icuSources/common/unicode/uchar.h

   1 // © 2016 and later: Unicode, Inc. and others.
   2 // License & terms of use: http://www.unicode.org/copyright.html
   3 /*
   4 **********************************************************************
   5 *   Copyright (C) 1997-2016, International Business Machines
   6 *   Corporation and others.  All Rights Reserved.
   7 **********************************************************************
   8 *
   9 * File UCHAR.H
  10 *
  11 * Modification History:
  12 *
  13 *   Date        Name        Description
  14 *   04/02/97    aliu        Creation.
  15 *   03/29/99    helena      Updated for C APIs.
  16 *   4/15/99     Madhu       Updated for C Implementation and Javadoc
  17 *   5/20/99     Madhu       Added the function u_getVersion()
  18 *   8/19/1999   srl         Upgraded scripts to Unicode 3.0
  19 *   8/27/1999   schererm    UCharDirection constants: U_...
  20 *   11/11/1999  weiv        added u_isalnum(), cleaned comments
  21 *   01/11/2000  helena      Renamed u_getVersion to u_getUnicodeVersion().
  22 ******************************************************************************
  23 */
  24
  25 #ifndef UCHAR_H
  26 #define UCHAR_H
  27
  28 #include "unicode/utypes.h"
  29 #include "unicode/stringoptions.h"
  30
  31 U_CDECL_BEGIN
  32
  33 /*==========================================================================*/
  34 /* Unicode version number                                                   */
  35 /*==========================================================================*/
  36 /**
  37  * Unicode version number, default for the current ICU version.
  38  * The actual Unicode Character Database (UCD) data is stored in uprops.dat
  39  * and may be generated from UCD files from a different Unicode version.
  40  * Call u_getUnicodeVersion to get the actual Unicode version of the data.
  41  *
  42  * @see u_getUnicodeVersion
  43  * @stable ICU 2.0
  44  */
  45 #define U_UNICODE_VERSION "11.0"
  46
  47 /**
  48  * \file
  49  * \brief C API: Unicode Properties
  50  *
  51  * This C API provides low-level access to the Unicode Character Database.
  52  * In addition to raw property values, some convenience functions calculate
  53  * derived properties, for example for Java-style programming.
  54  *
  55  * Unicode assigns each code point (not just assigned character) values for
  56  * many properties.
  57  * Most of them are simple boolean flags, or constants from a small enumerated list.
  58  * For some properties, values are strings or other relatively more complex types.
  59  *
  60  * For more information see
  61  * "About the Unicode Character Database" (http://www.unicode.org/ucd/)
  62  * and the ICU User Guide chapter on Properties (http://icu-project.org/userguide/properties.html).
  63  *
  64  * Many functions are designed to match java.lang.Character functions.
  65  * See the individual function documentation,
  66  * and see the JDK 1.4 java.lang.Character documentation
  67  * at http://java.sun.com/j2se/1.4/docs/api/java/lang/Character.html
  68  *
  69  * There are also functions that provide easy migration from C/POSIX functions
  70  * like isblank(). Their use is generally discouraged because the C/POSIX
  71  * standards do not define their semantics beyond the ASCII range, which means
  72  * that different implementations exhibit very different behavior.
  73  * Instead, Unicode properties should be used directly.
  74  *
  75  * There are also only a few, broad C/POSIX character classes, and they tend
  76  * to be used for conflicting purposes. For example, the "isalpha()" class
  77  * is sometimes used to determine word boundaries, while a more sophisticated
  78  * approach would at least distinguish initial letters from continuation
  79  * characters (the latter including combining marks).
  80  * (In ICU, BreakIterator is the most sophisticated API for word boundaries.)
  81  * Another example: There is no "istitle()" class for titlecase characters.
  82  *
  83  * ICU 3.4 and later provides API access for all twelve C/POSIX character classes.
  84  * ICU implements them according to the Standard Recommendations in
  85  * Annex C: Compatibility Properties of UTS #18 Unicode Regular Expressions
  86  * (http://www.unicode.org/reports/tr18/#Compatibility_Properties).
  87  *
  88  * API access for C/POSIX character classes is as follows:
  89  * - alpha:     u_isUAlphabetic(c) or u_hasBinaryProperty(c, UCHAR_ALPHABETIC)
  90  * - lower:     u_isULowercase(c) or u_hasBinaryProperty(c, UCHAR_LOWERCASE)
  91  * - upper:     u_isUUppercase(c) or u_hasBinaryProperty(c, UCHAR_UPPERCASE)
  92  * - punct:     u_ispunct(c)
  93  * - digit:     u_isdigit(c) or u_charType(c)==U_DECIMAL_DIGIT_NUMBER
  94  * - xdigit:    u_isxdigit(c) or u_hasBinaryProperty(c, UCHAR_POSIX_XDIGIT)
  95  * - alnum:     u_hasBinaryProperty(c, UCHAR_POSIX_ALNUM)
  96  * - space:     u_isUWhiteSpace(c) or u_hasBinaryProperty(c, UCHAR_WHITE_SPACE)
  97  * - blank:     u_isblank(c) or u_hasBinaryProperty(c, UCHAR_POSIX_BLANK)
  98  * - cntrl:     u_charType(c)==U_CONTROL_CHAR
  99  * - graph:     u_hasBinaryProperty(c, UCHAR_POSIX_GRAPH)
 100  * - print:     u_hasBinaryProperty(c, UCHAR_POSIX_PRINT)
 101  *
 102  * Note: Some of the u_isxyz() functions in uchar.h predate, and do not match,
 103  * the Standard Recommendations in UTS #18. Instead, they match Java
 104  * functions according to their API documentation.
 105  *
 106  * \htmlonly
 107  * The C/POSIX character classes are also available in UnicodeSet patterns,
 108  * using patterns like [:graph:] or \p{graph}.
 109  * \endhtmlonly
 110  *
 111  * Note: There are several ICU whitespace functions.
 112  * Comparison:
 113  * - u_isUWhiteSpace=UCHAR_WHITE_SPACE: Unicode White_Space property;
 114  *       most of general categories "Z" (separators) + most whitespace ISO controls
 115  *       (including no-break spaces, but excluding IS1..IS4)
 116  * - u_isWhitespace: Java isWhitespace; Z + whitespace ISO controls but excluding no-break spaces
 117  * - u_isJavaSpaceChar: Java isSpaceChar; just Z (including no-break spaces)
 118  * - u_isspace: Z + whitespace ISO controls (including no-break spaces)
 119  * - u_isblank: "horizontal spaces" = TAB + Zs
 120  */
 121
 122 /**
 123  * Constants.
 124  */
 125
 126 /** The lowest Unicode code point value. Code points are non-negative. @stable ICU 2.0 */
 127 #define UCHAR_MIN_VALUE 0
 128
 129 /**
 130  * The highest Unicode code point value (scalar value) according to
 131  * The Unicode Standard. This is a 21-bit value (20.1 bits, rounded up).
 132  * For a single character, UChar32 is a simple type that can hold any code point value.
 133  *
 134  * @see UChar32
 135  * @stable ICU 2.0
 136  */
 137 #define UCHAR_MAX_VALUE 0x10ffff
 138
 139 /**
 140  * Get a single-bit bit set (a flag) from a bit number 0..31.
 141  * @stable ICU 2.1
 142  */
 143 #define U_MASK(x) ((uint32_t)1<<(x))
 144
 145 /**
 146  * Selection constants for Unicode properties.
 147  * These constants are used in functions like u_hasBinaryProperty to select
 148  * one of the Unicode properties.
 149  *
 150  * The properties APIs are intended to reflect Unicode properties as defined
 151  * in the Unicode Character Database (UCD) and Unicode Technical Reports (UTR).
 152  *
 153  * For details about the properties see
 154  * UAX #44: Unicode Character Database (http://www.unicode.org/reports/tr44/).
 155  *
 156  * Important: If ICU is built with UCD files from Unicode versions below, e.g., 3.2,
 157  * then properties marked with "new in Unicode 3.2" are not or not fully available.
 158  * Check u_getUnicodeVersion to be sure.
 159  *
 160  * @see u_hasBinaryProperty
 161  * @see u_getIntPropertyValue
 162  * @see u_getUnicodeVersion
 163  * @stable ICU 2.1
 164  */
 165 typedef enum UProperty {
 166     /*
 167      * Note: UProperty constants are parsed by preparseucd.py.
 168      * It matches lines like
 169      *     UCHAR_<Unicode property name>=<integer>,
 170      */
 171
 172     /*  Note: Place UCHAR_ALPHABETIC before UCHAR_BINARY_START so that
 173     debuggers display UCHAR_ALPHABETIC as the symbolic name for 0,
 174     rather than UCHAR_BINARY_START.  Likewise for other *_START
 175     identifiers. */
 176
 177     /** Binary property Alphabetic. Same as u_isUAlphabetic, different from u_isalpha.
 178         Lu+Ll+Lt+Lm+Lo+Nl+Other_Alphabetic @stable ICU 2.1 */
 179     UCHAR_ALPHABETIC=0,
 180     /** First constant for binary Unicode properties. @stable ICU 2.1 */
 181     UCHAR_BINARY_START=UCHAR_ALPHABETIC,
 182     /** Binary property ASCII_Hex_Digit. 0-9 A-F a-f @stable ICU 2.1 */
 183     UCHAR_ASCII_HEX_DIGIT=1,
 184     /** Binary property Bidi_Control.
 185         Format controls which have specific functions
 186         in the Bidi Algorithm. @stable ICU 2.1 */
 187     UCHAR_BIDI_CONTROL=2,
 188     /** Binary property Bidi_Mirrored.
 189         Characters that may change display in RTL text.
 190         Same as u_isMirrored.
 191         See Bidi Algorithm, UTR 9. @stable ICU 2.1 */
 192     UCHAR_BIDI_MIRRORED=3,
 193     /** Binary property Dash. Variations of dashes. @stable ICU 2.1 */
 194     UCHAR_DASH=4,
 195     /** Binary property Default_Ignorable_Code_Point (new in Unicode 3.2).
 196         Ignorable in most processing.
 197         <2060..206F, FFF0..FFFB, E0000..E0FFF>+Other_Default_Ignorable_Code_Point+(Cf+Cc+Cs-White_Space) @stable ICU 2.1 */
 198     UCHAR_DEFAULT_IGNORABLE_CODE_POINT=5,
 199     /** Binary property Deprecated (new in Unicode 3.2).
 200         The usage of deprecated characters is strongly discouraged. @stable ICU 2.1 */
 201     UCHAR_DEPRECATED=6,
 202     /** Binary property Diacritic. Characters that linguistically modify
 203         the meaning of another character to which they apply. @stable ICU 2.1 */
 204     UCHAR_DIACRITIC=7,
 205     /** Binary property Extender.
 206         Extend the value or shape of a preceding alphabetic character,
 207         e.g., length and iteration marks. @stable ICU 2.1 */
 208     UCHAR_EXTENDER=8,
 209     /** Binary property Full_Composition_Exclusion.
 210         CompositionExclusions.txt+Singleton Decompositions+
 211         Non-Starter Decompositions. @stable ICU 2.1 */
 212     UCHAR_FULL_COMPOSITION_EXCLUSION=9,
 213     /** Binary property Grapheme_Base (new in Unicode 3.2).
 214         For programmatic determination of grapheme cluster boundaries.
 215         [0..10FFFF]-Cc-Cf-Cs-Co-Cn-Zl-Zp-Grapheme_Link-Grapheme_Extend-CGJ @stable ICU 2.1 */
 216     UCHAR_GRAPHEME_BASE=10,
 217     /** Binary property Grapheme_Extend (new in Unicode 3.2).
 218         For programmatic determination of grapheme cluster boundaries.
 219         Me+Mn+Mc+Other_Grapheme_Extend-Grapheme_Link-CGJ @stable ICU 2.1 */
 220     UCHAR_GRAPHEME_EXTEND=11,
 221     /** Binary property Grapheme_Link (new in Unicode 3.2).
 222         For programmatic determination of grapheme cluster boundaries. @stable ICU 2.1 */
 223     UCHAR_GRAPHEME_LINK=12,
 224     /** Binary property Hex_Digit.
 225         Characters commonly used for hexadecimal numbers. @stable ICU 2.1 */
 226     UCHAR_HEX_DIGIT=13,
 227     /** Binary property Hyphen. Dashes used to mark connections
 228         between pieces of words, plus the Katakana middle dot. @stable ICU 2.1 */
 229     UCHAR_HYPHEN=14,
 230     /** Binary property ID_Continue.
 231         Characters that can continue an identifier.
 232         DerivedCoreProperties.txt also says "NOTE: Cf characters should be filtered out."
 233         ID_Start+Mn+Mc+Nd+Pc @stable ICU 2.1 */
 234     UCHAR_ID_CONTINUE=15,
 235     /** Binary property ID_Start.
 236         Characters that can start an identifier.
 237         Lu+Ll+Lt+Lm+Lo+Nl @stable ICU 2.1 */
 238     UCHAR_ID_START=16,
 239     /** Binary property Ideographic.
 240         CJKV ideographs. @stable ICU 2.1 */
 241     UCHAR_IDEOGRAPHIC=17,
 242     /** Binary property IDS_Binary_Operator (new in Unicode 3.2).
 243         For programmatic determination of
 244         Ideographic Description Sequences. @stable ICU 2.1 */
 245     UCHAR_IDS_BINARY_OPERATOR=18,
 246     /** Binary property IDS_Trinary_Operator (new in Unicode 3.2).
 247         For programmatic determination of
 248         Ideographic Description Sequences. @stable ICU 2.1 */
 249     UCHAR_IDS_TRINARY_OPERATOR=19,
 250     /** Binary property Join_Control.
 251         Format controls for cursive joining and ligation. @stable ICU 2.1 */
 252     UCHAR_JOIN_CONTROL=20,
 253     /** Binary property Logical_Order_Exception (new in Unicode 3.2).
 254         Characters that do not use logical order and
 255         require special handling in most processing. @stable ICU 2.1 */
 256     UCHAR_LOGICAL_ORDER_EXCEPTION=21,
 257     /** Binary property Lowercase. Same as u_isULowercase, different from u_islower.
 258         Ll+Other_Lowercase @stable ICU 2.1 */
 259     UCHAR_LOWERCASE=22,
 260     /** Binary property Math. Sm+Other_Math @stable ICU 2.1 */
 261     UCHAR_MATH=23,
 262     /** Binary property Noncharacter_Code_Point.
 263         Code points that are explicitly defined as illegal
 264         for the encoding of characters. @stable ICU 2.1 */
 265     UCHAR_NONCHARACTER_CODE_POINT=24,
 266     /** Binary property Quotation_Mark. @stable ICU 2.1 */
 267     UCHAR_QUOTATION_MARK=25,
 268     /** Binary property Radical (new in Unicode 3.2).
 269         For programmatic determination of
 270         Ideographic Description Sequences. @stable ICU 2.1 */
 271     UCHAR_RADICAL=26,
 272     /** Binary property Soft_Dotted (new in Unicode 3.2).
 273         Characters with a "soft dot", like i or j.
 274         An accent placed on these characters causes
 275         the dot to disappear. @stable ICU 2.1 */
 276     UCHAR_SOFT_DOTTED=27,
 277     /** Binary property Terminal_Punctuation.
 278         Punctuation characters that generally mark
 279         the end of textual units. @stable ICU 2.1 */
 280     UCHAR_TERMINAL_PUNCTUATION=28,
 281     /** Binary property Unified_Ideograph (new in Unicode 3.2).
 282         For programmatic determination of
 283         Ideographic Description Sequences. @stable ICU 2.1 */
 284     UCHAR_UNIFIED_IDEOGRAPH=29,
 285     /** Binary property Uppercase. Same as u_isUUppercase, different from u_isupper.
 286         Lu+Other_Uppercase @stable ICU 2.1 */
 287     UCHAR_UPPERCASE=30,
 288     /** Binary property White_Space.
 289         Same as u_isUWhiteSpace, different from u_isspace and u_isWhitespace.
 290         Space characters+TAB+CR+LF-ZWSP-ZWNBSP @stable ICU 2.1 */
 291     UCHAR_WHITE_SPACE=31,
 292     /** Binary property XID_Continue.
 293         ID_Continue modified to allow closure under
 294         normalization forms NFKC and NFKD. @stable ICU 2.1 */
 295     UCHAR_XID_CONTINUE=32,
 296     /** Binary property XID_Start. ID_Start modified to allow
 297         closure under normalization forms NFKC and NFKD. @stable ICU 2.1 */
 298     UCHAR_XID_START=33,
 299     /** Binary property Case_Sensitive. Either the source of a case
 300         mapping or _in_ the target of a case mapping. Not the same as
 301         the general category Cased_Letter. @stable ICU 2.6 */
 302    UCHAR_CASE_SENSITIVE=34,
 303     /** Binary property STerm (new in Unicode 4.0.1).
 304         Sentence Terminal. Used in UAX #29: Text Boundaries
 305         (http://www.unicode.org/reports/tr29/)
 306         @stable ICU 3.0 */
 307     UCHAR_S_TERM=35,
 308     /** Binary property Variation_Selector (new in Unicode 4.0.1).
 309         Indicates all those characters that qualify as Variation Selectors.
 310         For details on the behavior of these characters,
 311         see StandardizedVariants.html and 15.6 Variation Selectors.
 312         @stable ICU 3.0 */
 313     UCHAR_VARIATION_SELECTOR=36,
 314     /** Binary property NFD_Inert.
 315         ICU-specific property for characters that are inert under NFD,
 316         i.e., they do not interact with adjacent characters.
 317         See the documentation for the Normalizer2 class and the
 318         Normalizer2::isInert() method.
 319         @stable ICU 3.0 */
 320     UCHAR_NFD_INERT=37,
 321     /** Binary property NFKD_Inert.
 322         ICU-specific property for characters that are inert under NFKD,
 323         i.e., they do not interact with adjacent characters.
 324         See the documentation for the Normalizer2 class and the
 325         Normalizer2::isInert() method.
 326         @stable ICU 3.0 */
 327     UCHAR_NFKD_INERT=38,
 328     /** Binary property NFC_Inert.
 329         ICU-specific property for characters that are inert under NFC,
 330         i.e., they do not interact with adjacent characters.
 331         See the documentation for the Normalizer2 class and the
 332         Normalizer2::isInert() method.
 333         @stable ICU 3.0 */
 334     UCHAR_NFC_INERT=39,
 335     /** Binary property NFKC_Inert.
 336         ICU-specific property for characters that are inert under NFKC,
 337         i.e., they do not interact with adjacent characters.
 338         See the documentation for the Normalizer2 class and the
 339         Normalizer2::isInert() method.
 340         @stable ICU 3.0 */
 341     UCHAR_NFKC_INERT=40,
 342     /** Binary Property Segment_Starter.
 343         ICU-specific property for characters that are starters in terms of
 344         Unicode normalization and combining character sequences.
 345         They have ccc=0 and do not occur in non-initial position of the
 346         canonical decomposition of any character
 347         (like a-umlaut in NFD and a Jamo T in an NFD(Hangul LVT)).
 348         ICU uses this property for segmenting a string for generating a set of
 349         canonically equivalent strings, e.g. for canonical closure while
 350         processing collation tailoring rules.
 351         @stable ICU 3.0 */
 352     UCHAR_SEGMENT_STARTER=41,
 353     /** Binary property Pattern_Syntax (new in Unicode 4.1).
 354         See UAX #31 Identifier and Pattern Syntax
 355         (http://www.unicode.org/reports/tr31/)
 356         @stable ICU 3.4 */
 357     UCHAR_PATTERN_SYNTAX=42,
 358     /** Binary property Pattern_White_Space (new in Unicode 4.1).
 359         See UAX #31 Identifier and Pattern Syntax
 360         (http://www.unicode.org/reports/tr31/)
 361         @stable ICU 3.4 */
 362     UCHAR_PATTERN_WHITE_SPACE=43,
 363     /** Binary property alnum (a C/POSIX character class).
 364         Implemented according to the UTS #18 Annex C Standard Recommendation.
 365         See the uchar.h file documentation.
 366         @stable ICU 3.4 */
 367     UCHAR_POSIX_ALNUM=44,
 368     /** Binary property blank (a C/POSIX character class).
 369         Implemented according to the UTS #18 Annex C Standard Recommendation.
 370         See the uchar.h file documentation.
 371         @stable ICU 3.4 */
 372     UCHAR_POSIX_BLANK=45,
 373     /** Binary property graph (a C/POSIX character class).
 374         Implemented according to the UTS #18 Annex C Standard Recommendation.
 375         See the uchar.h file documentation.
 376         @stable ICU 3.4 */
 377     UCHAR_POSIX_GRAPH=46,
 378     /** Binary property print (a C/POSIX character class).
 379         Implemented according to the UTS #18 Annex C Standard Recommendation.
 380         See the uchar.h file documentation.
 381         @stable ICU 3.4 */
 382     UCHAR_POSIX_PRINT=47,
 383     /** Binary property xdigit (a C/POSIX character class).
 384         Implemented according to the UTS #18 Annex C Standard Recommendation.
 385         See the uchar.h file documentation.
 386         @stable ICU 3.4 */
 387     UCHAR_POSIX_XDIGIT=48,
 388     /** Binary property Cased. For Lowercase, Uppercase and Titlecase characters. @stable ICU 4.4 */
 389     UCHAR_CASED=49,
 390     /** Binary property Case_Ignorable. Used in context-sensitive case mappings. @stable ICU 4.4 */
 391     UCHAR_CASE_IGNORABLE=50,
 392     /** Binary property Changes_When_Lowercased. @stable ICU 4.4 */
 393     UCHAR_CHANGES_WHEN_LOWERCASED=51,
 394     /** Binary property Changes_When_Uppercased. @stable ICU 4.4 */
 395     UCHAR_CHANGES_WHEN_UPPERCASED=52,
 396     /** Binary property Changes_When_Titlecased. @stable ICU 4.4 */
 397     UCHAR_CHANGES_WHEN_TITLECASED=53,
 398     /** Binary property Changes_When_Casefolded. @stable ICU 4.4 */
 399     UCHAR_CHANGES_WHEN_CASEFOLDED=54,
 400     /** Binary property Changes_When_Casemapped. @stable ICU 4.4 */
 401     UCHAR_CHANGES_WHEN_CASEMAPPED=55,
 402     /** Binary property Changes_When_NFKC_Casefolded. @stable ICU 4.4 */
 403     UCHAR_CHANGES_WHEN_NFKC_CASEFOLDED=56,
 404     /**
 405      * Binary property Emoji.
 406      * See http://www.unicode.org/reports/tr51/#Emoji_Properties
 407      *
 408      * @stable ICU 57
 409      */
 410     UCHAR_EMOJI=57,
 411     /**
 412      * Binary property Emoji_Presentation.
 413      * See http://www.unicode.org/reports/tr51/#Emoji_Properties
 414      *
 415      * @stable ICU 57
 416      */
 417     UCHAR_EMOJI_PRESENTATION=58,
 418     /**
 419      * Binary property Emoji_Modifier.
 420      * See http://www.unicode.org/reports/tr51/#Emoji_Properties
 421      *
 422      * @stable ICU 57
 423      */
 424     UCHAR_EMOJI_MODIFIER=59,
 425     /**
 426      * Binary property Emoji_Modifier_Base.
 427      * See http://www.unicode.org/reports/tr51/#Emoji_Properties
 428      *
 429      * @stable ICU 57
 430      */
 431     UCHAR_EMOJI_MODIFIER_BASE=60,
 432     /**
 433      * Binary property Emoji_Component.
 434      * See http://www.unicode.org/reports/tr51/#Emoji_Properties
 435      *
 436      * @stable ICU 60
 437      */
 438     UCHAR_EMOJI_COMPONENT=61,
 439     /**
 440      * Binary property Regional_Indicator.
 441      * @stable ICU 60
 442      */
 443     UCHAR_REGIONAL_INDICATOR=62,
 444     /**
 445      * Binary property Prepended_Concatenation_Mark.
 446      * @stable ICU 60
 447      */
 448     UCHAR_PREPENDED_CONCATENATION_MARK=63,
 449     /**
 450      * Binary property Extended_Pictographic.
 451      * See http://www.unicode.org/reports/tr51/#Emoji_Properties
 452      *
 453      * @stable ICU 62
 454      */
 455     UCHAR_EXTENDED_PICTOGRAPHIC=64,
 456 #ifndef U_HIDE_DEPRECATED_API
 457     /**
 458      * One more than the last constant for binary Unicode properties.
 459      * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420.
 460      */
 461     UCHAR_BINARY_LIMIT,
 462 #endif  // U_HIDE_DEPRECATED_API
 463
 464     /** Enumerated property Bidi_Class.
 465         Same as u_charDirection, returns UCharDirection values. @stable ICU 2.2 */
 466     UCHAR_BIDI_CLASS=0x1000,
 467     /** First constant for enumerated/integer Unicode properties. @stable ICU 2.2 */
 468     UCHAR_INT_START=UCHAR_BIDI_CLASS,
 469     /** Enumerated property Block.
 470         Same as ublock_getCode, returns UBlockCode values. @stable ICU 2.2 */
 471     UCHAR_BLOCK=0x1001,
 472     /** Enumerated property Canonical_Combining_Class.
 473         Same as u_getCombiningClass, returns 8-bit numeric values. @stable ICU 2.2 */
 474     UCHAR_CANONICAL_COMBINING_CLASS=0x1002,
 475     /** Enumerated property Decomposition_Type.
 476         Returns UDecompositionType values. @stable ICU 2.2 */
 477     UCHAR_DECOMPOSITION_TYPE=0x1003,
 478     /** Enumerated property East_Asian_Width.
 479         See http://www.unicode.org/reports/tr11/
 480         Returns UEastAsianWidth values. @stable ICU 2.2 */
 481     UCHAR_EAST_ASIAN_WIDTH=0x1004,
 482     /** Enumerated property General_Category.
 483         Same as u_charType, returns UCharCategory values. @stable ICU 2.2 */
 484     UCHAR_GENERAL_CATEGORY=0x1005,
 485     /** Enumerated property Joining_Group.
 486         Returns UJoiningGroup values. @stable ICU 2.2 */
 487     UCHAR_JOINING_GROUP=0x1006,
 488     /** Enumerated property Joining_Type.
 489         Returns UJoiningType values. @stable ICU 2.2 */
 490     UCHAR_JOINING_TYPE=0x1007,
 491     /** Enumerated property Line_Break.
 492         Returns ULineBreak values. @stable ICU 2.2 */
 493     UCHAR_LINE_BREAK=0x1008,
 494     /** Enumerated property Numeric_Type.
 495         Returns UNumericType values. @stable ICU 2.2 */
 496     UCHAR_NUMERIC_TYPE=0x1009,
 497     /** Enumerated property Script.
 498         Same as uscript_getScript, returns UScriptCode values. @stable ICU 2.2 */
 499     UCHAR_SCRIPT=0x100A,
 500     /** Enumerated property Hangul_Syllable_Type, new in Unicode 4.
 501         Returns UHangulSyllableType values. @stable ICU 2.6 */
 502     UCHAR_HANGUL_SYLLABLE_TYPE=0x100B,
 503     /** Enumerated property NFD_Quick_Check.
 504         Returns UNormalizationCheckResult values. @stable ICU 3.0 */
 505     UCHAR_NFD_QUICK_CHECK=0x100C,
 506     /** Enumerated property NFKD_Quick_Check.
 507         Returns UNormalizationCheckResult values. @stable ICU 3.0 */
 508     UCHAR_NFKD_QUICK_CHECK=0x100D,
 509     /** Enumerated property NFC_Quick_Check.
 510         Returns UNormalizationCheckResult values. @stable ICU 3.0 */
 511     UCHAR_NFC_QUICK_CHECK=0x100E,
 512     /** Enumerated property NFKC_Quick_Check.
 513         Returns UNormalizationCheckResult values. @stable ICU 3.0 */
 514     UCHAR_NFKC_QUICK_CHECK=0x100F,
 515     /** Enumerated property Lead_Canonical_Combining_Class.
 516         ICU-specific property for the ccc of the first code point
 517         of the decomposition, or lccc(c)=ccc(NFD(c)[0]).
 518         Useful for checking for canonically ordered text;
 519         see UNORM_FCD and http://www.unicode.org/notes/tn5/#FCD .
 520         Returns 8-bit numeric values like UCHAR_CANONICAL_COMBINING_CLASS. @stable ICU 3.0 */
 521     UCHAR_LEAD_CANONICAL_COMBINING_CLASS=0x1010,
 522     /** Enumerated property Trail_Canonical_Combining_Class.
 523         ICU-specific property for the ccc of the last code point
 524         of the decomposition, or tccc(c)=ccc(NFD(c)[last]).
 525         Useful for checking for canonically ordered text;
 526         see UNORM_FCD and http://www.unicode.org/notes/tn5/#FCD .
 527         Returns 8-bit numeric values like UCHAR_CANONICAL_COMBINING_CLASS. @stable ICU 3.0 */
 528     UCHAR_TRAIL_CANONICAL_COMBINING_CLASS=0x1011,
 529     /** Enumerated property Grapheme_Cluster_Break (new in Unicode 4.1).
 530         Used in UAX #29: Text Boundaries
 531         (http://www.unicode.org/reports/tr29/)
 532         Returns UGraphemeClusterBreak values. @stable ICU 3.4 */
 533     UCHAR_GRAPHEME_CLUSTER_BREAK=0x1012,
 534     /** Enumerated property Sentence_Break (new in Unicode 4.1).
 535         Used in UAX #29: Text Boundaries
 536         (http://www.unicode.org/reports/tr29/)
 537         Returns USentenceBreak values. @stable ICU 3.4 */
 538     UCHAR_SENTENCE_BREAK=0x1013,
 539     /** Enumerated property Word_Break (new in Unicode 4.1).
 540         Used in UAX #29: Text Boundaries
 541         (http://www.unicode.org/reports/tr29/)
 542         Returns UWordBreakValues values. @stable ICU 3.4 */
 543     UCHAR_WORD_BREAK=0x1014,
 544     /** Enumerated property Bidi_Paired_Bracket_Type (new in Unicode 6.3).
 545         Used in UAX #9: Unicode Bidirectional Algorithm
 546         (http://www.unicode.org/reports/tr9/)
 547         Returns UBidiPairedBracketType values. @stable ICU 52 */
 548     UCHAR_BIDI_PAIRED_BRACKET_TYPE=0x1015,
 549 #ifndef U_HIDE_DEPRECATED_API
 550     /**
 551      * One more than the last constant for enumerated/integer Unicode properties.
 552      * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420.
 553      */
 554     UCHAR_INT_LIMIT=0x1016,
 555 #endif  // U_HIDE_DEPRECATED_API
 556
 557     /** Bitmask property General_Category_Mask.
 558         This is the General_Category property returned as a bit mask.
 559         When used in u_getIntPropertyValue(c), same as U_MASK(u_charType(c)),
 560         returns bit masks for UCharCategory values where exactly one bit is set.
 561         When used with u_getPropertyValueName() and u_getPropertyValueEnum(),
 562         a multi-bit mask is used for sets of categories like "Letters".
 563         Mask values should be cast to uint32_t.
 564         @stable ICU 2.4 */
 565     UCHAR_GENERAL_CATEGORY_MASK=0x2000,
 566     /** First constant for bit-mask Unicode properties. @stable ICU 2.4 */
 567     UCHAR_MASK_START=UCHAR_GENERAL_CATEGORY_MASK,
 568 #ifndef U_HIDE_DEPRECATED_API
 569     /**
 570      * One more than the last constant for bit-mask Unicode properties.
 571      * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420.
 572      */
 573     UCHAR_MASK_LIMIT=0x2001,
 574 #endif  // U_HIDE_DEPRECATED_API
 575
 576     /** Double property Numeric_Value.
 577         Corresponds to u_getNumericValue. @stable ICU 2.4 */
 578     UCHAR_NUMERIC_VALUE=0x3000,
 579     /** First constant for double Unicode properties. @stable ICU 2.4 */
 580     UCHAR_DOUBLE_START=UCHAR_NUMERIC_VALUE,
 581 #ifndef U_HIDE_DEPRECATED_API
 582     /**
 583      * One more than the last constant for double Unicode properties.
 584      * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420.
 585      */
 586     UCHAR_DOUBLE_LIMIT=0x3001,
 587 #endif  // U_HIDE_DEPRECATED_API
 588
 589     /** String property Age.
 590         Corresponds to u_charAge. @stable ICU 2.4 */
 591     UCHAR_AGE=0x4000,
 592     /** First constant for string Unicode properties. @stable ICU 2.4 */
 593     UCHAR_STRING_START=UCHAR_AGE,
 594     /** String property Bidi_Mirroring_Glyph.
 595         Corresponds to u_charMirror. @stable ICU 2.4 */
 596     UCHAR_BIDI_MIRRORING_GLYPH=0x4001,
 597     /** String property Case_Folding.
 598         Corresponds to u_strFoldCase in ustring.h. @stable ICU 2.4 */
 599     UCHAR_CASE_FOLDING=0x4002,
 600 #ifndef U_HIDE_DEPRECATED_API
 601     /** Deprecated string property ISO_Comment.
 602         Corresponds to u_getISOComment. @deprecated ICU 49 */
 603     UCHAR_ISO_COMMENT=0x4003,
 604 #endif  /* U_HIDE_DEPRECATED_API */
 605     /** String property Lowercase_Mapping.
 606         Corresponds to u_strToLower in ustring.h. @stable ICU 2.4 */
 607     UCHAR_LOWERCASE_MAPPING=0x4004,
 608     /** String property Name.
 609         Corresponds to u_charName. @stable ICU 2.4 */
 610     UCHAR_NAME=0x4005,
 611     /** String property Simple_Case_Folding.
 612         Corresponds to u_foldCase. @stable ICU 2.4 */
 613     UCHAR_SIMPLE_CASE_FOLDING=0x4006,
 614     /** String property Simple_Lowercase_Mapping.
 615         Corresponds to u_tolower. @stable ICU 2.4 */
 616     UCHAR_SIMPLE_LOWERCASE_MAPPING=0x4007,
 617     /** String property Simple_Titlecase_Mapping.
 618         Corresponds to u_totitle. @stable ICU 2.4 */
 619     UCHAR_SIMPLE_TITLECASE_MAPPING=0x4008,
 620     /** String property Simple_Uppercase_Mapping.
 621         Corresponds to u_toupper. @stable ICU 2.4 */
 622     UCHAR_SIMPLE_UPPERCASE_MAPPING=0x4009,
 623     /** String property Titlecase_Mapping.
 624         Corresponds to u_strToTitle in ustring.h. @stable ICU 2.4 */
 625     UCHAR_TITLECASE_MAPPING=0x400A,
 626 #ifndef U_HIDE_DEPRECATED_API
 627     /** String property Unicode_1_Name.
 628         This property is of little practical value.
 629         Beginning with ICU 49, ICU APIs return an empty string for this property.
 630         Corresponds to u_charName(U_UNICODE_10_CHAR_NAME). @deprecated ICU 49 */
 631     UCHAR_UNICODE_1_NAME=0x400B,
 632 #endif  /* U_HIDE_DEPRECATED_API */
 633     /** String property Uppercase_Mapping.
 634         Corresponds to u_strToUpper in ustring.h. @stable ICU 2.4 */
 635     UCHAR_UPPERCASE_MAPPING=0x400C,
 636     /** String property Bidi_Paired_Bracket (new in Unicode 6.3).
 637         Corresponds to u_getBidiPairedBracket. @stable ICU 52 */
 638     UCHAR_BIDI_PAIRED_BRACKET=0x400D,
 639 #ifndef U_HIDE_DEPRECATED_API
 640     /**
 641      * One more than the last constant for string Unicode properties.
 642      * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420.
 643      */
 644     UCHAR_STRING_LIMIT=0x400E,
 645 #endif  // U_HIDE_DEPRECATED_API
 646
 647     /** Miscellaneous property Script_Extensions (new in Unicode 6.0).
 648         Some characters are commonly used in multiple scripts.
 649         For more information, see UAX #24: http://www.unicode.org/reports/tr24/.
 650         Corresponds to uscript_hasScript and uscript_getScriptExtensions in uscript.h.
 651         @stable ICU 4.6 */
 652     UCHAR_SCRIPT_EXTENSIONS=0x7000,
 653     /** First constant for Unicode properties with unusual value types. @stable ICU 4.6 */
 654     UCHAR_OTHER_PROPERTY_START=UCHAR_SCRIPT_EXTENSIONS,
 655 #ifndef U_HIDE_DEPRECATED_API
 656     /**
 657      * One more than the last constant for Unicode properties with unusual value types.
 658      * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420.
 659      */
 660     UCHAR_OTHER_PROPERTY_LIMIT=0x7001,
 661 #endif  // U_HIDE_DEPRECATED_API
 662
 663     /** Represents a nonexistent or invalid property or property value. @stable ICU 2.4 */
 664     UCHAR_INVALID_CODE = -1
 665 } UProperty;
 666
 667 /**
 668  * Data for enumerated Unicode general category types.
 669  * See http://www.unicode.org/Public/UNIDATA/UnicodeData.html .
 670  * @stable ICU 2.0
 671  */
 672 typedef enum UCharCategory
 673 {
 674     /*
 675      * Note: UCharCategory constants and their API comments are parsed by preparseucd.py.
 676      * It matches pairs of lines like
 677      *     / ** <Unicode 2-letter General_Category value> comment... * /
 678      *     U_<[A-Z_]+> = <integer>,
 679      */
 680
 681     /** Non-category for unassigned and non-character code points. @stable ICU 2.0 */
 682     U_UNASSIGNED              = 0,
 683     /** Cn "Other, Not Assigned (no characters in [UnicodeData.txt] have this property)" (same as U_UNASSIGNED!) @stable ICU 2.0 */
 684     U_GENERAL_OTHER_TYPES     = 0,
 685     /** Lu @stable ICU 2.0 */
 686     U_UPPERCASE_LETTER        = 1,
 687     /** Ll @stable ICU 2.0 */
 688     U_LOWERCASE_LETTER        = 2,
 689     /** Lt @stable ICU 2.0 */
 690     U_TITLECASE_LETTER        = 3,
 691     /** Lm @stable ICU 2.0 */
 692     U_MODIFIER_LETTER         = 4,
 693     /** Lo @stable ICU 2.0 */
 694     U_OTHER_LETTER            = 5,
 695     /** Mn @stable ICU 2.0 */
 696     U_NON_SPACING_MARK        = 6,
 697     /** Me @stable ICU 2.0 */
 698     U_ENCLOSING_MARK          = 7,
 699     /** Mc @stable ICU 2.0 */
 700     U_COMBINING_SPACING_MARK  = 8,
 701     /** Nd @stable ICU 2.0 */
 702     U_DECIMAL_DIGIT_NUMBER    = 9,
 703     /** Nl @stable ICU 2.0 */
 704     U_LETTER_NUMBER           = 10,
 705     /** No @stable ICU 2.0 */
 706     U_OTHER_NUMBER            = 11,
 707     /** Zs @stable ICU 2.0 */
 708     U_SPACE_SEPARATOR         = 12,
 709     /** Zl @stable ICU 2.0 */
 710     U_LINE_SEPARATOR          = 13,
 711     /** Zp @stable ICU 2.0 */
 712     U_PARAGRAPH_SEPARATOR     = 14,
 713     /** Cc @stable ICU 2.0 */
 714     U_CONTROL_CHAR            = 15,
 715     /** Cf @stable ICU 2.0 */
 716     U_FORMAT_CHAR             = 16,
 717     /** Co @stable ICU 2.0 */
 718     U_PRIVATE_USE_CHAR        = 17,
 719     /** Cs @stable ICU 2.0 */
 720     U_SURROGATE               = 18,
 721     /** Pd @stable ICU 2.0 */
 722     U_DASH_PUNCTUATION        = 19,
 723     /** Ps @stable ICU 2.0 */
 724     U_START_PUNCTUATION       = 20,
 725     /** Pe @stable ICU 2.0 */
 726     U_END_PUNCTUATION         = 21,
 727     /** Pc @stable ICU 2.0 */
 728     U_CONNECTOR_PUNCTUATION   = 22,
 729     /** Po @stable ICU 2.0 */
 730     U_OTHER_PUNCTUATION       = 23,
 731     /** Sm @stable ICU 2.0 */
 732     U_MATH_SYMBOL             = 24,
 733     /** Sc @stable ICU 2.0 */
 734     U_CURRENCY_SYMBOL         = 25,
 735     /** Sk @stable ICU 2.0 */
 736     U_MODIFIER_SYMBOL         = 26,
 737     /** So @stable ICU 2.0 */
 738     U_OTHER_SYMBOL            = 27,
 739     /** Pi @stable ICU 2.0 */
 740     U_INITIAL_PUNCTUATION     = 28,
 741     /** Pf @stable ICU 2.0 */
 742     U_FINAL_PUNCTUATION       = 29,
 743     /**
 744      * One higher than the last enum UCharCategory constant.
 745      * This numeric value is stable (will not change), see
 746      * http://www.unicode.org/policies/stability_policy.html#Property_Value
 747      *
 748      * @stable ICU 2.0
 749      */
 750     U_CHAR_CATEGORY_COUNT
 751 } UCharCategory;
 752
 753 /**
 754  * U_GC_XX_MASK constants are bit flags corresponding to Unicode
 755  * general category values.
 756  * For each category, the nth bit is set if the numeric value of the
 757  * corresponding UCharCategory constant is n.
 758  *
 759  * There are also some U_GC_Y_MASK constants for groups of general categories
 760  * like L for all letter categories.
 761  *
 762  * @see u_charType
 763  * @see U_GET_GC_MASK
 764  * @see UCharCategory
 765  * @stable ICU 2.1
 766  */
 767 #define U_GC_CN_MASK    U_MASK(U_GENERAL_OTHER_TYPES)
 768
 769 /** Mask constant for a UCharCategory. @stable ICU 2.1 */
 770 #define U_GC_LU_MASK    U_MASK(U_UPPERCASE_LETTER)
 771 /** Mask constant for a UCharCategory. @stable ICU 2.1 */
 772 #define U_GC_LL_MASK    U_MASK(U_LOWERCASE_LETTER)
 773 /** Mask constant for a UCharCategory. @stable ICU 2.1 */
 774 #define U_GC_LT_MASK    U_MASK(U_TITLECASE_LETTER)
 775 /** Mask constant for a UCharCategory. @stable ICU 2.1 */
 776 #define U_GC_LM_MASK    U_MASK(U_MODIFIER_LETTER)
 777 /** Mask constant for a UCharCategory. @stable ICU 2.1 */
 778 #define U_GC_LO_MASK    U_MASK(U_OTHER_LETTER)
 779
 780 /** Mask constant for a UCharCategory. @stable ICU 2.1 */
 781 #define U_GC_MN_MASK    U_MASK(U_NON_SPACING_MARK)
 782 /** Mask constant for a UCharCategory. @stable ICU 2.1 */
 783 #define U_GC_ME_MASK    U_MASK(U_ENCLOSING_MARK)
 784 /** Mask constant for a UCharCategory. @stable ICU 2.1 */
 785 #define U_GC_MC_MASK    U_MASK(U_COMBINING_SPACING_MARK)
 786
 787 /** Mask constant for a UCharCategory. @stable ICU 2.1 */
 788 #define U_GC_ND_MASK    U_MASK(U_DECIMAL_DIGIT_NUMBER)
 789 /** Mask constant for a UCharCategory. @stable ICU 2.1 */
 790 #define U_GC_NL_MASK    U_MASK(U_LETTER_NUMBER)
 791 /** Mask constant for a UCharCategory. @stable ICU 2.1 */
 792 #define U_GC_NO_MASK    U_MASK(U_OTHER_NUMBER)
 793
 794 /** Mask constant for a UCharCategory. @stable ICU 2.1 */
 795 #define U_GC_ZS_MASK    U_MASK(U_SPACE_SEPARATOR)
 796 /** Mask constant for a UCharCategory. @stable ICU 2.1 */
 797 #define U_GC_ZL_MASK    U_MASK(U_LINE_SEPARATOR)
 798 /** Mask constant for a UCharCategory. @stable ICU 2.1 */
 799 #define U_GC_ZP_MASK    U_MASK(U_PARAGRAPH_SEPARATOR)
 800
 801 /** Mask constant for a UCharCategory. @stable ICU 2.1 */
 802 #define U_GC_CC_MASK    U_MASK(U_CONTROL_CHAR)
 803 /** Mask constant for a UCharCategory. @stable ICU 2.1 */
 804 #define U_GC_CF_MASK    U_MASK(U_FORMAT_CHAR)
 805 /** Mask constant for a UCharCategory. @stable ICU 2.1 */
 806 #define U_GC_CO_MASK    U_MASK(U_PRIVATE_USE_CHAR)
 807 /** Mask constant for a UCharCategory. @stable ICU 2.1 */
 808 #define U_GC_CS_MASK    U_MASK(U_SURROGATE)
 809
 810 /** Mask constant for a UCharCategory. @stable ICU 2.1 */
 811 #define U_GC_PD_MASK    U_MASK(U_DASH_PUNCTUATION)
 812 /** Mask constant for a UCharCategory. @stable ICU 2.1 */
 813 #define U_GC_PS_MASK    U_MASK(U_START_PUNCTUATION)
 814 /** Mask constant for a UCharCategory. @stable ICU 2.1 */
 815 #define U_GC_PE_MASK    U_MASK(U_END_PUNCTUATION)
 816 /** Mask constant for a UCharCategory. @stable ICU 2.1 */
 817 #define U_GC_PC_MASK    U_MASK(U_CONNECTOR_PUNCTUATION)
 818 /** Mask constant for a UCharCategory. @stable ICU 2.1 */
 819 #define U_GC_PO_MASK    U_MASK(U_OTHER_PUNCTUATION)
 820
 821 /** Mask constant for a UCharCategory. @stable ICU 2.1 */
 822 #define U_GC_SM_MASK    U_MASK(U_MATH_SYMBOL)
 823 /** Mask constant for a UCharCategory. @stable ICU 2.1 */
 824 #define U_GC_SC_MASK    U_MASK(U_CURRENCY_SYMBOL)
 825 /** Mask constant for a UCharCategory. @stable ICU 2.1 */
 826 #define U_GC_SK_MASK    U_MASK(U_MODIFIER_SYMBOL)
 827 /** Mask constant for a UCharCategory. @stable ICU 2.1 */
 828 #define U_GC_SO_MASK    U_MASK(U_OTHER_SYMBOL)
 829
 830 /** Mask constant for a UCharCategory. @stable ICU 2.1 */
 831 #define U_GC_PI_MASK    U_MASK(U_INITIAL_PUNCTUATION)
 832 /** Mask constant for a UCharCategory. @stable ICU 2.1 */
 833 #define U_GC_PF_MASK    U_MASK(U_FINAL_PUNCTUATION)
 834
 835
 836 /** Mask constant for multiple UCharCategory bits (L Letters). @stable ICU 2.1 */
 837 #define U_GC_L_MASK \
 838             (U_GC_LU_MASK|U_GC_LL_MASK|U_GC_LT_MASK|U_GC_LM_MASK|U_GC_LO_MASK)
 839
 840 /** Mask constant for multiple UCharCategory bits (LC Cased Letters). @stable ICU 2.1 */
 841 #define U_GC_LC_MASK \
 842             (U_GC_LU_MASK|U_GC_LL_MASK|U_GC_LT_MASK)
 843
 844 /** Mask constant for multiple UCharCategory bits (M Marks). @stable ICU 2.1 */
 845 #define U_GC_M_MASK (U_GC_MN_MASK|U_GC_ME_MASK|U_GC_MC_MASK)
 846
 847 /** Mask constant for multiple UCharCategory bits (N Numbers). @stable ICU 2.1 */
 848 #define U_GC_N_MASK (U_GC_ND_MASK|U_GC_NL_MASK|U_GC_NO_MASK)
 849
 850 /** Mask constant for multiple UCharCategory bits (Z Separators). @stable ICU 2.1 */
 851 #define U_GC_Z_MASK (U_GC_ZS_MASK|U_GC_ZL_MASK|U_GC_ZP_MASK)
 852
 853 /** Mask constant for multiple UCharCategory bits (C Others). @stable ICU 2.1 */
 854 #define U_GC_C_MASK \
 855             (U_GC_CN_MASK|U_GC_CC_MASK|U_GC_CF_MASK|U_GC_CO_MASK|U_GC_CS_MASK)
 856
 857 /** Mask constant for multiple UCharCategory bits (P Punctuation). @stable ICU 2.1 */
 858 #define U_GC_P_MASK \
 859             (U_GC_PD_MASK|U_GC_PS_MASK|U_GC_PE_MASK|U_GC_PC_MASK|U_GC_PO_MASK| \
 860              U_GC_PI_MASK|U_GC_PF_MASK)
 861
 862 /** Mask constant for multiple UCharCategory bits (S Symbols). @stable ICU 2.1 */
 863 #define U_GC_S_MASK (U_GC_SM_MASK|U_GC_SC_MASK|U_GC_SK_MASK|U_GC_SO_MASK)
 864
 865 /**
 866  * This specifies the language directional property of a character set.
 867  * @stable ICU 2.0
 868  */
 869 typedef enum UCharDirection {
 870     /*
 871      * Note: UCharDirection constants and their API comments are parsed by preparseucd.py.
 872      * It matches pairs of lines like
 873      *     / ** <Unicode 1..3-letter Bidi_Class value> comment... * /
 874      *     U_<[A-Z_]+> = <integer>,
 875      */
 876
 877     /** L @stable ICU 2.0 */
 878     U_LEFT_TO_RIGHT               = 0,
 879     /** R @stable ICU 2.0 */
 880     U_RIGHT_TO_LEFT               = 1,
 881     /** EN @stable ICU 2.0 */
 882     U_EUROPEAN_NUMBER             = 2,
 883     /** ES @stable ICU 2.0 */
 884     U_EUROPEAN_NUMBER_SEPARATOR   = 3,
 885     /** ET @stable ICU 2.0 */
 886     U_EUROPEAN_NUMBER_TERMINATOR  = 4,
 887     /** AN @stable ICU 2.0 */
 888     U_ARABIC_NUMBER               = 5,
 889     /** CS @stable ICU 2.0 */
 890     U_COMMON_NUMBER_SEPARATOR     = 6,
 891     /** B @stable ICU 2.0 */
 892     U_BLOCK_SEPARATOR             = 7,
 893     /** S @stable ICU 2.0 */
 894     U_SEGMENT_SEPARATOR           = 8,
 895     /** WS @stable ICU 2.0 */
 896     U_WHITE_SPACE_NEUTRAL         = 9,
 897     /** ON @stable ICU 2.0 */
 898     U_OTHER_NEUTRAL               = 10,
 899     /** LRE @stable ICU 2.0 */
 900     U_LEFT_TO_RIGHT_EMBEDDING     = 11,
 901     /** LRO @stable ICU 2.0 */
 902     U_LEFT_TO_RIGHT_OVERRIDE      = 12,
 903     /** AL @stable ICU 2.0 */
 904     U_RIGHT_TO_LEFT_ARABIC        = 13,
 905     /** RLE @stable ICU 2.0 */
 906     U_RIGHT_TO_LEFT_EMBEDDING     = 14,
 907     /** RLO @stable ICU 2.0 */
 908     U_RIGHT_TO_LEFT_OVERRIDE      = 15,
 909     /** PDF @stable ICU 2.0 */
 910     U_POP_DIRECTIONAL_FORMAT      = 16,
 911     /** NSM @stable ICU 2.0 */
 912     U_DIR_NON_SPACING_MARK        = 17,
 913     /** BN @stable ICU 2.0 */
 914     U_BOUNDARY_NEUTRAL            = 18,
 915     /** FSI @stable ICU 52 */
 916     U_FIRST_STRONG_ISOLATE        = 19,
 917     /** LRI @stable ICU 52 */
 918     U_LEFT_TO_RIGHT_ISOLATE       = 20,
 919     /** RLI @stable ICU 52 */
 920     U_RIGHT_TO_LEFT_ISOLATE       = 21,
 921     /** PDI @stable ICU 52 */
 922     U_POP_DIRECTIONAL_ISOLATE     = 22,
 923 #ifndef U_HIDE_DEPRECATED_API
 924     /**
 925      * One more than the highest UCharDirection value.
 926      * The highest value is available via u_getIntPropertyMaxValue(UCHAR_BIDI_CLASS).
 927      *
 928      * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420.
 929      */
 930     U_CHAR_DIRECTION_COUNT
 931 #endif  // U_HIDE_DEPRECATED_API
 932 } UCharDirection;
 933
 934 /**
 935  * Bidi Paired Bracket Type constants.
 936  *
 937  * @see UCHAR_BIDI_PAIRED_BRACKET_TYPE
 938  * @stable ICU 52
 939  */
 940 typedef enum UBidiPairedBracketType {
 941     /*
 942      * Note: UBidiPairedBracketType constants are parsed by preparseucd.py.
 943      * It matches lines like
 944      *     U_BPT_<Unicode Bidi_Paired_Bracket_Type value name>
 945      */
 946
 947     /** Not a paired bracket. @stable ICU 52 */
 948     U_BPT_NONE,
 949     /** Open paired bracket. @stable ICU 52 */
 950     U_BPT_OPEN,
 951     /** Close paired bracket. @stable ICU 52 */
 952     U_BPT_CLOSE,
 953 #ifndef U_HIDE_DEPRECATED_API
 954     /**
 955      * One more than the highest normal UBidiPairedBracketType value.
 956      * The highest value is available via u_getIntPropertyMaxValue(UCHAR_BIDI_PAIRED_BRACKET_TYPE).
 957      *
 958      * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420.
 959      */
 960     U_BPT_COUNT /* 3 */
 961 #endif  // U_HIDE_DEPRECATED_API
 962 } UBidiPairedBracketType;
 963
 964 /**
 965  * Constants for Unicode blocks, see the Unicode Data file Blocks.txt
 966  * @stable ICU 2.0
 967  */
 968 enum UBlockCode {
 969     /*
 970      * Note: UBlockCode constants are parsed by preparseucd.py.
 971      * It matches lines like
 972      *     UBLOCK_<Unicode Block value name> = <integer>,
 973      */
 974
 975     /** New No_Block value in Unicode 4. @stable ICU 2.6 */
 976     UBLOCK_NO_BLOCK = 0, /*[none]*/ /* Special range indicating No_Block */
 977
 978     /** @stable ICU 2.0 */
 979     UBLOCK_BASIC_LATIN = 1, /*[0000]*/
 980
 981     /** @stable ICU 2.0 */
 982     UBLOCK_LATIN_1_SUPPLEMENT=2, /*[0080]*/
 983
 984     /** @stable ICU 2.0 */
 985     UBLOCK_LATIN_EXTENDED_A =3, /*[0100]*/
 986
 987     /** @stable ICU 2.0 */
 988     UBLOCK_LATIN_EXTENDED_B =4, /*[0180]*/
 989
 990     /** @stable ICU 2.0 */
 991     UBLOCK_IPA_EXTENSIONS =5, /*[0250]*/
 992
 993     /** @stable ICU 2.0 */
 994     UBLOCK_SPACING_MODIFIER_LETTERS =6, /*[02B0]*/
 995
 996     /** @stable ICU 2.0 */
 997     UBLOCK_COMBINING_DIACRITICAL_MARKS =7, /*[0300]*/
 998
 999     /**
1000      * Unicode 3.2 renames this block to "Greek and Coptic".
1001      * @stable ICU 2.0
1002      */
1003     UBLOCK_GREEK =8, /*[0370]*/
1004
1005     /** @stable ICU 2.0 */
1006     UBLOCK_CYRILLIC =9, /*[0400]*/
1007
1008     /** @stable ICU 2.0 */
1009     UBLOCK_ARMENIAN =10, /*[0530]*/
1010
1011     /** @stable ICU 2.0 */
1012     UBLOCK_HEBREW =11, /*[0590]*/
1013
1014     /** @stable ICU 2.0 */
1015     UBLOCK_ARABIC =12, /*[0600]*/
1016
1017     /** @stable ICU 2.0 */
1018     UBLOCK_SYRIAC =13, /*[0700]*/
1019
1020     /** @stable ICU 2.0 */
1021     UBLOCK_THAANA =14, /*[0780]*/
1022
1023     /** @stable ICU 2.0 */
1024     UBLOCK_DEVANAGARI =15, /*[0900]*/
1025
1026     /** @stable ICU 2.0 */
1027     UBLOCK_BENGALI =16, /*[0980]*/
1028
1029     /** @stable ICU 2.0 */
1030     UBLOCK_GURMUKHI =17, /*[0A00]*/
1031
1032     /** @stable ICU 2.0 */
1033     UBLOCK_GUJARATI =18, /*[0A80]*/
1034
1035     /** @stable ICU 2.0 */
1036     UBLOCK_ORIYA =19, /*[0B00]*/
1037
1038     /** @stable ICU 2.0 */
1039     UBLOCK_TAMIL =20, /*[0B80]*/
1040
1041     /** @stable ICU 2.0 */
1042     UBLOCK_TELUGU =21, /*[0C00]*/
1043
1044     /** @stable ICU 2.0 */
1045     UBLOCK_KANNADA =22, /*[0C80]*/
1046
1047     /** @stable ICU 2.0 */
1048     UBLOCK_MALAYALAM =23, /*[0D00]*/
1049
1050     /** @stable ICU 2.0 */
1051     UBLOCK_SINHALA =24, /*[0D80]*/
1052
1053     /** @stable ICU 2.0 */
1054     UBLOCK_THAI =25, /*[0E00]*/
1055
1056     /** @stable ICU 2.0 */
1057     UBLOCK_LAO =26, /*[0E80]*/
1058
1059     /** @stable ICU 2.0 */
1060     UBLOCK_TIBETAN =27, /*[0F00]*/
1061
1062     /** @stable ICU 2.0 */
1063     UBLOCK_MYANMAR =28, /*[1000]*/
1064
1065     /** @stable ICU 2.0 */
1066     UBLOCK_GEORGIAN =29, /*[10A0]*/
1067
1068     /** @stable ICU 2.0 */
1069     UBLOCK_HANGUL_JAMO =30, /*[1100]*/
1070
1071     /** @stable ICU 2.0 */
1072     UBLOCK_ETHIOPIC =31, /*[1200]*/
1073
1074     /** @stable ICU 2.0 */
1075     UBLOCK_CHEROKEE =32, /*[13A0]*/
1076
1077     /** @stable ICU 2.0 */
1078     UBLOCK_UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS =33, /*[1400]*/
1079
1080     /** @stable ICU 2.0 */
1081     UBLOCK_OGHAM =34, /*[1680]*/
1082
1083     /** @stable ICU 2.0 */
1084     UBLOCK_RUNIC =35, /*[16A0]*/
1085
1086     /** @stable ICU 2.0 */
1087     UBLOCK_KHMER =36, /*[1780]*/
1088
1089     /** @stable ICU 2.0 */
1090     UBLOCK_MONGOLIAN =37, /*[1800]*/
1091
1092     /** @stable ICU 2.0 */
1093     UBLOCK_LATIN_EXTENDED_ADDITIONAL =38, /*[1E00]*/
1094
1095     /** @stable ICU 2.0 */
1096     UBLOCK_GREEK_EXTENDED =39, /*[1F00]*/
1097
1098     /** @stable ICU 2.0 */
1099     UBLOCK_GENERAL_PUNCTUATION =40, /*[2000]*/
1100
1101     /** @stable ICU 2.0 */
1102     UBLOCK_SUPERSCRIPTS_AND_SUBSCRIPTS =41, /*[2070]*/
1103
1104     /** @stable ICU 2.0 */
1105     UBLOCK_CURRENCY_SYMBOLS =42, /*[20A0]*/
1106
1107     /**
1108      * Unicode 3.2 renames this block to "Combining Diacritical Marks for Symbols".
1109      * @stable ICU 2.0
1110      */
1111     UBLOCK_COMBINING_MARKS_FOR_SYMBOLS =43, /*[20D0]*/
1112
1113     /** @stable ICU 2.0 */
1114     UBLOCK_LETTERLIKE_SYMBOLS =44, /*[2100]*/
1115
1116     /** @stable ICU 2.0 */
1117     UBLOCK_NUMBER_FORMS =45, /*[2150]*/
1118
1119     /** @stable ICU 2.0 */
1120     UBLOCK_ARROWS =46, /*[2190]*/
1121
1122     /** @stable ICU 2.0 */
1123     UBLOCK_MATHEMATICAL_OPERATORS =47, /*[2200]*/
1124
1125     /** @stable ICU 2.0 */
1126     UBLOCK_MISCELLANEOUS_TECHNICAL =48, /*[2300]*/
1127
1128     /** @stable ICU 2.0 */
1129     UBLOCK_CONTROL_PICTURES =49, /*[2400]*/
1130
1131     /** @stable ICU 2.0 */
1132     UBLOCK_OPTICAL_CHARACTER_RECOGNITION =50, /*[2440]*/
1133
1134     /** @stable ICU 2.0 */
1135     UBLOCK_ENCLOSED_ALPHANUMERICS =51, /*[2460]*/
1136
1137     /** @stable ICU 2.0 */
1138     UBLOCK_BOX_DRAWING =52, /*[2500]*/
1139
1140     /** @stable ICU 2.0 */
1141     UBLOCK_BLOCK_ELEMENTS =53, /*[2580]*/
1142
1143     /** @stable ICU 2.0 */
1144     UBLOCK_GEOMETRIC_SHAPES =54, /*[25A0]*/
1145
1146     /** @stable ICU 2.0 */
1147     UBLOCK_MISCELLANEOUS_SYMBOLS =55, /*[2600]*/
1148
1149     /** @stable ICU 2.0 */
1150     UBLOCK_DINGBATS =56, /*[2700]*/
1151
1152     /** @stable ICU 2.0 */
1153     UBLOCK_BRAILLE_PATTERNS =57, /*[2800]*/
1154
1155     /** @stable ICU 2.0 */
1156     UBLOCK_CJK_RADICALS_SUPPLEMENT =58, /*[2E80]*/
1157
1158     /** @stable ICU 2.0 */
1159     UBLOCK_KANGXI_RADICALS =59, /*[2F00]*/
1160
1161     /** @stable ICU 2.0 */
1162     UBLOCK_IDEOGRAPHIC_DESCRIPTION_CHARACTERS =60, /*[2FF0]*/
1163
1164     /** @stable ICU 2.0 */
1165     UBLOCK_CJK_SYMBOLS_AND_PUNCTUATION =61, /*[3000]*/
1166
1167     /** @stable ICU 2.0 */
1168     UBLOCK_HIRAGANA =62, /*[3040]*/
1169
1170     /** @stable ICU 2.0 */
1171     UBLOCK_KATAKANA =63, /*[30A0]*/
1172
1173     /** @stable ICU 2.0 */
1174     UBLOCK_BOPOMOFO =64, /*[3100]*/
1175
1176     /** @stable ICU 2.0 */
1177     UBLOCK_HANGUL_COMPATIBILITY_JAMO =65, /*[3130]*/
1178
1179     /** @stable ICU 2.0 */
1180     UBLOCK_KANBUN =66, /*[3190]*/
1181
1182     /** @stable ICU 2.0 */
1183     UBLOCK_BOPOMOFO_EXTENDED =67, /*[31A0]*/
1184
1185     /** @stable ICU 2.0 */
1186     UBLOCK_ENCLOSED_CJK_LETTERS_AND_MONTHS =68, /*[3200]*/
1187
1188     /** @stable ICU 2.0 */
1189     UBLOCK_CJK_COMPATIBILITY =69, /*[3300]*/
1190
1191     /** @stable ICU 2.0 */
1192     UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_A =70, /*[3400]*/
1193
1194     /** @stable ICU 2.0 */
1195     UBLOCK_CJK_UNIFIED_IDEOGRAPHS =71, /*[4E00]*/
1196
1197     /** @stable ICU 2.0 */
1198     UBLOCK_YI_SYLLABLES =72, /*[A000]*/
1199
1200     /** @stable ICU 2.0 */
1201     UBLOCK_YI_RADICALS =73, /*[A490]*/
1202
1203     /** @stable ICU 2.0 */
1204     UBLOCK_HANGUL_SYLLABLES =74, /*[AC00]*/
1205
1206     /** @stable ICU 2.0 */
1207     UBLOCK_HIGH_SURROGATES =75, /*[D800]*/
1208
1209     /** @stable ICU 2.0 */
1210     UBLOCK_HIGH_PRIVATE_USE_SURROGATES =76, /*[DB80]*/
1211
1212     /** @stable ICU 2.0 */
1213     UBLOCK_LOW_SURROGATES =77, /*[DC00]*/
1214
1215     /**
1216      * Same as UBLOCK_PRIVATE_USE.
1217      * Until Unicode 3.1.1, the corresponding block name was "Private Use",
1218      * and multiple code point ranges had this block.
1219      * Unicode 3.2 renames the block for the BMP PUA to "Private Use Area" and
1220      * adds separate blocks for the supplementary PUAs.
1221      *
1222      * @stable ICU 2.0
1223      */
1224     UBLOCK_PRIVATE_USE_AREA =78, /*[E000]*/
1225     /**
1226      * Same as UBLOCK_PRIVATE_USE_AREA.
1227      * Until Unicode 3.1.1, the corresponding block name was "Private Use",
1228      * and multiple code point ranges had this block.
1229      * Unicode 3.2 renames the block for the BMP PUA to "Private Use Area" and
1230      * adds separate blocks for the supplementary PUAs.
1231      *
1232      * @stable ICU 2.0
1233      */
1234     UBLOCK_PRIVATE_USE = UBLOCK_PRIVATE_USE_AREA,
1235
1236     /** @stable ICU 2.0 */
1237     UBLOCK_CJK_COMPATIBILITY_IDEOGRAPHS =79, /*[F900]*/
1238
1239     /** @stable ICU 2.0 */
1240     UBLOCK_ALPHABETIC_PRESENTATION_FORMS =80, /*[FB00]*/
1241
1242     /** @stable ICU 2.0 */
1243     UBLOCK_ARABIC_PRESENTATION_FORMS_A =81, /*[FB50]*/
1244
1245     /** @stable ICU 2.0 */
1246     UBLOCK_COMBINING_HALF_MARKS =82, /*[FE20]*/
1247
1248     /** @stable ICU 2.0 */
1249     UBLOCK_CJK_COMPATIBILITY_FORMS =83, /*[FE30]*/
1250
1251     /** @stable ICU 2.0 */
1252     UBLOCK_SMALL_FORM_VARIANTS =84, /*[FE50]*/
1253
1254     /** @stable ICU 2.0 */
1255     UBLOCK_ARABIC_PRESENTATION_FORMS_B =85, /*[FE70]*/
1256
1257     /** @stable ICU 2.0 */
1258     UBLOCK_SPECIALS =86, /*[FFF0]*/
1259
1260     /** @stable ICU 2.0 */
1261     UBLOCK_HALFWIDTH_AND_FULLWIDTH_FORMS =87, /*[FF00]*/
1262
1263     /* New blocks in Unicode 3.1 */
1264
1265     /** @stable ICU 2.0 */
1266     UBLOCK_OLD_ITALIC = 88, /*[10300]*/
1267     /** @stable ICU 2.0 */
1268     UBLOCK_GOTHIC = 89, /*[10330]*/
1269     /** @stable ICU 2.0 */
1270     UBLOCK_DESERET = 90, /*[10400]*/
1271     /** @stable ICU 2.0 */
1272     UBLOCK_BYZANTINE_MUSICAL_SYMBOLS = 91, /*[1D000]*/
1273     /** @stable ICU 2.0 */
1274     UBLOCK_MUSICAL_SYMBOLS = 92, /*[1D100]*/
1275     /** @stable ICU 2.0 */
1276     UBLOCK_MATHEMATICAL_ALPHANUMERIC_SYMBOLS = 93, /*[1D400]*/
1277     /** @stable ICU 2.0 */
1278     UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_B  = 94, /*[20000]*/
1279     /** @stable ICU 2.0 */
1280     UBLOCK_CJK_COMPATIBILITY_IDEOGRAPHS_SUPPLEMENT = 95, /*[2F800]*/
1281     /** @stable ICU 2.0 */
1282     UBLOCK_TAGS = 96, /*[E0000]*/
1283
1284     /* New blocks in Unicode 3.2 */
1285
1286     /** @stable ICU 3.0  */
1287     UBLOCK_CYRILLIC_SUPPLEMENT = 97, /*[0500]*/
1288     /**
1289      * Unicode 4.0.1 renames the "Cyrillic Supplementary" block to "Cyrillic Supplement".
1290      * @stable ICU 2.2
1291      */
1292     UBLOCK_CYRILLIC_SUPPLEMENTARY = UBLOCK_CYRILLIC_SUPPLEMENT,
1293     /** @stable ICU 2.2 */
1294     UBLOCK_TAGALOG = 98, /*[1700]*/
1295     /** @stable ICU 2.2 */
1296     UBLOCK_HANUNOO = 99, /*[1720]*/
1297     /** @stable ICU 2.2 */
1298     UBLOCK_BUHID = 100, /*[1740]*/
1299     /** @stable ICU 2.2 */
1300     UBLOCK_TAGBANWA = 101, /*[1760]*/
1301     /** @stable ICU 2.2 */
1302     UBLOCK_MISCELLANEOUS_MATHEMATICAL_SYMBOLS_A = 102, /*[27C0]*/
1303     /** @stable ICU 2.2 */
1304     UBLOCK_SUPPLEMENTAL_ARROWS_A = 103, /*[27F0]*/
1305     /** @stable ICU 2.2 */
1306     UBLOCK_SUPPLEMENTAL_ARROWS_B = 104, /*[2900]*/
1307     /** @stable ICU 2.2 */
1308     UBLOCK_MISCELLANEOUS_MATHEMATICAL_SYMBOLS_B = 105, /*[2980]*/
1309     /** @stable ICU 2.2 */
1310     UBLOCK_SUPPLEMENTAL_MATHEMATICAL_OPERATORS = 106, /*[2A00]*/
1311     /** @stable ICU 2.2 */
1312     UBLOCK_KATAKANA_PHONETIC_EXTENSIONS = 107, /*[31F0]*/
1313     /** @stable ICU 2.2 */
1314     UBLOCK_VARIATION_SELECTORS = 108, /*[FE00]*/
1315     /** @stable ICU 2.2 */
1316     UBLOCK_SUPPLEMENTARY_PRIVATE_USE_AREA_A = 109, /*[F0000]*/
1317     /** @stable ICU 2.2 */
1318     UBLOCK_SUPPLEMENTARY_PRIVATE_USE_AREA_B = 110, /*[100000]*/
1319
1320     /* New blocks in Unicode 4 */
1321
1322     /** @stable ICU 2.6 */
1323     UBLOCK_LIMBU = 111, /*[1900]*/
1324     /** @stable ICU 2.6 */
1325     UBLOCK_TAI_LE = 112, /*[1950]*/
1326     /** @stable ICU 2.6 */
1327     UBLOCK_KHMER_SYMBOLS = 113, /*[19E0]*/
1328     /** @stable ICU 2.6 */
1329     UBLOCK_PHONETIC_EXTENSIONS = 114, /*[1D00]*/
1330     /** @stable ICU 2.6 */
1331     UBLOCK_MISCELLANEOUS_SYMBOLS_AND_ARROWS = 115, /*[2B00]*/
1332     /** @stable ICU 2.6 */
1333     UBLOCK_YIJING_HEXAGRAM_SYMBOLS = 116, /*[4DC0]*/
1334     /** @stable ICU 2.6 */
1335     UBLOCK_LINEAR_B_SYLLABARY = 117, /*[10000]*/
1336     /** @stable ICU 2.6 */
1337     UBLOCK_LINEAR_B_IDEOGRAMS = 118, /*[10080]*/
1338     /** @stable ICU 2.6 */
1339     UBLOCK_AEGEAN_NUMBERS = 119, /*[10100]*/
1340     /** @stable ICU 2.6 */
1341     UBLOCK_UGARITIC = 120, /*[10380]*/
1342     /** @stable ICU 2.6 */
1343     UBLOCK_SHAVIAN = 121, /*[10450]*/
1344     /** @stable ICU 2.6 */
1345     UBLOCK_OSMANYA = 122, /*[10480]*/
1346     /** @stable ICU 2.6 */
1347     UBLOCK_CYPRIOT_SYLLABARY = 123, /*[10800]*/
1348     /** @stable ICU 2.6 */
1349     UBLOCK_TAI_XUAN_JING_SYMBOLS = 124, /*[1D300]*/
1350     /** @stable ICU 2.6 */
1351     UBLOCK_VARIATION_SELECTORS_SUPPLEMENT = 125, /*[E0100]*/
1352
1353     /* New blocks in Unicode 4.1 */
1354
1355     /** @stable ICU 3.4 */
1356     UBLOCK_ANCIENT_GREEK_MUSICAL_NOTATION = 126, /*[1D200]*/
1357     /** @stable ICU 3.4 */
1358     UBLOCK_ANCIENT_GREEK_NUMBERS = 127, /*[10140]*/
1359     /** @stable ICU 3.4 */
1360     UBLOCK_ARABIC_SUPPLEMENT = 128, /*[0750]*/
1361     /** @stable ICU 3.4 */
1362     UBLOCK_BUGINESE = 129, /*[1A00]*/
1363     /** @stable ICU 3.4 */
1364     UBLOCK_CJK_STROKES = 130, /*[31C0]*/
1365     /** @stable ICU 3.4 */
1366     UBLOCK_COMBINING_DIACRITICAL_MARKS_SUPPLEMENT = 131, /*[1DC0]*/
1367     /** @stable ICU 3.4 */
1368     UBLOCK_COPTIC = 132, /*[2C80]*/
1369     /** @stable ICU 3.4 */
1370     UBLOCK_ETHIOPIC_EXTENDED = 133, /*[2D80]*/
1371     /** @stable ICU 3.4 */
1372     UBLOCK_ETHIOPIC_SUPPLEMENT = 134, /*[1380]*/
1373     /** @stable ICU 3.4 */
1374     UBLOCK_GEORGIAN_SUPPLEMENT = 135, /*[2D00]*/
1375     /** @stable ICU 3.4 */
1376     UBLOCK_GLAGOLITIC = 136, /*[2C00]*/
1377     /** @stable ICU 3.4 */
1378     UBLOCK_KHAROSHTHI = 137, /*[10A00]*/
1379     /** @stable ICU 3.4 */
1380     UBLOCK_MODIFIER_TONE_LETTERS = 138, /*[A700]*/
1381     /** @stable ICU 3.4 */
1382     UBLOCK_NEW_TAI_LUE = 139, /*[1980]*/
1383     /** @stable ICU 3.4 */
1384     UBLOCK_OLD_PERSIAN = 140, /*[103A0]*/
1385     /** @stable ICU 3.4 */
1386     UBLOCK_PHONETIC_EXTENSIONS_SUPPLEMENT = 141, /*[1D80]*/
1387     /** @stable ICU 3.4 */
1388     UBLOCK_SUPPLEMENTAL_PUNCTUATION = 142, /*[2E00]*/
1389     /** @stable ICU 3.4 */
1390     UBLOCK_SYLOTI_NAGRI = 143, /*[A800]*/
1391     /** @stable ICU 3.4 */
1392     UBLOCK_TIFINAGH = 144, /*[2D30]*/
1393     /** @stable ICU 3.4 */
1394     UBLOCK_VERTICAL_FORMS = 145, /*[FE10]*/
1395
1396     /* New blocks in Unicode 5.0 */
1397
1398     /** @stable ICU 3.6 */
1399     UBLOCK_NKO = 146, /*[07C0]*/
1400     /** @stable ICU 3.6 */
1401     UBLOCK_BALINESE = 147, /*[1B00]*/
1402     /** @stable ICU 3.6 */
1403     UBLOCK_LATIN_EXTENDED_C = 148, /*[2C60]*/
1404     /** @stable ICU 3.6 */
1405     UBLOCK_LATIN_EXTENDED_D = 149, /*[A720]*/
1406     /** @stable ICU 3.6 */
1407     UBLOCK_PHAGS_PA = 150, /*[A840]*/
1408     /** @stable ICU 3.6 */
1409     UBLOCK_PHOENICIAN = 151, /*[10900]*/
1410     /** @stable ICU 3.6 */
1411     UBLOCK_CUNEIFORM = 152, /*[12000]*/
1412     /** @stable ICU 3.6 */
1413     UBLOCK_CUNEIFORM_NUMBERS_AND_PUNCTUATION = 153, /*[12400]*/
1414     /** @stable ICU 3.6 */
1415     UBLOCK_COUNTING_ROD_NUMERALS = 154, /*[1D360]*/
1416
1417     /* New blocks in Unicode 5.1 */
1418
1419     /** @stable ICU 4.0 */
1420     UBLOCK_SUNDANESE = 155, /*[1B80]*/
1421     /** @stable ICU 4.0 */
1422     UBLOCK_LEPCHA = 156, /*[1C00]*/
1423     /** @stable ICU 4.0 */
1424     UBLOCK_OL_CHIKI = 157, /*[1C50]*/
1425     /** @stable ICU 4.0 */
1426     UBLOCK_CYRILLIC_EXTENDED_A = 158, /*[2DE0]*/
1427     /** @stable ICU 4.0 */
1428     UBLOCK_VAI = 159, /*[A500]*/
1429     /** @stable ICU 4.0 */
1430     UBLOCK_CYRILLIC_EXTENDED_B = 160, /*[A640]*/
1431     /** @stable ICU 4.0 */
1432     UBLOCK_SAURASHTRA = 161, /*[A880]*/
1433     /** @stable ICU 4.0 */
1434     UBLOCK_KAYAH_LI = 162, /*[A900]*/
1435     /** @stable ICU 4.0 */
1436     UBLOCK_REJANG = 163, /*[A930]*/
1437     /** @stable ICU 4.0 */
1438     UBLOCK_CHAM = 164, /*[AA00]*/
1439     /** @stable ICU 4.0 */
1440     UBLOCK_ANCIENT_SYMBOLS = 165, /*[10190]*/
1441     /** @stable ICU 4.0 */
1442     UBLOCK_PHAISTOS_DISC = 166, /*[101D0]*/
1443     /** @stable ICU 4.0 */
1444     UBLOCK_LYCIAN = 167, /*[10280]*/
1445     /** @stable ICU 4.0 */
1446     UBLOCK_CARIAN = 168, /*[102A0]*/
1447     /** @stable ICU 4.0 */
1448     UBLOCK_LYDIAN = 169, /*[10920]*/
1449     /** @stable ICU 4.0 */
1450     UBLOCK_MAHJONG_TILES = 170, /*[1F000]*/
1451     /** @stable ICU 4.0 */
1452     UBLOCK_DOMINO_TILES = 171, /*[1F030]*/
1453
1454     /* New blocks in Unicode 5.2 */
1455
1456     /** @stable ICU 4.4 */
1457     UBLOCK_SAMARITAN = 172, /*[0800]*/
1458     /** @stable ICU 4.4 */
1459     UBLOCK_UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS_EXTENDED = 173, /*[18B0]*/
1460     /** @stable ICU 4.4 */
1461     UBLOCK_TAI_THAM = 174, /*[1A20]*/
1462     /** @stable ICU 4.4 */
1463     UBLOCK_VEDIC_EXTENSIONS = 175, /*[1CD0]*/
1464     /** @stable ICU 4.4 */
1465     UBLOCK_LISU = 176, /*[A4D0]*/
1466     /** @stable ICU 4.4 */
1467     UBLOCK_BAMUM = 177, /*[A6A0]*/
1468     /** @stable ICU 4.4 */
1469     UBLOCK_COMMON_INDIC_NUMBER_FORMS = 178, /*[A830]*/
1470     /** @stable ICU 4.4 */
1471     UBLOCK_DEVANAGARI_EXTENDED = 179, /*[A8E0]*/
1472     /** @stable ICU 4.4 */
1473     UBLOCK_HANGUL_JAMO_EXTENDED_A = 180, /*[A960]*/
1474     /** @stable ICU 4.4 */
1475     UBLOCK_JAVANESE = 181, /*[A980]*/
1476     /** @stable ICU 4.4 */
1477     UBLOCK_MYANMAR_EXTENDED_A = 182, /*[AA60]*/
1478     /** @stable ICU 4.4 */
1479     UBLOCK_TAI_VIET = 183, /*[AA80]*/
1480     /** @stable ICU 4.4 */
1481     UBLOCK_MEETEI_MAYEK = 184, /*[ABC0]*/
1482     /** @stable ICU 4.4 */
1483     UBLOCK_HANGUL_JAMO_EXTENDED_B = 185, /*[D7B0]*/
1484     /** @stable ICU 4.4 */
1485     UBLOCK_IMPERIAL_ARAMAIC = 186, /*[10840]*/
1486     /** @stable ICU 4.4 */
1487     UBLOCK_OLD_SOUTH_ARABIAN = 187, /*[10A60]*/
1488     /** @stable ICU 4.4 */
1489     UBLOCK_AVESTAN = 188, /*[10B00]*/
1490     /** @stable ICU 4.4 */
1491     UBLOCK_INSCRIPTIONAL_PARTHIAN = 189, /*[10B40]*/
1492     /** @stable ICU 4.4 */
1493     UBLOCK_INSCRIPTIONAL_PAHLAVI = 190, /*[10B60]*/
1494     /** @stable ICU 4.4 */
1495     UBLOCK_OLD_TURKIC = 191, /*[10C00]*/
1496     /** @stable ICU 4.4 */
1497     UBLOCK_RUMI_NUMERAL_SYMBOLS = 192, /*[10E60]*/
1498     /** @stable ICU 4.4 */
1499     UBLOCK_KAITHI = 193, /*[11080]*/
1500     /** @stable ICU 4.4 */
1501     UBLOCK_EGYPTIAN_HIEROGLYPHS = 194, /*[13000]*/
1502     /** @stable ICU 4.4 */
1503     UBLOCK_ENCLOSED_ALPHANUMERIC_SUPPLEMENT = 195, /*[1F100]*/
1504     /** @stable ICU 4.4 */
1505     UBLOCK_ENCLOSED_IDEOGRAPHIC_SUPPLEMENT = 196, /*[1F200]*/
1506     /** @stable ICU 4.4 */
1507     UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_C = 197, /*[2A700]*/
1508
1509     /* New blocks in Unicode 6.0 */
1510
1511     /** @stable ICU 4.6 */
1512     UBLOCK_MANDAIC = 198, /*[0840]*/
1513     /** @stable ICU 4.6 */
1514     UBLOCK_BATAK = 199, /*[1BC0]*/
1515     /** @stable ICU 4.6 */
1516     UBLOCK_ETHIOPIC_EXTENDED_A = 200, /*[AB00]*/
1517     /** @stable ICU 4.6 */
1518     UBLOCK_BRAHMI = 201, /*[11000]*/
1519     /** @stable ICU 4.6 */
1520     UBLOCK_BAMUM_SUPPLEMENT = 202, /*[16800]*/
1521     /** @stable ICU 4.6 */
1522     UBLOCK_KANA_SUPPLEMENT = 203, /*[1B000]*/
1523     /** @stable ICU 4.6 */
1524     UBLOCK_PLAYING_CARDS = 204, /*[1F0A0]*/
1525     /** @stable ICU 4.6 */
1526     UBLOCK_MISCELLANEOUS_SYMBOLS_AND_PICTOGRAPHS = 205, /*[1F300]*/
1527     /** @stable ICU 4.6 */
1528     UBLOCK_EMOTICONS = 206, /*[1F600]*/
1529     /** @stable ICU 4.6 */
1530     UBLOCK_TRANSPORT_AND_MAP_SYMBOLS = 207, /*[1F680]*/
1531     /** @stable ICU 4.6 */
1532     UBLOCK_ALCHEMICAL_SYMBOLS = 208, /*[1F700]*/
1533     /** @stable ICU 4.6 */
1534     UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_D = 209, /*[2B740]*/
1535
1536     /* New blocks in Unicode 6.1 */
1537
1538     /** @stable ICU 49 */
1539     UBLOCK_ARABIC_EXTENDED_A = 210, /*[08A0]*/
1540     /** @stable ICU 49 */
1541     UBLOCK_ARABIC_MATHEMATICAL_ALPHABETIC_SYMBOLS = 211, /*[1EE00]*/
1542     /** @stable ICU 49 */
1543     UBLOCK_CHAKMA = 212, /*[11100]*/
1544     /** @stable ICU 49 */
1545     UBLOCK_MEETEI_MAYEK_EXTENSIONS = 213, /*[AAE0]*/
1546     /** @stable ICU 49 */
1547     UBLOCK_MEROITIC_CURSIVE = 214, /*[109A0]*/
1548     /** @stable ICU 49 */
1549     UBLOCK_MEROITIC_HIEROGLYPHS = 215, /*[10980]*/
1550     /** @stable ICU 49 */
1551     UBLOCK_MIAO = 216, /*[16F00]*/
1552     /** @stable ICU 49 */
1553     UBLOCK_SHARADA = 217, /*[11180]*/
1554     /** @stable ICU 49 */
1555     UBLOCK_SORA_SOMPENG = 218, /*[110D0]*/
1556     /** @stable ICU 49 */
1557     UBLOCK_SUNDANESE_SUPPLEMENT = 219, /*[1CC0]*/
1558     /** @stable ICU 49 */
1559     UBLOCK_TAKRI = 220, /*[11680]*/
1560
1561     /* New blocks in Unicode 7.0 */
1562
1563     /** @stable ICU 54 */
1564     UBLOCK_BASSA_VAH = 221, /*[16AD0]*/
1565     /** @stable ICU 54 */
1566     UBLOCK_CAUCASIAN_ALBANIAN = 222, /*[10530]*/
1567     /** @stable ICU 54 */
1568     UBLOCK_COPTIC_EPACT_NUMBERS = 223, /*[102E0]*/
1569     /** @stable ICU 54 */
1570     UBLOCK_COMBINING_DIACRITICAL_MARKS_EXTENDED = 224, /*[1AB0]*/
1571     /** @stable ICU 54 */
1572     UBLOCK_DUPLOYAN = 225, /*[1BC00]*/
1573     /** @stable ICU 54 */
1574     UBLOCK_ELBASAN = 226, /*[10500]*/
1575     /** @stable ICU 54 */
1576     UBLOCK_GEOMETRIC_SHAPES_EXTENDED = 227, /*[1F780]*/
1577     /** @stable ICU 54 */
1578     UBLOCK_GRANTHA = 228, /*[11300]*/
1579     /** @stable ICU 54 */
1580     UBLOCK_KHOJKI = 229, /*[11200]*/
1581     /** @stable ICU 54 */
1582     UBLOCK_KHUDAWADI = 230, /*[112B0]*/
1583     /** @stable ICU 54 */
1584     UBLOCK_LATIN_EXTENDED_E = 231, /*[AB30]*/
1585     /** @stable ICU 54 */
1586     UBLOCK_LINEAR_A = 232, /*[10600]*/
1587     /** @stable ICU 54 */
1588     UBLOCK_MAHAJANI = 233, /*[11150]*/
1589     /** @stable ICU 54 */
1590     UBLOCK_MANICHAEAN = 234, /*[10AC0]*/
1591     /** @stable ICU 54 */
1592     UBLOCK_MENDE_KIKAKUI = 235, /*[1E800]*/
1593     /** @stable ICU 54 */
1594     UBLOCK_MODI = 236, /*[11600]*/
1595     /** @stable ICU 54 */
1596     UBLOCK_MRO = 237, /*[16A40]*/
1597     /** @stable ICU 54 */
1598     UBLOCK_MYANMAR_EXTENDED_B = 238, /*[A9E0]*/
1599     /** @stable ICU 54 */
1600     UBLOCK_NABATAEAN = 239, /*[10880]*/
1601     /** @stable ICU 54 */
1602     UBLOCK_OLD_NORTH_ARABIAN = 240, /*[10A80]*/
1603     /** @stable ICU 54 */
1604     UBLOCK_OLD_PERMIC = 241, /*[10350]*/
1605     /** @stable ICU 54 */
1606     UBLOCK_ORNAMENTAL_DINGBATS = 242, /*[1F650]*/
1607     /** @stable ICU 54 */
1608     UBLOCK_PAHAWH_HMONG = 243, /*[16B00]*/
1609     /** @stable ICU 54 */
1610     UBLOCK_PALMYRENE = 244, /*[10860]*/
1611     /** @stable ICU 54 */
1612     UBLOCK_PAU_CIN_HAU = 245, /*[11AC0]*/
1613     /** @stable ICU 54 */
1614     UBLOCK_PSALTER_PAHLAVI = 246, /*[10B80]*/
1615     /** @stable ICU 54 */
1616     UBLOCK_SHORTHAND_FORMAT_CONTROLS = 247, /*[1BCA0]*/
1617     /** @stable ICU 54 */
1618     UBLOCK_SIDDHAM = 248, /*[11580]*/
1619     /** @stable ICU 54 */
1620     UBLOCK_SINHALA_ARCHAIC_NUMBERS = 249, /*[111E0]*/
1621     /** @stable ICU 54 */
1622     UBLOCK_SUPPLEMENTAL_ARROWS_C = 250, /*[1F800]*/
1623     /** @stable ICU 54 */
1624     UBLOCK_TIRHUTA = 251, /*[11480]*/
1625     /** @stable ICU 54 */
1626     UBLOCK_WARANG_CITI = 252, /*[118A0]*/
1627
1628     /* New blocks in Unicode 8.0 */
1629
1630     /** @stable ICU 56 */
1631     UBLOCK_AHOM = 253, /*[11700]*/
1632     /** @stable ICU 56 */
1633     UBLOCK_ANATOLIAN_HIEROGLYPHS = 254, /*[14400]*/
1634     /** @stable ICU 56 */
1635     UBLOCK_CHEROKEE_SUPPLEMENT = 255, /*[AB70]*/
1636     /** @stable ICU 56 */
1637     UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_E = 256, /*[2B820]*/
1638     /** @stable ICU 56 */
1639     UBLOCK_EARLY_DYNASTIC_CUNEIFORM = 257, /*[12480]*/
1640     /** @stable ICU 56 */
1641     UBLOCK_HATRAN = 258, /*[108E0]*/
1642     /** @stable ICU 56 */
1643     UBLOCK_MULTANI = 259, /*[11280]*/
1644     /** @stable ICU 56 */
1645     UBLOCK_OLD_HUNGARIAN = 260, /*[10C80]*/
1646     /** @stable ICU 56 */
1647     UBLOCK_SUPPLEMENTAL_SYMBOLS_AND_PICTOGRAPHS = 261, /*[1F900]*/
1648     /** @stable ICU 56 */
1649     UBLOCK_SUTTON_SIGNWRITING = 262, /*[1D800]*/
1650
1651     /* New blocks in Unicode 9.0 */
1652
1653     /** @stable ICU 58 */
1654     UBLOCK_ADLAM = 263, /*[1E900]*/
1655     /** @stable ICU 58 */
1656     UBLOCK_BHAIKSUKI = 264, /*[11C00]*/
1657     /** @stable ICU 58 */
1658     UBLOCK_CYRILLIC_EXTENDED_C = 265, /*[1C80]*/
1659     /** @stable ICU 58 */
1660     UBLOCK_GLAGOLITIC_SUPPLEMENT = 266, /*[1E000]*/
1661     /** @stable ICU 58 */
1662     UBLOCK_IDEOGRAPHIC_SYMBOLS_AND_PUNCTUATION = 267, /*[16FE0]*/
1663     /** @stable ICU 58 */
1664     UBLOCK_MARCHEN = 268, /*[11C70]*/
1665     /** @stable ICU 58 */
1666     UBLOCK_MONGOLIAN_SUPPLEMENT = 269, /*[11660]*/
1667     /** @stable ICU 58 */
1668     UBLOCK_NEWA = 270, /*[11400]*/
1669     /** @stable ICU 58 */
1670     UBLOCK_OSAGE = 271, /*[104B0]*/
1671     /** @stable ICU 58 */
1672     UBLOCK_TANGUT = 272, /*[17000]*/
1673     /** @stable ICU 58 */
1674     UBLOCK_TANGUT_COMPONENTS = 273, /*[18800]*/
1675
1676     // New blocks in Unicode 10.0
1677
1678     /** @stable ICU 60 */
1679     UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_F = 274, /*[2CEB0]*/
1680     /** @stable ICU 60 */
1681     UBLOCK_KANA_EXTENDED_A = 275, /*[1B100]*/
1682     /** @stable ICU 60 */
1683     UBLOCK_MASARAM_GONDI = 276, /*[11D00]*/
1684     /** @stable ICU 60 */
1685     UBLOCK_NUSHU = 277, /*[1B170]*/
1686     /** @stable ICU 60 */
1687     UBLOCK_SOYOMBO = 278, /*[11A50]*/
1688     /** @stable ICU 60 */
1689     UBLOCK_SYRIAC_SUPPLEMENT = 279, /*[0860]*/
1690     /** @stable ICU 60 */
1691     UBLOCK_ZANABAZAR_SQUARE = 280, /*[11A00]*/
1692
1693     // New blocks in Unicode 11.0
1694
1695     /** @stable ICU 62 */
1696     UBLOCK_CHESS_SYMBOLS = 281, /*[1FA00]*/
1697     /** @stable ICU 62 */
1698     UBLOCK_DOGRA = 282, /*[11800]*/
1699     /** @stable ICU 62 */
1700     UBLOCK_GEORGIAN_EXTENDED = 283, /*[1C90]*/
1701     /** @stable ICU 62 */
1702     UBLOCK_GUNJALA_GONDI = 284, /*[11D60]*/
1703     /** @stable ICU 62 */
1704     UBLOCK_HANIFI_ROHINGYA = 285, /*[10D00]*/
1705     /** @stable ICU 62 */
1706     UBLOCK_INDIC_SIYAQ_NUMBERS = 286, /*[1EC70]*/
1707     /** @stable ICU 62 */
1708     UBLOCK_MAKASAR = 287, /*[11EE0]*/
1709     /** @stable ICU 62 */
1710     UBLOCK_MAYAN_NUMERALS = 288, /*[1D2E0]*/
1711     /** @stable ICU 62 */
1712     UBLOCK_MEDEFAIDRIN = 289, /*[16E40]*/
1713     /** @stable ICU 62 */
1714     UBLOCK_OLD_SOGDIAN = 290, /*[10F00]*/
1715     /** @stable ICU 62 */
1716     UBLOCK_SOGDIAN = 291, /*[10F30]*/
1717
1718 #ifndef U_HIDE_DEPRECATED_API
1719     /**
1720      * One more than the highest normal UBlockCode value.
1721      * The highest value is available via u_getIntPropertyMaxValue(UCHAR_BLOCK).
1722      *
1723      * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420.
1724      */
1725     UBLOCK_COUNT = 292,
1726 #endif  // U_HIDE_DEPRECATED_API
1727
1728     /** @stable ICU 2.0 */
1729     UBLOCK_INVALID_CODE=-1
1730 };
1731
1732 /** @stable ICU 2.0 */
1733 typedef enum UBlockCode UBlockCode;
1734
1735 /**
1736  * East Asian Width constants.
1737  *
1738  * @see UCHAR_EAST_ASIAN_WIDTH
1739  * @see u_getIntPropertyValue
1740  * @stable ICU 2.2
1741  */
1742 typedef enum UEastAsianWidth {
1743     /*
1744      * Note: UEastAsianWidth constants are parsed by preparseucd.py.
1745      * It matches lines like
1746      *     U_EA_<Unicode East_Asian_Width value name>
1747      */
1748
1749     U_EA_NEUTRAL,   /*[N]*/
1750     U_EA_AMBIGUOUS, /*[A]*/
1751     U_EA_HALFWIDTH, /*[H]*/
1752     U_EA_FULLWIDTH, /*[F]*/
1753     U_EA_NARROW,    /*[Na]*/
1754     U_EA_WIDE,      /*[W]*/
1755 #ifndef U_HIDE_DEPRECATED_API
1756     /**
1757      * One more than the highest normal UEastAsianWidth value.
1758      * The highest value is available via u_getIntPropertyMaxValue(UCHAR_EAST_ASIAN_WIDTH).
1759      *
1760      * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420.
1761      */
1762     U_EA_COUNT
1763 #endif  // U_HIDE_DEPRECATED_API
1764 } UEastAsianWidth;
1765
1766 /**
1767  * Selector constants for u_charName().
1768  * u_charName() returns the "modern" name of a
1769  * Unicode character; or the name that was defined in
1770  * Unicode version 1.0, before the Unicode standard merged
1771  * with ISO-10646; or an "extended" name that gives each
1772  * Unicode code point a unique name.
1773  *
1774  * @see u_charName
1775  * @stable ICU 2.0
1776  */
1777 typedef enum UCharNameChoice {
1778     /** Unicode character name (Name property). @stable ICU 2.0 */
1779     U_UNICODE_CHAR_NAME,
1780 #ifndef U_HIDE_DEPRECATED_API
1781     /**
1782      * The Unicode_1_Name property value which is of little practical value.
1783      * Beginning with ICU 49, ICU APIs return an empty string for this name choice.
1784      * @deprecated ICU 49
1785      */
1786     U_UNICODE_10_CHAR_NAME,
1787 #endif  /* U_HIDE_DEPRECATED_API */
1788     /** Standard or synthetic character name. @stable ICU 2.0 */
1789     U_EXTENDED_CHAR_NAME = U_UNICODE_CHAR_NAME+2,
1790     /** Corrected name from NameAliases.txt. @stable ICU 4.4 */
1791     U_CHAR_NAME_ALIAS,
1792 #ifndef U_HIDE_DEPRECATED_API
1793     /**
1794      * One more than the highest normal UCharNameChoice value.
1795      * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420.
1796      */
1797     U_CHAR_NAME_CHOICE_COUNT
1798 #endif  // U_HIDE_DEPRECATED_API
1799 } UCharNameChoice;
1800
1801 /**
1802  * Selector constants for u_getPropertyName() and
1803  * u_getPropertyValueName().  These selectors are used to choose which
1804  * name is returned for a given property or value.  All properties and
1805  * values have a long name.  Most have a short name, but some do not.
1806  * Unicode allows for additional names, beyond the long and short
1807  * name, which would be indicated by U_LONG_PROPERTY_NAME + i, where
1808  * i=1, 2,...
1809  *
1810  * @see u_getPropertyName()
1811  * @see u_getPropertyValueName()
1812  * @stable ICU 2.4
1813  */
1814 typedef enum UPropertyNameChoice {
1815     U_SHORT_PROPERTY_NAME,
1816     U_LONG_PROPERTY_NAME,
1817 #ifndef U_HIDE_DEPRECATED_API
1818     /**
1819      * One more than the highest normal UPropertyNameChoice value.
1820      * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420.
1821      */
1822     U_PROPERTY_NAME_CHOICE_COUNT
1823 #endif  // U_HIDE_DEPRECATED_API
1824 } UPropertyNameChoice;
1825
1826 /**
1827  * Decomposition Type constants.
1828  *
1829  * @see UCHAR_DECOMPOSITION_TYPE
1830  * @stable ICU 2.2
1831  */
1832 typedef enum UDecompositionType {
1833     /*
1834      * Note: UDecompositionType constants are parsed by preparseucd.py.
1835      * It matches lines like
1836      *     U_DT_<Unicode Decomposition_Type value name>
1837      */
1838
1839     U_DT_NONE,              /*[none]*/
1840     U_DT_CANONICAL,         /*[can]*/
1841     U_DT_COMPAT,            /*[com]*/
1842     U_DT_CIRCLE,            /*[enc]*/
1843     U_DT_FINAL,             /*[fin]*/
1844     U_DT_FONT,              /*[font]*/
1845     U_DT_FRACTION,          /*[fra]*/
1846     U_DT_INITIAL,           /*[init]*/
1847     U_DT_ISOLATED,          /*[iso]*/
1848     U_DT_MEDIAL,            /*[med]*/
1849     U_DT_NARROW,            /*[nar]*/
1850     U_DT_NOBREAK,           /*[nb]*/
1851     U_DT_SMALL,             /*[sml]*/
1852     U_DT_SQUARE,            /*[sqr]*/
1853     U_DT_SUB,               /*[sub]*/
1854     U_DT_SUPER,             /*[sup]*/
1855     U_DT_VERTICAL,          /*[vert]*/
1856     U_DT_WIDE,              /*[wide]*/
1857 #ifndef U_HIDE_DEPRECATED_API
1858     /**
1859      * One more than the highest normal UDecompositionType value.
1860      * The highest value is available via u_getIntPropertyMaxValue(UCHAR_DECOMPOSITION_TYPE).
1861      *
1862      * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420.
1863      */
1864     U_DT_COUNT /* 18 */
1865 #endif  // U_HIDE_DEPRECATED_API
1866 } UDecompositionType;
1867
1868 /**
1869  * Joining Type constants.
1870  *
1871  * @see UCHAR_JOINING_TYPE
1872  * @stable ICU 2.2
1873  */
1874 typedef enum UJoiningType {
1875     /*
1876      * Note: UJoiningType constants are parsed by preparseucd.py.
1877      * It matches lines like
1878      *     U_JT_<Unicode Joining_Type value name>
1879      */
1880
1881     U_JT_NON_JOINING,       /*[U]*/
1882     U_JT_JOIN_CAUSING,      /*[C]*/
1883     U_JT_DUAL_JOINING,      /*[D]*/
1884     U_JT_LEFT_JOINING,      /*[L]*/
1885     U_JT_RIGHT_JOINING,     /*[R]*/
1886     U_JT_TRANSPARENT,       /*[T]*/
1887 #ifndef U_HIDE_DEPRECATED_API
1888     /**
1889      * One more than the highest normal UJoiningType value.
1890      * The highest value is available via u_getIntPropertyMaxValue(UCHAR_JOINING_TYPE).
1891      *
1892      * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420.
1893      */
1894     U_JT_COUNT /* 6 */
1895 #endif  // U_HIDE_DEPRECATED_API
1896 } UJoiningType;
1897
1898 /**
1899  * Joining Group constants.
1900  *
1901  * @see UCHAR_JOINING_GROUP
1902  * @stable ICU 2.2
1903  */
1904 typedef enum UJoiningGroup {
1905     /*
1906      * Note: UJoiningGroup constants are parsed by preparseucd.py.
1907      * It matches lines like
1908      *     U_JG_<Unicode Joining_Group value name>
1909      */
1910
1911     U_JG_NO_JOINING_GROUP,
1912     U_JG_AIN,
1913     U_JG_ALAPH,
1914     U_JG_ALEF,
1915     U_JG_BEH,
1916     U_JG_BETH,
1917     U_JG_DAL,
1918     U_JG_DALATH_RISH,
1919     U_JG_E,
1920     U_JG_FEH,
1921     U_JG_FINAL_SEMKATH,
1922     U_JG_GAF,
1923     U_JG_GAMAL,
1924     U_JG_HAH,
1925     U_JG_TEH_MARBUTA_GOAL,  /**< @stable ICU 4.6 */
1926     U_JG_HAMZA_ON_HEH_GOAL=U_JG_TEH_MARBUTA_GOAL,
1927     U_JG_HE,
1928     U_JG_HEH,
1929     U_JG_HEH_GOAL,
1930     U_JG_HETH,
1931     U_JG_KAF,
1932     U_JG_KAPH,
1933     U_JG_KNOTTED_HEH,
1934     U_JG_LAM,
1935     U_JG_LAMADH,
1936     U_JG_MEEM,
1937     U_JG_MIM,
1938     U_JG_NOON,
1939     U_JG_NUN,
1940     U_JG_PE,
1941     U_JG_QAF,
1942     U_JG_QAPH,
1943     U_JG_REH,
1944     U_JG_REVERSED_PE,
1945     U_JG_SAD,
1946     U_JG_SADHE,
1947     U_JG_SEEN,
1948     U_JG_SEMKATH,
1949     U_JG_SHIN,
1950     U_JG_SWASH_KAF,
1951     U_JG_SYRIAC_WAW,
1952     U_JG_TAH,
1953     U_JG_TAW,
1954     U_JG_TEH_MARBUTA,
1955     U_JG_TETH,
1956     U_JG_WAW,
1957     U_JG_YEH,
1958     U_JG_YEH_BARREE,
1959     U_JG_YEH_WITH_TAIL,
1960     U_JG_YUDH,
1961     U_JG_YUDH_HE,
1962     U_JG_ZAIN,
1963     U_JG_FE,        /**< @stable ICU 2.6 */
1964     U_JG_KHAPH,     /**< @stable ICU 2.6 */
1965     U_JG_ZHAIN,     /**< @stable ICU 2.6 */
1966     U_JG_BURUSHASKI_YEH_BARREE, /**< @stable ICU 4.0 */
1967     U_JG_FARSI_YEH, /**< @stable ICU 4.4 */
1968     U_JG_NYA,       /**< @stable ICU 4.4 */
1969     U_JG_ROHINGYA_YEH,  /**< @stable ICU 49 */
1970     U_JG_MANICHAEAN_ALEPH,  /**< @stable ICU 54 */
1971     U_JG_MANICHAEAN_AYIN,  /**< @stable ICU 54 */
1972     U_JG_MANICHAEAN_BETH,  /**< @stable ICU 54 */
1973     U_JG_MANICHAEAN_DALETH,  /**< @stable ICU 54 */
1974     U_JG_MANICHAEAN_DHAMEDH,  /**< @stable ICU 54 */
1975     U_JG_MANICHAEAN_FIVE,  /**< @stable ICU 54 */
1976     U_JG_MANICHAEAN_GIMEL,  /**< @stable ICU 54 */
1977     U_JG_MANICHAEAN_HETH,  /**< @stable ICU 54 */
1978     U_JG_MANICHAEAN_HUNDRED,  /**< @stable ICU 54 */
1979     U_JG_MANICHAEAN_KAPH,  /**< @stable ICU 54 */
1980     U_JG_MANICHAEAN_LAMEDH,  /**< @stable ICU 54 */
1981     U_JG_MANICHAEAN_MEM,  /**< @stable ICU 54 */
1982     U_JG_MANICHAEAN_NUN,  /**< @stable ICU 54 */
1983     U_JG_MANICHAEAN_ONE,  /**< @stable ICU 54 */
1984     U_JG_MANICHAEAN_PE,  /**< @stable ICU 54 */
1985     U_JG_MANICHAEAN_QOPH,  /**< @stable ICU 54 */
1986     U_JG_MANICHAEAN_RESH,  /**< @stable ICU 54 */
1987     U_JG_MANICHAEAN_SADHE,  /**< @stable ICU 54 */
1988     U_JG_MANICHAEAN_SAMEKH,  /**< @stable ICU 54 */
1989     U_JG_MANICHAEAN_TAW,  /**< @stable ICU 54 */
1990     U_JG_MANICHAEAN_TEN,  /**< @stable ICU 54 */
1991     U_JG_MANICHAEAN_TETH,  /**< @stable ICU 54 */
1992     U_JG_MANICHAEAN_THAMEDH,  /**< @stable ICU 54 */
1993     U_JG_MANICHAEAN_TWENTY,  /**< @stable ICU 54 */
1994     U_JG_MANICHAEAN_WAW,  /**< @stable ICU 54 */
1995     U_JG_MANICHAEAN_YODH,  /**< @stable ICU 54 */
1996     U_JG_MANICHAEAN_ZAYIN,  /**< @stable ICU 54 */
1997     U_JG_STRAIGHT_WAW,  /**< @stable ICU 54 */
1998     U_JG_AFRICAN_FEH,  /**< @stable ICU 58 */
1999     U_JG_AFRICAN_NOON,  /**< @stable ICU 58 */
2000     U_JG_AFRICAN_QAF,  /**< @stable ICU 58 */
2001
2002     U_JG_MALAYALAM_BHA,  /**< @stable ICU 60 */
2003     U_JG_MALAYALAM_JA,  /**< @stable ICU 60 */
2004     U_JG_MALAYALAM_LLA,  /**< @stable ICU 60 */
2005     U_JG_MALAYALAM_LLLA,  /**< @stable ICU 60 */
2006     U_JG_MALAYALAM_NGA,  /**< @stable ICU 60 */
2007     U_JG_MALAYALAM_NNA,  /**< @stable ICU 60 */
2008     U_JG_MALAYALAM_NNNA,  /**< @stable ICU 60 */
2009     U_JG_MALAYALAM_NYA,  /**< @stable ICU 60 */
2010     U_JG_MALAYALAM_RA,  /**< @stable ICU 60 */
2011     U_JG_MALAYALAM_SSA,  /**< @stable ICU 60 */
2012     U_JG_MALAYALAM_TTA,  /**< @stable ICU 60 */
2013
2014     U_JG_HANIFI_ROHINGYA_KINNA_YA,  /**< @stable ICU 62 */
2015     U_JG_HANIFI_ROHINGYA_PA,  /**< @stable ICU 62 */
2016
2017 #ifndef U_HIDE_DEPRECATED_API
2018     /**
2019      * One more than the highest normal UJoiningGroup value.
2020      * The highest value is available via u_getIntPropertyMaxValue(UCHAR_JOINING_GROUP).
2021      *
2022      * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420.
2023      */
2024     U_JG_COUNT
2025 #endif  // U_HIDE_DEPRECATED_API
2026 } UJoiningGroup;
2027
2028 /**
2029  * Grapheme Cluster Break constants.
2030  *
2031  * @see UCHAR_GRAPHEME_CLUSTER_BREAK
2032  * @stable ICU 3.4
2033  */
2034 typedef enum UGraphemeClusterBreak {
2035     /*
2036      * Note: UGraphemeClusterBreak constants are parsed by preparseucd.py.
2037      * It matches lines like
2038      *     U_GCB_<Unicode Grapheme_Cluster_Break value name>
2039      */
2040
2041     U_GCB_OTHER = 0,            /*[XX]*/
2042     U_GCB_CONTROL = 1,          /*[CN]*/
2043     U_GCB_CR = 2,               /*[CR]*/
2044     U_GCB_EXTEND = 3,           /*[EX]*/
2045     U_GCB_L = 4,                /*[L]*/
2046     U_GCB_LF = 5,               /*[LF]*/
2047     U_GCB_LV = 6,               /*[LV]*/
2048     U_GCB_LVT = 7,              /*[LVT]*/
2049     U_GCB_T = 8,                /*[T]*/
2050     U_GCB_V = 9,                /*[V]*/
2051     /** @stable ICU 4.0 */
2052     U_GCB_SPACING_MARK = 10,    /*[SM]*/ /* from here on: new in Unicode 5.1/ICU 4.0 */
2053     /** @stable ICU 4.0 */
2054     U_GCB_PREPEND = 11,         /*[PP]*/
2055     /** @stable ICU 50 */
2056     U_GCB_REGIONAL_INDICATOR = 12,  /*[RI]*/ /* new in Unicode 6.2/ICU 50 */
2057     /** @stable ICU 58 */
2058     U_GCB_E_BASE = 13,          /*[EB]*/ /* from here on: new in Unicode 9.0/ICU 58 */
2059     /** @stable ICU 58 */
2060     U_GCB_E_BASE_GAZ = 14,      /*[EBG]*/
2061     /** @stable ICU 58 */
2062     U_GCB_E_MODIFIER = 15,      /*[EM]*/
2063     /** @stable ICU 58 */
2064     U_GCB_GLUE_AFTER_ZWJ = 16,  /*[GAZ]*/
2065     /** @stable ICU 58 */
2066     U_GCB_ZWJ = 17,             /*[ZWJ]*/
2067
2068 #ifndef U_HIDE_DEPRECATED_API
2069     /**
2070      * One more than the highest normal UGraphemeClusterBreak value.
2071      * The highest value is available via u_getIntPropertyMaxValue(UCHAR_GRAPHEME_CLUSTER_BREAK).
2072      *
2073      * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420.
2074      */
2075     U_GCB_COUNT = 18
2076 #endif  // U_HIDE_DEPRECATED_API
2077 } UGraphemeClusterBreak;
2078
2079 /**
2080  * Word Break constants.
2081  * (UWordBreak is a pre-existing enum type in ubrk.h for word break status tags.)
2082  *
2083  * @see UCHAR_WORD_BREAK
2084  * @stable ICU 3.4
2085  */
2086 typedef enum UWordBreakValues {
2087     /*
2088      * Note: UWordBreakValues constants are parsed by preparseucd.py.
2089      * It matches lines like
2090      *     U_WB_<Unicode Word_Break value name>
2091      */
2092
2093     U_WB_OTHER = 0,             /*[XX]*/
2094     U_WB_ALETTER = 1,           /*[LE]*/
2095     U_WB_FORMAT = 2,            /*[FO]*/
2096     U_WB_KATAKANA = 3,          /*[KA]*/
2097     U_WB_MIDLETTER = 4,         /*[ML]*/
2098     U_WB_MIDNUM = 5,            /*[MN]*/
2099     U_WB_NUMERIC = 6,           /*[NU]*/
2100     U_WB_EXTENDNUMLET = 7,      /*[EX]*/
2101     /** @stable ICU 4.0 */
2102     U_WB_CR = 8,                /*[CR]*/ /* from here on: new in Unicode 5.1/ICU 4.0 */
2103     /** @stable ICU 4.0 */
2104     U_WB_EXTEND = 9,            /*[Extend]*/
2105     /** @stable ICU 4.0 */
2106     U_WB_LF = 10,               /*[LF]*/
2107     /** @stable ICU 4.0 */
2108     U_WB_MIDNUMLET =11,         /*[MB]*/
2109     /** @stable ICU 4.0 */
2110     U_WB_NEWLINE =12,           /*[NL]*/
2111     /** @stable ICU 50 */
2112     U_WB_REGIONAL_INDICATOR = 13,   /*[RI]*/ /* new in Unicode 6.2/ICU 50 */
2113     /** @stable ICU 52 */
2114     U_WB_HEBREW_LETTER = 14,    /*[HL]*/ /* from here on: new in Unicode 6.3/ICU 52 */
2115     /** @stable ICU 52 */
2116     U_WB_SINGLE_QUOTE = 15,     /*[SQ]*/
2117     /** @stable ICU 52 */
2118     U_WB_DOUBLE_QUOTE = 16,     /*[DQ]*/
2119     /** @stable ICU 58 */
2120     U_WB_E_BASE = 17,           /*[EB]*/ /* from here on: new in Unicode 9.0/ICU 58 */
2121     /** @stable ICU 58 */
2122     U_WB_E_BASE_GAZ = 18,       /*[EBG]*/
2123     /** @stable ICU 58 */
2124     U_WB_E_MODIFIER = 19,       /*[EM]*/
2125     /** @stable ICU 58 */
2126     U_WB_GLUE_AFTER_ZWJ = 20,   /*[GAZ]*/
2127     /** @stable ICU 58 */
2128     U_WB_ZWJ = 21,              /*[ZWJ]*/
2129     /** @stable ICU 62 */
2130     U_WB_WSEGSPACE = 22,        /*[WSEGSPACE]*/
2131
2132 #ifndef U_HIDE_DEPRECATED_API
2133     /**
2134      * One more than the highest normal UWordBreakValues value.
2135      * The highest value is available via u_getIntPropertyMaxValue(UCHAR_WORD_BREAK).
2136      *
2137      * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420.
2138      */
2139     U_WB_COUNT = 23
2140 #endif  // U_HIDE_DEPRECATED_API
2141 } UWordBreakValues;
2142
2143 /**
2144  * Sentence Break constants.
2145  *
2146  * @see UCHAR_SENTENCE_BREAK
2147  * @stable ICU 3.4
2148  */
2149 typedef enum USentenceBreak {
2150     /*
2151      * Note: USentenceBreak constants are parsed by preparseucd.py.
2152      * It matches lines like
2153      *     U_SB_<Unicode Sentence_Break value name>
2154      */
2155
2156     U_SB_OTHER = 0,             /*[XX]*/
2157     U_SB_ATERM = 1,             /*[AT]*/
2158     U_SB_CLOSE = 2,             /*[CL]*/
2159     U_SB_FORMAT = 3,            /*[FO]*/
2160     U_SB_LOWER = 4,             /*[LO]*/
2161     U_SB_NUMERIC = 5,           /*[NU]*/
2162     U_SB_OLETTER = 6,           /*[LE]*/
2163     U_SB_SEP = 7,               /*[SE]*/
2164     U_SB_SP = 8,                /*[SP]*/
2165     U_SB_STERM = 9,             /*[ST]*/
2166     U_SB_UPPER = 10,            /*[UP]*/
2167     U_SB_CR = 11,               /*[CR]*/ /* from here on: new in Unicode 5.1/ICU 4.0 */
2168     U_SB_EXTEND = 12,           /*[EX]*/
2169     U_SB_LF = 13,               /*[LF]*/
2170     U_SB_SCONTINUE = 14,        /*[SC]*/
2171 #ifndef U_HIDE_DEPRECATED_API
2172     /**
2173      * One more than the highest normal USentenceBreak value.
2174      * The highest value is available via u_getIntPropertyMaxValue(UCHAR_SENTENCE_BREAK).
2175      *
2176      * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420.
2177      */
2178     U_SB_COUNT = 15
2179 #endif  // U_HIDE_DEPRECATED_API
2180 } USentenceBreak;
2181
2182 /**
2183  * Line Break constants.
2184  *
2185  * @see UCHAR_LINE_BREAK
2186  * @stable ICU 2.2
2187  */
2188 typedef enum ULineBreak {
2189     /*
2190      * Note: ULineBreak constants are parsed by preparseucd.py.
2191      * It matches lines like
2192      *     U_LB_<Unicode Line_Break value name>
2193      */
2194
2195     U_LB_UNKNOWN = 0,           /*[XX]*/
2196     U_LB_AMBIGUOUS = 1,         /*[AI]*/
2197     U_LB_ALPHABETIC = 2,        /*[AL]*/
2198     U_LB_BREAK_BOTH = 3,        /*[B2]*/
2199     U_LB_BREAK_AFTER = 4,       /*[BA]*/
2200     U_LB_BREAK_BEFORE = 5,      /*[BB]*/
2201     U_LB_MANDATORY_BREAK = 6,   /*[BK]*/
2202     U_LB_CONTINGENT_BREAK = 7,  /*[CB]*/
2203     U_LB_CLOSE_PUNCTUATION = 8, /*[CL]*/
2204     U_LB_COMBINING_MARK = 9,    /*[CM]*/
2205     U_LB_CARRIAGE_RETURN = 10,   /*[CR]*/
2206     U_LB_EXCLAMATION = 11,       /*[EX]*/
2207     U_LB_GLUE = 12,              /*[GL]*/
2208     U_LB_HYPHEN = 13,            /*[HY]*/
2209     U_LB_IDEOGRAPHIC = 14,       /*[ID]*/
2210     /** Renamed from the misspelled "inseperable" in Unicode 4.0.1/ICU 3.0 @stable ICU 3.0 */
2211     U_LB_INSEPARABLE = 15,       /*[IN]*/
2212     U_LB_INSEPERABLE = U_LB_INSEPARABLE,
2213     U_LB_INFIX_NUMERIC = 16,     /*[IS]*/
2214     U_LB_LINE_FEED = 17,         /*[LF]*/
2215     U_LB_NONSTARTER = 18,        /*[NS]*/
2216     U_LB_NUMERIC = 19,           /*[NU]*/
2217     U_LB_OPEN_PUNCTUATION = 20,  /*[OP]*/
2218     U_LB_POSTFIX_NUMERIC = 21,   /*[PO]*/
2219     U_LB_PREFIX_NUMERIC = 22,    /*[PR]*/
2220     U_LB_QUOTATION = 23,         /*[QU]*/
2221     U_LB_COMPLEX_CONTEXT = 24,   /*[SA]*/
2222     U_LB_SURROGATE = 25,         /*[SG]*/
2223     U_LB_SPACE = 26,             /*[SP]*/
2224     U_LB_BREAK_SYMBOLS = 27,     /*[SY]*/
2225     U_LB_ZWSPACE = 28,           /*[ZW]*/
2226     /** @stable ICU 2.6 */
2227     U_LB_NEXT_LINE = 29,         /*[NL]*/ /* from here on: new in Unicode 4/ICU 2.6 */
2228     /** @stable ICU 2.6 */
2229     U_LB_WORD_JOINER = 30,       /*[WJ]*/
2230     /** @stable ICU 3.4 */
2231     U_LB_H2 = 31,                /*[H2]*/ /* from here on: new in Unicode 4.1/ICU 3.4 */
2232     /** @stable ICU 3.4 */
2233     U_LB_H3 = 32,                /*[H3]*/
2234     /** @stable ICU 3.4 */
2235     U_LB_JL = 33,                /*[JL]*/
2236     /** @stable ICU 3.4 */
2237     U_LB_JT = 34,                /*[JT]*/
2238     /** @stable ICU 3.4 */
2239     U_LB_JV = 35,                /*[JV]*/
2240     /** @stable ICU 4.4 */
2241     U_LB_CLOSE_PARENTHESIS = 36, /*[CP]*/ /* new in Unicode 5.2/ICU 4.4 */
2242     /** @stable ICU 49 */
2243     U_LB_CONDITIONAL_JAPANESE_STARTER = 37,/*[CJ]*/ /* new in Unicode 6.1/ICU 49 */
2244     /** @stable ICU 49 */
2245     U_LB_HEBREW_LETTER = 38,     /*[HL]*/ /* new in Unicode 6.1/ICU 49 */
2246     /** @stable ICU 50 */
2247     U_LB_REGIONAL_INDICATOR = 39,/*[RI]*/ /* new in Unicode 6.2/ICU 50 */
2248     /** @stable ICU 58 */
2249     U_LB_E_BASE = 40,            /*[EB]*/ /* from here on: new in Unicode 9.0/ICU 58 */
2250     /** @stable ICU 58 */
2251     U_LB_E_MODIFIER = 41,        /*[EM]*/
2252     /** @stable ICU 58 */
2253     U_LB_ZWJ = 42,               /*[ZWJ]*/
2254 #ifndef U_HIDE_DEPRECATED_API
2255     /**
2256      * One more than the highest normal ULineBreak value.
2257      * The highest value is available via u_getIntPropertyMaxValue(UCHAR_LINE_BREAK).
2258      *
2259      * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420.
2260      */
2261     U_LB_COUNT = 43
2262 #endif  // U_HIDE_DEPRECATED_API
2263 } ULineBreak;
2264
2265 /**
2266  * Numeric Type constants.
2267  *
2268  * @see UCHAR_NUMERIC_TYPE
2269  * @stable ICU 2.2
2270  */
2271 typedef enum UNumericType {
2272     /*
2273      * Note: UNumericType constants are parsed by preparseucd.py.
2274      * It matches lines like
2275      *     U_NT_<Unicode Numeric_Type value name>
2276      */
2277
2278     U_NT_NONE,              /*[None]*/
2279     U_NT_DECIMAL,           /*[de]*/
2280     U_NT_DIGIT,             /*[di]*/
2281     U_NT_NUMERIC,           /*[nu]*/
2282 #ifndef U_HIDE_DEPRECATED_API
2283     /**
2284      * One more than the highest normal UNumericType value.
2285      * The highest value is available via u_getIntPropertyMaxValue(UCHAR_NUMERIC_TYPE).
2286      *
2287      * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420.
2288      */
2289     U_NT_COUNT
2290 #endif  // U_HIDE_DEPRECATED_API
2291 } UNumericType;
2292
2293 /**
2294  * Hangul Syllable Type constants.
2295  *
2296  * @see UCHAR_HANGUL_SYLLABLE_TYPE
2297  * @stable ICU 2.6
2298  */
2299 typedef enum UHangulSyllableType {
2300     /*
2301      * Note: UHangulSyllableType constants are parsed by preparseucd.py.
2302      * It matches lines like
2303      *     U_HST_<Unicode Hangul_Syllable_Type value name>
2304      */
2305
2306     U_HST_NOT_APPLICABLE,   /*[NA]*/
2307     U_HST_LEADING_JAMO,     /*[L]*/
2308     U_HST_VOWEL_JAMO,       /*[V]*/
2309     U_HST_TRAILING_JAMO,    /*[T]*/
2310     U_HST_LV_SYLLABLE,      /*[LV]*/
2311     U_HST_LVT_SYLLABLE,     /*[LVT]*/
2312 #ifndef U_HIDE_DEPRECATED_API
2313     /**
2314      * One more than the highest normal UHangulSyllableType value.
2315      * The highest value is available via u_getIntPropertyMaxValue(UCHAR_HANGUL_SYLLABLE_TYPE).
2316      *
2317      * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420.
2318      */
2319     U_HST_COUNT
2320 #endif  // U_HIDE_DEPRECATED_API
2321 } UHangulSyllableType;
2322
2323 /**
2324  * Check a binary Unicode property for a code point.
2325  *
2326  * Unicode, especially in version 3.2, defines many more properties than the
2327  * original set in UnicodeData.txt.
2328  *
2329  * The properties APIs are intended to reflect Unicode properties as defined
2330  * in the Unicode Character Database (UCD) and Unicode Technical Reports (UTR).
2331  * For details about the properties see http://www.unicode.org/ucd/ .
2332  * For names of Unicode properties see the UCD file PropertyAliases.txt.
2333  *
2334  * Important: If ICU is built with UCD files from Unicode versions below 3.2,
2335  * then properties marked with "new in Unicode 3.2" are not or not fully available.
2336  *
2337  * @param c Code point to test.
2338  * @param which UProperty selector constant, identifies which binary property to check.
2339  *        Must be UCHAR_BINARY_START<=which<UCHAR_BINARY_LIMIT.
2340  * @return TRUE or FALSE according to the binary Unicode property value for c.
2341  *         Also FALSE if 'which' is out of bounds or if the Unicode version
2342  *         does not have data for the property at all, or not for this code point.
2343  *
2344  * @see UProperty
2345  * @see u_getIntPropertyValue
2346  * @see u_getUnicodeVersion
2347  * @stable ICU 2.1
2348  */
2349 U_STABLE UBool U_EXPORT2
2350 u_hasBinaryProperty(UChar32 c, UProperty which);
2351
2352 /**
2353  * Check if a code point has the Alphabetic Unicode property.
2354  * Same as u_hasBinaryProperty(c, UCHAR_ALPHABETIC).
2355  * This is different from u_isalpha!
2356  * @param c Code point to test
2357  * @return true if the code point has the Alphabetic Unicode property, false otherwise
2358  *
2359  * @see UCHAR_ALPHABETIC
2360  * @see u_isalpha
2361  * @see u_hasBinaryProperty
2362  * @stable ICU 2.1
2363  */
2364 U_STABLE UBool U_EXPORT2
2365 u_isUAlphabetic(UChar32 c);
2366
2367 /**
2368  * Check if a code point has the Lowercase Unicode property.
2369  * Same as u_hasBinaryProperty(c, UCHAR_LOWERCASE).
2370  * This is different from u_islower!
2371  * @param c Code point to test
2372  * @return true if the code point has the Lowercase Unicode property, false otherwise
2373  *
2374  * @see UCHAR_LOWERCASE
2375  * @see u_islower
2376  * @see u_hasBinaryProperty
2377  * @stable ICU 2.1
2378  */
2379 U_STABLE UBool U_EXPORT2
2380 u_isULowercase(UChar32 c);
2381
2382 /**
2383  * Check if a code point has the Uppercase Unicode property.
2384  * Same as u_hasBinaryProperty(c, UCHAR_UPPERCASE).
2385  * This is different from u_isupper!
2386  * @param c Code point to test
2387  * @return true if the code point has the Uppercase Unicode property, false otherwise
2388  *
2389  * @see UCHAR_UPPERCASE
2390  * @see u_isupper
2391  * @see u_hasBinaryProperty
2392  * @stable ICU 2.1
2393  */
2394 U_STABLE UBool U_EXPORT2
2395 u_isUUppercase(UChar32 c);
2396
2397 /**
2398  * Check if a code point has the White_Space Unicode property.
2399  * Same as u_hasBinaryProperty(c, UCHAR_WHITE_SPACE).
2400  * This is different from both u_isspace and u_isWhitespace!
2401  *
2402  * Note: There are several ICU whitespace functions; please see the uchar.h
2403  * file documentation for a detailed comparison.
2404  *
2405  * @param c Code point to test
2406  * @return true if the code point has the White_Space Unicode property, false otherwise.
2407  *
2408  * @see UCHAR_WHITE_SPACE
2409  * @see u_isWhitespace
2410  * @see u_isspace
2411  * @see u_isJavaSpaceChar
2412  * @see u_hasBinaryProperty
2413  * @stable ICU 2.1
2414  */
2415 U_STABLE UBool U_EXPORT2
2416 u_isUWhiteSpace(UChar32 c);
2417
2418 /**
2419  * Get the property value for an enumerated or integer Unicode property for a code point.
2420  * Also returns binary and mask property values.
2421  *
2422  * Unicode, especially in version 3.2, defines many more properties than the
2423  * original set in UnicodeData.txt.
2424  *
2425  * The properties APIs are intended to reflect Unicode properties as defined
2426  * in the Unicode Character Database (UCD) and Unicode Technical Reports (UTR).
2427  * For details about the properties see http://www.unicode.org/ .
2428  * For names of Unicode properties see the UCD file PropertyAliases.txt.
2429  *
2430  * Sample usage:
2431  * UEastAsianWidth ea=(UEastAsianWidth)u_getIntPropertyValue(c, UCHAR_EAST_ASIAN_WIDTH);
2432  * UBool b=(UBool)u_getIntPropertyValue(c, UCHAR_IDEOGRAPHIC);
2433  *
2434  * @param c Code point to test.
2435  * @param which UProperty selector constant, identifies which property to check.
2436  *        Must be UCHAR_BINARY_START<=which<UCHAR_BINARY_LIMIT
2437  *        or UCHAR_INT_START<=which<UCHAR_INT_LIMIT
2438  *        or UCHAR_MASK_START<=which<UCHAR_MASK_LIMIT.
2439  * @return Numeric value that is directly the property value or,
2440  *         for enumerated properties, corresponds to the numeric value of the enumerated
2441  *         constant of the respective property value enumeration type
2442  *         (cast to enum type if necessary).
2443  *         Returns 0 or 1 (for FALSE/TRUE) for binary Unicode properties.
2444  *         Returns a bit-mask for mask properties.
2445  *         Returns 0 if 'which' is out of bounds or if the Unicode version
2446  *         does not have data for the property at all, or not for this code point.
2447  *
2448  * @see UProperty
2449  * @see u_hasBinaryProperty
2450  * @see u_getIntPropertyMinValue
2451  * @see u_getIntPropertyMaxValue
2452  * @see u_getUnicodeVersion
2453  * @stable ICU 2.2
2454  */
2455 U_STABLE int32_t U_EXPORT2
2456 u_getIntPropertyValue(UChar32 c, UProperty which);
2457
2458 /**
2459  * Get the minimum value for an enumerated/integer/binary Unicode property.
2460  * Can be used together with u_getIntPropertyMaxValue
2461  * to allocate arrays of UnicodeSet or similar.
2462  *
2463  * @param which UProperty selector constant, identifies which binary property to check.
2464  *        Must be UCHAR_BINARY_START<=which<UCHAR_BINARY_LIMIT
2465  *        or UCHAR_INT_START<=which<UCHAR_INT_LIMIT.
2466  * @return Minimum value returned by u_getIntPropertyValue for a Unicode property.
2467  *         0 if the property selector is out of range.
2468  *
2469  * @see UProperty
2470  * @see u_hasBinaryProperty
2471  * @see u_getUnicodeVersion
2472  * @see u_getIntPropertyMaxValue
2473  * @see u_getIntPropertyValue
2474  * @stable ICU 2.2
2475  */
2476 U_STABLE int32_t U_EXPORT2
2477 u_getIntPropertyMinValue(UProperty which);
2478
2479 /**
2480  * Get the maximum value for an enumerated/integer/binary Unicode property.
2481  * Can be used together with u_getIntPropertyMinValue
2482  * to allocate arrays of UnicodeSet or similar.
2483  *
2484  * Examples for min/max values (for Unicode 3.2):
2485  *
2486  * - UCHAR_BIDI_CLASS:    0/18 (U_LEFT_TO_RIGHT/U_BOUNDARY_NEUTRAL)
2487  * - UCHAR_SCRIPT:        0/45 (USCRIPT_COMMON/USCRIPT_TAGBANWA)
2488  * - UCHAR_IDEOGRAPHIC:   0/1  (FALSE/TRUE)
2489  *
2490  * For undefined UProperty constant values, min/max values will be 0/-1.
2491  *
2492  * @param which UProperty selector constant, identifies which binary property to check.
2493  *        Must be UCHAR_BINARY_START<=which<UCHAR_BINARY_LIMIT
2494  *        or UCHAR_INT_START<=which<UCHAR_INT_LIMIT.
2495  * @return Maximum value returned by u_getIntPropertyValue for a Unicode property.
2496  *         <=0 if the property selector is out of range.
2497  *
2498  * @see UProperty
2499  * @see u_hasBinaryProperty
2500  * @see u_getUnicodeVersion
2501  * @see u_getIntPropertyMaxValue
2502  * @see u_getIntPropertyValue
2503  * @stable ICU 2.2
2504  */
2505 U_STABLE int32_t U_EXPORT2
2506 u_getIntPropertyMaxValue(UProperty which);
2507
2508 /**
2509  * Get the numeric value for a Unicode code point as defined in the
2510  * Unicode Character Database.
2511  *
2512  * A "double" return type is necessary because
2513  * some numeric values are fractions, negative, or too large for int32_t.
2514  *
2515  * For characters without any numeric values in the Unicode Character Database,
2516  * this function will return U_NO_NUMERIC_VALUE.
2517  * Note: This is different from the Unicode Standard which specifies NaN as the default value.
2518  * (NaN is not available on all platforms.)
2519  *
2520  * Similar to java.lang.Character.getNumericValue(), but u_getNumericValue()
2521  * also supports negative values, large values, and fractions,
2522  * while Java's getNumericValue() returns values 10..35 for ASCII letters.
2523  *
2524  * @param c Code point to get the numeric value for.
2525  * @return Numeric value of c, or U_NO_NUMERIC_VALUE if none is defined.
2526  *
2527  * @see U_NO_NUMERIC_VALUE
2528  * @stable ICU 2.2
2529  */
2530 U_STABLE double U_EXPORT2
2531 u_getNumericValue(UChar32 c);
2532
2533 /**
2534  * Special value that is returned by u_getNumericValue when
2535  * no numeric value is defined for a code point.
2536  *
2537  * @see u_getNumericValue
2538  * @stable ICU 2.2
2539  */
2540 #define U_NO_NUMERIC_VALUE ((double)-123456789.)
2541
2542 /**
2543  * Determines whether the specified code point has the general category "Ll"
2544  * (lowercase letter).
2545  *
2546  * Same as java.lang.Character.isLowerCase().
2547  *
2548  * This misses some characters that are also lowercase but
2549  * have a different general category value.
2550  * In order to include those, use UCHAR_LOWERCASE.
2551  *
2552  * In addition to being equivalent to a Java function, this also serves
2553  * as a C/POSIX migration function.
2554  * See the comments about C/POSIX character classification functions in the
2555  * documentation at the top of this header file.
2556  *
2557  * @param c the code point to be tested
2558  * @return TRUE if the code point is an Ll lowercase letter
2559  *
2560  * @see UCHAR_LOWERCASE
2561  * @see u_isupper
2562  * @see u_istitle
2563  * @stable ICU 2.0
2564  */
2565 U_STABLE UBool U_EXPORT2
2566 u_islower(UChar32 c);
2567
2568 /**
2569  * Determines whether the specified code point has the general category "Lu"
2570  * (uppercase letter).
2571  *
2572  * Same as java.lang.Character.isUpperCase().
2573  *
2574  * This misses some characters that are also uppercase but
2575  * have a different general category value.
2576  * In order to include those, use UCHAR_UPPERCASE.
2577  *
2578  * In addition to being equivalent to a Java function, this also serves
2579  * as a C/POSIX migration function.
2580  * See the comments about C/POSIX character classification functions in the
2581  * documentation at the top of this header file.
2582  *
2583  * @param c the code point to be tested
2584  * @return TRUE if the code point is an Lu uppercase letter
2585  *
2586  * @see UCHAR_UPPERCASE
2587  * @see u_islower
2588  * @see u_istitle
2589  * @see u_tolower
2590  * @stable ICU 2.0
2591  */
2592 U_STABLE UBool U_EXPORT2
2593 u_isupper(UChar32 c);
2594
2595 /**
2596  * Determines whether the specified code point is a titlecase letter.
2597  * True for general category "Lt" (titlecase letter).
2598  *
2599  * Same as java.lang.Character.isTitleCase().
2600  *
2601  * @param c the code point to be tested
2602  * @return TRUE if the code point is an Lt titlecase letter
2603  *
2604  * @see u_isupper
2605  * @see u_islower
2606  * @see u_totitle
2607  * @stable ICU 2.0
2608  */
2609 U_STABLE UBool U_EXPORT2
2610 u_istitle(UChar32 c);
2611
2612 /**
2613  * Determines whether the specified code point is a digit character according to Java.
2614  * True for characters with general category "Nd" (decimal digit numbers).
2615  * Beginning with Unicode 4, this is the same as
2616  * testing for the Numeric_Type of Decimal.
2617  *
2618  * Same as java.lang.Character.isDigit().
2619  *
2620  * In addition to being equivalent to a Java function, this also serves
2621  * as a C/POSIX migration function.
2622  * See the comments about C/POSIX character classification functions in the
2623  * documentation at the top of this header file.
2624  *
2625  * @param c the code point to be tested
2626  * @return TRUE if the code point is a digit character according to Character.isDigit()
2627  *
2628  * @stable ICU 2.0
2629  */
2630 U_STABLE UBool U_EXPORT2
2631 u_isdigit(UChar32 c);
2632
2633 /**
2634  * Determines whether the specified code point is a letter character.
2635  * True for general categories "L" (letters).
2636  *
2637  * Same as java.lang.Character.isLetter().
2638  *
2639  * In addition to being equivalent to a Java function, this also serves
2640  * as a C/POSIX migration function.
2641  * See the comments about C/POSIX character classification functions in the
2642  * documentation at the top of this header file.
2643  *
2644  * @param c the code point to be tested
2645  * @return TRUE if the code point is a letter character
2646  *
2647  * @see u_isdigit
2648  * @see u_isalnum
2649  * @stable ICU 2.0
2650  */
2651 U_STABLE UBool U_EXPORT2
2652 u_isalpha(UChar32 c);
2653
2654 /**
2655  * Determines whether the specified code point is an alphanumeric character
2656  * (letter or digit) according to Java.
2657  * True for characters with general categories
2658  * "L" (letters) and "Nd" (decimal digit numbers).
2659  *
2660  * Same as java.lang.Character.isLetterOrDigit().
2661  *
2662  * In addition to being equivalent to a Java function, this also serves
2663  * as a C/POSIX migration function.
2664  * See the comments about C/POSIX character classification functions in the
2665  * documentation at the top of this header file.
2666  *
2667  * @param c the code point to be tested
2668  * @return TRUE if the code point is an alphanumeric character according to Character.isLetterOrDigit()
2669  *
2670  * @stable ICU 2.0
2671  */
2672 U_STABLE UBool U_EXPORT2
2673 u_isalnum(UChar32 c);
2674
2675 /**
2676  * Determines whether the specified code point is a hexadecimal digit.
2677  * This is equivalent to u_digit(c, 16)>=0.
2678  * True for characters with general category "Nd" (decimal digit numbers)
2679  * as well as Latin letters a-f and A-F in both ASCII and Fullwidth ASCII.
2680  * (That is, for letters with code points
2681  * 0041..0046, 0061..0066, FF21..FF26, FF41..FF46.)
2682  *
2683  * In order to narrow the definition of hexadecimal digits to only ASCII
2684  * characters, use (c<=0x7f && u_isxdigit(c)).
2685  *
2686  * This is a C/POSIX migration function.
2687  * See the comments about C/POSIX character classification functions in the
2688  * documentation at the top of this header file.
2689  *
2690  * @param c the code point to be tested
2691  * @return TRUE if the code point is a hexadecimal digit
2692  *
2693  * @stable ICU 2.6
2694  */
2695 U_STABLE UBool U_EXPORT2
2696 u_isxdigit(UChar32 c);
2697
2698 /**
2699  * Determines whether the specified code point is a punctuation character.
2700  * True for characters with general categories "P" (punctuation).
2701  *
2702  * This is a C/POSIX migration function.
2703  * See the comments about C/POSIX character classification functions in the
2704  * documentation at the top of this header file.
2705  *
2706  * @param c the code point to be tested
2707  * @return TRUE if the code point is a punctuation character
2708  *
2709  * @stable ICU 2.6
2710  */
2711 U_STABLE UBool U_EXPORT2
2712 u_ispunct(UChar32 c);
2713
2714 /**
2715  * Determines whether the specified code point is a "graphic" character
2716  * (printable, excluding spaces).
2717  * TRUE for all characters except those with general categories
2718  * "Cc" (control codes), "Cf" (format controls), "Cs" (surrogates),
2719  * "Cn" (unassigned), and "Z" (separators).
2720  *
2721  * This is a C/POSIX migration function.
2722  * See the comments about C/POSIX character classification functions in the
2723  * documentation at the top of this header file.
2724  *
2725  * @param c the code point to be tested
2726  * @return TRUE if the code point is a "graphic" character
2727  *
2728  * @stable ICU 2.6
2729  */
2730 U_STABLE UBool U_EXPORT2
2731 u_isgraph(UChar32 c);
2732
2733 /**
2734  * Determines whether the specified code point is a "blank" or "horizontal space",
2735  * a character that visibly separates words on a line.
2736  * The following are equivalent definitions:
2737  *
2738  * TRUE for Unicode White_Space characters except for "vertical space controls"
2739  * where "vertical space controls" are the following characters:
2740  * U+000A (LF) U+000B (VT) U+000C (FF) U+000D (CR) U+0085 (NEL) U+2028 (LS) U+2029 (PS)
2741  *
2742  * same as
2743  *
2744  * TRUE for U+0009 (TAB) and characters with general category "Zs" (space separators).
2745  *
2746  * Note: There are several ICU whitespace functions; please see the uchar.h
2747  * file documentation for a detailed comparison.
2748  *
2749  * This is a C/POSIX migration function.
2750  * See the comments about C/POSIX character classification functions in the
2751  * documentation at the top of this header file.
2752  *
2753  * @param c the code point to be tested
2754  * @return TRUE if the code point is a "blank"
2755  *
2756  * @stable ICU 2.6
2757  */
2758 U_STABLE UBool U_EXPORT2
2759 u_isblank(UChar32 c);
2760
2761 /**
2762  * Determines whether the specified code point is "defined",
2763  * which usually means that it is assigned a character.
2764  * True for general categories other than "Cn" (other, not assigned),
2765  * i.e., true for all code points mentioned in UnicodeData.txt.
2766  *
2767  * Note that non-character code points (e.g., U+FDD0) are not "defined"
2768  * (they are Cn), but surrogate code points are "defined" (Cs).
2769  *
2770  * Same as java.lang.Character.isDefined().
2771  *
2772  * @param c the code point to be tested
2773  * @return TRUE if the code point is assigned a character
2774  *
2775  * @see u_isdigit
2776  * @see u_isalpha
2777  * @see u_isalnum
2778  * @see u_isupper
2779  * @see u_islower
2780  * @see u_istitle
2781  * @stable ICU 2.0
2782  */
2783 U_STABLE UBool U_EXPORT2
2784 u_isdefined(UChar32 c);
2785
2786 /**
2787  * Determines if the specified character is a space character or not.
2788  *
2789  * Note: There are several ICU whitespace functions; please see the uchar.h
2790  * file documentation for a detailed comparison.
2791  *
2792  * This is a C/POSIX migration function.
2793  * See the comments about C/POSIX character classification functions in the
2794  * documentation at the top of this header file.
2795  *
2796  * @param c    the character to be tested
2797  * @return  true if the character is a space character; false otherwise.
2798  *
2799  * @see u_isJavaSpaceChar
2800  * @see u_isWhitespace
2801  * @see u_isUWhiteSpace
2802  * @stable ICU 2.0
2803  */
2804 U_STABLE UBool U_EXPORT2
2805 u_isspace(UChar32 c);
2806
2807 /**
2808  * Determine if the specified code point is a space character according to Java.
2809  * True for characters with general categories "Z" (separators),
2810  * which does not include control codes (e.g., TAB or Line Feed).
2811  *
2812  * Same as java.lang.Character.isSpaceChar().
2813  *
2814  * Note: There are several ICU whitespace functions; please see the uchar.h
2815  * file documentation for a detailed comparison.
2816  *
2817  * @param c the code point to be tested
2818  * @return TRUE if the code point is a space character according to Character.isSpaceChar()
2819  *
2820  * @see u_isspace
2821  * @see u_isWhitespace
2822  * @see u_isUWhiteSpace
2823  * @stable ICU 2.6
2824  */
2825 U_STABLE UBool U_EXPORT2
2826 u_isJavaSpaceChar(UChar32 c);
2827
2828 /**
2829  * Determines if the specified code point is a whitespace character according to Java/ICU.
2830  * A character is considered to be a Java whitespace character if and only
2831  * if it satisfies one of the following criteria:
2832  *
2833  * - It is a Unicode Separator character (categories "Z" = "Zs" or "Zl" or "Zp"), but is not
2834  *      also a non-breaking space (U+00A0 NBSP or U+2007 Figure Space or U+202F Narrow NBSP).
2835  * - It is U+0009 HORIZONTAL TABULATION.
2836  * - It is U+000A LINE FEED.
2837  * - It is U+000B VERTICAL TABULATION.
2838  * - It is U+000C FORM FEED.
2839  * - It is U+000D CARRIAGE RETURN.
2840  * - It is U+001C FILE SEPARATOR.
2841  * - It is U+001D GROUP SEPARATOR.
2842  * - It is U+001E RECORD SEPARATOR.
2843  * - It is U+001F UNIT SEPARATOR.
2844  *
2845  * This API tries to sync with the semantics of Java's
2846  * java.lang.Character.isWhitespace(), but it may not return
2847  * the exact same results because of the Unicode version
2848  * difference.
2849  *
2850  * Note: Unicode 4.0.1 changed U+200B ZERO WIDTH SPACE from a Space Separator (Zs)
2851  * to a Format Control (Cf). Since then, isWhitespace(0x200b) returns false.
2852  * See http://www.unicode.org/versions/Unicode4.0.1/
2853  *
2854  * Note: There are several ICU whitespace functions; please see the uchar.h
2855  * file documentation for a detailed comparison.
2856  *
2857  * @param c the code point to be tested
2858  * @return TRUE if the code point is a whitespace character according to Java/ICU
2859  *
2860  * @see u_isspace
2861  * @see u_isJavaSpaceChar
2862  * @see u_isUWhiteSpace
2863  * @stable ICU 2.0
2864  */
2865 U_STABLE UBool U_EXPORT2
2866 u_isWhitespace(UChar32 c);
2867
2868 /**
2869  * Determines whether the specified code point is a control character
2870  * (as defined by this function).
2871  * A control character is one of the following:
2872  * - ISO 8-bit control character (U+0000..U+001f and U+007f..U+009f)
2873  * - U_CONTROL_CHAR (Cc)
2874  * - U_FORMAT_CHAR (Cf)
2875  * - U_LINE_SEPARATOR (Zl)
2876  * - U_PARAGRAPH_SEPARATOR (Zp)
2877  *
2878  * This is a C/POSIX migration function.
2879  * See the comments about C/POSIX character classification functions in the
2880  * documentation at the top of this header file.
2881  *
2882  * @param c the code point to be tested
2883  * @return TRUE if the code point is a control character
2884  *
2885  * @see UCHAR_DEFAULT_IGNORABLE_CODE_POINT
2886  * @see u_isprint
2887  * @stable ICU 2.0
2888  */
2889 U_STABLE UBool U_EXPORT2
2890 u_iscntrl(UChar32 c);
2891
2892 /**
2893  * Determines whether the specified code point is an ISO control code.
2894  * True for U+0000..U+001f and U+007f..U+009f (general category "Cc").
2895  *
2896  * Same as java.lang.Character.isISOControl().
2897  *
2898  * @param c the code point to be tested
2899  * @return TRUE if the code point is an ISO control code
2900  *
2901  * @see u_iscntrl
2902  * @stable ICU 2.6
2903  */
2904 U_STABLE UBool U_EXPORT2
2905 u_isISOControl(UChar32 c);
2906
2907 /**
2908  * Determines whether the specified code point is a printable character.
2909  * True for general categories <em>other</em> than "C" (controls).
2910  *
2911  * This is a C/POSIX migration function.
2912  * See the comments about C/POSIX character classification functions in the
2913  * documentation at the top of this header file.
2914  *
2915  * @param c the code point to be tested
2916  * @return TRUE if the code point is a printable character
2917  *
2918  * @see UCHAR_DEFAULT_IGNORABLE_CODE_POINT
2919  * @see u_iscntrl
2920  * @stable ICU 2.0
2921  */
2922 U_STABLE UBool U_EXPORT2
2923 u_isprint(UChar32 c);
2924
2925 /**
2926  * Determines whether the specified code point is a base character.
2927  * True for general categories "L" (letters), "N" (numbers),
2928  * "Mc" (spacing combining marks), and "Me" (enclosing marks).
2929  *
2930  * Note that this is different from the Unicode definition in
2931  * chapter 3.5, conformance clause D13,
2932  * which defines base characters to be all characters (not Cn)
2933  * that do not graphically combine with preceding characters (M)
2934  * and that are neither control (Cc) or format (Cf) characters.
2935  *
2936  * @param c the code point to be tested
2937  * @return TRUE if the code point is a base character according to this function
2938  *
2939  * @see u_isalpha
2940  * @see u_isdigit
2941  * @stable ICU 2.0
2942  */
2943 U_STABLE UBool U_EXPORT2
2944 u_isbase(UChar32 c);
2945
2946 /**
2947  * Returns the bidirectional category value for the code point,
2948  * which is used in the Unicode bidirectional algorithm
2949  * (UAX #9 http://www.unicode.org/reports/tr9/).
2950  * Note that some <em>unassigned</em> code points have bidi values
2951  * of R or AL because they are in blocks that are reserved
2952  * for Right-To-Left scripts.
2953  *
2954  * Same as java.lang.Character.getDirectionality()
2955  *
2956  * @param c the code point to be tested
2957  * @return the bidirectional category (UCharDirection) value
2958  *
2959  * @see UCharDirection
2960  * @stable ICU 2.0
2961  */
2962 U_STABLE UCharDirection U_EXPORT2
2963 u_charDirection(UChar32 c);
2964
2965 /**
2966  * Determines whether the code point has the Bidi_Mirrored property.
2967  * This property is set for characters that are commonly used in
2968  * Right-To-Left contexts and need to be displayed with a "mirrored"
2969  * glyph.
2970  *
2971  * Same as java.lang.Character.isMirrored().
2972  * Same as UCHAR_BIDI_MIRRORED
2973  *
2974  * @param c the code point to be tested
2975  * @return TRUE if the character has the Bidi_Mirrored property
2976  *
2977  * @see UCHAR_BIDI_MIRRORED
2978  * @stable ICU 2.0
2979  */
2980 U_STABLE UBool U_EXPORT2
2981 u_isMirrored(UChar32 c);
2982
2983 /**
2984  * Maps the specified character to a "mirror-image" character.
2985  * For characters with the Bidi_Mirrored property, implementations
2986  * sometimes need a "poor man's" mapping to another Unicode
2987  * character (code point) such that the default glyph may serve
2988  * as the mirror-image of the default glyph of the specified
2989  * character. This is useful for text conversion to and from
2990  * codepages with visual order, and for displays without glyph
2991  * selection capabilities.
2992  *
2993  * @param c the code point to be mapped
2994  * @return another Unicode code point that may serve as a mirror-image
2995  *         substitute, or c itself if there is no such mapping or c
2996  *         does not have the Bidi_Mirrored property
2997  *
2998  * @see UCHAR_BIDI_MIRRORED
2999  * @see u_isMirrored
3000  * @stable ICU 2.0
3001  */
3002 U_STABLE UChar32 U_EXPORT2
3003 u_charMirror(UChar32 c);
3004
3005 /**
3006  * Maps the specified character to its paired bracket character.
3007  * For Bidi_Paired_Bracket_Type!=None, this is the same as u_charMirror().
3008  * Otherwise c itself is returned.
3009  * See http://www.unicode.org/reports/tr9/
3010  *
3011  * @param c the code point to be mapped
3012  * @return the paired bracket code point,
3013  *         or c itself if there is no such mapping
3014  *         (Bidi_Paired_Bracket_Type=None)
3015  *
3016  * @see UCHAR_BIDI_PAIRED_BRACKET
3017  * @see UCHAR_BIDI_PAIRED_BRACKET_TYPE
3018  * @see u_charMirror
3019  * @stable ICU 52
3020  */
3021 U_STABLE UChar32 U_EXPORT2
3022 u_getBidiPairedBracket(UChar32 c);
3023
3024 /**
3025  * Returns the general category value for the code point.
3026  *
3027  * Same as java.lang.Character.getType().
3028  *
3029  * @param c the code point to be tested
3030  * @return the general category (UCharCategory) value
3031  *
3032  * @see UCharCategory
3033  * @stable ICU 2.0
3034  */
3035 U_STABLE int8_t U_EXPORT2
3036 u_charType(UChar32 c);
3037
3038 /**
3039  * Get a single-bit bit set for the general category of a character.
3040  * This bit set can be compared bitwise with U_GC_SM_MASK, U_GC_L_MASK, etc.
3041  * Same as U_MASK(u_charType(c)).
3042  *
3043  * @param c the code point to be tested
3044  * @return a single-bit mask corresponding to the general category (UCharCategory) value
3045  *
3046  * @see u_charType
3047  * @see UCharCategory
3048  * @see U_GC_CN_MASK
3049  * @stable ICU 2.1
3050  */
3051 #define U_GET_GC_MASK(c) U_MASK(u_charType(c))
3052
3053 /**
3054  * Callback from u_enumCharTypes(), is called for each contiguous range
3055  * of code points c (where start<=c<limit)
3056  * with the same Unicode general category ("character type").
3057  *
3058  * The callback function can stop the enumeration by returning FALSE.
3059  *
3060  * @param context an opaque pointer, as passed into utrie_enum()
3061  * @param start the first code point in a contiguous range with value
3062  * @param limit one past the last code point in a contiguous range with value
3063  * @param type the general category for all code points in [start..limit[
3064  * @return FALSE to stop the enumeration
3065  *
3066  * @stable ICU 2.1
3067  * @see UCharCategory
3068  * @see u_enumCharTypes
3069  */
3070 typedef UBool U_CALLCONV
3071 UCharEnumTypeRange(const void *context, UChar32 start, UChar32 limit, UCharCategory type);
3072
3073 /**
3074  * Enumerate efficiently all code points with their Unicode general categories.
3075  *
3076  * This is useful for building data structures (e.g., UnicodeSet's),
3077  * for enumerating all assigned code points (type!=U_UNASSIGNED), etc.
3078  *
3079  * For each contiguous range of code points with a given general category ("character type"),
3080  * the UCharEnumTypeRange function is called.
3081  * Adjacent ranges have different types.
3082  * The Unicode Standard guarantees that the numeric value of the type is 0..31.
3083  *
3084  * @param enumRange a pointer to a function that is called for each contiguous range
3085  *                  of code points with the same general category
3086  * @param context an opaque pointer that is passed on to the callback function
3087  *
3088  * @stable ICU 2.1
3089  * @see UCharCategory
3090  * @see UCharEnumTypeRange
3091  */
3092 U_STABLE void U_EXPORT2
3093 u_enumCharTypes(UCharEnumTypeRange *enumRange, const void *context);
3094
3095 #if !UCONFIG_NO_NORMALIZATION
3096
3097 /**
3098  * Returns the combining class of the code point as specified in UnicodeData.txt.
3099  *
3100  * @param c the code point of the character
3101  * @return the combining class of the character
3102  * @stable ICU 2.0
3103  */
3104 U_STABLE uint8_t U_EXPORT2
3105 u_getCombiningClass(UChar32 c);
3106
3107 #endif
3108
3109 /**
3110  * Returns the decimal digit value of a decimal digit character.
3111  * Such characters have the general category "Nd" (decimal digit numbers)
3112  * and a Numeric_Type of Decimal.
3113  *
3114  * Unlike ICU releases before 2.6, no digit values are returned for any
3115  * Han characters because Han number characters are often used with a special
3116  * Chinese-style number format (with characters for powers of 10 in between)
3117  * instead of in decimal-positional notation.
3118  * Unicode 4 explicitly assigns Han number characters the Numeric_Type
3119  * Numeric instead of Decimal.
3120  * See Jitterbug 1483 for more details.
3121  *
3122  * Use u_getIntPropertyValue(c, UCHAR_NUMERIC_TYPE) and u_getNumericValue()
3123  * for complete numeric Unicode properties.
3124  *
3125  * @param c the code point for which to get the decimal digit value
3126  * @return the decimal digit value of c,
3127  *         or -1 if c is not a decimal digit character
3128  *
3129  * @see u_getNumericValue
3130  * @stable ICU 2.0
3131  */
3132 U_STABLE int32_t U_EXPORT2
3133 u_charDigitValue(UChar32 c);
3134
3135 /**
3136  * Returns the Unicode allocation block that contains the character.
3137  *
3138  * @param c the code point to be tested
3139  * @return the block value (UBlockCode) for c
3140  *
3141  * @see UBlockCode
3142  * @stable ICU 2.0
3143  */
3144 U_STABLE UBlockCode U_EXPORT2
3145 ublock_getCode(UChar32 c);
3146
3147 /**
3148  * Retrieve the name of a Unicode character.
3149  * Depending on <code>nameChoice</code>, the character name written
3150  * into the buffer is the "modern" name or the name that was defined
3151  * in Unicode version 1.0.
3152  * The name contains only "invariant" characters
3153  * like A-Z, 0-9, space, and '-'.
3154  * Unicode 1.0 names are only retrieved if they are different from the modern
3155  * names and if the data file contains the data for them. gennames may or may
3156  * not be called with a command line option to include 1.0 names in unames.dat.
3157  *
3158  * @param code The character (code point) for which to get the name.
3159  *             It must be <code>0<=code<=0x10ffff</code>.
3160  * @param nameChoice Selector for which name to get.
3161  * @param buffer Destination address for copying the name.
3162  *               The name will always be zero-terminated.
3163  *               If there is no name, then the buffer will be set to the empty string.
3164  * @param bufferLength <code>==sizeof(buffer)</code>
3165  * @param pErrorCode Pointer to a UErrorCode variable;
3166  *        check for <code>U_SUCCESS()</code> after <code>u_charName()</code>
3167  *        returns.
3168  * @return The length of the name, or 0 if there is no name for this character.
3169  *         If the bufferLength is less than or equal to the length, then the buffer
3170  *         contains the truncated name and the returned length indicates the full
3171  *         length of the name.
3172  *         The length does not include the zero-termination.
3173  *
3174  * @see UCharNameChoice
3175  * @see u_charFromName
3176  * @see u_enumCharNames
3177  * @stable ICU 2.0
3178  */
3179 U_STABLE int32_t U_EXPORT2
3180 u_charName(UChar32 code, UCharNameChoice nameChoice,
3181            char *buffer, int32_t bufferLength,
3182            UErrorCode *pErrorCode);
3183
3184 #ifndef U_HIDE_DEPRECATED_API
3185 /**
3186  * Returns an empty string.
3187  * Used to return the ISO 10646 comment for a character.
3188  * The Unicode ISO_Comment property is deprecated and has no values.
3189  *
3190  * @param c The character (code point) for which to get the ISO comment.
3191  *             It must be <code>0<=c<=0x10ffff</code>.
3192  * @param dest Destination address for copying the comment.
3193  *             The comment will be zero-terminated if possible.
3194  *             If there is no comment, then the buffer will be set to the empty string.
3195  * @param destCapacity <code>==sizeof(dest)</code>
3196  * @param pErrorCode Pointer to a UErrorCode variable;
3197  *        check for <code>U_SUCCESS()</code> after <code>u_getISOComment()</code>
3198  *        returns.
3199  * @return 0
3200  *
3201  * @deprecated ICU 49
3202  */
3203 U_DEPRECATED int32_t U_EXPORT2
3204 u_getISOComment(UChar32 c,
3205                 char *dest, int32_t destCapacity,
3206                 UErrorCode *pErrorCode);
3207 #endif  /* U_HIDE_DEPRECATED_API */
3208
3209 /**
3210  * Find a Unicode character by its name and return its code point value.
3211  * The name is matched exactly and completely.
3212  * If the name does not correspond to a code point, <i>pErrorCode</i>
3213  * is set to <code>U_INVALID_CHAR_FOUND</code>.
3214  * A Unicode 1.0 name is matched only if it differs from the modern name.
3215  * Unicode names are all uppercase. Extended names are lowercase followed
3216  * by an uppercase hexadecimal number, and within angle brackets.
3217  *
3218  * @param nameChoice Selector for which name to match.
3219  * @param name The name to match.
3220  * @param pErrorCode Pointer to a UErrorCode variable
3221  * @return The Unicode value of the code point with the given name,
3222  *         or an undefined value if there is no such code point.
3223  *
3224  * @see UCharNameChoice
3225  * @see u_charName
3226  * @see u_enumCharNames
3227  * @stable ICU 1.7
3228  */
3229 U_STABLE UChar32 U_EXPORT2
3230 u_charFromName(UCharNameChoice nameChoice,
3231                const char *name,
3232                UErrorCode *pErrorCode);
3233
3234 /**
3235  * Type of a callback function for u_enumCharNames() that gets called
3236  * for each Unicode character with the code point value and
3237  * the character name.
3238  * If such a function returns FALSE, then the enumeration is stopped.
3239  *
3240  * @param context The context pointer that was passed to u_enumCharNames().
3241  * @param code The Unicode code point for the character with this name.
3242  * @param nameChoice Selector for which kind of names is enumerated.
3243  * @param name The character's name, zero-terminated.
3244  * @param length The length of the name.
3245  * @return TRUE if the enumeration should continue, FALSE to stop it.
3246  *
3247  * @see UCharNameChoice
3248  * @see u_enumCharNames
3249  * @stable ICU 1.7
3250  */
3251 typedef UBool U_CALLCONV UEnumCharNamesFn(void *context,
3252                                UChar32 code,
3253                                UCharNameChoice nameChoice,
3254                                const char *name,
3255                                int32_t length);
3256
3257 /**
3258  * Enumerate all assigned Unicode characters between the start and limit
3259  * code points (start inclusive, limit exclusive) and call a function
3260  * for each, passing the code point value and the character name.
3261  * For Unicode 1.0 names, only those are enumerated that differ from the
3262  * modern names.
3263  *
3264  * @param start The first code point in the enumeration range.
3265  * @param limit One more than the last code point in the enumeration range
3266  *              (the first one after the range).
3267  * @param fn The function that is to be called for each character name.
3268  * @param context An arbitrary pointer that is passed to the function.
3269  * @param nameChoice Selector for which kind of names to enumerate.
3270  * @param pErrorCode Pointer to a UErrorCode variable
3271  *
3272  * @see UCharNameChoice
3273  * @see UEnumCharNamesFn
3274  * @see u_charName
3275  * @see u_charFromName
3276  * @stable ICU 1.7
3277  */
3278 U_STABLE void U_EXPORT2
3279 u_enumCharNames(UChar32 start, UChar32 limit,
3280                 UEnumCharNamesFn *fn,
3281                 void *context,
3282                 UCharNameChoice nameChoice,
3283                 UErrorCode *pErrorCode);
3284
3285 /**
3286  * Return the Unicode name for a given property, as given in the
3287  * Unicode database file PropertyAliases.txt.
3288  *
3289  * In addition, this function maps the property
3290  * UCHAR_GENERAL_CATEGORY_MASK to the synthetic names "gcm" /
3291  * "General_Category_Mask".  These names are not in
3292  * PropertyAliases.txt.
3293  *
3294  * @param property UProperty selector other than UCHAR_INVALID_CODE.
3295  *         If out of range, NULL is returned.
3296  *
3297  * @param nameChoice selector for which name to get.  If out of range,
3298  *         NULL is returned.  All properties have a long name.  Most
3299  *         have a short name, but some do not.  Unicode allows for
3300  *         additional names; if present these will be returned by
3301  *         U_LONG_PROPERTY_NAME + i, where i=1, 2,...
3302  *
3303  * @return a pointer to the name, or NULL if either the
3304  *         property or the nameChoice is out of range.  If a given
3305  *         nameChoice returns NULL, then all larger values of
3306  *         nameChoice will return NULL, with one exception: if NULL is
3307  *         returned for U_SHORT_PROPERTY_NAME, then
3308  *         U_LONG_PROPERTY_NAME (and higher) may still return a
3309  *         non-NULL value.  The returned pointer is valid until
3310  *         u_cleanup() is called.
3311  *
3312  * @see UProperty
3313  * @see UPropertyNameChoice
3314  * @stable ICU 2.4
3315  */
3316 U_STABLE const char* U_EXPORT2
3317 u_getPropertyName(UProperty property,
3318                   UPropertyNameChoice nameChoice);
3319
3320 /**
3321  * Return the UProperty enum for a given property name, as specified
3322  * in the Unicode database file PropertyAliases.txt.  Short, long, and
3323  * any other variants are recognized.
3324  *
3325  * In addition, this function maps the synthetic names "gcm" /
3326  * "General_Category_Mask" to the property
3327  * UCHAR_GENERAL_CATEGORY_MASK.  These names are not in
3328  * PropertyAliases.txt.
3329  *
3330  * @param alias the property name to be matched.  The name is compared
3331  *         using "loose matching" as described in PropertyAliases.txt.
3332  *
3333  * @return a UProperty enum, or UCHAR_INVALID_CODE if the given name
3334  *         does not match any property.
3335  *
3336  * @see UProperty
3337  * @stable ICU 2.4
3338  */
3339 U_STABLE UProperty U_EXPORT2
3340 u_getPropertyEnum(const char* alias);
3341
3342 /**
3343  * Return the Unicode name for a given property value, as given in the
3344  * Unicode database file PropertyValueAliases.txt.
3345  *
3346  * Note: Some of the names in PropertyValueAliases.txt can only be
3347  * retrieved using UCHAR_GENERAL_CATEGORY_MASK, not
3348  * UCHAR_GENERAL_CATEGORY.  These include: "C" / "Other", "L" /
3349  * "Letter", "LC" / "Cased_Letter", "M" / "Mark", "N" / "Number", "P"
3350  * / "Punctuation", "S" / "Symbol", and "Z" / "Separator".
3351  *
3352  * @param property UProperty selector constant.
3353  *        Must be UCHAR_BINARY_START<=which<UCHAR_BINARY_LIMIT
3354  *        or UCHAR_INT_START<=which<UCHAR_INT_LIMIT
3355  *        or UCHAR_MASK_START<=which<UCHAR_MASK_LIMIT.
3356  *        If out of range, NULL is returned.
3357  *
3358  * @param value selector for a value for the given property.  If out
3359  *         of range, NULL is returned.  In general, valid values range
3360  *         from 0 up to some maximum.  There are a few exceptions:
3361  *         (1.) UCHAR_BLOCK values begin at the non-zero value
3362  *         UBLOCK_BASIC_LATIN.  (2.)  UCHAR_CANONICAL_COMBINING_CLASS
3363  *         values are not contiguous and range from 0..240.  (3.)
3364  *         UCHAR_GENERAL_CATEGORY_MASK values are not values of
3365  *         UCharCategory, but rather mask values produced by
3366  *         U_GET_GC_MASK().  This allows grouped categories such as
3367  *         [:L:] to be represented.  Mask values range
3368  *         non-contiguously from 1..U_GC_P_MASK.
3369  *
3370  * @param nameChoice selector for which name to get.  If out of range,
3371  *         NULL is returned.  All values have a long name.  Most have
3372  *         a short name, but some do not.  Unicode allows for
3373  *         additional names; if present these will be returned by
3374  *         U_LONG_PROPERTY_NAME + i, where i=1, 2,...
3375
3376  * @return a pointer to the name, or NULL if either the
3377  *         property or the nameChoice is out of range.  If a given
3378  *         nameChoice returns NULL, then all larger values of
3379  *         nameChoice will return NULL, with one exception: if NULL is
3380  *         returned for U_SHORT_PROPERTY_NAME, then
3381  *         U_LONG_PROPERTY_NAME (and higher) may still return a
3382  *         non-NULL value.  The returned pointer is valid until
3383  *         u_cleanup() is called.
3384  *
3385  * @see UProperty
3386  * @see UPropertyNameChoice
3387  * @stable ICU 2.4
3388  */
3389 U_STABLE const char* U_EXPORT2
3390 u_getPropertyValueName(UProperty property,
3391                        int32_t value,
3392                        UPropertyNameChoice nameChoice);
3393
3394 /**
3395  * Return the property value integer for a given value name, as
3396  * specified in the Unicode database file PropertyValueAliases.txt.
3397  * Short, long, and any other variants are recognized.
3398  *
3399  * Note: Some of the names in PropertyValueAliases.txt will only be
3400  * recognized with UCHAR_GENERAL_CATEGORY_MASK, not
3401  * UCHAR_GENERAL_CATEGORY.  These include: "C" / "Other", "L" /
3402  * "Letter", "LC" / "Cased_Letter", "M" / "Mark", "N" / "Number", "P"
3403  * / "Punctuation", "S" / "Symbol", and "Z" / "Separator".
3404  *
3405  * @param property UProperty selector constant.
3406  *        Must be UCHAR_BINARY_START<=which<UCHAR_BINARY_LIMIT
3407  *        or UCHAR_INT_START<=which<UCHAR_INT_LIMIT
3408  *        or UCHAR_MASK_START<=which<UCHAR_MASK_LIMIT.
3409  *        If out of range, UCHAR_INVALID_CODE is returned.
3410  *
3411  * @param alias the value name to be matched.  The name is compared
3412  *         using "loose matching" as described in
3413  *         PropertyValueAliases.txt.
3414  *
3415  * @return a value integer or UCHAR_INVALID_CODE if the given name
3416  *         does not match any value of the given property, or if the
3417  *         property is invalid.  Note: UCHAR_GENERAL_CATEGORY_MASK values
3418  *         are not values of UCharCategory, but rather mask values
3419  *         produced by U_GET_GC_MASK().  This allows grouped
3420  *         categories such as [:L:] to be represented.
3421  *
3422  * @see UProperty
3423  * @stable ICU 2.4
3424  */
3425 U_STABLE int32_t U_EXPORT2
3426 u_getPropertyValueEnum(UProperty property,
3427                        const char* alias);
3428
3429 /**
3430  * Determines if the specified character is permissible as the
3431  * first character in an identifier according to Unicode
3432  * (The Unicode Standard, Version 3.0, chapter 5.16 Identifiers).
3433  * True for characters with general categories "L" (letters) and "Nl" (letter numbers).
3434  *
3435  * Same as java.lang.Character.isUnicodeIdentifierStart().
3436  * Same as UCHAR_ID_START
3437  *
3438  * @param c the code point to be tested
3439  * @return TRUE if the code point may start an identifier
3440  *
3441  * @see UCHAR_ID_START
3442  * @see u_isalpha
3443  * @see u_isIDPart
3444  * @stable ICU 2.0
3445  */
3446 U_STABLE UBool U_EXPORT2
3447 u_isIDStart(UChar32 c);
3448
3449 /**
3450  * Determines if the specified character is permissible
3451  * in an identifier according to Java.
3452  * True for characters with general categories "L" (letters),
3453  * "Nl" (letter numbers), "Nd" (decimal digits),
3454  * "Mc" and "Mn" (combining marks), "Pc" (connecting punctuation), and
3455  * u_isIDIgnorable(c).
3456  *
3457  * Same as java.lang.Character.isUnicodeIdentifierPart().
3458  * Almost the same as Unicode's ID_Continue (UCHAR_ID_CONTINUE)
3459  * except that Unicode recommends to ignore Cf which is less than
3460  * u_isIDIgnorable(c).
3461  *
3462  * @param c the code point to be tested
3463  * @return TRUE if the code point may occur in an identifier according to Java
3464  *
3465  * @see UCHAR_ID_CONTINUE
3466  * @see u_isIDStart
3467  * @see u_isIDIgnorable
3468  * @stable ICU 2.0
3469  */
3470 U_STABLE UBool U_EXPORT2
3471 u_isIDPart(UChar32 c);
3472
3473 /**
3474  * Determines if the specified character should be regarded
3475  * as an ignorable character in an identifier,
3476  * according to Java.
3477  * True for characters with general category "Cf" (format controls) as well as
3478  * non-whitespace ISO controls
3479  * (U+0000..U+0008, U+000E..U+001B, U+007F..U+009F).
3480  *
3481  * Same as java.lang.Character.isIdentifierIgnorable().
3482  *
3483  * Note that Unicode just recommends to ignore Cf (format controls).
3484  *
3485  * @param c the code point to be tested
3486  * @return TRUE if the code point is ignorable in identifiers according to Java
3487  *
3488  * @see UCHAR_DEFAULT_IGNORABLE_CODE_POINT
3489  * @see u_isIDStart
3490  * @see u_isIDPart
3491  * @stable ICU 2.0
3492  */
3493 U_STABLE UBool U_EXPORT2
3494 u_isIDIgnorable(UChar32 c);
3495
3496 /**
3497  * Determines if the specified character is permissible as the
3498  * first character in a Java identifier.
3499  * In addition to u_isIDStart(c), true for characters with
3500  * general categories "Sc" (currency symbols) and "Pc" (connecting punctuation).
3501  *
3502  * Same as java.lang.Character.isJavaIdentifierStart().
3503  *
3504  * @param c the code point to be tested
3505  * @return TRUE if the code point may start a Java identifier
3506  *
3507  * @see     u_isJavaIDPart
3508  * @see     u_isalpha
3509  * @see     u_isIDStart
3510  * @stable ICU 2.0
3511  */
3512 U_STABLE UBool U_EXPORT2
3513 u_isJavaIDStart(UChar32 c);
3514
3515 /**
3516  * Determines if the specified character is permissible
3517  * in a Java identifier.
3518  * In addition to u_isIDPart(c), true for characters with
3519  * general category "Sc" (currency symbols).
3520  *
3521  * Same as java.lang.Character.isJavaIdentifierPart().
3522  *
3523  * @param c the code point to be tested
3524  * @return TRUE if the code point may occur in a Java identifier
3525  *
3526  * @see     u_isIDIgnorable
3527  * @see     u_isJavaIDStart
3528  * @see     u_isalpha
3529  * @see     u_isdigit
3530  * @see     u_isIDPart
3531  * @stable ICU 2.0
3532  */
3533 U_STABLE UBool U_EXPORT2
3534 u_isJavaIDPart(UChar32 c);
3535
3536 /**
3537  * The given character is mapped to its lowercase equivalent according to
3538  * UnicodeData.txt; if the character has no lowercase equivalent, the character
3539  * itself is returned.
3540  *
3541  * Same as java.lang.Character.toLowerCase().
3542  *
3543  * This function only returns the simple, single-code point case mapping.
3544  * Full case mappings should be used whenever possible because they produce
3545  * better results by working on whole strings.
3546  * They take into account the string context and the language and can map
3547  * to a result string with a different length as appropriate.
3548  * Full case mappings are applied by the string case mapping functions,
3549  * see ustring.h and the UnicodeString class.
3550  * See also the User Guide chapter on C/POSIX migration:
3551  * http://icu-project.org/userguide/posix.html#case_mappings
3552  *
3553  * @param c the code point to be mapped
3554  * @return the Simple_Lowercase_Mapping of the code point, if any;
3555  *         otherwise the code point itself.
3556  * @stable ICU 2.0
3557  */
3558 U_STABLE UChar32 U_EXPORT2
3559 u_tolower(UChar32 c);
3560
3561 /**
3562  * The given character is mapped to its uppercase equivalent according to UnicodeData.txt;
3563  * if the character has no uppercase equivalent, the character itself is
3564  * returned.
3565  *
3566  * Same as java.lang.Character.toUpperCase().
3567  *
3568  * This function only returns the simple, single-code point case mapping.
3569  * Full case mappings should be used whenever possible because they produce
3570  * better results by working on whole strings.
3571  * They take into account the string context and the language and can map
3572  * to a result string with a different length as appropriate.
3573  * Full case mappings are applied by the string case mapping functions,
3574  * see ustring.h and the UnicodeString class.
3575  * See also the User Guide chapter on C/POSIX migration:
3576  * http://icu-project.org/userguide/posix.html#case_mappings
3577  *
3578  * @param c the code point to be mapped
3579  * @return the Simple_Uppercase_Mapping of the code point, if any;
3580  *         otherwise the code point itself.
3581  * @stable ICU 2.0
3582  */
3583 U_STABLE UChar32 U_EXPORT2
3584 u_toupper(UChar32 c);
3585
3586 /**
3587  * The given character is mapped to its titlecase equivalent
3588  * according to UnicodeData.txt;
3589  * if none is defined, the character itself is returned.
3590  *
3591  * Same as java.lang.Character.toTitleCase().
3592  *
3593  * This function only returns the simple, single-code point case mapping.
3594  * Full case mappings should be used whenever possible because they produce
3595  * better results by working on whole strings.
3596  * They take into account the string context and the language and can map
3597  * to a result string with a different length as appropriate.
3598  * Full case mappings are applied by the string case mapping functions,
3599  * see ustring.h and the UnicodeString class.
3600  * See also the User Guide chapter on C/POSIX migration:
3601  * http://icu-project.org/userguide/posix.html#case_mappings
3602  *
3603  * @param c the code point to be mapped
3604  * @return the Simple_Titlecase_Mapping of the code point, if any;
3605  *         otherwise the code point itself.
3606  * @stable ICU 2.0
3607  */
3608 U_STABLE UChar32 U_EXPORT2
3609 u_totitle(UChar32 c);
3610
3611 /**
3612  * The given character is mapped to its case folding equivalent according to
3613  * UnicodeData.txt and CaseFolding.txt;
3614  * if the character has no case folding equivalent, the character
3615  * itself is returned.
3616  *
3617  * This function only returns the simple, single-code point case mapping.
3618  * Full case mappings should be used whenever possible because they produce
3619  * better results by working on whole strings.
3620  * They take into account the string context and the language and can map
3621  * to a result string with a different length as appropriate.
3622  * Full case mappings are applied by the string case mapping functions,
3623  * see ustring.h and the UnicodeString class.
3624  * See also the User Guide chapter on C/POSIX migration:
3625  * http://icu-project.org/userguide/posix.html#case_mappings
3626  *
3627  * @param c the code point to be mapped
3628  * @param options Either U_FOLD_CASE_DEFAULT or U_FOLD_CASE_EXCLUDE_SPECIAL_I
3629  * @return the Simple_Case_Folding of the code point, if any;
3630  *         otherwise the code point itself.
3631  * @stable ICU 2.0
3632  */
3633 U_STABLE UChar32 U_EXPORT2
3634 u_foldCase(UChar32 c, uint32_t options);
3635
3636 /**
3637  * Returns the decimal digit value of the code point in the
3638  * specified radix.
3639  *
3640  * If the radix is not in the range <code>2<=radix<=36</code> or if the
3641  * value of <code>c</code> is not a valid digit in the specified
3642  * radix, <code>-1</code> is returned. A character is a valid digit
3643  * if at least one of the following is true:
3644  * <ul>
3645  * <li>The character has a decimal digit value.
3646  *     Such characters have the general category "Nd" (decimal digit numbers)
3647  *     and a Numeric_Type of Decimal.
3648  *     In this case the value is the character's decimal digit value.</li>
3649  * <li>The character is one of the uppercase Latin letters
3650  *     <code>'A'</code> through <code>'Z'</code>.
3651  *     In this case the value is <code>c-'A'+10</code>.</li>
3652  * <li>The character is one of the lowercase Latin letters
3653  *     <code>'a'</code> through <code>'z'</code>.
3654  *     In this case the value is <code>ch-'a'+10</code>.</li>
3655  * <li>Latin letters from both the ASCII range (0061..007A, 0041..005A)
3656  *     as well as from the Fullwidth ASCII range (FF41..FF5A, FF21..FF3A)
3657  *     are recognized.</li>
3658  * </ul>
3659  *
3660  * Same as java.lang.Character.digit().
3661  *
3662  * @param   ch      the code point to be tested.
3663  * @param   radix   the radix.
3664  * @return  the numeric value represented by the character in the
3665  *          specified radix,
3666  *          or -1 if there is no value or if the value exceeds the radix.
3667  *
3668  * @see     UCHAR_NUMERIC_TYPE
3669  * @see     u_forDigit
3670  * @see     u_charDigitValue
3671  * @see     u_isdigit
3672  * @stable ICU 2.0
3673  */
3674 U_STABLE int32_t U_EXPORT2
3675 u_digit(UChar32 ch, int8_t radix);
3676
3677 /**
3678  * Determines the character representation for a specific digit in
3679  * the specified radix. If the value of <code>radix</code> is not a
3680  * valid radix, or the value of <code>digit</code> is not a valid
3681  * digit in the specified radix, the null character
3682  * (<code>U+0000</code>) is returned.
3683  * <p>
3684  * The <code>radix</code> argument is valid if it is greater than or
3685  * equal to 2 and less than or equal to 36.
3686  * The <code>digit</code> argument is valid if
3687  * <code>0 <= digit < radix</code>.
3688  * <p>
3689  * If the digit is less than 10, then
3690  * <code>'0' + digit</code> is returned. Otherwise, the value
3691  * <code>'a' + digit - 10</code> is returned.
3692  *
3693  * Same as java.lang.Character.forDigit().
3694  *
3695  * @param   digit   the number to convert to a character.
3696  * @param   radix   the radix.
3697  * @return  the <code>char</code> representation of the specified digit
3698  *          in the specified radix.
3699  *
3700  * @see     u_digit
3701  * @see     u_charDigitValue
3702  * @see     u_isdigit
3703  * @stable ICU 2.0
3704  */
3705 U_STABLE UChar32 U_EXPORT2
3706 u_forDigit(int32_t digit, int8_t radix);
3707
3708 /**
3709  * Get the "age" of the code point.
3710  * The "age" is the Unicode version when the code point was first
3711  * designated (as a non-character or for Private Use)
3712  * or assigned a character.
3713  * This can be useful to avoid emitting code points to receiving
3714  * processes that do not accept newer characters.
3715  * The data is from the UCD file DerivedAge.txt.
3716  *
3717  * @param c The code point.
3718  * @param versionArray The Unicode version number array, to be filled in.
3719  *
3720  * @stable ICU 2.1
3721  */
3722 U_STABLE void U_EXPORT2
3723 u_charAge(UChar32 c, UVersionInfo versionArray);
3724
3725 /**
3726  * Gets the Unicode version information.
3727  * The version array is filled in with the version information
3728  * for the Unicode standard that is currently used by ICU.
3729  * For example, Unicode version 3.1.1 is represented as an array with
3730  * the values { 3, 1, 1, 0 }.
3731  *
3732  * @param versionArray an output array that will be filled in with
3733  *                     the Unicode version number
3734  * @stable ICU 2.0
3735  */
3736 U_STABLE void U_EXPORT2
3737 u_getUnicodeVersion(UVersionInfo versionArray);
3738
3739 #if !UCONFIG_NO_NORMALIZATION
3740 /**
3741  * Get the FC_NFKC_Closure property string for a character.
3742  * See Unicode Standard Annex #15 for details, search for "FC_NFKC_Closure"
3743  * or for "FNC": http://www.unicode.org/reports/tr15/
3744  *
3745  * @param c The character (code point) for which to get the FC_NFKC_Closure string.
3746  *             It must be <code>0<=c<=0x10ffff</code>.
3747  * @param dest Destination address for copying the string.
3748  *             The string will be zero-terminated if possible.
3749  *             If there is no FC_NFKC_Closure string,
3750  *             then the buffer will be set to the empty string.
3751  * @param destCapacity <code>==sizeof(dest)</code>
3752  * @param pErrorCode Pointer to a UErrorCode variable.
3753  * @return The length of the string, or 0 if there is no FC_NFKC_Closure string for this character.
3754  *         If the destCapacity is less than or equal to the length, then the buffer
3755  *         contains the truncated name and the returned length indicates the full
3756  *         length of the name.
3757  *         The length does not include the zero-termination.
3758  *
3759  * @stable ICU 2.2
3760  */
3761 U_STABLE int32_t U_EXPORT2
3762 u_getFC_NFKC_Closure(UChar32 c, UChar *dest, int32_t destCapacity, UErrorCode *pErrorCode);
3763
3764 #endif
3765
3766
3767 U_CDECL_END
3768
3769 #endif /*_UCHAR*/
3770 /*eof*/