1999-12-28 23:39:02 +00:00
|
|
|
/*
|
|
|
|
**********************************************************************
|
2011-08-01 02:20:46 +00:00
|
|
|
* Copyright (C) 1997-2011, International Business Machines
|
1999-12-28 23:39:02 +00:00
|
|
|
* Corporation and others. All Rights Reserved.
|
|
|
|
**********************************************************************
|
|
|
|
*
|
|
|
|
* File UCHAR.H
|
|
|
|
*
|
|
|
|
* Modification History:
|
|
|
|
*
|
|
|
|
* Date Name Description
|
|
|
|
* 04/02/97 aliu Creation.
|
|
|
|
* 03/29/99 helena Updated for C APIs.
|
|
|
|
* 4/15/99 Madhu Updated for C Implementation and Javadoc
|
|
|
|
* 5/20/99 Madhu Added the function u_getVersion()
|
|
|
|
* 8/19/1999 srl Upgraded scripts to Unicode 3.0
|
|
|
|
* 8/27/1999 schererm UCharDirection constants: U_...
|
|
|
|
* 11/11/1999 weiv added u_isalnum(), cleaned comments
|
2000-01-11 23:20:26 +00:00
|
|
|
* 01/11/2000 helena Renamed u_getVersion to u_getUnicodeVersion().
|
2001-03-21 20:44:20 +00:00
|
|
|
******************************************************************************
|
1999-12-28 23:39:02 +00:00
|
|
|
*/
|
|
|
|
|
|
|
|
#ifndef UCHAR_H
|
|
|
|
#define UCHAR_H
|
|
|
|
|
|
|
|
#include "unicode/utypes.h"
|
2002-01-12 00:11:09 +00:00
|
|
|
|
|
|
|
U_CDECL_BEGIN
|
|
|
|
|
2001-03-21 20:44:20 +00:00
|
|
|
/*==========================================================================*/
|
|
|
|
/* Unicode version number */
|
|
|
|
/*==========================================================================*/
|
2002-03-13 23:31:12 +00:00
|
|
|
/**
|
|
|
|
* Unicode version number, default for the current ICU version.
|
|
|
|
* The actual Unicode Character Database (UCD) data is stored in uprops.dat
|
|
|
|
* and may be generated from UCD files from a different Unicode version.
|
|
|
|
* Call u_getUnicodeVersion to get the actual Unicode version of the data.
|
|
|
|
*
|
|
|
|
* @see u_getUnicodeVersion
|
2002-12-04 23:39:56 +00:00
|
|
|
* @stable ICU 2.0
|
2002-03-13 23:31:12 +00:00
|
|
|
*/
|
2011-12-08 22:37:24 +00:00
|
|
|
#define U_UNICODE_VERSION "6.1"
|
1999-12-28 23:39:02 +00:00
|
|
|
|
|
|
|
/**
|
2000-12-08 18:43:57 +00:00
|
|
|
* \file
|
2003-02-11 01:59:32 +00:00
|
|
|
* \brief C API: Unicode Properties
|
2000-12-08 18:43:57 +00:00
|
|
|
*
|
2003-02-11 01:59:32 +00:00
|
|
|
* This C API provides low-level access to the Unicode Character Database.
|
|
|
|
* In addition to raw property values, some convenience functions calculate
|
|
|
|
* derived properties, for example for Java-style programming.
|
|
|
|
*
|
|
|
|
* Unicode assigns each code point (not just assigned character) values for
|
|
|
|
* many properties.
|
|
|
|
* Most of them are simple boolean flags, or constants from a small enumerated list.
|
|
|
|
* For some properties, values are strings or other relatively more complex types.
|
|
|
|
*
|
|
|
|
* For more information see
|
|
|
|
* "About the Unicode Character Database" (http://www.unicode.org/ucd/)
|
2007-06-11 19:14:47 +00:00
|
|
|
* and the ICU User Guide chapter on Properties (http://icu-project.org/userguide/properties.html).
|
2003-02-09 21:02:26 +00:00
|
|
|
*
|
|
|
|
* Many functions are designed to match java.lang.Character functions.
|
|
|
|
* See the individual function documentation,
|
2005-02-18 00:19:33 +00:00
|
|
|
* and see the JDK 1.4 java.lang.Character documentation
|
|
|
|
* at http://java.sun.com/j2se/1.4/docs/api/java/lang/Character.html
|
2003-04-24 23:09:26 +00:00
|
|
|
*
|
|
|
|
* There are also functions that provide easy migration from C/POSIX functions
|
|
|
|
* like isblank(). Their use is generally discouraged because the C/POSIX
|
|
|
|
* standards do not define their semantics beyond the ASCII range, which means
|
|
|
|
* that different implementations exhibit very different behavior.
|
|
|
|
* Instead, Unicode properties should be used directly.
|
|
|
|
*
|
|
|
|
* There are also only a few, broad C/POSIX character classes, and they tend
|
|
|
|
* to be used for conflicting purposes. For example, the "isalpha()" class
|
|
|
|
* is sometimes used to determine word boundaries, while a more sophisticated
|
|
|
|
* approach would at least distinguish initial letters from continuation
|
|
|
|
* characters (the latter including combining marks).
|
|
|
|
* (In ICU, BreakIterator is the most sophisticated API for word boundaries.)
|
|
|
|
* Another example: There is no "istitle()" class for titlecase characters.
|
|
|
|
*
|
2005-05-28 22:54:36 +00:00
|
|
|
* ICU 3.4 and later provides API access for all twelve C/POSIX character classes.
|
|
|
|
* ICU implements them according to the Standard Recommendations in
|
|
|
|
* Annex C: Compatibility Properties of UTS #18 Unicode Regular Expressions
|
|
|
|
* (http://www.unicode.org/reports/tr18/#Compatibility_Properties).
|
|
|
|
*
|
|
|
|
* API access for C/POSIX character classes is as follows:
|
|
|
|
* - alpha: u_isUAlphabetic(c) or u_hasBinaryProperty(c, UCHAR_ALPHABETIC)
|
|
|
|
* - lower: u_isULowercase(c) or u_hasBinaryProperty(c, UCHAR_LOWERCASE)
|
|
|
|
* - upper: u_isUUppercase(c) or u_hasBinaryProperty(c, UCHAR_UPPERCASE)
|
|
|
|
* - punct: u_ispunct(c)
|
2005-05-30 21:18:01 +00:00
|
|
|
* - digit: u_isdigit(c) or u_charType(c)==U_DECIMAL_DIGIT_NUMBER
|
2005-05-28 22:54:36 +00:00
|
|
|
* - xdigit: u_isxdigit(c) or u_hasBinaryProperty(c, UCHAR_POSIX_XDIGIT)
|
|
|
|
* - alnum: u_hasBinaryProperty(c, UCHAR_POSIX_ALNUM)
|
|
|
|
* - space: u_isUWhiteSpace(c) or u_hasBinaryProperty(c, UCHAR_WHITE_SPACE)
|
|
|
|
* - blank: u_isblank(c) or u_hasBinaryProperty(c, UCHAR_POSIX_BLANK)
|
|
|
|
* - cntrl: u_charType(c)==U_CONTROL_CHAR
|
|
|
|
* - graph: u_hasBinaryProperty(c, UCHAR_POSIX_GRAPH)
|
|
|
|
* - print: u_hasBinaryProperty(c, UCHAR_POSIX_PRINT)
|
|
|
|
*
|
|
|
|
* Note: Some of the u_isxyz() functions in uchar.h predate, and do not match,
|
|
|
|
* the Standard Recommendations in UTS #18. Instead, they match Java
|
|
|
|
* functions according to their API documentation.
|
|
|
|
*
|
2005-06-22 21:07:14 +00:00
|
|
|
* \htmlonly
|
2005-05-28 22:54:36 +00:00
|
|
|
* The C/POSIX character classes are also available in UnicodeSet patterns,
|
|
|
|
* using patterns like [:graph:] or \p{graph}.
|
2005-06-22 21:07:14 +00:00
|
|
|
* \endhtmlonly
|
2003-05-30 21:12:00 +00:00
|
|
|
*
|
|
|
|
* Note: There are several ICU whitespace functions.
|
|
|
|
* Comparison:
|
|
|
|
* - u_isUWhiteSpace=UCHAR_WHITE_SPACE: Unicode White_Space property;
|
|
|
|
* most of general categories "Z" (separators) + most whitespace ISO controls
|
|
|
|
* (including no-break spaces, but excluding IS1..IS4 and ZWSP)
|
|
|
|
* - u_isWhitespace: Java isWhitespace; Z + whitespace ISO controls but excluding no-break spaces
|
|
|
|
* - u_isJavaSpaceChar: Java isSpaceChar; just Z (including no-break spaces)
|
|
|
|
* - u_isspace: Z + whitespace ISO controls (including no-break spaces)
|
|
|
|
* - u_isblank: "horizontal spaces" = TAB + Zs - ZWSP
|
1999-12-28 23:39:02 +00:00
|
|
|
*/
|
|
|
|
|
|
|
|
/**
|
|
|
|
* Constants.
|
|
|
|
*/
|
|
|
|
|
2002-12-05 00:30:16 +00:00
|
|
|
/** The lowest Unicode code point value. Code points are non-negative. @stable ICU 2.0 */
|
2000-03-24 17:45:45 +00:00
|
|
|
#define UCHAR_MIN_VALUE 0
|
|
|
|
|
1999-12-28 23:39:02 +00:00
|
|
|
/**
|
2000-03-24 17:45:45 +00:00
|
|
|
* The highest Unicode code point value (scalar value) according to
|
|
|
|
* The Unicode Standard. This is a 21-bit value (20.1 bits, rounded up).
|
|
|
|
* For a single character, UChar32 is a simple type that can hold any code point value.
|
2003-02-11 01:59:32 +00:00
|
|
|
*
|
|
|
|
* @see UChar32
|
2002-12-05 00:30:16 +00:00
|
|
|
* @stable ICU 2.0
|
1999-12-28 23:39:02 +00:00
|
|
|
*/
|
2000-03-24 17:45:45 +00:00
|
|
|
#define UCHAR_MAX_VALUE 0x10ffff
|
1999-12-28 23:39:02 +00:00
|
|
|
|
2002-03-13 23:31:12 +00:00
|
|
|
/**
|
|
|
|
* Get a single-bit bit set (a flag) from a bit number 0..31.
|
2003-02-11 01:59:32 +00:00
|
|
|
* @stable ICU 2.1
|
2002-03-13 23:31:12 +00:00
|
|
|
*/
|
|
|
|
#define U_MASK(x) ((uint32_t)1<<(x))
|
|
|
|
|
2002-03-06 23:31:11 +00:00
|
|
|
/**
|
|
|
|
* Selection constants for Unicode properties.
|
|
|
|
* These constants are used in functions like u_hasBinaryProperty to select
|
|
|
|
* one of the Unicode properties.
|
|
|
|
*
|
|
|
|
* The properties APIs are intended to reflect Unicode properties as defined
|
|
|
|
* in the Unicode Character Database (UCD) and Unicode Technical Reports (UTR).
|
2003-02-11 01:59:32 +00:00
|
|
|
* For details about the properties see http://www.unicode.org/ucd/ .
|
2002-03-06 23:31:11 +00:00
|
|
|
* For names of Unicode properties see the UCD file PropertyAliases.txt.
|
|
|
|
*
|
2003-02-11 01:59:32 +00:00
|
|
|
* Important: If ICU is built with UCD files from Unicode versions below, e.g., 3.2,
|
2002-03-06 23:31:11 +00:00
|
|
|
* then properties marked with "new in Unicode 3.2" are not or not fully available.
|
|
|
|
* Check u_getUnicodeVersion to be sure.
|
|
|
|
*
|
2002-07-04 00:38:51 +00:00
|
|
|
* @see u_hasBinaryProperty
|
|
|
|
* @see u_getIntPropertyValue
|
2002-03-06 23:31:11 +00:00
|
|
|
* @see u_getUnicodeVersion
|
2003-02-11 01:59:32 +00:00
|
|
|
* @stable ICU 2.1
|
2002-03-06 23:31:11 +00:00
|
|
|
*/
|
2005-06-28 22:23:05 +00:00
|
|
|
typedef enum UProperty {
|
2011-12-23 04:20:35 +00:00
|
|
|
/*
|
|
|
|
* Note: UProperty constants are parsed by preparseucd.py.
|
|
|
|
* It matches lines like
|
|
|
|
* UCHAR_<Unicode property name>=<integer>,
|
|
|
|
*/
|
2002-10-30 18:24:53 +00:00
|
|
|
|
2003-02-11 01:59:32 +00:00
|
|
|
/* Note: Place UCHAR_ALPHABETIC before UCHAR_BINARY_START so that
|
2004-11-11 23:34:58 +00:00
|
|
|
debuggers display UCHAR_ALPHABETIC as the symbolic name for 0,
|
|
|
|
rather than UCHAR_BINARY_START. Likewise for other *_START
|
|
|
|
identifiers. */
|
2003-02-11 23:27:40 +00:00
|
|
|
|
2002-03-06 23:31:11 +00:00
|
|
|
/** Binary property Alphabetic. Same as u_isUAlphabetic, different from u_isalpha.
|
2003-02-11 01:59:32 +00:00
|
|
|
Lu+Ll+Lt+Lm+Lo+Nl+Other_Alphabetic @stable ICU 2.1 */
|
2002-11-22 19:36:55 +00:00
|
|
|
UCHAR_ALPHABETIC=0,
|
2003-02-11 01:59:32 +00:00
|
|
|
/** First constant for binary Unicode properties. @stable ICU 2.1 */
|
2002-11-22 19:36:55 +00:00
|
|
|
UCHAR_BINARY_START=UCHAR_ALPHABETIC,
|
2003-02-11 01:59:32 +00:00
|
|
|
/** Binary property ASCII_Hex_Digit. 0-9 A-F a-f @stable ICU 2.1 */
|
2006-02-07 01:54:15 +00:00
|
|
|
UCHAR_ASCII_HEX_DIGIT=1,
|
2002-03-06 23:31:11 +00:00
|
|
|
/** Binary property Bidi_Control.
|
|
|
|
Format controls which have specific functions
|
2003-02-11 01:59:32 +00:00
|
|
|
in the Bidi Algorithm. @stable ICU 2.1 */
|
2006-02-07 01:54:15 +00:00
|
|
|
UCHAR_BIDI_CONTROL=2,
|
2002-03-06 23:31:11 +00:00
|
|
|
/** Binary property Bidi_Mirrored.
|
|
|
|
Characters that may change display in RTL text.
|
|
|
|
Same as u_isMirrored.
|
2003-02-11 01:59:32 +00:00
|
|
|
See Bidi Algorithm, UTR 9. @stable ICU 2.1 */
|
2006-02-07 01:54:15 +00:00
|
|
|
UCHAR_BIDI_MIRRORED=3,
|
2003-02-11 01:59:32 +00:00
|
|
|
/** Binary property Dash. Variations of dashes. @stable ICU 2.1 */
|
2006-02-07 01:54:15 +00:00
|
|
|
UCHAR_DASH=4,
|
2002-03-06 23:31:11 +00:00
|
|
|
/** Binary property Default_Ignorable_Code_Point (new in Unicode 3.2).
|
|
|
|
Ignorable in most processing.
|
2003-02-11 01:59:32 +00:00
|
|
|
<2060..206F, FFF0..FFFB, E0000..E0FFF>+Other_Default_Ignorable_Code_Point+(Cf+Cc+Cs-White_Space) @stable ICU 2.1 */
|
2006-02-07 01:54:15 +00:00
|
|
|
UCHAR_DEFAULT_IGNORABLE_CODE_POINT=5,
|
2002-03-06 23:31:11 +00:00
|
|
|
/** Binary property Deprecated (new in Unicode 3.2).
|
2003-02-11 01:59:32 +00:00
|
|
|
The usage of deprecated characters is strongly discouraged. @stable ICU 2.1 */
|
2006-02-07 01:54:15 +00:00
|
|
|
UCHAR_DEPRECATED=6,
|
2002-03-06 23:31:11 +00:00
|
|
|
/** Binary property Diacritic. Characters that linguistically modify
|
2003-02-11 01:59:32 +00:00
|
|
|
the meaning of another character to which they apply. @stable ICU 2.1 */
|
2006-02-07 01:54:15 +00:00
|
|
|
UCHAR_DIACRITIC=7,
|
2002-03-06 23:31:11 +00:00
|
|
|
/** Binary property Extender.
|
|
|
|
Extend the value or shape of a preceding alphabetic character,
|
2003-02-11 01:59:32 +00:00
|
|
|
e.g., length and iteration marks. @stable ICU 2.1 */
|
2006-02-07 01:54:15 +00:00
|
|
|
UCHAR_EXTENDER=8,
|
2002-03-06 23:31:11 +00:00
|
|
|
/** Binary property Full_Composition_Exclusion.
|
|
|
|
CompositionExclusions.txt+Singleton Decompositions+
|
2003-02-11 01:59:32 +00:00
|
|
|
Non-Starter Decompositions. @stable ICU 2.1 */
|
2006-02-07 01:54:15 +00:00
|
|
|
UCHAR_FULL_COMPOSITION_EXCLUSION=9,
|
2002-03-06 23:31:11 +00:00
|
|
|
/** Binary property Grapheme_Base (new in Unicode 3.2).
|
|
|
|
For programmatic determination of grapheme cluster boundaries.
|
2003-02-11 01:59:32 +00:00
|
|
|
[0..10FFFF]-Cc-Cf-Cs-Co-Cn-Zl-Zp-Grapheme_Link-Grapheme_Extend-CGJ @stable ICU 2.1 */
|
2006-02-07 01:54:15 +00:00
|
|
|
UCHAR_GRAPHEME_BASE=10,
|
2002-03-06 23:31:11 +00:00
|
|
|
/** Binary property Grapheme_Extend (new in Unicode 3.2).
|
|
|
|
For programmatic determination of grapheme cluster boundaries.
|
2003-02-11 01:59:32 +00:00
|
|
|
Me+Mn+Mc+Other_Grapheme_Extend-Grapheme_Link-CGJ @stable ICU 2.1 */
|
2006-02-07 01:54:15 +00:00
|
|
|
UCHAR_GRAPHEME_EXTEND=11,
|
2002-03-06 23:31:11 +00:00
|
|
|
/** Binary property Grapheme_Link (new in Unicode 3.2).
|
2003-02-11 01:59:32 +00:00
|
|
|
For programmatic determination of grapheme cluster boundaries. @stable ICU 2.1 */
|
2006-02-07 01:54:15 +00:00
|
|
|
UCHAR_GRAPHEME_LINK=12,
|
2002-03-06 23:31:11 +00:00
|
|
|
/** Binary property Hex_Digit.
|
2003-02-11 01:59:32 +00:00
|
|
|
Characters commonly used for hexadecimal numbers. @stable ICU 2.1 */
|
2006-02-07 01:54:15 +00:00
|
|
|
UCHAR_HEX_DIGIT=13,
|
2002-03-06 23:31:11 +00:00
|
|
|
/** Binary property Hyphen. Dashes used to mark connections
|
2003-02-11 01:59:32 +00:00
|
|
|
between pieces of words, plus the Katakana middle dot. @stable ICU 2.1 */
|
2006-02-07 01:54:15 +00:00
|
|
|
UCHAR_HYPHEN=14,
|
2002-03-06 23:31:11 +00:00
|
|
|
/** Binary property ID_Continue.
|
|
|
|
Characters that can continue an identifier.
|
2003-02-11 01:59:32 +00:00
|
|
|
DerivedCoreProperties.txt also says "NOTE: Cf characters should be filtered out."
|
|
|
|
ID_Start+Mn+Mc+Nd+Pc @stable ICU 2.1 */
|
2006-02-07 01:54:15 +00:00
|
|
|
UCHAR_ID_CONTINUE=15,
|
2002-03-06 23:31:11 +00:00
|
|
|
/** Binary property ID_Start.
|
|
|
|
Characters that can start an identifier.
|
2003-02-11 01:59:32 +00:00
|
|
|
Lu+Ll+Lt+Lm+Lo+Nl @stable ICU 2.1 */
|
2006-02-07 01:54:15 +00:00
|
|
|
UCHAR_ID_START=16,
|
2002-03-12 19:09:08 +00:00
|
|
|
/** Binary property Ideographic.
|
2003-02-11 01:59:32 +00:00
|
|
|
CJKV ideographs. @stable ICU 2.1 */
|
2006-02-07 01:54:15 +00:00
|
|
|
UCHAR_IDEOGRAPHIC=17,
|
2002-03-06 23:31:11 +00:00
|
|
|
/** Binary property IDS_Binary_Operator (new in Unicode 3.2).
|
|
|
|
For programmatic determination of
|
2003-02-11 01:59:32 +00:00
|
|
|
Ideographic Description Sequences. @stable ICU 2.1 */
|
2006-02-07 01:54:15 +00:00
|
|
|
UCHAR_IDS_BINARY_OPERATOR=18,
|
2002-03-06 23:31:11 +00:00
|
|
|
/** Binary property IDS_Trinary_Operator (new in Unicode 3.2).
|
|
|
|
For programmatic determination of
|
2003-02-11 01:59:32 +00:00
|
|
|
Ideographic Description Sequences. @stable ICU 2.1 */
|
2006-02-07 01:54:15 +00:00
|
|
|
UCHAR_IDS_TRINARY_OPERATOR=19,
|
2002-03-06 23:31:11 +00:00
|
|
|
/** Binary property Join_Control.
|
2003-02-11 01:59:32 +00:00
|
|
|
Format controls for cursive joining and ligation. @stable ICU 2.1 */
|
2006-02-07 01:54:15 +00:00
|
|
|
UCHAR_JOIN_CONTROL=20,
|
2002-03-06 23:31:11 +00:00
|
|
|
/** Binary property Logical_Order_Exception (new in Unicode 3.2).
|
|
|
|
Characters that do not use logical order and
|
2003-02-11 01:59:32 +00:00
|
|
|
require special handling in most processing. @stable ICU 2.1 */
|
2006-02-07 01:54:15 +00:00
|
|
|
UCHAR_LOGICAL_ORDER_EXCEPTION=21,
|
2002-03-06 23:31:11 +00:00
|
|
|
/** Binary property Lowercase. Same as u_isULowercase, different from u_islower.
|
2003-02-11 01:59:32 +00:00
|
|
|
Ll+Other_Lowercase @stable ICU 2.1 */
|
2006-02-07 01:54:15 +00:00
|
|
|
UCHAR_LOWERCASE=22,
|
2003-02-11 01:59:32 +00:00
|
|
|
/** Binary property Math. Sm+Other_Math @stable ICU 2.1 */
|
2006-02-07 01:54:15 +00:00
|
|
|
UCHAR_MATH=23,
|
2002-03-06 23:31:11 +00:00
|
|
|
/** Binary property Noncharacter_Code_Point.
|
|
|
|
Code points that are explicitly defined as illegal
|
2003-02-11 01:59:32 +00:00
|
|
|
for the encoding of characters. @stable ICU 2.1 */
|
2006-02-07 01:54:15 +00:00
|
|
|
UCHAR_NONCHARACTER_CODE_POINT=24,
|
2003-02-11 01:59:32 +00:00
|
|
|
/** Binary property Quotation_Mark. @stable ICU 2.1 */
|
2006-02-07 01:54:15 +00:00
|
|
|
UCHAR_QUOTATION_MARK=25,
|
2002-03-06 23:31:11 +00:00
|
|
|
/** Binary property Radical (new in Unicode 3.2).
|
|
|
|
For programmatic determination of
|
2003-02-11 01:59:32 +00:00
|
|
|
Ideographic Description Sequences. @stable ICU 2.1 */
|
2006-02-07 01:54:15 +00:00
|
|
|
UCHAR_RADICAL=26,
|
2002-03-06 23:31:11 +00:00
|
|
|
/** Binary property Soft_Dotted (new in Unicode 3.2).
|
|
|
|
Characters with a "soft dot", like i or j.
|
|
|
|
An accent placed on these characters causes
|
2003-02-11 01:59:32 +00:00
|
|
|
the dot to disappear. @stable ICU 2.1 */
|
2006-02-07 01:54:15 +00:00
|
|
|
UCHAR_SOFT_DOTTED=27,
|
2002-03-06 23:31:11 +00:00
|
|
|
/** Binary property Terminal_Punctuation.
|
|
|
|
Punctuation characters that generally mark
|
2003-02-11 01:59:32 +00:00
|
|
|
the end of textual units. @stable ICU 2.1 */
|
2006-02-07 01:54:15 +00:00
|
|
|
UCHAR_TERMINAL_PUNCTUATION=28,
|
2002-03-06 23:31:11 +00:00
|
|
|
/** Binary property Unified_Ideograph (new in Unicode 3.2).
|
|
|
|
For programmatic determination of
|
2003-02-11 01:59:32 +00:00
|
|
|
Ideographic Description Sequences. @stable ICU 2.1 */
|
2006-02-07 01:54:15 +00:00
|
|
|
UCHAR_UNIFIED_IDEOGRAPH=29,
|
2002-03-06 23:31:11 +00:00
|
|
|
/** Binary property Uppercase. Same as u_isUUppercase, different from u_isupper.
|
2003-02-11 01:59:32 +00:00
|
|
|
Lu+Other_Uppercase @stable ICU 2.1 */
|
2006-02-07 01:54:15 +00:00
|
|
|
UCHAR_UPPERCASE=30,
|
2002-03-06 23:31:11 +00:00
|
|
|
/** Binary property White_Space.
|
|
|
|
Same as u_isUWhiteSpace, different from u_isspace and u_isWhitespace.
|
2003-02-11 01:59:32 +00:00
|
|
|
Space characters+TAB+CR+LF-ZWSP-ZWNBSP @stable ICU 2.1 */
|
2006-02-07 01:54:15 +00:00
|
|
|
UCHAR_WHITE_SPACE=31,
|
2002-03-06 23:31:11 +00:00
|
|
|
/** Binary property XID_Continue.
|
|
|
|
ID_Continue modified to allow closure under
|
2003-02-11 01:59:32 +00:00
|
|
|
normalization forms NFKC and NFKD. @stable ICU 2.1 */
|
2006-02-07 01:54:15 +00:00
|
|
|
UCHAR_XID_CONTINUE=32,
|
2002-03-06 23:31:11 +00:00
|
|
|
/** Binary property XID_Start. ID_Start modified to allow
|
2003-02-11 01:59:32 +00:00
|
|
|
closure under normalization forms NFKC and NFKD. @stable ICU 2.1 */
|
2006-02-07 01:54:15 +00:00
|
|
|
UCHAR_XID_START=33,
|
2003-02-20 22:47:18 +00:00
|
|
|
/** Binary property Case_Sensitive. Either the source of a case
|
|
|
|
mapping or _in_ the target of a case mapping. Not the same as
|
2004-11-02 07:28:07 +00:00
|
|
|
the general category Cased_Letter. @stable ICU 2.6 */
|
2006-02-07 01:54:15 +00:00
|
|
|
UCHAR_CASE_SENSITIVE=34,
|
2004-04-02 17:41:06 +00:00
|
|
|
/** Binary property STerm (new in Unicode 4.0.1).
|
|
|
|
Sentence Terminal. Used in UAX #29: Text Boundaries
|
|
|
|
(http://www.unicode.org/reports/tr29/)
|
2006-01-18 03:34:19 +00:00
|
|
|
@stable ICU 3.0 */
|
2006-02-07 01:54:15 +00:00
|
|
|
UCHAR_S_TERM=35,
|
2004-04-02 17:41:06 +00:00
|
|
|
/** Binary property Variation_Selector (new in Unicode 4.0.1).
|
|
|
|
Indicates all those characters that qualify as Variation Selectors.
|
|
|
|
For details on the behavior of these characters,
|
|
|
|
see StandardizedVariants.html and 15.6 Variation Selectors.
|
2006-01-18 03:34:19 +00:00
|
|
|
@stable ICU 3.0 */
|
2006-02-07 01:54:15 +00:00
|
|
|
UCHAR_VARIATION_SELECTOR=36,
|
2004-05-04 18:52:35 +00:00
|
|
|
/** Binary property NFD_Inert.
|
|
|
|
ICU-specific property for characters that are inert under NFD,
|
|
|
|
i.e., they do not interact with adjacent characters.
|
2010-01-06 23:50:03 +00:00
|
|
|
See the documentation for the Normalizer2 class and the
|
|
|
|
Normalizer2::isInert() method.
|
2006-01-18 03:34:19 +00:00
|
|
|
@stable ICU 3.0 */
|
2006-02-07 01:54:15 +00:00
|
|
|
UCHAR_NFD_INERT=37,
|
2004-05-04 18:52:35 +00:00
|
|
|
/** Binary property NFKD_Inert.
|
|
|
|
ICU-specific property for characters that are inert under NFKD,
|
|
|
|
i.e., they do not interact with adjacent characters.
|
2010-01-06 23:50:03 +00:00
|
|
|
See the documentation for the Normalizer2 class and the
|
|
|
|
Normalizer2::isInert() method.
|
2006-01-18 03:34:19 +00:00
|
|
|
@stable ICU 3.0 */
|
2006-02-07 01:54:15 +00:00
|
|
|
UCHAR_NFKD_INERT=38,
|
2004-05-04 18:52:35 +00:00
|
|
|
/** Binary property NFC_Inert.
|
|
|
|
ICU-specific property for characters that are inert under NFC,
|
|
|
|
i.e., they do not interact with adjacent characters.
|
2010-01-06 23:50:03 +00:00
|
|
|
See the documentation for the Normalizer2 class and the
|
|
|
|
Normalizer2::isInert() method.
|
2006-01-18 03:34:19 +00:00
|
|
|
@stable ICU 3.0 */
|
2006-02-07 01:54:15 +00:00
|
|
|
UCHAR_NFC_INERT=39,
|
2004-05-04 18:52:35 +00:00
|
|
|
/** Binary property NFKC_Inert.
|
|
|
|
ICU-specific property for characters that are inert under NFKC,
|
|
|
|
i.e., they do not interact with adjacent characters.
|
2010-01-06 23:50:03 +00:00
|
|
|
See the documentation for the Normalizer2 class and the
|
|
|
|
Normalizer2::isInert() method.
|
2006-01-18 03:34:19 +00:00
|
|
|
@stable ICU 3.0 */
|
2006-02-07 01:54:15 +00:00
|
|
|
UCHAR_NFKC_INERT=40,
|
2004-05-04 18:52:35 +00:00
|
|
|
/** Binary Property Segment_Starter.
|
|
|
|
ICU-specific property for characters that are starters in terms of
|
|
|
|
Unicode normalization and combining character sequences.
|
|
|
|
They have ccc=0 and do not occur in non-initial position of the
|
|
|
|
canonical decomposition of any character
|
2010-01-19 23:39:42 +00:00
|
|
|
(like a-umlaut in NFD and a Jamo T in an NFD(Hangul LVT)).
|
2004-05-04 18:52:35 +00:00
|
|
|
ICU uses this property for segmenting a string for generating a set of
|
|
|
|
canonically equivalent strings, e.g. for canonical closure while
|
|
|
|
processing collation tailoring rules.
|
2006-01-18 03:34:19 +00:00
|
|
|
@stable ICU 3.0 */
|
2006-02-07 01:54:15 +00:00
|
|
|
UCHAR_SEGMENT_STARTER=41,
|
2005-01-10 18:02:54 +00:00
|
|
|
/** Binary property Pattern_Syntax (new in Unicode 4.1).
|
|
|
|
See UAX #31 Identifier and Pattern Syntax
|
|
|
|
(http://www.unicode.org/reports/tr31/)
|
2007-08-19 08:59:28 +00:00
|
|
|
@stable ICU 3.4 */
|
2006-02-07 01:54:15 +00:00
|
|
|
UCHAR_PATTERN_SYNTAX=42,
|
2005-01-10 18:02:54 +00:00
|
|
|
/** Binary property Pattern_White_Space (new in Unicode 4.1).
|
|
|
|
See UAX #31 Identifier and Pattern Syntax
|
|
|
|
(http://www.unicode.org/reports/tr31/)
|
2007-08-19 08:59:28 +00:00
|
|
|
@stable ICU 3.4 */
|
2006-02-07 01:54:15 +00:00
|
|
|
UCHAR_PATTERN_WHITE_SPACE=43,
|
2005-05-28 22:54:36 +00:00
|
|
|
/** Binary property alnum (a C/POSIX character class).
|
|
|
|
Implemented according to the UTS #18 Annex C Standard Recommendation.
|
|
|
|
See the uchar.h file documentation.
|
2007-08-19 08:59:28 +00:00
|
|
|
@stable ICU 3.4 */
|
2006-02-07 01:54:15 +00:00
|
|
|
UCHAR_POSIX_ALNUM=44,
|
2005-05-28 22:54:36 +00:00
|
|
|
/** Binary property blank (a C/POSIX character class).
|
|
|
|
Implemented according to the UTS #18 Annex C Standard Recommendation.
|
|
|
|
See the uchar.h file documentation.
|
2007-08-19 08:59:28 +00:00
|
|
|
@stable ICU 3.4 */
|
2006-02-07 01:54:15 +00:00
|
|
|
UCHAR_POSIX_BLANK=45,
|
2005-05-28 22:54:36 +00:00
|
|
|
/** Binary property graph (a C/POSIX character class).
|
|
|
|
Implemented according to the UTS #18 Annex C Standard Recommendation.
|
|
|
|
See the uchar.h file documentation.
|
2007-08-19 08:59:28 +00:00
|
|
|
@stable ICU 3.4 */
|
2006-02-07 01:54:15 +00:00
|
|
|
UCHAR_POSIX_GRAPH=46,
|
2005-05-28 22:54:36 +00:00
|
|
|
/** Binary property print (a C/POSIX character class).
|
|
|
|
Implemented according to the UTS #18 Annex C Standard Recommendation.
|
|
|
|
See the uchar.h file documentation.
|
2007-08-19 08:59:28 +00:00
|
|
|
@stable ICU 3.4 */
|
2006-02-07 01:54:15 +00:00
|
|
|
UCHAR_POSIX_PRINT=47,
|
2005-05-28 22:54:36 +00:00
|
|
|
/** Binary property xdigit (a C/POSIX character class).
|
|
|
|
Implemented according to the UTS #18 Annex C Standard Recommendation.
|
|
|
|
See the uchar.h file documentation.
|
2007-08-19 08:59:28 +00:00
|
|
|
@stable ICU 3.4 */
|
2006-02-07 01:54:15 +00:00
|
|
|
UCHAR_POSIX_XDIGIT=48,
|
2010-09-21 00:12:49 +00:00
|
|
|
/** Binary property Cased. For Lowercase, Uppercase and Titlecase characters. @stable ICU 4.4 */
|
2009-11-13 19:25:21 +00:00
|
|
|
UCHAR_CASED=49,
|
2010-09-21 00:12:49 +00:00
|
|
|
/** Binary property Case_Ignorable. Used in context-sensitive case mappings. @stable ICU 4.4 */
|
2009-11-13 19:25:21 +00:00
|
|
|
UCHAR_CASE_IGNORABLE=50,
|
2010-09-21 00:12:49 +00:00
|
|
|
/** Binary property Changes_When_Lowercased. @stable ICU 4.4 */
|
2009-11-13 19:25:21 +00:00
|
|
|
UCHAR_CHANGES_WHEN_LOWERCASED=51,
|
2010-09-21 00:12:49 +00:00
|
|
|
/** Binary property Changes_When_Uppercased. @stable ICU 4.4 */
|
2009-11-13 19:25:21 +00:00
|
|
|
UCHAR_CHANGES_WHEN_UPPERCASED=52,
|
2010-09-21 00:12:49 +00:00
|
|
|
/** Binary property Changes_When_Titlecased. @stable ICU 4.4 */
|
2009-11-13 19:25:21 +00:00
|
|
|
UCHAR_CHANGES_WHEN_TITLECASED=53,
|
2010-09-21 00:12:49 +00:00
|
|
|
/** Binary property Changes_When_Casefolded. @stable ICU 4.4 */
|
2009-11-13 19:25:21 +00:00
|
|
|
UCHAR_CHANGES_WHEN_CASEFOLDED=54,
|
2010-09-21 00:12:49 +00:00
|
|
|
/** Binary property Changes_When_Casemapped. @stable ICU 4.4 */
|
2009-11-13 19:25:21 +00:00
|
|
|
UCHAR_CHANGES_WHEN_CASEMAPPED=55,
|
2010-09-21 00:12:49 +00:00
|
|
|
/** Binary property Changes_When_NFKC_Casefolded. @stable ICU 4.4 */
|
2010-01-06 23:50:03 +00:00
|
|
|
UCHAR_CHANGES_WHEN_NFKC_CASEFOLDED=56,
|
2003-02-11 01:59:32 +00:00
|
|
|
/** One more than the last constant for binary Unicode properties. @stable ICU 2.1 */
|
2010-01-06 23:50:03 +00:00
|
|
|
UCHAR_BINARY_LIMIT=57,
|
2002-07-04 00:38:51 +00:00
|
|
|
|
|
|
|
/** Enumerated property Bidi_Class.
|
2003-11-18 02:37:24 +00:00
|
|
|
Same as u_charDirection, returns UCharDirection values. @stable ICU 2.2 */
|
2002-11-22 19:36:55 +00:00
|
|
|
UCHAR_BIDI_CLASS=0x1000,
|
2003-11-18 02:37:24 +00:00
|
|
|
/** First constant for enumerated/integer Unicode properties. @stable ICU 2.2 */
|
2002-11-22 19:36:55 +00:00
|
|
|
UCHAR_INT_START=UCHAR_BIDI_CLASS,
|
2002-07-04 00:38:51 +00:00
|
|
|
/** Enumerated property Block.
|
2003-11-18 02:37:24 +00:00
|
|
|
Same as ublock_getCode, returns UBlockCode values. @stable ICU 2.2 */
|
2006-02-07 01:54:15 +00:00
|
|
|
UCHAR_BLOCK=0x1001,
|
2002-07-04 00:38:51 +00:00
|
|
|
/** Enumerated property Canonical_Combining_Class.
|
2003-11-18 02:37:24 +00:00
|
|
|
Same as u_getCombiningClass, returns 8-bit numeric values. @stable ICU 2.2 */
|
2006-02-07 01:54:15 +00:00
|
|
|
UCHAR_CANONICAL_COMBINING_CLASS=0x1002,
|
2002-07-04 16:46:36 +00:00
|
|
|
/** Enumerated property Decomposition_Type.
|
2003-11-18 02:37:24 +00:00
|
|
|
Returns UDecompositionType values. @stable ICU 2.2 */
|
2006-02-07 01:54:15 +00:00
|
|
|
UCHAR_DECOMPOSITION_TYPE=0x1003,
|
2002-07-04 00:38:51 +00:00
|
|
|
/** Enumerated property East_Asian_Width.
|
|
|
|
See http://www.unicode.org/reports/tr11/
|
2003-11-18 02:37:24 +00:00
|
|
|
Returns UEastAsianWidth values. @stable ICU 2.2 */
|
2006-02-07 01:54:15 +00:00
|
|
|
UCHAR_EAST_ASIAN_WIDTH=0x1004,
|
2002-07-04 00:38:51 +00:00
|
|
|
/** Enumerated property General_Category.
|
2003-11-18 02:37:24 +00:00
|
|
|
Same as u_charType, returns UCharCategory values. @stable ICU 2.2 */
|
2006-02-07 01:54:15 +00:00
|
|
|
UCHAR_GENERAL_CATEGORY=0x1005,
|
2002-07-04 16:46:36 +00:00
|
|
|
/** Enumerated property Joining_Group.
|
2003-11-18 02:37:24 +00:00
|
|
|
Returns UJoiningGroup values. @stable ICU 2.2 */
|
2006-02-07 01:54:15 +00:00
|
|
|
UCHAR_JOINING_GROUP=0x1006,
|
2002-07-04 16:46:36 +00:00
|
|
|
/** Enumerated property Joining_Type.
|
2003-11-18 02:37:24 +00:00
|
|
|
Returns UJoiningType values. @stable ICU 2.2 */
|
2006-02-07 01:54:15 +00:00
|
|
|
UCHAR_JOINING_TYPE=0x1007,
|
2002-07-04 16:46:36 +00:00
|
|
|
/** Enumerated property Line_Break.
|
2003-11-18 02:37:24 +00:00
|
|
|
Returns ULineBreak values. @stable ICU 2.2 */
|
2006-02-07 01:54:15 +00:00
|
|
|
UCHAR_LINE_BREAK=0x1008,
|
2002-07-04 00:38:51 +00:00
|
|
|
/** Enumerated property Numeric_Type.
|
2003-11-18 02:37:24 +00:00
|
|
|
Returns UNumericType values. @stable ICU 2.2 */
|
2006-02-07 01:54:15 +00:00
|
|
|
UCHAR_NUMERIC_TYPE=0x1009,
|
2002-07-04 00:38:51 +00:00
|
|
|
/** Enumerated property Script.
|
2003-11-18 02:37:24 +00:00
|
|
|
Same as uscript_getScript, returns UScriptCode values. @stable ICU 2.2 */
|
2006-02-07 01:54:15 +00:00
|
|
|
UCHAR_SCRIPT=0x100A,
|
2003-03-08 02:00:06 +00:00
|
|
|
/** Enumerated property Hangul_Syllable_Type, new in Unicode 4.
|
2004-11-02 07:28:07 +00:00
|
|
|
Returns UHangulSyllableType values. @stable ICU 2.6 */
|
2006-02-07 01:54:15 +00:00
|
|
|
UCHAR_HANGUL_SYLLABLE_TYPE=0x100B,
|
2004-04-07 00:28:39 +00:00
|
|
|
/** Enumerated property NFD_Quick_Check.
|
2006-01-18 03:34:19 +00:00
|
|
|
Returns UNormalizationCheckResult values. @stable ICU 3.0 */
|
2006-02-07 01:54:15 +00:00
|
|
|
UCHAR_NFD_QUICK_CHECK=0x100C,
|
2004-04-07 00:28:39 +00:00
|
|
|
/** Enumerated property NFKD_Quick_Check.
|
2006-01-18 03:34:19 +00:00
|
|
|
Returns UNormalizationCheckResult values. @stable ICU 3.0 */
|
2006-02-07 01:54:15 +00:00
|
|
|
UCHAR_NFKD_QUICK_CHECK=0x100D,
|
2004-04-07 00:28:39 +00:00
|
|
|
/** Enumerated property NFC_Quick_Check.
|
2006-01-18 03:34:19 +00:00
|
|
|
Returns UNormalizationCheckResult values. @stable ICU 3.0 */
|
2006-02-07 01:54:15 +00:00
|
|
|
UCHAR_NFC_QUICK_CHECK=0x100E,
|
2004-04-07 00:28:39 +00:00
|
|
|
/** Enumerated property NFKC_Quick_Check.
|
2006-01-18 03:34:19 +00:00
|
|
|
Returns UNormalizationCheckResult values. @stable ICU 3.0 */
|
2006-02-07 01:54:15 +00:00
|
|
|
UCHAR_NFKC_QUICK_CHECK=0x100F,
|
2004-04-07 02:57:06 +00:00
|
|
|
/** Enumerated property Lead_Canonical_Combining_Class.
|
|
|
|
ICU-specific property for the ccc of the first code point
|
|
|
|
of the decomposition, or lccc(c)=ccc(NFD(c)[0]).
|
|
|
|
Useful for checking for canonically ordered text;
|
|
|
|
see UNORM_FCD and http://www.unicode.org/notes/tn5/#FCD .
|
2006-01-18 03:34:19 +00:00
|
|
|
Returns 8-bit numeric values like UCHAR_CANONICAL_COMBINING_CLASS. @stable ICU 3.0 */
|
2006-02-07 01:54:15 +00:00
|
|
|
UCHAR_LEAD_CANONICAL_COMBINING_CLASS=0x1010,
|
2004-04-07 02:57:06 +00:00
|
|
|
/** Enumerated property Trail_Canonical_Combining_Class.
|
|
|
|
ICU-specific property for the ccc of the last code point
|
|
|
|
of the decomposition, or tccc(c)=ccc(NFD(c)[last]).
|
|
|
|
Useful for checking for canonically ordered text;
|
|
|
|
see UNORM_FCD and http://www.unicode.org/notes/tn5/#FCD .
|
2006-01-18 03:34:19 +00:00
|
|
|
Returns 8-bit numeric values like UCHAR_CANONICAL_COMBINING_CLASS. @stable ICU 3.0 */
|
2006-02-07 01:54:15 +00:00
|
|
|
UCHAR_TRAIL_CANONICAL_COMBINING_CLASS=0x1011,
|
2005-01-10 18:02:54 +00:00
|
|
|
/** Enumerated property Grapheme_Cluster_Break (new in Unicode 4.1).
|
|
|
|
Used in UAX #29: Text Boundaries
|
|
|
|
(http://www.unicode.org/reports/tr29/)
|
2007-08-19 08:59:28 +00:00
|
|
|
Returns UGraphemeClusterBreak values. @stable ICU 3.4 */
|
2006-02-07 01:54:15 +00:00
|
|
|
UCHAR_GRAPHEME_CLUSTER_BREAK=0x1012,
|
2005-01-10 18:02:54 +00:00
|
|
|
/** Enumerated property Sentence_Break (new in Unicode 4.1).
|
|
|
|
Used in UAX #29: Text Boundaries
|
|
|
|
(http://www.unicode.org/reports/tr29/)
|
2007-08-19 08:59:28 +00:00
|
|
|
Returns USentenceBreak values. @stable ICU 3.4 */
|
2006-02-07 01:54:15 +00:00
|
|
|
UCHAR_SENTENCE_BREAK=0x1013,
|
2005-01-10 18:02:54 +00:00
|
|
|
/** Enumerated property Word_Break (new in Unicode 4.1).
|
|
|
|
Used in UAX #29: Text Boundaries
|
|
|
|
(http://www.unicode.org/reports/tr29/)
|
2007-08-19 08:59:28 +00:00
|
|
|
Returns UWordBreakValues values. @stable ICU 3.4 */
|
2006-02-07 01:54:15 +00:00
|
|
|
UCHAR_WORD_BREAK=0x1014,
|
2003-11-18 02:37:24 +00:00
|
|
|
/** One more than the last constant for enumerated/integer Unicode properties. @stable ICU 2.2 */
|
2006-02-07 01:54:15 +00:00
|
|
|
UCHAR_INT_LIMIT=0x1015,
|
2002-10-30 18:24:53 +00:00
|
|
|
|
2003-01-22 17:57:04 +00:00
|
|
|
/** Bitmask property General_Category_Mask.
|
|
|
|
This is the General_Category property returned as a bit mask.
|
2002-12-10 00:33:45 +00:00
|
|
|
When used in u_getIntPropertyValue(c), same as U_MASK(u_charType(c)),
|
|
|
|
returns bit masks for UCharCategory values where exactly one bit is set.
|
|
|
|
When used with u_getPropertyValueName() and u_getPropertyValueEnum(),
|
|
|
|
a multi-bit mask is used for sets of categories like "Letters".
|
|
|
|
Mask values should be cast to uint32_t.
|
2004-03-26 19:42:04 +00:00
|
|
|
@stable ICU 2.4 */
|
2002-12-10 00:33:45 +00:00
|
|
|
UCHAR_GENERAL_CATEGORY_MASK=0x2000,
|
2004-03-26 19:42:04 +00:00
|
|
|
/** First constant for bit-mask Unicode properties. @stable ICU 2.4 */
|
2002-12-10 00:33:45 +00:00
|
|
|
UCHAR_MASK_START=UCHAR_GENERAL_CATEGORY_MASK,
|
2004-03-26 19:42:04 +00:00
|
|
|
/** One more than the last constant for bit-mask Unicode properties. @stable ICU 2.4 */
|
2006-02-07 01:54:15 +00:00
|
|
|
UCHAR_MASK_LIMIT=0x2001,
|
2002-12-10 00:33:45 +00:00
|
|
|
|
2002-10-30 18:24:53 +00:00
|
|
|
/** Double property Numeric_Value.
|
2004-03-26 19:42:04 +00:00
|
|
|
Corresponds to u_getNumericValue. @stable ICU 2.4 */
|
2002-12-10 00:33:45 +00:00
|
|
|
UCHAR_NUMERIC_VALUE=0x3000,
|
2004-03-26 19:42:04 +00:00
|
|
|
/** First constant for double Unicode properties. @stable ICU 2.4 */
|
2002-11-22 19:36:55 +00:00
|
|
|
UCHAR_DOUBLE_START=UCHAR_NUMERIC_VALUE,
|
2004-03-26 19:42:04 +00:00
|
|
|
/** One more than the last constant for double Unicode properties. @stable ICU 2.4 */
|
2006-02-07 01:54:15 +00:00
|
|
|
UCHAR_DOUBLE_LIMIT=0x3001,
|
2002-10-30 18:24:53 +00:00
|
|
|
|
|
|
|
/** String property Age.
|
2004-03-26 19:42:04 +00:00
|
|
|
Corresponds to u_charAge. @stable ICU 2.4 */
|
2002-12-10 00:33:45 +00:00
|
|
|
UCHAR_AGE=0x4000,
|
2004-03-26 19:42:04 +00:00
|
|
|
/** First constant for string Unicode properties. @stable ICU 2.4 */
|
2002-11-22 19:36:55 +00:00
|
|
|
UCHAR_STRING_START=UCHAR_AGE,
|
2002-10-30 18:24:53 +00:00
|
|
|
/** String property Bidi_Mirroring_Glyph.
|
2004-03-26 19:42:04 +00:00
|
|
|
Corresponds to u_charMirror. @stable ICU 2.4 */
|
2006-02-07 01:54:15 +00:00
|
|
|
UCHAR_BIDI_MIRRORING_GLYPH=0x4001,
|
2002-10-30 18:24:53 +00:00
|
|
|
/** String property Case_Folding.
|
2004-03-26 19:42:04 +00:00
|
|
|
Corresponds to u_strFoldCase in ustring.h. @stable ICU 2.4 */
|
2006-02-07 01:54:15 +00:00
|
|
|
UCHAR_CASE_FOLDING=0x4002,
|
2011-12-15 21:43:35 +00:00
|
|
|
/** Deprecated string property ISO_Comment.
|
|
|
|
Corresponds to u_getISOComment. @deprecated ICU 49 */
|
2006-02-07 01:54:15 +00:00
|
|
|
UCHAR_ISO_COMMENT=0x4003,
|
2002-10-30 18:24:53 +00:00
|
|
|
/** String property Lowercase_Mapping.
|
2004-03-26 19:42:04 +00:00
|
|
|
Corresponds to u_strToLower in ustring.h. @stable ICU 2.4 */
|
2006-02-07 01:54:15 +00:00
|
|
|
UCHAR_LOWERCASE_MAPPING=0x4004,
|
2002-10-30 18:24:53 +00:00
|
|
|
/** String property Name.
|
2004-03-26 19:42:04 +00:00
|
|
|
Corresponds to u_charName. @stable ICU 2.4 */
|
2006-02-07 01:54:15 +00:00
|
|
|
UCHAR_NAME=0x4005,
|
2002-10-30 18:24:53 +00:00
|
|
|
/** String property Simple_Case_Folding.
|
2004-03-26 19:42:04 +00:00
|
|
|
Corresponds to u_foldCase. @stable ICU 2.4 */
|
2006-02-07 01:54:15 +00:00
|
|
|
UCHAR_SIMPLE_CASE_FOLDING=0x4006,
|
2002-10-30 18:24:53 +00:00
|
|
|
/** String property Simple_Lowercase_Mapping.
|
2004-03-26 19:42:04 +00:00
|
|
|
Corresponds to u_tolower. @stable ICU 2.4 */
|
2006-02-07 01:54:15 +00:00
|
|
|
UCHAR_SIMPLE_LOWERCASE_MAPPING=0x4007,
|
2002-10-30 18:24:53 +00:00
|
|
|
/** String property Simple_Titlecase_Mapping.
|
2004-03-26 19:42:04 +00:00
|
|
|
Corresponds to u_totitle. @stable ICU 2.4 */
|
2006-02-07 01:54:15 +00:00
|
|
|
UCHAR_SIMPLE_TITLECASE_MAPPING=0x4008,
|
2002-10-30 18:24:53 +00:00
|
|
|
/** String property Simple_Uppercase_Mapping.
|
2004-03-26 19:42:04 +00:00
|
|
|
Corresponds to u_toupper. @stable ICU 2.4 */
|
2006-02-07 01:54:15 +00:00
|
|
|
UCHAR_SIMPLE_UPPERCASE_MAPPING=0x4009,
|
2002-10-30 18:24:53 +00:00
|
|
|
/** String property Titlecase_Mapping.
|
2004-03-26 19:42:04 +00:00
|
|
|
Corresponds to u_strToTitle in ustring.h. @stable ICU 2.4 */
|
2006-02-07 01:54:15 +00:00
|
|
|
UCHAR_TITLECASE_MAPPING=0x400A,
|
2002-10-30 18:24:53 +00:00
|
|
|
/** String property Unicode_1_Name.
|
2011-12-15 21:43:35 +00:00
|
|
|
This property is of little practical value.
|
|
|
|
Beginning with ICU 49, ICU APIs return an empty string for this property.
|
|
|
|
Corresponds to u_charName(U_UNICODE_10_CHAR_NAME). @deprecated ICU 49 */
|
2006-02-07 01:54:15 +00:00
|
|
|
UCHAR_UNICODE_1_NAME=0x400B,
|
2002-10-30 18:24:53 +00:00
|
|
|
/** String property Uppercase_Mapping.
|
2004-03-26 19:42:04 +00:00
|
|
|
Corresponds to u_strToUpper in ustring.h. @stable ICU 2.4 */
|
2006-02-07 01:54:15 +00:00
|
|
|
UCHAR_UPPERCASE_MAPPING=0x400C,
|
2004-03-26 19:42:04 +00:00
|
|
|
/** One more than the last constant for string Unicode properties. @stable ICU 2.4 */
|
2006-02-07 01:54:15 +00:00
|
|
|
UCHAR_STRING_LIMIT=0x400D,
|
2002-10-30 18:24:53 +00:00
|
|
|
|
2011-08-01 02:20:46 +00:00
|
|
|
#ifndef U_HIDE_DRAFT_API
|
2010-09-21 00:12:49 +00:00
|
|
|
/** Provisional property Script_Extensions (new in Unicode 6.0).
|
|
|
|
As a provisional property, it may be modified or removed
|
|
|
|
in future versions of the Unicode Standard, and thus in ICU.
|
|
|
|
Some characters are commonly used in multiple scripts.
|
|
|
|
For more information, see UAX #24: http://www.unicode.org/reports/tr24/.
|
|
|
|
Corresponds to uscript_hasScript and uscript_getScriptExtensions in uscript.h.
|
|
|
|
@draft ICU 4.6 */
|
|
|
|
UCHAR_SCRIPT_EXTENSIONS=0x7000,
|
|
|
|
/** First constant for Unicode properties with unusual value types. @draft ICU 4.6 */
|
|
|
|
UCHAR_OTHER_PROPERTY_START=UCHAR_SCRIPT_EXTENSIONS,
|
|
|
|
/** One more than the last constant for Unicode properties with unusual value types.
|
|
|
|
* @draft ICU 4.6 */
|
|
|
|
UCHAR_OTHER_PROPERTY_LIMIT=0x7001,
|
2011-08-01 02:20:46 +00:00
|
|
|
#endif /* U_HIDE_DRAFT_API */
|
2010-09-21 00:12:49 +00:00
|
|
|
|
2004-03-26 19:42:04 +00:00
|
|
|
/** Represents a nonexistent or invalid property or property value. @stable ICU 2.4 */
|
2002-10-30 18:24:53 +00:00
|
|
|
UCHAR_INVALID_CODE = -1
|
2002-08-21 19:12:24 +00:00
|
|
|
} UProperty;
|
2002-03-06 23:31:11 +00:00
|
|
|
|
2001-10-11 22:11:38 +00:00
|
|
|
/**
|
|
|
|
* Data for enumerated Unicode general category types.
|
|
|
|
* See http://www.unicode.org/Public/UNIDATA/UnicodeData.html .
|
2002-12-04 23:39:56 +00:00
|
|
|
* @stable ICU 2.0
|
1999-12-28 23:39:02 +00:00
|
|
|
*/
|
2005-06-28 22:23:05 +00:00
|
|
|
typedef enum UCharCategory
|
|
|
|
{
|
2011-12-23 04:20:35 +00:00
|
|
|
/*
|
|
|
|
* Note: UCharCategory constants and their API comments are parsed by preparseucd.py.
|
|
|
|
* It matches pairs of lines like
|
|
|
|
* / ** <Unicode 2-letter General_Category value> comment... * /
|
|
|
|
* U_<[A-Z_]+> = <integer>,
|
|
|
|
*/
|
2002-10-30 18:24:53 +00:00
|
|
|
|
2002-12-05 00:30:16 +00:00
|
|
|
/** Non-category for unassigned and non-character code points. @stable ICU 2.0 */
|
2001-03-21 20:44:20 +00:00
|
|
|
U_UNASSIGNED = 0,
|
2002-12-05 00:30:16 +00:00
|
|
|
/** Cn "Other, Not Assigned (no characters in [UnicodeData.txt] have this property)" (same as U_UNASSIGNED!) @stable ICU 2.0 */
|
2001-10-11 22:11:38 +00:00
|
|
|
U_GENERAL_OTHER_TYPES = 0,
|
2002-12-05 00:30:16 +00:00
|
|
|
/** Lu @stable ICU 2.0 */
|
1999-12-28 23:39:02 +00:00
|
|
|
U_UPPERCASE_LETTER = 1,
|
2002-12-05 00:30:16 +00:00
|
|
|
/** Ll @stable ICU 2.0 */
|
1999-12-28 23:39:02 +00:00
|
|
|
U_LOWERCASE_LETTER = 2,
|
2002-12-05 00:30:16 +00:00
|
|
|
/** Lt @stable ICU 2.0 */
|
1999-12-28 23:39:02 +00:00
|
|
|
U_TITLECASE_LETTER = 3,
|
2002-12-05 00:30:16 +00:00
|
|
|
/** Lm @stable ICU 2.0 */
|
1999-12-28 23:39:02 +00:00
|
|
|
U_MODIFIER_LETTER = 4,
|
2002-12-05 00:30:16 +00:00
|
|
|
/** Lo @stable ICU 2.0 */
|
1999-12-28 23:39:02 +00:00
|
|
|
U_OTHER_LETTER = 5,
|
2002-12-05 00:30:16 +00:00
|
|
|
/** Mn @stable ICU 2.0 */
|
1999-12-28 23:39:02 +00:00
|
|
|
U_NON_SPACING_MARK = 6,
|
2002-12-05 00:30:16 +00:00
|
|
|
/** Me @stable ICU 2.0 */
|
1999-12-28 23:39:02 +00:00
|
|
|
U_ENCLOSING_MARK = 7,
|
2002-12-05 00:30:16 +00:00
|
|
|
/** Mc @stable ICU 2.0 */
|
1999-12-28 23:39:02 +00:00
|
|
|
U_COMBINING_SPACING_MARK = 8,
|
2002-12-05 00:30:16 +00:00
|
|
|
/** Nd @stable ICU 2.0 */
|
1999-12-28 23:39:02 +00:00
|
|
|
U_DECIMAL_DIGIT_NUMBER = 9,
|
2002-12-05 00:30:16 +00:00
|
|
|
/** Nl @stable ICU 2.0 */
|
1999-12-28 23:39:02 +00:00
|
|
|
U_LETTER_NUMBER = 10,
|
2002-12-05 00:30:16 +00:00
|
|
|
/** No @stable ICU 2.0 */
|
1999-12-28 23:39:02 +00:00
|
|
|
U_OTHER_NUMBER = 11,
|
2002-12-05 00:30:16 +00:00
|
|
|
/** Zs @stable ICU 2.0 */
|
1999-12-28 23:39:02 +00:00
|
|
|
U_SPACE_SEPARATOR = 12,
|
2002-12-05 00:30:16 +00:00
|
|
|
/** Zl @stable ICU 2.0 */
|
1999-12-28 23:39:02 +00:00
|
|
|
U_LINE_SEPARATOR = 13,
|
2002-12-05 00:30:16 +00:00
|
|
|
/** Zp @stable ICU 2.0 */
|
1999-12-28 23:39:02 +00:00
|
|
|
U_PARAGRAPH_SEPARATOR = 14,
|
2002-12-05 00:30:16 +00:00
|
|
|
/** Cc @stable ICU 2.0 */
|
1999-12-28 23:39:02 +00:00
|
|
|
U_CONTROL_CHAR = 15,
|
2002-12-05 00:30:16 +00:00
|
|
|
/** Cf @stable ICU 2.0 */
|
1999-12-28 23:39:02 +00:00
|
|
|
U_FORMAT_CHAR = 16,
|
2002-12-05 00:30:16 +00:00
|
|
|
/** Co @stable ICU 2.0 */
|
1999-12-28 23:39:02 +00:00
|
|
|
U_PRIVATE_USE_CHAR = 17,
|
2002-12-05 00:30:16 +00:00
|
|
|
/** Cs @stable ICU 2.0 */
|
1999-12-28 23:39:02 +00:00
|
|
|
U_SURROGATE = 18,
|
2002-12-05 00:30:16 +00:00
|
|
|
/** Pd @stable ICU 2.0 */
|
1999-12-28 23:39:02 +00:00
|
|
|
U_DASH_PUNCTUATION = 19,
|
2002-12-05 00:30:16 +00:00
|
|
|
/** Ps @stable ICU 2.0 */
|
1999-12-28 23:39:02 +00:00
|
|
|
U_START_PUNCTUATION = 20,
|
2002-12-05 00:30:16 +00:00
|
|
|
/** Pe @stable ICU 2.0 */
|
1999-12-28 23:39:02 +00:00
|
|
|
U_END_PUNCTUATION = 21,
|
2002-12-05 00:30:16 +00:00
|
|
|
/** Pc @stable ICU 2.0 */
|
1999-12-28 23:39:02 +00:00
|
|
|
U_CONNECTOR_PUNCTUATION = 22,
|
2002-12-05 00:30:16 +00:00
|
|
|
/** Po @stable ICU 2.0 */
|
1999-12-28 23:39:02 +00:00
|
|
|
U_OTHER_PUNCTUATION = 23,
|
2002-12-05 00:30:16 +00:00
|
|
|
/** Sm @stable ICU 2.0 */
|
1999-12-28 23:39:02 +00:00
|
|
|
U_MATH_SYMBOL = 24,
|
2002-12-05 00:30:16 +00:00
|
|
|
/** Sc @stable ICU 2.0 */
|
1999-12-28 23:39:02 +00:00
|
|
|
U_CURRENCY_SYMBOL = 25,
|
2002-12-05 00:30:16 +00:00
|
|
|
/** Sk @stable ICU 2.0 */
|
1999-12-28 23:39:02 +00:00
|
|
|
U_MODIFIER_SYMBOL = 26,
|
2002-12-05 00:30:16 +00:00
|
|
|
/** So @stable ICU 2.0 */
|
1999-12-28 23:39:02 +00:00
|
|
|
U_OTHER_SYMBOL = 27,
|
2002-12-05 00:30:16 +00:00
|
|
|
/** Pi @stable ICU 2.0 */
|
1999-12-28 23:39:02 +00:00
|
|
|
U_INITIAL_PUNCTUATION = 28,
|
2002-12-05 00:30:16 +00:00
|
|
|
/** Pf @stable ICU 2.0 */
|
1999-12-28 23:39:02 +00:00
|
|
|
U_FINAL_PUNCTUATION = 29,
|
2002-12-05 00:30:16 +00:00
|
|
|
/** One higher than the last enum UCharCategory constant. @stable ICU 2.0 */
|
1999-12-28 23:39:02 +00:00
|
|
|
U_CHAR_CATEGORY_COUNT
|
2002-08-21 19:12:24 +00:00
|
|
|
} UCharCategory;
|
2001-11-13 22:47:47 +00:00
|
|
|
|
2002-03-13 23:31:12 +00:00
|
|
|
/**
|
|
|
|
* U_GC_XX_MASK constants are bit flags corresponding to Unicode
|
|
|
|
* general category values.
|
|
|
|
* For each category, the nth bit is set if the numeric value of the
|
|
|
|
* corresponding UCharCategory constant is n.
|
|
|
|
*
|
|
|
|
* There are also some U_GC_Y_MASK constants for groups of general categories
|
2002-12-11 22:49:18 +00:00
|
|
|
* like L for all letter categories.
|
2002-03-13 23:31:12 +00:00
|
|
|
*
|
|
|
|
* @see u_charType
|
|
|
|
* @see U_GET_GC_MASK
|
|
|
|
* @see UCharCategory
|
2003-02-11 01:59:32 +00:00
|
|
|
* @stable ICU 2.1
|
2002-03-13 23:31:12 +00:00
|
|
|
*/
|
|
|
|
#define U_GC_CN_MASK U_MASK(U_GENERAL_OTHER_TYPES)
|
|
|
|
|
2003-02-11 01:59:32 +00:00
|
|
|
/** Mask constant for a UCharCategory. @stable ICU 2.1 */
|
2002-03-13 23:31:12 +00:00
|
|
|
#define U_GC_LU_MASK U_MASK(U_UPPERCASE_LETTER)
|
2003-02-11 01:59:32 +00:00
|
|
|
/** Mask constant for a UCharCategory. @stable ICU 2.1 */
|
2002-03-13 23:31:12 +00:00
|
|
|
#define U_GC_LL_MASK U_MASK(U_LOWERCASE_LETTER)
|
2003-02-11 01:59:32 +00:00
|
|
|
/** Mask constant for a UCharCategory. @stable ICU 2.1 */
|
2002-03-13 23:31:12 +00:00
|
|
|
#define U_GC_LT_MASK U_MASK(U_TITLECASE_LETTER)
|
2003-02-11 01:59:32 +00:00
|
|
|
/** Mask constant for a UCharCategory. @stable ICU 2.1 */
|
2002-03-13 23:31:12 +00:00
|
|
|
#define U_GC_LM_MASK U_MASK(U_MODIFIER_LETTER)
|
2003-02-11 01:59:32 +00:00
|
|
|
/** Mask constant for a UCharCategory. @stable ICU 2.1 */
|
2002-03-13 23:31:12 +00:00
|
|
|
#define U_GC_LO_MASK U_MASK(U_OTHER_LETTER)
|
|
|
|
|
2003-02-11 01:59:32 +00:00
|
|
|
/** Mask constant for a UCharCategory. @stable ICU 2.1 */
|
2002-03-13 23:31:12 +00:00
|
|
|
#define U_GC_MN_MASK U_MASK(U_NON_SPACING_MARK)
|
2003-02-11 01:59:32 +00:00
|
|
|
/** Mask constant for a UCharCategory. @stable ICU 2.1 */
|
2002-03-13 23:31:12 +00:00
|
|
|
#define U_GC_ME_MASK U_MASK(U_ENCLOSING_MARK)
|
2003-02-11 01:59:32 +00:00
|
|
|
/** Mask constant for a UCharCategory. @stable ICU 2.1 */
|
2002-03-13 23:31:12 +00:00
|
|
|
#define U_GC_MC_MASK U_MASK(U_COMBINING_SPACING_MARK)
|
|
|
|
|
2003-02-11 01:59:32 +00:00
|
|
|
/** Mask constant for a UCharCategory. @stable ICU 2.1 */
|
2002-03-13 23:31:12 +00:00
|
|
|
#define U_GC_ND_MASK U_MASK(U_DECIMAL_DIGIT_NUMBER)
|
2003-02-11 01:59:32 +00:00
|
|
|
/** Mask constant for a UCharCategory. @stable ICU 2.1 */
|
2002-03-13 23:31:12 +00:00
|
|
|
#define U_GC_NL_MASK U_MASK(U_LETTER_NUMBER)
|
2003-02-11 01:59:32 +00:00
|
|
|
/** Mask constant for a UCharCategory. @stable ICU 2.1 */
|
2002-03-13 23:31:12 +00:00
|
|
|
#define U_GC_NO_MASK U_MASK(U_OTHER_NUMBER)
|
|
|
|
|
2003-02-11 01:59:32 +00:00
|
|
|
/** Mask constant for a UCharCategory. @stable ICU 2.1 */
|
2002-03-13 23:31:12 +00:00
|
|
|
#define U_GC_ZS_MASK U_MASK(U_SPACE_SEPARATOR)
|
2003-02-11 01:59:32 +00:00
|
|
|
/** Mask constant for a UCharCategory. @stable ICU 2.1 */
|
2002-03-13 23:31:12 +00:00
|
|
|
#define U_GC_ZL_MASK U_MASK(U_LINE_SEPARATOR)
|
2003-02-11 01:59:32 +00:00
|
|
|
/** Mask constant for a UCharCategory. @stable ICU 2.1 */
|
2002-03-13 23:31:12 +00:00
|
|
|
#define U_GC_ZP_MASK U_MASK(U_PARAGRAPH_SEPARATOR)
|
|
|
|
|
2003-02-11 01:59:32 +00:00
|
|
|
/** Mask constant for a UCharCategory. @stable ICU 2.1 */
|
2002-03-13 23:31:12 +00:00
|
|
|
#define U_GC_CC_MASK U_MASK(U_CONTROL_CHAR)
|
2003-02-11 01:59:32 +00:00
|
|
|
/** Mask constant for a UCharCategory. @stable ICU 2.1 */
|
2002-03-13 23:31:12 +00:00
|
|
|
#define U_GC_CF_MASK U_MASK(U_FORMAT_CHAR)
|
2003-02-11 01:59:32 +00:00
|
|
|
/** Mask constant for a UCharCategory. @stable ICU 2.1 */
|
2002-03-13 23:31:12 +00:00
|
|
|
#define U_GC_CO_MASK U_MASK(U_PRIVATE_USE_CHAR)
|
2003-02-11 01:59:32 +00:00
|
|
|
/** Mask constant for a UCharCategory. @stable ICU 2.1 */
|
2002-03-13 23:31:12 +00:00
|
|
|
#define U_GC_CS_MASK U_MASK(U_SURROGATE)
|
|
|
|
|
2003-02-11 01:59:32 +00:00
|
|
|
/** Mask constant for a UCharCategory. @stable ICU 2.1 */
|
2002-03-13 23:31:12 +00:00
|
|
|
#define U_GC_PD_MASK U_MASK(U_DASH_PUNCTUATION)
|
2003-02-11 01:59:32 +00:00
|
|
|
/** Mask constant for a UCharCategory. @stable ICU 2.1 */
|
2002-03-13 23:31:12 +00:00
|
|
|
#define U_GC_PS_MASK U_MASK(U_START_PUNCTUATION)
|
2003-02-11 01:59:32 +00:00
|
|
|
/** Mask constant for a UCharCategory. @stable ICU 2.1 */
|
2002-03-13 23:31:12 +00:00
|
|
|
#define U_GC_PE_MASK U_MASK(U_END_PUNCTUATION)
|
2003-02-11 01:59:32 +00:00
|
|
|
/** Mask constant for a UCharCategory. @stable ICU 2.1 */
|
2002-03-13 23:31:12 +00:00
|
|
|
#define U_GC_PC_MASK U_MASK(U_CONNECTOR_PUNCTUATION)
|
2003-02-11 01:59:32 +00:00
|
|
|
/** Mask constant for a UCharCategory. @stable ICU 2.1 */
|
2002-03-13 23:31:12 +00:00
|
|
|
#define U_GC_PO_MASK U_MASK(U_OTHER_PUNCTUATION)
|
|
|
|
|
2003-02-11 01:59:32 +00:00
|
|
|
/** Mask constant for a UCharCategory. @stable ICU 2.1 */
|
2002-03-13 23:31:12 +00:00
|
|
|
#define U_GC_SM_MASK U_MASK(U_MATH_SYMBOL)
|
2003-02-11 01:59:32 +00:00
|
|
|
/** Mask constant for a UCharCategory. @stable ICU 2.1 */
|
2002-03-13 23:31:12 +00:00
|
|
|
#define U_GC_SC_MASK U_MASK(U_CURRENCY_SYMBOL)
|
2003-02-11 01:59:32 +00:00
|
|
|
/** Mask constant for a UCharCategory. @stable ICU 2.1 */
|
2002-03-13 23:31:12 +00:00
|
|
|
#define U_GC_SK_MASK U_MASK(U_MODIFIER_SYMBOL)
|
2003-02-11 01:59:32 +00:00
|
|
|
/** Mask constant for a UCharCategory. @stable ICU 2.1 */
|
2002-03-13 23:31:12 +00:00
|
|
|
#define U_GC_SO_MASK U_MASK(U_OTHER_SYMBOL)
|
|
|
|
|
2003-02-11 01:59:32 +00:00
|
|
|
/** Mask constant for a UCharCategory. @stable ICU 2.1 */
|
2002-03-13 23:31:12 +00:00
|
|
|
#define U_GC_PI_MASK U_MASK(U_INITIAL_PUNCTUATION)
|
2003-02-11 01:59:32 +00:00
|
|
|
/** Mask constant for a UCharCategory. @stable ICU 2.1 */
|
2002-03-13 23:31:12 +00:00
|
|
|
#define U_GC_PF_MASK U_MASK(U_FINAL_PUNCTUATION)
|
|
|
|
|
|
|
|
|
2003-02-11 01:59:32 +00:00
|
|
|
/** Mask constant for multiple UCharCategory bits (L Letters). @stable ICU 2.1 */
|
2002-03-13 23:31:12 +00:00
|
|
|
#define U_GC_L_MASK \
|
|
|
|
(U_GC_LU_MASK|U_GC_LL_MASK|U_GC_LT_MASK|U_GC_LM_MASK|U_GC_LO_MASK)
|
|
|
|
|
2003-02-11 01:59:32 +00:00
|
|
|
/** Mask constant for multiple UCharCategory bits (LC Cased Letters). @stable ICU 2.1 */
|
2002-10-30 18:24:53 +00:00
|
|
|
#define U_GC_LC_MASK \
|
|
|
|
(U_GC_LU_MASK|U_GC_LL_MASK|U_GC_LT_MASK)
|
|
|
|
|
2003-02-11 01:59:32 +00:00
|
|
|
/** Mask constant for multiple UCharCategory bits (M Marks). @stable ICU 2.1 */
|
2002-03-13 23:31:12 +00:00
|
|
|
#define U_GC_M_MASK (U_GC_MN_MASK|U_GC_ME_MASK|U_GC_MC_MASK)
|
|
|
|
|
2003-02-11 01:59:32 +00:00
|
|
|
/** Mask constant for multiple UCharCategory bits (N Numbers). @stable ICU 2.1 */
|
2002-03-13 23:31:12 +00:00
|
|
|
#define U_GC_N_MASK (U_GC_ND_MASK|U_GC_NL_MASK|U_GC_NO_MASK)
|
|
|
|
|
2003-02-11 01:59:32 +00:00
|
|
|
/** Mask constant for multiple UCharCategory bits (Z Separators). @stable ICU 2.1 */
|
2002-03-13 23:31:12 +00:00
|
|
|
#define U_GC_Z_MASK (U_GC_ZS_MASK|U_GC_ZL_MASK|U_GC_ZP_MASK)
|
|
|
|
|
2003-02-11 01:59:32 +00:00
|
|
|
/** Mask constant for multiple UCharCategory bits (C Others). @stable ICU 2.1 */
|
2002-03-13 23:31:12 +00:00
|
|
|
#define U_GC_C_MASK \
|
|
|
|
(U_GC_CN_MASK|U_GC_CC_MASK|U_GC_CF_MASK|U_GC_CO_MASK|U_GC_CS_MASK)
|
|
|
|
|
2003-02-11 01:59:32 +00:00
|
|
|
/** Mask constant for multiple UCharCategory bits (P Punctuation). @stable ICU 2.1 */
|
2002-03-13 23:31:12 +00:00
|
|
|
#define U_GC_P_MASK \
|
|
|
|
(U_GC_PD_MASK|U_GC_PS_MASK|U_GC_PE_MASK|U_GC_PC_MASK|U_GC_PO_MASK| \
|
|
|
|
U_GC_PI_MASK|U_GC_PF_MASK)
|
|
|
|
|
2003-02-11 01:59:32 +00:00
|
|
|
/** Mask constant for multiple UCharCategory bits (S Symbols). @stable ICU 2.1 */
|
2002-03-13 23:31:12 +00:00
|
|
|
#define U_GC_S_MASK (U_GC_SM_MASK|U_GC_SC_MASK|U_GC_SK_MASK|U_GC_SO_MASK)
|
|
|
|
|
1999-12-28 23:39:02 +00:00
|
|
|
/**
|
|
|
|
* This specifies the language directional property of a character set.
|
2002-12-04 23:39:56 +00:00
|
|
|
* @stable ICU 2.0
|
1999-12-28 23:39:02 +00:00
|
|
|
*/
|
2005-06-28 22:23:05 +00:00
|
|
|
typedef enum UCharDirection {
|
2011-12-23 04:20:35 +00:00
|
|
|
/*
|
|
|
|
* Note: UCharDirection constants and their API comments are parsed by preparseucd.py.
|
|
|
|
* It matches pairs of lines like
|
|
|
|
* / ** <Unicode 1..3-letter Bidi_Class value> comment... * /
|
|
|
|
* U_<[A-Z_]+> = <integer>,
|
|
|
|
*/
|
2002-10-30 18:24:53 +00:00
|
|
|
|
2002-12-05 00:30:16 +00:00
|
|
|
/** L @stable ICU 2.0 */
|
2003-02-11 23:27:40 +00:00
|
|
|
U_LEFT_TO_RIGHT = 0,
|
2002-12-05 00:30:16 +00:00
|
|
|
/** R @stable ICU 2.0 */
|
2003-02-11 23:27:40 +00:00
|
|
|
U_RIGHT_TO_LEFT = 1,
|
2002-12-05 00:30:16 +00:00
|
|
|
/** EN @stable ICU 2.0 */
|
1999-12-28 23:39:02 +00:00
|
|
|
U_EUROPEAN_NUMBER = 2,
|
2002-12-05 00:30:16 +00:00
|
|
|
/** ES @stable ICU 2.0 */
|
1999-12-28 23:39:02 +00:00
|
|
|
U_EUROPEAN_NUMBER_SEPARATOR = 3,
|
2002-12-05 00:30:16 +00:00
|
|
|
/** ET @stable ICU 2.0 */
|
1999-12-28 23:39:02 +00:00
|
|
|
U_EUROPEAN_NUMBER_TERMINATOR = 4,
|
2002-12-05 00:30:16 +00:00
|
|
|
/** AN @stable ICU 2.0 */
|
1999-12-28 23:39:02 +00:00
|
|
|
U_ARABIC_NUMBER = 5,
|
2002-12-05 00:30:16 +00:00
|
|
|
/** CS @stable ICU 2.0 */
|
1999-12-28 23:39:02 +00:00
|
|
|
U_COMMON_NUMBER_SEPARATOR = 6,
|
2002-12-05 00:30:16 +00:00
|
|
|
/** B @stable ICU 2.0 */
|
1999-12-28 23:39:02 +00:00
|
|
|
U_BLOCK_SEPARATOR = 7,
|
2002-12-05 00:30:16 +00:00
|
|
|
/** S @stable ICU 2.0 */
|
1999-12-28 23:39:02 +00:00
|
|
|
U_SEGMENT_SEPARATOR = 8,
|
2002-12-05 00:30:16 +00:00
|
|
|
/** WS @stable ICU 2.0 */
|
2003-02-11 23:27:40 +00:00
|
|
|
U_WHITE_SPACE_NEUTRAL = 9,
|
2002-12-05 00:30:16 +00:00
|
|
|
/** ON @stable ICU 2.0 */
|
2003-02-11 23:27:40 +00:00
|
|
|
U_OTHER_NEUTRAL = 10,
|
2002-12-05 00:30:16 +00:00
|
|
|
/** LRE @stable ICU 2.0 */
|
1999-12-28 23:39:02 +00:00
|
|
|
U_LEFT_TO_RIGHT_EMBEDDING = 11,
|
2002-12-05 00:30:16 +00:00
|
|
|
/** LRO @stable ICU 2.0 */
|
1999-12-28 23:39:02 +00:00
|
|
|
U_LEFT_TO_RIGHT_OVERRIDE = 12,
|
2002-12-05 00:30:16 +00:00
|
|
|
/** AL @stable ICU 2.0 */
|
1999-12-28 23:39:02 +00:00
|
|
|
U_RIGHT_TO_LEFT_ARABIC = 13,
|
2002-12-05 00:30:16 +00:00
|
|
|
/** RLE @stable ICU 2.0 */
|
1999-12-28 23:39:02 +00:00
|
|
|
U_RIGHT_TO_LEFT_EMBEDDING = 14,
|
2002-12-05 00:30:16 +00:00
|
|
|
/** RLO @stable ICU 2.0 */
|
1999-12-28 23:39:02 +00:00
|
|
|
U_RIGHT_TO_LEFT_OVERRIDE = 15,
|
2002-12-05 00:30:16 +00:00
|
|
|
/** PDF @stable ICU 2.0 */
|
1999-12-28 23:39:02 +00:00
|
|
|
U_POP_DIRECTIONAL_FORMAT = 16,
|
2002-12-05 00:30:16 +00:00
|
|
|
/** NSM @stable ICU 2.0 */
|
1999-12-28 23:39:02 +00:00
|
|
|
U_DIR_NON_SPACING_MARK = 17,
|
2002-12-05 00:30:16 +00:00
|
|
|
/** BN @stable ICU 2.0 */
|
1999-12-28 23:39:02 +00:00
|
|
|
U_BOUNDARY_NEUTRAL = 18,
|
2002-12-05 00:30:16 +00:00
|
|
|
/** @stable ICU 2.0 */
|
1999-12-28 23:39:02 +00:00
|
|
|
U_CHAR_DIRECTION_COUNT
|
2002-08-22 17:59:47 +00:00
|
|
|
} UCharDirection;
|
1999-12-28 23:39:02 +00:00
|
|
|
|
2000-11-29 03:50:58 +00:00
|
|
|
/**
|
2003-02-11 01:59:32 +00:00
|
|
|
* Constants for Unicode blocks, see the Unicode Data file Blocks.txt
|
2002-12-04 23:39:56 +00:00
|
|
|
* @stable ICU 2.0
|
2000-03-22 18:31:40 +00:00
|
|
|
*/
|
2001-09-11 05:00:34 +00:00
|
|
|
enum UBlockCode {
|
2011-12-23 04:20:35 +00:00
|
|
|
/*
|
|
|
|
* Note: UBlockCode constants are parsed by preparseucd.py.
|
|
|
|
* It matches lines like
|
|
|
|
* UBLOCK_<Unicode Block value name> = <integer>,
|
|
|
|
*/
|
2004-03-26 19:42:04 +00:00
|
|
|
|
2004-11-02 07:28:07 +00:00
|
|
|
/** New No_Block value in Unicode 4. @stable ICU 2.6 */
|
2003-03-04 19:55:37 +00:00
|
|
|
UBLOCK_NO_BLOCK = 0, /*[none]*/ /* Special range indicating No_Block */
|
2003-03-04 00:42:54 +00:00
|
|
|
|
2002-12-05 00:30:16 +00:00
|
|
|
/** @stable ICU 2.0 */
|
2011-12-23 04:20:35 +00:00
|
|
|
UBLOCK_BASIC_LATIN = 1, /*[0000]*/
|
2001-11-13 22:47:47 +00:00
|
|
|
|
2002-12-05 00:30:16 +00:00
|
|
|
/** @stable ICU 2.0 */
|
2002-10-30 18:24:53 +00:00
|
|
|
UBLOCK_LATIN_1_SUPPLEMENT=2, /*[0080]*/
|
2001-09-11 05:00:34 +00:00
|
|
|
|
2002-12-05 00:30:16 +00:00
|
|
|
/** @stable ICU 2.0 */
|
2002-10-30 18:24:53 +00:00
|
|
|
UBLOCK_LATIN_EXTENDED_A =3, /*[0100]*/
|
2001-09-11 05:00:34 +00:00
|
|
|
|
2002-12-05 00:30:16 +00:00
|
|
|
/** @stable ICU 2.0 */
|
2002-10-30 18:24:53 +00:00
|
|
|
UBLOCK_LATIN_EXTENDED_B =4, /*[0180]*/
|
2001-09-11 05:00:34 +00:00
|
|
|
|
2002-12-05 00:30:16 +00:00
|
|
|
/** @stable ICU 2.0 */
|
2002-10-30 18:24:53 +00:00
|
|
|
UBLOCK_IPA_EXTENSIONS =5, /*[0250]*/
|
2003-02-11 23:27:40 +00:00
|
|
|
|
2002-12-05 00:30:16 +00:00
|
|
|
/** @stable ICU 2.0 */
|
2002-10-30 18:24:53 +00:00
|
|
|
UBLOCK_SPACING_MODIFIER_LETTERS =6, /*[02B0]*/
|
2001-09-11 05:00:34 +00:00
|
|
|
|
2002-12-05 00:30:16 +00:00
|
|
|
/** @stable ICU 2.0 */
|
2002-10-30 18:24:53 +00:00
|
|
|
UBLOCK_COMBINING_DIACRITICAL_MARKS =7, /*[0300]*/
|
2003-02-11 23:27:40 +00:00
|
|
|
|
2002-05-31 01:25:20 +00:00
|
|
|
/**
|
|
|
|
* Unicode 3.2 renames this block to "Greek and Coptic".
|
2002-12-04 23:39:56 +00:00
|
|
|
* @stable ICU 2.0
|
2002-05-31 01:25:20 +00:00
|
|
|
*/
|
2002-10-30 18:24:53 +00:00
|
|
|
UBLOCK_GREEK =8, /*[0370]*/
|
2001-09-11 05:00:34 +00:00
|
|
|
|
2002-12-05 00:30:16 +00:00
|
|
|
/** @stable ICU 2.0 */
|
2002-10-30 18:24:53 +00:00
|
|
|
UBLOCK_CYRILLIC =9, /*[0400]*/
|
2001-09-11 05:00:34 +00:00
|
|
|
|
2002-12-05 00:30:16 +00:00
|
|
|
/** @stable ICU 2.0 */
|
2002-10-30 18:24:53 +00:00
|
|
|
UBLOCK_ARMENIAN =10, /*[0530]*/
|
2001-09-11 05:00:34 +00:00
|
|
|
|
2002-12-05 00:30:16 +00:00
|
|
|
/** @stable ICU 2.0 */
|
2002-10-30 18:24:53 +00:00
|
|
|
UBLOCK_HEBREW =11, /*[0590]*/
|
2001-09-11 05:00:34 +00:00
|
|
|
|
2002-12-05 00:30:16 +00:00
|
|
|
/** @stable ICU 2.0 */
|
2002-10-30 18:24:53 +00:00
|
|
|
UBLOCK_ARABIC =12, /*[0600]*/
|
2001-09-11 05:00:34 +00:00
|
|
|
|
2002-12-05 00:30:16 +00:00
|
|
|
/** @stable ICU 2.0 */
|
2002-10-30 18:24:53 +00:00
|
|
|
UBLOCK_SYRIAC =13, /*[0700]*/
|
2001-09-11 05:00:34 +00:00
|
|
|
|
2002-12-05 00:30:16 +00:00
|
|
|
/** @stable ICU 2.0 */
|
2002-10-30 18:24:53 +00:00
|
|
|
UBLOCK_THAANA =14, /*[0780]*/
|
2001-09-11 05:00:34 +00:00
|
|
|
|
2002-12-05 00:30:16 +00:00
|
|
|
/** @stable ICU 2.0 */
|
2002-10-30 18:24:53 +00:00
|
|
|
UBLOCK_DEVANAGARI =15, /*[0900]*/
|
2001-09-11 05:00:34 +00:00
|
|
|
|
2002-12-05 00:30:16 +00:00
|
|
|
/** @stable ICU 2.0 */
|
2002-10-30 18:24:53 +00:00
|
|
|
UBLOCK_BENGALI =16, /*[0980]*/
|
2001-09-11 05:00:34 +00:00
|
|
|
|
2002-12-05 00:30:16 +00:00
|
|
|
/** @stable ICU 2.0 */
|
2002-10-30 18:24:53 +00:00
|
|
|
UBLOCK_GURMUKHI =17, /*[0A00]*/
|
2001-09-11 05:00:34 +00:00
|
|
|
|
2002-12-05 00:30:16 +00:00
|
|
|
/** @stable ICU 2.0 */
|
2002-10-30 18:24:53 +00:00
|
|
|
UBLOCK_GUJARATI =18, /*[0A80]*/
|
2001-09-11 05:00:34 +00:00
|
|
|
|
2002-12-05 00:30:16 +00:00
|
|
|
/** @stable ICU 2.0 */
|
2002-10-30 18:24:53 +00:00
|
|
|
UBLOCK_ORIYA =19, /*[0B00]*/
|
2001-09-11 05:00:34 +00:00
|
|
|
|
2002-12-05 00:30:16 +00:00
|
|
|
/** @stable ICU 2.0 */
|
2002-10-30 18:24:53 +00:00
|
|
|
UBLOCK_TAMIL =20, /*[0B80]*/
|
2001-09-11 05:00:34 +00:00
|
|
|
|
2002-12-05 00:30:16 +00:00
|
|
|
/** @stable ICU 2.0 */
|
2002-10-30 18:24:53 +00:00
|
|
|
UBLOCK_TELUGU =21, /*[0C00]*/
|
2001-09-11 05:00:34 +00:00
|
|
|
|
2002-12-05 00:30:16 +00:00
|
|
|
/** @stable ICU 2.0 */
|
2002-10-30 18:24:53 +00:00
|
|
|
UBLOCK_KANNADA =22, /*[0C80]*/
|
2001-09-11 05:00:34 +00:00
|
|
|
|
2002-12-05 00:30:16 +00:00
|
|
|
/** @stable ICU 2.0 */
|
2002-10-30 18:24:53 +00:00
|
|
|
UBLOCK_MALAYALAM =23, /*[0D00]*/
|
2001-09-11 05:00:34 +00:00
|
|
|
|
2002-12-05 00:30:16 +00:00
|
|
|
/** @stable ICU 2.0 */
|
2002-10-30 18:24:53 +00:00
|
|
|
UBLOCK_SINHALA =24, /*[0D80]*/
|
2001-09-11 05:00:34 +00:00
|
|
|
|
2002-12-05 00:30:16 +00:00
|
|
|
/** @stable ICU 2.0 */
|
2002-10-30 18:24:53 +00:00
|
|
|
UBLOCK_THAI =25, /*[0E00]*/
|
2001-09-11 05:00:34 +00:00
|
|
|
|
2002-12-05 00:30:16 +00:00
|
|
|
/** @stable ICU 2.0 */
|
2002-10-30 18:24:53 +00:00
|
|
|
UBLOCK_LAO =26, /*[0E80]*/
|
2001-09-11 05:00:34 +00:00
|
|
|
|
2002-12-05 00:30:16 +00:00
|
|
|
/** @stable ICU 2.0 */
|
2002-10-30 18:24:53 +00:00
|
|
|
UBLOCK_TIBETAN =27, /*[0F00]*/
|
2001-09-11 05:00:34 +00:00
|
|
|
|
2002-12-05 00:30:16 +00:00
|
|
|
/** @stable ICU 2.0 */
|
2002-10-30 18:24:53 +00:00
|
|
|
UBLOCK_MYANMAR =28, /*[1000]*/
|
2001-09-11 05:00:34 +00:00
|
|
|
|
2002-12-05 00:30:16 +00:00
|
|
|
/** @stable ICU 2.0 */
|
2002-10-30 18:24:53 +00:00
|
|
|
UBLOCK_GEORGIAN =29, /*[10A0]*/
|
2001-09-11 05:00:34 +00:00
|
|
|
|
2002-12-05 00:30:16 +00:00
|
|
|
/** @stable ICU 2.0 */
|
2002-10-30 18:24:53 +00:00
|
|
|
UBLOCK_HANGUL_JAMO =30, /*[1100]*/
|
2001-09-11 05:00:34 +00:00
|
|
|
|
2002-12-05 00:30:16 +00:00
|
|
|
/** @stable ICU 2.0 */
|
2002-10-30 18:24:53 +00:00
|
|
|
UBLOCK_ETHIOPIC =31, /*[1200]*/
|
2001-09-11 05:00:34 +00:00
|
|
|
|
2002-12-05 00:30:16 +00:00
|
|
|
/** @stable ICU 2.0 */
|
2002-10-30 18:24:53 +00:00
|
|
|
UBLOCK_CHEROKEE =32, /*[13A0]*/
|
2001-09-11 05:00:34 +00:00
|
|
|
|
2002-12-05 00:30:16 +00:00
|
|
|
/** @stable ICU 2.0 */
|
2002-10-30 18:24:53 +00:00
|
|
|
UBLOCK_UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS =33, /*[1400]*/
|
2001-09-11 05:00:34 +00:00
|
|
|
|
2002-12-05 00:30:16 +00:00
|
|
|
/** @stable ICU 2.0 */
|
2002-10-30 18:24:53 +00:00
|
|
|
UBLOCK_OGHAM =34, /*[1680]*/
|
2001-09-11 05:00:34 +00:00
|
|
|
|
2002-12-05 00:30:16 +00:00
|
|
|
/** @stable ICU 2.0 */
|
2002-10-30 18:24:53 +00:00
|
|
|
UBLOCK_RUNIC =35, /*[16A0]*/
|
2001-09-11 05:00:34 +00:00
|
|
|
|
2002-12-05 00:30:16 +00:00
|
|
|
/** @stable ICU 2.0 */
|
2002-10-30 18:24:53 +00:00
|
|
|
UBLOCK_KHMER =36, /*[1780]*/
|
2001-09-11 05:00:34 +00:00
|
|
|
|
2002-12-05 00:30:16 +00:00
|
|
|
/** @stable ICU 2.0 */
|
2002-10-30 18:24:53 +00:00
|
|
|
UBLOCK_MONGOLIAN =37, /*[1800]*/
|
2001-09-11 05:00:34 +00:00
|
|
|
|
2002-12-05 00:30:16 +00:00
|
|
|
/** @stable ICU 2.0 */
|
2002-10-30 18:24:53 +00:00
|
|
|
UBLOCK_LATIN_EXTENDED_ADDITIONAL =38, /*[1E00]*/
|
2001-09-11 05:00:34 +00:00
|
|
|
|
2002-12-05 00:30:16 +00:00
|
|
|
/** @stable ICU 2.0 */
|
2002-10-30 18:24:53 +00:00
|
|
|
UBLOCK_GREEK_EXTENDED =39, /*[1F00]*/
|
2001-09-11 05:00:34 +00:00
|
|
|
|
2002-12-05 00:30:16 +00:00
|
|
|
/** @stable ICU 2.0 */
|
2002-10-30 18:24:53 +00:00
|
|
|
UBLOCK_GENERAL_PUNCTUATION =40, /*[2000]*/
|
2001-09-11 05:00:34 +00:00
|
|
|
|
2002-12-05 00:30:16 +00:00
|
|
|
/** @stable ICU 2.0 */
|
2002-10-30 18:24:53 +00:00
|
|
|
UBLOCK_SUPERSCRIPTS_AND_SUBSCRIPTS =41, /*[2070]*/
|
2003-02-11 23:27:40 +00:00
|
|
|
|
2002-12-05 00:30:16 +00:00
|
|
|
/** @stable ICU 2.0 */
|
2002-10-30 18:24:53 +00:00
|
|
|
UBLOCK_CURRENCY_SYMBOLS =42, /*[20A0]*/
|
2003-02-11 23:27:40 +00:00
|
|
|
|
2002-05-31 01:25:20 +00:00
|
|
|
/**
|
|
|
|
* Unicode 3.2 renames this block to "Combining Diacritical Marks for Symbols".
|
2002-12-04 23:39:56 +00:00
|
|
|
* @stable ICU 2.0
|
2002-05-31 01:25:20 +00:00
|
|
|
*/
|
2002-10-30 18:24:53 +00:00
|
|
|
UBLOCK_COMBINING_MARKS_FOR_SYMBOLS =43, /*[20D0]*/
|
2003-02-11 23:27:40 +00:00
|
|
|
|
2002-12-05 00:30:16 +00:00
|
|
|
/** @stable ICU 2.0 */
|
2002-10-30 18:24:53 +00:00
|
|
|
UBLOCK_LETTERLIKE_SYMBOLS =44, /*[2100]*/
|
2003-02-11 23:27:40 +00:00
|
|
|
|
2002-12-05 00:30:16 +00:00
|
|
|
/** @stable ICU 2.0 */
|
2002-10-30 18:24:53 +00:00
|
|
|
UBLOCK_NUMBER_FORMS =45, /*[2150]*/
|
2001-09-11 05:00:34 +00:00
|
|
|
|
2002-12-05 00:30:16 +00:00
|
|
|
/** @stable ICU 2.0 */
|
2002-10-30 18:24:53 +00:00
|
|
|
UBLOCK_ARROWS =46, /*[2190]*/
|
2001-09-11 05:00:34 +00:00
|
|
|
|
2002-12-05 00:30:16 +00:00
|
|
|
/** @stable ICU 2.0 */
|
2002-10-30 18:24:53 +00:00
|
|
|
UBLOCK_MATHEMATICAL_OPERATORS =47, /*[2200]*/
|
2001-09-11 05:00:34 +00:00
|
|
|
|
2002-12-05 00:30:16 +00:00
|
|
|
/** @stable ICU 2.0 */
|
2002-10-30 18:24:53 +00:00
|
|
|
UBLOCK_MISCELLANEOUS_TECHNICAL =48, /*[2300]*/
|
2001-09-11 05:00:34 +00:00
|
|
|
|
2002-12-05 00:30:16 +00:00
|
|
|
/** @stable ICU 2.0 */
|
2002-10-30 18:24:53 +00:00
|
|
|
UBLOCK_CONTROL_PICTURES =49, /*[2400]*/
|
2003-02-11 23:27:40 +00:00
|
|
|
|
2002-12-05 00:30:16 +00:00
|
|
|
/** @stable ICU 2.0 */
|
2002-10-30 18:24:53 +00:00
|
|
|
UBLOCK_OPTICAL_CHARACTER_RECOGNITION =50, /*[2440]*/
|
2001-09-11 05:00:34 +00:00
|
|
|
|
2002-12-05 00:30:16 +00:00
|
|
|
/** @stable ICU 2.0 */
|
2002-10-30 18:24:53 +00:00
|
|
|
UBLOCK_ENCLOSED_ALPHANUMERICS =51, /*[2460]*/
|
2001-09-11 05:00:34 +00:00
|
|
|
|
2002-12-05 00:30:16 +00:00
|
|
|
/** @stable ICU 2.0 */
|
2002-10-30 18:24:53 +00:00
|
|
|
UBLOCK_BOX_DRAWING =52, /*[2500]*/
|
2001-09-11 05:00:34 +00:00
|
|
|
|
2002-12-05 00:30:16 +00:00
|
|
|
/** @stable ICU 2.0 */
|
2002-10-30 18:24:53 +00:00
|
|
|
UBLOCK_BLOCK_ELEMENTS =53, /*[2580]*/
|
2001-09-11 05:00:34 +00:00
|
|
|
|
2002-12-05 00:30:16 +00:00
|
|
|
/** @stable ICU 2.0 */
|
2002-10-30 18:24:53 +00:00
|
|
|
UBLOCK_GEOMETRIC_SHAPES =54, /*[25A0]*/
|
2001-09-11 05:00:34 +00:00
|
|
|
|
2002-12-05 00:30:16 +00:00
|
|
|
/** @stable ICU 2.0 */
|
2002-10-30 18:24:53 +00:00
|
|
|
UBLOCK_MISCELLANEOUS_SYMBOLS =55, /*[2600]*/
|
2001-09-11 05:00:34 +00:00
|
|
|
|
2002-12-05 00:30:16 +00:00
|
|
|
/** @stable ICU 2.0 */
|
2002-10-30 18:24:53 +00:00
|
|
|
UBLOCK_DINGBATS =56, /*[2700]*/
|
2001-09-11 05:00:34 +00:00
|
|
|
|
2002-12-05 00:30:16 +00:00
|
|
|
/** @stable ICU 2.0 */
|
2002-10-30 18:24:53 +00:00
|
|
|
UBLOCK_BRAILLE_PATTERNS =57, /*[2800]*/
|
2001-09-11 05:00:34 +00:00
|
|
|
|
2002-12-05 00:30:16 +00:00
|
|
|
/** @stable ICU 2.0 */
|
2002-10-30 18:24:53 +00:00
|
|
|
UBLOCK_CJK_RADICALS_SUPPLEMENT =58, /*[2E80]*/
|
2001-09-11 05:00:34 +00:00
|
|
|
|
2002-12-05 00:30:16 +00:00
|
|
|
/** @stable ICU 2.0 */
|
2002-10-30 18:24:53 +00:00
|
|
|
UBLOCK_KANGXI_RADICALS =59, /*[2F00]*/
|
2001-09-11 05:00:34 +00:00
|
|
|
|
2002-12-05 00:30:16 +00:00
|
|
|
/** @stable ICU 2.0 */
|
2002-10-30 18:24:53 +00:00
|
|
|
UBLOCK_IDEOGRAPHIC_DESCRIPTION_CHARACTERS =60, /*[2FF0]*/
|
2001-09-11 05:00:34 +00:00
|
|
|
|
2002-12-05 00:30:16 +00:00
|
|
|
/** @stable ICU 2.0 */
|
2002-10-30 18:24:53 +00:00
|
|
|
UBLOCK_CJK_SYMBOLS_AND_PUNCTUATION =61, /*[3000]*/
|
2001-09-11 05:00:34 +00:00
|
|
|
|
2002-12-05 00:30:16 +00:00
|
|
|
/** @stable ICU 2.0 */
|
2002-10-30 18:24:53 +00:00
|
|
|
UBLOCK_HIRAGANA =62, /*[3040]*/
|
2001-09-11 05:00:34 +00:00
|
|
|
|
2002-12-05 00:30:16 +00:00
|
|
|
/** @stable ICU 2.0 */
|
2002-10-30 18:24:53 +00:00
|
|
|
UBLOCK_KATAKANA =63, /*[30A0]*/
|
2001-09-11 05:00:34 +00:00
|
|
|
|
2002-12-05 00:30:16 +00:00
|
|
|
/** @stable ICU 2.0 */
|
2002-10-30 18:24:53 +00:00
|
|
|
UBLOCK_BOPOMOFO =64, /*[3100]*/
|
2001-09-11 05:00:34 +00:00
|
|
|
|
2002-12-05 00:30:16 +00:00
|
|
|
/** @stable ICU 2.0 */
|
2002-10-30 18:24:53 +00:00
|
|
|
UBLOCK_HANGUL_COMPATIBILITY_JAMO =65, /*[3130]*/
|
2001-09-11 05:00:34 +00:00
|
|
|
|
2002-12-05 00:30:16 +00:00
|
|
|
/** @stable ICU 2.0 */
|
2002-10-30 18:24:53 +00:00
|
|
|
UBLOCK_KANBUN =66, /*[3190]*/
|
2001-09-11 05:00:34 +00:00
|
|
|
|
2002-12-05 00:30:16 +00:00
|
|
|
/** @stable ICU 2.0 */
|
2002-10-30 18:24:53 +00:00
|
|
|
UBLOCK_BOPOMOFO_EXTENDED =67, /*[31A0]*/
|
2001-09-11 05:00:34 +00:00
|
|
|
|
2002-12-05 00:30:16 +00:00
|
|
|
/** @stable ICU 2.0 */
|
2002-10-30 18:24:53 +00:00
|
|
|
UBLOCK_ENCLOSED_CJK_LETTERS_AND_MONTHS =68, /*[3200]*/
|
2001-09-11 05:00:34 +00:00
|
|
|
|
2002-12-05 00:30:16 +00:00
|
|
|
/** @stable ICU 2.0 */
|
2002-10-30 18:24:53 +00:00
|
|
|
UBLOCK_CJK_COMPATIBILITY =69, /*[3300]*/
|
2001-09-11 05:00:34 +00:00
|
|
|
|
2002-12-05 00:30:16 +00:00
|
|
|
/** @stable ICU 2.0 */
|
2002-10-30 18:24:53 +00:00
|
|
|
UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_A =70, /*[3400]*/
|
2001-09-11 05:00:34 +00:00
|
|
|
|
2002-12-05 00:30:16 +00:00
|
|
|
/** @stable ICU 2.0 */
|
2002-10-30 18:24:53 +00:00
|
|
|
UBLOCK_CJK_UNIFIED_IDEOGRAPHS =71, /*[4E00]*/
|
2001-09-11 05:00:34 +00:00
|
|
|
|
2002-12-05 00:30:16 +00:00
|
|
|
/** @stable ICU 2.0 */
|
2002-10-30 18:24:53 +00:00
|
|
|
UBLOCK_YI_SYLLABLES =72, /*[A000]*/
|
2001-09-11 05:00:34 +00:00
|
|
|
|
2002-12-05 00:30:16 +00:00
|
|
|
/** @stable ICU 2.0 */
|
2002-10-30 18:24:53 +00:00
|
|
|
UBLOCK_YI_RADICALS =73, /*[A490]*/
|
2001-09-11 05:00:34 +00:00
|
|
|
|
2002-12-05 00:30:16 +00:00
|
|
|
/** @stable ICU 2.0 */
|
2002-10-30 18:24:53 +00:00
|
|
|
UBLOCK_HANGUL_SYLLABLES =74, /*[AC00]*/
|
2001-09-11 05:00:34 +00:00
|
|
|
|
2002-12-05 00:30:16 +00:00
|
|
|
/** @stable ICU 2.0 */
|
2002-10-30 18:24:53 +00:00
|
|
|
UBLOCK_HIGH_SURROGATES =75, /*[D800]*/
|
2001-09-11 05:00:34 +00:00
|
|
|
|
2002-12-05 00:30:16 +00:00
|
|
|
/** @stable ICU 2.0 */
|
2002-10-30 18:24:53 +00:00
|
|
|
UBLOCK_HIGH_PRIVATE_USE_SURROGATES =76, /*[DB80]*/
|
2001-09-11 05:00:34 +00:00
|
|
|
|
2002-12-05 00:30:16 +00:00
|
|
|
/** @stable ICU 2.0 */
|
2002-10-30 18:24:53 +00:00
|
|
|
UBLOCK_LOW_SURROGATES =77, /*[DC00]*/
|
2001-09-11 05:00:34 +00:00
|
|
|
|
2002-05-31 01:25:20 +00:00
|
|
|
/**
|
2011-12-20 07:48:49 +00:00
|
|
|
* Same as UBLOCK_PRIVATE_USE.
|
2002-07-18 19:08:43 +00:00
|
|
|
* Until Unicode 3.1.1, the corresponding block name was "Private Use",
|
|
|
|
* and multiple code point ranges had this block.
|
|
|
|
* Unicode 3.2 renames the block for the BMP PUA to "Private Use Area" and
|
|
|
|
* adds separate blocks for the supplementary PUAs.
|
|
|
|
*
|
2002-12-04 23:39:56 +00:00
|
|
|
* @stable ICU 2.0
|
2002-05-31 01:25:20 +00:00
|
|
|
*/
|
2011-12-20 07:48:49 +00:00
|
|
|
UBLOCK_PRIVATE_USE_AREA =78, /*[E000]*/
|
2002-07-18 19:08:43 +00:00
|
|
|
/**
|
2011-12-20 07:48:49 +00:00
|
|
|
* Same as UBLOCK_PRIVATE_USE_AREA.
|
2002-07-18 19:08:43 +00:00
|
|
|
* Until Unicode 3.1.1, the corresponding block name was "Private Use",
|
|
|
|
* and multiple code point ranges had this block.
|
|
|
|
* Unicode 3.2 renames the block for the BMP PUA to "Private Use Area" and
|
|
|
|
* adds separate blocks for the supplementary PUAs.
|
|
|
|
*
|
2002-12-04 23:39:56 +00:00
|
|
|
* @stable ICU 2.0
|
2002-07-18 19:08:43 +00:00
|
|
|
*/
|
2011-12-20 07:48:49 +00:00
|
|
|
UBLOCK_PRIVATE_USE = UBLOCK_PRIVATE_USE_AREA,
|
2001-09-11 05:00:34 +00:00
|
|
|
|
2002-12-05 00:30:16 +00:00
|
|
|
/** @stable ICU 2.0 */
|
2002-10-30 18:24:53 +00:00
|
|
|
UBLOCK_CJK_COMPATIBILITY_IDEOGRAPHS =79, /*[F900]*/
|
2001-09-11 05:00:34 +00:00
|
|
|
|
2002-12-05 00:30:16 +00:00
|
|
|
/** @stable ICU 2.0 */
|
2002-10-30 18:24:53 +00:00
|
|
|
UBLOCK_ALPHABETIC_PRESENTATION_FORMS =80, /*[FB00]*/
|
2001-09-11 05:00:34 +00:00
|
|
|
|
2002-12-05 00:30:16 +00:00
|
|
|
/** @stable ICU 2.0 */
|
2002-10-30 18:24:53 +00:00
|
|
|
UBLOCK_ARABIC_PRESENTATION_FORMS_A =81, /*[FB50]*/
|
2001-09-11 05:00:34 +00:00
|
|
|
|
2002-12-05 00:30:16 +00:00
|
|
|
/** @stable ICU 2.0 */
|
2002-10-30 18:24:53 +00:00
|
|
|
UBLOCK_COMBINING_HALF_MARKS =82, /*[FE20]*/
|
2001-09-11 05:00:34 +00:00
|
|
|
|
2002-12-05 00:30:16 +00:00
|
|
|
/** @stable ICU 2.0 */
|
2002-10-30 18:24:53 +00:00
|
|
|
UBLOCK_CJK_COMPATIBILITY_FORMS =83, /*[FE30]*/
|
2001-09-11 05:00:34 +00:00
|
|
|
|
2002-12-05 00:30:16 +00:00
|
|
|
/** @stable ICU 2.0 */
|
2002-10-30 18:24:53 +00:00
|
|
|
UBLOCK_SMALL_FORM_VARIANTS =84, /*[FE50]*/
|
2001-09-11 05:00:34 +00:00
|
|
|
|
2002-12-05 00:30:16 +00:00
|
|
|
/** @stable ICU 2.0 */
|
2002-10-30 18:24:53 +00:00
|
|
|
UBLOCK_ARABIC_PRESENTATION_FORMS_B =85, /*[FE70]*/
|
2001-09-11 05:00:34 +00:00
|
|
|
|
2002-12-05 00:30:16 +00:00
|
|
|
/** @stable ICU 2.0 */
|
2002-10-30 18:24:53 +00:00
|
|
|
UBLOCK_SPECIALS =86, /*[FFF0]*/
|
2001-09-11 05:00:34 +00:00
|
|
|
|
2002-12-05 00:30:16 +00:00
|
|
|
/** @stable ICU 2.0 */
|
2002-10-30 18:24:53 +00:00
|
|
|
UBLOCK_HALFWIDTH_AND_FULLWIDTH_FORMS =87, /*[FF00]*/
|
2003-02-11 23:27:40 +00:00
|
|
|
|
2003-03-04 00:42:54 +00:00
|
|
|
/* New blocks in Unicode 3.1 */
|
|
|
|
|
2002-12-05 00:30:16 +00:00
|
|
|
/** @stable ICU 2.0 */
|
2011-12-20 07:48:49 +00:00
|
|
|
UBLOCK_OLD_ITALIC = 88, /*[10300]*/
|
2002-12-05 00:30:16 +00:00
|
|
|
/** @stable ICU 2.0 */
|
2011-12-20 07:48:49 +00:00
|
|
|
UBLOCK_GOTHIC = 89, /*[10330]*/
|
2002-12-05 00:30:16 +00:00
|
|
|
/** @stable ICU 2.0 */
|
2011-12-20 07:48:49 +00:00
|
|
|
UBLOCK_DESERET = 90, /*[10400]*/
|
2002-12-05 00:30:16 +00:00
|
|
|
/** @stable ICU 2.0 */
|
2011-12-20 07:48:49 +00:00
|
|
|
UBLOCK_BYZANTINE_MUSICAL_SYMBOLS = 91, /*[1D000]*/
|
2002-12-05 00:30:16 +00:00
|
|
|
/** @stable ICU 2.0 */
|
2011-12-20 07:48:49 +00:00
|
|
|
UBLOCK_MUSICAL_SYMBOLS = 92, /*[1D100]*/
|
2002-12-05 00:30:16 +00:00
|
|
|
/** @stable ICU 2.0 */
|
2011-12-20 07:48:49 +00:00
|
|
|
UBLOCK_MATHEMATICAL_ALPHANUMERIC_SYMBOLS = 93, /*[1D400]*/
|
2002-12-05 00:30:16 +00:00
|
|
|
/** @stable ICU 2.0 */
|
2011-12-20 07:48:49 +00:00
|
|
|
UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_B = 94, /*[20000]*/
|
2002-12-05 00:30:16 +00:00
|
|
|
/** @stable ICU 2.0 */
|
2011-12-20 07:48:49 +00:00
|
|
|
UBLOCK_CJK_COMPATIBILITY_IDEOGRAPHS_SUPPLEMENT = 95, /*[2F800]*/
|
2002-12-05 00:30:16 +00:00
|
|
|
/** @stable ICU 2.0 */
|
2002-10-30 18:24:53 +00:00
|
|
|
UBLOCK_TAGS = 96, /*[E0000]*/
|
2002-05-31 01:25:20 +00:00
|
|
|
|
|
|
|
/* New blocks in Unicode 3.2 */
|
|
|
|
|
2011-12-20 07:48:49 +00:00
|
|
|
/** @stable ICU 3.0 */
|
|
|
|
UBLOCK_CYRILLIC_SUPPLEMENT = 97, /*[0500]*/
|
2004-04-02 17:41:06 +00:00
|
|
|
/**
|
|
|
|
* Unicode 4.0.1 renames the "Cyrillic Supplementary" block to "Cyrillic Supplement".
|
2004-04-06 05:55:17 +00:00
|
|
|
* @stable ICU 2.2
|
2004-04-02 17:41:06 +00:00
|
|
|
*/
|
2011-12-20 07:48:49 +00:00
|
|
|
UBLOCK_CYRILLIC_SUPPLEMENTARY = UBLOCK_CYRILLIC_SUPPLEMENT,
|
2003-11-18 02:37:24 +00:00
|
|
|
/** @stable ICU 2.2 */
|
2002-10-30 18:24:53 +00:00
|
|
|
UBLOCK_TAGALOG = 98, /*[1700]*/
|
2003-11-18 02:37:24 +00:00
|
|
|
/** @stable ICU 2.2 */
|
2002-10-30 18:24:53 +00:00
|
|
|
UBLOCK_HANUNOO = 99, /*[1720]*/
|
2003-11-18 02:37:24 +00:00
|
|
|
/** @stable ICU 2.2 */
|
2002-10-30 18:24:53 +00:00
|
|
|
UBLOCK_BUHID = 100, /*[1740]*/
|
2003-11-18 02:37:24 +00:00
|
|
|
/** @stable ICU 2.2 */
|
2002-10-30 18:24:53 +00:00
|
|
|
UBLOCK_TAGBANWA = 101, /*[1760]*/
|
2003-11-18 02:37:24 +00:00
|
|
|
/** @stable ICU 2.2 */
|
2002-10-30 18:24:53 +00:00
|
|
|
UBLOCK_MISCELLANEOUS_MATHEMATICAL_SYMBOLS_A = 102, /*[27C0]*/
|
2003-11-18 02:37:24 +00:00
|
|
|
/** @stable ICU 2.2 */
|
2002-10-30 18:24:53 +00:00
|
|
|
UBLOCK_SUPPLEMENTAL_ARROWS_A = 103, /*[27F0]*/
|
2003-11-18 02:37:24 +00:00
|
|
|
/** @stable ICU 2.2 */
|
2002-10-30 18:24:53 +00:00
|
|
|
UBLOCK_SUPPLEMENTAL_ARROWS_B = 104, /*[2900]*/
|
2003-11-18 02:37:24 +00:00
|
|
|
/** @stable ICU 2.2 */
|
2002-10-30 18:24:53 +00:00
|
|
|
UBLOCK_MISCELLANEOUS_MATHEMATICAL_SYMBOLS_B = 105, /*[2980]*/
|
2003-11-18 02:37:24 +00:00
|
|
|
/** @stable ICU 2.2 */
|
2002-10-30 18:24:53 +00:00
|
|
|
UBLOCK_SUPPLEMENTAL_MATHEMATICAL_OPERATORS = 106, /*[2A00]*/
|
2003-11-18 02:37:24 +00:00
|
|
|
/** @stable ICU 2.2 */
|
2002-10-30 18:24:53 +00:00
|
|
|
UBLOCK_KATAKANA_PHONETIC_EXTENSIONS = 107, /*[31F0]*/
|
2003-11-18 02:37:24 +00:00
|
|
|
/** @stable ICU 2.2 */
|
2002-10-30 18:24:53 +00:00
|
|
|
UBLOCK_VARIATION_SELECTORS = 108, /*[FE00]*/
|
2003-11-18 02:37:24 +00:00
|
|
|
/** @stable ICU 2.2 */
|
2002-10-30 18:24:53 +00:00
|
|
|
UBLOCK_SUPPLEMENTARY_PRIVATE_USE_AREA_A = 109, /*[F0000]*/
|
2003-11-18 02:37:24 +00:00
|
|
|
/** @stable ICU 2.2 */
|
2002-10-30 18:24:53 +00:00
|
|
|
UBLOCK_SUPPLEMENTARY_PRIVATE_USE_AREA_B = 110, /*[100000]*/
|
2002-05-31 01:25:20 +00:00
|
|
|
|
2003-03-04 00:42:54 +00:00
|
|
|
/* New blocks in Unicode 4 */
|
|
|
|
|
2004-11-02 07:28:07 +00:00
|
|
|
/** @stable ICU 2.6 */
|
2003-03-04 00:42:54 +00:00
|
|
|
UBLOCK_LIMBU = 111, /*[1900]*/
|
2004-11-02 07:28:07 +00:00
|
|
|
/** @stable ICU 2.6 */
|
2003-03-04 00:42:54 +00:00
|
|
|
UBLOCK_TAI_LE = 112, /*[1950]*/
|
2004-11-02 07:28:07 +00:00
|
|
|
/** @stable ICU 2.6 */
|
2003-03-04 00:42:54 +00:00
|
|
|
UBLOCK_KHMER_SYMBOLS = 113, /*[19E0]*/
|
2004-11-02 07:28:07 +00:00
|
|
|
/** @stable ICU 2.6 */
|
2003-03-04 00:42:54 +00:00
|
|
|
UBLOCK_PHONETIC_EXTENSIONS = 114, /*[1D00]*/
|
2004-11-02 07:28:07 +00:00
|
|
|
/** @stable ICU 2.6 */
|
2003-03-04 00:42:54 +00:00
|
|
|
UBLOCK_MISCELLANEOUS_SYMBOLS_AND_ARROWS = 115, /*[2B00]*/
|
2004-11-02 07:28:07 +00:00
|
|
|
/** @stable ICU 2.6 */
|
2003-03-04 00:42:54 +00:00
|
|
|
UBLOCK_YIJING_HEXAGRAM_SYMBOLS = 116, /*[4DC0]*/
|
2004-11-02 07:28:07 +00:00
|
|
|
/** @stable ICU 2.6 */
|
2003-03-04 00:42:54 +00:00
|
|
|
UBLOCK_LINEAR_B_SYLLABARY = 117, /*[10000]*/
|
2004-11-02 07:28:07 +00:00
|
|
|
/** @stable ICU 2.6 */
|
2003-03-04 00:42:54 +00:00
|
|
|
UBLOCK_LINEAR_B_IDEOGRAMS = 118, /*[10080]*/
|
2004-11-02 07:28:07 +00:00
|
|
|
/** @stable ICU 2.6 */
|
2003-03-04 00:42:54 +00:00
|
|
|
UBLOCK_AEGEAN_NUMBERS = 119, /*[10100]*/
|
2004-11-02 07:28:07 +00:00
|
|
|
/** @stable ICU 2.6 */
|
2003-03-04 00:42:54 +00:00
|
|
|
UBLOCK_UGARITIC = 120, /*[10380]*/
|
2004-11-02 07:28:07 +00:00
|
|
|
/** @stable ICU 2.6 */
|
2003-03-04 00:42:54 +00:00
|
|
|
UBLOCK_SHAVIAN = 121, /*[10450]*/
|
2004-11-02 07:28:07 +00:00
|
|
|
/** @stable ICU 2.6 */
|
2003-03-04 00:42:54 +00:00
|
|
|
UBLOCK_OSMANYA = 122, /*[10480]*/
|
2004-11-02 07:28:07 +00:00
|
|
|
/** @stable ICU 2.6 */
|
2003-03-04 00:42:54 +00:00
|
|
|
UBLOCK_CYPRIOT_SYLLABARY = 123, /*[10800]*/
|
2004-11-02 07:28:07 +00:00
|
|
|
/** @stable ICU 2.6 */
|
2003-03-04 00:42:54 +00:00
|
|
|
UBLOCK_TAI_XUAN_JING_SYMBOLS = 124, /*[1D300]*/
|
2004-11-02 07:28:07 +00:00
|
|
|
/** @stable ICU 2.6 */
|
2003-03-04 00:42:54 +00:00
|
|
|
UBLOCK_VARIATION_SELECTORS_SUPPLEMENT = 125, /*[E0100]*/
|
|
|
|
|
2005-01-10 18:02:54 +00:00
|
|
|
/* New blocks in Unicode 4.1 */
|
|
|
|
|
2007-08-19 08:59:28 +00:00
|
|
|
/** @stable ICU 3.4 */
|
2005-01-10 18:02:54 +00:00
|
|
|
UBLOCK_ANCIENT_GREEK_MUSICAL_NOTATION = 126, /*[1D200]*/
|
2007-08-19 08:59:28 +00:00
|
|
|
/** @stable ICU 3.4 */
|
2005-01-10 18:02:54 +00:00
|
|
|
UBLOCK_ANCIENT_GREEK_NUMBERS = 127, /*[10140]*/
|
2007-08-19 08:59:28 +00:00
|
|
|
/** @stable ICU 3.4 */
|
2005-01-10 18:02:54 +00:00
|
|
|
UBLOCK_ARABIC_SUPPLEMENT = 128, /*[0750]*/
|
2007-08-19 08:59:28 +00:00
|
|
|
/** @stable ICU 3.4 */
|
2005-01-10 18:02:54 +00:00
|
|
|
UBLOCK_BUGINESE = 129, /*[1A00]*/
|
2007-08-19 08:59:28 +00:00
|
|
|
/** @stable ICU 3.4 */
|
2005-02-21 22:46:36 +00:00
|
|
|
UBLOCK_CJK_STROKES = 130, /*[31C0]*/
|
2007-08-19 08:59:28 +00:00
|
|
|
/** @stable ICU 3.4 */
|
2005-01-10 18:02:54 +00:00
|
|
|
UBLOCK_COMBINING_DIACRITICAL_MARKS_SUPPLEMENT = 131, /*[1DC0]*/
|
2007-08-19 08:59:28 +00:00
|
|
|
/** @stable ICU 3.4 */
|
2005-01-10 18:02:54 +00:00
|
|
|
UBLOCK_COPTIC = 132, /*[2C80]*/
|
2007-08-19 08:59:28 +00:00
|
|
|
/** @stable ICU 3.4 */
|
2005-01-10 18:02:54 +00:00
|
|
|
UBLOCK_ETHIOPIC_EXTENDED = 133, /*[2D80]*/
|
2007-08-19 08:59:28 +00:00
|
|
|
/** @stable ICU 3.4 */
|
2005-01-10 18:02:54 +00:00
|
|
|
UBLOCK_ETHIOPIC_SUPPLEMENT = 134, /*[1380]*/
|
2007-08-19 08:59:28 +00:00
|
|
|
/** @stable ICU 3.4 */
|
2005-01-10 18:02:54 +00:00
|
|
|
UBLOCK_GEORGIAN_SUPPLEMENT = 135, /*[2D00]*/
|
2007-08-19 08:59:28 +00:00
|
|
|
/** @stable ICU 3.4 */
|
2005-01-10 18:02:54 +00:00
|
|
|
UBLOCK_GLAGOLITIC = 136, /*[2C00]*/
|
2007-08-19 08:59:28 +00:00
|
|
|
/** @stable ICU 3.4 */
|
2005-01-10 18:02:54 +00:00
|
|
|
UBLOCK_KHAROSHTHI = 137, /*[10A00]*/
|
2007-08-19 08:59:28 +00:00
|
|
|
/** @stable ICU 3.4 */
|
2005-01-10 18:02:54 +00:00
|
|
|
UBLOCK_MODIFIER_TONE_LETTERS = 138, /*[A700]*/
|
2007-08-19 08:59:28 +00:00
|
|
|
/** @stable ICU 3.4 */
|
2005-01-10 18:02:54 +00:00
|
|
|
UBLOCK_NEW_TAI_LUE = 139, /*[1980]*/
|
2007-08-19 08:59:28 +00:00
|
|
|
/** @stable ICU 3.4 */
|
2005-01-10 18:02:54 +00:00
|
|
|
UBLOCK_OLD_PERSIAN = 140, /*[103A0]*/
|
2007-08-19 08:59:28 +00:00
|
|
|
/** @stable ICU 3.4 */
|
2005-01-10 18:02:54 +00:00
|
|
|
UBLOCK_PHONETIC_EXTENSIONS_SUPPLEMENT = 141, /*[1D80]*/
|
2007-08-19 08:59:28 +00:00
|
|
|
/** @stable ICU 3.4 */
|
2005-01-10 18:02:54 +00:00
|
|
|
UBLOCK_SUPPLEMENTAL_PUNCTUATION = 142, /*[2E00]*/
|
2007-08-19 08:59:28 +00:00
|
|
|
/** @stable ICU 3.4 */
|
2005-01-10 18:02:54 +00:00
|
|
|
UBLOCK_SYLOTI_NAGRI = 143, /*[A800]*/
|
2007-08-19 08:59:28 +00:00
|
|
|
/** @stable ICU 3.4 */
|
2005-02-21 22:46:36 +00:00
|
|
|
UBLOCK_TIFINAGH = 144, /*[2D30]*/
|
2007-08-19 08:59:28 +00:00
|
|
|
/** @stable ICU 3.4 */
|
2005-01-10 18:02:54 +00:00
|
|
|
UBLOCK_VERTICAL_FORMS = 145, /*[FE10]*/
|
|
|
|
|
2006-03-03 20:59:01 +00:00
|
|
|
/* New blocks in Unicode 5.0 */
|
|
|
|
|
2007-08-19 08:59:28 +00:00
|
|
|
/** @stable ICU 3.6 */
|
2006-03-03 20:59:01 +00:00
|
|
|
UBLOCK_NKO = 146, /*[07C0]*/
|
2007-08-19 08:59:28 +00:00
|
|
|
/** @stable ICU 3.6 */
|
2006-03-03 20:59:01 +00:00
|
|
|
UBLOCK_BALINESE = 147, /*[1B00]*/
|
2007-08-19 08:59:28 +00:00
|
|
|
/** @stable ICU 3.6 */
|
2006-03-03 20:59:01 +00:00
|
|
|
UBLOCK_LATIN_EXTENDED_C = 148, /*[2C60]*/
|
2007-08-19 08:59:28 +00:00
|
|
|
/** @stable ICU 3.6 */
|
2006-03-03 20:59:01 +00:00
|
|
|
UBLOCK_LATIN_EXTENDED_D = 149, /*[A720]*/
|
2007-08-19 08:59:28 +00:00
|
|
|
/** @stable ICU 3.6 */
|
2006-03-03 20:59:01 +00:00
|
|
|
UBLOCK_PHAGS_PA = 150, /*[A840]*/
|
2007-08-19 08:59:28 +00:00
|
|
|
/** @stable ICU 3.6 */
|
2006-03-03 20:59:01 +00:00
|
|
|
UBLOCK_PHOENICIAN = 151, /*[10900]*/
|
2007-08-19 08:59:28 +00:00
|
|
|
/** @stable ICU 3.6 */
|
2006-03-03 20:59:01 +00:00
|
|
|
UBLOCK_CUNEIFORM = 152, /*[12000]*/
|
2007-08-19 08:59:28 +00:00
|
|
|
/** @stable ICU 3.6 */
|
2006-03-03 20:59:01 +00:00
|
|
|
UBLOCK_CUNEIFORM_NUMBERS_AND_PUNCTUATION = 153, /*[12400]*/
|
2007-08-19 08:59:28 +00:00
|
|
|
/** @stable ICU 3.6 */
|
2006-03-03 20:59:01 +00:00
|
|
|
UBLOCK_COUNTING_ROD_NUMERALS = 154, /*[1D360]*/
|
|
|
|
|
2008-04-04 22:47:43 +00:00
|
|
|
/* New blocks in Unicode 5.1 */
|
|
|
|
|
2009-03-19 04:03:31 +00:00
|
|
|
/** @stable ICU 4.0 */
|
2008-04-04 22:47:43 +00:00
|
|
|
UBLOCK_SUNDANESE = 155, /*[1B80]*/
|
2009-03-19 04:03:31 +00:00
|
|
|
/** @stable ICU 4.0 */
|
2008-04-04 22:47:43 +00:00
|
|
|
UBLOCK_LEPCHA = 156, /*[1C00]*/
|
2009-03-19 04:03:31 +00:00
|
|
|
/** @stable ICU 4.0 */
|
2008-04-04 22:47:43 +00:00
|
|
|
UBLOCK_OL_CHIKI = 157, /*[1C50]*/
|
2009-03-19 04:03:31 +00:00
|
|
|
/** @stable ICU 4.0 */
|
2008-04-04 22:47:43 +00:00
|
|
|
UBLOCK_CYRILLIC_EXTENDED_A = 158, /*[2DE0]*/
|
2009-03-19 04:03:31 +00:00
|
|
|
/** @stable ICU 4.0 */
|
2008-04-04 22:47:43 +00:00
|
|
|
UBLOCK_VAI = 159, /*[A500]*/
|
2009-03-19 04:03:31 +00:00
|
|
|
/** @stable ICU 4.0 */
|
2008-04-04 22:47:43 +00:00
|
|
|
UBLOCK_CYRILLIC_EXTENDED_B = 160, /*[A640]*/
|
2009-03-19 04:03:31 +00:00
|
|
|
/** @stable ICU 4.0 */
|
2008-04-04 22:47:43 +00:00
|
|
|
UBLOCK_SAURASHTRA = 161, /*[A880]*/
|
2009-03-19 04:03:31 +00:00
|
|
|
/** @stable ICU 4.0 */
|
2008-04-04 22:47:43 +00:00
|
|
|
UBLOCK_KAYAH_LI = 162, /*[A900]*/
|
2009-03-19 04:03:31 +00:00
|
|
|
/** @stable ICU 4.0 */
|
2008-04-04 22:47:43 +00:00
|
|
|
UBLOCK_REJANG = 163, /*[A930]*/
|
2009-03-19 04:03:31 +00:00
|
|
|
/** @stable ICU 4.0 */
|
2008-04-04 22:47:43 +00:00
|
|
|
UBLOCK_CHAM = 164, /*[AA00]*/
|
2009-03-19 04:03:31 +00:00
|
|
|
/** @stable ICU 4.0 */
|
2008-04-04 22:47:43 +00:00
|
|
|
UBLOCK_ANCIENT_SYMBOLS = 165, /*[10190]*/
|
2009-03-19 04:03:31 +00:00
|
|
|
/** @stable ICU 4.0 */
|
2008-04-04 22:47:43 +00:00
|
|
|
UBLOCK_PHAISTOS_DISC = 166, /*[101D0]*/
|
2009-03-19 04:03:31 +00:00
|
|
|
/** @stable ICU 4.0 */
|
2008-04-04 22:47:43 +00:00
|
|
|
UBLOCK_LYCIAN = 167, /*[10280]*/
|
2009-03-19 04:03:31 +00:00
|
|
|
/** @stable ICU 4.0 */
|
2008-04-04 22:47:43 +00:00
|
|
|
UBLOCK_CARIAN = 168, /*[102A0]*/
|
2009-03-19 04:03:31 +00:00
|
|
|
/** @stable ICU 4.0 */
|
2008-04-04 22:47:43 +00:00
|
|
|
UBLOCK_LYDIAN = 169, /*[10920]*/
|
2009-03-19 04:03:31 +00:00
|
|
|
/** @stable ICU 4.0 */
|
2008-04-04 22:47:43 +00:00
|
|
|
UBLOCK_MAHJONG_TILES = 170, /*[1F000]*/
|
2009-03-19 04:03:31 +00:00
|
|
|
/** @stable ICU 4.0 */
|
2008-04-04 22:47:43 +00:00
|
|
|
UBLOCK_DOMINO_TILES = 171, /*[1F030]*/
|
|
|
|
|
2009-11-13 19:25:21 +00:00
|
|
|
/* New blocks in Unicode 5.2 */
|
|
|
|
|
2010-09-21 00:12:49 +00:00
|
|
|
/** @stable ICU 4.4 */
|
2009-11-13 19:25:21 +00:00
|
|
|
UBLOCK_SAMARITAN = 172, /*[0800]*/
|
2010-09-21 00:12:49 +00:00
|
|
|
/** @stable ICU 4.4 */
|
2009-11-13 19:25:21 +00:00
|
|
|
UBLOCK_UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS_EXTENDED = 173, /*[18B0]*/
|
2010-09-21 00:12:49 +00:00
|
|
|
/** @stable ICU 4.4 */
|
2009-11-13 19:25:21 +00:00
|
|
|
UBLOCK_TAI_THAM = 174, /*[1A20]*/
|
2010-09-21 00:12:49 +00:00
|
|
|
/** @stable ICU 4.4 */
|
2009-11-13 19:25:21 +00:00
|
|
|
UBLOCK_VEDIC_EXTENSIONS = 175, /*[1CD0]*/
|
2010-09-21 00:12:49 +00:00
|
|
|
/** @stable ICU 4.4 */
|
2009-11-13 19:25:21 +00:00
|
|
|
UBLOCK_LISU = 176, /*[A4D0]*/
|
2010-09-21 00:12:49 +00:00
|
|
|
/** @stable ICU 4.4 */
|
2009-11-13 19:25:21 +00:00
|
|
|
UBLOCK_BAMUM = 177, /*[A6A0]*/
|
2010-09-21 00:12:49 +00:00
|
|
|
/** @stable ICU 4.4 */
|
2009-11-13 19:25:21 +00:00
|
|
|
UBLOCK_COMMON_INDIC_NUMBER_FORMS = 178, /*[A830]*/
|
2010-09-21 00:12:49 +00:00
|
|
|
/** @stable ICU 4.4 */
|
2009-11-13 19:25:21 +00:00
|
|
|
UBLOCK_DEVANAGARI_EXTENDED = 179, /*[A8E0]*/
|
2010-09-21 00:12:49 +00:00
|
|
|
/** @stable ICU 4.4 */
|
2009-11-13 19:25:21 +00:00
|
|
|
UBLOCK_HANGUL_JAMO_EXTENDED_A = 180, /*[A960]*/
|
2010-09-21 00:12:49 +00:00
|
|
|
/** @stable ICU 4.4 */
|
2009-11-13 19:25:21 +00:00
|
|
|
UBLOCK_JAVANESE = 181, /*[A980]*/
|
2010-09-21 00:12:49 +00:00
|
|
|
/** @stable ICU 4.4 */
|
2009-11-13 19:25:21 +00:00
|
|
|
UBLOCK_MYANMAR_EXTENDED_A = 182, /*[AA60]*/
|
2010-09-21 00:12:49 +00:00
|
|
|
/** @stable ICU 4.4 */
|
2009-11-13 19:25:21 +00:00
|
|
|
UBLOCK_TAI_VIET = 183, /*[AA80]*/
|
2010-09-21 00:12:49 +00:00
|
|
|
/** @stable ICU 4.4 */
|
2009-11-13 19:25:21 +00:00
|
|
|
UBLOCK_MEETEI_MAYEK = 184, /*[ABC0]*/
|
2010-09-21 00:12:49 +00:00
|
|
|
/** @stable ICU 4.4 */
|
2009-11-13 19:25:21 +00:00
|
|
|
UBLOCK_HANGUL_JAMO_EXTENDED_B = 185, /*[D7B0]*/
|
2010-09-21 00:12:49 +00:00
|
|
|
/** @stable ICU 4.4 */
|
2009-11-13 19:25:21 +00:00
|
|
|
UBLOCK_IMPERIAL_ARAMAIC = 186, /*[10840]*/
|
2010-09-21 00:12:49 +00:00
|
|
|
/** @stable ICU 4.4 */
|
2009-11-13 19:25:21 +00:00
|
|
|
UBLOCK_OLD_SOUTH_ARABIAN = 187, /*[10A60]*/
|
2010-09-21 00:12:49 +00:00
|
|
|
/** @stable ICU 4.4 */
|
2009-11-13 19:25:21 +00:00
|
|
|
UBLOCK_AVESTAN = 188, /*[10B00]*/
|
2010-09-21 00:12:49 +00:00
|
|
|
/** @stable ICU 4.4 */
|
2009-11-13 19:25:21 +00:00
|
|
|
UBLOCK_INSCRIPTIONAL_PARTHIAN = 189, /*[10B40]*/
|
2010-09-21 00:12:49 +00:00
|
|
|
/** @stable ICU 4.4 */
|
2009-11-13 19:25:21 +00:00
|
|
|
UBLOCK_INSCRIPTIONAL_PAHLAVI = 190, /*[10B60]*/
|
2010-09-21 00:12:49 +00:00
|
|
|
/** @stable ICU 4.4 */
|
2009-11-13 19:25:21 +00:00
|
|
|
UBLOCK_OLD_TURKIC = 191, /*[10C00]*/
|
2010-09-21 00:12:49 +00:00
|
|
|
/** @stable ICU 4.4 */
|
2009-11-13 19:25:21 +00:00
|
|
|
UBLOCK_RUMI_NUMERAL_SYMBOLS = 192, /*[10E60]*/
|
2010-09-21 00:12:49 +00:00
|
|
|
/** @stable ICU 4.4 */
|
2009-11-13 19:25:21 +00:00
|
|
|
UBLOCK_KAITHI = 193, /*[11080]*/
|
2010-09-21 00:12:49 +00:00
|
|
|
/** @stable ICU 4.4 */
|
2009-11-13 19:25:21 +00:00
|
|
|
UBLOCK_EGYPTIAN_HIEROGLYPHS = 194, /*[13000]*/
|
2010-09-21 00:12:49 +00:00
|
|
|
/** @stable ICU 4.4 */
|
2009-11-13 19:25:21 +00:00
|
|
|
UBLOCK_ENCLOSED_ALPHANUMERIC_SUPPLEMENT = 195, /*[1F100]*/
|
2010-09-21 00:12:49 +00:00
|
|
|
/** @stable ICU 4.4 */
|
2009-11-13 19:25:21 +00:00
|
|
|
UBLOCK_ENCLOSED_IDEOGRAPHIC_SUPPLEMENT = 196, /*[1F200]*/
|
2010-09-21 00:12:49 +00:00
|
|
|
/** @stable ICU 4.4 */
|
2009-11-13 19:25:21 +00:00
|
|
|
UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_C = 197, /*[2A700]*/
|
|
|
|
|
2010-09-21 00:12:49 +00:00
|
|
|
/* New blocks in Unicode 6.0 */
|
|
|
|
|
|
|
|
/** @stable ICU 4.6 */
|
|
|
|
UBLOCK_MANDAIC = 198, /*[0840]*/
|
|
|
|
/** @stable ICU 4.6 */
|
|
|
|
UBLOCK_BATAK = 199, /*[1BC0]*/
|
|
|
|
/** @stable ICU 4.6 */
|
|
|
|
UBLOCK_ETHIOPIC_EXTENDED_A = 200, /*[AB00]*/
|
|
|
|
/** @stable ICU 4.6 */
|
|
|
|
UBLOCK_BRAHMI = 201, /*[11000]*/
|
|
|
|
/** @stable ICU 4.6 */
|
|
|
|
UBLOCK_BAMUM_SUPPLEMENT = 202, /*[16800]*/
|
|
|
|
/** @stable ICU 4.6 */
|
|
|
|
UBLOCK_KANA_SUPPLEMENT = 203, /*[1B000]*/
|
|
|
|
/** @stable ICU 4.6 */
|
|
|
|
UBLOCK_PLAYING_CARDS = 204, /*[1F0A0]*/
|
|
|
|
/** @stable ICU 4.6 */
|
|
|
|
UBLOCK_MISCELLANEOUS_SYMBOLS_AND_PICTOGRAPHS = 205, /*[1F300]*/
|
|
|
|
/** @stable ICU 4.6 */
|
|
|
|
UBLOCK_EMOTICONS = 206, /*[1F600]*/
|
|
|
|
/** @stable ICU 4.6 */
|
|
|
|
UBLOCK_TRANSPORT_AND_MAP_SYMBOLS = 207, /*[1F680]*/
|
|
|
|
/** @stable ICU 4.6 */
|
|
|
|
UBLOCK_ALCHEMICAL_SYMBOLS = 208, /*[1F700]*/
|
|
|
|
/** @stable ICU 4.6 */
|
|
|
|
UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_D = 209, /*[2B740]*/
|
|
|
|
|
2011-12-08 22:37:24 +00:00
|
|
|
/* New blocks in Unicode 6.1 */
|
|
|
|
|
|
|
|
/** @stable ICU 49 */
|
|
|
|
UBLOCK_ARABIC_EXTENDED_A = 210, /*[08A0]*/
|
|
|
|
/** @stable ICU 49 */
|
|
|
|
UBLOCK_ARABIC_MATHEMATICAL_ALPHABETIC_SYMBOLS = 211, /*[1EE00]*/
|
|
|
|
/** @stable ICU 49 */
|
|
|
|
UBLOCK_CHAKMA = 212, /*[11100]*/
|
|
|
|
/** @stable ICU 49 */
|
|
|
|
UBLOCK_MEETEI_MAYEK_EXTENSIONS = 213, /*[AAE0]*/
|
|
|
|
/** @stable ICU 49 */
|
|
|
|
UBLOCK_MEROITIC_CURSIVE = 214, /*[109A0]*/
|
|
|
|
/** @stable ICU 49 */
|
|
|
|
UBLOCK_MEROITIC_HIEROGLYPHS = 215, /*[10980]*/
|
|
|
|
/** @stable ICU 49 */
|
|
|
|
UBLOCK_MIAO = 216, /*[16F00]*/
|
|
|
|
/** @stable ICU 49 */
|
|
|
|
UBLOCK_SHARADA = 217, /*[11180]*/
|
|
|
|
/** @stable ICU 49 */
|
|
|
|
UBLOCK_SORA_SOMPENG = 218, /*[110D0]*/
|
|
|
|
/** @stable ICU 49 */
|
|
|
|
UBLOCK_SUNDANESE_SUPPLEMENT = 219, /*[1CC0]*/
|
|
|
|
/** @stable ICU 49 */
|
|
|
|
UBLOCK_TAKRI = 220, /*[11680]*/
|
|
|
|
|
|
|
|
/** @stable ICU 2.0 */
|
|
|
|
UBLOCK_COUNT = 221,
|
2001-09-11 05:00:34 +00:00
|
|
|
|
2002-12-05 00:30:16 +00:00
|
|
|
/** @stable ICU 2.0 */
|
2002-08-21 21:07:59 +00:00
|
|
|
UBLOCK_INVALID_CODE=-1
|
1999-12-28 23:39:02 +00:00
|
|
|
};
|
2001-09-21 23:13:40 +00:00
|
|
|
|
2002-12-05 00:30:16 +00:00
|
|
|
/** @stable ICU 2.0 */
|
2001-09-11 05:00:34 +00:00
|
|
|
typedef enum UBlockCode UBlockCode;
|
1999-12-28 23:39:02 +00:00
|
|
|
|
2002-07-04 00:38:51 +00:00
|
|
|
/**
|
|
|
|
* East Asian Width constants.
|
|
|
|
*
|
|
|
|
* @see UCHAR_EAST_ASIAN_WIDTH
|
2002-08-21 19:12:24 +00:00
|
|
|
* @see u_getIntPropertyValue
|
2003-11-18 02:37:24 +00:00
|
|
|
* @stable ICU 2.2
|
2002-07-04 00:38:51 +00:00
|
|
|
*/
|
2005-06-28 22:23:05 +00:00
|
|
|
typedef enum UEastAsianWidth {
|
2011-12-23 04:20:35 +00:00
|
|
|
/*
|
|
|
|
* Note: UEastAsianWidth constants are parsed by preparseucd.py.
|
|
|
|
* It matches lines like
|
|
|
|
* U_EA_<Unicode East_Asian_Width value name>
|
|
|
|
*/
|
|
|
|
|
|
|
|
U_EA_NEUTRAL, /*[N]*/
|
2002-10-30 18:24:53 +00:00
|
|
|
U_EA_AMBIGUOUS, /*[A]*/
|
|
|
|
U_EA_HALFWIDTH, /*[H]*/
|
|
|
|
U_EA_FULLWIDTH, /*[F]*/
|
|
|
|
U_EA_NARROW, /*[Na]*/
|
|
|
|
U_EA_WIDE, /*[W]*/
|
2002-07-04 00:38:51 +00:00
|
|
|
U_EA_COUNT
|
2002-08-21 19:12:24 +00:00
|
|
|
} UEastAsianWidth;
|
2002-07-04 00:38:51 +00:00
|
|
|
|
1999-12-28 23:39:02 +00:00
|
|
|
/**
|
|
|
|
* Selector constants for u_charName().
|
2003-02-03 22:34:59 +00:00
|
|
|
* u_charName() returns the "modern" name of a
|
2002-02-14 05:36:48 +00:00
|
|
|
* Unicode character; or the name that was defined in
|
1999-12-28 23:39:02 +00:00
|
|
|
* Unicode version 1.0, before the Unicode standard merged
|
2002-02-14 05:36:48 +00:00
|
|
|
* with ISO-10646; or an "extended" name that gives each
|
|
|
|
* Unicode code point a unique name.
|
1999-12-28 23:39:02 +00:00
|
|
|
*
|
2001-11-09 18:17:40 +00:00
|
|
|
* @see u_charName
|
2002-12-04 23:39:56 +00:00
|
|
|
* @stable ICU 2.0
|
1999-12-28 23:39:02 +00:00
|
|
|
*/
|
2005-06-28 22:23:05 +00:00
|
|
|
typedef enum UCharNameChoice {
|
2011-12-15 21:43:35 +00:00
|
|
|
/** Unicode character name (Name property). @stable ICU 2.0 */
|
1999-12-28 23:39:02 +00:00
|
|
|
U_UNICODE_CHAR_NAME,
|
2011-12-15 21:43:35 +00:00
|
|
|
/**
|
|
|
|
* The Unicode_1_Name property value which is of little practical value.
|
|
|
|
* Beginning with ICU 49, ICU APIs return an empty string for this name choice.
|
|
|
|
* @deprecated ICU 49
|
|
|
|
*/
|
1999-12-28 23:39:02 +00:00
|
|
|
U_UNICODE_10_CHAR_NAME,
|
2011-12-15 21:43:35 +00:00
|
|
|
/** Standard or synthetic character name. @stable ICU 2.0 */
|
2002-02-14 05:36:48 +00:00
|
|
|
U_EXTENDED_CHAR_NAME,
|
2011-12-15 21:43:35 +00:00
|
|
|
/** Corrected name from NameAliases.txt. @stable ICU 4.4 */
|
|
|
|
U_CHAR_NAME_ALIAS,
|
|
|
|
/** @stable ICU 2.0 */
|
1999-12-28 23:39:02 +00:00
|
|
|
U_CHAR_NAME_CHOICE_COUNT
|
2002-08-21 19:12:24 +00:00
|
|
|
} UCharNameChoice;
|
1999-12-28 23:39:02 +00:00
|
|
|
|
2002-10-30 18:24:53 +00:00
|
|
|
/**
|
|
|
|
* Selector constants for u_getPropertyName() and
|
|
|
|
* u_getPropertyValueName(). These selectors are used to choose which
|
|
|
|
* name is returned for a given property or value. All properties and
|
|
|
|
* values have a long name. Most have a short name, but some do not.
|
|
|
|
* Unicode allows for additional names, beyond the long and short
|
|
|
|
* name, which would be indicated by U_LONG_PROPERTY_NAME + i, where
|
|
|
|
* i=1, 2,...
|
|
|
|
*
|
|
|
|
* @see u_getPropertyName()
|
|
|
|
* @see u_getPropertyValueName()
|
2004-03-26 19:42:04 +00:00
|
|
|
* @stable ICU 2.4
|
2002-10-30 18:24:53 +00:00
|
|
|
*/
|
2005-06-28 22:23:05 +00:00
|
|
|
typedef enum UPropertyNameChoice {
|
2002-10-30 18:24:53 +00:00
|
|
|
U_SHORT_PROPERTY_NAME,
|
|
|
|
U_LONG_PROPERTY_NAME,
|
|
|
|
U_PROPERTY_NAME_CHOICE_COUNT
|
|
|
|
} UPropertyNameChoice;
|
|
|
|
|
2002-07-04 16:46:36 +00:00
|
|
|
/**
|
|
|
|
* Decomposition Type constants.
|
|
|
|
*
|
|
|
|
* @see UCHAR_DECOMPOSITION_TYPE
|
2003-11-18 02:37:24 +00:00
|
|
|
* @stable ICU 2.2
|
2002-07-04 16:46:36 +00:00
|
|
|
*/
|
2005-06-28 22:23:05 +00:00
|
|
|
typedef enum UDecompositionType {
|
2011-12-23 04:20:35 +00:00
|
|
|
/*
|
|
|
|
* Note: UDecompositionType constants are parsed by preparseucd.py.
|
|
|
|
* It matches lines like
|
|
|
|
* U_DT_<Unicode Decomposition_Type value name>
|
|
|
|
*/
|
|
|
|
|
|
|
|
U_DT_NONE, /*[none]*/
|
2002-10-30 18:24:53 +00:00
|
|
|
U_DT_CANONICAL, /*[can]*/
|
|
|
|
U_DT_COMPAT, /*[com]*/
|
|
|
|
U_DT_CIRCLE, /*[enc]*/
|
|
|
|
U_DT_FINAL, /*[fin]*/
|
|
|
|
U_DT_FONT, /*[font]*/
|
|
|
|
U_DT_FRACTION, /*[fra]*/
|
|
|
|
U_DT_INITIAL, /*[init]*/
|
|
|
|
U_DT_ISOLATED, /*[iso]*/
|
|
|
|
U_DT_MEDIAL, /*[med]*/
|
|
|
|
U_DT_NARROW, /*[nar]*/
|
|
|
|
U_DT_NOBREAK, /*[nb]*/
|
|
|
|
U_DT_SMALL, /*[sml]*/
|
|
|
|
U_DT_SQUARE, /*[sqr]*/
|
|
|
|
U_DT_SUB, /*[sub]*/
|
|
|
|
U_DT_SUPER, /*[sup]*/
|
|
|
|
U_DT_VERTICAL, /*[vert]*/
|
|
|
|
U_DT_WIDE, /*[wide]*/
|
2002-07-04 16:46:36 +00:00
|
|
|
U_DT_COUNT /* 18 */
|
2002-08-21 19:12:24 +00:00
|
|
|
} UDecompositionType;
|
2002-07-04 16:46:36 +00:00
|
|
|
|
|
|
|
/**
|
|
|
|
* Joining Type constants.
|
|
|
|
*
|
|
|
|
* @see UCHAR_JOINING_TYPE
|
2003-11-18 02:37:24 +00:00
|
|
|
* @stable ICU 2.2
|
2002-07-04 16:46:36 +00:00
|
|
|
*/
|
2005-06-28 22:23:05 +00:00
|
|
|
typedef enum UJoiningType {
|
2011-12-23 04:20:35 +00:00
|
|
|
/*
|
|
|
|
* Note: UJoiningType constants are parsed by preparseucd.py.
|
|
|
|
* It matches lines like
|
|
|
|
* U_JT_<Unicode Joining_Type value name>
|
|
|
|
*/
|
|
|
|
|
|
|
|
U_JT_NON_JOINING, /*[U]*/
|
2002-10-30 18:24:53 +00:00
|
|
|
U_JT_JOIN_CAUSING, /*[C]*/
|
|
|
|
U_JT_DUAL_JOINING, /*[D]*/
|
|
|
|
U_JT_LEFT_JOINING, /*[L]*/
|
|
|
|
U_JT_RIGHT_JOINING, /*[R]*/
|
|
|
|
U_JT_TRANSPARENT, /*[T]*/
|
2002-07-04 16:46:36 +00:00
|
|
|
U_JT_COUNT /* 6 */
|
2002-08-21 19:12:24 +00:00
|
|
|
} UJoiningType;
|
2002-07-04 16:46:36 +00:00
|
|
|
|
|
|
|
/**
|
|
|
|
* Joining Group constants.
|
|
|
|
*
|
|
|
|
* @see UCHAR_JOINING_GROUP
|
2003-11-18 02:37:24 +00:00
|
|
|
* @stable ICU 2.2
|
2002-07-04 16:46:36 +00:00
|
|
|
*/
|
2005-06-28 22:23:05 +00:00
|
|
|
typedef enum UJoiningGroup {
|
2011-12-23 04:20:35 +00:00
|
|
|
/*
|
|
|
|
* Note: UJoiningGroup constants are parsed by preparseucd.py.
|
|
|
|
* It matches lines like
|
|
|
|
* U_JG_<Unicode Joining_Group value name>
|
|
|
|
*/
|
|
|
|
|
2002-07-04 16:46:36 +00:00
|
|
|
U_JG_NO_JOINING_GROUP,
|
|
|
|
U_JG_AIN,
|
|
|
|
U_JG_ALAPH,
|
|
|
|
U_JG_ALEF,
|
|
|
|
U_JG_BEH,
|
|
|
|
U_JG_BETH,
|
|
|
|
U_JG_DAL,
|
|
|
|
U_JG_DALATH_RISH,
|
|
|
|
U_JG_E,
|
|
|
|
U_JG_FEH,
|
|
|
|
U_JG_FINAL_SEMKATH,
|
|
|
|
U_JG_GAF,
|
|
|
|
U_JG_GAMAL,
|
|
|
|
U_JG_HAH,
|
2010-09-21 00:12:49 +00:00
|
|
|
U_JG_TEH_MARBUTA_GOAL, /**< @stable ICU 4.6 */
|
|
|
|
U_JG_HAMZA_ON_HEH_GOAL=U_JG_TEH_MARBUTA_GOAL,
|
2002-07-04 16:46:36 +00:00
|
|
|
U_JG_HE,
|
|
|
|
U_JG_HEH,
|
|
|
|
U_JG_HEH_GOAL,
|
|
|
|
U_JG_HETH,
|
|
|
|
U_JG_KAF,
|
|
|
|
U_JG_KAPH,
|
|
|
|
U_JG_KNOTTED_HEH,
|
|
|
|
U_JG_LAM,
|
|
|
|
U_JG_LAMADH,
|
|
|
|
U_JG_MEEM,
|
|
|
|
U_JG_MIM,
|
|
|
|
U_JG_NOON,
|
|
|
|
U_JG_NUN,
|
|
|
|
U_JG_PE,
|
|
|
|
U_JG_QAF,
|
|
|
|
U_JG_QAPH,
|
|
|
|
U_JG_REH,
|
|
|
|
U_JG_REVERSED_PE,
|
|
|
|
U_JG_SAD,
|
|
|
|
U_JG_SADHE,
|
|
|
|
U_JG_SEEN,
|
|
|
|
U_JG_SEMKATH,
|
|
|
|
U_JG_SHIN,
|
|
|
|
U_JG_SWASH_KAF,
|
|
|
|
U_JG_SYRIAC_WAW,
|
|
|
|
U_JG_TAH,
|
|
|
|
U_JG_TAW,
|
|
|
|
U_JG_TEH_MARBUTA,
|
|
|
|
U_JG_TETH,
|
|
|
|
U_JG_WAW,
|
|
|
|
U_JG_YEH,
|
|
|
|
U_JG_YEH_BARREE,
|
|
|
|
U_JG_YEH_WITH_TAIL,
|
|
|
|
U_JG_YUDH,
|
|
|
|
U_JG_YUDH_HE,
|
|
|
|
U_JG_ZAIN,
|
2004-11-02 07:28:07 +00:00
|
|
|
U_JG_FE, /**< @stable ICU 2.6 */
|
|
|
|
U_JG_KHAPH, /**< @stable ICU 2.6 */
|
|
|
|
U_JG_ZHAIN, /**< @stable ICU 2.6 */
|
2009-03-19 04:03:31 +00:00
|
|
|
U_JG_BURUSHASKI_YEH_BARREE, /**< @stable ICU 4.0 */
|
2010-09-21 00:12:49 +00:00
|
|
|
U_JG_FARSI_YEH, /**< @stable ICU 4.4 */
|
|
|
|
U_JG_NYA, /**< @stable ICU 4.4 */
|
2011-12-08 22:37:24 +00:00
|
|
|
U_JG_ROHINGYA_YEH, /**< @stable ICU 49 */
|
2003-03-04 00:42:54 +00:00
|
|
|
U_JG_COUNT
|
2002-08-21 19:12:24 +00:00
|
|
|
} UJoiningGroup;
|
2002-07-04 16:46:36 +00:00
|
|
|
|
2005-01-10 18:02:54 +00:00
|
|
|
/**
|
|
|
|
* Grapheme Cluster Break constants.
|
|
|
|
*
|
|
|
|
* @see UCHAR_GRAPHEME_CLUSTER_BREAK
|
2007-08-19 08:59:28 +00:00
|
|
|
* @stable ICU 3.4
|
2005-01-10 18:02:54 +00:00
|
|
|
*/
|
2005-06-28 22:23:05 +00:00
|
|
|
typedef enum UGraphemeClusterBreak {
|
2011-12-23 04:20:35 +00:00
|
|
|
/*
|
|
|
|
* Note: UGraphemeClusterBreak constants are parsed by preparseucd.py.
|
|
|
|
* It matches lines like
|
|
|
|
* U_GCB_<Unicode Grapheme_Cluster_Break value name>
|
|
|
|
*/
|
|
|
|
|
|
|
|
U_GCB_OTHER = 0, /*[XX]*/
|
2006-02-07 01:54:15 +00:00
|
|
|
U_GCB_CONTROL = 1, /*[CN]*/
|
|
|
|
U_GCB_CR = 2, /*[CR]*/
|
|
|
|
U_GCB_EXTEND = 3, /*[EX]*/
|
|
|
|
U_GCB_L = 4, /*[L]*/
|
|
|
|
U_GCB_LF = 5, /*[LF]*/
|
|
|
|
U_GCB_LV = 6, /*[LV]*/
|
|
|
|
U_GCB_LVT = 7, /*[LVT]*/
|
|
|
|
U_GCB_T = 8, /*[T]*/
|
|
|
|
U_GCB_V = 9, /*[V]*/
|
2008-04-04 22:47:43 +00:00
|
|
|
U_GCB_SPACING_MARK = 10, /*[SM]*/ /* from here on: new in Unicode 5.1/ICU 4.0 */
|
|
|
|
U_GCB_PREPEND = 11, /*[PP]*/
|
|
|
|
U_GCB_COUNT = 12
|
2005-01-10 18:02:54 +00:00
|
|
|
} UGraphemeClusterBreak;
|
|
|
|
|
|
|
|
/**
|
|
|
|
* Word Break constants.
|
|
|
|
* (UWordBreak is a pre-existing enum type in ubrk.h for word break status tags.)
|
|
|
|
*
|
|
|
|
* @see UCHAR_WORD_BREAK
|
2007-08-19 08:59:28 +00:00
|
|
|
* @stable ICU 3.4
|
2005-01-10 18:02:54 +00:00
|
|
|
*/
|
2005-06-28 22:23:05 +00:00
|
|
|
typedef enum UWordBreakValues {
|
2011-12-23 04:20:35 +00:00
|
|
|
/*
|
|
|
|
* Note: UWordBreakValues constants are parsed by preparseucd.py.
|
|
|
|
* It matches lines like
|
|
|
|
* U_WB_<Unicode Word_Break value name>
|
|
|
|
*/
|
|
|
|
|
|
|
|
U_WB_OTHER = 0, /*[XX]*/
|
2006-02-07 01:54:15 +00:00
|
|
|
U_WB_ALETTER = 1, /*[LE]*/
|
|
|
|
U_WB_FORMAT = 2, /*[FO]*/
|
|
|
|
U_WB_KATAKANA = 3, /*[KA]*/
|
|
|
|
U_WB_MIDLETTER = 4, /*[ML]*/
|
|
|
|
U_WB_MIDNUM = 5, /*[MN]*/
|
|
|
|
U_WB_NUMERIC = 6, /*[NU]*/
|
|
|
|
U_WB_EXTENDNUMLET = 7, /*[EX]*/
|
2008-04-04 22:47:43 +00:00
|
|
|
U_WB_CR = 8, /*[CR]*/ /* from here on: new in Unicode 5.1/ICU 4.0 */
|
|
|
|
U_WB_EXTEND = 9, /*[Extend]*/
|
|
|
|
U_WB_LF = 10, /*[LF]*/
|
|
|
|
U_WB_MIDNUMLET =11, /*[MB]*/
|
|
|
|
U_WB_NEWLINE =12, /*[NL]*/
|
|
|
|
U_WB_COUNT = 13
|
2005-01-10 18:02:54 +00:00
|
|
|
} UWordBreakValues;
|
|
|
|
|
|
|
|
/**
|
|
|
|
* Sentence Break constants.
|
|
|
|
*
|
|
|
|
* @see UCHAR_SENTENCE_BREAK
|
2007-08-19 08:59:28 +00:00
|
|
|
* @stable ICU 3.4
|
2005-01-10 18:02:54 +00:00
|
|
|
*/
|
2005-06-28 22:23:05 +00:00
|
|
|
typedef enum USentenceBreak {
|
2011-12-23 04:20:35 +00:00
|
|
|
/*
|
|
|
|
* Note: USentenceBreak constants are parsed by preparseucd.py.
|
|
|
|
* It matches lines like
|
|
|
|
* U_SB_<Unicode Sentence_Break value name>
|
|
|
|
*/
|
|
|
|
|
|
|
|
U_SB_OTHER = 0, /*[XX]*/
|
2006-02-07 01:54:15 +00:00
|
|
|
U_SB_ATERM = 1, /*[AT]*/
|
|
|
|
U_SB_CLOSE = 2, /*[CL]*/
|
|
|
|
U_SB_FORMAT = 3, /*[FO]*/
|
|
|
|
U_SB_LOWER = 4, /*[LO]*/
|
|
|
|
U_SB_NUMERIC = 5, /*[NU]*/
|
|
|
|
U_SB_OLETTER = 6, /*[LE]*/
|
|
|
|
U_SB_SEP = 7, /*[SE]*/
|
|
|
|
U_SB_SP = 8, /*[SP]*/
|
|
|
|
U_SB_STERM = 9, /*[ST]*/
|
2008-04-04 22:47:43 +00:00
|
|
|
U_SB_UPPER = 10, /*[UP]*/
|
|
|
|
U_SB_CR = 11, /*[CR]*/ /* from here on: new in Unicode 5.1/ICU 4.0 */
|
|
|
|
U_SB_EXTEND = 12, /*[EX]*/
|
|
|
|
U_SB_LF = 13, /*[LF]*/
|
|
|
|
U_SB_SCONTINUE = 14, /*[SC]*/
|
|
|
|
U_SB_COUNT = 15
|
2005-01-10 18:02:54 +00:00
|
|
|
} USentenceBreak;
|
|
|
|
|
2002-07-04 16:46:36 +00:00
|
|
|
/**
|
|
|
|
* Line Break constants.
|
|
|
|
*
|
|
|
|
* @see UCHAR_LINE_BREAK
|
2003-11-18 02:37:24 +00:00
|
|
|
* @stable ICU 2.2
|
2002-07-04 16:46:36 +00:00
|
|
|
*/
|
2005-06-28 22:23:05 +00:00
|
|
|
typedef enum ULineBreak {
|
2011-12-23 04:20:35 +00:00
|
|
|
/*
|
|
|
|
* Note: ULineBreak constants are parsed by preparseucd.py.
|
|
|
|
* It matches lines like
|
|
|
|
* U_LB_<Unicode Line_Break value name>
|
|
|
|
*/
|
|
|
|
|
|
|
|
U_LB_UNKNOWN = 0, /*[XX]*/
|
2006-02-07 01:54:15 +00:00
|
|
|
U_LB_AMBIGUOUS = 1, /*[AI]*/
|
|
|
|
U_LB_ALPHABETIC = 2, /*[AL]*/
|
|
|
|
U_LB_BREAK_BOTH = 3, /*[B2]*/
|
|
|
|
U_LB_BREAK_AFTER = 4, /*[BA]*/
|
|
|
|
U_LB_BREAK_BEFORE = 5, /*[BB]*/
|
|
|
|
U_LB_MANDATORY_BREAK = 6, /*[BK]*/
|
|
|
|
U_LB_CONTINGENT_BREAK = 7, /*[CB]*/
|
|
|
|
U_LB_CLOSE_PUNCTUATION = 8, /*[CL]*/
|
|
|
|
U_LB_COMBINING_MARK = 9, /*[CM]*/
|
|
|
|
U_LB_CARRIAGE_RETURN = 10, /*[CR]*/
|
|
|
|
U_LB_EXCLAMATION = 11, /*[EX]*/
|
|
|
|
U_LB_GLUE = 12, /*[GL]*/
|
|
|
|
U_LB_HYPHEN = 13, /*[HY]*/
|
|
|
|
U_LB_IDEOGRAPHIC = 14, /*[ID]*/
|
2006-07-31 20:52:01 +00:00
|
|
|
/** Renamed from the misspelled "inseperable" in Unicode 4.0.1/ICU 3.0 @stable ICU 3.0 */
|
2011-12-20 07:48:49 +00:00
|
|
|
U_LB_INSEPARABLE = 15, /*[IN]*/
|
|
|
|
U_LB_INSEPERABLE = U_LB_INSEPARABLE,
|
2006-02-07 01:54:15 +00:00
|
|
|
U_LB_INFIX_NUMERIC = 16, /*[IS]*/
|
|
|
|
U_LB_LINE_FEED = 17, /*[LF]*/
|
|
|
|
U_LB_NONSTARTER = 18, /*[NS]*/
|
|
|
|
U_LB_NUMERIC = 19, /*[NU]*/
|
|
|
|
U_LB_OPEN_PUNCTUATION = 20, /*[OP]*/
|
|
|
|
U_LB_POSTFIX_NUMERIC = 21, /*[PO]*/
|
|
|
|
U_LB_PREFIX_NUMERIC = 22, /*[PR]*/
|
|
|
|
U_LB_QUOTATION = 23, /*[QU]*/
|
|
|
|
U_LB_COMPLEX_CONTEXT = 24, /*[SA]*/
|
|
|
|
U_LB_SURROGATE = 25, /*[SG]*/
|
|
|
|
U_LB_SPACE = 26, /*[SP]*/
|
|
|
|
U_LB_BREAK_SYMBOLS = 27, /*[SY]*/
|
|
|
|
U_LB_ZWSPACE = 28, /*[ZW]*/
|
|
|
|
U_LB_NEXT_LINE = 29, /*[NL]*/ /* from here on: new in Unicode 4/ICU 2.6 */
|
|
|
|
U_LB_WORD_JOINER = 30, /*[WJ]*/
|
|
|
|
U_LB_H2 = 31, /*[H2]*/ /* from here on: new in Unicode 4.1/ICU 3.4 */
|
|
|
|
U_LB_H3 = 32, /*[H3]*/
|
|
|
|
U_LB_JL = 33, /*[JL]*/
|
|
|
|
U_LB_JT = 34, /*[JT]*/
|
|
|
|
U_LB_JV = 35, /*[JV]*/
|
2009-11-13 19:25:21 +00:00
|
|
|
U_LB_CLOSE_PARENTHESIS = 36, /*[CP]*/ /* new in Unicode 5.2/ICU 4.4 */
|
2011-12-08 22:37:24 +00:00
|
|
|
U_LB_CONDITIONAL_JAPANESE_STARTER = 37,/*[CJ]*/ /* new in Unicode 6.1/ICU 49 */
|
|
|
|
U_LB_HEBREW_LETTER = 38, /*[HL]*/ /* new in Unicode 6.1/ICU 49 */
|
|
|
|
U_LB_COUNT = 39
|
2002-08-21 19:12:24 +00:00
|
|
|
} ULineBreak;
|
2002-07-04 16:46:36 +00:00
|
|
|
|
2002-07-04 00:38:51 +00:00
|
|
|
/**
|
|
|
|
* Numeric Type constants.
|
|
|
|
*
|
|
|
|
* @see UCHAR_NUMERIC_TYPE
|
2003-11-18 02:37:24 +00:00
|
|
|
* @stable ICU 2.2
|
2002-07-04 00:38:51 +00:00
|
|
|
*/
|
2005-06-28 22:23:05 +00:00
|
|
|
typedef enum UNumericType {
|
2011-12-23 04:20:35 +00:00
|
|
|
/*
|
|
|
|
* Note: UNumericType constants are parsed by preparseucd.py.
|
|
|
|
* It matches lines like
|
|
|
|
* U_NT_<Unicode Numeric_Type value name>
|
|
|
|
*/
|
|
|
|
|
|
|
|
U_NT_NONE, /*[None]*/
|
2002-10-30 18:24:53 +00:00
|
|
|
U_NT_DECIMAL, /*[de]*/
|
|
|
|
U_NT_DIGIT, /*[di]*/
|
|
|
|
U_NT_NUMERIC, /*[nu]*/
|
2002-07-04 00:38:51 +00:00
|
|
|
U_NT_COUNT
|
2002-08-21 19:12:24 +00:00
|
|
|
} UNumericType;
|
2002-07-04 00:38:51 +00:00
|
|
|
|
2003-03-08 02:00:06 +00:00
|
|
|
/**
|
|
|
|
* Hangul Syllable Type constants.
|
|
|
|
*
|
|
|
|
* @see UCHAR_HANGUL_SYLLABLE_TYPE
|
2004-11-02 07:28:07 +00:00
|
|
|
* @stable ICU 2.6
|
2003-03-08 02:00:06 +00:00
|
|
|
*/
|
2005-06-28 22:23:05 +00:00
|
|
|
typedef enum UHangulSyllableType {
|
2011-12-23 04:20:35 +00:00
|
|
|
/*
|
|
|
|
* Note: UHangulSyllableType constants are parsed by preparseucd.py.
|
|
|
|
* It matches lines like
|
|
|
|
* U_HST_<Unicode Hangul_Syllable_Type value name>
|
|
|
|
*/
|
|
|
|
|
|
|
|
U_HST_NOT_APPLICABLE, /*[NA]*/
|
2003-03-08 02:00:06 +00:00
|
|
|
U_HST_LEADING_JAMO, /*[L]*/
|
|
|
|
U_HST_VOWEL_JAMO, /*[V]*/
|
|
|
|
U_HST_TRAILING_JAMO, /*[T]*/
|
|
|
|
U_HST_LV_SYLLABLE, /*[LV]*/
|
|
|
|
U_HST_LVT_SYLLABLE, /*[LVT]*/
|
|
|
|
U_HST_COUNT
|
|
|
|
} UHangulSyllableType;
|
|
|
|
|
2002-03-06 23:31:11 +00:00
|
|
|
/**
|
|
|
|
* Check a binary Unicode property for a code point.
|
|
|
|
*
|
|
|
|
* Unicode, especially in version 3.2, defines many more properties than the
|
|
|
|
* original set in UnicodeData.txt.
|
|
|
|
*
|
|
|
|
* The properties APIs are intended to reflect Unicode properties as defined
|
|
|
|
* in the Unicode Character Database (UCD) and Unicode Technical Reports (UTR).
|
2003-02-11 01:59:32 +00:00
|
|
|
* For details about the properties see http://www.unicode.org/ucd/ .
|
2002-03-06 23:31:11 +00:00
|
|
|
* For names of Unicode properties see the UCD file PropertyAliases.txt.
|
|
|
|
*
|
|
|
|
* Important: If ICU is built with UCD files from Unicode versions below 3.2,
|
|
|
|
* then properties marked with "new in Unicode 3.2" are not or not fully available.
|
|
|
|
*
|
|
|
|
* @param c Code point to test.
|
|
|
|
* @param which UProperty selector constant, identifies which binary property to check.
|
|
|
|
* Must be UCHAR_BINARY_START<=which<UCHAR_BINARY_LIMIT.
|
|
|
|
* @return TRUE or FALSE according to the binary Unicode property value for c.
|
2002-12-11 23:28:44 +00:00
|
|
|
* Also FALSE if 'which' is out of bounds or if the Unicode version
|
2002-03-06 23:31:11 +00:00
|
|
|
* does not have data for the property at all, or not for this code point.
|
|
|
|
*
|
|
|
|
* @see UProperty
|
2002-07-04 00:38:51 +00:00
|
|
|
* @see u_getIntPropertyValue
|
2002-03-06 23:31:11 +00:00
|
|
|
* @see u_getUnicodeVersion
|
2003-02-11 01:59:32 +00:00
|
|
|
* @stable ICU 2.1
|
2002-03-06 23:31:11 +00:00
|
|
|
*/
|
2004-03-26 19:42:04 +00:00
|
|
|
U_STABLE UBool U_EXPORT2
|
2002-03-12 19:09:08 +00:00
|
|
|
u_hasBinaryProperty(UChar32 c, UProperty which);
|
2002-03-06 23:31:11 +00:00
|
|
|
|
|
|
|
/**
|
|
|
|
* Check if a code point has the Alphabetic Unicode property.
|
|
|
|
* Same as u_hasBinaryProperty(c, UCHAR_ALPHABETIC).
|
|
|
|
* This is different from u_isalpha!
|
2002-07-03 12:05:56 +00:00
|
|
|
* @param c Code point to test
|
|
|
|
* @return true if the code point has the Alphabetic Unicode property, false otherwise
|
2002-03-06 23:31:11 +00:00
|
|
|
*
|
|
|
|
* @see UCHAR_ALPHABETIC
|
|
|
|
* @see u_isalpha
|
|
|
|
* @see u_hasBinaryProperty
|
2003-02-11 01:59:32 +00:00
|
|
|
* @stable ICU 2.1
|
2002-03-06 23:31:11 +00:00
|
|
|
*/
|
2004-03-26 19:42:04 +00:00
|
|
|
U_STABLE UBool U_EXPORT2
|
2002-03-12 19:09:08 +00:00
|
|
|
u_isUAlphabetic(UChar32 c);
|
2002-03-06 23:31:11 +00:00
|
|
|
|
|
|
|
/**
|
|
|
|
* Check if a code point has the Lowercase Unicode property.
|
|
|
|
* Same as u_hasBinaryProperty(c, UCHAR_LOWERCASE).
|
|
|
|
* This is different from u_islower!
|
2002-07-03 12:05:56 +00:00
|
|
|
* @param c Code point to test
|
|
|
|
* @return true if the code point has the Lowercase Unicode property, false otherwise
|
2002-03-06 23:31:11 +00:00
|
|
|
*
|
|
|
|
* @see UCHAR_LOWERCASE
|
|
|
|
* @see u_islower
|
|
|
|
* @see u_hasBinaryProperty
|
2003-02-11 01:59:32 +00:00
|
|
|
* @stable ICU 2.1
|
2002-03-06 23:31:11 +00:00
|
|
|
*/
|
2004-03-26 19:42:04 +00:00
|
|
|
U_STABLE UBool U_EXPORT2
|
2002-03-12 19:09:08 +00:00
|
|
|
u_isULowercase(UChar32 c);
|
2002-03-06 23:31:11 +00:00
|
|
|
|
|
|
|
/**
|
|
|
|
* Check if a code point has the Uppercase Unicode property.
|
|
|
|
* Same as u_hasBinaryProperty(c, UCHAR_UPPERCASE).
|
|
|
|
* This is different from u_isupper!
|
2002-07-03 12:05:56 +00:00
|
|
|
* @param c Code point to test
|
|
|
|
* @return true if the code point has the Uppercase Unicode property, false otherwise
|
2002-03-06 23:31:11 +00:00
|
|
|
*
|
|
|
|
* @see UCHAR_UPPERCASE
|
|
|
|
* @see u_isupper
|
|
|
|
* @see u_hasBinaryProperty
|
2003-02-11 01:59:32 +00:00
|
|
|
* @stable ICU 2.1
|
2002-03-06 23:31:11 +00:00
|
|
|
*/
|
2004-03-26 19:42:04 +00:00
|
|
|
U_STABLE UBool U_EXPORT2
|
2002-03-12 19:09:08 +00:00
|
|
|
u_isUUppercase(UChar32 c);
|
2002-03-06 23:31:11 +00:00
|
|
|
|
|
|
|
/**
|
|
|
|
* Check if a code point has the White_Space Unicode property.
|
|
|
|
* Same as u_hasBinaryProperty(c, UCHAR_WHITE_SPACE).
|
|
|
|
* This is different from both u_isspace and u_isWhitespace!
|
2003-02-11 01:59:32 +00:00
|
|
|
*
|
2003-05-30 21:12:00 +00:00
|
|
|
* Note: There are several ICU whitespace functions; please see the uchar.h
|
|
|
|
* file documentation for a detailed comparison.
|
2003-02-11 01:59:32 +00:00
|
|
|
*
|
2002-07-03 12:05:56 +00:00
|
|
|
* @param c Code point to test
|
|
|
|
* @return true if the code point has the White_Space Unicode property, false otherwise.
|
2002-03-06 23:31:11 +00:00
|
|
|
*
|
|
|
|
* @see UCHAR_WHITE_SPACE
|
|
|
|
* @see u_isWhitespace
|
|
|
|
* @see u_isspace
|
2003-02-09 21:02:26 +00:00
|
|
|
* @see u_isJavaSpaceChar
|
2002-03-06 23:31:11 +00:00
|
|
|
* @see u_hasBinaryProperty
|
2003-02-11 01:59:32 +00:00
|
|
|
* @stable ICU 2.1
|
2002-03-06 23:31:11 +00:00
|
|
|
*/
|
2004-03-26 19:42:04 +00:00
|
|
|
U_STABLE UBool U_EXPORT2
|
2002-03-12 19:09:08 +00:00
|
|
|
u_isUWhiteSpace(UChar32 c);
|
2002-03-06 23:31:11 +00:00
|
|
|
|
2002-07-04 00:38:51 +00:00
|
|
|
/**
|
|
|
|
* Get the property value for an enumerated or integer Unicode property for a code point.
|
2002-12-11 23:28:44 +00:00
|
|
|
* Also returns binary and mask property values.
|
2002-07-04 00:38:51 +00:00
|
|
|
*
|
|
|
|
* Unicode, especially in version 3.2, defines many more properties than the
|
|
|
|
* original set in UnicodeData.txt.
|
|
|
|
*
|
|
|
|
* The properties APIs are intended to reflect Unicode properties as defined
|
|
|
|
* in the Unicode Character Database (UCD) and Unicode Technical Reports (UTR).
|
|
|
|
* For details about the properties see http://www.unicode.org/ .
|
|
|
|
* For names of Unicode properties see the UCD file PropertyAliases.txt.
|
|
|
|
*
|
|
|
|
* Sample usage:
|
|
|
|
* UEastAsianWidth ea=(UEastAsianWidth)u_getIntPropertyValue(c, UCHAR_EAST_ASIAN_WIDTH);
|
|
|
|
* UBool b=(UBool)u_getIntPropertyValue(c, UCHAR_IDEOGRAPHIC);
|
|
|
|
*
|
|
|
|
* @param c Code point to test.
|
2002-10-30 18:24:53 +00:00
|
|
|
* @param which UProperty selector constant, identifies which property to check.
|
2002-07-04 00:38:51 +00:00
|
|
|
* Must be UCHAR_BINARY_START<=which<UCHAR_BINARY_LIMIT
|
2002-12-10 00:33:45 +00:00
|
|
|
* or UCHAR_INT_START<=which<UCHAR_INT_LIMIT
|
|
|
|
* or UCHAR_MASK_START<=which<UCHAR_MASK_LIMIT.
|
2002-07-04 00:38:51 +00:00
|
|
|
* @return Numeric value that is directly the property value or,
|
|
|
|
* for enumerated properties, corresponds to the numeric value of the enumerated
|
|
|
|
* constant of the respective property value enumeration type
|
|
|
|
* (cast to enum type if necessary).
|
|
|
|
* Returns 0 or 1 (for FALSE/TRUE) for binary Unicode properties.
|
2002-12-11 23:28:44 +00:00
|
|
|
* Returns a bit-mask for mask properties.
|
|
|
|
* Returns 0 if 'which' is out of bounds or if the Unicode version
|
2002-07-04 00:38:51 +00:00
|
|
|
* does not have data for the property at all, or not for this code point.
|
|
|
|
*
|
|
|
|
* @see UProperty
|
|
|
|
* @see u_hasBinaryProperty
|
|
|
|
* @see u_getIntPropertyMinValue
|
|
|
|
* @see u_getIntPropertyMaxValue
|
|
|
|
* @see u_getUnicodeVersion
|
2003-11-18 02:37:24 +00:00
|
|
|
* @stable ICU 2.2
|
2002-07-04 00:38:51 +00:00
|
|
|
*/
|
2004-03-26 19:42:04 +00:00
|
|
|
U_STABLE int32_t U_EXPORT2
|
2002-07-04 00:38:51 +00:00
|
|
|
u_getIntPropertyValue(UChar32 c, UProperty which);
|
|
|
|
|
|
|
|
/**
|
|
|
|
* Get the minimum value for an enumerated/integer/binary Unicode property.
|
|
|
|
* Can be used together with u_getIntPropertyMaxValue
|
|
|
|
* to allocate arrays of UnicodeSet or similar.
|
|
|
|
*
|
|
|
|
* @param which UProperty selector constant, identifies which binary property to check.
|
|
|
|
* Must be UCHAR_BINARY_START<=which<UCHAR_BINARY_LIMIT
|
2002-12-11 01:09:02 +00:00
|
|
|
* or UCHAR_INT_START<=which<UCHAR_INT_LIMIT.
|
2002-07-04 00:38:51 +00:00
|
|
|
* @return Minimum value returned by u_getIntPropertyValue for a Unicode property.
|
|
|
|
* 0 if the property selector is out of range.
|
|
|
|
*
|
|
|
|
* @see UProperty
|
|
|
|
* @see u_hasBinaryProperty
|
|
|
|
* @see u_getUnicodeVersion
|
|
|
|
* @see u_getIntPropertyMaxValue
|
|
|
|
* @see u_getIntPropertyValue
|
2003-11-18 02:37:24 +00:00
|
|
|
* @stable ICU 2.2
|
2002-07-04 00:38:51 +00:00
|
|
|
*/
|
2004-03-26 19:42:04 +00:00
|
|
|
U_STABLE int32_t U_EXPORT2
|
2002-07-04 00:38:51 +00:00
|
|
|
u_getIntPropertyMinValue(UProperty which);
|
|
|
|
|
|
|
|
/**
|
|
|
|
* Get the maximum value for an enumerated/integer/binary Unicode property.
|
|
|
|
* Can be used together with u_getIntPropertyMinValue
|
|
|
|
* to allocate arrays of UnicodeSet or similar.
|
|
|
|
*
|
|
|
|
* Examples for min/max values (for Unicode 3.2):
|
|
|
|
*
|
|
|
|
* - UCHAR_BIDI_CLASS: 0/18 (U_LEFT_TO_RIGHT/U_BOUNDARY_NEUTRAL)
|
2002-11-14 02:16:22 +00:00
|
|
|
* - UCHAR_SCRIPT: 0/45 (USCRIPT_COMMON/USCRIPT_TAGBANWA)
|
2002-07-04 00:38:51 +00:00
|
|
|
* - UCHAR_IDEOGRAPHIC: 0/1 (FALSE/TRUE)
|
|
|
|
*
|
2002-11-13 20:03:11 +00:00
|
|
|
* For undefined UProperty constant values, min/max values will be 0/-1.
|
2002-11-14 02:16:22 +00:00
|
|
|
*
|
2002-07-04 00:38:51 +00:00
|
|
|
* @param which UProperty selector constant, identifies which binary property to check.
|
|
|
|
* Must be UCHAR_BINARY_START<=which<UCHAR_BINARY_LIMIT
|
2002-12-11 01:09:02 +00:00
|
|
|
* or UCHAR_INT_START<=which<UCHAR_INT_LIMIT.
|
2002-07-04 00:38:51 +00:00
|
|
|
* @return Maximum value returned by u_getIntPropertyValue for a Unicode property.
|
2002-11-13 20:03:11 +00:00
|
|
|
* <=0 if the property selector is out of range.
|
2002-07-04 00:38:51 +00:00
|
|
|
*
|
|
|
|
* @see UProperty
|
|
|
|
* @see u_hasBinaryProperty
|
|
|
|
* @see u_getUnicodeVersion
|
|
|
|
* @see u_getIntPropertyMaxValue
|
|
|
|
* @see u_getIntPropertyValue
|
2003-11-18 02:37:24 +00:00
|
|
|
* @stable ICU 2.2
|
2002-07-04 00:38:51 +00:00
|
|
|
*/
|
2004-03-26 19:42:04 +00:00
|
|
|
U_STABLE int32_t U_EXPORT2
|
2002-07-04 00:38:51 +00:00
|
|
|
u_getIntPropertyMaxValue(UProperty which);
|
|
|
|
|
|
|
|
/**
|
|
|
|
* Get the numeric value for a Unicode code point as defined in the
|
|
|
|
* Unicode Character Database.
|
|
|
|
*
|
|
|
|
* A "double" return type is necessary because
|
|
|
|
* some numeric values are fractions, negative, or too large for int32_t.
|
|
|
|
*
|
|
|
|
* For characters without any numeric values in the Unicode Character Database,
|
|
|
|
* this function will return U_NO_NUMERIC_VALUE.
|
2011-12-15 23:29:52 +00:00
|
|
|
* Note: This is different from the Unicode Standard which specifies NaN as the default value.
|
|
|
|
* (NaN is not available on all platforms.)
|
2002-07-04 00:38:51 +00:00
|
|
|
*
|
2003-02-11 23:27:40 +00:00
|
|
|
* Similar to java.lang.Character.getNumericValue(), but u_getNumericValue()
|
2003-02-13 01:46:14 +00:00
|
|
|
* also supports negative values, large values, and fractions,
|
|
|
|
* while Java's getNumericValue() returns values 10..35 for ASCII letters.
|
2003-02-11 23:27:40 +00:00
|
|
|
*
|
2002-07-04 00:38:51 +00:00
|
|
|
* @param c Code point to get the numeric value for.
|
|
|
|
* @return Numeric value of c, or U_NO_NUMERIC_VALUE if none is defined.
|
|
|
|
*
|
|
|
|
* @see U_NO_NUMERIC_VALUE
|
2003-11-18 02:37:24 +00:00
|
|
|
* @stable ICU 2.2
|
2002-07-04 00:38:51 +00:00
|
|
|
*/
|
2004-03-26 19:42:04 +00:00
|
|
|
U_STABLE double U_EXPORT2
|
2002-07-04 00:38:51 +00:00
|
|
|
u_getNumericValue(UChar32 c);
|
|
|
|
|
|
|
|
/**
|
|
|
|
* Special value that is returned by u_getNumericValue when
|
|
|
|
* no numeric value is defined for a code point.
|
|
|
|
*
|
|
|
|
* @see u_getNumericValue
|
2003-11-18 02:37:24 +00:00
|
|
|
* @stable ICU 2.2
|
2002-07-04 00:38:51 +00:00
|
|
|
*/
|
|
|
|
#define U_NO_NUMERIC_VALUE ((double)-123456789.)
|
|
|
|
|
1999-12-28 23:39:02 +00:00
|
|
|
/**
|
2003-02-11 01:59:32 +00:00
|
|
|
* Determines whether the specified code point has the general category "Ll"
|
|
|
|
* (lowercase letter).
|
1999-12-28 23:39:02 +00:00
|
|
|
*
|
2003-02-11 01:59:32 +00:00
|
|
|
* Same as java.lang.Character.isLowerCase().
|
|
|
|
*
|
|
|
|
* This misses some characters that are also lowercase but
|
|
|
|
* have a different general category value.
|
|
|
|
* In order to include those, use UCHAR_LOWERCASE.
|
|
|
|
*
|
2003-04-24 23:09:26 +00:00
|
|
|
* In addition to being equivalent to a Java function, this also serves
|
|
|
|
* as a C/POSIX migration function.
|
|
|
|
* See the comments about C/POSIX character classification functions in the
|
|
|
|
* documentation at the top of this header file.
|
|
|
|
*
|
2003-02-11 01:59:32 +00:00
|
|
|
* @param c the code point to be tested
|
|
|
|
* @return TRUE if the code point is an Ll lowercase letter
|
|
|
|
*
|
|
|
|
* @see UCHAR_LOWERCASE
|
2001-11-09 18:17:40 +00:00
|
|
|
* @see u_isupper
|
|
|
|
* @see u_istitle
|
2002-12-04 23:39:56 +00:00
|
|
|
* @stable ICU 2.0
|
1999-12-28 23:39:02 +00:00
|
|
|
*/
|
2004-03-26 19:42:04 +00:00
|
|
|
U_STABLE UBool U_EXPORT2
|
2000-02-03 19:54:49 +00:00
|
|
|
u_islower(UChar32 c);
|
1999-12-28 23:39:02 +00:00
|
|
|
|
|
|
|
/**
|
2003-02-11 01:59:32 +00:00
|
|
|
* Determines whether the specified code point has the general category "Lu"
|
|
|
|
* (uppercase letter).
|
1999-12-28 23:39:02 +00:00
|
|
|
*
|
2003-02-11 01:59:32 +00:00
|
|
|
* Same as java.lang.Character.isUpperCase().
|
|
|
|
*
|
|
|
|
* This misses some characters that are also uppercase but
|
|
|
|
* have a different general category value.
|
|
|
|
* In order to include those, use UCHAR_UPPERCASE.
|
|
|
|
*
|
2003-04-24 23:09:26 +00:00
|
|
|
* In addition to being equivalent to a Java function, this also serves
|
|
|
|
* as a C/POSIX migration function.
|
|
|
|
* See the comments about C/POSIX character classification functions in the
|
|
|
|
* documentation at the top of this header file.
|
|
|
|
*
|
2003-02-11 01:59:32 +00:00
|
|
|
* @param c the code point to be tested
|
|
|
|
* @return TRUE if the code point is an Lu uppercase letter
|
|
|
|
*
|
|
|
|
* @see UCHAR_UPPERCASE
|
2001-11-09 18:17:40 +00:00
|
|
|
* @see u_islower
|
1999-12-28 23:39:02 +00:00
|
|
|
* @see u_istitle
|
2001-11-09 18:17:40 +00:00
|
|
|
* @see u_tolower
|
2002-12-04 23:39:56 +00:00
|
|
|
* @stable ICU 2.0
|
1999-12-28 23:39:02 +00:00
|
|
|
*/
|
2004-03-26 19:42:04 +00:00
|
|
|
U_STABLE UBool U_EXPORT2
|
2000-02-03 19:54:49 +00:00
|
|
|
u_isupper(UChar32 c);
|
1999-12-28 23:39:02 +00:00
|
|
|
|
|
|
|
/**
|
2003-02-11 01:59:32 +00:00
|
|
|
* Determines whether the specified code point is a titlecase letter.
|
|
|
|
* True for general category "Lt" (titlecase letter).
|
|
|
|
*
|
|
|
|
* Same as java.lang.Character.isTitleCase().
|
|
|
|
*
|
|
|
|
* @param c the code point to be tested
|
|
|
|
* @return TRUE if the code point is an Lt titlecase letter
|
1999-12-28 23:39:02 +00:00
|
|
|
*
|
2001-11-09 18:17:40 +00:00
|
|
|
* @see u_isupper
|
|
|
|
* @see u_islower
|
|
|
|
* @see u_totitle
|
2002-12-04 23:39:56 +00:00
|
|
|
* @stable ICU 2.0
|
1999-12-28 23:39:02 +00:00
|
|
|
*/
|
2004-03-26 19:42:04 +00:00
|
|
|
U_STABLE UBool U_EXPORT2
|
2000-02-03 19:54:49 +00:00
|
|
|
u_istitle(UChar32 c);
|
1999-12-28 23:39:02 +00:00
|
|
|
|
|
|
|
/**
|
2003-02-09 21:02:26 +00:00
|
|
|
* Determines whether the specified code point is a digit character according to Java.
|
|
|
|
* True for characters with general category "Nd" (decimal digit numbers).
|
2003-04-09 19:04:01 +00:00
|
|
|
* Beginning with Unicode 4, this is the same as
|
|
|
|
* testing for the Numeric_Type of Decimal.
|
2003-02-09 21:02:26 +00:00
|
|
|
*
|
|
|
|
* Same as java.lang.Character.isDigit().
|
|
|
|
*
|
2003-04-24 23:09:26 +00:00
|
|
|
* In addition to being equivalent to a Java function, this also serves
|
|
|
|
* as a C/POSIX migration function.
|
|
|
|
* See the comments about C/POSIX character classification functions in the
|
|
|
|
* documentation at the top of this header file.
|
|
|
|
*
|
2003-02-09 21:02:26 +00:00
|
|
|
* @param c the code point to be tested
|
|
|
|
* @return TRUE if the code point is a digit character according to Character.isDigit()
|
2001-01-23 23:45:21 +00:00
|
|
|
*
|
2002-12-04 23:39:56 +00:00
|
|
|
* @stable ICU 2.0
|
1999-12-28 23:39:02 +00:00
|
|
|
*/
|
2004-03-26 19:42:04 +00:00
|
|
|
U_STABLE UBool U_EXPORT2
|
2000-02-03 19:54:49 +00:00
|
|
|
u_isdigit(UChar32 c);
|
1999-12-28 23:39:02 +00:00
|
|
|
|
2003-02-11 01:59:32 +00:00
|
|
|
/**
|
|
|
|
* Determines whether the specified code point is a letter character.
|
|
|
|
* True for general categories "L" (letters).
|
|
|
|
*
|
|
|
|
* Same as java.lang.Character.isLetter().
|
|
|
|
*
|
2003-04-24 23:09:26 +00:00
|
|
|
* In addition to being equivalent to a Java function, this also serves
|
|
|
|
* as a C/POSIX migration function.
|
|
|
|
* See the comments about C/POSIX character classification functions in the
|
|
|
|
* documentation at the top of this header file.
|
|
|
|
*
|
2003-02-11 01:59:32 +00:00
|
|
|
* @param c the code point to be tested
|
|
|
|
* @return TRUE if the code point is a letter character
|
|
|
|
*
|
|
|
|
* @see u_isdigit
|
|
|
|
* @see u_isalnum
|
|
|
|
* @stable ICU 2.0
|
|
|
|
*/
|
2004-03-26 19:42:04 +00:00
|
|
|
U_STABLE UBool U_EXPORT2
|
2003-02-11 01:59:32 +00:00
|
|
|
u_isalpha(UChar32 c);
|
|
|
|
|
1999-12-28 23:39:02 +00:00
|
|
|
/**
|
2003-02-09 21:02:26 +00:00
|
|
|
* Determines whether the specified code point is an alphanumeric character
|
|
|
|
* (letter or digit) according to Java.
|
|
|
|
* True for characters with general categories
|
|
|
|
* "L" (letters) and "Nd" (decimal digit numbers).
|
|
|
|
*
|
|
|
|
* Same as java.lang.Character.isLetterOrDigit().
|
|
|
|
*
|
2003-04-24 23:09:26 +00:00
|
|
|
* In addition to being equivalent to a Java function, this also serves
|
|
|
|
* as a C/POSIX migration function.
|
|
|
|
* See the comments about C/POSIX character classification functions in the
|
|
|
|
* documentation at the top of this header file.
|
|
|
|
*
|
2003-02-09 21:02:26 +00:00
|
|
|
* @param c the code point to be tested
|
|
|
|
* @return TRUE if the code point is an alphanumeric character according to Character.isLetterOrDigit()
|
1999-12-28 23:39:02 +00:00
|
|
|
*
|
2002-12-04 23:39:56 +00:00
|
|
|
* @stable ICU 2.0
|
1999-12-28 23:39:02 +00:00
|
|
|
*/
|
2004-03-26 19:42:04 +00:00
|
|
|
U_STABLE UBool U_EXPORT2
|
2000-02-03 19:54:49 +00:00
|
|
|
u_isalnum(UChar32 c);
|
1999-12-28 23:39:02 +00:00
|
|
|
|
2003-04-24 23:09:26 +00:00
|
|
|
/**
|
|
|
|
* Determines whether the specified code point is a hexadecimal digit.
|
|
|
|
* This is equivalent to u_digit(c, 16)>=0.
|
|
|
|
* True for characters with general category "Nd" (decimal digit numbers)
|
|
|
|
* as well as Latin letters a-f and A-F in both ASCII and Fullwidth ASCII.
|
|
|
|
* (That is, for letters with code points
|
|
|
|
* 0041..0046, 0061..0066, FF21..FF26, FF41..FF46.)
|
|
|
|
*
|
|
|
|
* In order to narrow the definition of hexadecimal digits to only ASCII
|
|
|
|
* characters, use (c<=0x7f && u_isxdigit(c)).
|
|
|
|
*
|
|
|
|
* This is a C/POSIX migration function.
|
|
|
|
* See the comments about C/POSIX character classification functions in the
|
|
|
|
* documentation at the top of this header file.
|
|
|
|
*
|
|
|
|
* @param c the code point to be tested
|
|
|
|
* @return TRUE if the code point is a hexadecimal digit
|
|
|
|
*
|
2004-11-02 07:28:07 +00:00
|
|
|
* @stable ICU 2.6
|
2003-04-24 23:09:26 +00:00
|
|
|
*/
|
2004-11-02 07:28:07 +00:00
|
|
|
U_STABLE UBool U_EXPORT2
|
2003-04-24 23:09:26 +00:00
|
|
|
u_isxdigit(UChar32 c);
|
|
|
|
|
|
|
|
/**
|
|
|
|
* Determines whether the specified code point is a punctuation character.
|
|
|
|
* True for characters with general categories "P" (punctuation).
|
|
|
|
*
|
|
|
|
* This is a C/POSIX migration function.
|
|
|
|
* See the comments about C/POSIX character classification functions in the
|
|
|
|
* documentation at the top of this header file.
|
|
|
|
*
|
|
|
|
* @param c the code point to be tested
|
|
|
|
* @return TRUE if the code point is a punctuation character
|
|
|
|
*
|
2004-11-02 07:28:07 +00:00
|
|
|
* @stable ICU 2.6
|
2003-04-24 23:09:26 +00:00
|
|
|
*/
|
2004-11-02 07:28:07 +00:00
|
|
|
U_STABLE UBool U_EXPORT2
|
2003-04-24 23:09:26 +00:00
|
|
|
u_ispunct(UChar32 c);
|
|
|
|
|
|
|
|
/**
|
|
|
|
* Determines whether the specified code point is a "graphic" character
|
|
|
|
* (printable, excluding spaces).
|
|
|
|
* TRUE for all characters except those with general categories
|
|
|
|
* "Cc" (control codes), "Cf" (format controls), "Cs" (surrogates),
|
|
|
|
* "Cn" (unassigned), and "Z" (separators).
|
|
|
|
*
|
|
|
|
* This is a C/POSIX migration function.
|
|
|
|
* See the comments about C/POSIX character classification functions in the
|
|
|
|
* documentation at the top of this header file.
|
|
|
|
*
|
|
|
|
* @param c the code point to be tested
|
|
|
|
* @return TRUE if the code point is a "graphic" character
|
|
|
|
*
|
2004-11-02 07:28:07 +00:00
|
|
|
* @stable ICU 2.6
|
2003-04-24 23:09:26 +00:00
|
|
|
*/
|
2004-11-02 07:28:07 +00:00
|
|
|
U_STABLE UBool U_EXPORT2
|
2003-04-24 23:09:26 +00:00
|
|
|
u_isgraph(UChar32 c);
|
|
|
|
|
|
|
|
/**
|
|
|
|
* Determines whether the specified code point is a "blank" or "horizontal space",
|
|
|
|
* a character that visibly separates words on a line.
|
|
|
|
* The following are equivalent definitions:
|
|
|
|
*
|
|
|
|
* TRUE for Unicode White_Space characters except for "vertical space controls"
|
2003-05-30 21:12:00 +00:00
|
|
|
* where "vertical space controls" are the following characters:
|
2003-04-24 23:09:26 +00:00
|
|
|
* U+000A (LF) U+000B (VT) U+000C (FF) U+000D (CR) U+0085 (NEL) U+2028 (LS) U+2029 (PS)
|
|
|
|
*
|
|
|
|
* same as
|
|
|
|
*
|
|
|
|
* TRUE for U+0009 (TAB) and characters with general category "Zs" (space separators)
|
|
|
|
* except Zero Width Space (ZWSP, U+200B).
|
|
|
|
*
|
2003-05-30 21:12:00 +00:00
|
|
|
* Note: There are several ICU whitespace functions; please see the uchar.h
|
|
|
|
* file documentation for a detailed comparison.
|
2003-04-24 23:09:26 +00:00
|
|
|
*
|
|
|
|
* This is a C/POSIX migration function.
|
|
|
|
* See the comments about C/POSIX character classification functions in the
|
|
|
|
* documentation at the top of this header file.
|
|
|
|
*
|
|
|
|
* @param c the code point to be tested
|
|
|
|
* @return TRUE if the code point is a "blank"
|
|
|
|
*
|
2004-11-02 07:28:07 +00:00
|
|
|
* @stable ICU 2.6
|
2003-04-24 23:09:26 +00:00
|
|
|
*/
|
2004-11-02 07:28:07 +00:00
|
|
|
U_STABLE UBool U_EXPORT2
|
2003-04-24 23:09:26 +00:00
|
|
|
u_isblank(UChar32 c);
|
|
|
|
|
1999-12-28 23:39:02 +00:00
|
|
|
/**
|
2003-02-11 01:59:32 +00:00
|
|
|
* Determines whether the specified code point is "defined",
|
|
|
|
* which usually means that it is assigned a character.
|
|
|
|
* True for general categories other than "Cn" (other, not assigned),
|
|
|
|
* i.e., true for all code points mentioned in UnicodeData.txt.
|
1999-12-28 23:39:02 +00:00
|
|
|
*
|
2003-04-24 23:09:26 +00:00
|
|
|
* Note that non-character code points (e.g., U+FDD0) are not "defined"
|
|
|
|
* (they are Cn), but surrogate code points are "defined" (Cs).
|
2003-02-11 01:59:32 +00:00
|
|
|
*
|
|
|
|
* Same as java.lang.Character.isDefined().
|
|
|
|
*
|
|
|
|
* @param c the code point to be tested
|
|
|
|
* @return TRUE if the code point is assigned a character
|
1999-12-28 23:39:02 +00:00
|
|
|
*
|
2001-11-09 18:17:40 +00:00
|
|
|
* @see u_isdigit
|
|
|
|
* @see u_isalpha
|
|
|
|
* @see u_isalnum
|
|
|
|
* @see u_isupper
|
|
|
|
* @see u_islower
|
|
|
|
* @see u_istitle
|
2002-12-04 23:39:56 +00:00
|
|
|
* @stable ICU 2.0
|
1999-12-28 23:39:02 +00:00
|
|
|
*/
|
2004-03-26 19:42:04 +00:00
|
|
|
U_STABLE UBool U_EXPORT2
|
2000-02-03 19:54:49 +00:00
|
|
|
u_isdefined(UChar32 c);
|
1999-12-28 23:39:02 +00:00
|
|
|
|
|
|
|
/**
|
|
|
|
* Determines if the specified character is a space character or not.
|
2003-02-11 01:59:32 +00:00
|
|
|
*
|
2003-05-30 21:12:00 +00:00
|
|
|
* Note: There are several ICU whitespace functions; please see the uchar.h
|
|
|
|
* file documentation for a detailed comparison.
|
2003-04-24 23:09:26 +00:00
|
|
|
*
|
|
|
|
* This is a C/POSIX migration function.
|
|
|
|
* See the comments about C/POSIX character classification functions in the
|
|
|
|
* documentation at the top of this header file.
|
1999-12-28 23:39:02 +00:00
|
|
|
*
|
2002-07-03 12:05:56 +00:00
|
|
|
* @param c the character to be tested
|
1999-12-28 23:39:02 +00:00
|
|
|
* @return true if the character is a space character; false otherwise.
|
2003-02-09 21:02:26 +00:00
|
|
|
*
|
|
|
|
* @see u_isJavaSpaceChar
|
|
|
|
* @see u_isWhitespace
|
|
|
|
* @see u_isUWhiteSpace
|
2002-12-04 23:39:56 +00:00
|
|
|
* @stable ICU 2.0
|
1999-12-28 23:39:02 +00:00
|
|
|
*/
|
2004-03-26 19:42:04 +00:00
|
|
|
U_STABLE UBool U_EXPORT2
|
2000-02-03 19:54:49 +00:00
|
|
|
u_isspace(UChar32 c);
|
1999-12-28 23:39:02 +00:00
|
|
|
|
2000-05-18 17:40:19 +00:00
|
|
|
/**
|
2003-02-09 21:02:26 +00:00
|
|
|
* Determine if the specified code point is a space character according to Java.
|
|
|
|
* True for characters with general categories "Z" (separators),
|
|
|
|
* which does not include control codes (e.g., TAB or Line Feed).
|
|
|
|
*
|
|
|
|
* Same as java.lang.Character.isSpaceChar().
|
|
|
|
*
|
2003-05-30 21:12:00 +00:00
|
|
|
* Note: There are several ICU whitespace functions; please see the uchar.h
|
|
|
|
* file documentation for a detailed comparison.
|
2003-02-11 01:59:32 +00:00
|
|
|
*
|
2003-02-09 21:02:26 +00:00
|
|
|
* @param c the code point to be tested
|
|
|
|
* @return TRUE if the code point is a space character according to Character.isSpaceChar()
|
|
|
|
*
|
|
|
|
* @see u_isspace
|
|
|
|
* @see u_isWhitespace
|
|
|
|
* @see u_isUWhiteSpace
|
2004-11-02 07:28:07 +00:00
|
|
|
* @stable ICU 2.6
|
2003-02-09 21:02:26 +00:00
|
|
|
*/
|
2004-11-02 07:28:07 +00:00
|
|
|
U_STABLE UBool U_EXPORT2
|
2003-02-09 21:02:26 +00:00
|
|
|
u_isJavaSpaceChar(UChar32 c);
|
|
|
|
|
|
|
|
/**
|
|
|
|
* Determines if the specified code point is a whitespace character according to Java/ICU.
|
|
|
|
* A character is considered to be a Java whitespace character if and only
|
2000-05-18 17:40:19 +00:00
|
|
|
* if it satisfies one of the following criteria:
|
|
|
|
*
|
2010-02-26 20:12:09 +00:00
|
|
|
* - It is a Unicode Separator character (categories "Z" = "Zs" or "Zl" or "Zp"), but is not
|
|
|
|
* also a non-breaking space (U+00A0 NBSP or U+2007 Figure Space or U+202F Narrow NBSP).
|
2003-02-09 21:02:26 +00:00
|
|
|
* - It is U+0009 HORIZONTAL TABULATION.
|
|
|
|
* - It is U+000A LINE FEED.
|
|
|
|
* - It is U+000B VERTICAL TABULATION.
|
|
|
|
* - It is U+000C FORM FEED.
|
|
|
|
* - It is U+000D CARRIAGE RETURN.
|
|
|
|
* - It is U+001C FILE SEPARATOR.
|
|
|
|
* - It is U+001D GROUP SEPARATOR.
|
|
|
|
* - It is U+001E RECORD SEPARATOR.
|
|
|
|
* - It is U+001F UNIT SEPARATOR.
|
|
|
|
*
|
2010-02-26 20:12:09 +00:00
|
|
|
* This API tries to sync with the semantics of Java's
|
|
|
|
* java.lang.Character.isWhitespace(), but it may not return
|
|
|
|
* the exact same results because of the Unicode version
|
|
|
|
* difference.
|
|
|
|
*
|
|
|
|
* Note: Unicode 4.0.1 changed U+200B ZERO WIDTH SPACE from a Space Separator (Zs)
|
|
|
|
* to a Format Control (Cf). Since then, isWhitespace(0x200b) returns false.
|
|
|
|
* See http://www.unicode.org/versions/Unicode4.0.1/
|
2003-02-09 21:02:26 +00:00
|
|
|
*
|
2003-05-30 21:12:00 +00:00
|
|
|
* Note: There are several ICU whitespace functions; please see the uchar.h
|
|
|
|
* file documentation for a detailed comparison.
|
2003-02-11 01:59:32 +00:00
|
|
|
*
|
2003-02-09 21:02:26 +00:00
|
|
|
* @param c the code point to be tested
|
|
|
|
* @return TRUE if the code point is a whitespace character according to Java/ICU
|
|
|
|
*
|
|
|
|
* @see u_isspace
|
|
|
|
* @see u_isJavaSpaceChar
|
|
|
|
* @see u_isUWhiteSpace
|
2002-12-04 23:39:56 +00:00
|
|
|
* @stable ICU 2.0
|
2000-05-18 17:40:19 +00:00
|
|
|
*/
|
2004-03-26 19:42:04 +00:00
|
|
|
U_STABLE UBool U_EXPORT2
|
2000-05-18 17:40:19 +00:00
|
|
|
u_isWhitespace(UChar32 c);
|
|
|
|
|
1999-12-28 23:39:02 +00:00
|
|
|
/**
|
2003-02-11 01:59:32 +00:00
|
|
|
* Determines whether the specified code point is a control character
|
|
|
|
* (as defined by this function).
|
2001-03-17 01:56:34 +00:00
|
|
|
* A control character is one of the following:
|
|
|
|
* - ISO 8-bit control character (U+0000..U+001f and U+007f..U+009f)
|
|
|
|
* - U_CONTROL_CHAR (Cc)
|
|
|
|
* - U_FORMAT_CHAR (Cf)
|
|
|
|
* - U_LINE_SEPARATOR (Zl)
|
|
|
|
* - U_PARAGRAPH_SEPARATOR (Zp)
|
1999-12-28 23:39:02 +00:00
|
|
|
*
|
2003-04-24 23:09:26 +00:00
|
|
|
* This is a C/POSIX migration function.
|
|
|
|
* See the comments about C/POSIX character classification functions in the
|
|
|
|
* documentation at the top of this header file.
|
|
|
|
*
|
2003-02-11 01:59:32 +00:00
|
|
|
* @param c the code point to be tested
|
|
|
|
* @return TRUE if the code point is a control character
|
1999-12-28 23:39:02 +00:00
|
|
|
*
|
2003-02-11 01:59:32 +00:00
|
|
|
* @see UCHAR_DEFAULT_IGNORABLE_CODE_POINT
|
2001-11-09 18:17:40 +00:00
|
|
|
* @see u_isprint
|
2002-12-04 23:39:56 +00:00
|
|
|
* @stable ICU 2.0
|
1999-12-28 23:39:02 +00:00
|
|
|
*/
|
2004-03-26 19:42:04 +00:00
|
|
|
U_STABLE UBool U_EXPORT2
|
2000-02-03 19:54:49 +00:00
|
|
|
u_iscntrl(UChar32 c);
|
1999-12-28 23:39:02 +00:00
|
|
|
|
2003-02-09 21:02:26 +00:00
|
|
|
/**
|
|
|
|
* Determines whether the specified code point is an ISO control code.
|
2003-02-11 01:59:32 +00:00
|
|
|
* True for U+0000..U+001f and U+007f..U+009f (general category "Cc").
|
2003-02-09 21:02:26 +00:00
|
|
|
*
|
|
|
|
* Same as java.lang.Character.isISOControl().
|
|
|
|
*
|
|
|
|
* @param c the code point to be tested
|
|
|
|
* @return TRUE if the code point is an ISO control code
|
|
|
|
*
|
|
|
|
* @see u_iscntrl
|
2004-11-02 07:28:07 +00:00
|
|
|
* @stable ICU 2.6
|
2003-02-09 21:02:26 +00:00
|
|
|
*/
|
2004-11-02 07:28:07 +00:00
|
|
|
U_STABLE UBool U_EXPORT2
|
2003-02-09 21:02:26 +00:00
|
|
|
u_isISOControl(UChar32 c);
|
1999-12-28 23:39:02 +00:00
|
|
|
|
|
|
|
/**
|
2003-02-11 01:59:32 +00:00
|
|
|
* Determines whether the specified code point is a printable character.
|
|
|
|
* True for general categories <em>other</em> than "C" (controls).
|
1999-12-28 23:39:02 +00:00
|
|
|
*
|
2003-04-24 23:09:26 +00:00
|
|
|
* This is a C/POSIX migration function.
|
|
|
|
* See the comments about C/POSIX character classification functions in the
|
|
|
|
* documentation at the top of this header file.
|
|
|
|
*
|
2003-02-11 01:59:32 +00:00
|
|
|
* @param c the code point to be tested
|
|
|
|
* @return TRUE if the code point is a printable character
|
1999-12-28 23:39:02 +00:00
|
|
|
*
|
2003-02-11 01:59:32 +00:00
|
|
|
* @see UCHAR_DEFAULT_IGNORABLE_CODE_POINT
|
2001-11-09 18:17:40 +00:00
|
|
|
* @see u_iscntrl
|
2002-12-04 23:39:56 +00:00
|
|
|
* @stable ICU 2.0
|
1999-12-28 23:39:02 +00:00
|
|
|
*/
|
2004-03-26 19:42:04 +00:00
|
|
|
U_STABLE UBool U_EXPORT2
|
2000-02-03 19:54:49 +00:00
|
|
|
u_isprint(UChar32 c);
|
1999-12-28 23:39:02 +00:00
|
|
|
|
|
|
|
/**
|
2003-02-11 01:59:32 +00:00
|
|
|
* Determines whether the specified code point is a base character.
|
|
|
|
* True for general categories "L" (letters), "N" (numbers),
|
|
|
|
* "Mc" (spacing combining marks), and "Me" (enclosing marks).
|
|
|
|
*
|
|
|
|
* Note that this is different from the Unicode definition in
|
|
|
|
* chapter 3.5, conformance clause D13,
|
|
|
|
* which defines base characters to be all characters (not Cn)
|
|
|
|
* that do not graphically combine with preceding characters (M)
|
|
|
|
* and that are neither control (Cc) or format (Cf) characters.
|
1999-12-28 23:39:02 +00:00
|
|
|
*
|
2003-02-11 01:59:32 +00:00
|
|
|
* @param c the code point to be tested
|
|
|
|
* @return TRUE if the code point is a base character according to this function
|
1999-12-28 23:39:02 +00:00
|
|
|
*
|
2001-11-09 18:17:40 +00:00
|
|
|
* @see u_isalpha
|
|
|
|
* @see u_isdigit
|
2002-12-04 23:39:56 +00:00
|
|
|
* @stable ICU 2.0
|
1999-12-28 23:39:02 +00:00
|
|
|
*/
|
2004-03-26 19:42:04 +00:00
|
|
|
U_STABLE UBool U_EXPORT2
|
2000-02-03 19:54:49 +00:00
|
|
|
u_isbase(UChar32 c);
|
2000-04-24 22:31:22 +00:00
|
|
|
|
1999-12-28 23:39:02 +00:00
|
|
|
/**
|
2003-02-11 01:59:32 +00:00
|
|
|
* Returns the bidirectional category value for the code point,
|
|
|
|
* which is used in the Unicode bidirectional algorithm
|
|
|
|
* (UAX #9 http://www.unicode.org/reports/tr9/).
|
|
|
|
* Note that some <em>unassigned</em> code points have bidi values
|
|
|
|
* of R or AL because they are in blocks that are reserved
|
|
|
|
* for Right-To-Left scripts.
|
|
|
|
*
|
|
|
|
* Same as java.lang.Character.getDirectionality()
|
|
|
|
*
|
|
|
|
* @param c the code point to be tested
|
|
|
|
* @return the bidirectional category (UCharDirection) value
|
|
|
|
*
|
2001-11-09 18:17:40 +00:00
|
|
|
* @see UCharDirection
|
2002-12-04 23:39:56 +00:00
|
|
|
* @stable ICU 2.0
|
2001-11-09 18:17:40 +00:00
|
|
|
*/
|
2004-03-26 19:42:04 +00:00
|
|
|
U_STABLE UCharDirection U_EXPORT2
|
2000-02-03 19:54:49 +00:00
|
|
|
u_charDirection(UChar32 c);
|
1999-12-28 23:39:02 +00:00
|
|
|
|
2000-04-24 22:31:22 +00:00
|
|
|
/**
|
2003-02-11 01:59:32 +00:00
|
|
|
* Determines whether the code point has the Bidi_Mirrored property.
|
2000-04-24 22:31:22 +00:00
|
|
|
* This property is set for characters that are commonly used in
|
|
|
|
* Right-To-Left contexts and need to be displayed with a "mirrored"
|
|
|
|
* glyph.
|
|
|
|
*
|
2003-02-11 01:59:32 +00:00
|
|
|
* Same as java.lang.Character.isMirrored().
|
|
|
|
* Same as UCHAR_BIDI_MIRRORED
|
|
|
|
*
|
|
|
|
* @param c the code point to be tested
|
|
|
|
* @return TRUE if the character has the Bidi_Mirrored property
|
|
|
|
*
|
|
|
|
* @see UCHAR_BIDI_MIRRORED
|
2002-12-04 23:39:56 +00:00
|
|
|
* @stable ICU 2.0
|
2000-04-24 22:31:22 +00:00
|
|
|
*/
|
2004-03-26 19:42:04 +00:00
|
|
|
U_STABLE UBool U_EXPORT2
|
2000-04-24 22:31:22 +00:00
|
|
|
u_isMirrored(UChar32 c);
|
|
|
|
|
|
|
|
/**
|
|
|
|
* Maps the specified character to a "mirror-image" character.
|
2003-02-11 01:59:32 +00:00
|
|
|
* For characters with the Bidi_Mirrored property, implementations
|
2000-04-24 22:31:22 +00:00
|
|
|
* sometimes need a "poor man's" mapping to another Unicode
|
|
|
|
* character (code point) such that the default glyph may serve
|
|
|
|
* as the mirror-image of the default glyph of the specified
|
|
|
|
* character. This is useful for text conversion to and from
|
|
|
|
* codepages with visual order, and for displays without glyph
|
|
|
|
* selecetion capabilities.
|
|
|
|
*
|
2003-02-11 01:59:32 +00:00
|
|
|
* @param c the code point to be mapped
|
2000-04-24 22:31:22 +00:00
|
|
|
* @return another Unicode code point that may serve as a mirror-image
|
|
|
|
* substitute, or c itself if there is no such mapping or c
|
2003-02-11 01:59:32 +00:00
|
|
|
* does not have the Bidi_Mirrored property
|
|
|
|
*
|
|
|
|
* @see UCHAR_BIDI_MIRRORED
|
|
|
|
* @see u_isMirrored
|
2002-12-04 23:39:56 +00:00
|
|
|
* @stable ICU 2.0
|
2000-04-24 22:31:22 +00:00
|
|
|
*/
|
2004-03-26 19:42:04 +00:00
|
|
|
U_STABLE UChar32 U_EXPORT2
|
2000-04-24 22:31:22 +00:00
|
|
|
u_charMirror(UChar32 c);
|
|
|
|
|
1999-12-28 23:39:02 +00:00
|
|
|
/**
|
2003-02-11 01:59:32 +00:00
|
|
|
* Returns the general category value for the code point.
|
|
|
|
*
|
|
|
|
* Same as java.lang.Character.getType().
|
|
|
|
*
|
|
|
|
* @param c the code point to be tested
|
|
|
|
* @return the general category (UCharCategory) value
|
2001-01-23 23:45:21 +00:00
|
|
|
*
|
1999-12-28 23:39:02 +00:00
|
|
|
* @see UCharCategory
|
2002-12-04 23:39:56 +00:00
|
|
|
* @stable ICU 2.0
|
1999-12-28 23:39:02 +00:00
|
|
|
*/
|
2004-03-26 19:42:04 +00:00
|
|
|
U_STABLE int8_t U_EXPORT2
|
2000-02-03 19:54:49 +00:00
|
|
|
u_charType(UChar32 c);
|
1999-12-28 23:39:02 +00:00
|
|
|
|
2002-03-13 23:31:12 +00:00
|
|
|
/**
|
|
|
|
* Get a single-bit bit set for the general category of a character.
|
|
|
|
* This bit set can be compared bitwise with U_GC_SM_MASK, U_GC_L_MASK, etc.
|
|
|
|
* Same as U_MASK(u_charType(c)).
|
|
|
|
*
|
2003-02-11 01:59:32 +00:00
|
|
|
* @param c the code point to be tested
|
|
|
|
* @return a single-bit mask corresponding to the general category (UCharCategory) value
|
|
|
|
*
|
2002-03-13 23:31:12 +00:00
|
|
|
* @see u_charType
|
|
|
|
* @see UCharCategory
|
|
|
|
* @see U_GC_CN_MASK
|
2003-02-11 01:59:32 +00:00
|
|
|
* @stable ICU 2.1
|
2002-03-13 23:31:12 +00:00
|
|
|
*/
|
|
|
|
#define U_GET_GC_MASK(c) U_MASK(u_charType(c))
|
|
|
|
|
2002-01-12 00:11:09 +00:00
|
|
|
/**
|
|
|
|
* Callback from u_enumCharTypes(), is called for each contiguous range
|
|
|
|
* of code points c (where start<=c<limit)
|
|
|
|
* with the same Unicode general category ("character type").
|
|
|
|
*
|
|
|
|
* The callback function can stop the enumeration by returning FALSE.
|
|
|
|
*
|
|
|
|
* @param context an opaque pointer, as passed into utrie_enum()
|
|
|
|
* @param start the first code point in a contiguous range with value
|
|
|
|
* @param limit one past the last code point in a contiguous range with value
|
|
|
|
* @param type the general category for all code points in [start..limit[
|
|
|
|
* @return FALSE to stop the enumeration
|
|
|
|
*
|
2003-02-11 01:59:32 +00:00
|
|
|
* @stable ICU 2.1
|
2002-01-12 00:11:09 +00:00
|
|
|
* @see UCharCategory
|
|
|
|
* @see u_enumCharTypes
|
|
|
|
*/
|
|
|
|
typedef UBool U_CALLCONV
|
|
|
|
UCharEnumTypeRange(const void *context, UChar32 start, UChar32 limit, UCharCategory type);
|
|
|
|
|
|
|
|
/**
|
|
|
|
* Enumerate efficiently all code points with their Unicode general categories.
|
|
|
|
*
|
|
|
|
* This is useful for building data structures (e.g., UnicodeSet's),
|
|
|
|
* for enumerating all assigned code points (type!=U_UNASSIGNED), etc.
|
|
|
|
*
|
|
|
|
* For each contiguous range of code points with a given general category ("character type"),
|
|
|
|
* the UCharEnumTypeRange function is called.
|
|
|
|
* Adjacent ranges have different types.
|
|
|
|
* The Unicode Standard guarantees that the numeric value of the type is 0..31.
|
|
|
|
*
|
|
|
|
* @param enumRange a pointer to a function that is called for each contiguous range
|
|
|
|
* of code points with the same general category
|
|
|
|
* @param context an opaque pointer that is passed on to the callback function
|
|
|
|
*
|
2003-02-11 01:59:32 +00:00
|
|
|
* @stable ICU 2.1
|
2002-01-12 00:11:09 +00:00
|
|
|
* @see UCharCategory
|
|
|
|
* @see UCharEnumTypeRange
|
|
|
|
*/
|
2004-03-26 19:42:04 +00:00
|
|
|
U_STABLE void U_EXPORT2
|
2002-01-12 00:11:09 +00:00
|
|
|
u_enumCharTypes(UCharEnumTypeRange *enumRange, const void *context);
|
|
|
|
|
2003-05-06 01:37:52 +00:00
|
|
|
#if !UCONFIG_NO_NORMALIZATION
|
|
|
|
|
2001-01-23 23:45:21 +00:00
|
|
|
/**
|
|
|
|
* Returns the combining class of the code point as specified in UnicodeData.txt.
|
|
|
|
*
|
|
|
|
* @param c the code point of the character
|
|
|
|
* @return the combining class of the character
|
2002-12-04 23:39:56 +00:00
|
|
|
* @stable ICU 2.0
|
2001-01-23 23:45:21 +00:00
|
|
|
*/
|
2004-03-26 19:42:04 +00:00
|
|
|
U_STABLE uint8_t U_EXPORT2
|
2001-01-23 23:45:21 +00:00
|
|
|
u_getCombiningClass(UChar32 c);
|
|
|
|
|
2003-05-06 01:37:52 +00:00
|
|
|
#endif
|
|
|
|
|
1999-12-28 23:39:02 +00:00
|
|
|
/**
|
2003-04-09 19:04:01 +00:00
|
|
|
* Returns the decimal digit value of a decimal digit character.
|
2003-02-11 23:27:40 +00:00
|
|
|
* Such characters have the general category "Nd" (decimal digit numbers)
|
|
|
|
* and a Numeric_Type of Decimal.
|
2003-02-11 01:59:32 +00:00
|
|
|
*
|
2003-04-09 19:04:01 +00:00
|
|
|
* Unlike ICU releases before 2.6, no digit values are returned for any
|
|
|
|
* Han characters because Han number characters are often used with a special
|
|
|
|
* Chinese-style number format (with characters for powers of 10 in between)
|
|
|
|
* instead of in decimal-positional notation.
|
|
|
|
* Unicode 4 explicitly assigns Han number characters the Numeric_Type
|
|
|
|
* Numeric instead of Decimal.
|
|
|
|
* See Jitterbug 1483 for more details.
|
|
|
|
*
|
|
|
|
* Use u_getIntPropertyValue(c, UCHAR_NUMERIC_TYPE) and u_getNumericValue()
|
|
|
|
* for complete numeric Unicode properties.
|
|
|
|
*
|
|
|
|
* @param c the code point for which to get the decimal digit value
|
|
|
|
* @return the decimal digit value of c,
|
2003-02-11 01:59:32 +00:00
|
|
|
* or -1 if c is not a decimal digit character
|
1999-12-28 23:39:02 +00:00
|
|
|
*
|
2003-02-11 01:59:32 +00:00
|
|
|
* @see u_getNumericValue
|
2002-12-04 23:39:56 +00:00
|
|
|
* @stable ICU 2.0
|
1999-12-28 23:39:02 +00:00
|
|
|
*/
|
2004-03-26 19:42:04 +00:00
|
|
|
U_STABLE int32_t U_EXPORT2
|
2000-02-03 19:54:49 +00:00
|
|
|
u_charDigitValue(UChar32 c);
|
1999-12-28 23:39:02 +00:00
|
|
|
|
|
|
|
/**
|
2001-09-11 05:00:34 +00:00
|
|
|
* Returns the Unicode allocation block that contains the character.
|
1999-12-28 23:39:02 +00:00
|
|
|
*
|
2003-02-11 01:59:32 +00:00
|
|
|
* @param c the code point to be tested
|
|
|
|
* @return the block value (UBlockCode) for c
|
|
|
|
*
|
|
|
|
* @see UBlockCode
|
2002-12-04 23:39:56 +00:00
|
|
|
* @stable ICU 2.0
|
1999-12-28 23:39:02 +00:00
|
|
|
*/
|
2004-03-26 19:42:04 +00:00
|
|
|
U_STABLE UBlockCode U_EXPORT2
|
2003-02-11 01:59:32 +00:00
|
|
|
ublock_getCode(UChar32 c);
|
1999-12-28 23:39:02 +00:00
|
|
|
|
|
|
|
/**
|
|
|
|
* Retrieve the name of a Unicode character.
|
|
|
|
* Depending on <code>nameChoice</code>, the character name written
|
|
|
|
* into the buffer is the "modern" name or the name that was defined
|
|
|
|
* in Unicode version 1.0.
|
|
|
|
* The name contains only "invariant" characters
|
|
|
|
* like A-Z, 0-9, space, and '-'.
|
2000-10-10 17:33:09 +00:00
|
|
|
* Unicode 1.0 names are only retrieved if they are different from the modern
|
|
|
|
* names and if the data file contains the data for them. gennames may or may
|
|
|
|
* not be called with a command line option to include 1.0 names in unames.dat.
|
1999-12-28 23:39:02 +00:00
|
|
|
*
|
|
|
|
* @param code The character (code point) for which to get the name.
|
2002-07-08 16:40:57 +00:00
|
|
|
* It must be <code>0<=code<=0x10ffff</code>.
|
1999-12-28 23:39:02 +00:00
|
|
|
* @param nameChoice Selector for which name to get.
|
|
|
|
* @param buffer Destination address for copying the name.
|
2000-10-11 16:10:25 +00:00
|
|
|
* The name will always be zero-terminated.
|
|
|
|
* If there is no name, then the buffer will be set to the empty string.
|
1999-12-28 23:39:02 +00:00
|
|
|
* @param bufferLength <code>==sizeof(buffer)</code>
|
|
|
|
* @param pErrorCode Pointer to a UErrorCode variable;
|
|
|
|
* check for <code>U_SUCCESS()</code> after <code>u_charName()</code>
|
|
|
|
* returns.
|
2000-10-11 16:10:25 +00:00
|
|
|
* @return The length of the name, or 0 if there is no name for this character.
|
|
|
|
* If the bufferLength is less than or equal to the length, then the buffer
|
|
|
|
* contains the truncated name and the returned length indicates the full
|
|
|
|
* length of the name.
|
|
|
|
* The length does not include the zero-termination.
|
1999-12-28 23:39:02 +00:00
|
|
|
*
|
|
|
|
* @see UCharNameChoice
|
2000-10-11 16:10:25 +00:00
|
|
|
* @see u_charFromName
|
|
|
|
* @see u_enumCharNames
|
2002-12-04 23:39:56 +00:00
|
|
|
* @stable ICU 2.0
|
1999-12-28 23:39:02 +00:00
|
|
|
*/
|
2004-03-26 19:42:04 +00:00
|
|
|
U_STABLE int32_t U_EXPORT2
|
2000-10-10 17:33:09 +00:00
|
|
|
u_charName(UChar32 code, UCharNameChoice nameChoice,
|
2002-03-12 01:32:42 +00:00
|
|
|
char *buffer, int32_t bufferLength,
|
1999-12-28 23:39:02 +00:00
|
|
|
UErrorCode *pErrorCode);
|
|
|
|
|
2002-07-08 16:40:57 +00:00
|
|
|
/**
|
2011-12-15 21:43:35 +00:00
|
|
|
* Returns an empty string.
|
|
|
|
* Used to return the ISO 10646 comment for a character.
|
|
|
|
* The Unicode ISO_Comment property is deprecated and has no values.
|
2009-11-13 19:25:21 +00:00
|
|
|
*
|
2002-07-08 16:40:57 +00:00
|
|
|
* @param c The character (code point) for which to get the ISO comment.
|
|
|
|
* It must be <code>0<=c<=0x10ffff</code>.
|
|
|
|
* @param dest Destination address for copying the comment.
|
|
|
|
* The comment will be zero-terminated if possible.
|
|
|
|
* If there is no comment, then the buffer will be set to the empty string.
|
|
|
|
* @param destCapacity <code>==sizeof(dest)</code>
|
|
|
|
* @param pErrorCode Pointer to a UErrorCode variable;
|
|
|
|
* check for <code>U_SUCCESS()</code> after <code>u_getISOComment()</code>
|
|
|
|
* returns.
|
2011-12-15 21:43:35 +00:00
|
|
|
* @return 0
|
2002-07-08 16:40:57 +00:00
|
|
|
*
|
2011-12-15 21:43:35 +00:00
|
|
|
* @deprecated ICU 49
|
2002-07-08 16:40:57 +00:00
|
|
|
*/
|
2004-03-26 19:42:04 +00:00
|
|
|
U_STABLE int32_t U_EXPORT2
|
2002-07-08 16:40:57 +00:00
|
|
|
u_getISOComment(UChar32 c,
|
|
|
|
char *dest, int32_t destCapacity,
|
|
|
|
UErrorCode *pErrorCode);
|
|
|
|
|
2000-06-29 18:27:07 +00:00
|
|
|
/**
|
|
|
|
* Find a Unicode character by its name and return its code point value.
|
2000-10-11 16:10:25 +00:00
|
|
|
* The name is matched exactly and completely.
|
2002-02-15 19:10:38 +00:00
|
|
|
* If the name does not correspond to a code point, <i>pErrorCode</i>
|
|
|
|
* is set to <code>U_INVALID_CHAR_FOUND</code>.
|
2000-10-11 16:10:25 +00:00
|
|
|
* A Unicode 1.0 name is matched only if it differs from the modern name.
|
2002-02-15 19:10:38 +00:00
|
|
|
* Unicode names are all uppercase. Extended names are lowercase followed
|
|
|
|
* by an uppercase hexadecimal number, and within angle brackets.
|
2000-10-11 16:10:25 +00:00
|
|
|
*
|
|
|
|
* @param nameChoice Selector for which name to match.
|
|
|
|
* @param name The name to match.
|
|
|
|
* @param pErrorCode Pointer to a UErrorCode variable
|
2002-02-15 19:10:38 +00:00
|
|
|
* @return The Unicode value of the code point with the given name,
|
|
|
|
* or an undefined value if there is no such code point.
|
2000-10-11 16:10:25 +00:00
|
|
|
*
|
|
|
|
* @see UCharNameChoice
|
|
|
|
* @see u_charName
|
|
|
|
* @see u_enumCharNames
|
2002-12-11 22:49:18 +00:00
|
|
|
* @stable ICU 1.7
|
2000-06-29 18:27:07 +00:00
|
|
|
*/
|
2004-03-26 19:42:04 +00:00
|
|
|
U_STABLE UChar32 U_EXPORT2
|
2000-06-29 18:27:07 +00:00
|
|
|
u_charFromName(UCharNameChoice nameChoice,
|
|
|
|
const char *name,
|
|
|
|
UErrorCode *pErrorCode);
|
|
|
|
|
|
|
|
/**
|
|
|
|
* Type of a callback function for u_enumCharNames() that gets called
|
|
|
|
* for each Unicode character with the code point value and
|
|
|
|
* the character name.
|
|
|
|
* If such a function returns FALSE, then the enumeration is stopped.
|
2000-10-11 16:10:25 +00:00
|
|
|
*
|
|
|
|
* @param context The context pointer that was passed to u_enumCharNames().
|
|
|
|
* @param code The Unicode code point for the character with this name.
|
|
|
|
* @param nameChoice Selector for which kind of names is enumerated.
|
|
|
|
* @param name The character's name, zero-terminated.
|
|
|
|
* @param length The length of the name.
|
|
|
|
* @return TRUE if the enumeration should continue, FALSE to stop it.
|
|
|
|
*
|
|
|
|
* @see UCharNameChoice
|
|
|
|
* @see u_enumCharNames
|
2002-12-11 22:49:18 +00:00
|
|
|
* @stable ICU 1.7
|
2000-06-29 18:27:07 +00:00
|
|
|
*/
|
2006-02-21 18:30:10 +00:00
|
|
|
typedef UBool U_CALLCONV UEnumCharNamesFn(void *context,
|
2000-06-29 18:27:07 +00:00
|
|
|
UChar32 code,
|
|
|
|
UCharNameChoice nameChoice,
|
2000-10-10 17:33:09 +00:00
|
|
|
const char *name,
|
2002-03-12 01:32:42 +00:00
|
|
|
int32_t length);
|
2000-06-29 18:27:07 +00:00
|
|
|
|
|
|
|
/**
|
|
|
|
* Enumerate all assigned Unicode characters between the start and limit
|
|
|
|
* code points (start inclusive, limit exclusive) and call a function
|
|
|
|
* for each, passing the code point value and the character name.
|
2000-10-11 16:10:25 +00:00
|
|
|
* For Unicode 1.0 names, only those are enumerated that differ from the
|
|
|
|
* modern names.
|
|
|
|
*
|
|
|
|
* @param start The first code point in the enumeration range.
|
|
|
|
* @param limit One more than the last code point in the enumeration range
|
|
|
|
* (the first one after the range).
|
|
|
|
* @param fn The function that is to be called for each character name.
|
|
|
|
* @param context An arbitrary pointer that is passed to the function.
|
|
|
|
* @param nameChoice Selector for which kind of names to enumerate.
|
|
|
|
* @param pErrorCode Pointer to a UErrorCode variable
|
|
|
|
*
|
|
|
|
* @see UCharNameChoice
|
|
|
|
* @see UEnumCharNamesFn
|
|
|
|
* @see u_charName
|
|
|
|
* @see u_charFromName
|
2002-12-11 22:49:18 +00:00
|
|
|
* @stable ICU 1.7
|
2000-06-29 18:27:07 +00:00
|
|
|
*/
|
2004-03-26 19:42:04 +00:00
|
|
|
U_STABLE void U_EXPORT2
|
2000-06-29 18:27:07 +00:00
|
|
|
u_enumCharNames(UChar32 start, UChar32 limit,
|
|
|
|
UEnumCharNamesFn *fn,
|
|
|
|
void *context,
|
|
|
|
UCharNameChoice nameChoice,
|
|
|
|
UErrorCode *pErrorCode);
|
|
|
|
|
2002-10-30 18:24:53 +00:00
|
|
|
/**
|
|
|
|
* Return the Unicode name for a given property, as given in the
|
|
|
|
* Unicode database file PropertyAliases.txt.
|
|
|
|
*
|
2002-12-11 01:09:02 +00:00
|
|
|
* In addition, this function maps the property
|
|
|
|
* UCHAR_GENERAL_CATEGORY_MASK to the synthetic names "gcm" /
|
|
|
|
* "General_Category_Mask". These names are not in
|
|
|
|
* PropertyAliases.txt.
|
|
|
|
*
|
2002-10-30 18:24:53 +00:00
|
|
|
* @param property UProperty selector other than UCHAR_INVALID_CODE.
|
|
|
|
* If out of range, NULL is returned.
|
|
|
|
*
|
|
|
|
* @param nameChoice selector for which name to get. If out of range,
|
|
|
|
* NULL is returned. All properties have a long name. Most
|
|
|
|
* have a short name, but some do not. Unicode allows for
|
|
|
|
* additional names; if present these will be returned by
|
|
|
|
* U_LONG_PROPERTY_NAME + i, where i=1, 2,...
|
|
|
|
*
|
|
|
|
* @return a pointer to the name, or NULL if either the
|
|
|
|
* property or the nameChoice is out of range. If a given
|
|
|
|
* nameChoice returns NULL, then all larger values of
|
|
|
|
* nameChoice will return NULL, with one exception: if NULL is
|
|
|
|
* returned for U_SHORT_PROPERTY_NAME, then
|
|
|
|
* U_LONG_PROPERTY_NAME (and higher) may still return a
|
|
|
|
* non-NULL value. The returned pointer is valid until
|
|
|
|
* u_cleanup() is called.
|
|
|
|
*
|
|
|
|
* @see UProperty
|
|
|
|
* @see UPropertyNameChoice
|
2004-03-26 19:42:04 +00:00
|
|
|
* @stable ICU 2.4
|
2002-10-30 18:24:53 +00:00
|
|
|
*/
|
2004-03-26 19:42:04 +00:00
|
|
|
U_STABLE const char* U_EXPORT2
|
2002-10-30 18:24:53 +00:00
|
|
|
u_getPropertyName(UProperty property,
|
|
|
|
UPropertyNameChoice nameChoice);
|
|
|
|
|
|
|
|
/**
|
|
|
|
* Return the UProperty enum for a given property name, as specified
|
|
|
|
* in the Unicode database file PropertyAliases.txt. Short, long, and
|
|
|
|
* any other variants are recognized.
|
|
|
|
*
|
2002-12-11 01:09:02 +00:00
|
|
|
* In addition, this function maps the synthetic names "gcm" /
|
|
|
|
* "General_Category_Mask" to the property
|
|
|
|
* UCHAR_GENERAL_CATEGORY_MASK. These names are not in
|
|
|
|
* PropertyAliases.txt.
|
|
|
|
*
|
2002-10-30 18:24:53 +00:00
|
|
|
* @param alias the property name to be matched. The name is compared
|
|
|
|
* using "loose matching" as described in PropertyAliases.txt.
|
|
|
|
*
|
|
|
|
* @return a UProperty enum, or UCHAR_INVALID_CODE if the given name
|
|
|
|
* does not match any property.
|
|
|
|
*
|
|
|
|
* @see UProperty
|
2004-03-26 19:42:04 +00:00
|
|
|
* @stable ICU 2.4
|
2002-10-30 18:24:53 +00:00
|
|
|
*/
|
2004-03-26 19:42:04 +00:00
|
|
|
U_STABLE UProperty U_EXPORT2
|
2002-10-30 18:24:53 +00:00
|
|
|
u_getPropertyEnum(const char* alias);
|
|
|
|
|
|
|
|
/**
|
|
|
|
* Return the Unicode name for a given property value, as given in the
|
|
|
|
* Unicode database file PropertyValueAliases.txt.
|
|
|
|
*
|
2002-12-11 01:09:02 +00:00
|
|
|
* Note: Some of the names in PropertyValueAliases.txt can only be
|
|
|
|
* retrieved using UCHAR_GENERAL_CATEGORY_MASK, not
|
|
|
|
* UCHAR_GENERAL_CATEGORY. These include: "C" / "Other", "L" /
|
|
|
|
* "Letter", "LC" / "Cased_Letter", "M" / "Mark", "N" / "Number", "P"
|
|
|
|
* / "Punctuation", "S" / "Symbol", and "Z" / "Separator".
|
|
|
|
*
|
2002-12-10 00:33:45 +00:00
|
|
|
* @param property UProperty selector constant.
|
|
|
|
* Must be UCHAR_BINARY_START<=which<UCHAR_BINARY_LIMIT
|
|
|
|
* or UCHAR_INT_START<=which<UCHAR_INT_LIMIT
|
|
|
|
* or UCHAR_MASK_START<=which<UCHAR_MASK_LIMIT.
|
|
|
|
* If out of range, NULL is returned.
|
2002-10-30 18:24:53 +00:00
|
|
|
*
|
|
|
|
* @param value selector for a value for the given property. If out
|
|
|
|
* of range, NULL is returned. In general, valid values range
|
|
|
|
* from 0 up to some maximum. There are a few exceptions:
|
|
|
|
* (1.) UCHAR_BLOCK values begin at the non-zero value
|
|
|
|
* UBLOCK_BASIC_LATIN. (2.) UCHAR_CANONICAL_COMBINING_CLASS
|
|
|
|
* values are not contiguous and range from 0..240. (3.)
|
2002-12-11 01:09:02 +00:00
|
|
|
* UCHAR_GENERAL_CATEGORY_MASK values are not values of
|
2002-10-30 18:24:53 +00:00
|
|
|
* UCharCategory, but rather mask values produced by
|
|
|
|
* U_GET_GC_MASK(). This allows grouped categories such as
|
|
|
|
* [:L:] to be represented. Mask values range
|
|
|
|
* non-contiguously from 1..U_GC_P_MASK.
|
|
|
|
*
|
|
|
|
* @param nameChoice selector for which name to get. If out of range,
|
|
|
|
* NULL is returned. All values have a long name. Most have
|
|
|
|
* a short name, but some do not. Unicode allows for
|
|
|
|
* additional names; if present these will be returned by
|
|
|
|
* U_LONG_PROPERTY_NAME + i, where i=1, 2,...
|
|
|
|
|
|
|
|
* @return a pointer to the name, or NULL if either the
|
|
|
|
* property or the nameChoice is out of range. If a given
|
|
|
|
* nameChoice returns NULL, then all larger values of
|
|
|
|
* nameChoice will return NULL, with one exception: if NULL is
|
|
|
|
* returned for U_SHORT_PROPERTY_NAME, then
|
|
|
|
* U_LONG_PROPERTY_NAME (and higher) may still return a
|
|
|
|
* non-NULL value. The returned pointer is valid until
|
|
|
|
* u_cleanup() is called.
|
|
|
|
*
|
|
|
|
* @see UProperty
|
|
|
|
* @see UPropertyNameChoice
|
2004-03-26 19:42:04 +00:00
|
|
|
* @stable ICU 2.4
|
2002-10-30 18:24:53 +00:00
|
|
|
*/
|
2004-03-26 19:42:04 +00:00
|
|
|
U_STABLE const char* U_EXPORT2
|
2002-10-30 18:24:53 +00:00
|
|
|
u_getPropertyValueName(UProperty property,
|
|
|
|
int32_t value,
|
|
|
|
UPropertyNameChoice nameChoice);
|
|
|
|
|
|
|
|
/**
|
|
|
|
* Return the property value integer for a given value name, as
|
|
|
|
* specified in the Unicode database file PropertyValueAliases.txt.
|
|
|
|
* Short, long, and any other variants are recognized.
|
|
|
|
*
|
2002-12-11 01:09:02 +00:00
|
|
|
* Note: Some of the names in PropertyValueAliases.txt will only be
|
|
|
|
* recognized with UCHAR_GENERAL_CATEGORY_MASK, not
|
|
|
|
* UCHAR_GENERAL_CATEGORY. These include: "C" / "Other", "L" /
|
|
|
|
* "Letter", "LC" / "Cased_Letter", "M" / "Mark", "N" / "Number", "P"
|
|
|
|
* / "Punctuation", "S" / "Symbol", and "Z" / "Separator".
|
|
|
|
*
|
2002-12-10 00:33:45 +00:00
|
|
|
* @param property UProperty selector constant.
|
|
|
|
* Must be UCHAR_BINARY_START<=which<UCHAR_BINARY_LIMIT
|
|
|
|
* or UCHAR_INT_START<=which<UCHAR_INT_LIMIT
|
|
|
|
* or UCHAR_MASK_START<=which<UCHAR_MASK_LIMIT.
|
|
|
|
* If out of range, UCHAR_INVALID_CODE is returned.
|
2002-10-30 18:24:53 +00:00
|
|
|
*
|
|
|
|
* @param alias the value name to be matched. The name is compared
|
|
|
|
* using "loose matching" as described in
|
|
|
|
* PropertyValueAliases.txt.
|
|
|
|
*
|
|
|
|
* @return a value integer or UCHAR_INVALID_CODE if the given name
|
|
|
|
* does not match any value of the given property, or if the
|
2010-02-26 05:31:59 +00:00
|
|
|
* property is invalid. Note: UCHAR_GENERAL_CATEGORY_MASK values
|
2002-10-30 18:24:53 +00:00
|
|
|
* are not values of UCharCategory, but rather mask values
|
|
|
|
* produced by U_GET_GC_MASK(). This allows grouped
|
|
|
|
* categories such as [:L:] to be represented.
|
|
|
|
*
|
|
|
|
* @see UProperty
|
2004-03-26 19:42:04 +00:00
|
|
|
* @stable ICU 2.4
|
2002-10-30 18:24:53 +00:00
|
|
|
*/
|
2004-03-26 19:42:04 +00:00
|
|
|
U_STABLE int32_t U_EXPORT2
|
2002-10-30 18:24:53 +00:00
|
|
|
u_getPropertyValueEnum(UProperty property,
|
|
|
|
const char* alias);
|
|
|
|
|
1999-12-28 23:39:02 +00:00
|
|
|
/**
|
2003-02-09 21:02:26 +00:00
|
|
|
* Determines if the specified character is permissible as the
|
2003-02-11 01:59:32 +00:00
|
|
|
* first character in an identifier according to Unicode
|
|
|
|
* (The Unicode Standard, Version 3.0, chapter 5.16 Identifiers).
|
2003-02-09 21:02:26 +00:00
|
|
|
* True for characters with general categories "L" (letters) and "Nl" (letter numbers).
|
2001-11-09 18:17:40 +00:00
|
|
|
*
|
2003-02-09 21:02:26 +00:00
|
|
|
* Same as java.lang.Character.isUnicodeIdentifierStart().
|
2003-02-11 01:59:32 +00:00
|
|
|
* Same as UCHAR_ID_START
|
2003-02-09 21:02:26 +00:00
|
|
|
*
|
|
|
|
* @param c the code point to be tested
|
2003-02-11 01:59:32 +00:00
|
|
|
* @return TRUE if the code point may start an identifier
|
2003-02-09 21:02:26 +00:00
|
|
|
*
|
2003-02-11 01:59:32 +00:00
|
|
|
* @see UCHAR_ID_START
|
2003-02-09 21:02:26 +00:00
|
|
|
* @see u_isalpha
|
|
|
|
* @see u_isIDPart
|
2002-12-04 23:39:56 +00:00
|
|
|
* @stable ICU 2.0
|
2001-11-09 18:17:40 +00:00
|
|
|
*/
|
2004-03-26 19:42:04 +00:00
|
|
|
U_STABLE UBool U_EXPORT2
|
2000-02-03 19:54:49 +00:00
|
|
|
u_isIDStart(UChar32 c);
|
2001-11-09 18:17:40 +00:00
|
|
|
|
1999-12-28 23:39:02 +00:00
|
|
|
/**
|
2003-02-11 01:59:32 +00:00
|
|
|
* Determines if the specified character is permissible
|
|
|
|
* in an identifier according to Java.
|
|
|
|
* True for characters with general categories "L" (letters),
|
|
|
|
* "Nl" (letter numbers), "Nd" (decimal digits),
|
|
|
|
* "Mc" and "Mn" (combining marks), "Pc" (connecting punctuation), and
|
|
|
|
* u_isIDIgnorable(c).
|
2003-02-09 21:02:26 +00:00
|
|
|
*
|
2003-02-11 01:59:32 +00:00
|
|
|
* Same as java.lang.Character.isUnicodeIdentifierPart().
|
|
|
|
* Almost the same as Unicode's ID_Continue (UCHAR_ID_CONTINUE)
|
|
|
|
* except that Unicode recommends to ignore Cf which is less than
|
|
|
|
* u_isIDIgnorable(c).
|
|
|
|
*
|
|
|
|
* @param c the code point to be tested
|
|
|
|
* @return TRUE if the code point may occur in an identifier according to Java
|
|
|
|
*
|
|
|
|
* @see UCHAR_ID_CONTINUE
|
|
|
|
* @see u_isIDStart
|
|
|
|
* @see u_isIDIgnorable
|
2002-12-04 23:39:56 +00:00
|
|
|
* @stable ICU 2.0
|
2001-11-09 18:17:40 +00:00
|
|
|
*/
|
2004-03-26 19:42:04 +00:00
|
|
|
U_STABLE UBool U_EXPORT2
|
2000-02-03 19:54:49 +00:00
|
|
|
u_isIDPart(UChar32 c);
|
2001-11-09 18:17:40 +00:00
|
|
|
|
1999-12-28 23:39:02 +00:00
|
|
|
/**
|
2003-02-09 21:02:26 +00:00
|
|
|
* Determines if the specified character should be regarded
|
|
|
|
* as an ignorable character in an identifier,
|
|
|
|
* according to Java.
|
|
|
|
* True for characters with general category "Cf" (format controls) as well as
|
|
|
|
* non-whitespace ISO controls
|
2010-02-26 20:12:09 +00:00
|
|
|
* (U+0000..U+0008, U+000E..U+001B, U+007F..U+009F).
|
2003-02-09 21:02:26 +00:00
|
|
|
*
|
2010-02-26 20:12:09 +00:00
|
|
|
* Same as java.lang.Character.isIdentifierIgnorable().
|
2003-02-09 21:02:26 +00:00
|
|
|
*
|
2003-02-11 01:59:32 +00:00
|
|
|
* Note that Unicode just recommends to ignore Cf (format controls).
|
|
|
|
*
|
2003-02-09 21:02:26 +00:00
|
|
|
* @param c the code point to be tested
|
|
|
|
* @return TRUE if the code point is ignorable in identifiers according to Java
|
|
|
|
*
|
|
|
|
* @see UCHAR_DEFAULT_IGNORABLE_CODE_POINT
|
|
|
|
* @see u_isIDStart
|
|
|
|
* @see u_isIDPart
|
2002-12-04 23:39:56 +00:00
|
|
|
* @stable ICU 2.0
|
2001-11-09 18:17:40 +00:00
|
|
|
*/
|
2004-03-26 19:42:04 +00:00
|
|
|
U_STABLE UBool U_EXPORT2
|
2000-02-03 19:54:49 +00:00
|
|
|
u_isIDIgnorable(UChar32 c);
|
2001-11-09 18:17:40 +00:00
|
|
|
|
|
|
|
/**
|
2003-02-11 01:59:32 +00:00
|
|
|
* Determines if the specified character is permissible as the
|
|
|
|
* first character in a Java identifier.
|
|
|
|
* In addition to u_isIDStart(c), true for characters with
|
|
|
|
* general categories "Sc" (currency symbols) and "Pc" (connecting punctuation).
|
|
|
|
*
|
|
|
|
* Same as java.lang.Character.isJavaIdentifierStart().
|
|
|
|
*
|
|
|
|
* @param c the code point to be tested
|
|
|
|
* @return TRUE if the code point may start a Java identifier
|
2001-11-09 18:17:40 +00:00
|
|
|
*
|
|
|
|
* @see u_isJavaIDPart
|
|
|
|
* @see u_isalpha
|
|
|
|
* @see u_isIDStart
|
2002-12-04 23:39:56 +00:00
|
|
|
* @stable ICU 2.0
|
2001-11-09 18:17:40 +00:00
|
|
|
*/
|
2004-03-26 19:42:04 +00:00
|
|
|
U_STABLE UBool U_EXPORT2
|
2000-02-03 19:54:49 +00:00
|
|
|
u_isJavaIDStart(UChar32 c);
|
1999-12-28 23:39:02 +00:00
|
|
|
|
2001-11-09 18:17:40 +00:00
|
|
|
/**
|
2003-02-11 01:59:32 +00:00
|
|
|
* Determines if the specified character is permissible
|
|
|
|
* in a Java identifier.
|
|
|
|
* In addition to u_isIDPart(c), true for characters with
|
|
|
|
* general category "Sc" (currency symbols).
|
|
|
|
*
|
|
|
|
* Same as java.lang.Character.isJavaIdentifierPart().
|
|
|
|
*
|
|
|
|
* @param c the code point to be tested
|
|
|
|
* @return TRUE if the code point may occur in a Java identifier
|
|
|
|
*
|
2001-11-09 18:17:40 +00:00
|
|
|
* @see u_isIDIgnorable
|
|
|
|
* @see u_isJavaIDStart
|
|
|
|
* @see u_isalpha
|
|
|
|
* @see u_isdigit
|
|
|
|
* @see u_isIDPart
|
2002-12-04 23:39:56 +00:00
|
|
|
* @stable ICU 2.0
|
2001-11-09 18:17:40 +00:00
|
|
|
*/
|
2004-03-26 19:42:04 +00:00
|
|
|
U_STABLE UBool U_EXPORT2
|
2000-02-03 19:54:49 +00:00
|
|
|
u_isJavaIDPart(UChar32 c);
|
1999-12-28 23:39:02 +00:00
|
|
|
|
|
|
|
/**
|
|
|
|
* The given character is mapped to its lowercase equivalent according to
|
2003-02-11 23:27:40 +00:00
|
|
|
* UnicodeData.txt; if the character has no lowercase equivalent, the character
|
1999-12-28 23:39:02 +00:00
|
|
|
* itself is returned.
|
2003-02-11 23:27:40 +00:00
|
|
|
*
|
|
|
|
* Same as java.lang.Character.toLowerCase().
|
|
|
|
*
|
|
|
|
* This function only returns the simple, single-code point case mapping.
|
2005-06-17 23:47:15 +00:00
|
|
|
* Full case mappings should be used whenever possible because they produce
|
|
|
|
* better results by working on whole strings.
|
|
|
|
* They take into account the string context and the language and can map
|
|
|
|
* to a result string with a different length as appropriate.
|
2003-02-11 23:27:40 +00:00
|
|
|
* Full case mappings are applied by the string case mapping functions,
|
|
|
|
* see ustring.h and the UnicodeString class.
|
2005-06-17 23:47:15 +00:00
|
|
|
* See also the User Guide chapter on C/POSIX migration:
|
2007-06-11 19:14:47 +00:00
|
|
|
* http://icu-project.org/userguide/posix.html#case_mappings
|
2003-02-11 23:27:40 +00:00
|
|
|
*
|
|
|
|
* @param c the code point to be mapped
|
|
|
|
* @return the Simple_Lowercase_Mapping of the code point, if any;
|
|
|
|
* otherwise the code point itself.
|
2002-12-04 23:39:56 +00:00
|
|
|
* @stable ICU 2.0
|
1999-12-28 23:39:02 +00:00
|
|
|
*/
|
2004-03-26 19:42:04 +00:00
|
|
|
U_STABLE UChar32 U_EXPORT2
|
2000-02-03 19:54:49 +00:00
|
|
|
u_tolower(UChar32 c);
|
1999-12-28 23:39:02 +00:00
|
|
|
|
|
|
|
/**
|
2001-01-23 23:45:21 +00:00
|
|
|
* The given character is mapped to its uppercase equivalent according to UnicodeData.txt;
|
2003-02-11 23:27:40 +00:00
|
|
|
* if the character has no uppercase equivalent, the character itself is
|
1999-12-28 23:39:02 +00:00
|
|
|
* returned.
|
2003-02-11 23:27:40 +00:00
|
|
|
*
|
|
|
|
* Same as java.lang.Character.toUpperCase().
|
|
|
|
*
|
|
|
|
* This function only returns the simple, single-code point case mapping.
|
2005-06-17 23:47:15 +00:00
|
|
|
* Full case mappings should be used whenever possible because they produce
|
|
|
|
* better results by working on whole strings.
|
|
|
|
* They take into account the string context and the language and can map
|
|
|
|
* to a result string with a different length as appropriate.
|
2003-02-11 23:27:40 +00:00
|
|
|
* Full case mappings are applied by the string case mapping functions,
|
|
|
|
* see ustring.h and the UnicodeString class.
|
2005-06-17 23:47:15 +00:00
|
|
|
* See also the User Guide chapter on C/POSIX migration:
|
2007-06-11 19:14:47 +00:00
|
|
|
* http://icu-project.org/userguide/posix.html#case_mappings
|
2003-02-11 23:27:40 +00:00
|
|
|
*
|
|
|
|
* @param c the code point to be mapped
|
|
|
|
* @return the Simple_Uppercase_Mapping of the code point, if any;
|
|
|
|
* otherwise the code point itself.
|
2002-12-04 23:39:56 +00:00
|
|
|
* @stable ICU 2.0
|
1999-12-28 23:39:02 +00:00
|
|
|
*/
|
2004-03-26 19:42:04 +00:00
|
|
|
U_STABLE UChar32 U_EXPORT2
|
2000-02-03 19:54:49 +00:00
|
|
|
u_toupper(UChar32 c);
|
2001-11-09 18:17:40 +00:00
|
|
|
|
1999-12-28 23:39:02 +00:00
|
|
|
/**
|
2003-02-11 23:27:40 +00:00
|
|
|
* The given character is mapped to its titlecase equivalent
|
|
|
|
* according to UnicodeData.txt;
|
|
|
|
* if none is defined, the character itself is returned.
|
|
|
|
*
|
|
|
|
* Same as java.lang.Character.toTitleCase().
|
1999-12-28 23:39:02 +00:00
|
|
|
*
|
2003-02-11 23:27:40 +00:00
|
|
|
* This function only returns the simple, single-code point case mapping.
|
2005-06-17 23:47:15 +00:00
|
|
|
* Full case mappings should be used whenever possible because they produce
|
|
|
|
* better results by working on whole strings.
|
|
|
|
* They take into account the string context and the language and can map
|
|
|
|
* to a result string with a different length as appropriate.
|
2003-02-11 23:27:40 +00:00
|
|
|
* Full case mappings are applied by the string case mapping functions,
|
|
|
|
* see ustring.h and the UnicodeString class.
|
2005-06-17 23:47:15 +00:00
|
|
|
* See also the User Guide chapter on C/POSIX migration:
|
2007-06-11 19:14:47 +00:00
|
|
|
* http://icu-project.org/userguide/posix.html#case_mappings
|
2003-02-11 23:27:40 +00:00
|
|
|
*
|
|
|
|
* @param c the code point to be mapped
|
|
|
|
* @return the Simple_Titlecase_Mapping of the code point, if any;
|
|
|
|
* otherwise the code point itself.
|
2002-12-04 23:39:56 +00:00
|
|
|
* @stable ICU 2.0
|
1999-12-28 23:39:02 +00:00
|
|
|
*/
|
2004-03-26 19:42:04 +00:00
|
|
|
U_STABLE UChar32 U_EXPORT2
|
2000-02-03 19:54:49 +00:00
|
|
|
u_totitle(UChar32 c);
|
1999-12-28 23:39:02 +00:00
|
|
|
|
2002-12-05 00:30:16 +00:00
|
|
|
/** Option value for case folding: use default mappings defined in CaseFolding.txt. @stable ICU 2.0 */
|
2001-02-14 00:47:36 +00:00
|
|
|
#define U_FOLD_CASE_DEFAULT 0
|
2002-06-03 03:33:44 +00:00
|
|
|
|
|
|
|
/**
|
|
|
|
* Option value for case folding:
|
|
|
|
*
|
|
|
|
* Use the modified set of mappings provided in CaseFolding.txt to handle dotted I
|
|
|
|
* and dotless i appropriately for Turkic languages (tr, az).
|
|
|
|
*
|
|
|
|
* Before Unicode 3.2, CaseFolding.txt contains mappings marked with 'I' that
|
|
|
|
* are to be included for default mappings and
|
|
|
|
* excluded for the Turkic-specific mappings.
|
|
|
|
*
|
|
|
|
* Unicode 3.2 CaseFolding.txt instead contains mappings marked with 'T' that
|
|
|
|
* are to be excluded for default mappings and
|
|
|
|
* included for the Turkic-specific mappings.
|
|
|
|
*
|
2002-12-04 23:39:56 +00:00
|
|
|
* @stable ICU 2.0
|
2002-06-03 03:33:44 +00:00
|
|
|
*/
|
2001-02-14 00:47:36 +00:00
|
|
|
#define U_FOLD_CASE_EXCLUDE_SPECIAL_I 1
|
|
|
|
|
|
|
|
/**
|
|
|
|
* The given character is mapped to its case folding equivalent according to
|
2003-02-11 23:27:40 +00:00
|
|
|
* UnicodeData.txt and CaseFolding.txt;
|
|
|
|
* if the character has no case folding equivalent, the character
|
2001-02-14 00:47:36 +00:00
|
|
|
* itself is returned.
|
|
|
|
*
|
2003-02-11 23:27:40 +00:00
|
|
|
* This function only returns the simple, single-code point case mapping.
|
2005-06-17 23:47:15 +00:00
|
|
|
* Full case mappings should be used whenever possible because they produce
|
|
|
|
* better results by working on whole strings.
|
|
|
|
* They take into account the string context and the language and can map
|
|
|
|
* to a result string with a different length as appropriate.
|
2003-02-11 23:27:40 +00:00
|
|
|
* Full case mappings are applied by the string case mapping functions,
|
|
|
|
* see ustring.h and the UnicodeString class.
|
2005-06-17 23:47:15 +00:00
|
|
|
* See also the User Guide chapter on C/POSIX migration:
|
2007-06-11 19:14:47 +00:00
|
|
|
* http://icu-project.org/userguide/posix.html#case_mappings
|
2003-02-11 23:27:40 +00:00
|
|
|
*
|
|
|
|
* @param c the code point to be mapped
|
2001-02-14 00:47:36 +00:00
|
|
|
* @param options Either U_FOLD_CASE_DEFAULT or U_FOLD_CASE_EXCLUDE_SPECIAL_I
|
2003-02-11 23:27:40 +00:00
|
|
|
* @return the Simple_Case_Folding of the code point, if any;
|
|
|
|
* otherwise the code point itself.
|
2002-12-04 23:39:56 +00:00
|
|
|
* @stable ICU 2.0
|
2001-02-14 00:47:36 +00:00
|
|
|
*/
|
2004-03-26 19:42:04 +00:00
|
|
|
U_STABLE UChar32 U_EXPORT2
|
2001-02-14 00:47:36 +00:00
|
|
|
u_foldCase(UChar32 c, uint32_t options);
|
|
|
|
|
2001-09-21 00:27:17 +00:00
|
|
|
/**
|
2003-02-11 23:27:40 +00:00
|
|
|
* Returns the decimal digit value of the code point in the
|
|
|
|
* specified radix.
|
|
|
|
*
|
|
|
|
* If the radix is not in the range <code>2<=radix<=36</code> or if the
|
|
|
|
* value of <code>c</code> is not a valid digit in the specified
|
|
|
|
* radix, <code>-1</code> is returned. A character is a valid digit
|
2001-09-21 00:27:17 +00:00
|
|
|
* if at least one of the following is true:
|
|
|
|
* <ul>
|
2003-02-11 23:27:40 +00:00
|
|
|
* <li>The character has a decimal digit value.
|
|
|
|
* Such characters have the general category "Nd" (decimal digit numbers)
|
|
|
|
* and a Numeric_Type of Decimal.
|
|
|
|
* In this case the value is the character's decimal digit value.</li>
|
|
|
|
* <li>The character is one of the uppercase Latin letters
|
|
|
|
* <code>'A'</code> through <code>'Z'</code>.
|
|
|
|
* In this case the value is <code>c-'A'+10</code>.</li>
|
|
|
|
* <li>The character is one of the lowercase Latin letters
|
|
|
|
* <code>'a'</code> through <code>'z'</code>.
|
|
|
|
* In this case the value is <code>ch-'a'+10</code>.</li>
|
2003-04-24 23:09:26 +00:00
|
|
|
* <li>Latin letters from both the ASCII range (0061..007A, 0041..005A)
|
|
|
|
* as well as from the Fullwidth ASCII range (FF41..FF5A, FF21..FF3A)
|
|
|
|
* are recognized.</li>
|
2001-09-21 00:27:17 +00:00
|
|
|
* </ul>
|
|
|
|
*
|
2003-04-24 23:09:26 +00:00
|
|
|
* Same as java.lang.Character.digit().
|
2003-02-11 23:27:40 +00:00
|
|
|
*
|
2003-04-26 00:12:33 +00:00
|
|
|
* @param ch the code point to be tested.
|
2001-09-21 00:27:17 +00:00
|
|
|
* @param radix the radix.
|
|
|
|
* @return the numeric value represented by the character in the
|
2003-02-11 23:27:40 +00:00
|
|
|
* specified radix,
|
|
|
|
* or -1 if there is no value or if the value exceeds the radix.
|
2001-09-21 00:27:17 +00:00
|
|
|
*
|
2003-02-11 23:27:40 +00:00
|
|
|
* @see UCHAR_NUMERIC_TYPE
|
2001-09-21 00:27:17 +00:00
|
|
|
* @see u_forDigit
|
|
|
|
* @see u_charDigitValue
|
|
|
|
* @see u_isdigit
|
2002-12-04 23:39:56 +00:00
|
|
|
* @stable ICU 2.0
|
2001-09-21 00:27:17 +00:00
|
|
|
*/
|
2004-03-26 19:42:04 +00:00
|
|
|
U_STABLE int32_t U_EXPORT2
|
2001-09-21 00:27:17 +00:00
|
|
|
u_digit(UChar32 ch, int8_t radix);
|
|
|
|
|
|
|
|
/**
|
2003-02-11 23:27:40 +00:00
|
|
|
* Determines the character representation for a specific digit in
|
|
|
|
* the specified radix. If the value of <code>radix</code> is not a
|
|
|
|
* valid radix, or the value of <code>digit</code> is not a valid
|
2001-09-21 00:27:17 +00:00
|
|
|
* digit in the specified radix, the null character
|
2003-02-11 23:27:40 +00:00
|
|
|
* (<code>U+0000</code>) is returned.
|
2001-09-21 00:27:17 +00:00
|
|
|
* <p>
|
2003-02-11 23:27:40 +00:00
|
|
|
* The <code>radix</code> argument is valid if it is greater than or
|
2001-09-21 00:27:17 +00:00
|
|
|
* equal to 2 and less than or equal to 36.
|
|
|
|
* The <code>digit</code> argument is valid if
|
2003-02-11 23:27:40 +00:00
|
|
|
* <code>0 <= digit < radix</code>.
|
2001-09-21 00:27:17 +00:00
|
|
|
* <p>
|
2003-02-11 23:27:40 +00:00
|
|
|
* If the digit is less than 10, then
|
|
|
|
* <code>'0' + digit</code> is returned. Otherwise, the value
|
|
|
|
* <code>'a' + digit - 10</code> is returned.
|
|
|
|
*
|
|
|
|
* Same as java.lang.Character.forDigit().
|
2001-09-21 00:27:17 +00:00
|
|
|
*
|
|
|
|
* @param digit the number to convert to a character.
|
|
|
|
* @param radix the radix.
|
|
|
|
* @return the <code>char</code> representation of the specified digit
|
2003-02-11 23:27:40 +00:00
|
|
|
* in the specified radix.
|
2001-09-21 00:27:17 +00:00
|
|
|
*
|
|
|
|
* @see u_digit
|
|
|
|
* @see u_charDigitValue
|
|
|
|
* @see u_isdigit
|
2002-12-04 23:39:56 +00:00
|
|
|
* @stable ICU 2.0
|
2001-09-21 00:27:17 +00:00
|
|
|
*/
|
2004-03-26 19:42:04 +00:00
|
|
|
U_STABLE UChar32 U_EXPORT2
|
2001-09-21 00:27:17 +00:00
|
|
|
u_forDigit(int32_t digit, int8_t radix);
|
|
|
|
|
2002-03-04 01:22:45 +00:00
|
|
|
/**
|
|
|
|
* Get the "age" of the code point.
|
|
|
|
* The "age" is the Unicode version when the code point was first
|
|
|
|
* designated (as a non-character or for Private Use)
|
|
|
|
* or assigned a character.
|
|
|
|
* This can be useful to avoid emitting code points to receiving
|
|
|
|
* processes that do not accept newer characters.
|
|
|
|
* The data is from the UCD file DerivedAge.txt.
|
|
|
|
*
|
|
|
|
* @param c The code point.
|
|
|
|
* @param versionArray The Unicode version number array, to be filled in.
|
|
|
|
*
|
2003-02-11 01:59:32 +00:00
|
|
|
* @stable ICU 2.1
|
2002-03-04 01:22:45 +00:00
|
|
|
*/
|
2004-03-26 19:42:04 +00:00
|
|
|
U_STABLE void U_EXPORT2
|
2002-03-04 01:22:45 +00:00
|
|
|
u_charAge(UChar32 c, UVersionInfo versionArray);
|
|
|
|
|
1999-12-28 23:39:02 +00:00
|
|
|
/**
|
2003-02-11 23:27:40 +00:00
|
|
|
* Gets the Unicode version information.
|
|
|
|
* The version array is filled in with the version information
|
|
|
|
* for the Unicode standard that is currently used by ICU.
|
|
|
|
* For example, Unicode version 3.1.1 is represented as an array with
|
|
|
|
* the values { 3, 1, 1, 0 }.
|
|
|
|
*
|
|
|
|
* @param versionArray an output array that will be filled in with
|
|
|
|
* the Unicode version number
|
2002-12-04 23:39:56 +00:00
|
|
|
* @stable ICU 2.0
|
1999-12-28 23:39:02 +00:00
|
|
|
*/
|
2004-03-26 19:42:04 +00:00
|
|
|
U_STABLE void U_EXPORT2
|
2003-04-26 00:12:33 +00:00
|
|
|
u_getUnicodeVersion(UVersionInfo versionArray);
|
1999-12-28 23:39:02 +00:00
|
|
|
|
2010-03-09 23:11:48 +00:00
|
|
|
#if !UCONFIG_NO_NORMALIZATION
|
2002-07-08 16:40:57 +00:00
|
|
|
/**
|
|
|
|
* Get the FC_NFKC_Closure property string for a character.
|
|
|
|
* See Unicode Standard Annex #15 for details, search for "FC_NFKC_Closure"
|
|
|
|
* or for "FNC": http://www.unicode.org/reports/tr15/
|
|
|
|
*
|
|
|
|
* @param c The character (code point) for which to get the FC_NFKC_Closure string.
|
|
|
|
* It must be <code>0<=c<=0x10ffff</code>.
|
|
|
|
* @param dest Destination address for copying the string.
|
|
|
|
* The string will be zero-terminated if possible.
|
|
|
|
* If there is no FC_NFKC_Closure string,
|
|
|
|
* then the buffer will be set to the empty string.
|
|
|
|
* @param destCapacity <code>==sizeof(dest)</code>
|
|
|
|
* @param pErrorCode Pointer to a UErrorCode variable.
|
|
|
|
* @return The length of the string, or 0 if there is no FC_NFKC_Closure string for this character.
|
|
|
|
* If the destCapacity is less than or equal to the length, then the buffer
|
|
|
|
* contains the truncated name and the returned length indicates the full
|
|
|
|
* length of the name.
|
|
|
|
* The length does not include the zero-termination.
|
2003-02-11 23:27:40 +00:00
|
|
|
*
|
2003-11-18 02:37:24 +00:00
|
|
|
* @stable ICU 2.2
|
2002-07-08 16:40:57 +00:00
|
|
|
*/
|
2004-03-26 19:42:04 +00:00
|
|
|
U_STABLE int32_t U_EXPORT2
|
2002-07-08 16:40:57 +00:00
|
|
|
u_getFC_NFKC_Closure(UChar32 c, UChar *dest, int32_t destCapacity, UErrorCode *pErrorCode);
|
|
|
|
|
2010-03-09 23:11:48 +00:00
|
|
|
#endif
|
|
|
|
|
|
|
|
|
2002-01-12 00:11:09 +00:00
|
|
|
U_CDECL_END
|
|
|
|
|
1999-12-28 23:39:02 +00:00
|
|
|
#endif /*_UCHAR*/
|
|
|
|
/*eof*/
|