itself if there is no such mapping or c
jpayne@69 3282 * does not have the Bidi_Mirrored property
jpayne@69 3283 *
jpayne@69 3284 * @see UCHAR_BIDI_MIRRORED
jpayne@69 3285 * @see u_isMirrored
jpayne@69 3286 * @stable ICU 2.0
jpayne@69 3287 */
jpayne@69 3288 U_STABLE UChar32 U_EXPORT2
jpayne@69 3289 u_charMirror(UChar32 c);
jpayne@69 3290
jpayne@69 3291 /**
jpayne@69 3292 * Maps the specified character to its paired bracket character.
jpayne@69 3293 * For Bidi_Paired_Bracket_Type!=None, this is the same as u_charMirror().
jpayne@69 3294 * Otherwise c itself is returned.
jpayne@69 3295 * See http://www.unicode.org/reports/tr9/
jpayne@69 3296 *
jpayne@69 3297 * @param c the code point to be mapped
jpayne@69 3298 * @return the paired bracket code point,
jpayne@69 3299 * or c itself if there is no such mapping
jpayne@69 3300 * (Bidi_Paired_Bracket_Type=None)
jpayne@69 3301 *
jpayne@69 3302 * @see UCHAR_BIDI_PAIRED_BRACKET
jpayne@69 3303 * @see UCHAR_BIDI_PAIRED_BRACKET_TYPE
jpayne@69 3304 * @see u_charMirror
jpayne@69 3305 * @stable ICU 52
jpayne@69 3306 */
jpayne@69 3307 U_STABLE UChar32 U_EXPORT2
jpayne@69 3308 u_getBidiPairedBracket(UChar32 c);
jpayne@69 3309
jpayne@69 3310 /**
jpayne@69 3311 * Returns the general category value for the code point.
jpayne@69 3312 *
jpayne@69 3313 * Same as java.lang.Character.getType().
jpayne@69 3314 *
jpayne@69 3315 * @param c the code point to be tested
jpayne@69 3316 * @return the general category (UCharCategory) value
jpayne@69 3317 *
jpayne@69 3318 * @see UCharCategory
jpayne@69 3319 * @stable ICU 2.0
jpayne@69 3320 */
jpayne@69 3321 U_STABLE int8_t U_EXPORT2
jpayne@69 3322 u_charType(UChar32 c);
jpayne@69 3323
jpayne@69 3324 /**
jpayne@69 3325 * Get a single-bit bit set for the general category of a character.
jpayne@69 3326 * This bit set can be compared bitwise with U_GC_SM_MASK, U_GC_L_MASK, etc.
jpayne@69 3327 * Same as U_MASK(u_charType(c)).
jpayne@69 3328 *
jpayne@69 3329 * @param c the code point to be tested
jpayne@69 3330 * @return a single-bit mask corresponding to the general category (UCharCategory) value
jpayne@69 3331 *
jpayne@69 3332 * @see u_charType
jpayne@69 3333 * @see UCharCategory
jpayne@69 3334 * @see U_GC_CN_MASK
jpayne@69 3335 * @stable ICU 2.1
jpayne@69 3336 */
jpayne@69 3337 #define U_GET_GC_MASK(c) U_MASK(u_charType(c))
jpayne@69 3338
jpayne@69 3339 /**
jpayne@69 3340 * Callback from u_enumCharTypes(), is called for each contiguous range
jpayne@69 3341 * of code points c (where start<=c<limit)
jpayne@69 3342 * with the same Unicode general category ("character type").
jpayne@69 3343 *
jpayne@69 3344 * The callback function can stop the enumeration by returning FALSE.
jpayne@69 3345 *
jpayne@69 3346 * @param context an opaque pointer, as passed into utrie_enum()
jpayne@69 3347 * @param start the first code point in a contiguous range with value
jpayne@69 3348 * @param limit one past the last code point in a contiguous range with value
jpayne@69 3349 * @param type the general category for all code points in [start..limit[
jpayne@69 3350 * @return FALSE to stop the enumeration
jpayne@69 3351 *
jpayne@69 3352 * @stable ICU 2.1
jpayne@69 3353 * @see UCharCategory
jpayne@69 3354 * @see u_enumCharTypes
jpayne@69 3355 */
jpayne@69 3356 typedef UBool U_CALLCONV
jpayne@69 3357 UCharEnumTypeRange(const void *context, UChar32 start, UChar32 limit, UCharCategory type);
jpayne@69 3358
jpayne@69 3359 /**
jpayne@69 3360 * Enumerate efficiently all code points with their Unicode general categories.
jpayne@69 3361 *
jpayne@69 3362 * This is useful for building data structures (e.g., UnicodeSet's),
jpayne@69 3363 * for enumerating all assigned code points (type!=U_UNASSIGNED), etc.
jpayne@69 3364 *
jpayne@69 3365 * For each contiguous range of code points with a given general category ("character type"),
jpayne@69 3366 * the UCharEnumTypeRange function is called.
jpayne@69 3367 * Adjacent ranges have different types.
jpayne@69 3368 * The Unicode Standard guarantees that the numeric value of the type is 0..31.
jpayne@69 3369 *
jpayne@69 3370 * @param enumRange a pointer to a function that is called for each contiguous range
jpayne@69 3371 * of code points with the same general category
jpayne@69 3372 * @param context an opaque pointer that is passed on to the callback function
jpayne@69 3373 *
jpayne@69 3374 * @stable ICU 2.1
jpayne@69 3375 * @see UCharCategory
jpayne@69 3376 * @see UCharEnumTypeRange
jpayne@69 3377 */
jpayne@69 3378 U_STABLE void U_EXPORT2
jpayne@69 3379 u_enumCharTypes(UCharEnumTypeRange *enumRange, const void *context);
jpayne@69 3380
jpayne@69 3381 #if !UCONFIG_NO_NORMALIZATION
jpayne@69 3382
jpayne@69 3383 /**
jpayne@69 3384 * Returns the combining class of the code point as specified in UnicodeData.txt.
jpayne@69 3385 *
jpayne@69 3386 * @param c the code point of the character
jpayne@69 3387 * @return the combining class of the character
jpayne@69 3388 * @stable ICU 2.0
jpayne@69 3389 */
jpayne@69 3390 U_STABLE uint8_t U_EXPORT2
jpayne@69 3391 u_getCombiningClass(UChar32 c);
jpayne@69 3392
jpayne@69 3393 #endif
jpayne@69 3394
jpayne@69 3395 /**
jpayne@69 3396 * Returns the decimal digit value of a decimal digit character.
jpayne@69 3397 * Such characters have the general category "Nd" (decimal digit numbers)
jpayne@69 3398 * and a Numeric_Type of Decimal.
jpayne@69 3399 *
jpayne@69 3400 * Unlike ICU releases before 2.6, no digit values are returned for any
jpayne@69 3401 * Han characters because Han number characters are often used with a special
jpayne@69 3402 * Chinese-style number format (with characters for powers of 10 in between)
jpayne@69 3403 * instead of in decimal-positional notation.
jpayne@69 3404 * Unicode 4 explicitly assigns Han number characters the Numeric_Type
jpayne@69 3405 * Numeric instead of Decimal.
jpayne@69 3406 * See Jitterbug 1483 for more details.
jpayne@69 3407 *
jpayne@69 3408 * Use u_getIntPropertyValue(c, UCHAR_NUMERIC_TYPE) and u_getNumericValue()
jpayne@69 3409 * for complete numeric Unicode properties.
jpayne@69 3410 *
jpayne@69 3411 * @param c the code point for which to get the decimal digit value
jpayne@69 3412 * @return the decimal digit value of c,
jpayne@69 3413 * or -1 if c is not a decimal digit character
jpayne@69 3414 *
jpayne@69 3415 * @see u_getNumericValue
jpayne@69 3416 * @stable ICU 2.0
jpayne@69 3417 */
jpayne@69 3418 U_STABLE int32_t U_EXPORT2
jpayne@69 3419 u_charDigitValue(UChar32 c);
jpayne@69 3420
jpayne@69 3421 /**
jpayne@69 3422 * Returns the Unicode allocation block that contains the character.
jpayne@69 3423 *
jpayne@69 3424 * @param c the code point to be tested
jpayne@69 3425 * @return the block value (UBlockCode) for c
jpayne@69 3426 *
jpayne@69 3427 * @see UBlockCode
jpayne@69 3428 * @stable ICU 2.0
jpayne@69 3429 */
jpayne@69 3430 U_STABLE UBlockCode U_EXPORT2
jpayne@69 3431 ublock_getCode(UChar32 c);
jpayne@69 3432
jpayne@69 3433 /**
jpayne@69 3434 * Retrieve the name of a Unicode character.
jpayne@69 3435 * Depending on <code>nameChoice</code>, the character name written
jpayne@69 3436 * into the buffer is the "modern" name or the name that was defined
jpayne@69 3437 * in Unicode version 1.0.
jpayne@69 3438 * The name contains only "invariant" characters
jpayne@69 3439 * like A-Z, 0-9, space, and '-'.
jpayne@69 3440 * Unicode 1.0 names are only retrieved if they are different from the modern
jpayne@69 3441 * names and if the data file contains the data for them. gennames may or may
jpayne@69 3442 * not be called with a command line option to include 1.0 names in unames.dat.
jpayne@69 3443 *
jpayne@69 3444 * @param code The character (code point) for which to get the name.
jpayne@69 3445 * It must be <code>0<=code<=0x10ffff</code>.
jpayne@69 3446 * @param nameChoice Selector for which name to get.
jpayne@69 3447 * @param buffer Destination address for copying the name.
jpayne@69 3448 * The name will always be zero-terminated.
jpayne@69 3449 * If there is no name, then the buffer will be set to the empty string.
jpayne@69 3450 * @param bufferLength <code>==sizeof(buffer)</code>
jpayne@69 3451 * @param pErrorCode Pointer to a UErrorCode variable;
jpayne@69 3452 * check for <code>U_SUCCESS()</code> after <code>u_charName()</code>
jpayne@69 3453 * returns.
jpayne@69 3454 * @return The length of the name, or 0 if there is no name for this character.
jpayne@69 3455 * If the bufferLength is less than or equal to the length, then the buffer
jpayne@69 3456 * contains the truncated name and the returned length indicates the full
jpayne@69 3457 * length of the name.
jpayne@69 3458 * The length does not include the zero-termination.
jpayne@69 3459 *
jpayne@69 3460 * @see UCharNameChoice
jpayne@69 3461 * @see u_charFromName
jpayne@69 3462 * @see u_enumCharNames
jpayne@69 3463 * @stable ICU 2.0
jpayne@69 3464 */
jpayne@69 3465 U_STABLE int32_t U_EXPORT2
jpayne@69 3466 u_charName(UChar32 code, UCharNameChoice nameChoice,
jpayne@69 3467 char *buffer, int32_t bufferLength,
jpayne@69 3468 UErrorCode *pErrorCode);
jpayne@69 3469
jpayne@69 3470 #ifndef U_HIDE_DEPRECATED_API
jpayne@69 3471 /**
jpayne@69 3472 * Returns an empty string.
jpayne@69 3473 * Used to return the ISO 10646 comment for a character.
jpayne@69 3474 * The Unicode ISO_Comment property is deprecated and has no values.
jpayne@69 3475 *
jpayne@69 3476 * @param c The character (code point) for which to get the ISO comment.
jpayne@69 3477 * It must be <code>0<=c<=0x10ffff</code>.
jpayne@69 3478 * @param dest Destination address for copying the comment.
jpayne@69 3479 * The comment will be zero-terminated if possible.
jpayne@69 3480 * If there is no comment, then the buffer will be set to the empty string.
jpayne@69 3481 * @param destCapacity <code>==sizeof(dest)</code>
jpayne@69 3482 * @param pErrorCode Pointer to a UErrorCode variable;
jpayne@69 3483 * check for <code>U_SUCCESS()</code> after <code>u_getISOComment()</code>
jpayne@69 3484 * returns.
jpayne@69 3485 * @return 0
jpayne@69 3486 *
jpayne@69 3487 * @deprecated ICU 49
jpayne@69 3488 */
jpayne@69 3489 U_DEPRECATED int32_t U_EXPORT2
jpayne@69 3490 u_getISOComment(UChar32 c,
jpayne@69 3491 char *dest, int32_t destCapacity,
jpayne@69 3492 UErrorCode *pErrorCode);
jpayne@69 3493 #endif /* U_HIDE_DEPRECATED_API */
jpayne@69 3494
jpayne@69 3495 /**
jpayne@69 3496 * Find a Unicode character by its name and return its code point value.
jpayne@69 3497 * The name is matched exactly and completely.
jpayne@69 3498 * If the name does not correspond to a code point, <i>pErrorCode</i>
jpayne@69 3499 * is set to <code>U_INVALID_CHAR_FOUND</code>.
jpayne@69 3500 * A Unicode 1.0 name is matched only if it differs from the modern name.
jpayne@69 3501 * Unicode names are all uppercase. Extended names are lowercase followed
jpayne@69 3502 * by an uppercase hexadecimal number, and within angle brackets.
jpayne@69 3503 *
jpayne@69 3504 * @param nameChoice Selector for which name to match.
jpayne@69 3505 * @param name The name to match.
jpayne@69 3506 * @param pErrorCode Pointer to a UErrorCode variable
jpayne@69 3507 * @return The Unicode value of the code point with the given name,
jpayne@69 3508 * or an undefined value if there is no such code point.
jpayne@69 3509 *
jpayne@69 3510 * @see UCharNameChoice
jpayne@69 3511 * @see u_charName
jpayne@69 3512 * @see u_enumCharNames
jpayne@69 3513 * @stable ICU 1.7
jpayne@69 3514 */
jpayne@69 3515 U_STABLE UChar32 U_EXPORT2
jpayne@69 3516 u_charFromName(UCharNameChoice nameChoice,
jpayne@69 3517 const char *name,
jpayne@69 3518 UErrorCode *pErrorCode);
jpayne@69 3519
jpayne@69 3520 /**
jpayne@69 3521 * Type of a callback function for u_enumCharNames() that gets called
jpayne@69 3522 * for each Unicode character with the code point value and
jpayne@69 3523 * the character name.
jpayne@69 3524 * If such a function returns FALSE, then the enumeration is stopped.
jpayne@69 3525 *
jpayne@69 3526 * @param context The context pointer that was passed to u_enumCharNames().
jpayne@69 3527 * @param code The Unicode code point for the character with this name.
jpayne@69 3528 * @param nameChoice Selector for which kind of names is enumerated.
jpayne@69 3529 * @param name The character's name, zero-terminated.
jpayne@69 3530 * @param length The length of the name.
jpayne@69 3531 * @return TRUE if the enumeration should continue, FALSE to stop it.
jpayne@69 3532 *
jpayne@69 3533 * @see UCharNameChoice
jpayne@69 3534 * @see u_enumCharNames
jpayne@69 3535 * @stable ICU 1.7
jpayne@69 3536 */
jpayne@69 3537 typedef UBool U_CALLCONV UEnumCharNamesFn(void *context,
jpayne@69 3538 UChar32 code,
jpayne@69 3539 UCharNameChoice nameChoice,
jpayne@69 3540 const char *name,
jpayne@69 3541 int32_t length);
jpayne@69 3542
jpayne@69 3543 /**
jpayne@69 3544 * Enumerate all assigned Unicode characters between the start and limit
jpayne@69 3545 * code points (start inclusive, limit exclusive) and call a function
jpayne@69 3546 * for each, passing the code point value and the character name.
jpayne@69 3547 * For Unicode 1.0 names, only those are enumerated that differ from the
jpayne@69 3548 * modern names.
jpayne@69 3549 *
jpayne@69 3550 * @param start The first code point in the enumeration range.
jpayne@69 3551 * @param limit One more than the last code point in the enumeration range
jpayne@69 3552 * (the first one after the range).
jpayne@69 3553 * @param fn The function that is to be called for each character name.
jpayne@69 3554 * @param context An arbitrary pointer that is passed to the function.
jpayne@69 3555 * @param nameChoice Selector for which kind of names to enumerate.
jpayne@69 3556 * @param pErrorCode Pointer to a UErrorCode variable
jpayne@69 3557 *
jpayne@69 3558 * @see UCharNameChoice
jpayne@69 3559 * @see UEnumCharNamesFn
jpayne@69 3560 * @see u_charName
jpayne@69 3561 * @see u_charFromName
jpayne@69 3562 * @stable ICU 1.7
jpayne@69 3563 */
jpayne@69 3564 U_STABLE void U_EXPORT2
jpayne@69 3565 u_enumCharNames(UChar32 start, UChar32 limit,
jpayne@69 3566 UEnumCharNamesFn *fn,
jpayne@69 3567 void *context,
jpayne@69 3568 UCharNameChoice nameChoice,
jpayne@69 3569 UErrorCode *pErrorCode);
jpayne@69 3570
jpayne@69 3571 /**
jpayne@69 3572 * Return the Unicode name for a given property, as given in the
jpayne@69 3573 * Unicode database file PropertyAliases.txt.
jpayne@69 3574 *
jpayne@69 3575 * In addition, this function maps the property
jpayne@69 3576 * UCHAR_GENERAL_CATEGORY_MASK to the synthetic names "gcm" /
jpayne@69 3577 * "General_Category_Mask". These names are not in
jpayne@69 3578 * PropertyAliases.txt.
jpayne@69 3579 *
jpayne@69 3580 * @param property UProperty selector other than UCHAR_INVALID_CODE.
jpayne@69 3581 * If out of range, NULL is returned.
jpayne@69 3582 *
jpayne@69 3583 * @param nameChoice selector for which name to get. If out of range,
jpayne@69 3584 * NULL is returned. All properties have a long name. Most
jpayne@69 3585 * have a short name, but some do not. Unicode allows for
jpayne@69 3586 * additional names; if present these will be returned by
jpayne@69 3587 * U_LONG_PROPERTY_NAME + i, where i=1, 2,...
jpayne@69 3588 *
jpayne@69 3589 * @return a pointer to the name, or NULL if either the
jpayne@69 3590 * property or the nameChoice is out of range. If a given
jpayne@69 3591 * nameChoice returns NULL, then all larger values of
jpayne@69 3592 * nameChoice will return NULL, with one exception: if NULL is
jpayne@69 3593 * returned for U_SHORT_PROPERTY_NAME, then
jpayne@69 3594 * U_LONG_PROPERTY_NAME (and higher) may still return a
jpayne@69 3595 * non-NULL value. The returned pointer is valid until
jpayne@69 3596 * u_cleanup() is called.
jpayne@69 3597 *
jpayne@69 3598 * @see UProperty
jpayne@69 3599 * @see UPropertyNameChoice
jpayne@69 3600 * @stable ICU 2.4
jpayne@69 3601 */
jpayne@69 3602 U_STABLE const char* U_EXPORT2
jpayne@69 3603 u_getPropertyName(UProperty property,
jpayne@69 3604 UPropertyNameChoice nameChoice);
jpayne@69 3605
jpayne@69 3606 /**
jpayne@69 3607 * Return the UProperty enum for a given property name, as specified
jpayne@69 3608 * in the Unicode database file PropertyAliases.txt. Short, long, and
jpayne@69 3609 * any other variants are recognized.
jpayne@69 3610 *
jpayne@69 3611 * In addition, this function maps the synthetic names "gcm" /
jpayne@69 3612 * "General_Category_Mask" to the property
jpayne@69 3613 * UCHAR_GENERAL_CATEGORY_MASK. These names are not in
jpayne@69 3614 * PropertyAliases.txt.
jpayne@69 3615 *
jpayne@69 3616 * @param alias the property name to be matched. The name is compared
jpayne@69 3617 * using "loose matching" as described in PropertyAliases.txt.
jpayne@69 3618 *
jpayne@69 3619 * @return a UProperty enum, or UCHAR_INVALID_CODE if the given name
jpayne@69 3620 * does not match any property.
jpayne@69 3621 *
jpayne@69 3622 * @see UProperty
jpayne@69 3623 * @stable ICU 2.4
jpayne@69 3624 */
jpayne@69 3625 U_STABLE UProperty U_EXPORT2
jpayne@69 3626 u_getPropertyEnum(const char* alias);
jpayne@69 3627
jpayne@69 3628 /**
jpayne@69 3629 * Return the Unicode name for a given property value, as given in the
jpayne@69 3630 * Unicode database file PropertyValueAliases.txt.
jpayne@69 3631 *
jpayne@69 3632 * Note: Some of the names in PropertyValueAliases.txt can only be
jpayne@69 3633 * retrieved using UCHAR_GENERAL_CATEGORY_MASK, not
jpayne@69 3634 * UCHAR_GENERAL_CATEGORY. These include: "C" / "Other", "L" /
jpayne@69 3635 * "Letter", "LC" / "Cased_Letter", "M" / "Mark", "N" / "Number", "P"
jpayne@69 3636 * / "Punctuation", "S" / "Symbol", and "Z" / "Separator".
jpayne@69 3637 *
jpayne@69 3638 * @param property UProperty selector constant.
jpayne@69 3639 * Must be UCHAR_BINARY_START<=which<UCHAR_BINARY_LIMIT
jpayne@69 3640 * or UCHAR_INT_START<=which<UCHAR_INT_LIMIT
jpayne@69 3641 * or UCHAR_MASK_START<=which<UCHAR_MASK_LIMIT.
jpayne@69 3642 * If out of range, NULL is returned.
jpayne@69 3643 *
jpayne@69 3644 * @param value selector for a value for the given property. If out
jpayne@69 3645 * of range, NULL is returned. In general, valid values range
jpayne@69 3646 * from 0 up to some maximum. There are a few exceptions:
jpayne@69 3647 * (1.) UCHAR_BLOCK values begin at the non-zero value
jpayne@69 3648 * UBLOCK_BASIC_LATIN. (2.) UCHAR_CANONICAL_COMBINING_CLASS
jpayne@69 3649 * values are not contiguous and range from 0..240. (3.)
jpayne@69 3650 * UCHAR_GENERAL_CATEGORY_MASK values are not values of
jpayne@69 3651 * UCharCategory, but rather mask values produced by
jpayne@69 3652 * U_GET_GC_MASK(). This allows grouped categories such as
jpayne@69 3653 * [:L:] to be represented. Mask values range
jpayne@69 3654 * non-contiguously from 1..U_GC_P_MASK.
jpayne@69 3655 *
jpayne@69 3656 * @param nameChoice selector for which name to get. If out of range,
jpayne@69 3657 * NULL is returned. All values have a long name. Most have
jpayne@69 3658 * a short name, but some do not. Unicode allows for
jpayne@69 3659 * additional names; if present these will be returned by
jpayne@69 3660 * U_LONG_PROPERTY_NAME + i, where i=1, 2,...
jpayne@69 3661
jpayne@69 3662 * @return a pointer to the name, or NULL if either the
jpayne@69 3663 * property or the nameChoice is out of range. If a given
jpayne@69 3664 * nameChoice returns NULL, then all larger values of
jpayne@69 3665 * nameChoice will return NULL, with one exception: if NULL is
jpayne@69 3666 * returned for U_SHORT_PROPERTY_NAME, then
jpayne@69 3667 * U_LONG_PROPERTY_NAME (and higher) may still return a
jpayne@69 3668 * non-NULL value. The returned pointer is valid until
jpayne@69 3669 * u_cleanup() is called.
jpayne@69 3670 *
jpayne@69 3671 * @see UProperty
jpayne@69 3672 * @see UPropertyNameChoice
jpayne@69 3673 * @stable ICU 2.4
jpayne@69 3674 */
jpayne@69 3675 U_STABLE const char* U_EXPORT2
jpayne@69 3676 u_getPropertyValueName(UProperty property,
jpayne@69 3677 int32_t value,
jpayne@69 3678 UPropertyNameChoice nameChoice);
jpayne@69 3679
jpayne@69 3680 /**
jpayne@69 3681 * Return the property value integer for a given value name, as
jpayne@69 3682 * specified in the Unicode database file PropertyValueAliases.txt.
jpayne@69 3683 * Short, long, and any other variants are recognized.
jpayne@69 3684 *
jpayne@69 3685 * Note: Some of the names in PropertyValueAliases.txt will only be
jpayne@69 3686 * recognized with UCHAR_GENERAL_CATEGORY_MASK, not
jpayne@69 3687 * UCHAR_GENERAL_CATEGORY. These include: "C" / "Other", "L" /
jpayne@69 3688 * "Letter", "LC" / "Cased_Letter", "M" / "Mark", "N" / "Number", "P"
jpayne@69 3689 * / "Punctuation", "S" / "Symbol", and "Z" / "Separator".
jpayne@69 3690 *
jpayne@69 3691 * @param property UProperty selector constant.
jpayne@69 3692 * Must be UCHAR_BINARY_START<=which<UCHAR_BINARY_LIMIT
jpayne@69 3693 * or UCHAR_INT_START<=which<UCHAR_INT_LIMIT
jpayne@69 3694 * or UCHAR_MASK_START<=which<UCHAR_MASK_LIMIT.
jpayne@69 3695 * If out of range, UCHAR_INVALID_CODE is returned.
jpayne@69 3696 *
jpayne@69 3697 * @param alias the value name to be matched. The name is compared
jpayne@69 3698 * using "loose matching" as described in
jpayne@69 3699 * PropertyValueAliases.txt.
jpayne@69 3700 *
jpayne@69 3701 * @return a value integer or UCHAR_INVALID_CODE if the given name
jpayne@69 3702 * does not match any value of the given property, or if the
jpayne@69 3703 * property is invalid. Note: UCHAR_GENERAL_CATEGORY_MASK values
jpayne@69 3704 * are not values of UCharCategory, but rather mask values
jpayne@69 3705 * produced by U_GET_GC_MASK(). This allows grouped
jpayne@69 3706 * categories such as [:L:] to be represented.
jpayne@69 3707 *
jpayne@69 3708 * @see UProperty
jpayne@69 3709 * @stable ICU 2.4
jpayne@69 3710 */
jpayne@69 3711 U_STABLE int32_t U_EXPORT2
jpayne@69 3712 u_getPropertyValueEnum(UProperty property,
jpayne@69 3713 const char* alias);
jpayne@69 3714
jpayne@69 3715 /**
jpayne@69 3716 * Determines if the specified character is permissible as the
jpayne@69 3717 * first character in an identifier according to Unicode
jpayne@69 3718 * (The Unicode Standard, Version 3.0, chapter 5.16 Identifiers).
jpayne@69 3719 * True for characters with general categories "L" (letters) and "Nl" (letter numbers).
jpayne@69 3720 *
jpayne@69 3721 * Same as java.lang.Character.isUnicodeIdentifierStart().
jpayne@69 3722 * Same as UCHAR_ID_START
jpayne@69 3723 *
jpayne@69 3724 * @param c the code point to be tested
jpayne@69 3725 * @return TRUE if the code point may start an identifier
jpayne@69 3726 *
jpayne@69 3727 * @see UCHAR_ID_START
jpayne@69 3728 * @see u_isalpha
jpayne@69 3729 * @see u_isIDPart
jpayne@69 3730 * @stable ICU 2.0
jpayne@69 3731 */
jpayne@69 3732 U_STABLE UBool U_EXPORT2
jpayne@69 3733 u_isIDStart(UChar32 c);
jpayne@69 3734
jpayne@69 3735 /**
jpayne@69 3736 * Determines if the specified character is permissible
jpayne@69 3737 * in an identifier according to Java.
jpayne@69 3738 * True for characters with general categories "L" (letters),
jpayne@69 3739 * "Nl" (letter numbers), "Nd" (decimal digits),
jpayne@69 3740 * "Mc" and "Mn" (combining marks), "Pc" (connecting punctuation), and
jpayne@69 3741 * u_isIDIgnorable(c).
jpayne@69 3742 *
jpayne@69 3743 * Same as java.lang.Character.isUnicodeIdentifierPart().
jpayne@69 3744 * Almost the same as Unicode's ID_Continue (UCHAR_ID_CONTINUE)
jpayne@69 3745 * except that Unicode recommends to ignore Cf which is less than
jpayne@69 3746 * u_isIDIgnorable(c).
jpayne@69 3747 *
jpayne@69 3748 * @param c the code point to be tested
jpayne@69 3749 * @return TRUE if the code point may occur in an identifier according to Java
jpayne@69 3750 *
jpayne@69 3751 * @see UCHAR_ID_CONTINUE
jpayne@69 3752 * @see u_isIDStart
jpayne@69 3753 * @see u_isIDIgnorable
jpayne@69 3754 * @stable ICU 2.0
jpayne@69 3755 */
jpayne@69 3756 U_STABLE UBool U_EXPORT2
jpayne@69 3757 u_isIDPart(UChar32 c);
jpayne@69 3758
jpayne@69 3759 /**
jpayne@69 3760 * Determines if the specified character should be regarded
jpayne@69 3761 * as an ignorable character in an identifier,
jpayne@69 3762 * according to Java.
jpayne@69 3763 * True for characters with general category "Cf" (format controls) as well as
jpayne@69 3764 * non-whitespace ISO controls
jpayne@69 3765 * (U+0000..U+0008, U+000E..U+001B, U+007F..U+009F).
jpayne@69 3766 *
jpayne@69 3767 * Same as java.lang.Character.isIdentifierIgnorable().
jpayne@69 3768 *
jpayne@69 3769 * Note that Unicode just recommends to ignore Cf (format controls).
jpayne@69 3770 *
jpayne@69 3771 * @param c the code point to be tested
jpayne@69 3772 * @return TRUE if the code point is ignorable in identifiers according to Java
jpayne@69 3773 *
jpayne@69 3774 * @see UCHAR_DEFAULT_IGNORABLE_CODE_POINT
jpayne@69 3775 * @see u_isIDStart
jpayne@69 3776 * @see u_isIDPart
jpayne@69 3777 * @stable ICU 2.0
jpayne@69 3778 */
jpayne@69 3779 U_STABLE UBool U_EXPORT2
jpayne@69 3780 u_isIDIgnorable(UChar32 c);
jpayne@69 3781
jpayne@69 3782 /**
jpayne@69 3783 * Determines if the specified character is permissible as the
jpayne@69 3784 * first character in a Java identifier.
jpayne@69 3785 * In addition to u_isIDStart(c), true for characters with
jpayne@69 3786 * general categories "Sc" (currency symbols) and "Pc" (connecting punctuation).
jpayne@69 3787 *
jpayne@69 3788 * Same as java.lang.Character.isJavaIdentifierStart().
jpayne@69 3789 *
jpayne@69 3790 * @param c the code point to be tested
jpayne@69 3791 * @return TRUE if the code point may start a Java identifier
jpayne@69 3792 *
jpayne@69 3793 * @see u_isJavaIDPart
jpayne@69 3794 * @see u_isalpha
jpayne@69 3795 * @see u_isIDStart
jpayne@69 3796 * @stable ICU 2.0
jpayne@69 3797 */
jpayne@69 3798 U_STABLE UBool U_EXPORT2
jpayne@69 3799 u_isJavaIDStart(UChar32 c);
jpayne@69 3800
jpayne@69 3801 /**
jpayne@69 3802 * Determines if the specified character is permissible
jpayne@69 3803 * in a Java identifier.
jpayne@69 3804 * In addition to u_isIDPart(c), true for characters with
jpayne@69 3805 * general category "Sc" (currency symbols).
jpayne@69 3806 *
jpayne@69 3807 * Same as java.lang.Character.isJavaIdentifierPart().
jpayne@69 3808 *
jpayne@69 3809 * @param c the code point to be tested
jpayne@69 3810 * @return TRUE if the code point may occur in a Java identifier
jpayne@69 3811 *
jpayne@69 3812 * @see u_isIDIgnorable
jpayne@69 3813 * @see u_isJavaIDStart
jpayne@69 3814 * @see u_isalpha
jpayne@69 3815 * @see u_isdigit
jpayne@69 3816 * @see u_isIDPart
jpayne@69 3817 * @stable ICU 2.0
jpayne@69 3818 */
jpayne@69 3819 U_STABLE UBool U_EXPORT2
jpayne@69 3820 u_isJavaIDPart(UChar32 c);
jpayne@69 3821
jpayne@69 3822 /**
jpayne@69 3823 * The given character is mapped to its lowercase equivalent according to
jpayne@69 3824 * UnicodeData.txt; if the character has no lowercase equivalent, the character
jpayne@69 3825 * itself is returned.
jpayne@69 3826 *
jpayne@69 3827 * Same as java.lang.Character.toLowerCase().
jpayne@69 3828 *
jpayne@69 3829 * This function only returns the simple, single-code point case mapping.
jpayne@69 3830 * Full case mappings should be used whenever possible because they produce
jpayne@69 3831 * better results by working on whole strings.
jpayne@69 3832 * They take into account the string context and the language and can map
jpayne@69 3833 * to a result string with a different length as appropriate.
jpayne@69 3834 * Full case mappings are applied by the string case mapping functions,
jpayne@69 3835 * see ustring.h and the UnicodeString class.
jpayne@69 3836 * See also the User Guide chapter on C/POSIX migration:
jpayne@69 3837 * http://icu-project.org/userguide/posix.html#case_mappings
jpayne@69 3838 *
jpayne@69 3839 * @param c the code point to be mapped
jpayne@69 3840 * @return the Simple_Lowercase_Mapping of the code point, if any;
jpayne@69 3841 * otherwise the code point itself.
jpayne@69 3842 * @stable ICU 2.0
jpayne@69 3843 */
jpayne@69 3844 U_STABLE UChar32 U_EXPORT2
jpayne@69 3845 u_tolower(UChar32 c);
jpayne@69 3846
jpayne@69 3847 /**
jpayne@69 3848 * The given character is mapped to its uppercase equivalent according to UnicodeData.txt;
jpayne@69 3849 * if the character has no uppercase equivalent, the character itself is
jpayne@69 3850 * returned.
jpayne@69 3851 *
jpayne@69 3852 * Same as java.lang.Character.toUpperCase().
jpayne@69 3853 *
jpayne@69 3854 * This function only returns the simple, single-code point case mapping.
jpayne@69 3855 * Full case mappings should be used whenever possible because they produce
jpayne@69 3856 * better results by working on whole strings.
jpayne@69 3857 * They take into account the string context and the language and can map
jpayne@69 3858 * to a result string with a different length as appropriate.
jpayne@69 3859 * Full case mappings are applied by the string case mapping functions,
jpayne@69 3860 * see ustring.h and the UnicodeString class.
jpayne@69 3861 * See also the User Guide chapter on C/POSIX migration:
jpayne@69 3862 * http://icu-project.org/userguide/posix.html#case_mappings
jpayne@69 3863 *
jpayne@69 3864 * @param c the code point to be mapped
jpayne@69 3865 * @return the Simple_Uppercase_Mapping of the code point, if any;
jpayne@69 3866 * otherwise the code point itself.
jpayne@69 3867 * @stable ICU 2.0
jpayne@69 3868 */
jpayne@69 3869 U_STABLE UChar32 U_EXPORT2
jpayne@69 3870 u_toupper(UChar32 c);
jpayne@69 3871
jpayne@69 3872 /**
jpayne@69 3873 * The given character is mapped to its titlecase equivalent
jpayne@69 3874 * according to UnicodeData.txt;
jpayne@69 3875 * if none is defined, the character itself is returned.
jpayne@69 3876 *
jpayne@69 3877 * Same as java.lang.Character.toTitleCase().
jpayne@69 3878 *
jpayne@69 3879 * This function only returns the simple, single-code point case mapping.
jpayne@69 3880 * Full case mappings should be used whenever possible because they produce
jpayne@69 3881 * better results by working on whole strings.
jpayne@69 3882 * They take into account the string context and the language and can map
jpayne@69 3883 * to a result string with a different length as appropriate.
jpayne@69 3884 * Full case mappings are applied by the string case mapping functions,
jpayne@69 3885 * see ustring.h and the UnicodeString class.
jpayne@69 3886 * See also the User Guide chapter on C/POSIX migration:
jpayne@69 3887 * http://icu-project.org/userguide/posix.html#case_mappings
jpayne@69 3888 *
jpayne@69 3889 * @param c the code point to be mapped
jpayne@69 3890 * @return the Simple_Titlecase_Mapping of the code point, if any;
jpayne@69 3891 * otherwise the code point itself.
jpayne@69 3892 * @stable ICU 2.0
jpayne@69 3893 */
jpayne@69 3894 U_STABLE UChar32 U_EXPORT2
jpayne@69 3895 u_totitle(UChar32 c);
jpayne@69 3896
jpayne@69 3897 /**
jpayne@69 3898 * The given character is mapped to its case folding equivalent according to
jpayne@69 3899 * UnicodeData.txt and CaseFolding.txt;
jpayne@69 3900 * if the character has no case folding equivalent, the character
jpayne@69 3901 * itself is returned.
jpayne@69 3902 *
jpayne@69 3903 * This function only returns the simple, single-code point case mapping.
jpayne@69 3904 * Full case mappings should be used whenever possible because they produce
jpayne@69 3905 * better results by working on whole strings.
jpayne@69 3906 * They take into account the string context and the language and can map
jpayne@69 3907 * to a result string with a different length as appropriate.
jpayne@69 3908 * Full case mappings are applied by the string case mapping functions,
jpayne@69 3909 * see ustring.h and the UnicodeString class.
jpayne@69 3910 * See also the User Guide chapter on C/POSIX migration:
jpayne@69 3911 * http://icu-project.org/userguide/posix.html#case_mappings
jpayne@69 3912 *
jpayne@69 3913 * @param c the code point to be mapped
jpayne@69 3914 * @param options Either U_FOLD_CASE_DEFAULT or U_FOLD_CASE_EXCLUDE_SPECIAL_I
jpayne@69 3915 * @return the Simple_Case_Folding of the code point, if any;
jpayne@69 3916 * otherwise the code point itself.
jpayne@69 3917 * @stable ICU 2.0
jpayne@69 3918 */
jpayne@69 3919 U_STABLE UChar32 U_EXPORT2
jpayne@69 3920 u_foldCase(UChar32 c, uint32_t options);
jpayne@69 3921
jpayne@69 3922 /**
jpayne@69 3923 * Returns the decimal digit value of the code point in the
jpayne@69 3924 * specified radix.
jpayne@69 3925 *
jpayne@69 3926 * If the radix is not in the range <code>2<=radix<=36</code> or if the
jpayne@69 3927 * value of <code>c</code> is not a valid digit in the specified
jpayne@69 3928 * radix, <code>-1</code> is returned. A character is a valid digit
jpayne@69 3929 * if at least one of the following is true:
jpayne@69 3930 * <ul>
jpayne@69 3931 * <li>The character has a decimal digit value.
jpayne@69 3932 * Such characters have the general category "Nd" (decimal digit numbers)
jpayne@69 3933 * and a Numeric_Type of Decimal.
jpayne@69 3934 * In this case the value is the character's decimal digit value.</li>
jpayne@69 3935 * <li>The character is one of the uppercase Latin letters
jpayne@69 3936 * <code>'A'</code> through <code>'Z'</code>.
jpayne@69 3937 * In this case the value is <code>c-'A'+10</code>.</li>
jpayne@69 3938 * <li>The character is one of the lowercase Latin letters
jpayne@69 3939 * <code>'a'</code> through <code>'z'</code>.
jpayne@69 3940 * In this case the value is <code>ch-'a'+10</code>.</li>
jpayne@69 3941 * <li>Latin letters from both the ASCII range (0061..007A, 0041..005A)
jpayne@69 3942 * as well as from the Fullwidth ASCII range (FF41..FF5A, FF21..FF3A)
jpayne@69 3943 * are recognized.</li>
jpayne@69 3944 * </ul>
jpayne@69 3945 *
jpayne@69 3946 * Same as java.lang.Character.digit().
jpayne@69 3947 *
jpayne@69 3948 * @param ch the code point to be tested.
jpayne@69 3949 * @param radix the radix.
jpayne@69 3950 * @return the numeric value represented by the character in the
jpayne@69 3951 * specified radix,
jpayne@69 3952 * or -1 if there is no value or if the value exceeds the radix.
jpayne@69 3953 *
jpayne@69 3954 * @see UCHAR_NUMERIC_TYPE
jpayne@69 3955 * @see u_forDigit
jpayne@69 3956 * @see u_charDigitValue
jpayne@69 3957 * @see u_isdigit
jpayne@69 3958 * @stable ICU 2.0
jpayne@69 3959 */
jpayne@69 3960 U_STABLE int32_t U_EXPORT2
jpayne@69 3961 u_digit(UChar32 ch, int8_t radix);
jpayne@69 3962
jpayne@69 3963 /**
jpayne@69 3964 * Determines the character representation for a specific digit in
jpayne@69 3965 * the specified radix. If the value of <code>radix</code> is not a
jpayne@69 3966 * valid radix, or the value of <code>digit</code> is not a valid
jpayne@69 3967 * digit in the specified radix, the null character
jpayne@69 3968 * (<code>U+0000</code>) is returned.
jpayne@69 3969 * <p>
jpayne@69 3970 * The <code>radix</code> argument is valid if it is greater than or
jpayne@69 3971 * equal to 2 and less than or equal to 36.
jpayne@69 3972 * The <code>digit</code> argument is valid if
jpayne@69 3973 * <code>0 <= digit < radix</code>.
jpayne@69 3974 * <p>
jpayne@69 3975 * If the digit is less than 10, then
jpayne@69 3976 * <code>'0' + digit</code> is returned. Otherwise, the value
jpayne@69 3977 * <code>'a' + digit - 10</code> is returned.
jpayne@69 3978 *
jpayne@69 3979 * Same as java.lang.Character.forDigit().
jpayne@69 3980 *
jpayne@69 3981 * @param digit the number to convert to a character.
jpayne@69 3982 * @param radix the radix.
jpayne@69 3983 * @return the <code>char</code> representation of the specified digit
jpayne@69 3984 * in the specified radix.
jpayne@69 3985 *
jpayne@69 3986 * @see u_digit
jpayne@69 3987 * @see u_charDigitValue
jpayne@69 3988 * @see u_isdigit
jpayne@69 3989 * @stable ICU 2.0
jpayne@69 3990 */
jpayne@69 3991 U_STABLE UChar32 U_EXPORT2
jpayne@69 3992 u_forDigit(int32_t digit, int8_t radix);
jpayne@69 3993
jpayne@69 3994 /**
jpayne@69 3995 * Get the "age" of the code point.
jpayne@69 3996 * The "age" is the Unicode version when the code point was first
jpayne@69 3997 * designated (as a non-character or for Private Use)
jpayne@69 3998 * or assigned a character.
jpayne@69 3999 * This can be useful to avoid emitting code points to receiving
jpayne@69 4000 * processes that do not accept newer characters.
jpayne@69 4001 * The data is from the UCD file DerivedAge.txt.
jpayne@69 4002 *
jpayne@69 4003 * @param c The code point.
jpayne@69 4004 * @param versionArray The Unicode version number array, to be filled in.
jpayne@69 4005 *
jpayne@69 4006 * @stable ICU 2.1
jpayne@69 4007 */
jpayne@69 4008 U_STABLE void U_EXPORT2
jpayne@69 4009 u_charAge(UChar32 c, UVersionInfo versionArray);
jpayne@69 4010
jpayne@69 4011 /**
jpayne@69 4012 * Gets the Unicode version information.
jpayne@69 4013 * The version array is filled in with the version information
jpayne@69 4014 * for the Unicode standard that is currently used by ICU.
jpayne@69 4015 * For example, Unicode version 3.1.1 is represented as an array with
jpayne@69 4016 * the values { 3, 1, 1, 0 }.
jpayne@69 4017 *
jpayne@69 4018 * @param versionArray an output array that will be filled in with
jpayne@69 4019 * the Unicode version number
jpayne@69 4020 * @stable ICU 2.0
jpayne@69 4021 */
jpayne@69 4022 U_STABLE void U_EXPORT2
jpayne@69 4023 u_getUnicodeVersion(UVersionInfo versionArray);
jpayne@69 4024
jpayne@69 4025 #if !UCONFIG_NO_NORMALIZATION
jpayne@69 4026 /**
jpayne@69 4027 * Get the FC_NFKC_Closure property string for a character.
jpayne@69 4028 * See Unicode Standard Annex #15 for details, search for "FC_NFKC_Closure"
jpayne@69 4029 * or for "FNC": http://www.unicode.org/reports/tr15/
jpayne@69 4030 *
jpayne@69 4031 * @param c The character (code point) for which to get the FC_NFKC_Closure string.
jpayne@69 4032 * It must be <code>0<=c<=0x10ffff</code>.
jpayne@69 4033 * @param dest Destination address for copying the string.
jpayne@69 4034 * The string will be zero-terminated if possible.
jpayne@69 4035 * If there is no FC_NFKC_Closure string,
jpayne@69 4036 * then the buffer will be set to the empty string.
jpayne@69 4037 * @param destCapacity <code>==sizeof(dest)</code>
jpayne@69 4038 * @param pErrorCode Pointer to a UErrorCode variable.
jpayne@69 4039 * @return The length of the string, or 0 if there is no FC_NFKC_Closure string for this character.
jpayne@69 4040 * If the destCapacity is less than or equal to the length, then the buffer
jpayne@69 4041 * contains the truncated name and the returned length indicates the full
jpayne@69 4042 * length of the name.
jpayne@69 4043 * The length does not include the zero-termination.
jpayne@69 4044 *
jpayne@69 4045 * @stable ICU 2.2
jpayne@69 4046 */
jpayne@69 4047 U_STABLE int32_t U_EXPORT2
jpayne@69 4048 u_getFC_NFKC_Closure(UChar32 c, UChar *dest, int32_t destCapacity, UErrorCode *pErrorCode);
jpayne@69 4049
jpayne@69 4050 #endif
jpayne@69 4051
jpayne@69 4052
jpayne@69 4053 U_CDECL_END
jpayne@69 4054
jpayne@69 4055 #endif /*_UCHAR*/
jpayne@69 4056 /*eof*/