Symaptic: os/textandloc/fontservices/textshaperplugin/IcuSource/common/unicode/uchar.h@260cb5ec6c19 (annotated)

sl@0	1	/*
sl@0	2	**********************************************************************
sl@0	3	* Copyright (C) 1997-2005, International Business Machines
sl@0	4	* Corporation and others. All Rights Reserved.
sl@0	5	**********************************************************************
sl@0	6	*
sl@0	7	* File UCHAR.H
sl@0	8	*
sl@0	9	* Modification History:
sl@0	10	*
sl@0	11	* Date Name Description
sl@0	12	* 04/02/97 aliu Creation.
sl@0	13	* 03/29/99 helena Updated for C APIs.
sl@0	14	* 4/15/99 Madhu Updated for C Implementation and Javadoc
sl@0	15	* 5/20/99 Madhu Added the function u_getVersion()
sl@0	16	* 8/19/1999 srl Upgraded scripts to Unicode 3.0
sl@0	17	* 8/27/1999 schererm UCharDirection constants: U_...
sl@0	18	* 11/11/1999 weiv added u_isalnum(), cleaned comments
sl@0	19	* 01/11/2000 helena Renamed u_getVersion to u_getUnicodeVersion().
sl@0	20	******************************************************************************
sl@0	21	*/
sl@0	22
sl@0	23	#ifndef UCHAR_H
sl@0	24	#define UCHAR_H
sl@0	25
sl@0	26	#include "unicode/utypes.h"
sl@0	27
sl@0	28	U_CDECL_BEGIN
sl@0	29
sl@0	30	/==========================================================================/
sl@0	31	/* Unicode version number */
sl@0	32	/==========================================================================/
sl@0	33	/**
sl@0	34	* Unicode version number, default for the current ICU version.
sl@0	35	* The actual Unicode Character Database (UCD) data is stored in uprops.dat
sl@0	36	* and may be generated from UCD files from a different Unicode version.
sl@0	37	* Call u_getUnicodeVersion to get the actual Unicode version of the data.
sl@0	38	*
sl@0	39	* @see u_getUnicodeVersion
sl@0	40	* @stable ICU 2.0
sl@0	41	*/
sl@0	42	#define U_UNICODE_VERSION "4.1"
sl@0	43
sl@0	44	/**
sl@0	45	* \file
sl@0	46	* \brief C API: Unicode Properties
sl@0	47	*
sl@0	48	* This C API provides low-level access to the Unicode Character Database.
sl@0	49	* In addition to raw property values, some convenience functions calculate
sl@0	50	* derived properties, for example for Java-style programming.
sl@0	51	*
sl@0	52	* Unicode assigns each code point (not just assigned character) values for
sl@0	53	* many properties.
sl@0	54	* Most of them are simple boolean flags, or constants from a small enumerated list.
sl@0	55	* For some properties, values are strings or other relatively more complex types.
sl@0	56	*
sl@0	57	* For more information see
sl@0	58	* "About the Unicode Character Database" (http://www.unicode.org/ucd/)
sl@0	59	* and the ICU User Guide chapter on Properties (http://icu.sourceforge.net/userguide/properties.html).
sl@0	60	*
sl@0	61	* Many functions are designed to match java.lang.Character functions.
sl@0	62	* See the individual function documentation,
sl@0	63	* and see the JDK 1.4 java.lang.Character documentation
sl@0	64	* at http://java.sun.com/j2se/1.4/docs/api/java/lang/Character.html
sl@0	65	*
sl@0	66	* There are also functions that provide easy migration from C/POSIX functions
sl@0	67	* like isblank(). Their use is generally discouraged because the C/POSIX
sl@0	68	* standards do not define their semantics beyond the ASCII range, which means
sl@0	69	* that different implementations exhibit very different behavior.
sl@0	70	* Instead, Unicode properties should be used directly.
sl@0	71	*
sl@0	72	* There are also only a few, broad C/POSIX character classes, and they tend
sl@0	73	* to be used for conflicting purposes. For example, the "isalpha()" class
sl@0	74	* is sometimes used to determine word boundaries, while a more sophisticated
sl@0	75	* approach would at least distinguish initial letters from continuation
sl@0	76	* characters (the latter including combining marks).
sl@0	77	* (In ICU, BreakIterator is the most sophisticated API for word boundaries.)
sl@0	78	* Another example: There is no "istitle()" class for titlecase characters.
sl@0	79	*
sl@0	80	* ICU 3.4 and later provides API access for all twelve C/POSIX character classes.
sl@0	81	* ICU implements them according to the Standard Recommendations in
sl@0	82	* Annex C: Compatibility Properties of UTS #18 Unicode Regular Expressions
sl@0	83	* (http://www.unicode.org/reports/tr18/#Compatibility_Properties).
sl@0	84	*
sl@0	85	* API access for C/POSIX character classes is as follows:
sl@0	86	* - alpha: u_isUAlphabetic(c) or u_hasBinaryProperty(c, UCHAR_ALPHABETIC)
sl@0	87	* - lower: u_isULowercase(c) or u_hasBinaryProperty(c, UCHAR_LOWERCASE)
sl@0	88	* - upper: u_isUUppercase(c) or u_hasBinaryProperty(c, UCHAR_UPPERCASE)
sl@0	89	* - punct: u_ispunct(c)
sl@0	90	* - digit: u_isdigit(c) or u_charType(c)==U_DECIMAL_DIGIT_NUMBER
sl@0	91	* - xdigit: u_isxdigit(c) or u_hasBinaryProperty(c, UCHAR_POSIX_XDIGIT)
sl@0	92	* - alnum: u_hasBinaryProperty(c, UCHAR_POSIX_ALNUM)
sl@0	93	* - space: u_isUWhiteSpace(c) or u_hasBinaryProperty(c, UCHAR_WHITE_SPACE)
sl@0	94	* - blank: u_isblank(c) or u_hasBinaryProperty(c, UCHAR_POSIX_BLANK)
sl@0	95	* - cntrl: u_charType(c)==U_CONTROL_CHAR
sl@0	96	* - graph: u_hasBinaryProperty(c, UCHAR_POSIX_GRAPH)
sl@0	97	* - print: u_hasBinaryProperty(c, UCHAR_POSIX_PRINT)
sl@0	98	*
sl@0	99	* Note: Some of the u_isxyz() functions in uchar.h predate, and do not match,
sl@0	100	* the Standard Recommendations in UTS #18. Instead, they match Java
sl@0	101	* functions according to their API documentation.
sl@0	102	*
sl@0	103	* \htmlonly
sl@0	104	* The C/POSIX character classes are also available in UnicodeSet patterns,
sl@0	105	* using patterns like [:graph:] or \p{graph}.
sl@0	106	* \endhtmlonly
sl@0	107	*
sl@0	108	* Note: There are several ICU whitespace functions.
sl@0	109	* Comparison:
sl@0	110	* - u_isUWhiteSpace=UCHAR_WHITE_SPACE: Unicode White_Space property;
sl@0	111	* most of general categories "Z" (separators) + most whitespace ISO controls
sl@0	112	* (including no-break spaces, but excluding IS1..IS4 and ZWSP)
sl@0	113	* - u_isWhitespace: Java isWhitespace; Z + whitespace ISO controls but excluding no-break spaces
sl@0	114	* - u_isJavaSpaceChar: Java isSpaceChar; just Z (including no-break spaces)
sl@0	115	* - u_isspace: Z + whitespace ISO controls (including no-break spaces)
sl@0	116	* - u_isblank: "horizontal spaces" = TAB + Zs - ZWSP
sl@0	117	*/
sl@0	118
sl@0	119	/**
sl@0	120	* Constants.
sl@0	121	*/
sl@0	122
sl@0	123	/** The lowest Unicode code point value. Code points are non-negative. @stable ICU 2.0 */
sl@0	124	#define UCHAR_MIN_VALUE 0
sl@0	125
sl@0	126	/**
sl@0	127	* The highest Unicode code point value (scalar value) according to
sl@0	128	* The Unicode Standard. This is a 21-bit value (20.1 bits, rounded up).
sl@0	129	* For a single character, UChar32 is a simple type that can hold any code point value.
sl@0	130	*
sl@0	131	* @see UChar32
sl@0	132	* @stable ICU 2.0
sl@0	133	*/
sl@0	134	#define UCHAR_MAX_VALUE 0x10ffff
sl@0	135
sl@0	136	/**
sl@0	137	* Get a single-bit bit set (a flag) from a bit number 0..31.
sl@0	138	* @stable ICU 2.1
sl@0	139	*/
sl@0	140	#define U_MASK(x) ((uint32_t)1<<(x))
sl@0	141
sl@0	142	/*
sl@0	143	* !! Note: Several comments in this file are machine-read by the
sl@0	144	* genpname tool. These comments describe the correspondence between
sl@0	145	* icu enum constants and UCD entities. Do not delete them. Update
sl@0	146	* these comments as needed.
sl@0	147	*
sl@0	148	* Any comment of the form "/ [name] /" (spaces added) is such
sl@0	149	* a comment.
sl@0	150	*
sl@0	151	* The U_JG_* and U_GC_*_MASK constants are matched by their symbolic
sl@0	152	* name, which must match PropertyValueAliases.txt.
sl@0	153	*/
sl@0	154
sl@0	155	/**
sl@0	156	* Selection constants for Unicode properties.
sl@0	157	* These constants are used in functions like u_hasBinaryProperty to select
sl@0	158	* one of the Unicode properties.
sl@0	159	*
sl@0	160	* The properties APIs are intended to reflect Unicode properties as defined
sl@0	161	* in the Unicode Character Database (UCD) and Unicode Technical Reports (UTR).
sl@0	162	* For details about the properties see http://www.unicode.org/ucd/ .
sl@0	163	* For names of Unicode properties see the UCD file PropertyAliases.txt.
sl@0	164	*
sl@0	165	* Important: If ICU is built with UCD files from Unicode versions below, e.g., 3.2,
sl@0	166	* then properties marked with "new in Unicode 3.2" are not or not fully available.
sl@0	167	* Check u_getUnicodeVersion to be sure.
sl@0	168	*
sl@0	169	* @see u_hasBinaryProperty
sl@0	170	* @see u_getIntPropertyValue
sl@0	171	* @see u_getUnicodeVersion
sl@0	172	* @stable ICU 2.1
sl@0	173	*/
sl@0	174	typedef enum UProperty {
sl@0	175	/* See note !!. Comments of the form "Binary property Dash",
sl@0	176	"Enumerated property Script", "Double property Numeric_Value",
sl@0	177	and "String property Age" are read by genpname. */
sl@0	178
sl@0	179	/* Note: Place UCHAR_ALPHABETIC before UCHAR_BINARY_START so that
sl@0	180	debuggers display UCHAR_ALPHABETIC as the symbolic name for 0,
sl@0	181	rather than UCHAR_BINARY_START. Likewise for other *_START
sl@0	182	identifiers. */
sl@0	183
sl@0	184	/** Binary property Alphabetic. Same as u_isUAlphabetic, different from u_isalpha.
sl@0	185	Lu+Ll+Lt+Lm+Lo+Nl+Other_Alphabetic @stable ICU 2.1 */
sl@0	186	UCHAR_ALPHABETIC=0,
sl@0	187	/** First constant for binary Unicode properties. @stable ICU 2.1 */
sl@0	188	UCHAR_BINARY_START=UCHAR_ALPHABETIC,
sl@0	189	/** Binary property ASCII_Hex_Digit. 0-9 A-F a-f @stable ICU 2.1 */
sl@0	190	UCHAR_ASCII_HEX_DIGIT,
sl@0	191	/** Binary property Bidi_Control.
sl@0	192	Format controls which have specific functions
sl@0	193	in the Bidi Algorithm. @stable ICU 2.1 */
sl@0	194	UCHAR_BIDI_CONTROL,
sl@0	195	/** Binary property Bidi_Mirrored.
sl@0	196	Characters that may change display in RTL text.
sl@0	197	Same as u_isMirrored.
sl@0	198	See Bidi Algorithm, UTR 9. @stable ICU 2.1 */
sl@0	199	UCHAR_BIDI_MIRRORED,
sl@0	200	/** Binary property Dash. Variations of dashes. @stable ICU 2.1 */
sl@0	201	UCHAR_DASH,
sl@0	202	/** Binary property Default_Ignorable_Code_Point (new in Unicode 3.2).
sl@0	203	Ignorable in most processing.
sl@0	204	<2060..206F, FFF0..FFFB, E0000..E0FFF>+Other_Default_Ignorable_Code_Point+(Cf+Cc+Cs-White_Space) @stable ICU 2.1 */
sl@0	205	UCHAR_DEFAULT_IGNORABLE_CODE_POINT,
sl@0	206	/** Binary property Deprecated (new in Unicode 3.2).
sl@0	207	The usage of deprecated characters is strongly discouraged. @stable ICU 2.1 */
sl@0	208	UCHAR_DEPRECATED,
sl@0	209	/** Binary property Diacritic. Characters that linguistically modify
sl@0	210	the meaning of another character to which they apply. @stable ICU 2.1 */
sl@0	211	UCHAR_DIACRITIC,
sl@0	212	/** Binary property Extender.
sl@0	213	Extend the value or shape of a preceding alphabetic character,
sl@0	214	e.g., length and iteration marks. @stable ICU 2.1 */
sl@0	215	UCHAR_EXTENDER,
sl@0	216	/** Binary property Full_Composition_Exclusion.
sl@0	217	CompositionExclusions.txt+Singleton Decompositions+
sl@0	218	Non-Starter Decompositions. @stable ICU 2.1 */
sl@0	219	UCHAR_FULL_COMPOSITION_EXCLUSION,
sl@0	220	/** Binary property Grapheme_Base (new in Unicode 3.2).
sl@0	221	For programmatic determination of grapheme cluster boundaries.
sl@0	222	[0..10FFFF]-Cc-Cf-Cs-Co-Cn-Zl-Zp-Grapheme_Link-Grapheme_Extend-CGJ @stable ICU 2.1 */
sl@0	223	UCHAR_GRAPHEME_BASE,
sl@0	224	/** Binary property Grapheme_Extend (new in Unicode 3.2).
sl@0	225	For programmatic determination of grapheme cluster boundaries.
sl@0	226	Me+Mn+Mc+Other_Grapheme_Extend-Grapheme_Link-CGJ @stable ICU 2.1 */
sl@0	227	UCHAR_GRAPHEME_EXTEND,
sl@0	228	/** Binary property Grapheme_Link (new in Unicode 3.2).
sl@0	229	For programmatic determination of grapheme cluster boundaries. @stable ICU 2.1 */
sl@0	230	UCHAR_GRAPHEME_LINK,
sl@0	231	/** Binary property Hex_Digit.
sl@0	232	Characters commonly used for hexadecimal numbers. @stable ICU 2.1 */
sl@0	233	UCHAR_HEX_DIGIT,
sl@0	234	/** Binary property Hyphen. Dashes used to mark connections
sl@0	235	between pieces of words, plus the Katakana middle dot. @stable ICU 2.1 */
sl@0	236	UCHAR_HYPHEN,
sl@0	237	/** Binary property ID_Continue.
sl@0	238	Characters that can continue an identifier.
sl@0	239	DerivedCoreProperties.txt also says "NOTE: Cf characters should be filtered out."
sl@0	240	ID_Start+Mn+Mc+Nd+Pc @stable ICU 2.1 */
sl@0	241	UCHAR_ID_CONTINUE,
sl@0	242	/** Binary property ID_Start.
sl@0	243	Characters that can start an identifier.
sl@0	244	Lu+Ll+Lt+Lm+Lo+Nl @stable ICU 2.1 */
sl@0	245	UCHAR_ID_START,
sl@0	246	/** Binary property Ideographic.
sl@0	247	CJKV ideographs. @stable ICU 2.1 */
sl@0	248	UCHAR_IDEOGRAPHIC,
sl@0	249	/** Binary property IDS_Binary_Operator (new in Unicode 3.2).
sl@0	250	For programmatic determination of
sl@0	251	Ideographic Description Sequences. @stable ICU 2.1 */
sl@0	252	UCHAR_IDS_BINARY_OPERATOR,
sl@0	253	/** Binary property IDS_Trinary_Operator (new in Unicode 3.2).
sl@0	254	For programmatic determination of
sl@0	255	Ideographic Description Sequences. @stable ICU 2.1 */
sl@0	256	UCHAR_IDS_TRINARY_OPERATOR,
sl@0	257	/** Binary property Join_Control.
sl@0	258	Format controls for cursive joining and ligation. @stable ICU 2.1 */
sl@0	259	UCHAR_JOIN_CONTROL,
sl@0	260	/** Binary property Logical_Order_Exception (new in Unicode 3.2).
sl@0	261	Characters that do not use logical order and
sl@0	262	require special handling in most processing. @stable ICU 2.1 */
sl@0	263	UCHAR_LOGICAL_ORDER_EXCEPTION,
sl@0	264	/** Binary property Lowercase. Same as u_isULowercase, different from u_islower.
sl@0	265	Ll+Other_Lowercase @stable ICU 2.1 */
sl@0	266	UCHAR_LOWERCASE,
sl@0	267	/** Binary property Math. Sm+Other_Math @stable ICU 2.1 */
sl@0	268	UCHAR_MATH,
sl@0	269	/** Binary property Noncharacter_Code_Point.
sl@0	270	Code points that are explicitly defined as illegal
sl@0	271	for the encoding of characters. @stable ICU 2.1 */
sl@0	272	UCHAR_NONCHARACTER_CODE_POINT,
sl@0	273	/** Binary property Quotation_Mark. @stable ICU 2.1 */
sl@0	274	UCHAR_QUOTATION_MARK,
sl@0	275	/** Binary property Radical (new in Unicode 3.2).
sl@0	276	For programmatic determination of
sl@0	277	Ideographic Description Sequences. @stable ICU 2.1 */
sl@0	278	UCHAR_RADICAL,
sl@0	279	/** Binary property Soft_Dotted (new in Unicode 3.2).
sl@0	280	Characters with a "soft dot", like i or j.
sl@0	281	An accent placed on these characters causes
sl@0	282	the dot to disappear. @stable ICU 2.1 */
sl@0	283	UCHAR_SOFT_DOTTED,
sl@0	284	/** Binary property Terminal_Punctuation.
sl@0	285	Punctuation characters that generally mark
sl@0	286	the end of textual units. @stable ICU 2.1 */
sl@0	287	UCHAR_TERMINAL_PUNCTUATION,
sl@0	288	/** Binary property Unified_Ideograph (new in Unicode 3.2).
sl@0	289	For programmatic determination of
sl@0	290	Ideographic Description Sequences. @stable ICU 2.1 */
sl@0	291	UCHAR_UNIFIED_IDEOGRAPH,
sl@0	292	/** Binary property Uppercase. Same as u_isUUppercase, different from u_isupper.
sl@0	293	Lu+Other_Uppercase @stable ICU 2.1 */
sl@0	294	UCHAR_UPPERCASE,
sl@0	295	/** Binary property White_Space.
sl@0	296	Same as u_isUWhiteSpace, different from u_isspace and u_isWhitespace.
sl@0	297	Space characters+TAB+CR+LF-ZWSP-ZWNBSP @stable ICU 2.1 */
sl@0	298	UCHAR_WHITE_SPACE,
sl@0	299	/** Binary property XID_Continue.
sl@0	300	ID_Continue modified to allow closure under
sl@0	301	normalization forms NFKC and NFKD. @stable ICU 2.1 */
sl@0	302	UCHAR_XID_CONTINUE,
sl@0	303	/** Binary property XID_Start. ID_Start modified to allow
sl@0	304	closure under normalization forms NFKC and NFKD. @stable ICU 2.1 */
sl@0	305	UCHAR_XID_START,
sl@0	306	/** Binary property Case_Sensitive. Either the source of a case
sl@0	307	mapping or _in_ the target of a case mapping. Not the same as
sl@0	308	the general category Cased_Letter. @stable ICU 2.6 */
sl@0	309	UCHAR_CASE_SENSITIVE,
sl@0	310	/** Binary property STerm (new in Unicode 4.0.1).
sl@0	311	Sentence Terminal. Used in UAX #29: Text Boundaries
sl@0	312	(http://www.unicode.org/reports/tr29/)
sl@0	313	@draft ICU 3.0 */
sl@0	314	UCHAR_S_TERM,
sl@0	315	/** Binary property Variation_Selector (new in Unicode 4.0.1).
sl@0	316	Indicates all those characters that qualify as Variation Selectors.
sl@0	317	For details on the behavior of these characters,
sl@0	318	see StandardizedVariants.html and 15.6 Variation Selectors.
sl@0	319	@draft ICU 3.0 */
sl@0	320	UCHAR_VARIATION_SELECTOR,
sl@0	321	/** Binary property NFD_Inert.
sl@0	322	ICU-specific property for characters that are inert under NFD,
sl@0	323	i.e., they do not interact with adjacent characters.
sl@0	324	Used for example in normalizing transforms in incremental mode
sl@0	325	to find the boundary of safely normalizable text despite possible
sl@0	326	text additions.
sl@0	327
sl@0	328	There is one such property per normalization form.
sl@0	329	These properties are computed as follows - an inert character is:
sl@0	330	a) unassigned, or ALL of the following:
sl@0	331	b) of combining class 0.
sl@0	332	c) not decomposed by this normalization form.
sl@0	333	AND if NFC or NFKC,
sl@0	334	d) can never compose with a previous character.
sl@0	335	e) can never compose with a following character.
sl@0	336	f) can never change if another character is added.
sl@0	337	Example: a-breve might satisfy all but f, but if you
sl@0	338	add an ogonek it changes to a-ogonek + breve
sl@0	339
sl@0	340	See also com.ibm.text.UCD.NFSkippable in the ICU4J repository,
sl@0	341	and icu/source/common/unormimp.h .
sl@0	342	@draft ICU 3.0 */
sl@0	343	UCHAR_NFD_INERT,
sl@0	344	/** Binary property NFKD_Inert.
sl@0	345	ICU-specific property for characters that are inert under NFKD,
sl@0	346	i.e., they do not interact with adjacent characters.
sl@0	347	Used for example in normalizing transforms in incremental mode
sl@0	348	to find the boundary of safely normalizable text despite possible
sl@0	349	text additions.
sl@0	350	@see UCHAR_NFD_INERT
sl@0	351	@draft ICU 3.0 */
sl@0	352	UCHAR_NFKD_INERT,
sl@0	353	/** Binary property NFC_Inert.
sl@0	354	ICU-specific property for characters that are inert under NFC,
sl@0	355	i.e., they do not interact with adjacent characters.
sl@0	356	Used for example in normalizing transforms in incremental mode
sl@0	357	to find the boundary of safely normalizable text despite possible
sl@0	358	text additions.
sl@0	359	@see UCHAR_NFD_INERT
sl@0	360	@draft ICU 3.0 */
sl@0	361	UCHAR_NFC_INERT,
sl@0	362	/** Binary property NFKC_Inert.
sl@0	363	ICU-specific property for characters that are inert under NFKC,
sl@0	364	i.e., they do not interact with adjacent characters.
sl@0	365	Used for example in normalizing transforms in incremental mode
sl@0	366	to find the boundary of safely normalizable text despite possible
sl@0	367	text additions.
sl@0	368	@see UCHAR_NFD_INERT
sl@0	369	@draft ICU 3.0 */
sl@0	370	UCHAR_NFKC_INERT,
sl@0	371	/** Binary Property Segment_Starter.
sl@0	372	ICU-specific property for characters that are starters in terms of
sl@0	373	Unicode normalization and combining character sequences.
sl@0	374	They have ccc=0 and do not occur in non-initial position of the
sl@0	375	canonical decomposition of any character
sl@0	376	(like " in NFD(a-umlaut) and a Jamo T in an NFD(Hangul LVT)).
sl@0	377	ICU uses this property for segmenting a string for generating a set of
sl@0	378	canonically equivalent strings, e.g. for canonical closure while
sl@0	379	processing collation tailoring rules.
sl@0	380	@draft ICU 3.0 */
sl@0	381	UCHAR_SEGMENT_STARTER,
sl@0	382	/** Binary property Pattern_Syntax (new in Unicode 4.1).
sl@0	383	See UAX #31 Identifier and Pattern Syntax
sl@0	384	(http://www.unicode.org/reports/tr31/)
sl@0	385	@draft ICU 3.4 */
sl@0	386	UCHAR_PATTERN_SYNTAX,
sl@0	387	/** Binary property Pattern_White_Space (new in Unicode 4.1).
sl@0	388	See UAX #31 Identifier and Pattern Syntax
sl@0	389	(http://www.unicode.org/reports/tr31/)
sl@0	390	@draft ICU 3.4 */
sl@0	391	UCHAR_PATTERN_WHITE_SPACE,
sl@0	392	/** Binary property alnum (a C/POSIX character class).
sl@0	393	Implemented according to the UTS #18 Annex C Standard Recommendation.
sl@0	394	See the uchar.h file documentation.
sl@0	395	@draft ICU 3.4 */
sl@0	396	UCHAR_POSIX_ALNUM,
sl@0	397	/** Binary property blank (a C/POSIX character class).
sl@0	398	Implemented according to the UTS #18 Annex C Standard Recommendation.
sl@0	399	See the uchar.h file documentation.
sl@0	400	@draft ICU 3.4 */
sl@0	401	UCHAR_POSIX_BLANK,
sl@0	402	/** Binary property graph (a C/POSIX character class).
sl@0	403	Implemented according to the UTS #18 Annex C Standard Recommendation.
sl@0	404	See the uchar.h file documentation.
sl@0	405	@draft ICU 3.4 */
sl@0	406	UCHAR_POSIX_GRAPH,
sl@0	407	/** Binary property print (a C/POSIX character class).
sl@0	408	Implemented according to the UTS #18 Annex C Standard Recommendation.
sl@0	409	See the uchar.h file documentation.
sl@0	410	@draft ICU 3.4 */
sl@0	411	UCHAR_POSIX_PRINT,
sl@0	412	/** Binary property xdigit (a C/POSIX character class).
sl@0	413	Implemented according to the UTS #18 Annex C Standard Recommendation.
sl@0	414	See the uchar.h file documentation.
sl@0	415	@draft ICU 3.4 */
sl@0	416	UCHAR_POSIX_XDIGIT,
sl@0	417	/** One more than the last constant for binary Unicode properties. @stable ICU 2.1 */
sl@0	418	UCHAR_BINARY_LIMIT,
sl@0	419
sl@0	420	/** Enumerated property Bidi_Class.
sl@0	421	Same as u_charDirection, returns UCharDirection values. @stable ICU 2.2 */
sl@0	422	UCHAR_BIDI_CLASS=0x1000,
sl@0	423	/** First constant for enumerated/integer Unicode properties. @stable ICU 2.2 */
sl@0	424	UCHAR_INT_START=UCHAR_BIDI_CLASS,
sl@0	425	/** Enumerated property Block.
sl@0	426	Same as ublock_getCode, returns UBlockCode values. @stable ICU 2.2 */
sl@0	427	UCHAR_BLOCK,
sl@0	428	/** Enumerated property Canonical_Combining_Class.
sl@0	429	Same as u_getCombiningClass, returns 8-bit numeric values. @stable ICU 2.2 */
sl@0	430	UCHAR_CANONICAL_COMBINING_CLASS,
sl@0	431	/** Enumerated property Decomposition_Type.
sl@0	432	Returns UDecompositionType values. @stable ICU 2.2 */
sl@0	433	UCHAR_DECOMPOSITION_TYPE,
sl@0	434	/** Enumerated property East_Asian_Width.
sl@0	435	See http://www.unicode.org/reports/tr11/
sl@0	436	Returns UEastAsianWidth values. @stable ICU 2.2 */
sl@0	437	UCHAR_EAST_ASIAN_WIDTH,
sl@0	438	/** Enumerated property General_Category.
sl@0	439	Same as u_charType, returns UCharCategory values. @stable ICU 2.2 */
sl@0	440	UCHAR_GENERAL_CATEGORY,
sl@0	441	/** Enumerated property Joining_Group.
sl@0	442	Returns UJoiningGroup values. @stable ICU 2.2 */
sl@0	443	UCHAR_JOINING_GROUP,
sl@0	444	/** Enumerated property Joining_Type.
sl@0	445	Returns UJoiningType values. @stable ICU 2.2 */
sl@0	446	UCHAR_JOINING_TYPE,
sl@0	447	/** Enumerated property Line_Break.
sl@0	448	Returns ULineBreak values. @stable ICU 2.2 */
sl@0	449	UCHAR_LINE_BREAK,
sl@0	450	/** Enumerated property Numeric_Type.
sl@0	451	Returns UNumericType values. @stable ICU 2.2 */
sl@0	452	UCHAR_NUMERIC_TYPE,
sl@0	453	/** Enumerated property Script.
sl@0	454	Same as uscript_getScript, returns UScriptCode values. @stable ICU 2.2 */
sl@0	455	UCHAR_SCRIPT,
sl@0	456	/** Enumerated property Hangul_Syllable_Type, new in Unicode 4.
sl@0	457	Returns UHangulSyllableType values. @stable ICU 2.6 */
sl@0	458	UCHAR_HANGUL_SYLLABLE_TYPE,
sl@0	459	/** Enumerated property NFD_Quick_Check.
sl@0	460	Returns UNormalizationCheckResult values. @draft ICU 3.0 */
sl@0	461	UCHAR_NFD_QUICK_CHECK,
sl@0	462	/** Enumerated property NFKD_Quick_Check.
sl@0	463	Returns UNormalizationCheckResult values. @draft ICU 3.0 */
sl@0	464	UCHAR_NFKD_QUICK_CHECK,
sl@0	465	/** Enumerated property NFC_Quick_Check.
sl@0	466	Returns UNormalizationCheckResult values. @draft ICU 3.0 */
sl@0	467	UCHAR_NFC_QUICK_CHECK,
sl@0	468	/** Enumerated property NFKC_Quick_Check.
sl@0	469	Returns UNormalizationCheckResult values. @draft ICU 3.0 */
sl@0	470	UCHAR_NFKC_QUICK_CHECK,
sl@0	471	/** Enumerated property Lead_Canonical_Combining_Class.
sl@0	472	ICU-specific property for the ccc of the first code point
sl@0	473	of the decomposition, or lccc(c)=ccc(NFD(c)[0]).
sl@0	474	Useful for checking for canonically ordered text;
sl@0	475	see UNORM_FCD and http://www.unicode.org/notes/tn5/#FCD .
sl@0	476	Returns 8-bit numeric values like UCHAR_CANONICAL_COMBINING_CLASS. @draft ICU 3.0 */
sl@0	477	UCHAR_LEAD_CANONICAL_COMBINING_CLASS,
sl@0	478	/** Enumerated property Trail_Canonical_Combining_Class.
sl@0	479	ICU-specific property for the ccc of the last code point
sl@0	480	of the decomposition, or tccc(c)=ccc(NFD(c)[last]).
sl@0	481	Useful for checking for canonically ordered text;
sl@0	482	see UNORM_FCD and http://www.unicode.org/notes/tn5/#FCD .
sl@0	483	Returns 8-bit numeric values like UCHAR_CANONICAL_COMBINING_CLASS. @draft ICU 3.0 */
sl@0	484	UCHAR_TRAIL_CANONICAL_COMBINING_CLASS,
sl@0	485	/** Enumerated property Grapheme_Cluster_Break (new in Unicode 4.1).
sl@0	486	Used in UAX #29: Text Boundaries
sl@0	487	(http://www.unicode.org/reports/tr29/)
sl@0	488	Returns UGraphemeClusterBreak values. @draft ICU 3.4 */
sl@0	489	UCHAR_GRAPHEME_CLUSTER_BREAK,
sl@0	490	/** Enumerated property Sentence_Break (new in Unicode 4.1).
sl@0	491	Used in UAX #29: Text Boundaries
sl@0	492	(http://www.unicode.org/reports/tr29/)
sl@0	493	Returns USentenceBreak values. @draft ICU 3.4 */
sl@0	494	UCHAR_SENTENCE_BREAK,
sl@0	495	/** Enumerated property Word_Break (new in Unicode 4.1).
sl@0	496	Used in UAX #29: Text Boundaries
sl@0	497	(http://www.unicode.org/reports/tr29/)
sl@0	498	Returns UWordBreakValues values. @draft ICU 3.4 */
sl@0	499	UCHAR_WORD_BREAK,
sl@0	500	/** One more than the last constant for enumerated/integer Unicode properties. @stable ICU 2.2 */
sl@0	501	UCHAR_INT_LIMIT,
sl@0	502
sl@0	503	/** Bitmask property General_Category_Mask.
sl@0	504	This is the General_Category property returned as a bit mask.
sl@0	505	When used in u_getIntPropertyValue(c), same as U_MASK(u_charType(c)),
sl@0	506	returns bit masks for UCharCategory values where exactly one bit is set.
sl@0	507	When used with u_getPropertyValueName() and u_getPropertyValueEnum(),
sl@0	508	a multi-bit mask is used for sets of categories like "Letters".
sl@0	509	Mask values should be cast to uint32_t.
sl@0	510	@stable ICU 2.4 */
sl@0	511	UCHAR_GENERAL_CATEGORY_MASK=0x2000,
sl@0	512	/** First constant for bit-mask Unicode properties. @stable ICU 2.4 */
sl@0	513	UCHAR_MASK_START=UCHAR_GENERAL_CATEGORY_MASK,
sl@0	514	/** One more than the last constant for bit-mask Unicode properties. @stable ICU 2.4 */
sl@0	515	UCHAR_MASK_LIMIT,
sl@0	516
sl@0	517	/** Double property Numeric_Value.
sl@0	518	Corresponds to u_getNumericValue. @stable ICU 2.4 */
sl@0	519	UCHAR_NUMERIC_VALUE=0x3000,
sl@0	520	/** First constant for double Unicode properties. @stable ICU 2.4 */
sl@0	521	UCHAR_DOUBLE_START=UCHAR_NUMERIC_VALUE,
sl@0	522	/** One more than the last constant for double Unicode properties. @stable ICU 2.4 */
sl@0	523	UCHAR_DOUBLE_LIMIT,
sl@0	524
sl@0	525	/** String property Age.
sl@0	526	Corresponds to u_charAge. @stable ICU 2.4 */
sl@0	527	UCHAR_AGE=0x4000,
sl@0	528	/** First constant for string Unicode properties. @stable ICU 2.4 */
sl@0	529	UCHAR_STRING_START=UCHAR_AGE,
sl@0	530	/** String property Bidi_Mirroring_Glyph.
sl@0	531	Corresponds to u_charMirror. @stable ICU 2.4 */
sl@0	532	UCHAR_BIDI_MIRRORING_GLYPH,
sl@0	533	/** String property Case_Folding.
sl@0	534	Corresponds to u_strFoldCase in ustring.h. @stable ICU 2.4 */
sl@0	535	UCHAR_CASE_FOLDING,
sl@0	536	/** String property ISO_Comment.
sl@0	537	Corresponds to u_getISOComment. @stable ICU 2.4 */
sl@0	538	UCHAR_ISO_COMMENT,
sl@0	539	/** String property Lowercase_Mapping.
sl@0	540	Corresponds to u_strToLower in ustring.h. @stable ICU 2.4 */
sl@0	541	UCHAR_LOWERCASE_MAPPING,
sl@0	542	/** String property Name.
sl@0	543	Corresponds to u_charName. @stable ICU 2.4 */
sl@0	544	UCHAR_NAME,
sl@0	545	/** String property Simple_Case_Folding.
sl@0	546	Corresponds to u_foldCase. @stable ICU 2.4 */
sl@0	547	UCHAR_SIMPLE_CASE_FOLDING,
sl@0	548	/** String property Simple_Lowercase_Mapping.
sl@0	549	Corresponds to u_tolower. @stable ICU 2.4 */
sl@0	550	UCHAR_SIMPLE_LOWERCASE_MAPPING,
sl@0	551	/** String property Simple_Titlecase_Mapping.
sl@0	552	Corresponds to u_totitle. @stable ICU 2.4 */
sl@0	553	UCHAR_SIMPLE_TITLECASE_MAPPING,
sl@0	554	/** String property Simple_Uppercase_Mapping.
sl@0	555	Corresponds to u_toupper. @stable ICU 2.4 */
sl@0	556	UCHAR_SIMPLE_UPPERCASE_MAPPING,
sl@0	557	/** String property Titlecase_Mapping.
sl@0	558	Corresponds to u_strToTitle in ustring.h. @stable ICU 2.4 */
sl@0	559	UCHAR_TITLECASE_MAPPING,
sl@0	560	/** String property Unicode_1_Name.
sl@0	561	Corresponds to u_charName. @stable ICU 2.4 */
sl@0	562	UCHAR_UNICODE_1_NAME,
sl@0	563	/** String property Uppercase_Mapping.
sl@0	564	Corresponds to u_strToUpper in ustring.h. @stable ICU 2.4 */
sl@0	565	UCHAR_UPPERCASE_MAPPING,
sl@0	566	/** One more than the last constant for string Unicode properties. @stable ICU 2.4 */
sl@0	567	UCHAR_STRING_LIMIT,
sl@0	568
sl@0	569	/** Represents a nonexistent or invalid property or property value. @stable ICU 2.4 */
sl@0	570	UCHAR_INVALID_CODE = -1
sl@0	571	} UProperty;
sl@0	572
sl@0	573	/**
sl@0	574	* Data for enumerated Unicode general category types.
sl@0	575	* See http://www.unicode.org/Public/UNIDATA/UnicodeData.html .
sl@0	576	* @stable ICU 2.0
sl@0	577	*/
sl@0	578	typedef enum UCharCategory
sl@0	579	{
sl@0	580	/** See note !!. Comments of the form "Cn" are read by genpname. */
sl@0	581
sl@0	582	/** Non-category for unassigned and non-character code points. @stable ICU 2.0 */
sl@0	583	U_UNASSIGNED = 0,
sl@0	584	/** Cn "Other, Not Assigned (no characters in [UnicodeData.txt] have this property)" (same as U_UNASSIGNED!) @stable ICU 2.0 */
sl@0	585	U_GENERAL_OTHER_TYPES = 0,
sl@0	586	/** Lu @stable ICU 2.0 */
sl@0	587	U_UPPERCASE_LETTER = 1,
sl@0	588	/** Ll @stable ICU 2.0 */
sl@0	589	U_LOWERCASE_LETTER = 2,
sl@0	590	/** Lt @stable ICU 2.0 */
sl@0	591	U_TITLECASE_LETTER = 3,
sl@0	592	/** Lm @stable ICU 2.0 */
sl@0	593	U_MODIFIER_LETTER = 4,
sl@0	594	/** Lo @stable ICU 2.0 */
sl@0	595	U_OTHER_LETTER = 5,
sl@0	596	/** Mn @stable ICU 2.0 */
sl@0	597	U_NON_SPACING_MARK = 6,
sl@0	598	/** Me @stable ICU 2.0 */
sl@0	599	U_ENCLOSING_MARK = 7,
sl@0	600	/** Mc @stable ICU 2.0 */
sl@0	601	U_COMBINING_SPACING_MARK = 8,
sl@0	602	/** Nd @stable ICU 2.0 */
sl@0	603	U_DECIMAL_DIGIT_NUMBER = 9,
sl@0	604	/** Nl @stable ICU 2.0 */
sl@0	605	U_LETTER_NUMBER = 10,
sl@0	606	/** No @stable ICU 2.0 */
sl@0	607	U_OTHER_NUMBER = 11,
sl@0	608	/** Zs @stable ICU 2.0 */
sl@0	609	U_SPACE_SEPARATOR = 12,
sl@0	610	/** Zl @stable ICU 2.0 */
sl@0	611	U_LINE_SEPARATOR = 13,
sl@0	612	/** Zp @stable ICU 2.0 */
sl@0	613	U_PARAGRAPH_SEPARATOR = 14,
sl@0	614	/** Cc @stable ICU 2.0 */
sl@0	615	U_CONTROL_CHAR = 15,
sl@0	616	/** Cf @stable ICU 2.0 */
sl@0	617	U_FORMAT_CHAR = 16,
sl@0	618	/** Co @stable ICU 2.0 */
sl@0	619	U_PRIVATE_USE_CHAR = 17,
sl@0	620	/** Cs @stable ICU 2.0 */
sl@0	621	U_SURROGATE = 18,
sl@0	622	/** Pd @stable ICU 2.0 */
sl@0	623	U_DASH_PUNCTUATION = 19,
sl@0	624	/** Ps @stable ICU 2.0 */
sl@0	625	U_START_PUNCTUATION = 20,
sl@0	626	/** Pe @stable ICU 2.0 */
sl@0	627	U_END_PUNCTUATION = 21,
sl@0	628	/** Pc @stable ICU 2.0 */
sl@0	629	U_CONNECTOR_PUNCTUATION = 22,
sl@0	630	/** Po @stable ICU 2.0 */
sl@0	631	U_OTHER_PUNCTUATION = 23,
sl@0	632	/** Sm @stable ICU 2.0 */
sl@0	633	U_MATH_SYMBOL = 24,
sl@0	634	/** Sc @stable ICU 2.0 */
sl@0	635	U_CURRENCY_SYMBOL = 25,
sl@0	636	/** Sk @stable ICU 2.0 */
sl@0	637	U_MODIFIER_SYMBOL = 26,
sl@0	638	/** So @stable ICU 2.0 */
sl@0	639	U_OTHER_SYMBOL = 27,
sl@0	640	/** Pi @stable ICU 2.0 */
sl@0	641	U_INITIAL_PUNCTUATION = 28,
sl@0	642	/** Pf @stable ICU 2.0 */
sl@0	643	U_FINAL_PUNCTUATION = 29,
sl@0	644	/** One higher than the last enum UCharCategory constant. @stable ICU 2.0 */
sl@0	645	U_CHAR_CATEGORY_COUNT
sl@0	646	} UCharCategory;
sl@0	647
sl@0	648	/**
sl@0	649	* U_GC_XX_MASK constants are bit flags corresponding to Unicode
sl@0	650	* general category values.
sl@0	651	* For each category, the nth bit is set if the numeric value of the
sl@0	652	* corresponding UCharCategory constant is n.
sl@0	653	*
sl@0	654	* There are also some U_GC_Y_MASK constants for groups of general categories
sl@0	655	* like L for all letter categories.
sl@0	656	*
sl@0	657	* @see u_charType
sl@0	658	* @see U_GET_GC_MASK
sl@0	659	* @see UCharCategory
sl@0	660	* @stable ICU 2.1
sl@0	661	*/
sl@0	662	#define U_GC_CN_MASK U_MASK(U_GENERAL_OTHER_TYPES)
sl@0	663
sl@0	664	/** Mask constant for a UCharCategory. @stable ICU 2.1 */
sl@0	665	#define U_GC_LU_MASK U_MASK(U_UPPERCASE_LETTER)
sl@0	666	/** Mask constant for a UCharCategory. @stable ICU 2.1 */
sl@0	667	#define U_GC_LL_MASK U_MASK(U_LOWERCASE_LETTER)
sl@0	668	/** Mask constant for a UCharCategory. @stable ICU 2.1 */
sl@0	669	#define U_GC_LT_MASK U_MASK(U_TITLECASE_LETTER)
sl@0	670	/** Mask constant for a UCharCategory. @stable ICU 2.1 */
sl@0	671	#define U_GC_LM_MASK U_MASK(U_MODIFIER_LETTER)
sl@0	672	/** Mask constant for a UCharCategory. @stable ICU 2.1 */
sl@0	673	#define U_GC_LO_MASK U_MASK(U_OTHER_LETTER)
sl@0	674
sl@0	675	/** Mask constant for a UCharCategory. @stable ICU 2.1 */
sl@0	676	#define U_GC_MN_MASK U_MASK(U_NON_SPACING_MARK)
sl@0	677	/** Mask constant for a UCharCategory. @stable ICU 2.1 */
sl@0	678	#define U_GC_ME_MASK U_MASK(U_ENCLOSING_MARK)
sl@0	679	/** Mask constant for a UCharCategory. @stable ICU 2.1 */
sl@0	680	#define U_GC_MC_MASK U_MASK(U_COMBINING_SPACING_MARK)
sl@0	681
sl@0	682	/** Mask constant for a UCharCategory. @stable ICU 2.1 */
sl@0	683	#define U_GC_ND_MASK U_MASK(U_DECIMAL_DIGIT_NUMBER)
sl@0	684	/** Mask constant for a UCharCategory. @stable ICU 2.1 */
sl@0	685	#define U_GC_NL_MASK U_MASK(U_LETTER_NUMBER)
sl@0	686	/** Mask constant for a UCharCategory. @stable ICU 2.1 */
sl@0	687	#define U_GC_NO_MASK U_MASK(U_OTHER_NUMBER)
sl@0	688
sl@0	689	/** Mask constant for a UCharCategory. @stable ICU 2.1 */
sl@0	690	#define U_GC_ZS_MASK U_MASK(U_SPACE_SEPARATOR)
sl@0	691	/** Mask constant for a UCharCategory. @stable ICU 2.1 */
sl@0	692	#define U_GC_ZL_MASK U_MASK(U_LINE_SEPARATOR)
sl@0	693	/** Mask constant for a UCharCategory. @stable ICU 2.1 */
sl@0	694	#define U_GC_ZP_MASK U_MASK(U_PARAGRAPH_SEPARATOR)
sl@0	695
sl@0	696	/** Mask constant for a UCharCategory. @stable ICU 2.1 */
sl@0	697	#define U_GC_CC_MASK U_MASK(U_CONTROL_CHAR)
sl@0	698	/** Mask constant for a UCharCategory. @stable ICU 2.1 */
sl@0	699	#define U_GC_CF_MASK U_MASK(U_FORMAT_CHAR)
sl@0	700	/** Mask constant for a UCharCategory. @stable ICU 2.1 */
sl@0	701	#define U_GC_CO_MASK U_MASK(U_PRIVATE_USE_CHAR)
sl@0	702	/** Mask constant for a UCharCategory. @stable ICU 2.1 */
sl@0	703	#define U_GC_CS_MASK U_MASK(U_SURROGATE)
sl@0	704
sl@0	705	/** Mask constant for a UCharCategory. @stable ICU 2.1 */
sl@0	706	#define U_GC_PD_MASK U_MASK(U_DASH_PUNCTUATION)
sl@0	707	/** Mask constant for a UCharCategory. @stable ICU 2.1 */
sl@0	708	#define U_GC_PS_MASK U_MASK(U_START_PUNCTUATION)
sl@0	709	/** Mask constant for a UCharCategory. @stable ICU 2.1 */
sl@0	710	#define U_GC_PE_MASK U_MASK(U_END_PUNCTUATION)
sl@0	711	/** Mask constant for a UCharCategory. @stable ICU 2.1 */
sl@0	712	#define U_GC_PC_MASK U_MASK(U_CONNECTOR_PUNCTUATION)
sl@0	713	/** Mask constant for a UCharCategory. @stable ICU 2.1 */
sl@0	714	#define U_GC_PO_MASK U_MASK(U_OTHER_PUNCTUATION)
sl@0	715
sl@0	716	/** Mask constant for a UCharCategory. @stable ICU 2.1 */
sl@0	717	#define U_GC_SM_MASK U_MASK(U_MATH_SYMBOL)
sl@0	718	/** Mask constant for a UCharCategory. @stable ICU 2.1 */
sl@0	719	#define U_GC_SC_MASK U_MASK(U_CURRENCY_SYMBOL)
sl@0	720	/** Mask constant for a UCharCategory. @stable ICU 2.1 */
sl@0	721	#define U_GC_SK_MASK U_MASK(U_MODIFIER_SYMBOL)
sl@0	722	/** Mask constant for a UCharCategory. @stable ICU 2.1 */
sl@0	723	#define U_GC_SO_MASK U_MASK(U_OTHER_SYMBOL)
sl@0	724
sl@0	725	/** Mask constant for a UCharCategory. @stable ICU 2.1 */
sl@0	726	#define U_GC_PI_MASK U_MASK(U_INITIAL_PUNCTUATION)
sl@0	727	/** Mask constant for a UCharCategory. @stable ICU 2.1 */
sl@0	728	#define U_GC_PF_MASK U_MASK(U_FINAL_PUNCTUATION)
sl@0	729
sl@0	730
sl@0	731	/** Mask constant for multiple UCharCategory bits (L Letters). @stable ICU 2.1 */
sl@0	732	#define U_GC_L_MASK \
sl@0	733	(U_GC_LU_MASK\|U_GC_LL_MASK\|U_GC_LT_MASK\|U_GC_LM_MASK\|U_GC_LO_MASK)
sl@0	734
sl@0	735	/** Mask constant for multiple UCharCategory bits (LC Cased Letters). @stable ICU 2.1 */
sl@0	736	#define U_GC_LC_MASK \
sl@0	737	(U_GC_LU_MASK\|U_GC_LL_MASK\|U_GC_LT_MASK)
sl@0	738
sl@0	739	/** Mask constant for multiple UCharCategory bits (M Marks). @stable ICU 2.1 */
sl@0	740	#define U_GC_M_MASK (U_GC_MN_MASK\|U_GC_ME_MASK\|U_GC_MC_MASK)
sl@0	741
sl@0	742	/** Mask constant for multiple UCharCategory bits (N Numbers). @stable ICU 2.1 */
sl@0	743	#define U_GC_N_MASK (U_GC_ND_MASK\|U_GC_NL_MASK\|U_GC_NO_MASK)
sl@0	744
sl@0	745	/** Mask constant for multiple UCharCategory bits (Z Separators). @stable ICU 2.1 */
sl@0	746	#define U_GC_Z_MASK (U_GC_ZS_MASK\|U_GC_ZL_MASK\|U_GC_ZP_MASK)
sl@0	747
sl@0	748	/** Mask constant for multiple UCharCategory bits (C Others). @stable ICU 2.1 */
sl@0	749	#define U_GC_C_MASK \
sl@0	750	(U_GC_CN_MASK\|U_GC_CC_MASK\|U_GC_CF_MASK\|U_GC_CO_MASK\|U_GC_CS_MASK)
sl@0	751
sl@0	752	/** Mask constant for multiple UCharCategory bits (P Punctuation). @stable ICU 2.1 */
sl@0	753	#define U_GC_P_MASK \
sl@0	754	(U_GC_PD_MASK\|U_GC_PS_MASK\|U_GC_PE_MASK\|U_GC_PC_MASK\|U_GC_PO_MASK\| \
sl@0	755	U_GC_PI_MASK\|U_GC_PF_MASK)
sl@0	756
sl@0	757	/** Mask constant for multiple UCharCategory bits (S Symbols). @stable ICU 2.1 */
sl@0	758	#define U_GC_S_MASK (U_GC_SM_MASK\|U_GC_SC_MASK\|U_GC_SK_MASK\|U_GC_SO_MASK)
sl@0	759
sl@0	760	/**
sl@0	761	* This specifies the language directional property of a character set.
sl@0	762	* @stable ICU 2.0
sl@0	763	*/
sl@0	764	typedef enum UCharDirection {
sl@0	765	/** See note !!. Comments of the form "EN" are read by genpname. */
sl@0	766
sl@0	767	/** L @stable ICU 2.0 */
sl@0	768	U_LEFT_TO_RIGHT = 0,
sl@0	769	/** R @stable ICU 2.0 */
sl@0	770	U_RIGHT_TO_LEFT = 1,
sl@0	771	/** EN @stable ICU 2.0 */
sl@0	772	U_EUROPEAN_NUMBER = 2,
sl@0	773	/** ES @stable ICU 2.0 */
sl@0	774	U_EUROPEAN_NUMBER_SEPARATOR = 3,
sl@0	775	/** ET @stable ICU 2.0 */
sl@0	776	U_EUROPEAN_NUMBER_TERMINATOR = 4,
sl@0	777	/** AN @stable ICU 2.0 */
sl@0	778	U_ARABIC_NUMBER = 5,
sl@0	779	/** CS @stable ICU 2.0 */
sl@0	780	U_COMMON_NUMBER_SEPARATOR = 6,
sl@0	781	/** B @stable ICU 2.0 */
sl@0	782	U_BLOCK_SEPARATOR = 7,
sl@0	783	/** S @stable ICU 2.0 */
sl@0	784	U_SEGMENT_SEPARATOR = 8,
sl@0	785	/** WS @stable ICU 2.0 */
sl@0	786	U_WHITE_SPACE_NEUTRAL = 9,
sl@0	787	/** ON @stable ICU 2.0 */
sl@0	788	U_OTHER_NEUTRAL = 10,
sl@0	789	/** LRE @stable ICU 2.0 */
sl@0	790	U_LEFT_TO_RIGHT_EMBEDDING = 11,
sl@0	791	/** LRO @stable ICU 2.0 */
sl@0	792	U_LEFT_TO_RIGHT_OVERRIDE = 12,
sl@0	793	/** AL @stable ICU 2.0 */
sl@0	794	U_RIGHT_TO_LEFT_ARABIC = 13,
sl@0	795	/** RLE @stable ICU 2.0 */
sl@0	796	U_RIGHT_TO_LEFT_EMBEDDING = 14,
sl@0	797	/** RLO @stable ICU 2.0 */
sl@0	798	U_RIGHT_TO_LEFT_OVERRIDE = 15,
sl@0	799	/** PDF @stable ICU 2.0 */
sl@0	800	U_POP_DIRECTIONAL_FORMAT = 16,
sl@0	801	/** NSM @stable ICU 2.0 */
sl@0	802	U_DIR_NON_SPACING_MARK = 17,
sl@0	803	/** BN @stable ICU 2.0 */
sl@0	804	U_BOUNDARY_NEUTRAL = 18,
sl@0	805	/** @stable ICU 2.0 */
sl@0	806	U_CHAR_DIRECTION_COUNT
sl@0	807	} UCharDirection;
sl@0	808
sl@0	809	/**
sl@0	810	* Constants for Unicode blocks, see the Unicode Data file Blocks.txt
sl@0	811	* @stable ICU 2.0
sl@0	812	*/
sl@0	813	enum UBlockCode {
sl@0	814
sl@0	815	/** New No_Block value in Unicode 4. @stable ICU 2.6 */
sl@0	816	UBLOCK_NO_BLOCK = 0, /[none]/ /* Special range indicating No_Block */
sl@0	817
sl@0	818	/** @stable ICU 2.0 */
sl@0	819	UBLOCK_BASIC_LATIN = 1, /[0000]/ /See note !!/
sl@0	820
sl@0	821	/** @stable ICU 2.0 */
sl@0	822	UBLOCK_LATIN_1_SUPPLEMENT=2, /[0080]/
sl@0	823
sl@0	824	/** @stable ICU 2.0 */
sl@0	825	UBLOCK_LATIN_EXTENDED_A =3, /[0100]/
sl@0	826
sl@0	827	/** @stable ICU 2.0 */
sl@0	828	UBLOCK_LATIN_EXTENDED_B =4, /[0180]/
sl@0	829
sl@0	830	/** @stable ICU 2.0 */
sl@0	831	UBLOCK_IPA_EXTENSIONS =5, /[0250]/
sl@0	832
sl@0	833	/** @stable ICU 2.0 */
sl@0	834	UBLOCK_SPACING_MODIFIER_LETTERS =6, /[02B0]/
sl@0	835
sl@0	836	/** @stable ICU 2.0 */
sl@0	837	UBLOCK_COMBINING_DIACRITICAL_MARKS =7, /[0300]/
sl@0	838
sl@0	839	/**
sl@0	840	* Unicode 3.2 renames this block to "Greek and Coptic".
sl@0	841	* @stable ICU 2.0
sl@0	842	*/
sl@0	843	UBLOCK_GREEK =8, /[0370]/
sl@0	844
sl@0	845	/** @stable ICU 2.0 */
sl@0	846	UBLOCK_CYRILLIC =9, /[0400]/
sl@0	847
sl@0	848	/** @stable ICU 2.0 */
sl@0	849	UBLOCK_ARMENIAN =10, /[0530]/
sl@0	850
sl@0	851	/** @stable ICU 2.0 */
sl@0	852	UBLOCK_HEBREW =11, /[0590]/
sl@0	853
sl@0	854	/** @stable ICU 2.0 */
sl@0	855	UBLOCK_ARABIC =12, /[0600]/
sl@0	856
sl@0	857	/** @stable ICU 2.0 */
sl@0	858	UBLOCK_SYRIAC =13, /[0700]/
sl@0	859
sl@0	860	/** @stable ICU 2.0 */
sl@0	861	UBLOCK_THAANA =14, /[0780]/
sl@0	862
sl@0	863	/** @stable ICU 2.0 */
sl@0	864	UBLOCK_DEVANAGARI =15, /[0900]/
sl@0	865
sl@0	866	/** @stable ICU 2.0 */
sl@0	867	UBLOCK_BENGALI =16, /[0980]/
sl@0	868
sl@0	869	/** @stable ICU 2.0 */
sl@0	870	UBLOCK_GURMUKHI =17, /[0A00]/
sl@0	871
sl@0	872	/** @stable ICU 2.0 */
sl@0	873	UBLOCK_GUJARATI =18, /[0A80]/
sl@0	874
sl@0	875	/** @stable ICU 2.0 */
sl@0	876	UBLOCK_ORIYA =19, /[0B00]/
sl@0	877
sl@0	878	/** @stable ICU 2.0 */
sl@0	879	UBLOCK_TAMIL =20, /[0B80]/
sl@0	880
sl@0	881	/** @stable ICU 2.0 */
sl@0	882	UBLOCK_TELUGU =21, /[0C00]/
sl@0	883
sl@0	884	/** @stable ICU 2.0 */
sl@0	885	UBLOCK_KANNADA =22, /[0C80]/
sl@0	886
sl@0	887	/** @stable ICU 2.0 */
sl@0	888	UBLOCK_MALAYALAM =23, /[0D00]/
sl@0	889
sl@0	890	/** @stable ICU 2.0 */
sl@0	891	UBLOCK_SINHALA =24, /[0D80]/
sl@0	892
sl@0	893	/** @stable ICU 2.0 */
sl@0	894	UBLOCK_THAI =25, /[0E00]/
sl@0	895
sl@0	896	/** @stable ICU 2.0 */
sl@0	897	UBLOCK_LAO =26, /[0E80]/
sl@0	898
sl@0	899	/** @stable ICU 2.0 */
sl@0	900	UBLOCK_TIBETAN =27, /[0F00]/
sl@0	901
sl@0	902	/** @stable ICU 2.0 */
sl@0	903	UBLOCK_MYANMAR =28, /[1000]/
sl@0	904
sl@0	905	/** @stable ICU 2.0 */
sl@0	906	UBLOCK_GEORGIAN =29, /[10A0]/
sl@0	907
sl@0	908	/** @stable ICU 2.0 */
sl@0	909	UBLOCK_HANGUL_JAMO =30, /[1100]/
sl@0	910
sl@0	911	/** @stable ICU 2.0 */
sl@0	912	UBLOCK_ETHIOPIC =31, /[1200]/
sl@0	913
sl@0	914	/** @stable ICU 2.0 */
sl@0	915	UBLOCK_CHEROKEE =32, /[13A0]/
sl@0	916
sl@0	917	/** @stable ICU 2.0 */
sl@0	918	UBLOCK_UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS =33, /[1400]/
sl@0	919
sl@0	920	/** @stable ICU 2.0 */
sl@0	921	UBLOCK_OGHAM =34, /[1680]/
sl@0	922
sl@0	923	/** @stable ICU 2.0 */
sl@0	924	UBLOCK_RUNIC =35, /[16A0]/
sl@0	925
sl@0	926	/** @stable ICU 2.0 */
sl@0	927	UBLOCK_KHMER =36, /[1780]/
sl@0	928
sl@0	929	/** @stable ICU 2.0 */
sl@0	930	UBLOCK_MONGOLIAN =37, /[1800]/
sl@0	931
sl@0	932	/** @stable ICU 2.0 */
sl@0	933	UBLOCK_LATIN_EXTENDED_ADDITIONAL =38, /[1E00]/
sl@0	934
sl@0	935	/** @stable ICU 2.0 */
sl@0	936	UBLOCK_GREEK_EXTENDED =39, /[1F00]/
sl@0	937
sl@0	938	/** @stable ICU 2.0 */
sl@0	939	UBLOCK_GENERAL_PUNCTUATION =40, /[2000]/
sl@0	940
sl@0	941	/** @stable ICU 2.0 */
sl@0	942	UBLOCK_SUPERSCRIPTS_AND_SUBSCRIPTS =41, /[2070]/
sl@0	943
sl@0	944	/** @stable ICU 2.0 */
sl@0	945	UBLOCK_CURRENCY_SYMBOLS =42, /[20A0]/
sl@0	946
sl@0	947	/**
sl@0	948	* Unicode 3.2 renames this block to "Combining Diacritical Marks for Symbols".
sl@0	949	* @stable ICU 2.0
sl@0	950	*/
sl@0	951	UBLOCK_COMBINING_MARKS_FOR_SYMBOLS =43, /[20D0]/
sl@0	952
sl@0	953	/** @stable ICU 2.0 */
sl@0	954	UBLOCK_LETTERLIKE_SYMBOLS =44, /[2100]/
sl@0	955
sl@0	956	/** @stable ICU 2.0 */
sl@0	957	UBLOCK_NUMBER_FORMS =45, /[2150]/
sl@0	958
sl@0	959	/** @stable ICU 2.0 */
sl@0	960	UBLOCK_ARROWS =46, /[2190]/
sl@0	961
sl@0	962	/** @stable ICU 2.0 */
sl@0	963	UBLOCK_MATHEMATICAL_OPERATORS =47, /[2200]/
sl@0	964
sl@0	965	/** @stable ICU 2.0 */
sl@0	966	UBLOCK_MISCELLANEOUS_TECHNICAL =48, /[2300]/
sl@0	967
sl@0	968	/** @stable ICU 2.0 */
sl@0	969	UBLOCK_CONTROL_PICTURES =49, /[2400]/
sl@0	970
sl@0	971	/** @stable ICU 2.0 */
sl@0	972	UBLOCK_OPTICAL_CHARACTER_RECOGNITION =50, /[2440]/
sl@0	973
sl@0	974	/** @stable ICU 2.0 */
sl@0	975	UBLOCK_ENCLOSED_ALPHANUMERICS =51, /[2460]/
sl@0	976
sl@0	977	/** @stable ICU 2.0 */
sl@0	978	UBLOCK_BOX_DRAWING =52, /[2500]/
sl@0	979
sl@0	980	/** @stable ICU 2.0 */
sl@0	981	UBLOCK_BLOCK_ELEMENTS =53, /[2580]/
sl@0	982
sl@0	983	/** @stable ICU 2.0 */
sl@0	984	UBLOCK_GEOMETRIC_SHAPES =54, /[25A0]/
sl@0	985
sl@0	986	/** @stable ICU 2.0 */
sl@0	987	UBLOCK_MISCELLANEOUS_SYMBOLS =55, /[2600]/
sl@0	988
sl@0	989	/** @stable ICU 2.0 */
sl@0	990	UBLOCK_DINGBATS =56, /[2700]/
sl@0	991
sl@0	992	/** @stable ICU 2.0 */
sl@0	993	UBLOCK_BRAILLE_PATTERNS =57, /[2800]/
sl@0	994
sl@0	995	/** @stable ICU 2.0 */
sl@0	996	UBLOCK_CJK_RADICALS_SUPPLEMENT =58, /[2E80]/
sl@0	997
sl@0	998	/** @stable ICU 2.0 */
sl@0	999	UBLOCK_KANGXI_RADICALS =59, /[2F00]/
sl@0	1000
sl@0	1001	/** @stable ICU 2.0 */
sl@0	1002	UBLOCK_IDEOGRAPHIC_DESCRIPTION_CHARACTERS =60, /[2FF0]/
sl@0	1003
sl@0	1004	/** @stable ICU 2.0 */
sl@0	1005	UBLOCK_CJK_SYMBOLS_AND_PUNCTUATION =61, /[3000]/
sl@0	1006
sl@0	1007	/** @stable ICU 2.0 */
sl@0	1008	UBLOCK_HIRAGANA =62, /[3040]/
sl@0	1009
sl@0	1010	/** @stable ICU 2.0 */
sl@0	1011	UBLOCK_KATAKANA =63, /[30A0]/
sl@0	1012
sl@0	1013	/** @stable ICU 2.0 */
sl@0	1014	UBLOCK_BOPOMOFO =64, /[3100]/
sl@0	1015
sl@0	1016	/** @stable ICU 2.0 */
sl@0	1017	UBLOCK_HANGUL_COMPATIBILITY_JAMO =65, /[3130]/
sl@0	1018
sl@0	1019	/** @stable ICU 2.0 */
sl@0	1020	UBLOCK_KANBUN =66, /[3190]/
sl@0	1021
sl@0	1022	/** @stable ICU 2.0 */
sl@0	1023	UBLOCK_BOPOMOFO_EXTENDED =67, /[31A0]/
sl@0	1024
sl@0	1025	/** @stable ICU 2.0 */
sl@0	1026	UBLOCK_ENCLOSED_CJK_LETTERS_AND_MONTHS =68, /[3200]/
sl@0	1027
sl@0	1028	/** @stable ICU 2.0 */
sl@0	1029	UBLOCK_CJK_COMPATIBILITY =69, /[3300]/
sl@0	1030
sl@0	1031	/** @stable ICU 2.0 */
sl@0	1032	UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_A =70, /[3400]/
sl@0	1033
sl@0	1034	/** @stable ICU 2.0 */
sl@0	1035	UBLOCK_CJK_UNIFIED_IDEOGRAPHS =71, /[4E00]/
sl@0	1036
sl@0	1037	/** @stable ICU 2.0 */
sl@0	1038	UBLOCK_YI_SYLLABLES =72, /[A000]/
sl@0	1039
sl@0	1040	/** @stable ICU 2.0 */
sl@0	1041	UBLOCK_YI_RADICALS =73, /[A490]/
sl@0	1042
sl@0	1043	/** @stable ICU 2.0 */
sl@0	1044	UBLOCK_HANGUL_SYLLABLES =74, /[AC00]/
sl@0	1045
sl@0	1046	/** @stable ICU 2.0 */
sl@0	1047	UBLOCK_HIGH_SURROGATES =75, /[D800]/
sl@0	1048
sl@0	1049	/** @stable ICU 2.0 */
sl@0	1050	UBLOCK_HIGH_PRIVATE_USE_SURROGATES =76, /[DB80]/
sl@0	1051
sl@0	1052	/** @stable ICU 2.0 */
sl@0	1053	UBLOCK_LOW_SURROGATES =77, /[DC00]/
sl@0	1054
sl@0	1055	/**
sl@0	1056	* Same as UBLOCK_PRIVATE_USE_AREA.
sl@0	1057	* Until Unicode 3.1.1, the corresponding block name was "Private Use",
sl@0	1058	* and multiple code point ranges had this block.
sl@0	1059	* Unicode 3.2 renames the block for the BMP PUA to "Private Use Area" and
sl@0	1060	* adds separate blocks for the supplementary PUAs.
sl@0	1061	*
sl@0	1062	* @stable ICU 2.0
sl@0	1063	*/
sl@0	1064	UBLOCK_PRIVATE_USE = 78,
sl@0	1065	/**
sl@0	1066	* Same as UBLOCK_PRIVATE_USE.
sl@0	1067	* Until Unicode 3.1.1, the corresponding block name was "Private Use",
sl@0	1068	* and multiple code point ranges had this block.
sl@0	1069	* Unicode 3.2 renames the block for the BMP PUA to "Private Use Area" and
sl@0	1070	* adds separate blocks for the supplementary PUAs.
sl@0	1071	*
sl@0	1072	* @stable ICU 2.0
sl@0	1073	*/
sl@0	1074	UBLOCK_PRIVATE_USE_AREA =UBLOCK_PRIVATE_USE, /[E000]/
sl@0	1075
sl@0	1076	/** @stable ICU 2.0 */
sl@0	1077	UBLOCK_CJK_COMPATIBILITY_IDEOGRAPHS =79, /[F900]/
sl@0	1078
sl@0	1079	/** @stable ICU 2.0 */
sl@0	1080	UBLOCK_ALPHABETIC_PRESENTATION_FORMS =80, /[FB00]/
sl@0	1081
sl@0	1082	/** @stable ICU 2.0 */
sl@0	1083	UBLOCK_ARABIC_PRESENTATION_FORMS_A =81, /[FB50]/
sl@0	1084
sl@0	1085	/** @stable ICU 2.0 */
sl@0	1086	UBLOCK_COMBINING_HALF_MARKS =82, /[FE20]/
sl@0	1087
sl@0	1088	/** @stable ICU 2.0 */
sl@0	1089	UBLOCK_CJK_COMPATIBILITY_FORMS =83, /[FE30]/
sl@0	1090
sl@0	1091	/** @stable ICU 2.0 */
sl@0	1092	UBLOCK_SMALL_FORM_VARIANTS =84, /[FE50]/
sl@0	1093
sl@0	1094	/** @stable ICU 2.0 */
sl@0	1095	UBLOCK_ARABIC_PRESENTATION_FORMS_B =85, /[FE70]/
sl@0	1096
sl@0	1097	/** @stable ICU 2.0 */
sl@0	1098	UBLOCK_SPECIALS =86, /[FFF0]/
sl@0	1099
sl@0	1100	/** @stable ICU 2.0 */
sl@0	1101	UBLOCK_HALFWIDTH_AND_FULLWIDTH_FORMS =87, /[FF00]/
sl@0	1102
sl@0	1103	/* New blocks in Unicode 3.1 */
sl@0	1104
sl@0	1105	/** @stable ICU 2.0 */
sl@0	1106	UBLOCK_OLD_ITALIC = 88 , /[10300]/
sl@0	1107	/** @stable ICU 2.0 */
sl@0	1108	UBLOCK_GOTHIC = 89 , /[10330]/
sl@0	1109	/** @stable ICU 2.0 */
sl@0	1110	UBLOCK_DESERET = 90 , /[10400]/
sl@0	1111	/** @stable ICU 2.0 */
sl@0	1112	UBLOCK_BYZANTINE_MUSICAL_SYMBOLS = 91 , /[1D000]/
sl@0	1113	/** @stable ICU 2.0 */
sl@0	1114	UBLOCK_MUSICAL_SYMBOLS = 92 , /[1D100]/
sl@0	1115	/** @stable ICU 2.0 */
sl@0	1116	UBLOCK_MATHEMATICAL_ALPHANUMERIC_SYMBOLS = 93 , /[1D400]/
sl@0	1117	/** @stable ICU 2.0 */
sl@0	1118	UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_B = 94 , /[20000]/
sl@0	1119	/** @stable ICU 2.0 */
sl@0	1120	UBLOCK_CJK_COMPATIBILITY_IDEOGRAPHS_SUPPLEMENT = 95 , /[2F800]/
sl@0	1121	/** @stable ICU 2.0 */
sl@0	1122	UBLOCK_TAGS = 96, /[E0000]/
sl@0	1123
sl@0	1124	/* New blocks in Unicode 3.2 */
sl@0	1125
sl@0	1126	/**
sl@0	1127	* Unicode 4.0.1 renames the "Cyrillic Supplementary" block to "Cyrillic Supplement".
sl@0	1128	* @stable ICU 2.2
sl@0	1129	*/
sl@0	1130	UBLOCK_CYRILLIC_SUPPLEMENTARY = 97,
sl@0	1131	/** @draft ICU 3.0 */
sl@0	1132	UBLOCK_CYRILLIC_SUPPLEMENT = UBLOCK_CYRILLIC_SUPPLEMENTARY, /[0500]/
sl@0	1133	/** @stable ICU 2.2 */
sl@0	1134	UBLOCK_TAGALOG = 98, /[1700]/
sl@0	1135	/** @stable ICU 2.2 */
sl@0	1136	UBLOCK_HANUNOO = 99, /[1720]/
sl@0	1137	/** @stable ICU 2.2 */
sl@0	1138	UBLOCK_BUHID = 100, /[1740]/
sl@0	1139	/** @stable ICU 2.2 */
sl@0	1140	UBLOCK_TAGBANWA = 101, /[1760]/
sl@0	1141	/** @stable ICU 2.2 */
sl@0	1142	UBLOCK_MISCELLANEOUS_MATHEMATICAL_SYMBOLS_A = 102, /[27C0]/
sl@0	1143	/** @stable ICU 2.2 */
sl@0	1144	UBLOCK_SUPPLEMENTAL_ARROWS_A = 103, /[27F0]/
sl@0	1145	/** @stable ICU 2.2 */
sl@0	1146	UBLOCK_SUPPLEMENTAL_ARROWS_B = 104, /[2900]/
sl@0	1147	/** @stable ICU 2.2 */
sl@0	1148	UBLOCK_MISCELLANEOUS_MATHEMATICAL_SYMBOLS_B = 105, /[2980]/
sl@0	1149	/** @stable ICU 2.2 */
sl@0	1150	UBLOCK_SUPPLEMENTAL_MATHEMATICAL_OPERATORS = 106, /[2A00]/
sl@0	1151	/** @stable ICU 2.2 */
sl@0	1152	UBLOCK_KATAKANA_PHONETIC_EXTENSIONS = 107, /[31F0]/
sl@0	1153	/** @stable ICU 2.2 */
sl@0	1154	UBLOCK_VARIATION_SELECTORS = 108, /[FE00]/
sl@0	1155	/** @stable ICU 2.2 */
sl@0	1156	UBLOCK_SUPPLEMENTARY_PRIVATE_USE_AREA_A = 109, /[F0000]/
sl@0	1157	/** @stable ICU 2.2 */
sl@0	1158	UBLOCK_SUPPLEMENTARY_PRIVATE_USE_AREA_B = 110, /[100000]/
sl@0	1159
sl@0	1160	/* New blocks in Unicode 4 */
sl@0	1161
sl@0	1162	/** @stable ICU 2.6 */
sl@0	1163	UBLOCK_LIMBU = 111, /[1900]/
sl@0	1164	/** @stable ICU 2.6 */
sl@0	1165	UBLOCK_TAI_LE = 112, /[1950]/
sl@0	1166	/** @stable ICU 2.6 */
sl@0	1167	UBLOCK_KHMER_SYMBOLS = 113, /[19E0]/
sl@0	1168	/** @stable ICU 2.6 */
sl@0	1169	UBLOCK_PHONETIC_EXTENSIONS = 114, /[1D00]/
sl@0	1170	/** @stable ICU 2.6 */
sl@0	1171	UBLOCK_MISCELLANEOUS_SYMBOLS_AND_ARROWS = 115, /[2B00]/
sl@0	1172	/** @stable ICU 2.6 */
sl@0	1173	UBLOCK_YIJING_HEXAGRAM_SYMBOLS = 116, /[4DC0]/
sl@0	1174	/** @stable ICU 2.6 */
sl@0	1175	UBLOCK_LINEAR_B_SYLLABARY = 117, /[10000]/
sl@0	1176	/** @stable ICU 2.6 */
sl@0	1177	UBLOCK_LINEAR_B_IDEOGRAMS = 118, /[10080]/
sl@0	1178	/** @stable ICU 2.6 */
sl@0	1179	UBLOCK_AEGEAN_NUMBERS = 119, /[10100]/
sl@0	1180	/** @stable ICU 2.6 */
sl@0	1181	UBLOCK_UGARITIC = 120, /[10380]/
sl@0	1182	/** @stable ICU 2.6 */
sl@0	1183	UBLOCK_SHAVIAN = 121, /[10450]/
sl@0	1184	/** @stable ICU 2.6 */
sl@0	1185	UBLOCK_OSMANYA = 122, /[10480]/
sl@0	1186	/** @stable ICU 2.6 */
sl@0	1187	UBLOCK_CYPRIOT_SYLLABARY = 123, /[10800]/
sl@0	1188	/** @stable ICU 2.6 */
sl@0	1189	UBLOCK_TAI_XUAN_JING_SYMBOLS = 124, /[1D300]/
sl@0	1190	/** @stable ICU 2.6 */
sl@0	1191	UBLOCK_VARIATION_SELECTORS_SUPPLEMENT = 125, /[E0100]/
sl@0	1192
sl@0	1193	/* New blocks in Unicode 4.1 */
sl@0	1194
sl@0	1195	/** @draft ICU 3.4 */
sl@0	1196	UBLOCK_ANCIENT_GREEK_MUSICAL_NOTATION = 126, /[1D200]/
sl@0	1197	/** @draft ICU 3.4 */
sl@0	1198	UBLOCK_ANCIENT_GREEK_NUMBERS = 127, /[10140]/
sl@0	1199	/** @draft ICU 3.4 */
sl@0	1200	UBLOCK_ARABIC_SUPPLEMENT = 128, /[0750]/
sl@0	1201	/** @draft ICU 3.4 */
sl@0	1202	UBLOCK_BUGINESE = 129, /[1A00]/
sl@0	1203	/** @draft ICU 3.4 */
sl@0	1204	UBLOCK_CJK_STROKES = 130, /[31C0]/
sl@0	1205	/** @draft ICU 3.4 */
sl@0	1206	UBLOCK_COMBINING_DIACRITICAL_MARKS_SUPPLEMENT = 131, /[1DC0]/
sl@0	1207	/** @draft ICU 3.4 */
sl@0	1208	UBLOCK_COPTIC = 132, /[2C80]/
sl@0	1209	/** @draft ICU 3.4 */
sl@0	1210	UBLOCK_ETHIOPIC_EXTENDED = 133, /[2D80]/
sl@0	1211	/** @draft ICU 3.4 */
sl@0	1212	UBLOCK_ETHIOPIC_SUPPLEMENT = 134, /[1380]/
sl@0	1213	/** @draft ICU 3.4 */
sl@0	1214	UBLOCK_GEORGIAN_SUPPLEMENT = 135, /[2D00]/
sl@0	1215	/** @draft ICU 3.4 */
sl@0	1216	UBLOCK_GLAGOLITIC = 136, /[2C00]/
sl@0	1217	/** @draft ICU 3.4 */
sl@0	1218	UBLOCK_KHAROSHTHI = 137, /[10A00]/
sl@0	1219	/** @draft ICU 3.4 */
sl@0	1220	UBLOCK_MODIFIER_TONE_LETTERS = 138, /[A700]/
sl@0	1221	/** @draft ICU 3.4 */
sl@0	1222	UBLOCK_NEW_TAI_LUE = 139, /[1980]/
sl@0	1223	/** @draft ICU 3.4 */
sl@0	1224	UBLOCK_OLD_PERSIAN = 140, /[103A0]/
sl@0	1225	/** @draft ICU 3.4 */
sl@0	1226	UBLOCK_PHONETIC_EXTENSIONS_SUPPLEMENT = 141, /[1D80]/
sl@0	1227	/** @draft ICU 3.4 */
sl@0	1228	UBLOCK_SUPPLEMENTAL_PUNCTUATION = 142, /[2E00]/
sl@0	1229	/** @draft ICU 3.4 */
sl@0	1230	UBLOCK_SYLOTI_NAGRI = 143, /[A800]/
sl@0	1231	/** @draft ICU 3.4 */
sl@0	1232	UBLOCK_TIFINAGH = 144, /[2D30]/
sl@0	1233	/** @draft ICU 3.4 */
sl@0	1234	UBLOCK_VERTICAL_FORMS = 145, /[FE10]/
sl@0	1235
sl@0	1236	/** @stable ICU 2.0 */
sl@0	1237	UBLOCK_COUNT,
sl@0	1238
sl@0	1239	/** @stable ICU 2.0 */
sl@0	1240	UBLOCK_INVALID_CODE=-1
sl@0	1241	};
sl@0	1242
sl@0	1243	/** @stable ICU 2.0 */
sl@0	1244	typedef enum UBlockCode UBlockCode;
sl@0	1245
sl@0	1246	/**
sl@0	1247	* East Asian Width constants.
sl@0	1248	*
sl@0	1249	* @see UCHAR_EAST_ASIAN_WIDTH
sl@0	1250	* @see u_getIntPropertyValue
sl@0	1251	* @stable ICU 2.2
sl@0	1252	*/
sl@0	1253	typedef enum UEastAsianWidth {
sl@0	1254	U_EA_NEUTRAL, /[N]/ /See note !!/
sl@0	1255	U_EA_AMBIGUOUS, /[A]/
sl@0	1256	U_EA_HALFWIDTH, /[H]/
sl@0	1257	U_EA_FULLWIDTH, /[F]/
sl@0	1258	U_EA_NARROW, /[Na]/
sl@0	1259	U_EA_WIDE, /[W]/
sl@0	1260	U_EA_COUNT
sl@0	1261	} UEastAsianWidth;
sl@0	1262	/*
sl@0	1263	* Implementation note:
sl@0	1264	* Keep UEastAsianWidth constant values in sync with names list in genprops/props2.c.
sl@0	1265	*/
sl@0	1266
sl@0	1267	/**
sl@0	1268	* Selector constants for u_charName().
sl@0	1269	* u_charName() returns the "modern" name of a
sl@0	1270	* Unicode character; or the name that was defined in
sl@0	1271	* Unicode version 1.0, before the Unicode standard merged
sl@0	1272	* with ISO-10646; or an "extended" name that gives each
sl@0	1273	* Unicode code point a unique name.
sl@0	1274	*
sl@0	1275	* @see u_charName
sl@0	1276	* @stable ICU 2.0
sl@0	1277	*/
sl@0	1278	typedef enum UCharNameChoice {
sl@0	1279	U_UNICODE_CHAR_NAME,
sl@0	1280	U_UNICODE_10_CHAR_NAME,
sl@0	1281	U_EXTENDED_CHAR_NAME,
sl@0	1282	U_CHAR_NAME_CHOICE_COUNT
sl@0	1283	} UCharNameChoice;
sl@0	1284
sl@0	1285	/**
sl@0	1286	* Selector constants for u_getPropertyName() and
sl@0	1287	* u_getPropertyValueName(). These selectors are used to choose which
sl@0	1288	* name is returned for a given property or value. All properties and
sl@0	1289	* values have a long name. Most have a short name, but some do not.
sl@0	1290	* Unicode allows for additional names, beyond the long and short
sl@0	1291	* name, which would be indicated by U_LONG_PROPERTY_NAME + i, where
sl@0	1292	* i=1, 2,...
sl@0	1293	*
sl@0	1294	* @see u_getPropertyName()
sl@0	1295	* @see u_getPropertyValueName()
sl@0	1296	* @stable ICU 2.4
sl@0	1297	*/
sl@0	1298	typedef enum UPropertyNameChoice {
sl@0	1299	U_SHORT_PROPERTY_NAME,
sl@0	1300	U_LONG_PROPERTY_NAME,
sl@0	1301	U_PROPERTY_NAME_CHOICE_COUNT
sl@0	1302	} UPropertyNameChoice;
sl@0	1303
sl@0	1304	/**
sl@0	1305	* Decomposition Type constants.
sl@0	1306	*
sl@0	1307	* @see UCHAR_DECOMPOSITION_TYPE
sl@0	1308	* @stable ICU 2.2
sl@0	1309	*/
sl@0	1310	typedef enum UDecompositionType {
sl@0	1311	U_DT_NONE, /[none]/ /See note !!/
sl@0	1312	U_DT_CANONICAL, /[can]/
sl@0	1313	U_DT_COMPAT, /[com]/
sl@0	1314	U_DT_CIRCLE, /[enc]/
sl@0	1315	U_DT_FINAL, /[fin]/
sl@0	1316	U_DT_FONT, /[font]/
sl@0	1317	U_DT_FRACTION, /[fra]/
sl@0	1318	U_DT_INITIAL, /[init]/
sl@0	1319	U_DT_ISOLATED, /[iso]/
sl@0	1320	U_DT_MEDIAL, /[med]/
sl@0	1321	U_DT_NARROW, /[nar]/
sl@0	1322	U_DT_NOBREAK, /[nb]/
sl@0	1323	U_DT_SMALL, /[sml]/
sl@0	1324	U_DT_SQUARE, /[sqr]/
sl@0	1325	U_DT_SUB, /[sub]/
sl@0	1326	U_DT_SUPER, /[sup]/
sl@0	1327	U_DT_VERTICAL, /[vert]/
sl@0	1328	U_DT_WIDE, /[wide]/
sl@0	1329	U_DT_COUNT /* 18 */
sl@0	1330	} UDecompositionType;
sl@0	1331
sl@0	1332	/**
sl@0	1333	* Joining Type constants.
sl@0	1334	*
sl@0	1335	* @see UCHAR_JOINING_TYPE
sl@0	1336	* @stable ICU 2.2
sl@0	1337	*/
sl@0	1338	typedef enum UJoiningType {
sl@0	1339	U_JT_NON_JOINING, /[U]/ /See note !!/
sl@0	1340	U_JT_JOIN_CAUSING, /[C]/
sl@0	1341	U_JT_DUAL_JOINING, /[D]/
sl@0	1342	U_JT_LEFT_JOINING, /[L]/
sl@0	1343	U_JT_RIGHT_JOINING, /[R]/
sl@0	1344	U_JT_TRANSPARENT, /[T]/
sl@0	1345	U_JT_COUNT /* 6 */
sl@0	1346	} UJoiningType;
sl@0	1347
sl@0	1348	/**
sl@0	1349	* Joining Group constants.
sl@0	1350	*
sl@0	1351	* @see UCHAR_JOINING_GROUP
sl@0	1352	* @stable ICU 2.2
sl@0	1353	*/
sl@0	1354	typedef enum UJoiningGroup {
sl@0	1355	U_JG_NO_JOINING_GROUP,
sl@0	1356	U_JG_AIN,
sl@0	1357	U_JG_ALAPH,
sl@0	1358	U_JG_ALEF,
sl@0	1359	U_JG_BEH,
sl@0	1360	U_JG_BETH,
sl@0	1361	U_JG_DAL,
sl@0	1362	U_JG_DALATH_RISH,
sl@0	1363	U_JG_E,
sl@0	1364	U_JG_FEH,
sl@0	1365	U_JG_FINAL_SEMKATH,
sl@0	1366	U_JG_GAF,
sl@0	1367	U_JG_GAMAL,
sl@0	1368	U_JG_HAH,
sl@0	1369	U_JG_HAMZA_ON_HEH_GOAL,
sl@0	1370	U_JG_HE,
sl@0	1371	U_JG_HEH,
sl@0	1372	U_JG_HEH_GOAL,
sl@0	1373	U_JG_HETH,
sl@0	1374	U_JG_KAF,
sl@0	1375	U_JG_KAPH,
sl@0	1376	U_JG_KNOTTED_HEH,
sl@0	1377	U_JG_LAM,
sl@0	1378	U_JG_LAMADH,
sl@0	1379	U_JG_MEEM,
sl@0	1380	U_JG_MIM,
sl@0	1381	U_JG_NOON,
sl@0	1382	U_JG_NUN,
sl@0	1383	U_JG_PE,
sl@0	1384	U_JG_QAF,
sl@0	1385	U_JG_QAPH,
sl@0	1386	U_JG_REH,
sl@0	1387	U_JG_REVERSED_PE,
sl@0	1388	U_JG_SAD,
sl@0	1389	U_JG_SADHE,
sl@0	1390	U_JG_SEEN,
sl@0	1391	U_JG_SEMKATH,
sl@0	1392	U_JG_SHIN,
sl@0	1393	U_JG_SWASH_KAF,
sl@0	1394	U_JG_SYRIAC_WAW,
sl@0	1395	U_JG_TAH,
sl@0	1396	U_JG_TAW,
sl@0	1397	U_JG_TEH_MARBUTA,
sl@0	1398	U_JG_TETH,
sl@0	1399	U_JG_WAW,
sl@0	1400	U_JG_YEH,
sl@0	1401	U_JG_YEH_BARREE,
sl@0	1402	U_JG_YEH_WITH_TAIL,
sl@0	1403	U_JG_YUDH,
sl@0	1404	U_JG_YUDH_HE,
sl@0	1405	U_JG_ZAIN,
sl@0	1406	U_JG_FE, /*< @stable ICU 2.6 /
sl@0	1407	U_JG_KHAPH, /*< @stable ICU 2.6 /
sl@0	1408	U_JG_ZHAIN, /*< @stable ICU 2.6 /
sl@0	1409	U_JG_COUNT
sl@0	1410	} UJoiningGroup;
sl@0	1411
sl@0	1412	/**
sl@0	1413	* Grapheme Cluster Break constants.
sl@0	1414	*
sl@0	1415	* @see UCHAR_GRAPHEME_CLUSTER_BREAK
sl@0	1416	* @draft ICU 3.4
sl@0	1417	*/
sl@0	1418	typedef enum UGraphemeClusterBreak {
sl@0	1419	U_GCB_OTHER, /[XX]/ /See note !!/
sl@0	1420	U_GCB_CONTROL, /[CN]/
sl@0	1421	U_GCB_CR, /[CR]/
sl@0	1422	U_GCB_EXTEND, /[EX]/
sl@0	1423	U_GCB_L, /[L]/
sl@0	1424	U_GCB_LF, /[LF]/
sl@0	1425	U_GCB_LV, /[LV]/
sl@0	1426	U_GCB_LVT, /[LVT]/
sl@0	1427	U_GCB_T, /[T]/
sl@0	1428	U_GCB_V, /[V]/
sl@0	1429	U_GCB_COUNT
sl@0	1430	} UGraphemeClusterBreak;
sl@0	1431
sl@0	1432	/**
sl@0	1433	* Word Break constants.
sl@0	1434	* (UWordBreak is a pre-existing enum type in ubrk.h for word break status tags.)
sl@0	1435	*
sl@0	1436	* @see UCHAR_WORD_BREAK
sl@0	1437	* @draft ICU 3.4
sl@0	1438	*/
sl@0	1439	typedef enum UWordBreakValues {
sl@0	1440	U_WB_OTHER, /[XX]/ /See note !!/
sl@0	1441	U_WB_ALETTER, /[LE]/
sl@0	1442	U_WB_FORMAT, /[FO]/
sl@0	1443	U_WB_KATAKANA, /[KA]/
sl@0	1444	U_WB_MIDLETTER, /[ML]/
sl@0	1445	U_WB_MIDNUM, /[MN]/
sl@0	1446	U_WB_NUMERIC, /[NU]/
sl@0	1447	U_WB_EXTENDNUMLET, /[EX]/
sl@0	1448	U_WB_COUNT
sl@0	1449	} UWordBreakValues;
sl@0	1450
sl@0	1451	/**
sl@0	1452	* Sentence Break constants.
sl@0	1453	*
sl@0	1454	* @see UCHAR_SENTENCE_BREAK
sl@0	1455	* @draft ICU 3.4
sl@0	1456	*/
sl@0	1457	typedef enum USentenceBreak {
sl@0	1458	U_SB_OTHER, /[XX]/ /See note !!/
sl@0	1459	U_SB_ATERM, /[AT]/
sl@0	1460	U_SB_CLOSE, /[CL]/
sl@0	1461	U_SB_FORMAT, /[FO]/
sl@0	1462	U_SB_LOWER, /[LO]/
sl@0	1463	U_SB_NUMERIC, /[NU]/
sl@0	1464	U_SB_OLETTER, /[LE]/
sl@0	1465	U_SB_SEP, /[SE]/
sl@0	1466	U_SB_SP, /[SP]/
sl@0	1467	U_SB_STERM, /[ST]/
sl@0	1468	U_SB_UPPER, /[UP]/
sl@0	1469	U_SB_COUNT
sl@0	1470	} USentenceBreak;
sl@0	1471
sl@0	1472	/**
sl@0	1473	* Line Break constants.
sl@0	1474	*
sl@0	1475	* @see UCHAR_LINE_BREAK
sl@0	1476	* @stable ICU 2.2
sl@0	1477	*/
sl@0	1478	typedef enum ULineBreak {
sl@0	1479	U_LB_UNKNOWN, /[XX]/ /See note !!/
sl@0	1480	U_LB_AMBIGUOUS, /[AI]/
sl@0	1481	U_LB_ALPHABETIC, /[AL]/
sl@0	1482	U_LB_BREAK_BOTH, /[B2]/
sl@0	1483	U_LB_BREAK_AFTER, /[BA]/
sl@0	1484	U_LB_BREAK_BEFORE, /[BB]/
sl@0	1485	U_LB_MANDATORY_BREAK, /[BK]/
sl@0	1486	U_LB_CONTINGENT_BREAK, /[CB]/
sl@0	1487	U_LB_CLOSE_PUNCTUATION, /[CL]/
sl@0	1488	U_LB_COMBINING_MARK, /[CM]/
sl@0	1489	U_LB_CARRIAGE_RETURN, /[CR]/
sl@0	1490	U_LB_EXCLAMATION, /[EX]/
sl@0	1491	U_LB_GLUE, /[GL]/
sl@0	1492	U_LB_HYPHEN, /[HY]/
sl@0	1493	U_LB_IDEOGRAPHIC, /[ID]/
sl@0	1494	U_LB_INSEPERABLE,
sl@0	1495	/** Renamed from the misspelled "inseperable" in Unicode 4.0.1/ICU 3.0 @draft ICU 3.0 */
sl@0	1496	U_LB_INSEPARABLE=U_LB_INSEPERABLE,/[IN]/
sl@0	1497	U_LB_INFIX_NUMERIC, /[IS]/
sl@0	1498	U_LB_LINE_FEED, /[LF]/
sl@0	1499	U_LB_NONSTARTER, /[NS]/
sl@0	1500	U_LB_NUMERIC, /[NU]/
sl@0	1501	U_LB_OPEN_PUNCTUATION, /[OP]/
sl@0	1502	U_LB_POSTFIX_NUMERIC, /[PO]/
sl@0	1503	U_LB_PREFIX_NUMERIC, /[PR]/
sl@0	1504	U_LB_QUOTATION, /[QU]/
sl@0	1505	U_LB_COMPLEX_CONTEXT, /[SA]/
sl@0	1506	U_LB_SURROGATE, /[SG]/
sl@0	1507	U_LB_SPACE, /[SP]/
sl@0	1508	U_LB_BREAK_SYMBOLS, /[SY]/
sl@0	1509	U_LB_ZWSPACE, /[ZW]/
sl@0	1510	U_LB_NEXT_LINE, /[NL]/ /* from here on: new in Unicode 4/ICU 2.6 */
sl@0	1511	U_LB_WORD_JOINER, /[WJ]/
sl@0	1512	U_LB_H2, /[H2]/ /* from here on: new in Unicode 4.1/ICU 3.4 */
sl@0	1513	U_LB_H3, /[H3]/
sl@0	1514	U_LB_JL, /[JL]/
sl@0	1515	U_LB_JT, /[JT]/
sl@0	1516	U_LB_JV, /[JV]/
sl@0	1517	U_LB_COUNT
sl@0	1518	} ULineBreak;
sl@0	1519
sl@0	1520	/**
sl@0	1521	* Numeric Type constants.
sl@0	1522	*
sl@0	1523	* @see UCHAR_NUMERIC_TYPE
sl@0	1524	* @stable ICU 2.2
sl@0	1525	*/
sl@0	1526	typedef enum UNumericType {
sl@0	1527	U_NT_NONE, /[None]/ /See note !!/
sl@0	1528	U_NT_DECIMAL, /[de]/
sl@0	1529	U_NT_DIGIT, /[di]/
sl@0	1530	U_NT_NUMERIC, /[nu]/
sl@0	1531	U_NT_COUNT
sl@0	1532	} UNumericType;
sl@0	1533
sl@0	1534	/**
sl@0	1535	* Hangul Syllable Type constants.
sl@0	1536	*
sl@0	1537	* @see UCHAR_HANGUL_SYLLABLE_TYPE
sl@0	1538	* @stable ICU 2.6
sl@0	1539	*/
sl@0	1540	typedef enum UHangulSyllableType {
sl@0	1541	U_HST_NOT_APPLICABLE, /[NA]/ /See note !!/
sl@0	1542	U_HST_LEADING_JAMO, /[L]/
sl@0	1543	U_HST_VOWEL_JAMO, /[V]/
sl@0	1544	U_HST_TRAILING_JAMO, /[T]/
sl@0	1545	U_HST_LV_SYLLABLE, /[LV]/
sl@0	1546	U_HST_LVT_SYLLABLE, /[LVT]/
sl@0	1547	U_HST_COUNT
sl@0	1548	} UHangulSyllableType;
sl@0	1549
sl@0	1550	/**
sl@0	1551	* Check a binary Unicode property for a code point.
sl@0	1552	*
sl@0	1553	* Unicode, especially in version 3.2, defines many more properties than the
sl@0	1554	* original set in UnicodeData.txt.
sl@0	1555	*
sl@0	1556	* The properties APIs are intended to reflect Unicode properties as defined
sl@0	1557	* in the Unicode Character Database (UCD) and Unicode Technical Reports (UTR).
sl@0	1558	* For details about the properties see http://www.unicode.org/ucd/ .
sl@0	1559	* For names of Unicode properties see the UCD file PropertyAliases.txt.
sl@0	1560	*
sl@0	1561	* Important: If ICU is built with UCD files from Unicode versions below 3.2,
sl@0	1562	* then properties marked with "new in Unicode 3.2" are not or not fully available.
sl@0	1563	*
sl@0	1564	* @param c Code point to test.
sl@0	1565	* @param which UProperty selector constant, identifies which binary property to check.
sl@0	1566	* Must be UCHAR_BINARY_START<=which<UCHAR_BINARY_LIMIT.
sl@0	1567	* @return TRUE or FALSE according to the binary Unicode property value for c.
sl@0	1568	* Also FALSE if 'which' is out of bounds or if the Unicode version
sl@0	1569	* does not have data for the property at all, or not for this code point.
sl@0	1570	*
sl@0	1571	* @see UProperty
sl@0	1572	* @see u_getIntPropertyValue
sl@0	1573	* @see u_getUnicodeVersion
sl@0	1574	* @stable ICU 2.1
sl@0	1575	*/
sl@0	1576	U_STABLE UBool U_EXPORT2
sl@0	1577	u_hasBinaryProperty(UChar32 c, UProperty which);
sl@0	1578
sl@0	1579	/**
sl@0	1580	* Check if a code point has the Alphabetic Unicode property.
sl@0	1581	* Same as u_hasBinaryProperty(c, UCHAR_ALPHABETIC).
sl@0	1582	* This is different from u_isalpha!
sl@0	1583	* @param c Code point to test
sl@0	1584	* @return true if the code point has the Alphabetic Unicode property, false otherwise
sl@0	1585	*
sl@0	1586	* @see UCHAR_ALPHABETIC
sl@0	1587	* @see u_isalpha
sl@0	1588	* @see u_hasBinaryProperty
sl@0	1589	* @stable ICU 2.1
sl@0	1590	*/
sl@0	1591	U_STABLE UBool U_EXPORT2
sl@0	1592	u_isUAlphabetic(UChar32 c);
sl@0	1593
sl@0	1594	/**
sl@0	1595	* Check if a code point has the Lowercase Unicode property.
sl@0	1596	* Same as u_hasBinaryProperty(c, UCHAR_LOWERCASE).
sl@0	1597	* This is different from u_islower!
sl@0	1598	* @param c Code point to test
sl@0	1599	* @return true if the code point has the Lowercase Unicode property, false otherwise
sl@0	1600	*
sl@0	1601	* @see UCHAR_LOWERCASE
sl@0	1602	* @see u_islower
sl@0	1603	* @see u_hasBinaryProperty
sl@0	1604	* @stable ICU 2.1
sl@0	1605	*/
sl@0	1606	U_STABLE UBool U_EXPORT2
sl@0	1607	u_isULowercase(UChar32 c);
sl@0	1608
sl@0	1609	/**
sl@0	1610	* Check if a code point has the Uppercase Unicode property.
sl@0	1611	* Same as u_hasBinaryProperty(c, UCHAR_UPPERCASE).
sl@0	1612	* This is different from u_isupper!
sl@0	1613	* @param c Code point to test
sl@0	1614	* @return true if the code point has the Uppercase Unicode property, false otherwise
sl@0	1615	*
sl@0	1616	* @see UCHAR_UPPERCASE
sl@0	1617	* @see u_isupper
sl@0	1618	* @see u_hasBinaryProperty
sl@0	1619	* @stable ICU 2.1
sl@0	1620	*/
sl@0	1621	U_STABLE UBool U_EXPORT2
sl@0	1622	u_isUUppercase(UChar32 c);
sl@0	1623
sl@0	1624	/**
sl@0	1625	* Check if a code point has the White_Space Unicode property.
sl@0	1626	* Same as u_hasBinaryProperty(c, UCHAR_WHITE_SPACE).
sl@0	1627	* This is different from both u_isspace and u_isWhitespace!
sl@0	1628	*
sl@0	1629	* Note: There are several ICU whitespace functions; please see the uchar.h
sl@0	1630	* file documentation for a detailed comparison.
sl@0	1631	*
sl@0	1632	* @param c Code point to test
sl@0	1633	* @return true if the code point has the White_Space Unicode property, false otherwise.
sl@0	1634	*
sl@0	1635	* @see UCHAR_WHITE_SPACE
sl@0	1636	* @see u_isWhitespace
sl@0	1637	* @see u_isspace
sl@0	1638	* @see u_isJavaSpaceChar
sl@0	1639	* @see u_hasBinaryProperty
sl@0	1640	* @stable ICU 2.1
sl@0	1641	*/
sl@0	1642	U_STABLE UBool U_EXPORT2
sl@0	1643	u_isUWhiteSpace(UChar32 c);
sl@0	1644
sl@0	1645	/**
sl@0	1646	* Get the property value for an enumerated or integer Unicode property for a code point.
sl@0	1647	* Also returns binary and mask property values.
sl@0	1648	*
sl@0	1649	* Unicode, especially in version 3.2, defines many more properties than the
sl@0	1650	* original set in UnicodeData.txt.
sl@0	1651	*
sl@0	1652	* The properties APIs are intended to reflect Unicode properties as defined
sl@0	1653	* in the Unicode Character Database (UCD) and Unicode Technical Reports (UTR).
sl@0	1654	* For details about the properties see http://www.unicode.org/ .
sl@0	1655	* For names of Unicode properties see the UCD file PropertyAliases.txt.
sl@0	1656	*
sl@0	1657	* Sample usage:
sl@0	1658	* UEastAsianWidth ea=(UEastAsianWidth)u_getIntPropertyValue(c, UCHAR_EAST_ASIAN_WIDTH);
sl@0	1659	* UBool b=(UBool)u_getIntPropertyValue(c, UCHAR_IDEOGRAPHIC);
sl@0	1660	*
sl@0	1661	* @param c Code point to test.
sl@0	1662	* @param which UProperty selector constant, identifies which property to check.
sl@0	1663	* Must be UCHAR_BINARY_START<=which<UCHAR_BINARY_LIMIT
sl@0	1664	* or UCHAR_INT_START<=which<UCHAR_INT_LIMIT
sl@0	1665	* or UCHAR_MASK_START<=which<UCHAR_MASK_LIMIT.
sl@0	1666	* @return Numeric value that is directly the property value or,
sl@0	1667	* for enumerated properties, corresponds to the numeric value of the enumerated
sl@0	1668	* constant of the respective property value enumeration type
sl@0	1669	* (cast to enum type if necessary).
sl@0	1670	* Returns 0 or 1 (for FALSE/TRUE) for binary Unicode properties.
sl@0	1671	* Returns a bit-mask for mask properties.
sl@0	1672	* Returns 0 if 'which' is out of bounds or if the Unicode version
sl@0	1673	* does not have data for the property at all, or not for this code point.
sl@0	1674	*
sl@0	1675	* @see UProperty
sl@0	1676	* @see u_hasBinaryProperty
sl@0	1677	* @see u_getIntPropertyMinValue
sl@0	1678	* @see u_getIntPropertyMaxValue
sl@0	1679	* @see u_getUnicodeVersion
sl@0	1680	* @stable ICU 2.2
sl@0	1681	*/
sl@0	1682	U_STABLE int32_t U_EXPORT2
sl@0	1683	u_getIntPropertyValue(UChar32 c, UProperty which);
sl@0	1684
sl@0	1685	/**
sl@0	1686	* Get the minimum value for an enumerated/integer/binary Unicode property.
sl@0	1687	* Can be used together with u_getIntPropertyMaxValue
sl@0	1688	* to allocate arrays of UnicodeSet or similar.
sl@0	1689	*
sl@0	1690	* @param which UProperty selector constant, identifies which binary property to check.
sl@0	1691	* Must be UCHAR_BINARY_START<=which<UCHAR_BINARY_LIMIT
sl@0	1692	* or UCHAR_INT_START<=which<UCHAR_INT_LIMIT.
sl@0	1693	* @return Minimum value returned by u_getIntPropertyValue for a Unicode property.
sl@0	1694	* 0 if the property selector is out of range.
sl@0	1695	*
sl@0	1696	* @see UProperty
sl@0	1697	* @see u_hasBinaryProperty
sl@0	1698	* @see u_getUnicodeVersion
sl@0	1699	* @see u_getIntPropertyMaxValue
sl@0	1700	* @see u_getIntPropertyValue
sl@0	1701	* @stable ICU 2.2
sl@0	1702	*/
sl@0	1703	U_STABLE int32_t U_EXPORT2
sl@0	1704	u_getIntPropertyMinValue(UProperty which);
sl@0	1705
sl@0	1706	/**
sl@0	1707	* Get the maximum value for an enumerated/integer/binary Unicode property.
sl@0	1708	* Can be used together with u_getIntPropertyMinValue
sl@0	1709	* to allocate arrays of UnicodeSet or similar.
sl@0	1710	*
sl@0	1711	* Examples for min/max values (for Unicode 3.2):
sl@0	1712	*
sl@0	1713	* - UCHAR_BIDI_CLASS: 0/18 (U_LEFT_TO_RIGHT/U_BOUNDARY_NEUTRAL)
sl@0	1714	* - UCHAR_SCRIPT: 0/45 (USCRIPT_COMMON/USCRIPT_TAGBANWA)
sl@0	1715	* - UCHAR_IDEOGRAPHIC: 0/1 (FALSE/TRUE)
sl@0	1716	*
sl@0	1717	* For undefined UProperty constant values, min/max values will be 0/-1.
sl@0	1718	*
sl@0	1719	* @param which UProperty selector constant, identifies which binary property to check.
sl@0	1720	* Must be UCHAR_BINARY_START<=which<UCHAR_BINARY_LIMIT
sl@0	1721	* or UCHAR_INT_START<=which<UCHAR_INT_LIMIT.
sl@0	1722	* @return Maximum value returned by u_getIntPropertyValue for a Unicode property.
sl@0	1723	* <=0 if the property selector is out of range.
sl@0	1724	*
sl@0	1725	* @see UProperty
sl@0	1726	* @see u_hasBinaryProperty
sl@0	1727	* @see u_getUnicodeVersion
sl@0	1728	* @see u_getIntPropertyMaxValue
sl@0	1729	* @see u_getIntPropertyValue
sl@0	1730	* @stable ICU 2.2
sl@0	1731	*/
sl@0	1732	U_STABLE int32_t U_EXPORT2
sl@0	1733	u_getIntPropertyMaxValue(UProperty which);
sl@0	1734
sl@0	1735	/**
sl@0	1736	* Get the numeric value for a Unicode code point as defined in the
sl@0	1737	* Unicode Character Database.
sl@0	1738	*
sl@0	1739	* A "double" return type is necessary because
sl@0	1740	* some numeric values are fractions, negative, or too large for int32_t.
sl@0	1741	*
sl@0	1742	* For characters without any numeric values in the Unicode Character Database,
sl@0	1743	* this function will return U_NO_NUMERIC_VALUE.
sl@0	1744	*
sl@0	1745	* Similar to java.lang.Character.getNumericValue(), but u_getNumericValue()
sl@0	1746	* also supports negative values, large values, and fractions,
sl@0	1747	* while Java's getNumericValue() returns values 10..35 for ASCII letters.
sl@0	1748	*
sl@0	1749	* @param c Code point to get the numeric value for.
sl@0	1750	* @return Numeric value of c, or U_NO_NUMERIC_VALUE if none is defined.
sl@0	1751	*
sl@0	1752	* @see U_NO_NUMERIC_VALUE
sl@0	1753	* @stable ICU 2.2
sl@0	1754	*/
sl@0	1755	U_STABLE double U_EXPORT2
sl@0	1756	u_getNumericValue(UChar32 c);
sl@0	1757
sl@0	1758	/**
sl@0	1759	* Special value that is returned by u_getNumericValue when
sl@0	1760	* no numeric value is defined for a code point.
sl@0	1761	*
sl@0	1762	* @see u_getNumericValue
sl@0	1763	* @stable ICU 2.2
sl@0	1764	*/
sl@0	1765	#define U_NO_NUMERIC_VALUE ((double)-123456789.)
sl@0	1766
sl@0	1767	/**
sl@0	1768	* Determines whether the specified code point has the general category "Ll"
sl@0	1769	* (lowercase letter).
sl@0	1770	*
sl@0	1771	* Same as java.lang.Character.isLowerCase().
sl@0	1772	*
sl@0	1773	* This misses some characters that are also lowercase but
sl@0	1774	* have a different general category value.
sl@0	1775	* In order to include those, use UCHAR_LOWERCASE.
sl@0	1776	*
sl@0	1777	* In addition to being equivalent to a Java function, this also serves
sl@0	1778	* as a C/POSIX migration function.
sl@0	1779	* See the comments about C/POSIX character classification functions in the
sl@0	1780	* documentation at the top of this header file.
sl@0	1781	*
sl@0	1782	* @param c the code point to be tested
sl@0	1783	* @return TRUE if the code point is an Ll lowercase letter
sl@0	1784	*
sl@0	1785	* @see UCHAR_LOWERCASE
sl@0	1786	* @see u_isupper
sl@0	1787	* @see u_istitle
sl@0	1788	* @stable ICU 2.0
sl@0	1789	*/
sl@0	1790	U_STABLE UBool U_EXPORT2
sl@0	1791	u_islower(UChar32 c);
sl@0	1792
sl@0	1793	/**
sl@0	1794	* Determines whether the specified code point has the general category "Lu"
sl@0	1795	* (uppercase letter).
sl@0	1796	*
sl@0	1797	* Same as java.lang.Character.isUpperCase().
sl@0	1798	*
sl@0	1799	* This misses some characters that are also uppercase but
sl@0	1800	* have a different general category value.
sl@0	1801	* In order to include those, use UCHAR_UPPERCASE.
sl@0	1802	*
sl@0	1803	* In addition to being equivalent to a Java function, this also serves
sl@0	1804	* as a C/POSIX migration function.
sl@0	1805	* See the comments about C/POSIX character classification functions in the
sl@0	1806	* documentation at the top of this header file.
sl@0	1807	*
sl@0	1808	* @param c the code point to be tested
sl@0	1809	* @return TRUE if the code point is an Lu uppercase letter
sl@0	1810	*
sl@0	1811	* @see UCHAR_UPPERCASE
sl@0	1812	* @see u_islower
sl@0	1813	* @see u_istitle
sl@0	1814	* @see u_tolower
sl@0	1815	* @stable ICU 2.0
sl@0	1816	*/
sl@0	1817	U_STABLE UBool U_EXPORT2
sl@0	1818	u_isupper(UChar32 c);
sl@0	1819
sl@0	1820	/**
sl@0	1821	* Determines whether the specified code point is a titlecase letter.
sl@0	1822	* True for general category "Lt" (titlecase letter).
sl@0	1823	*
sl@0	1824	* Same as java.lang.Character.isTitleCase().
sl@0	1825	*
sl@0	1826	* @param c the code point to be tested
sl@0	1827	* @return TRUE if the code point is an Lt titlecase letter
sl@0	1828	*
sl@0	1829	* @see u_isupper
sl@0	1830	* @see u_islower
sl@0	1831	* @see u_totitle
sl@0	1832	* @stable ICU 2.0
sl@0	1833	*/
sl@0	1834	U_STABLE UBool U_EXPORT2
sl@0	1835	u_istitle(UChar32 c);
sl@0	1836
sl@0	1837	/**
sl@0	1838	* Determines whether the specified code point is a digit character according to Java.
sl@0	1839	* True for characters with general category "Nd" (decimal digit numbers).
sl@0	1840	* Beginning with Unicode 4, this is the same as
sl@0	1841	* testing for the Numeric_Type of Decimal.
sl@0	1842	*
sl@0	1843	* Same as java.lang.Character.isDigit().
sl@0	1844	*
sl@0	1845	* In addition to being equivalent to a Java function, this also serves
sl@0	1846	* as a C/POSIX migration function.
sl@0	1847	* See the comments about C/POSIX character classification functions in the
sl@0	1848	* documentation at the top of this header file.
sl@0	1849	*
sl@0	1850	* @param c the code point to be tested
sl@0	1851	* @return TRUE if the code point is a digit character according to Character.isDigit()
sl@0	1852	*
sl@0	1853	* @stable ICU 2.0
sl@0	1854	*/
sl@0	1855	U_STABLE UBool U_EXPORT2
sl@0	1856	u_isdigit(UChar32 c);
sl@0	1857
sl@0	1858	/**
sl@0	1859	* Determines whether the specified code point is a letter character.
sl@0	1860	* True for general categories "L" (letters).
sl@0	1861	*
sl@0	1862	* Same as java.lang.Character.isLetter().
sl@0	1863	*
sl@0	1864	* In addition to being equivalent to a Java function, this also serves
sl@0	1865	* as a C/POSIX migration function.
sl@0	1866	* See the comments about C/POSIX character classification functions in the
sl@0	1867	* documentation at the top of this header file.
sl@0	1868	*
sl@0	1869	* @param c the code point to be tested
sl@0	1870	* @return TRUE if the code point is a letter character
sl@0	1871	*
sl@0	1872	* @see u_isdigit
sl@0	1873	* @see u_isalnum
sl@0	1874	* @stable ICU 2.0
sl@0	1875	*/
sl@0	1876	U_STABLE UBool U_EXPORT2
sl@0	1877	u_isalpha(UChar32 c);
sl@0	1878
sl@0	1879	/**
sl@0	1880	* Determines whether the specified code point is an alphanumeric character
sl@0	1881	* (letter or digit) according to Java.
sl@0	1882	* True for characters with general categories
sl@0	1883	* "L" (letters) and "Nd" (decimal digit numbers).
sl@0	1884	*
sl@0	1885	* Same as java.lang.Character.isLetterOrDigit().
sl@0	1886	*
sl@0	1887	* In addition to being equivalent to a Java function, this also serves
sl@0	1888	* as a C/POSIX migration function.
sl@0	1889	* See the comments about C/POSIX character classification functions in the
sl@0	1890	* documentation at the top of this header file.
sl@0	1891	*
sl@0	1892	* @param c the code point to be tested
sl@0	1893	* @return TRUE if the code point is an alphanumeric character according to Character.isLetterOrDigit()
sl@0	1894	*
sl@0	1895	* @stable ICU 2.0
sl@0	1896	*/
sl@0	1897	U_STABLE UBool U_EXPORT2
sl@0	1898	u_isalnum(UChar32 c);
sl@0	1899
sl@0	1900	/**
sl@0	1901	* Determines whether the specified code point is a hexadecimal digit.
sl@0	1902	* This is equivalent to u_digit(c, 16)>=0.
sl@0	1903	* True for characters with general category "Nd" (decimal digit numbers)
sl@0	1904	* as well as Latin letters a-f and A-F in both ASCII and Fullwidth ASCII.
sl@0	1905	* (That is, for letters with code points
sl@0	1906	* 0041..0046, 0061..0066, FF21..FF26, FF41..FF46.)
sl@0	1907	*
sl@0	1908	* In order to narrow the definition of hexadecimal digits to only ASCII
sl@0	1909	* characters, use (c<=0x7f && u_isxdigit(c)).
sl@0	1910	*
sl@0	1911	* This is a C/POSIX migration function.
sl@0	1912	* See the comments about C/POSIX character classification functions in the
sl@0	1913	* documentation at the top of this header file.
sl@0	1914	*
sl@0	1915	* @param c the code point to be tested
sl@0	1916	* @return TRUE if the code point is a hexadecimal digit
sl@0	1917	*
sl@0	1918	* @stable ICU 2.6
sl@0	1919	*/
sl@0	1920	U_STABLE UBool U_EXPORT2
sl@0	1921	u_isxdigit(UChar32 c);
sl@0	1922
sl@0	1923	/**
sl@0	1924	* Determines whether the specified code point is a punctuation character.
sl@0	1925	* True for characters with general categories "P" (punctuation).
sl@0	1926	*
sl@0	1927	* This is a C/POSIX migration function.
sl@0	1928	* See the comments about C/POSIX character classification functions in the
sl@0	1929	* documentation at the top of this header file.
sl@0	1930	*
sl@0	1931	* @param c the code point to be tested
sl@0	1932	* @return TRUE if the code point is a punctuation character
sl@0	1933	*
sl@0	1934	* @stable ICU 2.6
sl@0	1935	*/
sl@0	1936	U_STABLE UBool U_EXPORT2
sl@0	1937	u_ispunct(UChar32 c);
sl@0	1938
sl@0	1939	/**
sl@0	1940	* Determines whether the specified code point is a "graphic" character
sl@0	1941	* (printable, excluding spaces).
sl@0	1942	* TRUE for all characters except those with general categories
sl@0	1943	* "Cc" (control codes), "Cf" (format controls), "Cs" (surrogates),
sl@0	1944	* "Cn" (unassigned), and "Z" (separators).
sl@0	1945	*
sl@0	1946	* This is a C/POSIX migration function.
sl@0	1947	* See the comments about C/POSIX character classification functions in the
sl@0	1948	* documentation at the top of this header file.
sl@0	1949	*
sl@0	1950	* @param c the code point to be tested
sl@0	1951	* @return TRUE if the code point is a "graphic" character
sl@0	1952	*
sl@0	1953	* @stable ICU 2.6
sl@0	1954	*/
sl@0	1955	U_STABLE UBool U_EXPORT2
sl@0	1956	u_isgraph(UChar32 c);
sl@0	1957
sl@0	1958	/**
sl@0	1959	* Determines whether the specified code point is a "blank" or "horizontal space",
sl@0	1960	* a character that visibly separates words on a line.
sl@0	1961	* The following are equivalent definitions:
sl@0	1962	*
sl@0	1963	* TRUE for Unicode White_Space characters except for "vertical space controls"
sl@0	1964	* where "vertical space controls" are the following characters:
sl@0	1965	* U+000A (LF) U+000B (VT) U+000C (FF) U+000D (CR) U+0085 (NEL) U+2028 (LS) U+2029 (PS)
sl@0	1966	*
sl@0	1967	* same as
sl@0	1968	*
sl@0	1969	* TRUE for U+0009 (TAB) and characters with general category "Zs" (space separators)
sl@0	1970	* except Zero Width Space (ZWSP, U+200B).
sl@0	1971	*
sl@0	1972	* Note: There are several ICU whitespace functions; please see the uchar.h
sl@0	1973	* file documentation for a detailed comparison.
sl@0	1974	*
sl@0	1975	* This is a C/POSIX migration function.
sl@0	1976	* See the comments about C/POSIX character classification functions in the
sl@0	1977	* documentation at the top of this header file.
sl@0	1978	*
sl@0	1979	* @param c the code point to be tested
sl@0	1980	* @return TRUE if the code point is a "blank"
sl@0	1981	*
sl@0	1982	* @stable ICU 2.6
sl@0	1983	*/
sl@0	1984	U_STABLE UBool U_EXPORT2
sl@0	1985	u_isblank(UChar32 c);
sl@0	1986
sl@0	1987	/**
sl@0	1988	* Determines whether the specified code point is "defined",
sl@0	1989	* which usually means that it is assigned a character.
sl@0	1990	* True for general categories other than "Cn" (other, not assigned),
sl@0	1991	* i.e., true for all code points mentioned in UnicodeData.txt.
sl@0	1992	*
sl@0	1993	* Note that non-character code points (e.g., U+FDD0) are not "defined"
sl@0	1994	* (they are Cn), but surrogate code points are "defined" (Cs).
sl@0	1995	*
sl@0	1996	* Same as java.lang.Character.isDefined().
sl@0	1997	*
sl@0	1998	* @param c the code point to be tested
sl@0	1999	* @return TRUE if the code point is assigned a character
sl@0	2000	*
sl@0	2001	* @see u_isdigit
sl@0	2002	* @see u_isalpha
sl@0	2003	* @see u_isalnum
sl@0	2004	* @see u_isupper
sl@0	2005	* @see u_islower
sl@0	2006	* @see u_istitle
sl@0	2007	* @stable ICU 2.0
sl@0	2008	*/
sl@0	2009	U_STABLE UBool U_EXPORT2
sl@0	2010	u_isdefined(UChar32 c);
sl@0	2011
sl@0	2012	/**
sl@0	2013	* Determines if the specified character is a space character or not.
sl@0	2014	*
sl@0	2015	* Note: There are several ICU whitespace functions; please see the uchar.h
sl@0	2016	* file documentation for a detailed comparison.
sl@0	2017	*
sl@0	2018	* This is a C/POSIX migration function.
sl@0	2019	* See the comments about C/POSIX character classification functions in the
sl@0	2020	* documentation at the top of this header file.
sl@0	2021	*
sl@0	2022	* @param c the character to be tested
sl@0	2023	* @return true if the character is a space character; false otherwise.
sl@0	2024	*
sl@0	2025	* @see u_isJavaSpaceChar
sl@0	2026	* @see u_isWhitespace
sl@0	2027	* @see u_isUWhiteSpace
sl@0	2028	* @stable ICU 2.0
sl@0	2029	*/
sl@0	2030	U_STABLE UBool U_EXPORT2
sl@0	2031	u_isspace(UChar32 c);
sl@0	2032
sl@0	2033	/**
sl@0	2034	* Determine if the specified code point is a space character according to Java.
sl@0	2035	* True for characters with general categories "Z" (separators),
sl@0	2036	* which does not include control codes (e.g., TAB or Line Feed).
sl@0	2037	*
sl@0	2038	* Same as java.lang.Character.isSpaceChar().
sl@0	2039	*
sl@0	2040	* Note: There are several ICU whitespace functions; please see the uchar.h
sl@0	2041	* file documentation for a detailed comparison.
sl@0	2042	*
sl@0	2043	* @param c the code point to be tested
sl@0	2044	* @return TRUE if the code point is a space character according to Character.isSpaceChar()
sl@0	2045	*
sl@0	2046	* @see u_isspace
sl@0	2047	* @see u_isWhitespace
sl@0	2048	* @see u_isUWhiteSpace
sl@0	2049	* @stable ICU 2.6
sl@0	2050	*/
sl@0	2051	U_STABLE UBool U_EXPORT2
sl@0	2052	u_isJavaSpaceChar(UChar32 c);
sl@0	2053
sl@0	2054	/**
sl@0	2055	* Determines if the specified code point is a whitespace character according to Java/ICU.
sl@0	2056	* A character is considered to be a Java whitespace character if and only
sl@0	2057	* if it satisfies one of the following criteria:
sl@0	2058	*
sl@0	2059	* - It is a Unicode separator (categories "Z"), but is not
sl@0	2060	* a no-break space (U+00A0 NBSP or U+2007 Figure Space or U+202F Narrow NBSP).
sl@0	2061	* - It is U+0009 HORIZONTAL TABULATION.
sl@0	2062	* - It is U+000A LINE FEED.
sl@0	2063	* - It is U+000B VERTICAL TABULATION.
sl@0	2064	* - It is U+000C FORM FEED.
sl@0	2065	* - It is U+000D CARRIAGE RETURN.
sl@0	2066	* - It is U+001C FILE SEPARATOR.
sl@0	2067	* - It is U+001D GROUP SEPARATOR.
sl@0	2068	* - It is U+001E RECORD SEPARATOR.
sl@0	2069	* - It is U+001F UNIT SEPARATOR.
sl@0	2070	* - It is U+0085 NEXT LINE.
sl@0	2071	*
sl@0	2072	* Same as java.lang.Character.isWhitespace() except that Java omits U+0085.
sl@0	2073	*
sl@0	2074	* Note: There are several ICU whitespace functions; please see the uchar.h
sl@0	2075	* file documentation for a detailed comparison.
sl@0	2076	*
sl@0	2077	* @param c the code point to be tested
sl@0	2078	* @return TRUE if the code point is a whitespace character according to Java/ICU
sl@0	2079	*
sl@0	2080	* @see u_isspace
sl@0	2081	* @see u_isJavaSpaceChar
sl@0	2082	* @see u_isUWhiteSpace
sl@0	2083	* @stable ICU 2.0
sl@0	2084	*/
sl@0	2085	U_STABLE UBool U_EXPORT2
sl@0	2086	u_isWhitespace(UChar32 c);
sl@0	2087
sl@0	2088	/**
sl@0	2089	* Determines whether the specified code point is a control character
sl@0	2090	* (as defined by this function).
sl@0	2091	* A control character is one of the following:
sl@0	2092	* - ISO 8-bit control character (U+0000..U+001f and U+007f..U+009f)
sl@0	2093	* - U_CONTROL_CHAR (Cc)
sl@0	2094	* - U_FORMAT_CHAR (Cf)
sl@0	2095	* - U_LINE_SEPARATOR (Zl)
sl@0	2096	* - U_PARAGRAPH_SEPARATOR (Zp)
sl@0	2097	*
sl@0	2098	* This is a C/POSIX migration function.
sl@0	2099	* See the comments about C/POSIX character classification functions in the
sl@0	2100	* documentation at the top of this header file.
sl@0	2101	*
sl@0	2102	* @param c the code point to be tested
sl@0	2103	* @return TRUE if the code point is a control character
sl@0	2104	*
sl@0	2105	* @see UCHAR_DEFAULT_IGNORABLE_CODE_POINT
sl@0	2106	* @see u_isprint
sl@0	2107	* @stable ICU 2.0
sl@0	2108	*/
sl@0	2109	U_STABLE UBool U_EXPORT2
sl@0	2110	u_iscntrl(UChar32 c);
sl@0	2111
sl@0	2112	/**
sl@0	2113	* Determines whether the specified code point is an ISO control code.
sl@0	2114	* True for U+0000..U+001f and U+007f..U+009f (general category "Cc").
sl@0	2115	*
sl@0	2116	* Same as java.lang.Character.isISOControl().
sl@0	2117	*
sl@0	2118	* @param c the code point to be tested
sl@0	2119	* @return TRUE if the code point is an ISO control code
sl@0	2120	*
sl@0	2121	* @see u_iscntrl
sl@0	2122	* @stable ICU 2.6
sl@0	2123	*/
sl@0	2124	U_STABLE UBool U_EXPORT2
sl@0	2125	u_isISOControl(UChar32 c);
sl@0	2126
sl@0	2127	/**
sl@0	2128	* Determines whether the specified code point is a printable character.
sl@0	2129	* True for general categories <em>other</em> than "C" (controls).
sl@0	2130	*
sl@0	2131	* This is a C/POSIX migration function.
sl@0	2132	* See the comments about C/POSIX character classification functions in the
sl@0	2133	* documentation at the top of this header file.
sl@0	2134	*
sl@0	2135	* @param c the code point to be tested
sl@0	2136	* @return TRUE if the code point is a printable character
sl@0	2137	*
sl@0	2138	* @see UCHAR_DEFAULT_IGNORABLE_CODE_POINT
sl@0	2139	* @see u_iscntrl
sl@0	2140	* @stable ICU 2.0
sl@0	2141	*/
sl@0	2142	U_STABLE UBool U_EXPORT2
sl@0	2143	u_isprint(UChar32 c);
sl@0	2144
sl@0	2145	/**
sl@0	2146	* Determines whether the specified code point is a base character.
sl@0	2147	* True for general categories "L" (letters), "N" (numbers),
sl@0	2148	* "Mc" (spacing combining marks), and "Me" (enclosing marks).
sl@0	2149	*
sl@0	2150	* Note that this is different from the Unicode definition in
sl@0	2151	* chapter 3.5, conformance clause D13,
sl@0	2152	* which defines base characters to be all characters (not Cn)
sl@0	2153	* that do not graphically combine with preceding characters (M)
sl@0	2154	* and that are neither control (Cc) or format (Cf) characters.
sl@0	2155	*
sl@0	2156	* @param c the code point to be tested
sl@0	2157	* @return TRUE if the code point is a base character according to this function
sl@0	2158	*
sl@0	2159	* @see u_isalpha
sl@0	2160	* @see u_isdigit
sl@0	2161	* @stable ICU 2.0
sl@0	2162	*/
sl@0	2163	U_STABLE UBool U_EXPORT2
sl@0	2164	u_isbase(UChar32 c);
sl@0	2165
sl@0	2166	/**
sl@0	2167	* Returns the bidirectional category value for the code point,
sl@0	2168	* which is used in the Unicode bidirectional algorithm
sl@0	2169	* (UAX #9 http://www.unicode.org/reports/tr9/).
sl@0	2170	* Note that some <em>unassigned</em> code points have bidi values
sl@0	2171	* of R or AL because they are in blocks that are reserved
sl@0	2172	* for Right-To-Left scripts.
sl@0	2173	*
sl@0	2174	* Same as java.lang.Character.getDirectionality()
sl@0	2175	*
sl@0	2176	* @param c the code point to be tested
sl@0	2177	* @return the bidirectional category (UCharDirection) value
sl@0	2178	*
sl@0	2179	* @see UCharDirection
sl@0	2180	* @stable ICU 2.0
sl@0	2181	*/
sl@0	2182	U_STABLE UCharDirection U_EXPORT2
sl@0	2183	u_charDirection(UChar32 c);
sl@0	2184
sl@0	2185	/**
sl@0	2186	* Determines whether the code point has the Bidi_Mirrored property.
sl@0	2187	* This property is set for characters that are commonly used in
sl@0	2188	* Right-To-Left contexts and need to be displayed with a "mirrored"
sl@0	2189	* glyph.
sl@0	2190	*
sl@0	2191	* Same as java.lang.Character.isMirrored().
sl@0	2192	* Same as UCHAR_BIDI_MIRRORED
sl@0	2193	*
sl@0	2194	* @param c the code point to be tested
sl@0	2195	* @return TRUE if the character has the Bidi_Mirrored property
sl@0	2196	*
sl@0	2197	* @see UCHAR_BIDI_MIRRORED
sl@0	2198	* @stable ICU 2.0
sl@0	2199	*/
sl@0	2200	U_STABLE UBool U_EXPORT2
sl@0	2201	u_isMirrored(UChar32 c);
sl@0	2202
sl@0	2203	/**
sl@0	2204	* Maps the specified character to a "mirror-image" character.
sl@0	2205	* For characters with the Bidi_Mirrored property, implementations
sl@0	2206	* sometimes need a "poor man's" mapping to another Unicode
sl@0	2207	* character (code point) such that the default glyph may serve
sl@0	2208	* as the mirror-image of the default glyph of the specified
sl@0	2209	* character. This is useful for text conversion to and from
sl@0	2210	* codepages with visual order, and for displays without glyph
sl@0	2211	* selecetion capabilities.
sl@0	2212	*
sl@0	2213	* @param c the code point to be mapped
sl@0	2214	* @return another Unicode code point that may serve as a mirror-image
sl@0	2215	* substitute, or c itself if there is no such mapping or c
sl@0	2216	* does not have the Bidi_Mirrored property
sl@0	2217	*
sl@0	2218	* @see UCHAR_BIDI_MIRRORED
sl@0	2219	* @see u_isMirrored
sl@0	2220	* @stable ICU 2.0
sl@0	2221	*/
sl@0	2222	U_STABLE UChar32 U_EXPORT2
sl@0	2223	u_charMirror(UChar32 c);
sl@0	2224
sl@0	2225	/**
sl@0	2226	* Returns the general category value for the code point.
sl@0	2227	*
sl@0	2228	* Same as java.lang.Character.getType().
sl@0	2229	*
sl@0	2230	* @param c the code point to be tested
sl@0	2231	* @return the general category (UCharCategory) value
sl@0	2232	*
sl@0	2233	* @see UCharCategory
sl@0	2234	* @stable ICU 2.0
sl@0	2235	*/
sl@0	2236	U_STABLE int8_t U_EXPORT2
sl@0	2237	u_charType(UChar32 c);
sl@0	2238
sl@0	2239	/**
sl@0	2240	* Get a single-bit bit set for the general category of a character.
sl@0	2241	* This bit set can be compared bitwise with U_GC_SM_MASK, U_GC_L_MASK, etc.
sl@0	2242	* Same as U_MASK(u_charType(c)).
sl@0	2243	*
sl@0	2244	* @param c the code point to be tested
sl@0	2245	* @return a single-bit mask corresponding to the general category (UCharCategory) value
sl@0	2246	*
sl@0	2247	* @see u_charType
sl@0	2248	* @see UCharCategory
sl@0	2249	* @see U_GC_CN_MASK
sl@0	2250	* @stable ICU 2.1
sl@0	2251	*/
sl@0	2252	#define U_GET_GC_MASK(c) U_MASK(u_charType(c))
sl@0	2253
sl@0	2254	/**
sl@0	2255	* Callback from u_enumCharTypes(), is called for each contiguous range
sl@0	2256	* of code points c (where start<=c<limit)
sl@0	2257	* with the same Unicode general category ("character type").
sl@0	2258	*
sl@0	2259	* The callback function can stop the enumeration by returning FALSE.
sl@0	2260	*
sl@0	2261	* @param context an opaque pointer, as passed into utrie_enum()
sl@0	2262	* @param start the first code point in a contiguous range with value
sl@0	2263	* @param limit one past the last code point in a contiguous range with value
sl@0	2264	* @param type the general category for all code points in [start..limit[
sl@0	2265	* @return FALSE to stop the enumeration
sl@0	2266	*
sl@0	2267	* @stable ICU 2.1
sl@0	2268	* @see UCharCategory
sl@0	2269	* @see u_enumCharTypes
sl@0	2270	*/
sl@0	2271	typedef UBool U_CALLCONV
sl@0	2272	UCharEnumTypeRange(const void *context, UChar32 start, UChar32 limit, UCharCategory type);
sl@0	2273
sl@0	2274	/**
sl@0	2275	* Enumerate efficiently all code points with their Unicode general categories.
sl@0	2276	*
sl@0	2277	* This is useful for building data structures (e.g., UnicodeSet's),
sl@0	2278	* for enumerating all assigned code points (type!=U_UNASSIGNED), etc.
sl@0	2279	*
sl@0	2280	* For each contiguous range of code points with a given general category ("character type"),
sl@0	2281	* the UCharEnumTypeRange function is called.
sl@0	2282	* Adjacent ranges have different types.
sl@0	2283	* The Unicode Standard guarantees that the numeric value of the type is 0..31.
sl@0	2284	*
sl@0	2285	* @param enumRange a pointer to a function that is called for each contiguous range
sl@0	2286	* of code points with the same general category
sl@0	2287	* @param context an opaque pointer that is passed on to the callback function
sl@0	2288	*
sl@0	2289	* @stable ICU 2.1
sl@0	2290	* @see UCharCategory
sl@0	2291	* @see UCharEnumTypeRange
sl@0	2292	*/
sl@0	2293	U_STABLE void U_EXPORT2
sl@0	2294	u_enumCharTypes(UCharEnumTypeRange enumRange, const void context);
sl@0	2295
sl@0	2296	#if !UCONFIG_NO_NORMALIZATION
sl@0	2297
sl@0	2298	/**
sl@0	2299	* Returns the combining class of the code point as specified in UnicodeData.txt.
sl@0	2300	*
sl@0	2301	* @param c the code point of the character
sl@0	2302	* @return the combining class of the character
sl@0	2303	* @stable ICU 2.0
sl@0	2304	*/
sl@0	2305	U_STABLE uint8_t U_EXPORT2
sl@0	2306	u_getCombiningClass(UChar32 c);
sl@0	2307
sl@0	2308	#endif
sl@0	2309
sl@0	2310	/**
sl@0	2311	* Returns the decimal digit value of a decimal digit character.
sl@0	2312	* Such characters have the general category "Nd" (decimal digit numbers)
sl@0	2313	* and a Numeric_Type of Decimal.
sl@0	2314	*
sl@0	2315	* Unlike ICU releases before 2.6, no digit values are returned for any
sl@0	2316	* Han characters because Han number characters are often used with a special
sl@0	2317	* Chinese-style number format (with characters for powers of 10 in between)
sl@0	2318	* instead of in decimal-positional notation.
sl@0	2319	* Unicode 4 explicitly assigns Han number characters the Numeric_Type
sl@0	2320	* Numeric instead of Decimal.
sl@0	2321	* See Jitterbug 1483 for more details.
sl@0	2322	*
sl@0	2323	* Use u_getIntPropertyValue(c, UCHAR_NUMERIC_TYPE) and u_getNumericValue()
sl@0	2324	* for complete numeric Unicode properties.
sl@0	2325	*
sl@0	2326	* @param c the code point for which to get the decimal digit value
sl@0	2327	* @return the decimal digit value of c,
sl@0	2328	* or -1 if c is not a decimal digit character
sl@0	2329	*
sl@0	2330	* @see u_getNumericValue
sl@0	2331	* @stable ICU 2.0
sl@0	2332	*/
sl@0	2333	U_STABLE int32_t U_EXPORT2
sl@0	2334	u_charDigitValue(UChar32 c);
sl@0	2335
sl@0	2336	/**
sl@0	2337	* Returns the Unicode allocation block that contains the character.
sl@0	2338	*
sl@0	2339	* @param c the code point to be tested
sl@0	2340	* @return the block value (UBlockCode) for c
sl@0	2341	*
sl@0	2342	* @see UBlockCode
sl@0	2343	* @stable ICU 2.0
sl@0	2344	*/
sl@0	2345	U_STABLE UBlockCode U_EXPORT2
sl@0	2346	ublock_getCode(UChar32 c);
sl@0	2347
sl@0	2348	/**
sl@0	2349	* Retrieve the name of a Unicode character.
sl@0	2350	* Depending on <code>nameChoice</code>, the character name written
sl@0	2351	* into the buffer is the "modern" name or the name that was defined
sl@0	2352	* in Unicode version 1.0.
sl@0	2353	* The name contains only "invariant" characters
sl@0	2354	* like A-Z, 0-9, space, and '-'.
sl@0	2355	* Unicode 1.0 names are only retrieved if they are different from the modern
sl@0	2356	* names and if the data file contains the data for them. gennames may or may
sl@0	2357	* not be called with a command line option to include 1.0 names in unames.dat.
sl@0	2358	*
sl@0	2359	* @param code The character (code point) for which to get the name.
sl@0	2360	* It must be <code>0<=code<=0x10ffff</code>.
sl@0	2361	* @param nameChoice Selector for which name to get.
sl@0	2362	* @param buffer Destination address for copying the name.
sl@0	2363	* The name will always be zero-terminated.
sl@0	2364	* If there is no name, then the buffer will be set to the empty string.
sl@0	2365	* @param bufferLength <code>==sizeof(buffer)</code>
sl@0	2366	* @param pErrorCode Pointer to a UErrorCode variable;
sl@0	2367	* check for <code>U_SUCCESS()</code> after <code>u_charName()</code>
sl@0	2368	* returns.
sl@0	2369	* @return The length of the name, or 0 if there is no name for this character.
sl@0	2370	* If the bufferLength is less than or equal to the length, then the buffer
sl@0	2371	* contains the truncated name and the returned length indicates the full
sl@0	2372	* length of the name.
sl@0	2373	* The length does not include the zero-termination.
sl@0	2374	*
sl@0	2375	* @see UCharNameChoice
sl@0	2376	* @see u_charFromName
sl@0	2377	* @see u_enumCharNames
sl@0	2378	* @stable ICU 2.0
sl@0	2379	*/
sl@0	2380	U_STABLE int32_t U_EXPORT2
sl@0	2381	u_charName(UChar32 code, UCharNameChoice nameChoice,
sl@0	2382	char *buffer, int32_t bufferLength,
sl@0	2383	UErrorCode *pErrorCode);
sl@0	2384
sl@0	2385	/**
sl@0	2386	* Get the ISO 10646 comment for a character.
sl@0	2387	* The ISO 10646 comment is an informative field in the Unicode Character
sl@0	2388	* Database (UnicodeData.txt field 11) and is from the ISO 10646 names list.
sl@0	2389	*
sl@0	2390	* @param c The character (code point) for which to get the ISO comment.
sl@0	2391	* It must be <code>0<=c<=0x10ffff</code>.
sl@0	2392	* @param dest Destination address for copying the comment.
sl@0	2393	* The comment will be zero-terminated if possible.
sl@0	2394	* If there is no comment, then the buffer will be set to the empty string.
sl@0	2395	* @param destCapacity <code>==sizeof(dest)</code>
sl@0	2396	* @param pErrorCode Pointer to a UErrorCode variable;
sl@0	2397	* check for <code>U_SUCCESS()</code> after <code>u_getISOComment()</code>
sl@0	2398	* returns.
sl@0	2399	* @return The length of the comment, or 0 if there is no comment for this character.
sl@0	2400	* If the destCapacity is less than or equal to the length, then the buffer
sl@0	2401	* contains the truncated name and the returned length indicates the full
sl@0	2402	* length of the name.
sl@0	2403	* The length does not include the zero-termination.
sl@0	2404	*
sl@0	2405	* @stable ICU 2.2
sl@0	2406	*/
sl@0	2407	U_STABLE int32_t U_EXPORT2
sl@0	2408	u_getISOComment(UChar32 c,
sl@0	2409	char *dest, int32_t destCapacity,
sl@0	2410	UErrorCode *pErrorCode);
sl@0	2411
sl@0	2412	/**
sl@0	2413	* Find a Unicode character by its name and return its code point value.
sl@0	2414	* The name is matched exactly and completely.
sl@0	2415	* If the name does not correspond to a code point, <i>pErrorCode</i>
sl@0	2416	* is set to <code>U_INVALID_CHAR_FOUND</code>.
sl@0	2417	* A Unicode 1.0 name is matched only if it differs from the modern name.
sl@0	2418	* Unicode names are all uppercase. Extended names are lowercase followed
sl@0	2419	* by an uppercase hexadecimal number, and within angle brackets.
sl@0	2420	*
sl@0	2421	* @param nameChoice Selector for which name to match.
sl@0	2422	* @param name The name to match.
sl@0	2423	* @param pErrorCode Pointer to a UErrorCode variable
sl@0	2424	* @return The Unicode value of the code point with the given name,
sl@0	2425	* or an undefined value if there is no such code point.
sl@0	2426	*
sl@0	2427	* @see UCharNameChoice
sl@0	2428	* @see u_charName
sl@0	2429	* @see u_enumCharNames
sl@0	2430	* @stable ICU 1.7
sl@0	2431	*/
sl@0	2432	U_STABLE UChar32 U_EXPORT2
sl@0	2433	u_charFromName(UCharNameChoice nameChoice,
sl@0	2434	const char *name,
sl@0	2435	UErrorCode *pErrorCode);
sl@0	2436
sl@0	2437	/**
sl@0	2438	* Type of a callback function for u_enumCharNames() that gets called
sl@0	2439	* for each Unicode character with the code point value and
sl@0	2440	* the character name.
sl@0	2441	* If such a function returns FALSE, then the enumeration is stopped.
sl@0	2442	*
sl@0	2443	* @param context The context pointer that was passed to u_enumCharNames().
sl@0	2444	* @param code The Unicode code point for the character with this name.
sl@0	2445	* @param nameChoice Selector for which kind of names is enumerated.
sl@0	2446	* @param name The character's name, zero-terminated.
sl@0	2447	* @param length The length of the name.
sl@0	2448	* @return TRUE if the enumeration should continue, FALSE to stop it.
sl@0	2449	*
sl@0	2450	* @see UCharNameChoice
sl@0	2451	* @see u_enumCharNames
sl@0	2452	* @stable ICU 1.7
sl@0	2453	*/
sl@0	2454	typedef UBool UEnumCharNamesFn(void *context,
sl@0	2455	UChar32 code,
sl@0	2456	UCharNameChoice nameChoice,
sl@0	2457	const char *name,
sl@0	2458	int32_t length);
sl@0	2459
sl@0	2460	/**
sl@0	2461	* Enumerate all assigned Unicode characters between the start and limit
sl@0	2462	* code points (start inclusive, limit exclusive) and call a function
sl@0	2463	* for each, passing the code point value and the character name.
sl@0	2464	* For Unicode 1.0 names, only those are enumerated that differ from the
sl@0	2465	* modern names.
sl@0	2466	*
sl@0	2467	* @param start The first code point in the enumeration range.
sl@0	2468	* @param limit One more than the last code point in the enumeration range
sl@0	2469	* (the first one after the range).
sl@0	2470	* @param fn The function that is to be called for each character name.
sl@0	2471	* @param context An arbitrary pointer that is passed to the function.
sl@0	2472	* @param nameChoice Selector for which kind of names to enumerate.
sl@0	2473	* @param pErrorCode Pointer to a UErrorCode variable
sl@0	2474	*
sl@0	2475	* @see UCharNameChoice
sl@0	2476	* @see UEnumCharNamesFn
sl@0	2477	* @see u_charName
sl@0	2478	* @see u_charFromName
sl@0	2479	* @stable ICU 1.7
sl@0	2480	*/
sl@0	2481	U_STABLE void U_EXPORT2
sl@0	2482	u_enumCharNames(UChar32 start, UChar32 limit,
sl@0	2483	UEnumCharNamesFn *fn,
sl@0	2484	void *context,
sl@0	2485	UCharNameChoice nameChoice,
sl@0	2486	UErrorCode *pErrorCode);
sl@0	2487
sl@0	2488	/**
sl@0	2489	* Return the Unicode name for a given property, as given in the
sl@0	2490	* Unicode database file PropertyAliases.txt.
sl@0	2491	*
sl@0	2492	* In addition, this function maps the property
sl@0	2493	* UCHAR_GENERAL_CATEGORY_MASK to the synthetic names "gcm" /
sl@0	2494	* "General_Category_Mask". These names are not in
sl@0	2495	* PropertyAliases.txt.
sl@0	2496	*
sl@0	2497	* @param property UProperty selector other than UCHAR_INVALID_CODE.
sl@0	2498	* If out of range, NULL is returned.
sl@0	2499	*
sl@0	2500	* @param nameChoice selector for which name to get. If out of range,
sl@0	2501	* NULL is returned. All properties have a long name. Most
sl@0	2502	* have a short name, but some do not. Unicode allows for
sl@0	2503	* additional names; if present these will be returned by
sl@0	2504	* U_LONG_PROPERTY_NAME + i, where i=1, 2,...
sl@0	2505	*
sl@0	2506	* @return a pointer to the name, or NULL if either the
sl@0	2507	* property or the nameChoice is out of range. If a given
sl@0	2508	* nameChoice returns NULL, then all larger values of
sl@0	2509	* nameChoice will return NULL, with one exception: if NULL is
sl@0	2510	* returned for U_SHORT_PROPERTY_NAME, then
sl@0	2511	* U_LONG_PROPERTY_NAME (and higher) may still return a
sl@0	2512	* non-NULL value. The returned pointer is valid until
sl@0	2513	* u_cleanup() is called.
sl@0	2514	*
sl@0	2515	* @see UProperty
sl@0	2516	* @see UPropertyNameChoice
sl@0	2517	* @stable ICU 2.4
sl@0	2518	*/
sl@0	2519	U_STABLE const char* U_EXPORT2
sl@0	2520	u_getPropertyName(UProperty property,
sl@0	2521	UPropertyNameChoice nameChoice);
sl@0	2522
sl@0	2523	/**
sl@0	2524	* Return the UProperty enum for a given property name, as specified
sl@0	2525	* in the Unicode database file PropertyAliases.txt. Short, long, and
sl@0	2526	* any other variants are recognized.
sl@0	2527	*
sl@0	2528	* In addition, this function maps the synthetic names "gcm" /
sl@0	2529	* "General_Category_Mask" to the property
sl@0	2530	* UCHAR_GENERAL_CATEGORY_MASK. These names are not in
sl@0	2531	* PropertyAliases.txt.
sl@0	2532	*
sl@0	2533	* @param alias the property name to be matched. The name is compared
sl@0	2534	* using "loose matching" as described in PropertyAliases.txt.
sl@0	2535	*
sl@0	2536	* @return a UProperty enum, or UCHAR_INVALID_CODE if the given name
sl@0	2537	* does not match any property.
sl@0	2538	*
sl@0	2539	* @see UProperty
sl@0	2540	* @stable ICU 2.4
sl@0	2541	*/
sl@0	2542	U_STABLE UProperty U_EXPORT2
sl@0	2543	u_getPropertyEnum(const char* alias);
sl@0	2544
sl@0	2545	/**
sl@0	2546	* Return the Unicode name for a given property value, as given in the
sl@0	2547	* Unicode database file PropertyValueAliases.txt.
sl@0	2548	*
sl@0	2549	* Note: Some of the names in PropertyValueAliases.txt can only be
sl@0	2550	* retrieved using UCHAR_GENERAL_CATEGORY_MASK, not
sl@0	2551	* UCHAR_GENERAL_CATEGORY. These include: "C" / "Other", "L" /
sl@0	2552	* "Letter", "LC" / "Cased_Letter", "M" / "Mark", "N" / "Number", "P"
sl@0	2553	* / "Punctuation", "S" / "Symbol", and "Z" / "Separator".
sl@0	2554	*
sl@0	2555	* @param property UProperty selector constant.
sl@0	2556	* Must be UCHAR_BINARY_START<=which<UCHAR_BINARY_LIMIT
sl@0	2557	* or UCHAR_INT_START<=which<UCHAR_INT_LIMIT
sl@0	2558	* or UCHAR_MASK_START<=which<UCHAR_MASK_LIMIT.
sl@0	2559	* If out of range, NULL is returned.
sl@0	2560	*
sl@0	2561	* @param value selector for a value for the given property. If out
sl@0	2562	* of range, NULL is returned. In general, valid values range
sl@0	2563	* from 0 up to some maximum. There are a few exceptions:
sl@0	2564	* (1.) UCHAR_BLOCK values begin at the non-zero value
sl@0	2565	* UBLOCK_BASIC_LATIN. (2.) UCHAR_CANONICAL_COMBINING_CLASS
sl@0	2566	* values are not contiguous and range from 0..240. (3.)
sl@0	2567	* UCHAR_GENERAL_CATEGORY_MASK values are not values of
sl@0	2568	* UCharCategory, but rather mask values produced by
sl@0	2569	* U_GET_GC_MASK(). This allows grouped categories such as
sl@0	2570	* [:L:] to be represented. Mask values range
sl@0	2571	* non-contiguously from 1..U_GC_P_MASK.
sl@0	2572	*
sl@0	2573	* @param nameChoice selector for which name to get. If out of range,
sl@0	2574	* NULL is returned. All values have a long name. Most have
sl@0	2575	* a short name, but some do not. Unicode allows for
sl@0	2576	* additional names; if present these will be returned by
sl@0	2577	* U_LONG_PROPERTY_NAME + i, where i=1, 2,...
sl@0	2578
sl@0	2579	* @return a pointer to the name, or NULL if either the
sl@0	2580	* property or the nameChoice is out of range. If a given
sl@0	2581	* nameChoice returns NULL, then all larger values of
sl@0	2582	* nameChoice will return NULL, with one exception: if NULL is
sl@0	2583	* returned for U_SHORT_PROPERTY_NAME, then
sl@0	2584	* U_LONG_PROPERTY_NAME (and higher) may still return a
sl@0	2585	* non-NULL value. The returned pointer is valid until
sl@0	2586	* u_cleanup() is called.
sl@0	2587	*
sl@0	2588	* @see UProperty
sl@0	2589	* @see UPropertyNameChoice
sl@0	2590	* @stable ICU 2.4
sl@0	2591	*/
sl@0	2592	U_STABLE const char* U_EXPORT2
sl@0	2593	u_getPropertyValueName(UProperty property,
sl@0	2594	int32_t value,
sl@0	2595	UPropertyNameChoice nameChoice);
sl@0	2596
sl@0	2597	/**
sl@0	2598	* Return the property value integer for a given value name, as
sl@0	2599	* specified in the Unicode database file PropertyValueAliases.txt.
sl@0	2600	* Short, long, and any other variants are recognized.
sl@0	2601	*
sl@0	2602	* Note: Some of the names in PropertyValueAliases.txt will only be
sl@0	2603	* recognized with UCHAR_GENERAL_CATEGORY_MASK, not
sl@0	2604	* UCHAR_GENERAL_CATEGORY. These include: "C" / "Other", "L" /
sl@0	2605	* "Letter", "LC" / "Cased_Letter", "M" / "Mark", "N" / "Number", "P"
sl@0	2606	* / "Punctuation", "S" / "Symbol", and "Z" / "Separator".
sl@0	2607	*
sl@0	2608	* @param property UProperty selector constant.
sl@0	2609	* Must be UCHAR_BINARY_START<=which<UCHAR_BINARY_LIMIT
sl@0	2610	* or UCHAR_INT_START<=which<UCHAR_INT_LIMIT
sl@0	2611	* or UCHAR_MASK_START<=which<UCHAR_MASK_LIMIT.
sl@0	2612	* If out of range, UCHAR_INVALID_CODE is returned.
sl@0	2613	*
sl@0	2614	* @param alias the value name to be matched. The name is compared
sl@0	2615	* using "loose matching" as described in
sl@0	2616	* PropertyValueAliases.txt.
sl@0	2617	*
sl@0	2618	* @return a value integer or UCHAR_INVALID_CODE if the given name
sl@0	2619	* does not match any value of the given property, or if the
sl@0	2620	* property is invalid. Note: U CHAR_GENERAL_CATEGORY values
sl@0	2621	* are not values of UCharCategory, but rather mask values
sl@0	2622	* produced by U_GET_GC_MASK(). This allows grouped
sl@0	2623	* categories such as [:L:] to be represented.
sl@0	2624	*
sl@0	2625	* @see UProperty
sl@0	2626	* @stable ICU 2.4
sl@0	2627	*/
sl@0	2628	U_STABLE int32_t U_EXPORT2
sl@0	2629	u_getPropertyValueEnum(UProperty property,
sl@0	2630	const char* alias);
sl@0	2631
sl@0	2632	/**
sl@0	2633	* Determines if the specified character is permissible as the
sl@0	2634	* first character in an identifier according to Unicode
sl@0	2635	* (The Unicode Standard, Version 3.0, chapter 5.16 Identifiers).
sl@0	2636	* True for characters with general categories "L" (letters) and "Nl" (letter numbers).
sl@0	2637	*
sl@0	2638	* Same as java.lang.Character.isUnicodeIdentifierStart().
sl@0	2639	* Same as UCHAR_ID_START
sl@0	2640	*
sl@0	2641	* @param c the code point to be tested
sl@0	2642	* @return TRUE if the code point may start an identifier
sl@0	2643	*
sl@0	2644	* @see UCHAR_ID_START
sl@0	2645	* @see u_isalpha
sl@0	2646	* @see u_isIDPart
sl@0	2647	* @stable ICU 2.0
sl@0	2648	*/
sl@0	2649	U_STABLE UBool U_EXPORT2
sl@0	2650	u_isIDStart(UChar32 c);
sl@0	2651
sl@0	2652	/**
sl@0	2653	* Determines if the specified character is permissible
sl@0	2654	* in an identifier according to Java.
sl@0	2655	* True for characters with general categories "L" (letters),
sl@0	2656	* "Nl" (letter numbers), "Nd" (decimal digits),
sl@0	2657	* "Mc" and "Mn" (combining marks), "Pc" (connecting punctuation), and
sl@0	2658	* u_isIDIgnorable(c).
sl@0	2659	*
sl@0	2660	* Same as java.lang.Character.isUnicodeIdentifierPart().
sl@0	2661	* Almost the same as Unicode's ID_Continue (UCHAR_ID_CONTINUE)
sl@0	2662	* except that Unicode recommends to ignore Cf which is less than
sl@0	2663	* u_isIDIgnorable(c).
sl@0	2664	*
sl@0	2665	* @param c the code point to be tested
sl@0	2666	* @return TRUE if the code point may occur in an identifier according to Java
sl@0	2667	*
sl@0	2668	* @see UCHAR_ID_CONTINUE
sl@0	2669	* @see u_isIDStart
sl@0	2670	* @see u_isIDIgnorable
sl@0	2671	* @stable ICU 2.0
sl@0	2672	*/
sl@0	2673	U_STABLE UBool U_EXPORT2
sl@0	2674	u_isIDPart(UChar32 c);
sl@0	2675
sl@0	2676	/**
sl@0	2677	* Determines if the specified character should be regarded
sl@0	2678	* as an ignorable character in an identifier,
sl@0	2679	* according to Java.
sl@0	2680	* True for characters with general category "Cf" (format controls) as well as
sl@0	2681	* non-whitespace ISO controls
sl@0	2682	* (U+0000..U+0008, U+000E..U+001B, U+007F..U+0084, U+0086..U+009F).
sl@0	2683	*
sl@0	2684	* Same as java.lang.Character.isIdentifierIgnorable()
sl@0	2685	* except that Java also returns TRUE for U+0085 Next Line
sl@0	2686	* (it omits U+0085 from whitespace ISO controls).
sl@0	2687	*
sl@0	2688	* Note that Unicode just recommends to ignore Cf (format controls).
sl@0	2689	*
sl@0	2690	* @param c the code point to be tested
sl@0	2691	* @return TRUE if the code point is ignorable in identifiers according to Java
sl@0	2692	*
sl@0	2693	* @see UCHAR_DEFAULT_IGNORABLE_CODE_POINT
sl@0	2694	* @see u_isIDStart
sl@0	2695	* @see u_isIDPart
sl@0	2696	* @stable ICU 2.0
sl@0	2697	*/
sl@0	2698	U_STABLE UBool U_EXPORT2
sl@0	2699	u_isIDIgnorable(UChar32 c);
sl@0	2700
sl@0	2701	/**
sl@0	2702	* Determines if the specified character is permissible as the
sl@0	2703	* first character in a Java identifier.
sl@0	2704	* In addition to u_isIDStart(c), true for characters with
sl@0	2705	* general categories "Sc" (currency symbols) and "Pc" (connecting punctuation).
sl@0	2706	*
sl@0	2707	* Same as java.lang.Character.isJavaIdentifierStart().
sl@0	2708	*
sl@0	2709	* @param c the code point to be tested
sl@0	2710	* @return TRUE if the code point may start a Java identifier
sl@0	2711	*
sl@0	2712	* @see u_isJavaIDPart
sl@0	2713	* @see u_isalpha
sl@0	2714	* @see u_isIDStart
sl@0	2715	* @stable ICU 2.0
sl@0	2716	*/
sl@0	2717	U_STABLE UBool U_EXPORT2
sl@0	2718	u_isJavaIDStart(UChar32 c);
sl@0	2719
sl@0	2720	/**
sl@0	2721	* Determines if the specified character is permissible
sl@0	2722	* in a Java identifier.
sl@0	2723	* In addition to u_isIDPart(c), true for characters with
sl@0	2724	* general category "Sc" (currency symbols).
sl@0	2725	*
sl@0	2726	* Same as java.lang.Character.isJavaIdentifierPart().
sl@0	2727	*
sl@0	2728	* @param c the code point to be tested
sl@0	2729	* @return TRUE if the code point may occur in a Java identifier
sl@0	2730	*
sl@0	2731	* @see u_isIDIgnorable
sl@0	2732	* @see u_isJavaIDStart
sl@0	2733	* @see u_isalpha
sl@0	2734	* @see u_isdigit
sl@0	2735	* @see u_isIDPart
sl@0	2736	* @stable ICU 2.0
sl@0	2737	*/
sl@0	2738	U_STABLE UBool U_EXPORT2
sl@0	2739	u_isJavaIDPart(UChar32 c);
sl@0	2740
sl@0	2741	/**
sl@0	2742	* The given character is mapped to its lowercase equivalent according to
sl@0	2743	* UnicodeData.txt; if the character has no lowercase equivalent, the character
sl@0	2744	* itself is returned.
sl@0	2745	*
sl@0	2746	* Same as java.lang.Character.toLowerCase().
sl@0	2747	*
sl@0	2748	* This function only returns the simple, single-code point case mapping.
sl@0	2749	* Full case mappings should be used whenever possible because they produce
sl@0	2750	* better results by working on whole strings.
sl@0	2751	* They take into account the string context and the language and can map
sl@0	2752	* to a result string with a different length as appropriate.
sl@0	2753	* Full case mappings are applied by the string case mapping functions,
sl@0	2754	* see ustring.h and the UnicodeString class.
sl@0	2755	* See also the User Guide chapter on C/POSIX migration:
sl@0	2756	* http://icu.sourceforge.net/userguide/posix.html#case_mappings
sl@0	2757	*
sl@0	2758	* @param c the code point to be mapped
sl@0	2759	* @return the Simple_Lowercase_Mapping of the code point, if any;
sl@0	2760	* otherwise the code point itself.
sl@0	2761	* @stable ICU 2.0
sl@0	2762	*/
sl@0	2763	U_STABLE UChar32 U_EXPORT2
sl@0	2764	u_tolower(UChar32 c);
sl@0	2765
sl@0	2766	/**
sl@0	2767	* The given character is mapped to its uppercase equivalent according to UnicodeData.txt;
sl@0	2768	* if the character has no uppercase equivalent, the character itself is
sl@0	2769	* returned.
sl@0	2770	*
sl@0	2771	* Same as java.lang.Character.toUpperCase().
sl@0	2772	*
sl@0	2773	* This function only returns the simple, single-code point case mapping.
sl@0	2774	* Full case mappings should be used whenever possible because they produce
sl@0	2775	* better results by working on whole strings.
sl@0	2776	* They take into account the string context and the language and can map
sl@0	2777	* to a result string with a different length as appropriate.
sl@0	2778	* Full case mappings are applied by the string case mapping functions,
sl@0	2779	* see ustring.h and the UnicodeString class.
sl@0	2780	* See also the User Guide chapter on C/POSIX migration:
sl@0	2781	* http://icu.sourceforge.net/userguide/posix.html#case_mappings
sl@0	2782	*
sl@0	2783	* @param c the code point to be mapped
sl@0	2784	* @return the Simple_Uppercase_Mapping of the code point, if any;
sl@0	2785	* otherwise the code point itself.
sl@0	2786	* @stable ICU 2.0
sl@0	2787	*/
sl@0	2788	U_STABLE UChar32 U_EXPORT2
sl@0	2789	u_toupper(UChar32 c);
sl@0	2790
sl@0	2791	/**
sl@0	2792	* The given character is mapped to its titlecase equivalent
sl@0	2793	* according to UnicodeData.txt;
sl@0	2794	* if none is defined, the character itself is returned.
sl@0	2795	*
sl@0	2796	* Same as java.lang.Character.toTitleCase().
sl@0	2797	*
sl@0	2798	* This function only returns the simple, single-code point case mapping.
sl@0	2799	* Full case mappings should be used whenever possible because they produce
sl@0	2800	* better results by working on whole strings.
sl@0	2801	* They take into account the string context and the language and can map
sl@0	2802	* to a result string with a different length as appropriate.
sl@0	2803	* Full case mappings are applied by the string case mapping functions,
sl@0	2804	* see ustring.h and the UnicodeString class.
sl@0	2805	* See also the User Guide chapter on C/POSIX migration:
sl@0	2806	* http://icu.sourceforge.net/userguide/posix.html#case_mappings
sl@0	2807	*
sl@0	2808	* @param c the code point to be mapped
sl@0	2809	* @return the Simple_Titlecase_Mapping of the code point, if any;
sl@0	2810	* otherwise the code point itself.
sl@0	2811	* @stable ICU 2.0
sl@0	2812	*/
sl@0	2813	U_STABLE UChar32 U_EXPORT2
sl@0	2814	u_totitle(UChar32 c);
sl@0	2815
sl@0	2816	/** Option value for case folding: use default mappings defined in CaseFolding.txt. @stable ICU 2.0 */
sl@0	2817	#define U_FOLD_CASE_DEFAULT 0
sl@0	2818
sl@0	2819	/**
sl@0	2820	* Option value for case folding:
sl@0	2821	*
sl@0	2822	* Use the modified set of mappings provided in CaseFolding.txt to handle dotted I
sl@0	2823	* and dotless i appropriately for Turkic languages (tr, az).
sl@0	2824	*
sl@0	2825	* Before Unicode 3.2, CaseFolding.txt contains mappings marked with 'I' that
sl@0	2826	* are to be included for default mappings and
sl@0	2827	* excluded for the Turkic-specific mappings.
sl@0	2828	*
sl@0	2829	* Unicode 3.2 CaseFolding.txt instead contains mappings marked with 'T' that
sl@0	2830	* are to be excluded for default mappings and
sl@0	2831	* included for the Turkic-specific mappings.
sl@0	2832	*
sl@0	2833	* @stable ICU 2.0
sl@0	2834	*/
sl@0	2835	#define U_FOLD_CASE_EXCLUDE_SPECIAL_I 1
sl@0	2836
sl@0	2837	/**
sl@0	2838	* The given character is mapped to its case folding equivalent according to
sl@0	2839	* UnicodeData.txt and CaseFolding.txt;
sl@0	2840	* if the character has no case folding equivalent, the character
sl@0	2841	* itself is returned.
sl@0	2842	*
sl@0	2843	* This function only returns the simple, single-code point case mapping.
sl@0	2844	* Full case mappings should be used whenever possible because they produce
sl@0	2845	* better results by working on whole strings.
sl@0	2846	* They take into account the string context and the language and can map
sl@0	2847	* to a result string with a different length as appropriate.
sl@0	2848	* Full case mappings are applied by the string case mapping functions,
sl@0	2849	* see ustring.h and the UnicodeString class.
sl@0	2850	* See also the User Guide chapter on C/POSIX migration:
sl@0	2851	* http://icu.sourceforge.net/userguide/posix.html#case_mappings
sl@0	2852	*
sl@0	2853	* @param c the code point to be mapped
sl@0	2854	* @param options Either U_FOLD_CASE_DEFAULT or U_FOLD_CASE_EXCLUDE_SPECIAL_I
sl@0	2855	* @return the Simple_Case_Folding of the code point, if any;
sl@0	2856	* otherwise the code point itself.
sl@0	2857	* @stable ICU 2.0
sl@0	2858	*/
sl@0	2859	U_STABLE UChar32 U_EXPORT2
sl@0	2860	u_foldCase(UChar32 c, uint32_t options);
sl@0	2861
sl@0	2862	/**
sl@0	2863	* Returns the decimal digit value of the code point in the
sl@0	2864	* specified radix.
sl@0	2865	*
sl@0	2866	* If the radix is not in the range <code>2<=radix<=36</code> or if the
sl@0	2867	* value of <code>c</code> is not a valid digit in the specified
sl@0	2868	* radix, <code>-1</code> is returned. A character is a valid digit
sl@0	2869	* if at least one of the following is true:
sl@0	2870	* <ul>
sl@0	2871	* <li>The character has a decimal digit value.
sl@0	2872	* Such characters have the general category "Nd" (decimal digit numbers)
sl@0	2873	* and a Numeric_Type of Decimal.
sl@0	2874	* In this case the value is the character's decimal digit value.</li>
sl@0	2875	* <li>The character is one of the uppercase Latin letters
sl@0	2876	* <code>'A'</code> through <code>'Z'</code>.
sl@0	2877	* In this case the value is <code>c-'A'+10</code>.</li>
sl@0	2878	* <li>The character is one of the lowercase Latin letters
sl@0	2879	* <code>'a'</code> through <code>'z'</code>.
sl@0	2880	* In this case the value is <code>ch-'a'+10</code>.</li>
sl@0	2881	* <li>Latin letters from both the ASCII range (0061..007A, 0041..005A)
sl@0	2882	* as well as from the Fullwidth ASCII range (FF41..FF5A, FF21..FF3A)
sl@0	2883	* are recognized.</li>
sl@0	2884	* </ul>
sl@0	2885	*
sl@0	2886	* Same as java.lang.Character.digit().
sl@0	2887	*
sl@0	2888	* @param ch the code point to be tested.
sl@0	2889	* @param radix the radix.
sl@0	2890	* @return the numeric value represented by the character in the
sl@0	2891	* specified radix,
sl@0	2892	* or -1 if there is no value or if the value exceeds the radix.
sl@0	2893	*
sl@0	2894	* @see UCHAR_NUMERIC_TYPE
sl@0	2895	* @see u_forDigit
sl@0	2896	* @see u_charDigitValue
sl@0	2897	* @see u_isdigit
sl@0	2898	* @stable ICU 2.0
sl@0	2899	*/
sl@0	2900	U_STABLE int32_t U_EXPORT2
sl@0	2901	u_digit(UChar32 ch, int8_t radix);
sl@0	2902
sl@0	2903	/**
sl@0	2904	* Determines the character representation for a specific digit in
sl@0	2905	* the specified radix. If the value of <code>radix</code> is not a
sl@0	2906	* valid radix, or the value of <code>digit</code> is not a valid
sl@0	2907	* digit in the specified radix, the null character
sl@0	2908	* (<code>U+0000</code>) is returned.
sl@0	2909	* <p>
sl@0	2910	* The <code>radix</code> argument is valid if it is greater than or
sl@0	2911	* equal to 2 and less than or equal to 36.
sl@0	2912	* The <code>digit</code> argument is valid if
sl@0	2913	* <code>0 <= digit < radix</code>.
sl@0	2914	* <p>
sl@0	2915	* If the digit is less than 10, then
sl@0	2916	* <code>'0' + digit</code> is returned. Otherwise, the value
sl@0	2917	* <code>'a' + digit - 10</code> is returned.
sl@0	2918	*
sl@0	2919	* Same as java.lang.Character.forDigit().
sl@0	2920	*
sl@0	2921	* @param digit the number to convert to a character.
sl@0	2922	* @param radix the radix.
sl@0	2923	* @return the <code>char</code> representation of the specified digit
sl@0	2924	* in the specified radix.
sl@0	2925	*
sl@0	2926	* @see u_digit
sl@0	2927	* @see u_charDigitValue
sl@0	2928	* @see u_isdigit
sl@0	2929	* @stable ICU 2.0
sl@0	2930	*/
sl@0	2931	U_STABLE UChar32 U_EXPORT2
sl@0	2932	u_forDigit(int32_t digit, int8_t radix);
sl@0	2933
sl@0	2934	/**
sl@0	2935	* Get the "age" of the code point.
sl@0	2936	* The "age" is the Unicode version when the code point was first
sl@0	2937	* designated (as a non-character or for Private Use)
sl@0	2938	* or assigned a character.
sl@0	2939	* This can be useful to avoid emitting code points to receiving
sl@0	2940	* processes that do not accept newer characters.
sl@0	2941	* The data is from the UCD file DerivedAge.txt.
sl@0	2942	*
sl@0	2943	* @param c The code point.
sl@0	2944	* @param versionArray The Unicode version number array, to be filled in.
sl@0	2945	*
sl@0	2946	* @stable ICU 2.1
sl@0	2947	*/
sl@0	2948	U_STABLE void U_EXPORT2
sl@0	2949	u_charAge(UChar32 c, UVersionInfo versionArray);
sl@0	2950
sl@0	2951	/**
sl@0	2952	* Gets the Unicode version information.
sl@0	2953	* The version array is filled in with the version information
sl@0	2954	* for the Unicode standard that is currently used by ICU.
sl@0	2955	* For example, Unicode version 3.1.1 is represented as an array with
sl@0	2956	* the values { 3, 1, 1, 0 }.
sl@0	2957	*
sl@0	2958	* @param versionArray an output array that will be filled in with
sl@0	2959	* the Unicode version number
sl@0	2960	* @stable ICU 2.0
sl@0	2961	*/
sl@0	2962	U_STABLE void U_EXPORT2
sl@0	2963	u_getUnicodeVersion(UVersionInfo versionArray);
sl@0	2964
sl@0	2965	/**
sl@0	2966	* Get the FC_NFKC_Closure property string for a character.
sl@0	2967	* See Unicode Standard Annex #15 for details, search for "FC_NFKC_Closure"
sl@0	2968	* or for "FNC": http://www.unicode.org/reports/tr15/
sl@0	2969	*
sl@0	2970	* @param c The character (code point) for which to get the FC_NFKC_Closure string.
sl@0	2971	* It must be <code>0<=c<=0x10ffff</code>.
sl@0	2972	* @param dest Destination address for copying the string.
sl@0	2973	* The string will be zero-terminated if possible.
sl@0	2974	* If there is no FC_NFKC_Closure string,
sl@0	2975	* then the buffer will be set to the empty string.
sl@0	2976	* @param destCapacity <code>==sizeof(dest)</code>
sl@0	2977	* @param pErrorCode Pointer to a UErrorCode variable.
sl@0	2978	* @return The length of the string, or 0 if there is no FC_NFKC_Closure string for this character.
sl@0	2979	* If the destCapacity is less than or equal to the length, then the buffer
sl@0	2980	* contains the truncated name and the returned length indicates the full
sl@0	2981	* length of the name.
sl@0	2982	* The length does not include the zero-termination.
sl@0	2983	*
sl@0	2984	* @stable ICU 2.2
sl@0	2985	*/
sl@0	2986	U_STABLE int32_t U_EXPORT2
sl@0	2987	u_getFC_NFKC_Closure(UChar32 c, UChar dest, int32_t destCapacity, UErrorCode pErrorCode);
sl@0	2988
sl@0	2989	U_CDECL_END
sl@0	2990
sl@0	2991	#endif /_UCHAR/
sl@0	2992	/eof/

author	sl
	Tue, 10 Jun 2014 14:32:02 +0200
changeset 1	260cb5ec6c19
permissions	-rw-r--r--