w32tex
About: TeX Live provides a comprehensive TeX system including all the major TeX-related programs, macro packages, and fonts that are free software. Windows sources.
  Fossies Dox: w32tex-src.tar.xz  ("unofficial" and yet experimental doxygen-generated source code documentation)  

uchar.h
Go to the documentation of this file.
1 // © 2016 and later: Unicode, Inc. and others.
2 // License & terms of use: http://www.unicode.org/copyright.html
3 /*
4 **********************************************************************
5 * Copyright (C) 1997-2016, International Business Machines
6 * Corporation and others. All Rights Reserved.
7 **********************************************************************
8 *
9 * File UCHAR.H
10 *
11 * Modification History:
12 *
13 * Date Name Description
14 * 04/02/97 aliu Creation.
15 * 03/29/99 helena Updated for C APIs.
16 * 4/15/99 Madhu Updated for C Implementation and Javadoc
17 * 5/20/99 Madhu Added the function u_getVersion()
18 * 8/19/1999 srl Upgraded scripts to Unicode 3.0
19 * 8/27/1999 schererm UCharDirection constants: U_...
20 * 11/11/1999 weiv added u_isalnum(), cleaned comments
21 * 01/11/2000 helena Renamed u_getVersion to u_getUnicodeVersion().
22 ******************************************************************************
23 */
24 
25 #ifndef UCHAR_H
26 #define UCHAR_H
27 
28 #include "unicode/utypes.h"
29 #include "unicode/stringoptions.h"
30 #include "unicode/ucpmap.h"
31 
32 #if !defined(USET_DEFINED) && !defined(U_IN_DOXYGEN)
33 
34 #define USET_DEFINED
35 
36 /**
37  * USet is the C API type corresponding to C++ class UnicodeSet.
38  * It is forward-declared here to avoid including unicode/uset.h file if related
39  * APIs are not used.
40  *
41  * @see ucnv_getUnicodeSet
42  * @stable ICU 2.4
43  */
44 typedef struct USet USet;
45 
46 #endif
47 
48 
50 
51 /*==========================================================================*/
52 /* Unicode version number */
53 /*==========================================================================*/
54 /**
55  * Unicode version number, default for the current ICU version.
56  * The actual Unicode Character Database (UCD) data is stored in uprops.dat
57  * and may be generated from UCD files from a different Unicode version.
58  * Call u_getUnicodeVersion to get the actual Unicode version of the data.
59  *
60  * @see u_getUnicodeVersion
61  * @stable ICU 2.0
62  */
63 #define U_UNICODE_VERSION "13.0"
64 
65 /**
66  * \file
67  * \brief C API: Unicode Properties
68  *
69  * This C API provides low-level access to the Unicode Character Database.
70  * In addition to raw property values, some convenience functions calculate
71  * derived properties, for example for Java-style programming.
72  *
73  * Unicode assigns each code point (not just assigned character) values for
74  * many properties.
75  * Most of them are simple boolean flags, or constants from a small enumerated list.
76  * For some properties, values are strings or other relatively more complex types.
77  *
78  * For more information see
79  * "About the Unicode Character Database" (http://www.unicode.org/ucd/)
80  * and the ICU User Guide chapter on Properties (http://icu-project.org/userguide/properties.html).
81  *
82  * Many properties are accessible via generic functions that take a UProperty selector.
83  * - u_hasBinaryProperty() returns a binary value (true/false) per property and code point.
84  * - u_getIntPropertyValue() returns an integer value per property and code point.
85  * For each supported enumerated or catalog property, there is
86  * an enum type for all of the property's values, and
87  * u_getIntPropertyValue() returns the numeric values of those constants.
88  * - u_getBinaryPropertySet() returns a set for each ICU-supported binary property with
89  * all code points for which the property is true.
90  * - u_getIntPropertyMap() returns a map for each
91  * ICU-supported enumerated/catalog/int-valued property which
92  * maps all Unicode code points to their values for that property.
93  *
94  * Many functions are designed to match java.lang.Character functions.
95  * See the individual function documentation,
96  * and see the JDK 1.4 java.lang.Character documentation
97  * at http://java.sun.com/j2se/1.4/docs/api/java/lang/Character.html
98  *
99  * There are also functions that provide easy migration from C/POSIX functions
100  * like isblank(). Their use is generally discouraged because the C/POSIX
101  * standards do not define their semantics beyond the ASCII range, which means
102  * that different implementations exhibit very different behavior.
103  * Instead, Unicode properties should be used directly.
104  *
105  * There are also only a few, broad C/POSIX character classes, and they tend
106  * to be used for conflicting purposes. For example, the "isalpha()" class
107  * is sometimes used to determine word boundaries, while a more sophisticated
108  * approach would at least distinguish initial letters from continuation
109  * characters (the latter including combining marks).
110  * (In ICU, BreakIterator is the most sophisticated API for word boundaries.)
111  * Another example: There is no "istitle()" class for titlecase characters.
112  *
113  * ICU 3.4 and later provides API access for all twelve C/POSIX character classes.
114  * ICU implements them according to the Standard Recommendations in
115  * Annex C: Compatibility Properties of UTS #18 Unicode Regular Expressions
116  * (http://www.unicode.org/reports/tr18/#Compatibility_Properties).
117  *
118  * API access for C/POSIX character classes is as follows:
119  * - alpha: u_isUAlphabetic(c) or u_hasBinaryProperty(c, UCHAR_ALPHABETIC)
120  * - lower: u_isULowercase(c) or u_hasBinaryProperty(c, UCHAR_LOWERCASE)
121  * - upper: u_isUUppercase(c) or u_hasBinaryProperty(c, UCHAR_UPPERCASE)
122  * - punct: u_ispunct(c)
123  * - digit: u_isdigit(c) or u_charType(c)==U_DECIMAL_DIGIT_NUMBER
124  * - xdigit: u_isxdigit(c) or u_hasBinaryProperty(c, UCHAR_POSIX_XDIGIT)
125  * - alnum: u_hasBinaryProperty(c, UCHAR_POSIX_ALNUM)
126  * - space: u_isUWhiteSpace(c) or u_hasBinaryProperty(c, UCHAR_WHITE_SPACE)
127  * - blank: u_isblank(c) or u_hasBinaryProperty(c, UCHAR_POSIX_BLANK)
128  * - cntrl: u_charType(c)==U_CONTROL_CHAR
129  * - graph: u_hasBinaryProperty(c, UCHAR_POSIX_GRAPH)
130  * - print: u_hasBinaryProperty(c, UCHAR_POSIX_PRINT)
131  *
132  * Note: Some of the u_isxyz() functions in uchar.h predate, and do not match,
133  * the Standard Recommendations in UTS #18. Instead, they match Java
134  * functions according to their API documentation.
135  *
136  * \htmlonly
137  * The C/POSIX character classes are also available in UnicodeSet patterns,
138  * using patterns like [:graph:] or \p{graph}.
139  * \endhtmlonly
140  *
141  * Note: There are several ICU whitespace functions.
142  * Comparison:
143  * - u_isUWhiteSpace=UCHAR_WHITE_SPACE: Unicode White_Space property;
144  * most of general categories "Z" (separators) + most whitespace ISO controls
145  * (including no-break spaces, but excluding IS1..IS4)
146  * - u_isWhitespace: Java isWhitespace; Z + whitespace ISO controls but excluding no-break spaces
147  * - u_isJavaSpaceChar: Java isSpaceChar; just Z (including no-break spaces)
148  * - u_isspace: Z + whitespace ISO controls (including no-break spaces)
149  * - u_isblank: "horizontal spaces" = TAB + Zs
150  */
151 
152 /**
153  * Constants.
154  */
155 
156 /** The lowest Unicode code point value. Code points are non-negative. @stable ICU 2.0 */
157 #define UCHAR_MIN_VALUE 0
158 
159 /**
160  * The highest Unicode code point value (scalar value) according to
161  * The Unicode Standard. This is a 21-bit value (20.1 bits, rounded up).
162  * For a single character, UChar32 is a simple type that can hold any code point value.
163  *
164  * @see UChar32
165  * @stable ICU 2.0
166  */
167 #define UCHAR_MAX_VALUE 0x10ffff
168 
169 /**
170  * Get a single-bit bit set (a flag) from a bit number 0..31.
171  * @stable ICU 2.1
172  */
173 #define U_MASK(x) ((uint32_t)1<<(x))
174 
175 /**
176  * Selection constants for Unicode properties.
177  * These constants are used in functions like u_hasBinaryProperty to select
178  * one of the Unicode properties.
179  *
180  * The properties APIs are intended to reflect Unicode properties as defined
181  * in the Unicode Character Database (UCD) and Unicode Technical Reports (UTR).
182  *
183  * For details about the properties see
184  * UAX #44: Unicode Character Database (http://www.unicode.org/reports/tr44/).
185  *
186  * Important: If ICU is built with UCD files from Unicode versions below, e.g., 3.2,
187  * then properties marked with "new in Unicode 3.2" are not or not fully available.
188  * Check u_getUnicodeVersion to be sure.
189  *
190  * @see u_hasBinaryProperty
191  * @see u_getIntPropertyValue
192  * @see u_getUnicodeVersion
193  * @stable ICU 2.1
194  */
195 typedef enum UProperty {
196  /*
197  * Note: UProperty constants are parsed by preparseucd.py.
198  * It matches lines like
199  * UCHAR_<Unicode property name>=<integer>,
200  */
201 
202  /* Note: Place UCHAR_ALPHABETIC before UCHAR_BINARY_START so that
203  debuggers display UCHAR_ALPHABETIC as the symbolic name for 0,
204  rather than UCHAR_BINARY_START. Likewise for other *_START
205  identifiers. */
206 
207  /** Binary property Alphabetic. Same as u_isUAlphabetic, different from u_isalpha.
208  Lu+Ll+Lt+Lm+Lo+Nl+Other_Alphabetic @stable ICU 2.1 */
210  /** First constant for binary Unicode properties. @stable ICU 2.1 */
212  /** Binary property ASCII_Hex_Digit. 0-9 A-F a-f @stable ICU 2.1 */
214  /** Binary property Bidi_Control.
215  Format controls which have specific functions
216  in the Bidi Algorithm. @stable ICU 2.1 */
218  /** Binary property Bidi_Mirrored.
219  Characters that may change display in RTL text.
220  Same as u_isMirrored.
221  See Bidi Algorithm, UTR 9. @stable ICU 2.1 */
223  /** Binary property Dash. Variations of dashes. @stable ICU 2.1 */
225  /** Binary property Default_Ignorable_Code_Point (new in Unicode 3.2).
226  Ignorable in most processing.
227  <2060..206F, FFF0..FFFB, E0000..E0FFF>+Other_Default_Ignorable_Code_Point+(Cf+Cc+Cs-White_Space) @stable ICU 2.1 */
229  /** Binary property Deprecated (new in Unicode 3.2).
230  The usage of deprecated characters is strongly discouraged. @stable ICU 2.1 */
232  /** Binary property Diacritic. Characters that linguistically modify
233  the meaning of another character to which they apply. @stable ICU 2.1 */
235  /** Binary property Extender.
236  Extend the value or shape of a preceding alphabetic character,
237  e.g., length and iteration marks. @stable ICU 2.1 */
239  /** Binary property Full_Composition_Exclusion.
240  CompositionExclusions.txt+Singleton Decompositions+
241  Non-Starter Decompositions. @stable ICU 2.1 */
243  /** Binary property Grapheme_Base (new in Unicode 3.2).
244  For programmatic determination of grapheme cluster boundaries.
245  [0..10FFFF]-Cc-Cf-Cs-Co-Cn-Zl-Zp-Grapheme_Link-Grapheme_Extend-CGJ @stable ICU 2.1 */
247  /** Binary property Grapheme_Extend (new in Unicode 3.2).
248  For programmatic determination of grapheme cluster boundaries.
249  Me+Mn+Mc+Other_Grapheme_Extend-Grapheme_Link-CGJ @stable ICU 2.1 */
251  /** Binary property Grapheme_Link (new in Unicode 3.2).
252  For programmatic determination of grapheme cluster boundaries. @stable ICU 2.1 */
254  /** Binary property Hex_Digit.
255  Characters commonly used for hexadecimal numbers. @stable ICU 2.1 */
257  /** Binary property Hyphen. Dashes used to mark connections
258  between pieces of words, plus the Katakana middle dot. @stable ICU 2.1 */
260  /** Binary property ID_Continue.
261  Characters that can continue an identifier.
262  DerivedCoreProperties.txt also says "NOTE: Cf characters should be filtered out."
263  ID_Start+Mn+Mc+Nd+Pc @stable ICU 2.1 */
265  /** Binary property ID_Start.
266  Characters that can start an identifier.
267  Lu+Ll+Lt+Lm+Lo+Nl @stable ICU 2.1 */
269  /** Binary property Ideographic.
270  CJKV ideographs. @stable ICU 2.1 */
272  /** Binary property IDS_Binary_Operator (new in Unicode 3.2).
273  For programmatic determination of
274  Ideographic Description Sequences. @stable ICU 2.1 */
276  /** Binary property IDS_Trinary_Operator (new in Unicode 3.2).
277  For programmatic determination of
278  Ideographic Description Sequences. @stable ICU 2.1 */
280  /** Binary property Join_Control.
281  Format controls for cursive joining and ligation. @stable ICU 2.1 */
283  /** Binary property Logical_Order_Exception (new in Unicode 3.2).
284  Characters that do not use logical order and
285  require special handling in most processing. @stable ICU 2.1 */
287  /** Binary property Lowercase. Same as u_isULowercase, different from u_islower.
288  Ll+Other_Lowercase @stable ICU 2.1 */
290  /** Binary property Math. Sm+Other_Math @stable ICU 2.1 */
292  /** Binary property Noncharacter_Code_Point.
293  Code points that are explicitly defined as illegal
294  for the encoding of characters. @stable ICU 2.1 */
296  /** Binary property Quotation_Mark. @stable ICU 2.1 */
298  /** Binary property Radical (new in Unicode 3.2).
299  For programmatic determination of
300  Ideographic Description Sequences. @stable ICU 2.1 */
302  /** Binary property Soft_Dotted (new in Unicode 3.2).
303  Characters with a "soft dot", like i or j.
304  An accent placed on these characters causes
305  the dot to disappear. @stable ICU 2.1 */
307  /** Binary property Terminal_Punctuation.
308  Punctuation characters that generally mark
309  the end of textual units. @stable ICU 2.1 */
311  /** Binary property Unified_Ideograph (new in Unicode 3.2).
312  For programmatic determination of
313  Ideographic Description Sequences. @stable ICU 2.1 */
315  /** Binary property Uppercase. Same as u_isUUppercase, different from u_isupper.
316  Lu+Other_Uppercase @stable ICU 2.1 */
318  /** Binary property White_Space.
319  Same as u_isUWhiteSpace, different from u_isspace and u_isWhitespace.
320  Space characters+TAB+CR+LF-ZWSP-ZWNBSP @stable ICU 2.1 */
322  /** Binary property XID_Continue.
323  ID_Continue modified to allow closure under
324  normalization forms NFKC and NFKD. @stable ICU 2.1 */
326  /** Binary property XID_Start. ID_Start modified to allow
327  closure under normalization forms NFKC and NFKD. @stable ICU 2.1 */
329  /** Binary property Case_Sensitive. Either the source of a case
330  mapping or _in_ the target of a case mapping. Not the same as
331  the general category Cased_Letter. @stable ICU 2.6 */
333  /** Binary property STerm (new in Unicode 4.0.1).
334  Sentence Terminal. Used in UAX #29: Text Boundaries
335  (http://www.unicode.org/reports/tr29/)
336  @stable ICU 3.0 */
338  /** Binary property Variation_Selector (new in Unicode 4.0.1).
339  Indicates all those characters that qualify as Variation Selectors.
340  For details on the behavior of these characters,
341  see StandardizedVariants.html and 15.6 Variation Selectors.
342  @stable ICU 3.0 */
344  /** Binary property NFD_Inert.
345  ICU-specific property for characters that are inert under NFD,
346  i.e., they do not interact with adjacent characters.
347  See the documentation for the Normalizer2 class and the
348  Normalizer2::isInert() method.
349  @stable ICU 3.0 */
351  /** Binary property NFKD_Inert.
352  ICU-specific property for characters that are inert under NFKD,
353  i.e., they do not interact with adjacent characters.
354  See the documentation for the Normalizer2 class and the
355  Normalizer2::isInert() method.
356  @stable ICU 3.0 */
358  /** Binary property NFC_Inert.
359  ICU-specific property for characters that are inert under NFC,
360  i.e., they do not interact with adjacent characters.
361  See the documentation for the Normalizer2 class and the
362  Normalizer2::isInert() method.
363  @stable ICU 3.0 */
365  /** Binary property NFKC_Inert.
366  ICU-specific property for characters that are inert under NFKC,
367  i.e., they do not interact with adjacent characters.
368  See the documentation for the Normalizer2 class and the
369  Normalizer2::isInert() method.
370  @stable ICU 3.0 */
372  /** Binary Property Segment_Starter.
373  ICU-specific property for characters that are starters in terms of
374  Unicode normalization and combining character sequences.
375  They have ccc=0 and do not occur in non-initial position of the
376  canonical decomposition of any character
377  (like a-umlaut in NFD and a Jamo T in an NFD(Hangul LVT)).
378  ICU uses this property for segmenting a string for generating a set of
379  canonically equivalent strings, e.g. for canonical closure while
380  processing collation tailoring rules.
381  @stable ICU 3.0 */
383  /** Binary property Pattern_Syntax (new in Unicode 4.1).
384  See UAX #31 Identifier and Pattern Syntax
385  (http://www.unicode.org/reports/tr31/)
386  @stable ICU 3.4 */
388  /** Binary property Pattern_White_Space (new in Unicode 4.1).
389  See UAX #31 Identifier and Pattern Syntax
390  (http://www.unicode.org/reports/tr31/)
391  @stable ICU 3.4 */
393  /** Binary property alnum (a C/POSIX character class).
394  Implemented according to the UTS #18 Annex C Standard Recommendation.
395  See the uchar.h file documentation.
396  @stable ICU 3.4 */
398  /** Binary property blank (a C/POSIX character class).
399  Implemented according to the UTS #18 Annex C Standard Recommendation.
400  See the uchar.h file documentation.
401  @stable ICU 3.4 */
403  /** Binary property graph (a C/POSIX character class).
404  Implemented according to the UTS #18 Annex C Standard Recommendation.
405  See the uchar.h file documentation.
406  @stable ICU 3.4 */
408  /** Binary property print (a C/POSIX character class).
409  Implemented according to the UTS #18 Annex C Standard Recommendation.
410  See the uchar.h file documentation.
411  @stable ICU 3.4 */
413  /** Binary property xdigit (a C/POSIX character class).
414  Implemented according to the UTS #18 Annex C Standard Recommendation.
415  See the uchar.h file documentation.
416  @stable ICU 3.4 */
418  /** Binary property Cased. For Lowercase, Uppercase and Titlecase characters. @stable ICU 4.4 */
420  /** Binary property Case_Ignorable. Used in context-sensitive case mappings. @stable ICU 4.4 */
422  /** Binary property Changes_When_Lowercased. @stable ICU 4.4 */
424  /** Binary property Changes_When_Uppercased. @stable ICU 4.4 */
426  /** Binary property Changes_When_Titlecased. @stable ICU 4.4 */
428  /** Binary property Changes_When_Casefolded. @stable ICU 4.4 */
430  /** Binary property Changes_When_Casemapped. @stable ICU 4.4 */
432  /** Binary property Changes_When_NFKC_Casefolded. @stable ICU 4.4 */
434  /**
435  * Binary property Emoji.
436  * See http://www.unicode.org/reports/tr51/#Emoji_Properties
437  *
438  * @stable ICU 57
439  */
441  /**
442  * Binary property Emoji_Presentation.
443  * See http://www.unicode.org/reports/tr51/#Emoji_Properties
444  *
445  * @stable ICU 57
446  */
448  /**
449  * Binary property Emoji_Modifier.
450  * See http://www.unicode.org/reports/tr51/#Emoji_Properties
451  *
452  * @stable ICU 57
453  */
455  /**
456  * Binary property Emoji_Modifier_Base.
457  * See http://www.unicode.org/reports/tr51/#Emoji_Properties
458  *
459  * @stable ICU 57
460  */
462  /**
463  * Binary property Emoji_Component.
464  * See http://www.unicode.org/reports/tr51/#Emoji_Properties
465  *
466  * @stable ICU 60
467  */
469  /**
470  * Binary property Regional_Indicator.
471  * @stable ICU 60
472  */
474  /**
475  * Binary property Prepended_Concatenation_Mark.
476  * @stable ICU 60
477  */
479  /**
480  * Binary property Extended_Pictographic.
481  * See http://www.unicode.org/reports/tr51/#Emoji_Properties
482  *
483  * @stable ICU 62
484  */
486 #ifndef U_HIDE_DEPRECATED_API
487  /**
488  * One more than the last constant for binary Unicode properties.
489  * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420.
490  */
492 #endif // U_HIDE_DEPRECATED_API
493 
494  /** Enumerated property Bidi_Class.
495  Same as u_charDirection, returns UCharDirection values. @stable ICU 2.2 */
497  /** First constant for enumerated/integer Unicode properties. @stable ICU 2.2 */
499  /** Enumerated property Block.
500  Same as ublock_getCode, returns UBlockCode values. @stable ICU 2.2 */
501  UCHAR_BLOCK=0x1001,
502  /** Enumerated property Canonical_Combining_Class.
503  Same as u_getCombiningClass, returns 8-bit numeric values. @stable ICU 2.2 */
505  /** Enumerated property Decomposition_Type.
506  Returns UDecompositionType values. @stable ICU 2.2 */
508  /** Enumerated property East_Asian_Width.
509  See http://www.unicode.org/reports/tr11/
510  Returns UEastAsianWidth values. @stable ICU 2.2 */
512  /** Enumerated property General_Category.
513  Same as u_charType, returns UCharCategory values. @stable ICU 2.2 */
515  /** Enumerated property Joining_Group.
516  Returns UJoiningGroup values. @stable ICU 2.2 */
518  /** Enumerated property Joining_Type.
519  Returns UJoiningType values. @stable ICU 2.2 */
521  /** Enumerated property Line_Break.
522  Returns ULineBreak values. @stable ICU 2.2 */
524  /** Enumerated property Numeric_Type.
525  Returns UNumericType values. @stable ICU 2.2 */
527  /** Enumerated property Script.
528  Same as uscript_getScript, returns UScriptCode values. @stable ICU 2.2 */
529  UCHAR_SCRIPT=0x100A,
530  /** Enumerated property Hangul_Syllable_Type, new in Unicode 4.
531  Returns UHangulSyllableType values. @stable ICU 2.6 */
533  /** Enumerated property NFD_Quick_Check.
534  Returns UNormalizationCheckResult values. @stable ICU 3.0 */
536  /** Enumerated property NFKD_Quick_Check.
537  Returns UNormalizationCheckResult values. @stable ICU 3.0 */
539  /** Enumerated property NFC_Quick_Check.
540  Returns UNormalizationCheckResult values. @stable ICU 3.0 */
542  /** Enumerated property NFKC_Quick_Check.
543  Returns UNormalizationCheckResult values. @stable ICU 3.0 */
545  /** Enumerated property Lead_Canonical_Combining_Class.
546  ICU-specific property for the ccc of the first code point
547  of the decomposition, or lccc(c)=ccc(NFD(c)[0]).
548  Useful for checking for canonically ordered text;
549  see UNORM_FCD and http://www.unicode.org/notes/tn5/#FCD .
550  Returns 8-bit numeric values like UCHAR_CANONICAL_COMBINING_CLASS. @stable ICU 3.0 */
552  /** Enumerated property Trail_Canonical_Combining_Class.
553  ICU-specific property for the ccc of the last code point
554  of the decomposition, or tccc(c)=ccc(NFD(c)[last]).
555  Useful for checking for canonically ordered text;
556  see UNORM_FCD and http://www.unicode.org/notes/tn5/#FCD .
557  Returns 8-bit numeric values like UCHAR_CANONICAL_COMBINING_CLASS. @stable ICU 3.0 */
559  /** Enumerated property Grapheme_Cluster_Break (new in Unicode 4.1).
560  Used in UAX #29: Text Boundaries
561  (http://www.unicode.org/reports/tr29/)
562  Returns UGraphemeClusterBreak values. @stable ICU 3.4 */
564  /** Enumerated property Sentence_Break (new in Unicode 4.1).
565  Used in UAX #29: Text Boundaries
566  (http://www.unicode.org/reports/tr29/)
567  Returns USentenceBreak values. @stable ICU 3.4 */
569  /** Enumerated property Word_Break (new in Unicode 4.1).
570  Used in UAX #29: Text Boundaries
571  (http://www.unicode.org/reports/tr29/)
572  Returns UWordBreakValues values. @stable ICU 3.4 */
574  /** Enumerated property Bidi_Paired_Bracket_Type (new in Unicode 6.3).
575  Used in UAX #9: Unicode Bidirectional Algorithm
576  (http://www.unicode.org/reports/tr9/)
577  Returns UBidiPairedBracketType values. @stable ICU 52 */
579  /**
580  * Enumerated property Indic_Positional_Category.
581  * New in Unicode 6.0 as provisional property Indic_Matra_Category;
582  * renamed and changed to informative in Unicode 8.0.
583  * See http://www.unicode.org/reports/tr44/#IndicPositionalCategory.txt
584  * @stable ICU 63
585  */
587  /**
588  * Enumerated property Indic_Syllabic_Category.
589  * New in Unicode 6.0 as provisional; informative since Unicode 8.0.
590  * See http://www.unicode.org/reports/tr44/#IndicSyllabicCategory.txt
591  * @stable ICU 63
592  */
594  /**
595  * Enumerated property Vertical_Orientation.
596  * Used for UAX #50 Unicode Vertical Text Layout (https://www.unicode.org/reports/tr50/).
597  * New as a UCD property in Unicode 10.0.
598  * @stable ICU 63
599  */
601 #ifndef U_HIDE_DEPRECATED_API
602  /**
603  * One more than the last constant for enumerated/integer Unicode properties.
604  * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420.
605  */
607 #endif // U_HIDE_DEPRECATED_API
608 
609  /** Bitmask property General_Category_Mask.
610  This is the General_Category property returned as a bit mask.
611  When used in u_getIntPropertyValue(c), same as U_MASK(u_charType(c)),
612  returns bit masks for UCharCategory values where exactly one bit is set.
613  When used with u_getPropertyValueName() and u_getPropertyValueEnum(),
614  a multi-bit mask is used for sets of categories like "Letters".
615  Mask values should be cast to uint32_t.
616  @stable ICU 2.4 */
618  /** First constant for bit-mask Unicode properties. @stable ICU 2.4 */
620 #ifndef U_HIDE_DEPRECATED_API
621  /**
622  * One more than the last constant for bit-mask Unicode properties.
623  * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420.
624  */
626 #endif // U_HIDE_DEPRECATED_API
627 
628  /** Double property Numeric_Value.
629  Corresponds to u_getNumericValue. @stable ICU 2.4 */
631  /** First constant for double Unicode properties. @stable ICU 2.4 */
633 #ifndef U_HIDE_DEPRECATED_API
634  /**
635  * One more than the last constant for double Unicode properties.
636  * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420.
637  */
639 #endif // U_HIDE_DEPRECATED_API
640 
641  /** String property Age.
642  Corresponds to u_charAge. @stable ICU 2.4 */
643  UCHAR_AGE=0x4000,
644  /** First constant for string Unicode properties. @stable ICU 2.4 */
646  /** String property Bidi_Mirroring_Glyph.
647  Corresponds to u_charMirror. @stable ICU 2.4 */
649  /** String property Case_Folding.
650  Corresponds to u_strFoldCase in ustring.h. @stable ICU 2.4 */
652 #ifndef U_HIDE_DEPRECATED_API
653  /** Deprecated string property ISO_Comment.
654  Corresponds to u_getISOComment. @deprecated ICU 49 */
656 #endif /* U_HIDE_DEPRECATED_API */
657  /** String property Lowercase_Mapping.
658  Corresponds to u_strToLower in ustring.h. @stable ICU 2.4 */
660  /** String property Name.
661  Corresponds to u_charName. @stable ICU 2.4 */
662  UCHAR_NAME=0x4005,
663  /** String property Simple_Case_Folding.
664  Corresponds to u_foldCase. @stable ICU 2.4 */
666  /** String property Simple_Lowercase_Mapping.
667  Corresponds to u_tolower. @stable ICU 2.4 */
669  /** String property Simple_Titlecase_Mapping.
670  Corresponds to u_totitle. @stable ICU 2.4 */
672  /** String property Simple_Uppercase_Mapping.
673  Corresponds to u_toupper. @stable ICU 2.4 */
675  /** String property Titlecase_Mapping.
676  Corresponds to u_strToTitle in ustring.h. @stable ICU 2.4 */
678 #ifndef U_HIDE_DEPRECATED_API
679  /** String property Unicode_1_Name.
680  This property is of little practical value.
681  Beginning with ICU 49, ICU APIs return an empty string for this property.
682  Corresponds to u_charName(U_UNICODE_10_CHAR_NAME). @deprecated ICU 49 */
684 #endif /* U_HIDE_DEPRECATED_API */
685  /** String property Uppercase_Mapping.
686  Corresponds to u_strToUpper in ustring.h. @stable ICU 2.4 */
688  /** String property Bidi_Paired_Bracket (new in Unicode 6.3).
689  Corresponds to u_getBidiPairedBracket. @stable ICU 52 */
691 #ifndef U_HIDE_DEPRECATED_API
692  /**
693  * One more than the last constant for string Unicode properties.
694  * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420.
695  */
697 #endif // U_HIDE_DEPRECATED_API
698 
699  /** Miscellaneous property Script_Extensions (new in Unicode 6.0).
700  Some characters are commonly used in multiple scripts.
701  For more information, see UAX #24: http://www.unicode.org/reports/tr24/.
702  Corresponds to uscript_hasScript and uscript_getScriptExtensions in uscript.h.
703  @stable ICU 4.6 */
705  /** First constant for Unicode properties with unusual value types. @stable ICU 4.6 */
707 #ifndef U_HIDE_DEPRECATED_API
708  /**
709  * One more than the last constant for Unicode properties with unusual value types.
710  * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420.
711  */
713 #endif // U_HIDE_DEPRECATED_API
714 
715  /** Represents a nonexistent or invalid property or property value. @stable ICU 2.4 */
716  UCHAR_INVALID_CODE = -1
718 
719 /**
720  * Data for enumerated Unicode general category types.
721  * See http://www.unicode.org/Public/UNIDATA/UnicodeData.html .
722  * @stable ICU 2.0
723  */
724 typedef enum UCharCategory
725 {
726  /*
727  * Note: UCharCategory constants and their API comments are parsed by preparseucd.py.
728  * It matches pairs of lines like
729  * / ** <Unicode 2-letter General_Category value> comment... * /
730  * U_<[A-Z_]+> = <integer>,
731  */
732 
733  /** Non-category for unassigned and non-character code points. @stable ICU 2.0 */
735  /** Cn "Other, Not Assigned (no characters in [UnicodeData.txt] have this property)" (same as U_UNASSIGNED!) @stable ICU 2.0 */
737  /** Lu @stable ICU 2.0 */
739  /** Ll @stable ICU 2.0 */
741  /** Lt @stable ICU 2.0 */
743  /** Lm @stable ICU 2.0 */
745  /** Lo @stable ICU 2.0 */
747  /** Mn @stable ICU 2.0 */
749  /** Me @stable ICU 2.0 */
751  /** Mc @stable ICU 2.0 */
753  /** Nd @stable ICU 2.0 */
755  /** Nl @stable ICU 2.0 */
757  /** No @stable ICU 2.0 */
759  /** Zs @stable ICU 2.0 */
761  /** Zl @stable ICU 2.0 */
763  /** Zp @stable ICU 2.0 */
765  /** Cc @stable ICU 2.0 */
767  /** Cf @stable ICU 2.0 */
769  /** Co @stable ICU 2.0 */
771  /** Cs @stable ICU 2.0 */
773  /** Pd @stable ICU 2.0 */
775  /** Ps @stable ICU 2.0 */
777  /** Pe @stable ICU 2.0 */
779  /** Pc @stable ICU 2.0 */
781  /** Po @stable ICU 2.0 */
783  /** Sm @stable ICU 2.0 */
785  /** Sc @stable ICU 2.0 */
787  /** Sk @stable ICU 2.0 */
789  /** So @stable ICU 2.0 */
791  /** Pi @stable ICU 2.0 */
793  /** Pf @stable ICU 2.0 */
795  /**
796  * One higher than the last enum UCharCategory constant.
797  * This numeric value is stable (will not change), see
798  * http://www.unicode.org/policies/stability_policy.html#Property_Value
799  *
800  * @stable ICU 2.0
801  */
804 
805 /**
806  * U_GC_XX_MASK constants are bit flags corresponding to Unicode
807  * general category values.
808  * For each category, the nth bit is set if the numeric value of the
809  * corresponding UCharCategory constant is n.
810  *
811  * There are also some U_GC_Y_MASK constants for groups of general categories
812  * like L for all letter categories.
813  *
814  * @see u_charType
815  * @see U_GET_GC_MASK
816  * @see UCharCategory
817  * @stable ICU 2.1
818  */
819 #define U_GC_CN_MASK U_MASK(U_GENERAL_OTHER_TYPES)
820 
821 /** Mask constant for a UCharCategory. @stable ICU 2.1 */
822 #define U_GC_LU_MASK U_MASK(U_UPPERCASE_LETTER)
823 /** Mask constant for a UCharCategory. @stable ICU 2.1 */
824 #define U_GC_LL_MASK U_MASK(U_LOWERCASE_LETTER)
825 /** Mask constant for a UCharCategory. @stable ICU 2.1 */
826 #define U_GC_LT_MASK U_MASK(U_TITLECASE_LETTER)
827 /** Mask constant for a UCharCategory. @stable ICU 2.1 */
828 #define U_GC_LM_MASK U_MASK(U_MODIFIER_LETTER)
829 /** Mask constant for a UCharCategory. @stable ICU 2.1 */
830 #define U_GC_LO_MASK U_MASK(U_OTHER_LETTER)
831 
832 /** Mask constant for a UCharCategory. @stable ICU 2.1 */
833 #define U_GC_MN_MASK U_MASK(U_NON_SPACING_MARK)
834 /** Mask constant for a UCharCategory. @stable ICU 2.1 */
835 #define U_GC_ME_MASK U_MASK(U_ENCLOSING_MARK)
836 /** Mask constant for a UCharCategory. @stable ICU 2.1 */
837 #define U_GC_MC_MASK U_MASK(U_COMBINING_SPACING_MARK)
838 
839 /** Mask constant for a UCharCategory. @stable ICU 2.1 */
840 #define U_GC_ND_MASK U_MASK(U_DECIMAL_DIGIT_NUMBER)
841 /** Mask constant for a UCharCategory. @stable ICU 2.1 */
842 #define U_GC_NL_MASK U_MASK(U_LETTER_NUMBER)
843 /** Mask constant for a UCharCategory. @stable ICU 2.1 */
844 #define U_GC_NO_MASK U_MASK(U_OTHER_NUMBER)
845 
846 /** Mask constant for a UCharCategory. @stable ICU 2.1 */
847 #define U_GC_ZS_MASK U_MASK(U_SPACE_SEPARATOR)
848 /** Mask constant for a UCharCategory. @stable ICU 2.1 */
849 #define U_GC_ZL_MASK U_MASK(U_LINE_SEPARATOR)
850 /** Mask constant for a UCharCategory. @stable ICU 2.1 */
851 #define U_GC_ZP_MASK U_MASK(U_PARAGRAPH_SEPARATOR)
852 
853 /** Mask constant for a UCharCategory. @stable ICU 2.1 */
854 #define U_GC_CC_MASK U_MASK(U_CONTROL_CHAR)
855 /** Mask constant for a UCharCategory. @stable ICU 2.1 */
856 #define U_GC_CF_MASK U_MASK(U_FORMAT_CHAR)
857 /** Mask constant for a UCharCategory. @stable ICU 2.1 */
858 #define U_GC_CO_MASK U_MASK(U_PRIVATE_USE_CHAR)
859 /** Mask constant for a UCharCategory. @stable ICU 2.1 */
860 #define U_GC_CS_MASK U_MASK(U_SURROGATE)
861 
862 /** Mask constant for a UCharCategory. @stable ICU 2.1 */
863 #define U_GC_PD_MASK U_MASK(U_DASH_PUNCTUATION)
864 /** Mask constant for a UCharCategory. @stable ICU 2.1 */
865 #define U_GC_PS_MASK U_MASK(U_START_PUNCTUATION)
866 /** Mask constant for a UCharCategory. @stable ICU 2.1 */
867 #define U_GC_PE_MASK U_MASK(U_END_PUNCTUATION)
868 /** Mask constant for a UCharCategory. @stable ICU 2.1 */
869 #define U_GC_PC_MASK U_MASK(U_CONNECTOR_PUNCTUATION)
870 /** Mask constant for a UCharCategory. @stable ICU 2.1 */
871 #define U_GC_PO_MASK U_MASK(U_OTHER_PUNCTUATION)
872 
873 /** Mask constant for a UCharCategory. @stable ICU 2.1 */
874 #define U_GC_SM_MASK U_MASK(U_MATH_SYMBOL)
875 /** Mask constant for a UCharCategory. @stable ICU 2.1 */
876 #define U_GC_SC_MASK U_MASK(U_CURRENCY_SYMBOL)
877 /** Mask constant for a UCharCategory. @stable ICU 2.1 */
878 #define U_GC_SK_MASK U_MASK(U_MODIFIER_SYMBOL)
879 /** Mask constant for a UCharCategory. @stable ICU 2.1 */
880 #define U_GC_SO_MASK U_MASK(U_OTHER_SYMBOL)
881 
882 /** Mask constant for a UCharCategory. @stable ICU 2.1 */
883 #define U_GC_PI_MASK U_MASK(U_INITIAL_PUNCTUATION)
884 /** Mask constant for a UCharCategory. @stable ICU 2.1 */
885 #define U_GC_PF_MASK U_MASK(U_FINAL_PUNCTUATION)
886 
887 
888 /** Mask constant for multiple UCharCategory bits (L Letters). @stable ICU 2.1 */
889 #define U_GC_L_MASK \
890  (U_GC_LU_MASK|U_GC_LL_MASK|U_GC_LT_MASK|U_GC_LM_MASK|U_GC_LO_MASK)
891 
892 /** Mask constant for multiple UCharCategory bits (LC Cased Letters). @stable ICU 2.1 */
893 #define U_GC_LC_MASK \
894  (U_GC_LU_MASK|U_GC_LL_MASK|U_GC_LT_MASK)
895 
896 /** Mask constant for multiple UCharCategory bits (M Marks). @stable ICU 2.1 */
897 #define U_GC_M_MASK (U_GC_MN_MASK|U_GC_ME_MASK|U_GC_MC_MASK)
898 
899 /** Mask constant for multiple UCharCategory bits (N Numbers). @stable ICU 2.1 */
900 #define U_GC_N_MASK (U_GC_ND_MASK|U_GC_NL_MASK|U_GC_NO_MASK)
901 
902 /** Mask constant for multiple UCharCategory bits (Z Separators). @stable ICU 2.1 */
903 #define U_GC_Z_MASK (U_GC_ZS_MASK|U_GC_ZL_MASK|U_GC_ZP_MASK)
904 
905 /** Mask constant for multiple UCharCategory bits (C Others). @stable ICU 2.1 */
906 #define U_GC_C_MASK \
907  (U_GC_CN_MASK|U_GC_CC_MASK|U_GC_CF_MASK|U_GC_CO_MASK|U_GC_CS_MASK)
908 
909 /** Mask constant for multiple UCharCategory bits (P Punctuation). @stable ICU 2.1 */
910 #define U_GC_P_MASK \
911  (U_GC_PD_MASK|U_GC_PS_MASK|U_GC_PE_MASK|U_GC_PC_MASK|U_GC_PO_MASK| \
912  U_GC_PI_MASK|U_GC_PF_MASK)
913 
914 /** Mask constant for multiple UCharCategory bits (S Symbols). @stable ICU 2.1 */
915 #define U_GC_S_MASK (U_GC_SM_MASK|U_GC_SC_MASK|U_GC_SK_MASK|U_GC_SO_MASK)
916 
917 /**
918  * This specifies the language directional property of a character set.
919  * @stable ICU 2.0
920  */
921 typedef enum UCharDirection {
922  /*
923  * Note: UCharDirection constants and their API comments are parsed by preparseucd.py.
924  * It matches pairs of lines like
925  * / ** <Unicode 1..3-letter Bidi_Class value> comment... * /
926  * U_<[A-Z_]+> = <integer>,
927  */
928 
929  /** L @stable ICU 2.0 */
931  /** R @stable ICU 2.0 */
933  /** EN @stable ICU 2.0 */
935  /** ES @stable ICU 2.0 */
937  /** ET @stable ICU 2.0 */
939  /** AN @stable ICU 2.0 */
941  /** CS @stable ICU 2.0 */
943  /** B @stable ICU 2.0 */
945  /** S @stable ICU 2.0 */
947  /** WS @stable ICU 2.0 */
949  /** ON @stable ICU 2.0 */
951  /** LRE @stable ICU 2.0 */
953  /** LRO @stable ICU 2.0 */
955  /** AL @stable ICU 2.0 */
957  /** RLE @stable ICU 2.0 */
959  /** RLO @stable ICU 2.0 */
961  /** PDF @stable ICU 2.0 */
963  /** NSM @stable ICU 2.0 */
965  /** BN @stable ICU 2.0 */
967  /** FSI @stable ICU 52 */
969  /** LRI @stable ICU 52 */
971  /** RLI @stable ICU 52 */
973  /** PDI @stable ICU 52 */
975 #ifndef U_HIDE_DEPRECATED_API
976  /**
977  * One more than the highest UCharDirection value.
978  * The highest value is available via u_getIntPropertyMaxValue(UCHAR_BIDI_CLASS).
979  *
980  * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420.
981  */
983 #endif // U_HIDE_DEPRECATED_API
985 
986 /**
987  * Bidi Paired Bracket Type constants.
988  *
989  * @see UCHAR_BIDI_PAIRED_BRACKET_TYPE
990  * @stable ICU 52
991  */
993  /*
994  * Note: UBidiPairedBracketType constants are parsed by preparseucd.py.
995  * It matches lines like
996  * U_BPT_<Unicode Bidi_Paired_Bracket_Type value name>
997  */
998 
999  /** Not a paired bracket. @stable ICU 52 */
1001  /** Open paired bracket. @stable ICU 52 */
1003  /** Close paired bracket. @stable ICU 52 */
1005 #ifndef U_HIDE_DEPRECATED_API
1006  /**
1007  * One more than the highest normal UBidiPairedBracketType value.
1008  * The highest value is available via u_getIntPropertyMaxValue(UCHAR_BIDI_PAIRED_BRACKET_TYPE).
1009  *
1010  * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420.
1011  */
1012  U_BPT_COUNT /* 3 */
1013 #endif // U_HIDE_DEPRECATED_API
1015 
1016 /**
1017  * Constants for Unicode blocks, see the Unicode Data file Blocks.txt
1018  * @stable ICU 2.0
1019  */
1021  /*
1022  * Note: UBlockCode constants are parsed by preparseucd.py.
1023  * It matches lines like
1024  * UBLOCK_<Unicode Block value name> = <integer>,
1025  */
1026 
1027  /** New No_Block value in Unicode 4. @stable ICU 2.6 */
1028  UBLOCK_NO_BLOCK = 0, /*[none]*/ /* Special range indicating No_Block */
1029 
1030  /** @stable ICU 2.0 */
1031  UBLOCK_BASIC_LATIN = 1, /*[0000]*/
1032 
1033  /** @stable ICU 2.0 */
1035 
1036  /** @stable ICU 2.0 */
1038 
1039  /** @stable ICU 2.0 */
1041 
1042  /** @stable ICU 2.0 */
1043  UBLOCK_IPA_EXTENSIONS =5, /*[0250]*/
1044 
1045  /** @stable ICU 2.0 */
1047 
1048  /** @stable ICU 2.0 */
1050 
1051  /**
1052  * Unicode 3.2 renames this block to "Greek and Coptic".
1053  * @stable ICU 2.0
1054  */
1055  UBLOCK_GREEK =8, /*[0370]*/
1056 
1057  /** @stable ICU 2.0 */
1058  UBLOCK_CYRILLIC =9, /*[0400]*/
1059 
1060  /** @stable ICU 2.0 */
1061  UBLOCK_ARMENIAN =10, /*[0530]*/
1062 
1063  /** @stable ICU 2.0 */
1064  UBLOCK_HEBREW =11, /*[0590]*/
1065 
1066  /** @stable ICU 2.0 */
1067  UBLOCK_ARABIC =12, /*[0600]*/
1068 
1069  /** @stable ICU 2.0 */
1070  UBLOCK_SYRIAC =13, /*[0700]*/
1071 
1072  /** @stable ICU 2.0 */
1073  UBLOCK_THAANA =14, /*[0780]*/
1074 
1075  /** @stable ICU 2.0 */
1076  UBLOCK_DEVANAGARI =15, /*[0900]*/
1077 
1078  /** @stable ICU 2.0 */
1079  UBLOCK_BENGALI =16, /*[0980]*/
1080 
1081  /** @stable ICU 2.0 */
1082  UBLOCK_GURMUKHI =17, /*[0A00]*/
1083 
1084  /** @stable ICU 2.0 */
1085  UBLOCK_GUJARATI =18, /*[0A80]*/
1086 
1087  /** @stable ICU 2.0 */
1088  UBLOCK_ORIYA =19, /*[0B00]*/
1089 
1090  /** @stable ICU 2.0 */
1091  UBLOCK_TAMIL =20, /*[0B80]*/
1092 
1093  /** @stable ICU 2.0 */
1094  UBLOCK_TELUGU =21, /*[0C00]*/
1095 
1096  /** @stable ICU 2.0 */
1097  UBLOCK_KANNADA =22, /*[0C80]*/
1098 
1099  /** @stable ICU 2.0 */
1100  UBLOCK_MALAYALAM =23, /*[0D00]*/
1101 
1102  /** @stable ICU 2.0 */
1103  UBLOCK_SINHALA =24, /*[0D80]*/
1104 
1105  /** @stable ICU 2.0 */
1106  UBLOCK_THAI =25, /*[0E00]*/
1107 
1108  /** @stable ICU 2.0 */
1109  UBLOCK_LAO =26, /*[0E80]*/
1110 
1111  /** @stable ICU 2.0 */
1112  UBLOCK_TIBETAN =27, /*[0F00]*/
1113 
1114  /** @stable ICU 2.0 */
1115  UBLOCK_MYANMAR =28, /*[1000]*/
1116 
1117  /** @stable ICU 2.0 */
1118  UBLOCK_GEORGIAN =29, /*[10A0]*/
1119 
1120  /** @stable ICU 2.0 */
1121  UBLOCK_HANGUL_JAMO =30, /*[1100]*/
1122 
1123  /** @stable ICU 2.0 */
1124  UBLOCK_ETHIOPIC =31, /*[1200]*/
1125 
1126  /** @stable ICU 2.0 */
1127  UBLOCK_CHEROKEE =32, /*[13A0]*/
1128 
1129  /** @stable ICU 2.0 */
1131 
1132  /** @stable ICU 2.0 */
1133  UBLOCK_OGHAM =34, /*[1680]*/
1134 
1135  /** @stable ICU 2.0 */
1136  UBLOCK_RUNIC =35, /*[16A0]*/
1137 
1138  /** @stable ICU 2.0 */
1139  UBLOCK_KHMER =36, /*[1780]*/
1140 
1141  /** @stable ICU 2.0 */
1142  UBLOCK_MONGOLIAN =37, /*[1800]*/
1143 
1144  /** @stable ICU 2.0 */
1146 
1147  /** @stable ICU 2.0 */
1148  UBLOCK_GREEK_EXTENDED =39, /*[1F00]*/
1149 
1150  /** @stable ICU 2.0 */
1152 
1153  /** @stable ICU 2.0 */
1155 
1156  /** @stable ICU 2.0 */
1157  UBLOCK_CURRENCY_SYMBOLS =42, /*[20A0]*/
1158 
1159  /**
1160  * Unicode 3.2 renames this block to "Combining Diacritical Marks for Symbols".
1161  * @stable ICU 2.0
1162  */
1164 
1165  /** @stable ICU 2.0 */
1167 
1168  /** @stable ICU 2.0 */
1169  UBLOCK_NUMBER_FORMS =45, /*[2150]*/
1170 
1171  /** @stable ICU 2.0 */
1172  UBLOCK_ARROWS =46, /*[2190]*/
1173 
1174  /** @stable ICU 2.0 */
1176 
1177  /** @stable ICU 2.0 */
1179 
1180  /** @stable ICU 2.0 */
1181  UBLOCK_CONTROL_PICTURES =49, /*[2400]*/
1182 
1183  /** @stable ICU 2.0 */
1185 
1186  /** @stable ICU 2.0 */
1188 
1189  /** @stable ICU 2.0 */
1190  UBLOCK_BOX_DRAWING =52, /*[2500]*/
1191 
1192  /** @stable ICU 2.0 */
1193  UBLOCK_BLOCK_ELEMENTS =53, /*[2580]*/
1194 
1195  /** @stable ICU 2.0 */
1196  UBLOCK_GEOMETRIC_SHAPES =54, /*[25A0]*/
1197 
1198  /** @stable ICU 2.0 */
1200 
1201  /** @stable ICU 2.0 */
1202  UBLOCK_DINGBATS =56, /*[2700]*/
1203 
1204  /** @stable ICU 2.0 */
1205  UBLOCK_BRAILLE_PATTERNS =57, /*[2800]*/
1206 
1207  /** @stable ICU 2.0 */
1209 
1210  /** @stable ICU 2.0 */
1211  UBLOCK_KANGXI_RADICALS =59, /*[2F00]*/
1212 
1213  /** @stable ICU 2.0 */
1215 
1216  /** @stable ICU 2.0 */
1218 
1219  /** @stable ICU 2.0 */
1220  UBLOCK_HIRAGANA =62, /*[3040]*/
1221 
1222  /** @stable ICU 2.0 */
1223  UBLOCK_KATAKANA =63, /*[30A0]*/
1224 
1225  /** @stable ICU 2.0 */
1226  UBLOCK_BOPOMOFO =64, /*[3100]*/
1227 
1228  /** @stable ICU 2.0 */
1230 
1231  /** @stable ICU 2.0 */
1232  UBLOCK_KANBUN =66, /*[3190]*/
1233 
1234  /** @stable ICU 2.0 */
1236 
1237  /** @stable ICU 2.0 */
1239 
1240  /** @stable ICU 2.0 */
1242 
1243  /** @stable ICU 2.0 */
1245 
1246  /** @stable ICU 2.0 */
1248 
1249  /** @stable ICU 2.0 */
1250  UBLOCK_YI_SYLLABLES =72, /*[A000]*/
1251 
1252  /** @stable ICU 2.0 */
1253  UBLOCK_YI_RADICALS =73, /*[A490]*/
1254 
1255  /** @stable ICU 2.0 */
1256  UBLOCK_HANGUL_SYLLABLES =74, /*[AC00]*/
1257 
1258  /** @stable ICU 2.0 */
1259  UBLOCK_HIGH_SURROGATES =75, /*[D800]*/
1260 
1261  /** @stable ICU 2.0 */
1263 
1264  /** @stable ICU 2.0 */
1265  UBLOCK_LOW_SURROGATES =77, /*[DC00]*/
1266 
1267  /**
1268  * Same as UBLOCK_PRIVATE_USE.
1269  * Until Unicode 3.1.1, the corresponding block name was "Private Use",
1270  * and multiple code point ranges had this block.
1271  * Unicode 3.2 renames the block for the BMP PUA to "Private Use Area" and
1272  * adds separate blocks for the supplementary PUAs.
1273  *
1274  * @stable ICU 2.0
1275  */
1276  UBLOCK_PRIVATE_USE_AREA =78, /*[E000]*/
1277  /**
1278  * Same as UBLOCK_PRIVATE_USE_AREA.
1279  * Until Unicode 3.1.1, the corresponding block name was "Private Use",
1280  * and multiple code point ranges had this block.
1281  * Unicode 3.2 renames the block for the BMP PUA to "Private Use Area" and
1282  * adds separate blocks for the supplementary PUAs.
1283  *
1284  * @stable ICU 2.0
1285  */
1287 
1288  /** @stable ICU 2.0 */
1290 
1291  /** @stable ICU 2.0 */
1293 
1294  /** @stable ICU 2.0 */
1296 
1297  /** @stable ICU 2.0 */
1299 
1300  /** @stable ICU 2.0 */
1302 
1303  /** @stable ICU 2.0 */
1305 
1306  /** @stable ICU 2.0 */
1308 
1309  /** @stable ICU 2.0 */
1310  UBLOCK_SPECIALS =86, /*[FFF0]*/
1311 
1312  /** @stable ICU 2.0 */
1314 
1315  /* New blocks in Unicode 3.1 */
1316 
1317  /** @stable ICU 2.0 */
1318  UBLOCK_OLD_ITALIC = 88, /*[10300]*/
1319  /** @stable ICU 2.0 */
1320  UBLOCK_GOTHIC = 89, /*[10330]*/
1321  /** @stable ICU 2.0 */
1322  UBLOCK_DESERET = 90, /*[10400]*/
1323  /** @stable ICU 2.0 */
1325  /** @stable ICU 2.0 */
1326  UBLOCK_MUSICAL_SYMBOLS = 92, /*[1D100]*/
1327  /** @stable ICU 2.0 */
1329  /** @stable ICU 2.0 */
1331  /** @stable ICU 2.0 */
1333  /** @stable ICU 2.0 */
1334  UBLOCK_TAGS = 96, /*[E0000]*/
1335 
1336  /* New blocks in Unicode 3.2 */
1337 
1338  /** @stable ICU 3.0 */
1340  /**
1341  * Unicode 4.0.1 renames the "Cyrillic Supplementary" block to "Cyrillic Supplement".
1342  * @stable ICU 2.2
1343  */
1345  /** @stable ICU 2.2 */
1346  UBLOCK_TAGALOG = 98, /*[1700]*/
1347  /** @stable ICU 2.2 */
1348  UBLOCK_HANUNOO = 99, /*[1720]*/
1349  /** @stable ICU 2.2 */
1350  UBLOCK_BUHID = 100, /*[1740]*/
1351  /** @stable ICU 2.2 */
1352  UBLOCK_TAGBANWA = 101, /*[1760]*/
1353  /** @stable ICU 2.2 */
1355  /** @stable ICU 2.2 */
1357  /** @stable ICU 2.2 */
1359  /** @stable ICU 2.2 */
1361  /** @stable ICU 2.2 */
1363  /** @stable ICU 2.2 */
1365  /** @stable ICU 2.2 */
1366  UBLOCK_VARIATION_SELECTORS = 108, /*[FE00]*/
1367  /** @stable ICU 2.2 */
1369  /** @stable ICU 2.2 */
1371 
1372  /* New blocks in Unicode 4 */
1373 
1374  /** @stable ICU 2.6 */
1375  UBLOCK_LIMBU = 111, /*[1900]*/
1376  /** @stable ICU 2.6 */
1377  UBLOCK_TAI_LE = 112, /*[1950]*/
1378  /** @stable ICU 2.6 */
1379  UBLOCK_KHMER_SYMBOLS = 113, /*[19E0]*/
1380  /** @stable ICU 2.6 */
1381  UBLOCK_PHONETIC_EXTENSIONS = 114, /*[1D00]*/
1382  /** @stable ICU 2.6 */
1384  /** @stable ICU 2.6 */
1386  /** @stable ICU 2.6 */
1387  UBLOCK_LINEAR_B_SYLLABARY = 117, /*[10000]*/
1388  /** @stable ICU 2.6 */
1389  UBLOCK_LINEAR_B_IDEOGRAMS = 118, /*[10080]*/
1390  /** @stable ICU 2.6 */
1391  UBLOCK_AEGEAN_NUMBERS = 119, /*[10100]*/
1392  /** @stable ICU 2.6 */
1393  UBLOCK_UGARITIC = 120, /*[10380]*/
1394  /** @stable ICU 2.6 */
1395  UBLOCK_SHAVIAN = 121, /*[10450]*/
1396  /** @stable ICU 2.6 */
1397  UBLOCK_OSMANYA = 122, /*[10480]*/
1398  /** @stable ICU 2.6 */
1399  UBLOCK_CYPRIOT_SYLLABARY = 123, /*[10800]*/
1400  /** @stable ICU 2.6 */
1401  UBLOCK_TAI_XUAN_JING_SYMBOLS = 124, /*[1D300]*/
1402  /** @stable ICU 2.6 */
1404 
1405  /* New blocks in Unicode 4.1 */
1406 
1407  /** @stable ICU 3.4 */
1409  /** @stable ICU 3.4 */
1410  UBLOCK_ANCIENT_GREEK_NUMBERS = 127, /*[10140]*/
1411  /** @stable ICU 3.4 */
1412  UBLOCK_ARABIC_SUPPLEMENT = 128, /*[0750]*/
1413  /** @stable ICU 3.4 */
1414  UBLOCK_BUGINESE = 129, /*[1A00]*/
1415  /** @stable ICU 3.4 */
1416  UBLOCK_CJK_STROKES = 130, /*[31C0]*/
1417  /** @stable ICU 3.4 */
1419  /** @stable ICU 3.4 */
1420  UBLOCK_COPTIC = 132, /*[2C80]*/
1421  /** @stable ICU 3.4 */
1422  UBLOCK_ETHIOPIC_EXTENDED = 133, /*[2D80]*/
1423  /** @stable ICU 3.4 */
1424  UBLOCK_ETHIOPIC_SUPPLEMENT = 134, /*[1380]*/
1425  /** @stable ICU 3.4 */
1426  UBLOCK_GEORGIAN_SUPPLEMENT = 135, /*[2D00]*/
1427  /** @stable ICU 3.4 */
1428  UBLOCK_GLAGOLITIC = 136, /*[2C00]*/
1429  /** @stable ICU 3.4 */
1430  UBLOCK_KHAROSHTHI = 137, /*[10A00]*/
1431  /** @stable ICU 3.4 */
1433  /** @stable ICU 3.4 */
1434  UBLOCK_NEW_TAI_LUE = 139, /*[1980]*/
1435  /** @stable ICU 3.4 */
1436  UBLOCK_OLD_PERSIAN = 140, /*[103A0]*/
1437  /** @stable ICU 3.4 */
1439  /** @stable ICU 3.4 */
1441  /** @stable ICU 3.4 */
1442  UBLOCK_SYLOTI_NAGRI = 143, /*[A800]*/
1443  /** @stable ICU 3.4 */
1444  UBLOCK_TIFINAGH = 144, /*[2D30]*/
1445  /** @stable ICU 3.4 */
1446  UBLOCK_VERTICAL_FORMS = 145, /*[FE10]*/
1447 
1448  /* New blocks in Unicode 5.0 */
1449 
1450  /** @stable ICU 3.6 */
1451  UBLOCK_NKO = 146, /*[07C0]*/
1452  /** @stable ICU 3.6 */
1453  UBLOCK_BALINESE = 147, /*[1B00]*/
1454  /** @stable ICU 3.6 */
1455  UBLOCK_LATIN_EXTENDED_C = 148, /*[2C60]*/
1456  /** @stable ICU 3.6 */
1457  UBLOCK_LATIN_EXTENDED_D = 149, /*[A720]*/
1458  /** @stable ICU 3.6 */
1459  UBLOCK_PHAGS_PA = 150, /*[A840]*/
1460  /** @stable ICU 3.6 */
1461  UBLOCK_PHOENICIAN = 151, /*[10900]*/
1462  /** @stable ICU 3.6 */
1463  UBLOCK_CUNEIFORM = 152, /*[12000]*/
1464  /** @stable ICU 3.6 */
1466  /** @stable ICU 3.6 */
1467  UBLOCK_COUNTING_ROD_NUMERALS = 154, /*[1D360]*/
1468 
1469  /* New blocks in Unicode 5.1 */
1470 
1471  /** @stable ICU 4.0 */
1472  UBLOCK_SUNDANESE = 155, /*[1B80]*/
1473  /** @stable ICU 4.0 */
1474  UBLOCK_LEPCHA = 156, /*[1C00]*/
1475  /** @stable ICU 4.0 */
1476  UBLOCK_OL_CHIKI = 157, /*[1C50]*/
1477  /** @stable ICU 4.0 */
1478  UBLOCK_CYRILLIC_EXTENDED_A = 158, /*[2DE0]*/
1479  /** @stable ICU 4.0 */
1480  UBLOCK_VAI = 159, /*[A500]*/
1481  /** @stable ICU 4.0 */
1482  UBLOCK_CYRILLIC_EXTENDED_B = 160, /*[A640]*/
1483  /** @stable ICU 4.0 */
1484  UBLOCK_SAURASHTRA = 161, /*[A880]*/
1485  /** @stable ICU 4.0 */
1486  UBLOCK_KAYAH_LI = 162, /*[A900]*/
1487  /** @stable ICU 4.0 */
1488  UBLOCK_REJANG = 163, /*[A930]*/
1489  /** @stable ICU 4.0 */
1490  UBLOCK_CHAM = 164, /*[AA00]*/
1491  /** @stable ICU 4.0 */
1492  UBLOCK_ANCIENT_SYMBOLS = 165, /*[10190]*/
1493  /** @stable ICU 4.0 */
1494  UBLOCK_PHAISTOS_DISC = 166, /*[101D0]*/
1495  /** @stable ICU 4.0 */
1496  UBLOCK_LYCIAN = 167, /*[10280]*/
1497  /** @stable ICU 4.0 */
1498  UBLOCK_CARIAN = 168, /*[102A0]*/
1499  /** @stable ICU 4.0 */
1500  UBLOCK_LYDIAN = 169, /*[10920]*/
1501  /** @stable ICU 4.0 */
1502  UBLOCK_MAHJONG_TILES = 170, /*[1F000]*/
1503  /** @stable ICU 4.0 */
1504  UBLOCK_DOMINO_TILES = 171, /*[1F030]*/
1505 
1506  /* New blocks in Unicode 5.2 */
1507 
1508  /** @stable ICU 4.4 */
1509  UBLOCK_SAMARITAN = 172, /*[0800]*/
1510  /** @stable ICU 4.4 */
1512  /** @stable ICU 4.4 */
1513  UBLOCK_TAI_THAM = 174, /*[1A20]*/
1514  /** @stable ICU 4.4 */
1515  UBLOCK_VEDIC_EXTENSIONS = 175, /*[1CD0]*/
1516  /** @stable ICU 4.4 */
1517  UBLOCK_LISU = 176, /*[A4D0]*/
1518  /** @stable ICU 4.4 */
1519  UBLOCK_BAMUM = 177, /*[A6A0]*/
1520  /** @stable ICU 4.4 */
1522  /** @stable ICU 4.4 */
1523  UBLOCK_DEVANAGARI_EXTENDED = 179, /*[A8E0]*/
1524  /** @stable ICU 4.4 */
1526  /** @stable ICU 4.4 */
1527  UBLOCK_JAVANESE = 181, /*[A980]*/
1528  /** @stable ICU 4.4 */
1529  UBLOCK_MYANMAR_EXTENDED_A = 182, /*[AA60]*/
1530  /** @stable ICU 4.4 */
1531  UBLOCK_TAI_VIET = 183, /*[AA80]*/
1532  /** @stable ICU 4.4 */
1533  UBLOCK_MEETEI_MAYEK = 184, /*[ABC0]*/
1534  /** @stable ICU 4.4 */
1536  /** @stable ICU 4.4 */
1537  UBLOCK_IMPERIAL_ARAMAIC = 186, /*[10840]*/
1538  /** @stable ICU 4.4 */
1539  UBLOCK_OLD_SOUTH_ARABIAN = 187, /*[10A60]*/
1540  /** @stable ICU 4.4 */
1541  UBLOCK_AVESTAN = 188, /*[10B00]*/
1542  /** @stable ICU 4.4 */
1544  /** @stable ICU 4.4 */
1545  UBLOCK_INSCRIPTIONAL_PAHLAVI = 190, /*[10B60]*/
1546  /** @stable ICU 4.4 */
1547  UBLOCK_OLD_TURKIC = 191, /*[10C00]*/
1548  /** @stable ICU 4.4 */
1549  UBLOCK_RUMI_NUMERAL_SYMBOLS = 192, /*[10E60]*/
1550  /** @stable ICU 4.4 */
1551  UBLOCK_KAITHI = 193, /*[11080]*/
1552  /** @stable ICU 4.4 */
1553  UBLOCK_EGYPTIAN_HIEROGLYPHS = 194, /*[13000]*/
1554  /** @stable ICU 4.4 */
1556  /** @stable ICU 4.4 */
1558  /** @stable ICU 4.4 */
1560 
1561  /* New blocks in Unicode 6.0 */
1562 
1563  /** @stable ICU 4.6 */
1564  UBLOCK_MANDAIC = 198, /*[0840]*/
1565  /** @stable ICU 4.6 */
1566  UBLOCK_BATAK = 199, /*[1BC0]*/
1567  /** @stable ICU 4.6 */
1568  UBLOCK_ETHIOPIC_EXTENDED_A = 200, /*[AB00]*/
1569  /** @stable ICU 4.6 */
1570  UBLOCK_BRAHMI = 201, /*[11000]*/
1571  /** @stable ICU 4.6 */
1572  UBLOCK_BAMUM_SUPPLEMENT = 202, /*[16800]*/
1573  /** @stable ICU 4.6 */
1574  UBLOCK_KANA_SUPPLEMENT = 203, /*[1B000]*/
1575  /** @stable ICU 4.6 */
1576  UBLOCK_PLAYING_CARDS = 204, /*[1F0A0]*/
1577  /** @stable ICU 4.6 */
1579  /** @stable ICU 4.6 */
1580  UBLOCK_EMOTICONS = 206, /*[1F600]*/
1581  /** @stable ICU 4.6 */
1583  /** @stable ICU 4.6 */
1584  UBLOCK_ALCHEMICAL_SYMBOLS = 208, /*[1F700]*/
1585  /** @stable ICU 4.6 */
1587 
1588  /* New blocks in Unicode 6.1 */
1589 
1590  /** @stable ICU 49 */
1591  UBLOCK_ARABIC_EXTENDED_A = 210, /*[08A0]*/
1592  /** @stable ICU 49 */
1594  /** @stable ICU 49 */
1595  UBLOCK_CHAKMA = 212, /*[11100]*/
1596  /** @stable ICU 49 */
1598  /** @stable ICU 49 */
1599  UBLOCK_MEROITIC_CURSIVE = 214, /*[109A0]*/
1600  /** @stable ICU 49 */
1601  UBLOCK_MEROITIC_HIEROGLYPHS = 215, /*[10980]*/
1602  /** @stable ICU 49 */
1603  UBLOCK_MIAO = 216, /*[16F00]*/
1604  /** @stable ICU 49 */
1605  UBLOCK_SHARADA = 217, /*[11180]*/
1606  /** @stable ICU 49 */
1607  UBLOCK_SORA_SOMPENG = 218, /*[110D0]*/
1608  /** @stable ICU 49 */
1610  /** @stable ICU 49 */
1611  UBLOCK_TAKRI = 220, /*[11680]*/
1612 
1613  /* New blocks in Unicode 7.0 */
1614 
1615  /** @stable ICU 54 */
1616  UBLOCK_BASSA_VAH = 221, /*[16AD0]*/
1617  /** @stable ICU 54 */
1618  UBLOCK_CAUCASIAN_ALBANIAN = 222, /*[10530]*/
1619  /** @stable ICU 54 */
1620  UBLOCK_COPTIC_EPACT_NUMBERS = 223, /*[102E0]*/
1621  /** @stable ICU 54 */
1623  /** @stable ICU 54 */
1624  UBLOCK_DUPLOYAN = 225, /*[1BC00]*/
1625  /** @stable ICU 54 */
1626  UBLOCK_ELBASAN = 226, /*[10500]*/
1627  /** @stable ICU 54 */
1629  /** @stable ICU 54 */
1630  UBLOCK_GRANTHA = 228, /*[11300]*/
1631  /** @stable ICU 54 */
1632  UBLOCK_KHOJKI = 229, /*[11200]*/
1633  /** @stable ICU 54 */
1634  UBLOCK_KHUDAWADI = 230, /*[112B0]*/
1635  /** @stable ICU 54 */
1636  UBLOCK_LATIN_EXTENDED_E = 231, /*[AB30]*/
1637  /** @stable ICU 54 */
1638  UBLOCK_LINEAR_A = 232, /*[10600]*/
1639  /** @stable ICU 54 */
1640  UBLOCK_MAHAJANI = 233, /*[11150]*/
1641  /** @stable ICU 54 */
1642  UBLOCK_MANICHAEAN = 234, /*[10AC0]*/
1643  /** @stable ICU 54 */
1644  UBLOCK_MENDE_KIKAKUI = 235, /*[1E800]*/
1645  /** @stable ICU 54 */
1646  UBLOCK_MODI = 236, /*[11600]*/
1647  /** @stable ICU 54 */
1648  UBLOCK_MRO = 237, /*[16A40]*/
1649  /** @stable ICU 54 */
1650  UBLOCK_MYANMAR_EXTENDED_B = 238, /*[A9E0]*/
1651  /** @stable ICU 54 */
1652  UBLOCK_NABATAEAN = 239, /*[10880]*/
1653  /** @stable ICU 54 */
1654  UBLOCK_OLD_NORTH_ARABIAN = 240, /*[10A80]*/
1655  /** @stable ICU 54 */
1656  UBLOCK_OLD_PERMIC = 241, /*[10350]*/
1657  /** @stable ICU 54 */
1658  UBLOCK_ORNAMENTAL_DINGBATS = 242, /*[1F650]*/
1659  /** @stable ICU 54 */
1660  UBLOCK_PAHAWH_HMONG = 243, /*[16B00]*/
1661  /** @stable ICU 54 */
1662  UBLOCK_PALMYRENE = 244, /*[10860]*/
1663  /** @stable ICU 54 */
1664  UBLOCK_PAU_CIN_HAU = 245, /*[11AC0]*/
1665  /** @stable ICU 54 */
1666  UBLOCK_PSALTER_PAHLAVI = 246, /*[10B80]*/
1667  /** @stable ICU 54 */
1669  /** @stable ICU 54 */
1670  UBLOCK_SIDDHAM = 248, /*[11580]*/
1671  /** @stable ICU 54 */
1673  /** @stable ICU 54 */
1674  UBLOCK_SUPPLEMENTAL_ARROWS_C = 250, /*[1F800]*/
1675  /** @stable ICU 54 */
1676  UBLOCK_TIRHUTA = 251, /*[11480]*/
1677  /** @stable ICU 54 */
1678  UBLOCK_WARANG_CITI = 252, /*[118A0]*/
1679 
1680  /* New blocks in Unicode 8.0 */
1681 
1682  /** @stable ICU 56 */
1683  UBLOCK_AHOM = 253, /*[11700]*/
1684  /** @stable ICU 56 */
1685  UBLOCK_ANATOLIAN_HIEROGLYPHS = 254, /*[14400]*/
1686  /** @stable ICU 56 */
1687  UBLOCK_CHEROKEE_SUPPLEMENT = 255, /*[AB70]*/
1688  /** @stable ICU 56 */
1690  /** @stable ICU 56 */
1692  /** @stable ICU 56 */
1693  UBLOCK_HATRAN = 258, /*[108E0]*/
1694  /** @stable ICU 56 */
1695  UBLOCK_MULTANI = 259, /*[11280]*/
1696  /** @stable ICU 56 */
1697  UBLOCK_OLD_HUNGARIAN = 260, /*[10C80]*/
1698  /** @stable ICU 56 */
1700  /** @stable ICU 56 */
1701  UBLOCK_SUTTON_SIGNWRITING = 262, /*[1D800]*/
1702 
1703  /* New blocks in Unicode 9.0 */
1704 
1705  /** @stable ICU 58 */
1706  UBLOCK_ADLAM = 263, /*[1E900]*/
1707  /** @stable ICU 58 */
1708  UBLOCK_BHAIKSUKI = 264, /*[11C00]*/
1709  /** @stable ICU 58 */
1710  UBLOCK_CYRILLIC_EXTENDED_C = 265, /*[1C80]*/
1711  /** @stable ICU 58 */
1712  UBLOCK_GLAGOLITIC_SUPPLEMENT = 266, /*[1E000]*/
1713  /** @stable ICU 58 */
1715  /** @stable ICU 58 */
1716  UBLOCK_MARCHEN = 268, /*[11C70]*/
1717  /** @stable ICU 58 */
1718  UBLOCK_MONGOLIAN_SUPPLEMENT = 269, /*[11660]*/
1719  /** @stable ICU 58 */
1720  UBLOCK_NEWA = 270, /*[11400]*/
1721  /** @stable ICU 58 */
1722  UBLOCK_OSAGE = 271, /*[104B0]*/
1723  /** @stable ICU 58 */
1724  UBLOCK_TANGUT = 272, /*[17000]*/
1725  /** @stable ICU 58 */
1726  UBLOCK_TANGUT_COMPONENTS = 273, /*[18800]*/
1727 
1728  // New blocks in Unicode 10.0
1729 
1730  /** @stable ICU 60 */
1732  /** @stable ICU 60 */
1733  UBLOCK_KANA_EXTENDED_A = 275, /*[1B100]*/
1734  /** @stable ICU 60 */
1735  UBLOCK_MASARAM_GONDI = 276, /*[11D00]*/
1736  /** @stable ICU 60 */
1737  UBLOCK_NUSHU = 277, /*[1B170]*/
1738  /** @stable ICU 60 */
1739  UBLOCK_SOYOMBO = 278, /*[11A50]*/
1740  /** @stable ICU 60 */
1741  UBLOCK_SYRIAC_SUPPLEMENT = 279, /*[0860]*/
1742  /** @stable ICU 60 */
1743  UBLOCK_ZANABAZAR_SQUARE = 280, /*[11A00]*/
1744 
1745  // New blocks in Unicode 11.0
1746 
1747  /** @stable ICU 62 */
1748  UBLOCK_CHESS_SYMBOLS = 281, /*[1FA00]*/
1749  /** @stable ICU 62 */
1750  UBLOCK_DOGRA = 282, /*[11800]*/
1751  /** @stable ICU 62 */
1752  UBLOCK_GEORGIAN_EXTENDED = 283, /*[1C90]*/
1753  /** @stable ICU 62 */
1754  UBLOCK_GUNJALA_GONDI = 284, /*[11D60]*/
1755  /** @stable ICU 62 */
1756  UBLOCK_HANIFI_ROHINGYA = 285, /*[10D00]*/
1757  /** @stable ICU 62 */
1758  UBLOCK_INDIC_SIYAQ_NUMBERS = 286, /*[1EC70]*/
1759  /** @stable ICU 62 */
1760  UBLOCK_MAKASAR = 287, /*[11EE0]*/
1761  /** @stable ICU 62 */
1762  UBLOCK_MAYAN_NUMERALS = 288, /*[1D2E0]*/
1763  /** @stable ICU 62 */
1764  UBLOCK_MEDEFAIDRIN = 289, /*[16E40]*/
1765  /** @stable ICU 62 */
1766  UBLOCK_OLD_SOGDIAN = 290, /*[10F00]*/
1767  /** @stable ICU 62 */
1768  UBLOCK_SOGDIAN = 291, /*[10F30]*/
1769 
1770  // New blocks in Unicode 12.0
1771 
1772  /** @stable ICU 64 */
1774  /** @stable ICU 64 */
1775  UBLOCK_ELYMAIC = 293, /*[10FE0]*/
1776  /** @stable ICU 64 */
1777  UBLOCK_NANDINAGARI = 294, /*[119A0]*/
1778  /** @stable ICU 64 */
1780  /** @stable ICU 64 */
1781  UBLOCK_OTTOMAN_SIYAQ_NUMBERS = 296, /*[1ED00]*/
1782  /** @stable ICU 64 */
1783  UBLOCK_SMALL_KANA_EXTENSION = 297, /*[1B130]*/
1784  /** @stable ICU 64 */
1786  /** @stable ICU 64 */
1787  UBLOCK_TAMIL_SUPPLEMENT = 299, /*[11FC0]*/
1788  /** @stable ICU 64 */
1789  UBLOCK_WANCHO = 300, /*[1E2C0]*/
1790 
1791  // New blocks in Unicode 13.0
1792 
1793  /** @stable ICU 66 */
1794  UBLOCK_CHORASMIAN = 301, /*[10FB0]*/
1795  /** @stable ICU 66 */
1797  /** @stable ICU 66 */
1798  UBLOCK_DIVES_AKURU = 303, /*[11900]*/
1799  /** @stable ICU 66 */
1800  UBLOCK_KHITAN_SMALL_SCRIPT = 304, /*[18B00]*/
1801  /** @stable ICU 66 */
1802  UBLOCK_LISU_SUPPLEMENT = 305, /*[11FB0]*/
1803  /** @stable ICU 66 */
1805  /** @stable ICU 66 */
1806  UBLOCK_TANGUT_SUPPLEMENT = 307, /*[18D00]*/
1807  /** @stable ICU 66 */
1808  UBLOCK_YEZIDI = 308, /*[10E80]*/
1809 
1810 #ifndef U_HIDE_DEPRECATED_API
1811  /**
1812  * One more than the highest normal UBlockCode value.
1813  * The highest value is available via u_getIntPropertyMaxValue(UCHAR_BLOCK).
1814  *
1815  * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420.
1816  */
1818 #endif // U_HIDE_DEPRECATED_API
1819 
1820  /** @stable ICU 2.0 */
1822 };
1823 
1824 /** @stable ICU 2.0 */
1825 typedef enum UBlockCode UBlockCode;
1826 
1827 /**
1828  * East Asian Width constants.
1829  *
1830  * @see UCHAR_EAST_ASIAN_WIDTH
1831  * @see u_getIntPropertyValue
1832  * @stable ICU 2.2
1833  */
1834 typedef enum UEastAsianWidth {
1835  /*
1836  * Note: UEastAsianWidth constants are parsed by preparseucd.py.
1837  * It matches lines like
1838  * U_EA_<Unicode East_Asian_Width value name>
1839  */
1840 
1841  U_EA_NEUTRAL, /*[N]*/
1845  U_EA_NARROW, /*[Na]*/
1846  U_EA_WIDE, /*[W]*/
1847 #ifndef U_HIDE_DEPRECATED_API
1848  /**
1849  * One more than the highest normal UEastAsianWidth value.
1850  * The highest value is available via u_getIntPropertyMaxValue(UCHAR_EAST_ASIAN_WIDTH).
1851  *
1852  * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420.
1853  */
1854  U_EA_COUNT
1855 #endif // U_HIDE_DEPRECATED_API
1857 
1858 /**
1859  * Selector constants for u_charName().
1860  * u_charName() returns the "modern" name of a
1861  * Unicode character; or the name that was defined in
1862  * Unicode version 1.0, before the Unicode standard merged
1863  * with ISO-10646; or an "extended" name that gives each
1864  * Unicode code point a unique name.
1865  *
1866  * @see u_charName
1867  * @stable ICU 2.0
1868  */
1869 typedef enum UCharNameChoice {
1870  /** Unicode character name (Name property). @stable ICU 2.0 */
1872 #ifndef U_HIDE_DEPRECATED_API
1873  /**
1874  * The Unicode_1_Name property value which is of little practical value.
1875  * Beginning with ICU 49, ICU APIs return an empty string for this name choice.
1876  * @deprecated ICU 49
1877  */
1879 #endif /* U_HIDE_DEPRECATED_API */
1880  /** Standard or synthetic character name. @stable ICU 2.0 */
1882  /** Corrected name from NameAliases.txt. @stable ICU 4.4 */
1884 #ifndef U_HIDE_DEPRECATED_API
1885  /**
1886  * One more than the highest normal UCharNameChoice value.
1887  * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420.
1888  */
1890 #endif // U_HIDE_DEPRECATED_API
1892 
1893 /**
1894  * Selector constants for u_getPropertyName() and
1895  * u_getPropertyValueName(). These selectors are used to choose which
1896  * name is returned for a given property or value. All properties and
1897  * values have a long name. Most have a short name, but some do not.
1898  * Unicode allows for additional names, beyond the long and short
1899  * name, which would be indicated by U_LONG_PROPERTY_NAME + i, where
1900  * i=1, 2,...
1901  *
1902  * @see u_getPropertyName()
1903  * @see u_getPropertyValueName()
1904  * @stable ICU 2.4
1905  */
1906 typedef enum UPropertyNameChoice {
1909 #ifndef U_HIDE_DEPRECATED_API
1910  /**
1911  * One more than the highest normal UPropertyNameChoice value.
1912  * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420.
1913  */
1915 #endif // U_HIDE_DEPRECATED_API
1917 
1918 /**
1919  * Decomposition Type constants.
1920  *
1921  * @see UCHAR_DECOMPOSITION_TYPE
1922  * @stable ICU 2.2
1923  */
1924 typedef enum UDecompositionType {
1925  /*
1926  * Note: UDecompositionType constants are parsed by preparseucd.py.
1927  * It matches lines like
1928  * U_DT_<Unicode Decomposition_Type value name>
1929  */
1930 
1931  U_DT_NONE, /*[none]*/
1932  U_DT_CANONICAL, /*[can]*/
1933  U_DT_COMPAT, /*[com]*/
1934  U_DT_CIRCLE, /*[enc]*/
1935  U_DT_FINAL, /*[fin]*/
1936  U_DT_FONT, /*[font]*/
1937  U_DT_FRACTION, /*[fra]*/
1938  U_DT_INITIAL, /*[init]*/
1939  U_DT_ISOLATED, /*[iso]*/
1940  U_DT_MEDIAL, /*[med]*/
1941  U_DT_NARROW, /*[nar]*/
1942  U_DT_NOBREAK, /*[nb]*/
1943  U_DT_SMALL, /*[sml]*/
1944  U_DT_SQUARE, /*[sqr]*/
1945  U_DT_SUB, /*[sub]*/
1946  U_DT_SUPER, /*[sup]*/
1947  U_DT_VERTICAL, /*[vert]*/
1948  U_DT_WIDE, /*[wide]*/
1949 #ifndef U_HIDE_DEPRECATED_API
1950  /**
1951  * One more than the highest normal UDecompositionType value.
1952  * The highest value is available via u_getIntPropertyMaxValue(UCHAR_DECOMPOSITION_TYPE).
1953  *
1954  * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420.
1955  */
1956  U_DT_COUNT /* 18 */
1957 #endif // U_HIDE_DEPRECATED_API
1959 
1960 /**
1961  * Joining Type constants.
1962  *
1963  * @see UCHAR_JOINING_TYPE
1964  * @stable ICU 2.2
1965  */
1966 typedef enum UJoiningType {
1967  /*
1968  * Note: UJoiningType constants are parsed by preparseucd.py.
1969  * It matches lines like
1970  * U_JT_<Unicode Joining_Type value name>
1971  */
1972 
1979 #ifndef U_HIDE_DEPRECATED_API
1980  /**
1981  * One more than the highest normal UJoiningType value.
1982  * The highest value is available via u_getIntPropertyMaxValue(UCHAR_JOINING_TYPE).
1983  *
1984  * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420.
1985  */
1986  U_JT_COUNT /* 6 */
1987 #endif // U_HIDE_DEPRECATED_API
1989 
1990 /**
1991  * Joining Group constants.
1992  *
1993  * @see UCHAR_JOINING_GROUP
1994  * @stable ICU 2.2
1995  */
1996 typedef enum UJoiningGroup {
1997  /*
1998  * Note: UJoiningGroup constants are parsed by preparseucd.py.
1999  * It matches lines like
2000  * U_JG_<Unicode Joining_Group value name>
2001  */
2002 
2017  U_JG_TEH_MARBUTA_GOAL, /**< @stable ICU 4.6 */
2055  U_JG_FE, /**< @stable ICU 2.6 */
2056  U_JG_KHAPH, /**< @stable ICU 2.6 */
2057  U_JG_ZHAIN, /**< @stable ICU 2.6 */
2058  U_JG_BURUSHASKI_YEH_BARREE, /**< @stable ICU 4.0 */
2059  U_JG_FARSI_YEH, /**< @stable ICU 4.4 */
2060  U_JG_NYA, /**< @stable ICU 4.4 */
2061  U_JG_ROHINGYA_YEH, /**< @stable ICU 49 */
2062  U_JG_MANICHAEAN_ALEPH, /**< @stable ICU 54 */
2063  U_JG_MANICHAEAN_AYIN, /**< @stable ICU 54 */
2064  U_JG_MANICHAEAN_BETH, /**< @stable ICU 54 */
2065  U_JG_MANICHAEAN_DALETH, /**< @stable ICU 54 */
2066  U_JG_MANICHAEAN_DHAMEDH, /**< @stable ICU 54 */
2067  U_JG_MANICHAEAN_FIVE, /**< @stable ICU 54 */
2068  U_JG_MANICHAEAN_GIMEL, /**< @stable ICU 54 */
2069  U_JG_MANICHAEAN_HETH, /**< @stable ICU 54 */
2070  U_JG_MANICHAEAN_HUNDRED, /**< @stable ICU 54 */
2071  U_JG_MANICHAEAN_KAPH, /**< @stable ICU 54 */
2072  U_JG_MANICHAEAN_LAMEDH, /**< @stable ICU 54 */
2073  U_JG_MANICHAEAN_MEM, /**< @stable ICU 54 */
2074  U_JG_MANICHAEAN_NUN, /**< @stable ICU 54 */
2075  U_JG_MANICHAEAN_ONE, /**< @stable ICU 54 */
2076  U_JG_MANICHAEAN_PE, /**< @stable ICU 54 */
2077  U_JG_MANICHAEAN_QOPH, /**< @stable ICU 54 */
2078  U_JG_MANICHAEAN_RESH, /**< @stable ICU 54 */
2079  U_JG_MANICHAEAN_SADHE, /**< @stable ICU 54 */
2080  U_JG_MANICHAEAN_SAMEKH, /**< @stable ICU 54 */
2081  U_JG_MANICHAEAN_TAW, /**< @stable ICU 54 */
2082  U_JG_MANICHAEAN_TEN, /**< @stable ICU 54 */
2083  U_JG_MANICHAEAN_TETH, /**< @stable ICU 54 */
2084  U_JG_MANICHAEAN_THAMEDH, /**< @stable ICU 54 */
2085  U_JG_MANICHAEAN_TWENTY, /**< @stable ICU 54 */
2086  U_JG_MANICHAEAN_WAW, /**< @stable ICU 54 */
2087  U_JG_MANICHAEAN_YODH, /**< @stable ICU 54 */
2088  U_JG_MANICHAEAN_ZAYIN, /**< @stable ICU 54 */
2089  U_JG_STRAIGHT_WAW, /**< @stable ICU 54 */
2090  U_JG_AFRICAN_FEH, /**< @stable ICU 58 */
2091  U_JG_AFRICAN_NOON, /**< @stable ICU 58 */
2092  U_JG_AFRICAN_QAF, /**< @stable ICU 58 */
2093 
2094  U_JG_MALAYALAM_BHA, /**< @stable ICU 60 */
2095  U_JG_MALAYALAM_JA, /**< @stable ICU 60 */
2096  U_JG_MALAYALAM_LLA, /**< @stable ICU 60 */
2097  U_JG_MALAYALAM_LLLA, /**< @stable ICU 60 */
2098  U_JG_MALAYALAM_NGA, /**< @stable ICU 60 */
2099  U_JG_MALAYALAM_NNA, /**< @stable ICU 60 */
2100  U_JG_MALAYALAM_NNNA, /**< @stable ICU 60 */
2101  U_JG_MALAYALAM_NYA, /**< @stable ICU 60 */
2102  U_JG_MALAYALAM_RA, /**< @stable ICU 60 */
2103  U_JG_MALAYALAM_SSA, /**< @stable ICU 60 */
2104  U_JG_MALAYALAM_TTA, /**< @stable ICU 60 */
2105 
2106  U_JG_HANIFI_ROHINGYA_KINNA_YA, /**< @stable ICU 62 */
2107  U_JG_HANIFI_ROHINGYA_PA, /**< @stable ICU 62 */
2108 
2109 #ifndef U_HIDE_DEPRECATED_API
2110  /**
2111  * One more than the highest normal UJoiningGroup value.
2112  * The highest value is available via u_getIntPropertyMaxValue(UCHAR_JOINING_GROUP).
2113  *
2114  * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420.
2115  */
2116  U_JG_COUNT
2117 #endif // U_HIDE_DEPRECATED_API
2119 
2120 /**
2121  * Grapheme Cluster Break constants.
2122  *
2123  * @see UCHAR_GRAPHEME_CLUSTER_BREAK
2124  * @stable ICU 3.4
2125  */
2127  /*
2128  * Note: UGraphemeClusterBreak constants are parsed by preparseucd.py.
2129  * It matches lines like
2130  * U_GCB_<Unicode Grapheme_Cluster_Break value name>
2131  */
2132 
2133  U_GCB_OTHER = 0, /*[XX]*/
2134  U_GCB_CONTROL = 1, /*[CN]*/
2135  U_GCB_CR = 2, /*[CR]*/
2136  U_GCB_EXTEND = 3, /*[EX]*/
2137  U_GCB_L = 4, /*[L]*/
2138  U_GCB_LF = 5, /*[LF]*/
2139  U_GCB_LV = 6, /*[LV]*/
2140  U_GCB_LVT = 7, /*[LVT]*/
2141  U_GCB_T = 8, /*[T]*/
2142  U_GCB_V = 9, /*[V]*/
2143  /** @stable ICU 4.0 */
2144  U_GCB_SPACING_MARK = 10, /*[SM]*/ /* from here on: new in Unicode 5.1/ICU 4.0 */
2145  /** @stable ICU 4.0 */
2146  U_GCB_PREPEND = 11, /*[PP]*/
2147  /** @stable ICU 50 */
2148  U_GCB_REGIONAL_INDICATOR = 12, /*[RI]*/ /* new in Unicode 6.2/ICU 50 */
2149  /** @stable ICU 58 */
2150  U_GCB_E_BASE = 13, /*[EB]*/ /* from here on: new in Unicode 9.0/ICU 58 */
2151  /** @stable ICU 58 */
2152  U_GCB_E_BASE_GAZ = 14, /*[EBG]*/
2153  /** @stable ICU 58 */
2154  U_GCB_E_MODIFIER = 15, /*[EM]*/
2155  /** @stable ICU 58 */
2156  U_GCB_GLUE_AFTER_ZWJ = 16, /*[GAZ]*/
2157  /** @stable ICU 58 */
2158  U_GCB_ZWJ = 17, /*[ZWJ]*/
2159 
2160 #ifndef U_HIDE_DEPRECATED_API
2161  /**
2162  * One more than the highest normal UGraphemeClusterBreak value.
2163  * The highest value is available via u_getIntPropertyMaxValue(UCHAR_GRAPHEME_CLUSTER_BREAK).
2164  *
2165  * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420.
2166  */
2167  U_GCB_COUNT = 18
2168 #endif // U_HIDE_DEPRECATED_API
2170 
2171 /**
2172  * Word Break constants.
2173  * (UWordBreak is a pre-existing enum type in ubrk.h for word break status tags.)
2174  *
2175  * @see UCHAR_WORD_BREAK
2176  * @stable ICU 3.4
2177  */
2178 typedef enum UWordBreakValues {
2179  /*
2180  * Note: UWordBreakValues constants are parsed by preparseucd.py.
2181  * It matches lines like
2182  * U_WB_<Unicode Word_Break value name>
2183  */
2184 
2185  U_WB_OTHER = 0, /*[XX]*/
2186  U_WB_ALETTER = 1, /*[LE]*/
2187  U_WB_FORMAT = 2, /*[FO]*/
2188  U_WB_KATAKANA = 3, /*[KA]*/
2189  U_WB_MIDLETTER = 4, /*[ML]*/
2190  U_WB_MIDNUM = 5, /*[MN]*/
2191  U_WB_NUMERIC = 6, /*[NU]*/
2192  U_WB_EXTENDNUMLET = 7, /*[EX]*/
2193  /** @stable ICU 4.0 */
2194  U_WB_CR = 8, /*[CR]*/ /* from here on: new in Unicode 5.1/ICU 4.0 */
2195  /** @stable ICU 4.0 */
2196  U_WB_EXTEND = 9, /*[Extend]*/
2197  /** @stable ICU 4.0 */
2198  U_WB_LF = 10, /*[LF]*/
2199  /** @stable ICU 4.0 */
2200  U_WB_MIDNUMLET =11, /*[MB]*/
2201  /** @stable ICU 4.0 */
2202  U_WB_NEWLINE =12, /*[NL]*/
2203  /** @stable ICU 50 */
2204  U_WB_REGIONAL_INDICATOR = 13, /*[RI]*/ /* new in Unicode 6.2/ICU 50 */
2205  /** @stable ICU 52 */
2206  U_WB_HEBREW_LETTER = 14, /*[HL]*/ /* from here on: new in Unicode 6.3/ICU 52 */
2207  /** @stable ICU 52 */
2208  U_WB_SINGLE_QUOTE = 15, /*[SQ]*/
2209  /** @stable ICU 52 */
2210  U_WB_DOUBLE_QUOTE = 16, /*[DQ]*/
2211  /** @stable ICU 58 */
2212  U_WB_E_BASE = 17, /*[EB]*/ /* from here on: new in Unicode 9.0/ICU 58 */
2213  /** @stable ICU 58 */
2214  U_WB_E_BASE_GAZ = 18, /*[EBG]*/
2215  /** @stable ICU 58 */
2216  U_WB_E_MODIFIER = 19, /*[EM]*/
2217  /** @stable ICU 58 */
2218  U_WB_GLUE_AFTER_ZWJ = 20, /*[GAZ]*/
2219  /** @stable ICU 58 */
2220  U_WB_ZWJ = 21, /*[ZWJ]*/
2221  /** @stable ICU 62 */
2222  U_WB_WSEGSPACE = 22, /*[WSEGSPACE]*/
2223 
2224 #ifndef U_HIDE_DEPRECATED_API
2225  /**
2226  * One more than the highest normal UWordBreakValues value.
2227  * The highest value is available via u_getIntPropertyMaxValue(UCHAR_WORD_BREAK).
2228  *
2229  * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420.
2230  */
2231  U_WB_COUNT = 23
2232 #endif // U_HIDE_DEPRECATED_API
2234 
2235 /**
2236  * Sentence Break constants.
2237  *
2238  * @see UCHAR_SENTENCE_BREAK
2239  * @stable ICU 3.4
2240  */
2241 typedef enum USentenceBreak {
2242  /*
2243  * Note: USentenceBreak constants are parsed by preparseucd.py.
2244  * It matches lines like
2245  * U_SB_<Unicode Sentence_Break value name>
2246  */
2247 
2248  U_SB_OTHER = 0, /*[XX]*/
2249  U_SB_ATERM = 1, /*[AT]*/
2250  U_SB_CLOSE = 2, /*[CL]*/
2251  U_SB_FORMAT = 3, /*[FO]*/
2252  U_SB_LOWER = 4, /*[LO]*/
2253  U_SB_NUMERIC = 5, /*[NU]*/
2254  U_SB_OLETTER = 6, /*[LE]*/
2255  U_SB_SEP = 7, /*[SE]*/
2256  U_SB_SP = 8, /*[SP]*/
2257  U_SB_STERM = 9, /*[ST]*/
2258  U_SB_UPPER = 10, /*[UP]*/
2259  U_SB_CR = 11, /*[CR]*/ /* from here on: new in Unicode 5.1/ICU 4.0 */
2260  U_SB_EXTEND = 12, /*[EX]*/
2261  U_SB_LF = 13, /*[LF]*/
2262  U_SB_SCONTINUE = 14, /*[SC]*/
2263 #ifndef U_HIDE_DEPRECATED_API
2264  /**
2265  * One more than the highest normal USentenceBreak value.
2266  * The highest value is available via u_getIntPropertyMaxValue(UCHAR_SENTENCE_BREAK).
2267  *
2268  * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420.
2269  */
2270  U_SB_COUNT = 15
2271 #endif // U_HIDE_DEPRECATED_API
2273 
2274 /**
2275  * Line Break constants.
2276  *
2277  * @see UCHAR_LINE_BREAK
2278  * @stable ICU 2.2
2279  */
2280 typedef enum ULineBreak {
2281  /*
2282  * Note: ULineBreak constants are parsed by preparseucd.py.
2283  * It matches lines like
2284  * U_LB_<Unicode Line_Break value name>
2285  */
2286 
2287  U_LB_UNKNOWN = 0, /*[XX]*/
2288  U_LB_AMBIGUOUS = 1, /*[AI]*/
2289  U_LB_ALPHABETIC = 2, /*[AL]*/
2290  U_LB_BREAK_BOTH = 3, /*[B2]*/
2291  U_LB_BREAK_AFTER = 4, /*[BA]*/
2292  U_LB_BREAK_BEFORE = 5, /*[BB]*/
2293  U_LB_MANDATORY_BREAK = 6, /*[BK]*/
2296  U_LB_COMBINING_MARK = 9, /*[CM]*/
2297  U_LB_CARRIAGE_RETURN = 10, /*[CR]*/
2298  U_LB_EXCLAMATION = 11, /*[EX]*/
2299  U_LB_GLUE = 12, /*[GL]*/
2300  U_LB_HYPHEN = 13, /*[HY]*/
2301  U_LB_IDEOGRAPHIC = 14, /*[ID]*/
2302  /** Renamed from the misspelled "inseperable" in Unicode 4.0.1/ICU 3.0 @stable ICU 3.0 */
2303  U_LB_INSEPARABLE = 15, /*[IN]*/
2305  U_LB_INFIX_NUMERIC = 16, /*[IS]*/
2306  U_LB_LINE_FEED = 17, /*[LF]*/
2307  U_LB_NONSTARTER = 18, /*[NS]*/
2308  U_LB_NUMERIC = 19, /*[NU]*/
2309  U_LB_OPEN_PUNCTUATION = 20, /*[OP]*/
2310  U_LB_POSTFIX_NUMERIC = 21, /*[PO]*/
2311  U_LB_PREFIX_NUMERIC = 22, /*[PR]*/
2312  U_LB_QUOTATION = 23, /*[QU]*/
2313  U_LB_COMPLEX_CONTEXT = 24, /*[SA]*/
2314  U_LB_SURROGATE = 25, /*[SG]*/
2315  U_LB_SPACE = 26, /*[SP]*/
2316  U_LB_BREAK_SYMBOLS = 27, /*[SY]*/
2317  U_LB_ZWSPACE = 28, /*[ZW]*/
2318  /** @stable ICU 2.6 */
2319  U_LB_NEXT_LINE = 29, /*[NL]*/ /* from here on: new in Unicode 4/ICU 2.6 */
2320  /** @stable ICU 2.6 */
2321  U_LB_WORD_JOINER = 30, /*[WJ]*/
2322  /** @stable ICU 3.4 */
2323  U_LB_H2 = 31, /*[H2]*/ /* from here on: new in Unicode 4.1/ICU 3.4 */
2324  /** @stable ICU 3.4 */
2325  U_LB_H3 = 32, /*[H3]*/
2326  /** @stable ICU 3.4 */
2327  U_LB_JL = 33, /*[JL]*/
2328  /** @stable ICU 3.4 */
2329  U_LB_JT = 34, /*[JT]*/
2330  /** @stable ICU 3.4 */
2331  U_LB_JV = 35, /*[JV]*/
2332  /** @stable ICU 4.4 */
2333  U_LB_CLOSE_PARENTHESIS = 36, /*[CP]*/ /* new in Unicode 5.2/ICU 4.4 */
2334  /** @stable ICU 49 */
2335  U_LB_CONDITIONAL_JAPANESE_STARTER = 37,/*[CJ]*/ /* new in Unicode 6.1/ICU 49 */
2336  /** @stable ICU 49 */
2337  U_LB_HEBREW_LETTER = 38, /*[HL]*/ /* new in Unicode 6.1/ICU 49 */
2338  /** @stable ICU 50 */
2339  U_LB_REGIONAL_INDICATOR = 39,/*[RI]*/ /* new in Unicode 6.2/ICU 50 */
2340  /** @stable ICU 58 */
2341  U_LB_E_BASE = 40, /*[EB]*/ /* from here on: new in Unicode 9.0/ICU 58 */
2342  /** @stable ICU 58 */
2343  U_LB_E_MODIFIER = 41, /*[EM]*/
2344  /** @stable ICU 58 */
2345  U_LB_ZWJ = 42, /*[ZWJ]*/
2346 #ifndef U_HIDE_DEPRECATED_API
2347  /**
2348  * One more than the highest normal ULineBreak value.
2349  * The highest value is available via u_getIntPropertyMaxValue(UCHAR_LINE_BREAK).
2350  *
2351  * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420.
2352  */
2353  U_LB_COUNT = 43
2354 #endif // U_HIDE_DEPRECATED_API
2356 
2357 /**
2358  * Numeric Type constants.
2359  *
2360  * @see UCHAR_NUMERIC_TYPE
2361  * @stable ICU 2.2
2362  */
2363 typedef enum UNumericType {
2364  /*
2365  * Note: UNumericType constants are parsed by preparseucd.py.
2366  * It matches lines like
2367  * U_NT_<Unicode Numeric_Type value name>
2368  */
2369 
2370  U_NT_NONE, /*[None]*/
2371  U_NT_DECIMAL, /*[de]*/
2372  U_NT_DIGIT, /*[di]*/
2373  U_NT_NUMERIC, /*[nu]*/
2374 #ifndef U_HIDE_DEPRECATED_API
2375  /**
2376  * One more than the highest normal UNumericType value.
2377  * The highest value is available via u_getIntPropertyMaxValue(UCHAR_NUMERIC_TYPE).
2378  *
2379  * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420.
2380  */
2381  U_NT_COUNT
2382 #endif // U_HIDE_DEPRECATED_API
2384 
2385 /**
2386  * Hangul Syllable Type constants.
2387  *
2388  * @see UCHAR_HANGUL_SYLLABLE_TYPE
2389  * @stable ICU 2.6
2390  */
2391 typedef enum UHangulSyllableType {
2392  /*
2393  * Note: UHangulSyllableType constants are parsed by preparseucd.py.
2394  * It matches lines like
2395  * U_HST_<Unicode Hangul_Syllable_Type value name>
2396  */
2397 
2404 #ifndef U_HIDE_DEPRECATED_API
2405  /**
2406  * One more than the highest normal UHangulSyllableType value.
2407  * The highest value is available via u_getIntPropertyMaxValue(UCHAR_HANGUL_SYLLABLE_TYPE).
2408  *
2409  * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420.
2410  */
2411  U_HST_COUNT
2412 #endif // U_HIDE_DEPRECATED_API
2414 
2415 /**
2416  * Indic Positional Category constants.
2417  *
2418  * @see UCHAR_INDIC_POSITIONAL_CATEGORY
2419  * @stable ICU 63
2420  */
2422  /*
2423  * Note: UIndicPositionalCategory constants are parsed by preparseucd.py.
2424  * It matches lines like
2425  * U_INPC_<Unicode Indic_Positional_Category value name>
2426  */
2427 
2428  /** @stable ICU 63 */
2430  /** @stable ICU 63 */
2432  /** @stable ICU 63 */
2434  /** @stable ICU 63 */
2436  /** @stable ICU 63 */
2438  /** @stable ICU 63 */
2440  /** @stable ICU 63 */
2442  /** @stable ICU 63 */
2444  /** @stable ICU 63 */
2446  /** @stable ICU 63 */
2448  /** @stable ICU 63 */
2450  /** @stable ICU 63 */
2452  /** @stable ICU 63 */
2454  /** @stable ICU 63 */
2456  /** @stable ICU 63 */
2458  /** @stable ICU 66 */
2461 
2462 /**
2463  * Indic Syllabic Category constants.
2464  *
2465  * @see UCHAR_INDIC_SYLLABIC_CATEGORY
2466  * @stable ICU 63
2467  */
2469  /*
2470  * Note: UIndicSyllabicCategory constants are parsed by preparseucd.py.
2471  * It matches lines like
2472  * U_INSC_<Unicode Indic_Syllabic_Category value name>
2473  */
2474 
2475  /** @stable ICU 63 */
2477  /** @stable ICU 63 */
2479  /** @stable ICU 63 */
2481  /** @stable ICU 63 */
2483  /** @stable ICU 63 */
2485  /** @stable ICU 63 */
2487  /** @stable ICU 63 */
2489  /** @stable ICU 63 */
2491  /** @stable ICU 63 */
2493  /** @stable ICU 63 */
2495  /** @stable ICU 63 */
2497  /** @stable ICU 63 */
2499  /** @stable ICU 63 */
2501  /** @stable ICU 63 */
2503  /** @stable ICU 63 */
2505  /** @stable ICU 63 */
2507  /** @stable ICU 63 */
2509  /** @stable ICU 63 */
2511  /** @stable ICU 63 */
2513  /** @stable ICU 63 */
2515  /** @stable ICU 63 */
2517  /** @stable ICU 63 */
2519  /** @stable ICU 63 */
2521  /** @stable ICU 63 */
2523  /** @stable ICU 63 */
2525  /** @stable ICU 63 */
2527  /** @stable ICU 63 */
2529  /** @stable ICU 63 */
2531  /** @stable ICU 63 */
2533  /** @stable ICU 63 */
2535  /** @stable ICU 63 */
2537  /** @stable ICU 63 */
2539  /** @stable ICU 63 */
2541  /** @stable ICU 63 */
2543  /** @stable ICU 63 */
2545  /** @stable ICU 63 */
2548 
2549 /**
2550  * Vertical Orientation constants.
2551  *
2552  * @see UCHAR_VERTICAL_ORIENTATION
2553  * @stable ICU 63
2554  */
2555 typedef enum UVerticalOrientation {
2556  /*
2557  * Note: UVerticalOrientation constants are parsed by preparseucd.py.
2558  * It matches lines like
2559  * U_VO_<Unicode Vertical_Orientation value name>
2560  */
2561 
2562  /** @stable ICU 63 */
2564  /** @stable ICU 63 */
2566  /** @stable ICU 63 */
2568  /** @stable ICU 63 */
2571 
2572 /**
2573  * Check a binary Unicode property for a code point.
2574  *
2575  * Unicode, especially in version 3.2, defines many more properties than the
2576  * original set in UnicodeData.txt.
2577  *
2578  * The properties APIs are intended to reflect Unicode properties as defined
2579  * in the Unicode Character Database (UCD) and Unicode Technical Reports (UTR).
2580  * For details about the properties see http://www.unicode.org/ucd/ .
2581  * For names of Unicode properties see the UCD file PropertyAliases.txt.
2582  *
2583  * Important: If ICU is built with UCD files from Unicode versions below 3.2,
2584  * then properties marked with "new in Unicode 3.2" are not or not fully available.
2585  *
2586  * @param c Code point to test.
2587  * @param which UProperty selector constant, identifies which binary property to check.
2588  * Must be UCHAR_BINARY_START<=which<UCHAR_BINARY_LIMIT.
2589  * @return true or false according to the binary Unicode property value for c.
2590  * Also false if 'which' is out of bounds or if the Unicode version
2591  * does not have data for the property at all, or not for this code point.
2592  *
2593  * @see UProperty
2594  * @see u_getBinaryPropertySet
2595  * @see u_getIntPropertyValue
2596  * @see u_getUnicodeVersion
2597  * @stable ICU 2.1
2598  */
2601 
2602 /**
2603  * Returns a frozen USet for a binary property.
2604  * The library retains ownership over the returned object.
2605  * Sets an error code if the property number is not one for a binary property.
2606  *
2607  * The returned set contains all code points for which the property is true.
2608  *
2609  * @param property UCHAR_BINARY_START..UCHAR_BINARY_LIMIT-1
2610  * @param pErrorCode an in/out ICU UErrorCode
2611  * @return the property as a set
2612  * @see UProperty
2613  * @see u_hasBinaryProperty
2614  * @see Unicode::fromUSet
2615  * @stable ICU 63
2616  */
2617 U_CAPI const USet * U_EXPORT2
2618 u_getBinaryPropertySet(UProperty property, UErrorCode *pErrorCode);
2619 
2620 /**
2621  * Check if a code point has the Alphabetic Unicode property.
2622  * Same as u_hasBinaryProperty(c, UCHAR_ALPHABETIC).
2623  * This is different from u_isalpha!
2624  * @param c Code point to test
2625  * @return true if the code point has the Alphabetic Unicode property, false otherwise
2626  *
2627  * @see UCHAR_ALPHABETIC
2628  * @see u_isalpha
2629  * @see u_hasBinaryProperty
2630  * @stable ICU 2.1
2631  */
2634 
2635 /**
2636  * Check if a code point has the Lowercase Unicode property.
2637  * Same as u_hasBinaryProperty(c, UCHAR_LOWERCASE).
2638  * This is different from u_islower!
2639  * @param c Code point to test
2640  * @return true if the code point has the Lowercase Unicode property, false otherwise
2641  *
2642  * @see UCHAR_LOWERCASE
2643  * @see u_islower
2644  * @see u_hasBinaryProperty
2645  * @stable ICU 2.1
2646  */
2649 
2650 /**
2651  * Check if a code point has the Uppercase Unicode property.
2652  * Same as u_hasBinaryProperty(c, UCHAR_UPPERCASE).
2653  * This is different from u_isupper!
2654  * @param c Code point to test
2655  * @return true if the code point has the Uppercase Unicode property, false otherwise
2656  *
2657  * @see UCHAR_UPPERCASE
2658  * @see u_isupper
2659  * @see u_hasBinaryProperty
2660  * @stable ICU 2.1
2661  */
2664 
2665 /**
2666  * Check if a code point has the White_Space Unicode property.
2667  * Same as u_hasBinaryProperty(c, UCHAR_WHITE_SPACE).
2668  * This is different from both u_isspace and u_isWhitespace!
2669  *
2670  * Note: There are several ICU whitespace functions; please see the uchar.h
2671  * file documentation for a detailed comparison.
2672  *
2673  * @param c Code point to test
2674  * @return true if the code point has the White_Space Unicode property, false otherwise.
2675  *
2676  * @see UCHAR_WHITE_SPACE
2677  * @see u_isWhitespace
2678  * @see u_isspace
2679  * @see u_isJavaSpaceChar
2680  * @see u_hasBinaryProperty
2681  * @stable ICU 2.1
2682  */
2685 
2686 /**
2687  * Get the property value for an enumerated or integer Unicode property for a code point.
2688  * Also returns binary and mask property values.
2689  *
2690  * Unicode, especially in version 3.2, defines many more properties than the
2691  * original set in UnicodeData.txt.
2692  *
2693  * The properties APIs are intended to reflect Unicode properties as defined
2694  * in the Unicode Character Database (UCD) and Unicode Technical Reports (UTR).
2695  * For details about the properties see http://www.unicode.org/ .
2696  * For names of Unicode properties see the UCD file PropertyAliases.txt.
2697  *
2698  * Sample usage:
2699  * UEastAsianWidth ea=(UEastAsianWidth)u_getIntPropertyValue(c, UCHAR_EAST_ASIAN_WIDTH);
2700  * UBool b=(UBool)u_getIntPropertyValue(c, UCHAR_IDEOGRAPHIC);
2701  *
2702  * @param c Code point to test.
2703  * @param which UProperty selector constant, identifies which property to check.
2704  * Must be UCHAR_BINARY_START<=which<UCHAR_BINARY_LIMIT
2705  * or UCHAR_INT_START<=which<UCHAR_INT_LIMIT
2706  * or UCHAR_MASK_START<=which<UCHAR_MASK_LIMIT.
2707  * @return Numeric value that is directly the property value or,
2708  * for enumerated properties, corresponds to the numeric value of the enumerated
2709  * constant of the respective property value enumeration type
2710  * (cast to enum type if necessary).
2711  * Returns 0 or 1 (for false/true) for binary Unicode properties.
2712  * Returns a bit-mask for mask properties.
2713  * Returns 0 if 'which' is out of bounds or if the Unicode version
2714  * does not have data for the property at all, or not for this code point.
2715  *
2716  * @see UProperty
2717  * @see u_hasBinaryProperty
2718  * @see u_getIntPropertyMinValue
2719  * @see u_getIntPropertyMaxValue
2720  * @see u_getIntPropertyMap
2721  * @see u_getUnicodeVersion
2722  * @stable ICU 2.2
2723  */
2726 
2727 /**
2728  * Get the minimum value for an enumerated/integer/binary Unicode property.
2729  * Can be used together with u_getIntPropertyMaxValue
2730  * to allocate arrays of UnicodeSet or similar.
2731  *
2732  * @param which UProperty selector constant, identifies which binary property to check.
2733  * Must be UCHAR_BINARY_START<=which<UCHAR_BINARY_LIMIT
2734  * or UCHAR_INT_START<=which<UCHAR_INT_LIMIT.
2735  * @return Minimum value returned by u_getIntPropertyValue for a Unicode property.
2736  * 0 if the property selector is out of range.
2737  *
2738  * @see UProperty
2739  * @see u_hasBinaryProperty
2740  * @see u_getUnicodeVersion
2741  * @see u_getIntPropertyMaxValue
2742  * @see u_getIntPropertyValue
2743  * @stable ICU 2.2
2744  */
2747 
2748 /**
2749  * Get the maximum value for an enumerated/integer/binary Unicode property.
2750  * Can be used together with u_getIntPropertyMinValue
2751  * to allocate arrays of UnicodeSet or similar.
2752  *
2753  * Examples for min/max values (for Unicode 3.2):
2754  *
2755  * - UCHAR_BIDI_CLASS: 0/18 (U_LEFT_TO_RIGHT/U_BOUNDARY_NEUTRAL)
2756  * - UCHAR_SCRIPT: 0/45 (USCRIPT_COMMON/USCRIPT_TAGBANWA)
2757  * - UCHAR_IDEOGRAPHIC: 0/1 (false/true)
2758  *
2759  * For undefined UProperty constant values, min/max values will be 0/-1.
2760  *
2761  * @param which UProperty selector constant, identifies which binary property to check.
2762  * Must be UCHAR_BINARY_START<=which<UCHAR_BINARY_LIMIT
2763  * or UCHAR_INT_START<=which<UCHAR_INT_LIMIT.
2764  * @return Maximum value returned by u_getIntPropertyValue for a Unicode property.
2765  * <=0 if the property selector is out of range.
2766  *
2767  * @see UProperty
2768  * @see u_hasBinaryProperty
2769  * @see u_getUnicodeVersion
2770  * @see u_getIntPropertyMaxValue
2771  * @see u_getIntPropertyValue
2772  * @stable ICU 2.2
2773  */
2776 
2777 /**
2778  * Returns an immutable UCPMap for an enumerated/catalog/int-valued property.
2779  * The library retains ownership over the returned object.
2780  * Sets an error code if the property number is not one for an "int property".
2781  *
2782  * The returned object maps all Unicode code points to their values for that property.
2783  * For documentation of the integer values see u_getIntPropertyValue().
2784  *
2785  * @param property UCHAR_INT_START..UCHAR_INT_LIMIT-1
2786  * @param pErrorCode an in/out ICU UErrorCode
2787  * @return the property as a map
2788  * @see UProperty
2789  * @see u_getIntPropertyValue
2790  * @stable ICU 63
2791  */
2792 U_CAPI const UCPMap * U_EXPORT2
2793 u_getIntPropertyMap(UProperty property, UErrorCode *pErrorCode);
2794 
2795 /**
2796  * Get the numeric value for a Unicode code point as defined in the
2797  * Unicode Character Database.
2798  *
2799  * A "double" return type is necessary because
2800  * some numeric values are fractions, negative, or too large for int32_t.
2801  *
2802  * For characters without any numeric values in the Unicode Character Database,
2803  * this function will return U_NO_NUMERIC_VALUE.
2804  * Note: This is different from the Unicode Standard which specifies NaN as the default value.
2805  * (NaN is not available on all platforms.)
2806  *
2807  * Similar to java.lang.Character.getNumericValue(), but u_getNumericValue()
2808  * also supports negative values, large values, and fractions,
2809  * while Java's getNumericValue() returns values 10..35 for ASCII letters.
2810  *
2811  * @param c Code point to get the numeric value for.
2812  * @return Numeric value of c, or U_NO_NUMERIC_VALUE if none is defined.
2813  *
2814  * @see U_NO_NUMERIC_VALUE
2815  * @stable ICU 2.2
2816  */
2817 U_CAPI double U_EXPORT2
2819 
2820 /**
2821  * Special value that is returned by u_getNumericValue when
2822  * no numeric value is defined for a code point.
2823  *
2824  * @see u_getNumericValue
2825  * @stable ICU 2.2
2826  */
2827 #define U_NO_NUMERIC_VALUE ((double)-123456789.)
2828 
2829 /**
2830  * Determines whether the specified code point has the general category "Ll"
2831  * (lowercase letter).
2832  *
2833  * Same as java.lang.Character.isLowerCase().
2834  *
2835  * This misses some characters that are also lowercase but
2836  * have a different general category value.
2837  * In order to include those, use UCHAR_LOWERCASE.
2838  *
2839  * In addition to being equivalent to a Java function, this also serves
2840  * as a C/POSIX migration function.
2841  * See the comments about C/POSIX character classification functions in the
2842  * documentation at the top of this header file.
2843  *
2844  * @param c the code point to be tested
2845  * @return true if the code point is an Ll lowercase letter
2846  *
2847  * @see UCHAR_LOWERCASE
2848  * @see u_isupper
2849  * @see u_istitle
2850  * @stable ICU 2.0
2851  */
2854 
2855 /**
2856  * Determines whether the specified code point has the general category "Lu"
2857  * (uppercase letter).
2858  *
2859  * Same as java.lang.Character.isUpperCase().
2860  *
2861  * This misses some characters that are also uppercase but
2862  * have a different general category value.
2863  * In order to include those, use UCHAR_UPPERCASE.
2864  *
2865  * In addition to being equivalent to a Java function, this also serves
2866  * as a C/POSIX migration function.
2867  * See the comments about C/POSIX character classification functions in the
2868  * documentation at the top of this header file.
2869  *
2870  * @param c the code point to be tested
2871  * @return true if the code point is an Lu uppercase letter
2872  *
2873  * @see UCHAR_UPPERCASE
2874  * @see u_islower
2875  * @see u_istitle
2876  * @see u_tolower
2877  * @stable ICU 2.0
2878  */
2881 
2882 /**
2883  * Determines whether the specified code point is a titlecase letter.
2884  * True for general category "Lt" (titlecase letter).
2885  *
2886  * Same as java.lang.Character.isTitleCase().
2887  *
2888  * @param c the code point to be tested
2889  * @return true if the code point is an Lt titlecase letter
2890  *
2891  * @see u_isupper
2892  * @see u_islower
2893  * @see u_totitle
2894  * @stable ICU 2.0
2895  */
2898 
2899 /**
2900  * Determines whether the specified code point is a digit character according to Java.
2901  * True for characters with general category "Nd" (decimal digit numbers).
2902  * Beginning with Unicode 4, this is the same as
2903  * testing for the Numeric_Type of Decimal.
2904  *
2905  * Same as java.lang.Character.isDigit().
2906  *
2907  * In addition to being equivalent to a Java function, this also serves
2908  * as a C/POSIX migration function.
2909  * See the comments about C/POSIX character classification functions in the
2910  * documentation at the top of this header file.
2911  *
2912  * @param c the code point to be tested
2913  * @return true if the code point is a digit character according to Character.isDigit()
2914  *
2915  * @stable ICU 2.0
2916  */
2919 
2920 /**
2921  * Determines whether the specified code point is a letter character.
2922  * True for general categories "L" (letters).
2923  *
2924  * Same as java.lang.Character.isLetter().
2925  *
2926  * In addition to being equivalent to a Java function, this also serves
2927  * as a C/POSIX migration function.
2928  * See the comments about C/POSIX character classification functions in the
2929  * documentation at the top of this header file.
2930  *
2931  * @param c the code point to be tested
2932  * @return true if the code point is a letter character
2933  *
2934  * @see u_isdigit
2935  * @see u_isalnum
2936  * @stable ICU 2.0
2937  */
2940 
2941 /**
2942  * Determines whether the specified code point is an alphanumeric character
2943  * (letter or digit) according to Java.
2944  * True for characters with general categories
2945  * "L" (letters) and "Nd" (decimal digit numbers).
2946  *
2947  * Same as java.lang.Character.isLetterOrDigit().
2948  *
2949  * In addition to being equivalent to a Java function, this also serves
2950  * as a C/POSIX migration function.
2951  * See the comments about C/POSIX character classification functions in the
2952  * documentation at the top of this header file.
2953  *
2954  * @param c the code point to be tested
2955  * @return true if the code point is an alphanumeric character according to Character.isLetterOrDigit()
2956  *
2957  * @stable ICU 2.0
2958  */
2961 
2962 /**
2963  * Determines whether the specified code point is a hexadecimal digit.
2964  * This is equivalent to u_digit(c, 16)>=0.
2965  * True for characters with general category "Nd" (decimal digit numbers)
2966  * as well as Latin letters a-f and A-F in both ASCII and Fullwidth ASCII.
2967  * (That is, for letters with code points
2968  * 0041..0046, 0061..0066, FF21..FF26, FF41..FF46.)
2969  *
2970  * In order to narrow the definition of hexadecimal digits to only ASCII
2971  * characters, use (c<=0x7f && u_isxdigit(c)).
2972  *
2973  * This is a C/POSIX migration function.
2974  * See the comments about C/POSIX character classification functions in the
2975  * documentation at the top of this header file.
2976  *
2977  * @param c the code point to be tested
2978  * @return true if the code point is a hexadecimal digit
2979  *
2980  * @stable ICU 2.6
2981  */
2984 
2985 /**
2986  * Determines whether the specified code point is a punctuation character.
2987  * True for characters with general categories "P" (punctuation).
2988  *
2989  * This is a C/POSIX migration function.
2990  * See the comments about C/POSIX character classification functions in the
2991  * documentation at the top of this header file.
2992  *
2993  * @param c the code point to be tested
2994  * @return true if the code point is a punctuation character
2995  *
2996  * @stable ICU 2.6
2997  */
3000 
3001 /**
3002  * Determines whether the specified code point is a "graphic" character
3003  * (printable, excluding spaces).
3004  * true for all characters except those with general categories
3005  * "Cc" (control codes), "Cf" (format controls), "Cs" (surrogates),
3006  * "Cn" (unassigned), and "Z" (separators).
3007  *
3008  * This is a C/POSIX migration function.
3009  * See the comments about C/POSIX character classification functions in the
3010  * documentation at the top of this header file.
3011  *
3012  * @param c the code point to be tested
3013  * @return true if the code point is a "graphic" character
3014  *
3015  * @stable ICU 2.6
3016  */
3019 
3020 /**
3021  * Determines whether the specified code point is a "blank" or "horizontal space",
3022  * a character that visibly separates words on a line.
3023  * The following are equivalent definitions:
3024  *
3025  * true for Unicode White_Space characters except for "vertical space controls"
3026  * where "vertical space controls" are the following characters:
3027  * U+000A (LF) U+000B (VT) U+000C (FF) U+000D (CR) U+0085 (NEL) U+2028 (LS) U+2029 (PS)
3028  *
3029  * same as
3030  *
3031  * true for U+0009 (TAB) and characters with general category "Zs" (space separators).
3032  *
3033  * Note: There are several ICU whitespace functions; please see the uchar.h
3034  * file documentation for a detailed comparison.
3035  *
3036  * This is a C/POSIX migration function.
3037  * See the comments about C/POSIX character classification functions in the
3038  * documentation at the top of this header file.
3039  *
3040  * @param c the code point to be tested
3041  * @return true if the code point is a "blank"
3042  *
3043  * @stable ICU 2.6
3044  */
3047 
3048 /**
3049  * Determines whether the specified code point is "defined",
3050  * which usually means that it is assigned a character.
3051  * True for general categories other than "Cn" (other, not assigned),
3052  * i.e., true for all code points mentioned in UnicodeData.txt.
3053  *
3054  * Note that non-character code points (e.g., U+FDD0) are not "defined"
3055  * (they are Cn), but surrogate code points are "defined" (Cs).
3056  *
3057  * Same as java.lang.Character.isDefined().
3058  *
3059  * @param c the code point to be tested
3060  * @return true if the code point is assigned a character
3061  *
3062  * @see u_isdigit
3063  * @see u_isalpha
3064  * @see u_isalnum
3065  * @see u_isupper
3066  * @see u_islower
3067  * @see u_istitle
3068  * @stable ICU 2.0
3069  */
3072 
3073 /**
3074  * Determines if the specified character is a space character or not.
3075  *
3076  * Note: There are several ICU whitespace functions; please see the uchar.h
3077  * file documentation for a detailed comparison.
3078  *
3079  * This is a C/POSIX migration function.
3080  * See the comments about C/POSIX character classification functions in the
3081  * documentation at the top of this header file.
3082  *
3083  * @param c the character to be tested
3084  * @return true if the character is a space character; false otherwise.
3085  *
3086  * @see u_isJavaSpaceChar
3087  * @see u_isWhitespace
3088  * @see u_isUWhiteSpace
3089  * @stable ICU 2.0
3090  */
3093 
3094 /**
3095  * Determine if the specified code point is a space character according to Java.
3096  * True for characters with general categories "Z" (separators),
3097  * which does not include control codes (e.g., TAB or Line Feed).
3098  *
3099  * Same as java.lang.Character.isSpaceChar().
3100  *
3101  * Note: There are several ICU whitespace functions; please see the uchar.h
3102  * file documentation for a detailed comparison.
3103  *
3104  * @param c the code point to be tested
3105  * @return true if the code point is a space character according to Character.isSpaceChar()
3106  *
3107  * @see u_isspace
3108  * @see u_isWhitespace
3109  * @see u_isUWhiteSpace
3110  * @stable ICU 2.6
3111  */
3114 
3115 /**
3116  * Determines if the specified code point is a whitespace character according to Java/ICU.
3117  * A character is considered to be a Java whitespace character if and only
3118  * if it satisfies one of the following criteria:
3119  *
3120  * - It is a Unicode Separator character (categories "Z" = "Zs" or "Zl" or "Zp"), but is not
3121  * also a non-breaking space (U+00A0 NBSP or U+2007 Figure Space or U+202F Narrow NBSP).
3122  * - It is U+0009 HORIZONTAL TABULATION.
3123  * - It is U+000A LINE FEED.
3124  * - It is U+000B VERTICAL TABULATION.
3125  * - It is U+000C FORM FEED.
3126  * - It is U+000D CARRIAGE RETURN.
3127  * - It is U+001C FILE SEPARATOR.
3128  * - It is U+001D GROUP SEPARATOR.
3129  * - It is U+001E RECORD SEPARATOR.
3130  * - It is U+001F UNIT SEPARATOR.
3131  *
3132  * This API tries to sync with the semantics of Java's
3133  * java.lang.Character.isWhitespace(), but it may not return
3134  * the exact same results because of the Unicode version
3135  * difference.
3136  *
3137  * Note: Unicode 4.0.1 changed U+200B ZERO WIDTH SPACE from a Space Separator (Zs)
3138  * to a Format Control (Cf). Since then, isWhitespace(0x200b) returns false.
3139  * See http://www.unicode.org/versions/Unicode4.0.1/
3140  *
3141  * Note: There are several ICU whitespace functions; please see the uchar.h
3142  * file documentation for a detailed comparison.
3143  *
3144  * @param c the code point to be tested
3145  * @return true if the code point is a whitespace character according to Java/ICU
3146  *
3147  * @see u_isspace
3148  * @see u_isJavaSpaceChar
3149  * @see u_isUWhiteSpace
3150  * @stable ICU 2.0
3151  */
3154 
3155 /**
3156  * Determines whether the specified code point is a control character
3157  * (as defined by this function).
3158  * A control character is one of the following:
3159  * - ISO 8-bit control character (U+0000..U+001f and U+007f..U+009f)
3160  * - U_CONTROL_CHAR (Cc)
3161  * - U_FORMAT_CHAR (Cf)
3162  * - U_LINE_SEPARATOR (Zl)
3163  * - U_PARAGRAPH_SEPARATOR (Zp)
3164  *
3165  * This is a C/POSIX migration function.
3166  * See the comments about C/POSIX character classification functions in the
3167  * documentation at the top of this header file.
3168  *
3169  * @param c the code point to be tested
3170  * @return true if the code point is a control character
3171  *
3172  * @see UCHAR_DEFAULT_IGNORABLE_CODE_POINT
3173  * @see u_isprint
3174  * @stable ICU 2.0
3175  */
3178 
3179 /**
3180  * Determines whether the specified code point is an ISO control code.
3181  * True for U+0000..U+001f and U+007f..U+009f (general category "Cc").
3182  *
3183  * Same as java.lang.Character.isISOControl().
3184  *
3185  * @param c the code point to be tested
3186  * @return true if the code point is an ISO control code
3187  *
3188  * @see u_iscntrl
3189  * @stable ICU 2.6
3190  */
3193 
3194 /**
3195  * Determines whether the specified code point is a printable character.
3196  * True for general categories <em>other</em> than "C" (controls).
3197  *
3198  * This is a C/POSIX migration function.
3199  * See the comments about C/POSIX character classification functions in the
3200  * documentation at the top of this header file.
3201  *
3202  * @param c the code point to be tested
3203  * @return true if the code point is a printable character
3204  *
3205  * @see UCHAR_DEFAULT_IGNORABLE_CODE_POINT
3206  * @see u_iscntrl
3207  * @stable ICU 2.0
3208  */
3211 
3212 /**
3213  * Non-standard: Determines whether the specified code point is a base character.
3214  * True for general categories "L" (letters), "N" (numbers),
3215  * "Mc" (spacing combining marks), and "Me" (enclosing marks).
3216  *
3217  * Note that this is different from the Unicode Standard definition in
3218  * chapter 3.6, conformance clause D51 “Base character”,
3219  * which defines base characters as the code points with general categories
3220  * Letter (L), Number (N), Punctuation (P), Symbol (S), or Space Separator (Zs).
3221  *
3222  * @param c the code point to be tested
3223  * @return true if the code point is a base character according to this function
3224  *
3225  * @see u_isalpha
3226  * @see u_isdigit
3227  * @stable ICU 2.0
3228  */
3230 u_isbase(UChar32 c);
3231 
3232 /**
3233  * Returns the bidirectional category value for the code point,
3234  * which is used in the Unicode bidirectional algorithm
3235  * (UAX #9 http://www.unicode.org/reports/tr9/).
3236  * Note that some <em>unassigned</em> code points have bidi values
3237  * of R or AL because they are in blocks that are reserved
3238  * for Right-To-Left scripts.
3239  *
3240  * Same as java.lang.Character.getDirectionality()
3241  *
3242  * @param c the code point to be tested
3243  * @return the bidirectional category (UCharDirection) value
3244  *
3245  * @see UCharDirection
3246  * @stable ICU 2.0
3247  */
3250 
3251 /**
3252  * Determines whether the code point has the Bidi_Mirrored property.
3253  * This property is set for characters that are commonly used in
3254  * Right-To-Left contexts and need to be displayed with a "mirrored"
3255  * glyph.
3256  *
3257  * Same as java.lang.Character.isMirrored().
3258  * Same as UCHAR_BIDI_MIRRORED
3259  *
3260  * @param c the code point to be tested
3261  * @return true if the character has the Bidi_Mirrored property
3262  *
3263  * @see UCHAR_BIDI_MIRRORED
3264  * @stable ICU 2.0
3265  */
3268 
3269 /**
3270  * Maps the specified character to a "mirror-image" character.
3271  * For characters with the Bidi_Mirrored property, implementations
3272  * sometimes need a "poor man's" mapping to another Unicode
3273  * character (code point) such that the default glyph may serve
3274  * as the mirror-image of the default glyph of the specified
3275  * character. This is useful for text conversion to and from
3276  * codepages with visual order, and for displays without glyph
3277  * selection capabilities.
3278  *
3279  * @param c the code point to be mapped
3280  * @return another Unicode code point that may serve as a mirror-image
3281  * substitute, or c itself if there is no such mapping or c
3282  * does not have the Bidi_Mirrored property
3283  *
3284  * @see UCHAR_BIDI_MIRRORED
3285  * @see u_isMirrored
3286  * @stable ICU 2.0
3287  */
3290 
3291 /**
3292  * Maps the specified character to its paired bracket character.
3293  * For Bidi_Paired_Bracket_Type!=None, this is the same as u_charMirror().
3294  * Otherwise c itself is returned.
3295  * See http://www.unicode.org/reports/tr9/
3296  *
3297  * @param c the code point to be mapped
3298  * @return the paired bracket code point,
3299  * or c itself if there is no such mapping
3300  * (Bidi_Paired_Bracket_Type=None)
3301  *
3302  * @see UCHAR_BIDI_PAIRED_BRACKET
3303  * @see UCHAR_BIDI_PAIRED_BRACKET_TYPE
3304  * @see u_charMirror
3305  * @stable ICU 52
3306  */
3309 
3310 /**
3311  * Returns the general category value for the code point.
3312  *
3313  * Same as java.lang.Character.getType().
3314  *
3315  * @param c the code point to be tested
3316  * @return the general category (UCharCategory) value
3317  *
3318  * @see UCharCategory
3319  * @stable ICU 2.0
3320  */
3323 
3324 /**
3325  * Get a single-bit bit set for the general category of a character.
3326  * This bit set can be compared bitwise with U_GC_SM_MASK, U_GC_L_MASK, etc.
3327  * Same as U_MASK(u_charType(c)).
3328  *
3329  * @param c the code point to be tested
3330  * @return a single-bit mask corresponding to the general category (UCharCategory) value
3331  *
3332  * @see u_charType
3333  * @see UCharCategory
3334  * @see U_GC_CN_MASK
3335  * @stable ICU 2.1
3336  */
3337 #define U_GET_GC_MASK(c) U_MASK(u_charType(c))
3338 
3339 /**
3340  * Callback from u_enumCharTypes(), is called for each contiguous range
3341  * of code points c (where start<=c<limit)
3342  * with the same Unicode general category ("character type").
3343  *
3344  * The callback function can stop the enumeration by returning false.
3345  *
3346  * @param context an opaque pointer, as passed into utrie_enum()
3347  * @param start the first code point in a contiguous range with value
3348  * @param limit one past the last code point in a contiguous range with value
3349  * @param type the general category for all code points in [start..limit[
3350  * @return false to stop the enumeration
3351  *
3352  * @stable ICU 2.1
3353  * @see UCharCategory
3354  * @see u_enumCharTypes
3355  */
3356 typedef UBool U_CALLCONV
3358 
3359 /**
3360  * Enumerate efficiently all code points with their Unicode general categories.
3361  *
3362  * This is useful for building data structures (e.g., UnicodeSet's),
3363  * for enumerating all assigned code points (type!=U_UNASSIGNED), etc.
3364  *
3365  * For each contiguous range of code points with a given general category ("character type"),
3366  * the UCharEnumTypeRange function is called.
3367  * Adjacent ranges have different types.
3368  * The Unicode Standard guarantees that the numeric value of the type is 0..31.
3369  *
3370  * @param enumRange a pointer to a function that is called for each contiguous range
3371  * of code points with the same general category
3372  * @param context an opaque pointer that is passed on to the callback function
3373  *
3374  * @stable ICU 2.1
3375  * @see UCharCategory
3376  * @see UCharEnumTypeRange
3377  */
3378 U_CAPI void U_EXPORT2
3379 u_enumCharTypes(UCharEnumTypeRange *enumRange, const void *context);
3380 
3381 #if !UCONFIG_NO_NORMALIZATION
3382 
3383 /**
3384  * Returns the combining class of the code point as specified in UnicodeData.txt.
3385  *
3386  * @param c the code point of the character
3387  * @return the combining class of the character
3388  * @stable ICU 2.0
3389  */
3392 
3393 #endif
3394 
3395 /**
3396  * Returns the decimal digit value of a decimal digit character.
3397  * Such characters have the general category "Nd" (decimal digit numbers)
3398  * and a Numeric_Type of Decimal.
3399  *
3400  * Unlike ICU releases before 2.6, no digit values are returned for any
3401  * Han characters because Han number characters are often used with a special
3402  * Chinese-style number format (with characters for powers of 10 in between)
3403  * instead of in decimal-positional notation.
3404  * Unicode 4 explicitly assigns Han number characters the Numeric_Type
3405  * Numeric instead of Decimal.
3406  * See Jitterbug 1483 for more details.
3407  *
3408  * Use u_getIntPropertyValue(c, UCHAR_NUMERIC_TYPE) and u_getNumericValue()
3409  * for complete numeric Unicode properties.
3410  *
3411  * @param c the code point for which to get the decimal digit value
3412  * @return the decimal digit value of c,
3413  * or -1 if c is not a decimal digit character
3414  *
3415  * @see u_getNumericValue
3416  * @stable ICU 2.0
3417  */
3420 
3421 /**
3422  * Returns the Unicode allocation block that contains the character.
3423  *
3424  * @param c the code point to be tested
3425  * @return the block value (UBlockCode) for c
3426  *
3427  * @see UBlockCode
3428  * @stable ICU 2.0
3429  */
3432 
3433 /**
3434  * Retrieve the name of a Unicode character.
3435  * Depending on <code>nameChoice</code>, the character name written
3436  * into the buffer is the "modern" name or the name that was defined
3437  * in Unicode version 1.0.
3438  * The name contains only "invariant" characters
3439  * like A-Z, 0-9, space, and '-'.
3440  * Unicode 1.0 names are only retrieved if they are different from the modern
3441  * names and if the data file contains the data for them. gennames may or may
3442  * not be called with a command line option to include 1.0 names in unames.dat.
3443  *
3444  * @param code The character (code point) for which to get the name.
3445  * It must be <code>0<=code<=0x10ffff</code>.
3446  * @param nameChoice Selector for which name to get.
3447  * @param buffer Destination address for copying the name.
3448  * The name will always be zero-terminated.
3449  * If there is no name, then the buffer will be set to the empty string.
3450  * @param bufferLength <code>==sizeof(buffer)</code>
3451  * @param pErrorCode Pointer to a UErrorCode variable;
3452  * check for <code>U_SUCCESS()</code> after <code>u_charName()</code>
3453  * returns.
3454  * @return The length of the name, or 0 if there is no name for this character.
3455  * If the bufferLength is less than or equal to the length, then the buffer
3456  * contains the truncated name and the returned length indicates the full
3457  * length of the name.
3458  * The length does not include the zero-termination.
3459  *
3460  * @see UCharNameChoice
3461  * @see u_charFromName
3462  * @see u_enumCharNames
3463  * @stable ICU 2.0
3464  */
3467  char *buffer, int32_t bufferLength,
3468  UErrorCode *pErrorCode);
3469 
3470 #ifndef U_HIDE_DEPRECATED_API
3471 /**
3472  * Returns an empty string.
3473  * Used to return the ISO 10646 comment for a character.
3474  * The Unicode ISO_Comment property is deprecated and has no values.
3475  *
3476  * @param c The character (code point) for which to get the ISO comment.
3477  * It must be <code>0<=c<=0x10ffff</code>.
3478  * @param dest Destination address for copying the comment.
3479  * The comment will be zero-terminated if possible.
3480  * If there is no comment, then the buffer will be set to the empty string.
3481  * @param destCapacity <code>==sizeof(dest)</code>
3482  * @param pErrorCode Pointer to a UErrorCode variable;
3483  * check for <code>U_SUCCESS()</code> after <code>u_getISOComment()</code>
3484  * returns.
3485  * @return 0
3486  *
3487  * @deprecated ICU 49
3488  */
3491  char *dest, int32_t destCapacity,
3492  UErrorCode *pErrorCode);
3493 #endif /* U_HIDE_DEPRECATED_API */
3494 
3495 /**
3496  * Find a Unicode character by its name and return its code point value.
3497  * The name is matched exactly and completely.
3498  * If the name does not correspond to a code point, <i>pErrorCode</i>
3499  * is set to <code>U_INVALID_CHAR_FOUND</code>.
3500  * A Unicode 1.0 name is matched only if it differs from the modern name.
3501  * Unicode names are all uppercase. Extended names are lowercase followed
3502  * by an uppercase hexadecimal number, and within angle brackets.
3503  *
3504  * @param nameChoice Selector for which name to match.
3505  * @param name The name to match.
3506  * @param pErrorCode Pointer to a UErrorCode variable
3507  * @return The Unicode value of the code point with the given name,
3508  * or an undefined value if there is no such code point.
3509  *
3510  * @see UCharNameChoice
3511  * @see u_charName
3512  * @see u_enumCharNames
3513  * @stable ICU 1.7
3514  */
3516 u_charFromName(UCharNameChoice nameChoice,
3517  const char *name,
3518  UErrorCode *pErrorCode);
3519 
3520 /**
3521  * Type of a callback function for u_enumCharNames() that gets called
3522  * for each Unicode character with the code point value and
3523  * the character name.
3524  * If such a function returns false, then the enumeration is stopped.
3525  *
3526  * @param context The context pointer that was passed to u_enumCharNames().
3527  * @param code The Unicode code point for the character with this name.
3528  * @param nameChoice Selector for which kind of names is enumerated.
3529  * @param name The character's name, zero-terminated.
3530  * @param length The length of the name.
3531  * @return true if the enumeration should continue, false to stop it.
3532  *
3533  * @see UCharNameChoice
3534  * @see u_enumCharNames
3535  * @stable ICU 1.7
3536  */
3538  UChar32 code,
3539  UCharNameChoice nameChoice,
3540  const char *name,
3541  int32_t length);
3542 
3543 /**
3544  * Enumerate all assigned Unicode characters between the start and limit
3545  * code points (start inclusive, limit exclusive) and call a function
3546  * for each, passing the code point value and the character name.
3547  * For Unicode 1.0 names, only those are enumerated that differ from the
3548  * modern names.
3549  *
3550  * @param start The first code point in the enumeration range.
3551  * @param limit One more than the last code point in the enumeration range
3552  * (the first one after the range).
3553  * @param fn The function that is to be called for each character name.
3554  * @param context An arbitrary pointer that is passed to the function.
3555  * @param nameChoice Selector for which kind of names to enumerate.
3556  * @param pErrorCode Pointer to a UErrorCode variable
3557  *
3558  * @see UCharNameChoice
3559  * @see UEnumCharNamesFn
3560  * @see u_charName
3561  * @see u_charFromName
3562  * @stable ICU 1.7
3563  */
3564 U_CAPI void U_EXPORT2
3567  void *context,
3568  UCharNameChoice nameChoice,
3569  UErrorCode *pErrorCode);
3570 
3571 /**
3572  * Return the Unicode name for a given property, as given in the
3573  * Unicode database file PropertyAliases.txt.
3574  *
3575  * In addition, this function maps the property
3576  * UCHAR_GENERAL_CATEGORY_MASK to the synthetic names "gcm" /
3577  * "General_Category_Mask". These names are not in
3578  * PropertyAliases.txt.
3579  *
3580  * @param property UProperty selector other than UCHAR_INVALID_CODE.
3581  * If out of range, NULL is returned.
3582  *
3583  * @param nameChoice selector for which name to get. If out of range,
3584  * NULL is returned. All properties have a long name. Most
3585  * have a short name, but some do not. Unicode allows for
3586  * additional names; if present these will be returned by
3587  * U_LONG_PROPERTY_NAME + i, where i=1, 2,...
3588  *
3589  * @return a pointer to the name, or NULL if either the
3590  * property or the nameChoice is out of range. If a given
3591  * nameChoice returns NULL, then all larger values of
3592  * nameChoice will return NULL, with one exception: if NULL is
3593  * returned for U_SHORT_PROPERTY_NAME, then
3594  * U_LONG_PROPERTY_NAME (and higher) may still return a
3595  * non-NULL value. The returned pointer is valid until
3596  * u_cleanup() is called.
3597  *
3598  * @see UProperty
3599  * @see UPropertyNameChoice
3600  * @stable ICU 2.4
3601  */
3602 U_CAPI const char* U_EXPORT2
3603 u_getPropertyName(UProperty property,
3604  UPropertyNameChoice nameChoice);
3605 
3606 /**
3607  * Return the UProperty enum for a given property name, as specified
3608  * in the Unicode database file PropertyAliases.txt. Short, long, and
3609  * any other variants are recognized.
3610  *
3611  * In addition, this function maps the synthetic names "gcm" /
3612  * "General_Category_Mask" to the property
3613  * UCHAR_GENERAL_CATEGORY_MASK. These names are not in
3614  * PropertyAliases.txt.
3615  *
3616  * @param alias the property name to be matched. The name is compared
3617  * using "loose matching" as described in PropertyAliases.txt.
3618  *
3619  * @return a UProperty enum, or UCHAR_INVALID_CODE if the given name
3620  * does not match any property.
3621  *
3622  * @see UProperty
3623  * @stable ICU 2.4
3624  */
3626 u_getPropertyEnum(const char* alias);
3627 
3628 /**
3629  * Return the Unicode name for a given property value, as given in the
3630  * Unicode database file PropertyValueAliases.txt.
3631  *
3632  * Note: Some of the names in PropertyValueAliases.txt can only be
3633  * retrieved using UCHAR_GENERAL_CATEGORY_MASK, not
3634  * UCHAR_GENERAL_CATEGORY. These include: "C" / "Other", "L" /
3635  * "Letter", "LC" / "Cased_Letter", "M" / "Mark", "N" / "Number", "P"
3636  * / "Punctuation", "S" / "Symbol", and "Z" / "Separator".
3637  *
3638  * @param property UProperty selector constant.
3639  * Must be UCHAR_BINARY_START<=which<UCHAR_BINARY_LIMIT
3640  * or UCHAR_INT_START<=which<UCHAR_INT_LIMIT
3641  * or UCHAR_MASK_START<=which<UCHAR_MASK_LIMIT.
3642  * If out of range, NULL is returned.
3643  *
3644  * @param value selector for a value for the given property. If out
3645  * of range, NULL is returned. In general, valid values range
3646  * from 0 up to some maximum. There are a few exceptions:
3647  * (1.) UCHAR_BLOCK values begin at the non-zero value
3648  * UBLOCK_BASIC_LATIN. (2.) UCHAR_CANONICAL_COMBINING_CLASS
3649  * values are not contiguous and range from 0..240. (3.)
3650  * UCHAR_GENERAL_CATEGORY_MASK values are not values of
3651  * UCharCategory, but rather mask values produced by
3652  * U_GET_GC_MASK(). This allows grouped categories such as
3653  * [:L:] to be represented. Mask values range
3654  * non-contiguously from 1..U_GC_P_MASK.
3655  *
3656  * @param nameChoice selector for which name to get. If out of range,
3657  * NULL is returned. All values have a long name. Most have
3658  * a short name, but some do not. Unicode allows for
3659  * additional names; if present these will be returned by
3660  * U_LONG_PROPERTY_NAME + i, where i=1, 2,...
3661 
3662  * @return a pointer to the name, or NULL if either the
3663  * property or the nameChoice is out of range. If a given
3664  * nameChoice returns NULL, then all larger values of
3665  * nameChoice will return NULL, with one exception: if NULL is
3666  * returned for U_SHORT_PROPERTY_NAME, then
3667  * U_LONG_PROPERTY_NAME (and higher) may still return a
3668  * non-NULL value. The returned pointer is valid until
3669  * u_cleanup() is called.
3670  *
3671  * @see UProperty
3672  * @see UPropertyNameChoice
3673  * @stable ICU 2.4
3674  */
3675 U_CAPI const char* U_EXPORT2
3677  int32_t value,
3678  UPropertyNameChoice nameChoice);
3679 
3680 /**
3681  * Return the property value integer for a given value name, as
3682  * specified in the Unicode database file PropertyValueAliases.txt.
3683  * Short, long, and any other variants are recognized.
3684  *
3685  * Note: Some of the names in PropertyValueAliases.txt will only be
3686  * recognized with UCHAR_GENERAL_CATEGORY_MASK, not
3687  * UCHAR_GENERAL_CATEGORY. These include: "C" / "Other", "L" /
3688  * "Letter", "LC" / "Cased_Letter", "M" / "Mark", "N" / "Number", "P"
3689  * / "Punctuation", "S" / "Symbol", and "Z" / "Separator".
3690  *
3691  * @param property UProperty selector constant.
3692  * Must be UCHAR_BINARY_START<=which<UCHAR_BINARY_LIMIT
3693  * or UCHAR_INT_START<=which<UCHAR_INT_LIMIT
3694  * or UCHAR_MASK_START<=which<UCHAR_MASK_LIMIT.
3695  * If out of range, UCHAR_INVALID_CODE is returned.
3696  *
3697  * @param alias the value name to be matched. The name is compared
3698  * using "loose matching" as described in
3699  * PropertyValueAliases.txt.
3700  *
3701  * @return a value integer or UCHAR_INVALID_CODE if the given name
3702  * does not match any value of the given property, or if the
3703  * property is invalid. Note: UCHAR_GENERAL_CATEGORY_MASK values
3704  * are not values of UCharCategory, but rather mask values
3705  * produced by U_GET_GC_MASK(). This allows grouped
3706  * categories such as [:L:] to be represented.
3707  *
3708  * @see UProperty
3709  * @stable ICU 2.4
3710  */
3713  const char* alias);
3714 
3715 /**
3716  * Determines if the specified character is permissible as the
3717  * first character in an identifier according to Unicode
3718  * (The Unicode Standard, Version 3.0, chapter 5.16 Identifiers).
3719  * True for characters with general categories "L" (letters) and "Nl" (letter numbers).
3720  *
3721  * Same as java.lang.Character.isUnicodeIdentifierStart().
3722  * Same as UCHAR_ID_START
3723  *
3724  * @param c the code point to be tested
3725  * @return true if the code point may start an identifier
3726  *
3727  * @see UCHAR_ID_START
3728  * @see u_isalpha
3729  * @see u_isIDPart
3730  * @stable ICU 2.0
3731  */
3734 
3735 /**
3736  * Determines if the specified character is permissible
3737  * in an identifier according to Java.
3738  * True for characters with general categories "L" (letters),
3739  * "Nl" (letter numbers), "Nd" (decimal digits),
3740  * "Mc" and "Mn" (combining marks), "Pc" (connecting punctuation), and
3741  * u_isIDIgnorable(c).
3742  *
3743  * Same as java.lang.Character.isUnicodeIdentifierPart().
3744  * Almost the same as Unicode's ID_Continue (UCHAR_ID_CONTINUE)
3745  * except that Unicode recommends to ignore Cf which is less than
3746  * u_isIDIgnorable(c).
3747  *
3748  * @param c the code point to be tested
3749  * @return true if the code point may occur in an identifier according to Java
3750  *
3751  * @see UCHAR_ID_CONTINUE
3752  * @see u_isIDStart
3753  * @see u_isIDIgnorable
3754  * @stable ICU 2.0
3755  */
3758 
3759 /**
3760  * Determines if the specified character should be regarded
3761  * as an ignorable character in an identifier,
3762  * according to Java.
3763  * True for characters with general category "Cf" (format controls) as well as
3764  * non-whitespace ISO controls
3765  * (U+0000..U+0008, U+000E..U+001B, U+007F..U+009F).
3766  *
3767  * Same as java.lang.Character.isIdentifierIgnorable().
3768  *
3769  * Note that Unicode just recommends to ignore Cf (format controls).
3770  *
3771  * @param c the code point to be tested
3772  * @return true if the code point is ignorable in identifiers according to Java
3773  *
3774  * @see UCHAR_DEFAULT_IGNORABLE_CODE_POINT
3775  * @see u_isIDStart
3776  * @see u_isIDPart
3777  * @stable ICU 2.0
3778  */
3781 
3782 /**
3783  * Determines if the specified character is permissible as the
3784  * first character in a Java identifier.
3785  * In addition to u_isIDStart(c), true for characters with
3786  * general categories "Sc" (currency symbols) and "Pc" (connecting punctuation).
3787  *
3788  * Same as java.lang.Character.isJavaIdentifierStart().
3789  *
3790  * @param c the code point to be tested
3791  * @return true if the code point may start a Java identifier
3792  *
3793  * @see u_isJavaIDPart
3794  * @see u_isalpha
3795  * @see u_isIDStart
3796  * @stable ICU 2.0
3797  */
3800 
3801 /**
3802  * Determines if the specified character is permissible
3803  * in a Java identifier.
3804  * In addition to u_isIDPart(c), true for characters with
3805  * general category "Sc" (currency symbols).
3806  *
3807  * Same as java.lang.Character.isJavaIdentifierPart().
3808  *
3809  * @param c the code point to be tested
3810  * @return true if the code point may occur in a Java identifier
3811  *
3812  * @see u_isIDIgnorable
3813  * @see u_isJavaIDStart
3814  * @see u_isalpha
3815  * @see u_isdigit
3816  * @see u_isIDPart
3817  * @stable ICU 2.0
3818  */
3821 
3822 /**
3823  * The given character is mapped to its lowercase equivalent according to
3824  * UnicodeData.txt; if the character has no lowercase equivalent, the character
3825  * itself is returned.
3826  *
3827  * Same as java.lang.Character.toLowerCase().
3828  *
3829  * This function only returns the simple, single-code point case mapping.
3830  * Full case mappings should be used whenever possible because they produce
3831  * better results by working on whole strings.
3832  * They take into account the string context and the language and can map
3833  * to a result string with a different length as appropriate.
3834  * Full case mappings are applied by the string case mapping functions,
3835  * see ustring.h and the UnicodeString class.
3836  * See also the User Guide chapter on C/POSIX migration:
3837  * http://icu-project.org/userguide/posix.html#case_mappings
3838  *
3839  * @param c the code point to be mapped
3840  * @return the Simple_Lowercase_Mapping of the code point, if any;
3841  * otherwise the code point itself.
3842  * @stable ICU 2.0
3843  */
3846 
3847 /**
3848  * The given character is mapped to its uppercase equivalent according to UnicodeData.txt;
3849  * if the character has no uppercase equivalent, the character itself is
3850  * returned.
3851  *
3852  * Same as java.lang.Character.toUpperCase().
3853  *
3854  * This function only returns the simple, single-code point case mapping.
3855  * Full case mappings should be used whenever possible because they produce
3856  * better results by working on whole strings.
3857  * They take into account the string context and the language and can map
3858  * to a result string with a different length as appropriate.
3859  * Full case mappings are applied by the string case mapping functions,
3860  * see ustring.h and the UnicodeString class.
3861  * See also the User Guide chapter on C/POSIX migration:
3862  * http://icu-project.org/userguide/posix.html#case_mappings
3863  *
3864  * @param c the code point to be mapped
3865  * @return the Simple_Uppercase_Mapping of the code point, if any;
3866  * otherwise the code point itself.
3867  * @stable ICU 2.0
3868  */
3871 
3872 /**
3873  * The given character is mapped to its titlecase equivalent
3874  * according to UnicodeData.txt;
3875  * if none is defined, the character itself is returned.
3876  *
3877  * Same as java.lang.Character.toTitleCase().
3878  *
3879  * This function only returns the simple, single-code point case mapping.
3880  * Full case mappings should be used whenever possible because they produce
3881  * better results by working on whole strings.
3882  * They take into account the string context and the language and can map
3883  * to a result string with a different length as appropriate.
3884  * Full case mappings are applied by the string case mapping functions,
3885  * see ustring.h and the UnicodeString class.
3886  * See also the User Guide chapter on C/POSIX migration:
3887  * http://icu-project.org/userguide/posix.html#case_mappings
3888  *
3889  * @param c the code point to be mapped
3890  * @return the Simple_Titlecase_Mapping of the code point, if any;
3891  * otherwise the code point itself.
3892  * @stable ICU 2.0
3893  */
3896 
3897 /**
3898  * The given character is mapped to its case folding equivalent according to
3899  * UnicodeData.txt and CaseFolding.txt;
3900  * if the character has no case folding equivalent, the character
3901  * itself is returned.
3902  *
3903  * This function only returns the simple, single-code point case mapping.
3904  * Full case mappings should be used whenever possible because they produce
3905  * better results by working on whole strings.
3906  * They take into account the string context and the language and can map
3907  * to a result string with a different length as appropriate.
3908  * Full case mappings are applied by the string case mapping functions,
3909  * see ustring.h and the UnicodeString class.
3910  * See also the User Guide chapter on C/POSIX migration:
3911  * http://icu-project.org/userguide/posix.html#case_mappings
3912  *
3913  * @param c the code point to be mapped
3914  * @param options Either U_FOLD_CASE_DEFAULT or U_FOLD_CASE_EXCLUDE_SPECIAL_I
3915  * @return the Simple_Case_Folding of the code point, if any;
3916  * otherwise the code point itself.
3917  * @stable ICU 2.0
3918  */
3921 
3922 /**
3923  * Returns the decimal digit value of the code point in the
3924  * specified radix.
3925  *
3926  * If the radix is not in the range <code>2<=radix<=36</code> or if the
3927  * value of <code>c</code> is not a valid digit in the specified
3928  * radix, <code>-1</code> is returned. A character is a valid digit
3929  * if at least one of the following is true:
3930  * <ul>
3931  * <li>The character has a decimal digit value.
3932  * Such characters have the general category "Nd" (decimal digit numbers)
3933  * and a Numeric_Type of Decimal.
3934  * In this case the value is the character's decimal digit value.</li>
3935  * <li>The character is one of the uppercase Latin letters
3936  * <code>'A'</code> through <code>'Z'</code>.
3937  * In this case the value is <code>c-'A'+10</code>.</li>
3938  * <li>The character is one of the lowercase Latin letters
3939  * <code>'a'</code> through <code>'z'</code>.
3940  * In this case the value is <code>ch-'a'+10</code>.</li>
3941  * <li>Latin letters from both the ASCII range (0061..007A, 0041..005A)
3942  * as well as from the Fullwidth ASCII range (FF41..FF5A, FF21..FF3A)
3943  * are recognized.</li>
3944  * </ul>
3945  *
3946  * Same as java.lang.Character.digit().
3947  *
3948  * @param ch the code point to be tested.
3949  * @param radix the radix.
3950  * @return the numeric value represented by the character in the
3951  * specified radix,
3952  * or -1 if there is no value or if the value exceeds the radix.
3953  *
3954  * @see UCHAR_NUMERIC_TYPE
3955  * @see u_forDigit
3956  * @see u_charDigitValue
3957  * @see u_isdigit
3958  * @stable ICU 2.0
3959  */
3962 
3963 /**
3964  * Determines the character representation for a specific digit in
3965  * the specified radix. If the value of <code>radix</code> is not a
3966  * valid radix, or the value of <code>digit</code> is not a valid
3967  * digit in the specified radix, the null character
3968  * (<code>U+0000</code>) is returned.
3969  * <p>
3970  * The <code>radix</code> argument is valid if it is greater than or
3971  * equal to 2 and less than or equal to 36.
3972  * The <code>digit</code> argument is valid if
3973  * <code>0 <= digit < radix</code>.
3974  * <p>
3975  * If the digit is less than 10, then
3976  * <code>'0' + digit</code> is returned. Otherwise, the value
3977  * <code>'a' + digit - 10</code> is returned.
3978  *
3979  * Same as java.lang.Character.forDigit().
3980  *
3981  * @param digit the number to convert to a character.
3982  * @param radix the radix.
3983  * @return the <code>char</code> representation of the specified digit
3984  * in the specified radix.
3985  *
3986  * @see u_digit
3987  * @see u_charDigitValue
3988  * @see u_isdigit
3989  * @stable ICU 2.0
3990  */
3993 
3994 /**
3995  * Get the "age" of the code point.
3996  * The "age" is the Unicode version when the code point was first
3997  * designated (as a non-character or for Private Use)
3998  * or assigned a character.
3999  * This can be useful to avoid emitting code points to receiving
4000  * processes that do not accept newer characters.
4001  * The data is from the UCD file DerivedAge.txt.
4002  *
4003  * @param c The code point.
4004  * @param versionArray The Unicode version number array, to be filled in.
4005  *
4006  * @stable ICU 2.1
4007  */
4008 U_CAPI void U_EXPORT2
4009 u_charAge(UChar32 c, UVersionInfo versionArray);
4010 
4011 /**
4012  * Gets the Unicode version information.
4013  * The version array is filled in with the version information
4014  * for the Unicode standard that is currently used by ICU.
4015  * For example, Unicode version 3.1.1 is represented as an array with
4016  * the values { 3, 1, 1, 0 }.
4017  *
4018  * @param versionArray an output array that will be filled in with
4019  * the Unicode version number
4020  * @stable ICU 2.0
4021  */
4022 U_CAPI void U_EXPORT2
4023 u_getUnicodeVersion(UVersionInfo versionArray);
4024 
4025 #if !UCONFIG_NO_NORMALIZATION
4026 /**
4027  * Get the FC_NFKC_Closure property string for a character.
4028  * See Unicode Standard Annex #15 for details, search for "FC_NFKC_Closure"
4029  * or for "FNC": http://www.unicode.org/reports/tr15/
4030  *
4031  * @param c The character (code point) for which to get the FC_NFKC_Closure string.
4032  * It must be <code>0<=c<=0x10ffff</code>.
4033  * @param dest Destination address for copying the string.
4034  * The string will be zero-terminated if possible.
4035  * If there is no FC_NFKC_Closure string,
4036  * then the buffer will be set to the empty string.
4037  * @param destCapacity <code>==sizeof(dest)</code>
4038  * @param pErrorCode Pointer to a UErrorCode variable.
4039  * @return The length of the string, or 0 if there is no FC_NFKC_Closure string for this character.
4040  * If the destCapacity is less than or equal to the length, then the buffer
4041  * contains the truncated name and the returned length indicates the full
4042  * length of the name.
4043  * The length does not include the zero-termination.
4044  *
4045  * @stable ICU 2.2
4046  */
4048 u_getFC_NFKC_Closure(UChar32 c, UChar *dest, int32_t destCapacity, UErrorCode *pErrorCode);
4049 
4050 #endif
4051 
4052 
4054 
4055 #endif /*_UCHAR*/
4056 /*eof*/
#define type(a)
Definition: aptex-macros.h:171
#define name
static int radix
Definition: aptex.h:450
char * digit
Definition: io.c:63
#define c(n)
Definition: gpos-common.c:150
unsigned char UChar
Definition: bzip2.c:163
unsigned int uint32_t
Definition: stdint.h:80
signed int int32_t
Definition: stdint.h:77
unsigned char uint8_t
Definition: stdint.h:78
signed char int8_t
Definition: stdint.h:75
const char * alias
Definition: nkf.c:1121
#define length(c)
Definition: ctangleboot.c:65
#define dest
#define U_CALLCONV
Definition: platform.h:877
#define U_EXPORT2
Definition: platform.h:844
string fn
Definition: fc-lang.py:335
C API: Bit set option bit constants for various string and character processing functions.
Definition: utils.c:300
Definition: inftrees.h:24
ch
Definition: t4ht.c:1443
UBlockCode
Definition: uchar.h:1020
@ UBLOCK_NANDINAGARI
Definition: uchar.h:1777
@ UBLOCK_MRO
Definition: uchar.h:1648
@ UBLOCK_UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS_EXTENDED
Definition: uchar.h:1511
@ UBLOCK_COUNT
Definition: uchar.h:1817
@ UBLOCK_OPTICAL_CHARACTER_RECOGNITION
Definition: uchar.h:1184
@ UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_B
Definition: uchar.h:1330
@ UBLOCK_INSCRIPTIONAL_PAHLAVI
Definition: uchar.h:1545
@ UBLOCK_KHMER
Definition: uchar.h:1139
@ UBLOCK_BHAIKSUKI
Definition: uchar.h:1708
@ UBLOCK_DUPLOYAN
Definition: uchar.h:1624
@ UBLOCK_MEDEFAIDRIN
Definition: uchar.h:1764
@ UBLOCK_BALINESE
Definition: uchar.h:1453
@ UBLOCK_HEBREW
Definition: uchar.h:1064
@ UBLOCK_YIJING_HEXAGRAM_SYMBOLS
Definition: uchar.h:1385
@ UBLOCK_SUPPLEMENTAL_SYMBOLS_AND_PICTOGRAPHS
Definition: uchar.h:1699
@ UBLOCK_CYRILLIC
Definition: uchar.h:1058
@ UBLOCK_SPECIALS
Definition: uchar.h:1310
@ UBLOCK_HALFWIDTH_AND_FULLWIDTH_FORMS
Definition: uchar.h:1313
@ UBLOCK_NEWA
Definition: uchar.h:1720
@ UBLOCK_ARROWS
Definition: uchar.h:1172
@ UBLOCK_CJK_SYMBOLS_AND_PUNCTUATION
Definition: uchar.h:1217
@ UBLOCK_TAKRI
Definition: uchar.h:1611
@ UBLOCK_BOX_DRAWING
Definition: uchar.h:1190
@ UBLOCK_CURRENCY_SYMBOLS
Definition: uchar.h:1157
@ UBLOCK_MISCELLANEOUS_SYMBOLS
Definition: uchar.h:1199
@ UBLOCK_ANCIENT_GREEK_NUMBERS
Definition: uchar.h:1410
@ UBLOCK_OLD_PERMIC
Definition: uchar.h:1656
@ UBLOCK_CJK_STROKES
Definition: uchar.h:1416
@ UBLOCK_PALMYRENE
Definition: uchar.h:1662
@ UBLOCK_OGHAM
Definition: uchar.h:1133
@ UBLOCK_SUTTON_SIGNWRITING
Definition: uchar.h:1701
@ UBLOCK_ANATOLIAN_HIEROGLYPHS
Definition: uchar.h:1685
@ UBLOCK_SYMBOLS_FOR_LEGACY_COMPUTING
Definition: uchar.h:1804
@ UBLOCK_SUPPLEMENTAL_PUNCTUATION
Definition: uchar.h:1440
@ UBLOCK_MEROITIC_HIEROGLYPHS
Definition: uchar.h:1601
@ UBLOCK_EMOTICONS
Definition: uchar.h:1580
@ UBLOCK_INDIC_SIYAQ_NUMBERS
Definition: uchar.h:1758
@ UBLOCK_REJANG
Definition: uchar.h:1488
@ UBLOCK_TAGALOG
Definition: uchar.h:1346
@ UBLOCK_LISU
Definition: uchar.h:1517
@ UBLOCK_COPTIC_EPACT_NUMBERS
Definition: uchar.h:1620
@ UBLOCK_SUPERSCRIPTS_AND_SUBSCRIPTS
Definition: uchar.h:1154
@ UBLOCK_TAGS
Definition: uchar.h:1334
@ UBLOCK_MIAO
Definition: uchar.h:1603
@ UBLOCK_TAMIL_SUPPLEMENT
Definition: uchar.h:1787
@ UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_C
Definition: uchar.h:1559
@ UBLOCK_LIMBU
Definition: uchar.h:1375
@ UBLOCK_LYDIAN
Definition: uchar.h:1500
@ UBLOCK_NYIAKENG_PUACHUE_HMONG
Definition: uchar.h:1779
@ UBLOCK_PHONETIC_EXTENSIONS_SUPPLEMENT
Definition: uchar.h:1438
@ UBLOCK_TAI_THAM
Definition: uchar.h:1513
@ UBLOCK_MAHJONG_TILES
Definition: uchar.h:1502
@ UBLOCK_PLAYING_CARDS
Definition: uchar.h:1576
@ UBLOCK_TRANSPORT_AND_MAP_SYMBOLS
Definition: uchar.h:1582
@ UBLOCK_IDEOGRAPHIC_DESCRIPTION_CHARACTERS
Definition: uchar.h:1214
@ UBLOCK_BASIC_LATIN
Definition: uchar.h:1031
@ UBLOCK_GURMUKHI
Definition: uchar.h:1082
@ UBLOCK_SYMBOLS_AND_PICTOGRAPHS_EXTENDED_A
Definition: uchar.h:1785
@ UBLOCK_HATRAN
Definition: uchar.h:1693
@ UBLOCK_PRIVATE_USE_AREA
Definition: uchar.h:1276
@ UBLOCK_ARMENIAN
Definition: uchar.h:1061
@ UBLOCK_HANGUL_JAMO
Definition: uchar.h:1121
@ UBLOCK_VERTICAL_FORMS
Definition: uchar.h:1446
@ UBLOCK_SINHALA_ARCHAIC_NUMBERS
Definition: uchar.h:1672
@ UBLOCK_SOGDIAN
Definition: uchar.h:1768
@ UBLOCK_TIRHUTA
Definition: uchar.h:1676
@ UBLOCK_ELBASAN
Definition: uchar.h:1626
@ UBLOCK_MATHEMATICAL_ALPHANUMERIC_SYMBOLS
Definition: uchar.h:1328
@ UBLOCK_KHITAN_SMALL_SCRIPT
Definition: uchar.h:1800
@ UBLOCK_NUMBER_FORMS
Definition: uchar.h:1169
@ UBLOCK_CHAM
Definition: uchar.h:1490
@ UBLOCK_TANGUT
Definition: uchar.h:1724
@ UBLOCK_TAMIL
Definition: uchar.h:1091
@ UBLOCK_BLOCK_ELEMENTS
Definition: uchar.h:1193
@ UBLOCK_ENCLOSED_ALPHANUMERIC_SUPPLEMENT
Definition: uchar.h:1555
@ UBLOCK_CUNEIFORM_NUMBERS_AND_PUNCTUATION
Definition: uchar.h:1465
@ UBLOCK_LEPCHA
Definition: uchar.h:1474
@ UBLOCK_COMBINING_DIACRITICAL_MARKS_SUPPLEMENT
Definition: uchar.h:1418
@ UBLOCK_VARIATION_SELECTORS_SUPPLEMENT
Definition: uchar.h:1403
@ UBLOCK_DOMINO_TILES
Definition: uchar.h:1504
@ UBLOCK_COMBINING_DIACRITICAL_MARKS_EXTENDED
Definition: uchar.h:1622
@ UBLOCK_EGYPTIAN_HIEROGLYPHS
Definition: uchar.h:1553
@ UBLOCK_IPA_EXTENSIONS
Definition: uchar.h:1043
@ UBLOCK_TANGUT_COMPONENTS
Definition: uchar.h:1726
@ UBLOCK_CHEROKEE_SUPPLEMENT
Definition: uchar.h:1687
@ UBLOCK_ELYMAIC
Definition: uchar.h:1775
@ UBLOCK_LATIN_EXTENDED_A
Definition: uchar.h:1037
@ UBLOCK_HANUNOO
Definition: uchar.h:1348
@ UBLOCK_LAO
Definition: uchar.h:1109
@ UBLOCK_SUNDANESE_SUPPLEMENT
Definition: uchar.h:1609
@ UBLOCK_CYRILLIC_EXTENDED_A
Definition: uchar.h:1478
@ UBLOCK_HANGUL_JAMO_EXTENDED_B
Definition: uchar.h:1535
@ UBLOCK_SAMARITAN
Definition: uchar.h:1509
@ UBLOCK_SUPPLEMENTAL_ARROWS_A
Definition: uchar.h:1356
@ UBLOCK_GLAGOLITIC
Definition: uchar.h:1428
@ UBLOCK_INSCRIPTIONAL_PARTHIAN
Definition: uchar.h:1543
@ UBLOCK_WARANG_CITI
Definition: uchar.h:1678
@ UBLOCK_MONGOLIAN
Definition: uchar.h:1142
@ UBLOCK_NKO
Definition: uchar.h:1451
@ UBLOCK_ARABIC_EXTENDED_A
Definition: uchar.h:1591
@ UBLOCK_LYCIAN
Definition: uchar.h:1496
@ UBLOCK_CYRILLIC_EXTENDED_C
Definition: uchar.h:1710
@ UBLOCK_DINGBATS
Definition: uchar.h:1202
@ UBLOCK_OTTOMAN_SIYAQ_NUMBERS
Definition: uchar.h:1781
@ UBLOCK_LINEAR_B_SYLLABARY
Definition: uchar.h:1387
@ UBLOCK_ENCLOSED_CJK_LETTERS_AND_MONTHS
Definition: uchar.h:1238
@ UBLOCK_CHAKMA
Definition: uchar.h:1595
@ UBLOCK_SPACING_MODIFIER_LETTERS
Definition: uchar.h:1046
@ UBLOCK_MEROITIC_CURSIVE
Definition: uchar.h:1599
@ UBLOCK_CYRILLIC_EXTENDED_B
Definition: uchar.h:1482
@ UBLOCK_GENERAL_PUNCTUATION
Definition: uchar.h:1151
@ UBLOCK_MONGOLIAN_SUPPLEMENT
Definition: uchar.h:1718
@ UBLOCK_MISCELLANEOUS_TECHNICAL
Definition: uchar.h:1178
@ UBLOCK_TAI_XUAN_JING_SYMBOLS
Definition: uchar.h:1401
@ UBLOCK_NABATAEAN
Definition: uchar.h:1652
@ UBLOCK_TAGBANWA
Definition: uchar.h:1352
@ UBLOCK_CUNEIFORM
Definition: uchar.h:1463
@ UBLOCK_CONTROL_PICTURES
Definition: uchar.h:1181
@ UBLOCK_GREEK
Definition: uchar.h:1055
@ UBLOCK_HIGH_SURROGATES
Definition: uchar.h:1259
@ UBLOCK_COUNTING_ROD_NUMERALS
Definition: uchar.h:1467
@ UBLOCK_AEGEAN_NUMBERS
Definition: uchar.h:1391
@ UBLOCK_BENGALI
Definition: uchar.h:1079
@ UBLOCK_LATIN_EXTENDED_E
Definition: uchar.h:1636
@ UBLOCK_LINEAR_B_IDEOGRAMS
Definition: uchar.h:1389
@ UBLOCK_PAU_CIN_HAU
Definition: uchar.h:1664
@ UBLOCK_BUHID
Definition: uchar.h:1350
@ UBLOCK_GUNJALA_GONDI
Definition: uchar.h:1754
@ UBLOCK_RUMI_NUMERAL_SYMBOLS
Definition: uchar.h:1549
@ UBLOCK_HIGH_PRIVATE_USE_SURROGATES
Definition: uchar.h:1262
@ UBLOCK_MEETEI_MAYEK_EXTENSIONS
Definition: uchar.h:1597
@ UBLOCK_COMMON_INDIC_NUMBER_FORMS
Definition: uchar.h:1521
@ UBLOCK_ZANABAZAR_SQUARE
Definition: uchar.h:1743
@ UBLOCK_SUNDANESE
Definition: uchar.h:1472
@ UBLOCK_CHESS_SYMBOLS
Definition: uchar.h:1748
@ UBLOCK_ENCLOSED_ALPHANUMERICS
Definition: uchar.h:1187
@ UBLOCK_COMBINING_HALF_MARKS
Definition: uchar.h:1298
@ UBLOCK_MANDAIC
Definition: uchar.h:1564
@ UBLOCK_GLAGOLITIC_SUPPLEMENT
Definition: uchar.h:1712
@ UBLOCK_OSMANYA
Definition: uchar.h:1397
@ UBLOCK_DOGRA
Definition: uchar.h:1750
@ UBLOCK_IMPERIAL_ARAMAIC
Definition: uchar.h:1537
@ UBLOCK_BRAILLE_PATTERNS
Definition: uchar.h:1205
@ UBLOCK_OLD_HUNGARIAN
Definition: uchar.h:1697
@ UBLOCK_MATHEMATICAL_OPERATORS
Definition: uchar.h:1175
@ UBLOCK_KHOJKI
Definition: uchar.h:1632
@ UBLOCK_DIVES_AKURU
Definition: uchar.h:1798
@ UBLOCK_ORIYA
Definition: uchar.h:1088
@ UBLOCK_NO_BLOCK
Definition: uchar.h:1028
@ UBLOCK_YI_RADICALS
Definition: uchar.h:1253
@ UBLOCK_BUGINESE
Definition: uchar.h:1414
@ UBLOCK_TANGUT_SUPPLEMENT
Definition: uchar.h:1806
@ UBLOCK_SMALL_FORM_VARIANTS
Definition: uchar.h:1304
@ UBLOCK_OLD_SOGDIAN
Definition: uchar.h:1766
@ UBLOCK_GEORGIAN_EXTENDED
Definition: uchar.h:1752
@ UBLOCK_TIFINAGH
Definition: uchar.h:1444
@ UBLOCK_MISCELLANEOUS_MATHEMATICAL_SYMBOLS_B
Definition: uchar.h:1360
@ UBLOCK_LATIN_EXTENDED_D
Definition: uchar.h:1457
@ UBLOCK_LATIN_EXTENDED_ADDITIONAL
Definition: uchar.h:1145
@ UBLOCK_MEETEI_MAYEK
Definition: uchar.h:1533
@ UBLOCK_EGYPTIAN_HIEROGLYPH_FORMAT_CONTROLS
Definition: uchar.h:1773
@ UBLOCK_MYANMAR
Definition: uchar.h:1115
@ UBLOCK_OL_CHIKI
Definition: uchar.h:1476
@ UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_D
Definition: uchar.h:1586
@ UBLOCK_SHORTHAND_FORMAT_CONTROLS
Definition: uchar.h:1668
@ UBLOCK_COMBINING_MARKS_FOR_SYMBOLS
Definition: uchar.h:1163
@ UBLOCK_MISCELLANEOUS_SYMBOLS_AND_PICTOGRAPHS
Definition: uchar.h:1578
@ UBLOCK_UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS
Definition: uchar.h:1130
@ UBLOCK_BOPOMOFO
Definition: uchar.h:1226
@ UBLOCK_KATAKANA_PHONETIC_EXTENSIONS
Definition: uchar.h:1364
@ UBLOCK_MARCHEN
Definition: uchar.h:1716
@ UBLOCK_MODI
Definition: uchar.h:1646
@ UBLOCK_YEZIDI
Definition: uchar.h:1808
@ UBLOCK_SUPPLEMENTAL_MATHEMATICAL_OPERATORS
Definition: uchar.h:1362
@ UBLOCK_MULTANI
Definition: uchar.h:1695
@ UBLOCK_ETHIOPIC_EXTENDED
Definition: uchar.h:1422
@ UBLOCK_AVESTAN
Definition: uchar.h:1541
@ UBLOCK_PRIVATE_USE
Definition: uchar.h:1286
@ UBLOCK_GEORGIAN_SUPPLEMENT
Definition: uchar.h:1426
@ UBLOCK_COPTIC
Definition: uchar.h:1420
@ UBLOCK_HANGUL_COMPATIBILITY_JAMO
Definition: uchar.h:1229
@ UBLOCK_LOW_SURROGATES
Definition: uchar.h:1265
@ UBLOCK_SOYOMBO
Definition: uchar.h:1739
@ UBLOCK_ARABIC_SUPPLEMENT
Definition: uchar.h:1412
@ UBLOCK_HANGUL_SYLLABLES
Definition: uchar.h:1256
@ UBLOCK_MISCELLANEOUS_SYMBOLS_AND_ARROWS
Definition: uchar.h:1383
@ UBLOCK_CJK_COMPATIBILITY
Definition: uchar.h:1241
@ UBLOCK_CARIAN
Definition: uchar.h:1498
@ UBLOCK_HANIFI_ROHINGYA
Definition: uchar.h:1756
@ UBLOCK_TIBETAN
Definition: uchar.h:1112
@ UBLOCK_BASSA_VAH
Definition: uchar.h:1616
@ UBLOCK_OLD_TURKIC
Definition: uchar.h:1547
@ UBLOCK_CJK_RADICALS_SUPPLEMENT
Definition: uchar.h:1208
@ UBLOCK_ADLAM
Definition: uchar.h:1706
@ UBLOCK_MASARAM_GONDI
Definition: uchar.h:1735
@ UBLOCK_ARABIC_PRESENTATION_FORMS_B
Definition: uchar.h:1307
@ UBLOCK_RUNIC
Definition: uchar.h:1136
@ UBLOCK_ARABIC_PRESENTATION_FORMS_A
Definition: uchar.h:1295
@ UBLOCK_ENCLOSED_IDEOGRAPHIC_SUPPLEMENT
Definition: uchar.h:1557
@ UBLOCK_CHORASMIAN
Definition: uchar.h:1794
@ UBLOCK_BOPOMOFO_EXTENDED
Definition: uchar.h:1235
@ UBLOCK_IDEOGRAPHIC_SYMBOLS_AND_PUNCTUATION
Definition: uchar.h:1714
@ UBLOCK_KANGXI_RADICALS
Definition: uchar.h:1211
@ UBLOCK_SORA_SOMPENG
Definition: uchar.h:1607
@ UBLOCK_KANA_SUPPLEMENT
Definition: uchar.h:1574
@ UBLOCK_CHEROKEE
Definition: uchar.h:1127
@ UBLOCK_BRAHMI
Definition: uchar.h:1570
@ UBLOCK_SYLOTI_NAGRI
Definition: uchar.h:1442
@ UBLOCK_CYPRIOT_SYLLABARY
Definition: uchar.h:1399
@ UBLOCK_ETHIOPIC_SUPPLEMENT
Definition: uchar.h:1424
@ UBLOCK_KHAROSHTHI
Definition: uchar.h:1430
@ UBLOCK_OLD_ITALIC
Definition: uchar.h:1318
@ UBLOCK_OLD_SOUTH_ARABIAN
Definition: uchar.h:1539
@ UBLOCK_SUPPLEMENTARY_PRIVATE_USE_AREA_B
Definition: uchar.h:1370
@ UBLOCK_MALAYALAM
Definition: uchar.h:1100
@ UBLOCK_KHMER_SYMBOLS
Definition: uchar.h:1379
@ UBLOCK_JAVANESE
Definition: uchar.h:1527
@ UBLOCK_BAMUM_SUPPLEMENT
Definition: uchar.h:1572
@ UBLOCK_CYRILLIC_SUPPLEMENT
Definition: uchar.h:1339
@ UBLOCK_MYANMAR_EXTENDED_B
Definition: uchar.h:1650
@ UBLOCK_ANCIENT_GREEK_MUSICAL_NOTATION
Definition: uchar.h:1408
@ UBLOCK_BATAK
Definition: uchar.h:1566
@ UBLOCK_SYRIAC_SUPPLEMENT
Definition: uchar.h:1741
@ UBLOCK_PAHAWH_HMONG
Definition: uchar.h:1660
@ UBLOCK_ORNAMENTAL_DINGBATS
Definition: uchar.h:1658
@ UBLOCK_SINHALA
Definition: uchar.h:1103
@ UBLOCK_AHOM
Definition: uchar.h:1683
@ UBLOCK_NEW_TAI_LUE
Definition: uchar.h:1434
@ UBLOCK_SIDDHAM
Definition: uchar.h:1670
@ UBLOCK_OLD_NORTH_ARABIAN
Definition: uchar.h:1654
@ UBLOCK_YI_SYLLABLES
Definition: uchar.h:1250
@ UBLOCK_TELUGU
Definition: uchar.h:1094
@ UBLOCK_DEVANAGARI_EXTENDED
Definition: uchar.h:1523
@ UBLOCK_SHARADA
Definition: uchar.h:1605
@ UBLOCK_SUPPLEMENTARY_PRIVATE_USE_AREA_A
Definition: uchar.h:1368
@ UBLOCK_DESERET
Definition: uchar.h:1322
@ UBLOCK_ARABIC_MATHEMATICAL_ALPHABETIC_SYMBOLS
Definition: uchar.h:1593
@ UBLOCK_SAURASHTRA
Definition: uchar.h:1484
@ UBLOCK_KANBUN
Definition: uchar.h:1232
@ UBLOCK_HIRAGANA
Definition: uchar.h:1220
@ UBLOCK_KANNADA
Definition: uchar.h:1097
@ UBLOCK_SUPPLEMENTAL_ARROWS_C
Definition: uchar.h:1674
@ UBLOCK_GEORGIAN
Definition: uchar.h:1118
@ UBLOCK_DEVANAGARI
Definition: uchar.h:1076
@ UBLOCK_LISU_SUPPLEMENT
Definition: uchar.h:1802
@ UBLOCK_KATAKANA
Definition: uchar.h:1223
@ UBLOCK_TAI_VIET
Definition: uchar.h:1531
@ UBLOCK_LATIN_EXTENDED_B
Definition: uchar.h:1040
@ UBLOCK_THAANA
Definition: uchar.h:1073
@ UBLOCK_MODIFIER_TONE_LETTERS
Definition: uchar.h:1432
@ UBLOCK_KHUDAWADI
Definition: uchar.h:1634
@ UBLOCK_LINEAR_A
Definition: uchar.h:1638
@ UBLOCK_CJK_UNIFIED_IDEOGRAPHS
Definition: uchar.h:1247
@ UBLOCK_GRANTHA
Definition: uchar.h:1630
@ UBLOCK_ETHIOPIC
Definition: uchar.h:1124
@ UBLOCK_SYRIAC
Definition: uchar.h:1070
@ UBLOCK_GREEK_EXTENDED
Definition: uchar.h:1148
@ UBLOCK_CJK_COMPATIBILITY_FORMS
Definition: uchar.h:1301
@ UBLOCK_CJK_COMPATIBILITY_IDEOGRAPHS
Definition: uchar.h:1289
@ UBLOCK_MAYAN_NUMERALS
Definition: uchar.h:1762
@ UBLOCK_KAYAH_LI
Definition: uchar.h:1486
@ UBLOCK_VEDIC_EXTENSIONS
Definition: uchar.h:1515
@ UBLOCK_PHAISTOS_DISC
Definition: uchar.h:1494
@ UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_A
Definition: uchar.h:1244
@ UBLOCK_LATIN_1_SUPPLEMENT
Definition: uchar.h:1034
@ UBLOCK_PHOENICIAN
Definition: uchar.h:1461
@ UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_G
Definition: uchar.h:1796
@ UBLOCK_MISCELLANEOUS_MATHEMATICAL_SYMBOLS_A
Definition: uchar.h:1354
@ UBLOCK_CAUCASIAN_ALBANIAN
Definition: uchar.h:1618
@ UBLOCK_ALCHEMICAL_SYMBOLS
Definition: uchar.h:1584
@ UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_F
Definition: uchar.h:1731
@ UBLOCK_MYANMAR_EXTENDED_A
Definition: uchar.h:1529
@ UBLOCK_EARLY_DYNASTIC_CUNEIFORM
Definition: uchar.h:1691
@ UBLOCK_MENDE_KIKAKUI
Definition: uchar.h:1644
@ UBLOCK_VAI
Definition: uchar.h:1480
@ UBLOCK_PHONETIC_EXTENSIONS
Definition: uchar.h:1381
@ UBLOCK_PHAGS_PA
Definition: uchar.h:1459
@ UBLOCK_OLD_PERSIAN
Definition: uchar.h:1436
@ UBLOCK_KAITHI
Definition: uchar.h:1551
@ UBLOCK_GEOMETRIC_SHAPES
Definition: uchar.h:1196
@ UBLOCK_LATIN_EXTENDED_C
Definition: uchar.h:1455
@ UBLOCK_SUPPLEMENTAL_ARROWS_B
Definition: uchar.h:1358
@ UBLOCK_MAHAJANI
Definition: uchar.h:1640
@ UBLOCK_OSAGE
Definition: uchar.h:1722
@ UBLOCK_INVALID_CODE
Definition: uchar.h:1821
@ UBLOCK_TAI_LE
Definition: uchar.h:1377
@ UBLOCK_MAKASAR
Definition: uchar.h:1760
@ UBLOCK_GOTHIC
Definition: uchar.h:1320
@ UBLOCK_ETHIOPIC_EXTENDED_A
Definition: uchar.h:1568
@ UBLOCK_GEOMETRIC_SHAPES_EXTENDED
Definition: uchar.h:1628
@ UBLOCK_MANICHAEAN
Definition: uchar.h:1642
@ UBLOCK_ALPHABETIC_PRESENTATION_FORMS
Definition: uchar.h:1292
@ UBLOCK_MUSICAL_SYMBOLS
Definition: uchar.h:1326
@ UBLOCK_LETTERLIKE_SYMBOLS
Definition: uchar.h:1166
@ UBLOCK_ARABIC
Definition: uchar.h:1067
@ UBLOCK_NUSHU
Definition: uchar.h:1737
@ UBLOCK_CYRILLIC_SUPPLEMENTARY
Definition: uchar.h:1344
@ UBLOCK_HANGUL_JAMO_EXTENDED_A
Definition: uchar.h:1525
@ UBLOCK_BYZANTINE_MUSICAL_SYMBOLS
Definition: uchar.h:1324
@ UBLOCK_ANCIENT_SYMBOLS
Definition: uchar.h:1492
@ UBLOCK_UGARITIC
Definition: uchar.h:1393
@ UBLOCK_SMALL_KANA_EXTENSION
Definition: uchar.h:1783
@ UBLOCK_GUJARATI
Definition: uchar.h:1085
@ UBLOCK_CJK_COMPATIBILITY_IDEOGRAPHS_SUPPLEMENT
Definition: uchar.h:1332
@ UBLOCK_COMBINING_DIACRITICAL_MARKS
Definition: uchar.h:1049
@ UBLOCK_PSALTER_PAHLAVI
Definition: uchar.h:1666
@ UBLOCK_THAI
Definition: uchar.h:1106
@ UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_E
Definition: uchar.h:1689
@ UBLOCK_KANA_EXTENDED_A
Definition: uchar.h:1733
@ UBLOCK_VARIATION_SELECTORS
Definition: uchar.h:1366
@ UBLOCK_BAMUM
Definition: uchar.h:1519
@ UBLOCK_WANCHO
Definition: uchar.h:1789
@ UBLOCK_SHAVIAN
Definition: uchar.h:1395
UCharNameChoice
Definition: uchar.h:1869
@ U_CHAR_NAME_CHOICE_COUNT
Definition: uchar.h:1889
@ U_UNICODE_10_CHAR_NAME
Definition: uchar.h:1878
@ U_CHAR_NAME_ALIAS
Definition: uchar.h:1883
@ U_EXTENDED_CHAR_NAME
Definition: uchar.h:1881
@ U_UNICODE_CHAR_NAME
Definition: uchar.h:1871
UJoiningType
Definition: uchar.h:1966
@ U_JT_NON_JOINING
Definition: uchar.h:1973
@ U_JT_LEFT_JOINING
Definition: uchar.h:1976
@ U_JT_TRANSPARENT
Definition: uchar.h:1978
@ U_JT_JOIN_CAUSING
Definition: uchar.h:1974
@ U_JT_RIGHT_JOINING
Definition: uchar.h:1977
@ U_JT_DUAL_JOINING
Definition: uchar.h:1975
@ U_JT_COUNT
Definition: uchar.h:1986
UIndicPositionalCategory
Definition: uchar.h:2421
@ U_INPC_BOTTOM
Definition: uchar.h:2431
@ U_INPC_VISUAL_ORDER_LEFT
Definition: uchar.h:2457
@ U_INPC_TOP_AND_BOTTOM_AND_RIGHT
Definition: uchar.h:2449
@ U_INPC_TOP_AND_BOTTOM_AND_LEFT
Definition: uchar.h:2459
@ U_INPC_TOP_AND_RIGHT
Definition: uchar.h:2455
@ U_INPC_BOTTOM_AND_LEFT
Definition: uchar.h:2433
@ U_INPC_LEFT_AND_RIGHT
Definition: uchar.h:2439
@ U_INPC_RIGHT
Definition: uchar.h:2443
@ U_INPC_TOP_AND_LEFT_AND_RIGHT
Definition: uchar.h:2453
@ U_INPC_LEFT
Definition: uchar.h:2437
@ U_INPC_NA
Definition: uchar.h:2429
@ U_INPC_TOP
Definition: uchar.h:2445
@ U_INPC_TOP_AND_LEFT
Definition: uchar.h:2451
@ U_INPC_OVERSTRUCK
Definition: uchar.h:2441
@ U_INPC_TOP_AND_BOTTOM
Definition: uchar.h:2447
@ U_INPC_BOTTOM_AND_RIGHT
Definition: uchar.h:2435
UCharDirection
Definition: uchar.h:921
@ U_SEGMENT_SEPARATOR
Definition: uchar.h:946
@ U_EUROPEAN_NUMBER_TERMINATOR
Definition: uchar.h:938
@ U_BOUNDARY_NEUTRAL
Definition: uchar.h:966
@ U_RIGHT_TO_LEFT_ARABIC
Definition: uchar.h:956
@ U_RIGHT_TO_LEFT
Definition: uchar.h:932
@ U_POP_DIRECTIONAL_ISOLATE
Definition: uchar.h:974
@ U_COMMON_NUMBER_SEPARATOR
Definition: uchar.h:942
@ U_LEFT_TO_RIGHT
Definition: uchar.h:930
@ U_DIR_NON_SPACING_MARK
Definition: uchar.h:964
@ U_FIRST_STRONG_ISOLATE
Definition: uchar.h:968
@ U_ARABIC_NUMBER
Definition: uchar.h:940
@ U_POP_DIRECTIONAL_FORMAT
Definition: uchar.h:962
@ U_OTHER_NEUTRAL
Definition: uchar.h:950
@ U_CHAR_DIRECTION_COUNT
Definition: uchar.h:982
@ U_WHITE_SPACE_NEUTRAL
Definition: uchar.h:948
@ U_RIGHT_TO_LEFT_OVERRIDE
Definition: uchar.h:960
@ U_RIGHT_TO_LEFT_EMBEDDING
Definition: uchar.h:958
@ U_EUROPEAN_NUMBER_SEPARATOR
Definition: uchar.h:936
@ U_LEFT_TO_RIGHT_ISOLATE
Definition: uchar.h:970
@ U_LEFT_TO_RIGHT_OVERRIDE
Definition: uchar.h:954
@ U_EUROPEAN_NUMBER
Definition: uchar.h:934
@ U_BLOCK_SEPARATOR
Definition: uchar.h:944
@ U_LEFT_TO_RIGHT_EMBEDDING
Definition: uchar.h:952
@ U_RIGHT_TO_LEFT_ISOLATE
Definition: uchar.h:972
UPropertyNameChoice
Definition: uchar.h:1906
@ U_SHORT_PROPERTY_NAME
Definition: uchar.h:1907
@ U_LONG_PROPERTY_NAME
Definition: uchar.h:1908
@ U_PROPERTY_NAME_CHOICE_COUNT
Definition: uchar.h:1914
UBool UEnumCharNamesFn(void *context, UChar32 code, UCharNameChoice nameChoice, const char *name, int32_t length)
Definition: uchar.h:3537
ULineBreak
Definition: uchar.h:2280
@ U_LB_CARRIAGE_RETURN
Definition: uchar.h:2297
@ U_LB_ZWSPACE
Definition: uchar.h:2317
@ U_LB_COMPLEX_CONTEXT
Definition: uchar.h:2313
@ U_LB_OPEN_PUNCTUATION
Definition: uchar.h:2309
@ U_LB_CONTINGENT_BREAK
Definition: uchar.h:2294
@ U_LB_BREAK_BOTH
Definition: uchar.h:2290
@ U_LB_E_MODIFIER
Definition: uchar.h:2343
@ U_LB_BREAK_SYMBOLS
Definition: uchar.h:2316
@ U_LB_WORD_JOINER
Definition: uchar.h:2321
@ U_LB_CLOSE_PUNCTUATION
Definition: uchar.h:2295
@ U_LB_H3
Definition: uchar.h:2325
@ U_LB_H2
Definition: uchar.h:2323
@ U_LB_MANDATORY_BREAK
Definition: uchar.h:2293
@ U_LB_CONDITIONAL_JAPANESE_STARTER
Definition: uchar.h:2335
@ U_LB_COMBINING_MARK
Definition: uchar.h:2296
@ U_LB_NEXT_LINE
Definition: uchar.h:2319
@ U_LB_INSEPARABLE
Definition: uchar.h:2303
@ U_LB_SURROGATE
Definition: uchar.h:2314
@ U_LB_EXCLAMATION
Definition: uchar.h:2298
@ U_LB_BREAK_AFTER
Definition: uchar.h:2291
@ U_LB_E_BASE
Definition: uchar.h:2341
@ U_LB_POSTFIX_NUMERIC
Definition: uchar.h:2310
@ U_LB_JV
Definition: uchar.h:2331
@ U_LB_INSEPERABLE
Definition: uchar.h:2304
@ U_LB_PREFIX_NUMERIC
Definition: uchar.h:2311
@ U_LB_SPACE
Definition: uchar.h:2315
@ U_LB_NONSTARTER
Definition: uchar.h:2307
@ U_LB_JL
Definition: uchar.h:2327
@ U_LB_CLOSE_PARENTHESIS
Definition: uchar.h:2333
@ U_LB_NUMERIC
Definition: uchar.h:2308
@ U_LB_HYPHEN
Definition: uchar.h:2300
@ U_LB_QUOTATION
Definition: uchar.h:2312
@ U_LB_ALPHABETIC
Definition: uchar.h:2289
@ U_LB_ZWJ
Definition: uchar.h:2345
@ U_LB_INFIX_NUMERIC
Definition: uchar.h:2305
@ U_LB_COUNT
Definition: uchar.h:2353
@ U_LB_AMBIGUOUS
Definition: uchar.h:2288
@ U_LB_IDEOGRAPHIC
Definition: uchar.h:2301
@ U_LB_REGIONAL_INDICATOR
Definition: uchar.h:2339
@ U_LB_BREAK_BEFORE
Definition: uchar.h:2292
@ U_LB_HEBREW_LETTER
Definition: uchar.h:2337
@ U_LB_LINE_FEED
Definition: uchar.h:2306
@ U_LB_GLUE
Definition: uchar.h:2299
@ U_LB_JT
Definition: uchar.h:2329
@ U_LB_UNKNOWN
Definition: uchar.h:2287
UCharCategory
Definition: uchar.h:725
@ U_FORMAT_CHAR
Definition: uchar.h:768
@ U_SPACE_SEPARATOR
Definition: uchar.h:760
@ U_MODIFIER_SYMBOL
Definition: uchar.h:788
@ U_GENERAL_OTHER_TYPES
Definition: uchar.h:736
@ U_TITLECASE_LETTER
Definition: uchar.h:742
@ U_PRIVATE_USE_CHAR
Definition: uchar.h:770
@ U_OTHER_SYMBOL
Definition: uchar.h:790
@ U_UPPERCASE_LETTER
Definition: uchar.h:738
@ U_MODIFIER_LETTER
Definition: uchar.h:744
@ U_PARAGRAPH_SEPARATOR
Definition: uchar.h:764
@ U_OTHER_PUNCTUATION
Definition: uchar.h:782
@ U_ENCLOSING_MARK
Definition: uchar.h:750
@ U_INITIAL_PUNCTUATION
Definition: uchar.h:792
@ U_UNASSIGNED
Definition: uchar.h:734
@ U_CURRENCY_SYMBOL
Definition: uchar.h:786
@ U_COMBINING_SPACING_MARK
Definition: uchar.h:752
@ U_CONTROL_CHAR
Definition: uchar.h:766
@ U_OTHER_LETTER
Definition: uchar.h:746
@ U_NON_SPACING_MARK
Definition: uchar.h:748
@ U_START_PUNCTUATION
Definition: uchar.h:776
@ U_CONNECTOR_PUNCTUATION
Definition: uchar.h:780
@ U_END_PUNCTUATION
Definition: uchar.h:778
@ U_OTHER_NUMBER
Definition: uchar.h:758
@ U_LINE_SEPARATOR
Definition: uchar.h:762
@ U_DASH_PUNCTUATION
Definition: uchar.h:774
@ U_MATH_SYMBOL
Definition: uchar.h:784
@ U_CHAR_CATEGORY_COUNT
Definition: uchar.h:802
@ U_DECIMAL_DIGIT_NUMBER
Definition: uchar.h:754
@ U_LOWERCASE_LETTER
Definition: uchar.h:740
@ U_FINAL_PUNCTUATION
Definition: uchar.h:794
@ U_LETTER_NUMBER
Definition: uchar.h:756
@ U_SURROGATE
Definition: uchar.h:772
UVerticalOrientation
Definition: uchar.h:2555
@ U_VO_UPRIGHT
Definition: uchar.h:2569
@ U_VO_TRANSFORMED_UPRIGHT
Definition: uchar.h:2567
@ U_VO_ROTATED
Definition: uchar.h:2563
@ U_VO_TRANSFORMED_ROTATED
Definition: uchar.h:2565
UJoiningGroup
Definition: uchar.h:1996
@ U_JG_FE
Definition: uchar.h:2055
@ U_JG_BURUSHASKI_YEH_BARREE
Definition: uchar.h:2058
@ U_JG_MANICHAEAN_KAPH
Definition: uchar.h:2071
@ U_JG_SEMKATH
Definition: uchar.h:2040
@ U_JG_LAMADH
Definition: uchar.h:2027
@ U_JG_NUN
Definition: uchar.h:2031
@ U_JG_SWASH_KAF
Definition: uchar.h:2042
@ U_JG_SHIN
Definition: uchar.h:2041
@ U_JG_YUDH
Definition: uchar.h:2052
@ U_JG_ALAPH
Definition: uchar.h:2005
@ U_JG_MANICHAEAN_SAMEKH
Definition: uchar.h:2080
@ U_JG_MANICHAEAN_ZAYIN
Definition: uchar.h:2088
@ U_JG_MALAYALAM_TTA
Definition: uchar.h:2104
@ U_JG_ALEF
Definition: uchar.h:2006
@ U_JG_PE
Definition: uchar.h:2032
@ U_JG_MANICHAEAN_AYIN
Definition: uchar.h:2063
@ U_JG_MANICHAEAN_ALEPH
Definition: uchar.h:2062
@ U_JG_YEH
Definition: uchar.h:2049
@ U_JG_FARSI_YEH
Definition: uchar.h:2059
@ U_JG_MEEM
Definition: uchar.h:2028
@ U_JG_MANICHAEAN_DALETH
Definition: uchar.h:2065
@ U_JG_MANICHAEAN_FIVE
Definition: uchar.h:2067
@ U_JG_MANICHAEAN_SADHE
Definition: uchar.h:2079
@ U_JG_GAF
Definition: uchar.h:2014
@ U_JG_MANICHAEAN_TAW
Definition: uchar.h:2081
@ U_JG_MALAYALAM_LLLA
Definition: uchar.h:2097
@ U_JG_MALAYALAM_NNNA
Definition: uchar.h:2100
@ U_JG_DAL
Definition: uchar.h:2009
@ U_JG_MANICHAEAN_ONE
Definition: uchar.h:2075
@ U_JG_MALAYALAM_LLA
Definition: uchar.h:2096
@ U_JG_TETH
Definition: uchar.h:2047
@ U_JG_YUDH_HE
Definition: uchar.h:2053
@ U_JG_AFRICAN_FEH
Definition: uchar.h:2090
@ U_JG_HE
Definition: uchar.h:2019
@ U_JG_LAM
Definition: uchar.h:2026
@ U_JG_HANIFI_ROHINGYA_PA
Definition: uchar.h:2107
@ U_JG_MALAYALAM_BHA
Definition: uchar.h:2094
@ U_JG_BEH
Definition: uchar.h:2007
@ U_JG_MANICHAEAN_TWENTY
Definition: uchar.h:2085
@ U_JG_REH
Definition: uchar.h:2035
@ U_JG_ZAIN
Definition: uchar.h:2054
@ U_JG_MANICHAEAN_THAMEDH
Definition: uchar.h:2084
@ U_JG_MANICHAEAN_PE
Definition: uchar.h:2076
@ U_JG_GAMAL
Definition: uchar.h:2015
@ U_JG_FINAL_SEMKATH
Definition: uchar.h:2013
@ U_JG_SAD
Definition: uchar.h:2037
@ U_JG_ZHAIN
Definition: uchar.h:2057
@ U_JG_HEH_GOAL
Definition: uchar.h:2021
@ U_JG_MANICHAEAN_TETH
Definition: uchar.h:2083
@ U_JG_HETH
Definition: uchar.h:2022
@ U_JG_MANICHAEAN_BETH
Definition: uchar.h:2064
@ U_JG_COUNT
Definition: uchar.h:2116
@ U_JG_FEH
Definition: uchar.h:2012
@ U_JG_MANICHAEAN_TEN
Definition: uchar.h:2082
@ U_JG_SEEN
Definition: uchar.h:2039
@ U_JG_TAH
Definition: uchar.h:2044
@ U_JG_NOON
Definition: uchar.h:2030
@ U_JG_MANICHAEAN_GIMEL
Definition: uchar.h:2068
@ U_JG_KNOTTED_HEH
Definition: uchar.h:2025
@ U_JG_HAH
Definition: uchar.h:2016
@ U_JG_QAF
Definition: uchar.h:2033
@ U_JG_MIM
Definition: uchar.h:2029
@ U_JG_TEH_MARBUTA_GOAL
Definition: uchar.h:2017
@ U_JG_AFRICAN_NOON
Definition: uchar.h:2091
@ U_JG_HAMZA_ON_HEH_GOAL
Definition: uchar.h:2018
@ U_JG_E
Definition: uchar.h:2011
@ U_JG_MALAYALAM_NGA
Definition: uchar.h:2098