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