1 /* 2 ********************************************************************** 3 * Copyright (C) 1997-2004, International Business Machines 4 * Corporation and others. All Rights Reserved. 5 ********************************************************************** 6 * 7 * File UCHAR.H 8 * 9 * Modification History: 10 * 11 * Date Name Description 12 * 04/02/97 aliu Creation. 13 * 03/29/99 helena Updated for C APIs. 14 * 4/15/99 Madhu Updated for C Implementation and Javadoc 15 * 5/20/99 Madhu Added the function u_getVersion() 16 * 8/19/1999 srl Upgraded scripts to Unicode 3.0 17 * 8/27/1999 schererm UCharDirection constants: U_... 18 * 11/11/1999 weiv added u_isalnum(), cleaned comments 19 * 01/11/2000 helena Renamed u_getVersion to u_getUnicodeVersion(). 20 ****************************************************************************** 21 */ 22 23 #ifndef UCHAR_H 24 #define UCHAR_H 25 26 #include "unicode/utypes.h" 27 28 U_CDECL_BEGIN 29 30 /*==========================================================================*/ 31 /* Unicode version number */ 32 /*==========================================================================*/ 33 /** 34 * Unicode version number, default for the current ICU version. 35 * The actual Unicode Character Database (UCD) data is stored in uprops.dat 36 * and may be generated from UCD files from a different Unicode version. 37 * Call u_getUnicodeVersion to get the actual Unicode version of the data. 38 * 39 * @see u_getUnicodeVersion 40 * @stable ICU 2.0 41 */ 42 #define U_UNICODE_VERSION "4.0.1" 43 44 /** 45 * \file 46 * \brief C API: Unicode Properties 47 * 48 * This C API provides low-level access to the Unicode Character Database. 49 * In addition to raw property values, some convenience functions calculate 50 * derived properties, for example for Java-style programming. 51 * 52 * Unicode assigns each code point (not just assigned character) values for 53 * many properties. 54 * Most of them are simple boolean flags, or constants from a small enumerated list. 55 * For some properties, values are strings or other relatively more complex types. 56 * 57 * For more information see 58 * "About the Unicode Character Database" (http://www.unicode.org/ucd/) 59 * and the ICU User Guide chapter on Properties (http://oss.software.ibm.com/icu/userguide/properties.html). 60 * 61 * Many functions are designed to match java.lang.Character functions. 62 * See the individual function documentation, 63 * and see the JDK 1.4.1 java.lang.Character documentation 64 * at http://java.sun.com/j2se/1.4.1/docs/api/java/lang/Character.html 65 * 66 * There are also functions that provide easy migration from C/POSIX functions 67 * like isblank(). Their use is generally discouraged because the C/POSIX 68 * standards do not define their semantics beyond the ASCII range, which means 69 * that different implementations exhibit very different behavior. 70 * Instead, Unicode properties should be used directly. 71 * 72 * There are also only a few, broad C/POSIX character classes, and they tend 73 * to be used for conflicting purposes. For example, the "isalpha()" class 74 * is sometimes used to determine word boundaries, while a more sophisticated 75 * approach would at least distinguish initial letters from continuation 76 * characters (the latter including combining marks). 77 * (In ICU, BreakIterator is the most sophisticated API for word boundaries.) 78 * Another example: There is no "istitle()" class for titlecase characters. 79 * 80 * A summary of the behavior of some C/POSIX character classification implementations 81 * for Unicode is available at http://oss.software.ibm.com/cvs/icu/~checkout~/icuhtml/design/posix_classes.html 82 * 83 * <strong>Important</strong>: 84 * The behavior of the ICU C/POSIX-style character classification 85 * functions is subject to change according to discussion of the above summary. 86 * 87 * Note: There are several ICU whitespace functions. 88 * Comparison: 89 * - u_isUWhiteSpace=UCHAR_WHITE_SPACE: Unicode White_Space property; 90 * most of general categories "Z" (separators) + most whitespace ISO controls 91 * (including no-break spaces, but excluding IS1..IS4 and ZWSP) 92 * - u_isWhitespace: Java isWhitespace; Z + whitespace ISO controls but excluding no-break spaces 93 * - u_isJavaSpaceChar: Java isSpaceChar; just Z (including no-break spaces) 94 * - u_isspace: Z + whitespace ISO controls (including no-break spaces) 95 * - u_isblank: "horizontal spaces" = TAB + Zs - ZWSP 96 */ 97 98 /** 99 * Constants. 100 */ 101 102 /** The lowest Unicode code point value. Code points are non-negative. @stable ICU 2.0 */ 103 #define UCHAR_MIN_VALUE 0 104 105 /** 106 * The highest Unicode code point value (scalar value) according to 107 * The Unicode Standard. This is a 21-bit value (20.1 bits, rounded up). 108 * For a single character, UChar32 is a simple type that can hold any code point value. 109 * 110 * @see UChar32 111 * @stable ICU 2.0 112 */ 113 #define UCHAR_MAX_VALUE 0x10ffff 114 115 /** 116 * Get a single-bit bit set (a flag) from a bit number 0..31. 117 * @stable ICU 2.1 118 */ 119 #define U_MASK(x) ((uint32_t)1<<(x)) 120 121 /* 122 * !! Note: Several comments in this file are machine-read by the 123 * genpname tool. These comments describe the correspondence between 124 * icu enum constants and UCD entities. Do not delete them. Update 125 * these comments as needed. 126 * 127 * Any comment of the form "/ *[name]* /" (spaces added) is such 128 * a comment. 129 * 130 * The U_JG_* and U_GC_*_MASK constants are matched by their symbolic 131 * name, which must match PropertyValueAliases.txt. 132 */ 133 134 /** 135 * Selection constants for Unicode properties. 136 * These constants are used in functions like u_hasBinaryProperty to select 137 * one of the Unicode properties. 138 * 139 * The properties APIs are intended to reflect Unicode properties as defined 140 * in the Unicode Character Database (UCD) and Unicode Technical Reports (UTR). 141 * For details about the properties see http://www.unicode.org/ucd/ . 142 * For names of Unicode properties see the UCD file PropertyAliases.txt. 143 * 144 * Important: If ICU is built with UCD files from Unicode versions below, e.g., 3.2, 145 * then properties marked with "new in Unicode 3.2" are not or not fully available. 146 * Check u_getUnicodeVersion to be sure. 147 * 148 * @see u_hasBinaryProperty 149 * @see u_getIntPropertyValue 150 * @see u_getUnicodeVersion 151 * @stable ICU 2.1 152 */ 153 typedef enum UProperty { 154 /* See note !!. Comments of the form "Binary property Dash", 155 "Enumerated property Script", "Double property Numeric_Value", 156 and "String property Age" are read by genpname. */ 157 158 /* Note: Place UCHAR_ALPHABETIC before UCHAR_BINARY_START so that 159 debuggers display UCHAR_ALPHABETIC as the symbolic name for 0, 160 rather than UCHAR_BINARY_START. Likewise for other *_START 161 identifiers. */ 162 163 /** Binary property Alphabetic. Same as u_isUAlphabetic, different from u_isalpha. 164 Lu+Ll+Lt+Lm+Lo+Nl+Other_Alphabetic @stable ICU 2.1 */ 165 UCHAR_ALPHABETIC=0, 166 /** First constant for binary Unicode properties. @stable ICU 2.1 */ 167 UCHAR_BINARY_START=UCHAR_ALPHABETIC, 168 /** Binary property ASCII_Hex_Digit. 0-9 A-F a-f @stable ICU 2.1 */ 169 UCHAR_ASCII_HEX_DIGIT, 170 /** Binary property Bidi_Control. 171 Format controls which have specific functions 172 in the Bidi Algorithm. @stable ICU 2.1 */ 173 UCHAR_BIDI_CONTROL, 174 /** Binary property Bidi_Mirrored. 175 Characters that may change display in RTL text. 176 Same as u_isMirrored. 177 See Bidi Algorithm, UTR 9. @stable ICU 2.1 */ 178 UCHAR_BIDI_MIRRORED, 179 /** Binary property Dash. Variations of dashes. @stable ICU 2.1 */ 180 UCHAR_DASH, 181 /** Binary property Default_Ignorable_Code_Point (new in Unicode 3.2). 182 Ignorable in most processing. 183 <2060..206F, FFF0..FFFB, E0000..E0FFF>+Other_Default_Ignorable_Code_Point+(Cf+Cc+Cs-White_Space) @stable ICU 2.1 */ 184 UCHAR_DEFAULT_IGNORABLE_CODE_POINT, 185 /** Binary property Deprecated (new in Unicode 3.2). 186 The usage of deprecated characters is strongly discouraged. @stable ICU 2.1 */ 187 UCHAR_DEPRECATED, 188 /** Binary property Diacritic. Characters that linguistically modify 189 the meaning of another character to which they apply. @stable ICU 2.1 */ 190 UCHAR_DIACRITIC, 191 /** Binary property Extender. 192 Extend the value or shape of a preceding alphabetic character, 193 e.g., length and iteration marks. @stable ICU 2.1 */ 194 UCHAR_EXTENDER, 195 /** Binary property Full_Composition_Exclusion. 196 CompositionExclusions.txt+Singleton Decompositions+ 197 Non-Starter Decompositions. @stable ICU 2.1 */ 198 UCHAR_FULL_COMPOSITION_EXCLUSION, 199 /** Binary property Grapheme_Base (new in Unicode 3.2). 200 For programmatic determination of grapheme cluster boundaries. 201 [0..10FFFF]-Cc-Cf-Cs-Co-Cn-Zl-Zp-Grapheme_Link-Grapheme_Extend-CGJ @stable ICU 2.1 */ 202 UCHAR_GRAPHEME_BASE, 203 /** Binary property Grapheme_Extend (new in Unicode 3.2). 204 For programmatic determination of grapheme cluster boundaries. 205 Me+Mn+Mc+Other_Grapheme_Extend-Grapheme_Link-CGJ @stable ICU 2.1 */ 206 UCHAR_GRAPHEME_EXTEND, 207 /** Binary property Grapheme_Link (new in Unicode 3.2). 208 For programmatic determination of grapheme cluster boundaries. @stable ICU 2.1 */ 209 UCHAR_GRAPHEME_LINK, 210 /** Binary property Hex_Digit. 211 Characters commonly used for hexadecimal numbers. @stable ICU 2.1 */ 212 UCHAR_HEX_DIGIT, 213 /** Binary property Hyphen. Dashes used to mark connections 214 between pieces of words, plus the Katakana middle dot. @stable ICU 2.1 */ 215 UCHAR_HYPHEN, 216 /** Binary property ID_Continue. 217 Characters that can continue an identifier. 218 DerivedCoreProperties.txt also says "NOTE: Cf characters should be filtered out." 219 ID_Start+Mn+Mc+Nd+Pc @stable ICU 2.1 */ 220 UCHAR_ID_CONTINUE, 221 /** Binary property ID_Start. 222 Characters that can start an identifier. 223 Lu+Ll+Lt+Lm+Lo+Nl @stable ICU 2.1 */ 224 UCHAR_ID_START, 225 /** Binary property Ideographic. 226 CJKV ideographs. @stable ICU 2.1 */ 227 UCHAR_IDEOGRAPHIC, 228 /** Binary property IDS_Binary_Operator (new in Unicode 3.2). 229 For programmatic determination of 230 Ideographic Description Sequences. @stable ICU 2.1 */ 231 UCHAR_IDS_BINARY_OPERATOR, 232 /** Binary property IDS_Trinary_Operator (new in Unicode 3.2). 233 For programmatic determination of 234 Ideographic Description Sequences. @stable ICU 2.1 */ 235 UCHAR_IDS_TRINARY_OPERATOR, 236 /** Binary property Join_Control. 237 Format controls for cursive joining and ligation. @stable ICU 2.1 */ 238 UCHAR_JOIN_CONTROL, 239 /** Binary property Logical_Order_Exception (new in Unicode 3.2). 240 Characters that do not use logical order and 241 require special handling in most processing. @stable ICU 2.1 */ 242 UCHAR_LOGICAL_ORDER_EXCEPTION, 243 /** Binary property Lowercase. Same as u_isULowercase, different from u_islower. 244 Ll+Other_Lowercase @stable ICU 2.1 */ 245 UCHAR_LOWERCASE, 246 /** Binary property Math. Sm+Other_Math @stable ICU 2.1 */ 247 UCHAR_MATH, 248 /** Binary property Noncharacter_Code_Point. 249 Code points that are explicitly defined as illegal 250 for the encoding of characters. @stable ICU 2.1 */ 251 UCHAR_NONCHARACTER_CODE_POINT, 252 /** Binary property Quotation_Mark. @stable ICU 2.1 */ 253 UCHAR_QUOTATION_MARK, 254 /** Binary property Radical (new in Unicode 3.2). 255 For programmatic determination of 256 Ideographic Description Sequences. @stable ICU 2.1 */ 257 UCHAR_RADICAL, 258 /** Binary property Soft_Dotted (new in Unicode 3.2). 259 Characters with a "soft dot", like i or j. 260 An accent placed on these characters causes 261 the dot to disappear. @stable ICU 2.1 */ 262 UCHAR_SOFT_DOTTED, 263 /** Binary property Terminal_Punctuation. 264 Punctuation characters that generally mark 265 the end of textual units. @stable ICU 2.1 */ 266 UCHAR_TERMINAL_PUNCTUATION, 267 /** Binary property Unified_Ideograph (new in Unicode 3.2). 268 For programmatic determination of 269 Ideographic Description Sequences. @stable ICU 2.1 */ 270 UCHAR_UNIFIED_IDEOGRAPH, 271 /** Binary property Uppercase. Same as u_isUUppercase, different from u_isupper. 272 Lu+Other_Uppercase @stable ICU 2.1 */ 273 UCHAR_UPPERCASE, 274 /** Binary property White_Space. 275 Same as u_isUWhiteSpace, different from u_isspace and u_isWhitespace. 276 Space characters+TAB+CR+LF-ZWSP-ZWNBSP @stable ICU 2.1 */ 277 UCHAR_WHITE_SPACE, 278 /** Binary property XID_Continue. 279 ID_Continue modified to allow closure under 280 normalization forms NFKC and NFKD. @stable ICU 2.1 */ 281 UCHAR_XID_CONTINUE, 282 /** Binary property XID_Start. ID_Start modified to allow 283 closure under normalization forms NFKC and NFKD. @stable ICU 2.1 */ 284 UCHAR_XID_START, 285 /** Binary property Case_Sensitive. Either the source of a case 286 mapping or _in_ the target of a case mapping. Not the same as 287 the general category Cased_Letter. @stable ICU 2.6 */ 288 UCHAR_CASE_SENSITIVE, 289 /** Binary property STerm (new in Unicode 4.0.1). 290 Sentence Terminal. Used in UAX #29: Text Boundaries 291 (http://www.unicode.org/reports/tr29/) 292 @draft ICU 3.0 */ 293 UCHAR_S_TERM, 294 /** Binary property Variation_Selector (new in Unicode 4.0.1). 295 Indicates all those characters that qualify as Variation Selectors. 296 For details on the behavior of these characters, 297 see StandardizedVariants.html and 15.6 Variation Selectors. 298 @draft ICU 3.0 */ 299 UCHAR_VARIATION_SELECTOR, 300 /** Binary property NFD_Inert. 301 ICU-specific property for characters that are inert under NFD, 302 i.e., they do not interact with adjacent characters. 303 Used for example in normalizing transforms in incremental mode 304 to find the boundary of safely normalizable text despite possible 305 text additions. 306 307 There is one such property per normalization form. 308 These properties are computed as follows - an inert character is: 309 a) unassigned, or ALL of the following: 310 b) of combining class 0. 311 c) not decomposed by this normalization form. 312 AND if NFC or NFKC, 313 d) can never compose with a previous character. 314 e) can never compose with a following character. 315 f) can never change if another character is added. 316 Example: a-breve might satisfy all but f, but if you 317 add an ogonek it changes to a-ogonek + breve 318 319 See also com.ibm.text.UCD.NFSkippable in the ICU4J repository, 320 and icu/source/common/unormimp.h . 321 @draft ICU 3.0 */ 322 UCHAR_NFD_INERT, 323 /** Binary property NFKD_Inert. 324 ICU-specific property for characters that are inert under NFKD, 325 i.e., they do not interact with adjacent characters. 326 Used for example in normalizing transforms in incremental mode 327 to find the boundary of safely normalizable text despite possible 328 text additions. 329 @see UCHAR_NFD_INERT 330 @draft ICU 3.0 */ 331 UCHAR_NFKD_INERT, 332 /** Binary property NFC_Inert. 333 ICU-specific property for characters that are inert under NFC, 334 i.e., they do not interact with adjacent characters. 335 Used for example in normalizing transforms in incremental mode 336 to find the boundary of safely normalizable text despite possible 337 text additions. 338 @see UCHAR_NFD_INERT 339 @draft ICU 3.0 */ 340 UCHAR_NFC_INERT, 341 /** Binary property NFKC_Inert. 342 ICU-specific property for characters that are inert under NFKC, 343 i.e., they do not interact with adjacent characters. 344 Used for example in normalizing transforms in incremental mode 345 to find the boundary of safely normalizable text despite possible 346 text additions. 347 @see UCHAR_NFD_INERT 348 @draft ICU 3.0 */ 349 UCHAR_NFKC_INERT, 350 /** Binary Property Segment_Starter. 351 ICU-specific property for characters that are starters in terms of 352 Unicode normalization and combining character sequences. 353 They have ccc=0 and do not occur in non-initial position of the 354 canonical decomposition of any character 355 (like " in NFD(a-umlaut) and a Jamo T in an NFD(Hangul LVT)). 356 ICU uses this property for segmenting a string for generating a set of 357 canonically equivalent strings, e.g. for canonical closure while 358 processing collation tailoring rules. 359 @draft ICU 3.0 */ 360 UCHAR_SEGMENT_STARTER, 361 /** One more than the last constant for binary Unicode properties. @stable ICU 2.1 */ 362 UCHAR_BINARY_LIMIT, 363 364 /** Enumerated property Bidi_Class. 365 Same as u_charDirection, returns UCharDirection values. @stable ICU 2.2 */ 366 UCHAR_BIDI_CLASS=0x1000, 367 /** First constant for enumerated/integer Unicode properties. @stable ICU 2.2 */ 368 UCHAR_INT_START=UCHAR_BIDI_CLASS, 369 /** Enumerated property Block. 370 Same as ublock_getCode, returns UBlockCode values. @stable ICU 2.2 */ 371 UCHAR_BLOCK, 372 /** Enumerated property Canonical_Combining_Class. 373 Same as u_getCombiningClass, returns 8-bit numeric values. @stable ICU 2.2 */ 374 UCHAR_CANONICAL_COMBINING_CLASS, 375 /** Enumerated property Decomposition_Type. 376 Returns UDecompositionType values. @stable ICU 2.2 */ 377 UCHAR_DECOMPOSITION_TYPE, 378 /** Enumerated property East_Asian_Width. 379 See http://www.unicode.org/reports/tr11/ 380 Returns UEastAsianWidth values. @stable ICU 2.2 */ 381 UCHAR_EAST_ASIAN_WIDTH, 382 /** Enumerated property General_Category. 383 Same as u_charType, returns UCharCategory values. @stable ICU 2.2 */ 384 UCHAR_GENERAL_CATEGORY, 385 /** Enumerated property Joining_Group. 386 Returns UJoiningGroup values. @stable ICU 2.2 */ 387 UCHAR_JOINING_GROUP, 388 /** Enumerated property Joining_Type. 389 Returns UJoiningType values. @stable ICU 2.2 */ 390 UCHAR_JOINING_TYPE, 391 /** Enumerated property Line_Break. 392 Returns ULineBreak values. @stable ICU 2.2 */ 393 UCHAR_LINE_BREAK, 394 /** Enumerated property Numeric_Type. 395 Returns UNumericType values. @stable ICU 2.2 */ 396 UCHAR_NUMERIC_TYPE, 397 /** Enumerated property Script. 398 Same as uscript_getScript, returns UScriptCode values. @stable ICU 2.2 */ 399 UCHAR_SCRIPT, 400 /** Enumerated property Hangul_Syllable_Type, new in Unicode 4. 401 Returns UHangulSyllableType values. @stable ICU 2.6 */ 402 UCHAR_HANGUL_SYLLABLE_TYPE, 403 /** Enumerated property NFD_Quick_Check. 404 Returns UNormalizationCheckResult values. @draft ICU 3.0 */ 405 UCHAR_NFD_QUICK_CHECK, 406 /** Enumerated property NFKD_Quick_Check. 407 Returns UNormalizationCheckResult values. @draft ICU 3.0 */ 408 UCHAR_NFKD_QUICK_CHECK, 409 /** Enumerated property NFC_Quick_Check. 410 Returns UNormalizationCheckResult values. @draft ICU 3.0 */ 411 UCHAR_NFC_QUICK_CHECK, 412 /** Enumerated property NFKC_Quick_Check. 413 Returns UNormalizationCheckResult values. @draft ICU 3.0 */ 414 UCHAR_NFKC_QUICK_CHECK, 415 /** Enumerated property Lead_Canonical_Combining_Class. 416 ICU-specific property for the ccc of the first code point 417 of the decomposition, or lccc(c)=ccc(NFD(c)[0]). 418 Useful for checking for canonically ordered text; 419 see UNORM_FCD and http://www.unicode.org/notes/tn5/#FCD . 420 Returns 8-bit numeric values like UCHAR_CANONICAL_COMBINING_CLASS. @draft ICU 3.0 */ 421 UCHAR_LEAD_CANONICAL_COMBINING_CLASS, 422 /** Enumerated property Trail_Canonical_Combining_Class. 423 ICU-specific property for the ccc of the last code point 424 of the decomposition, or tccc(c)=ccc(NFD(c)[last]). 425 Useful for checking for canonically ordered text; 426 see UNORM_FCD and http://www.unicode.org/notes/tn5/#FCD . 427 Returns 8-bit numeric values like UCHAR_CANONICAL_COMBINING_CLASS. @draft ICU 3.0 */ 428 UCHAR_TRAIL_CANONICAL_COMBINING_CLASS, 429 /** One more than the last constant for enumerated/integer Unicode properties. @stable ICU 2.2 */ 430 UCHAR_INT_LIMIT, 431 432 /** Bitmask property General_Category_Mask. 433 This is the General_Category property returned as a bit mask. 434 When used in u_getIntPropertyValue(c), same as U_MASK(u_charType(c)), 435 returns bit masks for UCharCategory values where exactly one bit is set. 436 When used with u_getPropertyValueName() and u_getPropertyValueEnum(), 437 a multi-bit mask is used for sets of categories like "Letters". 438 Mask values should be cast to uint32_t. 439 @stable ICU 2.4 */ 440 UCHAR_GENERAL_CATEGORY_MASK=0x2000, 441 /** First constant for bit-mask Unicode properties. @stable ICU 2.4 */ 442 UCHAR_MASK_START=UCHAR_GENERAL_CATEGORY_MASK, 443 /** One more than the last constant for bit-mask Unicode properties. @stable ICU 2.4 */ 444 UCHAR_MASK_LIMIT, 445 446 /** Double property Numeric_Value. 447 Corresponds to u_getNumericValue. @stable ICU 2.4 */ 448 UCHAR_NUMERIC_VALUE=0x3000, 449 /** First constant for double Unicode properties. @stable ICU 2.4 */ 450 UCHAR_DOUBLE_START=UCHAR_NUMERIC_VALUE, 451 /** One more than the last constant for double Unicode properties. @stable ICU 2.4 */ 452 UCHAR_DOUBLE_LIMIT, 453 454 /** String property Age. 455 Corresponds to u_charAge. @stable ICU 2.4 */ 456 UCHAR_AGE=0x4000, 457 /** First constant for string Unicode properties. @stable ICU 2.4 */ 458 UCHAR_STRING_START=UCHAR_AGE, 459 /** String property Bidi_Mirroring_Glyph. 460 Corresponds to u_charMirror. @stable ICU 2.4 */ 461 UCHAR_BIDI_MIRRORING_GLYPH, 462 /** String property Case_Folding. 463 Corresponds to u_strFoldCase in ustring.h. @stable ICU 2.4 */ 464 UCHAR_CASE_FOLDING, 465 /** String property ISO_Comment. 466 Corresponds to u_getISOComment. @stable ICU 2.4 */ 467 UCHAR_ISO_COMMENT, 468 /** String property Lowercase_Mapping. 469 Corresponds to u_strToLower in ustring.h. @stable ICU 2.4 */ 470 UCHAR_LOWERCASE_MAPPING, 471 /** String property Name. 472 Corresponds to u_charName. @stable ICU 2.4 */ 473 UCHAR_NAME, 474 /** String property Simple_Case_Folding. 475 Corresponds to u_foldCase. @stable ICU 2.4 */ 476 UCHAR_SIMPLE_CASE_FOLDING, 477 /** String property Simple_Lowercase_Mapping. 478 Corresponds to u_tolower. @stable ICU 2.4 */ 479 UCHAR_SIMPLE_LOWERCASE_MAPPING, 480 /** String property Simple_Titlecase_Mapping. 481 Corresponds to u_totitle. @stable ICU 2.4 */ 482 UCHAR_SIMPLE_TITLECASE_MAPPING, 483 /** String property Simple_Uppercase_Mapping. 484 Corresponds to u_toupper. @stable ICU 2.4 */ 485 UCHAR_SIMPLE_UPPERCASE_MAPPING, 486 /** String property Titlecase_Mapping. 487 Corresponds to u_strToTitle in ustring.h. @stable ICU 2.4 */ 488 UCHAR_TITLECASE_MAPPING, 489 /** String property Unicode_1_Name. 490 Corresponds to u_charName. @stable ICU 2.4 */ 491 UCHAR_UNICODE_1_NAME, 492 /** String property Uppercase_Mapping. 493 Corresponds to u_strToUpper in ustring.h. @stable ICU 2.4 */ 494 UCHAR_UPPERCASE_MAPPING, 495 /** One more than the last constant for string Unicode properties. @stable ICU 2.4 */ 496 UCHAR_STRING_LIMIT, 497 498 /** Represents a nonexistent or invalid property or property value. @stable ICU 2.4 */ 499 UCHAR_INVALID_CODE = -1 500 } UProperty; 501 502 /** 503 * Data for enumerated Unicode general category types. 504 * See http://www.unicode.org/Public/UNIDATA/UnicodeData.html . 505 * @stable ICU 2.0 506 */ 507 typedef enum UCharCategory 508 { 509 /** See note !!. Comments of the form "Cn" are read by genpname. */ 510 511 /** Non-category for unassigned and non-character code points. @stable ICU 2.0 */ 512 U_UNASSIGNED = 0, 513 /** Cn "Other, Not Assigned (no characters in [UnicodeData.txt] have this property)" (same as U_UNASSIGNED!) @stable ICU 2.0 */ 514 U_GENERAL_OTHER_TYPES = 0, 515 /** Lu @stable ICU 2.0 */ 516 U_UPPERCASE_LETTER = 1, 517 /** Ll @stable ICU 2.0 */ 518 U_LOWERCASE_LETTER = 2, 519 /** Lt @stable ICU 2.0 */ 520 U_TITLECASE_LETTER = 3, 521 /** Lm @stable ICU 2.0 */ 522 U_MODIFIER_LETTER = 4, 523 /** Lo @stable ICU 2.0 */ 524 U_OTHER_LETTER = 5, 525 /** Mn @stable ICU 2.0 */ 526 U_NON_SPACING_MARK = 6, 527 /** Me @stable ICU 2.0 */ 528 U_ENCLOSING_MARK = 7, 529 /** Mc @stable ICU 2.0 */ 530 U_COMBINING_SPACING_MARK = 8, 531 /** Nd @stable ICU 2.0 */ 532 U_DECIMAL_DIGIT_NUMBER = 9, 533 /** Nl @stable ICU 2.0 */ 534 U_LETTER_NUMBER = 10, 535 /** No @stable ICU 2.0 */ 536 U_OTHER_NUMBER = 11, 537 /** Zs @stable ICU 2.0 */ 538 U_SPACE_SEPARATOR = 12, 539 /** Zl @stable ICU 2.0 */ 540 U_LINE_SEPARATOR = 13, 541 /** Zp @stable ICU 2.0 */ 542 U_PARAGRAPH_SEPARATOR = 14, 543 /** Cc @stable ICU 2.0 */ 544 U_CONTROL_CHAR = 15, 545 /** Cf @stable ICU 2.0 */ 546 U_FORMAT_CHAR = 16, 547 /** Co @stable ICU 2.0 */ 548 U_PRIVATE_USE_CHAR = 17, 549 /** Cs @stable ICU 2.0 */ 550 U_SURROGATE = 18, 551 /** Pd @stable ICU 2.0 */ 552 U_DASH_PUNCTUATION = 19, 553 /** Ps @stable ICU 2.0 */ 554 U_START_PUNCTUATION = 20, 555 /** Pe @stable ICU 2.0 */ 556 U_END_PUNCTUATION = 21, 557 /** Pc @stable ICU 2.0 */ 558 U_CONNECTOR_PUNCTUATION = 22, 559 /** Po @stable ICU 2.0 */ 560 U_OTHER_PUNCTUATION = 23, 561 /** Sm @stable ICU 2.0 */ 562 U_MATH_SYMBOL = 24, 563 /** Sc @stable ICU 2.0 */ 564 U_CURRENCY_SYMBOL = 25, 565 /** Sk @stable ICU 2.0 */ 566 U_MODIFIER_SYMBOL = 26, 567 /** So @stable ICU 2.0 */ 568 U_OTHER_SYMBOL = 27, 569 /** Pi @stable ICU 2.0 */ 570 U_INITIAL_PUNCTUATION = 28, 571 /** Pf @stable ICU 2.0 */ 572 U_FINAL_PUNCTUATION = 29, 573 /** One higher than the last enum UCharCategory constant. @stable ICU 2.0 */ 574 U_CHAR_CATEGORY_COUNT 575 } UCharCategory; 576 577 /** 578 * U_GC_XX_MASK constants are bit flags corresponding to Unicode 579 * general category values. 580 * For each category, the nth bit is set if the numeric value of the 581 * corresponding UCharCategory constant is n. 582 * 583 * There are also some U_GC_Y_MASK constants for groups of general categories 584 * like L for all letter categories. 585 * 586 * @see u_charType 587 * @see U_GET_GC_MASK 588 * @see UCharCategory 589 * @stable ICU 2.1 590 */ 591 #define U_GC_CN_MASK U_MASK(U_GENERAL_OTHER_TYPES) 592 593 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 594 #define U_GC_LU_MASK U_MASK(U_UPPERCASE_LETTER) 595 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 596 #define U_GC_LL_MASK U_MASK(U_LOWERCASE_LETTER) 597 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 598 #define U_GC_LT_MASK U_MASK(U_TITLECASE_LETTER) 599 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 600 #define U_GC_LM_MASK U_MASK(U_MODIFIER_LETTER) 601 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 602 #define U_GC_LO_MASK U_MASK(U_OTHER_LETTER) 603 604 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 605 #define U_GC_MN_MASK U_MASK(U_NON_SPACING_MARK) 606 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 607 #define U_GC_ME_MASK U_MASK(U_ENCLOSING_MARK) 608 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 609 #define U_GC_MC_MASK U_MASK(U_COMBINING_SPACING_MARK) 610 611 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 612 #define U_GC_ND_MASK U_MASK(U_DECIMAL_DIGIT_NUMBER) 613 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 614 #define U_GC_NL_MASK U_MASK(U_LETTER_NUMBER) 615 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 616 #define U_GC_NO_MASK U_MASK(U_OTHER_NUMBER) 617 618 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 619 #define U_GC_ZS_MASK U_MASK(U_SPACE_SEPARATOR) 620 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 621 #define U_GC_ZL_MASK U_MASK(U_LINE_SEPARATOR) 622 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 623 #define U_GC_ZP_MASK U_MASK(U_PARAGRAPH_SEPARATOR) 624 625 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 626 #define U_GC_CC_MASK U_MASK(U_CONTROL_CHAR) 627 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 628 #define U_GC_CF_MASK U_MASK(U_FORMAT_CHAR) 629 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 630 #define U_GC_CO_MASK U_MASK(U_PRIVATE_USE_CHAR) 631 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 632 #define U_GC_CS_MASK U_MASK(U_SURROGATE) 633 634 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 635 #define U_GC_PD_MASK U_MASK(U_DASH_PUNCTUATION) 636 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 637 #define U_GC_PS_MASK U_MASK(U_START_PUNCTUATION) 638 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 639 #define U_GC_PE_MASK U_MASK(U_END_PUNCTUATION) 640 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 641 #define U_GC_PC_MASK U_MASK(U_CONNECTOR_PUNCTUATION) 642 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 643 #define U_GC_PO_MASK U_MASK(U_OTHER_PUNCTUATION) 644 645 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 646 #define U_GC_SM_MASK U_MASK(U_MATH_SYMBOL) 647 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 648 #define U_GC_SC_MASK U_MASK(U_CURRENCY_SYMBOL) 649 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 650 #define U_GC_SK_MASK U_MASK(U_MODIFIER_SYMBOL) 651 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 652 #define U_GC_SO_MASK U_MASK(U_OTHER_SYMBOL) 653 654 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 655 #define U_GC_PI_MASK U_MASK(U_INITIAL_PUNCTUATION) 656 /** Mask constant for a UCharCategory. @stable ICU 2.1 */ 657 #define U_GC_PF_MASK U_MASK(U_FINAL_PUNCTUATION) 658 659 660 /** Mask constant for multiple UCharCategory bits (L Letters). @stable ICU 2.1 */ 661 #define U_GC_L_MASK \ 662 (U_GC_LU_MASK|U_GC_LL_MASK|U_GC_LT_MASK|U_GC_LM_MASK|U_GC_LO_MASK) 663 664 /** Mask constant for multiple UCharCategory bits (LC Cased Letters). @stable ICU 2.1 */ 665 #define U_GC_LC_MASK \ 666 (U_GC_LU_MASK|U_GC_LL_MASK|U_GC_LT_MASK) 667 668 /** Mask constant for multiple UCharCategory bits (M Marks). @stable ICU 2.1 */ 669 #define U_GC_M_MASK (U_GC_MN_MASK|U_GC_ME_MASK|U_GC_MC_MASK) 670 671 /** Mask constant for multiple UCharCategory bits (N Numbers). @stable ICU 2.1 */ 672 #define U_GC_N_MASK (U_GC_ND_MASK|U_GC_NL_MASK|U_GC_NO_MASK) 673 674 /** Mask constant for multiple UCharCategory bits (Z Separators). @stable ICU 2.1 */ 675 #define U_GC_Z_MASK (U_GC_ZS_MASK|U_GC_ZL_MASK|U_GC_ZP_MASK) 676 677 /** Mask constant for multiple UCharCategory bits (C Others). @stable ICU 2.1 */ 678 #define U_GC_C_MASK \ 679 (U_GC_CN_MASK|U_GC_CC_MASK|U_GC_CF_MASK|U_GC_CO_MASK|U_GC_CS_MASK) 680 681 /** Mask constant for multiple UCharCategory bits (P Punctuation). @stable ICU 2.1 */ 682 #define U_GC_P_MASK \ 683 (U_GC_PD_MASK|U_GC_PS_MASK|U_GC_PE_MASK|U_GC_PC_MASK|U_GC_PO_MASK| \ 684 U_GC_PI_MASK|U_GC_PF_MASK) 685 686 /** Mask constant for multiple UCharCategory bits (S Symbols). @stable ICU 2.1 */ 687 #define U_GC_S_MASK (U_GC_SM_MASK|U_GC_SC_MASK|U_GC_SK_MASK|U_GC_SO_MASK) 688 689 /** 690 * This specifies the language directional property of a character set. 691 * @stable ICU 2.0 692 */ 693 typedef enum UCharDirection { 694 /** See note !!. Comments of the form "EN" are read by genpname. */ 695 696 /** L @stable ICU 2.0 */ 697 U_LEFT_TO_RIGHT = 0, 698 /** R @stable ICU 2.0 */ 699 U_RIGHT_TO_LEFT = 1, 700 /** EN @stable ICU 2.0 */ 701 U_EUROPEAN_NUMBER = 2, 702 /** ES @stable ICU 2.0 */ 703 U_EUROPEAN_NUMBER_SEPARATOR = 3, 704 /** ET @stable ICU 2.0 */ 705 U_EUROPEAN_NUMBER_TERMINATOR = 4, 706 /** AN @stable ICU 2.0 */ 707 U_ARABIC_NUMBER = 5, 708 /** CS @stable ICU 2.0 */ 709 U_COMMON_NUMBER_SEPARATOR = 6, 710 /** B @stable ICU 2.0 */ 711 U_BLOCK_SEPARATOR = 7, 712 /** S @stable ICU 2.0 */ 713 U_SEGMENT_SEPARATOR = 8, 714 /** WS @stable ICU 2.0 */ 715 U_WHITE_SPACE_NEUTRAL = 9, 716 /** ON @stable ICU 2.0 */ 717 U_OTHER_NEUTRAL = 10, 718 /** LRE @stable ICU 2.0 */ 719 U_LEFT_TO_RIGHT_EMBEDDING = 11, 720 /** LRO @stable ICU 2.0 */ 721 U_LEFT_TO_RIGHT_OVERRIDE = 12, 722 /** AL @stable ICU 2.0 */ 723 U_RIGHT_TO_LEFT_ARABIC = 13, 724 /** RLE @stable ICU 2.0 */ 725 U_RIGHT_TO_LEFT_EMBEDDING = 14, 726 /** RLO @stable ICU 2.0 */ 727 U_RIGHT_TO_LEFT_OVERRIDE = 15, 728 /** PDF @stable ICU 2.0 */ 729 U_POP_DIRECTIONAL_FORMAT = 16, 730 /** NSM @stable ICU 2.0 */ 731 U_DIR_NON_SPACING_MARK = 17, 732 /** BN @stable ICU 2.0 */ 733 U_BOUNDARY_NEUTRAL = 18, 734 /** @stable ICU 2.0 */ 735 U_CHAR_DIRECTION_COUNT 736 } UCharDirection; 737 738 /** 739 * Constants for Unicode blocks, see the Unicode Data file Blocks.txt 740 * @stable ICU 2.0 741 */ 742 enum UBlockCode { 743 744 /** New No_Block value in Unicode 4. @stable ICU 2.6 */ 745 UBLOCK_NO_BLOCK = 0, /*[none]*/ /* Special range indicating No_Block */ 746 747 /** @stable ICU 2.0 */ 748 UBLOCK_BASIC_LATIN = 1, /*[0000]*/ /*See note !!*/ 749 750 /** @stable ICU 2.0 */ 751 UBLOCK_LATIN_1_SUPPLEMENT=2, /*[0080]*/ 752 753 /** @stable ICU 2.0 */ 754 UBLOCK_LATIN_EXTENDED_A =3, /*[0100]*/ 755 756 /** @stable ICU 2.0 */ 757 UBLOCK_LATIN_EXTENDED_B =4, /*[0180]*/ 758 759 /** @stable ICU 2.0 */ 760 UBLOCK_IPA_EXTENSIONS =5, /*[0250]*/ 761 762 /** @stable ICU 2.0 */ 763 UBLOCK_SPACING_MODIFIER_LETTERS =6, /*[02B0]*/ 764 765 /** @stable ICU 2.0 */ 766 UBLOCK_COMBINING_DIACRITICAL_MARKS =7, /*[0300]*/ 767 768 /** 769 * Unicode 3.2 renames this block to "Greek and Coptic". 770 * @stable ICU 2.0 771 */ 772 UBLOCK_GREEK =8, /*[0370]*/ 773 774 /** @stable ICU 2.0 */ 775 UBLOCK_CYRILLIC =9, /*[0400]*/ 776 777 /** @stable ICU 2.0 */ 778 UBLOCK_ARMENIAN =10, /*[0530]*/ 779 780 /** @stable ICU 2.0 */ 781 UBLOCK_HEBREW =11, /*[0590]*/ 782 783 /** @stable ICU 2.0 */ 784 UBLOCK_ARABIC =12, /*[0600]*/ 785 786 /** @stable ICU 2.0 */ 787 UBLOCK_SYRIAC =13, /*[0700]*/ 788 789 /** @stable ICU 2.0 */ 790 UBLOCK_THAANA =14, /*[0780]*/ 791 792 /** @stable ICU 2.0 */ 793 UBLOCK_DEVANAGARI =15, /*[0900]*/ 794 795 /** @stable ICU 2.0 */ 796 UBLOCK_BENGALI =16, /*[0980]*/ 797 798 /** @stable ICU 2.0 */ 799 UBLOCK_GURMUKHI =17, /*[0A00]*/ 800 801 /** @stable ICU 2.0 */ 802 UBLOCK_GUJARATI =18, /*[0A80]*/ 803 804 /** @stable ICU 2.0 */ 805 UBLOCK_ORIYA =19, /*[0B00]*/ 806 807 /** @stable ICU 2.0 */ 808 UBLOCK_TAMIL =20, /*[0B80]*/ 809 810 /** @stable ICU 2.0 */ 811 UBLOCK_TELUGU =21, /*[0C00]*/ 812 813 /** @stable ICU 2.0 */ 814 UBLOCK_KANNADA =22, /*[0C80]*/ 815 816 /** @stable ICU 2.0 */ 817 UBLOCK_MALAYALAM =23, /*[0D00]*/ 818 819 /** @stable ICU 2.0 */ 820 UBLOCK_SINHALA =24, /*[0D80]*/ 821 822 /** @stable ICU 2.0 */ 823 UBLOCK_THAI =25, /*[0E00]*/ 824 825 /** @stable ICU 2.0 */ 826 UBLOCK_LAO =26, /*[0E80]*/ 827 828 /** @stable ICU 2.0 */ 829 UBLOCK_TIBETAN =27, /*[0F00]*/ 830 831 /** @stable ICU 2.0 */ 832 UBLOCK_MYANMAR =28, /*[1000]*/ 833 834 /** @stable ICU 2.0 */ 835 UBLOCK_GEORGIAN =29, /*[10A0]*/ 836 837 /** @stable ICU 2.0 */ 838 UBLOCK_HANGUL_JAMO =30, /*[1100]*/ 839 840 /** @stable ICU 2.0 */ 841 UBLOCK_ETHIOPIC =31, /*[1200]*/ 842 843 /** @stable ICU 2.0 */ 844 UBLOCK_CHEROKEE =32, /*[13A0]*/ 845 846 /** @stable ICU 2.0 */ 847 UBLOCK_UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS =33, /*[1400]*/ 848 849 /** @stable ICU 2.0 */ 850 UBLOCK_OGHAM =34, /*[1680]*/ 851 852 /** @stable ICU 2.0 */ 853 UBLOCK_RUNIC =35, /*[16A0]*/ 854 855 /** @stable ICU 2.0 */ 856 UBLOCK_KHMER =36, /*[1780]*/ 857 858 /** @stable ICU 2.0 */ 859 UBLOCK_MONGOLIAN =37, /*[1800]*/ 860 861 /** @stable ICU 2.0 */ 862 UBLOCK_LATIN_EXTENDED_ADDITIONAL =38, /*[1E00]*/ 863 864 /** @stable ICU 2.0 */ 865 UBLOCK_GREEK_EXTENDED =39, /*[1F00]*/ 866 867 /** @stable ICU 2.0 */ 868 UBLOCK_GENERAL_PUNCTUATION =40, /*[2000]*/ 869 870 /** @stable ICU 2.0 */ 871 UBLOCK_SUPERSCRIPTS_AND_SUBSCRIPTS =41, /*[2070]*/ 872 873 /** @stable ICU 2.0 */ 874 UBLOCK_CURRENCY_SYMBOLS =42, /*[20A0]*/ 875 876 /** 877 * Unicode 3.2 renames this block to "Combining Diacritical Marks for Symbols". 878 * @stable ICU 2.0 879 */ 880 UBLOCK_COMBINING_MARKS_FOR_SYMBOLS =43, /*[20D0]*/ 881 882 /** @stable ICU 2.0 */ 883 UBLOCK_LETTERLIKE_SYMBOLS =44, /*[2100]*/ 884 885 /** @stable ICU 2.0 */ 886 UBLOCK_NUMBER_FORMS =45, /*[2150]*/ 887 888 /** @stable ICU 2.0 */ 889 UBLOCK_ARROWS =46, /*[2190]*/ 890 891 /** @stable ICU 2.0 */ 892 UBLOCK_MATHEMATICAL_OPERATORS =47, /*[2200]*/ 893 894 /** @stable ICU 2.0 */ 895 UBLOCK_MISCELLANEOUS_TECHNICAL =48, /*[2300]*/ 896 897 /** @stable ICU 2.0 */ 898 UBLOCK_CONTROL_PICTURES =49, /*[2400]*/ 899 900 /** @stable ICU 2.0 */ 901 UBLOCK_OPTICAL_CHARACTER_RECOGNITION =50, /*[2440]*/ 902 903 /** @stable ICU 2.0 */ 904 UBLOCK_ENCLOSED_ALPHANUMERICS =51, /*[2460]*/ 905 906 /** @stable ICU 2.0 */ 907 UBLOCK_BOX_DRAWING =52, /*[2500]*/ 908 909 /** @stable ICU 2.0 */ 910 UBLOCK_BLOCK_ELEMENTS =53, /*[2580]*/ 911 912 /** @stable ICU 2.0 */ 913 UBLOCK_GEOMETRIC_SHAPES =54, /*[25A0]*/ 914 915 /** @stable ICU 2.0 */ 916 UBLOCK_MISCELLANEOUS_SYMBOLS =55, /*[2600]*/ 917 918 /** @stable ICU 2.0 */ 919 UBLOCK_DINGBATS =56, /*[2700]*/ 920 921 /** @stable ICU 2.0 */ 922 UBLOCK_BRAILLE_PATTERNS =57, /*[2800]*/ 923 924 /** @stable ICU 2.0 */ 925 UBLOCK_CJK_RADICALS_SUPPLEMENT =58, /*[2E80]*/ 926 927 /** @stable ICU 2.0 */ 928 UBLOCK_KANGXI_RADICALS =59, /*[2F00]*/ 929 930 /** @stable ICU 2.0 */ 931 UBLOCK_IDEOGRAPHIC_DESCRIPTION_CHARACTERS =60, /*[2FF0]*/ 932 933 /** @stable ICU 2.0 */ 934 UBLOCK_CJK_SYMBOLS_AND_PUNCTUATION =61, /*[3000]*/ 935 936 /** @stable ICU 2.0 */ 937 UBLOCK_HIRAGANA =62, /*[3040]*/ 938 939 /** @stable ICU 2.0 */ 940 UBLOCK_KATAKANA =63, /*[30A0]*/ 941 942 /** @stable ICU 2.0 */ 943 UBLOCK_BOPOMOFO =64, /*[3100]*/ 944 945 /** @stable ICU 2.0 */ 946 UBLOCK_HANGUL_COMPATIBILITY_JAMO =65, /*[3130]*/ 947 948 /** @stable ICU 2.0 */ 949 UBLOCK_KANBUN =66, /*[3190]*/ 950 951 /** @stable ICU 2.0 */ 952 UBLOCK_BOPOMOFO_EXTENDED =67, /*[31A0]*/ 953 954 /** @stable ICU 2.0 */ 955 UBLOCK_ENCLOSED_CJK_LETTERS_AND_MONTHS =68, /*[3200]*/ 956 957 /** @stable ICU 2.0 */ 958 UBLOCK_CJK_COMPATIBILITY =69, /*[3300]*/ 959 960 /** @stable ICU 2.0 */ 961 UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_A =70, /*[3400]*/ 962 963 /** @stable ICU 2.0 */ 964 UBLOCK_CJK_UNIFIED_IDEOGRAPHS =71, /*[4E00]*/ 965 966 /** @stable ICU 2.0 */ 967 UBLOCK_YI_SYLLABLES =72, /*[A000]*/ 968 969 /** @stable ICU 2.0 */ 970 UBLOCK_YI_RADICALS =73, /*[A490]*/ 971 972 /** @stable ICU 2.0 */ 973 UBLOCK_HANGUL_SYLLABLES =74, /*[AC00]*/ 974 975 /** @stable ICU 2.0 */ 976 UBLOCK_HIGH_SURROGATES =75, /*[D800]*/ 977 978 /** @stable ICU 2.0 */ 979 UBLOCK_HIGH_PRIVATE_USE_SURROGATES =76, /*[DB80]*/ 980 981 /** @stable ICU 2.0 */ 982 UBLOCK_LOW_SURROGATES =77, /*[DC00]*/ 983 984 /** 985 * Same as UBLOCK_PRIVATE_USE_AREA. 986 * Until Unicode 3.1.1, the corresponding block name was "Private Use", 987 * and multiple code point ranges had this block. 988 * Unicode 3.2 renames the block for the BMP PUA to "Private Use Area" and 989 * adds separate blocks for the supplementary PUAs. 990 * 991 * @stable ICU 2.0 992 */ 993 UBLOCK_PRIVATE_USE = 78, 994 /** 995 * Same as UBLOCK_PRIVATE_USE. 996 * Until Unicode 3.1.1, the corresponding block name was "Private Use", 997 * and multiple code point ranges had this block. 998 * Unicode 3.2 renames the block for the BMP PUA to "Private Use Area" and 999 * adds separate blocks for the supplementary PUAs. 1000 * 1001 * @stable ICU 2.0 1002 */ 1003 UBLOCK_PRIVATE_USE_AREA =UBLOCK_PRIVATE_USE, /*[E000]*/ 1004 1005 /** @stable ICU 2.0 */ 1006 UBLOCK_CJK_COMPATIBILITY_IDEOGRAPHS =79, /*[F900]*/ 1007 1008 /** @stable ICU 2.0 */ 1009 UBLOCK_ALPHABETIC_PRESENTATION_FORMS =80, /*[FB00]*/ 1010 1011 /** @stable ICU 2.0 */ 1012 UBLOCK_ARABIC_PRESENTATION_FORMS_A =81, /*[FB50]*/ 1013 1014 /** @stable ICU 2.0 */ 1015 UBLOCK_COMBINING_HALF_MARKS =82, /*[FE20]*/ 1016 1017 /** @stable ICU 2.0 */ 1018 UBLOCK_CJK_COMPATIBILITY_FORMS =83, /*[FE30]*/ 1019 1020 /** @stable ICU 2.0 */ 1021 UBLOCK_SMALL_FORM_VARIANTS =84, /*[FE50]*/ 1022 1023 /** @stable ICU 2.0 */ 1024 UBLOCK_ARABIC_PRESENTATION_FORMS_B =85, /*[FE70]*/ 1025 1026 /** @stable ICU 2.0 */ 1027 UBLOCK_SPECIALS =86, /*[FFF0]*/ 1028 1029 /** @stable ICU 2.0 */ 1030 UBLOCK_HALFWIDTH_AND_FULLWIDTH_FORMS =87, /*[FF00]*/ 1031 1032 /* New blocks in Unicode 3.1 */ 1033 1034 /** @stable ICU 2.0 */ 1035 UBLOCK_OLD_ITALIC = 88 , /*[10300]*/ 1036 /** @stable ICU 2.0 */ 1037 UBLOCK_GOTHIC = 89 , /*[10330]*/ 1038 /** @stable ICU 2.0 */ 1039 UBLOCK_DESERET = 90 , /*[10400]*/ 1040 /** @stable ICU 2.0 */ 1041 UBLOCK_BYZANTINE_MUSICAL_SYMBOLS = 91 , /*[1D000]*/ 1042 /** @stable ICU 2.0 */ 1043 UBLOCK_MUSICAL_SYMBOLS = 92 , /*[1D100]*/ 1044 /** @stable ICU 2.0 */ 1045 UBLOCK_MATHEMATICAL_ALPHANUMERIC_SYMBOLS = 93 , /*[1D400]*/ 1046 /** @stable ICU 2.0 */ 1047 UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_B = 94 , /*[20000]*/ 1048 /** @stable ICU 2.0 */ 1049 UBLOCK_CJK_COMPATIBILITY_IDEOGRAPHS_SUPPLEMENT = 95 , /*[2F800]*/ 1050 /** @stable ICU 2.0 */ 1051 UBLOCK_TAGS = 96, /*[E0000]*/ 1052 1053 /* New blocks in Unicode 3.2 */ 1054 1055 /** 1056 * Unicode 4.0.1 renames the "Cyrillic Supplementary" block to "Cyrillic Supplement". 1057 * @stable ICU 2.2 1058 */ 1059 UBLOCK_CYRILLIC_SUPPLEMENTARY = 97, 1060 /** @draft ICU 3.0 */ 1061 UBLOCK_CYRILLIC_SUPPLEMENT = UBLOCK_CYRILLIC_SUPPLEMENTARY, /*[0500]*/ 1062 /** @stable ICU 2.2 */ 1063 UBLOCK_TAGALOG = 98, /*[1700]*/ 1064 /** @stable ICU 2.2 */ 1065 UBLOCK_HANUNOO = 99, /*[1720]*/ 1066 /** @stable ICU 2.2 */ 1067 UBLOCK_BUHID = 100, /*[1740]*/ 1068 /** @stable ICU 2.2 */ 1069 UBLOCK_TAGBANWA = 101, /*[1760]*/ 1070 /** @stable ICU 2.2 */ 1071 UBLOCK_MISCELLANEOUS_MATHEMATICAL_SYMBOLS_A = 102, /*[27C0]*/ 1072 /** @stable ICU 2.2 */ 1073 UBLOCK_SUPPLEMENTAL_ARROWS_A = 103, /*[27F0]*/ 1074 /** @stable ICU 2.2 */ 1075 UBLOCK_SUPPLEMENTAL_ARROWS_B = 104, /*[2900]*/ 1076 /** @stable ICU 2.2 */ 1077 UBLOCK_MISCELLANEOUS_MATHEMATICAL_SYMBOLS_B = 105, /*[2980]*/ 1078 /** @stable ICU 2.2 */ 1079 UBLOCK_SUPPLEMENTAL_MATHEMATICAL_OPERATORS = 106, /*[2A00]*/ 1080 /** @stable ICU 2.2 */ 1081 UBLOCK_KATAKANA_PHONETIC_EXTENSIONS = 107, /*[31F0]*/ 1082 /** @stable ICU 2.2 */ 1083 UBLOCK_VARIATION_SELECTORS = 108, /*[FE00]*/ 1084 /** @stable ICU 2.2 */ 1085 UBLOCK_SUPPLEMENTARY_PRIVATE_USE_AREA_A = 109, /*[F0000]*/ 1086 /** @stable ICU 2.2 */ 1087 UBLOCK_SUPPLEMENTARY_PRIVATE_USE_AREA_B = 110, /*[100000]*/ 1088 1089 /* New blocks in Unicode 4 */ 1090 1091 /** @stable ICU 2.6 */ 1092 UBLOCK_LIMBU = 111, /*[1900]*/ 1093 /** @stable ICU 2.6 */ 1094 UBLOCK_TAI_LE = 112, /*[1950]*/ 1095 /** @stable ICU 2.6 */ 1096 UBLOCK_KHMER_SYMBOLS = 113, /*[19E0]*/ 1097 /** @stable ICU 2.6 */ 1098 UBLOCK_PHONETIC_EXTENSIONS = 114, /*[1D00]*/ 1099 /** @stable ICU 2.6 */ 1100 UBLOCK_MISCELLANEOUS_SYMBOLS_AND_ARROWS = 115, /*[2B00]*/ 1101 /** @stable ICU 2.6 */ 1102 UBLOCK_YIJING_HEXAGRAM_SYMBOLS = 116, /*[4DC0]*/ 1103 /** @stable ICU 2.6 */ 1104 UBLOCK_LINEAR_B_SYLLABARY = 117, /*[10000]*/ 1105 /** @stable ICU 2.6 */ 1106 UBLOCK_LINEAR_B_IDEOGRAMS = 118, /*[10080]*/ 1107 /** @stable ICU 2.6 */ 1108 UBLOCK_AEGEAN_NUMBERS = 119, /*[10100]*/ 1109 /** @stable ICU 2.6 */ 1110 UBLOCK_UGARITIC = 120, /*[10380]*/ 1111 /** @stable ICU 2.6 */ 1112 UBLOCK_SHAVIAN = 121, /*[10450]*/ 1113 /** @stable ICU 2.6 */ 1114 UBLOCK_OSMANYA = 122, /*[10480]*/ 1115 /** @stable ICU 2.6 */ 1116 UBLOCK_CYPRIOT_SYLLABARY = 123, /*[10800]*/ 1117 /** @stable ICU 2.6 */ 1118 UBLOCK_TAI_XUAN_JING_SYMBOLS = 124, /*[1D300]*/ 1119 /** @stable ICU 2.6 */ 1120 UBLOCK_VARIATION_SELECTORS_SUPPLEMENT = 125, /*[E0100]*/ 1121 1122 /** @stable ICU 2.0 */ 1123 UBLOCK_COUNT, 1124 1125 /** @stable ICU 2.0 */ 1126 UBLOCK_INVALID_CODE=-1 1127 }; 1128 1129 /** @stable ICU 2.0 */ 1130 typedef enum UBlockCode UBlockCode; 1131 1132 /** 1133 * East Asian Width constants. 1134 * 1135 * @see UCHAR_EAST_ASIAN_WIDTH 1136 * @see u_getIntPropertyValue 1137 * @stable ICU 2.2 1138 */ 1139 typedef enum UEastAsianWidth { 1140 U_EA_NEUTRAL, /*[N]*/ /*See note !!*/ 1141 U_EA_AMBIGUOUS, /*[A]*/ 1142 U_EA_HALFWIDTH, /*[H]*/ 1143 U_EA_FULLWIDTH, /*[F]*/ 1144 U_EA_NARROW, /*[Na]*/ 1145 U_EA_WIDE, /*[W]*/ 1146 U_EA_COUNT 1147 } UEastAsianWidth; 1148 /* 1149 * Implementation note: 1150 * Keep UEastAsianWidth constant values in sync with names list in genprops/props2.c. 1151 */ 1152 1153 /** 1154 * Selector constants for u_charName(). 1155 * u_charName() returns the "modern" name of a 1156 * Unicode character; or the name that was defined in 1157 * Unicode version 1.0, before the Unicode standard merged 1158 * with ISO-10646; or an "extended" name that gives each 1159 * Unicode code point a unique name. 1160 * 1161 * @see u_charName 1162 * @stable ICU 2.0 1163 */ 1164 typedef enum UCharNameChoice { 1165 U_UNICODE_CHAR_NAME, 1166 U_UNICODE_10_CHAR_NAME, 1167 U_EXTENDED_CHAR_NAME, 1168 U_CHAR_NAME_CHOICE_COUNT 1169 } UCharNameChoice; 1170 1171 /** 1172 * Selector constants for u_getPropertyName() and 1173 * u_getPropertyValueName(). These selectors are used to choose which 1174 * name is returned for a given property or value. All properties and 1175 * values have a long name. Most have a short name, but some do not. 1176 * Unicode allows for additional names, beyond the long and short 1177 * name, which would be indicated by U_LONG_PROPERTY_NAME + i, where 1178 * i=1, 2,... 1179 * 1180 * @see u_getPropertyName() 1181 * @see u_getPropertyValueName() 1182 * @stable ICU 2.4 1183 */ 1184 typedef enum UPropertyNameChoice { 1185 U_SHORT_PROPERTY_NAME, 1186 U_LONG_PROPERTY_NAME, 1187 U_PROPERTY_NAME_CHOICE_COUNT 1188 } UPropertyNameChoice; 1189 1190 /** 1191 * Decomposition Type constants. 1192 * 1193 * @see UCHAR_DECOMPOSITION_TYPE 1194 * @stable ICU 2.2 1195 */ 1196 typedef enum UDecompositionType { 1197 U_DT_NONE, /*[none]*/ /*See note !!*/ 1198 U_DT_CANONICAL, /*[can]*/ 1199 U_DT_COMPAT, /*[com]*/ 1200 U_DT_CIRCLE, /*[enc]*/ 1201 U_DT_FINAL, /*[fin]*/ 1202 U_DT_FONT, /*[font]*/ 1203 U_DT_FRACTION, /*[fra]*/ 1204 U_DT_INITIAL, /*[init]*/ 1205 U_DT_ISOLATED, /*[iso]*/ 1206 U_DT_MEDIAL, /*[med]*/ 1207 U_DT_NARROW, /*[nar]*/ 1208 U_DT_NOBREAK, /*[nb]*/ 1209 U_DT_SMALL, /*[sml]*/ 1210 U_DT_SQUARE, /*[sqr]*/ 1211 U_DT_SUB, /*[sub]*/ 1212 U_DT_SUPER, /*[sup]*/ 1213 U_DT_VERTICAL, /*[vert]*/ 1214 U_DT_WIDE, /*[wide]*/ 1215 U_DT_COUNT /* 18 */ 1216 } UDecompositionType; 1217 1218 /** 1219 * Joining Type constants. 1220 * 1221 * @see UCHAR_JOINING_TYPE 1222 * @stable ICU 2.2 1223 */ 1224 typedef enum UJoiningType { 1225 U_JT_NON_JOINING, /*[U]*/ /*See note !!*/ 1226 U_JT_JOIN_CAUSING, /*[C]*/ 1227 U_JT_DUAL_JOINING, /*[D]*/ 1228 U_JT_LEFT_JOINING, /*[L]*/ 1229 U_JT_RIGHT_JOINING, /*[R]*/ 1230 U_JT_TRANSPARENT, /*[T]*/ 1231 U_JT_COUNT /* 6 */ 1232 } UJoiningType; 1233 1234 /** 1235 * Joining Group constants. 1236 * 1237 * @see UCHAR_JOINING_GROUP 1238 * @stable ICU 2.2 1239 */ 1240 typedef enum UJoiningGroup { 1241 U_JG_NO_JOINING_GROUP, 1242 U_JG_AIN, 1243 U_JG_ALAPH, 1244 U_JG_ALEF, 1245 U_JG_BEH, 1246 U_JG_BETH, 1247 U_JG_DAL, 1248 U_JG_DALATH_RISH, 1249 U_JG_E, 1250 U_JG_FEH, 1251 U_JG_FINAL_SEMKATH, 1252 U_JG_GAF, 1253 U_JG_GAMAL, 1254 U_JG_HAH, 1255 U_JG_HAMZA_ON_HEH_GOAL, 1256 U_JG_HE, 1257 U_JG_HEH, 1258 U_JG_HEH_GOAL, 1259 U_JG_HETH, 1260 U_JG_KAF, 1261 U_JG_KAPH, 1262 U_JG_KNOTTED_HEH, 1263 U_JG_LAM, 1264 U_JG_LAMADH, 1265 U_JG_MEEM, 1266 U_JG_MIM, 1267 U_JG_NOON, 1268 U_JG_NUN, 1269 U_JG_PE, 1270 U_JG_QAF, 1271 U_JG_QAPH, 1272 U_JG_REH, 1273 U_JG_REVERSED_PE, 1274 U_JG_SAD, 1275 U_JG_SADHE, 1276 U_JG_SEEN, 1277 U_JG_SEMKATH, 1278 U_JG_SHIN, 1279 U_JG_SWASH_KAF, 1280 U_JG_SYRIAC_WAW, 1281 U_JG_TAH, 1282 U_JG_TAW, 1283 U_JG_TEH_MARBUTA, 1284 U_JG_TETH, 1285 U_JG_WAW, 1286 U_JG_YEH, 1287 U_JG_YEH_BARREE, 1288 U_JG_YEH_WITH_TAIL, 1289 U_JG_YUDH, 1290 U_JG_YUDH_HE, 1291 U_JG_ZAIN, 1292 U_JG_FE, /**< @stable ICU 2.6 */ 1293 U_JG_KHAPH, /**< @stable ICU 2.6 */ 1294 U_JG_ZHAIN, /**< @stable ICU 2.6 */ 1295 U_JG_COUNT 1296 } UJoiningGroup; 1297 1298 /** 1299 * Line Break constants. 1300 * 1301 * @see UCHAR_LINE_BREAK 1302 * @stable ICU 2.2 1303 */ 1304 typedef enum ULineBreak { 1305 U_LB_UNKNOWN, /*[XX]*/ /*See note !!*/ 1306 U_LB_AMBIGUOUS, /*[AI]*/ 1307 U_LB_ALPHABETIC, /*[AL]*/ 1308 U_LB_BREAK_BOTH, /*[B2]*/ 1309 U_LB_BREAK_AFTER, /*[BA]*/ 1310 U_LB_BREAK_BEFORE, /*[BB]*/ 1311 U_LB_MANDATORY_BREAK, /*[BK]*/ 1312 U_LB_CONTINGENT_BREAK, /*[CB]*/ 1313 U_LB_CLOSE_PUNCTUATION, /*[CL]*/ 1314 U_LB_COMBINING_MARK, /*[CM]*/ 1315 U_LB_CARRIAGE_RETURN, /*[CR]*/ 1316 U_LB_EXCLAMATION, /*[EX]*/ 1317 U_LB_GLUE, /*[GL]*/ 1318 U_LB_HYPHEN, /*[HY]*/ 1319 U_LB_IDEOGRAPHIC, /*[ID]*/ 1320 U_LB_INSEPERABLE, 1321 /** Renamed from the misspelled "inseperable" in Unicode 4.0.1/ICU 3.0 @draft ICU 3.0 */ 1322 U_LB_INSEPARABLE=U_LB_INSEPERABLE,/*[IN]*/ 1323 U_LB_INFIX_NUMERIC, /*[IS]*/ 1324 U_LB_LINE_FEED, /*[LF]*/ 1325 U_LB_NONSTARTER, /*[NS]*/ 1326 U_LB_NUMERIC, /*[NU]*/ 1327 U_LB_OPEN_PUNCTUATION, /*[OP]*/ 1328 U_LB_POSTFIX_NUMERIC, /*[PO]*/ 1329 U_LB_PREFIX_NUMERIC, /*[PR]*/ 1330 U_LB_QUOTATION, /*[QU]*/ 1331 U_LB_COMPLEX_CONTEXT, /*[SA]*/ 1332 U_LB_SURROGATE, /*[SG]*/ 1333 U_LB_SPACE, /*[SP]*/ 1334 U_LB_BREAK_SYMBOLS, /*[SY]*/ 1335 U_LB_ZWSPACE, /*[ZW]*/ 1336 U_LB_NEXT_LINE, /*[NL]*/ /* from here on: new in Unicode 4/ICU 2.6 */ 1337 U_LB_WORD_JOINER, /*[WJ]*/ 1338 U_LB_COUNT 1339 } ULineBreak; 1340 1341 /** 1342 * Numeric Type constants. 1343 * 1344 * @see UCHAR_NUMERIC_TYPE 1345 * @stable ICU 2.2 1346 */ 1347 typedef enum UNumericType { 1348 U_NT_NONE, /*[None]*/ /*See note !!*/ 1349 U_NT_DECIMAL, /*[de]*/ 1350 U_NT_DIGIT, /*[di]*/ 1351 U_NT_NUMERIC, /*[nu]*/ 1352 U_NT_COUNT 1353 } UNumericType; 1354 1355 /** 1356 * Hangul Syllable Type constants. 1357 * 1358 * @see UCHAR_HANGUL_SYLLABLE_TYPE 1359 * @stable ICU 2.6 1360 */ 1361 typedef enum UHangulSyllableType { 1362 U_HST_NOT_APPLICABLE, /*[NA]*/ /*See note !!*/ 1363 U_HST_LEADING_JAMO, /*[L]*/ 1364 U_HST_VOWEL_JAMO, /*[V]*/ 1365 U_HST_TRAILING_JAMO, /*[T]*/ 1366 U_HST_LV_SYLLABLE, /*[LV]*/ 1367 U_HST_LVT_SYLLABLE, /*[LVT]*/ 1368 U_HST_COUNT 1369 } UHangulSyllableType; 1370 1371 /** 1372 * Check a binary Unicode property for a code point. 1373 * 1374 * Unicode, especially in version 3.2, defines many more properties than the 1375 * original set in UnicodeData.txt. 1376 * 1377 * The properties APIs are intended to reflect Unicode properties as defined 1378 * in the Unicode Character Database (UCD) and Unicode Technical Reports (UTR). 1379 * For details about the properties see http://www.unicode.org/ucd/ . 1380 * For names of Unicode properties see the UCD file PropertyAliases.txt. 1381 * 1382 * Important: If ICU is built with UCD files from Unicode versions below 3.2, 1383 * then properties marked with "new in Unicode 3.2" are not or not fully available. 1384 * 1385 * @param c Code point to test. 1386 * @param which UProperty selector constant, identifies which binary property to check. 1387 * Must be UCHAR_BINARY_START<=which<UCHAR_BINARY_LIMIT. 1388 * @return TRUE or FALSE according to the binary Unicode property value for c. 1389 * Also FALSE if 'which' is out of bounds or if the Unicode version 1390 * does not have data for the property at all, or not for this code point. 1391 * 1392 * @see UProperty 1393 * @see u_getIntPropertyValue 1394 * @see u_getUnicodeVersion 1395 * @stable ICU 2.1 1396 */ 1397 U_STABLE UBool U_EXPORT2 1398 u_hasBinaryProperty(UChar32 c, UProperty which); 1399 1400 /** 1401 * Check if a code point has the Alphabetic Unicode property. 1402 * Same as u_hasBinaryProperty(c, UCHAR_ALPHABETIC). 1403 * This is different from u_isalpha! 1404 * @param c Code point to test 1405 * @return true if the code point has the Alphabetic Unicode property, false otherwise 1406 * 1407 * @see UCHAR_ALPHABETIC 1408 * @see u_isalpha 1409 * @see u_hasBinaryProperty 1410 * @stable ICU 2.1 1411 */ 1412 U_STABLE UBool U_EXPORT2 1413 u_isUAlphabetic(UChar32 c); 1414 1415 /** 1416 * Check if a code point has the Lowercase Unicode property. 1417 * Same as u_hasBinaryProperty(c, UCHAR_LOWERCASE). 1418 * This is different from u_islower! 1419 * @param c Code point to test 1420 * @return true if the code point has the Lowercase Unicode property, false otherwise 1421 * 1422 * @see UCHAR_LOWERCASE 1423 * @see u_islower 1424 * @see u_hasBinaryProperty 1425 * @stable ICU 2.1 1426 */ 1427 U_STABLE UBool U_EXPORT2 1428 u_isULowercase(UChar32 c); 1429 1430 /** 1431 * Check if a code point has the Uppercase Unicode property. 1432 * Same as u_hasBinaryProperty(c, UCHAR_UPPERCASE). 1433 * This is different from u_isupper! 1434 * @param c Code point to test 1435 * @return true if the code point has the Uppercase Unicode property, false otherwise 1436 * 1437 * @see UCHAR_UPPERCASE 1438 * @see u_isupper 1439 * @see u_hasBinaryProperty 1440 * @stable ICU 2.1 1441 */ 1442 U_STABLE UBool U_EXPORT2 1443 u_isUUppercase(UChar32 c); 1444 1445 /** 1446 * Check if a code point has the White_Space Unicode property. 1447 * Same as u_hasBinaryProperty(c, UCHAR_WHITE_SPACE). 1448 * This is different from both u_isspace and u_isWhitespace! 1449 * 1450 * Note: There are several ICU whitespace functions; please see the uchar.h 1451 * file documentation for a detailed comparison. 1452 * 1453 * @param c Code point to test 1454 * @return true if the code point has the White_Space Unicode property, false otherwise. 1455 * 1456 * @see UCHAR_WHITE_SPACE 1457 * @see u_isWhitespace 1458 * @see u_isspace 1459 * @see u_isJavaSpaceChar 1460 * @see u_hasBinaryProperty 1461 * @stable ICU 2.1 1462 */ 1463 U_STABLE UBool U_EXPORT2 1464 u_isUWhiteSpace(UChar32 c); 1465 1466 /** 1467 * Get the property value for an enumerated or integer Unicode property for a code point. 1468 * Also returns binary and mask property values. 1469 * 1470 * Unicode, especially in version 3.2, defines many more properties than the 1471 * original set in UnicodeData.txt. 1472 * 1473 * The properties APIs are intended to reflect Unicode properties as defined 1474 * in the Unicode Character Database (UCD) and Unicode Technical Reports (UTR). 1475 * For details about the properties see http://www.unicode.org/ . 1476 * For names of Unicode properties see the UCD file PropertyAliases.txt. 1477 * 1478 * Sample usage: 1479 * UEastAsianWidth ea=(UEastAsianWidth)u_getIntPropertyValue(c, UCHAR_EAST_ASIAN_WIDTH); 1480 * UBool b=(UBool)u_getIntPropertyValue(c, UCHAR_IDEOGRAPHIC); 1481 * 1482 * @param c Code point to test. 1483 * @param which UProperty selector constant, identifies which property to check. 1484 * Must be UCHAR_BINARY_START<=which<UCHAR_BINARY_LIMIT 1485 * or UCHAR_INT_START<=which<UCHAR_INT_LIMIT 1486 * or UCHAR_MASK_START<=which<UCHAR_MASK_LIMIT. 1487 * @return Numeric value that is directly the property value or, 1488 * for enumerated properties, corresponds to the numeric value of the enumerated 1489 * constant of the respective property value enumeration type 1490 * (cast to enum type if necessary). 1491 * Returns 0 or 1 (for FALSE/TRUE) for binary Unicode properties. 1492 * Returns a bit-mask for mask properties. 1493 * Returns 0 if 'which' is out of bounds or if the Unicode version 1494 * does not have data for the property at all, or not for this code point. 1495 * 1496 * @see UProperty 1497 * @see u_hasBinaryProperty 1498 * @see u_getIntPropertyMinValue 1499 * @see u_getIntPropertyMaxValue 1500 * @see u_getUnicodeVersion 1501 * @stable ICU 2.2 1502 */ 1503 U_STABLE int32_t U_EXPORT2 1504 u_getIntPropertyValue(UChar32 c, UProperty which); 1505 1506 /** 1507 * Get the minimum value for an enumerated/integer/binary Unicode property. 1508 * Can be used together with u_getIntPropertyMaxValue 1509 * to allocate arrays of UnicodeSet or similar. 1510 * 1511 * @param which UProperty selector constant, identifies which binary property to check. 1512 * Must be UCHAR_BINARY_START<=which<UCHAR_BINARY_LIMIT 1513 * or UCHAR_INT_START<=which<UCHAR_INT_LIMIT. 1514 * @return Minimum value returned by u_getIntPropertyValue for a Unicode property. 1515 * 0 if the property selector is out of range. 1516 * 1517 * @see UProperty 1518 * @see u_hasBinaryProperty 1519 * @see u_getUnicodeVersion 1520 * @see u_getIntPropertyMaxValue 1521 * @see u_getIntPropertyValue 1522 * @stable ICU 2.2 1523 */ 1524 U_STABLE int32_t U_EXPORT2 1525 u_getIntPropertyMinValue(UProperty which); 1526 1527 /** 1528 * Get the maximum value for an enumerated/integer/binary Unicode property. 1529 * Can be used together with u_getIntPropertyMinValue 1530 * to allocate arrays of UnicodeSet or similar. 1531 * 1532 * Examples for min/max values (for Unicode 3.2): 1533 * 1534 * - UCHAR_BIDI_CLASS: 0/18 (U_LEFT_TO_RIGHT/U_BOUNDARY_NEUTRAL) 1535 * - UCHAR_SCRIPT: 0/45 (USCRIPT_COMMON/USCRIPT_TAGBANWA) 1536 * - UCHAR_IDEOGRAPHIC: 0/1 (FALSE/TRUE) 1537 * 1538 * For undefined UProperty constant values, min/max values will be 0/-1. 1539 * 1540 * @param which UProperty selector constant, identifies which binary property to check. 1541 * Must be UCHAR_BINARY_START<=which<UCHAR_BINARY_LIMIT 1542 * or UCHAR_INT_START<=which<UCHAR_INT_LIMIT. 1543 * @return Maximum value returned by u_getIntPropertyValue for a Unicode property. 1544 * <=0 if the property selector is out of range. 1545 * 1546 * @see UProperty 1547 * @see u_hasBinaryProperty 1548 * @see u_getUnicodeVersion 1549 * @see u_getIntPropertyMaxValue 1550 * @see u_getIntPropertyValue 1551 * @stable ICU 2.2 1552 */ 1553 U_STABLE int32_t U_EXPORT2 1554 u_getIntPropertyMaxValue(UProperty which); 1555 1556 /** 1557 * Get the numeric value for a Unicode code point as defined in the 1558 * Unicode Character Database. 1559 * 1560 * A "double" return type is necessary because 1561 * some numeric values are fractions, negative, or too large for int32_t. 1562 * 1563 * For characters without any numeric values in the Unicode Character Database, 1564 * this function will return U_NO_NUMERIC_VALUE. 1565 * 1566 * Similar to java.lang.Character.getNumericValue(), but u_getNumericValue() 1567 * also supports negative values, large values, and fractions, 1568 * while Java's getNumericValue() returns values 10..35 for ASCII letters. 1569 * 1570 * @param c Code point to get the numeric value for. 1571 * @return Numeric value of c, or U_NO_NUMERIC_VALUE if none is defined. 1572 * 1573 * @see U_NO_NUMERIC_VALUE 1574 * @stable ICU 2.2 1575 */ 1576 U_STABLE double U_EXPORT2 1577 u_getNumericValue(UChar32 c); 1578 1579 /** 1580 * Special value that is returned by u_getNumericValue when 1581 * no numeric value is defined for a code point. 1582 * 1583 * @see u_getNumericValue 1584 * @stable ICU 2.2 1585 */ 1586 #define U_NO_NUMERIC_VALUE ((double)-123456789.) 1587 1588 /** 1589 * Determines whether the specified code point has the general category "Ll" 1590 * (lowercase letter). 1591 * 1592 * Same as java.lang.Character.isLowerCase(). 1593 * 1594 * This misses some characters that are also lowercase but 1595 * have a different general category value. 1596 * In order to include those, use UCHAR_LOWERCASE. 1597 * 1598 * In addition to being equivalent to a Java function, this also serves 1599 * as a C/POSIX migration function. 1600 * See the comments about C/POSIX character classification functions in the 1601 * documentation at the top of this header file. 1602 * 1603 * @param c the code point to be tested 1604 * @return TRUE if the code point is an Ll lowercase letter 1605 * 1606 * @see UCHAR_LOWERCASE 1607 * @see u_isupper 1608 * @see u_istitle 1609 * @see u_islower 1610 * @stable ICU 2.0 1611 */ 1612 U_STABLE UBool U_EXPORT2 1613 u_islower(UChar32 c); 1614 1615 /** 1616 * Determines whether the specified code point has the general category "Lu" 1617 * (uppercase letter). 1618 * 1619 * Same as java.lang.Character.isUpperCase(). 1620 * 1621 * This misses some characters that are also uppercase but 1622 * have a different general category value. 1623 * In order to include those, use UCHAR_UPPERCASE. 1624 * 1625 * In addition to being equivalent to a Java function, this also serves 1626 * as a C/POSIX migration function. 1627 * See the comments about C/POSIX character classification functions in the 1628 * documentation at the top of this header file. 1629 * 1630 * @param c the code point to be tested 1631 * @return TRUE if the code point is an Lu uppercase letter 1632 * 1633 * @see UCHAR_UPPERCASE 1634 * @see u_islower 1635 * @see u_istitle 1636 * @see u_tolower 1637 * @stable ICU 2.0 1638 */ 1639 U_STABLE UBool U_EXPORT2 1640 u_isupper(UChar32 c); 1641 1642 /** 1643 * Determines whether the specified code point is a titlecase letter. 1644 * True for general category "Lt" (titlecase letter). 1645 * 1646 * Same as java.lang.Character.isTitleCase(). 1647 * 1648 * @param c the code point to be tested 1649 * @return TRUE if the code point is an Lt titlecase letter 1650 * 1651 * @see u_isupper 1652 * @see u_islower 1653 * @see u_totitle 1654 * @stable ICU 2.0 1655 */ 1656 U_STABLE UBool U_EXPORT2 1657 u_istitle(UChar32 c); 1658 1659 /** 1660 * Determines whether the specified code point is a digit character according to Java. 1661 * True for characters with general category "Nd" (decimal digit numbers). 1662 * Beginning with Unicode 4, this is the same as 1663 * testing for the Numeric_Type of Decimal. 1664 * 1665 * Same as java.lang.Character.isDigit(). 1666 * 1667 * In addition to being equivalent to a Java function, this also serves 1668 * as a C/POSIX migration function. 1669 * See the comments about C/POSIX character classification functions in the 1670 * documentation at the top of this header file. 1671 * 1672 * @param c the code point to be tested 1673 * @return TRUE if the code point is a digit character according to Character.isDigit() 1674 * 1675 * @stable ICU 2.0 1676 */ 1677 U_STABLE UBool U_EXPORT2 1678 u_isdigit(UChar32 c); 1679 1680 /** 1681 * Determines whether the specified code point is a letter character. 1682 * True for general categories "L" (letters). 1683 * 1684 * Same as java.lang.Character.isLetter(). 1685 * 1686 * In addition to being equivalent to a Java function, this also serves 1687 * as a C/POSIX migration function. 1688 * See the comments about C/POSIX character classification functions in the 1689 * documentation at the top of this header file. 1690 * 1691 * @param c the code point to be tested 1692 * @return TRUE if the code point is a letter character 1693 * 1694 * @see u_isdigit 1695 * @see u_isalnum 1696 * @stable ICU 2.0 1697 */ 1698 U_STABLE UBool U_EXPORT2 1699 u_isalpha(UChar32 c); 1700 1701 /** 1702 * Determines whether the specified code point is an alphanumeric character 1703 * (letter or digit) according to Java. 1704 * True for characters with general categories 1705 * "L" (letters) and "Nd" (decimal digit numbers). 1706 * 1707 * Same as java.lang.Character.isLetterOrDigit(). 1708 * 1709 * In addition to being equivalent to a Java function, this also serves 1710 * as a C/POSIX migration function. 1711 * See the comments about C/POSIX character classification functions in the 1712 * documentation at the top of this header file. 1713 * 1714 * @param c the code point to be tested 1715 * @return TRUE if the code point is an alphanumeric character according to Character.isLetterOrDigit() 1716 * 1717 * @stable ICU 2.0 1718 */ 1719 U_STABLE UBool U_EXPORT2 1720 u_isalnum(UChar32 c); 1721 1722 /** 1723 * Determines whether the specified code point is a hexadecimal digit. 1724 * This is equivalent to u_digit(c, 16)>=0. 1725 * True for characters with general category "Nd" (decimal digit numbers) 1726 * as well as Latin letters a-f and A-F in both ASCII and Fullwidth ASCII. 1727 * (That is, for letters with code points 1728 * 0041..0046, 0061..0066, FF21..FF26, FF41..FF46.) 1729 * 1730 * In order to narrow the definition of hexadecimal digits to only ASCII 1731 * characters, use (c<=0x7f && u_isxdigit(c)). 1732 * 1733 * This is a C/POSIX migration function. 1734 * See the comments about C/POSIX character classification functions in the 1735 * documentation at the top of this header file. 1736 * 1737 * @param c the code point to be tested 1738 * @return TRUE if the code point is a hexadecimal digit 1739 * 1740 * @stable ICU 2.6 1741 */ 1742 U_STABLE UBool U_EXPORT2 1743 u_isxdigit(UChar32 c); 1744 1745 /** 1746 * Determines whether the specified code point is a punctuation character. 1747 * True for characters with general categories "P" (punctuation). 1748 * 1749 * This is a C/POSIX migration function. 1750 * See the comments about C/POSIX character classification functions in the 1751 * documentation at the top of this header file. 1752 * 1753 * @param c the code point to be tested 1754 * @return TRUE if the code point is a punctuation character 1755 * 1756 * @stable ICU 2.6 1757 */ 1758 U_STABLE UBool U_EXPORT2 1759 u_ispunct(UChar32 c); 1760 1761 /** 1762 * Determines whether the specified code point is a "graphic" character 1763 * (printable, excluding spaces). 1764 * TRUE for all characters except those with general categories 1765 * "Cc" (control codes), "Cf" (format controls), "Cs" (surrogates), 1766 * "Cn" (unassigned), and "Z" (separators). 1767 * 1768 * This is a C/POSIX migration function. 1769 * See the comments about C/POSIX character classification functions in the 1770 * documentation at the top of this header file. 1771 * 1772 * @param c the code point to be tested 1773 * @return TRUE if the code point is a "graphic" character 1774 * 1775 * @stable ICU 2.6 1776 */ 1777 U_STABLE UBool U_EXPORT2 1778 u_isgraph(UChar32 c); 1779 1780 /** 1781 * Determines whether the specified code point is a "blank" or "horizontal space", 1782 * a character that visibly separates words on a line. 1783 * The following are equivalent definitions: 1784 * 1785 * TRUE for Unicode White_Space characters except for "vertical space controls" 1786 * where "vertical space controls" are the following characters: 1787 * U+000A (LF) U+000B (VT) U+000C (FF) U+000D (CR) U+0085 (NEL) U+2028 (LS) U+2029 (PS) 1788 * 1789 * same as 1790 * 1791 * TRUE for U+0009 (TAB) and characters with general category "Zs" (space separators) 1792 * except Zero Width Space (ZWSP, U+200B). 1793 * 1794 * Note: There are several ICU whitespace functions; please see the uchar.h 1795 * file documentation for a detailed comparison. 1796 * 1797 * This is a C/POSIX migration function. 1798 * See the comments about C/POSIX character classification functions in the 1799 * documentation at the top of this header file. 1800 * 1801 * @param c the code point to be tested 1802 * @return TRUE if the code point is a "blank" 1803 * 1804 * @stable ICU 2.6 1805 */ 1806 U_STABLE UBool U_EXPORT2 1807 u_isblank(UChar32 c); 1808 1809 /** 1810 * Determines whether the specified code point is "defined", 1811 * which usually means that it is assigned a character. 1812 * True for general categories other than "Cn" (other, not assigned), 1813 * i.e., true for all code points mentioned in UnicodeData.txt. 1814 * 1815 * Note that non-character code points (e.g., U+FDD0) are not "defined" 1816 * (they are Cn), but surrogate code points are "defined" (Cs). 1817 * 1818 * Same as java.lang.Character.isDefined(). 1819 * 1820 * @param c the code point to be tested 1821 * @return TRUE if the code point is assigned a character 1822 * 1823 * @see u_isdigit 1824 * @see u_isalpha 1825 * @see u_isalnum 1826 * @see u_isupper 1827 * @see u_islower 1828 * @see u_istitle 1829 * @stable ICU 2.0 1830 */ 1831 U_STABLE UBool U_EXPORT2 1832 u_isdefined(UChar32 c); 1833 1834 /** 1835 * Determines if the specified character is a space character or not. 1836 * 1837 * Note: There are several ICU whitespace functions; please see the uchar.h 1838 * file documentation for a detailed comparison. 1839 * 1840 * This is a C/POSIX migration function. 1841 * See the comments about C/POSIX character classification functions in the 1842 * documentation at the top of this header file. 1843 * 1844 * @param c the character to be tested 1845 * @return true if the character is a space character; false otherwise. 1846 * 1847 * @see u_isJavaSpaceChar 1848 * @see u_isWhitespace 1849 * @see u_isUWhiteSpace 1850 * @stable ICU 2.0 1851 */ 1852 U_STABLE UBool U_EXPORT2 1853 u_isspace(UChar32 c); 1854 1855 /** 1856 * Determine if the specified code point is a space character according to Java. 1857 * True for characters with general categories "Z" (separators), 1858 * which does not include control codes (e.g., TAB or Line Feed). 1859 * 1860 * Same as java.lang.Character.isSpaceChar(). 1861 * 1862 * Note: There are several ICU whitespace functions; please see the uchar.h 1863 * file documentation for a detailed comparison. 1864 * 1865 * @param c the code point to be tested 1866 * @return TRUE if the code point is a space character according to Character.isSpaceChar() 1867 * 1868 * @see u_isspace 1869 * @see u_isWhitespace 1870 * @see u_isUWhiteSpace 1871 * @stable ICU 2.6 1872 */ 1873 U_STABLE UBool U_EXPORT2 1874 u_isJavaSpaceChar(UChar32 c); 1875 1876 /** 1877 * Determines if the specified code point is a whitespace character according to Java/ICU. 1878 * A character is considered to be a Java whitespace character if and only 1879 * if it satisfies one of the following criteria: 1880 * 1881 * - It is a Unicode separator (categories "Z"), but is not 1882 * a no-break space (U+00A0 NBSP or U+2007 Figure Space or U+202F Narrow NBSP). 1883 * - It is U+0009 HORIZONTAL TABULATION. 1884 * - It is U+000A LINE FEED. 1885 * - It is U+000B VERTICAL TABULATION. 1886 * - It is U+000C FORM FEED. 1887 * - It is U+000D CARRIAGE RETURN. 1888 * - It is U+001C FILE SEPARATOR. 1889 * - It is U+001D GROUP SEPARATOR. 1890 * - It is U+001E RECORD SEPARATOR. 1891 * - It is U+001F UNIT SEPARATOR. 1892 * - It is U+0085 NEXT LINE. 1893 * 1894 * Same as java.lang.Character.isWhitespace() except that Java omits U+0085. 1895 * 1896 * Note: There are several ICU whitespace functions; please see the uchar.h 1897 * file documentation for a detailed comparison. 1898 * 1899 * @param c the code point to be tested 1900 * @return TRUE if the code point is a whitespace character according to Java/ICU 1901 * 1902 * @see u_isspace 1903 * @see u_isJavaSpaceChar 1904 * @see u_isUWhiteSpace 1905 * @stable ICU 2.0 1906 */ 1907 U_STABLE UBool U_EXPORT2 1908 u_isWhitespace(UChar32 c); 1909 1910 /** 1911 * Determines whether the specified code point is a control character 1912 * (as defined by this function). 1913 * A control character is one of the following: 1914 * - ISO 8-bit control character (U+0000..U+001f and U+007f..U+009f) 1915 * - U_CONTROL_CHAR (Cc) 1916 * - U_FORMAT_CHAR (Cf) 1917 * - U_LINE_SEPARATOR (Zl) 1918 * - U_PARAGRAPH_SEPARATOR (Zp) 1919 * 1920 * This is a C/POSIX migration function. 1921 * See the comments about C/POSIX character classification functions in the 1922 * documentation at the top of this header file. 1923 * 1924 * @param c the code point to be tested 1925 * @return TRUE if the code point is a control character 1926 * 1927 * @see UCHAR_DEFAULT_IGNORABLE_CODE_POINT 1928 * @see u_isprint 1929 * @stable ICU 2.0 1930 */ 1931 U_STABLE UBool U_EXPORT2 1932 u_iscntrl(UChar32 c); 1933 1934 /** 1935 * Determines whether the specified code point is an ISO control code. 1936 * True for U+0000..U+001f and U+007f..U+009f (general category "Cc"). 1937 * 1938 * Same as java.lang.Character.isISOControl(). 1939 * 1940 * @param c the code point to be tested 1941 * @return TRUE if the code point is an ISO control code 1942 * 1943 * @see u_iscntrl 1944 * @stable ICU 2.6 1945 */ 1946 U_STABLE UBool U_EXPORT2 1947 u_isISOControl(UChar32 c); 1948 1949 /** 1950 * Determines whether the specified code point is a printable character. 1951 * True for general categories <em>other</em> than "C" (controls). 1952 * 1953 * This is a C/POSIX migration function. 1954 * See the comments about C/POSIX character classification functions in the 1955 * documentation at the top of this header file. 1956 * 1957 * @param c the code point to be tested 1958 * @return TRUE if the code point is a printable character 1959 * 1960 * @see UCHAR_DEFAULT_IGNORABLE_CODE_POINT 1961 * @see u_iscntrl 1962 * @stable ICU 2.0 1963 */ 1964 U_STABLE UBool U_EXPORT2 1965 u_isprint(UChar32 c); 1966 1967 /** 1968 * Determines whether the specified code point is a base character. 1969 * True for general categories "L" (letters), "N" (numbers), 1970 * "Mc" (spacing combining marks), and "Me" (enclosing marks). 1971 * 1972 * Note that this is different from the Unicode definition in 1973 * chapter 3.5, conformance clause D13, 1974 * which defines base characters to be all characters (not Cn) 1975 * that do not graphically combine with preceding characters (M) 1976 * and that are neither control (Cc) or format (Cf) characters. 1977 * 1978 * @param c the code point to be tested 1979 * @return TRUE if the code point is a base character according to this function 1980 * 1981 * @see u_isalpha 1982 * @see u_isdigit 1983 * @stable ICU 2.0 1984 */ 1985 U_STABLE UBool U_EXPORT2 1986 u_isbase(UChar32 c); 1987 1988 /** 1989 * Returns the bidirectional category value for the code point, 1990 * which is used in the Unicode bidirectional algorithm 1991 * (UAX #9 http://www.unicode.org/reports/tr9/). 1992 * Note that some <em>unassigned</em> code points have bidi values 1993 * of R or AL because they are in blocks that are reserved 1994 * for Right-To-Left scripts. 1995 * 1996 * Same as java.lang.Character.getDirectionality() 1997 * 1998 * @param c the code point to be tested 1999 * @return the bidirectional category (UCharDirection) value 2000 * 2001 * @see UCharDirection 2002 * @stable ICU 2.0 2003 */ 2004 U_STABLE UCharDirection U_EXPORT2 2005 u_charDirection(UChar32 c); 2006 2007 /** 2008 * Determines whether the code point has the Bidi_Mirrored property. 2009 * This property is set for characters that are commonly used in 2010 * Right-To-Left contexts and need to be displayed with a "mirrored" 2011 * glyph. 2012 * 2013 * Same as java.lang.Character.isMirrored(). 2014 * Same as UCHAR_BIDI_MIRRORED 2015 * 2016 * @param c the code point to be tested 2017 * @return TRUE if the character has the Bidi_Mirrored property 2018 * 2019 * @see UCHAR_BIDI_MIRRORED 2020 * @stable ICU 2.0 2021 */ 2022 U_STABLE UBool U_EXPORT2 2023 u_isMirrored(UChar32 c); 2024 2025 /** 2026 * Maps the specified character to a "mirror-image" character. 2027 * For characters with the Bidi_Mirrored property, implementations 2028 * sometimes need a "poor man's" mapping to another Unicode 2029 * character (code point) such that the default glyph may serve 2030 * as the mirror-image of the default glyph of the specified 2031 * character. This is useful for text conversion to and from 2032 * codepages with visual order, and for displays without glyph 2033 * selecetion capabilities. 2034 * 2035 * @param c the code point to be mapped 2036 * @return another Unicode code point that may serve as a mirror-image 2037 * substitute, or c itself if there is no such mapping or c 2038 * does not have the Bidi_Mirrored property 2039 * 2040 * @see UCHAR_BIDI_MIRRORED 2041 * @see u_isMirrored 2042 * @stable ICU 2.0 2043 */ 2044 U_STABLE UChar32 U_EXPORT2 2045 u_charMirror(UChar32 c); 2046 2047 /** 2048 * Returns the general category value for the code point. 2049 * 2050 * Same as java.lang.Character.getType(). 2051 * 2052 * @param c the code point to be tested 2053 * @return the general category (UCharCategory) value 2054 * 2055 * @see UCharCategory 2056 * @stable ICU 2.0 2057 */ 2058 U_STABLE int8_t U_EXPORT2 2059 u_charType(UChar32 c); 2060 2061 /** 2062 * Get a single-bit bit set for the general category of a character. 2063 * This bit set can be compared bitwise with U_GC_SM_MASK, U_GC_L_MASK, etc. 2064 * Same as U_MASK(u_charType(c)). 2065 * 2066 * @param c the code point to be tested 2067 * @return a single-bit mask corresponding to the general category (UCharCategory) value 2068 * 2069 * @see u_charType 2070 * @see UCharCategory 2071 * @see U_GC_CN_MASK 2072 * @stable ICU 2.1 2073 */ 2074 #define U_GET_GC_MASK(c) U_MASK(u_charType(c)) 2075 2076 /** 2077 * Callback from u_enumCharTypes(), is called for each contiguous range 2078 * of code points c (where start<=c<limit) 2079 * with the same Unicode general category ("character type"). 2080 * 2081 * The callback function can stop the enumeration by returning FALSE. 2082 * 2083 * @param context an opaque pointer, as passed into utrie_enum() 2084 * @param start the first code point in a contiguous range with value 2085 * @param limit one past the last code point in a contiguous range with value 2086 * @param type the general category for all code points in [start..limit[ 2087 * @return FALSE to stop the enumeration 2088 * 2089 * @stable ICU 2.1 2090 * @see UCharCategory 2091 * @see u_enumCharTypes 2092 */ 2093 typedef UBool U_CALLCONV 2094 UCharEnumTypeRange(const void *context, UChar32 start, UChar32 limit, UCharCategory type); 2095 2096 /** 2097 * Enumerate efficiently all code points with their Unicode general categories. 2098 * 2099 * This is useful for building data structures (e.g., UnicodeSet's), 2100 * for enumerating all assigned code points (type!=U_UNASSIGNED), etc. 2101 * 2102 * For each contiguous range of code points with a given general category ("character type"), 2103 * the UCharEnumTypeRange function is called. 2104 * Adjacent ranges have different types. 2105 * The Unicode Standard guarantees that the numeric value of the type is 0..31. 2106 * 2107 * @param enumRange a pointer to a function that is called for each contiguous range 2108 * of code points with the same general category 2109 * @param context an opaque pointer that is passed on to the callback function 2110 * 2111 * @stable ICU 2.1 2112 * @see UCharCategory 2113 * @see UCharEnumTypeRange 2114 */ 2115 U_STABLE void U_EXPORT2 2116 u_enumCharTypes(UCharEnumTypeRange *enumRange, const void *context); 2117 2118 #if !UCONFIG_NO_NORMALIZATION 2119 2120 /** 2121 * Returns the combining class of the code point as specified in UnicodeData.txt. 2122 * 2123 * @param c the code point of the character 2124 * @return the combining class of the character 2125 * @stable ICU 2.0 2126 */ 2127 U_STABLE uint8_t U_EXPORT2 2128 u_getCombiningClass(UChar32 c); 2129 2130 #endif 2131 2132 /** 2133 * Returns the decimal digit value of a decimal digit character. 2134 * Such characters have the general category "Nd" (decimal digit numbers) 2135 * and a Numeric_Type of Decimal. 2136 * 2137 * Unlike ICU releases before 2.6, no digit values are returned for any 2138 * Han characters because Han number characters are often used with a special 2139 * Chinese-style number format (with characters for powers of 10 in between) 2140 * instead of in decimal-positional notation. 2141 * Unicode 4 explicitly assigns Han number characters the Numeric_Type 2142 * Numeric instead of Decimal. 2143 * See Jitterbug 1483 for more details. 2144 * 2145 * Use u_getIntPropertyValue(c, UCHAR_NUMERIC_TYPE) and u_getNumericValue() 2146 * for complete numeric Unicode properties. 2147 * 2148 * @param c the code point for which to get the decimal digit value 2149 * @return the decimal digit value of c, 2150 * or -1 if c is not a decimal digit character 2151 * 2152 * @see u_getNumericValue 2153 * @stable ICU 2.0 2154 */ 2155 U_STABLE int32_t U_EXPORT2 2156 u_charDigitValue(UChar32 c); 2157 2158 /** 2159 * Returns the Unicode allocation block that contains the character. 2160 * 2161 * @param c the code point to be tested 2162 * @return the block value (UBlockCode) for c 2163 * 2164 * @see UBlockCode 2165 * @stable ICU 2.0 2166 */ 2167 U_STABLE UBlockCode U_EXPORT2 2168 ublock_getCode(UChar32 c); 2169 2170 /** 2171 * Retrieve the name of a Unicode character. 2172 * Depending on <code>nameChoice</code>, the character name written 2173 * into the buffer is the "modern" name or the name that was defined 2174 * in Unicode version 1.0. 2175 * The name contains only "invariant" characters 2176 * like A-Z, 0-9, space, and '-'. 2177 * Unicode 1.0 names are only retrieved if they are different from the modern 2178 * names and if the data file contains the data for them. gennames may or may 2179 * not be called with a command line option to include 1.0 names in unames.dat. 2180 * 2181 * @param code The character (code point) for which to get the name. 2182 * It must be <code>0<=code<=0x10ffff</code>. 2183 * @param nameChoice Selector for which name to get. 2184 * @param buffer Destination address for copying the name. 2185 * The name will always be zero-terminated. 2186 * If there is no name, then the buffer will be set to the empty string. 2187 * @param bufferLength <code>==sizeof(buffer)</code> 2188 * @param pErrorCode Pointer to a UErrorCode variable; 2189 * check for <code>U_SUCCESS()</code> after <code>u_charName()</code> 2190 * returns. 2191 * @return The length of the name, or 0 if there is no name for this character. 2192 * If the bufferLength is less than or equal to the length, then the buffer 2193 * contains the truncated name and the returned length indicates the full 2194 * length of the name. 2195 * The length does not include the zero-termination. 2196 * 2197 * @see UCharNameChoice 2198 * @see u_charFromName 2199 * @see u_enumCharNames 2200 * @stable ICU 2.0 2201 */ 2202 U_STABLE int32_t U_EXPORT2 2203 u_charName(UChar32 code, UCharNameChoice nameChoice, 2204 char *buffer, int32_t bufferLength, 2205 UErrorCode *pErrorCode); 2206 2207 /** 2208 * Get the ISO 10646 comment for a character. 2209 * The ISO 10646 comment is an informative field in the Unicode Character 2210 * Database (UnicodeData.txt field 11) and is from the ISO 10646 names list. 2211 * 2212 * @param c The character (code point) for which to get the ISO comment. 2213 * It must be <code>0<=c<=0x10ffff</code>. 2214 * @param dest Destination address for copying the comment. 2215 * The comment will be zero-terminated if possible. 2216 * If there is no comment, then the buffer will be set to the empty string. 2217 * @param destCapacity <code>==sizeof(dest)</code> 2218 * @param pErrorCode Pointer to a UErrorCode variable; 2219 * check for <code>U_SUCCESS()</code> after <code>u_getISOComment()</code> 2220 * returns. 2221 * @return The length of the comment, or 0 if there is no comment for this character. 2222 * If the destCapacity is less than or equal to the length, then the buffer 2223 * contains the truncated name and the returned length indicates the full 2224 * length of the name. 2225 * The length does not include the zero-termination. 2226 * 2227 * @stable ICU 2.2 2228 */ 2229 U_STABLE int32_t U_EXPORT2 2230 u_getISOComment(UChar32 c, 2231 char *dest, int32_t destCapacity, 2232 UErrorCode *pErrorCode); 2233 2234 /** 2235 * Find a Unicode character by its name and return its code point value. 2236 * The name is matched exactly and completely. 2237 * If the name does not correspond to a code point, <i>pErrorCode</i> 2238 * is set to <code>U_INVALID_CHAR_FOUND</code>. 2239 * A Unicode 1.0 name is matched only if it differs from the modern name. 2240 * Unicode names are all uppercase. Extended names are lowercase followed 2241 * by an uppercase hexadecimal number, and within angle brackets. 2242 * 2243 * @param nameChoice Selector for which name to match. 2244 * @param name The name to match. 2245 * @param pErrorCode Pointer to a UErrorCode variable 2246 * @return The Unicode value of the code point with the given name, 2247 * or an undefined value if there is no such code point. 2248 * 2249 * @see UCharNameChoice 2250 * @see u_charName 2251 * @see u_enumCharNames 2252 * @stable ICU 1.7 2253 */ 2254 U_STABLE UChar32 U_EXPORT2 2255 u_charFromName(UCharNameChoice nameChoice, 2256 const char *name, 2257 UErrorCode *pErrorCode); 2258 2259 /** 2260 * Type of a callback function for u_enumCharNames() that gets called 2261 * for each Unicode character with the code point value and 2262 * the character name. 2263 * If such a function returns FALSE, then the enumeration is stopped. 2264 * 2265 * @param context The context pointer that was passed to u_enumCharNames(). 2266 * @param code The Unicode code point for the character with this name. 2267 * @param nameChoice Selector for which kind of names is enumerated. 2268 * @param name The character's name, zero-terminated. 2269 * @param length The length of the name. 2270 * @return TRUE if the enumeration should continue, FALSE to stop it. 2271 * 2272 * @see UCharNameChoice 2273 * @see u_enumCharNames 2274 * @stable ICU 1.7 2275 */ 2276 typedef UBool UEnumCharNamesFn(void *context, 2277 UChar32 code, 2278 UCharNameChoice nameChoice, 2279 const char *name, 2280 int32_t length); 2281 2282 /** 2283 * Enumerate all assigned Unicode characters between the start and limit 2284 * code points (start inclusive, limit exclusive) and call a function 2285 * for each, passing the code point value and the character name. 2286 * For Unicode 1.0 names, only those are enumerated that differ from the 2287 * modern names. 2288 * 2289 * @param start The first code point in the enumeration range. 2290 * @param limit One more than the last code point in the enumeration range 2291 * (the first one after the range). 2292 * @param fn The function that is to be called for each character name. 2293 * @param context An arbitrary pointer that is passed to the function. 2294 * @param nameChoice Selector for which kind of names to enumerate. 2295 * @param pErrorCode Pointer to a UErrorCode variable 2296 * 2297 * @see UCharNameChoice 2298 * @see UEnumCharNamesFn 2299 * @see u_charName 2300 * @see u_charFromName 2301 * @stable ICU 1.7 2302 */ 2303 U_STABLE void U_EXPORT2 2304 u_enumCharNames(UChar32 start, UChar32 limit, 2305 UEnumCharNamesFn *fn, 2306 void *context, 2307 UCharNameChoice nameChoice, 2308 UErrorCode *pErrorCode); 2309 2310 /** 2311 * Return the Unicode name for a given property, as given in the 2312 * Unicode database file PropertyAliases.txt. 2313 * 2314 * In addition, this function maps the property 2315 * UCHAR_GENERAL_CATEGORY_MASK to the synthetic names "gcm" / 2316 * "General_Category_Mask". These names are not in 2317 * PropertyAliases.txt. 2318 * 2319 * @param property UProperty selector other than UCHAR_INVALID_CODE. 2320 * If out of range, NULL is returned. 2321 * 2322 * @param nameChoice selector for which name to get. If out of range, 2323 * NULL is returned. All properties have a long name. Most 2324 * have a short name, but some do not. Unicode allows for 2325 * additional names; if present these will be returned by 2326 * U_LONG_PROPERTY_NAME + i, where i=1, 2,... 2327 * 2328 * @return a pointer to the name, or NULL if either the 2329 * property or the nameChoice is out of range. If a given 2330 * nameChoice returns NULL, then all larger values of 2331 * nameChoice will return NULL, with one exception: if NULL is 2332 * returned for U_SHORT_PROPERTY_NAME, then 2333 * U_LONG_PROPERTY_NAME (and higher) may still return a 2334 * non-NULL value. The returned pointer is valid until 2335 * u_cleanup() is called. 2336 * 2337 * @see UProperty 2338 * @see UPropertyNameChoice 2339 * @stable ICU 2.4 2340 */ 2341 U_STABLE const char* U_EXPORT2 2342 u_getPropertyName(UProperty property, 2343 UPropertyNameChoice nameChoice); 2344 2345 /** 2346 * Return the UProperty enum for a given property name, as specified 2347 * in the Unicode database file PropertyAliases.txt. Short, long, and 2348 * any other variants are recognized. 2349 * 2350 * In addition, this function maps the synthetic names "gcm" / 2351 * "General_Category_Mask" to the property 2352 * UCHAR_GENERAL_CATEGORY_MASK. These names are not in 2353 * PropertyAliases.txt. 2354 * 2355 * @param alias the property name to be matched. The name is compared 2356 * using "loose matching" as described in PropertyAliases.txt. 2357 * 2358 * @return a UProperty enum, or UCHAR_INVALID_CODE if the given name 2359 * does not match any property. 2360 * 2361 * @see UProperty 2362 * @stable ICU 2.4 2363 */ 2364 U_STABLE UProperty U_EXPORT2 2365 u_getPropertyEnum(const char* alias); 2366 2367 /** 2368 * Return the Unicode name for a given property value, as given in the 2369 * Unicode database file PropertyValueAliases.txt. 2370 * 2371 * Note: Some of the names in PropertyValueAliases.txt can only be 2372 * retrieved using UCHAR_GENERAL_CATEGORY_MASK, not 2373 * UCHAR_GENERAL_CATEGORY. These include: "C" / "Other", "L" / 2374 * "Letter", "LC" / "Cased_Letter", "M" / "Mark", "N" / "Number", "P" 2375 * / "Punctuation", "S" / "Symbol", and "Z" / "Separator". 2376 * 2377 * @param property UProperty selector constant. 2378 * Must be UCHAR_BINARY_START<=which<UCHAR_BINARY_LIMIT 2379 * or UCHAR_INT_START<=which<UCHAR_INT_LIMIT 2380 * or UCHAR_MASK_START<=which<UCHAR_MASK_LIMIT. 2381 * If out of range, NULL is returned. 2382 * 2383 * @param value selector for a value for the given property. If out 2384 * of range, NULL is returned. In general, valid values range 2385 * from 0 up to some maximum. There are a few exceptions: 2386 * (1.) UCHAR_BLOCK values begin at the non-zero value 2387 * UBLOCK_BASIC_LATIN. (2.) UCHAR_CANONICAL_COMBINING_CLASS 2388 * values are not contiguous and range from 0..240. (3.) 2389 * UCHAR_GENERAL_CATEGORY_MASK values are not values of 2390 * UCharCategory, but rather mask values produced by 2391 * U_GET_GC_MASK(). This allows grouped categories such as 2392 * [:L:] to be represented. Mask values range 2393 * non-contiguously from 1..U_GC_P_MASK. 2394 * 2395 * @param nameChoice selector for which name to get. If out of range, 2396 * NULL is returned. All values have a long name. Most have 2397 * a short name, but some do not. Unicode allows for 2398 * additional names; if present these will be returned by 2399 * U_LONG_PROPERTY_NAME + i, where i=1, 2,... 2400 2401 * @return a pointer to the name, or NULL if either the 2402 * property or the nameChoice is out of range. If a given 2403 * nameChoice returns NULL, then all larger values of 2404 * nameChoice will return NULL, with one exception: if NULL is 2405 * returned for U_SHORT_PROPERTY_NAME, then 2406 * U_LONG_PROPERTY_NAME (and higher) may still return a 2407 * non-NULL value. The returned pointer is valid until 2408 * u_cleanup() is called. 2409 * 2410 * @see UProperty 2411 * @see UPropertyNameChoice 2412 * @stable ICU 2.4 2413 */ 2414 U_STABLE const char* U_EXPORT2 2415 u_getPropertyValueName(UProperty property, 2416 int32_t value, 2417 UPropertyNameChoice nameChoice); 2418 2419 /** 2420 * Return the property value integer for a given value name, as 2421 * specified in the Unicode database file PropertyValueAliases.txt. 2422 * Short, long, and any other variants are recognized. 2423 * 2424 * Note: Some of the names in PropertyValueAliases.txt will only be 2425 * recognized with UCHAR_GENERAL_CATEGORY_MASK, not 2426 * UCHAR_GENERAL_CATEGORY. These include: "C" / "Other", "L" / 2427 * "Letter", "LC" / "Cased_Letter", "M" / "Mark", "N" / "Number", "P" 2428 * / "Punctuation", "S" / "Symbol", and "Z" / "Separator". 2429 * 2430 * @param property UProperty selector constant. 2431 * Must be UCHAR_BINARY_START<=which<UCHAR_BINARY_LIMIT 2432 * or UCHAR_INT_START<=which<UCHAR_INT_LIMIT 2433 * or UCHAR_MASK_START<=which<UCHAR_MASK_LIMIT. 2434 * If out of range, UCHAR_INVALID_CODE is returned. 2435 * 2436 * @param alias the value name to be matched. The name is compared 2437 * using "loose matching" as described in 2438 * PropertyValueAliases.txt. 2439 * 2440 * @return a value integer or UCHAR_INVALID_CODE if the given name 2441 * does not match any value of the given property, or if the 2442 * property is invalid. Note: U CHAR_GENERAL_CATEGORY values 2443 * are not values of UCharCategory, but rather mask values 2444 * produced by U_GET_GC_MASK(). This allows grouped 2445 * categories such as [:L:] to be represented. 2446 * 2447 * @see UProperty 2448 * @stable ICU 2.4 2449 */ 2450 U_STABLE int32_t U_EXPORT2 2451 u_getPropertyValueEnum(UProperty property, 2452 const char* alias); 2453 2454 /** 2455 * Determines if the specified character is permissible as the 2456 * first character in an identifier according to Unicode 2457 * (The Unicode Standard, Version 3.0, chapter 5.16 Identifiers). 2458 * True for characters with general categories "L" (letters) and "Nl" (letter numbers). 2459 * 2460 * Same as java.lang.Character.isUnicodeIdentifierStart(). 2461 * Same as UCHAR_ID_START 2462 * 2463 * @param c the code point to be tested 2464 * @return TRUE if the code point may start an identifier 2465 * 2466 * @see UCHAR_ID_START 2467 * @see u_isalpha 2468 * @see u_isIDPart 2469 * @stable ICU 2.0 2470 */ 2471 U_STABLE UBool U_EXPORT2 2472 u_isIDStart(UChar32 c); 2473 2474 /** 2475 * Determines if the specified character is permissible 2476 * in an identifier according to Java. 2477 * True for characters with general categories "L" (letters), 2478 * "Nl" (letter numbers), "Nd" (decimal digits), 2479 * "Mc" and "Mn" (combining marks), "Pc" (connecting punctuation), and 2480 * u_isIDIgnorable(c). 2481 * 2482 * Same as java.lang.Character.isUnicodeIdentifierPart(). 2483 * Almost the same as Unicode's ID_Continue (UCHAR_ID_CONTINUE) 2484 * except that Unicode recommends to ignore Cf which is less than 2485 * u_isIDIgnorable(c). 2486 * 2487 * @param c the code point to be tested 2488 * @return TRUE if the code point may occur in an identifier according to Java 2489 * 2490 * @see UCHAR_ID_CONTINUE 2491 * @see u_isIDStart 2492 * @see u_isIDIgnorable 2493 * @stable ICU 2.0 2494 */ 2495 U_STABLE UBool U_EXPORT2 2496 u_isIDPart(UChar32 c); 2497 2498 /** 2499 * Determines if the specified character should be regarded 2500 * as an ignorable character in an identifier, 2501 * according to Java. 2502 * True for characters with general category "Cf" (format controls) as well as 2503 * non-whitespace ISO controls 2504 * (U+0000..U+0008, U+000E..U+001B, U+007F..U+0084, U+0086..U+009F). 2505 * 2506 * Same as java.lang.Character.isIdentifierIgnorable() 2507 * except that Java also returns TRUE for U+0085 Next Line 2508 * (it omits U+0085 from whitespace ISO controls). 2509 * 2510 * Note that Unicode just recommends to ignore Cf (format controls). 2511 * 2512 * @param c the code point to be tested 2513 * @return TRUE if the code point is ignorable in identifiers according to Java 2514 * 2515 * @see UCHAR_DEFAULT_IGNORABLE_CODE_POINT 2516 * @see u_isIDStart 2517 * @see u_isIDPart 2518 * @stable ICU 2.0 2519 */ 2520 U_STABLE UBool U_EXPORT2 2521 u_isIDIgnorable(UChar32 c); 2522 2523 /** 2524 * Determines if the specified character is permissible as the 2525 * first character in a Java identifier. 2526 * In addition to u_isIDStart(c), true for characters with 2527 * general categories "Sc" (currency symbols) and "Pc" (connecting punctuation). 2528 * 2529 * Same as java.lang.Character.isJavaIdentifierStart(). 2530 * 2531 * @param c the code point to be tested 2532 * @return TRUE if the code point may start a Java identifier 2533 * 2534 * @see u_isJavaIDPart 2535 * @see u_isalpha 2536 * @see u_isIDStart 2537 * @stable ICU 2.0 2538 */ 2539 U_STABLE UBool U_EXPORT2 2540 u_isJavaIDStart(UChar32 c); 2541 2542 /** 2543 * Determines if the specified character is permissible 2544 * in a Java identifier. 2545 * In addition to u_isIDPart(c), true for characters with 2546 * general category "Sc" (currency symbols). 2547 * 2548 * Same as java.lang.Character.isJavaIdentifierPart(). 2549 * 2550 * @param c the code point to be tested 2551 * @return TRUE if the code point may occur in a Java identifier 2552 * 2553 * @see u_isIDIgnorable 2554 * @see u_isJavaIDStart 2555 * @see u_isalpha 2556 * @see u_isdigit 2557 * @see u_isIDPart 2558 * @stable ICU 2.0 2559 */ 2560 U_STABLE UBool U_EXPORT2 2561 u_isJavaIDPart(UChar32 c); 2562 2563 /** 2564 * The given character is mapped to its lowercase equivalent according to 2565 * UnicodeData.txt; if the character has no lowercase equivalent, the character 2566 * itself is returned. 2567 * 2568 * Same as java.lang.Character.toLowerCase(). 2569 * 2570 * This function only returns the simple, single-code point case mapping. 2571 * Full case mappings may result in zero, one or more code points and depend 2572 * on context or language etc. 2573 * Full case mappings are applied by the string case mapping functions, 2574 * see ustring.h and the UnicodeString class. 2575 * 2576 * @param c the code point to be mapped 2577 * @return the Simple_Lowercase_Mapping of the code point, if any; 2578 * otherwise the code point itself. 2579 * @stable ICU 2.0 2580 */ 2581 U_STABLE UChar32 U_EXPORT2 2582 u_tolower(UChar32 c); 2583 2584 /** 2585 * The given character is mapped to its uppercase equivalent according to UnicodeData.txt; 2586 * if the character has no uppercase equivalent, the character itself is 2587 * returned. 2588 * 2589 * Same as java.lang.Character.toUpperCase(). 2590 * 2591 * This function only returns the simple, single-code point case mapping. 2592 * Full case mappings may result in zero, one or more code points and depend 2593 * on context or language etc. 2594 * Full case mappings are applied by the string case mapping functions, 2595 * see ustring.h and the UnicodeString class. 2596 * 2597 * @param c the code point to be mapped 2598 * @return the Simple_Uppercase_Mapping of the code point, if any; 2599 * otherwise the code point itself. 2600 * @stable ICU 2.0 2601 */ 2602 U_STABLE UChar32 U_EXPORT2 2603 u_toupper(UChar32 c); 2604 2605 /** 2606 * The given character is mapped to its titlecase equivalent 2607 * according to UnicodeData.txt; 2608 * if none is defined, the character itself is returned. 2609 * 2610 * Same as java.lang.Character.toTitleCase(). 2611 * 2612 * This function only returns the simple, single-code point case mapping. 2613 * Full case mappings may result in zero, one or more code points and depend 2614 * on context or language etc. 2615 * Full case mappings are applied by the string case mapping functions, 2616 * see ustring.h and the UnicodeString class. 2617 * 2618 * @param c the code point to be mapped 2619 * @return the Simple_Titlecase_Mapping of the code point, if any; 2620 * otherwise the code point itself. 2621 * @stable ICU 2.0 2622 */ 2623 U_STABLE UChar32 U_EXPORT2 2624 u_totitle(UChar32 c); 2625 2626 /** Option value for case folding: use default mappings defined in CaseFolding.txt. @stable ICU 2.0 */ 2627 #define U_FOLD_CASE_DEFAULT 0 2628 2629 /** 2630 * Option value for case folding: 2631 * 2632 * Use the modified set of mappings provided in CaseFolding.txt to handle dotted I 2633 * and dotless i appropriately for Turkic languages (tr, az). 2634 * 2635 * Before Unicode 3.2, CaseFolding.txt contains mappings marked with 'I' that 2636 * are to be included for default mappings and 2637 * excluded for the Turkic-specific mappings. 2638 * 2639 * Unicode 3.2 CaseFolding.txt instead contains mappings marked with 'T' that 2640 * are to be excluded for default mappings and 2641 * included for the Turkic-specific mappings. 2642 * 2643 * @stable ICU 2.0 2644 */ 2645 #define U_FOLD_CASE_EXCLUDE_SPECIAL_I 1 2646 2647 /** 2648 * The given character is mapped to its case folding equivalent according to 2649 * UnicodeData.txt and CaseFolding.txt; 2650 * if the character has no case folding equivalent, the character 2651 * itself is returned. 2652 * 2653 * This function only returns the simple, single-code point case mapping. 2654 * Full case mappings may result in zero, one or more code points and depend 2655 * on context or language etc. 2656 * Full case mappings are applied by the string case mapping functions, 2657 * see ustring.h and the UnicodeString class. 2658 * 2659 * @param c the code point to be mapped 2660 * @param options Either U_FOLD_CASE_DEFAULT or U_FOLD_CASE_EXCLUDE_SPECIAL_I 2661 * @return the Simple_Case_Folding of the code point, if any; 2662 * otherwise the code point itself. 2663 * @stable ICU 2.0 2664 */ 2665 U_STABLE UChar32 U_EXPORT2 2666 u_foldCase(UChar32 c, uint32_t options); 2667 2668 /** 2669 * Returns the decimal digit value of the code point in the 2670 * specified radix. 2671 * 2672 * If the radix is not in the range <code>2<=radix<=36</code> or if the 2673 * value of <code>c</code> is not a valid digit in the specified 2674 * radix, <code>-1</code> is returned. A character is a valid digit 2675 * if at least one of the following is true: 2676 * <ul> 2677 * <li>The character has a decimal digit value. 2678 * Such characters have the general category "Nd" (decimal digit numbers) 2679 * and a Numeric_Type of Decimal. 2680 * In this case the value is the character's decimal digit value.</li> 2681 * <li>The character is one of the uppercase Latin letters 2682 * <code>'A'</code> through <code>'Z'</code>. 2683 * In this case the value is <code>c-'A'+10</code>.</li> 2684 * <li>The character is one of the lowercase Latin letters 2685 * <code>'a'</code> through <code>'z'</code>. 2686 * In this case the value is <code>ch-'a'+10</code>.</li> 2687 * <li>Latin letters from both the ASCII range (0061..007A, 0041..005A) 2688 * as well as from the Fullwidth ASCII range (FF41..FF5A, FF21..FF3A) 2689 * are recognized.</li> 2690 * </ul> 2691 * 2692 * Same as java.lang.Character.digit(). 2693 * 2694 * @param ch the code point to be tested. 2695 * @param radix the radix. 2696 * @return the numeric value represented by the character in the 2697 * specified radix, 2698 * or -1 if there is no value or if the value exceeds the radix. 2699 * 2700 * @see UCHAR_NUMERIC_TYPE 2701 * @see u_forDigit 2702 * @see u_charDigitValue 2703 * @see u_isdigit 2704 * @stable ICU 2.0 2705 */ 2706 U_STABLE int32_t U_EXPORT2 2707 u_digit(UChar32 ch, int8_t radix); 2708 2709 /** 2710 * Determines the character representation for a specific digit in 2711 * the specified radix. If the value of <code>radix</code> is not a 2712 * valid radix, or the value of <code>digit</code> is not a valid 2713 * digit in the specified radix, the null character 2714 * (<code>U+0000</code>) is returned. 2715 * <p> 2716 * The <code>radix</code> argument is valid if it is greater than or 2717 * equal to 2 and less than or equal to 36. 2718 * The <code>digit</code> argument is valid if 2719 * <code>0 <= digit < radix</code>. 2720 * <p> 2721 * If the digit is less than 10, then 2722 * <code>'0' + digit</code> is returned. Otherwise, the value 2723 * <code>'a' + digit - 10</code> is returned. 2724 * 2725 * Same as java.lang.Character.forDigit(). 2726 * 2727 * @param digit the number to convert to a character. 2728 * @param radix the radix. 2729 * @return the <code>char</code> representation of the specified digit 2730 * in the specified radix. 2731 * 2732 * @see u_digit 2733 * @see u_charDigitValue 2734 * @see u_isdigit 2735 * @stable ICU 2.0 2736 */ 2737 U_STABLE UChar32 U_EXPORT2 2738 u_forDigit(int32_t digit, int8_t radix); 2739 2740 /** 2741 * Get the "age" of the code point. 2742 * The "age" is the Unicode version when the code point was first 2743 * designated (as a non-character or for Private Use) 2744 * or assigned a character. 2745 * This can be useful to avoid emitting code points to receiving 2746 * processes that do not accept newer characters. 2747 * The data is from the UCD file DerivedAge.txt. 2748 * 2749 * @param c The code point. 2750 * @param versionArray The Unicode version number array, to be filled in. 2751 * 2752 * @stable ICU 2.1 2753 */ 2754 U_STABLE void U_EXPORT2 2755 u_charAge(UChar32 c, UVersionInfo versionArray); 2756 2757 /** 2758 * Gets the Unicode version information. 2759 * The version array is filled in with the version information 2760 * for the Unicode standard that is currently used by ICU. 2761 * For example, Unicode version 3.1.1 is represented as an array with 2762 * the values { 3, 1, 1, 0 }. 2763 * 2764 * @param versionArray an output array that will be filled in with 2765 * the Unicode version number 2766 * @stable ICU 2.0 2767 */ 2768 U_STABLE void U_EXPORT2 2769 u_getUnicodeVersion(UVersionInfo versionArray); 2770 2771 /** 2772 * Get the FC_NFKC_Closure property string for a character. 2773 * See Unicode Standard Annex #15 for details, search for "FC_NFKC_Closure" 2774 * or for "FNC": http://www.unicode.org/reports/tr15/ 2775 * 2776 * @param c The character (code point) for which to get the FC_NFKC_Closure string. 2777 * It must be <code>0<=c<=0x10ffff</code>. 2778 * @param dest Destination address for copying the string. 2779 * The string will be zero-terminated if possible. 2780 * If there is no FC_NFKC_Closure string, 2781 * then the buffer will be set to the empty string. 2782 * @param destCapacity <code>==sizeof(dest)</code> 2783 * @param pErrorCode Pointer to a UErrorCode variable. 2784 * @return The length of the string, or 0 if there is no FC_NFKC_Closure string for this character. 2785 * If the destCapacity is less than or equal to the length, then the buffer 2786 * contains the truncated name and the returned length indicates the full 2787 * length of the name. 2788 * The length does not include the zero-termination. 2789 * 2790 * @stable ICU 2.2 2791 */ 2792 U_STABLE int32_t U_EXPORT2 2793 u_getFC_NFKC_Closure(UChar32 c, UChar *dest, int32_t destCapacity, UErrorCode *pErrorCode); 2794 2795 U_CDECL_END 2796 2797 #endif /*_UCHAR*/ 2798 /*eof*/ 2799
