X-Git-Url: https://git.saurik.com/apple/icu.git/blobdiff_plain/374ca955a76ecab1204ca8bfa63ff9238d998416..249c4c5ea9376c24572daf9c2effa7484a282f14:/icuSources/common/unicode/uchar.h diff --git a/icuSources/common/unicode/uchar.h b/icuSources/common/unicode/uchar.h index 7fd490c8..6d31083e 100644 --- a/icuSources/common/unicode/uchar.h +++ b/icuSources/common/unicode/uchar.h @@ -1,6 +1,8 @@ +// © 2016 and later: Unicode, Inc. and others. +// License & terms of use: http://www.unicode.org/copyright.html /* ********************************************************************** -* Copyright (C) 1997-2004, International Business Machines +* Copyright (C) 1997-2016, International Business Machines * Corporation and others. All Rights Reserved. ********************************************************************** * @@ -24,6 +26,7 @@ #define UCHAR_H #include "unicode/utypes.h" +#include "unicode/stringoptions.h" U_CDECL_BEGIN @@ -39,7 +42,7 @@ U_CDECL_BEGIN * @see u_getUnicodeVersion * @stable ICU 2.0 */ -#define U_UNICODE_VERSION "4.0.1" +#define U_UNICODE_VERSION "11.0" /** * \file @@ -56,12 +59,12 @@ U_CDECL_BEGIN * * For more information see * "About the Unicode Character Database" (http://www.unicode.org/ucd/) - * and the ICU User Guide chapter on Properties (http://oss.software.ibm.com/icu/userguide/properties.html). + * and the ICU User Guide chapter on Properties (http://icu-project.org/userguide/properties.html). * * Many functions are designed to match java.lang.Character functions. * See the individual function documentation, - * and see the JDK 1.4.1 java.lang.Character documentation - * at http://java.sun.com/j2se/1.4.1/docs/api/java/lang/Character.html + * and see the JDK 1.4 java.lang.Character documentation + * at http://java.sun.com/j2se/1.4/docs/api/java/lang/Character.html * * There are also functions that provide easy migration from C/POSIX functions * like isblank(). Their use is generally discouraged because the C/POSIX @@ -77,22 +80,43 @@ U_CDECL_BEGIN * (In ICU, BreakIterator is the most sophisticated API for word boundaries.) * Another example: There is no "istitle()" class for titlecase characters. * - * A summary of the behavior of some C/POSIX character classification implementations - * for Unicode is available at http://oss.software.ibm.com/cvs/icu/~checkout~/icuhtml/design/posix_classes.html - * - * Important: - * The behavior of the ICU C/POSIX-style character classification - * functions is subject to change according to discussion of the above summary. + * ICU 3.4 and later provides API access for all twelve C/POSIX character classes. + * ICU implements them according to the Standard Recommendations in + * Annex C: Compatibility Properties of UTS #18 Unicode Regular Expressions + * (http://www.unicode.org/reports/tr18/#Compatibility_Properties). + * + * API access for C/POSIX character classes is as follows: + * - alpha: u_isUAlphabetic(c) or u_hasBinaryProperty(c, UCHAR_ALPHABETIC) + * - lower: u_isULowercase(c) or u_hasBinaryProperty(c, UCHAR_LOWERCASE) + * - upper: u_isUUppercase(c) or u_hasBinaryProperty(c, UCHAR_UPPERCASE) + * - punct: u_ispunct(c) + * - digit: u_isdigit(c) or u_charType(c)==U_DECIMAL_DIGIT_NUMBER + * - xdigit: u_isxdigit(c) or u_hasBinaryProperty(c, UCHAR_POSIX_XDIGIT) + * - alnum: u_hasBinaryProperty(c, UCHAR_POSIX_ALNUM) + * - space: u_isUWhiteSpace(c) or u_hasBinaryProperty(c, UCHAR_WHITE_SPACE) + * - blank: u_isblank(c) or u_hasBinaryProperty(c, UCHAR_POSIX_BLANK) + * - cntrl: u_charType(c)==U_CONTROL_CHAR + * - graph: u_hasBinaryProperty(c, UCHAR_POSIX_GRAPH) + * - print: u_hasBinaryProperty(c, UCHAR_POSIX_PRINT) + * + * Note: Some of the u_isxyz() functions in uchar.h predate, and do not match, + * the Standard Recommendations in UTS #18. Instead, they match Java + * functions according to their API documentation. + * + * \htmlonly + * The C/POSIX character classes are also available in UnicodeSet patterns, + * using patterns like [:graph:] or \p{graph}. + * \endhtmlonly * * Note: There are several ICU whitespace functions. * Comparison: * - u_isUWhiteSpace=UCHAR_WHITE_SPACE: Unicode White_Space property; * most of general categories "Z" (separators) + most whitespace ISO controls - * (including no-break spaces, but excluding IS1..IS4 and ZWSP) + * (including no-break spaces, but excluding IS1..IS4) * - u_isWhitespace: Java isWhitespace; Z + whitespace ISO controls but excluding no-break spaces * - u_isJavaSpaceChar: Java isSpaceChar; just Z (including no-break spaces) * - u_isspace: Z + whitespace ISO controls (including no-break spaces) - * - u_isblank: "horizontal spaces" = TAB + Zs - ZWSP + * - u_isblank: "horizontal spaces" = TAB + Zs */ /** @@ -118,19 +142,6 @@ U_CDECL_BEGIN */ #define U_MASK(x) ((uint32_t)1<<(x)) -/* - * !! Note: Several comments in this file are machine-read by the - * genpname tool. These comments describe the correspondence between - * icu enum constants and UCD entities. Do not delete them. Update - * these comments as needed. - * - * Any comment of the form "/ *[name]* /" (spaces added) is such - * a comment. - * - * The U_JG_* and U_GC_*_MASK constants are matched by their symbolic - * name, which must match PropertyValueAliases.txt. - */ - /** * Selection constants for Unicode properties. * These constants are used in functions like u_hasBinaryProperty to select @@ -138,8 +149,9 @@ U_CDECL_BEGIN * * The properties APIs are intended to reflect Unicode properties as defined * in the Unicode Character Database (UCD) and Unicode Technical Reports (UTR). - * For details about the properties see http://www.unicode.org/ucd/ . - * For names of Unicode properties see the UCD file PropertyAliases.txt. + * + * For details about the properties see + * UAX #44: Unicode Character Database (http://www.unicode.org/reports/tr44/). * * Important: If ICU is built with UCD files from Unicode versions below, e.g., 3.2, * then properties marked with "new in Unicode 3.2" are not or not fully available. @@ -151,9 +163,11 @@ U_CDECL_BEGIN * @stable ICU 2.1 */ typedef enum UProperty { - /* See note !!. Comments of the form "Binary property Dash", - "Enumerated property Script", "Double property Numeric_Value", - and "String property Age" are read by genpname. */ + /* + * Note: UProperty constants are parsed by preparseucd.py. + * It matches lines like + * UCHAR_=, + */ /* Note: Place UCHAR_ALPHABETIC before UCHAR_BINARY_START so that debuggers display UCHAR_ALPHABETIC as the symbolic name for 0, @@ -166,200 +180,286 @@ typedef enum UProperty { /** First constant for binary Unicode properties. @stable ICU 2.1 */ UCHAR_BINARY_START=UCHAR_ALPHABETIC, /** Binary property ASCII_Hex_Digit. 0-9 A-F a-f @stable ICU 2.1 */ - UCHAR_ASCII_HEX_DIGIT, + UCHAR_ASCII_HEX_DIGIT=1, /** Binary property Bidi_Control. Format controls which have specific functions in the Bidi Algorithm. @stable ICU 2.1 */ - UCHAR_BIDI_CONTROL, + UCHAR_BIDI_CONTROL=2, /** Binary property Bidi_Mirrored. Characters that may change display in RTL text. Same as u_isMirrored. See Bidi Algorithm, UTR 9. @stable ICU 2.1 */ - UCHAR_BIDI_MIRRORED, + UCHAR_BIDI_MIRRORED=3, /** Binary property Dash. Variations of dashes. @stable ICU 2.1 */ - UCHAR_DASH, + UCHAR_DASH=4, /** Binary property Default_Ignorable_Code_Point (new in Unicode 3.2). Ignorable in most processing. <2060..206F, FFF0..FFFB, E0000..E0FFF>+Other_Default_Ignorable_Code_Point+(Cf+Cc+Cs-White_Space) @stable ICU 2.1 */ - UCHAR_DEFAULT_IGNORABLE_CODE_POINT, + UCHAR_DEFAULT_IGNORABLE_CODE_POINT=5, /** Binary property Deprecated (new in Unicode 3.2). The usage of deprecated characters is strongly discouraged. @stable ICU 2.1 */ - UCHAR_DEPRECATED, + UCHAR_DEPRECATED=6, /** Binary property Diacritic. Characters that linguistically modify the meaning of another character to which they apply. @stable ICU 2.1 */ - UCHAR_DIACRITIC, + UCHAR_DIACRITIC=7, /** Binary property Extender. Extend the value or shape of a preceding alphabetic character, e.g., length and iteration marks. @stable ICU 2.1 */ - UCHAR_EXTENDER, + UCHAR_EXTENDER=8, /** Binary property Full_Composition_Exclusion. CompositionExclusions.txt+Singleton Decompositions+ Non-Starter Decompositions. @stable ICU 2.1 */ - UCHAR_FULL_COMPOSITION_EXCLUSION, + UCHAR_FULL_COMPOSITION_EXCLUSION=9, /** Binary property Grapheme_Base (new in Unicode 3.2). For programmatic determination of grapheme cluster boundaries. [0..10FFFF]-Cc-Cf-Cs-Co-Cn-Zl-Zp-Grapheme_Link-Grapheme_Extend-CGJ @stable ICU 2.1 */ - UCHAR_GRAPHEME_BASE, + UCHAR_GRAPHEME_BASE=10, /** Binary property Grapheme_Extend (new in Unicode 3.2). For programmatic determination of grapheme cluster boundaries. Me+Mn+Mc+Other_Grapheme_Extend-Grapheme_Link-CGJ @stable ICU 2.1 */ - UCHAR_GRAPHEME_EXTEND, + UCHAR_GRAPHEME_EXTEND=11, /** Binary property Grapheme_Link (new in Unicode 3.2). For programmatic determination of grapheme cluster boundaries. @stable ICU 2.1 */ - UCHAR_GRAPHEME_LINK, + UCHAR_GRAPHEME_LINK=12, /** Binary property Hex_Digit. Characters commonly used for hexadecimal numbers. @stable ICU 2.1 */ - UCHAR_HEX_DIGIT, + UCHAR_HEX_DIGIT=13, /** Binary property Hyphen. Dashes used to mark connections between pieces of words, plus the Katakana middle dot. @stable ICU 2.1 */ - UCHAR_HYPHEN, + UCHAR_HYPHEN=14, /** Binary property ID_Continue. Characters that can continue an identifier. DerivedCoreProperties.txt also says "NOTE: Cf characters should be filtered out." ID_Start+Mn+Mc+Nd+Pc @stable ICU 2.1 */ - UCHAR_ID_CONTINUE, + UCHAR_ID_CONTINUE=15, /** Binary property ID_Start. Characters that can start an identifier. Lu+Ll+Lt+Lm+Lo+Nl @stable ICU 2.1 */ - UCHAR_ID_START, + UCHAR_ID_START=16, /** Binary property Ideographic. CJKV ideographs. @stable ICU 2.1 */ - UCHAR_IDEOGRAPHIC, + UCHAR_IDEOGRAPHIC=17, /** Binary property IDS_Binary_Operator (new in Unicode 3.2). For programmatic determination of Ideographic Description Sequences. @stable ICU 2.1 */ - UCHAR_IDS_BINARY_OPERATOR, + UCHAR_IDS_BINARY_OPERATOR=18, /** Binary property IDS_Trinary_Operator (new in Unicode 3.2). For programmatic determination of Ideographic Description Sequences. @stable ICU 2.1 */ - UCHAR_IDS_TRINARY_OPERATOR, + UCHAR_IDS_TRINARY_OPERATOR=19, /** Binary property Join_Control. Format controls for cursive joining and ligation. @stable ICU 2.1 */ - UCHAR_JOIN_CONTROL, + UCHAR_JOIN_CONTROL=20, /** Binary property Logical_Order_Exception (new in Unicode 3.2). Characters that do not use logical order and require special handling in most processing. @stable ICU 2.1 */ - UCHAR_LOGICAL_ORDER_EXCEPTION, + UCHAR_LOGICAL_ORDER_EXCEPTION=21, /** Binary property Lowercase. Same as u_isULowercase, different from u_islower. Ll+Other_Lowercase @stable ICU 2.1 */ - UCHAR_LOWERCASE, + UCHAR_LOWERCASE=22, /** Binary property Math. Sm+Other_Math @stable ICU 2.1 */ - UCHAR_MATH, + UCHAR_MATH=23, /** Binary property Noncharacter_Code_Point. Code points that are explicitly defined as illegal for the encoding of characters. @stable ICU 2.1 */ - UCHAR_NONCHARACTER_CODE_POINT, + UCHAR_NONCHARACTER_CODE_POINT=24, /** Binary property Quotation_Mark. @stable ICU 2.1 */ - UCHAR_QUOTATION_MARK, + UCHAR_QUOTATION_MARK=25, /** Binary property Radical (new in Unicode 3.2). For programmatic determination of Ideographic Description Sequences. @stable ICU 2.1 */ - UCHAR_RADICAL, + UCHAR_RADICAL=26, /** Binary property Soft_Dotted (new in Unicode 3.2). Characters with a "soft dot", like i or j. An accent placed on these characters causes the dot to disappear. @stable ICU 2.1 */ - UCHAR_SOFT_DOTTED, + UCHAR_SOFT_DOTTED=27, /** Binary property Terminal_Punctuation. Punctuation characters that generally mark the end of textual units. @stable ICU 2.1 */ - UCHAR_TERMINAL_PUNCTUATION, + UCHAR_TERMINAL_PUNCTUATION=28, /** Binary property Unified_Ideograph (new in Unicode 3.2). For programmatic determination of Ideographic Description Sequences. @stable ICU 2.1 */ - UCHAR_UNIFIED_IDEOGRAPH, + UCHAR_UNIFIED_IDEOGRAPH=29, /** Binary property Uppercase. Same as u_isUUppercase, different from u_isupper. Lu+Other_Uppercase @stable ICU 2.1 */ - UCHAR_UPPERCASE, + UCHAR_UPPERCASE=30, /** Binary property White_Space. Same as u_isUWhiteSpace, different from u_isspace and u_isWhitespace. Space characters+TAB+CR+LF-ZWSP-ZWNBSP @stable ICU 2.1 */ - UCHAR_WHITE_SPACE, + UCHAR_WHITE_SPACE=31, /** Binary property XID_Continue. ID_Continue modified to allow closure under normalization forms NFKC and NFKD. @stable ICU 2.1 */ - UCHAR_XID_CONTINUE, + UCHAR_XID_CONTINUE=32, /** Binary property XID_Start. ID_Start modified to allow closure under normalization forms NFKC and NFKD. @stable ICU 2.1 */ - UCHAR_XID_START, + UCHAR_XID_START=33, /** Binary property Case_Sensitive. Either the source of a case mapping or _in_ the target of a case mapping. Not the same as the general category Cased_Letter. @stable ICU 2.6 */ - UCHAR_CASE_SENSITIVE, + UCHAR_CASE_SENSITIVE=34, /** Binary property STerm (new in Unicode 4.0.1). Sentence Terminal. Used in UAX #29: Text Boundaries (http://www.unicode.org/reports/tr29/) - @draft ICU 3.0 */ - UCHAR_S_TERM, + @stable ICU 3.0 */ + UCHAR_S_TERM=35, /** Binary property Variation_Selector (new in Unicode 4.0.1). Indicates all those characters that qualify as Variation Selectors. For details on the behavior of these characters, see StandardizedVariants.html and 15.6 Variation Selectors. - @draft ICU 3.0 */ - UCHAR_VARIATION_SELECTOR, + @stable ICU 3.0 */ + UCHAR_VARIATION_SELECTOR=36, /** Binary property NFD_Inert. ICU-specific property for characters that are inert under NFD, i.e., they do not interact with adjacent characters. - Used for example in normalizing transforms in incremental mode - to find the boundary of safely normalizable text despite possible - text additions. - - There is one such property per normalization form. - These properties are computed as follows - an inert character is: - a) unassigned, or ALL of the following: - b) of combining class 0. - c) not decomposed by this normalization form. - AND if NFC or NFKC, - d) can never compose with a previous character. - e) can never compose with a following character. - f) can never change if another character is added. - Example: a-breve might satisfy all but f, but if you - add an ogonek it changes to a-ogonek + breve - - See also com.ibm.text.UCD.NFSkippable in the ICU4J repository, - and icu/source/common/unormimp.h . - @draft ICU 3.0 */ - UCHAR_NFD_INERT, + See the documentation for the Normalizer2 class and the + Normalizer2::isInert() method. + @stable ICU 3.0 */ + UCHAR_NFD_INERT=37, /** Binary property NFKD_Inert. ICU-specific property for characters that are inert under NFKD, i.e., they do not interact with adjacent characters. - Used for example in normalizing transforms in incremental mode - to find the boundary of safely normalizable text despite possible - text additions. - @see UCHAR_NFD_INERT - @draft ICU 3.0 */ - UCHAR_NFKD_INERT, + See the documentation for the Normalizer2 class and the + Normalizer2::isInert() method. + @stable ICU 3.0 */ + UCHAR_NFKD_INERT=38, /** Binary property NFC_Inert. ICU-specific property for characters that are inert under NFC, i.e., they do not interact with adjacent characters. - Used for example in normalizing transforms in incremental mode - to find the boundary of safely normalizable text despite possible - text additions. - @see UCHAR_NFD_INERT - @draft ICU 3.0 */ - UCHAR_NFC_INERT, + See the documentation for the Normalizer2 class and the + Normalizer2::isInert() method. + @stable ICU 3.0 */ + UCHAR_NFC_INERT=39, /** Binary property NFKC_Inert. ICU-specific property for characters that are inert under NFKC, i.e., they do not interact with adjacent characters. - Used for example in normalizing transforms in incremental mode - to find the boundary of safely normalizable text despite possible - text additions. - @see UCHAR_NFD_INERT - @draft ICU 3.0 */ - UCHAR_NFKC_INERT, + See the documentation for the Normalizer2 class and the + Normalizer2::isInert() method. + @stable ICU 3.0 */ + UCHAR_NFKC_INERT=40, /** Binary Property Segment_Starter. ICU-specific property for characters that are starters in terms of Unicode normalization and combining character sequences. They have ccc=0 and do not occur in non-initial position of the canonical decomposition of any character - (like " in NFD(a-umlaut) and a Jamo T in an NFD(Hangul LVT)). + (like a-umlaut in NFD and a Jamo T in an NFD(Hangul LVT)). ICU uses this property for segmenting a string for generating a set of canonically equivalent strings, e.g. for canonical closure while processing collation tailoring rules. - @draft ICU 3.0 */ - UCHAR_SEGMENT_STARTER, - /** One more than the last constant for binary Unicode properties. @stable ICU 2.1 */ + @stable ICU 3.0 */ + UCHAR_SEGMENT_STARTER=41, + /** Binary property Pattern_Syntax (new in Unicode 4.1). + See UAX #31 Identifier and Pattern Syntax + (http://www.unicode.org/reports/tr31/) + @stable ICU 3.4 */ + UCHAR_PATTERN_SYNTAX=42, + /** Binary property Pattern_White_Space (new in Unicode 4.1). + See UAX #31 Identifier and Pattern Syntax + (http://www.unicode.org/reports/tr31/) + @stable ICU 3.4 */ + UCHAR_PATTERN_WHITE_SPACE=43, + /** Binary property alnum (a C/POSIX character class). + Implemented according to the UTS #18 Annex C Standard Recommendation. + See the uchar.h file documentation. + @stable ICU 3.4 */ + UCHAR_POSIX_ALNUM=44, + /** Binary property blank (a C/POSIX character class). + Implemented according to the UTS #18 Annex C Standard Recommendation. + See the uchar.h file documentation. + @stable ICU 3.4 */ + UCHAR_POSIX_BLANK=45, + /** Binary property graph (a C/POSIX character class). + Implemented according to the UTS #18 Annex C Standard Recommendation. + See the uchar.h file documentation. + @stable ICU 3.4 */ + UCHAR_POSIX_GRAPH=46, + /** Binary property print (a C/POSIX character class). + Implemented according to the UTS #18 Annex C Standard Recommendation. + See the uchar.h file documentation. + @stable ICU 3.4 */ + UCHAR_POSIX_PRINT=47, + /** Binary property xdigit (a C/POSIX character class). + Implemented according to the UTS #18 Annex C Standard Recommendation. + See the uchar.h file documentation. + @stable ICU 3.4 */ + UCHAR_POSIX_XDIGIT=48, + /** Binary property Cased. For Lowercase, Uppercase and Titlecase characters. @stable ICU 4.4 */ + UCHAR_CASED=49, + /** Binary property Case_Ignorable. Used in context-sensitive case mappings. @stable ICU 4.4 */ + UCHAR_CASE_IGNORABLE=50, + /** Binary property Changes_When_Lowercased. @stable ICU 4.4 */ + UCHAR_CHANGES_WHEN_LOWERCASED=51, + /** Binary property Changes_When_Uppercased. @stable ICU 4.4 */ + UCHAR_CHANGES_WHEN_UPPERCASED=52, + /** Binary property Changes_When_Titlecased. @stable ICU 4.4 */ + UCHAR_CHANGES_WHEN_TITLECASED=53, + /** Binary property Changes_When_Casefolded. @stable ICU 4.4 */ + UCHAR_CHANGES_WHEN_CASEFOLDED=54, + /** Binary property Changes_When_Casemapped. @stable ICU 4.4 */ + UCHAR_CHANGES_WHEN_CASEMAPPED=55, + /** Binary property Changes_When_NFKC_Casefolded. @stable ICU 4.4 */ + UCHAR_CHANGES_WHEN_NFKC_CASEFOLDED=56, + /** + * Binary property Emoji. + * See http://www.unicode.org/reports/tr51/#Emoji_Properties + * + * @stable ICU 57 + */ + UCHAR_EMOJI=57, + /** + * Binary property Emoji_Presentation. + * See http://www.unicode.org/reports/tr51/#Emoji_Properties + * + * @stable ICU 57 + */ + UCHAR_EMOJI_PRESENTATION=58, + /** + * Binary property Emoji_Modifier. + * See http://www.unicode.org/reports/tr51/#Emoji_Properties + * + * @stable ICU 57 + */ + UCHAR_EMOJI_MODIFIER=59, + /** + * Binary property Emoji_Modifier_Base. + * See http://www.unicode.org/reports/tr51/#Emoji_Properties + * + * @stable ICU 57 + */ + UCHAR_EMOJI_MODIFIER_BASE=60, + /** + * Binary property Emoji_Component. + * See http://www.unicode.org/reports/tr51/#Emoji_Properties + * + * @stable ICU 60 + */ + UCHAR_EMOJI_COMPONENT=61, + /** + * Binary property Regional_Indicator. + * @stable ICU 60 + */ + UCHAR_REGIONAL_INDICATOR=62, + /** + * Binary property Prepended_Concatenation_Mark. + * @stable ICU 60 + */ + UCHAR_PREPENDED_CONCATENATION_MARK=63, + /** + * Binary property Extended_Pictographic. + * See http://www.unicode.org/reports/tr51/#Emoji_Properties + * + * @stable ICU 62 + */ + UCHAR_EXTENDED_PICTOGRAPHIC=64, +#ifndef U_HIDE_DEPRECATED_API + /** + * One more than the last constant for binary Unicode properties. + * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. + */ UCHAR_BINARY_LIMIT, +#endif // U_HIDE_DEPRECATED_API /** Enumerated property Bidi_Class. Same as u_charDirection, returns UCharDirection values. @stable ICU 2.2 */ @@ -368,66 +468,91 @@ typedef enum UProperty { UCHAR_INT_START=UCHAR_BIDI_CLASS, /** Enumerated property Block. Same as ublock_getCode, returns UBlockCode values. @stable ICU 2.2 */ - UCHAR_BLOCK, + UCHAR_BLOCK=0x1001, /** Enumerated property Canonical_Combining_Class. Same as u_getCombiningClass, returns 8-bit numeric values. @stable ICU 2.2 */ - UCHAR_CANONICAL_COMBINING_CLASS, + UCHAR_CANONICAL_COMBINING_CLASS=0x1002, /** Enumerated property Decomposition_Type. Returns UDecompositionType values. @stable ICU 2.2 */ - UCHAR_DECOMPOSITION_TYPE, + UCHAR_DECOMPOSITION_TYPE=0x1003, /** Enumerated property East_Asian_Width. See http://www.unicode.org/reports/tr11/ Returns UEastAsianWidth values. @stable ICU 2.2 */ - UCHAR_EAST_ASIAN_WIDTH, + UCHAR_EAST_ASIAN_WIDTH=0x1004, /** Enumerated property General_Category. Same as u_charType, returns UCharCategory values. @stable ICU 2.2 */ - UCHAR_GENERAL_CATEGORY, + UCHAR_GENERAL_CATEGORY=0x1005, /** Enumerated property Joining_Group. Returns UJoiningGroup values. @stable ICU 2.2 */ - UCHAR_JOINING_GROUP, + UCHAR_JOINING_GROUP=0x1006, /** Enumerated property Joining_Type. Returns UJoiningType values. @stable ICU 2.2 */ - UCHAR_JOINING_TYPE, + UCHAR_JOINING_TYPE=0x1007, /** Enumerated property Line_Break. Returns ULineBreak values. @stable ICU 2.2 */ - UCHAR_LINE_BREAK, + UCHAR_LINE_BREAK=0x1008, /** Enumerated property Numeric_Type. Returns UNumericType values. @stable ICU 2.2 */ - UCHAR_NUMERIC_TYPE, + UCHAR_NUMERIC_TYPE=0x1009, /** Enumerated property Script. Same as uscript_getScript, returns UScriptCode values. @stable ICU 2.2 */ - UCHAR_SCRIPT, + UCHAR_SCRIPT=0x100A, /** Enumerated property Hangul_Syllable_Type, new in Unicode 4. Returns UHangulSyllableType values. @stable ICU 2.6 */ - UCHAR_HANGUL_SYLLABLE_TYPE, + UCHAR_HANGUL_SYLLABLE_TYPE=0x100B, /** Enumerated property NFD_Quick_Check. - Returns UNormalizationCheckResult values. @draft ICU 3.0 */ - UCHAR_NFD_QUICK_CHECK, + Returns UNormalizationCheckResult values. @stable ICU 3.0 */ + UCHAR_NFD_QUICK_CHECK=0x100C, /** Enumerated property NFKD_Quick_Check. - Returns UNormalizationCheckResult values. @draft ICU 3.0 */ - UCHAR_NFKD_QUICK_CHECK, + Returns UNormalizationCheckResult values. @stable ICU 3.0 */ + UCHAR_NFKD_QUICK_CHECK=0x100D, /** Enumerated property NFC_Quick_Check. - Returns UNormalizationCheckResult values. @draft ICU 3.0 */ - UCHAR_NFC_QUICK_CHECK, + Returns UNormalizationCheckResult values. @stable ICU 3.0 */ + UCHAR_NFC_QUICK_CHECK=0x100E, /** Enumerated property NFKC_Quick_Check. - Returns UNormalizationCheckResult values. @draft ICU 3.0 */ - UCHAR_NFKC_QUICK_CHECK, + Returns UNormalizationCheckResult values. @stable ICU 3.0 */ + UCHAR_NFKC_QUICK_CHECK=0x100F, /** Enumerated property Lead_Canonical_Combining_Class. ICU-specific property for the ccc of the first code point of the decomposition, or lccc(c)=ccc(NFD(c)[0]). Useful for checking for canonically ordered text; see UNORM_FCD and http://www.unicode.org/notes/tn5/#FCD . - Returns 8-bit numeric values like UCHAR_CANONICAL_COMBINING_CLASS. @draft ICU 3.0 */ - UCHAR_LEAD_CANONICAL_COMBINING_CLASS, + Returns 8-bit numeric values like UCHAR_CANONICAL_COMBINING_CLASS. @stable ICU 3.0 */ + UCHAR_LEAD_CANONICAL_COMBINING_CLASS=0x1010, /** Enumerated property Trail_Canonical_Combining_Class. ICU-specific property for the ccc of the last code point of the decomposition, or tccc(c)=ccc(NFD(c)[last]). Useful for checking for canonically ordered text; see UNORM_FCD and http://www.unicode.org/notes/tn5/#FCD . - Returns 8-bit numeric values like UCHAR_CANONICAL_COMBINING_CLASS. @draft ICU 3.0 */ - UCHAR_TRAIL_CANONICAL_COMBINING_CLASS, - /** One more than the last constant for enumerated/integer Unicode properties. @stable ICU 2.2 */ - UCHAR_INT_LIMIT, + Returns 8-bit numeric values like UCHAR_CANONICAL_COMBINING_CLASS. @stable ICU 3.0 */ + UCHAR_TRAIL_CANONICAL_COMBINING_CLASS=0x1011, + /** Enumerated property Grapheme_Cluster_Break (new in Unicode 4.1). + Used in UAX #29: Text Boundaries + (http://www.unicode.org/reports/tr29/) + Returns UGraphemeClusterBreak values. @stable ICU 3.4 */ + UCHAR_GRAPHEME_CLUSTER_BREAK=0x1012, + /** Enumerated property Sentence_Break (new in Unicode 4.1). + Used in UAX #29: Text Boundaries + (http://www.unicode.org/reports/tr29/) + Returns USentenceBreak values. @stable ICU 3.4 */ + UCHAR_SENTENCE_BREAK=0x1013, + /** Enumerated property Word_Break (new in Unicode 4.1). + Used in UAX #29: Text Boundaries + (http://www.unicode.org/reports/tr29/) + Returns UWordBreakValues values. @stable ICU 3.4 */ + UCHAR_WORD_BREAK=0x1014, + /** Enumerated property Bidi_Paired_Bracket_Type (new in Unicode 6.3). + Used in UAX #9: Unicode Bidirectional Algorithm + (http://www.unicode.org/reports/tr9/) + Returns UBidiPairedBracketType values. @stable ICU 52 */ + UCHAR_BIDI_PAIRED_BRACKET_TYPE=0x1015, +#ifndef U_HIDE_DEPRECATED_API + /** + * One more than the last constant for enumerated/integer Unicode properties. + * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. + */ + UCHAR_INT_LIMIT=0x1016, +#endif // U_HIDE_DEPRECATED_API /** Bitmask property General_Category_Mask. This is the General_Category property returned as a bit mask. @@ -440,16 +565,26 @@ typedef enum UProperty { UCHAR_GENERAL_CATEGORY_MASK=0x2000, /** First constant for bit-mask Unicode properties. @stable ICU 2.4 */ UCHAR_MASK_START=UCHAR_GENERAL_CATEGORY_MASK, - /** One more than the last constant for bit-mask Unicode properties. @stable ICU 2.4 */ - UCHAR_MASK_LIMIT, +#ifndef U_HIDE_DEPRECATED_API + /** + * One more than the last constant for bit-mask Unicode properties. + * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. + */ + UCHAR_MASK_LIMIT=0x2001, +#endif // U_HIDE_DEPRECATED_API /** Double property Numeric_Value. Corresponds to u_getNumericValue. @stable ICU 2.4 */ UCHAR_NUMERIC_VALUE=0x3000, /** First constant for double Unicode properties. @stable ICU 2.4 */ UCHAR_DOUBLE_START=UCHAR_NUMERIC_VALUE, - /** One more than the last constant for double Unicode properties. @stable ICU 2.4 */ - UCHAR_DOUBLE_LIMIT, +#ifndef U_HIDE_DEPRECATED_API + /** + * One more than the last constant for double Unicode properties. + * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. + */ + UCHAR_DOUBLE_LIMIT=0x3001, +#endif // U_HIDE_DEPRECATED_API /** String property Age. Corresponds to u_charAge. @stable ICU 2.4 */ @@ -458,42 +593,72 @@ typedef enum UProperty { UCHAR_STRING_START=UCHAR_AGE, /** String property Bidi_Mirroring_Glyph. Corresponds to u_charMirror. @stable ICU 2.4 */ - UCHAR_BIDI_MIRRORING_GLYPH, + UCHAR_BIDI_MIRRORING_GLYPH=0x4001, /** String property Case_Folding. Corresponds to u_strFoldCase in ustring.h. @stable ICU 2.4 */ - UCHAR_CASE_FOLDING, - /** String property ISO_Comment. - Corresponds to u_getISOComment. @stable ICU 2.4 */ - UCHAR_ISO_COMMENT, + UCHAR_CASE_FOLDING=0x4002, +#ifndef U_HIDE_DEPRECATED_API + /** Deprecated string property ISO_Comment. + Corresponds to u_getISOComment. @deprecated ICU 49 */ + UCHAR_ISO_COMMENT=0x4003, +#endif /* U_HIDE_DEPRECATED_API */ /** String property Lowercase_Mapping. Corresponds to u_strToLower in ustring.h. @stable ICU 2.4 */ - UCHAR_LOWERCASE_MAPPING, + UCHAR_LOWERCASE_MAPPING=0x4004, /** String property Name. Corresponds to u_charName. @stable ICU 2.4 */ - UCHAR_NAME, + UCHAR_NAME=0x4005, /** String property Simple_Case_Folding. Corresponds to u_foldCase. @stable ICU 2.4 */ - UCHAR_SIMPLE_CASE_FOLDING, + UCHAR_SIMPLE_CASE_FOLDING=0x4006, /** String property Simple_Lowercase_Mapping. Corresponds to u_tolower. @stable ICU 2.4 */ - UCHAR_SIMPLE_LOWERCASE_MAPPING, + UCHAR_SIMPLE_LOWERCASE_MAPPING=0x4007, /** String property Simple_Titlecase_Mapping. Corresponds to u_totitle. @stable ICU 2.4 */ - UCHAR_SIMPLE_TITLECASE_MAPPING, + UCHAR_SIMPLE_TITLECASE_MAPPING=0x4008, /** String property Simple_Uppercase_Mapping. Corresponds to u_toupper. @stable ICU 2.4 */ - UCHAR_SIMPLE_UPPERCASE_MAPPING, + UCHAR_SIMPLE_UPPERCASE_MAPPING=0x4009, /** String property Titlecase_Mapping. Corresponds to u_strToTitle in ustring.h. @stable ICU 2.4 */ - UCHAR_TITLECASE_MAPPING, + UCHAR_TITLECASE_MAPPING=0x400A, +#ifndef U_HIDE_DEPRECATED_API /** String property Unicode_1_Name. - Corresponds to u_charName. @stable ICU 2.4 */ - UCHAR_UNICODE_1_NAME, + This property is of little practical value. + Beginning with ICU 49, ICU APIs return an empty string for this property. + Corresponds to u_charName(U_UNICODE_10_CHAR_NAME). @deprecated ICU 49 */ + UCHAR_UNICODE_1_NAME=0x400B, +#endif /* U_HIDE_DEPRECATED_API */ /** String property Uppercase_Mapping. Corresponds to u_strToUpper in ustring.h. @stable ICU 2.4 */ - UCHAR_UPPERCASE_MAPPING, - /** One more than the last constant for string Unicode properties. @stable ICU 2.4 */ - UCHAR_STRING_LIMIT, + UCHAR_UPPERCASE_MAPPING=0x400C, + /** String property Bidi_Paired_Bracket (new in Unicode 6.3). + Corresponds to u_getBidiPairedBracket. @stable ICU 52 */ + UCHAR_BIDI_PAIRED_BRACKET=0x400D, +#ifndef U_HIDE_DEPRECATED_API + /** + * One more than the last constant for string Unicode properties. + * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. + */ + UCHAR_STRING_LIMIT=0x400E, +#endif // U_HIDE_DEPRECATED_API + + /** Miscellaneous property Script_Extensions (new in Unicode 6.0). + Some characters are commonly used in multiple scripts. + For more information, see UAX #24: http://www.unicode.org/reports/tr24/. + Corresponds to uscript_hasScript and uscript_getScriptExtensions in uscript.h. + @stable ICU 4.6 */ + UCHAR_SCRIPT_EXTENSIONS=0x7000, + /** First constant for Unicode properties with unusual value types. @stable ICU 4.6 */ + UCHAR_OTHER_PROPERTY_START=UCHAR_SCRIPT_EXTENSIONS, +#ifndef U_HIDE_DEPRECATED_API + /** + * One more than the last constant for Unicode properties with unusual value types. + * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. + */ + UCHAR_OTHER_PROPERTY_LIMIT=0x7001, +#endif // U_HIDE_DEPRECATED_API /** Represents a nonexistent or invalid property or property value. @stable ICU 2.4 */ UCHAR_INVALID_CODE = -1 @@ -506,7 +671,12 @@ typedef enum UProperty { */ typedef enum UCharCategory { - /** See note !!. Comments of the form "Cn" are read by genpname. */ + /* + * Note: UCharCategory constants and their API comments are parsed by preparseucd.py. + * It matches pairs of lines like + * / ** comment... * / + * U_<[A-Z_]+> = , + */ /** Non-category for unassigned and non-character code points. @stable ICU 2.0 */ U_UNASSIGNED = 0, @@ -570,7 +740,13 @@ typedef enum UCharCategory U_INITIAL_PUNCTUATION = 28, /** Pf @stable ICU 2.0 */ U_FINAL_PUNCTUATION = 29, - /** One higher than the last enum UCharCategory constant. @stable ICU 2.0 */ + /** + * One higher than the last enum UCharCategory constant. + * This numeric value is stable (will not change), see + * http://www.unicode.org/policies/stability_policy.html#Property_Value + * + * @stable ICU 2.0 + */ U_CHAR_CATEGORY_COUNT } UCharCategory; @@ -691,7 +867,12 @@ typedef enum UCharCategory * @stable ICU 2.0 */ typedef enum UCharDirection { - /** See note !!. Comments of the form "EN" are read by genpname. */ + /* + * Note: UCharDirection constants and their API comments are parsed by preparseucd.py. + * It matches pairs of lines like + * / ** comment... * / + * U_<[A-Z_]+> = , + */ /** L @stable ICU 2.0 */ U_LEFT_TO_RIGHT = 0, @@ -731,21 +912,71 @@ typedef enum UCharDirection { U_DIR_NON_SPACING_MARK = 17, /** BN @stable ICU 2.0 */ U_BOUNDARY_NEUTRAL = 18, - /** @stable ICU 2.0 */ + /** FSI @stable ICU 52 */ + U_FIRST_STRONG_ISOLATE = 19, + /** LRI @stable ICU 52 */ + U_LEFT_TO_RIGHT_ISOLATE = 20, + /** RLI @stable ICU 52 */ + U_RIGHT_TO_LEFT_ISOLATE = 21, + /** PDI @stable ICU 52 */ + U_POP_DIRECTIONAL_ISOLATE = 22, +#ifndef U_HIDE_DEPRECATED_API + /** + * One more than the highest UCharDirection value. + * The highest value is available via u_getIntPropertyMaxValue(UCHAR_BIDI_CLASS). + * + * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. + */ U_CHAR_DIRECTION_COUNT +#endif // U_HIDE_DEPRECATED_API } UCharDirection; +/** + * Bidi Paired Bracket Type constants. + * + * @see UCHAR_BIDI_PAIRED_BRACKET_TYPE + * @stable ICU 52 + */ +typedef enum UBidiPairedBracketType { + /* + * Note: UBidiPairedBracketType constants are parsed by preparseucd.py. + * It matches lines like + * U_BPT_ + */ + + /** Not a paired bracket. @stable ICU 52 */ + U_BPT_NONE, + /** Open paired bracket. @stable ICU 52 */ + U_BPT_OPEN, + /** Close paired bracket. @stable ICU 52 */ + U_BPT_CLOSE, +#ifndef U_HIDE_DEPRECATED_API + /** + * One more than the highest normal UBidiPairedBracketType value. + * The highest value is available via u_getIntPropertyMaxValue(UCHAR_BIDI_PAIRED_BRACKET_TYPE). + * + * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. + */ + U_BPT_COUNT /* 3 */ +#endif // U_HIDE_DEPRECATED_API +} UBidiPairedBracketType; + /** * Constants for Unicode blocks, see the Unicode Data file Blocks.txt * @stable ICU 2.0 */ enum UBlockCode { + /* + * Note: UBlockCode constants are parsed by preparseucd.py. + * It matches lines like + * UBLOCK_ = , + */ /** New No_Block value in Unicode 4. @stable ICU 2.6 */ UBLOCK_NO_BLOCK = 0, /*[none]*/ /* Special range indicating No_Block */ /** @stable ICU 2.0 */ - UBLOCK_BASIC_LATIN = 1, /*[0000]*/ /*See note !!*/ + UBLOCK_BASIC_LATIN = 1, /*[0000]*/ /** @stable ICU 2.0 */ UBLOCK_LATIN_1_SUPPLEMENT=2, /*[0080]*/ @@ -982,7 +1213,7 @@ enum UBlockCode { UBLOCK_LOW_SURROGATES =77, /*[DC00]*/ /** - * Same as UBLOCK_PRIVATE_USE_AREA. + * Same as UBLOCK_PRIVATE_USE. * Until Unicode 3.1.1, the corresponding block name was "Private Use", * and multiple code point ranges had this block. * Unicode 3.2 renames the block for the BMP PUA to "Private Use Area" and @@ -990,9 +1221,9 @@ enum UBlockCode { * * @stable ICU 2.0 */ - UBLOCK_PRIVATE_USE = 78, + UBLOCK_PRIVATE_USE_AREA =78, /*[E000]*/ /** - * Same as UBLOCK_PRIVATE_USE. + * Same as UBLOCK_PRIVATE_USE_AREA. * Until Unicode 3.1.1, the corresponding block name was "Private Use", * and multiple code point ranges had this block. * Unicode 3.2 renames the block for the BMP PUA to "Private Use Area" and @@ -1000,7 +1231,7 @@ enum UBlockCode { * * @stable ICU 2.0 */ - UBLOCK_PRIVATE_USE_AREA =UBLOCK_PRIVATE_USE, /*[E000]*/ + UBLOCK_PRIVATE_USE = UBLOCK_PRIVATE_USE_AREA, /** @stable ICU 2.0 */ UBLOCK_CJK_COMPATIBILITY_IDEOGRAPHS =79, /*[F900]*/ @@ -1032,33 +1263,33 @@ enum UBlockCode { /* New blocks in Unicode 3.1 */ /** @stable ICU 2.0 */ - UBLOCK_OLD_ITALIC = 88 , /*[10300]*/ + UBLOCK_OLD_ITALIC = 88, /*[10300]*/ /** @stable ICU 2.0 */ - UBLOCK_GOTHIC = 89 , /*[10330]*/ + UBLOCK_GOTHIC = 89, /*[10330]*/ /** @stable ICU 2.0 */ - UBLOCK_DESERET = 90 , /*[10400]*/ + UBLOCK_DESERET = 90, /*[10400]*/ /** @stable ICU 2.0 */ - UBLOCK_BYZANTINE_MUSICAL_SYMBOLS = 91 , /*[1D000]*/ + UBLOCK_BYZANTINE_MUSICAL_SYMBOLS = 91, /*[1D000]*/ /** @stable ICU 2.0 */ - UBLOCK_MUSICAL_SYMBOLS = 92 , /*[1D100]*/ + UBLOCK_MUSICAL_SYMBOLS = 92, /*[1D100]*/ /** @stable ICU 2.0 */ - UBLOCK_MATHEMATICAL_ALPHANUMERIC_SYMBOLS = 93 , /*[1D400]*/ + UBLOCK_MATHEMATICAL_ALPHANUMERIC_SYMBOLS = 93, /*[1D400]*/ /** @stable ICU 2.0 */ - UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_B = 94 , /*[20000]*/ + UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_B = 94, /*[20000]*/ /** @stable ICU 2.0 */ - UBLOCK_CJK_COMPATIBILITY_IDEOGRAPHS_SUPPLEMENT = 95 , /*[2F800]*/ + UBLOCK_CJK_COMPATIBILITY_IDEOGRAPHS_SUPPLEMENT = 95, /*[2F800]*/ /** @stable ICU 2.0 */ UBLOCK_TAGS = 96, /*[E0000]*/ /* New blocks in Unicode 3.2 */ + /** @stable ICU 3.0 */ + UBLOCK_CYRILLIC_SUPPLEMENT = 97, /*[0500]*/ /** * Unicode 4.0.1 renames the "Cyrillic Supplementary" block to "Cyrillic Supplement". * @stable ICU 2.2 */ - UBLOCK_CYRILLIC_SUPPLEMENTARY = 97, - /** @draft ICU 3.0 */ - UBLOCK_CYRILLIC_SUPPLEMENT = UBLOCK_CYRILLIC_SUPPLEMENTARY, /*[0500]*/ + UBLOCK_CYRILLIC_SUPPLEMENTARY = UBLOCK_CYRILLIC_SUPPLEMENT, /** @stable ICU 2.2 */ UBLOCK_TAGALOG = 98, /*[1700]*/ /** @stable ICU 2.2 */ @@ -1119,8 +1350,380 @@ enum UBlockCode { /** @stable ICU 2.6 */ UBLOCK_VARIATION_SELECTORS_SUPPLEMENT = 125, /*[E0100]*/ - /** @stable ICU 2.0 */ - UBLOCK_COUNT, + /* New blocks in Unicode 4.1 */ + + /** @stable ICU 3.4 */ + UBLOCK_ANCIENT_GREEK_MUSICAL_NOTATION = 126, /*[1D200]*/ + /** @stable ICU 3.4 */ + UBLOCK_ANCIENT_GREEK_NUMBERS = 127, /*[10140]*/ + /** @stable ICU 3.4 */ + UBLOCK_ARABIC_SUPPLEMENT = 128, /*[0750]*/ + /** @stable ICU 3.4 */ + UBLOCK_BUGINESE = 129, /*[1A00]*/ + /** @stable ICU 3.4 */ + UBLOCK_CJK_STROKES = 130, /*[31C0]*/ + /** @stable ICU 3.4 */ + UBLOCK_COMBINING_DIACRITICAL_MARKS_SUPPLEMENT = 131, /*[1DC0]*/ + /** @stable ICU 3.4 */ + UBLOCK_COPTIC = 132, /*[2C80]*/ + /** @stable ICU 3.4 */ + UBLOCK_ETHIOPIC_EXTENDED = 133, /*[2D80]*/ + /** @stable ICU 3.4 */ + UBLOCK_ETHIOPIC_SUPPLEMENT = 134, /*[1380]*/ + /** @stable ICU 3.4 */ + UBLOCK_GEORGIAN_SUPPLEMENT = 135, /*[2D00]*/ + /** @stable ICU 3.4 */ + UBLOCK_GLAGOLITIC = 136, /*[2C00]*/ + /** @stable ICU 3.4 */ + UBLOCK_KHAROSHTHI = 137, /*[10A00]*/ + /** @stable ICU 3.4 */ + UBLOCK_MODIFIER_TONE_LETTERS = 138, /*[A700]*/ + /** @stable ICU 3.4 */ + UBLOCK_NEW_TAI_LUE = 139, /*[1980]*/ + /** @stable ICU 3.4 */ + UBLOCK_OLD_PERSIAN = 140, /*[103A0]*/ + /** @stable ICU 3.4 */ + UBLOCK_PHONETIC_EXTENSIONS_SUPPLEMENT = 141, /*[1D80]*/ + /** @stable ICU 3.4 */ + UBLOCK_SUPPLEMENTAL_PUNCTUATION = 142, /*[2E00]*/ + /** @stable ICU 3.4 */ + UBLOCK_SYLOTI_NAGRI = 143, /*[A800]*/ + /** @stable ICU 3.4 */ + UBLOCK_TIFINAGH = 144, /*[2D30]*/ + /** @stable ICU 3.4 */ + UBLOCK_VERTICAL_FORMS = 145, /*[FE10]*/ + + /* New blocks in Unicode 5.0 */ + + /** @stable ICU 3.6 */ + UBLOCK_NKO = 146, /*[07C0]*/ + /** @stable ICU 3.6 */ + UBLOCK_BALINESE = 147, /*[1B00]*/ + /** @stable ICU 3.6 */ + UBLOCK_LATIN_EXTENDED_C = 148, /*[2C60]*/ + /** @stable ICU 3.6 */ + UBLOCK_LATIN_EXTENDED_D = 149, /*[A720]*/ + /** @stable ICU 3.6 */ + UBLOCK_PHAGS_PA = 150, /*[A840]*/ + /** @stable ICU 3.6 */ + UBLOCK_PHOENICIAN = 151, /*[10900]*/ + /** @stable ICU 3.6 */ + UBLOCK_CUNEIFORM = 152, /*[12000]*/ + /** @stable ICU 3.6 */ + UBLOCK_CUNEIFORM_NUMBERS_AND_PUNCTUATION = 153, /*[12400]*/ + /** @stable ICU 3.6 */ + UBLOCK_COUNTING_ROD_NUMERALS = 154, /*[1D360]*/ + + /* New blocks in Unicode 5.1 */ + + /** @stable ICU 4.0 */ + UBLOCK_SUNDANESE = 155, /*[1B80]*/ + /** @stable ICU 4.0 */ + UBLOCK_LEPCHA = 156, /*[1C00]*/ + /** @stable ICU 4.0 */ + UBLOCK_OL_CHIKI = 157, /*[1C50]*/ + /** @stable ICU 4.0 */ + UBLOCK_CYRILLIC_EXTENDED_A = 158, /*[2DE0]*/ + /** @stable ICU 4.0 */ + UBLOCK_VAI = 159, /*[A500]*/ + /** @stable ICU 4.0 */ + UBLOCK_CYRILLIC_EXTENDED_B = 160, /*[A640]*/ + /** @stable ICU 4.0 */ + UBLOCK_SAURASHTRA = 161, /*[A880]*/ + /** @stable ICU 4.0 */ + UBLOCK_KAYAH_LI = 162, /*[A900]*/ + /** @stable ICU 4.0 */ + UBLOCK_REJANG = 163, /*[A930]*/ + /** @stable ICU 4.0 */ + UBLOCK_CHAM = 164, /*[AA00]*/ + /** @stable ICU 4.0 */ + UBLOCK_ANCIENT_SYMBOLS = 165, /*[10190]*/ + /** @stable ICU 4.0 */ + UBLOCK_PHAISTOS_DISC = 166, /*[101D0]*/ + /** @stable ICU 4.0 */ + UBLOCK_LYCIAN = 167, /*[10280]*/ + /** @stable ICU 4.0 */ + UBLOCK_CARIAN = 168, /*[102A0]*/ + /** @stable ICU 4.0 */ + UBLOCK_LYDIAN = 169, /*[10920]*/ + /** @stable ICU 4.0 */ + UBLOCK_MAHJONG_TILES = 170, /*[1F000]*/ + /** @stable ICU 4.0 */ + UBLOCK_DOMINO_TILES = 171, /*[1F030]*/ + + /* New blocks in Unicode 5.2 */ + + /** @stable ICU 4.4 */ + UBLOCK_SAMARITAN = 172, /*[0800]*/ + /** @stable ICU 4.4 */ + UBLOCK_UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS_EXTENDED = 173, /*[18B0]*/ + /** @stable ICU 4.4 */ + UBLOCK_TAI_THAM = 174, /*[1A20]*/ + /** @stable ICU 4.4 */ + UBLOCK_VEDIC_EXTENSIONS = 175, /*[1CD0]*/ + /** @stable ICU 4.4 */ + UBLOCK_LISU = 176, /*[A4D0]*/ + /** @stable ICU 4.4 */ + UBLOCK_BAMUM = 177, /*[A6A0]*/ + /** @stable ICU 4.4 */ + UBLOCK_COMMON_INDIC_NUMBER_FORMS = 178, /*[A830]*/ + /** @stable ICU 4.4 */ + UBLOCK_DEVANAGARI_EXTENDED = 179, /*[A8E0]*/ + /** @stable ICU 4.4 */ + UBLOCK_HANGUL_JAMO_EXTENDED_A = 180, /*[A960]*/ + /** @stable ICU 4.4 */ + UBLOCK_JAVANESE = 181, /*[A980]*/ + /** @stable ICU 4.4 */ + UBLOCK_MYANMAR_EXTENDED_A = 182, /*[AA60]*/ + /** @stable ICU 4.4 */ + UBLOCK_TAI_VIET = 183, /*[AA80]*/ + /** @stable ICU 4.4 */ + UBLOCK_MEETEI_MAYEK = 184, /*[ABC0]*/ + /** @stable ICU 4.4 */ + UBLOCK_HANGUL_JAMO_EXTENDED_B = 185, /*[D7B0]*/ + /** @stable ICU 4.4 */ + UBLOCK_IMPERIAL_ARAMAIC = 186, /*[10840]*/ + /** @stable ICU 4.4 */ + UBLOCK_OLD_SOUTH_ARABIAN = 187, /*[10A60]*/ + /** @stable ICU 4.4 */ + UBLOCK_AVESTAN = 188, /*[10B00]*/ + /** @stable ICU 4.4 */ + UBLOCK_INSCRIPTIONAL_PARTHIAN = 189, /*[10B40]*/ + /** @stable ICU 4.4 */ + UBLOCK_INSCRIPTIONAL_PAHLAVI = 190, /*[10B60]*/ + /** @stable ICU 4.4 */ + UBLOCK_OLD_TURKIC = 191, /*[10C00]*/ + /** @stable ICU 4.4 */ + UBLOCK_RUMI_NUMERAL_SYMBOLS = 192, /*[10E60]*/ + /** @stable ICU 4.4 */ + UBLOCK_KAITHI = 193, /*[11080]*/ + /** @stable ICU 4.4 */ + UBLOCK_EGYPTIAN_HIEROGLYPHS = 194, /*[13000]*/ + /** @stable ICU 4.4 */ + UBLOCK_ENCLOSED_ALPHANUMERIC_SUPPLEMENT = 195, /*[1F100]*/ + /** @stable ICU 4.4 */ + UBLOCK_ENCLOSED_IDEOGRAPHIC_SUPPLEMENT = 196, /*[1F200]*/ + /** @stable ICU 4.4 */ + UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_C = 197, /*[2A700]*/ + + /* New blocks in Unicode 6.0 */ + + /** @stable ICU 4.6 */ + UBLOCK_MANDAIC = 198, /*[0840]*/ + /** @stable ICU 4.6 */ + UBLOCK_BATAK = 199, /*[1BC0]*/ + /** @stable ICU 4.6 */ + UBLOCK_ETHIOPIC_EXTENDED_A = 200, /*[AB00]*/ + /** @stable ICU 4.6 */ + UBLOCK_BRAHMI = 201, /*[11000]*/ + /** @stable ICU 4.6 */ + UBLOCK_BAMUM_SUPPLEMENT = 202, /*[16800]*/ + /** @stable ICU 4.6 */ + UBLOCK_KANA_SUPPLEMENT = 203, /*[1B000]*/ + /** @stable ICU 4.6 */ + UBLOCK_PLAYING_CARDS = 204, /*[1F0A0]*/ + /** @stable ICU 4.6 */ + UBLOCK_MISCELLANEOUS_SYMBOLS_AND_PICTOGRAPHS = 205, /*[1F300]*/ + /** @stable ICU 4.6 */ + UBLOCK_EMOTICONS = 206, /*[1F600]*/ + /** @stable ICU 4.6 */ + UBLOCK_TRANSPORT_AND_MAP_SYMBOLS = 207, /*[1F680]*/ + /** @stable ICU 4.6 */ + UBLOCK_ALCHEMICAL_SYMBOLS = 208, /*[1F700]*/ + /** @stable ICU 4.6 */ + UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_D = 209, /*[2B740]*/ + + /* New blocks in Unicode 6.1 */ + + /** @stable ICU 49 */ + UBLOCK_ARABIC_EXTENDED_A = 210, /*[08A0]*/ + /** @stable ICU 49 */ + UBLOCK_ARABIC_MATHEMATICAL_ALPHABETIC_SYMBOLS = 211, /*[1EE00]*/ + /** @stable ICU 49 */ + UBLOCK_CHAKMA = 212, /*[11100]*/ + /** @stable ICU 49 */ + UBLOCK_MEETEI_MAYEK_EXTENSIONS = 213, /*[AAE0]*/ + /** @stable ICU 49 */ + UBLOCK_MEROITIC_CURSIVE = 214, /*[109A0]*/ + /** @stable ICU 49 */ + UBLOCK_MEROITIC_HIEROGLYPHS = 215, /*[10980]*/ + /** @stable ICU 49 */ + UBLOCK_MIAO = 216, /*[16F00]*/ + /** @stable ICU 49 */ + UBLOCK_SHARADA = 217, /*[11180]*/ + /** @stable ICU 49 */ + UBLOCK_SORA_SOMPENG = 218, /*[110D0]*/ + /** @stable ICU 49 */ + UBLOCK_SUNDANESE_SUPPLEMENT = 219, /*[1CC0]*/ + /** @stable ICU 49 */ + UBLOCK_TAKRI = 220, /*[11680]*/ + + /* New blocks in Unicode 7.0 */ + + /** @stable ICU 54 */ + UBLOCK_BASSA_VAH = 221, /*[16AD0]*/ + /** @stable ICU 54 */ + UBLOCK_CAUCASIAN_ALBANIAN = 222, /*[10530]*/ + /** @stable ICU 54 */ + UBLOCK_COPTIC_EPACT_NUMBERS = 223, /*[102E0]*/ + /** @stable ICU 54 */ + UBLOCK_COMBINING_DIACRITICAL_MARKS_EXTENDED = 224, /*[1AB0]*/ + /** @stable ICU 54 */ + UBLOCK_DUPLOYAN = 225, /*[1BC00]*/ + /** @stable ICU 54 */ + UBLOCK_ELBASAN = 226, /*[10500]*/ + /** @stable ICU 54 */ + UBLOCK_GEOMETRIC_SHAPES_EXTENDED = 227, /*[1F780]*/ + /** @stable ICU 54 */ + UBLOCK_GRANTHA = 228, /*[11300]*/ + /** @stable ICU 54 */ + UBLOCK_KHOJKI = 229, /*[11200]*/ + /** @stable ICU 54 */ + UBLOCK_KHUDAWADI = 230, /*[112B0]*/ + /** @stable ICU 54 */ + UBLOCK_LATIN_EXTENDED_E = 231, /*[AB30]*/ + /** @stable ICU 54 */ + UBLOCK_LINEAR_A = 232, /*[10600]*/ + /** @stable ICU 54 */ + UBLOCK_MAHAJANI = 233, /*[11150]*/ + /** @stable ICU 54 */ + UBLOCK_MANICHAEAN = 234, /*[10AC0]*/ + /** @stable ICU 54 */ + UBLOCK_MENDE_KIKAKUI = 235, /*[1E800]*/ + /** @stable ICU 54 */ + UBLOCK_MODI = 236, /*[11600]*/ + /** @stable ICU 54 */ + UBLOCK_MRO = 237, /*[16A40]*/ + /** @stable ICU 54 */ + UBLOCK_MYANMAR_EXTENDED_B = 238, /*[A9E0]*/ + /** @stable ICU 54 */ + UBLOCK_NABATAEAN = 239, /*[10880]*/ + /** @stable ICU 54 */ + UBLOCK_OLD_NORTH_ARABIAN = 240, /*[10A80]*/ + /** @stable ICU 54 */ + UBLOCK_OLD_PERMIC = 241, /*[10350]*/ + /** @stable ICU 54 */ + UBLOCK_ORNAMENTAL_DINGBATS = 242, /*[1F650]*/ + /** @stable ICU 54 */ + UBLOCK_PAHAWH_HMONG = 243, /*[16B00]*/ + /** @stable ICU 54 */ + UBLOCK_PALMYRENE = 244, /*[10860]*/ + /** @stable ICU 54 */ + UBLOCK_PAU_CIN_HAU = 245, /*[11AC0]*/ + /** @stable ICU 54 */ + UBLOCK_PSALTER_PAHLAVI = 246, /*[10B80]*/ + /** @stable ICU 54 */ + UBLOCK_SHORTHAND_FORMAT_CONTROLS = 247, /*[1BCA0]*/ + /** @stable ICU 54 */ + UBLOCK_SIDDHAM = 248, /*[11580]*/ + /** @stable ICU 54 */ + UBLOCK_SINHALA_ARCHAIC_NUMBERS = 249, /*[111E0]*/ + /** @stable ICU 54 */ + UBLOCK_SUPPLEMENTAL_ARROWS_C = 250, /*[1F800]*/ + /** @stable ICU 54 */ + UBLOCK_TIRHUTA = 251, /*[11480]*/ + /** @stable ICU 54 */ + UBLOCK_WARANG_CITI = 252, /*[118A0]*/ + + /* New blocks in Unicode 8.0 */ + + /** @stable ICU 56 */ + UBLOCK_AHOM = 253, /*[11700]*/ + /** @stable ICU 56 */ + UBLOCK_ANATOLIAN_HIEROGLYPHS = 254, /*[14400]*/ + /** @stable ICU 56 */ + UBLOCK_CHEROKEE_SUPPLEMENT = 255, /*[AB70]*/ + /** @stable ICU 56 */ + UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_E = 256, /*[2B820]*/ + /** @stable ICU 56 */ + UBLOCK_EARLY_DYNASTIC_CUNEIFORM = 257, /*[12480]*/ + /** @stable ICU 56 */ + UBLOCK_HATRAN = 258, /*[108E0]*/ + /** @stable ICU 56 */ + UBLOCK_MULTANI = 259, /*[11280]*/ + /** @stable ICU 56 */ + UBLOCK_OLD_HUNGARIAN = 260, /*[10C80]*/ + /** @stable ICU 56 */ + UBLOCK_SUPPLEMENTAL_SYMBOLS_AND_PICTOGRAPHS = 261, /*[1F900]*/ + /** @stable ICU 56 */ + UBLOCK_SUTTON_SIGNWRITING = 262, /*[1D800]*/ + + /* New blocks in Unicode 9.0 */ + + /** @stable ICU 58 */ + UBLOCK_ADLAM = 263, /*[1E900]*/ + /** @stable ICU 58 */ + UBLOCK_BHAIKSUKI = 264, /*[11C00]*/ + /** @stable ICU 58 */ + UBLOCK_CYRILLIC_EXTENDED_C = 265, /*[1C80]*/ + /** @stable ICU 58 */ + UBLOCK_GLAGOLITIC_SUPPLEMENT = 266, /*[1E000]*/ + /** @stable ICU 58 */ + UBLOCK_IDEOGRAPHIC_SYMBOLS_AND_PUNCTUATION = 267, /*[16FE0]*/ + /** @stable ICU 58 */ + UBLOCK_MARCHEN = 268, /*[11C70]*/ + /** @stable ICU 58 */ + UBLOCK_MONGOLIAN_SUPPLEMENT = 269, /*[11660]*/ + /** @stable ICU 58 */ + UBLOCK_NEWA = 270, /*[11400]*/ + /** @stable ICU 58 */ + UBLOCK_OSAGE = 271, /*[104B0]*/ + /** @stable ICU 58 */ + UBLOCK_TANGUT = 272, /*[17000]*/ + /** @stable ICU 58 */ + UBLOCK_TANGUT_COMPONENTS = 273, /*[18800]*/ + + // New blocks in Unicode 10.0 + + /** @stable ICU 60 */ + UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_F = 274, /*[2CEB0]*/ + /** @stable ICU 60 */ + UBLOCK_KANA_EXTENDED_A = 275, /*[1B100]*/ + /** @stable ICU 60 */ + UBLOCK_MASARAM_GONDI = 276, /*[11D00]*/ + /** @stable ICU 60 */ + UBLOCK_NUSHU = 277, /*[1B170]*/ + /** @stable ICU 60 */ + UBLOCK_SOYOMBO = 278, /*[11A50]*/ + /** @stable ICU 60 */ + UBLOCK_SYRIAC_SUPPLEMENT = 279, /*[0860]*/ + /** @stable ICU 60 */ + UBLOCK_ZANABAZAR_SQUARE = 280, /*[11A00]*/ + + // New blocks in Unicode 11.0 + + /** @stable ICU 62 */ + UBLOCK_CHESS_SYMBOLS = 281, /*[1FA00]*/ + /** @stable ICU 62 */ + UBLOCK_DOGRA = 282, /*[11800]*/ + /** @stable ICU 62 */ + UBLOCK_GEORGIAN_EXTENDED = 283, /*[1C90]*/ + /** @stable ICU 62 */ + UBLOCK_GUNJALA_GONDI = 284, /*[11D60]*/ + /** @stable ICU 62 */ + UBLOCK_HANIFI_ROHINGYA = 285, /*[10D00]*/ + /** @stable ICU 62 */ + UBLOCK_INDIC_SIYAQ_NUMBERS = 286, /*[1EC70]*/ + /** @stable ICU 62 */ + UBLOCK_MAKASAR = 287, /*[11EE0]*/ + /** @stable ICU 62 */ + UBLOCK_MAYAN_NUMERALS = 288, /*[1D2E0]*/ + /** @stable ICU 62 */ + UBLOCK_MEDEFAIDRIN = 289, /*[16E40]*/ + /** @stable ICU 62 */ + UBLOCK_OLD_SOGDIAN = 290, /*[10F00]*/ + /** @stable ICU 62 */ + UBLOCK_SOGDIAN = 291, /*[10F30]*/ + +#ifndef U_HIDE_DEPRECATED_API + /** + * One more than the highest normal UBlockCode value. + * The highest value is available via u_getIntPropertyMaxValue(UCHAR_BLOCK). + * + * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. + */ + UBLOCK_COUNT = 292, +#endif // U_HIDE_DEPRECATED_API /** @stable ICU 2.0 */ UBLOCK_INVALID_CODE=-1 @@ -1137,18 +1740,28 @@ typedef enum UBlockCode UBlockCode; * @stable ICU 2.2 */ typedef enum UEastAsianWidth { - U_EA_NEUTRAL, /*[N]*/ /*See note !!*/ + /* + * Note: UEastAsianWidth constants are parsed by preparseucd.py. + * It matches lines like + * U_EA_ + */ + + U_EA_NEUTRAL, /*[N]*/ U_EA_AMBIGUOUS, /*[A]*/ U_EA_HALFWIDTH, /*[H]*/ U_EA_FULLWIDTH, /*[F]*/ U_EA_NARROW, /*[Na]*/ U_EA_WIDE, /*[W]*/ +#ifndef U_HIDE_DEPRECATED_API + /** + * One more than the highest normal UEastAsianWidth value. + * The highest value is available via u_getIntPropertyMaxValue(UCHAR_EAST_ASIAN_WIDTH). + * + * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. + */ U_EA_COUNT +#endif // U_HIDE_DEPRECATED_API } UEastAsianWidth; -/* - * Implementation note: - * Keep UEastAsianWidth constant values in sync with names list in genprops/props2.c. - */ /** * Selector constants for u_charName(). @@ -1162,10 +1775,27 @@ typedef enum UEastAsianWidth { * @stable ICU 2.0 */ typedef enum UCharNameChoice { + /** Unicode character name (Name property). @stable ICU 2.0 */ U_UNICODE_CHAR_NAME, +#ifndef U_HIDE_DEPRECATED_API + /** + * The Unicode_1_Name property value which is of little practical value. + * Beginning with ICU 49, ICU APIs return an empty string for this name choice. + * @deprecated ICU 49 + */ U_UNICODE_10_CHAR_NAME, - U_EXTENDED_CHAR_NAME, +#endif /* U_HIDE_DEPRECATED_API */ + /** Standard or synthetic character name. @stable ICU 2.0 */ + U_EXTENDED_CHAR_NAME = U_UNICODE_CHAR_NAME+2, + /** Corrected name from NameAliases.txt. @stable ICU 4.4 */ + U_CHAR_NAME_ALIAS, +#ifndef U_HIDE_DEPRECATED_API + /** + * One more than the highest normal UCharNameChoice value. + * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. + */ U_CHAR_NAME_CHOICE_COUNT +#endif // U_HIDE_DEPRECATED_API } UCharNameChoice; /** @@ -1184,7 +1814,13 @@ typedef enum UCharNameChoice { typedef enum UPropertyNameChoice { U_SHORT_PROPERTY_NAME, U_LONG_PROPERTY_NAME, +#ifndef U_HIDE_DEPRECATED_API + /** + * One more than the highest normal UPropertyNameChoice value. + * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. + */ U_PROPERTY_NAME_CHOICE_COUNT +#endif // U_HIDE_DEPRECATED_API } UPropertyNameChoice; /** @@ -1194,7 +1830,13 @@ typedef enum UPropertyNameChoice { * @stable ICU 2.2 */ typedef enum UDecompositionType { - U_DT_NONE, /*[none]*/ /*See note !!*/ + /* + * Note: UDecompositionType constants are parsed by preparseucd.py. + * It matches lines like + * U_DT_ + */ + + U_DT_NONE, /*[none]*/ U_DT_CANONICAL, /*[can]*/ U_DT_COMPAT, /*[com]*/ U_DT_CIRCLE, /*[enc]*/ @@ -1212,7 +1854,15 @@ typedef enum UDecompositionType { U_DT_SUPER, /*[sup]*/ U_DT_VERTICAL, /*[vert]*/ U_DT_WIDE, /*[wide]*/ +#ifndef U_HIDE_DEPRECATED_API + /** + * One more than the highest normal UDecompositionType value. + * The highest value is available via u_getIntPropertyMaxValue(UCHAR_DECOMPOSITION_TYPE). + * + * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. + */ U_DT_COUNT /* 18 */ +#endif // U_HIDE_DEPRECATED_API } UDecompositionType; /** @@ -1222,13 +1872,27 @@ typedef enum UDecompositionType { * @stable ICU 2.2 */ typedef enum UJoiningType { - U_JT_NON_JOINING, /*[U]*/ /*See note !!*/ + /* + * Note: UJoiningType constants are parsed by preparseucd.py. + * It matches lines like + * U_JT_ + */ + + U_JT_NON_JOINING, /*[U]*/ U_JT_JOIN_CAUSING, /*[C]*/ U_JT_DUAL_JOINING, /*[D]*/ U_JT_LEFT_JOINING, /*[L]*/ U_JT_RIGHT_JOINING, /*[R]*/ U_JT_TRANSPARENT, /*[T]*/ +#ifndef U_HIDE_DEPRECATED_API + /** + * One more than the highest normal UJoiningType value. + * The highest value is available via u_getIntPropertyMaxValue(UCHAR_JOINING_TYPE). + * + * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. + */ U_JT_COUNT /* 6 */ +#endif // U_HIDE_DEPRECATED_API } UJoiningType; /** @@ -1238,6 +1902,12 @@ typedef enum UJoiningType { * @stable ICU 2.2 */ typedef enum UJoiningGroup { + /* + * Note: UJoiningGroup constants are parsed by preparseucd.py. + * It matches lines like + * U_JG_ + */ + U_JG_NO_JOINING_GROUP, U_JG_AIN, U_JG_ALAPH, @@ -1252,7 +1922,8 @@ typedef enum UJoiningGroup { U_JG_GAF, U_JG_GAMAL, U_JG_HAH, - U_JG_HAMZA_ON_HEH_GOAL, + U_JG_TEH_MARBUTA_GOAL, /**< @stable ICU 4.6 */ + U_JG_HAMZA_ON_HEH_GOAL=U_JG_TEH_MARBUTA_GOAL, U_JG_HE, U_JG_HEH, U_JG_HEH_GOAL, @@ -1292,9 +1963,222 @@ typedef enum UJoiningGroup { U_JG_FE, /**< @stable ICU 2.6 */ U_JG_KHAPH, /**< @stable ICU 2.6 */ U_JG_ZHAIN, /**< @stable ICU 2.6 */ + U_JG_BURUSHASKI_YEH_BARREE, /**< @stable ICU 4.0 */ + U_JG_FARSI_YEH, /**< @stable ICU 4.4 */ + U_JG_NYA, /**< @stable ICU 4.4 */ + U_JG_ROHINGYA_YEH, /**< @stable ICU 49 */ + U_JG_MANICHAEAN_ALEPH, /**< @stable ICU 54 */ + U_JG_MANICHAEAN_AYIN, /**< @stable ICU 54 */ + U_JG_MANICHAEAN_BETH, /**< @stable ICU 54 */ + U_JG_MANICHAEAN_DALETH, /**< @stable ICU 54 */ + U_JG_MANICHAEAN_DHAMEDH, /**< @stable ICU 54 */ + U_JG_MANICHAEAN_FIVE, /**< @stable ICU 54 */ + U_JG_MANICHAEAN_GIMEL, /**< @stable ICU 54 */ + U_JG_MANICHAEAN_HETH, /**< @stable ICU 54 */ + U_JG_MANICHAEAN_HUNDRED, /**< @stable ICU 54 */ + U_JG_MANICHAEAN_KAPH, /**< @stable ICU 54 */ + U_JG_MANICHAEAN_LAMEDH, /**< @stable ICU 54 */ + U_JG_MANICHAEAN_MEM, /**< @stable ICU 54 */ + U_JG_MANICHAEAN_NUN, /**< @stable ICU 54 */ + U_JG_MANICHAEAN_ONE, /**< @stable ICU 54 */ + U_JG_MANICHAEAN_PE, /**< @stable ICU 54 */ + U_JG_MANICHAEAN_QOPH, /**< @stable ICU 54 */ + U_JG_MANICHAEAN_RESH, /**< @stable ICU 54 */ + U_JG_MANICHAEAN_SADHE, /**< @stable ICU 54 */ + U_JG_MANICHAEAN_SAMEKH, /**< @stable ICU 54 */ + U_JG_MANICHAEAN_TAW, /**< @stable ICU 54 */ + U_JG_MANICHAEAN_TEN, /**< @stable ICU 54 */ + U_JG_MANICHAEAN_TETH, /**< @stable ICU 54 */ + U_JG_MANICHAEAN_THAMEDH, /**< @stable ICU 54 */ + U_JG_MANICHAEAN_TWENTY, /**< @stable ICU 54 */ + U_JG_MANICHAEAN_WAW, /**< @stable ICU 54 */ + U_JG_MANICHAEAN_YODH, /**< @stable ICU 54 */ + U_JG_MANICHAEAN_ZAYIN, /**< @stable ICU 54 */ + U_JG_STRAIGHT_WAW, /**< @stable ICU 54 */ + U_JG_AFRICAN_FEH, /**< @stable ICU 58 */ + U_JG_AFRICAN_NOON, /**< @stable ICU 58 */ + U_JG_AFRICAN_QAF, /**< @stable ICU 58 */ + + U_JG_MALAYALAM_BHA, /**< @stable ICU 60 */ + U_JG_MALAYALAM_JA, /**< @stable ICU 60 */ + U_JG_MALAYALAM_LLA, /**< @stable ICU 60 */ + U_JG_MALAYALAM_LLLA, /**< @stable ICU 60 */ + U_JG_MALAYALAM_NGA, /**< @stable ICU 60 */ + U_JG_MALAYALAM_NNA, /**< @stable ICU 60 */ + U_JG_MALAYALAM_NNNA, /**< @stable ICU 60 */ + U_JG_MALAYALAM_NYA, /**< @stable ICU 60 */ + U_JG_MALAYALAM_RA, /**< @stable ICU 60 */ + U_JG_MALAYALAM_SSA, /**< @stable ICU 60 */ + U_JG_MALAYALAM_TTA, /**< @stable ICU 60 */ + + U_JG_HANIFI_ROHINGYA_KINNA_YA, /**< @stable ICU 62 */ + U_JG_HANIFI_ROHINGYA_PA, /**< @stable ICU 62 */ + +#ifndef U_HIDE_DEPRECATED_API + /** + * One more than the highest normal UJoiningGroup value. + * The highest value is available via u_getIntPropertyMaxValue(UCHAR_JOINING_GROUP). + * + * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. + */ U_JG_COUNT +#endif // U_HIDE_DEPRECATED_API } UJoiningGroup; +/** + * Grapheme Cluster Break constants. + * + * @see UCHAR_GRAPHEME_CLUSTER_BREAK + * @stable ICU 3.4 + */ +typedef enum UGraphemeClusterBreak { + /* + * Note: UGraphemeClusterBreak constants are parsed by preparseucd.py. + * It matches lines like + * U_GCB_ + */ + + U_GCB_OTHER = 0, /*[XX]*/ + U_GCB_CONTROL = 1, /*[CN]*/ + U_GCB_CR = 2, /*[CR]*/ + U_GCB_EXTEND = 3, /*[EX]*/ + U_GCB_L = 4, /*[L]*/ + U_GCB_LF = 5, /*[LF]*/ + U_GCB_LV = 6, /*[LV]*/ + U_GCB_LVT = 7, /*[LVT]*/ + U_GCB_T = 8, /*[T]*/ + U_GCB_V = 9, /*[V]*/ + /** @stable ICU 4.0 */ + U_GCB_SPACING_MARK = 10, /*[SM]*/ /* from here on: new in Unicode 5.1/ICU 4.0 */ + /** @stable ICU 4.0 */ + U_GCB_PREPEND = 11, /*[PP]*/ + /** @stable ICU 50 */ + U_GCB_REGIONAL_INDICATOR = 12, /*[RI]*/ /* new in Unicode 6.2/ICU 50 */ + /** @stable ICU 58 */ + U_GCB_E_BASE = 13, /*[EB]*/ /* from here on: new in Unicode 9.0/ICU 58 */ + /** @stable ICU 58 */ + U_GCB_E_BASE_GAZ = 14, /*[EBG]*/ + /** @stable ICU 58 */ + U_GCB_E_MODIFIER = 15, /*[EM]*/ + /** @stable ICU 58 */ + U_GCB_GLUE_AFTER_ZWJ = 16, /*[GAZ]*/ + /** @stable ICU 58 */ + U_GCB_ZWJ = 17, /*[ZWJ]*/ + +#ifndef U_HIDE_DEPRECATED_API + /** + * One more than the highest normal UGraphemeClusterBreak value. + * The highest value is available via u_getIntPropertyMaxValue(UCHAR_GRAPHEME_CLUSTER_BREAK). + * + * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. + */ + U_GCB_COUNT = 18 +#endif // U_HIDE_DEPRECATED_API +} UGraphemeClusterBreak; + +/** + * Word Break constants. + * (UWordBreak is a pre-existing enum type in ubrk.h for word break status tags.) + * + * @see UCHAR_WORD_BREAK + * @stable ICU 3.4 + */ +typedef enum UWordBreakValues { + /* + * Note: UWordBreakValues constants are parsed by preparseucd.py. + * It matches lines like + * U_WB_ + */ + + U_WB_OTHER = 0, /*[XX]*/ + U_WB_ALETTER = 1, /*[LE]*/ + U_WB_FORMAT = 2, /*[FO]*/ + U_WB_KATAKANA = 3, /*[KA]*/ + U_WB_MIDLETTER = 4, /*[ML]*/ + U_WB_MIDNUM = 5, /*[MN]*/ + U_WB_NUMERIC = 6, /*[NU]*/ + U_WB_EXTENDNUMLET = 7, /*[EX]*/ + /** @stable ICU 4.0 */ + U_WB_CR = 8, /*[CR]*/ /* from here on: new in Unicode 5.1/ICU 4.0 */ + /** @stable ICU 4.0 */ + U_WB_EXTEND = 9, /*[Extend]*/ + /** @stable ICU 4.0 */ + U_WB_LF = 10, /*[LF]*/ + /** @stable ICU 4.0 */ + U_WB_MIDNUMLET =11, /*[MB]*/ + /** @stable ICU 4.0 */ + U_WB_NEWLINE =12, /*[NL]*/ + /** @stable ICU 50 */ + U_WB_REGIONAL_INDICATOR = 13, /*[RI]*/ /* new in Unicode 6.2/ICU 50 */ + /** @stable ICU 52 */ + U_WB_HEBREW_LETTER = 14, /*[HL]*/ /* from here on: new in Unicode 6.3/ICU 52 */ + /** @stable ICU 52 */ + U_WB_SINGLE_QUOTE = 15, /*[SQ]*/ + /** @stable ICU 52 */ + U_WB_DOUBLE_QUOTE = 16, /*[DQ]*/ + /** @stable ICU 58 */ + U_WB_E_BASE = 17, /*[EB]*/ /* from here on: new in Unicode 9.0/ICU 58 */ + /** @stable ICU 58 */ + U_WB_E_BASE_GAZ = 18, /*[EBG]*/ + /** @stable ICU 58 */ + U_WB_E_MODIFIER = 19, /*[EM]*/ + /** @stable ICU 58 */ + U_WB_GLUE_AFTER_ZWJ = 20, /*[GAZ]*/ + /** @stable ICU 58 */ + U_WB_ZWJ = 21, /*[ZWJ]*/ + /** @stable ICU 62 */ + U_WB_WSEGSPACE = 22, /*[WSEGSPACE]*/ + +#ifndef U_HIDE_DEPRECATED_API + /** + * One more than the highest normal UWordBreakValues value. + * The highest value is available via u_getIntPropertyMaxValue(UCHAR_WORD_BREAK). + * + * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. + */ + U_WB_COUNT = 23 +#endif // U_HIDE_DEPRECATED_API +} UWordBreakValues; + +/** + * Sentence Break constants. + * + * @see UCHAR_SENTENCE_BREAK + * @stable ICU 3.4 + */ +typedef enum USentenceBreak { + /* + * Note: USentenceBreak constants are parsed by preparseucd.py. + * It matches lines like + * U_SB_ + */ + + U_SB_OTHER = 0, /*[XX]*/ + U_SB_ATERM = 1, /*[AT]*/ + U_SB_CLOSE = 2, /*[CL]*/ + U_SB_FORMAT = 3, /*[FO]*/ + U_SB_LOWER = 4, /*[LO]*/ + U_SB_NUMERIC = 5, /*[NU]*/ + U_SB_OLETTER = 6, /*[LE]*/ + U_SB_SEP = 7, /*[SE]*/ + U_SB_SP = 8, /*[SP]*/ + U_SB_STERM = 9, /*[ST]*/ + U_SB_UPPER = 10, /*[UP]*/ + U_SB_CR = 11, /*[CR]*/ /* from here on: new in Unicode 5.1/ICU 4.0 */ + U_SB_EXTEND = 12, /*[EX]*/ + U_SB_LF = 13, /*[LF]*/ + U_SB_SCONTINUE = 14, /*[SC]*/ +#ifndef U_HIDE_DEPRECATED_API + /** + * One more than the highest normal USentenceBreak value. + * The highest value is available via u_getIntPropertyMaxValue(UCHAR_SENTENCE_BREAK). + * + * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. + */ + U_SB_COUNT = 15 +#endif // U_HIDE_DEPRECATED_API +} USentenceBreak; + /** * Line Break constants. * @@ -1302,40 +2186,80 @@ typedef enum UJoiningGroup { * @stable ICU 2.2 */ typedef enum ULineBreak { - U_LB_UNKNOWN, /*[XX]*/ /*See note !!*/ - U_LB_AMBIGUOUS, /*[AI]*/ - U_LB_ALPHABETIC, /*[AL]*/ - U_LB_BREAK_BOTH, /*[B2]*/ - U_LB_BREAK_AFTER, /*[BA]*/ - U_LB_BREAK_BEFORE, /*[BB]*/ - U_LB_MANDATORY_BREAK, /*[BK]*/ - U_LB_CONTINGENT_BREAK, /*[CB]*/ - U_LB_CLOSE_PUNCTUATION, /*[CL]*/ - U_LB_COMBINING_MARK, /*[CM]*/ - U_LB_CARRIAGE_RETURN, /*[CR]*/ - U_LB_EXCLAMATION, /*[EX]*/ - U_LB_GLUE, /*[GL]*/ - U_LB_HYPHEN, /*[HY]*/ - U_LB_IDEOGRAPHIC, /*[ID]*/ - U_LB_INSEPERABLE, - /** Renamed from the misspelled "inseperable" in Unicode 4.0.1/ICU 3.0 @draft ICU 3.0 */ - U_LB_INSEPARABLE=U_LB_INSEPERABLE,/*[IN]*/ - U_LB_INFIX_NUMERIC, /*[IS]*/ - U_LB_LINE_FEED, /*[LF]*/ - U_LB_NONSTARTER, /*[NS]*/ - U_LB_NUMERIC, /*[NU]*/ - U_LB_OPEN_PUNCTUATION, /*[OP]*/ - U_LB_POSTFIX_NUMERIC, /*[PO]*/ - U_LB_PREFIX_NUMERIC, /*[PR]*/ - U_LB_QUOTATION, /*[QU]*/ - U_LB_COMPLEX_CONTEXT, /*[SA]*/ - U_LB_SURROGATE, /*[SG]*/ - U_LB_SPACE, /*[SP]*/ - U_LB_BREAK_SYMBOLS, /*[SY]*/ - U_LB_ZWSPACE, /*[ZW]*/ - U_LB_NEXT_LINE, /*[NL]*/ /* from here on: new in Unicode 4/ICU 2.6 */ - U_LB_WORD_JOINER, /*[WJ]*/ - U_LB_COUNT + /* + * Note: ULineBreak constants are parsed by preparseucd.py. + * It matches lines like + * U_LB_ + */ + + U_LB_UNKNOWN = 0, /*[XX]*/ + U_LB_AMBIGUOUS = 1, /*[AI]*/ + U_LB_ALPHABETIC = 2, /*[AL]*/ + U_LB_BREAK_BOTH = 3, /*[B2]*/ + U_LB_BREAK_AFTER = 4, /*[BA]*/ + U_LB_BREAK_BEFORE = 5, /*[BB]*/ + U_LB_MANDATORY_BREAK = 6, /*[BK]*/ + U_LB_CONTINGENT_BREAK = 7, /*[CB]*/ + U_LB_CLOSE_PUNCTUATION = 8, /*[CL]*/ + U_LB_COMBINING_MARK = 9, /*[CM]*/ + U_LB_CARRIAGE_RETURN = 10, /*[CR]*/ + U_LB_EXCLAMATION = 11, /*[EX]*/ + U_LB_GLUE = 12, /*[GL]*/ + U_LB_HYPHEN = 13, /*[HY]*/ + U_LB_IDEOGRAPHIC = 14, /*[ID]*/ + /** Renamed from the misspelled "inseperable" in Unicode 4.0.1/ICU 3.0 @stable ICU 3.0 */ + U_LB_INSEPARABLE = 15, /*[IN]*/ + U_LB_INSEPERABLE = U_LB_INSEPARABLE, + U_LB_INFIX_NUMERIC = 16, /*[IS]*/ + U_LB_LINE_FEED = 17, /*[LF]*/ + U_LB_NONSTARTER = 18, /*[NS]*/ + U_LB_NUMERIC = 19, /*[NU]*/ + U_LB_OPEN_PUNCTUATION = 20, /*[OP]*/ + U_LB_POSTFIX_NUMERIC = 21, /*[PO]*/ + U_LB_PREFIX_NUMERIC = 22, /*[PR]*/ + U_LB_QUOTATION = 23, /*[QU]*/ + U_LB_COMPLEX_CONTEXT = 24, /*[SA]*/ + U_LB_SURROGATE = 25, /*[SG]*/ + U_LB_SPACE = 26, /*[SP]*/ + U_LB_BREAK_SYMBOLS = 27, /*[SY]*/ + U_LB_ZWSPACE = 28, /*[ZW]*/ + /** @stable ICU 2.6 */ + U_LB_NEXT_LINE = 29, /*[NL]*/ /* from here on: new in Unicode 4/ICU 2.6 */ + /** @stable ICU 2.6 */ + U_LB_WORD_JOINER = 30, /*[WJ]*/ + /** @stable ICU 3.4 */ + U_LB_H2 = 31, /*[H2]*/ /* from here on: new in Unicode 4.1/ICU 3.4 */ + /** @stable ICU 3.4 */ + U_LB_H3 = 32, /*[H3]*/ + /** @stable ICU 3.4 */ + U_LB_JL = 33, /*[JL]*/ + /** @stable ICU 3.4 */ + U_LB_JT = 34, /*[JT]*/ + /** @stable ICU 3.4 */ + U_LB_JV = 35, /*[JV]*/ + /** @stable ICU 4.4 */ + U_LB_CLOSE_PARENTHESIS = 36, /*[CP]*/ /* new in Unicode 5.2/ICU 4.4 */ + /** @stable ICU 49 */ + U_LB_CONDITIONAL_JAPANESE_STARTER = 37,/*[CJ]*/ /* new in Unicode 6.1/ICU 49 */ + /** @stable ICU 49 */ + U_LB_HEBREW_LETTER = 38, /*[HL]*/ /* new in Unicode 6.1/ICU 49 */ + /** @stable ICU 50 */ + U_LB_REGIONAL_INDICATOR = 39,/*[RI]*/ /* new in Unicode 6.2/ICU 50 */ + /** @stable ICU 58 */ + U_LB_E_BASE = 40, /*[EB]*/ /* from here on: new in Unicode 9.0/ICU 58 */ + /** @stable ICU 58 */ + U_LB_E_MODIFIER = 41, /*[EM]*/ + /** @stable ICU 58 */ + U_LB_ZWJ = 42, /*[ZWJ]*/ +#ifndef U_HIDE_DEPRECATED_API + /** + * One more than the highest normal ULineBreak value. + * The highest value is available via u_getIntPropertyMaxValue(UCHAR_LINE_BREAK). + * + * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. + */ + U_LB_COUNT = 43 +#endif // U_HIDE_DEPRECATED_API } ULineBreak; /** @@ -1345,11 +2269,25 @@ typedef enum ULineBreak { * @stable ICU 2.2 */ typedef enum UNumericType { - U_NT_NONE, /*[None]*/ /*See note !!*/ + /* + * Note: UNumericType constants are parsed by preparseucd.py. + * It matches lines like + * U_NT_ + */ + + U_NT_NONE, /*[None]*/ U_NT_DECIMAL, /*[de]*/ U_NT_DIGIT, /*[di]*/ U_NT_NUMERIC, /*[nu]*/ +#ifndef U_HIDE_DEPRECATED_API + /** + * One more than the highest normal UNumericType value. + * The highest value is available via u_getIntPropertyMaxValue(UCHAR_NUMERIC_TYPE). + * + * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. + */ U_NT_COUNT +#endif // U_HIDE_DEPRECATED_API } UNumericType; /** @@ -1359,13 +2297,27 @@ typedef enum UNumericType { * @stable ICU 2.6 */ typedef enum UHangulSyllableType { - U_HST_NOT_APPLICABLE, /*[NA]*/ /*See note !!*/ + /* + * Note: UHangulSyllableType constants are parsed by preparseucd.py. + * It matches lines like + * U_HST_ + */ + + U_HST_NOT_APPLICABLE, /*[NA]*/ U_HST_LEADING_JAMO, /*[L]*/ U_HST_VOWEL_JAMO, /*[V]*/ U_HST_TRAILING_JAMO, /*[T]*/ U_HST_LV_SYLLABLE, /*[LV]*/ U_HST_LVT_SYLLABLE, /*[LVT]*/ +#ifndef U_HIDE_DEPRECATED_API + /** + * One more than the highest normal UHangulSyllableType value. + * The highest value is available via u_getIntPropertyMaxValue(UCHAR_HANGUL_SYLLABLE_TYPE). + * + * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. + */ U_HST_COUNT +#endif // U_HIDE_DEPRECATED_API } UHangulSyllableType; /** @@ -1562,6 +2514,8 @@ u_getIntPropertyMaxValue(UProperty which); * * For characters without any numeric values in the Unicode Character Database, * this function will return U_NO_NUMERIC_VALUE. + * Note: This is different from the Unicode Standard which specifies NaN as the default value. + * (NaN is not available on all platforms.) * * Similar to java.lang.Character.getNumericValue(), but u_getNumericValue() * also supports negative values, large values, and fractions, @@ -1606,7 +2560,6 @@ u_getNumericValue(UChar32 c); * @see UCHAR_LOWERCASE * @see u_isupper * @see u_istitle - * @see u_islower * @stable ICU 2.0 */ U_STABLE UBool U_EXPORT2 @@ -1788,8 +2741,7 @@ u_isgraph(UChar32 c); * * same as * - * TRUE for U+0009 (TAB) and characters with general category "Zs" (space separators) - * except Zero Width Space (ZWSP, U+200B). + * TRUE for U+0009 (TAB) and characters with general category "Zs" (space separators). * * Note: There are several ICU whitespace functions; please see the uchar.h * file documentation for a detailed comparison. @@ -1878,8 +2830,8 @@ u_isJavaSpaceChar(UChar32 c); * A character is considered to be a Java whitespace character if and only * if it satisfies one of the following criteria: * - * - It is a Unicode separator (categories "Z"), but is not - * a no-break space (U+00A0 NBSP or U+2007 Figure Space or U+202F Narrow NBSP). + * - It is a Unicode Separator character (categories "Z" = "Zs" or "Zl" or "Zp"), but is not + * also a non-breaking space (U+00A0 NBSP or U+2007 Figure Space or U+202F Narrow NBSP). * - It is U+0009 HORIZONTAL TABULATION. * - It is U+000A LINE FEED. * - It is U+000B VERTICAL TABULATION. @@ -1889,9 +2841,15 @@ u_isJavaSpaceChar(UChar32 c); * - It is U+001D GROUP SEPARATOR. * - It is U+001E RECORD SEPARATOR. * - It is U+001F UNIT SEPARATOR. - * - It is U+0085 NEXT LINE. * - * Same as java.lang.Character.isWhitespace() except that Java omits U+0085. + * This API tries to sync with the semantics of Java's + * java.lang.Character.isWhitespace(), but it may not return + * the exact same results because of the Unicode version + * difference. + * + * Note: Unicode 4.0.1 changed U+200B ZERO WIDTH SPACE from a Space Separator (Zs) + * to a Format Control (Cf). Since then, isWhitespace(0x200b) returns false. + * See http://www.unicode.org/versions/Unicode4.0.1/ * * Note: There are several ICU whitespace functions; please see the uchar.h * file documentation for a detailed comparison. @@ -2030,7 +2988,7 @@ u_isMirrored(UChar32 c); * as the mirror-image of the default glyph of the specified * character. This is useful for text conversion to and from * codepages with visual order, and for displays without glyph - * selecetion capabilities. + * selection capabilities. * * @param c the code point to be mapped * @return another Unicode code point that may serve as a mirror-image @@ -2044,6 +3002,25 @@ u_isMirrored(UChar32 c); U_STABLE UChar32 U_EXPORT2 u_charMirror(UChar32 c); +/** + * Maps the specified character to its paired bracket character. + * For Bidi_Paired_Bracket_Type!=None, this is the same as u_charMirror(). + * Otherwise c itself is returned. + * See http://www.unicode.org/reports/tr9/ + * + * @param c the code point to be mapped + * @return the paired bracket code point, + * or c itself if there is no such mapping + * (Bidi_Paired_Bracket_Type=None) + * + * @see UCHAR_BIDI_PAIRED_BRACKET + * @see UCHAR_BIDI_PAIRED_BRACKET_TYPE + * @see u_charMirror + * @stable ICU 52 + */ +U_STABLE UChar32 U_EXPORT2 +u_getBidiPairedBracket(UChar32 c); + /** * Returns the general category value for the code point. * @@ -2204,10 +3181,11 @@ u_charName(UChar32 code, UCharNameChoice nameChoice, char *buffer, int32_t bufferLength, UErrorCode *pErrorCode); +#ifndef U_HIDE_DEPRECATED_API /** - * Get the ISO 10646 comment for a character. - * The ISO 10646 comment is an informative field in the Unicode Character - * Database (UnicodeData.txt field 11) and is from the ISO 10646 names list. + * Returns an empty string. + * Used to return the ISO 10646 comment for a character. + * The Unicode ISO_Comment property is deprecated and has no values. * * @param c The character (code point) for which to get the ISO comment. * It must be 0<=c<=0x10ffff. @@ -2218,18 +3196,15 @@ u_charName(UChar32 code, UCharNameChoice nameChoice, * @param pErrorCode Pointer to a UErrorCode variable; * check for U_SUCCESS() after u_getISOComment() * returns. - * @return The length of the comment, or 0 if there is no comment for this character. - * If the destCapacity is less than or equal to the length, then the buffer - * contains the truncated name and the returned length indicates the full - * length of the name. - * The length does not include the zero-termination. + * @return 0 * - * @stable ICU 2.2 + * @deprecated ICU 49 */ -U_STABLE int32_t U_EXPORT2 +U_DEPRECATED int32_t U_EXPORT2 u_getISOComment(UChar32 c, char *dest, int32_t destCapacity, UErrorCode *pErrorCode); +#endif /* U_HIDE_DEPRECATED_API */ /** * Find a Unicode character by its name and return its code point value. @@ -2273,7 +3248,7 @@ u_charFromName(UCharNameChoice nameChoice, * @see u_enumCharNames * @stable ICU 1.7 */ -typedef UBool UEnumCharNamesFn(void *context, +typedef UBool U_CALLCONV UEnumCharNamesFn(void *context, UChar32 code, UCharNameChoice nameChoice, const char *name, @@ -2439,7 +3414,7 @@ u_getPropertyValueName(UProperty property, * * @return a value integer or UCHAR_INVALID_CODE if the given name * does not match any value of the given property, or if the - * property is invalid. Note: U CHAR_GENERAL_CATEGORY values + * property is invalid. Note: UCHAR_GENERAL_CATEGORY_MASK values * are not values of UCharCategory, but rather mask values * produced by U_GET_GC_MASK(). This allows grouped * categories such as [:L:] to be represented. @@ -2501,11 +3476,9 @@ u_isIDPart(UChar32 c); * according to Java. * True for characters with general category "Cf" (format controls) as well as * non-whitespace ISO controls - * (U+0000..U+0008, U+000E..U+001B, U+007F..U+0084, U+0086..U+009F). + * (U+0000..U+0008, U+000E..U+001B, U+007F..U+009F). * - * Same as java.lang.Character.isIdentifierIgnorable() - * except that Java also returns TRUE for U+0085 Next Line - * (it omits U+0085 from whitespace ISO controls). + * Same as java.lang.Character.isIdentifierIgnorable(). * * Note that Unicode just recommends to ignore Cf (format controls). * @@ -2568,10 +3541,14 @@ u_isJavaIDPart(UChar32 c); * Same as java.lang.Character.toLowerCase(). * * This function only returns the simple, single-code point case mapping. - * Full case mappings may result in zero, one or more code points and depend - * on context or language etc. + * Full case mappings should be used whenever possible because they produce + * better results by working on whole strings. + * They take into account the string context and the language and can map + * to a result string with a different length as appropriate. * Full case mappings are applied by the string case mapping functions, * see ustring.h and the UnicodeString class. + * See also the User Guide chapter on C/POSIX migration: + * http://icu-project.org/userguide/posix.html#case_mappings * * @param c the code point to be mapped * @return the Simple_Lowercase_Mapping of the code point, if any; @@ -2589,10 +3566,14 @@ u_tolower(UChar32 c); * Same as java.lang.Character.toUpperCase(). * * This function only returns the simple, single-code point case mapping. - * Full case mappings may result in zero, one or more code points and depend - * on context or language etc. + * Full case mappings should be used whenever possible because they produce + * better results by working on whole strings. + * They take into account the string context and the language and can map + * to a result string with a different length as appropriate. * Full case mappings are applied by the string case mapping functions, * see ustring.h and the UnicodeString class. + * See also the User Guide chapter on C/POSIX migration: + * http://icu-project.org/userguide/posix.html#case_mappings * * @param c the code point to be mapped * @return the Simple_Uppercase_Mapping of the code point, if any; @@ -2610,10 +3591,14 @@ u_toupper(UChar32 c); * Same as java.lang.Character.toTitleCase(). * * This function only returns the simple, single-code point case mapping. - * Full case mappings may result in zero, one or more code points and depend - * on context or language etc. + * Full case mappings should be used whenever possible because they produce + * better results by working on whole strings. + * They take into account the string context and the language and can map + * to a result string with a different length as appropriate. * Full case mappings are applied by the string case mapping functions, * see ustring.h and the UnicodeString class. + * See also the User Guide chapter on C/POSIX migration: + * http://icu-project.org/userguide/posix.html#case_mappings * * @param c the code point to be mapped * @return the Simple_Titlecase_Mapping of the code point, if any; @@ -2623,27 +3608,6 @@ u_toupper(UChar32 c); U_STABLE UChar32 U_EXPORT2 u_totitle(UChar32 c); -/** Option value for case folding: use default mappings defined in CaseFolding.txt. @stable ICU 2.0 */ -#define U_FOLD_CASE_DEFAULT 0 - -/** - * Option value for case folding: - * - * Use the modified set of mappings provided in CaseFolding.txt to handle dotted I - * and dotless i appropriately for Turkic languages (tr, az). - * - * Before Unicode 3.2, CaseFolding.txt contains mappings marked with 'I' that - * are to be included for default mappings and - * excluded for the Turkic-specific mappings. - * - * Unicode 3.2 CaseFolding.txt instead contains mappings marked with 'T' that - * are to be excluded for default mappings and - * included for the Turkic-specific mappings. - * - * @stable ICU 2.0 - */ -#define U_FOLD_CASE_EXCLUDE_SPECIAL_I 1 - /** * The given character is mapped to its case folding equivalent according to * UnicodeData.txt and CaseFolding.txt; @@ -2651,10 +3615,14 @@ u_totitle(UChar32 c); * itself is returned. * * This function only returns the simple, single-code point case mapping. - * Full case mappings may result in zero, one or more code points and depend - * on context or language etc. + * Full case mappings should be used whenever possible because they produce + * better results by working on whole strings. + * They take into account the string context and the language and can map + * to a result string with a different length as appropriate. * Full case mappings are applied by the string case mapping functions, * see ustring.h and the UnicodeString class. + * See also the User Guide chapter on C/POSIX migration: + * http://icu-project.org/userguide/posix.html#case_mappings * * @param c the code point to be mapped * @param options Either U_FOLD_CASE_DEFAULT or U_FOLD_CASE_EXCLUDE_SPECIAL_I @@ -2768,6 +3736,7 @@ u_charAge(UChar32 c, UVersionInfo versionArray); U_STABLE void U_EXPORT2 u_getUnicodeVersion(UVersionInfo versionArray); +#if !UCONFIG_NO_NORMALIZATION /** * Get the FC_NFKC_Closure property string for a character. * See Unicode Standard Annex #15 for details, search for "FC_NFKC_Closure" @@ -2792,6 +3761,9 @@ u_getUnicodeVersion(UVersionInfo versionArray); U_STABLE int32_t U_EXPORT2 u_getFC_NFKC_Closure(UChar32 c, UChar *dest, int32_t destCapacity, UErrorCode *pErrorCode); +#endif + + U_CDECL_END #endif /*_UCHAR*/