jpayne@69: // © 2016 and later: Unicode, Inc. and others. jpayne@69: // License & terms of use: http://www.unicode.org/copyright.html jpayne@69: /* jpayne@69: ********************************************************************** jpayne@69: * Copyright (C) 1997-2016, International Business Machines jpayne@69: * Corporation and others. All Rights Reserved. jpayne@69: ********************************************************************** jpayne@69: * jpayne@69: * File UCHAR.H jpayne@69: * jpayne@69: * Modification History: jpayne@69: * jpayne@69: * Date Name Description jpayne@69: * 04/02/97 aliu Creation. jpayne@69: * 03/29/99 helena Updated for C APIs. jpayne@69: * 4/15/99 Madhu Updated for C Implementation and Javadoc jpayne@69: * 5/20/99 Madhu Added the function u_getVersion() jpayne@69: * 8/19/1999 srl Upgraded scripts to Unicode 3.0 jpayne@69: * 8/27/1999 schererm UCharDirection constants: U_... jpayne@69: * 11/11/1999 weiv added u_isalnum(), cleaned comments jpayne@69: * 01/11/2000 helena Renamed u_getVersion to u_getUnicodeVersion(). jpayne@69: ****************************************************************************** jpayne@69: */ jpayne@69: jpayne@69: #ifndef UCHAR_H jpayne@69: #define UCHAR_H jpayne@69: jpayne@69: #include "unicode/utypes.h" jpayne@69: #include "unicode/stringoptions.h" jpayne@69: #include "unicode/ucpmap.h" jpayne@69: jpayne@69: #if !defined(USET_DEFINED) && !defined(U_IN_DOXYGEN) jpayne@69: jpayne@69: #define USET_DEFINED jpayne@69: jpayne@69: /** jpayne@69: * USet is the C API type corresponding to C++ class UnicodeSet. jpayne@69: * It is forward-declared here to avoid including unicode/uset.h file if related jpayne@69: * APIs are not used. jpayne@69: * jpayne@69: * @see ucnv_getUnicodeSet jpayne@69: * @stable ICU 2.4 jpayne@69: */ jpayne@69: typedef struct USet USet; jpayne@69: jpayne@69: #endif jpayne@69: jpayne@69: jpayne@69: U_CDECL_BEGIN jpayne@69: jpayne@69: /*==========================================================================*/ jpayne@69: /* Unicode version number */ jpayne@69: /*==========================================================================*/ jpayne@69: /** jpayne@69: * Unicode version number, default for the current ICU version. jpayne@69: * The actual Unicode Character Database (UCD) data is stored in uprops.dat jpayne@69: * and may be generated from UCD files from a different Unicode version. jpayne@69: * Call u_getUnicodeVersion to get the actual Unicode version of the data. jpayne@69: * jpayne@69: * @see u_getUnicodeVersion jpayne@69: * @stable ICU 2.0 jpayne@69: */ jpayne@69: #define U_UNICODE_VERSION "13.0" jpayne@69: jpayne@69: /** jpayne@69: * \file jpayne@69: * \brief C API: Unicode Properties jpayne@69: * jpayne@69: * This C API provides low-level access to the Unicode Character Database. jpayne@69: * In addition to raw property values, some convenience functions calculate jpayne@69: * derived properties, for example for Java-style programming. jpayne@69: * jpayne@69: * Unicode assigns each code point (not just assigned character) values for jpayne@69: * many properties. jpayne@69: * Most of them are simple boolean flags, or constants from a small enumerated list. jpayne@69: * For some properties, values are strings or other relatively more complex types. jpayne@69: * jpayne@69: * For more information see jpayne@69: * "About the Unicode Character Database" (http://www.unicode.org/ucd/) jpayne@69: * and the ICU User Guide chapter on Properties (http://icu-project.org/userguide/properties.html). jpayne@69: * jpayne@69: * Many properties are accessible via generic functions that take a UProperty selector. jpayne@69: * - u_hasBinaryProperty() returns a binary value (TRUE/FALSE) per property and code point. jpayne@69: * - u_getIntPropertyValue() returns an integer value per property and code point. jpayne@69: * For each supported enumerated or catalog property, there is jpayne@69: * an enum type for all of the property's values, and jpayne@69: * u_getIntPropertyValue() returns the numeric values of those constants. jpayne@69: * - u_getBinaryPropertySet() returns a set for each ICU-supported binary property with jpayne@69: * all code points for which the property is true. jpayne@69: * - u_getIntPropertyMap() returns a map for each jpayne@69: * ICU-supported enumerated/catalog/int-valued property which jpayne@69: * maps all Unicode code points to their values for that property. jpayne@69: * jpayne@69: * Many functions are designed to match java.lang.Character functions. jpayne@69: * See the individual function documentation, jpayne@69: * and see the JDK 1.4 java.lang.Character documentation jpayne@69: * at http://java.sun.com/j2se/1.4/docs/api/java/lang/Character.html jpayne@69: * jpayne@69: * There are also functions that provide easy migration from C/POSIX functions jpayne@69: * like isblank(). Their use is generally discouraged because the C/POSIX jpayne@69: * standards do not define their semantics beyond the ASCII range, which means jpayne@69: * that different implementations exhibit very different behavior. jpayne@69: * Instead, Unicode properties should be used directly. jpayne@69: * jpayne@69: * There are also only a few, broad C/POSIX character classes, and they tend jpayne@69: * to be used for conflicting purposes. For example, the "isalpha()" class jpayne@69: * is sometimes used to determine word boundaries, while a more sophisticated jpayne@69: * approach would at least distinguish initial letters from continuation jpayne@69: * characters (the latter including combining marks). jpayne@69: * (In ICU, BreakIterator is the most sophisticated API for word boundaries.) jpayne@69: * Another example: There is no "istitle()" class for titlecase characters. jpayne@69: * jpayne@69: * ICU 3.4 and later provides API access for all twelve C/POSIX character classes. jpayne@69: * ICU implements them according to the Standard Recommendations in jpayne@69: * Annex C: Compatibility Properties of UTS #18 Unicode Regular Expressions jpayne@69: * (http://www.unicode.org/reports/tr18/#Compatibility_Properties). jpayne@69: * jpayne@69: * API access for C/POSIX character classes is as follows: jpayne@69: * - alpha: u_isUAlphabetic(c) or u_hasBinaryProperty(c, UCHAR_ALPHABETIC) jpayne@69: * - lower: u_isULowercase(c) or u_hasBinaryProperty(c, UCHAR_LOWERCASE) jpayne@69: * - upper: u_isUUppercase(c) or u_hasBinaryProperty(c, UCHAR_UPPERCASE) jpayne@69: * - punct: u_ispunct(c) jpayne@69: * - digit: u_isdigit(c) or u_charType(c)==U_DECIMAL_DIGIT_NUMBER jpayne@69: * - xdigit: u_isxdigit(c) or u_hasBinaryProperty(c, UCHAR_POSIX_XDIGIT) jpayne@69: * - alnum: u_hasBinaryProperty(c, UCHAR_POSIX_ALNUM) jpayne@69: * - space: u_isUWhiteSpace(c) or u_hasBinaryProperty(c, UCHAR_WHITE_SPACE) jpayne@69: * - blank: u_isblank(c) or u_hasBinaryProperty(c, UCHAR_POSIX_BLANK) jpayne@69: * - cntrl: u_charType(c)==U_CONTROL_CHAR jpayne@69: * - graph: u_hasBinaryProperty(c, UCHAR_POSIX_GRAPH) jpayne@69: * - print: u_hasBinaryProperty(c, UCHAR_POSIX_PRINT) jpayne@69: * jpayne@69: * Note: Some of the u_isxyz() functions in uchar.h predate, and do not match, jpayne@69: * the Standard Recommendations in UTS #18. Instead, they match Java jpayne@69: * functions according to their API documentation. jpayne@69: * jpayne@69: * \htmlonly jpayne@69: * The C/POSIX character classes are also available in UnicodeSet patterns, jpayne@69: * using patterns like [:graph:] or \p{graph}. jpayne@69: * \endhtmlonly jpayne@69: * jpayne@69: * Note: There are several ICU whitespace functions. jpayne@69: * Comparison: jpayne@69: * - u_isUWhiteSpace=UCHAR_WHITE_SPACE: Unicode White_Space property; jpayne@69: * most of general categories "Z" (separators) + most whitespace ISO controls jpayne@69: * (including no-break spaces, but excluding IS1..IS4) jpayne@69: * - u_isWhitespace: Java isWhitespace; Z + whitespace ISO controls but excluding no-break spaces jpayne@69: * - u_isJavaSpaceChar: Java isSpaceChar; just Z (including no-break spaces) jpayne@69: * - u_isspace: Z + whitespace ISO controls (including no-break spaces) jpayne@69: * - u_isblank: "horizontal spaces" = TAB + Zs jpayne@69: */ jpayne@69: jpayne@69: /** jpayne@69: * Constants. jpayne@69: */ jpayne@69: jpayne@69: /** The lowest Unicode code point value. Code points are non-negative. @stable ICU 2.0 */ jpayne@69: #define UCHAR_MIN_VALUE 0 jpayne@69: jpayne@69: /** jpayne@69: * The highest Unicode code point value (scalar value) according to jpayne@69: * The Unicode Standard. This is a 21-bit value (20.1 bits, rounded up). jpayne@69: * For a single character, UChar32 is a simple type that can hold any code point value. jpayne@69: * jpayne@69: * @see UChar32 jpayne@69: * @stable ICU 2.0 jpayne@69: */ jpayne@69: #define UCHAR_MAX_VALUE 0x10ffff jpayne@69: jpayne@69: /** jpayne@69: * Get a single-bit bit set (a flag) from a bit number 0..31. jpayne@69: * @stable ICU 2.1 jpayne@69: */ jpayne@69: #define U_MASK(x) ((uint32_t)1<<(x)) jpayne@69: jpayne@69: /** jpayne@69: * Selection constants for Unicode properties. jpayne@69: * These constants are used in functions like u_hasBinaryProperty to select jpayne@69: * one of the Unicode properties. jpayne@69: * jpayne@69: * The properties APIs are intended to reflect Unicode properties as defined jpayne@69: * in the Unicode Character Database (UCD) and Unicode Technical Reports (UTR). jpayne@69: * jpayne@69: * For details about the properties see jpayne@69: * UAX #44: Unicode Character Database (http://www.unicode.org/reports/tr44/). jpayne@69: * jpayne@69: * Important: If ICU is built with UCD files from Unicode versions below, e.g., 3.2, jpayne@69: * then properties marked with "new in Unicode 3.2" are not or not fully available. jpayne@69: * Check u_getUnicodeVersion to be sure. jpayne@69: * jpayne@69: * @see u_hasBinaryProperty jpayne@69: * @see u_getIntPropertyValue jpayne@69: * @see u_getUnicodeVersion jpayne@69: * @stable ICU 2.1 jpayne@69: */ jpayne@69: typedef enum UProperty { jpayne@69: /* jpayne@69: * Note: UProperty constants are parsed by preparseucd.py. jpayne@69: * It matches lines like jpayne@69: * UCHAR_=, jpayne@69: */ jpayne@69: jpayne@69: /* Note: Place UCHAR_ALPHABETIC before UCHAR_BINARY_START so that jpayne@69: debuggers display UCHAR_ALPHABETIC as the symbolic name for 0, jpayne@69: rather than UCHAR_BINARY_START. Likewise for other *_START jpayne@69: identifiers. */ jpayne@69: jpayne@69: /** Binary property Alphabetic. Same as u_isUAlphabetic, different from u_isalpha. jpayne@69: Lu+Ll+Lt+Lm+Lo+Nl+Other_Alphabetic @stable ICU 2.1 */ jpayne@69: UCHAR_ALPHABETIC=0, jpayne@69: /** First constant for binary Unicode properties. @stable ICU 2.1 */ jpayne@69: UCHAR_BINARY_START=UCHAR_ALPHABETIC, jpayne@69: /** Binary property ASCII_Hex_Digit. 0-9 A-F a-f @stable ICU 2.1 */ jpayne@69: UCHAR_ASCII_HEX_DIGIT=1, jpayne@69: /** Binary property Bidi_Control. jpayne@69: Format controls which have specific functions jpayne@69: in the Bidi Algorithm. @stable ICU 2.1 */ jpayne@69: UCHAR_BIDI_CONTROL=2, jpayne@69: /** Binary property Bidi_Mirrored. jpayne@69: Characters that may change display in RTL text. jpayne@69: Same as u_isMirrored. jpayne@69: See Bidi Algorithm, UTR 9. @stable ICU 2.1 */ jpayne@69: UCHAR_BIDI_MIRRORED=3, jpayne@69: /** Binary property Dash. Variations of dashes. @stable ICU 2.1 */ jpayne@69: UCHAR_DASH=4, jpayne@69: /** Binary property Default_Ignorable_Code_Point (new in Unicode 3.2). jpayne@69: Ignorable in most processing. jpayne@69: <2060..206F, FFF0..FFFB, E0000..E0FFF>+Other_Default_Ignorable_Code_Point+(Cf+Cc+Cs-White_Space) @stable ICU 2.1 */ jpayne@69: UCHAR_DEFAULT_IGNORABLE_CODE_POINT=5, jpayne@69: /** Binary property Deprecated (new in Unicode 3.2). jpayne@69: The usage of deprecated characters is strongly discouraged. @stable ICU 2.1 */ jpayne@69: UCHAR_DEPRECATED=6, jpayne@69: /** Binary property Diacritic. Characters that linguistically modify jpayne@69: the meaning of another character to which they apply. @stable ICU 2.1 */ jpayne@69: UCHAR_DIACRITIC=7, jpayne@69: /** Binary property Extender. jpayne@69: Extend the value or shape of a preceding alphabetic character, jpayne@69: e.g., length and iteration marks. @stable ICU 2.1 */ jpayne@69: UCHAR_EXTENDER=8, jpayne@69: /** Binary property Full_Composition_Exclusion. jpayne@69: CompositionExclusions.txt+Singleton Decompositions+ jpayne@69: Non-Starter Decompositions. @stable ICU 2.1 */ jpayne@69: UCHAR_FULL_COMPOSITION_EXCLUSION=9, jpayne@69: /** Binary property Grapheme_Base (new in Unicode 3.2). jpayne@69: For programmatic determination of grapheme cluster boundaries. jpayne@69: [0..10FFFF]-Cc-Cf-Cs-Co-Cn-Zl-Zp-Grapheme_Link-Grapheme_Extend-CGJ @stable ICU 2.1 */ jpayne@69: UCHAR_GRAPHEME_BASE=10, jpayne@69: /** Binary property Grapheme_Extend (new in Unicode 3.2). jpayne@69: For programmatic determination of grapheme cluster boundaries. jpayne@69: Me+Mn+Mc+Other_Grapheme_Extend-Grapheme_Link-CGJ @stable ICU 2.1 */ jpayne@69: UCHAR_GRAPHEME_EXTEND=11, jpayne@69: /** Binary property Grapheme_Link (new in Unicode 3.2). jpayne@69: For programmatic determination of grapheme cluster boundaries. @stable ICU 2.1 */ jpayne@69: UCHAR_GRAPHEME_LINK=12, jpayne@69: /** Binary property Hex_Digit. jpayne@69: Characters commonly used for hexadecimal numbers. @stable ICU 2.1 */ jpayne@69: UCHAR_HEX_DIGIT=13, jpayne@69: /** Binary property Hyphen. Dashes used to mark connections jpayne@69: between pieces of words, plus the Katakana middle dot. @stable ICU 2.1 */ jpayne@69: UCHAR_HYPHEN=14, jpayne@69: /** Binary property ID_Continue. jpayne@69: Characters that can continue an identifier. jpayne@69: DerivedCoreProperties.txt also says "NOTE: Cf characters should be filtered out." jpayne@69: ID_Start+Mn+Mc+Nd+Pc @stable ICU 2.1 */ jpayne@69: UCHAR_ID_CONTINUE=15, jpayne@69: /** Binary property ID_Start. jpayne@69: Characters that can start an identifier. jpayne@69: Lu+Ll+Lt+Lm+Lo+Nl @stable ICU 2.1 */ jpayne@69: UCHAR_ID_START=16, jpayne@69: /** Binary property Ideographic. jpayne@69: CJKV ideographs. @stable ICU 2.1 */ jpayne@69: UCHAR_IDEOGRAPHIC=17, jpayne@69: /** Binary property IDS_Binary_Operator (new in Unicode 3.2). jpayne@69: For programmatic determination of jpayne@69: Ideographic Description Sequences. @stable ICU 2.1 */ jpayne@69: UCHAR_IDS_BINARY_OPERATOR=18, jpayne@69: /** Binary property IDS_Trinary_Operator (new in Unicode 3.2). jpayne@69: For programmatic determination of jpayne@69: Ideographic Description Sequences. @stable ICU 2.1 */ jpayne@69: UCHAR_IDS_TRINARY_OPERATOR=19, jpayne@69: /** Binary property Join_Control. jpayne@69: Format controls for cursive joining and ligation. @stable ICU 2.1 */ jpayne@69: UCHAR_JOIN_CONTROL=20, jpayne@69: /** Binary property Logical_Order_Exception (new in Unicode 3.2). jpayne@69: Characters that do not use logical order and jpayne@69: require special handling in most processing. @stable ICU 2.1 */ jpayne@69: UCHAR_LOGICAL_ORDER_EXCEPTION=21, jpayne@69: /** Binary property Lowercase. Same as u_isULowercase, different from u_islower. jpayne@69: Ll+Other_Lowercase @stable ICU 2.1 */ jpayne@69: UCHAR_LOWERCASE=22, jpayne@69: /** Binary property Math. Sm+Other_Math @stable ICU 2.1 */ jpayne@69: UCHAR_MATH=23, jpayne@69: /** Binary property Noncharacter_Code_Point. jpayne@69: Code points that are explicitly defined as illegal jpayne@69: for the encoding of characters. @stable ICU 2.1 */ jpayne@69: UCHAR_NONCHARACTER_CODE_POINT=24, jpayne@69: /** Binary property Quotation_Mark. @stable ICU 2.1 */ jpayne@69: UCHAR_QUOTATION_MARK=25, jpayne@69: /** Binary property Radical (new in Unicode 3.2). jpayne@69: For programmatic determination of jpayne@69: Ideographic Description Sequences. @stable ICU 2.1 */ jpayne@69: UCHAR_RADICAL=26, jpayne@69: /** Binary property Soft_Dotted (new in Unicode 3.2). jpayne@69: Characters with a "soft dot", like i or j. jpayne@69: An accent placed on these characters causes jpayne@69: the dot to disappear. @stable ICU 2.1 */ jpayne@69: UCHAR_SOFT_DOTTED=27, jpayne@69: /** Binary property Terminal_Punctuation. jpayne@69: Punctuation characters that generally mark jpayne@69: the end of textual units. @stable ICU 2.1 */ jpayne@69: UCHAR_TERMINAL_PUNCTUATION=28, jpayne@69: /** Binary property Unified_Ideograph (new in Unicode 3.2). jpayne@69: For programmatic determination of jpayne@69: Ideographic Description Sequences. @stable ICU 2.1 */ jpayne@69: UCHAR_UNIFIED_IDEOGRAPH=29, jpayne@69: /** Binary property Uppercase. Same as u_isUUppercase, different from u_isupper. jpayne@69: Lu+Other_Uppercase @stable ICU 2.1 */ jpayne@69: UCHAR_UPPERCASE=30, jpayne@69: /** Binary property White_Space. jpayne@69: Same as u_isUWhiteSpace, different from u_isspace and u_isWhitespace. jpayne@69: Space characters+TAB+CR+LF-ZWSP-ZWNBSP @stable ICU 2.1 */ jpayne@69: UCHAR_WHITE_SPACE=31, jpayne@69: /** Binary property XID_Continue. jpayne@69: ID_Continue modified to allow closure under jpayne@69: normalization forms NFKC and NFKD. @stable ICU 2.1 */ jpayne@69: UCHAR_XID_CONTINUE=32, jpayne@69: /** Binary property XID_Start. ID_Start modified to allow jpayne@69: closure under normalization forms NFKC and NFKD. @stable ICU 2.1 */ jpayne@69: UCHAR_XID_START=33, jpayne@69: /** Binary property Case_Sensitive. Either the source of a case jpayne@69: mapping or _in_ the target of a case mapping. Not the same as jpayne@69: the general category Cased_Letter. @stable ICU 2.6 */ jpayne@69: UCHAR_CASE_SENSITIVE=34, jpayne@69: /** Binary property STerm (new in Unicode 4.0.1). jpayne@69: Sentence Terminal. Used in UAX #29: Text Boundaries jpayne@69: (http://www.unicode.org/reports/tr29/) jpayne@69: @stable ICU 3.0 */ jpayne@69: UCHAR_S_TERM=35, jpayne@69: /** Binary property Variation_Selector (new in Unicode 4.0.1). jpayne@69: Indicates all those characters that qualify as Variation Selectors. jpayne@69: For details on the behavior of these characters, jpayne@69: see StandardizedVariants.html and 15.6 Variation Selectors. jpayne@69: @stable ICU 3.0 */ jpayne@69: UCHAR_VARIATION_SELECTOR=36, jpayne@69: /** Binary property NFD_Inert. jpayne@69: ICU-specific property for characters that are inert under NFD, jpayne@69: i.e., they do not interact with adjacent characters. jpayne@69: See the documentation for the Normalizer2 class and the jpayne@69: Normalizer2::isInert() method. jpayne@69: @stable ICU 3.0 */ jpayne@69: UCHAR_NFD_INERT=37, jpayne@69: /** Binary property NFKD_Inert. jpayne@69: ICU-specific property for characters that are inert under NFKD, jpayne@69: i.e., they do not interact with adjacent characters. jpayne@69: See the documentation for the Normalizer2 class and the jpayne@69: Normalizer2::isInert() method. jpayne@69: @stable ICU 3.0 */ jpayne@69: UCHAR_NFKD_INERT=38, jpayne@69: /** Binary property NFC_Inert. jpayne@69: ICU-specific property for characters that are inert under NFC, jpayne@69: i.e., they do not interact with adjacent characters. jpayne@69: See the documentation for the Normalizer2 class and the jpayne@69: Normalizer2::isInert() method. jpayne@69: @stable ICU 3.0 */ jpayne@69: UCHAR_NFC_INERT=39, jpayne@69: /** Binary property NFKC_Inert. jpayne@69: ICU-specific property for characters that are inert under NFKC, jpayne@69: i.e., they do not interact with adjacent characters. jpayne@69: See the documentation for the Normalizer2 class and the jpayne@69: Normalizer2::isInert() method. jpayne@69: @stable ICU 3.0 */ jpayne@69: UCHAR_NFKC_INERT=40, jpayne@69: /** Binary Property Segment_Starter. jpayne@69: ICU-specific property for characters that are starters in terms of jpayne@69: Unicode normalization and combining character sequences. jpayne@69: They have ccc=0 and do not occur in non-initial position of the jpayne@69: canonical decomposition of any character jpayne@69: (like a-umlaut in NFD and a Jamo T in an NFD(Hangul LVT)). jpayne@69: ICU uses this property for segmenting a string for generating a set of jpayne@69: canonically equivalent strings, e.g. for canonical closure while jpayne@69: processing collation tailoring rules. jpayne@69: @stable ICU 3.0 */ jpayne@69: UCHAR_SEGMENT_STARTER=41, jpayne@69: /** Binary property Pattern_Syntax (new in Unicode 4.1). jpayne@69: See UAX #31 Identifier and Pattern Syntax jpayne@69: (http://www.unicode.org/reports/tr31/) jpayne@69: @stable ICU 3.4 */ jpayne@69: UCHAR_PATTERN_SYNTAX=42, jpayne@69: /** Binary property Pattern_White_Space (new in Unicode 4.1). jpayne@69: See UAX #31 Identifier and Pattern Syntax jpayne@69: (http://www.unicode.org/reports/tr31/) jpayne@69: @stable ICU 3.4 */ jpayne@69: UCHAR_PATTERN_WHITE_SPACE=43, jpayne@69: /** Binary property alnum (a C/POSIX character class). jpayne@69: Implemented according to the UTS #18 Annex C Standard Recommendation. jpayne@69: See the uchar.h file documentation. jpayne@69: @stable ICU 3.4 */ jpayne@69: UCHAR_POSIX_ALNUM=44, jpayne@69: /** Binary property blank (a C/POSIX character class). jpayne@69: Implemented according to the UTS #18 Annex C Standard Recommendation. jpayne@69: See the uchar.h file documentation. jpayne@69: @stable ICU 3.4 */ jpayne@69: UCHAR_POSIX_BLANK=45, jpayne@69: /** Binary property graph (a C/POSIX character class). jpayne@69: Implemented according to the UTS #18 Annex C Standard Recommendation. jpayne@69: See the uchar.h file documentation. jpayne@69: @stable ICU 3.4 */ jpayne@69: UCHAR_POSIX_GRAPH=46, jpayne@69: /** Binary property print (a C/POSIX character class). jpayne@69: Implemented according to the UTS #18 Annex C Standard Recommendation. jpayne@69: See the uchar.h file documentation. jpayne@69: @stable ICU 3.4 */ jpayne@69: UCHAR_POSIX_PRINT=47, jpayne@69: /** Binary property xdigit (a C/POSIX character class). jpayne@69: Implemented according to the UTS #18 Annex C Standard Recommendation. jpayne@69: See the uchar.h file documentation. jpayne@69: @stable ICU 3.4 */ jpayne@69: UCHAR_POSIX_XDIGIT=48, jpayne@69: /** Binary property Cased. For Lowercase, Uppercase and Titlecase characters. @stable ICU 4.4 */ jpayne@69: UCHAR_CASED=49, jpayne@69: /** Binary property Case_Ignorable. Used in context-sensitive case mappings. @stable ICU 4.4 */ jpayne@69: UCHAR_CASE_IGNORABLE=50, jpayne@69: /** Binary property Changes_When_Lowercased. @stable ICU 4.4 */ jpayne@69: UCHAR_CHANGES_WHEN_LOWERCASED=51, jpayne@69: /** Binary property Changes_When_Uppercased. @stable ICU 4.4 */ jpayne@69: UCHAR_CHANGES_WHEN_UPPERCASED=52, jpayne@69: /** Binary property Changes_When_Titlecased. @stable ICU 4.4 */ jpayne@69: UCHAR_CHANGES_WHEN_TITLECASED=53, jpayne@69: /** Binary property Changes_When_Casefolded. @stable ICU 4.4 */ jpayne@69: UCHAR_CHANGES_WHEN_CASEFOLDED=54, jpayne@69: /** Binary property Changes_When_Casemapped. @stable ICU 4.4 */ jpayne@69: UCHAR_CHANGES_WHEN_CASEMAPPED=55, jpayne@69: /** Binary property Changes_When_NFKC_Casefolded. @stable ICU 4.4 */ jpayne@69: UCHAR_CHANGES_WHEN_NFKC_CASEFOLDED=56, jpayne@69: /** jpayne@69: * Binary property Emoji. jpayne@69: * See http://www.unicode.org/reports/tr51/#Emoji_Properties jpayne@69: * jpayne@69: * @stable ICU 57 jpayne@69: */ jpayne@69: UCHAR_EMOJI=57, jpayne@69: /** jpayne@69: * Binary property Emoji_Presentation. jpayne@69: * See http://www.unicode.org/reports/tr51/#Emoji_Properties jpayne@69: * jpayne@69: * @stable ICU 57 jpayne@69: */ jpayne@69: UCHAR_EMOJI_PRESENTATION=58, jpayne@69: /** jpayne@69: * Binary property Emoji_Modifier. jpayne@69: * See http://www.unicode.org/reports/tr51/#Emoji_Properties jpayne@69: * jpayne@69: * @stable ICU 57 jpayne@69: */ jpayne@69: UCHAR_EMOJI_MODIFIER=59, jpayne@69: /** jpayne@69: * Binary property Emoji_Modifier_Base. jpayne@69: * See http://www.unicode.org/reports/tr51/#Emoji_Properties jpayne@69: * jpayne@69: * @stable ICU 57 jpayne@69: */ jpayne@69: UCHAR_EMOJI_MODIFIER_BASE=60, jpayne@69: /** jpayne@69: * Binary property Emoji_Component. jpayne@69: * See http://www.unicode.org/reports/tr51/#Emoji_Properties jpayne@69: * jpayne@69: * @stable ICU 60 jpayne@69: */ jpayne@69: UCHAR_EMOJI_COMPONENT=61, jpayne@69: /** jpayne@69: * Binary property Regional_Indicator. jpayne@69: * @stable ICU 60 jpayne@69: */ jpayne@69: UCHAR_REGIONAL_INDICATOR=62, jpayne@69: /** jpayne@69: * Binary property Prepended_Concatenation_Mark. jpayne@69: * @stable ICU 60 jpayne@69: */ jpayne@69: UCHAR_PREPENDED_CONCATENATION_MARK=63, jpayne@69: /** jpayne@69: * Binary property Extended_Pictographic. jpayne@69: * See http://www.unicode.org/reports/tr51/#Emoji_Properties jpayne@69: * jpayne@69: * @stable ICU 62 jpayne@69: */ jpayne@69: UCHAR_EXTENDED_PICTOGRAPHIC=64, jpayne@69: #ifndef U_HIDE_DEPRECATED_API jpayne@69: /** jpayne@69: * One more than the last constant for binary Unicode properties. jpayne@69: * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. jpayne@69: */ jpayne@69: UCHAR_BINARY_LIMIT, jpayne@69: #endif // U_HIDE_DEPRECATED_API jpayne@69: jpayne@69: /** Enumerated property Bidi_Class. jpayne@69: Same as u_charDirection, returns UCharDirection values. @stable ICU 2.2 */ jpayne@69: UCHAR_BIDI_CLASS=0x1000, jpayne@69: /** First constant for enumerated/integer Unicode properties. @stable ICU 2.2 */ jpayne@69: UCHAR_INT_START=UCHAR_BIDI_CLASS, jpayne@69: /** Enumerated property Block. jpayne@69: Same as ublock_getCode, returns UBlockCode values. @stable ICU 2.2 */ jpayne@69: UCHAR_BLOCK=0x1001, jpayne@69: /** Enumerated property Canonical_Combining_Class. jpayne@69: Same as u_getCombiningClass, returns 8-bit numeric values. @stable ICU 2.2 */ jpayne@69: UCHAR_CANONICAL_COMBINING_CLASS=0x1002, jpayne@69: /** Enumerated property Decomposition_Type. jpayne@69: Returns UDecompositionType values. @stable ICU 2.2 */ jpayne@69: UCHAR_DECOMPOSITION_TYPE=0x1003, jpayne@69: /** Enumerated property East_Asian_Width. jpayne@69: See http://www.unicode.org/reports/tr11/ jpayne@69: Returns UEastAsianWidth values. @stable ICU 2.2 */ jpayne@69: UCHAR_EAST_ASIAN_WIDTH=0x1004, jpayne@69: /** Enumerated property General_Category. jpayne@69: Same as u_charType, returns UCharCategory values. @stable ICU 2.2 */ jpayne@69: UCHAR_GENERAL_CATEGORY=0x1005, jpayne@69: /** Enumerated property Joining_Group. jpayne@69: Returns UJoiningGroup values. @stable ICU 2.2 */ jpayne@69: UCHAR_JOINING_GROUP=0x1006, jpayne@69: /** Enumerated property Joining_Type. jpayne@69: Returns UJoiningType values. @stable ICU 2.2 */ jpayne@69: UCHAR_JOINING_TYPE=0x1007, jpayne@69: /** Enumerated property Line_Break. jpayne@69: Returns ULineBreak values. @stable ICU 2.2 */ jpayne@69: UCHAR_LINE_BREAK=0x1008, jpayne@69: /** Enumerated property Numeric_Type. jpayne@69: Returns UNumericType values. @stable ICU 2.2 */ jpayne@69: UCHAR_NUMERIC_TYPE=0x1009, jpayne@69: /** Enumerated property Script. jpayne@69: Same as uscript_getScript, returns UScriptCode values. @stable ICU 2.2 */ jpayne@69: UCHAR_SCRIPT=0x100A, jpayne@69: /** Enumerated property Hangul_Syllable_Type, new in Unicode 4. jpayne@69: Returns UHangulSyllableType values. @stable ICU 2.6 */ jpayne@69: UCHAR_HANGUL_SYLLABLE_TYPE=0x100B, jpayne@69: /** Enumerated property NFD_Quick_Check. jpayne@69: Returns UNormalizationCheckResult values. @stable ICU 3.0 */ jpayne@69: UCHAR_NFD_QUICK_CHECK=0x100C, jpayne@69: /** Enumerated property NFKD_Quick_Check. jpayne@69: Returns UNormalizationCheckResult values. @stable ICU 3.0 */ jpayne@69: UCHAR_NFKD_QUICK_CHECK=0x100D, jpayne@69: /** Enumerated property NFC_Quick_Check. jpayne@69: Returns UNormalizationCheckResult values. @stable ICU 3.0 */ jpayne@69: UCHAR_NFC_QUICK_CHECK=0x100E, jpayne@69: /** Enumerated property NFKC_Quick_Check. jpayne@69: Returns UNormalizationCheckResult values. @stable ICU 3.0 */ jpayne@69: UCHAR_NFKC_QUICK_CHECK=0x100F, jpayne@69: /** Enumerated property Lead_Canonical_Combining_Class. jpayne@69: ICU-specific property for the ccc of the first code point jpayne@69: of the decomposition, or lccc(c)=ccc(NFD(c)[0]). jpayne@69: Useful for checking for canonically ordered text; jpayne@69: see UNORM_FCD and http://www.unicode.org/notes/tn5/#FCD . jpayne@69: Returns 8-bit numeric values like UCHAR_CANONICAL_COMBINING_CLASS. @stable ICU 3.0 */ jpayne@69: UCHAR_LEAD_CANONICAL_COMBINING_CLASS=0x1010, jpayne@69: /** Enumerated property Trail_Canonical_Combining_Class. jpayne@69: ICU-specific property for the ccc of the last code point jpayne@69: of the decomposition, or tccc(c)=ccc(NFD(c)[last]). jpayne@69: Useful for checking for canonically ordered text; jpayne@69: see UNORM_FCD and http://www.unicode.org/notes/tn5/#FCD . jpayne@69: Returns 8-bit numeric values like UCHAR_CANONICAL_COMBINING_CLASS. @stable ICU 3.0 */ jpayne@69: UCHAR_TRAIL_CANONICAL_COMBINING_CLASS=0x1011, jpayne@69: /** Enumerated property Grapheme_Cluster_Break (new in Unicode 4.1). jpayne@69: Used in UAX #29: Text Boundaries jpayne@69: (http://www.unicode.org/reports/tr29/) jpayne@69: Returns UGraphemeClusterBreak values. @stable ICU 3.4 */ jpayne@69: UCHAR_GRAPHEME_CLUSTER_BREAK=0x1012, jpayne@69: /** Enumerated property Sentence_Break (new in Unicode 4.1). jpayne@69: Used in UAX #29: Text Boundaries jpayne@69: (http://www.unicode.org/reports/tr29/) jpayne@69: Returns USentenceBreak values. @stable ICU 3.4 */ jpayne@69: UCHAR_SENTENCE_BREAK=0x1013, jpayne@69: /** Enumerated property Word_Break (new in Unicode 4.1). jpayne@69: Used in UAX #29: Text Boundaries jpayne@69: (http://www.unicode.org/reports/tr29/) jpayne@69: Returns UWordBreakValues values. @stable ICU 3.4 */ jpayne@69: UCHAR_WORD_BREAK=0x1014, jpayne@69: /** Enumerated property Bidi_Paired_Bracket_Type (new in Unicode 6.3). jpayne@69: Used in UAX #9: Unicode Bidirectional Algorithm jpayne@69: (http://www.unicode.org/reports/tr9/) jpayne@69: Returns UBidiPairedBracketType values. @stable ICU 52 */ jpayne@69: UCHAR_BIDI_PAIRED_BRACKET_TYPE=0x1015, jpayne@69: /** jpayne@69: * Enumerated property Indic_Positional_Category. jpayne@69: * New in Unicode 6.0 as provisional property Indic_Matra_Category; jpayne@69: * renamed and changed to informative in Unicode 8.0. jpayne@69: * See http://www.unicode.org/reports/tr44/#IndicPositionalCategory.txt jpayne@69: * @stable ICU 63 jpayne@69: */ jpayne@69: UCHAR_INDIC_POSITIONAL_CATEGORY=0x1016, jpayne@69: /** jpayne@69: * Enumerated property Indic_Syllabic_Category. jpayne@69: * New in Unicode 6.0 as provisional; informative since Unicode 8.0. jpayne@69: * See http://www.unicode.org/reports/tr44/#IndicSyllabicCategory.txt jpayne@69: * @stable ICU 63 jpayne@69: */ jpayne@69: UCHAR_INDIC_SYLLABIC_CATEGORY=0x1017, jpayne@69: /** jpayne@69: * Enumerated property Vertical_Orientation. jpayne@69: * Used for UAX #50 Unicode Vertical Text Layout (https://www.unicode.org/reports/tr50/). jpayne@69: * New as a UCD property in Unicode 10.0. jpayne@69: * @stable ICU 63 jpayne@69: */ jpayne@69: UCHAR_VERTICAL_ORIENTATION=0x1018, jpayne@69: #ifndef U_HIDE_DEPRECATED_API jpayne@69: /** jpayne@69: * One more than the last constant for enumerated/integer Unicode properties. jpayne@69: * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. jpayne@69: */ jpayne@69: UCHAR_INT_LIMIT=0x1019, jpayne@69: #endif // U_HIDE_DEPRECATED_API jpayne@69: jpayne@69: /** Bitmask property General_Category_Mask. jpayne@69: This is the General_Category property returned as a bit mask. jpayne@69: When used in u_getIntPropertyValue(c), same as U_MASK(u_charType(c)), jpayne@69: returns bit masks for UCharCategory values where exactly one bit is set. jpayne@69: When used with u_getPropertyValueName() and u_getPropertyValueEnum(), jpayne@69: a multi-bit mask is used for sets of categories like "Letters". jpayne@69: Mask values should be cast to uint32_t. jpayne@69: @stable ICU 2.4 */ jpayne@69: UCHAR_GENERAL_CATEGORY_MASK=0x2000, jpayne@69: /** First constant for bit-mask Unicode properties. @stable ICU 2.4 */ jpayne@69: UCHAR_MASK_START=UCHAR_GENERAL_CATEGORY_MASK, jpayne@69: #ifndef U_HIDE_DEPRECATED_API jpayne@69: /** jpayne@69: * One more than the last constant for bit-mask Unicode properties. jpayne@69: * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. jpayne@69: */ jpayne@69: UCHAR_MASK_LIMIT=0x2001, jpayne@69: #endif // U_HIDE_DEPRECATED_API jpayne@69: jpayne@69: /** Double property Numeric_Value. jpayne@69: Corresponds to u_getNumericValue. @stable ICU 2.4 */ jpayne@69: UCHAR_NUMERIC_VALUE=0x3000, jpayne@69: /** First constant for double Unicode properties. @stable ICU 2.4 */ jpayne@69: UCHAR_DOUBLE_START=UCHAR_NUMERIC_VALUE, jpayne@69: #ifndef U_HIDE_DEPRECATED_API jpayne@69: /** jpayne@69: * One more than the last constant for double Unicode properties. jpayne@69: * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. jpayne@69: */ jpayne@69: UCHAR_DOUBLE_LIMIT=0x3001, jpayne@69: #endif // U_HIDE_DEPRECATED_API jpayne@69: jpayne@69: /** String property Age. jpayne@69: Corresponds to u_charAge. @stable ICU 2.4 */ jpayne@69: UCHAR_AGE=0x4000, jpayne@69: /** First constant for string Unicode properties. @stable ICU 2.4 */ jpayne@69: UCHAR_STRING_START=UCHAR_AGE, jpayne@69: /** String property Bidi_Mirroring_Glyph. jpayne@69: Corresponds to u_charMirror. @stable ICU 2.4 */ jpayne@69: UCHAR_BIDI_MIRRORING_GLYPH=0x4001, jpayne@69: /** String property Case_Folding. jpayne@69: Corresponds to u_strFoldCase in ustring.h. @stable ICU 2.4 */ jpayne@69: UCHAR_CASE_FOLDING=0x4002, jpayne@69: #ifndef U_HIDE_DEPRECATED_API jpayne@69: /** Deprecated string property ISO_Comment. jpayne@69: Corresponds to u_getISOComment. @deprecated ICU 49 */ jpayne@69: UCHAR_ISO_COMMENT=0x4003, jpayne@69: #endif /* U_HIDE_DEPRECATED_API */ jpayne@69: /** String property Lowercase_Mapping. jpayne@69: Corresponds to u_strToLower in ustring.h. @stable ICU 2.4 */ jpayne@69: UCHAR_LOWERCASE_MAPPING=0x4004, jpayne@69: /** String property Name. jpayne@69: Corresponds to u_charName. @stable ICU 2.4 */ jpayne@69: UCHAR_NAME=0x4005, jpayne@69: /** String property Simple_Case_Folding. jpayne@69: Corresponds to u_foldCase. @stable ICU 2.4 */ jpayne@69: UCHAR_SIMPLE_CASE_FOLDING=0x4006, jpayne@69: /** String property Simple_Lowercase_Mapping. jpayne@69: Corresponds to u_tolower. @stable ICU 2.4 */ jpayne@69: UCHAR_SIMPLE_LOWERCASE_MAPPING=0x4007, jpayne@69: /** String property Simple_Titlecase_Mapping. jpayne@69: Corresponds to u_totitle. @stable ICU 2.4 */ jpayne@69: UCHAR_SIMPLE_TITLECASE_MAPPING=0x4008, jpayne@69: /** String property Simple_Uppercase_Mapping. jpayne@69: Corresponds to u_toupper. @stable ICU 2.4 */ jpayne@69: UCHAR_SIMPLE_UPPERCASE_MAPPING=0x4009, jpayne@69: /** String property Titlecase_Mapping. jpayne@69: Corresponds to u_strToTitle in ustring.h. @stable ICU 2.4 */ jpayne@69: UCHAR_TITLECASE_MAPPING=0x400A, jpayne@69: #ifndef U_HIDE_DEPRECATED_API jpayne@69: /** String property Unicode_1_Name. jpayne@69: This property is of little practical value. jpayne@69: Beginning with ICU 49, ICU APIs return an empty string for this property. jpayne@69: Corresponds to u_charName(U_UNICODE_10_CHAR_NAME). @deprecated ICU 49 */ jpayne@69: UCHAR_UNICODE_1_NAME=0x400B, jpayne@69: #endif /* U_HIDE_DEPRECATED_API */ jpayne@69: /** String property Uppercase_Mapping. jpayne@69: Corresponds to u_strToUpper in ustring.h. @stable ICU 2.4 */ jpayne@69: UCHAR_UPPERCASE_MAPPING=0x400C, jpayne@69: /** String property Bidi_Paired_Bracket (new in Unicode 6.3). jpayne@69: Corresponds to u_getBidiPairedBracket. @stable ICU 52 */ jpayne@69: UCHAR_BIDI_PAIRED_BRACKET=0x400D, jpayne@69: #ifndef U_HIDE_DEPRECATED_API jpayne@69: /** jpayne@69: * One more than the last constant for string Unicode properties. jpayne@69: * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. jpayne@69: */ jpayne@69: UCHAR_STRING_LIMIT=0x400E, jpayne@69: #endif // U_HIDE_DEPRECATED_API jpayne@69: jpayne@69: /** Miscellaneous property Script_Extensions (new in Unicode 6.0). jpayne@69: Some characters are commonly used in multiple scripts. jpayne@69: For more information, see UAX #24: http://www.unicode.org/reports/tr24/. jpayne@69: Corresponds to uscript_hasScript and uscript_getScriptExtensions in uscript.h. jpayne@69: @stable ICU 4.6 */ jpayne@69: UCHAR_SCRIPT_EXTENSIONS=0x7000, jpayne@69: /** First constant for Unicode properties with unusual value types. @stable ICU 4.6 */ jpayne@69: UCHAR_OTHER_PROPERTY_START=UCHAR_SCRIPT_EXTENSIONS, jpayne@69: #ifndef U_HIDE_DEPRECATED_API jpayne@69: /** jpayne@69: * One more than the last constant for Unicode properties with unusual value types. jpayne@69: * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. jpayne@69: */ jpayne@69: UCHAR_OTHER_PROPERTY_LIMIT=0x7001, jpayne@69: #endif // U_HIDE_DEPRECATED_API jpayne@69: jpayne@69: /** Represents a nonexistent or invalid property or property value. @stable ICU 2.4 */ jpayne@69: UCHAR_INVALID_CODE = -1 jpayne@69: } UProperty; jpayne@69: jpayne@69: /** jpayne@69: * Data for enumerated Unicode general category types. jpayne@69: * See http://www.unicode.org/Public/UNIDATA/UnicodeData.html . jpayne@69: * @stable ICU 2.0 jpayne@69: */ jpayne@69: typedef enum UCharCategory jpayne@69: { jpayne@69: /* jpayne@69: * Note: UCharCategory constants and their API comments are parsed by preparseucd.py. jpayne@69: * It matches pairs of lines like jpayne@69: * / ** comment... * / jpayne@69: * U_<[A-Z_]+> = , jpayne@69: */ jpayne@69: jpayne@69: /** Non-category for unassigned and non-character code points. @stable ICU 2.0 */ jpayne@69: U_UNASSIGNED = 0, jpayne@69: /** Cn "Other, Not Assigned (no characters in [UnicodeData.txt] have this property)" (same as U_UNASSIGNED!) @stable ICU 2.0 */ jpayne@69: U_GENERAL_OTHER_TYPES = 0, jpayne@69: /** Lu @stable ICU 2.0 */ jpayne@69: U_UPPERCASE_LETTER = 1, jpayne@69: /** Ll @stable ICU 2.0 */ jpayne@69: U_LOWERCASE_LETTER = 2, jpayne@69: /** Lt @stable ICU 2.0 */ jpayne@69: U_TITLECASE_LETTER = 3, jpayne@69: /** Lm @stable ICU 2.0 */ jpayne@69: U_MODIFIER_LETTER = 4, jpayne@69: /** Lo @stable ICU 2.0 */ jpayne@69: U_OTHER_LETTER = 5, jpayne@69: /** Mn @stable ICU 2.0 */ jpayne@69: U_NON_SPACING_MARK = 6, jpayne@69: /** Me @stable ICU 2.0 */ jpayne@69: U_ENCLOSING_MARK = 7, jpayne@69: /** Mc @stable ICU 2.0 */ jpayne@69: U_COMBINING_SPACING_MARK = 8, jpayne@69: /** Nd @stable ICU 2.0 */ jpayne@69: U_DECIMAL_DIGIT_NUMBER = 9, jpayne@69: /** Nl @stable ICU 2.0 */ jpayne@69: U_LETTER_NUMBER = 10, jpayne@69: /** No @stable ICU 2.0 */ jpayne@69: U_OTHER_NUMBER = 11, jpayne@69: /** Zs @stable ICU 2.0 */ jpayne@69: U_SPACE_SEPARATOR = 12, jpayne@69: /** Zl @stable ICU 2.0 */ jpayne@69: U_LINE_SEPARATOR = 13, jpayne@69: /** Zp @stable ICU 2.0 */ jpayne@69: U_PARAGRAPH_SEPARATOR = 14, jpayne@69: /** Cc @stable ICU 2.0 */ jpayne@69: U_CONTROL_CHAR = 15, jpayne@69: /** Cf @stable ICU 2.0 */ jpayne@69: U_FORMAT_CHAR = 16, jpayne@69: /** Co @stable ICU 2.0 */ jpayne@69: U_PRIVATE_USE_CHAR = 17, jpayne@69: /** Cs @stable ICU 2.0 */ jpayne@69: U_SURROGATE = 18, jpayne@69: /** Pd @stable ICU 2.0 */ jpayne@69: U_DASH_PUNCTUATION = 19, jpayne@69: /** Ps @stable ICU 2.0 */ jpayne@69: U_START_PUNCTUATION = 20, jpayne@69: /** Pe @stable ICU 2.0 */ jpayne@69: U_END_PUNCTUATION = 21, jpayne@69: /** Pc @stable ICU 2.0 */ jpayne@69: U_CONNECTOR_PUNCTUATION = 22, jpayne@69: /** Po @stable ICU 2.0 */ jpayne@69: U_OTHER_PUNCTUATION = 23, jpayne@69: /** Sm @stable ICU 2.0 */ jpayne@69: U_MATH_SYMBOL = 24, jpayne@69: /** Sc @stable ICU 2.0 */ jpayne@69: U_CURRENCY_SYMBOL = 25, jpayne@69: /** Sk @stable ICU 2.0 */ jpayne@69: U_MODIFIER_SYMBOL = 26, jpayne@69: /** So @stable ICU 2.0 */ jpayne@69: U_OTHER_SYMBOL = 27, jpayne@69: /** Pi @stable ICU 2.0 */ jpayne@69: U_INITIAL_PUNCTUATION = 28, jpayne@69: /** Pf @stable ICU 2.0 */ jpayne@69: U_FINAL_PUNCTUATION = 29, jpayne@69: /** jpayne@69: * One higher than the last enum UCharCategory constant. jpayne@69: * This numeric value is stable (will not change), see jpayne@69: * http://www.unicode.org/policies/stability_policy.html#Property_Value jpayne@69: * jpayne@69: * @stable ICU 2.0 jpayne@69: */ jpayne@69: U_CHAR_CATEGORY_COUNT jpayne@69: } UCharCategory; jpayne@69: jpayne@69: /** jpayne@69: * U_GC_XX_MASK constants are bit flags corresponding to Unicode jpayne@69: * general category values. jpayne@69: * For each category, the nth bit is set if the numeric value of the jpayne@69: * corresponding UCharCategory constant is n. jpayne@69: * jpayne@69: * There are also some U_GC_Y_MASK constants for groups of general categories jpayne@69: * like L for all letter categories. jpayne@69: * jpayne@69: * @see u_charType jpayne@69: * @see U_GET_GC_MASK jpayne@69: * @see UCharCategory jpayne@69: * @stable ICU 2.1 jpayne@69: */ jpayne@69: #define U_GC_CN_MASK U_MASK(U_GENERAL_OTHER_TYPES) jpayne@69: jpayne@69: /** Mask constant for a UCharCategory. @stable ICU 2.1 */ jpayne@69: #define U_GC_LU_MASK U_MASK(U_UPPERCASE_LETTER) jpayne@69: /** Mask constant for a UCharCategory. @stable ICU 2.1 */ jpayne@69: #define U_GC_LL_MASK U_MASK(U_LOWERCASE_LETTER) jpayne@69: /** Mask constant for a UCharCategory. @stable ICU 2.1 */ jpayne@69: #define U_GC_LT_MASK U_MASK(U_TITLECASE_LETTER) jpayne@69: /** Mask constant for a UCharCategory. @stable ICU 2.1 */ jpayne@69: #define U_GC_LM_MASK U_MASK(U_MODIFIER_LETTER) jpayne@69: /** Mask constant for a UCharCategory. @stable ICU 2.1 */ jpayne@69: #define U_GC_LO_MASK U_MASK(U_OTHER_LETTER) jpayne@69: jpayne@69: /** Mask constant for a UCharCategory. @stable ICU 2.1 */ jpayne@69: #define U_GC_MN_MASK U_MASK(U_NON_SPACING_MARK) jpayne@69: /** Mask constant for a UCharCategory. @stable ICU 2.1 */ jpayne@69: #define U_GC_ME_MASK U_MASK(U_ENCLOSING_MARK) jpayne@69: /** Mask constant for a UCharCategory. @stable ICU 2.1 */ jpayne@69: #define U_GC_MC_MASK U_MASK(U_COMBINING_SPACING_MARK) jpayne@69: jpayne@69: /** Mask constant for a UCharCategory. @stable ICU 2.1 */ jpayne@69: #define U_GC_ND_MASK U_MASK(U_DECIMAL_DIGIT_NUMBER) jpayne@69: /** Mask constant for a UCharCategory. @stable ICU 2.1 */ jpayne@69: #define U_GC_NL_MASK U_MASK(U_LETTER_NUMBER) jpayne@69: /** Mask constant for a UCharCategory. @stable ICU 2.1 */ jpayne@69: #define U_GC_NO_MASK U_MASK(U_OTHER_NUMBER) jpayne@69: jpayne@69: /** Mask constant for a UCharCategory. @stable ICU 2.1 */ jpayne@69: #define U_GC_ZS_MASK U_MASK(U_SPACE_SEPARATOR) jpayne@69: /** Mask constant for a UCharCategory. @stable ICU 2.1 */ jpayne@69: #define U_GC_ZL_MASK U_MASK(U_LINE_SEPARATOR) jpayne@69: /** Mask constant for a UCharCategory. @stable ICU 2.1 */ jpayne@69: #define U_GC_ZP_MASK U_MASK(U_PARAGRAPH_SEPARATOR) jpayne@69: jpayne@69: /** Mask constant for a UCharCategory. @stable ICU 2.1 */ jpayne@69: #define U_GC_CC_MASK U_MASK(U_CONTROL_CHAR) jpayne@69: /** Mask constant for a UCharCategory. @stable ICU 2.1 */ jpayne@69: #define U_GC_CF_MASK U_MASK(U_FORMAT_CHAR) jpayne@69: /** Mask constant for a UCharCategory. @stable ICU 2.1 */ jpayne@69: #define U_GC_CO_MASK U_MASK(U_PRIVATE_USE_CHAR) jpayne@69: /** Mask constant for a UCharCategory. @stable ICU 2.1 */ jpayne@69: #define U_GC_CS_MASK U_MASK(U_SURROGATE) jpayne@69: jpayne@69: /** Mask constant for a UCharCategory. @stable ICU 2.1 */ jpayne@69: #define U_GC_PD_MASK U_MASK(U_DASH_PUNCTUATION) jpayne@69: /** Mask constant for a UCharCategory. @stable ICU 2.1 */ jpayne@69: #define U_GC_PS_MASK U_MASK(U_START_PUNCTUATION) jpayne@69: /** Mask constant for a UCharCategory. @stable ICU 2.1 */ jpayne@69: #define U_GC_PE_MASK U_MASK(U_END_PUNCTUATION) jpayne@69: /** Mask constant for a UCharCategory. @stable ICU 2.1 */ jpayne@69: #define U_GC_PC_MASK U_MASK(U_CONNECTOR_PUNCTUATION) jpayne@69: /** Mask constant for a UCharCategory. @stable ICU 2.1 */ jpayne@69: #define U_GC_PO_MASK U_MASK(U_OTHER_PUNCTUATION) jpayne@69: jpayne@69: /** Mask constant for a UCharCategory. @stable ICU 2.1 */ jpayne@69: #define U_GC_SM_MASK U_MASK(U_MATH_SYMBOL) jpayne@69: /** Mask constant for a UCharCategory. @stable ICU 2.1 */ jpayne@69: #define U_GC_SC_MASK U_MASK(U_CURRENCY_SYMBOL) jpayne@69: /** Mask constant for a UCharCategory. @stable ICU 2.1 */ jpayne@69: #define U_GC_SK_MASK U_MASK(U_MODIFIER_SYMBOL) jpayne@69: /** Mask constant for a UCharCategory. @stable ICU 2.1 */ jpayne@69: #define U_GC_SO_MASK U_MASK(U_OTHER_SYMBOL) jpayne@69: jpayne@69: /** Mask constant for a UCharCategory. @stable ICU 2.1 */ jpayne@69: #define U_GC_PI_MASK U_MASK(U_INITIAL_PUNCTUATION) jpayne@69: /** Mask constant for a UCharCategory. @stable ICU 2.1 */ jpayne@69: #define U_GC_PF_MASK U_MASK(U_FINAL_PUNCTUATION) jpayne@69: jpayne@69: jpayne@69: /** Mask constant for multiple UCharCategory bits (L Letters). @stable ICU 2.1 */ jpayne@69: #define U_GC_L_MASK \ jpayne@69: (U_GC_LU_MASK|U_GC_LL_MASK|U_GC_LT_MASK|U_GC_LM_MASK|U_GC_LO_MASK) jpayne@69: jpayne@69: /** Mask constant for multiple UCharCategory bits (LC Cased Letters). @stable ICU 2.1 */ jpayne@69: #define U_GC_LC_MASK \ jpayne@69: (U_GC_LU_MASK|U_GC_LL_MASK|U_GC_LT_MASK) jpayne@69: jpayne@69: /** Mask constant for multiple UCharCategory bits (M Marks). @stable ICU 2.1 */ jpayne@69: #define U_GC_M_MASK (U_GC_MN_MASK|U_GC_ME_MASK|U_GC_MC_MASK) jpayne@69: jpayne@69: /** Mask constant for multiple UCharCategory bits (N Numbers). @stable ICU 2.1 */ jpayne@69: #define U_GC_N_MASK (U_GC_ND_MASK|U_GC_NL_MASK|U_GC_NO_MASK) jpayne@69: jpayne@69: /** Mask constant for multiple UCharCategory bits (Z Separators). @stable ICU 2.1 */ jpayne@69: #define U_GC_Z_MASK (U_GC_ZS_MASK|U_GC_ZL_MASK|U_GC_ZP_MASK) jpayne@69: jpayne@69: /** Mask constant for multiple UCharCategory bits (C Others). @stable ICU 2.1 */ jpayne@69: #define U_GC_C_MASK \ jpayne@69: (U_GC_CN_MASK|U_GC_CC_MASK|U_GC_CF_MASK|U_GC_CO_MASK|U_GC_CS_MASK) jpayne@69: jpayne@69: /** Mask constant for multiple UCharCategory bits (P Punctuation). @stable ICU 2.1 */ jpayne@69: #define U_GC_P_MASK \ jpayne@69: (U_GC_PD_MASK|U_GC_PS_MASK|U_GC_PE_MASK|U_GC_PC_MASK|U_GC_PO_MASK| \ jpayne@69: U_GC_PI_MASK|U_GC_PF_MASK) jpayne@69: jpayne@69: /** Mask constant for multiple UCharCategory bits (S Symbols). @stable ICU 2.1 */ jpayne@69: #define U_GC_S_MASK (U_GC_SM_MASK|U_GC_SC_MASK|U_GC_SK_MASK|U_GC_SO_MASK) jpayne@69: jpayne@69: /** jpayne@69: * This specifies the language directional property of a character set. jpayne@69: * @stable ICU 2.0 jpayne@69: */ jpayne@69: typedef enum UCharDirection { jpayne@69: /* jpayne@69: * Note: UCharDirection constants and their API comments are parsed by preparseucd.py. jpayne@69: * It matches pairs of lines like jpayne@69: * / ** comment... * / jpayne@69: * U_<[A-Z_]+> = , jpayne@69: */ jpayne@69: jpayne@69: /** L @stable ICU 2.0 */ jpayne@69: U_LEFT_TO_RIGHT = 0, jpayne@69: /** R @stable ICU 2.0 */ jpayne@69: U_RIGHT_TO_LEFT = 1, jpayne@69: /** EN @stable ICU 2.0 */ jpayne@69: U_EUROPEAN_NUMBER = 2, jpayne@69: /** ES @stable ICU 2.0 */ jpayne@69: U_EUROPEAN_NUMBER_SEPARATOR = 3, jpayne@69: /** ET @stable ICU 2.0 */ jpayne@69: U_EUROPEAN_NUMBER_TERMINATOR = 4, jpayne@69: /** AN @stable ICU 2.0 */ jpayne@69: U_ARABIC_NUMBER = 5, jpayne@69: /** CS @stable ICU 2.0 */ jpayne@69: U_COMMON_NUMBER_SEPARATOR = 6, jpayne@69: /** B @stable ICU 2.0 */ jpayne@69: U_BLOCK_SEPARATOR = 7, jpayne@69: /** S @stable ICU 2.0 */ jpayne@69: U_SEGMENT_SEPARATOR = 8, jpayne@69: /** WS @stable ICU 2.0 */ jpayne@69: U_WHITE_SPACE_NEUTRAL = 9, jpayne@69: /** ON @stable ICU 2.0 */ jpayne@69: U_OTHER_NEUTRAL = 10, jpayne@69: /** LRE @stable ICU 2.0 */ jpayne@69: U_LEFT_TO_RIGHT_EMBEDDING = 11, jpayne@69: /** LRO @stable ICU 2.0 */ jpayne@69: U_LEFT_TO_RIGHT_OVERRIDE = 12, jpayne@69: /** AL @stable ICU 2.0 */ jpayne@69: U_RIGHT_TO_LEFT_ARABIC = 13, jpayne@69: /** RLE @stable ICU 2.0 */ jpayne@69: U_RIGHT_TO_LEFT_EMBEDDING = 14, jpayne@69: /** RLO @stable ICU 2.0 */ jpayne@69: U_RIGHT_TO_LEFT_OVERRIDE = 15, jpayne@69: /** PDF @stable ICU 2.0 */ jpayne@69: U_POP_DIRECTIONAL_FORMAT = 16, jpayne@69: /** NSM @stable ICU 2.0 */ jpayne@69: U_DIR_NON_SPACING_MARK = 17, jpayne@69: /** BN @stable ICU 2.0 */ jpayne@69: U_BOUNDARY_NEUTRAL = 18, jpayne@69: /** FSI @stable ICU 52 */ jpayne@69: U_FIRST_STRONG_ISOLATE = 19, jpayne@69: /** LRI @stable ICU 52 */ jpayne@69: U_LEFT_TO_RIGHT_ISOLATE = 20, jpayne@69: /** RLI @stable ICU 52 */ jpayne@69: U_RIGHT_TO_LEFT_ISOLATE = 21, jpayne@69: /** PDI @stable ICU 52 */ jpayne@69: U_POP_DIRECTIONAL_ISOLATE = 22, jpayne@69: #ifndef U_HIDE_DEPRECATED_API jpayne@69: /** jpayne@69: * One more than the highest UCharDirection value. jpayne@69: * The highest value is available via u_getIntPropertyMaxValue(UCHAR_BIDI_CLASS). jpayne@69: * jpayne@69: * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. jpayne@69: */ jpayne@69: U_CHAR_DIRECTION_COUNT jpayne@69: #endif // U_HIDE_DEPRECATED_API jpayne@69: } UCharDirection; jpayne@69: jpayne@69: /** jpayne@69: * Bidi Paired Bracket Type constants. jpayne@69: * jpayne@69: * @see UCHAR_BIDI_PAIRED_BRACKET_TYPE jpayne@69: * @stable ICU 52 jpayne@69: */ jpayne@69: typedef enum UBidiPairedBracketType { jpayne@69: /* jpayne@69: * Note: UBidiPairedBracketType constants are parsed by preparseucd.py. jpayne@69: * It matches lines like jpayne@69: * U_BPT_ jpayne@69: */ jpayne@69: jpayne@69: /** Not a paired bracket. @stable ICU 52 */ jpayne@69: U_BPT_NONE, jpayne@69: /** Open paired bracket. @stable ICU 52 */ jpayne@69: U_BPT_OPEN, jpayne@69: /** Close paired bracket. @stable ICU 52 */ jpayne@69: U_BPT_CLOSE, jpayne@69: #ifndef U_HIDE_DEPRECATED_API jpayne@69: /** jpayne@69: * One more than the highest normal UBidiPairedBracketType value. jpayne@69: * The highest value is available via u_getIntPropertyMaxValue(UCHAR_BIDI_PAIRED_BRACKET_TYPE). jpayne@69: * jpayne@69: * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. jpayne@69: */ jpayne@69: U_BPT_COUNT /* 3 */ jpayne@69: #endif // U_HIDE_DEPRECATED_API jpayne@69: } UBidiPairedBracketType; jpayne@69: jpayne@69: /** jpayne@69: * Constants for Unicode blocks, see the Unicode Data file Blocks.txt jpayne@69: * @stable ICU 2.0 jpayne@69: */ jpayne@69: enum UBlockCode { jpayne@69: /* jpayne@69: * Note: UBlockCode constants are parsed by preparseucd.py. jpayne@69: * It matches lines like jpayne@69: * UBLOCK_ = , jpayne@69: */ jpayne@69: jpayne@69: /** New No_Block value in Unicode 4. @stable ICU 2.6 */ jpayne@69: UBLOCK_NO_BLOCK = 0, /*[none]*/ /* Special range indicating No_Block */ jpayne@69: jpayne@69: /** @stable ICU 2.0 */ jpayne@69: UBLOCK_BASIC_LATIN = 1, /*[0000]*/ jpayne@69: jpayne@69: /** @stable ICU 2.0 */ jpayne@69: UBLOCK_LATIN_1_SUPPLEMENT=2, /*[0080]*/ jpayne@69: jpayne@69: /** @stable ICU 2.0 */ jpayne@69: UBLOCK_LATIN_EXTENDED_A =3, /*[0100]*/ jpayne@69: jpayne@69: /** @stable ICU 2.0 */ jpayne@69: UBLOCK_LATIN_EXTENDED_B =4, /*[0180]*/ jpayne@69: jpayne@69: /** @stable ICU 2.0 */ jpayne@69: UBLOCK_IPA_EXTENSIONS =5, /*[0250]*/ jpayne@69: jpayne@69: /** @stable ICU 2.0 */ jpayne@69: UBLOCK_SPACING_MODIFIER_LETTERS =6, /*[02B0]*/ jpayne@69: jpayne@69: /** @stable ICU 2.0 */ jpayne@69: UBLOCK_COMBINING_DIACRITICAL_MARKS =7, /*[0300]*/ jpayne@69: jpayne@69: /** jpayne@69: * Unicode 3.2 renames this block to "Greek and Coptic". jpayne@69: * @stable ICU 2.0 jpayne@69: */ jpayne@69: UBLOCK_GREEK =8, /*[0370]*/ jpayne@69: jpayne@69: /** @stable ICU 2.0 */ jpayne@69: UBLOCK_CYRILLIC =9, /*[0400]*/ jpayne@69: jpayne@69: /** @stable ICU 2.0 */ jpayne@69: UBLOCK_ARMENIAN =10, /*[0530]*/ jpayne@69: jpayne@69: /** @stable ICU 2.0 */ jpayne@69: UBLOCK_HEBREW =11, /*[0590]*/ jpayne@69: jpayne@69: /** @stable ICU 2.0 */ jpayne@69: UBLOCK_ARABIC =12, /*[0600]*/ jpayne@69: jpayne@69: /** @stable ICU 2.0 */ jpayne@69: UBLOCK_SYRIAC =13, /*[0700]*/ jpayne@69: jpayne@69: /** @stable ICU 2.0 */ jpayne@69: UBLOCK_THAANA =14, /*[0780]*/ jpayne@69: jpayne@69: /** @stable ICU 2.0 */ jpayne@69: UBLOCK_DEVANAGARI =15, /*[0900]*/ jpayne@69: jpayne@69: /** @stable ICU 2.0 */ jpayne@69: UBLOCK_BENGALI =16, /*[0980]*/ jpayne@69: jpayne@69: /** @stable ICU 2.0 */ jpayne@69: UBLOCK_GURMUKHI =17, /*[0A00]*/ jpayne@69: jpayne@69: /** @stable ICU 2.0 */ jpayne@69: UBLOCK_GUJARATI =18, /*[0A80]*/ jpayne@69: jpayne@69: /** @stable ICU 2.0 */ jpayne@69: UBLOCK_ORIYA =19, /*[0B00]*/ jpayne@69: jpayne@69: /** @stable ICU 2.0 */ jpayne@69: UBLOCK_TAMIL =20, /*[0B80]*/ jpayne@69: jpayne@69: /** @stable ICU 2.0 */ jpayne@69: UBLOCK_TELUGU =21, /*[0C00]*/ jpayne@69: jpayne@69: /** @stable ICU 2.0 */ jpayne@69: UBLOCK_KANNADA =22, /*[0C80]*/ jpayne@69: jpayne@69: /** @stable ICU 2.0 */ jpayne@69: UBLOCK_MALAYALAM =23, /*[0D00]*/ jpayne@69: jpayne@69: /** @stable ICU 2.0 */ jpayne@69: UBLOCK_SINHALA =24, /*[0D80]*/ jpayne@69: jpayne@69: /** @stable ICU 2.0 */ jpayne@69: UBLOCK_THAI =25, /*[0E00]*/ jpayne@69: jpayne@69: /** @stable ICU 2.0 */ jpayne@69: UBLOCK_LAO =26, /*[0E80]*/ jpayne@69: jpayne@69: /** @stable ICU 2.0 */ jpayne@69: UBLOCK_TIBETAN =27, /*[0F00]*/ jpayne@69: jpayne@69: /** @stable ICU 2.0 */ jpayne@69: UBLOCK_MYANMAR =28, /*[1000]*/ jpayne@69: jpayne@69: /** @stable ICU 2.0 */ jpayne@69: UBLOCK_GEORGIAN =29, /*[10A0]*/ jpayne@69: jpayne@69: /** @stable ICU 2.0 */ jpayne@69: UBLOCK_HANGUL_JAMO =30, /*[1100]*/ jpayne@69: jpayne@69: /** @stable ICU 2.0 */ jpayne@69: UBLOCK_ETHIOPIC =31, /*[1200]*/ jpayne@69: jpayne@69: /** @stable ICU 2.0 */ jpayne@69: UBLOCK_CHEROKEE =32, /*[13A0]*/ jpayne@69: jpayne@69: /** @stable ICU 2.0 */ jpayne@69: UBLOCK_UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS =33, /*[1400]*/ jpayne@69: jpayne@69: /** @stable ICU 2.0 */ jpayne@69: UBLOCK_OGHAM =34, /*[1680]*/ jpayne@69: jpayne@69: /** @stable ICU 2.0 */ jpayne@69: UBLOCK_RUNIC =35, /*[16A0]*/ jpayne@69: jpayne@69: /** @stable ICU 2.0 */ jpayne@69: UBLOCK_KHMER =36, /*[1780]*/ jpayne@69: jpayne@69: /** @stable ICU 2.0 */ jpayne@69: UBLOCK_MONGOLIAN =37, /*[1800]*/ jpayne@69: jpayne@69: /** @stable ICU 2.0 */ jpayne@69: UBLOCK_LATIN_EXTENDED_ADDITIONAL =38, /*[1E00]*/ jpayne@69: jpayne@69: /** @stable ICU 2.0 */ jpayne@69: UBLOCK_GREEK_EXTENDED =39, /*[1F00]*/ jpayne@69: jpayne@69: /** @stable ICU 2.0 */ jpayne@69: UBLOCK_GENERAL_PUNCTUATION =40, /*[2000]*/ jpayne@69: jpayne@69: /** @stable ICU 2.0 */ jpayne@69: UBLOCK_SUPERSCRIPTS_AND_SUBSCRIPTS =41, /*[2070]*/ jpayne@69: jpayne@69: /** @stable ICU 2.0 */ jpayne@69: UBLOCK_CURRENCY_SYMBOLS =42, /*[20A0]*/ jpayne@69: jpayne@69: /** jpayne@69: * Unicode 3.2 renames this block to "Combining Diacritical Marks for Symbols". jpayne@69: * @stable ICU 2.0 jpayne@69: */ jpayne@69: UBLOCK_COMBINING_MARKS_FOR_SYMBOLS =43, /*[20D0]*/ jpayne@69: jpayne@69: /** @stable ICU 2.0 */ jpayne@69: UBLOCK_LETTERLIKE_SYMBOLS =44, /*[2100]*/ jpayne@69: jpayne@69: /** @stable ICU 2.0 */ jpayne@69: UBLOCK_NUMBER_FORMS =45, /*[2150]*/ jpayne@69: jpayne@69: /** @stable ICU 2.0 */ jpayne@69: UBLOCK_ARROWS =46, /*[2190]*/ jpayne@69: jpayne@69: /** @stable ICU 2.0 */ jpayne@69: UBLOCK_MATHEMATICAL_OPERATORS =47, /*[2200]*/ jpayne@69: jpayne@69: /** @stable ICU 2.0 */ jpayne@69: UBLOCK_MISCELLANEOUS_TECHNICAL =48, /*[2300]*/ jpayne@69: jpayne@69: /** @stable ICU 2.0 */ jpayne@69: UBLOCK_CONTROL_PICTURES =49, /*[2400]*/ jpayne@69: jpayne@69: /** @stable ICU 2.0 */ jpayne@69: UBLOCK_OPTICAL_CHARACTER_RECOGNITION =50, /*[2440]*/ jpayne@69: jpayne@69: /** @stable ICU 2.0 */ jpayne@69: UBLOCK_ENCLOSED_ALPHANUMERICS =51, /*[2460]*/ jpayne@69: jpayne@69: /** @stable ICU 2.0 */ jpayne@69: UBLOCK_BOX_DRAWING =52, /*[2500]*/ jpayne@69: jpayne@69: /** @stable ICU 2.0 */ jpayne@69: UBLOCK_BLOCK_ELEMENTS =53, /*[2580]*/ jpayne@69: jpayne@69: /** @stable ICU 2.0 */ jpayne@69: UBLOCK_GEOMETRIC_SHAPES =54, /*[25A0]*/ jpayne@69: jpayne@69: /** @stable ICU 2.0 */ jpayne@69: UBLOCK_MISCELLANEOUS_SYMBOLS =55, /*[2600]*/ jpayne@69: jpayne@69: /** @stable ICU 2.0 */ jpayne@69: UBLOCK_DINGBATS =56, /*[2700]*/ jpayne@69: jpayne@69: /** @stable ICU 2.0 */ jpayne@69: UBLOCK_BRAILLE_PATTERNS =57, /*[2800]*/ jpayne@69: jpayne@69: /** @stable ICU 2.0 */ jpayne@69: UBLOCK_CJK_RADICALS_SUPPLEMENT =58, /*[2E80]*/ jpayne@69: jpayne@69: /** @stable ICU 2.0 */ jpayne@69: UBLOCK_KANGXI_RADICALS =59, /*[2F00]*/ jpayne@69: jpayne@69: /** @stable ICU 2.0 */ jpayne@69: UBLOCK_IDEOGRAPHIC_DESCRIPTION_CHARACTERS =60, /*[2FF0]*/ jpayne@69: jpayne@69: /** @stable ICU 2.0 */ jpayne@69: UBLOCK_CJK_SYMBOLS_AND_PUNCTUATION =61, /*[3000]*/ jpayne@69: jpayne@69: /** @stable ICU 2.0 */ jpayne@69: UBLOCK_HIRAGANA =62, /*[3040]*/ jpayne@69: jpayne@69: /** @stable ICU 2.0 */ jpayne@69: UBLOCK_KATAKANA =63, /*[30A0]*/ jpayne@69: jpayne@69: /** @stable ICU 2.0 */ jpayne@69: UBLOCK_BOPOMOFO =64, /*[3100]*/ jpayne@69: jpayne@69: /** @stable ICU 2.0 */ jpayne@69: UBLOCK_HANGUL_COMPATIBILITY_JAMO =65, /*[3130]*/ jpayne@69: jpayne@69: /** @stable ICU 2.0 */ jpayne@69: UBLOCK_KANBUN =66, /*[3190]*/ jpayne@69: jpayne@69: /** @stable ICU 2.0 */ jpayne@69: UBLOCK_BOPOMOFO_EXTENDED =67, /*[31A0]*/ jpayne@69: jpayne@69: /** @stable ICU 2.0 */ jpayne@69: UBLOCK_ENCLOSED_CJK_LETTERS_AND_MONTHS =68, /*[3200]*/ jpayne@69: jpayne@69: /** @stable ICU 2.0 */ jpayne@69: UBLOCK_CJK_COMPATIBILITY =69, /*[3300]*/ jpayne@69: jpayne@69: /** @stable ICU 2.0 */ jpayne@69: UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_A =70, /*[3400]*/ jpayne@69: jpayne@69: /** @stable ICU 2.0 */ jpayne@69: UBLOCK_CJK_UNIFIED_IDEOGRAPHS =71, /*[4E00]*/ jpayne@69: jpayne@69: /** @stable ICU 2.0 */ jpayne@69: UBLOCK_YI_SYLLABLES =72, /*[A000]*/ jpayne@69: jpayne@69: /** @stable ICU 2.0 */ jpayne@69: UBLOCK_YI_RADICALS =73, /*[A490]*/ jpayne@69: jpayne@69: /** @stable ICU 2.0 */ jpayne@69: UBLOCK_HANGUL_SYLLABLES =74, /*[AC00]*/ jpayne@69: jpayne@69: /** @stable ICU 2.0 */ jpayne@69: UBLOCK_HIGH_SURROGATES =75, /*[D800]*/ jpayne@69: jpayne@69: /** @stable ICU 2.0 */ jpayne@69: UBLOCK_HIGH_PRIVATE_USE_SURROGATES =76, /*[DB80]*/ jpayne@69: jpayne@69: /** @stable ICU 2.0 */ jpayne@69: UBLOCK_LOW_SURROGATES =77, /*[DC00]*/ jpayne@69: jpayne@69: /** jpayne@69: * Same as UBLOCK_PRIVATE_USE. jpayne@69: * Until Unicode 3.1.1, the corresponding block name was "Private Use", jpayne@69: * and multiple code point ranges had this block. jpayne@69: * Unicode 3.2 renames the block for the BMP PUA to "Private Use Area" and jpayne@69: * adds separate blocks for the supplementary PUAs. jpayne@69: * jpayne@69: * @stable ICU 2.0 jpayne@69: */ jpayne@69: UBLOCK_PRIVATE_USE_AREA =78, /*[E000]*/ jpayne@69: /** jpayne@69: * Same as UBLOCK_PRIVATE_USE_AREA. jpayne@69: * Until Unicode 3.1.1, the corresponding block name was "Private Use", jpayne@69: * and multiple code point ranges had this block. jpayne@69: * Unicode 3.2 renames the block for the BMP PUA to "Private Use Area" and jpayne@69: * adds separate blocks for the supplementary PUAs. jpayne@69: * jpayne@69: * @stable ICU 2.0 jpayne@69: */ jpayne@69: UBLOCK_PRIVATE_USE = UBLOCK_PRIVATE_USE_AREA, jpayne@69: jpayne@69: /** @stable ICU 2.0 */ jpayne@69: UBLOCK_CJK_COMPATIBILITY_IDEOGRAPHS =79, /*[F900]*/ jpayne@69: jpayne@69: /** @stable ICU 2.0 */ jpayne@69: UBLOCK_ALPHABETIC_PRESENTATION_FORMS =80, /*[FB00]*/ jpayne@69: jpayne@69: /** @stable ICU 2.0 */ jpayne@69: UBLOCK_ARABIC_PRESENTATION_FORMS_A =81, /*[FB50]*/ jpayne@69: jpayne@69: /** @stable ICU 2.0 */ jpayne@69: UBLOCK_COMBINING_HALF_MARKS =82, /*[FE20]*/ jpayne@69: jpayne@69: /** @stable ICU 2.0 */ jpayne@69: UBLOCK_CJK_COMPATIBILITY_FORMS =83, /*[FE30]*/ jpayne@69: jpayne@69: /** @stable ICU 2.0 */ jpayne@69: UBLOCK_SMALL_FORM_VARIANTS =84, /*[FE50]*/ jpayne@69: jpayne@69: /** @stable ICU 2.0 */ jpayne@69: UBLOCK_ARABIC_PRESENTATION_FORMS_B =85, /*[FE70]*/ jpayne@69: jpayne@69: /** @stable ICU 2.0 */ jpayne@69: UBLOCK_SPECIALS =86, /*[FFF0]*/ jpayne@69: jpayne@69: /** @stable ICU 2.0 */ jpayne@69: UBLOCK_HALFWIDTH_AND_FULLWIDTH_FORMS =87, /*[FF00]*/ jpayne@69: jpayne@69: /* New blocks in Unicode 3.1 */ jpayne@69: jpayne@69: /** @stable ICU 2.0 */ jpayne@69: UBLOCK_OLD_ITALIC = 88, /*[10300]*/ jpayne@69: /** @stable ICU 2.0 */ jpayne@69: UBLOCK_GOTHIC = 89, /*[10330]*/ jpayne@69: /** @stable ICU 2.0 */ jpayne@69: UBLOCK_DESERET = 90, /*[10400]*/ jpayne@69: /** @stable ICU 2.0 */ jpayne@69: UBLOCK_BYZANTINE_MUSICAL_SYMBOLS = 91, /*[1D000]*/ jpayne@69: /** @stable ICU 2.0 */ jpayne@69: UBLOCK_MUSICAL_SYMBOLS = 92, /*[1D100]*/ jpayne@69: /** @stable ICU 2.0 */ jpayne@69: UBLOCK_MATHEMATICAL_ALPHANUMERIC_SYMBOLS = 93, /*[1D400]*/ jpayne@69: /** @stable ICU 2.0 */ jpayne@69: UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_B = 94, /*[20000]*/ jpayne@69: /** @stable ICU 2.0 */ jpayne@69: UBLOCK_CJK_COMPATIBILITY_IDEOGRAPHS_SUPPLEMENT = 95, /*[2F800]*/ jpayne@69: /** @stable ICU 2.0 */ jpayne@69: UBLOCK_TAGS = 96, /*[E0000]*/ jpayne@69: jpayne@69: /* New blocks in Unicode 3.2 */ jpayne@69: jpayne@69: /** @stable ICU 3.0 */ jpayne@69: UBLOCK_CYRILLIC_SUPPLEMENT = 97, /*[0500]*/ jpayne@69: /** jpayne@69: * Unicode 4.0.1 renames the "Cyrillic Supplementary" block to "Cyrillic Supplement". jpayne@69: * @stable ICU 2.2 jpayne@69: */ jpayne@69: UBLOCK_CYRILLIC_SUPPLEMENTARY = UBLOCK_CYRILLIC_SUPPLEMENT, jpayne@69: /** @stable ICU 2.2 */ jpayne@69: UBLOCK_TAGALOG = 98, /*[1700]*/ jpayne@69: /** @stable ICU 2.2 */ jpayne@69: UBLOCK_HANUNOO = 99, /*[1720]*/ jpayne@69: /** @stable ICU 2.2 */ jpayne@69: UBLOCK_BUHID = 100, /*[1740]*/ jpayne@69: /** @stable ICU 2.2 */ jpayne@69: UBLOCK_TAGBANWA = 101, /*[1760]*/ jpayne@69: /** @stable ICU 2.2 */ jpayne@69: UBLOCK_MISCELLANEOUS_MATHEMATICAL_SYMBOLS_A = 102, /*[27C0]*/ jpayne@69: /** @stable ICU 2.2 */ jpayne@69: UBLOCK_SUPPLEMENTAL_ARROWS_A = 103, /*[27F0]*/ jpayne@69: /** @stable ICU 2.2 */ jpayne@69: UBLOCK_SUPPLEMENTAL_ARROWS_B = 104, /*[2900]*/ jpayne@69: /** @stable ICU 2.2 */ jpayne@69: UBLOCK_MISCELLANEOUS_MATHEMATICAL_SYMBOLS_B = 105, /*[2980]*/ jpayne@69: /** @stable ICU 2.2 */ jpayne@69: UBLOCK_SUPPLEMENTAL_MATHEMATICAL_OPERATORS = 106, /*[2A00]*/ jpayne@69: /** @stable ICU 2.2 */ jpayne@69: UBLOCK_KATAKANA_PHONETIC_EXTENSIONS = 107, /*[31F0]*/ jpayne@69: /** @stable ICU 2.2 */ jpayne@69: UBLOCK_VARIATION_SELECTORS = 108, /*[FE00]*/ jpayne@69: /** @stable ICU 2.2 */ jpayne@69: UBLOCK_SUPPLEMENTARY_PRIVATE_USE_AREA_A = 109, /*[F0000]*/ jpayne@69: /** @stable ICU 2.2 */ jpayne@69: UBLOCK_SUPPLEMENTARY_PRIVATE_USE_AREA_B = 110, /*[100000]*/ jpayne@69: jpayne@69: /* New blocks in Unicode 4 */ jpayne@69: jpayne@69: /** @stable ICU 2.6 */ jpayne@69: UBLOCK_LIMBU = 111, /*[1900]*/ jpayne@69: /** @stable ICU 2.6 */ jpayne@69: UBLOCK_TAI_LE = 112, /*[1950]*/ jpayne@69: /** @stable ICU 2.6 */ jpayne@69: UBLOCK_KHMER_SYMBOLS = 113, /*[19E0]*/ jpayne@69: /** @stable ICU 2.6 */ jpayne@69: UBLOCK_PHONETIC_EXTENSIONS = 114, /*[1D00]*/ jpayne@69: /** @stable ICU 2.6 */ jpayne@69: UBLOCK_MISCELLANEOUS_SYMBOLS_AND_ARROWS = 115, /*[2B00]*/ jpayne@69: /** @stable ICU 2.6 */ jpayne@69: UBLOCK_YIJING_HEXAGRAM_SYMBOLS = 116, /*[4DC0]*/ jpayne@69: /** @stable ICU 2.6 */ jpayne@69: UBLOCK_LINEAR_B_SYLLABARY = 117, /*[10000]*/ jpayne@69: /** @stable ICU 2.6 */ jpayne@69: UBLOCK_LINEAR_B_IDEOGRAMS = 118, /*[10080]*/ jpayne@69: /** @stable ICU 2.6 */ jpayne@69: UBLOCK_AEGEAN_NUMBERS = 119, /*[10100]*/ jpayne@69: /** @stable ICU 2.6 */ jpayne@69: UBLOCK_UGARITIC = 120, /*[10380]*/ jpayne@69: /** @stable ICU 2.6 */ jpayne@69: UBLOCK_SHAVIAN = 121, /*[10450]*/ jpayne@69: /** @stable ICU 2.6 */ jpayne@69: UBLOCK_OSMANYA = 122, /*[10480]*/ jpayne@69: /** @stable ICU 2.6 */ jpayne@69: UBLOCK_CYPRIOT_SYLLABARY = 123, /*[10800]*/ jpayne@69: /** @stable ICU 2.6 */ jpayne@69: UBLOCK_TAI_XUAN_JING_SYMBOLS = 124, /*[1D300]*/ jpayne@69: /** @stable ICU 2.6 */ jpayne@69: UBLOCK_VARIATION_SELECTORS_SUPPLEMENT = 125, /*[E0100]*/ jpayne@69: jpayne@69: /* New blocks in Unicode 4.1 */ jpayne@69: jpayne@69: /** @stable ICU 3.4 */ jpayne@69: UBLOCK_ANCIENT_GREEK_MUSICAL_NOTATION = 126, /*[1D200]*/ jpayne@69: /** @stable ICU 3.4 */ jpayne@69: UBLOCK_ANCIENT_GREEK_NUMBERS = 127, /*[10140]*/ jpayne@69: /** @stable ICU 3.4 */ jpayne@69: UBLOCK_ARABIC_SUPPLEMENT = 128, /*[0750]*/ jpayne@69: /** @stable ICU 3.4 */ jpayne@69: UBLOCK_BUGINESE = 129, /*[1A00]*/ jpayne@69: /** @stable ICU 3.4 */ jpayne@69: UBLOCK_CJK_STROKES = 130, /*[31C0]*/ jpayne@69: /** @stable ICU 3.4 */ jpayne@69: UBLOCK_COMBINING_DIACRITICAL_MARKS_SUPPLEMENT = 131, /*[1DC0]*/ jpayne@69: /** @stable ICU 3.4 */ jpayne@69: UBLOCK_COPTIC = 132, /*[2C80]*/ jpayne@69: /** @stable ICU 3.4 */ jpayne@69: UBLOCK_ETHIOPIC_EXTENDED = 133, /*[2D80]*/ jpayne@69: /** @stable ICU 3.4 */ jpayne@69: UBLOCK_ETHIOPIC_SUPPLEMENT = 134, /*[1380]*/ jpayne@69: /** @stable ICU 3.4 */ jpayne@69: UBLOCK_GEORGIAN_SUPPLEMENT = 135, /*[2D00]*/ jpayne@69: /** @stable ICU 3.4 */ jpayne@69: UBLOCK_GLAGOLITIC = 136, /*[2C00]*/ jpayne@69: /** @stable ICU 3.4 */ jpayne@69: UBLOCK_KHAROSHTHI = 137, /*[10A00]*/ jpayne@69: /** @stable ICU 3.4 */ jpayne@69: UBLOCK_MODIFIER_TONE_LETTERS = 138, /*[A700]*/ jpayne@69: /** @stable ICU 3.4 */ jpayne@69: UBLOCK_NEW_TAI_LUE = 139, /*[1980]*/ jpayne@69: /** @stable ICU 3.4 */ jpayne@69: UBLOCK_OLD_PERSIAN = 140, /*[103A0]*/ jpayne@69: /** @stable ICU 3.4 */ jpayne@69: UBLOCK_PHONETIC_EXTENSIONS_SUPPLEMENT = 141, /*[1D80]*/ jpayne@69: /** @stable ICU 3.4 */ jpayne@69: UBLOCK_SUPPLEMENTAL_PUNCTUATION = 142, /*[2E00]*/ jpayne@69: /** @stable ICU 3.4 */ jpayne@69: UBLOCK_SYLOTI_NAGRI = 143, /*[A800]*/ jpayne@69: /** @stable ICU 3.4 */ jpayne@69: UBLOCK_TIFINAGH = 144, /*[2D30]*/ jpayne@69: /** @stable ICU 3.4 */ jpayne@69: UBLOCK_VERTICAL_FORMS = 145, /*[FE10]*/ jpayne@69: jpayne@69: /* New blocks in Unicode 5.0 */ jpayne@69: jpayne@69: /** @stable ICU 3.6 */ jpayne@69: UBLOCK_NKO = 146, /*[07C0]*/ jpayne@69: /** @stable ICU 3.6 */ jpayne@69: UBLOCK_BALINESE = 147, /*[1B00]*/ jpayne@69: /** @stable ICU 3.6 */ jpayne@69: UBLOCK_LATIN_EXTENDED_C = 148, /*[2C60]*/ jpayne@69: /** @stable ICU 3.6 */ jpayne@69: UBLOCK_LATIN_EXTENDED_D = 149, /*[A720]*/ jpayne@69: /** @stable ICU 3.6 */ jpayne@69: UBLOCK_PHAGS_PA = 150, /*[A840]*/ jpayne@69: /** @stable ICU 3.6 */ jpayne@69: UBLOCK_PHOENICIAN = 151, /*[10900]*/ jpayne@69: /** @stable ICU 3.6 */ jpayne@69: UBLOCK_CUNEIFORM = 152, /*[12000]*/ jpayne@69: /** @stable ICU 3.6 */ jpayne@69: UBLOCK_CUNEIFORM_NUMBERS_AND_PUNCTUATION = 153, /*[12400]*/ jpayne@69: /** @stable ICU 3.6 */ jpayne@69: UBLOCK_COUNTING_ROD_NUMERALS = 154, /*[1D360]*/ jpayne@69: jpayne@69: /* New blocks in Unicode 5.1 */ jpayne@69: jpayne@69: /** @stable ICU 4.0 */ jpayne@69: UBLOCK_SUNDANESE = 155, /*[1B80]*/ jpayne@69: /** @stable ICU 4.0 */ jpayne@69: UBLOCK_LEPCHA = 156, /*[1C00]*/ jpayne@69: /** @stable ICU 4.0 */ jpayne@69: UBLOCK_OL_CHIKI = 157, /*[1C50]*/ jpayne@69: /** @stable ICU 4.0 */ jpayne@69: UBLOCK_CYRILLIC_EXTENDED_A = 158, /*[2DE0]*/ jpayne@69: /** @stable ICU 4.0 */ jpayne@69: UBLOCK_VAI = 159, /*[A500]*/ jpayne@69: /** @stable ICU 4.0 */ jpayne@69: UBLOCK_CYRILLIC_EXTENDED_B = 160, /*[A640]*/ jpayne@69: /** @stable ICU 4.0 */ jpayne@69: UBLOCK_SAURASHTRA = 161, /*[A880]*/ jpayne@69: /** @stable ICU 4.0 */ jpayne@69: UBLOCK_KAYAH_LI = 162, /*[A900]*/ jpayne@69: /** @stable ICU 4.0 */ jpayne@69: UBLOCK_REJANG = 163, /*[A930]*/ jpayne@69: /** @stable ICU 4.0 */ jpayne@69: UBLOCK_CHAM = 164, /*[AA00]*/ jpayne@69: /** @stable ICU 4.0 */ jpayne@69: UBLOCK_ANCIENT_SYMBOLS = 165, /*[10190]*/ jpayne@69: /** @stable ICU 4.0 */ jpayne@69: UBLOCK_PHAISTOS_DISC = 166, /*[101D0]*/ jpayne@69: /** @stable ICU 4.0 */ jpayne@69: UBLOCK_LYCIAN = 167, /*[10280]*/ jpayne@69: /** @stable ICU 4.0 */ jpayne@69: UBLOCK_CARIAN = 168, /*[102A0]*/ jpayne@69: /** @stable ICU 4.0 */ jpayne@69: UBLOCK_LYDIAN = 169, /*[10920]*/ jpayne@69: /** @stable ICU 4.0 */ jpayne@69: UBLOCK_MAHJONG_TILES = 170, /*[1F000]*/ jpayne@69: /** @stable ICU 4.0 */ jpayne@69: UBLOCK_DOMINO_TILES = 171, /*[1F030]*/ jpayne@69: jpayne@69: /* New blocks in Unicode 5.2 */ jpayne@69: jpayne@69: /** @stable ICU 4.4 */ jpayne@69: UBLOCK_SAMARITAN = 172, /*[0800]*/ jpayne@69: /** @stable ICU 4.4 */ jpayne@69: UBLOCK_UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS_EXTENDED = 173, /*[18B0]*/ jpayne@69: /** @stable ICU 4.4 */ jpayne@69: UBLOCK_TAI_THAM = 174, /*[1A20]*/ jpayne@69: /** @stable ICU 4.4 */ jpayne@69: UBLOCK_VEDIC_EXTENSIONS = 175, /*[1CD0]*/ jpayne@69: /** @stable ICU 4.4 */ jpayne@69: UBLOCK_LISU = 176, /*[A4D0]*/ jpayne@69: /** @stable ICU 4.4 */ jpayne@69: UBLOCK_BAMUM = 177, /*[A6A0]*/ jpayne@69: /** @stable ICU 4.4 */ jpayne@69: UBLOCK_COMMON_INDIC_NUMBER_FORMS = 178, /*[A830]*/ jpayne@69: /** @stable ICU 4.4 */ jpayne@69: UBLOCK_DEVANAGARI_EXTENDED = 179, /*[A8E0]*/ jpayne@69: /** @stable ICU 4.4 */ jpayne@69: UBLOCK_HANGUL_JAMO_EXTENDED_A = 180, /*[A960]*/ jpayne@69: /** @stable ICU 4.4 */ jpayne@69: UBLOCK_JAVANESE = 181, /*[A980]*/ jpayne@69: /** @stable ICU 4.4 */ jpayne@69: UBLOCK_MYANMAR_EXTENDED_A = 182, /*[AA60]*/ jpayne@69: /** @stable ICU 4.4 */ jpayne@69: UBLOCK_TAI_VIET = 183, /*[AA80]*/ jpayne@69: /** @stable ICU 4.4 */ jpayne@69: UBLOCK_MEETEI_MAYEK = 184, /*[ABC0]*/ jpayne@69: /** @stable ICU 4.4 */ jpayne@69: UBLOCK_HANGUL_JAMO_EXTENDED_B = 185, /*[D7B0]*/ jpayne@69: /** @stable ICU 4.4 */ jpayne@69: UBLOCK_IMPERIAL_ARAMAIC = 186, /*[10840]*/ jpayne@69: /** @stable ICU 4.4 */ jpayne@69: UBLOCK_OLD_SOUTH_ARABIAN = 187, /*[10A60]*/ jpayne@69: /** @stable ICU 4.4 */ jpayne@69: UBLOCK_AVESTAN = 188, /*[10B00]*/ jpayne@69: /** @stable ICU 4.4 */ jpayne@69: UBLOCK_INSCRIPTIONAL_PARTHIAN = 189, /*[10B40]*/ jpayne@69: /** @stable ICU 4.4 */ jpayne@69: UBLOCK_INSCRIPTIONAL_PAHLAVI = 190, /*[10B60]*/ jpayne@69: /** @stable ICU 4.4 */ jpayne@69: UBLOCK_OLD_TURKIC = 191, /*[10C00]*/ jpayne@69: /** @stable ICU 4.4 */ jpayne@69: UBLOCK_RUMI_NUMERAL_SYMBOLS = 192, /*[10E60]*/ jpayne@69: /** @stable ICU 4.4 */ jpayne@69: UBLOCK_KAITHI = 193, /*[11080]*/ jpayne@69: /** @stable ICU 4.4 */ jpayne@69: UBLOCK_EGYPTIAN_HIEROGLYPHS = 194, /*[13000]*/ jpayne@69: /** @stable ICU 4.4 */ jpayne@69: UBLOCK_ENCLOSED_ALPHANUMERIC_SUPPLEMENT = 195, /*[1F100]*/ jpayne@69: /** @stable ICU 4.4 */ jpayne@69: UBLOCK_ENCLOSED_IDEOGRAPHIC_SUPPLEMENT = 196, /*[1F200]*/ jpayne@69: /** @stable ICU 4.4 */ jpayne@69: UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_C = 197, /*[2A700]*/ jpayne@69: jpayne@69: /* New blocks in Unicode 6.0 */ jpayne@69: jpayne@69: /** @stable ICU 4.6 */ jpayne@69: UBLOCK_MANDAIC = 198, /*[0840]*/ jpayne@69: /** @stable ICU 4.6 */ jpayne@69: UBLOCK_BATAK = 199, /*[1BC0]*/ jpayne@69: /** @stable ICU 4.6 */ jpayne@69: UBLOCK_ETHIOPIC_EXTENDED_A = 200, /*[AB00]*/ jpayne@69: /** @stable ICU 4.6 */ jpayne@69: UBLOCK_BRAHMI = 201, /*[11000]*/ jpayne@69: /** @stable ICU 4.6 */ jpayne@69: UBLOCK_BAMUM_SUPPLEMENT = 202, /*[16800]*/ jpayne@69: /** @stable ICU 4.6 */ jpayne@69: UBLOCK_KANA_SUPPLEMENT = 203, /*[1B000]*/ jpayne@69: /** @stable ICU 4.6 */ jpayne@69: UBLOCK_PLAYING_CARDS = 204, /*[1F0A0]*/ jpayne@69: /** @stable ICU 4.6 */ jpayne@69: UBLOCK_MISCELLANEOUS_SYMBOLS_AND_PICTOGRAPHS = 205, /*[1F300]*/ jpayne@69: /** @stable ICU 4.6 */ jpayne@69: UBLOCK_EMOTICONS = 206, /*[1F600]*/ jpayne@69: /** @stable ICU 4.6 */ jpayne@69: UBLOCK_TRANSPORT_AND_MAP_SYMBOLS = 207, /*[1F680]*/ jpayne@69: /** @stable ICU 4.6 */ jpayne@69: UBLOCK_ALCHEMICAL_SYMBOLS = 208, /*[1F700]*/ jpayne@69: /** @stable ICU 4.6 */ jpayne@69: UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_D = 209, /*[2B740]*/ jpayne@69: jpayne@69: /* New blocks in Unicode 6.1 */ jpayne@69: jpayne@69: /** @stable ICU 49 */ jpayne@69: UBLOCK_ARABIC_EXTENDED_A = 210, /*[08A0]*/ jpayne@69: /** @stable ICU 49 */ jpayne@69: UBLOCK_ARABIC_MATHEMATICAL_ALPHABETIC_SYMBOLS = 211, /*[1EE00]*/ jpayne@69: /** @stable ICU 49 */ jpayne@69: UBLOCK_CHAKMA = 212, /*[11100]*/ jpayne@69: /** @stable ICU 49 */ jpayne@69: UBLOCK_MEETEI_MAYEK_EXTENSIONS = 213, /*[AAE0]*/ jpayne@69: /** @stable ICU 49 */ jpayne@69: UBLOCK_MEROITIC_CURSIVE = 214, /*[109A0]*/ jpayne@69: /** @stable ICU 49 */ jpayne@69: UBLOCK_MEROITIC_HIEROGLYPHS = 215, /*[10980]*/ jpayne@69: /** @stable ICU 49 */ jpayne@69: UBLOCK_MIAO = 216, /*[16F00]*/ jpayne@69: /** @stable ICU 49 */ jpayne@69: UBLOCK_SHARADA = 217, /*[11180]*/ jpayne@69: /** @stable ICU 49 */ jpayne@69: UBLOCK_SORA_SOMPENG = 218, /*[110D0]*/ jpayne@69: /** @stable ICU 49 */ jpayne@69: UBLOCK_SUNDANESE_SUPPLEMENT = 219, /*[1CC0]*/ jpayne@69: /** @stable ICU 49 */ jpayne@69: UBLOCK_TAKRI = 220, /*[11680]*/ jpayne@69: jpayne@69: /* New blocks in Unicode 7.0 */ jpayne@69: jpayne@69: /** @stable ICU 54 */ jpayne@69: UBLOCK_BASSA_VAH = 221, /*[16AD0]*/ jpayne@69: /** @stable ICU 54 */ jpayne@69: UBLOCK_CAUCASIAN_ALBANIAN = 222, /*[10530]*/ jpayne@69: /** @stable ICU 54 */ jpayne@69: UBLOCK_COPTIC_EPACT_NUMBERS = 223, /*[102E0]*/ jpayne@69: /** @stable ICU 54 */ jpayne@69: UBLOCK_COMBINING_DIACRITICAL_MARKS_EXTENDED = 224, /*[1AB0]*/ jpayne@69: /** @stable ICU 54 */ jpayne@69: UBLOCK_DUPLOYAN = 225, /*[1BC00]*/ jpayne@69: /** @stable ICU 54 */ jpayne@69: UBLOCK_ELBASAN = 226, /*[10500]*/ jpayne@69: /** @stable ICU 54 */ jpayne@69: UBLOCK_GEOMETRIC_SHAPES_EXTENDED = 227, /*[1F780]*/ jpayne@69: /** @stable ICU 54 */ jpayne@69: UBLOCK_GRANTHA = 228, /*[11300]*/ jpayne@69: /** @stable ICU 54 */ jpayne@69: UBLOCK_KHOJKI = 229, /*[11200]*/ jpayne@69: /** @stable ICU 54 */ jpayne@69: UBLOCK_KHUDAWADI = 230, /*[112B0]*/ jpayne@69: /** @stable ICU 54 */ jpayne@69: UBLOCK_LATIN_EXTENDED_E = 231, /*[AB30]*/ jpayne@69: /** @stable ICU 54 */ jpayne@69: UBLOCK_LINEAR_A = 232, /*[10600]*/ jpayne@69: /** @stable ICU 54 */ jpayne@69: UBLOCK_MAHAJANI = 233, /*[11150]*/ jpayne@69: /** @stable ICU 54 */ jpayne@69: UBLOCK_MANICHAEAN = 234, /*[10AC0]*/ jpayne@69: /** @stable ICU 54 */ jpayne@69: UBLOCK_MENDE_KIKAKUI = 235, /*[1E800]*/ jpayne@69: /** @stable ICU 54 */ jpayne@69: UBLOCK_MODI = 236, /*[11600]*/ jpayne@69: /** @stable ICU 54 */ jpayne@69: UBLOCK_MRO = 237, /*[16A40]*/ jpayne@69: /** @stable ICU 54 */ jpayne@69: UBLOCK_MYANMAR_EXTENDED_B = 238, /*[A9E0]*/ jpayne@69: /** @stable ICU 54 */ jpayne@69: UBLOCK_NABATAEAN = 239, /*[10880]*/ jpayne@69: /** @stable ICU 54 */ jpayne@69: UBLOCK_OLD_NORTH_ARABIAN = 240, /*[10A80]*/ jpayne@69: /** @stable ICU 54 */ jpayne@69: UBLOCK_OLD_PERMIC = 241, /*[10350]*/ jpayne@69: /** @stable ICU 54 */ jpayne@69: UBLOCK_ORNAMENTAL_DINGBATS = 242, /*[1F650]*/ jpayne@69: /** @stable ICU 54 */ jpayne@69: UBLOCK_PAHAWH_HMONG = 243, /*[16B00]*/ jpayne@69: /** @stable ICU 54 */ jpayne@69: UBLOCK_PALMYRENE = 244, /*[10860]*/ jpayne@69: /** @stable ICU 54 */ jpayne@69: UBLOCK_PAU_CIN_HAU = 245, /*[11AC0]*/ jpayne@69: /** @stable ICU 54 */ jpayne@69: UBLOCK_PSALTER_PAHLAVI = 246, /*[10B80]*/ jpayne@69: /** @stable ICU 54 */ jpayne@69: UBLOCK_SHORTHAND_FORMAT_CONTROLS = 247, /*[1BCA0]*/ jpayne@69: /** @stable ICU 54 */ jpayne@69: UBLOCK_SIDDHAM = 248, /*[11580]*/ jpayne@69: /** @stable ICU 54 */ jpayne@69: UBLOCK_SINHALA_ARCHAIC_NUMBERS = 249, /*[111E0]*/ jpayne@69: /** @stable ICU 54 */ jpayne@69: UBLOCK_SUPPLEMENTAL_ARROWS_C = 250, /*[1F800]*/ jpayne@69: /** @stable ICU 54 */ jpayne@69: UBLOCK_TIRHUTA = 251, /*[11480]*/ jpayne@69: /** @stable ICU 54 */ jpayne@69: UBLOCK_WARANG_CITI = 252, /*[118A0]*/ jpayne@69: jpayne@69: /* New blocks in Unicode 8.0 */ jpayne@69: jpayne@69: /** @stable ICU 56 */ jpayne@69: UBLOCK_AHOM = 253, /*[11700]*/ jpayne@69: /** @stable ICU 56 */ jpayne@69: UBLOCK_ANATOLIAN_HIEROGLYPHS = 254, /*[14400]*/ jpayne@69: /** @stable ICU 56 */ jpayne@69: UBLOCK_CHEROKEE_SUPPLEMENT = 255, /*[AB70]*/ jpayne@69: /** @stable ICU 56 */ jpayne@69: UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_E = 256, /*[2B820]*/ jpayne@69: /** @stable ICU 56 */ jpayne@69: UBLOCK_EARLY_DYNASTIC_CUNEIFORM = 257, /*[12480]*/ jpayne@69: /** @stable ICU 56 */ jpayne@69: UBLOCK_HATRAN = 258, /*[108E0]*/ jpayne@69: /** @stable ICU 56 */ jpayne@69: UBLOCK_MULTANI = 259, /*[11280]*/ jpayne@69: /** @stable ICU 56 */ jpayne@69: UBLOCK_OLD_HUNGARIAN = 260, /*[10C80]*/ jpayne@69: /** @stable ICU 56 */ jpayne@69: UBLOCK_SUPPLEMENTAL_SYMBOLS_AND_PICTOGRAPHS = 261, /*[1F900]*/ jpayne@69: /** @stable ICU 56 */ jpayne@69: UBLOCK_SUTTON_SIGNWRITING = 262, /*[1D800]*/ jpayne@69: jpayne@69: /* New blocks in Unicode 9.0 */ jpayne@69: jpayne@69: /** @stable ICU 58 */ jpayne@69: UBLOCK_ADLAM = 263, /*[1E900]*/ jpayne@69: /** @stable ICU 58 */ jpayne@69: UBLOCK_BHAIKSUKI = 264, /*[11C00]*/ jpayne@69: /** @stable ICU 58 */ jpayne@69: UBLOCK_CYRILLIC_EXTENDED_C = 265, /*[1C80]*/ jpayne@69: /** @stable ICU 58 */ jpayne@69: UBLOCK_GLAGOLITIC_SUPPLEMENT = 266, /*[1E000]*/ jpayne@69: /** @stable ICU 58 */ jpayne@69: UBLOCK_IDEOGRAPHIC_SYMBOLS_AND_PUNCTUATION = 267, /*[16FE0]*/ jpayne@69: /** @stable ICU 58 */ jpayne@69: UBLOCK_MARCHEN = 268, /*[11C70]*/ jpayne@69: /** @stable ICU 58 */ jpayne@69: UBLOCK_MONGOLIAN_SUPPLEMENT = 269, /*[11660]*/ jpayne@69: /** @stable ICU 58 */ jpayne@69: UBLOCK_NEWA = 270, /*[11400]*/ jpayne@69: /** @stable ICU 58 */ jpayne@69: UBLOCK_OSAGE = 271, /*[104B0]*/ jpayne@69: /** @stable ICU 58 */ jpayne@69: UBLOCK_TANGUT = 272, /*[17000]*/ jpayne@69: /** @stable ICU 58 */ jpayne@69: UBLOCK_TANGUT_COMPONENTS = 273, /*[18800]*/ jpayne@69: jpayne@69: // New blocks in Unicode 10.0 jpayne@69: jpayne@69: /** @stable ICU 60 */ jpayne@69: UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_F = 274, /*[2CEB0]*/ jpayne@69: /** @stable ICU 60 */ jpayne@69: UBLOCK_KANA_EXTENDED_A = 275, /*[1B100]*/ jpayne@69: /** @stable ICU 60 */ jpayne@69: UBLOCK_MASARAM_GONDI = 276, /*[11D00]*/ jpayne@69: /** @stable ICU 60 */ jpayne@69: UBLOCK_NUSHU = 277, /*[1B170]*/ jpayne@69: /** @stable ICU 60 */ jpayne@69: UBLOCK_SOYOMBO = 278, /*[11A50]*/ jpayne@69: /** @stable ICU 60 */ jpayne@69: UBLOCK_SYRIAC_SUPPLEMENT = 279, /*[0860]*/ jpayne@69: /** @stable ICU 60 */ jpayne@69: UBLOCK_ZANABAZAR_SQUARE = 280, /*[11A00]*/ jpayne@69: jpayne@69: // New blocks in Unicode 11.0 jpayne@69: jpayne@69: /** @stable ICU 62 */ jpayne@69: UBLOCK_CHESS_SYMBOLS = 281, /*[1FA00]*/ jpayne@69: /** @stable ICU 62 */ jpayne@69: UBLOCK_DOGRA = 282, /*[11800]*/ jpayne@69: /** @stable ICU 62 */ jpayne@69: UBLOCK_GEORGIAN_EXTENDED = 283, /*[1C90]*/ jpayne@69: /** @stable ICU 62 */ jpayne@69: UBLOCK_GUNJALA_GONDI = 284, /*[11D60]*/ jpayne@69: /** @stable ICU 62 */ jpayne@69: UBLOCK_HANIFI_ROHINGYA = 285, /*[10D00]*/ jpayne@69: /** @stable ICU 62 */ jpayne@69: UBLOCK_INDIC_SIYAQ_NUMBERS = 286, /*[1EC70]*/ jpayne@69: /** @stable ICU 62 */ jpayne@69: UBLOCK_MAKASAR = 287, /*[11EE0]*/ jpayne@69: /** @stable ICU 62 */ jpayne@69: UBLOCK_MAYAN_NUMERALS = 288, /*[1D2E0]*/ jpayne@69: /** @stable ICU 62 */ jpayne@69: UBLOCK_MEDEFAIDRIN = 289, /*[16E40]*/ jpayne@69: /** @stable ICU 62 */ jpayne@69: UBLOCK_OLD_SOGDIAN = 290, /*[10F00]*/ jpayne@69: /** @stable ICU 62 */ jpayne@69: UBLOCK_SOGDIAN = 291, /*[10F30]*/ jpayne@69: jpayne@69: // New blocks in Unicode 12.0 jpayne@69: jpayne@69: /** @stable ICU 64 */ jpayne@69: UBLOCK_EGYPTIAN_HIEROGLYPH_FORMAT_CONTROLS = 292, /*[13430]*/ jpayne@69: /** @stable ICU 64 */ jpayne@69: UBLOCK_ELYMAIC = 293, /*[10FE0]*/ jpayne@69: /** @stable ICU 64 */ jpayne@69: UBLOCK_NANDINAGARI = 294, /*[119A0]*/ jpayne@69: /** @stable ICU 64 */ jpayne@69: UBLOCK_NYIAKENG_PUACHUE_HMONG = 295, /*[1E100]*/ jpayne@69: /** @stable ICU 64 */ jpayne@69: UBLOCK_OTTOMAN_SIYAQ_NUMBERS = 296, /*[1ED00]*/ jpayne@69: /** @stable ICU 64 */ jpayne@69: UBLOCK_SMALL_KANA_EXTENSION = 297, /*[1B130]*/ jpayne@69: /** @stable ICU 64 */ jpayne@69: UBLOCK_SYMBOLS_AND_PICTOGRAPHS_EXTENDED_A = 298, /*[1FA70]*/ jpayne@69: /** @stable ICU 64 */ jpayne@69: UBLOCK_TAMIL_SUPPLEMENT = 299, /*[11FC0]*/ jpayne@69: /** @stable ICU 64 */ jpayne@69: UBLOCK_WANCHO = 300, /*[1E2C0]*/ jpayne@69: jpayne@69: // New blocks in Unicode 13.0 jpayne@69: jpayne@69: /** @stable ICU 66 */ jpayne@69: UBLOCK_CHORASMIAN = 301, /*[10FB0]*/ jpayne@69: /** @stable ICU 66 */ jpayne@69: UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_G = 302, /*[30000]*/ jpayne@69: /** @stable ICU 66 */ jpayne@69: UBLOCK_DIVES_AKURU = 303, /*[11900]*/ jpayne@69: /** @stable ICU 66 */ jpayne@69: UBLOCK_KHITAN_SMALL_SCRIPT = 304, /*[18B00]*/ jpayne@69: /** @stable ICU 66 */ jpayne@69: UBLOCK_LISU_SUPPLEMENT = 305, /*[11FB0]*/ jpayne@69: /** @stable ICU 66 */ jpayne@69: UBLOCK_SYMBOLS_FOR_LEGACY_COMPUTING = 306, /*[1FB00]*/ jpayne@69: /** @stable ICU 66 */ jpayne@69: UBLOCK_TANGUT_SUPPLEMENT = 307, /*[18D00]*/ jpayne@69: /** @stable ICU 66 */ jpayne@69: UBLOCK_YEZIDI = 308, /*[10E80]*/ jpayne@69: jpayne@69: #ifndef U_HIDE_DEPRECATED_API jpayne@69: /** jpayne@69: * One more than the highest normal UBlockCode value. jpayne@69: * The highest value is available via u_getIntPropertyMaxValue(UCHAR_BLOCK). jpayne@69: * jpayne@69: * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. jpayne@69: */ jpayne@69: UBLOCK_COUNT = 309, jpayne@69: #endif // U_HIDE_DEPRECATED_API jpayne@69: jpayne@69: /** @stable ICU 2.0 */ jpayne@69: UBLOCK_INVALID_CODE=-1 jpayne@69: }; jpayne@69: jpayne@69: /** @stable ICU 2.0 */ jpayne@69: typedef enum UBlockCode UBlockCode; jpayne@69: jpayne@69: /** jpayne@69: * East Asian Width constants. jpayne@69: * jpayne@69: * @see UCHAR_EAST_ASIAN_WIDTH jpayne@69: * @see u_getIntPropertyValue jpayne@69: * @stable ICU 2.2 jpayne@69: */ jpayne@69: typedef enum UEastAsianWidth { jpayne@69: /* jpayne@69: * Note: UEastAsianWidth constants are parsed by preparseucd.py. jpayne@69: * It matches lines like jpayne@69: * U_EA_ jpayne@69: */ jpayne@69: jpayne@69: U_EA_NEUTRAL, /*[N]*/ jpayne@69: U_EA_AMBIGUOUS, /*[A]*/ jpayne@69: U_EA_HALFWIDTH, /*[H]*/ jpayne@69: U_EA_FULLWIDTH, /*[F]*/ jpayne@69: U_EA_NARROW, /*[Na]*/ jpayne@69: U_EA_WIDE, /*[W]*/ jpayne@69: #ifndef U_HIDE_DEPRECATED_API jpayne@69: /** jpayne@69: * One more than the highest normal UEastAsianWidth value. jpayne@69: * The highest value is available via u_getIntPropertyMaxValue(UCHAR_EAST_ASIAN_WIDTH). jpayne@69: * jpayne@69: * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. jpayne@69: */ jpayne@69: U_EA_COUNT jpayne@69: #endif // U_HIDE_DEPRECATED_API jpayne@69: } UEastAsianWidth; jpayne@69: jpayne@69: /** jpayne@69: * Selector constants for u_charName(). jpayne@69: * u_charName() returns the "modern" name of a jpayne@69: * Unicode character; or the name that was defined in jpayne@69: * Unicode version 1.0, before the Unicode standard merged jpayne@69: * with ISO-10646; or an "extended" name that gives each jpayne@69: * Unicode code point a unique name. jpayne@69: * jpayne@69: * @see u_charName jpayne@69: * @stable ICU 2.0 jpayne@69: */ jpayne@69: typedef enum UCharNameChoice { jpayne@69: /** Unicode character name (Name property). @stable ICU 2.0 */ jpayne@69: U_UNICODE_CHAR_NAME, jpayne@69: #ifndef U_HIDE_DEPRECATED_API jpayne@69: /** jpayne@69: * The Unicode_1_Name property value which is of little practical value. jpayne@69: * Beginning with ICU 49, ICU APIs return an empty string for this name choice. jpayne@69: * @deprecated ICU 49 jpayne@69: */ jpayne@69: U_UNICODE_10_CHAR_NAME, jpayne@69: #endif /* U_HIDE_DEPRECATED_API */ jpayne@69: /** Standard or synthetic character name. @stable ICU 2.0 */ jpayne@69: U_EXTENDED_CHAR_NAME = U_UNICODE_CHAR_NAME+2, jpayne@69: /** Corrected name from NameAliases.txt. @stable ICU 4.4 */ jpayne@69: U_CHAR_NAME_ALIAS, jpayne@69: #ifndef U_HIDE_DEPRECATED_API jpayne@69: /** jpayne@69: * One more than the highest normal UCharNameChoice value. jpayne@69: * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. jpayne@69: */ jpayne@69: U_CHAR_NAME_CHOICE_COUNT jpayne@69: #endif // U_HIDE_DEPRECATED_API jpayne@69: } UCharNameChoice; jpayne@69: jpayne@69: /** jpayne@69: * Selector constants for u_getPropertyName() and jpayne@69: * u_getPropertyValueName(). These selectors are used to choose which jpayne@69: * name is returned for a given property or value. All properties and jpayne@69: * values have a long name. Most have a short name, but some do not. jpayne@69: * Unicode allows for additional names, beyond the long and short jpayne@69: * name, which would be indicated by U_LONG_PROPERTY_NAME + i, where jpayne@69: * i=1, 2,... jpayne@69: * jpayne@69: * @see u_getPropertyName() jpayne@69: * @see u_getPropertyValueName() jpayne@69: * @stable ICU 2.4 jpayne@69: */ jpayne@69: typedef enum UPropertyNameChoice { jpayne@69: U_SHORT_PROPERTY_NAME, jpayne@69: U_LONG_PROPERTY_NAME, jpayne@69: #ifndef U_HIDE_DEPRECATED_API jpayne@69: /** jpayne@69: * One more than the highest normal UPropertyNameChoice value. jpayne@69: * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. jpayne@69: */ jpayne@69: U_PROPERTY_NAME_CHOICE_COUNT jpayne@69: #endif // U_HIDE_DEPRECATED_API jpayne@69: } UPropertyNameChoice; jpayne@69: jpayne@69: /** jpayne@69: * Decomposition Type constants. jpayne@69: * jpayne@69: * @see UCHAR_DECOMPOSITION_TYPE jpayne@69: * @stable ICU 2.2 jpayne@69: */ jpayne@69: typedef enum UDecompositionType { jpayne@69: /* jpayne@69: * Note: UDecompositionType constants are parsed by preparseucd.py. jpayne@69: * It matches lines like jpayne@69: * U_DT_ jpayne@69: */ jpayne@69: jpayne@69: U_DT_NONE, /*[none]*/ jpayne@69: U_DT_CANONICAL, /*[can]*/ jpayne@69: U_DT_COMPAT, /*[com]*/ jpayne@69: U_DT_CIRCLE, /*[enc]*/ jpayne@69: U_DT_FINAL, /*[fin]*/ jpayne@69: U_DT_FONT, /*[font]*/ jpayne@69: U_DT_FRACTION, /*[fra]*/ jpayne@69: U_DT_INITIAL, /*[init]*/ jpayne@69: U_DT_ISOLATED, /*[iso]*/ jpayne@69: U_DT_MEDIAL, /*[med]*/ jpayne@69: U_DT_NARROW, /*[nar]*/ jpayne@69: U_DT_NOBREAK, /*[nb]*/ jpayne@69: U_DT_SMALL, /*[sml]*/ jpayne@69: U_DT_SQUARE, /*[sqr]*/ jpayne@69: U_DT_SUB, /*[sub]*/ jpayne@69: U_DT_SUPER, /*[sup]*/ jpayne@69: U_DT_VERTICAL, /*[vert]*/ jpayne@69: U_DT_WIDE, /*[wide]*/ jpayne@69: #ifndef U_HIDE_DEPRECATED_API jpayne@69: /** jpayne@69: * One more than the highest normal UDecompositionType value. jpayne@69: * The highest value is available via u_getIntPropertyMaxValue(UCHAR_DECOMPOSITION_TYPE). jpayne@69: * jpayne@69: * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. jpayne@69: */ jpayne@69: U_DT_COUNT /* 18 */ jpayne@69: #endif // U_HIDE_DEPRECATED_API jpayne@69: } UDecompositionType; jpayne@69: jpayne@69: /** jpayne@69: * Joining Type constants. jpayne@69: * jpayne@69: * @see UCHAR_JOINING_TYPE jpayne@69: * @stable ICU 2.2 jpayne@69: */ jpayne@69: typedef enum UJoiningType { jpayne@69: /* jpayne@69: * Note: UJoiningType constants are parsed by preparseucd.py. jpayne@69: * It matches lines like jpayne@69: * U_JT_ jpayne@69: */ jpayne@69: jpayne@69: U_JT_NON_JOINING, /*[U]*/ jpayne@69: U_JT_JOIN_CAUSING, /*[C]*/ jpayne@69: U_JT_DUAL_JOINING, /*[D]*/ jpayne@69: U_JT_LEFT_JOINING, /*[L]*/ jpayne@69: U_JT_RIGHT_JOINING, /*[R]*/ jpayne@69: U_JT_TRANSPARENT, /*[T]*/ jpayne@69: #ifndef U_HIDE_DEPRECATED_API jpayne@69: /** jpayne@69: * One more than the highest normal UJoiningType value. jpayne@69: * The highest value is available via u_getIntPropertyMaxValue(UCHAR_JOINING_TYPE). jpayne@69: * jpayne@69: * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. jpayne@69: */ jpayne@69: U_JT_COUNT /* 6 */ jpayne@69: #endif // U_HIDE_DEPRECATED_API jpayne@69: } UJoiningType; jpayne@69: jpayne@69: /** jpayne@69: * Joining Group constants. jpayne@69: * jpayne@69: * @see UCHAR_JOINING_GROUP jpayne@69: * @stable ICU 2.2 jpayne@69: */ jpayne@69: typedef enum UJoiningGroup { jpayne@69: /* jpayne@69: * Note: UJoiningGroup constants are parsed by preparseucd.py. jpayne@69: * It matches lines like jpayne@69: * U_JG_ jpayne@69: */ jpayne@69: jpayne@69: U_JG_NO_JOINING_GROUP, jpayne@69: U_JG_AIN, jpayne@69: U_JG_ALAPH, jpayne@69: U_JG_ALEF, jpayne@69: U_JG_BEH, jpayne@69: U_JG_BETH, jpayne@69: U_JG_DAL, jpayne@69: U_JG_DALATH_RISH, jpayne@69: U_JG_E, jpayne@69: U_JG_FEH, jpayne@69: U_JG_FINAL_SEMKATH, jpayne@69: U_JG_GAF, jpayne@69: U_JG_GAMAL, jpayne@69: U_JG_HAH, jpayne@69: U_JG_TEH_MARBUTA_GOAL, /**< @stable ICU 4.6 */ jpayne@69: U_JG_HAMZA_ON_HEH_GOAL=U_JG_TEH_MARBUTA_GOAL, jpayne@69: U_JG_HE, jpayne@69: U_JG_HEH, jpayne@69: U_JG_HEH_GOAL, jpayne@69: U_JG_HETH, jpayne@69: U_JG_KAF, jpayne@69: U_JG_KAPH, jpayne@69: U_JG_KNOTTED_HEH, jpayne@69: U_JG_LAM, jpayne@69: U_JG_LAMADH, jpayne@69: U_JG_MEEM, jpayne@69: U_JG_MIM, jpayne@69: U_JG_NOON, jpayne@69: U_JG_NUN, jpayne@69: U_JG_PE, jpayne@69: U_JG_QAF, jpayne@69: U_JG_QAPH, jpayne@69: U_JG_REH, jpayne@69: U_JG_REVERSED_PE, jpayne@69: U_JG_SAD, jpayne@69: U_JG_SADHE, jpayne@69: U_JG_SEEN, jpayne@69: U_JG_SEMKATH, jpayne@69: U_JG_SHIN, jpayne@69: U_JG_SWASH_KAF, jpayne@69: U_JG_SYRIAC_WAW, jpayne@69: U_JG_TAH, jpayne@69: U_JG_TAW, jpayne@69: U_JG_TEH_MARBUTA, jpayne@69: U_JG_TETH, jpayne@69: U_JG_WAW, jpayne@69: U_JG_YEH, jpayne@69: U_JG_YEH_BARREE, jpayne@69: U_JG_YEH_WITH_TAIL, jpayne@69: U_JG_YUDH, jpayne@69: U_JG_YUDH_HE, jpayne@69: U_JG_ZAIN, jpayne@69: U_JG_FE, /**< @stable ICU 2.6 */ jpayne@69: U_JG_KHAPH, /**< @stable ICU 2.6 */ jpayne@69: U_JG_ZHAIN, /**< @stable ICU 2.6 */ jpayne@69: U_JG_BURUSHASKI_YEH_BARREE, /**< @stable ICU 4.0 */ jpayne@69: U_JG_FARSI_YEH, /**< @stable ICU 4.4 */ jpayne@69: U_JG_NYA, /**< @stable ICU 4.4 */ jpayne@69: U_JG_ROHINGYA_YEH, /**< @stable ICU 49 */ jpayne@69: U_JG_MANICHAEAN_ALEPH, /**< @stable ICU 54 */ jpayne@69: U_JG_MANICHAEAN_AYIN, /**< @stable ICU 54 */ jpayne@69: U_JG_MANICHAEAN_BETH, /**< @stable ICU 54 */ jpayne@69: U_JG_MANICHAEAN_DALETH, /**< @stable ICU 54 */ jpayne@69: U_JG_MANICHAEAN_DHAMEDH, /**< @stable ICU 54 */ jpayne@69: U_JG_MANICHAEAN_FIVE, /**< @stable ICU 54 */ jpayne@69: U_JG_MANICHAEAN_GIMEL, /**< @stable ICU 54 */ jpayne@69: U_JG_MANICHAEAN_HETH, /**< @stable ICU 54 */ jpayne@69: U_JG_MANICHAEAN_HUNDRED, /**< @stable ICU 54 */ jpayne@69: U_JG_MANICHAEAN_KAPH, /**< @stable ICU 54 */ jpayne@69: U_JG_MANICHAEAN_LAMEDH, /**< @stable ICU 54 */ jpayne@69: U_JG_MANICHAEAN_MEM, /**< @stable ICU 54 */ jpayne@69: U_JG_MANICHAEAN_NUN, /**< @stable ICU 54 */ jpayne@69: U_JG_MANICHAEAN_ONE, /**< @stable ICU 54 */ jpayne@69: U_JG_MANICHAEAN_PE, /**< @stable ICU 54 */ jpayne@69: U_JG_MANICHAEAN_QOPH, /**< @stable ICU 54 */ jpayne@69: U_JG_MANICHAEAN_RESH, /**< @stable ICU 54 */ jpayne@69: U_JG_MANICHAEAN_SADHE, /**< @stable ICU 54 */ jpayne@69: U_JG_MANICHAEAN_SAMEKH, /**< @stable ICU 54 */ jpayne@69: U_JG_MANICHAEAN_TAW, /**< @stable ICU 54 */ jpayne@69: U_JG_MANICHAEAN_TEN, /**< @stable ICU 54 */ jpayne@69: U_JG_MANICHAEAN_TETH, /**< @stable ICU 54 */ jpayne@69: U_JG_MANICHAEAN_THAMEDH, /**< @stable ICU 54 */ jpayne@69: U_JG_MANICHAEAN_TWENTY, /**< @stable ICU 54 */ jpayne@69: U_JG_MANICHAEAN_WAW, /**< @stable ICU 54 */ jpayne@69: U_JG_MANICHAEAN_YODH, /**< @stable ICU 54 */ jpayne@69: U_JG_MANICHAEAN_ZAYIN, /**< @stable ICU 54 */ jpayne@69: U_JG_STRAIGHT_WAW, /**< @stable ICU 54 */ jpayne@69: U_JG_AFRICAN_FEH, /**< @stable ICU 58 */ jpayne@69: U_JG_AFRICAN_NOON, /**< @stable ICU 58 */ jpayne@69: U_JG_AFRICAN_QAF, /**< @stable ICU 58 */ jpayne@69: jpayne@69: U_JG_MALAYALAM_BHA, /**< @stable ICU 60 */ jpayne@69: U_JG_MALAYALAM_JA, /**< @stable ICU 60 */ jpayne@69: U_JG_MALAYALAM_LLA, /**< @stable ICU 60 */ jpayne@69: U_JG_MALAYALAM_LLLA, /**< @stable ICU 60 */ jpayne@69: U_JG_MALAYALAM_NGA, /**< @stable ICU 60 */ jpayne@69: U_JG_MALAYALAM_NNA, /**< @stable ICU 60 */ jpayne@69: U_JG_MALAYALAM_NNNA, /**< @stable ICU 60 */ jpayne@69: U_JG_MALAYALAM_NYA, /**< @stable ICU 60 */ jpayne@69: U_JG_MALAYALAM_RA, /**< @stable ICU 60 */ jpayne@69: U_JG_MALAYALAM_SSA, /**< @stable ICU 60 */ jpayne@69: U_JG_MALAYALAM_TTA, /**< @stable ICU 60 */ jpayne@69: jpayne@69: U_JG_HANIFI_ROHINGYA_KINNA_YA, /**< @stable ICU 62 */ jpayne@69: U_JG_HANIFI_ROHINGYA_PA, /**< @stable ICU 62 */ jpayne@69: jpayne@69: #ifndef U_HIDE_DEPRECATED_API jpayne@69: /** jpayne@69: * One more than the highest normal UJoiningGroup value. jpayne@69: * The highest value is available via u_getIntPropertyMaxValue(UCHAR_JOINING_GROUP). jpayne@69: * jpayne@69: * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. jpayne@69: */ jpayne@69: U_JG_COUNT jpayne@69: #endif // U_HIDE_DEPRECATED_API jpayne@69: } UJoiningGroup; jpayne@69: jpayne@69: /** jpayne@69: * Grapheme Cluster Break constants. jpayne@69: * jpayne@69: * @see UCHAR_GRAPHEME_CLUSTER_BREAK jpayne@69: * @stable ICU 3.4 jpayne@69: */ jpayne@69: typedef enum UGraphemeClusterBreak { jpayne@69: /* jpayne@69: * Note: UGraphemeClusterBreak constants are parsed by preparseucd.py. jpayne@69: * It matches lines like jpayne@69: * U_GCB_ jpayne@69: */ jpayne@69: jpayne@69: U_GCB_OTHER = 0, /*[XX]*/ jpayne@69: U_GCB_CONTROL = 1, /*[CN]*/ jpayne@69: U_GCB_CR = 2, /*[CR]*/ jpayne@69: U_GCB_EXTEND = 3, /*[EX]*/ jpayne@69: U_GCB_L = 4, /*[L]*/ jpayne@69: U_GCB_LF = 5, /*[LF]*/ jpayne@69: U_GCB_LV = 6, /*[LV]*/ jpayne@69: U_GCB_LVT = 7, /*[LVT]*/ jpayne@69: U_GCB_T = 8, /*[T]*/ jpayne@69: U_GCB_V = 9, /*[V]*/ jpayne@69: /** @stable ICU 4.0 */ jpayne@69: U_GCB_SPACING_MARK = 10, /*[SM]*/ /* from here on: new in Unicode 5.1/ICU 4.0 */ jpayne@69: /** @stable ICU 4.0 */ jpayne@69: U_GCB_PREPEND = 11, /*[PP]*/ jpayne@69: /** @stable ICU 50 */ jpayne@69: U_GCB_REGIONAL_INDICATOR = 12, /*[RI]*/ /* new in Unicode 6.2/ICU 50 */ jpayne@69: /** @stable ICU 58 */ jpayne@69: U_GCB_E_BASE = 13, /*[EB]*/ /* from here on: new in Unicode 9.0/ICU 58 */ jpayne@69: /** @stable ICU 58 */ jpayne@69: U_GCB_E_BASE_GAZ = 14, /*[EBG]*/ jpayne@69: /** @stable ICU 58 */ jpayne@69: U_GCB_E_MODIFIER = 15, /*[EM]*/ jpayne@69: /** @stable ICU 58 */ jpayne@69: U_GCB_GLUE_AFTER_ZWJ = 16, /*[GAZ]*/ jpayne@69: /** @stable ICU 58 */ jpayne@69: U_GCB_ZWJ = 17, /*[ZWJ]*/ jpayne@69: jpayne@69: #ifndef U_HIDE_DEPRECATED_API jpayne@69: /** jpayne@69: * One more than the highest normal UGraphemeClusterBreak value. jpayne@69: * The highest value is available via u_getIntPropertyMaxValue(UCHAR_GRAPHEME_CLUSTER_BREAK). jpayne@69: * jpayne@69: * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. jpayne@69: */ jpayne@69: U_GCB_COUNT = 18 jpayne@69: #endif // U_HIDE_DEPRECATED_API jpayne@69: } UGraphemeClusterBreak; jpayne@69: jpayne@69: /** jpayne@69: * Word Break constants. jpayne@69: * (UWordBreak is a pre-existing enum type in ubrk.h for word break status tags.) jpayne@69: * jpayne@69: * @see UCHAR_WORD_BREAK jpayne@69: * @stable ICU 3.4 jpayne@69: */ jpayne@69: typedef enum UWordBreakValues { jpayne@69: /* jpayne@69: * Note: UWordBreakValues constants are parsed by preparseucd.py. jpayne@69: * It matches lines like jpayne@69: * U_WB_ jpayne@69: */ jpayne@69: jpayne@69: U_WB_OTHER = 0, /*[XX]*/ jpayne@69: U_WB_ALETTER = 1, /*[LE]*/ jpayne@69: U_WB_FORMAT = 2, /*[FO]*/ jpayne@69: U_WB_KATAKANA = 3, /*[KA]*/ jpayne@69: U_WB_MIDLETTER = 4, /*[ML]*/ jpayne@69: U_WB_MIDNUM = 5, /*[MN]*/ jpayne@69: U_WB_NUMERIC = 6, /*[NU]*/ jpayne@69: U_WB_EXTENDNUMLET = 7, /*[EX]*/ jpayne@69: /** @stable ICU 4.0 */ jpayne@69: U_WB_CR = 8, /*[CR]*/ /* from here on: new in Unicode 5.1/ICU 4.0 */ jpayne@69: /** @stable ICU 4.0 */ jpayne@69: U_WB_EXTEND = 9, /*[Extend]*/ jpayne@69: /** @stable ICU 4.0 */ jpayne@69: U_WB_LF = 10, /*[LF]*/ jpayne@69: /** @stable ICU 4.0 */ jpayne@69: U_WB_MIDNUMLET =11, /*[MB]*/ jpayne@69: /** @stable ICU 4.0 */ jpayne@69: U_WB_NEWLINE =12, /*[NL]*/ jpayne@69: /** @stable ICU 50 */ jpayne@69: U_WB_REGIONAL_INDICATOR = 13, /*[RI]*/ /* new in Unicode 6.2/ICU 50 */ jpayne@69: /** @stable ICU 52 */ jpayne@69: U_WB_HEBREW_LETTER = 14, /*[HL]*/ /* from here on: new in Unicode 6.3/ICU 52 */ jpayne@69: /** @stable ICU 52 */ jpayne@69: U_WB_SINGLE_QUOTE = 15, /*[SQ]*/ jpayne@69: /** @stable ICU 52 */ jpayne@69: U_WB_DOUBLE_QUOTE = 16, /*[DQ]*/ jpayne@69: /** @stable ICU 58 */ jpayne@69: U_WB_E_BASE = 17, /*[EB]*/ /* from here on: new in Unicode 9.0/ICU 58 */ jpayne@69: /** @stable ICU 58 */ jpayne@69: U_WB_E_BASE_GAZ = 18, /*[EBG]*/ jpayne@69: /** @stable ICU 58 */ jpayne@69: U_WB_E_MODIFIER = 19, /*[EM]*/ jpayne@69: /** @stable ICU 58 */ jpayne@69: U_WB_GLUE_AFTER_ZWJ = 20, /*[GAZ]*/ jpayne@69: /** @stable ICU 58 */ jpayne@69: U_WB_ZWJ = 21, /*[ZWJ]*/ jpayne@69: /** @stable ICU 62 */ jpayne@69: U_WB_WSEGSPACE = 22, /*[WSEGSPACE]*/ jpayne@69: jpayne@69: #ifndef U_HIDE_DEPRECATED_API jpayne@69: /** jpayne@69: * One more than the highest normal UWordBreakValues value. jpayne@69: * The highest value is available via u_getIntPropertyMaxValue(UCHAR_WORD_BREAK). jpayne@69: * jpayne@69: * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. jpayne@69: */ jpayne@69: U_WB_COUNT = 23 jpayne@69: #endif // U_HIDE_DEPRECATED_API jpayne@69: } UWordBreakValues; jpayne@69: jpayne@69: /** jpayne@69: * Sentence Break constants. jpayne@69: * jpayne@69: * @see UCHAR_SENTENCE_BREAK jpayne@69: * @stable ICU 3.4 jpayne@69: */ jpayne@69: typedef enum USentenceBreak { jpayne@69: /* jpayne@69: * Note: USentenceBreak constants are parsed by preparseucd.py. jpayne@69: * It matches lines like jpayne@69: * U_SB_ jpayne@69: */ jpayne@69: jpayne@69: U_SB_OTHER = 0, /*[XX]*/ jpayne@69: U_SB_ATERM = 1, /*[AT]*/ jpayne@69: U_SB_CLOSE = 2, /*[CL]*/ jpayne@69: U_SB_FORMAT = 3, /*[FO]*/ jpayne@69: U_SB_LOWER = 4, /*[LO]*/ jpayne@69: U_SB_NUMERIC = 5, /*[NU]*/ jpayne@69: U_SB_OLETTER = 6, /*[LE]*/ jpayne@69: U_SB_SEP = 7, /*[SE]*/ jpayne@69: U_SB_SP = 8, /*[SP]*/ jpayne@69: U_SB_STERM = 9, /*[ST]*/ jpayne@69: U_SB_UPPER = 10, /*[UP]*/ jpayne@69: U_SB_CR = 11, /*[CR]*/ /* from here on: new in Unicode 5.1/ICU 4.0 */ jpayne@69: U_SB_EXTEND = 12, /*[EX]*/ jpayne@69: U_SB_LF = 13, /*[LF]*/ jpayne@69: U_SB_SCONTINUE = 14, /*[SC]*/ jpayne@69: #ifndef U_HIDE_DEPRECATED_API jpayne@69: /** jpayne@69: * One more than the highest normal USentenceBreak value. jpayne@69: * The highest value is available via u_getIntPropertyMaxValue(UCHAR_SENTENCE_BREAK). jpayne@69: * jpayne@69: * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. jpayne@69: */ jpayne@69: U_SB_COUNT = 15 jpayne@69: #endif // U_HIDE_DEPRECATED_API jpayne@69: } USentenceBreak; jpayne@69: jpayne@69: /** jpayne@69: * Line Break constants. jpayne@69: * jpayne@69: * @see UCHAR_LINE_BREAK jpayne@69: * @stable ICU 2.2 jpayne@69: */ jpayne@69: typedef enum ULineBreak { jpayne@69: /* jpayne@69: * Note: ULineBreak constants are parsed by preparseucd.py. jpayne@69: * It matches lines like jpayne@69: * U_LB_ jpayne@69: */ jpayne@69: jpayne@69: U_LB_UNKNOWN = 0, /*[XX]*/ jpayne@69: U_LB_AMBIGUOUS = 1, /*[AI]*/ jpayne@69: U_LB_ALPHABETIC = 2, /*[AL]*/ jpayne@69: U_LB_BREAK_BOTH = 3, /*[B2]*/ jpayne@69: U_LB_BREAK_AFTER = 4, /*[BA]*/ jpayne@69: U_LB_BREAK_BEFORE = 5, /*[BB]*/ jpayne@69: U_LB_MANDATORY_BREAK = 6, /*[BK]*/ jpayne@69: U_LB_CONTINGENT_BREAK = 7, /*[CB]*/ jpayne@69: U_LB_CLOSE_PUNCTUATION = 8, /*[CL]*/ jpayne@69: U_LB_COMBINING_MARK = 9, /*[CM]*/ jpayne@69: U_LB_CARRIAGE_RETURN = 10, /*[CR]*/ jpayne@69: U_LB_EXCLAMATION = 11, /*[EX]*/ jpayne@69: U_LB_GLUE = 12, /*[GL]*/ jpayne@69: U_LB_HYPHEN = 13, /*[HY]*/ jpayne@69: U_LB_IDEOGRAPHIC = 14, /*[ID]*/ jpayne@69: /** Renamed from the misspelled "inseperable" in Unicode 4.0.1/ICU 3.0 @stable ICU 3.0 */ jpayne@69: U_LB_INSEPARABLE = 15, /*[IN]*/ jpayne@69: U_LB_INSEPERABLE = U_LB_INSEPARABLE, jpayne@69: U_LB_INFIX_NUMERIC = 16, /*[IS]*/ jpayne@69: U_LB_LINE_FEED = 17, /*[LF]*/ jpayne@69: U_LB_NONSTARTER = 18, /*[NS]*/ jpayne@69: U_LB_NUMERIC = 19, /*[NU]*/ jpayne@69: U_LB_OPEN_PUNCTUATION = 20, /*[OP]*/ jpayne@69: U_LB_POSTFIX_NUMERIC = 21, /*[PO]*/ jpayne@69: U_LB_PREFIX_NUMERIC = 22, /*[PR]*/ jpayne@69: U_LB_QUOTATION = 23, /*[QU]*/ jpayne@69: U_LB_COMPLEX_CONTEXT = 24, /*[SA]*/ jpayne@69: U_LB_SURROGATE = 25, /*[SG]*/ jpayne@69: U_LB_SPACE = 26, /*[SP]*/ jpayne@69: U_LB_BREAK_SYMBOLS = 27, /*[SY]*/ jpayne@69: U_LB_ZWSPACE = 28, /*[ZW]*/ jpayne@69: /** @stable ICU 2.6 */ jpayne@69: U_LB_NEXT_LINE = 29, /*[NL]*/ /* from here on: new in Unicode 4/ICU 2.6 */ jpayne@69: /** @stable ICU 2.6 */ jpayne@69: U_LB_WORD_JOINER = 30, /*[WJ]*/ jpayne@69: /** @stable ICU 3.4 */ jpayne@69: U_LB_H2 = 31, /*[H2]*/ /* from here on: new in Unicode 4.1/ICU 3.4 */ jpayne@69: /** @stable ICU 3.4 */ jpayne@69: U_LB_H3 = 32, /*[H3]*/ jpayne@69: /** @stable ICU 3.4 */ jpayne@69: U_LB_JL = 33, /*[JL]*/ jpayne@69: /** @stable ICU 3.4 */ jpayne@69: U_LB_JT = 34, /*[JT]*/ jpayne@69: /** @stable ICU 3.4 */ jpayne@69: U_LB_JV = 35, /*[JV]*/ jpayne@69: /** @stable ICU 4.4 */ jpayne@69: U_LB_CLOSE_PARENTHESIS = 36, /*[CP]*/ /* new in Unicode 5.2/ICU 4.4 */ jpayne@69: /** @stable ICU 49 */ jpayne@69: U_LB_CONDITIONAL_JAPANESE_STARTER = 37,/*[CJ]*/ /* new in Unicode 6.1/ICU 49 */ jpayne@69: /** @stable ICU 49 */ jpayne@69: U_LB_HEBREW_LETTER = 38, /*[HL]*/ /* new in Unicode 6.1/ICU 49 */ jpayne@69: /** @stable ICU 50 */ jpayne@69: U_LB_REGIONAL_INDICATOR = 39,/*[RI]*/ /* new in Unicode 6.2/ICU 50 */ jpayne@69: /** @stable ICU 58 */ jpayne@69: U_LB_E_BASE = 40, /*[EB]*/ /* from here on: new in Unicode 9.0/ICU 58 */ jpayne@69: /** @stable ICU 58 */ jpayne@69: U_LB_E_MODIFIER = 41, /*[EM]*/ jpayne@69: /** @stable ICU 58 */ jpayne@69: U_LB_ZWJ = 42, /*[ZWJ]*/ jpayne@69: #ifndef U_HIDE_DEPRECATED_API jpayne@69: /** jpayne@69: * One more than the highest normal ULineBreak value. jpayne@69: * The highest value is available via u_getIntPropertyMaxValue(UCHAR_LINE_BREAK). jpayne@69: * jpayne@69: * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. jpayne@69: */ jpayne@69: U_LB_COUNT = 43 jpayne@69: #endif // U_HIDE_DEPRECATED_API jpayne@69: } ULineBreak; jpayne@69: jpayne@69: /** jpayne@69: * Numeric Type constants. jpayne@69: * jpayne@69: * @see UCHAR_NUMERIC_TYPE jpayne@69: * @stable ICU 2.2 jpayne@69: */ jpayne@69: typedef enum UNumericType { jpayne@69: /* jpayne@69: * Note: UNumericType constants are parsed by preparseucd.py. jpayne@69: * It matches lines like jpayne@69: * U_NT_ jpayne@69: */ jpayne@69: jpayne@69: U_NT_NONE, /*[None]*/ jpayne@69: U_NT_DECIMAL, /*[de]*/ jpayne@69: U_NT_DIGIT, /*[di]*/ jpayne@69: U_NT_NUMERIC, /*[nu]*/ jpayne@69: #ifndef U_HIDE_DEPRECATED_API jpayne@69: /** jpayne@69: * One more than the highest normal UNumericType value. jpayne@69: * The highest value is available via u_getIntPropertyMaxValue(UCHAR_NUMERIC_TYPE). jpayne@69: * jpayne@69: * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. jpayne@69: */ jpayne@69: U_NT_COUNT jpayne@69: #endif // U_HIDE_DEPRECATED_API jpayne@69: } UNumericType; jpayne@69: jpayne@69: /** jpayne@69: * Hangul Syllable Type constants. jpayne@69: * jpayne@69: * @see UCHAR_HANGUL_SYLLABLE_TYPE jpayne@69: * @stable ICU 2.6 jpayne@69: */ jpayne@69: typedef enum UHangulSyllableType { jpayne@69: /* jpayne@69: * Note: UHangulSyllableType constants are parsed by preparseucd.py. jpayne@69: * It matches lines like jpayne@69: * U_HST_ jpayne@69: */ jpayne@69: jpayne@69: U_HST_NOT_APPLICABLE, /*[NA]*/ jpayne@69: U_HST_LEADING_JAMO, /*[L]*/ jpayne@69: U_HST_VOWEL_JAMO, /*[V]*/ jpayne@69: U_HST_TRAILING_JAMO, /*[T]*/ jpayne@69: U_HST_LV_SYLLABLE, /*[LV]*/ jpayne@69: U_HST_LVT_SYLLABLE, /*[LVT]*/ jpayne@69: #ifndef U_HIDE_DEPRECATED_API jpayne@69: /** jpayne@69: * One more than the highest normal UHangulSyllableType value. jpayne@69: * The highest value is available via u_getIntPropertyMaxValue(UCHAR_HANGUL_SYLLABLE_TYPE). jpayne@69: * jpayne@69: * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. jpayne@69: */ jpayne@69: U_HST_COUNT jpayne@69: #endif // U_HIDE_DEPRECATED_API jpayne@69: } UHangulSyllableType; jpayne@69: jpayne@69: /** jpayne@69: * Indic Positional Category constants. jpayne@69: * jpayne@69: * @see UCHAR_INDIC_POSITIONAL_CATEGORY jpayne@69: * @stable ICU 63 jpayne@69: */ jpayne@69: typedef enum UIndicPositionalCategory { jpayne@69: /* jpayne@69: * Note: UIndicPositionalCategory constants are parsed by preparseucd.py. jpayne@69: * It matches lines like jpayne@69: * U_INPC_ jpayne@69: */ jpayne@69: jpayne@69: /** @stable ICU 63 */ jpayne@69: U_INPC_NA, jpayne@69: /** @stable ICU 63 */ jpayne@69: U_INPC_BOTTOM, jpayne@69: /** @stable ICU 63 */ jpayne@69: U_INPC_BOTTOM_AND_LEFT, jpayne@69: /** @stable ICU 63 */ jpayne@69: U_INPC_BOTTOM_AND_RIGHT, jpayne@69: /** @stable ICU 63 */ jpayne@69: U_INPC_LEFT, jpayne@69: /** @stable ICU 63 */ jpayne@69: U_INPC_LEFT_AND_RIGHT, jpayne@69: /** @stable ICU 63 */ jpayne@69: U_INPC_OVERSTRUCK, jpayne@69: /** @stable ICU 63 */ jpayne@69: U_INPC_RIGHT, jpayne@69: /** @stable ICU 63 */ jpayne@69: U_INPC_TOP, jpayne@69: /** @stable ICU 63 */ jpayne@69: U_INPC_TOP_AND_BOTTOM, jpayne@69: /** @stable ICU 63 */ jpayne@69: U_INPC_TOP_AND_BOTTOM_AND_RIGHT, jpayne@69: /** @stable ICU 63 */ jpayne@69: U_INPC_TOP_AND_LEFT, jpayne@69: /** @stable ICU 63 */ jpayne@69: U_INPC_TOP_AND_LEFT_AND_RIGHT, jpayne@69: /** @stable ICU 63 */ jpayne@69: U_INPC_TOP_AND_RIGHT, jpayne@69: /** @stable ICU 63 */ jpayne@69: U_INPC_VISUAL_ORDER_LEFT, jpayne@69: /** @stable ICU 66 */ jpayne@69: U_INPC_TOP_AND_BOTTOM_AND_LEFT, jpayne@69: } UIndicPositionalCategory; jpayne@69: jpayne@69: /** jpayne@69: * Indic Syllabic Category constants. jpayne@69: * jpayne@69: * @see UCHAR_INDIC_SYLLABIC_CATEGORY jpayne@69: * @stable ICU 63 jpayne@69: */ jpayne@69: typedef enum UIndicSyllabicCategory { jpayne@69: /* jpayne@69: * Note: UIndicSyllabicCategory constants are parsed by preparseucd.py. jpayne@69: * It matches lines like jpayne@69: * U_INSC_ jpayne@69: */ jpayne@69: jpayne@69: /** @stable ICU 63 */ jpayne@69: U_INSC_OTHER, jpayne@69: /** @stable ICU 63 */ jpayne@69: U_INSC_AVAGRAHA, jpayne@69: /** @stable ICU 63 */ jpayne@69: U_INSC_BINDU, jpayne@69: /** @stable ICU 63 */ jpayne@69: U_INSC_BRAHMI_JOINING_NUMBER, jpayne@69: /** @stable ICU 63 */ jpayne@69: U_INSC_CANTILLATION_MARK, jpayne@69: /** @stable ICU 63 */ jpayne@69: U_INSC_CONSONANT, jpayne@69: /** @stable ICU 63 */ jpayne@69: U_INSC_CONSONANT_DEAD, jpayne@69: /** @stable ICU 63 */ jpayne@69: U_INSC_CONSONANT_FINAL, jpayne@69: /** @stable ICU 63 */ jpayne@69: U_INSC_CONSONANT_HEAD_LETTER, jpayne@69: /** @stable ICU 63 */ jpayne@69: U_INSC_CONSONANT_INITIAL_POSTFIXED, jpayne@69: /** @stable ICU 63 */ jpayne@69: U_INSC_CONSONANT_KILLER, jpayne@69: /** @stable ICU 63 */ jpayne@69: U_INSC_CONSONANT_MEDIAL, jpayne@69: /** @stable ICU 63 */ jpayne@69: U_INSC_CONSONANT_PLACEHOLDER, jpayne@69: /** @stable ICU 63 */ jpayne@69: U_INSC_CONSONANT_PRECEDING_REPHA, jpayne@69: /** @stable ICU 63 */ jpayne@69: U_INSC_CONSONANT_PREFIXED, jpayne@69: /** @stable ICU 63 */ jpayne@69: U_INSC_CONSONANT_SUBJOINED, jpayne@69: /** @stable ICU 63 */ jpayne@69: U_INSC_CONSONANT_SUCCEEDING_REPHA, jpayne@69: /** @stable ICU 63 */ jpayne@69: U_INSC_CONSONANT_WITH_STACKER, jpayne@69: /** @stable ICU 63 */ jpayne@69: U_INSC_GEMINATION_MARK, jpayne@69: /** @stable ICU 63 */ jpayne@69: U_INSC_INVISIBLE_STACKER, jpayne@69: /** @stable ICU 63 */ jpayne@69: U_INSC_JOINER, jpayne@69: /** @stable ICU 63 */ jpayne@69: U_INSC_MODIFYING_LETTER, jpayne@69: /** @stable ICU 63 */ jpayne@69: U_INSC_NON_JOINER, jpayne@69: /** @stable ICU 63 */ jpayne@69: U_INSC_NUKTA, jpayne@69: /** @stable ICU 63 */ jpayne@69: U_INSC_NUMBER, jpayne@69: /** @stable ICU 63 */ jpayne@69: U_INSC_NUMBER_JOINER, jpayne@69: /** @stable ICU 63 */ jpayne@69: U_INSC_PURE_KILLER, jpayne@69: /** @stable ICU 63 */ jpayne@69: U_INSC_REGISTER_SHIFTER, jpayne@69: /** @stable ICU 63 */ jpayne@69: U_INSC_SYLLABLE_MODIFIER, jpayne@69: /** @stable ICU 63 */ jpayne@69: U_INSC_TONE_LETTER, jpayne@69: /** @stable ICU 63 */ jpayne@69: U_INSC_TONE_MARK, jpayne@69: /** @stable ICU 63 */ jpayne@69: U_INSC_VIRAMA, jpayne@69: /** @stable ICU 63 */ jpayne@69: U_INSC_VISARGA, jpayne@69: /** @stable ICU 63 */ jpayne@69: U_INSC_VOWEL, jpayne@69: /** @stable ICU 63 */ jpayne@69: U_INSC_VOWEL_DEPENDENT, jpayne@69: /** @stable ICU 63 */ jpayne@69: U_INSC_VOWEL_INDEPENDENT, jpayne@69: } UIndicSyllabicCategory; jpayne@69: jpayne@69: /** jpayne@69: * Vertical Orientation constants. jpayne@69: * jpayne@69: * @see UCHAR_VERTICAL_ORIENTATION jpayne@69: * @stable ICU 63 jpayne@69: */ jpayne@69: typedef enum UVerticalOrientation { jpayne@69: /* jpayne@69: * Note: UVerticalOrientation constants are parsed by preparseucd.py. jpayne@69: * It matches lines like jpayne@69: * U_VO_ jpayne@69: */ jpayne@69: jpayne@69: /** @stable ICU 63 */ jpayne@69: U_VO_ROTATED, jpayne@69: /** @stable ICU 63 */ jpayne@69: U_VO_TRANSFORMED_ROTATED, jpayne@69: /** @stable ICU 63 */ jpayne@69: U_VO_TRANSFORMED_UPRIGHT, jpayne@69: /** @stable ICU 63 */ jpayne@69: U_VO_UPRIGHT, jpayne@69: } UVerticalOrientation; jpayne@69: jpayne@69: /** jpayne@69: * Check a binary Unicode property for a code point. jpayne@69: * jpayne@69: * Unicode, especially in version 3.2, defines many more properties than the jpayne@69: * original set in UnicodeData.txt. jpayne@69: * jpayne@69: * The properties APIs are intended to reflect Unicode properties as defined jpayne@69: * in the Unicode Character Database (UCD) and Unicode Technical Reports (UTR). jpayne@69: * For details about the properties see http://www.unicode.org/ucd/ . jpayne@69: * For names of Unicode properties see the UCD file PropertyAliases.txt. jpayne@69: * jpayne@69: * Important: If ICU is built with UCD files from Unicode versions below 3.2, jpayne@69: * then properties marked with "new in Unicode 3.2" are not or not fully available. jpayne@69: * jpayne@69: * @param c Code point to test. jpayne@69: * @param which UProperty selector constant, identifies which binary property to check. jpayne@69: * Must be UCHAR_BINARY_START<=which=0. jpayne@69: * True for characters with general category "Nd" (decimal digit numbers) jpayne@69: * as well as Latin letters a-f and A-F in both ASCII and Fullwidth ASCII. jpayne@69: * (That is, for letters with code points jpayne@69: * 0041..0046, 0061..0066, FF21..FF26, FF41..FF46.) jpayne@69: * jpayne@69: * In order to narrow the definition of hexadecimal digits to only ASCII jpayne@69: * characters, use (c<=0x7f && u_isxdigit(c)). jpayne@69: * jpayne@69: * This is a C/POSIX migration function. jpayne@69: * See the comments about C/POSIX character classification functions in the jpayne@69: * documentation at the top of this header file. jpayne@69: * jpayne@69: * @param c the code point to be tested jpayne@69: * @return TRUE if the code point is a hexadecimal digit jpayne@69: * jpayne@69: * @stable ICU 2.6 jpayne@69: */ jpayne@69: U_STABLE UBool U_EXPORT2 jpayne@69: u_isxdigit(UChar32 c); jpayne@69: jpayne@69: /** jpayne@69: * Determines whether the specified code point is a punctuation character. jpayne@69: * True for characters with general categories "P" (punctuation). jpayne@69: * jpayne@69: * This is a C/POSIX migration function. jpayne@69: * See the comments about C/POSIX character classification functions in the jpayne@69: * documentation at the top of this header file. jpayne@69: * jpayne@69: * @param c the code point to be tested jpayne@69: * @return TRUE if the code point is a punctuation character jpayne@69: * jpayne@69: * @stable ICU 2.6 jpayne@69: */ jpayne@69: U_STABLE UBool U_EXPORT2 jpayne@69: u_ispunct(UChar32 c); jpayne@69: jpayne@69: /** jpayne@69: * Determines whether the specified code point is a "graphic" character jpayne@69: * (printable, excluding spaces). jpayne@69: * TRUE for all characters except those with general categories jpayne@69: * "Cc" (control codes), "Cf" (format controls), "Cs" (surrogates), jpayne@69: * "Cn" (unassigned), and "Z" (separators). jpayne@69: * jpayne@69: * This is a C/POSIX migration function. jpayne@69: * See the comments about C/POSIX character classification functions in the jpayne@69: * documentation at the top of this header file. jpayne@69: * jpayne@69: * @param c the code point to be tested jpayne@69: * @return TRUE if the code point is a "graphic" character jpayne@69: * jpayne@69: * @stable ICU 2.6 jpayne@69: */ jpayne@69: U_STABLE UBool U_EXPORT2 jpayne@69: u_isgraph(UChar32 c); jpayne@69: jpayne@69: /** jpayne@69: * Determines whether the specified code point is a "blank" or "horizontal space", jpayne@69: * a character that visibly separates words on a line. jpayne@69: * The following are equivalent definitions: jpayne@69: * jpayne@69: * TRUE for Unicode White_Space characters except for "vertical space controls" jpayne@69: * where "vertical space controls" are the following characters: jpayne@69: * U+000A (LF) U+000B (VT) U+000C (FF) U+000D (CR) U+0085 (NEL) U+2028 (LS) U+2029 (PS) jpayne@69: * jpayne@69: * same as jpayne@69: * jpayne@69: * TRUE for U+0009 (TAB) and characters with general category "Zs" (space separators). jpayne@69: * jpayne@69: * Note: There are several ICU whitespace functions; please see the uchar.h jpayne@69: * file documentation for a detailed comparison. jpayne@69: * jpayne@69: * This is a C/POSIX migration function. jpayne@69: * See the comments about C/POSIX character classification functions in the jpayne@69: * documentation at the top of this header file. jpayne@69: * jpayne@69: * @param c the code point to be tested jpayne@69: * @return TRUE if the code point is a "blank" jpayne@69: * jpayne@69: * @stable ICU 2.6 jpayne@69: */ jpayne@69: U_STABLE UBool U_EXPORT2 jpayne@69: u_isblank(UChar32 c); jpayne@69: jpayne@69: /** jpayne@69: * Determines whether the specified code point is "defined", jpayne@69: * which usually means that it is assigned a character. jpayne@69: * True for general categories other than "Cn" (other, not assigned), jpayne@69: * i.e., true for all code points mentioned in UnicodeData.txt. jpayne@69: * jpayne@69: * Note that non-character code points (e.g., U+FDD0) are not "defined" jpayne@69: * (they are Cn), but surrogate code points are "defined" (Cs). jpayne@69: * jpayne@69: * Same as java.lang.Character.isDefined(). jpayne@69: * jpayne@69: * @param c the code point to be tested jpayne@69: * @return TRUE if the code point is assigned a character jpayne@69: * jpayne@69: * @see u_isdigit jpayne@69: * @see u_isalpha jpayne@69: * @see u_isalnum jpayne@69: * @see u_isupper jpayne@69: * @see u_islower jpayne@69: * @see u_istitle jpayne@69: * @stable ICU 2.0 jpayne@69: */ jpayne@69: U_STABLE UBool U_EXPORT2 jpayne@69: u_isdefined(UChar32 c); jpayne@69: jpayne@69: /** jpayne@69: * Determines if the specified character is a space character or not. jpayne@69: * jpayne@69: * Note: There are several ICU whitespace functions; please see the uchar.h jpayne@69: * file documentation for a detailed comparison. jpayne@69: * jpayne@69: * This is a C/POSIX migration function. jpayne@69: * See the comments about C/POSIX character classification functions in the jpayne@69: * documentation at the top of this header file. jpayne@69: * jpayne@69: * @param c the character to be tested jpayne@69: * @return true if the character is a space character; false otherwise. jpayne@69: * jpayne@69: * @see u_isJavaSpaceChar jpayne@69: * @see u_isWhitespace jpayne@69: * @see u_isUWhiteSpace jpayne@69: * @stable ICU 2.0 jpayne@69: */ jpayne@69: U_STABLE UBool U_EXPORT2 jpayne@69: u_isspace(UChar32 c); jpayne@69: jpayne@69: /** jpayne@69: * Determine if the specified code point is a space character according to Java. jpayne@69: * True for characters with general categories "Z" (separators), jpayne@69: * which does not include control codes (e.g., TAB or Line Feed). jpayne@69: * jpayne@69: * Same as java.lang.Character.isSpaceChar(). jpayne@69: * jpayne@69: * Note: There are several ICU whitespace functions; please see the uchar.h jpayne@69: * file documentation for a detailed comparison. jpayne@69: * jpayne@69: * @param c the code point to be tested jpayne@69: * @return TRUE if the code point is a space character according to Character.isSpaceChar() jpayne@69: * jpayne@69: * @see u_isspace jpayne@69: * @see u_isWhitespace jpayne@69: * @see u_isUWhiteSpace jpayne@69: * @stable ICU 2.6 jpayne@69: */ jpayne@69: U_STABLE UBool U_EXPORT2 jpayne@69: u_isJavaSpaceChar(UChar32 c); jpayne@69: jpayne@69: /** jpayne@69: * Determines if the specified code point is a whitespace character according to Java/ICU. jpayne@69: * A character is considered to be a Java whitespace character if and only jpayne@69: * if it satisfies one of the following criteria: jpayne@69: * jpayne@69: * - It is a Unicode Separator character (categories "Z" = "Zs" or "Zl" or "Zp"), but is not jpayne@69: * also a non-breaking space (U+00A0 NBSP or U+2007 Figure Space or U+202F Narrow NBSP). jpayne@69: * - It is U+0009 HORIZONTAL TABULATION. jpayne@69: * - It is U+000A LINE FEED. jpayne@69: * - It is U+000B VERTICAL TABULATION. jpayne@69: * - It is U+000C FORM FEED. jpayne@69: * - It is U+000D CARRIAGE RETURN. jpayne@69: * - It is U+001C FILE SEPARATOR. jpayne@69: * - It is U+001D GROUP SEPARATOR. jpayne@69: * - It is U+001E RECORD SEPARATOR. jpayne@69: * - It is U+001F UNIT SEPARATOR. jpayne@69: * jpayne@69: * This API tries to sync with the semantics of Java's jpayne@69: * java.lang.Character.isWhitespace(), but it may not return jpayne@69: * the exact same results because of the Unicode version jpayne@69: * difference. jpayne@69: * jpayne@69: * Note: Unicode 4.0.1 changed U+200B ZERO WIDTH SPACE from a Space Separator (Zs) jpayne@69: * to a Format Control (Cf). Since then, isWhitespace(0x200b) returns false. jpayne@69: * See http://www.unicode.org/versions/Unicode4.0.1/ jpayne@69: * jpayne@69: * Note: There are several ICU whitespace functions; please see the uchar.h jpayne@69: * file documentation for a detailed comparison. jpayne@69: * jpayne@69: * @param c the code point to be tested jpayne@69: * @return TRUE if the code point is a whitespace character according to Java/ICU jpayne@69: * jpayne@69: * @see u_isspace jpayne@69: * @see u_isJavaSpaceChar jpayne@69: * @see u_isUWhiteSpace jpayne@69: * @stable ICU 2.0 jpayne@69: */ jpayne@69: U_STABLE UBool U_EXPORT2 jpayne@69: u_isWhitespace(UChar32 c); jpayne@69: jpayne@69: /** jpayne@69: * Determines whether the specified code point is a control character jpayne@69: * (as defined by this function). jpayne@69: * A control character is one of the following: jpayne@69: * - ISO 8-bit control character (U+0000..U+001f and U+007f..U+009f) jpayne@69: * - U_CONTROL_CHAR (Cc) jpayne@69: * - U_FORMAT_CHAR (Cf) jpayne@69: * - U_LINE_SEPARATOR (Zl) jpayne@69: * - U_PARAGRAPH_SEPARATOR (Zp) jpayne@69: * jpayne@69: * This is a C/POSIX migration function. jpayne@69: * See the comments about C/POSIX character classification functions in the jpayne@69: * documentation at the top of this header file. jpayne@69: * jpayne@69: * @param c the code point to be tested jpayne@69: * @return TRUE if the code point is a control character jpayne@69: * jpayne@69: * @see UCHAR_DEFAULT_IGNORABLE_CODE_POINT jpayne@69: * @see u_isprint jpayne@69: * @stable ICU 2.0 jpayne@69: */ jpayne@69: U_STABLE UBool U_EXPORT2 jpayne@69: u_iscntrl(UChar32 c); jpayne@69: jpayne@69: /** jpayne@69: * Determines whether the specified code point is an ISO control code. jpayne@69: * True for U+0000..U+001f and U+007f..U+009f (general category "Cc"). jpayne@69: * jpayne@69: * Same as java.lang.Character.isISOControl(). jpayne@69: * jpayne@69: * @param c the code point to be tested jpayne@69: * @return TRUE if the code point is an ISO control code jpayne@69: * jpayne@69: * @see u_iscntrl jpayne@69: * @stable ICU 2.6 jpayne@69: */ jpayne@69: U_STABLE UBool U_EXPORT2 jpayne@69: u_isISOControl(UChar32 c); jpayne@69: jpayne@69: /** jpayne@69: * Determines whether the specified code point is a printable character. jpayne@69: * True for general categories other than "C" (controls). jpayne@69: * jpayne@69: * This is a C/POSIX migration function. jpayne@69: * See the comments about C/POSIX character classification functions in the jpayne@69: * documentation at the top of this header file. jpayne@69: * jpayne@69: * @param c the code point to be tested jpayne@69: * @return TRUE if the code point is a printable character jpayne@69: * jpayne@69: * @see UCHAR_DEFAULT_IGNORABLE_CODE_POINT jpayne@69: * @see u_iscntrl jpayne@69: * @stable ICU 2.0 jpayne@69: */ jpayne@69: U_STABLE UBool U_EXPORT2 jpayne@69: u_isprint(UChar32 c); jpayne@69: jpayne@69: /** jpayne@69: * Non-standard: Determines whether the specified code point is a base character. jpayne@69: * True for general categories "L" (letters), "N" (numbers), jpayne@69: * "Mc" (spacing combining marks), and "Me" (enclosing marks). jpayne@69: * jpayne@69: * Note that this is different from the Unicode Standard definition in jpayne@69: * chapter 3.6, conformance clause D51 “Base character”, jpayne@69: * which defines base characters as the code points with general categories jpayne@69: * Letter (L), Number (N), Punctuation (P), Symbol (S), or Space Separator (Zs). jpayne@69: * jpayne@69: * @param c the code point to be tested jpayne@69: * @return TRUE if the code point is a base character according to this function jpayne@69: * jpayne@69: * @see u_isalpha jpayne@69: * @see u_isdigit jpayne@69: * @stable ICU 2.0 jpayne@69: */ jpayne@69: U_STABLE UBool U_EXPORT2 jpayne@69: u_isbase(UChar32 c); jpayne@69: jpayne@69: /** jpayne@69: * Returns the bidirectional category value for the code point, jpayne@69: * which is used in the Unicode bidirectional algorithm jpayne@69: * (UAX #9 http://www.unicode.org/reports/tr9/). jpayne@69: * Note that some unassigned code points have bidi values jpayne@69: * of R or AL because they are in blocks that are reserved jpayne@69: * for Right-To-Left scripts. jpayne@69: * jpayne@69: * Same as java.lang.Character.getDirectionality() jpayne@69: * jpayne@69: * @param c the code point to be tested jpayne@69: * @return the bidirectional category (UCharDirection) value jpayne@69: * jpayne@69: * @see UCharDirection jpayne@69: * @stable ICU 2.0 jpayne@69: */ jpayne@69: U_STABLE UCharDirection U_EXPORT2 jpayne@69: u_charDirection(UChar32 c); jpayne@69: jpayne@69: /** jpayne@69: * Determines whether the code point has the Bidi_Mirrored property. jpayne@69: * This property is set for characters that are commonly used in jpayne@69: * Right-To-Left contexts and need to be displayed with a "mirrored" jpayne@69: * glyph. jpayne@69: * jpayne@69: * Same as java.lang.Character.isMirrored(). jpayne@69: * Same as UCHAR_BIDI_MIRRORED jpayne@69: * jpayne@69: * @param c the code point to be tested jpayne@69: * @return TRUE if the character has the Bidi_Mirrored property jpayne@69: * jpayne@69: * @see UCHAR_BIDI_MIRRORED jpayne@69: * @stable ICU 2.0 jpayne@69: */ jpayne@69: U_STABLE UBool U_EXPORT2 jpayne@69: u_isMirrored(UChar32 c); jpayne@69: jpayne@69: /** jpayne@69: * Maps the specified character to a "mirror-image" character. jpayne@69: * For characters with the Bidi_Mirrored property, implementations jpayne@69: * sometimes need a "poor man's" mapping to another Unicode jpayne@69: * character (code point) such that the default glyph may serve jpayne@69: * as the mirror-image of the default glyph of the specified jpayne@69: * character. This is useful for text conversion to and from jpayne@69: * codepages with visual order, and for displays without glyph jpayne@69: * selection capabilities. jpayne@69: * jpayne@69: * @param c the code point to be mapped jpayne@69: * @return another Unicode code point that may serve as a mirror-image jpayne@69: * substitute, or c itself if there is no such mapping or c jpayne@69: * does not have the Bidi_Mirrored property jpayne@69: * jpayne@69: * @see UCHAR_BIDI_MIRRORED jpayne@69: * @see u_isMirrored jpayne@69: * @stable ICU 2.0 jpayne@69: */ jpayne@69: U_STABLE UChar32 U_EXPORT2 jpayne@69: u_charMirror(UChar32 c); jpayne@69: jpayne@69: /** jpayne@69: * Maps the specified character to its paired bracket character. jpayne@69: * For Bidi_Paired_Bracket_Type!=None, this is the same as u_charMirror(). jpayne@69: * Otherwise c itself is returned. jpayne@69: * See http://www.unicode.org/reports/tr9/ jpayne@69: * jpayne@69: * @param c the code point to be mapped jpayne@69: * @return the paired bracket code point, jpayne@69: * or c itself if there is no such mapping jpayne@69: * (Bidi_Paired_Bracket_Type=None) jpayne@69: * jpayne@69: * @see UCHAR_BIDI_PAIRED_BRACKET jpayne@69: * @see UCHAR_BIDI_PAIRED_BRACKET_TYPE jpayne@69: * @see u_charMirror jpayne@69: * @stable ICU 52 jpayne@69: */ jpayne@69: U_STABLE UChar32 U_EXPORT2 jpayne@69: u_getBidiPairedBracket(UChar32 c); jpayne@69: jpayne@69: /** jpayne@69: * Returns the general category value for the code point. jpayne@69: * jpayne@69: * Same as java.lang.Character.getType(). jpayne@69: * jpayne@69: * @param c the code point to be tested jpayne@69: * @return the general category (UCharCategory) value jpayne@69: * jpayne@69: * @see UCharCategory jpayne@69: * @stable ICU 2.0 jpayne@69: */ jpayne@69: U_STABLE int8_t U_EXPORT2 jpayne@69: u_charType(UChar32 c); jpayne@69: jpayne@69: /** jpayne@69: * Get a single-bit bit set for the general category of a character. jpayne@69: * This bit set can be compared bitwise with U_GC_SM_MASK, U_GC_L_MASK, etc. jpayne@69: * Same as U_MASK(u_charType(c)). jpayne@69: * jpayne@69: * @param c the code point to be tested jpayne@69: * @return a single-bit mask corresponding to the general category (UCharCategory) value jpayne@69: * jpayne@69: * @see u_charType jpayne@69: * @see UCharCategory jpayne@69: * @see U_GC_CN_MASK jpayne@69: * @stable ICU 2.1 jpayne@69: */ jpayne@69: #define U_GET_GC_MASK(c) U_MASK(u_charType(c)) jpayne@69: jpayne@69: /** jpayne@69: * Callback from u_enumCharTypes(), is called for each contiguous range jpayne@69: * of code points c (where start<=cnameChoice, the character name written jpayne@69: * into the buffer is the "modern" name or the name that was defined jpayne@69: * in Unicode version 1.0. jpayne@69: * The name contains only "invariant" characters jpayne@69: * like A-Z, 0-9, space, and '-'. jpayne@69: * Unicode 1.0 names are only retrieved if they are different from the modern jpayne@69: * names and if the data file contains the data for them. gennames may or may jpayne@69: * not be called with a command line option to include 1.0 names in unames.dat. jpayne@69: * jpayne@69: * @param code The character (code point) for which to get the name. jpayne@69: * It must be 0<=code<=0x10ffff. jpayne@69: * @param nameChoice Selector for which name to get. jpayne@69: * @param buffer Destination address for copying the name. jpayne@69: * The name will always be zero-terminated. jpayne@69: * If there is no name, then the buffer will be set to the empty string. jpayne@69: * @param bufferLength ==sizeof(buffer) jpayne@69: * @param pErrorCode Pointer to a UErrorCode variable; jpayne@69: * check for U_SUCCESS() after u_charName() jpayne@69: * returns. jpayne@69: * @return The length of the name, or 0 if there is no name for this character. jpayne@69: * If the bufferLength is less than or equal to the length, then the buffer jpayne@69: * contains the truncated name and the returned length indicates the full jpayne@69: * length of the name. jpayne@69: * The length does not include the zero-termination. jpayne@69: * jpayne@69: * @see UCharNameChoice jpayne@69: * @see u_charFromName jpayne@69: * @see u_enumCharNames jpayne@69: * @stable ICU 2.0 jpayne@69: */ jpayne@69: U_STABLE int32_t U_EXPORT2 jpayne@69: u_charName(UChar32 code, UCharNameChoice nameChoice, jpayne@69: char *buffer, int32_t bufferLength, jpayne@69: UErrorCode *pErrorCode); jpayne@69: jpayne@69: #ifndef U_HIDE_DEPRECATED_API jpayne@69: /** jpayne@69: * Returns an empty string. jpayne@69: * Used to return the ISO 10646 comment for a character. jpayne@69: * The Unicode ISO_Comment property is deprecated and has no values. jpayne@69: * jpayne@69: * @param c The character (code point) for which to get the ISO comment. jpayne@69: * It must be 0<=c<=0x10ffff. jpayne@69: * @param dest Destination address for copying the comment. jpayne@69: * The comment will be zero-terminated if possible. jpayne@69: * If there is no comment, then the buffer will be set to the empty string. jpayne@69: * @param destCapacity ==sizeof(dest) jpayne@69: * @param pErrorCode Pointer to a UErrorCode variable; jpayne@69: * check for U_SUCCESS() after u_getISOComment() jpayne@69: * returns. jpayne@69: * @return 0 jpayne@69: * jpayne@69: * @deprecated ICU 49 jpayne@69: */ jpayne@69: U_DEPRECATED int32_t U_EXPORT2 jpayne@69: u_getISOComment(UChar32 c, jpayne@69: char *dest, int32_t destCapacity, jpayne@69: UErrorCode *pErrorCode); jpayne@69: #endif /* U_HIDE_DEPRECATED_API */ jpayne@69: jpayne@69: /** jpayne@69: * Find a Unicode character by its name and return its code point value. jpayne@69: * The name is matched exactly and completely. jpayne@69: * If the name does not correspond to a code point, pErrorCode jpayne@69: * is set to U_INVALID_CHAR_FOUND. jpayne@69: * A Unicode 1.0 name is matched only if it differs from the modern name. jpayne@69: * Unicode names are all uppercase. Extended names are lowercase followed jpayne@69: * by an uppercase hexadecimal number, and within angle brackets. jpayne@69: * jpayne@69: * @param nameChoice Selector for which name to match. jpayne@69: * @param name The name to match. jpayne@69: * @param pErrorCode Pointer to a UErrorCode variable jpayne@69: * @return The Unicode value of the code point with the given name, jpayne@69: * or an undefined value if there is no such code point. jpayne@69: * jpayne@69: * @see UCharNameChoice jpayne@69: * @see u_charName jpayne@69: * @see u_enumCharNames jpayne@69: * @stable ICU 1.7 jpayne@69: */ jpayne@69: U_STABLE UChar32 U_EXPORT2 jpayne@69: u_charFromName(UCharNameChoice nameChoice, jpayne@69: const char *name, jpayne@69: UErrorCode *pErrorCode); jpayne@69: jpayne@69: /** jpayne@69: * Type of a callback function for u_enumCharNames() that gets called jpayne@69: * for each Unicode character with the code point value and jpayne@69: * the character name. jpayne@69: * If such a function returns FALSE, then the enumeration is stopped. jpayne@69: * jpayne@69: * @param context The context pointer that was passed to u_enumCharNames(). jpayne@69: * @param code The Unicode code point for the character with this name. jpayne@69: * @param nameChoice Selector for which kind of names is enumerated. jpayne@69: * @param name The character's name, zero-terminated. jpayne@69: * @param length The length of the name. jpayne@69: * @return TRUE if the enumeration should continue, FALSE to stop it. jpayne@69: * jpayne@69: * @see UCharNameChoice jpayne@69: * @see u_enumCharNames jpayne@69: * @stable ICU 1.7 jpayne@69: */ jpayne@69: typedef UBool U_CALLCONV UEnumCharNamesFn(void *context, jpayne@69: UChar32 code, jpayne@69: UCharNameChoice nameChoice, jpayne@69: const char *name, jpayne@69: int32_t length); jpayne@69: jpayne@69: /** jpayne@69: * Enumerate all assigned Unicode characters between the start and limit jpayne@69: * code points (start inclusive, limit exclusive) and call a function jpayne@69: * for each, passing the code point value and the character name. jpayne@69: * For Unicode 1.0 names, only those are enumerated that differ from the jpayne@69: * modern names. jpayne@69: * jpayne@69: * @param start The first code point in the enumeration range. jpayne@69: * @param limit One more than the last code point in the enumeration range jpayne@69: * (the first one after the range). jpayne@69: * @param fn The function that is to be called for each character name. jpayne@69: * @param context An arbitrary pointer that is passed to the function. jpayne@69: * @param nameChoice Selector for which kind of names to enumerate. jpayne@69: * @param pErrorCode Pointer to a UErrorCode variable jpayne@69: * jpayne@69: * @see UCharNameChoice jpayne@69: * @see UEnumCharNamesFn jpayne@69: * @see u_charName jpayne@69: * @see u_charFromName jpayne@69: * @stable ICU 1.7 jpayne@69: */ jpayne@69: U_STABLE void U_EXPORT2 jpayne@69: u_enumCharNames(UChar32 start, UChar32 limit, jpayne@69: UEnumCharNamesFn *fn, jpayne@69: void *context, jpayne@69: UCharNameChoice nameChoice, jpayne@69: UErrorCode *pErrorCode); jpayne@69: jpayne@69: /** jpayne@69: * Return the Unicode name for a given property, as given in the jpayne@69: * Unicode database file PropertyAliases.txt. jpayne@69: * jpayne@69: * In addition, this function maps the property jpayne@69: * UCHAR_GENERAL_CATEGORY_MASK to the synthetic names "gcm" / jpayne@69: * "General_Category_Mask". These names are not in jpayne@69: * PropertyAliases.txt. jpayne@69: * jpayne@69: * @param property UProperty selector other than UCHAR_INVALID_CODE. jpayne@69: * If out of range, NULL is returned. jpayne@69: * jpayne@69: * @param nameChoice selector for which name to get. If out of range, jpayne@69: * NULL is returned. All properties have a long name. Most jpayne@69: * have a short name, but some do not. Unicode allows for jpayne@69: * additional names; if present these will be returned by jpayne@69: * U_LONG_PROPERTY_NAME + i, where i=1, 2,... jpayne@69: * jpayne@69: * @return a pointer to the name, or NULL if either the jpayne@69: * property or the nameChoice is out of range. If a given jpayne@69: * nameChoice returns NULL, then all larger values of jpayne@69: * nameChoice will return NULL, with one exception: if NULL is jpayne@69: * returned for U_SHORT_PROPERTY_NAME, then jpayne@69: * U_LONG_PROPERTY_NAME (and higher) may still return a jpayne@69: * non-NULL value. The returned pointer is valid until jpayne@69: * u_cleanup() is called. jpayne@69: * jpayne@69: * @see UProperty jpayne@69: * @see UPropertyNameChoice jpayne@69: * @stable ICU 2.4 jpayne@69: */ jpayne@69: U_STABLE const char* U_EXPORT2 jpayne@69: u_getPropertyName(UProperty property, jpayne@69: UPropertyNameChoice nameChoice); jpayne@69: jpayne@69: /** jpayne@69: * Return the UProperty enum for a given property name, as specified jpayne@69: * in the Unicode database file PropertyAliases.txt. Short, long, and jpayne@69: * any other variants are recognized. jpayne@69: * jpayne@69: * In addition, this function maps the synthetic names "gcm" / jpayne@69: * "General_Category_Mask" to the property jpayne@69: * UCHAR_GENERAL_CATEGORY_MASK. These names are not in jpayne@69: * PropertyAliases.txt. jpayne@69: * jpayne@69: * @param alias the property name to be matched. The name is compared jpayne@69: * using "loose matching" as described in PropertyAliases.txt. jpayne@69: * jpayne@69: * @return a UProperty enum, or UCHAR_INVALID_CODE if the given name jpayne@69: * does not match any property. jpayne@69: * jpayne@69: * @see UProperty jpayne@69: * @stable ICU 2.4 jpayne@69: */ jpayne@69: U_STABLE UProperty U_EXPORT2 jpayne@69: u_getPropertyEnum(const char* alias); jpayne@69: jpayne@69: /** jpayne@69: * Return the Unicode name for a given property value, as given in the jpayne@69: * Unicode database file PropertyValueAliases.txt. jpayne@69: * jpayne@69: * Note: Some of the names in PropertyValueAliases.txt can only be jpayne@69: * retrieved using UCHAR_GENERAL_CATEGORY_MASK, not jpayne@69: * UCHAR_GENERAL_CATEGORY. These include: "C" / "Other", "L" / jpayne@69: * "Letter", "LC" / "Cased_Letter", "M" / "Mark", "N" / "Number", "P" jpayne@69: * / "Punctuation", "S" / "Symbol", and "Z" / "Separator". jpayne@69: * jpayne@69: * @param property UProperty selector constant. jpayne@69: * Must be UCHAR_BINARY_START<=which2<=radix<=36 or if the jpayne@69: * value of c is not a valid digit in the specified jpayne@69: * radix, -1 is returned. A character is a valid digit jpayne@69: * if at least one of the following is true: jpayne@69: *
    jpayne@69: *
  • The character has a decimal digit value. jpayne@69: * Such characters have the general category "Nd" (decimal digit numbers) jpayne@69: * and a Numeric_Type of Decimal. jpayne@69: * In this case the value is the character's decimal digit value.
    • jpayne@69: *
  • The character is one of the uppercase Latin letters jpayne@69: * 'A' through 'Z'. jpayne@69: * In this case the value is c-'A'+10.
    • jpayne@69: *
  • The character is one of the lowercase Latin letters jpayne@69: * 'a' through 'z'. jpayne@69: * In this case the value is ch-'a'+10.
    • jpayne@69: *
  • Latin letters from both the ASCII range (0061..007A, 0041..005A) jpayne@69: * as well as from the Fullwidth ASCII range (FF41..FF5A, FF21..FF3A) jpayne@69: * are recognized.
    • jpayne@69: *
jpayne@69: * jpayne@69: * Same as java.lang.Character.digit(). jpayne@69: * jpayne@69: * @param ch the code point to be tested. jpayne@69: * @param radix the radix. jpayne@69: * @return the numeric value represented by the character in the jpayne@69: * specified radix, jpayne@69: * or -1 if there is no value or if the value exceeds the radix. jpayne@69: * jpayne@69: * @see UCHAR_NUMERIC_TYPE jpayne@69: * @see u_forDigit jpayne@69: * @see u_charDigitValue jpayne@69: * @see u_isdigit jpayne@69: * @stable ICU 2.0 jpayne@69: */ jpayne@69: U_STABLE int32_t U_EXPORT2 jpayne@69: u_digit(UChar32 ch, int8_t radix); jpayne@69: jpayne@69: /** jpayne@69: * Determines the character representation for a specific digit in jpayne@69: * the specified radix. If the value of radix is not a jpayne@69: * valid radix, or the value of digit is not a valid jpayne@69: * digit in the specified radix, the null character jpayne@69: * (U+0000) is returned. jpayne@69: *

jpayne@69: * The radix argument is valid if it is greater than or jpayne@69: * equal to 2 and less than or equal to 36. jpayne@69: * The digit argument is valid if jpayne@69: * 0 <= digit < radix. jpayne@69: *

jpayne@69: * If the digit is less than 10, then jpayne@69: * '0' + digit is returned. Otherwise, the value jpayne@69: * 'a' + digit - 10 is returned. jpayne@69: * jpayne@69: * Same as java.lang.Character.forDigit(). jpayne@69: * jpayne@69: * @param digit the number to convert to a character. jpayne@69: * @param radix the radix. jpayne@69: * @return the char representation of the specified digit jpayne@69: * in the specified radix. jpayne@69: * jpayne@69: * @see u_digit jpayne@69: * @see u_charDigitValue jpayne@69: * @see u_isdigit jpayne@69: * @stable ICU 2.0 jpayne@69: */ jpayne@69: U_STABLE UChar32 U_EXPORT2 jpayne@69: u_forDigit(int32_t digit, int8_t radix); jpayne@69: jpayne@69: /** jpayne@69: * Get the "age" of the code point. jpayne@69: * The "age" is the Unicode version when the code point was first jpayne@69: * designated (as a non-character or for Private Use) jpayne@69: * or assigned a character. jpayne@69: * This can be useful to avoid emitting code points to receiving jpayne@69: * processes that do not accept newer characters. jpayne@69: * The data is from the UCD file DerivedAge.txt. jpayne@69: * jpayne@69: * @param c The code point. jpayne@69: * @param versionArray The Unicode version number array, to be filled in. jpayne@69: * jpayne@69: * @stable ICU 2.1 jpayne@69: */ jpayne@69: U_STABLE void U_EXPORT2 jpayne@69: u_charAge(UChar32 c, UVersionInfo versionArray); jpayne@69: jpayne@69: /** jpayne@69: * Gets the Unicode version information. jpayne@69: * The version array is filled in with the version information jpayne@69: * for the Unicode standard that is currently used by ICU. jpayne@69: * For example, Unicode version 3.1.1 is represented as an array with jpayne@69: * the values { 3, 1, 1, 0 }. jpayne@69: * jpayne@69: * @param versionArray an output array that will be filled in with jpayne@69: * the Unicode version number jpayne@69: * @stable ICU 2.0 jpayne@69: */ jpayne@69: U_STABLE void U_EXPORT2 jpayne@69: u_getUnicodeVersion(UVersionInfo versionArray); jpayne@69: jpayne@69: #if !UCONFIG_NO_NORMALIZATION jpayne@69: /** jpayne@69: * Get the FC_NFKC_Closure property string for a character. jpayne@69: * See Unicode Standard Annex #15 for details, search for "FC_NFKC_Closure" jpayne@69: * or for "FNC": http://www.unicode.org/reports/tr15/ jpayne@69: * jpayne@69: * @param c The character (code point) for which to get the FC_NFKC_Closure string. jpayne@69: * It must be 0<=c<=0x10ffff. jpayne@69: * @param dest Destination address for copying the string. jpayne@69: * The string will be zero-terminated if possible. jpayne@69: * If there is no FC_NFKC_Closure string, jpayne@69: * then the buffer will be set to the empty string. jpayne@69: * @param destCapacity ==sizeof(dest) jpayne@69: * @param pErrorCode Pointer to a UErrorCode variable. jpayne@69: * @return The length of the string, or 0 if there is no FC_NFKC_Closure string for this character. jpayne@69: * If the destCapacity is less than or equal to the length, then the buffer jpayne@69: * contains the truncated name and the returned length indicates the full jpayne@69: * length of the name. jpayne@69: * The length does not include the zero-termination. jpayne@69: * jpayne@69: * @stable ICU 2.2 jpayne@69: */ jpayne@69: U_STABLE int32_t U_EXPORT2 jpayne@69: u_getFC_NFKC_Closure(UChar32 c, UChar *dest, int32_t destCapacity, UErrorCode *pErrorCode); jpayne@69: jpayne@69: #endif jpayne@69: jpayne@69: jpayne@69: U_CDECL_END jpayne@69: jpayne@69: #endif /*_UCHAR*/ jpayne@69: /*eof*/