diff options
| author | The Android Open Source Project <initial-contribution@android.com> | 2009-03-03 18:28:41 -0800 |
|---|---|---|
| committer | The Android Open Source Project <initial-contribution@android.com> | 2009-03-03 18:28:41 -0800 |
| commit | 648161bb0edfc3d43db63caed5cc5213bc6cb78f (patch) | |
| tree | 4b825dc642cb6eb9a060e54bf8d69288fbee4904 /WebKit/mac/icu/unicode | |
| parent | a65af38181ac7d34544586bdb5cd004de93897ad (diff) | |
| download | external_webkit-648161bb0edfc3d43db63caed5cc5213bc6cb78f.zip external_webkit-648161bb0edfc3d43db63caed5cc5213bc6cb78f.tar.gz external_webkit-648161bb0edfc3d43db63caed5cc5213bc6cb78f.tar.bz2 | |
auto import from //depot/cupcake/@135843
Diffstat (limited to 'WebKit/mac/icu/unicode')
| -rw-r--r-- | WebKit/mac/icu/unicode/parseerr.h | 88 | ||||
| -rw-r--r-- | WebKit/mac/icu/unicode/platform.h | 267 | ||||
| -rw-r--r-- | WebKit/mac/icu/unicode/putil.h | 180 | ||||
| -rw-r--r-- | WebKit/mac/icu/unicode/uchar.h | 2798 | ||||
| -rw-r--r-- | WebKit/mac/icu/unicode/uconfig.h | 186 | ||||
| -rw-r--r-- | WebKit/mac/icu/unicode/uidna.h | 310 | ||||
| -rw-r--r-- | WebKit/mac/icu/unicode/uiter.h | 707 | ||||
| -rw-r--r-- | WebKit/mac/icu/unicode/umachine.h | 371 | ||||
| -rw-r--r-- | WebKit/mac/icu/unicode/unorm.h | 575 | ||||
| -rw-r--r-- | WebKit/mac/icu/unicode/urename.h | 1468 | ||||
| -rw-r--r-- | WebKit/mac/icu/unicode/uscript.h | 148 | ||||
| -rw-r--r-- | WebKit/mac/icu/unicode/ustring.h | 1320 | ||||
| -rw-r--r-- | WebKit/mac/icu/unicode/utf.h | 221 | ||||
| -rw-r--r-- | WebKit/mac/icu/unicode/utf16.h | 605 | ||||
| -rw-r--r-- | WebKit/mac/icu/unicode/utf8.h | 627 | ||||
| -rw-r--r-- | WebKit/mac/icu/unicode/utf_old.h | 1 | ||||
| -rw-r--r-- | WebKit/mac/icu/unicode/utypes.h | 745 | ||||
| -rw-r--r-- | WebKit/mac/icu/unicode/uversion.h | 216 |
18 files changed, 0 insertions, 10833 deletions
diff --git a/WebKit/mac/icu/unicode/parseerr.h b/WebKit/mac/icu/unicode/parseerr.h deleted file mode 100644 index d1ba394..0000000 --- a/WebKit/mac/icu/unicode/parseerr.h +++ /dev/null @@ -1,88 +0,0 @@ -/* -********************************************************************** -* Copyright (C) 1999-2004, International Business Machines -* Corporation and others. All Rights Reserved. -********************************************************************** -* Date Name Description -* 03/14/00 aliu Creation. -* 06/27/00 aliu Change from C++ class to C struct -********************************************************************** -*/ -#ifndef PARSEERR_H -#define PARSEERR_H - -#include "unicode/utypes.h" - - -/** - * The capacity of the context strings in UParseError. - * @stable ICU 2.0 - */ -enum { U_PARSE_CONTEXT_LEN = 16 }; - -/** - * A UParseError struct is used to returned detailed information about - * parsing errors. It is used by ICU parsing engines that parse long - * rules, patterns, or programs, where the text being parsed is long - * enough that more information than a UErrorCode is needed to - * localize the error. - * - * <p>The line, offset, and context fields are optional; parsing - * engines may choose not to use to use them. - * - * <p>The preContext and postContext strings include some part of the - * context surrounding the error. If the source text is "let for=7" - * and "for" is the error (e.g., because it is a reserved word), then - * some examples of what a parser might produce are the following: - * - * <pre> - * preContext postContext - * "" "" The parser does not support context - * "let " "=7" Pre- and post-context only - * "let " "for=7" Pre- and post-context and error text - * "" "for" Error text only - * </pre> - * - * <p>Examples of engines which use UParseError (or may use it in the - * future) are Transliterator, RuleBasedBreakIterator, and - * RegexPattern. - * - * @stable ICU 2.0 - */ -typedef struct UParseError { - - /** - * The line on which the error occured. If the parser uses this - * field, it sets it to the line number of the source text line on - * which the error appears, which will be be a value >= 1. If the - * parse does not support line numbers, the value will be <= 0. - * @stable ICU 2.0 - */ - int32_t line; - - /** - * The character offset to the error. If the line field is >= 1, - * then this is the offset from the start of the line. Otherwise, - * this is the offset from the start of the text. If the parser - * does not support this field, it will have a value < 0. - * @stable ICU 2.0 - */ - int32_t offset; - - /** - * Textual context before the error. Null-terminated. The empty - * string if not supported by parser. - * @stable ICU 2.0 - */ - UChar preContext[U_PARSE_CONTEXT_LEN]; - - /** - * The error itself and/or textual context after the error. - * Null-terminated. The empty string if not supported by parser. - * @stable ICU 2.0 - */ - UChar postContext[U_PARSE_CONTEXT_LEN]; - -} UParseError; - -#endif diff --git a/WebKit/mac/icu/unicode/platform.h b/WebKit/mac/icu/unicode/platform.h deleted file mode 100644 index 9595a26..0000000 --- a/WebKit/mac/icu/unicode/platform.h +++ /dev/null @@ -1,267 +0,0 @@ -/* -****************************************************************************** -* -* Copyright (C) 1997-2004, International Business Machines -* Corporation and others. All Rights Reserved. -* -****************************************************************************** -* -* FILE NAME : platform.h -* -* Date Name Description -* 05/13/98 nos Creation (content moved here from ptypes.h). -* 03/02/99 stephen Added AS400 support. -* 03/30/99 stephen Added Linux support. -* 04/13/99 stephen Reworked for autoconf. -****************************************************************************** -*/ - -/* Define the platform we're on. */ -#ifndef U_DARWIN -#define U_DARWIN -#endif - -/* Define whether inttypes.h is available */ -#ifndef U_HAVE_INTTYPES_H -#define U_HAVE_INTTYPES_H 1 -#endif - -/* - * Define what support for C++ streams is available. - * If U_IOSTREAM_SOURCE is set to 199711, then <iostream> is available - * (1997711 is the date the ISO/IEC C++ FDIS was published), and then - * one should qualify streams using the std namespace in ICU header - * files. - * If U_IOSTREAM_SOURCE is set to 198506, then <iostream.h> is - * available instead (198506 is the date when Stroustrup published - * "An Extensible I/O Facility for C++" at the summer USENIX conference). - * If U_IOSTREAM_SOURCE is 0, then C++ streams are not available and - * support for them will be silently suppressed in ICU. - * - */ - -#ifndef U_IOSTREAM_SOURCE -#define U_IOSTREAM_SOURCE 199711 -#endif - -/* Determines whether specific types are available */ -#ifndef U_HAVE_INT8_T -#define U_HAVE_INT8_T 1 -#endif - -#ifndef U_HAVE_UINT8_T -#define U_HAVE_UINT8_T 0 -#endif - -#ifndef U_HAVE_INT16_T -#define U_HAVE_INT16_T 1 -#endif - -#ifndef U_HAVE_UINT16_T -#define U_HAVE_UINT16_T 0 -#endif - -#ifndef U_HAVE_INT32_T -#define U_HAVE_INT32_T 1 -#endif - -#ifndef U_HAVE_UINT32_T -#define U_HAVE_UINT32_T 0 -#endif - -#ifndef U_HAVE_INT64_T -#define U_HAVE_INT64_T 1 -#endif - -#ifndef U_HAVE_UINT64_T -#define U_HAVE_UINT64_T 0 -#endif - -/*===========================================================================*/ -/* Generic data types */ -/*===========================================================================*/ - -#include <sys/types.h> - -/* If your platform does not have the <inttypes.h> header, you may - need to edit the typedefs below. */ -#if U_HAVE_INTTYPES_H - -/* autoconf 2.13 sometimes can't properly find the data types in <inttypes.h> */ -/* os/390 needs <inttypes.h>, but it doesn't have int8_t, and it sometimes */ -/* doesn't have uint8_t depending on the OS version. */ -/* So we have this work around. */ -#ifdef OS390 -/* The features header is needed to get (u)int64_t sometimes. */ -#include <features.h> -#if ! U_HAVE_INT8_T -typedef signed char int8_t; -#endif -#if !defined(__uint8_t) -#define __uint8_t 1 -typedef unsigned char uint8_t; -#endif -#endif /* OS390 */ - -#include <inttypes.h> - -#else /* U_HAVE_INTTYPES_H */ - -#if ! U_HAVE_INT8_T -typedef signed char int8_t; -#endif - -#if ! U_HAVE_UINT8_T -typedef unsigned char uint8_t; -#endif - -#if ! U_HAVE_INT16_T -typedef signed short int16_t; -#endif - -#if ! U_HAVE_UINT16_T -typedef unsigned short uint16_t; -#endif - -#if ! U_HAVE_INT32_T -typedef signed int int32_t; -#endif - -#if ! U_HAVE_UINT32_T -typedef unsigned int uint32_t; -#endif - -#if ! U_HAVE_INT64_T - typedef signed long long int64_t; -/* else we may not have a 64-bit type */ -#endif - -#if ! U_HAVE_UINT64_T - typedef unsigned long long uint64_t; -/* else we may not have a 64-bit type */ -#endif - -#endif - -/*===========================================================================*/ -/* Compiler and environment features */ -/*===========================================================================*/ - -/* Define whether namespace is supported */ -#ifndef U_HAVE_NAMESPACE -#define U_HAVE_NAMESPACE 1 -#endif - -/* Determines the endianness of the platform - It's done this way in case multiple architectures are being built at once. - For example, Darwin supports fat binaries, which can be both PPC and x86 based. */ -#if defined(BYTE_ORDER) && defined(BIG_ENDIAN) -#define U_IS_BIG_ENDIAN (BYTE_ORDER == BIG_ENDIAN) -#else -#define U_IS_BIG_ENDIAN 1 -#endif - -/* 1 or 0 to enable or disable threads. If undefined, default is: enable threads. */ -#define ICU_USE_THREADS 1 - -#ifndef U_DEBUG -#define U_DEBUG 0 -#endif - -#ifndef U_RELEASE -#define U_RELEASE 1 -#endif - -/* Determine whether to disable renaming or not. This overrides the - setting in umachine.h which is for all platforms. */ -#ifndef U_DISABLE_RENAMING -#define U_DISABLE_RENAMING 1 -#endif - -/* Determine whether to override new and delete. */ -#ifndef U_OVERRIDE_CXX_ALLOCATION -#define U_OVERRIDE_CXX_ALLOCATION 1 -#endif -/* Determine whether to override placement new and delete for STL. */ -#ifndef U_HAVE_PLACEMENT_NEW -#define U_HAVE_PLACEMENT_NEW 1 -#endif - -/* Determine whether to enable tracing. */ -#ifndef U_ENABLE_TRACING -#define U_ENABLE_TRACING 1 -#endif - -/* Define the library suffix in a C syntax. */ -#define U_HAVE_LIB_SUFFIX 0 -#define U_LIB_SUFFIX_C_NAME -#define U_LIB_SUFFIX_C_NAME_STRING "" - -/*===========================================================================*/ -/* Character data types */ -/*===========================================================================*/ - -#if defined(OS390) || defined(OS400) -# define U_CHARSET_FAMILY 1 -#endif - -/*===========================================================================*/ -/* Information about wchar support */ -/*===========================================================================*/ - -#define U_HAVE_WCHAR_H 1 -#define U_SIZEOF_WCHAR_T 4 - -#define U_HAVE_WCSCPY 1 - -/*===========================================================================*/ -/* Information about POSIX support */ -/*===========================================================================*/ - -#define U_HAVE_NL_LANGINFO 1 -#define U_HAVE_NL_LANGINFO_CODESET 1 -#define U_NL_LANGINFO_CODESET CODESET - -#if 1 -#define U_TZSET tzset -#endif -#if 0 -#define U_TIMEZONE -#endif -#if 1 -#define U_TZNAME tzname -#endif - -#define U_HAVE_MMAP 1 -#define U_HAVE_POPEN 1 - -/*===========================================================================*/ -/* Symbol import-export control */ -/*===========================================================================*/ - -#define U_EXPORT -/* U_CALLCONV is releated to U_EXPORT2 */ -#define U_EXPORT2 - -/* cygwin needs to export/import data */ -#ifdef U_CYGWIN -#define U_IMPORT __declspec(dllimport) -#else -#define U_IMPORT -#endif - -/*===========================================================================*/ -/* Code alignment and C function inlining */ -/*===========================================================================*/ - -#ifndef U_INLINE -#define U_INLINE inline -#endif - -#define U_ALIGN_CODE(n) - -/*===========================================================================*/ -/* Programs used by ICU code */ -/*===========================================================================*/ - -#define U_MAKE "/usr/bin/gnumake" diff --git a/WebKit/mac/icu/unicode/putil.h b/WebKit/mac/icu/unicode/putil.h deleted file mode 100644 index 685df53..0000000 --- a/WebKit/mac/icu/unicode/putil.h +++ /dev/null @@ -1,180 +0,0 @@ -/* -****************************************************************************** -* -* Copyright (C) 1997-2004, International Business Machines -* Corporation and others. All Rights Reserved. -* -****************************************************************************** -* -* FILE NAME : putil.h -* -* Date Name Description -* 05/14/98 nos Creation (content moved here from utypes.h). -* 06/17/99 erm Added IEEE_754 -* 07/22/98 stephen Added IEEEremainder, max, min, trunc -* 08/13/98 stephen Added isNegativeInfinity, isPositiveInfinity -* 08/24/98 stephen Added longBitsFromDouble -* 03/02/99 stephen Removed openFile(). Added AS400 support. -* 04/15/99 stephen Converted to C -* 11/15/99 helena Integrated S/390 changes for IEEE support. -* 01/11/00 helena Added u_getVersion. -****************************************************************************** -*/ - -#ifndef PUTIL_H -#define PUTIL_H - -#include "unicode/utypes.h" - -/* Define this to 1 if your platform supports IEEE 754 floating point, - to 0 if it does not. */ -#ifndef IEEE_754 -# define IEEE_754 1 -#endif - -/*==========================================================================*/ -/* Platform utilities */ -/*==========================================================================*/ - -/** - * Platform utilities isolates the platform dependencies of the - * libarary. For each platform which this code is ported to, these - * functions may have to be re-implemented. - */ - -/** - * Return the ICU data directory. - * The data directory is where common format ICU data files (.dat files) - * are loaded from. Note that normal use of the built-in ICU - * facilities does not require loading of an external data file; - * unless you are adding custom data to ICU, the data directory - * does not need to be set. - * - * The data directory is determined as follows: - * If u_setDataDirectory() has been called, that is it, otherwise - * if the ICU_DATA environment variable is set, use that, otherwise - * If a data directory was specifed at ICU build time - * (#define ICU_DATA_DIR "path"), use that, - * otherwise no data directory is available. - * - * @return the data directory, or an empty string ("") if no data directory has - * been specified. - * - * @stable ICU 2.0 - */ -U_STABLE const char* U_EXPORT2 u_getDataDirectory(void); - -/** - * Set the ICU data directory. - * The data directory is where common format ICU data files (.dat files) - * are loaded from. Note that normal use of the built-in ICU - * facilities does not require loading of an external data file; - * unless you are adding custom data to ICU, the data directory - * does not need to be set. - * - * This function should be called at most once in a process, before the - * first ICU operation (e.g., u_init()) that will require the loading of an - * ICU data file. - * This function is not thread-safe. Use it before calling ICU APIs from - * multiple threads. - * - * @param directory The directory to be set. - * - * @see u_init - * @stable ICU 2.0 - */ -U_STABLE void U_EXPORT2 u_setDataDirectory(const char *directory); - -/** - * Please use ucnv_getDefaultName() instead. - * Return the default codepage for this platform and locale. - * This function can call setlocale() on Unix platforms. Please read the - * platform documentation on setlocale() before calling this function. - * @return the default codepage for this platform - * @internal - */ -U_INTERNAL const char* U_EXPORT2 uprv_getDefaultCodepage(void); - -/** - * Please use uloc_getDefault() instead. - * Return the default locale ID string by querying ths system, or - * zero if one cannot be found. - * This function can call setlocale() on Unix platforms. Please read the - * platform documentation on setlocale() before calling this function. - * @return the default locale ID string - * @internal - */ -U_INTERNAL const char* U_EXPORT2 uprv_getDefaultLocaleID(void); - -/** - * Filesystem file and path separator characters. - * Example: '/' and ':' on Unix, '\\' and ';' on Windows. - * @stable ICU 2.0 - */ -#ifdef XP_MAC -# define U_FILE_SEP_CHAR ':' -# define U_FILE_ALT_SEP_CHAR ':' -# define U_PATH_SEP_CHAR ';' -# define U_FILE_SEP_STRING ":" -# define U_FILE_ALT_SEP_STRING ":" -# define U_PATH_SEP_STRING ";" -#elif defined(WIN32) || defined(OS2) -# define U_FILE_SEP_CHAR '\\' -# define U_FILE_ALT_SEP_CHAR '/' -# define U_PATH_SEP_CHAR ';' -# define U_FILE_SEP_STRING "\\" -# define U_FILE_ALT_SEP_STRING "/" -# define U_PATH_SEP_STRING ";" -#else -# define U_FILE_SEP_CHAR '/' -# define U_FILE_ALT_SEP_CHAR '/' -# define U_PATH_SEP_CHAR ':' -# define U_FILE_SEP_STRING "/" -# define U_FILE_ALT_SEP_STRING "/" -# define U_PATH_SEP_STRING ":" -#endif - -/** - * Convert char characters to UChar characters. - * This utility function is useful only for "invariant characters" - * that are encoded in the platform default encoding. - * They are a small, constant subset of the encoding and include - * just the latin letters, digits, and some punctuation. - * For details, see U_CHARSET_FAMILY. - * - * @param cs Input string, points to <code>length</code> - * character bytes from a subset of the platform encoding. - * @param us Output string, points to memory for <code>length</code> - * Unicode characters. - * @param length The number of characters to convert; this may - * include the terminating <code>NUL</code>. - * - * @see U_CHARSET_FAMILY - * @stable ICU 2.0 - */ -U_STABLE void U_EXPORT2 -u_charsToUChars(const char *cs, UChar *us, int32_t length); - -/** - * Convert UChar characters to char characters. - * This utility function is useful only for "invariant characters" - * that can be encoded in the platform default encoding. - * They are a small, constant subset of the encoding and include - * just the latin letters, digits, and some punctuation. - * For details, see U_CHARSET_FAMILY. - * - * @param us Input string, points to <code>length</code> - * Unicode characters that can be encoded with the - * codepage-invariant subset of the platform encoding. - * @param cs Output string, points to memory for <code>length</code> - * character bytes. - * @param length The number of characters to convert; this may - * include the terminating <code>NUL</code>. - * - * @see U_CHARSET_FAMILY - * @stable ICU 2.0 - */ -U_STABLE void U_EXPORT2 -u_UCharsToChars(const UChar *us, char *cs, int32_t length); - -#endif diff --git a/WebKit/mac/icu/unicode/uchar.h b/WebKit/mac/icu/unicode/uchar.h deleted file mode 100644 index 7fd490c..0000000 --- a/WebKit/mac/icu/unicode/uchar.h +++ /dev/null @@ -1,2798 +0,0 @@ -/* -********************************************************************** -* Copyright (C) 1997-2004, International Business Machines -* Corporation and others. All Rights Reserved. -********************************************************************** -* -* File UCHAR.H -* -* Modification History: -* -* Date Name Description -* 04/02/97 aliu Creation. -* 03/29/99 helena Updated for C APIs. -* 4/15/99 Madhu Updated for C Implementation and Javadoc -* 5/20/99 Madhu Added the function u_getVersion() -* 8/19/1999 srl Upgraded scripts to Unicode 3.0 -* 8/27/1999 schererm UCharDirection constants: U_... -* 11/11/1999 weiv added u_isalnum(), cleaned comments -* 01/11/2000 helena Renamed u_getVersion to u_getUnicodeVersion(). -****************************************************************************** -*/ - -#ifndef UCHAR_H -#define UCHAR_H - -#include "unicode/utypes.h" - -U_CDECL_BEGIN - -/*==========================================================================*/ -/* Unicode version number */ -/*==========================================================================*/ -/** - * Unicode version number, default for the current ICU version. - * The actual Unicode Character Database (UCD) data is stored in uprops.dat - * and may be generated from UCD files from a different Unicode version. - * Call u_getUnicodeVersion to get the actual Unicode version of the data. - * - * @see u_getUnicodeVersion - * @stable ICU 2.0 - */ -#define U_UNICODE_VERSION "4.0.1" - -/** - * \file - * \brief C API: Unicode Properties - * - * This C API provides low-level access to the Unicode Character Database. - * In addition to raw property values, some convenience functions calculate - * derived properties, for example for Java-style programming. - * - * Unicode assigns each code point (not just assigned character) values for - * many properties. - * Most of them are simple boolean flags, or constants from a small enumerated list. - * For some properties, values are strings or other relatively more complex types. - * - * For more information see - * "About the Unicode Character Database" (http://www.unicode.org/ucd/) - * and the ICU User Guide chapter on Properties (http://oss.software.ibm.com/icu/userguide/properties.html). - * - * Many functions are designed to match java.lang.Character functions. - * See the individual function documentation, - * and see the JDK 1.4.1 java.lang.Character documentation - * at http://java.sun.com/j2se/1.4.1/docs/api/java/lang/Character.html - * - * There are also functions that provide easy migration from C/POSIX functions - * like isblank(). Their use is generally discouraged because the C/POSIX - * standards do not define their semantics beyond the ASCII range, which means - * that different implementations exhibit very different behavior. - * Instead, Unicode properties should be used directly. - * - * There are also only a few, broad C/POSIX character classes, and they tend - * to be used for conflicting purposes. For example, the "isalpha()" class - * is sometimes used to determine word boundaries, while a more sophisticated - * approach would at least distinguish initial letters from continuation - * characters (the latter including combining marks). - * (In ICU, BreakIterator is the most sophisticated API for word boundaries.) - * Another example: There is no "istitle()" class for titlecase characters. - * - * A summary of the behavior of some C/POSIX character classification implementations - * for Unicode is available at http://oss.software.ibm.com/cvs/icu/~checkout~/icuhtml/design/posix_classes.html - * - * <strong>Important</strong>: - * The behavior of the ICU C/POSIX-style character classification - * functions is subject to change according to discussion of the above summary. - * - * Note: There are several ICU whitespace functions. - * Comparison: - * - u_isUWhiteSpace=UCHAR_WHITE_SPACE: Unicode White_Space property; - * most of general categories "Z" (separators) + most whitespace ISO controls - * (including no-break spaces, but excluding IS1..IS4 and ZWSP) - * - u_isWhitespace: Java isWhitespace; Z + whitespace ISO controls but excluding no-break spaces - * - u_isJavaSpaceChar: Java isSpaceChar; just Z (including no-break spaces) - * - u_isspace: Z + whitespace ISO controls (including no-break spaces) - * - u_isblank: "horizontal spaces" = TAB + Zs - ZWSP - */ - -/** - * Constants. - */ - -/** The lowest Unicode code point value. Code points are non-negative. @stable ICU 2.0 */ -#define UCHAR_MIN_VALUE 0 - -/** - * The highest Unicode code point value (scalar value) according to - * The Unicode Standard. This is a 21-bit value (20.1 bits, rounded up). - * For a single character, UChar32 is a simple type that can hold any code point value. - * - * @see UChar32 - * @stable ICU 2.0 - */ -#define UCHAR_MAX_VALUE 0x10ffff - -/** - * Get a single-bit bit set (a flag) from a bit number 0..31. - * @stable ICU 2.1 - */ -#define U_MASK(x) ((uint32_t)1<<(x)) - -/* - * !! Note: Several comments in this file are machine-read by the - * genpname tool. These comments describe the correspondence between - * icu enum constants and UCD entities. Do not delete them. Update - * these comments as needed. - * - * Any comment of the form "/ *[name]* /" (spaces added) is such - * a comment. - * - * The U_JG_* and U_GC_*_MASK constants are matched by their symbolic - * name, which must match PropertyValueAliases.txt. - */ - -/** - * Selection constants for Unicode properties. - * These constants are used in functions like u_hasBinaryProperty to select - * one of the Unicode properties. - * - * The properties APIs are intended to reflect Unicode properties as defined - * in the Unicode Character Database (UCD) and Unicode Technical Reports (UTR). - * For details about the properties see http://www.unicode.org/ucd/ . - * For names of Unicode properties see the UCD file PropertyAliases.txt. - * - * Important: If ICU is built with UCD files from Unicode versions below, e.g., 3.2, - * then properties marked with "new in Unicode 3.2" are not or not fully available. - * Check u_getUnicodeVersion to be sure. - * - * @see u_hasBinaryProperty - * @see u_getIntPropertyValue - * @see u_getUnicodeVersion - * @stable ICU 2.1 - */ -typedef enum UProperty { - /* See note !!. Comments of the form "Binary property Dash", - "Enumerated property Script", "Double property Numeric_Value", - and "String property Age" are read by genpname. */ - - /* Note: Place UCHAR_ALPHABETIC before UCHAR_BINARY_START so that - debuggers display UCHAR_ALPHABETIC as the symbolic name for 0, - rather than UCHAR_BINARY_START. Likewise for other *_START - identifiers. */ - - /** Binary property Alphabetic. Same as u_isUAlphabetic, different from u_isalpha. - Lu+Ll+Lt+Lm+Lo+Nl+Other_Alphabetic @stable ICU 2.1 */ - UCHAR_ALPHABETIC=0, - /** First constant for binary Unicode properties. @stable ICU 2.1 */ - UCHAR_BINARY_START=UCHAR_ALPHABETIC, - /** Binary property ASCII_Hex_Digit. 0-9 A-F a-f @stable ICU 2.1 */ - UCHAR_ASCII_HEX_DIGIT, - /** Binary property Bidi_Control. - Format controls which have specific functions - in the Bidi Algorithm. @stable ICU 2.1 */ - UCHAR_BIDI_CONTROL, - /** Binary property Bidi_Mirrored. - Characters that may change display in RTL text. - Same as u_isMirrored. - See Bidi Algorithm, UTR 9. @stable ICU 2.1 */ - UCHAR_BIDI_MIRRORED, - /** Binary property Dash. Variations of dashes. @stable ICU 2.1 */ - UCHAR_DASH, - /** Binary property Default_Ignorable_Code_Point (new in Unicode 3.2). - Ignorable in most processing. - <2060..206F, FFF0..FFFB, E0000..E0FFF>+Other_Default_Ignorable_Code_Point+(Cf+Cc+Cs-White_Space) @stable ICU 2.1 */ - UCHAR_DEFAULT_IGNORABLE_CODE_POINT, - /** Binary property Deprecated (new in Unicode 3.2). - The usage of deprecated characters is strongly discouraged. @stable ICU 2.1 */ - UCHAR_DEPRECATED, - /** Binary property Diacritic. Characters that linguistically modify - the meaning of another character to which they apply. @stable ICU 2.1 */ - UCHAR_DIACRITIC, - /** Binary property Extender. - Extend the value or shape of a preceding alphabetic character, - e.g., length and iteration marks. @stable ICU 2.1 */ - UCHAR_EXTENDER, - /** Binary property Full_Composition_Exclusion. - CompositionExclusions.txt+Singleton Decompositions+ - Non-Starter Decompositions. @stable ICU 2.1 */ - UCHAR_FULL_COMPOSITION_EXCLUSION, - /** Binary property Grapheme_Base (new in Unicode 3.2). - For programmatic determination of grapheme cluster boundaries. - [0..10FFFF]-Cc-Cf-Cs-Co-Cn-Zl-Zp-Grapheme_Link-Grapheme_Extend-CGJ @stable ICU 2.1 */ - UCHAR_GRAPHEME_BASE, - /** Binary property Grapheme_Extend (new in Unicode 3.2). - For programmatic determination of grapheme cluster boundaries. - Me+Mn+Mc+Other_Grapheme_Extend-Grapheme_Link-CGJ @stable ICU 2.1 */ - UCHAR_GRAPHEME_EXTEND, - /** Binary property Grapheme_Link (new in Unicode 3.2). - For programmatic determination of grapheme cluster boundaries. @stable ICU 2.1 */ - UCHAR_GRAPHEME_LINK, - /** Binary property Hex_Digit. - Characters commonly used for hexadecimal numbers. @stable ICU 2.1 */ - UCHAR_HEX_DIGIT, - /** Binary property Hyphen. Dashes used to mark connections - between pieces of words, plus the Katakana middle dot. @stable ICU 2.1 */ - UCHAR_HYPHEN, - /** Binary property ID_Continue. - Characters that can continue an identifier. - DerivedCoreProperties.txt also says "NOTE: Cf characters should be filtered out." - ID_Start+Mn+Mc+Nd+Pc @stable ICU 2.1 */ - UCHAR_ID_CONTINUE, - /** Binary property ID_Start. - Characters that can start an identifier. - Lu+Ll+Lt+Lm+Lo+Nl @stable ICU 2.1 */ - UCHAR_ID_START, - /** Binary property Ideographic. - CJKV ideographs. @stable ICU 2.1 */ - UCHAR_IDEOGRAPHIC, - /** Binary property IDS_Binary_Operator (new in Unicode 3.2). - For programmatic determination of - Ideographic Description Sequences. @stable ICU 2.1 */ - UCHAR_IDS_BINARY_OPERATOR, - /** Binary property IDS_Trinary_Operator (new in Unicode 3.2). - For programmatic determination of - Ideographic Description Sequences. @stable ICU 2.1 */ - UCHAR_IDS_TRINARY_OPERATOR, - /** Binary property Join_Control. - Format controls for cursive joining and ligation. @stable ICU 2.1 */ - UCHAR_JOIN_CONTROL, - /** Binary property Logical_Order_Exception (new in Unicode 3.2). - Characters that do not use logical order and - require special handling in most processing. @stable ICU 2.1 */ - UCHAR_LOGICAL_ORDER_EXCEPTION, - /** Binary property Lowercase. Same as u_isULowercase, different from u_islower. - Ll+Other_Lowercase @stable ICU 2.1 */ - UCHAR_LOWERCASE, - /** Binary property Math. Sm+Other_Math @stable ICU 2.1 */ - UCHAR_MATH, - /** Binary property Noncharacter_Code_Point. - Code points that are explicitly defined as illegal - for the encoding of characters. @stable ICU 2.1 */ - UCHAR_NONCHARACTER_CODE_POINT, - /** Binary property Quotation_Mark. @stable ICU 2.1 */ - UCHAR_QUOTATION_MARK, - /** Binary property Radical (new in Unicode 3.2). - For programmatic determination of - Ideographic Description Sequences. @stable ICU 2.1 */ - UCHAR_RADICAL, - /** Binary property Soft_Dotted (new in Unicode 3.2). - Characters with a "soft dot", like i or j. - An accent placed on these characters causes - the dot to disappear. @stable ICU 2.1 */ - UCHAR_SOFT_DOTTED, - /** Binary property Terminal_Punctuation. - Punctuation characters that generally mark - the end of textual units. @stable ICU 2.1 */ - UCHAR_TERMINAL_PUNCTUATION, - /** Binary property Unified_Ideograph (new in Unicode 3.2). - For programmatic determination of - Ideographic Description Sequences. @stable ICU 2.1 */ - UCHAR_UNIFIED_IDEOGRAPH, - /** Binary property Uppercase. Same as u_isUUppercase, different from u_isupper. - Lu+Other_Uppercase @stable ICU 2.1 */ - UCHAR_UPPERCASE, - /** Binary property White_Space. - Same as u_isUWhiteSpace, different from u_isspace and u_isWhitespace. - Space characters+TAB+CR+LF-ZWSP-ZWNBSP @stable ICU 2.1 */ - UCHAR_WHITE_SPACE, - /** Binary property XID_Continue. - ID_Continue modified to allow closure under - normalization forms NFKC and NFKD. @stable ICU 2.1 */ - UCHAR_XID_CONTINUE, - /** Binary property XID_Start. ID_Start modified to allow - closure under normalization forms NFKC and NFKD. @stable ICU 2.1 */ - UCHAR_XID_START, - /** Binary property Case_Sensitive. Either the source of a case - mapping or _in_ the target of a case mapping. Not the same as - the general category Cased_Letter. @stable ICU 2.6 */ - UCHAR_CASE_SENSITIVE, - /** Binary property STerm (new in Unicode 4.0.1). - Sentence Terminal. Used in UAX #29: Text Boundaries - (http://www.unicode.org/reports/tr29/) - @draft ICU 3.0 */ - UCHAR_S_TERM, - /** Binary property Variation_Selector (new in Unicode 4.0.1). - Indicates all those characters that qualify as Variation Selectors. - For details on the behavior of these characters, - see StandardizedVariants.html and 15.6 Variation Selectors. - @draft ICU 3.0 */ - UCHAR_VARIATION_SELECTOR, - /** Binary property NFD_Inert. - ICU-specific property for characters that are inert under NFD, - i.e., they do not interact with adjacent characters. - Used for example in normalizing transforms in incremental mode - to find the boundary of safely normalizable text despite possible - text additions. - - There is one such property per normalization form. - These properties are computed as follows - an inert character is: - a) unassigned, or ALL of the following: - b) of combining class 0. - c) not decomposed by this normalization form. - AND if NFC or NFKC, - d) can never compose with a previous character. - e) can never compose with a following character. - f) can never change if another character is added. - Example: a-breve might satisfy all but f, but if you - add an ogonek it changes to a-ogonek + breve - - See also com.ibm.text.UCD.NFSkippable in the ICU4J repository, - and icu/source/common/unormimp.h . - @draft ICU 3.0 */ - UCHAR_NFD_INERT, - /** Binary property NFKD_Inert. - ICU-specific property for characters that are inert under NFKD, - i.e., they do not interact with adjacent characters. - Used for example in normalizing transforms in incremental mode - to find the boundary of safely normalizable text despite possible - text additions. - @see UCHAR_NFD_INERT - @draft ICU 3.0 */ - UCHAR_NFKD_INERT, - /** Binary property NFC_Inert. - ICU-specific property for characters that are inert under NFC, - i.e., they do not interact with adjacent characters. - Used for example in normalizing transforms in incremental mode - to find the boundary of safely normalizable text despite possible - text additions. - @see UCHAR_NFD_INERT - @draft ICU 3.0 */ - UCHAR_NFC_INERT, - /** Binary property NFKC_Inert. - ICU-specific property for characters that are inert under NFKC, - i.e., they do not interact with adjacent characters. - Used for example in normalizing transforms in incremental mode - to find the boundary of safely normalizable text despite possible - text additions. - @see UCHAR_NFD_INERT - @draft ICU 3.0 */ - UCHAR_NFKC_INERT, - /** Binary Property Segment_Starter. - ICU-specific property for characters that are starters in terms of - Unicode normalization and combining character sequences. - They have ccc=0 and do not occur in non-initial position of the - canonical decomposition of any character - (like " in NFD(a-umlaut) and a Jamo T in an NFD(Hangul LVT)). - ICU uses this property for segmenting a string for generating a set of - canonically equivalent strings, e.g. for canonical closure while - processing collation tailoring rules. - @draft ICU 3.0 */ - UCHAR_SEGMENT_STARTER, - /** One more than the last constant for binary Unicode properties. @stable ICU 2.1 */ - UCHAR_BINARY_LIMIT, - - /** Enumerated property Bidi_Class. - Same as u_charDirection, returns UCharDirection values. @stable ICU 2.2 */ - UCHAR_BIDI_CLASS=0x1000, - /** First constant for enumerated/integer Unicode properties. @stable ICU 2.2 */ - UCHAR_INT_START=UCHAR_BIDI_CLASS, - /** Enumerated property Block. - Same as ublock_getCode, returns UBlockCode values. @stable ICU 2.2 */ - UCHAR_BLOCK, - /** Enumerated property Canonical_Combining_Class. - Same as u_getCombiningClass, returns 8-bit numeric values. @stable ICU 2.2 */ - UCHAR_CANONICAL_COMBINING_CLASS, - /** Enumerated property Decomposition_Type. - Returns UDecompositionType values. @stable ICU 2.2 */ - UCHAR_DECOMPOSITION_TYPE, - /** Enumerated property East_Asian_Width. - See http://www.unicode.org/reports/tr11/ - Returns UEastAsianWidth values. @stable ICU 2.2 */ - UCHAR_EAST_ASIAN_WIDTH, - /** Enumerated property General_Category. - Same as u_charType, returns UCharCategory values. @stable ICU 2.2 */ - UCHAR_GENERAL_CATEGORY, - /** Enumerated property Joining_Group. - Returns UJoiningGroup values. @stable ICU 2.2 */ - UCHAR_JOINING_GROUP, - /** Enumerated property Joining_Type. - Returns UJoiningType values. @stable ICU 2.2 */ - UCHAR_JOINING_TYPE, - /** Enumerated property Line_Break. - Returns ULineBreak values. @stable ICU 2.2 */ - UCHAR_LINE_BREAK, - /** Enumerated property Numeric_Type. - Returns UNumericType values. @stable ICU 2.2 */ - UCHAR_NUMERIC_TYPE, - /** Enumerated property Script. - Same as uscript_getScript, returns UScriptCode values. @stable ICU 2.2 */ - UCHAR_SCRIPT, - /** Enumerated property Hangul_Syllable_Type, new in Unicode 4. - Returns UHangulSyllableType values. @stable ICU 2.6 */ - UCHAR_HANGUL_SYLLABLE_TYPE, - /** Enumerated property NFD_Quick_Check. - Returns UNormalizationCheckResult values. @draft ICU 3.0 */ - UCHAR_NFD_QUICK_CHECK, - /** Enumerated property NFKD_Quick_Check. - Returns UNormalizationCheckResult values. @draft ICU 3.0 */ - UCHAR_NFKD_QUICK_CHECK, - /** Enumerated property NFC_Quick_Check. - Returns UNormalizationCheckResult values. @draft ICU 3.0 */ - UCHAR_NFC_QUICK_CHECK, - /** Enumerated property NFKC_Quick_Check. - Returns UNormalizationCheckResult values. @draft ICU 3.0 */ - UCHAR_NFKC_QUICK_CHECK, - /** Enumerated property Lead_Canonical_Combining_Class. - ICU-specific property for the ccc of the first code point - of the decomposition, or lccc(c)=ccc(NFD(c)[0]). - Useful for checking for canonically ordered text; - see UNORM_FCD and http://www.unicode.org/notes/tn5/#FCD . - Returns 8-bit numeric values like UCHAR_CANONICAL_COMBINING_CLASS. @draft ICU 3.0 */ - UCHAR_LEAD_CANONICAL_COMBINING_CLASS, - /** Enumerated property Trail_Canonical_Combining_Class. - ICU-specific property for the ccc of the last code point - of the decomposition, or tccc(c)=ccc(NFD(c)[last]). - Useful for checking for canonically ordered text; - see UNORM_FCD and http://www.unicode.org/notes/tn5/#FCD . - Returns 8-bit numeric values like UCHAR_CANONICAL_COMBINING_CLASS. @draft ICU 3.0 */ - UCHAR_TRAIL_CANONICAL_COMBINING_CLASS, - /** One more than the last constant for enumerated/integer Unicode properties. @stable ICU 2.2 */ - UCHAR_INT_LIMIT, - - /** Bitmask property General_Category_Mask. - This is the General_Category property returned as a bit mask. - When used in u_getIntPropertyValue(c), same as U_MASK(u_charType(c)), - returns bit masks for UCharCategory values where exactly one bit is set. - When used with u_getPropertyValueName() and u_getPropertyValueEnum(), - a multi-bit mask is used for sets of categories like "Letters". - Mask values should be cast to uint32_t. - @stable ICU 2.4 */ - UCHAR_GENERAL_CATEGORY_MASK=0x2000, - /** First constant for bit-mask Unicode properties. @stable ICU 2.4 */ - UCHAR_MASK_START=UCHAR_GENERAL_CATEGORY_MASK, - /** One more than the last constant for bit-mask Unicode properties. @stable ICU 2.4 */ - UCHAR_MASK_LIMIT, - - /** Double property Numeric_Value. - Corresponds to u_getNumericValue. @stable ICU 2.4 */ - UCHAR_NUMERIC_VALUE=0x3000, - /** First constant for double Unicode properties. @stable ICU 2.4 */ - UCHAR_DOUBLE_START=UCHAR_NUMERIC_VALUE, - /** One more than the last constant for double Unicode properties. @stable ICU 2.4 */ - UCHAR_DOUBLE_LIMIT, - - /** String property Age. - Corresponds to u_charAge. @stable ICU 2.4 */ - UCHAR_AGE=0x4000, - /** First constant for string Unicode properties. @stable ICU 2.4 */ - UCHAR_STRING_START=UCHAR_AGE, - /** String property Bidi_Mirroring_Glyph. - Corresponds to u_charMirror. @stable ICU 2.4 */ - UCHAR_BIDI_MIRRORING_GLYPH, - /** String property Case_Folding. - Corresponds to u_strFoldCase in ustring.h. @stable ICU 2.4 */ - UCHAR_CASE_FOLDING, - /** String property ISO_Comment. - Corresponds to u_getISOComment. @stable ICU 2.4 */ - UCHAR_ISO_COMMENT, - /** String property Lowercase_Mapping. - Corresponds to u_strToLower in ustring.h. @stable ICU 2.4 */ - UCHAR_LOWERCASE_MAPPING, - /** String property Name. - Corresponds to u_charName. @stable ICU 2.4 */ - UCHAR_NAME, - /** String property Simple_Case_Folding. - Corresponds to u_foldCase. @stable ICU 2.4 */ - UCHAR_SIMPLE_CASE_FOLDING, - /** String property Simple_Lowercase_Mapping. - Corresponds to u_tolower. @stable ICU 2.4 */ - UCHAR_SIMPLE_LOWERCASE_MAPPING, - /** String property Simple_Titlecase_Mapping. - Corresponds to u_totitle. @stable ICU 2.4 */ - UCHAR_SIMPLE_TITLECASE_MAPPING, - /** String property Simple_Uppercase_Mapping. - Corresponds to u_toupper. @stable ICU 2.4 */ - UCHAR_SIMPLE_UPPERCASE_MAPPING, - /** String property Titlecase_Mapping. - Corresponds to u_strToTitle in ustring.h. @stable ICU 2.4 */ - UCHAR_TITLECASE_MAPPING, - /** String property Unicode_1_Name. - Corresponds to u_charName. @stable ICU 2.4 */ - UCHAR_UNICODE_1_NAME, - /** String property Uppercase_Mapping. - Corresponds to u_strToUpper in ustring.h. @stable ICU 2.4 */ - UCHAR_UPPERCASE_MAPPING, - /** One more than the last constant for string Unicode properties. @stable ICU 2.4 */ - UCHAR_STRING_LIMIT, - - /** Represents a nonexistent or invalid property or property value. @stable ICU 2.4 */ - UCHAR_INVALID_CODE = -1 -} UProperty; - -/** - * Data for enumerated Unicode general category types. - * See http://www.unicode.org/Public/UNIDATA/UnicodeData.html . - * @stable ICU 2.0 - */ -typedef enum UCharCategory -{ - /** See note !!. Comments of the form "Cn" are read by genpname. */ - - /** Non-category for unassigned and non-character code points. @stable ICU 2.0 */ - U_UNASSIGNED = 0, - /** Cn "Other, Not Assigned (no characters in [UnicodeData.txt] have this property)" (same as U_UNASSIGNED!) @stable ICU 2.0 */ - U_GENERAL_OTHER_TYPES = 0, - /** Lu @stable ICU 2.0 */ - U_UPPERCASE_LETTER = 1, - /** Ll @stable ICU 2.0 */ - U_LOWERCASE_LETTER = 2, - /** Lt @stable ICU 2.0 */ - U_TITLECASE_LETTER = 3, - /** Lm @stable ICU 2.0 */ - U_MODIFIER_LETTER = 4, - /** Lo @stable ICU 2.0 */ - U_OTHER_LETTER = 5, - /** Mn @stable ICU 2.0 */ - U_NON_SPACING_MARK = 6, - /** Me @stable ICU 2.0 */ - U_ENCLOSING_MARK = 7, - /** Mc @stable ICU 2.0 */ - U_COMBINING_SPACING_MARK = 8, - /** Nd @stable ICU 2.0 */ - U_DECIMAL_DIGIT_NUMBER = 9, - /** Nl @stable ICU 2.0 */ - U_LETTER_NUMBER = 10, - /** No @stable ICU 2.0 */ - U_OTHER_NUMBER = 11, - /** Zs @stable ICU 2.0 */ - U_SPACE_SEPARATOR = 12, - /** Zl @stable ICU 2.0 */ - U_LINE_SEPARATOR = 13, - /** Zp @stable ICU 2.0 */ - U_PARAGRAPH_SEPARATOR = 14, - /** Cc @stable ICU 2.0 */ - U_CONTROL_CHAR = 15, - /** Cf @stable ICU 2.0 */ - U_FORMAT_CHAR = 16, - /** Co @stable ICU 2.0 */ - U_PRIVATE_USE_CHAR = 17, - /** Cs @stable ICU 2.0 */ - U_SURROGATE = 18, - /** Pd @stable ICU 2.0 */ - U_DASH_PUNCTUATION = 19, - /** Ps @stable ICU 2.0 */ - U_START_PUNCTUATION = 20, - /** Pe @stable ICU 2.0 */ - U_END_PUNCTUATION = 21, - /** Pc @stable ICU 2.0 */ - U_CONNECTOR_PUNCTUATION = 22, - /** Po @stable ICU 2.0 */ - U_OTHER_PUNCTUATION = 23, - /** Sm @stable ICU 2.0 */ - U_MATH_SYMBOL = 24, - /** Sc @stable ICU 2.0 */ - U_CURRENCY_SYMBOL = 25, - /** Sk @stable ICU 2.0 */ - U_MODIFIER_SYMBOL = 26, - /** So @stable ICU 2.0 */ - U_OTHER_SYMBOL = 27, - /** Pi @stable ICU 2.0 */ - U_INITIAL_PUNCTUATION = 28, - /** Pf @stable ICU 2.0 */ - U_FINAL_PUNCTUATION = 29, - /** One higher than the last enum UCharCategory constant. @stable ICU 2.0 */ - U_CHAR_CATEGORY_COUNT -} UCharCategory; - -/** - * U_GC_XX_MASK constants are bit flags corresponding to Unicode - * general category values. - * For each category, the nth bit is set if the numeric value of the - * corresponding UCharCategory constant is n. - * - * There are also some U_GC_Y_MASK constants for groups of general categories - * like L for all letter categories. - * - * @see u_charType - * @see U_GET_GC_MASK - * @see UCharCategory - * @stable ICU 2.1 - */ -#define U_GC_CN_MASK U_MASK(U_GENERAL_OTHER_TYPES) - -/** Mask constant for a UCharCategory. @stable ICU 2.1 */ -#define U_GC_LU_MASK U_MASK(U_UPPERCASE_LETTER) -/** Mask constant for a UCharCategory. @stable ICU 2.1 */ -#define U_GC_LL_MASK U_MASK(U_LOWERCASE_LETTER) -/** Mask constant for a UCharCategory. @stable ICU 2.1 */ -#define U_GC_LT_MASK U_MASK(U_TITLECASE_LETTER) -/** Mask constant for a UCharCategory. @stable ICU 2.1 */ -#define U_GC_LM_MASK U_MASK(U_MODIFIER_LETTER) -/** Mask constant for a UCharCategory. @stable ICU 2.1 */ -#define U_GC_LO_MASK U_MASK(U_OTHER_LETTER) - -/** Mask constant for a UCharCategory. @stable ICU 2.1 */ -#define U_GC_MN_MASK U_MASK(U_NON_SPACING_MARK) -/** Mask constant for a UCharCategory. @stable ICU 2.1 */ -#define U_GC_ME_MASK U_MASK(U_ENCLOSING_MARK) -/** Mask constant for a UCharCategory. @stable ICU 2.1 */ -#define U_GC_MC_MASK U_MASK(U_COMBINING_SPACING_MARK) - -/** Mask constant for a UCharCategory. @stable ICU 2.1 */ -#define U_GC_ND_MASK U_MASK(U_DECIMAL_DIGIT_NUMBER) -/** Mask constant for a UCharCategory. @stable ICU 2.1 */ -#define U_GC_NL_MASK U_MASK(U_LETTER_NUMBER) -/** Mask constant for a UCharCategory. @stable ICU 2.1 */ -#define U_GC_NO_MASK U_MASK(U_OTHER_NUMBER) - -/** Mask constant for a UCharCategory. @stable ICU 2.1 */ -#define U_GC_ZS_MASK U_MASK(U_SPACE_SEPARATOR) -/** Mask constant for a UCharCategory. @stable ICU 2.1 */ -#define U_GC_ZL_MASK U_MASK(U_LINE_SEPARATOR) -/** Mask constant for a UCharCategory. @stable ICU 2.1 */ -#define U_GC_ZP_MASK U_MASK(U_PARAGRAPH_SEPARATOR) - -/** Mask constant for a UCharCategory. @stable ICU 2.1 */ -#define U_GC_CC_MASK U_MASK(U_CONTROL_CHAR) -/** Mask constant for a UCharCategory. @stable ICU 2.1 */ -#define U_GC_CF_MASK U_MASK(U_FORMAT_CHAR) -/** Mask constant for a UCharCategory. @stable ICU 2.1 */ -#define U_GC_CO_MASK U_MASK(U_PRIVATE_USE_CHAR) -/** Mask constant for a UCharCategory. @stable ICU 2.1 */ -#define U_GC_CS_MASK U_MASK(U_SURROGATE) - -/** Mask constant for a UCharCategory. @stable ICU 2.1 */ -#define U_GC_PD_MASK U_MASK(U_DASH_PUNCTUATION) -/** Mask constant for a UCharCategory. @stable ICU 2.1 */ -#define U_GC_PS_MASK U_MASK(U_START_PUNCTUATION) -/** Mask constant for a UCharCategory. @stable ICU 2.1 */ -#define U_GC_PE_MASK U_MASK(U_END_PUNCTUATION) -/** Mask constant for a UCharCategory. @stable ICU 2.1 */ -#define U_GC_PC_MASK U_MASK(U_CONNECTOR_PUNCTUATION) -/** Mask constant for a UCharCategory. @stable ICU 2.1 */ -#define U_GC_PO_MASK U_MASK(U_OTHER_PUNCTUATION) - -/** Mask constant for a UCharCategory. @stable ICU 2.1 */ -#define U_GC_SM_MASK U_MASK(U_MATH_SYMBOL) -/** Mask constant for a UCharCategory. @stable ICU 2.1 */ -#define U_GC_SC_MASK U_MASK(U_CURRENCY_SYMBOL) -/** Mask constant for a UCharCategory. @stable ICU 2.1 */ -#define U_GC_SK_MASK U_MASK(U_MODIFIER_SYMBOL) -/** Mask constant for a UCharCategory. @stable ICU 2.1 */ -#define U_GC_SO_MASK U_MASK(U_OTHER_SYMBOL) - -/** Mask constant for a UCharCategory. @stable ICU 2.1 */ -#define U_GC_PI_MASK U_MASK(U_INITIAL_PUNCTUATION) -/** Mask constant for a UCharCategory. @stable ICU 2.1 */ -#define U_GC_PF_MASK U_MASK(U_FINAL_PUNCTUATION) - - -/** Mask constant for multiple UCharCategory bits (L Letters). @stable ICU 2.1 */ -#define U_GC_L_MASK \ - (U_GC_LU_MASK|U_GC_LL_MASK|U_GC_LT_MASK|U_GC_LM_MASK|U_GC_LO_MASK) - -/** Mask constant for multiple UCharCategory bits (LC Cased Letters). @stable ICU 2.1 */ -#define U_GC_LC_MASK \ - (U_GC_LU_MASK|U_GC_LL_MASK|U_GC_LT_MASK) - -/** Mask constant for multiple UCharCategory bits (M Marks). @stable ICU 2.1 */ -#define U_GC_M_MASK (U_GC_MN_MASK|U_GC_ME_MASK|U_GC_MC_MASK) - -/** Mask constant for multiple UCharCategory bits (N Numbers). @stable ICU 2.1 */ -#define U_GC_N_MASK (U_GC_ND_MASK|U_GC_NL_MASK|U_GC_NO_MASK) - -/** Mask constant for multiple UCharCategory bits (Z Separators). @stable ICU 2.1 */ -#define U_GC_Z_MASK (U_GC_ZS_MASK|U_GC_ZL_MASK|U_GC_ZP_MASK) - -/** Mask constant for multiple UCharCategory bits (C Others). @stable ICU 2.1 */ -#define U_GC_C_MASK \ - (U_GC_CN_MASK|U_GC_CC_MASK|U_GC_CF_MASK|U_GC_CO_MASK|U_GC_CS_MASK) - -/** Mask constant for multiple UCharCategory bits (P Punctuation). @stable ICU 2.1 */ -#define U_GC_P_MASK \ - (U_GC_PD_MASK|U_GC_PS_MASK|U_GC_PE_MASK|U_GC_PC_MASK|U_GC_PO_MASK| \ - U_GC_PI_MASK|U_GC_PF_MASK) - -/** Mask constant for multiple UCharCategory bits (S Symbols). @stable ICU 2.1 */ -#define U_GC_S_MASK (U_GC_SM_MASK|U_GC_SC_MASK|U_GC_SK_MASK|U_GC_SO_MASK) - -/** - * This specifies the language directional property of a character set. - * @stable ICU 2.0 - */ -typedef enum UCharDirection { - /** See note !!. Comments of the form "EN" are read by genpname. */ - - /** L @stable ICU 2.0 */ - U_LEFT_TO_RIGHT = 0, - /** R @stable ICU 2.0 */ - U_RIGHT_TO_LEFT = 1, - /** EN @stable ICU 2.0 */ - U_EUROPEAN_NUMBER = 2, - /** ES @stable ICU 2.0 */ - U_EUROPEAN_NUMBER_SEPARATOR = 3, - /** ET @stable ICU 2.0 */ - U_EUROPEAN_NUMBER_TERMINATOR = 4, - /** AN @stable ICU 2.0 */ - U_ARABIC_NUMBER = 5, - /** CS @stable ICU 2.0 */ - U_COMMON_NUMBER_SEPARATOR = 6, - /** B @stable ICU 2.0 */ - U_BLOCK_SEPARATOR = 7, - /** S @stable ICU 2.0 */ - U_SEGMENT_SEPARATOR = 8, - /** WS @stable ICU 2.0 */ - U_WHITE_SPACE_NEUTRAL = 9, - /** ON @stable ICU 2.0 */ - U_OTHER_NEUTRAL = 10, - /** LRE @stable ICU 2.0 */ - U_LEFT_TO_RIGHT_EMBEDDING = 11, - /** LRO @stable ICU 2.0 */ - U_LEFT_TO_RIGHT_OVERRIDE = 12, - /** AL @stable ICU 2.0 */ - U_RIGHT_TO_LEFT_ARABIC = 13, - /** RLE @stable ICU 2.0 */ - U_RIGHT_TO_LEFT_EMBEDDING = 14, - /** RLO @stable ICU 2.0 */ - U_RIGHT_TO_LEFT_OVERRIDE = 15, - /** PDF @stable ICU 2.0 */ - U_POP_DIRECTIONAL_FORMAT = 16, - /** NSM @stable ICU 2.0 */ - U_DIR_NON_SPACING_MARK = 17, - /** BN @stable ICU 2.0 */ - U_BOUNDARY_NEUTRAL = 18, - /** @stable ICU 2.0 */ - U_CHAR_DIRECTION_COUNT -} UCharDirection; - -/** - * Constants for Unicode blocks, see the Unicode Data file Blocks.txt - * @stable ICU 2.0 - */ -enum UBlockCode { - - /** New No_Block value in Unicode 4. @stable ICU 2.6 */ - UBLOCK_NO_BLOCK = 0, /*[none]*/ /* Special range indicating No_Block */ - - /** @stable ICU 2.0 */ - UBLOCK_BASIC_LATIN = 1, /*[0000]*/ /*See note !!*/ - - /** @stable ICU 2.0 */ - UBLOCK_LATIN_1_SUPPLEMENT=2, /*[0080]*/ - - /** @stable ICU 2.0 */ - UBLOCK_LATIN_EXTENDED_A =3, /*[0100]*/ - - /** @stable ICU 2.0 */ - UBLOCK_LATIN_EXTENDED_B =4, /*[0180]*/ - - /** @stable ICU 2.0 */ - UBLOCK_IPA_EXTENSIONS =5, /*[0250]*/ - - /** @stable ICU 2.0 */ - UBLOCK_SPACING_MODIFIER_LETTERS =6, /*[02B0]*/ - - /** @stable ICU 2.0 */ - UBLOCK_COMBINING_DIACRITICAL_MARKS =7, /*[0300]*/ - - /** - * Unicode 3.2 renames this block to "Greek and Coptic". - * @stable ICU 2.0 - */ - UBLOCK_GREEK =8, /*[0370]*/ - - /** @stable ICU 2.0 */ - UBLOCK_CYRILLIC =9, /*[0400]*/ - - /** @stable ICU 2.0 */ - UBLOCK_ARMENIAN =10, /*[0530]*/ - - /** @stable ICU 2.0 */ - UBLOCK_HEBREW =11, /*[0590]*/ - - /** @stable ICU 2.0 */ - UBLOCK_ARABIC =12, /*[0600]*/ - - /** @stable ICU 2.0 */ - UBLOCK_SYRIAC =13, /*[0700]*/ - - /** @stable ICU 2.0 */ - UBLOCK_THAANA =14, /*[0780]*/ - - /** @stable ICU 2.0 */ - UBLOCK_DEVANAGARI =15, /*[0900]*/ - - /** @stable ICU 2.0 */ - UBLOCK_BENGALI =16, /*[0980]*/ - - /** @stable ICU 2.0 */ - UBLOCK_GURMUKHI =17, /*[0A00]*/ - - /** @stable ICU 2.0 */ - UBLOCK_GUJARATI =18, /*[0A80]*/ - - /** @stable ICU 2.0 */ - UBLOCK_ORIYA =19, /*[0B00]*/ - - /** @stable ICU 2.0 */ - UBLOCK_TAMIL =20, /*[0B80]*/ - - /** @stable ICU 2.0 */ - UBLOCK_TELUGU =21, /*[0C00]*/ - - /** @stable ICU 2.0 */ - UBLOCK_KANNADA =22, /*[0C80]*/ - - /** @stable ICU 2.0 */ - UBLOCK_MALAYALAM =23, /*[0D00]*/ - - /** @stable ICU 2.0 */ - UBLOCK_SINHALA =24, /*[0D80]*/ - - /** @stable ICU 2.0 */ - UBLOCK_THAI =25, /*[0E00]*/ - - /** @stable ICU 2.0 */ - UBLOCK_LAO =26, /*[0E80]*/ - - /** @stable ICU 2.0 */ - UBLOCK_TIBETAN =27, /*[0F00]*/ - - /** @stable ICU 2.0 */ - UBLOCK_MYANMAR =28, /*[1000]*/ - - /** @stable ICU 2.0 */ - UBLOCK_GEORGIAN =29, /*[10A0]*/ - - /** @stable ICU 2.0 */ - UBLOCK_HANGUL_JAMO =30, /*[1100]*/ - - /** @stable ICU 2.0 */ - UBLOCK_ETHIOPIC =31, /*[1200]*/ - - /** @stable ICU 2.0 */ - UBLOCK_CHEROKEE =32, /*[13A0]*/ - - /** @stable ICU 2.0 */ - UBLOCK_UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS =33, /*[1400]*/ - - /** @stable ICU 2.0 */ - UBLOCK_OGHAM =34, /*[1680]*/ - - /** @stable ICU 2.0 */ - UBLOCK_RUNIC =35, /*[16A0]*/ - - /** @stable ICU 2.0 */ - UBLOCK_KHMER =36, /*[1780]*/ - - /** @stable ICU 2.0 */ - UBLOCK_MONGOLIAN =37, /*[1800]*/ - - /** @stable ICU 2.0 */ - UBLOCK_LATIN_EXTENDED_ADDITIONAL =38, /*[1E00]*/ - - /** @stable ICU 2.0 */ - UBLOCK_GREEK_EXTENDED =39, /*[1F00]*/ - - /** @stable ICU 2.0 */ - UBLOCK_GENERAL_PUNCTUATION =40, /*[2000]*/ - - /** @stable ICU 2.0 */ - UBLOCK_SUPERSCRIPTS_AND_SUBSCRIPTS =41, /*[2070]*/ - - /** @stable ICU 2.0 */ - UBLOCK_CURRENCY_SYMBOLS =42, /*[20A0]*/ - - /** - * Unicode 3.2 renames this block to "Combining Diacritical Marks for Symbols". - * @stable ICU 2.0 - */ - UBLOCK_COMBINING_MARKS_FOR_SYMBOLS =43, /*[20D0]*/ - - /** @stable ICU 2.0 */ - UBLOCK_LETTERLIKE_SYMBOLS =44, /*[2100]*/ - - /** @stable ICU 2.0 */ - UBLOCK_NUMBER_FORMS =45, /*[2150]*/ - - /** @stable ICU 2.0 */ - UBLOCK_ARROWS =46, /*[2190]*/ - - /** @stable ICU 2.0 */ - UBLOCK_MATHEMATICAL_OPERATORS =47, /*[2200]*/ - - /** @stable ICU 2.0 */ - UBLOCK_MISCELLANEOUS_TECHNICAL =48, /*[2300]*/ - - /** @stable ICU 2.0 */ - UBLOCK_CONTROL_PICTURES =49, /*[2400]*/ - - /** @stable ICU 2.0 */ - UBLOCK_OPTICAL_CHARACTER_RECOGNITION =50, /*[2440]*/ - - /** @stable ICU 2.0 */ - UBLOCK_ENCLOSED_ALPHANUMERICS =51, /*[2460]*/ - - /** @stable ICU 2.0 */ - UBLOCK_BOX_DRAWING =52, /*[2500]*/ - - /** @stable ICU 2.0 */ - UBLOCK_BLOCK_ELEMENTS =53, /*[2580]*/ - - /** @stable ICU 2.0 */ - UBLOCK_GEOMETRIC_SHAPES =54, /*[25A0]*/ - - /** @stable ICU 2.0 */ - UBLOCK_MISCELLANEOUS_SYMBOLS =55, /*[2600]*/ - - /** @stable ICU 2.0 */ - UBLOCK_DINGBATS =56, /*[2700]*/ - - /** @stable ICU 2.0 */ - UBLOCK_BRAILLE_PATTERNS =57, /*[2800]*/ - - /** @stable ICU 2.0 */ - UBLOCK_CJK_RADICALS_SUPPLEMENT =58, /*[2E80]*/ - - /** @stable ICU 2.0 */ - UBLOCK_KANGXI_RADICALS =59, /*[2F00]*/ - - /** @stable ICU 2.0 */ - UBLOCK_IDEOGRAPHIC_DESCRIPTION_CHARACTERS =60, /*[2FF0]*/ - - /** @stable ICU 2.0 */ - UBLOCK_CJK_SYMBOLS_AND_PUNCTUATION =61, /*[3000]*/ - - /** @stable ICU 2.0 */ - UBLOCK_HIRAGANA =62, /*[3040]*/ - - /** @stable ICU 2.0 */ - UBLOCK_KATAKANA =63, /*[30A0]*/ - - /** @stable ICU 2.0 */ - UBLOCK_BOPOMOFO =64, /*[3100]*/ - - /** @stable ICU 2.0 */ - UBLOCK_HANGUL_COMPATIBILITY_JAMO =65, /*[3130]*/ - - /** @stable ICU 2.0 */ - UBLOCK_KANBUN =66, /*[3190]*/ - - /** @stable ICU 2.0 */ - UBLOCK_BOPOMOFO_EXTENDED =67, /*[31A0]*/ - - /** @stable ICU 2.0 */ - UBLOCK_ENCLOSED_CJK_LETTERS_AND_MONTHS =68, /*[3200]*/ - - /** @stable ICU 2.0 */ - UBLOCK_CJK_COMPATIBILITY =69, /*[3300]*/ - - /** @stable ICU 2.0 */ - UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_A =70, /*[3400]*/ - - /** @stable ICU 2.0 */ - UBLOCK_CJK_UNIFIED_IDEOGRAPHS =71, /*[4E00]*/ - - /** @stable ICU 2.0 */ - UBLOCK_YI_SYLLABLES =72, /*[A000]*/ - - /** @stable ICU 2.0 */ - UBLOCK_YI_RADICALS =73, /*[A490]*/ - - /** @stable ICU 2.0 */ - UBLOCK_HANGUL_SYLLABLES =74, /*[AC00]*/ - - /** @stable ICU 2.0 */ - UBLOCK_HIGH_SURROGATES =75, /*[D800]*/ - - /** @stable ICU 2.0 */ - UBLOCK_HIGH_PRIVATE_USE_SURROGATES =76, /*[DB80]*/ - - /** @stable ICU 2.0 */ - UBLOCK_LOW_SURROGATES =77, /*[DC00]*/ - - /** - * Same as UBLOCK_PRIVATE_USE_AREA. - * Until Unicode 3.1.1, the corresponding block name was "Private Use", - * and multiple code point ranges had this block. - * Unicode 3.2 renames the block for the BMP PUA to "Private Use Area" and - * adds separate blocks for the supplementary PUAs. - * - * @stable ICU 2.0 - */ - UBLOCK_PRIVATE_USE = 78, - /** - * Same as UBLOCK_PRIVATE_USE. - * Until Unicode 3.1.1, the corresponding block name was "Private Use", - * and multiple code point ranges had this block. - * Unicode 3.2 renames the block for the BMP PUA to "Private Use Area" and - * adds separate blocks for the supplementary PUAs. - * - * @stable ICU 2.0 - */ - UBLOCK_PRIVATE_USE_AREA =UBLOCK_PRIVATE_USE, /*[E000]*/ - - /** @stable ICU 2.0 */ - UBLOCK_CJK_COMPATIBILITY_IDEOGRAPHS =79, /*[F900]*/ - - /** @stable ICU 2.0 */ - UBLOCK_ALPHABETIC_PRESENTATION_FORMS =80, /*[FB00]*/ - - /** @stable ICU 2.0 */ - UBLOCK_ARABIC_PRESENTATION_FORMS_A =81, /*[FB50]*/ - - /** @stable ICU 2.0 */ - UBLOCK_COMBINING_HALF_MARKS =82, /*[FE20]*/ - - /** @stable ICU 2.0 */ - UBLOCK_CJK_COMPATIBILITY_FORMS =83, /*[FE30]*/ - - /** @stable ICU 2.0 */ - UBLOCK_SMALL_FORM_VARIANTS =84, /*[FE50]*/ - - /** @stable ICU 2.0 */ - UBLOCK_ARABIC_PRESENTATION_FORMS_B =85, /*[FE70]*/ - - /** @stable ICU 2.0 */ - UBLOCK_SPECIALS =86, /*[FFF0]*/ - - /** @stable ICU 2.0 */ - UBLOCK_HALFWIDTH_AND_FULLWIDTH_FORMS =87, /*[FF00]*/ - - /* New blocks in Unicode 3.1 */ - - /** @stable ICU 2.0 */ - UBLOCK_OLD_ITALIC = 88 , /*[10300]*/ - /** @stable ICU 2.0 */ - UBLOCK_GOTHIC = 89 , /*[10330]*/ - /** @stable ICU 2.0 */ - UBLOCK_DESERET = 90 , /*[10400]*/ - /** @stable ICU 2.0 */ - UBLOCK_BYZANTINE_MUSICAL_SYMBOLS = 91 , /*[1D000]*/ - /** @stable ICU 2.0 */ - UBLOCK_MUSICAL_SYMBOLS = 92 , /*[1D100]*/ - /** @stable ICU 2.0 */ - UBLOCK_MATHEMATICAL_ALPHANUMERIC_SYMBOLS = 93 , /*[1D400]*/ - /** @stable ICU 2.0 */ - UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_B = 94 , /*[20000]*/ - /** @stable ICU 2.0 */ - UBLOCK_CJK_COMPATIBILITY_IDEOGRAPHS_SUPPLEMENT = 95 , /*[2F800]*/ - /** @stable ICU 2.0 */ - UBLOCK_TAGS = 96, /*[E0000]*/ - - /* New blocks in Unicode 3.2 */ - - /** - * Unicode 4.0.1 renames the "Cyrillic Supplementary" block to "Cyrillic Supplement". - * @stable ICU 2.2 - */ - UBLOCK_CYRILLIC_SUPPLEMENTARY = 97, - /** @draft ICU 3.0 */ - UBLOCK_CYRILLIC_SUPPLEMENT = UBLOCK_CYRILLIC_SUPPLEMENTARY, /*[0500]*/ - /** @stable ICU 2.2 */ - UBLOCK_TAGALOG = 98, /*[1700]*/ - /** @stable ICU 2.2 */ - UBLOCK_HANUNOO = 99, /*[1720]*/ - /** @stable ICU 2.2 */ - UBLOCK_BUHID = 100, /*[1740]*/ - /** @stable ICU 2.2 */ - UBLOCK_TAGBANWA = 101, /*[1760]*/ - /** @stable ICU 2.2 */ - UBLOCK_MISCELLANEOUS_MATHEMATICAL_SYMBOLS_A = 102, /*[27C0]*/ - /** @stable ICU 2.2 */ - UBLOCK_SUPPLEMENTAL_ARROWS_A = 103, /*[27F0]*/ - /** @stable ICU 2.2 */ - UBLOCK_SUPPLEMENTAL_ARROWS_B = 104, /*[2900]*/ - /** @stable ICU 2.2 */ - UBLOCK_MISCELLANEOUS_MATHEMATICAL_SYMBOLS_B = 105, /*[2980]*/ - /** @stable ICU 2.2 */ - UBLOCK_SUPPLEMENTAL_MATHEMATICAL_OPERATORS = 106, /*[2A00]*/ - /** @stable ICU 2.2 */ - UBLOCK_KATAKANA_PHONETIC_EXTENSIONS = 107, /*[31F0]*/ - /** @stable ICU 2.2 */ - UBLOCK_VARIATION_SELECTORS = 108, /*[FE00]*/ - /** @stable ICU 2.2 */ - UBLOCK_SUPPLEMENTARY_PRIVATE_USE_AREA_A = 109, /*[F0000]*/ - /** @stable ICU 2.2 */ - UBLOCK_SUPPLEMENTARY_PRIVATE_USE_AREA_B = 110, /*[100000]*/ - - /* New blocks in Unicode 4 */ - - /** @stable ICU 2.6 */ - UBLOCK_LIMBU = 111, /*[1900]*/ - /** @stable ICU 2.6 */ - UBLOCK_TAI_LE = 112, /*[1950]*/ - /** @stable ICU 2.6 */ - UBLOCK_KHMER_SYMBOLS = 113, /*[19E0]*/ - /** @stable ICU 2.6 */ - UBLOCK_PHONETIC_EXTENSIONS = 114, /*[1D00]*/ - /** @stable ICU 2.6 */ - UBLOCK_MISCELLANEOUS_SYMBOLS_AND_ARROWS = 115, /*[2B00]*/ - /** @stable ICU 2.6 */ - UBLOCK_YIJING_HEXAGRAM_SYMBOLS = 116, /*[4DC0]*/ - /** @stable ICU 2.6 */ - UBLOCK_LINEAR_B_SYLLABARY = 117, /*[10000]*/ - /** @stable ICU 2.6 */ - UBLOCK_LINEAR_B_IDEOGRAMS = 118, /*[10080]*/ - /** @stable ICU 2.6 */ - UBLOCK_AEGEAN_NUMBERS = 119, /*[10100]*/ - /** @stable ICU 2.6 */ - UBLOCK_UGARITIC = 120, /*[10380]*/ - /** @stable ICU 2.6 */ - UBLOCK_SHAVIAN = 121, /*[10450]*/ - /** @stable ICU 2.6 */ - UBLOCK_OSMANYA = 122, /*[10480]*/ - /** @stable ICU 2.6 */ - UBLOCK_CYPRIOT_SYLLABARY = 123, /*[10800]*/ - /** @stable ICU 2.6 */ - UBLOCK_TAI_XUAN_JING_SYMBOLS = 124, /*[1D300]*/ - /** @stable ICU 2.6 */ - UBLOCK_VARIATION_SELECTORS_SUPPLEMENT = 125, /*[E0100]*/ - - /** @stable ICU 2.0 */ - UBLOCK_COUNT, - - /** @stable ICU 2.0 */ - UBLOCK_INVALID_CODE=-1 -}; - -/** @stable ICU 2.0 */ -typedef enum UBlockCode UBlockCode; - -/** - * East Asian Width constants. - * - * @see UCHAR_EAST_ASIAN_WIDTH - * @see u_getIntPropertyValue - * @stable ICU 2.2 - */ -typedef enum UEastAsianWidth { - U_EA_NEUTRAL, /*[N]*/ /*See note !!*/ - U_EA_AMBIGUOUS, /*[A]*/ - U_EA_HALFWIDTH, /*[H]*/ - U_EA_FULLWIDTH, /*[F]*/ - U_EA_NARROW, /*[Na]*/ - U_EA_WIDE, /*[W]*/ - U_EA_COUNT -} UEastAsianWidth; -/* - * Implementation note: - * Keep UEastAsianWidth constant values in sync with names list in genprops/props2.c. - */ - -/** - * Selector constants for u_charName(). - * u_charName() returns the "modern" name of a - * Unicode character; or the name that was defined in - * Unicode version 1.0, before the Unicode standard merged - * with ISO-10646; or an "extended" name that gives each - * Unicode code point a unique name. - * - * @see u_charName - * @stable ICU 2.0 - */ -typedef enum UCharNameChoice { - U_UNICODE_CHAR_NAME, - U_UNICODE_10_CHAR_NAME, - U_EXTENDED_CHAR_NAME, - U_CHAR_NAME_CHOICE_COUNT -} UCharNameChoice; - -/** - * Selector constants for u_getPropertyName() and - * u_getPropertyValueName(). These selectors are used to choose which - * name is returned for a given property or value. All properties and - * values have a long name. Most have a short name, but some do not. - * Unicode allows for additional names, beyond the long and short - * name, which would be indicated by U_LONG_PROPERTY_NAME + i, where - * i=1, 2,... - * - * @see u_getPropertyName() - * @see u_getPropertyValueName() - * @stable ICU 2.4 - */ -typedef enum UPropertyNameChoice { - U_SHORT_PROPERTY_NAME, - U_LONG_PROPERTY_NAME, - U_PROPERTY_NAME_CHOICE_COUNT -} UPropertyNameChoice; - -/** - * Decomposition Type constants. - * - * @see UCHAR_DECOMPOSITION_TYPE - * @stable ICU 2.2 - */ -typedef enum UDecompositionType { - U_DT_NONE, /*[none]*/ /*See note !!*/ - U_DT_CANONICAL, /*[can]*/ - U_DT_COMPAT, /*[com]*/ - U_DT_CIRCLE, /*[enc]*/ - U_DT_FINAL, /*[fin]*/ - U_DT_FONT, /*[font]*/ - U_DT_FRACTION, /*[fra]*/ - U_DT_INITIAL, /*[init]*/ - U_DT_ISOLATED, /*[iso]*/ - U_DT_MEDIAL, /*[med]*/ - U_DT_NARROW, /*[nar]*/ - U_DT_NOBREAK, /*[nb]*/ - U_DT_SMALL, /*[sml]*/ - U_DT_SQUARE, /*[sqr]*/ - U_DT_SUB, /*[sub]*/ - U_DT_SUPER, /*[sup]*/ - U_DT_VERTICAL, /*[vert]*/ - U_DT_WIDE, /*[wide]*/ - U_DT_COUNT /* 18 */ -} UDecompositionType; - -/** - * Joining Type constants. - * - * @see UCHAR_JOINING_TYPE - * @stable ICU 2.2 - */ -typedef enum UJoiningType { - U_JT_NON_JOINING, /*[U]*/ /*See note !!*/ - U_JT_JOIN_CAUSING, /*[C]*/ - U_JT_DUAL_JOINING, /*[D]*/ - U_JT_LEFT_JOINING, /*[L]*/ - U_JT_RIGHT_JOINING, /*[R]*/ - U_JT_TRANSPARENT, /*[T]*/ - U_JT_COUNT /* 6 */ -} UJoiningType; - -/** - * Joining Group constants. - * - * @see UCHAR_JOINING_GROUP - * @stable ICU 2.2 - */ -typedef enum UJoiningGroup { - U_JG_NO_JOINING_GROUP, - U_JG_AIN, - U_JG_ALAPH, - U_JG_ALEF, - U_JG_BEH, - U_JG_BETH, - U_JG_DAL, - U_JG_DALATH_RISH, - U_JG_E, - U_JG_FEH, - U_JG_FINAL_SEMKATH, - U_JG_GAF, - U_JG_GAMAL, - U_JG_HAH, - U_JG_HAMZA_ON_HEH_GOAL, - U_JG_HE, - U_JG_HEH, - U_JG_HEH_GOAL, - U_JG_HETH, - U_JG_KAF, - U_JG_KAPH, - U_JG_KNOTTED_HEH, - U_JG_LAM, - U_JG_LAMADH, - U_JG_MEEM, - U_JG_MIM, - U_JG_NOON, - U_JG_NUN, - U_JG_PE, - U_JG_QAF, - U_JG_QAPH, - U_JG_REH, - U_JG_REVERSED_PE, - U_JG_SAD, - U_JG_SADHE, - U_JG_SEEN, - U_JG_SEMKATH, - U_JG_SHIN, - U_JG_SWASH_KAF, - U_JG_SYRIAC_WAW, - U_JG_TAH, - U_JG_TAW, - U_JG_TEH_MARBUTA, - U_JG_TETH, - U_JG_WAW, - U_JG_YEH, - U_JG_YEH_BARREE, - U_JG_YEH_WITH_TAIL, - U_JG_YUDH, - U_JG_YUDH_HE, - U_JG_ZAIN, - U_JG_FE, /**< @stable ICU 2.6 */ - U_JG_KHAPH, /**< @stable ICU 2.6 */ - U_JG_ZHAIN, /**< @stable ICU 2.6 */ - U_JG_COUNT -} UJoiningGroup; - -/** - * Line Break constants. - * - * @see UCHAR_LINE_BREAK - * @stable ICU 2.2 - */ -typedef enum ULineBreak { - U_LB_UNKNOWN, /*[XX]*/ /*See note !!*/ - U_LB_AMBIGUOUS, /*[AI]*/ - U_LB_ALPHABETIC, /*[AL]*/ - U_LB_BREAK_BOTH, /*[B2]*/ - U_LB_BREAK_AFTER, /*[BA]*/ - U_LB_BREAK_BEFORE, /*[BB]*/ - U_LB_MANDATORY_BREAK, /*[BK]*/ - U_LB_CONTINGENT_BREAK, /*[CB]*/ - U_LB_CLOSE_PUNCTUATION, /*[CL]*/ - U_LB_COMBINING_MARK, /*[CM]*/ - U_LB_CARRIAGE_RETURN, /*[CR]*/ - U_LB_EXCLAMATION, /*[EX]*/ - U_LB_GLUE, /*[GL]*/ - U_LB_HYPHEN, /*[HY]*/ - U_LB_IDEOGRAPHIC, /*[ID]*/ - U_LB_INSEPERABLE, - /** Renamed from the misspelled "inseperable" in Unicode 4.0.1/ICU 3.0 @draft ICU 3.0 */ - U_LB_INSEPARABLE=U_LB_INSEPERABLE,/*[IN]*/ - U_LB_INFIX_NUMERIC, /*[IS]*/ - U_LB_LINE_FEED, /*[LF]*/ - U_LB_NONSTARTER, /*[NS]*/ - U_LB_NUMERIC, /*[NU]*/ - U_LB_OPEN_PUNCTUATION, /*[OP]*/ - U_LB_POSTFIX_NUMERIC, /*[PO]*/ - U_LB_PREFIX_NUMERIC, /*[PR]*/ - U_LB_QUOTATION, /*[QU]*/ - U_LB_COMPLEX_CONTEXT, /*[SA]*/ - U_LB_SURROGATE, /*[SG]*/ - U_LB_SPACE, /*[SP]*/ - U_LB_BREAK_SYMBOLS, /*[SY]*/ - U_LB_ZWSPACE, /*[ZW]*/ - U_LB_NEXT_LINE, /*[NL]*/ /* from here on: new in Unicode 4/ICU 2.6 */ - U_LB_WORD_JOINER, /*[WJ]*/ - U_LB_COUNT -} ULineBreak; - -/** - * Numeric Type constants. - * - * @see UCHAR_NUMERIC_TYPE - * @stable ICU 2.2 - */ -typedef enum UNumericType { - U_NT_NONE, /*[None]*/ /*See note !!*/ - U_NT_DECIMAL, /*[de]*/ - U_NT_DIGIT, /*[di]*/ - U_NT_NUMERIC, /*[nu]*/ - U_NT_COUNT -} UNumericType; - -/** - * Hangul Syllable Type constants. - * - * @see UCHAR_HANGUL_SYLLABLE_TYPE - * @stable ICU 2.6 - */ -typedef enum UHangulSyllableType { - U_HST_NOT_APPLICABLE, /*[NA]*/ /*See note !!*/ - U_HST_LEADING_JAMO, /*[L]*/ - U_HST_VOWEL_JAMO, /*[V]*/ - U_HST_TRAILING_JAMO, /*[T]*/ - U_HST_LV_SYLLABLE, /*[LV]*/ - U_HST_LVT_SYLLABLE, /*[LVT]*/ - U_HST_COUNT -} UHangulSyllableType; - -/** - * Check a binary Unicode property for a code point. - * - * Unicode, especially in version 3.2, defines many more properties than the - * original set in UnicodeData.txt. - * - * The properties APIs are intended to reflect Unicode properties as defined - * in the Unicode Character Database (UCD) and Unicode Technical Reports (UTR). - * For details about the properties see http://www.unicode.org/ucd/ . - * For names of Unicode properties see the UCD file PropertyAliases.txt. - * - * Important: If ICU is built with UCD files from Unicode versions below 3.2, - * then properties marked with "new in Unicode 3.2" are not or not fully available. - * - * @param c Code point to test. - * @param which UProperty selector constant, identifies which binary property to check. - * Must be UCHAR_BINARY_START<=which<UCHAR_BINARY_LIMIT. - * @return TRUE or FALSE according to the binary Unicode property value for c. - * Also FALSE if 'which' is out of bounds or if the Unicode version - * does not have data for the property at all, or not for this code point. - * - * @see UProperty - * @see u_getIntPropertyValue - * @see u_getUnicodeVersion - * @stable ICU 2.1 - */ -U_STABLE UBool U_EXPORT2 -u_hasBinaryProperty(UChar32 c, UProperty which); - -/** - * Check if a code point has the Alphabetic Unicode property. - * Same as u_hasBinaryProperty(c, UCHAR_ALPHABETIC). - * This is different from u_isalpha! - * @param c Code point to test - * @return true if the code point has the Alphabetic Unicode property, false otherwise - * - * @see UCHAR_ALPHABETIC - * @see u_isalpha - * @see u_hasBinaryProperty - * @stable ICU 2.1 - */ -U_STABLE UBool U_EXPORT2 -u_isUAlphabetic(UChar32 c); - -/** - * Check if a code point has the Lowercase Unicode property. - * Same as u_hasBinaryProperty(c, UCHAR_LOWERCASE). - * This is different from u_islower! - * @param c Code point to test - * @return true if the code point has the Lowercase Unicode property, false otherwise - * - * @see UCHAR_LOWERCASE - * @see u_islower - * @see u_hasBinaryProperty - * @stable ICU 2.1 - */ -U_STABLE UBool U_EXPORT2 -u_isULowercase(UChar32 c); - -/** - * Check if a code point has the Uppercase Unicode property. - * Same as u_hasBinaryProperty(c, UCHAR_UPPERCASE). - * This is different from u_isupper! - * @param c Code point to test - * @return true if the code point has the Uppercase Unicode property, false otherwise - * - * @see UCHAR_UPPERCASE - * @see u_isupper - * @see u_hasBinaryProperty - * @stable ICU 2.1 - */ -U_STABLE UBool U_EXPORT2 -u_isUUppercase(UChar32 c); - -/** - * Check if a code point has the White_Space Unicode property. - * Same as u_hasBinaryProperty(c, UCHAR_WHITE_SPACE). - * This is different from both u_isspace and u_isWhitespace! - * - * Note: There are several ICU whitespace functions; please see the uchar.h - * file documentation for a detailed comparison. - * - * @param c Code point to test - * @return true if the code point has the White_Space Unicode property, false otherwise. - * - * @see UCHAR_WHITE_SPACE - * @see u_isWhitespace - * @see u_isspace - * @see u_isJavaSpaceChar - * @see u_hasBinaryProperty - * @stable ICU 2.1 - */ -U_STABLE UBool U_EXPORT2 -u_isUWhiteSpace(UChar32 c); - -/** - * Get the property value for an enumerated or integer Unicode property for a code point. - * Also returns binary and mask property values. - * - * Unicode, especially in version 3.2, defines many more properties than the - * original set in UnicodeData.txt. - * - * The properties APIs are intended to reflect Unicode properties as defined - * in the Unicode Character Database (UCD) and Unicode Technical Reports (UTR). - * For details about the properties see http://www.unicode.org/ . - * For names of Unicode properties see the UCD file PropertyAliases.txt. - * - * Sample usage: - * UEastAsianWidth ea=(UEastAsianWidth)u_getIntPropertyValue(c, UCHAR_EAST_ASIAN_WIDTH); - * UBool b=(UBool)u_getIntPropertyValue(c, UCHAR_IDEOGRAPHIC); - * - * @param c Code point to test. - * @param which UProperty selector constant, identifies which property to check. - * Must be UCHAR_BINARY_START<=which<UCHAR_BINARY_LIMIT - * or UCHAR_INT_START<=which<UCHAR_INT_LIMIT - * or UCHAR_MASK_START<=which<UCHAR_MASK_LIMIT. - * @return Numeric value that is directly the property value or, - * for enumerated properties, corresponds to the numeric value of the enumerated - * constant of the respective property value enumeration type - * (cast to enum type if necessary). - * Returns 0 or 1 (for FALSE/TRUE) for binary Unicode properties. - * Returns a bit-mask for mask properties. - * Returns 0 if 'which' is out of bounds or if the Unicode version - * does not have data for the property at all, or not for this code point. - * - * @see UProperty - * @see u_hasBinaryProperty - * @see u_getIntPropertyMinValue - * @see u_getIntPropertyMaxValue - * @see u_getUnicodeVersion - * @stable ICU 2.2 - */ -U_STABLE int32_t U_EXPORT2 -u_getIntPropertyValue(UChar32 c, UProperty which); - -/** - * Get the minimum value for an enumerated/integer/binary Unicode property. - * Can be used together with u_getIntPropertyMaxValue - * to allocate arrays of UnicodeSet or similar. - * - * @param which UProperty selector constant, identifies which binary property to check. - * Must be UCHAR_BINARY_START<=which<UCHAR_BINARY_LIMIT - * or UCHAR_INT_START<=which<UCHAR_INT_LIMIT. - * @return Minimum value returned by u_getIntPropertyValue for a Unicode property. - * 0 if the property selector is out of range. - * - * @see UProperty - * @see u_hasBinaryProperty - * @see u_getUnicodeVersion - * @see u_getIntPropertyMaxValue - * @see u_getIntPropertyValue - * @stable ICU 2.2 - */ -U_STABLE int32_t U_EXPORT2 -u_getIntPropertyMinValue(UProperty which); - -/** - * Get the maximum value for an enumerated/integer/binary Unicode property. - * Can be used together with u_getIntPropertyMinValue - * to allocate arrays of UnicodeSet or similar. - * - * Examples for min/max values (for Unicode 3.2): - * - * - UCHAR_BIDI_CLASS: 0/18 (U_LEFT_TO_RIGHT/U_BOUNDARY_NEUTRAL) - * - UCHAR_SCRIPT: 0/45 (USCRIPT_COMMON/USCRIPT_TAGBANWA) - * - UCHAR_IDEOGRAPHIC: 0/1 (FALSE/TRUE) - * - * For undefined UProperty constant values, min/max values will be 0/-1. - * - * @param which UProperty selector constant, identifies which binary property to check. - * Must be UCHAR_BINARY_START<=which<UCHAR_BINARY_LIMIT - * or UCHAR_INT_START<=which<UCHAR_INT_LIMIT. - * @return Maximum value returned by u_getIntPropertyValue for a Unicode property. - * <=0 if the property selector is out of range. - * - * @see UProperty - * @see u_hasBinaryProperty - * @see u_getUnicodeVersion - * @see u_getIntPropertyMaxValue - * @see u_getIntPropertyValue - * @stable ICU 2.2 - */ -U_STABLE int32_t U_EXPORT2 -u_getIntPropertyMaxValue(UProperty which); - -/** - * Get the numeric value for a Unicode code point as defined in the - * Unicode Character Database. - * - * A "double" return type is necessary because - * some numeric values are fractions, negative, or too large for int32_t. - * - * For characters without any numeric values in the Unicode Character Database, - * this function will return U_NO_NUMERIC_VALUE. - * - * Similar to java.lang.Character.getNumericValue(), but u_getNumericValue() - * also supports negative values, large values, and fractions, - * while Java's getNumericValue() returns values 10..35 for ASCII letters. - * - * @param c Code point to get the numeric value for. - * @return Numeric value of c, or U_NO_NUMERIC_VALUE if none is defined. - * - * @see U_NO_NUMERIC_VALUE - * @stable ICU 2.2 - */ -U_STABLE double U_EXPORT2 -u_getNumericValue(UChar32 c); - -/** - * Special value that is returned by u_getNumericValue when - * no numeric value is defined for a code point. - * - * @see u_getNumericValue - * @stable ICU 2.2 - */ -#define U_NO_NUMERIC_VALUE ((double)-123456789.) - -/** - * Determines whether the specified code point has the general category "Ll" - * (lowercase letter). - * - * Same as java.lang.Character.isLowerCase(). - * - * This misses some characters that are also lowercase but - * have a different general category value. - * In order to include those, use UCHAR_LOWERCASE. - * - * In addition to being equivalent to a Java function, this also serves - * as a C/POSIX migration function. - * See the comments about C/POSIX character classification functions in the - * documentation at the top of this header file. - * - * @param c the code point to be tested - * @return TRUE if the code point is an Ll lowercase letter - * - * @see UCHAR_LOWERCASE - * @see u_isupper - * @see u_istitle - * @see u_islower - * @stable ICU 2.0 - */ -U_STABLE UBool U_EXPORT2 -u_islower(UChar32 c); - -/** - * Determines whether the specified code point has the general category "Lu" - * (uppercase letter). - * - * Same as java.lang.Character.isUpperCase(). - * - * This misses some characters that are also uppercase but - * have a different general category value. - * In order to include those, use UCHAR_UPPERCASE. - * - * In addition to being equivalent to a Java function, this also serves - * as a C/POSIX migration function. - * See the comments about C/POSIX character classification functions in the - * documentation at the top of this header file. - * - * @param c the code point to be tested - * @return TRUE if the code point is an Lu uppercase letter - * - * @see UCHAR_UPPERCASE - * @see u_islower - * @see u_istitle - * @see u_tolower - * @stable ICU 2.0 - */ -U_STABLE UBool U_EXPORT2 -u_isupper(UChar32 c); - -/** - * Determines whether the specified code point is a titlecase letter. - * True for general category "Lt" (titlecase letter). - * - * Same as java.lang.Character.isTitleCase(). - * - * @param c the code point to be tested - * @return TRUE if the code point is an Lt titlecase letter - * - * @see u_isupper - * @see u_islower - * @see u_totitle - * @stable ICU 2.0 - */ -U_STABLE UBool U_EXPORT2 -u_istitle(UChar32 c); - -/** - * Determines whether the specified code point is a digit character according to Java. - * True for characters with general category "Nd" (decimal digit numbers). - * Beginning with Unicode 4, this is the same as - * testing for the Numeric_Type of Decimal. - * - * Same as java.lang.Character.isDigit(). - * - * In addition to being equivalent to a Java function, this also serves - * as a C/POSIX migration function. - * See the comments about C/POSIX character classification functions in the - * documentation at the top of this header file. - * - * @param c the code point to be tested - * @return TRUE if the code point is a digit character according to Character.isDigit() - * - * @stable ICU 2.0 - */ -U_STABLE UBool U_EXPORT2 -u_isdigit(UChar32 c); - -/** - * Determines whether the specified code point is a letter character. - * True for general categories "L" (letters). - * - * Same as java.lang.Character.isLetter(). - * - * In addition to being equivalent to a Java function, this also serves - * as a C/POSIX migration function. - * See the comments about C/POSIX character classification functions in the - * documentation at the top of this header file. - * - * @param c the code point to be tested - * @return TRUE if the code point is a letter character - * - * @see u_isdigit - * @see u_isalnum - * @stable ICU 2.0 - */ -U_STABLE UBool U_EXPORT2 -u_isalpha(UChar32 c); - -/** - * Determines whether the specified code point is an alphanumeric character - * (letter or digit) according to Java. - * True for characters with general categories - * "L" (letters) and "Nd" (decimal digit numbers). - * - * Same as java.lang.Character.isLetterOrDigit(). - * - * In addition to being equivalent to a Java function, this also serves - * as a C/POSIX migration function. - * See the comments about C/POSIX character classification functions in the - * documentation at the top of this header file. - * - * @param c the code point to be tested - * @return TRUE if the code point is an alphanumeric character according to Character.isLetterOrDigit() - * - * @stable ICU 2.0 - */ -U_STABLE UBool U_EXPORT2 -u_isalnum(UChar32 c); - -/** - * Determines whether the specified code point is a hexadecimal digit. - * This is equivalent to u_digit(c, 16)>=0. - * True for characters with general category "Nd" (decimal digit numbers) - * as well as Latin letters a-f and A-F in both ASCII and Fullwidth ASCII. - * (That is, for letters with code points - * 0041..0046, 0061..0066, FF21..FF26, FF41..FF46.) - * - * In order to narrow the definition of hexadecimal digits to only ASCII - * characters, use (c<=0x7f && u_isxdigit(c)). - * - * This is a C/POSIX migration function. - * See the comments about C/POSIX character classification functions in the - * documentation at the top of this header file. - * - * @param c the code point to be tested - * @return TRUE if the code point is a hexadecimal digit - * - * @stable ICU 2.6 - */ -U_STABLE UBool U_EXPORT2 -u_isxdigit(UChar32 c); - -/** - * Determines whether the specified code point is a punctuation character. - * True for characters with general categories "P" (punctuation). - * - * This is a C/POSIX migration function. - * See the comments about C/POSIX character classification functions in the - * documentation at the top of this header file. - * - * @param c the code point to be tested - * @return TRUE if the code point is a punctuation character - * - * @stable ICU 2.6 - */ -U_STABLE UBool U_EXPORT2 -u_ispunct(UChar32 c); - -/** - * Determines whether the specified code point is a "graphic" character - * (printable, excluding spaces). - * TRUE for all characters except those with general categories - * "Cc" (control codes), "Cf" (format controls), "Cs" (surrogates), - * "Cn" (unassigned), and "Z" (separators). - * - * This is a C/POSIX migration function. - * See the comments about C/POSIX character classification functions in the - * documentation at the top of this header file. - * - * @param c the code point to be tested - * @return TRUE if the code point is a "graphic" character - * - * @stable ICU 2.6 - */ -U_STABLE UBool U_EXPORT2 -u_isgraph(UChar32 c); - -/** - * Determines whether the specified code point is a "blank" or "horizontal space", - * a character that visibly separates words on a line. - * The following are equivalent definitions: - * - * TRUE for Unicode White_Space characters except for "vertical space controls" - * where "vertical space controls" are the following characters: - * U+000A (LF) U+000B (VT) U+000C (FF) U+000D (CR) U+0085 (NEL) U+2028 (LS) U+2029 (PS) - * - * same as - * - * TRUE for U+0009 (TAB) and characters with general category "Zs" (space separators) - * except Zero Width Space (ZWSP, U+200B). - * - * Note: There are several ICU whitespace functions; please see the uchar.h - * file documentation for a detailed comparison. - * - * This is a C/POSIX migration function. - * See the comments about C/POSIX character classification functions in the - * documentation at the top of this header file. - * - * @param c the code point to be tested - * @return TRUE if the code point is a "blank" - * - * @stable ICU 2.6 - */ -U_STABLE UBool U_EXPORT2 -u_isblank(UChar32 c); - -/** - * Determines whether the specified code point is "defined", - * which usually means that it is assigned a character. - * True for general categories other than "Cn" (other, not assigned), - * i.e., true for all code points mentioned in UnicodeData.txt. - * - * Note that non-character code points (e.g., U+FDD0) are not "defined" - * (they are Cn), but surrogate code points are "defined" (Cs). - * - * Same as java.lang.Character.isDefined(). - * - * @param c the code point to be tested - * @return TRUE if the code point is assigned a character - * - * @see u_isdigit - * @see u_isalpha - * @see u_isalnum - * @see u_isupper - * @see u_islower - * @see u_istitle - * @stable ICU 2.0 - */ -U_STABLE UBool U_EXPORT2 -u_isdefined(UChar32 c); - -/** - * Determines if the specified character is a space character or not. - * - * Note: There are several ICU whitespace functions; please see the uchar.h - * file documentation for a detailed comparison. - * - * This is a C/POSIX migration function. - * See the comments about C/POSIX character classification functions in the - * documentation at the top of this header file. - * - * @param c the character to be tested - * @return true if the character is a space character; false otherwise. - * - * @see u_isJavaSpaceChar - * @see u_isWhitespace - * @see u_isUWhiteSpace - * @stable ICU 2.0 - */ -U_STABLE UBool U_EXPORT2 -u_isspace(UChar32 c); - -/** - * Determine if the specified code point is a space character according to Java. - * True for characters with general categories "Z" (separators), - * which does not include control codes (e.g., TAB or Line Feed). - * - * Same as java.lang.Character.isSpaceChar(). - * - * Note: There are several ICU whitespace functions; please see the uchar.h - * file documentation for a detailed comparison. - * - * @param c the code point to be tested - * @return TRUE if the code point is a space character according to Character.isSpaceChar() - * - * @see u_isspace - * @see u_isWhitespace - * @see u_isUWhiteSpace - * @stable ICU 2.6 - */ -U_STABLE UBool U_EXPORT2 -u_isJavaSpaceChar(UChar32 c); - -/** - * Determines if the specified code point is a whitespace character according to Java/ICU. - * A character is considered to be a Java whitespace character if and only - * if it satisfies one of the following criteria: - * - * - It is a Unicode separator (categories "Z"), but is not - * a no-break space (U+00A0 NBSP or U+2007 Figure Space or U+202F Narrow NBSP). - * - It is U+0009 HORIZONTAL TABULATION. - * - It is U+000A LINE FEED. - * - It is U+000B VERTICAL TABULATION. - * - It is U+000C FORM FEED. - * - It is U+000D CARRIAGE RETURN. - * - It is U+001C FILE SEPARATOR. - * - It is U+001D GROUP SEPARATOR. - * - It is U+001E RECORD SEPARATOR. - * - It is U+001F UNIT SEPARATOR. - * - It is U+0085 NEXT LINE. - * - * Same as java.lang.Character.isWhitespace() except that Java omits U+0085. - * - * Note: There are several ICU whitespace functions; please see the uchar.h - * file documentation for a detailed comparison. - * - * @param c the code point to be tested - * @return TRUE if the code point is a whitespace character according to Java/ICU - * - * @see u_isspace - * @see u_isJavaSpaceChar - * @see u_isUWhiteSpace - * @stable ICU 2.0 - */ -U_STABLE UBool U_EXPORT2 -u_isWhitespace(UChar32 c); - -/** - * Determines whether the specified code point is a control character - * (as defined by this function). - * A control character is one of the following: - * - ISO 8-bit control character (U+0000..U+001f and U+007f..U+009f) - * - U_CONTROL_CHAR (Cc) - * - U_FORMAT_CHAR (Cf) - * - U_LINE_SEPARATOR (Zl) - * - U_PARAGRAPH_SEPARATOR (Zp) - * - * This is a C/POSIX migration function. - * See the comments about C/POSIX character classification functions in the - * documentation at the top of this header file. - * - * @param c the code point to be tested - * @return TRUE if the code point is a control character - * - * @see UCHAR_DEFAULT_IGNORABLE_CODE_POINT - * @see u_isprint - * @stable ICU 2.0 - */ -U_STABLE UBool U_EXPORT2 -u_iscntrl(UChar32 c); - -/** - * Determines whether the specified code point is an ISO control code. - * True for U+0000..U+001f and U+007f..U+009f (general category "Cc"). - * - * Same as java.lang.Character.isISOControl(). - * - * @param c the code point to be tested - * @return TRUE if the code point is an ISO control code - * - * @see u_iscntrl - * @stable ICU 2.6 - */ -U_STABLE UBool U_EXPORT2 -u_isISOControl(UChar32 c); - -/** - * Determines whether the specified code point is a printable character. - * True for general categories <em>other</em> than "C" (controls). - * - * This is a C/POSIX migration function. - * See the comments about C/POSIX character classification functions in the - * documentation at the top of this header file. - * - * @param c the code point to be tested - * @return TRUE if the code point is a printable character - * - * @see UCHAR_DEFAULT_IGNORABLE_CODE_POINT - * @see u_iscntrl - * @stable ICU 2.0 - */ -U_STABLE UBool U_EXPORT2 -u_isprint(UChar32 c); - -/** - * Determines whether the specified code point is a base character. - * True for general categories "L" (letters), "N" (numbers), - * "Mc" (spacing combining marks), and "Me" (enclosing marks). - * - * Note that this is different from the Unicode definition in - * chapter 3.5, conformance clause D13, - * which defines base characters to be all characters (not Cn) - * that do not graphically combine with preceding characters (M) - * and that are neither control (Cc) or format (Cf) characters. - * - * @param c the code point to be tested - * @return TRUE if the code point is a base character according to this function - * - * @see u_isalpha - * @see u_isdigit - * @stable ICU 2.0 - */ -U_STABLE UBool U_EXPORT2 -u_isbase(UChar32 c); - -/** - * Returns the bidirectional category value for the code point, - * which is used in the Unicode bidirectional algorithm - * (UAX #9 http://www.unicode.org/reports/tr9/). - * Note that some <em>unassigned</em> code points have bidi values - * of R or AL because they are in blocks that are reserved - * for Right-To-Left scripts. - * - * Same as java.lang.Character.getDirectionality() - * - * @param c the code point to be tested - * @return the bidirectional category (UCharDirection) value - * - * @see UCharDirection - * @stable ICU 2.0 - */ -U_STABLE UCharDirection U_EXPORT2 -u_charDirection(UChar32 c); - -/** - * Determines whether the code point has the Bidi_Mirrored property. - * This property is set for characters that are commonly used in - * Right-To-Left contexts and need to be displayed with a "mirrored" - * glyph. - * - * Same as java.lang.Character.isMirrored(). - * Same as UCHAR_BIDI_MIRRORED - * - * @param c the code point to be tested - * @return TRUE if the character has the Bidi_Mirrored property - * - * @see UCHAR_BIDI_MIRRORED - * @stable ICU 2.0 - */ -U_STABLE UBool U_EXPORT2 -u_isMirrored(UChar32 c); - -/** - * Maps the specified character to a "mirror-image" character. - * For characters with the Bidi_Mirrored property, implementations - * sometimes need a "poor man's" mapping to another Unicode - * character (code point) such that the default glyph may serve - * as the mirror-image of the default glyph of the specified - * character. This is useful for text conversion to and from - * codepages with visual order, and for displays without glyph - * selecetion capabilities. - * - * @param c the code point to be mapped - * @return another Unicode code point that may serve as a mirror-image - * substitute, or c itself if there is no such mapping or c - * does not have the Bidi_Mirrored property - * - * @see UCHAR_BIDI_MIRRORED - * @see u_isMirrored - * @stable ICU 2.0 - */ -U_STABLE UChar32 U_EXPORT2 -u_charMirror(UChar32 c); - -/** - * Returns the general category value for the code point. - * - * Same as java.lang.Character.getType(). - * - * @param c the code point to be tested - * @return the general category (UCharCategory) value - * - * @see UCharCategory - * @stable ICU 2.0 - */ -U_STABLE int8_t U_EXPORT2 -u_charType(UChar32 c); - -/** - * Get a single-bit bit set for the general category of a character. - * This bit set can be compared bitwise with U_GC_SM_MASK, U_GC_L_MASK, etc. - * Same as U_MASK(u_charType(c)). - * - * @param c the code point to be tested - * @return a single-bit mask corresponding to the general category (UCharCategory) value - * - * @see u_charType - * @see UCharCategory - * @see U_GC_CN_MASK - * @stable ICU 2.1 - */ -#define U_GET_GC_MASK(c) U_MASK(u_charType(c)) - -/** - * Callback from u_enumCharTypes(), is called for each contiguous range - * of code points c (where start<=c<limit) - * with the same Unicode general category ("character type"). - * - * The callback function can stop the enumeration by returning FALSE. - * - * @param context an opaque pointer, as passed into utrie_enum() - * @param start the first code point in a contiguous range with value - * @param limit one past the last code point in a contiguous range with value - * @param type the general category for all code points in [start..limit[ - * @return FALSE to stop the enumeration - * - * @stable ICU 2.1 - * @see UCharCategory - * @see u_enumCharTypes - */ -typedef UBool U_CALLCONV -UCharEnumTypeRange(const void *context, UChar32 start, UChar32 limit, UCharCategory type); - -/** - * Enumerate efficiently all code points with their Unicode general categories. - * - * This is useful for building data structures (e.g., UnicodeSet's), - * for enumerating all assigned code points (type!=U_UNASSIGNED), etc. - * - * For each contiguous range of code points with a given general category ("character type"), - * the UCharEnumTypeRange function is called. - * Adjacent ranges have different types. - * The Unicode Standard guarantees that the numeric value of the type is 0..31. - * - * @param enumRange a pointer to a function that is called for each contiguous range - * of code points with the same general category - * @param context an opaque pointer that is passed on to the callback function - * - * @stable ICU 2.1 - * @see UCharCategory - * @see UCharEnumTypeRange - */ -U_STABLE void U_EXPORT2 -u_enumCharTypes(UCharEnumTypeRange *enumRange, const void *context); - -#if !UCONFIG_NO_NORMALIZATION - -/** - * Returns the combining class of the code point as specified in UnicodeData.txt. - * - * @param c the code point of the character - * @return the combining class of the character - * @stable ICU 2.0 - */ -U_STABLE uint8_t U_EXPORT2 -u_getCombiningClass(UChar32 c); - -#endif - -/** - * Returns the decimal digit value of a decimal digit character. - * Such characters have the general category "Nd" (decimal digit numbers) - * and a Numeric_Type of Decimal. - * - * Unlike ICU releases before 2.6, no digit values are returned for any - * Han characters because Han number characters are often used with a special - * Chinese-style number format (with characters for powers of 10 in between) - * instead of in decimal-positional notation. - * Unicode 4 explicitly assigns Han number characters the Numeric_Type - * Numeric instead of Decimal. - * See Jitterbug 1483 for more details. - * - * Use u_getIntPropertyValue(c, UCHAR_NUMERIC_TYPE) and u_getNumericValue() - * for complete numeric Unicode properties. - * - * @param c the code point for which to get the decimal digit value - * @return the decimal digit value of c, - * or -1 if c is not a decimal digit character - * - * @see u_getNumericValue - * @stable ICU 2.0 - */ -U_STABLE int32_t U_EXPORT2 -u_charDigitValue(UChar32 c); - -/** - * Returns the Unicode allocation block that contains the character. - * - * @param c the code point to be tested - * @return the block value (UBlockCode) for c - * - * @see UBlockCode - * @stable ICU 2.0 - */ -U_STABLE UBlockCode U_EXPORT2 -ublock_getCode(UChar32 c); - -/** - * Retrieve the name of a Unicode character. - * Depending on <code>nameChoice</code>, the character name written - * into the buffer is the "modern" name or the name that was defined - * in Unicode version 1.0. - * The name contains only "invariant" characters - * like A-Z, 0-9, space, and '-'. - * Unicode 1.0 names are only retrieved if they are different from the modern - * names and if the data file contains the data for them. gennames may or may - * not be called with a command line option to include 1.0 names in unames.dat. - * - * @param code The character (code point) for which to get the name. - * It must be <code>0<=code<=0x10ffff</code>. - * @param nameChoice Selector for which name to get. - * @param buffer Destination address for copying the name. - * The name will always be zero-terminated. - * If there is no name, then the buffer will be set to the empty string. - * @param bufferLength <code>==sizeof(buffer)</code> - * @param pErrorCode Pointer to a UErrorCode variable; - * check for <code>U_SUCCESS()</code> after <code>u_charName()</code> - * returns. - * @return The length of the name, or 0 if there is no name for this character. - * If the bufferLength is less than or equal to the length, then the buffer - * contains the truncated name and the returned length indicates the full - * length of the name. - * The length does not include the zero-termination. - * - * @see UCharNameChoice - * @see u_charFromName - * @see u_enumCharNames - * @stable ICU 2.0 - */ -U_STABLE int32_t U_EXPORT2 -u_charName(UChar32 code, UCharNameChoice nameChoice, - char *buffer, int32_t bufferLength, - UErrorCode *pErrorCode); - -/** - * Get the ISO 10646 comment for a character. - * The ISO 10646 comment is an informative field in the Unicode Character - * Database (UnicodeData.txt field 11) and is from the ISO 10646 names list. - * - * @param c The character (code point) for which to get the ISO comment. - * It must be <code>0<=c<=0x10ffff</code>. - * @param dest Destination address for copying the comment. - * The comment will be zero-terminated if possible. - * If there is no comment, then the buffer will be set to the empty string. - * @param destCapacity <code>==sizeof(dest)</code> - * @param pErrorCode Pointer to a UErrorCode variable; - * check for <code>U_SUCCESS()</code> after <code>u_getISOComment()</code> - * returns. - * @return The length of the comment, or 0 if there is no comment for this character. - * If the destCapacity is less than or equal to the length, then the buffer - * contains the truncated name and the returned length indicates the full - * length of the name. - * The length does not include the zero-termination. - * - * @stable ICU 2.2 - */ -U_STABLE int32_t U_EXPORT2 -u_getISOComment(UChar32 c, - char *dest, int32_t destCapacity, - UErrorCode *pErrorCode); - -/** - * Find a Unicode character by its name and return its code point value. - * The name is matched exactly and completely. - * If the name does not correspond to a code point, <i>pErrorCode</i> - * is set to <code>U_INVALID_CHAR_FOUND</code>. - * A Unicode 1.0 name is matched only if it differs from the modern name. - * Unicode names are all uppercase. Extended names are lowercase followed - * by an uppercase hexadecimal number, and within angle brackets. - * - * @param nameChoice Selector for which name to match. - * @param name The name to match. - * @param pErrorCode Pointer to a UErrorCode variable - * @return The Unicode value of the code point with the given name, - * or an undefined value if there is no such code point. - * - * @see UCharNameChoice - * @see u_charName - * @see u_enumCharNames - * @stable ICU 1.7 - */ -U_STABLE UChar32 U_EXPORT2 -u_charFromName(UCharNameChoice nameChoice, - const char *name, - UErrorCode *pErrorCode); - -/** - * Type of a callback function for u_enumCharNames() that gets called - * for each Unicode character with the code point value and - * the character name. - * If such a function returns FALSE, then the enumeration is stopped. - * - * @param context The context pointer that was passed to u_enumCharNames(). - * @param code The Unicode code point for the character with this name. - * @param nameChoice Selector for which kind of names is enumerated. - * @param name The character's name, zero-terminated. - * @param length The length of the name. - * @return TRUE if the enumeration should continue, FALSE to stop it. - * - * @see UCharNameChoice - * @see u_enumCharNames - * @stable ICU 1.7 - */ -typedef UBool UEnumCharNamesFn(void *context, - UChar32 code, - UCharNameChoice nameChoice, - const char *name, - int32_t length); - -/** - * Enumerate all assigned Unicode characters between the start and limit - * code points (start inclusive, limit exclusive) and call a function - * for each, passing the code point value and the character name. - * For Unicode 1.0 names, only those are enumerated that differ from the - * modern names. - * - * @param start The first code point in the enumeration range. - * @param limit One more than the last code point in the enumeration range - * (the first one after the range). - * @param fn The function that is to be called for each character name. - * @param context An arbitrary pointer that is passed to the function. - * @param nameChoice Selector for which kind of names to enumerate. - * @param pErrorCode Pointer to a UErrorCode variable - * - * @see UCharNameChoice - * @see UEnumCharNamesFn - * @see u_charName - * @see u_charFromName - * @stable ICU 1.7 - */ -U_STABLE void U_EXPORT2 -u_enumCharNames(UChar32 start, UChar32 limit, - UEnumCharNamesFn *fn, - void *context, - UCharNameChoice nameChoice, - UErrorCode *pErrorCode); - -/** - * Return the Unicode name for a given property, as given in the - * Unicode database file PropertyAliases.txt. - * - * In addition, this function maps the property - * UCHAR_GENERAL_CATEGORY_MASK to the synthetic names "gcm" / - * "General_Category_Mask". These names are not in - * PropertyAliases.txt. - * - * @param property UProperty selector other than UCHAR_INVALID_CODE. - * If out of range, NULL is returned. - * - * @param nameChoice selector for which name to get. If out of range, - * NULL is returned. All properties have a long name. Most - * have a short name, but some do not. Unicode allows for - * additional names; if present these will be returned by - * U_LONG_PROPERTY_NAME + i, where i=1, 2,... - * - * @return a pointer to the name, or NULL if either the - * property or the nameChoice is out of range. If a given - * nameChoice returns NULL, then all larger values of - * nameChoice will return NULL, with one exception: if NULL is - * returned for U_SHORT_PROPERTY_NAME, then - * U_LONG_PROPERTY_NAME (and higher) may still return a - * non-NULL value. The returned pointer is valid until - * u_cleanup() is called. - * - * @see UProperty - * @see UPropertyNameChoice - * @stable ICU 2.4 - */ -U_STABLE const char* U_EXPORT2 -u_getPropertyName(UProperty property, - UPropertyNameChoice nameChoice); - -/** - * Return the UProperty enum for a given property name, as specified - * in the Unicode database file PropertyAliases.txt. Short, long, and - * any other variants are recognized. - * - * In addition, this function maps the synthetic names "gcm" / - * "General_Category_Mask" to the property - * UCHAR_GENERAL_CATEGORY_MASK. These names are not in - * PropertyAliases.txt. - * - * @param alias the property name to be matched. The name is compared - * using "loose matching" as described in PropertyAliases.txt. - * - * @return a UProperty enum, or UCHAR_INVALID_CODE if the given name - * does not match any property. - * - * @see UProperty - * @stable ICU 2.4 - */ -U_STABLE UProperty U_EXPORT2 -u_getPropertyEnum(const char* alias); - -/** - * Return the Unicode name for a given property value, as given in the - * Unicode database file PropertyValueAliases.txt. - * - * Note: Some of the names in PropertyValueAliases.txt can only be - * retrieved using UCHAR_GENERAL_CATEGORY_MASK, not - * UCHAR_GENERAL_CATEGORY. These include: "C" / "Other", "L" / - * "Letter", "LC" / "Cased_Letter", "M" / "Mark", "N" / "Number", "P" - * / "Punctuation", "S" / "Symbol", and "Z" / "Separator". - * - * @param property UProperty selector constant. - * Must be UCHAR_BINARY_START<=which<UCHAR_BINARY_LIMIT - * or UCHAR_INT_START<=which<UCHAR_INT_LIMIT - * or UCHAR_MASK_START<=which<UCHAR_MASK_LIMIT. - * If out of range, NULL is returned. - * - * @param value selector for a value for the given property. If out - * of range, NULL is returned. In general, valid values range - * from 0 up to some maximum. There are a few exceptions: - * (1.) UCHAR_BLOCK values begin at the non-zero value - * UBLOCK_BASIC_LATIN. (2.) UCHAR_CANONICAL_COMBINING_CLASS - * values are not contiguous and range from 0..240. (3.) - * UCHAR_GENERAL_CATEGORY_MASK values are not values of - * UCharCategory, but rather mask values produced by - * U_GET_GC_MASK(). This allows grouped categories such as - * [:L:] to be represented. Mask values range - * non-contiguously from 1..U_GC_P_MASK. - * - * @param nameChoice selector for which name to get. If out of range, - * NULL is returned. All values have a long name. Most have - * a short name, but some do not. Unicode allows for - * additional names; if present these will be returned by - * U_LONG_PROPERTY_NAME + i, where i=1, 2,... - - * @return a pointer to the name, or NULL if either the - * property or the nameChoice is out of range. If a given - * nameChoice returns NULL, then all larger values of - * nameChoice will return NULL, with one exception: if NULL is - * returned for U_SHORT_PROPERTY_NAME, then - * U_LONG_PROPERTY_NAME (and higher) may still return a - * non-NULL value. The returned pointer is valid until - * u_cleanup() is called. - * - * @see UProperty - * @see UPropertyNameChoice - * @stable ICU 2.4 - */ -U_STABLE const char* U_EXPORT2 -u_getPropertyValueName(UProperty property, - int32_t value, - UPropertyNameChoice nameChoice); - -/** - * Return the property value integer for a given value name, as - * specified in the Unicode database file PropertyValueAliases.txt. - * Short, long, and any other variants are recognized. - * - * Note: Some of the names in PropertyValueAliases.txt will only be - * recognized with UCHAR_GENERAL_CATEGORY_MASK, not - * UCHAR_GENERAL_CATEGORY. These include: "C" / "Other", "L" / - * "Letter", "LC" / "Cased_Letter", "M" / "Mark", "N" / "Number", "P" - * / "Punctuation", "S" / "Symbol", and "Z" / "Separator". - * - * @param property UProperty selector constant. - * Must be UCHAR_BINARY_START<=which<UCHAR_BINARY_LIMIT - * or UCHAR_INT_START<=which<UCHAR_INT_LIMIT - * or UCHAR_MASK_START<=which<UCHAR_MASK_LIMIT. - * If out of range, UCHAR_INVALID_CODE is returned. - * - * @param alias the value name to be matched. The name is compared - * using "loose matching" as described in - * PropertyValueAliases.txt. - * - * @return a value integer or UCHAR_INVALID_CODE if the given name - * does not match any value of the given property, or if the - * property is invalid. Note: U CHAR_GENERAL_CATEGORY values - * are not values of UCharCategory, but rather mask values - * produced by U_GET_GC_MASK(). This allows grouped - * categories such as [:L:] to be represented. - * - * @see UProperty - * @stable ICU 2.4 - */ -U_STABLE int32_t U_EXPORT2 -u_getPropertyValueEnum(UProperty property, - const char* alias); - -/** - * Determines if the specified character is permissible as the - * first character in an identifier according to Unicode - * (The Unicode Standard, Version 3.0, chapter 5.16 Identifiers). - * True for characters with general categories "L" (letters) and "Nl" (letter numbers). - * - * Same as java.lang.Character.isUnicodeIdentifierStart(). - * Same as UCHAR_ID_START - * - * @param c the code point to be tested - * @return TRUE if the code point may start an identifier - * - * @see UCHAR_ID_START - * @see u_isalpha - * @see u_isIDPart - * @stable ICU 2.0 - */ -U_STABLE UBool U_EXPORT2 -u_isIDStart(UChar32 c); - -/** - * Determines if the specified character is permissible - * in an identifier according to Java. - * True for characters with general categories "L" (letters), - * "Nl" (letter numbers), "Nd" (decimal digits), - * "Mc" and "Mn" (combining marks), "Pc" (connecting punctuation), and - * u_isIDIgnorable(c). - * - * Same as java.lang.Character.isUnicodeIdentifierPart(). - * Almost the same as Unicode's ID_Continue (UCHAR_ID_CONTINUE) - * except that Unicode recommends to ignore Cf which is less than - * u_isIDIgnorable(c). - * - * @param c the code point to be tested - * @return TRUE if the code point may occur in an identifier according to Java - * - * @see UCHAR_ID_CONTINUE - * @see u_isIDStart - * @see u_isIDIgnorable - * @stable ICU 2.0 - */ -U_STABLE UBool U_EXPORT2 -u_isIDPart(UChar32 c); - -/** - * Determines if the specified character should be regarded - * as an ignorable character in an identifier, - * according to Java. - * True for characters with general category "Cf" (format controls) as well as - * non-whitespace ISO controls - * (U+0000..U+0008, U+000E..U+001B, U+007F..U+0084, U+0086..U+009F). - * - * Same as java.lang.Character.isIdentifierIgnorable() - * except that Java also returns TRUE for U+0085 Next Line - * (it omits U+0085 from whitespace ISO controls). - * - * Note that Unicode just recommends to ignore Cf (format controls). - * - * @param c the code point to be tested - * @return TRUE if the code point is ignorable in identifiers according to Java - * - * @see UCHAR_DEFAULT_IGNORABLE_CODE_POINT - * @see u_isIDStart - * @see u_isIDPart - * @stable ICU 2.0 - */ -U_STABLE UBool U_EXPORT2 -u_isIDIgnorable(UChar32 c); - -/** - * Determines if the specified character is permissible as the - * first character in a Java identifier. - * In addition to u_isIDStart(c), true for characters with - * general categories "Sc" (currency symbols) and "Pc" (connecting punctuation). - * - * Same as java.lang.Character.isJavaIdentifierStart(). - * - * @param c the code point to be tested - * @return TRUE if the code point may start a Java identifier - * - * @see u_isJavaIDPart - * @see u_isalpha - * @see u_isIDStart - * @stable ICU 2.0 - */ -U_STABLE UBool U_EXPORT2 -u_isJavaIDStart(UChar32 c); - -/** - * Determines if the specified character is permissible - * in a Java identifier. - * In addition to u_isIDPart(c), true for characters with - * general category "Sc" (currency symbols). - * - * Same as java.lang.Character.isJavaIdentifierPart(). - * - * @param c the code point to be tested - * @return TRUE if the code point may occur in a Java identifier - * - * @see u_isIDIgnorable - * @see u_isJavaIDStart - * @see u_isalpha - * @see u_isdigit - * @see u_isIDPart - * @stable ICU 2.0 - */ -U_STABLE UBool U_EXPORT2 -u_isJavaIDPart(UChar32 c); - -/** - * The given character is mapped to its lowercase equivalent according to - * UnicodeData.txt; if the character has no lowercase equivalent, the character - * itself is returned. - * - * Same as java.lang.Character.toLowerCase(). - * - * This function only returns the simple, single-code point case mapping. - * Full case mappings may result in zero, one or more code points and depend - * on context or language etc. - * Full case mappings are applied by the string case mapping functions, - * see ustring.h and the UnicodeString class. - * - * @param c the code point to be mapped - * @return the Simple_Lowercase_Mapping of the code point, if any; - * otherwise the code point itself. - * @stable ICU 2.0 - */ -U_STABLE UChar32 U_EXPORT2 -u_tolower(UChar32 c); - -/** - * The given character is mapped to its uppercase equivalent according to UnicodeData.txt; - * if the character has no uppercase equivalent, the character itself is - * returned. - * - * Same as java.lang.Character.toUpperCase(). - * - * This function only returns the simple, single-code point case mapping. - * Full case mappings may result in zero, one or more code points and depend - * on context or language etc. - * Full case mappings are applied by the string case mapping functions, - * see ustring.h and the UnicodeString class. - * - * @param c the code point to be mapped - * @return the Simple_Uppercase_Mapping of the code point, if any; - * otherwise the code point itself. - * @stable ICU 2.0 - */ -U_STABLE UChar32 U_EXPORT2 -u_toupper(UChar32 c); - -/** - * The given character is mapped to its titlecase equivalent - * according to UnicodeData.txt; - * if none is defined, the character itself is returned. - * - * Same as java.lang.Character.toTitleCase(). - * - * This function only returns the simple, single-code point case mapping. - * Full case mappings may result in zero, one or more code points and depend - * on context or language etc. - * Full case mappings are applied by the string case mapping functions, - * see ustring.h and the UnicodeString class. - * - * @param c the code point to be mapped - * @return the Simple_Titlecase_Mapping of the code point, if any; - * otherwise the code point itself. - * @stable ICU 2.0 - */ -U_STABLE UChar32 U_EXPORT2 -u_totitle(UChar32 c); - -/** Option value for case folding: use default mappings defined in CaseFolding.txt. @stable ICU 2.0 */ -#define U_FOLD_CASE_DEFAULT 0 - -/** - * Option value for case folding: - * - * Use the modified set of mappings provided in CaseFolding.txt to handle dotted I - * and dotless i appropriately for Turkic languages (tr, az). - * - * Before Unicode 3.2, CaseFolding.txt contains mappings marked with 'I' that - * are to be included for default mappings and - * excluded for the Turkic-specific mappings. - * - * Unicode 3.2 CaseFolding.txt instead contains mappings marked with 'T' that - * are to be excluded for default mappings and - * included for the Turkic-specific mappings. - * - * @stable ICU 2.0 - */ -#define U_FOLD_CASE_EXCLUDE_SPECIAL_I 1 - -/** - * The given character is mapped to its case folding equivalent according to - * UnicodeData.txt and CaseFolding.txt; - * if the character has no case folding equivalent, the character - * itself is returned. - * - * This function only returns the simple, single-code point case mapping. - * Full case mappings may result in zero, one or more code points and depend - * on context or language etc. - * Full case mappings are applied by the string case mapping functions, - * see ustring.h and the UnicodeString class. - * - * @param c the code point to be mapped - * @param options Either U_FOLD_CASE_DEFAULT or U_FOLD_CASE_EXCLUDE_SPECIAL_I - * @return the Simple_Case_Folding of the code point, if any; - * otherwise the code point itself. - * @stable ICU 2.0 - */ -U_STABLE UChar32 U_EXPORT2 -u_foldCase(UChar32 c, uint32_t options); - -/** - * Returns the decimal digit value of the code point in the - * specified radix. - * - * If the radix is not in the range <code>2<=radix<=36</code> or if the - * value of <code>c</code> is not a valid digit in the specified - * radix, <code>-1</code> is returned. A character is a valid digit - * if at least one of the following is true: - * <ul> - * <li>The character has a decimal digit value. - * Such characters have the general category "Nd" (decimal digit numbers) - * and a Numeric_Type of Decimal. - * In this case the value is the character's decimal digit value.</li> - * <li>The character is one of the uppercase Latin letters - * <code>'A'</code> through <code>'Z'</code>. - * In this case the value is <code>c-'A'+10</code>.</li> - * <li>The character is one of the lowercase Latin letters - * <code>'a'</code> through <code>'z'</code>. - * In this case the value is <code>ch-'a'+10</code>.</li> - * <li>Latin letters from both the ASCII range (0061..007A, 0041..005A) - * as well as from the Fullwidth ASCII range (FF41..FF5A, FF21..FF3A) - * are recognized.</li> - * </ul> - * - * Same as java.lang.Character.digit(). - * - * @param ch the code point to be tested. - * @param radix the radix. - * @return the numeric value represented by the character in the - * specified radix, - * or -1 if there is no value or if the value exceeds the radix. - * - * @see UCHAR_NUMERIC_TYPE - * @see u_forDigit - * @see u_charDigitValue - * @see u_isdigit - * @stable ICU 2.0 - */ -U_STABLE int32_t U_EXPORT2 -u_digit(UChar32 ch, int8_t radix); - -/** - * Determines the character representation for a specific digit in - * the specified radix. If the value of <code>radix</code> is not a - * valid radix, or the value of <code>digit</code> is not a valid - * digit in the specified radix, the null character - * (<code>U+0000</code>) is returned. - * <p> - * The <code>radix</code> argument is valid if it is greater than or - * equal to 2 and less than or equal to 36. - * The <code>digit</code> argument is valid if - * <code>0 <= digit < radix</code>. - * <p> - * If the digit is less than 10, then - * <code>'0' + digit</code> is returned. Otherwise, the value - * <code>'a' + digit - 10</code> is returned. - * - * Same as java.lang.Character.forDigit(). - * - * @param digit the number to convert to a character. - * @param radix the radix. - * @return the <code>char</code> representation of the specified digit - * in the specified radix. - * - * @see u_digit - * @see u_charDigitValue - * @see u_isdigit - * @stable ICU 2.0 - */ -U_STABLE UChar32 U_EXPORT2 -u_forDigit(int32_t digit, int8_t radix); - -/** - * Get the "age" of the code point. - * The "age" is the Unicode version when the code point was first - * designated (as a non-character or for Private Use) - * or assigned a character. - * This can be useful to avoid emitting code points to receiving - * processes that do not accept newer characters. - * The data is from the UCD file DerivedAge.txt. - * - * @param c The code point. - * @param versionArray The Unicode version number array, to be filled in. - * - * @stable ICU 2.1 - */ -U_STABLE void U_EXPORT2 -u_charAge(UChar32 c, UVersionInfo versionArray); - -/** - * Gets the Unicode version information. - * The version array is filled in with the version information - * for the Unicode standard that is currently used by ICU. - * For example, Unicode version 3.1.1 is represented as an array with - * the values { 3, 1, 1, 0 }. - * - * @param versionArray an output array that will be filled in with - * the Unicode version number - * @stable ICU 2.0 - */ -U_STABLE void U_EXPORT2 -u_getUnicodeVersion(UVersionInfo versionArray); - -/** - * Get the FC_NFKC_Closure property string for a character. - * See Unicode Standard Annex #15 for details, search for "FC_NFKC_Closure" - * or for "FNC": http://www.unicode.org/reports/tr15/ - * - * @param c The character (code point) for which to get the FC_NFKC_Closure string. - * It must be <code>0<=c<=0x10ffff</code>. - * @param dest Destination address for copying the string. - * The string will be zero-terminated if possible. - * If there is no FC_NFKC_Closure string, - * then the buffer will be set to the empty string. - * @param destCapacity <code>==sizeof(dest)</code> - * @param pErrorCode Pointer to a UErrorCode variable. - * @return The length of the string, or 0 if there is no FC_NFKC_Closure string for this character. - * If the destCapacity is less than or equal to the length, then the buffer - * contains the truncated name and the returned length indicates the full - * length of the name. - * The length does not include the zero-termination. - * - * @stable ICU 2.2 - */ -U_STABLE int32_t U_EXPORT2 -u_getFC_NFKC_Closure(UChar32 c, UChar *dest, int32_t destCapacity, UErrorCode *pErrorCode); - -U_CDECL_END - -#endif /*_UCHAR*/ -/*eof*/ diff --git a/WebKit/mac/icu/unicode/uconfig.h b/WebKit/mac/icu/unicode/uconfig.h deleted file mode 100644 index 997cf68..0000000 --- a/WebKit/mac/icu/unicode/uconfig.h +++ /dev/null @@ -1,186 +0,0 @@ -/* -********************************************************************** -* Copyright (C) 2002-2004, International Business Machines -* Corporation and others. All Rights Reserved. -********************************************************************** -* file name: uconfig.h -* encoding: US-ASCII -* tab size: 8 (not used) -* indentation:4 -* -* created on: 2002sep19 -* created by: Markus W. Scherer -*/ - -#ifndef __UCONFIG_H__ -#define __UCONFIG_H__ - -/*! - * \file - * \brief Switches for excluding parts of ICU library code modules. - * - * Allows to build partial, smaller libraries for special purposes. - * By default, all modules are built. - * The switches are fairly coarse, controlling large modules. - * Basic services cannot be turned off. - * - * @stable ICU 2.4 - */ - -/** - * \def UCONFIG_ONLY_COLLATION - * This switch turns off modules that are not needed for collation. - * - * It does not turn off legacy conversion because that is necessary - * for ICU to work on EBCDIC platforms (for the default converter). - * If you want "only collation" and do not build for EBCDIC, - * then you can #define UCONFIG_NO_LEGACY_CONVERSION 1 as well. - * - * @stable ICU 2.4 - */ -#ifndef UCONFIG_ONLY_COLLATION -# define UCONFIG_ONLY_COLLATION 0 -#endif - -#if UCONFIG_ONLY_COLLATION - /* common library */ -# define UCONFIG_NO_BREAK_ITERATION 1 -# define UCONFIG_NO_IDNA 1 - - /* i18n library */ -# if UCONFIG_NO_COLLATION -# error Contradictory collation switches in uconfig.h. -# endif -# define UCONFIG_NO_FORMATTING 1 -# define UCONFIG_NO_TRANSLITERATION 1 -# define UCONFIG_NO_REGULAR_EXPRESSIONS 1 -#endif - -/* common library switches -------------------------------------------------- */ - -/** - * \def UCONFIG_NO_CONVERSION - * ICU will not completely build with this switch turned on. - * This switch turns off all converters. - * - * @draft ICU 3.2 - */ -#ifndef UCONFIG_NO_CONVERSION -# define UCONFIG_NO_CONVERSION 0 -#endif - -#if UCONFIG_NO_CONVERSION -# define UCONFIG_NO_LEGACY_CONVERSION 1 -#endif - -/** - * \def UCONFIG_NO_LEGACY_CONVERSION - * This switch turns off all converters except for - * - Unicode charsets (UTF-7/8/16/32, CESU-8, SCSU, BOCU-1) - * - US-ASCII - * - ISO-8859-1 - * - * Turning off legacy conversion is not possible on EBCDIC platforms - * because they need ibm-37 or ibm-1047 default converters. - * - * @stable ICU 2.4 - */ -#ifndef UCONFIG_NO_LEGACY_CONVERSION -# define UCONFIG_NO_LEGACY_CONVERSION 0 -#endif - -/** - * \def UCONFIG_NO_NORMALIZATION - * This switch turns off normalization. - * It implies turning off several other services as well, for example - * collation and IDNA. - * - * @stable ICU 2.6 - */ -#ifndef UCONFIG_NO_NORMALIZATION -# define UCONFIG_NO_NORMALIZATION 0 -#elif UCONFIG_NO_NORMALIZATION - /* common library */ -# define UCONFIG_NO_IDNA 1 - - /* i18n library */ -# if UCONFIG_ONLY_COLLATION -# error Contradictory collation switches in uconfig.h. -# endif -# define UCONFIG_NO_COLLATION 1 -# define UCONFIG_NO_TRANSLITERATION 1 -#endif - -/** - * \def UCONFIG_NO_BREAK_ITERATION - * This switch turns off break iteration. - * - * @stable ICU 2.4 - */ -#ifndef UCONFIG_NO_BREAK_ITERATION -# define UCONFIG_NO_BREAK_ITERATION 0 -#endif - -/** - * \def UCONFIG_NO_IDNA - * This switch turns off IDNA. - * - * @stable ICU 2.6 - */ -#ifndef UCONFIG_NO_IDNA -# define UCONFIG_NO_IDNA 0 -#endif - -/* i18n library switches ---------------------------------------------------- */ - -/** - * \def UCONFIG_NO_COLLATION - * This switch turns off collation and collation-based string search. - * - * @stable ICU 2.4 - */ -#ifndef UCONFIG_NO_COLLATION -# define UCONFIG_NO_COLLATION 0 -#endif - -/** - * \def UCONFIG_NO_FORMATTING - * This switch turns off formatting and calendar/timezone services. - * - * @stable ICU 2.4 - */ -#ifndef UCONFIG_NO_FORMATTING -# define UCONFIG_NO_FORMATTING 0 -#endif - -/** - * \def UCONFIG_NO_TRANSLITERATION - * This switch turns off transliteration. - * - * @stable ICU 2.4 - */ -#ifndef UCONFIG_NO_TRANSLITERATION -# define UCONFIG_NO_TRANSLITERATION 0 -#endif - -/** - * \def UCONFIG_NO_REGULAR_EXPRESSIONS - * This switch turns off regular expressions. - * - * @stable ICU 2.4 - */ -#ifndef UCONFIG_NO_REGULAR_EXPRESSIONS -# define UCONFIG_NO_REGULAR_EXPRESSIONS 0 -#endif - -/** - * \def UCONFIG_NO_SERVICE - * This switch turns off service registration. - * - * @draft ICU 3.2 - */ -#ifndef UCONFIG_NO_SERVICE -# define UCONFIG_NO_SERVICE 0 -#endif - -#endif diff --git a/WebKit/mac/icu/unicode/uidna.h b/WebKit/mac/icu/unicode/uidna.h deleted file mode 100644 index 7b1dd0b..0000000 --- a/WebKit/mac/icu/unicode/uidna.h +++ /dev/null @@ -1,310 +0,0 @@ -/* - ******************************************************************************* - * - * Copyright (C) 2003-2004, International Business Machines - * Corporation and others. All Rights Reserved. - * - ******************************************************************************* - * file name: uidna.h - * encoding: US-ASCII - * tab size: 8 (not used) - * indentation:4 - * - * created on: 2003feb1 - * created by: Ram Viswanadha - */ - -#ifndef __UIDNA_H__ -#define __UIDNA_H__ - -#include "unicode/utypes.h" - -#if !UCONFIG_NO_IDNA - -#include "unicode/parseerr.h" - -/** - *\file - * UIDNA API implements the IDNA protocol as defined in the IDNA RFC - * (http://www.ietf.org/rfc/rfc3490.txt). - * The RFC defines 2 operations: ToASCII and ToUnicode. Domain labels - * containing non-ASCII code points are required to be processed by - * ToASCII operation before passing it to resolver libraries. Domain names - * that are obtained from resolver libraries are required to be processed by - * ToUnicode operation before displaying the domain name to the user. - * IDNA requires that implementations process input strings with Nameprep - * (http://www.ietf.org/rfc/rfc3491.txt), - * which is a profile of Stringprep (http://www.ietf.org/rfc/rfc3454.txt), - * and then with Punycode (http://www.ietf.org/rfc/rfc3492.txt). - * Implementations of IDNA MUST fully implement Nameprep and Punycode; - * neither Nameprep nor Punycode are optional. - * The input and output of ToASCII and ToUnicode operations are Unicode - * and are designed to be chainable, i.e., applying ToASCII or ToUnicode operations - * multiple times to an input string will yield the same result as applying the operation - * once. - * ToUnicode(ToUnicode(ToUnicode...(ToUnicode(string)))) == ToUnicode(string) - * ToASCII(ToASCII(ToASCII...(ToASCII(string))) == ToASCII(string). - * - */ - -#ifndef U_HIDE_DRAFT_API - -/** - * Option to prohibit processing of unassigned codepoints in the input and - * do not check if the input conforms to STD-3 ASCII rules. - * - * @see uidna_toASCII uidna_toUnicode - * @stable ICU 2.6 - */ -#define UIDNA_DEFAULT 0x0000 -/** - * Option to allow processing of unassigned codepoints in the input - * - * @see uidna_toASCII uidna_toUnicode - * @stable ICU 2.6 - */ -#define UIDNA_ALLOW_UNASSIGNED 0x0001 -/** - * Option to check if input conforms to STD-3 ASCII rules - * - * @see uidna_toASCII uidna_toUnicode - * @stable ICU 2.6 - */ -#define UIDNA_USE_STD3_RULES 0x0002 - -#endif /*U_HIDE_DRAFT_API*/ - -/** - * This function implements the ToASCII operation as defined in the IDNA RFC. - * This operation is done on <b>single labels</b> before sending it to something that expects - * ASCII names. A label is an individual part of a domain name. Labels are usually - * separated by dots; e.g." "www.example.com" is composed of 3 labels - * "www","example", and "com". - * - * - * @param src Input UChar array containing label in Unicode. - * @param srcLength Number of UChars in src, or -1 if NUL-terminated. - * @param dest Output UChar array with ASCII (ACE encoded) label. - * @param destCapacity Size of dest. - * @param options A bit set of options: - * - * - UIDNA_DEFAULT Use default options, i.e., do not process unassigned code points - * and do not use STD3 ASCII rules - * If unassigned code points are found the operation fails with - * U_UNASSIGNED_ERROR error code. - * - * - UIDNA_ALLOW_UNASSIGNED Unassigned values can be converted to ASCII for query operations - * If this option is set, the unassigned code points are in the input - * are treated as normal Unicode code points. - * - * - UIDNA_USE_STD3_RULES Use STD3 ASCII rules for host name syntax restrictions - * If this option is set and the input does not satisfy STD3 rules, - * the operation will fail with U_IDNA_STD3_ASCII_RULES_ERROR - * - * @param parseError Pointer to UParseError struct to receive information on position - * of error if an error is encountered. Can be NULL. - * @param status ICU in/out error code parameter. - * U_INVALID_CHAR_FOUND if src contains - * unmatched single surrogates. - * U_INDEX_OUTOFBOUNDS_ERROR if src contains - * too many code points. - * U_BUFFER_OVERFLOW_ERROR if destCapacity is not enough - * @return Number of ASCII characters converted. - * @stable ICU 2.6 - */ -U_STABLE int32_t U_EXPORT2 -uidna_toASCII(const UChar* src, int32_t srcLength, - UChar* dest, int32_t destCapacity, - int32_t options, - UParseError* parseError, - UErrorCode* status); - - -/** - * This function implements the ToUnicode operation as defined in the IDNA RFC. - * This operation is done on <b>single labels</b> before sending it to something that expects - * Unicode names. A label is an individual part of a domain name. Labels are usually - * separated by dots; for e.g." "www.example.com" is composed of 3 labels - * "www","example", and "com". - * - * @param src Input UChar array containing ASCII (ACE encoded) label. - * @param srcLength Number of UChars in src, or -1 if NUL-terminated. - * @param dest Output Converted UChar array containing Unicode equivalent of label. - * @param destCapacity Size of dest. - * @param options A bit set of options: - * - * - UIDNA_DEFAULT Use default options, i.e., do not process unassigned code points - * and do not use STD3 ASCII rules - * If unassigned code points are found the operation fails with - * U_UNASSIGNED_ERROR error code. - * - * - UIDNA_ALLOW_UNASSIGNED Unassigned values can be converted to ASCII for query operations - * If this option is set, the unassigned code points are in the input - * are treated as normal Unicode code points. <b> Note: </b> This option is - * required on toUnicode operation because the RFC mandates - * verification of decoded ACE input by applying toASCII and comparing - * its output with source - * - * - * - * - UIDNA_USE_STD3_RULES Use STD3 ASCII rules for host name syntax restrictions - * If this option is set and the input does not satisfy STD3 rules, - * the operation will fail with U_IDNA_STD3_ASCII_RULES_ERROR - * - * @param parseError Pointer to UParseError struct to receive information on position - * of error if an error is encountered. Can be NULL. - * @param status ICU in/out error code parameter. - * U_INVALID_CHAR_FOUND if src contains - * unmatched single surrogates. - * U_INDEX_OUTOFBOUNDS_ERROR if src contains - * too many code points. - * U_BUFFER_OVERFLOW_ERROR if destCapacity is not enough - * @return Number of Unicode characters converted. - * @stable ICU 2.6 - */ -U_STABLE int32_t U_EXPORT2 -uidna_toUnicode(const UChar* src, int32_t srcLength, - UChar* dest, int32_t destCapacity, - int32_t options, - UParseError* parseError, - UErrorCode* status); - - -/** - * Convenience function that implements the IDNToASCII operation as defined in the IDNA RFC. - * This operation is done on complete domain names, e.g: "www.example.com". - * It is important to note that this operation can fail. If it fails, then the input - * domain name cannot be used as an Internationalized Domain Name and the application - * should have methods defined to deal with the failure. - * - * <b>Note:</b> IDNA RFC specifies that a conformant application should divide a domain name - * into separate labels, decide whether to apply allowUnassigned and useSTD3ASCIIRules on each, - * and then convert. This function does not offer that level of granularity. The options once - * set will apply to all labels in the domain name - * - * @param src Input UChar array containing IDN in Unicode. - * @param srcLength Number of UChars in src, or -1 if NUL-terminated. - * @param dest Output UChar array with ASCII (ACE encoded) IDN. - * @param destCapacity Size of dest. - * @param options A bit set of options: - * - * - UIDNA_DEFAULT Use default options, i.e., do not process unassigned code points - * and do not use STD3 ASCII rules - * If unassigned code points are found the operation fails with - * U_UNASSIGNED_CODE_POINT_FOUND error code. - * - * - UIDNA_ALLOW_UNASSIGNED Unassigned values can be converted to ASCII for query operations - * If this option is set, the unassigned code points are in the input - * are treated as normal Unicode code points. - * - * - UIDNA_USE_STD3_RULES Use STD3 ASCII rules for host name syntax restrictions - * If this option is set and the input does not satisfy STD3 rules, - * the operation will fail with U_IDNA_STD3_ASCII_RULES_ERROR - * - * @param parseError Pointer to UParseError struct to receive information on position - * of error if an error is encountered. Can be NULL. - * @param status ICU in/out error code parameter. - * U_INVALID_CHAR_FOUND if src contains - * unmatched single surrogates. - * U_INDEX_OUTOFBOUNDS_ERROR if src contains - * too many code points. - * U_BUFFER_OVERFLOW_ERROR if destCapacity is not enough - * @return Number of ASCII characters converted. - * @stable ICU 2.6 - */ -U_STABLE int32_t U_EXPORT2 -uidna_IDNToASCII( const UChar* src, int32_t srcLength, - UChar* dest, int32_t destCapacity, - int32_t options, - UParseError* parseError, - UErrorCode* status); - -/** - * Convenience function that implements the IDNToUnicode operation as defined in the IDNA RFC. - * This operation is done on complete domain names, e.g: "www.example.com". - * - * <b>Note:</b> IDNA RFC specifies that a conformant application should divide a domain name - * into separate labels, decide whether to apply allowUnassigned and useSTD3ASCIIRules on each, - * and then convert. This function does not offer that level of granularity. The options once - * set will apply to all labels in the domain name - * - * @param src Input UChar array containing IDN in ASCII (ACE encoded) form. - * @param srcLength Number of UChars in src, or -1 if NUL-terminated. - * @param dest Output UChar array containing Unicode equivalent of source IDN. - * @param destCapacity Size of dest. - * @param options A bit set of options: - * - * - UIDNA_DEFAULT Use default options, i.e., do not process unassigned code points - * and do not use STD3 ASCII rules - * If unassigned code points are found the operation fails with - * U_UNASSIGNED_CODE_POINT_FOUND error code. - * - * - UIDNA_ALLOW_UNASSIGNED Unassigned values can be converted to ASCII for query operations - * If this option is set, the unassigned code points are in the input - * are treated as normal Unicode code points. - * - * - UIDNA_USE_STD3_RULES Use STD3 ASCII rules for host name syntax restrictions - * If this option is set and the input does not satisfy STD3 rules, - * the operation will fail with U_IDNA_STD3_ASCII_RULES_ERROR - * - * @param parseError Pointer to UParseError struct to receive information on position - * of error if an error is encountered. Can be NULL. - * @param status ICU in/out error code parameter. - * U_INVALID_CHAR_FOUND if src contains - * unmatched single surrogates. - * U_INDEX_OUTOFBOUNDS_ERROR if src contains - * too many code points. - * U_BUFFER_OVERFLOW_ERROR if destCapacity is not enough - * @return Number of ASCII characters converted. - * @stable ICU 2.6 - */ -U_STABLE int32_t U_EXPORT2 -uidna_IDNToUnicode( const UChar* src, int32_t srcLength, - UChar* dest, int32_t destCapacity, - int32_t options, - UParseError* parseError, - UErrorCode* status); - -/** - * Compare two IDN strings for equivalence. - * This function splits the domain names into labels and compares them. - * According to IDN RFC, whenever two labels are compared, they are - * considered equal if and only if their ASCII forms (obtained by - * applying toASCII) match using an case-insensitive ASCII comparison. - * Two domain names are considered a match if and only if all labels - * match regardless of whether label separators match. - * - * @param s1 First source string. - * @param length1 Length of first source string, or -1 if NUL-terminated. - * - * @param s2 Second source string. - * @param length2 Length of second source string, or -1 if NUL-terminated. - * @param options A bit set of options: - * - * - UIDNA_DEFAULT Use default options, i.e., do not process unassigned code points - * and do not use STD3 ASCII rules - * If unassigned code points are found the operation fails with - * U_UNASSIGNED_CODE_POINT_FOUND error code. - * - * - UIDNA_ALLOW_UNASSIGNED Unassigned values can be converted to ASCII for query operations - * If this option is set, the unassigned code points are in the input - * are treated as normal Unicode code points. - * - * - UIDNA_USE_STD3_RULES Use STD3 ASCII rules for host name syntax restrictions - * If this option is set and the input does not satisfy STD3 rules, - * the operation will fail with U_IDNA_STD3_ASCII_RULES_ERROR - * - * @param status ICU error code in/out parameter. - * Must fulfill U_SUCCESS before the function call. - * @return <0 or 0 or >0 as usual for string comparisons - * @stable ICU 2.6 - */ -U_STABLE int32_t U_EXPORT2 -uidna_compare( const UChar *s1, int32_t length1, - const UChar *s2, int32_t length2, - int32_t options, - UErrorCode* status); - -#endif /* #if !UCONFIG_NO_IDNA */ - -#endif diff --git a/WebKit/mac/icu/unicode/uiter.h b/WebKit/mac/icu/unicode/uiter.h deleted file mode 100644 index 963df5c..0000000 --- a/WebKit/mac/icu/unicode/uiter.h +++ /dev/null @@ -1,707 +0,0 @@ -/* -******************************************************************************* -* -* Copyright (C) 2002-2004, International Business Machines -* Corporation and others. All Rights Reserved. -* -******************************************************************************* -* file name: uiter.h -* encoding: US-ASCII -* tab size: 8 (not used) -* indentation:4 -* -* created on: 2002jan18 -* created by: Markus W. Scherer -*/ - -#ifndef __UITER_H__ -#define __UITER_H__ - -/** - * \file - * \brief C API: Unicode Character Iteration - * - * @see UCharIterator - */ - -#include "unicode/utypes.h" - -#ifdef XP_CPLUSPLUS - U_NAMESPACE_BEGIN - - class CharacterIterator; - class Replaceable; - - U_NAMESPACE_END -#endif - -U_CDECL_BEGIN - -struct UCharIterator; -typedef struct UCharIterator UCharIterator; /**< C typedef for struct UCharIterator. @stable ICU 2.1 */ - -/** - * Origin constants for UCharIterator.getIndex() and UCharIterator.move(). - * @see UCharIteratorMove - * @see UCharIterator - * @stable ICU 2.1 - */ -typedef enum UCharIteratorOrigin { - UITER_START, UITER_CURRENT, UITER_LIMIT, UITER_ZERO, UITER_LENGTH -} UCharIteratorOrigin; - -/** Constants for UCharIterator. @stable ICU 2.6 */ -enum { - /** - * Constant value that may be returned by UCharIteratorMove - * indicating that the final UTF-16 index is not known, but that the move succeeded. - * This can occur when moving relative to limit or length, or - * when moving relative to the current index after a setState() - * when the current UTF-16 index is not known. - * - * It would be very inefficient to have to count from the beginning of the text - * just to get the current/limit/length index after moving relative to it. - * The actual index can be determined with getIndex(UITER_CURRENT) - * which will count the UChars if necessary. - * - * @stable ICU 2.6 - */ - UITER_UNKNOWN_INDEX=-2 -}; - - -/** - * Constant for UCharIterator getState() indicating an error or - * an unknown state. - * Returned by uiter_getState()/UCharIteratorGetState - * when an error occurs. - * Also, some UCharIterator implementations may not be able to return - * a valid state for each position. This will be clearly documented - * for each such iterator (none of the public ones here). - * - * @stable ICU 2.6 - */ -#define UITER_NO_STATE ((uint32_t)0xffffffff) - -/** - * Function type declaration for UCharIterator.getIndex(). - * - * Gets the current position, or the start or limit of the - * iteration range. - * - * This function may perform slowly for UITER_CURRENT after setState() was called, - * or for UITER_LENGTH, because an iterator implementation may have to count - * UChars if the underlying storage is not UTF-16. - * - * @param iter the UCharIterator structure ("this pointer") - * @param origin get the 0, start, limit, length, or current index - * @return the requested index, or U_SENTINEL in an error condition - * - * @see UCharIteratorOrigin - * @see UCharIterator - * @stable ICU 2.1 - */ -typedef int32_t U_CALLCONV -UCharIteratorGetIndex(UCharIterator *iter, UCharIteratorOrigin origin); - -/** - * Function type declaration for UCharIterator.move(). - * - * Use iter->move(iter, index, UITER_ZERO) like CharacterIterator::setIndex(index). - * - * Moves the current position relative to the start or limit of the - * iteration range, or relative to the current position itself. - * The movement is expressed in numbers of code units forward - * or backward by specifying a positive or negative delta. - * Out of bounds movement will be pinned to the start or limit. - * - * This function may perform slowly for moving relative to UITER_LENGTH - * because an iterator implementation may have to count the rest of the - * UChars if the native storage is not UTF-16. - * - * When moving relative to the limit or length, or - * relative to the current position after setState() was called, - * move() may return UITER_UNKNOWN_INDEX (-2) to avoid an inefficient - * determination of the actual UTF-16 index. - * The actual index can be determined with getIndex(UITER_CURRENT) - * which will count the UChars if necessary. - * See UITER_UNKNOWN_INDEX for details. - * - * @param iter the UCharIterator structure ("this pointer") - * @param delta can be positive, zero, or negative - * @param origin move relative to the 0, start, limit, length, or current index - * @return the new index, or U_SENTINEL on an error condition, - * or UITER_UNKNOWN_INDEX when the index is not known. - * - * @see UCharIteratorOrigin - * @see UCharIterator - * @see UITER_UNKNOWN_INDEX - * @stable ICU 2.1 - */ -typedef int32_t U_CALLCONV -UCharIteratorMove(UCharIterator *iter, int32_t delta, UCharIteratorOrigin origin); - -/** - * Function type declaration for UCharIterator.hasNext(). - * - * Check if current() and next() can still - * return another code unit. - * - * @param iter the UCharIterator structure ("this pointer") - * @return boolean value for whether current() and next() can still return another code unit - * - * @see UCharIterator - * @stable ICU 2.1 - */ -typedef UBool U_CALLCONV -UCharIteratorHasNext(UCharIterator *iter); - -/** - * Function type declaration for UCharIterator.hasPrevious(). - * - * Check if previous() can still return another code unit. - * - * @param iter the UCharIterator structure ("this pointer") - * @return boolean value for whether previous() can still return another code unit - * - * @see UCharIterator - * @stable ICU 2.1 - */ -typedef UBool U_CALLCONV -UCharIteratorHasPrevious(UCharIterator *iter); - -/** - * Function type declaration for UCharIterator.current(). - * - * Return the code unit at the current position, - * or U_SENTINEL if there is none (index is at the limit). - * - * @param iter the UCharIterator structure ("this pointer") - * @return the current code unit - * - * @see UCharIterator - * @stable ICU 2.1 - */ -typedef UChar32 U_CALLCONV -UCharIteratorCurrent(UCharIterator *iter); - -/** - * Function type declaration for UCharIterator.next(). - * - * Return the code unit at the current index and increment - * the index (post-increment, like s[i++]), - * or return U_SENTINEL if there is none (index is at the limit). - * - * @param iter the UCharIterator structure ("this pointer") - * @return the current code unit (and post-increment the current index) - * - * @see UCharIterator - * @stable ICU 2.1 - */ -typedef UChar32 U_CALLCONV -UCharIteratorNext(UCharIterator *iter); - -/** - * Function type declaration for UCharIterator.previous(). - * - * Decrement the index and return the code unit from there - * (pre-decrement, like s[--i]), - * or return U_SENTINEL if there is none (index is at the start). - * - * @param iter the UCharIterator structure ("this pointer") - * @return the previous code unit (after pre-decrementing the current index) - * - * @see UCharIterator - * @stable ICU 2.1 - */ -typedef UChar32 U_CALLCONV -UCharIteratorPrevious(UCharIterator *iter); - -/** - * Function type declaration for UCharIterator.reservedFn(). - * Reserved for future use. - * - * @param iter the UCharIterator structure ("this pointer") - * @param something some integer argument - * @return some integer - * - * @see UCharIterator - * @stable ICU 2.1 - */ -typedef int32_t U_CALLCONV -UCharIteratorReserved(UCharIterator *iter, int32_t something); - -/** - * Function type declaration for UCharIterator.getState(). - * - * Get the "state" of the iterator in the form of a single 32-bit word. - * It is recommended that the state value be calculated to be as small as - * is feasible. For strings with limited lengths, fewer than 32 bits may - * be sufficient. - * - * This is used together with setState()/UCharIteratorSetState - * to save and restore the iterator position more efficiently than with - * getIndex()/move(). - * - * The iterator state is defined as a uint32_t value because it is designed - * for use in ucol_nextSortKeyPart() which provides 32 bits to store the state - * of the character iterator. - * - * With some UCharIterator implementations (e.g., UTF-8), - * getting and setting the UTF-16 index with existing functions - * (getIndex(UITER_CURRENT) followed by move(pos, UITER_ZERO)) is possible but - * relatively slow because the iterator has to "walk" from a known index - * to the requested one. - * This takes more time the farther it needs to go. - * - * An opaque state value allows an iterator implementation to provide - * an internal index (UTF-8: the source byte array index) for - * fast, constant-time restoration. - * - * After calling setState(), a getIndex(UITER_CURRENT) may be slow because - * the UTF-16 index may not be restored as well, but the iterator can deliver - * the correct text contents and move relative to the current position - * without performance degradation. - * - * Some UCharIterator implementations may not be able to return - * a valid state for each position, in which case they return UITER_NO_STATE instead. - * This will be clearly documented for each such iterator (none of the public ones here). - * - * @param iter the UCharIterator structure ("this pointer") - * @return the state word - * - * @see UCharIterator - * @see UCharIteratorSetState - * @see UITER_NO_STATE - * @stable ICU 2.6 - */ -typedef uint32_t U_CALLCONV -UCharIteratorGetState(const UCharIterator *iter); - -/** - * Function type declaration for UCharIterator.setState(). - * - * Restore the "state" of the iterator using a state word from a getState() call. - * The iterator object need not be the same one as for which getState() was called, - * but it must be of the same type (set up using the same uiter_setXYZ function) - * and it must iterate over the same string - * (binary identical regardless of memory address). - * For more about the state word see UCharIteratorGetState. - * - * After calling setState(), a getIndex(UITER_CURRENT) may be slow because - * the UTF-16 index may not be restored as well, but the iterator can deliver - * the correct text contents and move relative to the current position - * without performance degradation. - * - * @param iter the UCharIterator structure ("this pointer") - * @param state the state word from a getState() call - * on a same-type, same-string iterator - * @param pErrorCode Must be a valid pointer to an error code value, - * which must not indicate a failure before the function call. - * - * @see UCharIterator - * @see UCharIteratorGetState - * @stable ICU 2.6 - */ -typedef void U_CALLCONV -UCharIteratorSetState(UCharIterator *iter, uint32_t state, UErrorCode *pErrorCode); - - -/** - * C API for code unit iteration. - * This can be used as a C wrapper around - * CharacterIterator, Replaceable, or implemented using simple strings, etc. - * - * There are two roles for using UCharIterator: - * - * A "provider" sets the necessary function pointers and controls the "protected" - * fields of the UCharIterator structure. A "provider" passes a UCharIterator - * into C APIs that need a UCharIterator as an abstract, flexible string interface. - * - * Implementations of such C APIs are "callers" of UCharIterator functions; - * they only use the "public" function pointers and never access the "protected" - * fields directly. - * - * The current() and next() functions only check the current index against the - * limit, and previous() only checks the current index against the start, - * to see if the iterator already reached the end of the iteration range. - * - * The assumption - in all iterators - is that the index is moved via the API, - * which means it won't go out of bounds, or the index is modified by - * user code that knows enough about the iterator implementation to set valid - * index values. - * - * UCharIterator functions return code unit values 0..0xffff, - * or U_SENTINEL if the iteration bounds are reached. - * - * @stable ICU 2.1 - */ -struct UCharIterator { - /** - * (protected) Pointer to string or wrapped object or similar. - * Not used by caller. - * @stable ICU 2.1 - */ - const void *context; - - /** - * (protected) Length of string or similar. - * Not used by caller. - * @stable ICU 2.1 - */ - int32_t length; - - /** - * (protected) Start index or similar. - * Not used by caller. - * @stable ICU 2.1 - */ - int32_t start; - - /** - * (protected) Current index or similar. - * Not used by caller. - * @stable ICU 2.1 - */ - int32_t index; - - /** - * (protected) Limit index or similar. - * Not used by caller. - * @stable ICU 2.1 - */ - int32_t limit; - - /** - * (protected) Used by UTF-8 iterators and possibly others. - * @stable ICU 2.1 - */ - int32_t reservedField; - - /** - * (public) Returns the current position or the - * start or limit index of the iteration range. - * - * @see UCharIteratorGetIndex - * @stable ICU 2.1 - */ - UCharIteratorGetIndex *getIndex; - - /** - * (public) Moves the current position relative to the start or limit of the - * iteration range, or relative to the current position itself. - * The movement is expressed in numbers of code units forward - * or backward by specifying a positive or negative delta. - * - * @see UCharIteratorMove - * @stable ICU 2.1 - */ - UCharIteratorMove *move; - - /** - * (public) Check if current() and next() can still - * return another code unit. - * - * @see UCharIteratorHasNext - * @stable ICU 2.1 - */ - UCharIteratorHasNext *hasNext; - - /** - * (public) Check if previous() can still return another code unit. - * - * @see UCharIteratorHasPrevious - * @stable ICU 2.1 - */ - UCharIteratorHasPrevious *hasPrevious; - - /** - * (public) Return the code unit at the current position, - * or U_SENTINEL if there is none (index is at the limit). - * - * @see UCharIteratorCurrent - * @stable ICU 2.1 - */ - UCharIteratorCurrent *current; - - /** - * (public) Return the code unit at the current index and increment - * the index (post-increment, like s[i++]), - * or return U_SENTINEL if there is none (index is at the limit). - * - * @see UCharIteratorNext - * @stable ICU 2.1 - */ - UCharIteratorNext *next; - - /** - * (public) Decrement the index and return the code unit from there - * (pre-decrement, like s[--i]), - * or return U_SENTINEL if there is none (index is at the start). - * - * @see UCharIteratorPrevious - * @stable ICU 2.1 - */ - UCharIteratorPrevious *previous; - - /** - * (public) Reserved for future use. Currently NULL. - * - * @see UCharIteratorReserved - * @stable ICU 2.1 - */ - UCharIteratorReserved *reservedFn; - - /** - * (public) Return the state of the iterator, to be restored later with setState(). - * This function pointer is NULL if the iterator does not implement it. - * - * @see UCharIteratorGet - * @stable ICU 2.6 - */ - UCharIteratorGetState *getState; - - /** - * (public) Restore the iterator state from the state word from a call - * to getState(). - * This function pointer is NULL if the iterator does not implement it. - * - * @see UCharIteratorSet - * @stable ICU 2.6 - */ - UCharIteratorSetState *setState; -}; - -/** - * Helper function for UCharIterator to get the code point - * at the current index. - * - * Return the code point that includes the code unit at the current position, - * or U_SENTINEL if there is none (index is at the limit). - * If the current code unit is a lead or trail surrogate, - * then the following or preceding surrogate is used to form - * the code point value. - * - * @param iter the UCharIterator structure ("this pointer") - * @return the current code point - * - * @see UCharIterator - * @see U16_GET - * @see UnicodeString::char32At() - * @stable ICU 2.1 - */ -U_STABLE UChar32 U_EXPORT2 -uiter_current32(UCharIterator *iter); - -/** - * Helper function for UCharIterator to get the next code point. - * - * Return the code point at the current index and increment - * the index (post-increment, like s[i++]), - * or return U_SENTINEL if there is none (index is at the limit). - * - * @param iter the UCharIterator structure ("this pointer") - * @return the current code point (and post-increment the current index) - * - * @see UCharIterator - * @see U16_NEXT - * @stable ICU 2.1 - */ -U_STABLE UChar32 U_EXPORT2 -uiter_next32(UCharIterator *iter); - -/** - * Helper function for UCharIterator to get the previous code point. - * - * Decrement the index and return the code point from there - * (pre-decrement, like s[--i]), - * or return U_SENTINEL if there is none (index is at the start). - * - * @param iter the UCharIterator structure ("this pointer") - * @return the previous code point (after pre-decrementing the current index) - * - * @see UCharIterator - * @see U16_PREV - * @stable ICU 2.1 - */ -U_STABLE UChar32 U_EXPORT2 -uiter_previous32(UCharIterator *iter); - -/** - * Get the "state" of the iterator in the form of a single 32-bit word. - * This is a convenience function that calls iter->getState(iter) - * if iter->getState is not NULL; - * if it is NULL or any other error occurs, then UITER_NO_STATE is returned. - * - * Some UCharIterator implementations may not be able to return - * a valid state for each position, in which case they return UITER_NO_STATE instead. - * This will be clearly documented for each such iterator (none of the public ones here). - * - * @param iter the UCharIterator structure ("this pointer") - * @return the state word - * - * @see UCharIterator - * @see UCharIteratorGetState - * @see UITER_NO_STATE - * @stable ICU 2.6 - */ -U_STABLE uint32_t U_EXPORT2 -uiter_getState(const UCharIterator *iter); - -/** - * Restore the "state" of the iterator using a state word from a getState() call. - * This is a convenience function that calls iter->setState(iter, state, pErrorCode) - * if iter->setState is not NULL; if it is NULL, then U_UNSUPPORTED_ERROR is set. - * - * @param iter the UCharIterator structure ("this pointer") - * @param state the state word from a getState() call - * on a same-type, same-string iterator - * @param pErrorCode Must be a valid pointer to an error code value, - * which must not indicate a failure before the function call. - * - * @see UCharIterator - * @see UCharIteratorSetState - * @stable ICU 2.6 - */ -U_STABLE void U_EXPORT2 -uiter_setState(UCharIterator *iter, uint32_t state, UErrorCode *pErrorCode); - -/** - * Set up a UCharIterator to iterate over a string. - * - * Sets the UCharIterator function pointers for iteration over the string s - * with iteration boundaries start=index=0 and length=limit=string length. - * The "provider" may set the start, index, and limit values at any time - * within the range 0..length. - * The length field will be ignored. - * - * The string pointer s is set into UCharIterator.context without copying - * or reallocating the string contents. - * - * getState() simply returns the current index. - * move() will always return the final index. - * - * @param iter UCharIterator structure to be set for iteration - * @param s String to iterate over - * @param length Length of s, or -1 if NUL-terminated - * - * @see UCharIterator - * @stable ICU 2.1 - */ -U_STABLE void U_EXPORT2 -uiter_setString(UCharIterator *iter, const UChar *s, int32_t length); - -/** - * Set up a UCharIterator to iterate over a UTF-16BE string - * (byte vector with a big-endian pair of bytes per UChar). - * - * Everything works just like with a normal UChar iterator (uiter_setString), - * except that UChars are assembled from byte pairs, - * and that the length argument here indicates an even number of bytes. - * - * getState() simply returns the current index. - * move() will always return the final index. - * - * @param iter UCharIterator structure to be set for iteration - * @param s UTF-16BE string to iterate over - * @param length Length of s as an even number of bytes, or -1 if NUL-terminated - * (NUL means pair of 0 bytes at even index from s) - * - * @see UCharIterator - * @see uiter_setString - * @stable ICU 2.6 - */ -U_STABLE void U_EXPORT2 -uiter_setUTF16BE(UCharIterator *iter, const char *s, int32_t length); - -/** - * Set up a UCharIterator to iterate over a UTF-8 string. - * - * Sets the UCharIterator function pointers for iteration over the UTF-8 string s - * with UTF-8 iteration boundaries 0 and length. - * The implementation counts the UTF-16 index on the fly and - * lazily evaluates the UTF-16 length of the text. - * - * The start field is used as the UTF-8 offset, the limit field as the UTF-8 length. - * When the reservedField is not 0, then it contains a supplementary code point - * and the UTF-16 index is between the two corresponding surrogates. - * At that point, the UTF-8 index is behind that code point. - * - * The UTF-8 string pointer s is set into UCharIterator.context without copying - * or reallocating the string contents. - * - * getState() returns a state value consisting of - * - the current UTF-8 source byte index (bits 31..1) - * - a flag (bit 0) that indicates whether the UChar position is in the middle - * of a surrogate pair - * (from a 4-byte UTF-8 sequence for the corresponding supplementary code point) - * - * getState() cannot also encode the UTF-16 index in the state value. - * move(relative to limit or length), or - * move(relative to current) after setState(), may return UITER_UNKNOWN_INDEX. - * - * @param iter UCharIterator structure to be set for iteration - * @param s UTF-8 string to iterate over - * @param length Length of s in bytes, or -1 if NUL-terminated - * - * @see UCharIterator - * @stable ICU 2.6 - */ -U_STABLE void U_EXPORT2 -uiter_setUTF8(UCharIterator *iter, const char *s, int32_t length); - -#ifdef XP_CPLUSPLUS - -/** - * Set up a UCharIterator to wrap around a C++ CharacterIterator. - * - * Sets the UCharIterator function pointers for iteration using the - * CharacterIterator charIter. - * - * The CharacterIterator pointer charIter is set into UCharIterator.context - * without copying or cloning the CharacterIterator object. - * The other "protected" UCharIterator fields are set to 0 and will be ignored. - * The iteration index and boundaries are controlled by the CharacterIterator. - * - * getState() simply returns the current index. - * move() will always return the final index. - * - * @param iter UCharIterator structure to be set for iteration - * @param charIter CharacterIterator to wrap - * - * @see UCharIterator - * @stable ICU 2.1 - */ -U_STABLE void U_EXPORT2 -uiter_setCharacterIterator(UCharIterator *iter, CharacterIterator *charIter); - -/** - * Set up a UCharIterator to iterate over a C++ Replaceable. - * - * Sets the UCharIterator function pointers for iteration over the - * Replaceable rep with iteration boundaries start=index=0 and - * length=limit=rep->length(). - * The "provider" may set the start, index, and limit values at any time - * within the range 0..length=rep->length(). - * The length field will be ignored. - * - * The Replaceable pointer rep is set into UCharIterator.context without copying - * or cloning/reallocating the Replaceable object. - * - * getState() simply returns the current index. - * move() will always return the final index. - * - * @param iter UCharIterator structure to be set for iteration - * @param rep Replaceable to iterate over - * - * @see UCharIterator - * @stable ICU 2.1 - */ -U_STABLE void U_EXPORT2 -uiter_setReplaceable(UCharIterator *iter, const Replaceable *rep); - -#endif - -U_CDECL_END - -#endif diff --git a/WebKit/mac/icu/unicode/umachine.h b/WebKit/mac/icu/unicode/umachine.h deleted file mode 100644 index d841f53..0000000 --- a/WebKit/mac/icu/unicode/umachine.h +++ /dev/null @@ -1,371 +0,0 @@ -/* -****************************************************************************** -* -* Copyright (C) 1999-2004, International Business Machines -* Corporation and others. All Rights Reserved. -* -****************************************************************************** -* file name: umachine.h -* encoding: US-ASCII -* tab size: 8 (not used) -* indentation:4 -* -* created on: 1999sep13 -* created by: Markus W. Scherer -* -* This file defines basic types and constants for utf.h to be -* platform-independent. umachine.h and utf.h are included into -* utypes.h to provide all the general definitions for ICU. -* All of these definitions used to be in utypes.h before -* the UTF-handling macros made this unmaintainable. -*/ - -#ifndef __UMACHINE_H__ -#define __UMACHINE_H__ - - -/** - * \file - * \brief Basic types and constants for UTF - * - * <h2> Basic types and constants for UTF </h2> - * This file defines basic types and constants for utf.h to be - * platform-independent. umachine.h and utf.h are included into - * utypes.h to provide all the general definitions for ICU. - * All of these definitions used to be in utypes.h before - * the UTF-handling macros made this unmaintainable. - * - */ -/*==========================================================================*/ -/* Include platform-dependent definitions */ -/* which are contained in the platform-specific file platform.h */ -/*==========================================================================*/ - -#if defined(WIN32) || defined(_WIN32) || defined(WIN64) || defined(_WIN64) -# include "unicode/pwin32.h" -#else -# include "unicode/platform.h" -#endif - -/* - * ANSI C headers: - * stddef.h defines wchar_t - */ -#include <stddef.h> - -/*==========================================================================*/ -/* XP_CPLUSPLUS is a cross-platform symbol which should be defined when */ -/* using C++. It should not be defined when compiling under C. */ -/*==========================================================================*/ - -#ifdef __cplusplus -# ifndef XP_CPLUSPLUS -# define XP_CPLUSPLUS -# endif -#else -# undef XP_CPLUSPLUS -#endif - -/*==========================================================================*/ -/* For C wrappers, we use the symbol U_STABLE. */ -/* This works properly if the includer is C or C++. */ -/* Functions are declared U_STABLE return-type U_EXPORT2 function-name()... */ -/*==========================================================================*/ - -/** - * \def U_CFUNC - * This is used in a declaration of a library private ICU C function. - * @stable ICU 2.4 - */ - -/** - * \def U_CDECL_BEGIN - * This is used to begin a declaration of a library private ICU C API. - * @stable ICU 2.4 - */ - -/** - * \def U_CDECL_END - * This is used to end a declaration of a library private ICU C API - * @stable ICU 2.4 - */ - -#ifdef XP_CPLUSPLUS -# define U_CFUNC extern "C" -# define U_CDECL_BEGIN extern "C" { -# define U_CDECL_END } -#else -# define U_CFUNC extern -# define U_CDECL_BEGIN -# define U_CDECL_END -#endif - -/** - * \def U_NAMESPACE_BEGIN - * This is used to begin a declaration of a public ICU C++ API. - * If the compiler doesn't support namespaces, this does nothing. - * @stable ICU 2.4 - */ - -/** - * \def U_NAMESPACE_END - * This is used to end a declaration of a public ICU C++ API - * If the compiler doesn't support namespaces, this does nothing. - * @stable ICU 2.4 - */ - -/** - * \def U_NAMESPACE_USE - * This is used to specify that the rest of the code uses the - * public ICU C++ API namespace. - * If the compiler doesn't support namespaces, this does nothing. - * @stable ICU 2.4 - */ - -/** - * \def U_NAMESPACE_QUALIFIER - * This is used to qualify that a function or class is part of - * the public ICU C++ API namespace. - * If the compiler doesn't support namespaces, this does nothing. - * @stable ICU 2.4 - */ - -/* Define namespace symbols if the compiler supports it. */ -#if U_HAVE_NAMESPACE -# define U_NAMESPACE_BEGIN namespace U_ICU_NAMESPACE { -# define U_NAMESPACE_END } -# define U_NAMESPACE_USE using namespace U_ICU_NAMESPACE; -# define U_NAMESPACE_QUALIFIER U_ICU_NAMESPACE:: -#else -# define U_NAMESPACE_BEGIN -# define U_NAMESPACE_END -# define U_NAMESPACE_USE -# define U_NAMESPACE_QUALIFIER -#endif - -/** This is used to declare a function as a public ICU C API @stable ICU 2.0*/ -#define U_CAPI U_CFUNC U_EXPORT -#define U_STABLE U_CAPI -#define U_DRAFT U_CAPI -#define U_DEPRECATED U_CAPI -#define U_OBSOLETE U_CAPI -#define U_INTERNAL U_CAPI - -/*==========================================================================*/ -/* limits for int32_t etc., like in POSIX inttypes.h */ -/*==========================================================================*/ - -#ifndef INT8_MIN -/** The smallest value an 8 bit signed integer can hold @stable ICU 2.0 */ -# define INT8_MIN ((int8_t)(-128)) -#endif -#ifndef INT16_MIN -/** The smallest value a 16 bit signed integer can hold @stable ICU 2.0 */ -# define INT16_MIN ((int16_t)(-32767-1)) -#endif -#ifndef INT32_MIN -/** The smallest value a 32 bit signed integer can hold @stable ICU 2.0 */ -# define INT32_MIN ((int32_t)(-2147483647-1)) -#endif - -#ifndef INT8_MAX -/** The largest value an 8 bit signed integer can hold @stable ICU 2.0 */ -# define INT8_MAX ((int8_t)(127)) -#endif -#ifndef INT16_MAX -/** The largest value a 16 bit signed integer can hold @stable ICU 2.0 */ -# define INT16_MAX ((int16_t)(32767)) -#endif -#ifndef INT32_MAX -/** The largest value a 32 bit signed integer can hold @stable ICU 2.0 */ -# define INT32_MAX ((int32_t)(2147483647)) -#endif - -#ifndef UINT8_MAX -/** The largest value an 8 bit unsigned integer can hold @stable ICU 2.0 */ -# define UINT8_MAX ((uint8_t)(255U)) -#endif -#ifndef UINT16_MAX -/** The largest value a 16 bit unsigned integer can hold @stable ICU 2.0 */ -# define UINT16_MAX ((uint16_t)(65535U)) -#endif -#ifndef UINT32_MAX -/** The largest value a 32 bit unsigned integer can hold @stable ICU 2.0 */ -# define UINT32_MAX ((uint32_t)(4294967295U)) -#endif - -#if defined(U_INT64_T_UNAVAILABLE) -# error int64_t is required for decimal format and rule-based number format. -#else -# ifndef INT64_C -/** - * Provides a platform independent way to specify a signed 64-bit integer constant. - * note: may be wrong for some 64 bit platforms - ensure your compiler provides INT64_C - * @draft ICU 2.8 - */ -# define INT64_C(c) c ## LL -# endif -# ifndef UINT64_C -/** - * Provides a platform independent way to specify an unsigned 64-bit integer constant. - * note: may be wrong for some 64 bit platforms - ensure your compiler provides UINT64_C - * @draft ICU 2.8 - */ -# define UINT64_C(c) c ## ULL -# endif -# ifndef U_INT64_MIN -/** The smallest value a 64 bit signed integer can hold @stable ICU 2.8 */ -# define U_INT64_MIN ((int64_t)(INT64_C(-9223372036854775807)-1)) -# endif -# ifndef U_INT64_MAX -/** The largest value a 64 bit signed integer can hold @stable ICU 2.8 */ -# define U_INT64_MAX ((int64_t)(INT64_C(9223372036854775807))) -# endif -# ifndef U_UINT64_MAX -/** The largest value a 64 bit unsigned integer can hold @stable ICU 2.8 */ -# define U_UINT64_MAX ((uint64_t)(UINT64_C(18446744073709551615))) -# endif -#endif - -/*==========================================================================*/ -/* Boolean data type */ -/*==========================================================================*/ - -/** The ICU boolean type @stable ICU 2.0 */ -typedef int8_t UBool; - -#ifndef TRUE -/** The TRUE value of a UBool @stable ICU 2.0 */ -# define TRUE 1 -#endif -#ifndef FALSE -/** The FALSE value of a UBool @stable ICU 2.0 */ -# define FALSE 0 -#endif - - -/*==========================================================================*/ -/* Unicode data types */ -/*==========================================================================*/ - -/* wchar_t-related definitions -------------------------------------------- */ - -/** - * \def U_HAVE_WCHAR_H - * Indicates whether <wchar.h> is available (1) or not (0). Set to 1 by default. - * - * @stable ICU 2.0 - */ -#ifndef U_HAVE_WCHAR_H -# define U_HAVE_WCHAR_H 1 -#endif - -/** - * \def U_SIZEOF_WCHAR_T - * U_SIZEOF_WCHAR_T==sizeof(wchar_t) (0 means it is not defined or autoconf could not set it) - * - * @stable ICU 2.0 - */ -#if U_SIZEOF_WCHAR_T==0 -# undef U_SIZEOF_WCHAR_T -# define U_SIZEOF_WCHAR_T 4 -#endif - -/* - * \def U_WCHAR_IS_UTF16 - * Defined if wchar_t uses UTF-16. - * - * @stable ICU 2.0 - */ -/* - * \def U_WCHAR_IS_UTF32 - * Defined if wchar_t uses UTF-32. - * - * @stable ICU 2.0 - */ -#if !defined(U_WCHAR_IS_UTF16) && !defined(U_WCHAR_IS_UTF32) -# ifdef __STDC_ISO_10646__ -# if (U_SIZEOF_WCHAR_T==2) -# define U_WCHAR_IS_UTF16 -# elif (U_SIZEOF_WCHAR_T==4) -# define U_WCHAR_IS_UTF32 -# endif -# elif defined __UCS2__ -# if (__OS390__ || __OS400__) && (U_SIZEOF_WCHAR_T==2) -# define U_WCHAR_IS_UTF16 -# endif -# elif defined __UCS4__ -# if (U_SIZEOF_WCHAR_T==4) -# define U_WCHAR_IS_UTF32 -# endif -# elif defined(WIN32) || defined(_WIN32) || defined(WIN64) || defined(_WIN64) -# define U_WCHAR_IS_UTF16 -# endif -#endif - -/* UChar and UChar32 definitions -------------------------------------------- */ - -/** Number of bytes in a UChar. @stable ICU 2.0 */ -#define U_SIZEOF_UCHAR 2 - -/** - * \var UChar - * Define UChar to be wchar_t if that is 16 bits wide; always assumed to be unsigned. - * If wchar_t is not 16 bits wide, then define UChar to be uint16_t. - * This makes the definition of UChar platform-dependent - * but allows direct string type compatibility with platforms with - * 16-bit wchar_t types. - * - * @stable ICU 2.0 - */ - -/* Define UChar to be compatible with wchar_t if possible. */ -#if U_SIZEOF_WCHAR_T==2 - typedef wchar_t UChar; -#else - typedef uint16_t UChar; -#endif - -/** - * Define UChar32 as a type for single Unicode code points. - * UChar32 is a signed 32-bit integer (same as int32_t). - * - * The Unicode code point range is 0..0x10ffff. - * All other values (negative or >=0x110000) are illegal as Unicode code points. - * They may be used as sentinel values to indicate "done", "error" - * or similar non-code point conditions. - * - * Before ICU 2.4 (Jitterbug 2146), UChar32 was defined - * to be wchar_t if that is 32 bits wide (wchar_t may be signed or unsigned) - * or else to be uint32_t. - * That is, the definition of UChar32 was platform-dependent. - * - * @see U_SENTINEL - * @stable ICU 2.4 - */ -typedef int32_t UChar32; - -/*==========================================================================*/ -/* U_INLINE and U_ALIGN_CODE Set default values if these are not already */ -/* defined. Definitions normally are in */ -/* platform.h or the corresponding file for */ -/* the OS in use. */ -/*==========================================================================*/ - -/** - * \def U_ALIGN_CODE - * This is used to align code fragments to a specific byte boundary. - * This is useful for getting consistent performance test results. - * @internal - */ -#ifndef U_ALIGN_CODE -# define U_ALIGN_CODE(n) -#endif - -#ifndef U_INLINE -# define U_INLINE -#endif - -#include "unicode/urename.h" - -#endif diff --git a/WebKit/mac/icu/unicode/unorm.h b/WebKit/mac/icu/unicode/unorm.h deleted file mode 100644 index 8bdbee7..0000000 --- a/WebKit/mac/icu/unicode/unorm.h +++ /dev/null @@ -1,575 +0,0 @@ -/* -******************************************************************************* -* Copyright (c) 1996-2004, International Business Machines Corporation -* and others. All Rights Reserved. -******************************************************************************* -* File unorm.h -* -* Created by: Vladimir Weinstein 12052000 -* -* Modification history : -* -* Date Name Description -* 02/01/01 synwee Added normalization quickcheck enum and method. -*/ -#ifndef UNORM_H -#define UNORM_H - -#include "unicode/utypes.h" - -#if !UCONFIG_NO_NORMALIZATION - -#include "unicode/uiter.h" - -/** - * \file - * \brief C API: Unicode Normalization - * - * <h2>Unicode normalization API</h2> - * - * <code>unorm_normalize</code> transforms Unicode text into an equivalent composed or - * decomposed form, allowing for easier sorting and searching of text. - * <code>unorm_normalize</code> supports the standard normalization forms described in - * <a href="http://www.unicode.org/unicode/reports/tr15/" target="unicode"> - * Unicode Standard Annex #15 — Unicode Normalization Forms</a>. - * - * Characters with accents or other adornments can be encoded in - * several different ways in Unicode. For example, take the character A-acute. - * In Unicode, this can be encoded as a single character (the - * "composed" form): - * - * \code - * 00C1 LATIN CAPITAL LETTER A WITH ACUTE - * \endcode - * - * or as two separate characters (the "decomposed" form): - * - * \code - * 0041 LATIN CAPITAL LETTER A - * 0301 COMBINING ACUTE ACCENT - * \endcode - * - * To a user of your program, however, both of these sequences should be - * treated as the same "user-level" character "A with acute accent". When you are searching or - * comparing text, you must ensure that these two sequences are treated - * equivalently. In addition, you must handle characters with more than one - * accent. Sometimes the order of a character's combining accents is - * significant, while in other cases accent sequences in different orders are - * really equivalent. - * - * Similarly, the string "ffi" can be encoded as three separate letters: - * - * \code - * 0066 LATIN SMALL LETTER F - * 0066 LATIN SMALL LETTER F - * 0069 LATIN SMALL LETTER I - * \endcode - * - * or as the single character - * - * \code - * FB03 LATIN SMALL LIGATURE FFI - * \endcode - * - * The ffi ligature is not a distinct semantic character, and strictly speaking - * it shouldn't be in Unicode at all, but it was included for compatibility - * with existing character sets that already provided it. The Unicode standard - * identifies such characters by giving them "compatibility" decompositions - * into the corresponding semantic characters. When sorting and searching, you - * will often want to use these mappings. - * - * <code>unorm_normalize</code> helps solve these problems by transforming text into the - * canonical composed and decomposed forms as shown in the first example above. - * In addition, you can have it perform compatibility decompositions so that - * you can treat compatibility characters the same as their equivalents. - * Finally, <code>unorm_normalize</code> rearranges accents into the proper canonical - * order, so that you do not have to worry about accent rearrangement on your - * own. - * - * Form FCD, "Fast C or D", is also designed for collation. - * It allows to work on strings that are not necessarily normalized - * with an algorithm (like in collation) that works under "canonical closure", i.e., it treats precomposed - * characters and their decomposed equivalents the same. - * - * It is not a normalization form because it does not provide for uniqueness of representation. Multiple strings - * may be canonically equivalent (their NFDs are identical) and may all conform to FCD without being identical - * themselves. - * - * The form is defined such that the "raw decomposition", the recursive canonical decomposition of each character, - * results in a string that is canonically ordered. This means that precomposed characters are allowed for as long - * as their decompositions do not need canonical reordering. - * - * Its advantage for a process like collation is that all NFD and most NFC texts - and many unnormalized texts - - * already conform to FCD and do not need to be normalized (NFD) for such a process. The FCD quick check will - * return UNORM_YES for most strings in practice. - * - * unorm_normalize(UNORM_FCD) may be implemented with UNORM_NFD. - * - * For more details on FCD see the collation design document: - * http://oss.software.ibm.com/cvs/icu/~checkout~/icuhtml/design/collation/ICU_collation_design.htm - * - * ICU collation performs either NFD or FCD normalization automatically if normalization - * is turned on for the collator object. - * Beyond collation and string search, normalized strings may be useful for string equivalence comparisons, - * transliteration/transcription, unique representations, etc. - * - * The W3C generally recommends to exchange texts in NFC. - * Note also that most legacy character encodings use only precomposed forms and often do not - * encode any combining marks by themselves. For conversion to such character encodings the - * Unicode text needs to be normalized to NFC. - * For more usage examples, see the Unicode Standard Annex. - */ - -/** - * Constants for normalization modes. - * @stable ICU 2.0 - */ -typedef enum { - /** No decomposition/composition. @stable ICU 2.0 */ - UNORM_NONE = 1, - /** Canonical decomposition. @stable ICU 2.0 */ - UNORM_NFD = 2, - /** Compatibility decomposition. @stable ICU 2.0 */ - UNORM_NFKD = 3, - /** Canonical decomposition followed by canonical composition. @stable ICU 2.0 */ - UNORM_NFC = 4, - /** Default normalization. @stable ICU 2.0 */ - UNORM_DEFAULT = UNORM_NFC, - /** Compatibility decomposition followed by canonical composition. @stable ICU 2.0 */ - UNORM_NFKC =5, - /** "Fast C or D" form. @stable ICU 2.0 */ - UNORM_FCD = 6, - - /** One more than the highest normalization mode constant. @stable ICU 2.0 */ - UNORM_MODE_COUNT -} UNormalizationMode; - -/** - * Constants for options flags for normalization. - * Use 0 for default options, - * including normalization according to the Unicode version - * that is currently supported by ICU (see u_getUnicodeVersion). - * @stable ICU 2.6 - */ -enum { - /** - * Options bit set value to select Unicode 3.2 normalization - * (except NormalizationCorrections). - * At most one Unicode version can be selected at a time. - * @stable ICU 2.6 - */ - UNORM_UNICODE_3_2=0x20 -}; - -/** - * Lowest-order bit number of unorm_compare() options bits corresponding to - * normalization options bits. - * - * The options parameter for unorm_compare() uses most bits for - * itself and for various comparison and folding flags. - * The most significant bits, however, are shifted down and passed on - * to the normalization implementation. - * (That is, from unorm_compare(..., options, ...), - * options>>UNORM_COMPARE_NORM_OPTIONS_SHIFT will be passed on to the - * internal normalization functions.) - * - * @see unorm_compare - * @stable ICU 2.6 - */ -#define UNORM_COMPARE_NORM_OPTIONS_SHIFT 20 - -/** - * Normalize a string. - * The string will be normalized according the specified normalization mode - * and options. - * - * @param source The string to normalize. - * @param sourceLength The length of source, or -1 if NUL-terminated. - * @param mode The normalization mode; one of UNORM_NONE, - * UNORM_NFD, UNORM_NFC, UNORM_NFKC, UNORM_NFKD, UNORM_DEFAULT. - * @param options The normalization options, ORed together (0 for no options). - * @param result A pointer to a buffer to receive the result string. - * The result string is NUL-terminated if possible. - * @param resultLength The maximum size of result. - * @param status A pointer to a UErrorCode to receive any errors. - * @return The total buffer size needed; if greater than resultLength, - * the output was truncated, and the error code is set to U_BUFFER_OVERFLOW_ERROR. - * @stable ICU 2.0 - */ -U_STABLE int32_t U_EXPORT2 -unorm_normalize(const UChar *source, int32_t sourceLength, - UNormalizationMode mode, int32_t options, - UChar *result, int32_t resultLength, - UErrorCode *status); -#endif -/** - * Result values for unorm_quickCheck(). - * For details see Unicode Technical Report 15. - * @stable ICU 2.0 - */ -typedef enum UNormalizationCheckResult { - /** - * Indicates that string is not in the normalized format - */ - UNORM_NO, - /** - * Indicates that string is in the normalized format - */ - UNORM_YES, - /** - * Indicates that string cannot be determined if it is in the normalized - * format without further thorough checks. - */ - UNORM_MAYBE -} UNormalizationCheckResult; -#if !UCONFIG_NO_NORMALIZATION -/** - * Performing quick check on a string, to quickly determine if the string is - * in a particular normalization format. - * Three types of result can be returned UNORM_YES, UNORM_NO or - * UNORM_MAYBE. Result UNORM_YES indicates that the argument - * string is in the desired normalized format, UNORM_NO determines that - * argument string is not in the desired normalized format. A - * UNORM_MAYBE result indicates that a more thorough check is required, - * the user may have to put the string in its normalized form and compare the - * results. - * - * @param source string for determining if it is in a normalized format - * @param sourcelength length of source to test, or -1 if NUL-terminated - * @param mode which normalization form to test for - * @param status a pointer to a UErrorCode to receive any errors - * @return UNORM_YES, UNORM_NO or UNORM_MAYBE - * - * @see unorm_isNormalized - * @stable ICU 2.0 - */ -U_STABLE UNormalizationCheckResult U_EXPORT2 -unorm_quickCheck(const UChar *source, int32_t sourcelength, - UNormalizationMode mode, - UErrorCode *status); - -/** - * Performing quick check on a string; same as unorm_quickCheck but - * takes an extra options parameter like most normalization functions. - * - * @param src String that is to be tested if it is in a normalization format. - * @param srcLength Length of source to test, or -1 if NUL-terminated. - * @param mode Which normalization form to test for. - * @param options The normalization options, ORed together (0 for no options). - * @param pErrorCode ICU error code in/out parameter. - * Must fulfill U_SUCCESS before the function call. - * @return UNORM_YES, UNORM_NO or UNORM_MAYBE - * - * @see unorm_quickCheck - * @see unorm_isNormalized - * @stable ICU 2.6 - */ -U_STABLE UNormalizationCheckResult U_EXPORT2 -unorm_quickCheckWithOptions(const UChar *src, int32_t srcLength, - UNormalizationMode mode, int32_t options, - UErrorCode *pErrorCode); - -/** - * Test if a string is in a given normalization form. - * This is semantically equivalent to source.equals(normalize(source, mode)) . - * - * Unlike unorm_quickCheck(), this function returns a definitive result, - * never a "maybe". - * For NFD, NFKD, and FCD, both functions work exactly the same. - * For NFC and NFKC where quickCheck may return "maybe", this function will - * perform further tests to arrive at a TRUE/FALSE result. - * - * @param src String that is to be tested if it is in a normalization format. - * @param srcLength Length of source to test, or -1 if NUL-terminated. - * @param mode Which normalization form to test for. - * @param pErrorCode ICU error code in/out parameter. - * Must fulfill U_SUCCESS before the function call. - * @return Boolean value indicating whether the source string is in the - * "mode" normalization form. - * - * @see unorm_quickCheck - * @stable ICU 2.2 - */ -U_STABLE UBool U_EXPORT2 -unorm_isNormalized(const UChar *src, int32_t srcLength, - UNormalizationMode mode, - UErrorCode *pErrorCode); - -/** - * Test if a string is in a given normalization form; same as unorm_isNormalized but - * takes an extra options parameter like most normalization functions. - * - * @param src String that is to be tested if it is in a normalization format. - * @param srcLength Length of source to test, or -1 if NUL-terminated. - * @param mode Which normalization form to test for. - * @param options The normalization options, ORed together (0 for no options). - * @param pErrorCode ICU error code in/out parameter. - * Must fulfill U_SUCCESS before the function call. - * @return Boolean value indicating whether the source string is in the - * "mode/options" normalization form. - * - * @see unorm_quickCheck - * @see unorm_isNormalized - * @stable ICU 2.6 - */ -U_STABLE UBool U_EXPORT2 -unorm_isNormalizedWithOptions(const UChar *src, int32_t srcLength, - UNormalizationMode mode, int32_t options, - UErrorCode *pErrorCode); - -/** - * Iterative normalization forward. - * This function (together with unorm_previous) is somewhat - * similar to the C++ Normalizer class (see its non-static functions). - * - * Iterative normalization is useful when only a small portion of a longer - * string/text needs to be processed. - * - * For example, the likelihood may be high that processing the first 10% of some - * text will be sufficient to find certain data. - * Another example: When one wants to concatenate two normalized strings and get a - * normalized result, it is much more efficient to normalize just a small part of - * the result around the concatenation place instead of re-normalizing everything. - * - * The input text is an instance of the C character iteration API UCharIterator. - * It may wrap around a simple string, a CharacterIterator, a Replaceable, or any - * other kind of text object. - * - * If a buffer overflow occurs, then the caller needs to reset the iterator to the - * old index and call the function again with a larger buffer - if the caller cares - * for the actual output. - * Regardless of the output buffer, the iterator will always be moved to the next - * normalization boundary. - * - * This function (like unorm_previous) serves two purposes: - * - * 1) To find the next boundary so that the normalization of the part of the text - * from the current position to that boundary does not affect and is not affected - * by the part of the text beyond that boundary. - * - * 2) To normalize the text up to the boundary. - * - * The second step is optional, per the doNormalize parameter. - * It is omitted for operations like string concatenation, where the two adjacent - * string ends need to be normalized together. - * In such a case, the output buffer will just contain a copy of the text up to the - * boundary. - * - * pNeededToNormalize is an output-only parameter. Its output value is only defined - * if normalization was requested (doNormalize) and successful (especially, no - * buffer overflow). - * It is useful for operations like a normalizing transliterator, where one would - * not want to replace a piece of text if it is not modified. - * - * If doNormalize==TRUE and pNeededToNormalize!=NULL then *pNeeded... is set TRUE - * if the normalization was necessary. - * - * If doNormalize==FALSE then *pNeededToNormalize will be set to FALSE. - * - * If the buffer overflows, then *pNeededToNormalize will be undefined; - * essentially, whenever U_FAILURE is true (like in buffer overflows), this result - * will be undefined. - * - * @param src The input text in the form of a C character iterator. - * @param dest The output buffer; can be NULL if destCapacity==0 for pure preflighting. - * @param destCapacity The number of UChars that fit into dest. - * @param mode The normalization mode. - * @param options The normalization options, ORed together (0 for no options). - * @param doNormalize Indicates if the source text up to the next boundary - * is to be normalized (TRUE) or just copied (FALSE). - * @param pNeededToNormalize Output flag indicating if the normalization resulted in - * different text from the input. - * Not defined if an error occurs including buffer overflow. - * Always FALSE if !doNormalize. - * @param pErrorCode ICU error code in/out parameter. - * Must fulfill U_SUCCESS before the function call. - * @return Length of output (number of UChars) when successful or buffer overflow. - * - * @see unorm_previous - * @see unorm_normalize - * - * @stable ICU 2.1 - */ -U_STABLE int32_t U_EXPORT2 -unorm_next(UCharIterator *src, - UChar *dest, int32_t destCapacity, - UNormalizationMode mode, int32_t options, - UBool doNormalize, UBool *pNeededToNormalize, - UErrorCode *pErrorCode); - -/** - * Iterative normalization backward. - * This function (together with unorm_next) is somewhat - * similar to the C++ Normalizer class (see its non-static functions). - * For all details see unorm_next. - * - * @param src The input text in the form of a C character iterator. - * @param dest The output buffer; can be NULL if destCapacity==0 for pure preflighting. - * @param destCapacity The number of UChars that fit into dest. - * @param mode The normalization mode. - * @param options The normalization options, ORed together (0 for no options). - * @param doNormalize Indicates if the source text up to the next boundary - * is to be normalized (TRUE) or just copied (FALSE). - * @param pNeededToNormalize Output flag indicating if the normalization resulted in - * different text from the input. - * Not defined if an error occurs including buffer overflow. - * Always FALSE if !doNormalize. - * @param pErrorCode ICU error code in/out parameter. - * Must fulfill U_SUCCESS before the function call. - * @return Length of output (number of UChars) when successful or buffer overflow. - * - * @see unorm_next - * @see unorm_normalize - * - * @stable ICU 2.1 - */ -U_STABLE int32_t U_EXPORT2 -unorm_previous(UCharIterator *src, - UChar *dest, int32_t destCapacity, - UNormalizationMode mode, int32_t options, - UBool doNormalize, UBool *pNeededToNormalize, - UErrorCode *pErrorCode); - -/** - * Concatenate normalized strings, making sure that the result is normalized as well. - * - * If both the left and the right strings are in - * the normalization form according to "mode/options", - * then the result will be - * - * \code - * dest=normalize(left+right, mode, options) - * \endcode - * - * With the input strings already being normalized, - * this function will use unorm_next() and unorm_previous() - * to find the adjacent end pieces of the input strings. - * Only the concatenation of these end pieces will be normalized and - * then concatenated with the remaining parts of the input strings. - * - * It is allowed to have dest==left to avoid copying the entire left string. - * - * @param left Left source string, may be same as dest. - * @param leftLength Length of left source string, or -1 if NUL-terminated. - * @param right Right source string. - * @param rightLength Length of right source string, or -1 if NUL-terminated. - * @param dest The output buffer; can be NULL if destCapacity==0 for pure preflighting. - * @param destCapacity The number of UChars that fit into dest. - * @param mode The normalization mode. - * @param options The normalization options, ORed together (0 for no options). - * @param pErrorCode ICU error code in/out parameter. - * Must fulfill U_SUCCESS before the function call. - * @return Length of output (number of UChars) when successful or buffer overflow. - * - * @see unorm_normalize - * @see unorm_next - * @see unorm_previous - * - * @stable ICU 2.1 - */ -U_STABLE int32_t U_EXPORT2 -unorm_concatenate(const UChar *left, int32_t leftLength, - const UChar *right, int32_t rightLength, - UChar *dest, int32_t destCapacity, - UNormalizationMode mode, int32_t options, - UErrorCode *pErrorCode); - -/** - * Option bit for unorm_compare: - * Both input strings are assumed to fulfill FCD conditions. - * @stable ICU 2.2 - */ -#define UNORM_INPUT_IS_FCD 0x20000 - -/** - * Option bit for unorm_compare: - * Perform case-insensitive comparison. - * @stable ICU 2.2 - */ -#define U_COMPARE_IGNORE_CASE 0x10000 - -#ifndef U_COMPARE_CODE_POINT_ORDER -/* see also unistr.h and ustring.h */ -/** - * Option bit for u_strCaseCompare, u_strcasecmp, unorm_compare, etc: - * Compare strings in code point order instead of code unit order. - * @stable ICU 2.2 - */ -#define U_COMPARE_CODE_POINT_ORDER 0x8000 -#endif - -/** - * Compare two strings for canonical equivalence. - * Further options include case-insensitive comparison and - * code point order (as opposed to code unit order). - * - * Canonical equivalence between two strings is defined as their normalized - * forms (NFD or NFC) being identical. - * This function compares strings incrementally instead of normalizing - * (and optionally case-folding) both strings entirely, - * improving performance significantly. - * - * Bulk normalization is only necessary if the strings do not fulfill the FCD - * conditions. Only in this case, and only if the strings are relatively long, - * is memory allocated temporarily. - * For FCD strings and short non-FCD strings there is no memory allocation. - * - * Semantically, this is equivalent to - * strcmp[CodePointOrder](NFD(foldCase(NFD(s1))), NFD(foldCase(NFD(s2)))) - * where code point order and foldCase are all optional. - * - * UAX 21 2.5 Caseless Matching specifies that for a canonical caseless match - * the case folding must be performed first, then the normalization. - * - * @param s1 First source string. - * @param length1 Length of first source string, or -1 if NUL-terminated. - * - * @param s2 Second source string. - * @param length2 Length of second source string, or -1 if NUL-terminated. - * - * @param options A bit set of options: - * - U_FOLD_CASE_DEFAULT or 0 is used for default options: - * Case-sensitive comparison in code unit order, and the input strings - * are quick-checked for FCD. - * - * - UNORM_INPUT_IS_FCD - * Set if the caller knows that both s1 and s2 fulfill the FCD conditions. - * If not set, the function will quickCheck for FCD - * and normalize if necessary. - * - * - U_COMPARE_CODE_POINT_ORDER - * Set to choose code point order instead of code unit order - * (see u_strCompare for details). - * - * - U_COMPARE_IGNORE_CASE - * Set to compare strings case-insensitively using case folding, - * instead of case-sensitively. - * If set, then the following case folding options are used. - * - * - Options as used with case-insensitive comparisons, currently: - * - * - U_FOLD_CASE_EXCLUDE_SPECIAL_I - * (see u_strCaseCompare for details) - * - * - regular normalization options shifted left by UNORM_COMPARE_NORM_OPTIONS_SHIFT - * - * @param pErrorCode ICU error code in/out parameter. - * Must fulfill U_SUCCESS before the function call. - * @return <0 or 0 or >0 as usual for string comparisons - * - * @see unorm_normalize - * @see UNORM_FCD - * @see u_strCompare - * @see u_strCaseCompare - * - * @stable ICU 2.2 - */ -U_STABLE int32_t U_EXPORT2 -unorm_compare(const UChar *s1, int32_t length1, - const UChar *s2, int32_t length2, - uint32_t options, - UErrorCode *pErrorCode); - -#endif /* #if !UCONFIG_NO_NORMALIZATION */ - -#endif diff --git a/WebKit/mac/icu/unicode/urename.h b/WebKit/mac/icu/unicode/urename.h deleted file mode 100644 index 5562592..0000000 --- a/WebKit/mac/icu/unicode/urename.h +++ /dev/null @@ -1,1468 +0,0 @@ -/* -******************************************************************************* -* Copyright (C) 2002-2004, International Business Machines -* Corporation and others. All Rights Reserved. -******************************************************************************* -* -* file name: urename.h -* encoding: US-ASCII -* tab size: 8 (not used) -* indentation:4 -* -* Created by: Perl script written by Vladimir Weinstein -* -* Contains data for renaming ICU exports. -* Gets included by umachine.h -* -* THIS FILE IS MACHINE-GENERATED, DON'T PLAY WITH IT IF YOU DON'T KNOW WHAT -* YOU ARE DOING, OTHERWISE VERY BAD THINGS WILL HAPPEN! -*/ - -#ifndef URENAME_H -#define URENAME_H - -/* Uncomment the following line to disable renaming on platforms - that do not use Autoconf. */ -/* #define U_DISABLE_RENAMING 1 */ - -#if !U_DISABLE_RENAMING - -/* C exports renaming data */ - -#define T_CString_int64ToString T_CString_int64ToString_3_2 -#define T_CString_integerToString T_CString_integerToString_3_2 -#define T_CString_stricmp T_CString_stricmp_3_2 -#define T_CString_stringToInteger T_CString_stringToInteger_3_2 -#define T_CString_strnicmp T_CString_strnicmp_3_2 -#define T_CString_toLowerCase T_CString_toLowerCase_3_2 -#define T_CString_toUpperCase T_CString_toUpperCase_3_2 -#define T_FileStream_close T_FileStream_close_3_2 -#define T_FileStream_eof T_FileStream_eof_3_2 -#define T_FileStream_error T_FileStream_error_3_2 -#define T_FileStream_file_exists T_FileStream_file_exists_3_2 -#define T_FileStream_getc T_FileStream_getc_3_2 -#define T_FileStream_open T_FileStream_open_3_2 -#define T_FileStream_peek T_FileStream_peek_3_2 -#define T_FileStream_putc T_FileStream_putc_3_2 -#define T_FileStream_read T_FileStream_read_3_2 -#define T_FileStream_readLine T_FileStream_readLine_3_2 -#define T_FileStream_remove T_FileStream_remove_3_2 -#define T_FileStream_rewind T_FileStream_rewind_3_2 -#define T_FileStream_size T_FileStream_size_3_2 -#define T_FileStream_stderr T_FileStream_stderr_3_2 -#define T_FileStream_stdin T_FileStream_stdin_3_2 -#define T_FileStream_stdout T_FileStream_stdout_3_2 -#define T_FileStream_ungetc T_FileStream_ungetc_3_2 -#define T_FileStream_write T_FileStream_write_3_2 -#define T_FileStream_writeLine T_FileStream_writeLine_3_2 -#define UCNV_FROM_U_CALLBACK_ESCAPE UCNV_FROM_U_CALLBACK_ESCAPE_3_2 -#define UCNV_FROM_U_CALLBACK_SKIP UCNV_FROM_U_CALLBACK_SKIP_3_2 -#define UCNV_FROM_U_CALLBACK_STOP UCNV_FROM_U_CALLBACK_STOP_3_2 -#define UCNV_FROM_U_CALLBACK_SUBSTITUTE UCNV_FROM_U_CALLBACK_SUBSTITUTE_3_2 -#define UCNV_TO_U_CALLBACK_ESCAPE UCNV_TO_U_CALLBACK_ESCAPE_3_2 -#define UCNV_TO_U_CALLBACK_SKIP UCNV_TO_U_CALLBACK_SKIP_3_2 -#define UCNV_TO_U_CALLBACK_STOP UCNV_TO_U_CALLBACK_STOP_3_2 -#define UCNV_TO_U_CALLBACK_SUBSTITUTE UCNV_TO_U_CALLBACK_SUBSTITUTE_3_2 -#define UDataMemory_createNewInstance UDataMemory_createNewInstance_3_2 -#define UDataMemory_init UDataMemory_init_3_2 -#define UDataMemory_isLoaded UDataMemory_isLoaded_3_2 -#define UDataMemory_normalizeDataPointer UDataMemory_normalizeDataPointer_3_2 -#define UDataMemory_setData UDataMemory_setData_3_2 -#define UDatamemory_assign UDatamemory_assign_3_2 -#define _ASCIIData _ASCIIData_3_2 -#define _Bocu1Data _Bocu1Data_3_2 -#define _CESU8Data _CESU8Data_3_2 -#define _HZData _HZData_3_2 -#define _IMAPData _IMAPData_3_2 -#define _ISCIIData _ISCIIData_3_2 -#define _ISO2022Data _ISO2022Data_3_2 -#define _LMBCSData1 _LMBCSData1_3_2 -#define _LMBCSData11 _LMBCSData11_3_2 -#define _LMBCSData16 _LMBCSData16_3_2 -#define _LMBCSData17 _LMBCSData17_3_2 -#define _LMBCSData18 _LMBCSData18_3_2 -#define _LMBCSData19 _LMBCSData19_3_2 -#define _LMBCSData2 _LMBCSData2_3_2 -#define _LMBCSData3 _LMBCSData3_3_2 -#define _LMBCSData4 _LMBCSData4_3_2 -#define _LMBCSData5 _LMBCSData5_3_2 -#define _LMBCSData6 _LMBCSData6_3_2 -#define _LMBCSData8 _LMBCSData8_3_2 -#define _Latin1Data _Latin1Data_3_2 -#define _MBCSData _MBCSData_3_2 -#define _SCSUData _SCSUData_3_2 -#define _UTF16BEData _UTF16BEData_3_2 -#define _UTF16Data _UTF16Data_3_2 -#define _UTF16LEData _UTF16LEData_3_2 -#define _UTF32BEData _UTF32BEData_3_2 -#define _UTF32Data _UTF32Data_3_2 -#define _UTF32LEData _UTF32LEData_3_2 -#define _UTF7Data _UTF7Data_3_2 -#define _UTF8Data _UTF8Data_3_2 -#define cmemory_cleanup cmemory_cleanup_3_2 -#define cmemory_inUse cmemory_inUse_3_2 -#define locale_getKeywords locale_getKeywords_3_2 -#define locale_get_default locale_get_default_3_2 -#define locale_set_default locale_set_default_3_2 -#define res_countArrayItems res_countArrayItems_3_2 -#define res_findResource res_findResource_3_2 -#define res_getAlias res_getAlias_3_2 -#define res_getArrayItem res_getArrayItem_3_2 -#define res_getBinary res_getBinary_3_2 -#define res_getIntVector res_getIntVector_3_2 -#define res_getResource res_getResource_3_2 -#define res_getString res_getString_3_2 -#define res_getTableItemByIndex res_getTableItemByIndex_3_2 -#define res_getTableItemByKey res_getTableItemByKey_3_2 -#define res_load res_load_3_2 -#define res_unload res_unload_3_2 -#define transliterator_cleanup transliterator_cleanup_3_2 -#define u_UCharsToChars u_UCharsToChars_3_2 -#define u_austrcpy u_austrcpy_3_2 -#define u_austrncpy u_austrncpy_3_2 -#define u_catclose u_catclose_3_2 -#define u_catgets u_catgets_3_2 -#define u_catopen u_catopen_3_2 -#define u_charAge u_charAge_3_2 -#define u_charDigitValue u_charDigitValue_3_2 -#define u_charDirection u_charDirection_3_2 -#define u_charFromName u_charFromName_3_2 -#define u_charMirror u_charMirror_3_2 -#define u_charName u_charName_3_2 -#define u_charType u_charType_3_2 -#define u_charsToUChars u_charsToUChars_3_2 -#define u_cleanup u_cleanup_3_2 -#define u_countChar32 u_countChar32_3_2 -#define u_digit u_digit_3_2 -#define u_enumCharNames u_enumCharNames_3_2 -#define u_enumCharTypes u_enumCharTypes_3_2 -#define u_errorName u_errorName_3_2 -#define u_fclose u_fclose_3_2 -#define u_feof u_feof_3_2 -#define u_fflush u_fflush_3_2 -#define u_fgetConverter u_fgetConverter_3_2 -#define u_fgetc u_fgetc_3_2 -#define u_fgetcodepage u_fgetcodepage_3_2 -#define u_fgetcx u_fgetcx_3_2 -#define u_fgetfile u_fgetfile_3_2 -#define u_fgetlocale u_fgetlocale_3_2 -#define u_fgets u_fgets_3_2 -#define u_file_read u_file_read_3_2 -#define u_file_write u_file_write_3_2 -#define u_file_write_flush u_file_write_flush_3_2 -#define u_finit u_finit_3_2 -#define u_foldCase u_foldCase_3_2 -#define u_fopen u_fopen_3_2 -#define u_forDigit u_forDigit_3_2 -#define u_formatMessage u_formatMessage_3_2 -#define u_formatMessageWithError u_formatMessageWithError_3_2 -#define u_fprintf u_fprintf_3_2 -#define u_fprintf_u u_fprintf_u_3_2 -#define u_fputc u_fputc_3_2 -#define u_fputs u_fputs_3_2 -#define u_frewind u_frewind_3_2 -#define u_fscanf u_fscanf_3_2 -#define u_fscanf_u u_fscanf_u_3_2 -#define u_fsetcodepage u_fsetcodepage_3_2 -#define u_fsetlocale u_fsetlocale_3_2 -#define u_fsettransliterator u_fsettransliterator_3_2 -#define u_fstropen u_fstropen_3_2 -#define u_fungetc u_fungetc_3_2 -#define u_getCombiningClass u_getCombiningClass_3_2 -#define u_getDataDirectory u_getDataDirectory_3_2 -#define u_getDefaultConverter u_getDefaultConverter_3_2 -#define u_getFC_NFKC_Closure u_getFC_NFKC_Closure_3_2 -#define u_getISOComment u_getISOComment_3_2 -#define u_getIntPropertyMaxValue u_getIntPropertyMaxValue_3_2 -#define u_getIntPropertyMinValue u_getIntPropertyMinValue_3_2 -#define u_getIntPropertyValue u_getIntPropertyValue_3_2 -#define u_getNumericValue u_getNumericValue_3_2 -#define u_getPropertyEnum u_getPropertyEnum_3_2 -#define u_getPropertyName u_getPropertyName_3_2 -#define u_getPropertyValueEnum u_getPropertyValueEnum_3_2 -#define u_getPropertyValueName u_getPropertyValueName_3_2 -#define u_getUnicodeProperties u_getUnicodeProperties_3_2 -#define u_getUnicodeVersion u_getUnicodeVersion_3_2 -#define u_getVersion u_getVersion_3_2 -#define u_growBufferFromStatic u_growBufferFromStatic_3_2 -#define u_hasBinaryProperty u_hasBinaryProperty_3_2 -#define u_init u_init_3_2 -#define u_isIDIgnorable u_isIDIgnorable_3_2 -#define u_isIDPart u_isIDPart_3_2 -#define u_isIDStart u_isIDStart_3_2 -#define u_isISOControl u_isISOControl_3_2 -#define u_isJavaIDPart u_isJavaIDPart_3_2 -#define u_isJavaIDStart u_isJavaIDStart_3_2 -#define u_isJavaSpaceChar u_isJavaSpaceChar_3_2 -#define u_isMirrored u_isMirrored_3_2 -#define u_isUAlphabetic u_isUAlphabetic_3_2 -#define u_isULowercase u_isULowercase_3_2 -#define u_isUUppercase u_isUUppercase_3_2 -#define u_isUWhiteSpace u_isUWhiteSpace_3_2 -#define u_isWhitespace u_isWhitespace_3_2 -#define u_isalnum u_isalnum_3_2 -#define u_isalpha u_isalpha_3_2 -#define u_isbase u_isbase_3_2 -#define u_isblank u_isblank_3_2 -#define u_iscntrl u_iscntrl_3_2 -#define u_isdefined u_isdefined_3_2 -#define u_isdigit u_isdigit_3_2 -#define u_isgraph u_isgraph_3_2 -#define u_islower u_islower_3_2 -#define u_isprint u_isprint_3_2 -#define u_ispunct u_ispunct_3_2 -#define u_isspace u_isspace_3_2 -#define u_istitle u_istitle_3_2 -#define u_isupper u_isupper_3_2 -#define u_isxdigit u_isxdigit_3_2 -#define u_lengthOfIdenticalLevelRun u_lengthOfIdenticalLevelRun_3_2 -#define u_locbund_close u_locbund_close_3_2 -#define u_locbund_getNumberFormat u_locbund_getNumberFormat_3_2 -#define u_locbund_init u_locbund_init_3_2 -#define u_memcasecmp u_memcasecmp_3_2 -#define u_memchr u_memchr_3_2 -#define u_memchr32 u_memchr32_3_2 -#define u_memcmp u_memcmp_3_2 -#define u_memcmpCodePointOrder u_memcmpCodePointOrder_3_2 -#define u_memcpy u_memcpy_3_2 -#define u_memmove u_memmove_3_2 -#define u_memrchr u_memrchr_3_2 -#define u_memrchr32 u_memrchr32_3_2 -#define u_memset u_memset_3_2 -#define u_parseMessage u_parseMessage_3_2 -#define u_parseMessageWithError u_parseMessageWithError_3_2 -#define u_printf_parse u_printf_parse_3_2 -#define u_releaseDefaultConverter u_releaseDefaultConverter_3_2 -#define u_scanf_parse u_scanf_parse_3_2 -#define u_setAtomicIncDecFunctions u_setAtomicIncDecFunctions_3_2 -#define u_setDataDirectory u_setDataDirectory_3_2 -#define u_setMemoryFunctions u_setMemoryFunctions_3_2 -#define u_setMutexFunctions u_setMutexFunctions_3_2 -#define u_shapeArabic u_shapeArabic_3_2 -#define u_snprintf u_snprintf_3_2 -#define u_snprintf_u u_snprintf_u_3_2 -#define u_sprintf u_sprintf_3_2 -#define u_sprintf_u u_sprintf_u_3_2 -#define u_sscanf u_sscanf_3_2 -#define u_sscanf_u u_sscanf_u_3_2 -#define u_strCaseCompare u_strCaseCompare_3_2 -#define u_strCompare u_strCompare_3_2 -#define u_strCompareIter u_strCompareIter_3_2 -#define u_strFindFirst u_strFindFirst_3_2 -#define u_strFindLast u_strFindLast_3_2 -#define u_strFoldCase u_strFoldCase_3_2 -#define u_strFromPunycode u_strFromPunycode_3_2 -#define u_strFromUTF32 u_strFromUTF32_3_2 -#define u_strFromUTF8 u_strFromUTF8_3_2 -#define u_strFromWCS u_strFromWCS_3_2 -#define u_strHasMoreChar32Than u_strHasMoreChar32Than_3_2 -#define u_strToLower u_strToLower_3_2 -#define u_strToPunycode u_strToPunycode_3_2 -#define u_strToTitle u_strToTitle_3_2 -#define u_strToUTF32 u_strToUTF32_3_2 -#define u_strToUTF8 u_strToUTF8_3_2 -#define u_strToUpper u_strToUpper_3_2 -#define u_strToWCS u_strToWCS_3_2 -#define u_strcasecmp u_strcasecmp_3_2 -#define u_strcat u_strcat_3_2 -#define u_strchr u_strchr_3_2 -#define u_strchr32 u_strchr32_3_2 -#define u_strcmp u_strcmp_3_2 -#define u_strcmpCodePointOrder u_strcmpCodePointOrder_3_2 -#define u_strcmpFold u_strcmpFold_3_2 -#define u_strcpy u_strcpy_3_2 -#define u_strcspn u_strcspn_3_2 -#define u_strlen u_strlen_3_2 -#define u_strncasecmp u_strncasecmp_3_2 -#define u_strncat u_strncat_3_2 -#define u_strncmp u_strncmp_3_2 -#define u_strncmpCodePointOrder u_strncmpCodePointOrder_3_2 -#define u_strncpy u_strncpy_3_2 -#define u_strpbrk u_strpbrk_3_2 -#define u_strrchr u_strrchr_3_2 -#define u_strrchr32 u_strrchr32_3_2 -#define u_strrstr u_strrstr_3_2 -#define u_strspn u_strspn_3_2 -#define u_strstr u_strstr_3_2 -#define u_strtok_r u_strtok_r_3_2 -#define u_terminateChars u_terminateChars_3_2 -#define u_terminateUChar32s u_terminateUChar32s_3_2 -#define u_terminateUChars u_terminateUChars_3_2 -#define u_terminateWChars u_terminateWChars_3_2 -#define u_tolower u_tolower_3_2 -#define u_totitle u_totitle_3_2 -#define u_toupper u_toupper_3_2 -#define u_uastrcpy u_uastrcpy_3_2 -#define u_uastrncpy u_uastrncpy_3_2 -#define u_unescape u_unescape_3_2 -#define u_unescapeAt u_unescapeAt_3_2 -#define u_versionFromString u_versionFromString_3_2 -#define u_versionToString u_versionToString_3_2 -#define u_vformatMessage u_vformatMessage_3_2 -#define u_vformatMessageWithError u_vformatMessageWithError_3_2 -#define u_vfprintf u_vfprintf_3_2 -#define u_vfprintf_u u_vfprintf_u_3_2 -#define u_vfscanf u_vfscanf_3_2 -#define u_vfscanf_u u_vfscanf_u_3_2 -#define u_vparseMessage u_vparseMessage_3_2 -#define u_vparseMessageWithError u_vparseMessageWithError_3_2 -#define u_vsnprintf u_vsnprintf_3_2 -#define u_vsnprintf_u u_vsnprintf_u_3_2 -#define u_vsprintf u_vsprintf_3_2 -#define u_vsprintf_u u_vsprintf_u_3_2 -#define u_vsscanf u_vsscanf_3_2 -#define u_vsscanf_u u_vsscanf_u_3_2 -#define u_writeDiff u_writeDiff_3_2 -#define u_writeIdenticalLevelRun u_writeIdenticalLevelRun_3_2 -#define u_writeIdenticalLevelRunTwoChars u_writeIdenticalLevelRunTwoChars_3_2 -#define ubidi_close ubidi_close_3_2 -#define ubidi_countRuns ubidi_countRuns_3_2 -#define ubidi_getDirection ubidi_getDirection_3_2 -#define ubidi_getLength ubidi_getLength_3_2 -#define ubidi_getLevelAt ubidi_getLevelAt_3_2 -#define ubidi_getLevels ubidi_getLevels_3_2 -#define ubidi_getLogicalIndex ubidi_getLogicalIndex_3_2 -#define ubidi_getLogicalMap ubidi_getLogicalMap_3_2 -#define ubidi_getLogicalRun ubidi_getLogicalRun_3_2 -#define ubidi_getMemory ubidi_getMemory_3_2 -#define ubidi_getParaLevel ubidi_getParaLevel_3_2 -#define ubidi_getRuns ubidi_getRuns_3_2 -#define ubidi_getText ubidi_getText_3_2 -#define ubidi_getVisualIndex ubidi_getVisualIndex_3_2 -#define ubidi_getVisualMap ubidi_getVisualMap_3_2 -#define ubidi_getVisualRun ubidi_getVisualRun_3_2 -#define ubidi_invertMap ubidi_invertMap_3_2 -#define ubidi_isInverse ubidi_isInverse_3_2 -#define ubidi_open ubidi_open_3_2 -#define ubidi_openSized ubidi_openSized_3_2 -#define ubidi_reorderLogical ubidi_reorderLogical_3_2 -#define ubidi_reorderVisual ubidi_reorderVisual_3_2 -#define ubidi_setInverse ubidi_setInverse_3_2 -#define ubidi_setLine ubidi_setLine_3_2 -#define ubidi_setPara ubidi_setPara_3_2 -#define ubidi_writeReordered ubidi_writeReordered_3_2 -#define ubidi_writeReverse ubidi_writeReverse_3_2 -#define ublock_getCode ublock_getCode_3_2 -#define ubrk_close ubrk_close_3_2 -#define ubrk_countAvailable ubrk_countAvailable_3_2 -#define ubrk_current ubrk_current_3_2 -#define ubrk_first ubrk_first_3_2 -#define ubrk_following ubrk_following_3_2 -#define ubrk_getAvailable ubrk_getAvailable_3_2 -#define ubrk_getLocaleByType ubrk_getLocaleByType_3_2 -#define ubrk_getRuleStatus ubrk_getRuleStatus_3_2 -#define ubrk_getRuleStatusVec ubrk_getRuleStatusVec_3_2 -#define ubrk_isBoundary ubrk_isBoundary_3_2 -#define ubrk_last ubrk_last_3_2 -#define ubrk_next ubrk_next_3_2 -#define ubrk_open ubrk_open_3_2 -#define ubrk_openRules ubrk_openRules_3_2 -#define ubrk_preceding ubrk_preceding_3_2 -#define ubrk_previous ubrk_previous_3_2 -#define ubrk_safeClone ubrk_safeClone_3_2 -#define ubrk_setText ubrk_setText_3_2 -#define ubrk_swap ubrk_swap_3_2 -#define ucal_add ucal_add_3_2 -#define ucal_clear ucal_clear_3_2 -#define ucal_clearField ucal_clearField_3_2 -#define ucal_close ucal_close_3_2 -#define ucal_countAvailable ucal_countAvailable_3_2 -#define ucal_equivalentTo ucal_equivalentTo_3_2 -#define ucal_get ucal_get_3_2 -#define ucal_getAttribute ucal_getAttribute_3_2 -#define ucal_getAvailable ucal_getAvailable_3_2 -#define ucal_getDSTSavings ucal_getDSTSavings_3_2 -#define ucal_getDefaultTimeZone ucal_getDefaultTimeZone_3_2 -#define ucal_getLimit ucal_getLimit_3_2 -#define ucal_getLocaleByType ucal_getLocaleByType_3_2 -#define ucal_getMillis ucal_getMillis_3_2 -#define ucal_getNow ucal_getNow_3_2 -#define ucal_getTimeZoneDisplayName ucal_getTimeZoneDisplayName_3_2 -#define ucal_inDaylightTime ucal_inDaylightTime_3_2 -#define ucal_isSet ucal_isSet_3_2 -#define ucal_open ucal_open_3_2 -#define ucal_openCountryTimeZones ucal_openCountryTimeZones_3_2 -#define ucal_openTimeZones ucal_openTimeZones_3_2 -#define ucal_roll ucal_roll_3_2 -#define ucal_set ucal_set_3_2 -#define ucal_setAttribute ucal_setAttribute_3_2 -#define ucal_setDate ucal_setDate_3_2 -#define ucal_setDateTime ucal_setDateTime_3_2 -#define ucal_setDefaultTimeZone ucal_setDefaultTimeZone_3_2 -#define ucal_setMillis ucal_setMillis_3_2 -#define ucal_setTimeZone ucal_setTimeZone_3_2 -#define ucase_addPropertyStarts ucase_addPropertyStarts_3_2 -#define ucase_close ucase_close_3_2 -#define ucase_fold ucase_fold_3_2 -#define ucase_getSingleton ucase_getSingleton_3_2 -#define ucase_getType ucase_getType_3_2 -#define ucase_getTypeOrIgnorable ucase_getTypeOrIgnorable_3_2 -#define ucase_isCaseSensitive ucase_isCaseSensitive_3_2 -#define ucase_isSoftDotted ucase_isSoftDotted_3_2 -#define ucase_open ucase_open_3_2 -#define ucase_openBinary ucase_openBinary_3_2 -#define ucase_swap ucase_swap_3_2 -#define ucase_toFullFolding ucase_toFullFolding_3_2 -#define ucase_toFullLower ucase_toFullLower_3_2 -#define ucase_toFullTitle ucase_toFullTitle_3_2 -#define ucase_toFullUpper ucase_toFullUpper_3_2 -#define ucase_tolower ucase_tolower_3_2 -#define ucase_totitle ucase_totitle_3_2 -#define ucase_toupper ucase_toupper_3_2 -#define uchar_addPropertyStarts uchar_addPropertyStarts_3_2 -#define uchar_getHST uchar_getHST_3_2 -#define uchar_swapNames uchar_swapNames_3_2 -#define ucln_common_lib_cleanup ucln_common_lib_cleanup_3_2 -#define ucln_common_registerCleanup ucln_common_registerCleanup_3_2 -#define ucln_i18n_registerCleanup ucln_i18n_registerCleanup_3_2 -#define ucln_registerCleanup ucln_registerCleanup_3_2 -#define ucmp8_close ucmp8_close_3_2 -#define ucmp8_compact ucmp8_compact_3_2 -#define ucmp8_expand ucmp8_expand_3_2 -#define ucmp8_flattenMem ucmp8_flattenMem_3_2 -#define ucmp8_getArray ucmp8_getArray_3_2 -#define ucmp8_getCount ucmp8_getCount_3_2 -#define ucmp8_getIndex ucmp8_getIndex_3_2 -#define ucmp8_getkBlockCount ucmp8_getkBlockCount_3_2 -#define ucmp8_getkUnicodeCount ucmp8_getkUnicodeCount_3_2 -#define ucmp8_init ucmp8_init_3_2 -#define ucmp8_initAdopt ucmp8_initAdopt_3_2 -#define ucmp8_initAlias ucmp8_initAlias_3_2 -#define ucmp8_initBogus ucmp8_initBogus_3_2 -#define ucmp8_initFromData ucmp8_initFromData_3_2 -#define ucmp8_isBogus ucmp8_isBogus_3_2 -#define ucmp8_open ucmp8_open_3_2 -#define ucmp8_openAdopt ucmp8_openAdopt_3_2 -#define ucmp8_openAlias ucmp8_openAlias_3_2 -#define ucmp8_set ucmp8_set_3_2 -#define ucmp8_setRange ucmp8_setRange_3_2 -#define ucnv_MBCSFromUChar32 ucnv_MBCSFromUChar32_3_2 -#define ucnv_MBCSFromUnicodeWithOffsets ucnv_MBCSFromUnicodeWithOffsets_3_2 -#define ucnv_MBCSGetType ucnv_MBCSGetType_3_2 -#define ucnv_MBCSGetUnicodeSetForBytes ucnv_MBCSGetUnicodeSetForBytes_3_2 -#define ucnv_MBCSGetUnicodeSetForUnicode ucnv_MBCSGetUnicodeSetForUnicode_3_2 -#define ucnv_MBCSIsLeadByte ucnv_MBCSIsLeadByte_3_2 -#define ucnv_MBCSSimpleGetNextUChar ucnv_MBCSSimpleGetNextUChar_3_2 -#define ucnv_MBCSToUnicodeWithOffsets ucnv_MBCSToUnicodeWithOffsets_3_2 -#define ucnv_cbFromUWriteBytes ucnv_cbFromUWriteBytes_3_2 -#define ucnv_cbFromUWriteSub ucnv_cbFromUWriteSub_3_2 -#define ucnv_cbFromUWriteUChars ucnv_cbFromUWriteUChars_3_2 -#define ucnv_cbToUWriteSub ucnv_cbToUWriteSub_3_2 -#define ucnv_cbToUWriteUChars ucnv_cbToUWriteUChars_3_2 -#define ucnv_close ucnv_close_3_2 -#define ucnv_compareNames ucnv_compareNames_3_2 -#define ucnv_convert ucnv_convert_3_2 -#define ucnv_convertEx ucnv_convertEx_3_2 -#define ucnv_copyPlatformString ucnv_copyPlatformString_3_2 -#define ucnv_countAliases ucnv_countAliases_3_2 -#define ucnv_countAvailable ucnv_countAvailable_3_2 -#define ucnv_countStandards ucnv_countStandards_3_2 -#define ucnv_createAlgorithmicConverter ucnv_createAlgorithmicConverter_3_2 -#define ucnv_createConverter ucnv_createConverter_3_2 -#define ucnv_createConverterFromPackage ucnv_createConverterFromPackage_3_2 -#define ucnv_createConverterFromSharedData ucnv_createConverterFromSharedData_3_2 -#define ucnv_detectUnicodeSignature ucnv_detectUnicodeSignature_3_2 -#define ucnv_extContinueMatchFromU ucnv_extContinueMatchFromU_3_2 -#define ucnv_extContinueMatchToU ucnv_extContinueMatchToU_3_2 -#define ucnv_extGetUnicodeSet ucnv_extGetUnicodeSet_3_2 -#define ucnv_extInitialMatchFromU ucnv_extInitialMatchFromU_3_2 -#define ucnv_extInitialMatchToU ucnv_extInitialMatchToU_3_2 -#define ucnv_extSimpleMatchFromU ucnv_extSimpleMatchFromU_3_2 -#define ucnv_extSimpleMatchToU ucnv_extSimpleMatchToU_3_2 -#define ucnv_fixFileSeparator ucnv_fixFileSeparator_3_2 -#define ucnv_flushCache ucnv_flushCache_3_2 -#define ucnv_fromAlgorithmic ucnv_fromAlgorithmic_3_2 -#define ucnv_fromUChars ucnv_fromUChars_3_2 -#define ucnv_fromUWriteBytes ucnv_fromUWriteBytes_3_2 -#define ucnv_fromUnicode ucnv_fromUnicode_3_2 -#define ucnv_fromUnicode_UTF8 ucnv_fromUnicode_UTF8_3_2 -#define ucnv_fromUnicode_UTF8_OFFSETS_LOGIC ucnv_fromUnicode_UTF8_OFFSETS_LOGIC_3_2 -#define ucnv_getAlias ucnv_getAlias_3_2 -#define ucnv_getAliases ucnv_getAliases_3_2 -#define ucnv_getAvailableName ucnv_getAvailableName_3_2 -#define ucnv_getCCSID ucnv_getCCSID_3_2 -#define ucnv_getCanonicalName ucnv_getCanonicalName_3_2 -#define ucnv_getCompleteUnicodeSet ucnv_getCompleteUnicodeSet_3_2 -#define ucnv_getDefaultName ucnv_getDefaultName_3_2 -#define ucnv_getDisplayName ucnv_getDisplayName_3_2 -#define ucnv_getFromUCallBack ucnv_getFromUCallBack_3_2 -#define ucnv_getInvalidChars ucnv_getInvalidChars_3_2 -#define ucnv_getInvalidUChars ucnv_getInvalidUChars_3_2 -#define ucnv_getMaxCharSize ucnv_getMaxCharSize_3_2 -#define ucnv_getMinCharSize ucnv_getMinCharSize_3_2 -#define ucnv_getName ucnv_getName_3_2 -#define ucnv_getNextUChar ucnv_getNextUChar_3_2 -#define ucnv_getNonSurrogateUnicodeSet ucnv_getNonSurrogateUnicodeSet_3_2 -#define ucnv_getPlatform ucnv_getPlatform_3_2 -#define ucnv_getStandard ucnv_getStandard_3_2 -#define ucnv_getStandardName ucnv_getStandardName_3_2 -#define ucnv_getStarters ucnv_getStarters_3_2 -#define ucnv_getSubstChars ucnv_getSubstChars_3_2 -#define ucnv_getToUCallBack ucnv_getToUCallBack_3_2 -#define ucnv_getType ucnv_getType_3_2 -#define ucnv_getUnicodeSet ucnv_getUnicodeSet_3_2 -#define ucnv_incrementRefCount ucnv_incrementRefCount_3_2 -#define ucnv_io_countAliases ucnv_io_countAliases_3_2 -#define ucnv_io_countAvailableAliases ucnv_io_countAvailableAliases_3_2 -#define ucnv_io_countAvailableConverters ucnv_io_countAvailableConverters_3_2 -#define ucnv_io_countStandards ucnv_io_countStandards_3_2 -#define ucnv_io_flushAvailableConverterCache ucnv_io_flushAvailableConverterCache_3_2 -#define ucnv_io_getAlias ucnv_io_getAlias_3_2 -#define ucnv_io_getAliases ucnv_io_getAliases_3_2 -#define ucnv_io_getAvailableConverter ucnv_io_getAvailableConverter_3_2 -#define ucnv_io_getConverterName ucnv_io_getConverterName_3_2 -#define ucnv_io_getDefaultConverterName ucnv_io_getDefaultConverterName_3_2 -#define ucnv_io_setDefaultConverterName ucnv_io_setDefaultConverterName_3_2 -#define ucnv_io_stripASCIIForCompare ucnv_io_stripASCIIForCompare_3_2 -#define ucnv_io_stripEBCDICForCompare ucnv_io_stripEBCDICForCompare_3_2 -#define ucnv_isAmbiguous ucnv_isAmbiguous_3_2 -#define ucnv_load ucnv_load_3_2 -#define ucnv_loadSharedData ucnv_loadSharedData_3_2 -#define ucnv_open ucnv_open_3_2 -#define ucnv_openAllNames ucnv_openAllNames_3_2 -#define ucnv_openCCSID ucnv_openCCSID_3_2 -#define ucnv_openPackage ucnv_openPackage_3_2 -#define ucnv_openStandardNames ucnv_openStandardNames_3_2 -#define ucnv_openU ucnv_openU_3_2 -#define ucnv_reset ucnv_reset_3_2 -#define ucnv_resetFromUnicode ucnv_resetFromUnicode_3_2 -#define ucnv_resetToUnicode ucnv_resetToUnicode_3_2 -#define ucnv_safeClone ucnv_safeClone_3_2 -#define ucnv_setDefaultName ucnv_setDefaultName_3_2 -#define ucnv_setFallback ucnv_setFallback_3_2 -#define ucnv_setFromUCallBack ucnv_setFromUCallBack_3_2 -#define ucnv_setSubstChars ucnv_setSubstChars_3_2 -#define ucnv_setToUCallBack ucnv_setToUCallBack_3_2 -#define ucnv_swap ucnv_swap_3_2 -#define ucnv_swapAliases ucnv_swapAliases_3_2 -#define ucnv_toAlgorithmic ucnv_toAlgorithmic_3_2 -#define ucnv_toUChars ucnv_toUChars_3_2 -#define ucnv_toUWriteCodePoint ucnv_toUWriteCodePoint_3_2 -#define ucnv_toUWriteUChars ucnv_toUWriteUChars_3_2 -#define ucnv_toUnicode ucnv_toUnicode_3_2 -#define ucnv_unload ucnv_unload_3_2 -#define ucnv_unloadSharedDataIfReady ucnv_unloadSharedDataIfReady_3_2 -#define ucnv_usesFallback ucnv_usesFallback_3_2 -#define ucol_allocWeights ucol_allocWeights_3_2 -#define ucol_assembleTailoringTable ucol_assembleTailoringTable_3_2 -#define ucol_calcSortKey ucol_calcSortKey_3_2 -#define ucol_calcSortKeySimpleTertiary ucol_calcSortKeySimpleTertiary_3_2 -#define ucol_cloneBinary ucol_cloneBinary_3_2 -#define ucol_cloneRuleData ucol_cloneRuleData_3_2 -#define ucol_close ucol_close_3_2 -#define ucol_closeElements ucol_closeElements_3_2 -#define ucol_collatorToIdentifier ucol_collatorToIdentifier_3_2 -#define ucol_countAvailable ucol_countAvailable_3_2 -#define ucol_createElements ucol_createElements_3_2 -#define ucol_doCE ucol_doCE_3_2 -#define ucol_equal ucol_equal_3_2 -#define ucol_equals ucol_equals_3_2 -#define ucol_getAttribute ucol_getAttribute_3_2 -#define ucol_getAttributeOrDefault ucol_getAttributeOrDefault_3_2 -#define ucol_getAvailable ucol_getAvailable_3_2 -#define ucol_getBound ucol_getBound_3_2 -#define ucol_getCEGenerator ucol_getCEGenerator_3_2 -#define ucol_getCEStrengthDifference ucol_getCEStrengthDifference_3_2 -#define ucol_getContractions ucol_getContractions_3_2 -#define ucol_getDisplayName ucol_getDisplayName_3_2 -#define ucol_getFirstCE ucol_getFirstCE_3_2 -#define ucol_getFunctionalEquivalent ucol_getFunctionalEquivalent_3_2 -#define ucol_getKeywordValues ucol_getKeywordValues_3_2 -#define ucol_getKeywords ucol_getKeywords_3_2 -#define ucol_getLocale ucol_getLocale_3_2 -#define ucol_getLocaleByType ucol_getLocaleByType_3_2 -#define ucol_getMaxExpansion ucol_getMaxExpansion_3_2 -#define ucol_getNextCE ucol_getNextCE_3_2 -#define ucol_getNextGenerated ucol_getNextGenerated_3_2 -#define ucol_getOffset ucol_getOffset_3_2 -#define ucol_getPrevCE ucol_getPrevCE_3_2 -#define ucol_getRules ucol_getRules_3_2 -#define ucol_getRulesEx ucol_getRulesEx_3_2 -#define ucol_getShortDefinitionString ucol_getShortDefinitionString_3_2 -#define ucol_getSimpleCEGenerator ucol_getSimpleCEGenerator_3_2 -#define ucol_getSortKey ucol_getSortKey_3_2 -#define ucol_getSortKeySize ucol_getSortKeySize_3_2 -#define ucol_getSortKeyWithAllocation ucol_getSortKeyWithAllocation_3_2 -#define ucol_getStrength ucol_getStrength_3_2 -#define ucol_getTailoredSet ucol_getTailoredSet_3_2 -#define ucol_getUCAVersion ucol_getUCAVersion_3_2 -#define ucol_getUnsafeSet ucol_getUnsafeSet_3_2 -#define ucol_getVariableTop ucol_getVariableTop_3_2 -#define ucol_getVersion ucol_getVersion_3_2 -#define ucol_greater ucol_greater_3_2 -#define ucol_greaterOrEqual ucol_greaterOrEqual_3_2 -#define ucol_identifierToShortString ucol_identifierToShortString_3_2 -#define ucol_initBuffers ucol_initBuffers_3_2 -#define ucol_initCollator ucol_initCollator_3_2 -#define ucol_initInverseUCA ucol_initInverseUCA_3_2 -#define ucol_initUCA ucol_initUCA_3_2 -#define ucol_inv_getGapPositions ucol_inv_getGapPositions_3_2 -#define ucol_inv_getNextCE ucol_inv_getNextCE_3_2 -#define ucol_inv_getPrevCE ucol_inv_getPrevCE_3_2 -#define ucol_isTailored ucol_isTailored_3_2 -#define ucol_keyHashCode ucol_keyHashCode_3_2 -#define ucol_mergeSortkeys ucol_mergeSortkeys_3_2 -#define ucol_next ucol_next_3_2 -#define ucol_nextSortKeyPart ucol_nextSortKeyPart_3_2 -#define ucol_nextWeight ucol_nextWeight_3_2 -#define ucol_normalizeShortDefinitionString ucol_normalizeShortDefinitionString_3_2 -#define ucol_open ucol_open_3_2 -#define ucol_openAvailableLocales ucol_openAvailableLocales_3_2 -#define ucol_openBinary ucol_openBinary_3_2 -#define ucol_openElements ucol_openElements_3_2 -#define ucol_openFromIdentifier ucol_openFromIdentifier_3_2 -#define ucol_openFromShortString ucol_openFromShortString_3_2 -#define ucol_openRules ucol_openRules_3_2 -#define ucol_open_internal ucol_open_internal_3_2 -#define ucol_previous ucol_previous_3_2 -#define ucol_primaryOrder ucol_primaryOrder_3_2 -#define ucol_prv_getSpecialCE ucol_prv_getSpecialCE_3_2 -#define ucol_prv_getSpecialPrevCE ucol_prv_getSpecialPrevCE_3_2 -#define ucol_reset ucol_reset_3_2 -#define ucol_restoreVariableTop ucol_restoreVariableTop_3_2 -#define ucol_safeClone ucol_safeClone_3_2 -#define ucol_secondaryOrder ucol_secondaryOrder_3_2 -#define ucol_setAttribute ucol_setAttribute_3_2 -#define ucol_setOffset ucol_setOffset_3_2 -#define ucol_setOptionsFromHeader ucol_setOptionsFromHeader_3_2 -#define ucol_setReqValidLocales ucol_setReqValidLocales_3_2 -#define ucol_setStrength ucol_setStrength_3_2 -#define ucol_setText ucol_setText_3_2 -#define ucol_setVariableTop ucol_setVariableTop_3_2 -#define ucol_shortStringToIdentifier ucol_shortStringToIdentifier_3_2 -#define ucol_sortKeyToString ucol_sortKeyToString_3_2 -#define ucol_strcoll ucol_strcoll_3_2 -#define ucol_strcollIter ucol_strcollIter_3_2 -#define ucol_swap ucol_swap_3_2 -#define ucol_swapBinary ucol_swapBinary_3_2 -#define ucol_swapInverseUCA ucol_swapInverseUCA_3_2 -#define ucol_tertiaryOrder ucol_tertiaryOrder_3_2 -#define ucol_tok_assembleTokenList ucol_tok_assembleTokenList_3_2 -#define ucol_tok_closeTokenList ucol_tok_closeTokenList_3_2 -#define ucol_tok_getNextArgument ucol_tok_getNextArgument_3_2 -#define ucol_tok_initTokenList ucol_tok_initTokenList_3_2 -#define ucol_tok_parseNextToken ucol_tok_parseNextToken_3_2 -#define ucol_updateInternalState ucol_updateInternalState_3_2 -#define ucurr_forLocale ucurr_forLocale_3_2 -#define ucurr_getDefaultFractionDigits ucurr_getDefaultFractionDigits_3_2 -#define ucurr_getName ucurr_getName_3_2 -#define ucurr_getRoundingIncrement ucurr_getRoundingIncrement_3_2 -#define ucurr_register ucurr_register_3_2 -#define ucurr_unregister ucurr_unregister_3_2 -#define udat_applyPattern udat_applyPattern_3_2 -#define udat_clone udat_clone_3_2 -#define udat_close udat_close_3_2 -#define udat_countAvailable udat_countAvailable_3_2 -#define udat_countSymbols udat_countSymbols_3_2 -#define udat_format udat_format_3_2 -#define udat_get2DigitYearStart udat_get2DigitYearStart_3_2 -#define udat_getAvailable udat_getAvailable_3_2 -#define udat_getCalendar udat_getCalendar_3_2 -#define udat_getLocaleByType udat_getLocaleByType_3_2 -#define udat_getNumberFormat udat_getNumberFormat_3_2 -#define udat_getSymbols udat_getSymbols_3_2 -#define udat_isLenient udat_isLenient_3_2 -#define udat_open udat_open_3_2 -#define udat_parse udat_parse_3_2 -#define udat_parseCalendar udat_parseCalendar_3_2 -#define udat_set2DigitYearStart udat_set2DigitYearStart_3_2 -#define udat_setCalendar udat_setCalendar_3_2 -#define udat_setLenient udat_setLenient_3_2 -#define udat_setNumberFormat udat_setNumberFormat_3_2 -#define udat_setSymbols udat_setSymbols_3_2 -#define udat_toPattern udat_toPattern_3_2 -#define udata_checkCommonData udata_checkCommonData_3_2 -#define udata_close udata_close_3_2 -#define udata_closeSwapper udata_closeSwapper_3_2 -#define udata_getHeaderSize udata_getHeaderSize_3_2 -#define udata_getInfo udata_getInfo_3_2 -#define udata_getInfoSize udata_getInfoSize_3_2 -#define udata_getLength udata_getLength_3_2 -#define udata_getMemory udata_getMemory_3_2 -#define udata_getRawMemory udata_getRawMemory_3_2 -#define udata_open udata_open_3_2 -#define udata_openChoice udata_openChoice_3_2 -#define udata_openSwapper udata_openSwapper_3_2 -#define udata_openSwapperForInputData udata_openSwapperForInputData_3_2 -#define udata_printError udata_printError_3_2 -#define udata_readInt16 udata_readInt16_3_2 -#define udata_readInt32 udata_readInt32_3_2 -#define udata_setAppData udata_setAppData_3_2 -#define udata_setCommonData udata_setCommonData_3_2 -#define udata_swapDataHeader udata_swapDataHeader_3_2 -#define udata_swapInvStringBlock udata_swapInvStringBlock_3_2 -#define uenum_close uenum_close_3_2 -#define uenum_count uenum_count_3_2 -#define uenum_next uenum_next_3_2 -#define uenum_nextDefault uenum_nextDefault_3_2 -#define uenum_openCharStringsEnumeration uenum_openCharStringsEnumeration_3_2 -#define uenum_openStringEnumeration uenum_openStringEnumeration_3_2 -#define uenum_reset uenum_reset_3_2 -#define uenum_unext uenum_unext_3_2 -#define uenum_unextDefault uenum_unextDefault_3_2 -#define ufile_close_translit ufile_close_translit_3_2 -#define ufile_fill_uchar_buffer ufile_fill_uchar_buffer_3_2 -#define ufile_flush_translit ufile_flush_translit_3_2 -#define ufile_getch ufile_getch_3_2 -#define ufile_getch32 ufile_getch32_3_2 -#define ufmt_64tou ufmt_64tou_3_2 -#define ufmt_defaultCPToUnicode ufmt_defaultCPToUnicode_3_2 -#define ufmt_digitvalue ufmt_digitvalue_3_2 -#define ufmt_isdigit ufmt_isdigit_3_2 -#define ufmt_ptou ufmt_ptou_3_2 -#define ufmt_uto64 ufmt_uto64_3_2 -#define ufmt_utop ufmt_utop_3_2 -#define uhash_close uhash_close_3_2 -#define uhash_compareCaselessUnicodeString uhash_compareCaselessUnicodeString_3_2 -#define uhash_compareChars uhash_compareChars_3_2 -#define uhash_compareIChars uhash_compareIChars_3_2 -#define uhash_compareLong uhash_compareLong_3_2 -#define uhash_compareUChars uhash_compareUChars_3_2 -#define uhash_compareUnicodeString uhash_compareUnicodeString_3_2 -#define uhash_count uhash_count_3_2 -#define uhash_deleteHashtable uhash_deleteHashtable_3_2 -#define uhash_deleteUVector uhash_deleteUVector_3_2 -#define uhash_deleteUnicodeString uhash_deleteUnicodeString_3_2 -#define uhash_find uhash_find_3_2 -#define uhash_freeBlock uhash_freeBlock_3_2 -#define uhash_get uhash_get_3_2 -#define uhash_geti uhash_geti_3_2 -#define uhash_hashCaselessUnicodeString uhash_hashCaselessUnicodeString_3_2 -#define uhash_hashChars uhash_hashChars_3_2 -#define uhash_hashIChars uhash_hashIChars_3_2 -#define uhash_hashLong uhash_hashLong_3_2 -#define uhash_hashUChars uhash_hashUChars_3_2 -#define uhash_hashUCharsN uhash_hashUCharsN_3_2 -#define uhash_hashUnicodeString uhash_hashUnicodeString_3_2 -#define uhash_iget uhash_iget_3_2 -#define uhash_igeti uhash_igeti_3_2 -#define uhash_iput uhash_iput_3_2 -#define uhash_iputi uhash_iputi_3_2 -#define uhash_iremove uhash_iremove_3_2 -#define uhash_iremovei uhash_iremovei_3_2 -#define uhash_nextElement uhash_nextElement_3_2 -#define uhash_open uhash_open_3_2 -#define uhash_openSize uhash_openSize_3_2 -#define uhash_put uhash_put_3_2 -#define uhash_puti uhash_puti_3_2 -#define uhash_remove uhash_remove_3_2 -#define uhash_removeAll uhash_removeAll_3_2 -#define uhash_removeElement uhash_removeElement_3_2 -#define uhash_removei uhash_removei_3_2 -#define uhash_setKeyComparator uhash_setKeyComparator_3_2 -#define uhash_setKeyDeleter uhash_setKeyDeleter_3_2 -#define uhash_setKeyHasher uhash_setKeyHasher_3_2 -#define uhash_setResizePolicy uhash_setResizePolicy_3_2 -#define uhash_setValueDeleter uhash_setValueDeleter_3_2 -#define uhash_toki uhash_toki_3_2 -#define uhash_tokp uhash_tokp_3_2 -#define uhst_addPropertyStarts uhst_addPropertyStarts_3_2 -#define uidna_IDNToASCII uidna_IDNToASCII_3_2 -#define uidna_IDNToUnicode uidna_IDNToUnicode_3_2 -#define uidna_compare uidna_compare_3_2 -#define uidna_toASCII uidna_toASCII_3_2 -#define uidna_toUnicode uidna_toUnicode_3_2 -#define uiter_current32 uiter_current32_3_2 -#define uiter_getState uiter_getState_3_2 -#define uiter_next32 uiter_next32_3_2 -#define uiter_previous32 uiter_previous32_3_2 -#define uiter_setCharacterIterator uiter_setCharacterIterator_3_2 -#define uiter_setReplaceable uiter_setReplaceable_3_2 -#define uiter_setState uiter_setState_3_2 -#define uiter_setString uiter_setString_3_2 -#define uiter_setUTF16BE uiter_setUTF16BE_3_2 -#define uiter_setUTF8 uiter_setUTF8_3_2 -#define uloc_acceptLanguage uloc_acceptLanguage_3_2 -#define uloc_acceptLanguageFromHTTP uloc_acceptLanguageFromHTTP_3_2 -#define uloc_canonicalize uloc_canonicalize_3_2 -#define uloc_countAvailable uloc_countAvailable_3_2 -#define uloc_getAvailable uloc_getAvailable_3_2 -#define uloc_getBaseName uloc_getBaseName_3_2 -#define uloc_getCountry uloc_getCountry_3_2 -#define uloc_getDefault uloc_getDefault_3_2 -#define uloc_getDisplayCountry uloc_getDisplayCountry_3_2 -#define uloc_getDisplayKeyword uloc_getDisplayKeyword_3_2 -#define uloc_getDisplayKeywordValue uloc_getDisplayKeywordValue_3_2 -#define uloc_getDisplayLanguage uloc_getDisplayLanguage_3_2 -#define uloc_getDisplayName uloc_getDisplayName_3_2 -#define uloc_getDisplayScript uloc_getDisplayScript_3_2 -#define uloc_getDisplayVariant uloc_getDisplayVariant_3_2 -#define uloc_getISO3Country uloc_getISO3Country_3_2 -#define uloc_getISO3Language uloc_getISO3Language_3_2 -#define uloc_getISOCountries uloc_getISOCountries_3_2 -#define uloc_getISOLanguages uloc_getISOLanguages_3_2 -#define uloc_getKeywordValue uloc_getKeywordValue_3_2 -#define uloc_getLCID uloc_getLCID_3_2 -#define uloc_getLanguage uloc_getLanguage_3_2 -#define uloc_getName uloc_getName_3_2 -#define uloc_getParent uloc_getParent_3_2 -#define uloc_getScript uloc_getScript_3_2 -#define uloc_getVariant uloc_getVariant_3_2 -#define uloc_openKeywordList uloc_openKeywordList_3_2 -#define uloc_openKeywords uloc_openKeywords_3_2 -#define uloc_setDefault uloc_setDefault_3_2 -#define uloc_setKeywordValue uloc_setKeywordValue_3_2 -#define ulocdata_getExemplarSet ulocdata_getExemplarSet_3_2 -#define ulocdata_getMeasurementSystem ulocdata_getMeasurementSystem_3_2 -#define ulocdata_getPaperSize ulocdata_getPaperSize_3_2 -#define umsg_applyPattern umsg_applyPattern_3_2 -#define umsg_clone umsg_clone_3_2 -#define umsg_close umsg_close_3_2 -#define umsg_format umsg_format_3_2 -#define umsg_getLocale umsg_getLocale_3_2 -#define umsg_getLocaleByType umsg_getLocaleByType_3_2 -#define umsg_open umsg_open_3_2 -#define umsg_parse umsg_parse_3_2 -#define umsg_setLocale umsg_setLocale_3_2 -#define umsg_toPattern umsg_toPattern_3_2 -#define umsg_vformat umsg_vformat_3_2 -#define umsg_vparse umsg_vparse_3_2 -#define umtx_atomic_dec umtx_atomic_dec_3_2 -#define umtx_atomic_inc umtx_atomic_inc_3_2 -#define umtx_cleanup umtx_cleanup_3_2 -#define umtx_destroy umtx_destroy_3_2 -#define umtx_init umtx_init_3_2 -#define umtx_lock umtx_lock_3_2 -#define umtx_unlock umtx_unlock_3_2 -#define unorm_addPropertyStarts unorm_addPropertyStarts_3_2 -#define unorm_closeIter unorm_closeIter_3_2 -#define unorm_compare unorm_compare_3_2 -#define unorm_compose unorm_compose_3_2 -#define unorm_concatenate unorm_concatenate_3_2 -#define unorm_decompose unorm_decompose_3_2 -#define unorm_getCanonStartSet unorm_getCanonStartSet_3_2 -#define unorm_getCanonicalDecomposition unorm_getCanonicalDecomposition_3_2 -#define unorm_getDecomposition unorm_getDecomposition_3_2 -#define unorm_getFCD16FromCodePoint unorm_getFCD16FromCodePoint_3_2 -#define unorm_getFCDTrie unorm_getFCDTrie_3_2 -#define unorm_getNX unorm_getNX_3_2 -#define unorm_getQuickCheck unorm_getQuickCheck_3_2 -#define unorm_getUnicodeVersion unorm_getUnicodeVersion_3_2 -#define unorm_haveData unorm_haveData_3_2 -#define unorm_internalIsFullCompositionExclusion unorm_internalIsFullCompositionExclusion_3_2 -#define unorm_internalNormalize unorm_internalNormalize_3_2 -#define unorm_internalNormalizeWithNX unorm_internalNormalizeWithNX_3_2 -#define unorm_internalQuickCheck unorm_internalQuickCheck_3_2 -#define unorm_isCanonSafeStart unorm_isCanonSafeStart_3_2 -#define unorm_isNFSkippable unorm_isNFSkippable_3_2 -#define unorm_isNormalized unorm_isNormalized_3_2 -#define unorm_isNormalizedWithOptions unorm_isNormalizedWithOptions_3_2 -#define unorm_next unorm_next_3_2 -#define unorm_normalize unorm_normalize_3_2 -#define unorm_openIter unorm_openIter_3_2 -#define unorm_previous unorm_previous_3_2 -#define unorm_quickCheck unorm_quickCheck_3_2 -#define unorm_quickCheckWithOptions unorm_quickCheckWithOptions_3_2 -#define unorm_setIter unorm_setIter_3_2 -#define unorm_swap unorm_swap_3_2 -#define unum_applyPattern unum_applyPattern_3_2 -#define unum_clone unum_clone_3_2 -#define unum_close unum_close_3_2 -#define unum_countAvailable unum_countAvailable_3_2 -#define unum_format unum_format_3_2 -#define unum_formatDouble unum_formatDouble_3_2 -#define unum_formatDoubleCurrency unum_formatDoubleCurrency_3_2 -#define unum_formatInt64 unum_formatInt64_3_2 -#define unum_getAttribute unum_getAttribute_3_2 -#define unum_getAvailable unum_getAvailable_3_2 -#define unum_getDoubleAttribute unum_getDoubleAttribute_3_2 -#define unum_getLocaleByType unum_getLocaleByType_3_2 -#define unum_getSymbol unum_getSymbol_3_2 -#define unum_getTextAttribute unum_getTextAttribute_3_2 -#define unum_open unum_open_3_2 -#define unum_parse unum_parse_3_2 -#define unum_parseDouble unum_parseDouble_3_2 -#define unum_parseDoubleCurrency unum_parseDoubleCurrency_3_2 -#define unum_parseInt64 unum_parseInt64_3_2 -#define unum_setAttribute unum_setAttribute_3_2 -#define unum_setDoubleAttribute unum_setDoubleAttribute_3_2 -#define unum_setSymbol unum_setSymbol_3_2 -#define unum_setTextAttribute unum_setTextAttribute_3_2 -#define unum_toPattern unum_toPattern_3_2 -#define upname_swap upname_swap_3_2 -#define uprops_getSource uprops_getSource_3_2 -#define uprops_swap uprops_swap_3_2 -#define uprv_asciiFromEbcdic uprv_asciiFromEbcdic_3_2 -#define uprv_asciitolower uprv_asciitolower_3_2 -#define uprv_ceil uprv_ceil_3_2 -#define uprv_cnttab_addContraction uprv_cnttab_addContraction_3_2 -#define uprv_cnttab_changeContraction uprv_cnttab_changeContraction_3_2 -#define uprv_cnttab_changeLastCE uprv_cnttab_changeLastCE_3_2 -#define uprv_cnttab_clone uprv_cnttab_clone_3_2 -#define uprv_cnttab_close uprv_cnttab_close_3_2 -#define uprv_cnttab_constructTable uprv_cnttab_constructTable_3_2 -#define uprv_cnttab_findCE uprv_cnttab_findCE_3_2 -#define uprv_cnttab_findCP uprv_cnttab_findCP_3_2 -#define uprv_cnttab_getCE uprv_cnttab_getCE_3_2 -#define uprv_cnttab_insertContraction uprv_cnttab_insertContraction_3_2 -#define uprv_cnttab_isTailored uprv_cnttab_isTailored_3_2 -#define uprv_cnttab_open uprv_cnttab_open_3_2 -#define uprv_cnttab_setContraction uprv_cnttab_setContraction_3_2 -#define uprv_compareASCIIPropertyNames uprv_compareASCIIPropertyNames_3_2 -#define uprv_compareEBCDICPropertyNames uprv_compareEBCDICPropertyNames_3_2 -#define uprv_compareInvAscii uprv_compareInvAscii_3_2 -#define uprv_compareInvEbcdic uprv_compareInvEbcdic_3_2 -#define uprv_convertToLCID uprv_convertToLCID_3_2 -#define uprv_convertToPosix uprv_convertToPosix_3_2 -#define uprv_copyAscii uprv_copyAscii_3_2 -#define uprv_copyEbcdic uprv_copyEbcdic_3_2 -#define uprv_dtostr uprv_dtostr_3_2 -#define uprv_ebcdicFromAscii uprv_ebcdicFromAscii_3_2 -#define uprv_ebcdictolower uprv_ebcdictolower_3_2 -#define uprv_fabs uprv_fabs_3_2 -#define uprv_floor uprv_floor_3_2 -#define uprv_fmax uprv_fmax_3_2 -#define uprv_fmin uprv_fmin_3_2 -#define uprv_fmod uprv_fmod_3_2 -#define uprv_free uprv_free_3_2 -#define uprv_getCharNameCharacters uprv_getCharNameCharacters_3_2 -#define uprv_getDefaultCodepage uprv_getDefaultCodepage_3_2 -#define uprv_getDefaultLocaleID uprv_getDefaultLocaleID_3_2 -#define uprv_getInfinity uprv_getInfinity_3_2 -#define uprv_getMaxCharNameLength uprv_getMaxCharNameLength_3_2 -#define uprv_getMaxValues uprv_getMaxValues_3_2 -#define uprv_getNaN uprv_getNaN_3_2 -#define uprv_getStaticCurrencyName uprv_getStaticCurrencyName_3_2 -#define uprv_getUTCtime uprv_getUTCtime_3_2 -#define uprv_haveProperties uprv_haveProperties_3_2 -#define uprv_init_collIterate uprv_init_collIterate_3_2 -#define uprv_int32Comparator uprv_int32Comparator_3_2 -#define uprv_isInfinite uprv_isInfinite_3_2 -#define uprv_isInvariantString uprv_isInvariantString_3_2 -#define uprv_isInvariantUString uprv_isInvariantUString_3_2 -#define uprv_isNaN uprv_isNaN_3_2 -#define uprv_isNegativeInfinity uprv_isNegativeInfinity_3_2 -#define uprv_isPositiveInfinity uprv_isPositiveInfinity_3_2 -#define uprv_isRuleWhiteSpace uprv_isRuleWhiteSpace_3_2 -#define uprv_itou uprv_itou_3_2 -#define uprv_loadPropsData uprv_loadPropsData_3_2 -#define uprv_log uprv_log_3_2 -#define uprv_log10 uprv_log10_3_2 -#define uprv_malloc uprv_malloc_3_2 -#define uprv_mapFile uprv_mapFile_3_2 -#define uprv_max uprv_max_3_2 -#define uprv_maxMantissa uprv_maxMantissa_3_2 -#define uprv_min uprv_min_3_2 -#define uprv_modf uprv_modf_3_2 -#define uprv_openRuleWhiteSpaceSet uprv_openRuleWhiteSpaceSet_3_2 -#define uprv_pathIsAbsolute uprv_pathIsAbsolute_3_2 -#define uprv_pow uprv_pow_3_2 -#define uprv_pow10 uprv_pow10_3_2 -#define uprv_realloc uprv_realloc_3_2 -#define uprv_round uprv_round_3_2 -#define uprv_sortArray uprv_sortArray_3_2 -#define uprv_strCompare uprv_strCompare_3_2 -#define uprv_strdup uprv_strdup_3_2 -#define uprv_strndup uprv_strndup_3_2 -#define uprv_syntaxError uprv_syntaxError_3_2 -#define uprv_timezone uprv_timezone_3_2 -#define uprv_toupper uprv_toupper_3_2 -#define uprv_trunc uprv_trunc_3_2 -#define uprv_tzname uprv_tzname_3_2 -#define uprv_tzset uprv_tzset_3_2 -#define uprv_uca_addAnElement uprv_uca_addAnElement_3_2 -#define uprv_uca_assembleTable uprv_uca_assembleTable_3_2 -#define uprv_uca_canonicalClosure uprv_uca_canonicalClosure_3_2 -#define uprv_uca_cloneTempTable uprv_uca_cloneTempTable_3_2 -#define uprv_uca_closeTempTable uprv_uca_closeTempTable_3_2 -#define uprv_uca_getCodePointFromRaw uprv_uca_getCodePointFromRaw_3_2 -#define uprv_uca_getImplicitFromRaw uprv_uca_getImplicitFromRaw_3_2 -#define uprv_uca_getImplicitPrimary uprv_uca_getImplicitPrimary_3_2 -#define uprv_uca_getRawFromCodePoint uprv_uca_getRawFromCodePoint_3_2 -#define uprv_uca_getRawFromImplicit uprv_uca_getRawFromImplicit_3_2 -#define uprv_uca_initImplicitConstants uprv_uca_initImplicitConstants_3_2 -#define uprv_uca_initTempTable uprv_uca_initTempTable_3_2 -#define uprv_uint16Comparator uprv_uint16Comparator_3_2 -#define uprv_uint32Comparator uprv_uint32Comparator_3_2 -#define uprv_unmapFile uprv_unmapFile_3_2 -#define uregex_appendReplacement uregex_appendReplacement_3_2 -#define uregex_appendTail uregex_appendTail_3_2 -#define uregex_clone uregex_clone_3_2 -#define uregex_close uregex_close_3_2 -#define uregex_end uregex_end_3_2 -#define uregex_find uregex_find_3_2 -#define uregex_findNext uregex_findNext_3_2 -#define uregex_flags uregex_flags_3_2 -#define uregex_getText uregex_getText_3_2 -#define uregex_group uregex_group_3_2 -#define uregex_groupCount uregex_groupCount_3_2 -#define uregex_lookingAt uregex_lookingAt_3_2 -#define uregex_matches uregex_matches_3_2 -#define uregex_open uregex_open_3_2 -#define uregex_openC uregex_openC_3_2 -#define uregex_pattern uregex_pattern_3_2 -#define uregex_replaceAll uregex_replaceAll_3_2 -#define uregex_replaceFirst uregex_replaceFirst_3_2 -#define uregex_reset uregex_reset_3_2 -#define uregex_setText uregex_setText_3_2 -#define uregex_split uregex_split_3_2 -#define uregex_start uregex_start_3_2 -#define ures_appendResPath ures_appendResPath_3_2 -#define ures_close ures_close_3_2 -#define ures_copyResb ures_copyResb_3_2 -#define ures_countArrayItems ures_countArrayItems_3_2 -#define ures_findResource ures_findResource_3_2 -#define ures_findSubResource ures_findSubResource_3_2 -#define ures_freeResPath ures_freeResPath_3_2 -#define ures_getBinary ures_getBinary_3_2 -#define ures_getByIndex ures_getByIndex_3_2 -#define ures_getByKey ures_getByKey_3_2 -#define ures_getByKeyWithFallback ures_getByKeyWithFallback_3_2 -#define ures_getFunctionalEquivalent ures_getFunctionalEquivalent_3_2 -#define ures_getInt ures_getInt_3_2 -#define ures_getIntVector ures_getIntVector_3_2 -#define ures_getKey ures_getKey_3_2 -#define ures_getKeywordValues ures_getKeywordValues_3_2 -#define ures_getLocale ures_getLocale_3_2 -#define ures_getLocaleByType ures_getLocaleByType_3_2 -#define ures_getName ures_getName_3_2 -#define ures_getNextResource ures_getNextResource_3_2 -#define ures_getNextString ures_getNextString_3_2 -#define ures_getPath ures_getPath_3_2 -#define ures_getSize ures_getSize_3_2 -#define ures_getString ures_getString_3_2 -#define ures_getStringByIndex ures_getStringByIndex_3_2 -#define ures_getStringByKey ures_getStringByKey_3_2 -#define ures_getType ures_getType_3_2 -#define ures_getUInt ures_getUInt_3_2 -#define ures_getVersion ures_getVersion_3_2 -#define ures_getVersionNumber ures_getVersionNumber_3_2 -#define ures_hasNext ures_hasNext_3_2 -#define ures_initStackObject ures_initStackObject_3_2 -#define ures_open ures_open_3_2 -#define ures_openAvailableLocales ures_openAvailableLocales_3_2 -#define ures_openDirect ures_openDirect_3_2 -#define ures_openFillIn ures_openFillIn_3_2 -#define ures_openU ures_openU_3_2 -#define ures_resetIterator ures_resetIterator_3_2 -#define ures_swap ures_swap_3_2 -#define uscript_closeRun uscript_closeRun_3_2 -#define uscript_getCode uscript_getCode_3_2 -#define uscript_getName uscript_getName_3_2 -#define uscript_getScript uscript_getScript_3_2 -#define uscript_getShortName uscript_getShortName_3_2 -#define uscript_nextRun uscript_nextRun_3_2 -#define uscript_openRun uscript_openRun_3_2 -#define uscript_resetRun uscript_resetRun_3_2 -#define uscript_setRunText uscript_setRunText_3_2 -#define usearch_close usearch_close_3_2 -#define usearch_first usearch_first_3_2 -#define usearch_following usearch_following_3_2 -#define usearch_getAttribute usearch_getAttribute_3_2 -#define usearch_getBreakIterator usearch_getBreakIterator_3_2 -#define usearch_getCollator usearch_getCollator_3_2 -#define usearch_getMatchedLength usearch_getMatchedLength_3_2 -#define usearch_getMatchedStart usearch_getMatchedStart_3_2 -#define usearch_getMatchedText usearch_getMatchedText_3_2 -#define usearch_getOffset usearch_getOffset_3_2 -#define usearch_getPattern usearch_getPattern_3_2 -#define usearch_getText usearch_getText_3_2 -#define usearch_handleNextCanonical usearch_handleNextCanonical_3_2 -#define usearch_handleNextExact usearch_handleNextExact_3_2 -#define usearch_handlePreviousCanonical usearch_handlePreviousCanonical_3_2 -#define usearch_handlePreviousExact usearch_handlePreviousExact_3_2 -#define usearch_last usearch_last_3_2 -#define usearch_next usearch_next_3_2 -#define usearch_open usearch_open_3_2 -#define usearch_openFromCollator usearch_openFromCollator_3_2 -#define usearch_preceding usearch_preceding_3_2 -#define usearch_previous usearch_previous_3_2 -#define usearch_reset usearch_reset_3_2 -#define usearch_setAttribute usearch_setAttribute_3_2 -#define usearch_setBreakIterator usearch_setBreakIterator_3_2 -#define usearch_setCollator usearch_setCollator_3_2 -#define usearch_setOffset usearch_setOffset_3_2 -#define usearch_setPattern usearch_setPattern_3_2 -#define usearch_setText usearch_setText_3_2 -#define userv_deleteStringPair userv_deleteStringPair_3_2 -#define uset_add uset_add_3_2 -#define uset_addAll uset_addAll_3_2 -#define uset_addRange uset_addRange_3_2 -#define uset_addString uset_addString_3_2 -#define uset_applyIntPropertyValue uset_applyIntPropertyValue_3_2 -#define uset_applyPattern uset_applyPattern_3_2 -#define uset_applyPropertyAlias uset_applyPropertyAlias_3_2 -#define uset_charAt uset_charAt_3_2 -#define uset_clear uset_clear_3_2 -#define uset_close uset_close_3_2 -#define uset_compact uset_compact_3_2 -#define uset_complement uset_complement_3_2 -#define uset_complementAll uset_complementAll_3_2 -#define uset_contains uset_contains_3_2 -#define uset_containsAll uset_containsAll_3_2 -#define uset_containsNone uset_containsNone_3_2 -#define uset_containsRange uset_containsRange_3_2 -#define uset_containsSome uset_containsSome_3_2 -#define uset_containsString uset_containsString_3_2 -#define uset_equals uset_equals_3_2 -#define uset_getItem uset_getItem_3_2 -#define uset_getItemCount uset_getItemCount_3_2 -#define uset_getSerializedRange uset_getSerializedRange_3_2 -#define uset_getSerializedRangeCount uset_getSerializedRangeCount_3_2 -#define uset_getSerializedSet uset_getSerializedSet_3_2 -#define uset_indexOf uset_indexOf_3_2 -#define uset_isEmpty uset_isEmpty_3_2 -#define uset_open uset_open_3_2 -#define uset_openPattern uset_openPattern_3_2 -#define uset_openPatternOptions uset_openPatternOptions_3_2 -#define uset_remove uset_remove_3_2 -#define uset_removeAll uset_removeAll_3_2 -#define uset_removeRange uset_removeRange_3_2 -#define uset_removeString uset_removeString_3_2 -#define uset_resemblesPattern uset_resemblesPattern_3_2 -#define uset_retain uset_retain_3_2 -#define uset_retainAll uset_retainAll_3_2 -#define uset_serialize uset_serialize_3_2 -#define uset_serializedContains uset_serializedContains_3_2 -#define uset_set uset_set_3_2 -#define uset_setSerializedToOne uset_setSerializedToOne_3_2 -#define uset_size uset_size_3_2 -#define uset_toPattern uset_toPattern_3_2 -#define usprep_close usprep_close_3_2 -#define usprep_open usprep_open_3_2 -#define usprep_prepare usprep_prepare_3_2 -#define usprep_swap usprep_swap_3_2 -#define ustr_foldCase ustr_foldCase_3_2 -#define ustr_toLower ustr_toLower_3_2 -#define ustr_toTitle ustr_toTitle_3_2 -#define ustr_toUpper ustr_toUpper_3_2 -#define utf8_appendCharSafeBody utf8_appendCharSafeBody_3_2 -#define utf8_back1SafeBody utf8_back1SafeBody_3_2 -#define utf8_countTrailBytes utf8_countTrailBytes_3_2 -#define utf8_nextCharSafeBody utf8_nextCharSafeBody_3_2 -#define utf8_prevCharSafeBody utf8_prevCharSafeBody_3_2 -#define utmscale_fromInt64 utmscale_fromInt64_3_2 -#define utmscale_getTimeScaleValue utmscale_getTimeScaleValue_3_2 -#define utmscale_toInt64 utmscale_toInt64_3_2 -#define utrace_cleanup utrace_cleanup_3_2 -#define utrace_data utrace_data_3_2 -#define utrace_entry utrace_entry_3_2 -#define utrace_exit utrace_exit_3_2 -#define utrace_format utrace_format_3_2 -#define utrace_functionName utrace_functionName_3_2 -#define utrace_getFunctions utrace_getFunctions_3_2 -#define utrace_getLevel utrace_getLevel_3_2 -#define utrace_level utrace_level_3_2 -#define utrace_setFunctions utrace_setFunctions_3_2 -#define utrace_setLevel utrace_setLevel_3_2 -#define utrace_vformat utrace_vformat_3_2 -#define utrans_clone utrans_clone_3_2 -#define utrans_close utrans_close_3_2 -#define utrans_countAvailableIDs utrans_countAvailableIDs_3_2 -#define utrans_getAvailableID utrans_getAvailableID_3_2 -#define utrans_getID utrans_getID_3_2 -#define utrans_getUnicodeID utrans_getUnicodeID_3_2 -#define utrans_open utrans_open_3_2 -#define utrans_openIDs utrans_openIDs_3_2 -#define utrans_openInverse utrans_openInverse_3_2 -#define utrans_openU utrans_openU_3_2 -#define utrans_register utrans_register_3_2 -#define utrans_rep_caseContextIterator utrans_rep_caseContextIterator_3_2 -#define utrans_setFilter utrans_setFilter_3_2 -#define utrans_trans utrans_trans_3_2 -#define utrans_transIncremental utrans_transIncremental_3_2 -#define utrans_transIncrementalUChars utrans_transIncrementalUChars_3_2 -#define utrans_transUChars utrans_transUChars_3_2 -#define utrans_unregister utrans_unregister_3_2 -#define utrans_unregisterID utrans_unregisterID_3_2 -#define utrie_clone utrie_clone_3_2 -#define utrie_close utrie_close_3_2 -#define utrie_enum utrie_enum_3_2 -#define utrie_get32 utrie_get32_3_2 -#define utrie_getData utrie_getData_3_2 -#define utrie_open utrie_open_3_2 -#define utrie_serialize utrie_serialize_3_2 -#define utrie_set32 utrie_set32_3_2 -#define utrie_setRange32 utrie_setRange32_3_2 -#define utrie_swap utrie_swap_3_2 -#define utrie_unserialize utrie_unserialize_3_2 -/* C++ class names renaming defines */ - -#ifdef XP_CPLUSPLUS -#if !U_HAVE_NAMESPACE - -#define AbsoluteValueSubstitution AbsoluteValueSubstitution_3_2 -#define AlternateSubstitutionSubtable AlternateSubstitutionSubtable_3_2 -#define AnchorTable AnchorTable_3_2 -#define AnyTransliterator AnyTransliterator_3_2 -#define ArabicOpenTypeLayoutEngine ArabicOpenTypeLayoutEngine_3_2 -#define ArabicShaping ArabicShaping_3_2 -#define BasicCalendarFactory BasicCalendarFactory_3_2 -#define BinarySearchLookupTable BinarySearchLookupTable_3_2 -#define BreakDictionary BreakDictionary_3_2 -#define BreakIterator BreakIterator_3_2 -#define BuddhistCalendar BuddhistCalendar_3_2 -#define CFactory CFactory_3_2 -#define Calendar Calendar_3_2 -#define CalendarAstronomer CalendarAstronomer_3_2 -#define CalendarCache CalendarCache_3_2 -#define CalendarData CalendarData_3_2 -#define CalendarService CalendarService_3_2 -#define CanonShaping CanonShaping_3_2 -#define CanonicalIterator CanonicalIterator_3_2 -#define CaseMapTransliterator CaseMapTransliterator_3_2 -#define ChainingContextualSubstitutionFormat1Subtable ChainingContextualSubstitutionFormat1Subtable_3_2 -#define ChainingContextualSubstitutionFormat2Subtable ChainingContextualSubstitutionFormat2Subtable_3_2 -#define ChainingContextualSubstitutionFormat3Subtable ChainingContextualSubstitutionFormat3Subtable_3_2 -#define ChainingContextualSubstitutionSubtable ChainingContextualSubstitutionSubtable_3_2 -#define CharSubstitutionFilter CharSubstitutionFilter_3_2 -#define CharacterIterator CharacterIterator_3_2 -#define ChoiceFormat ChoiceFormat_3_2 -#define ClassDefFormat1Table ClassDefFormat1Table_3_2 -#define ClassDefFormat2Table ClassDefFormat2Table_3_2 -#define ClassDefinitionTable ClassDefinitionTable_3_2 -#define CollationElementIterator CollationElementIterator_3_2 -#define CollationKey CollationKey_3_2 -#define Collator Collator_3_2 -#define CollatorFactory CollatorFactory_3_2 -#define CompoundTransliterator CompoundTransliterator_3_2 -#define ContextualGlyphSubstitutionProcessor ContextualGlyphSubstitutionProcessor_3_2 -#define ContextualSubstitutionBase ContextualSubstitutionBase_3_2 -#define ContextualSubstitutionFormat1Subtable ContextualSubstitutionFormat1Subtable_3_2 -#define ContextualSubstitutionFormat2Subtable ContextualSubstitutionFormat2Subtable_3_2 -#define ContextualSubstitutionFormat3Subtable ContextualSubstitutionFormat3Subtable_3_2 -#define ContextualSubstitutionSubtable ContextualSubstitutionSubtable_3_2 -#define CoverageFormat1Table CoverageFormat1Table_3_2 -#define CoverageFormat2Table CoverageFormat2Table_3_2 -#define CoverageTable CoverageTable_3_2 -#define CurrencyAmount CurrencyAmount_3_2 -#define CurrencyFormat CurrencyFormat_3_2 -#define CurrencyUnit CurrencyUnit_3_2 -#define CursiveAttachmentSubtable CursiveAttachmentSubtable_3_2 -#define DateFormat DateFormat_3_2 -#define DateFormatSymbols DateFormatSymbols_3_2 -#define DecimalFormat DecimalFormat_3_2 -#define DecimalFormatSymbols DecimalFormatSymbols_3_2 -#define DefaultCalendarFactory DefaultCalendarFactory_3_2 -#define DefaultCharMapper DefaultCharMapper_3_2 -#define DeviceTable DeviceTable_3_2 -#define DictionaryBasedBreakIterator DictionaryBasedBreakIterator_3_2 -#define DictionaryBasedBreakIteratorTables DictionaryBasedBreakIteratorTables_3_2 -#define DigitList DigitList_3_2 -#define Entry Entry_3_2 -#define EnumToOffset EnumToOffset_3_2 -#define EscapeTransliterator EscapeTransliterator_3_2 -#define EventListener EventListener_3_2 -#define ExtensionSubtable ExtensionSubtable_3_2 -#define FeatureListTable FeatureListTable_3_2 -#define FieldPosition FieldPosition_3_2 -#define FontRuns FontRuns_3_2 -#define Format Format_3_2 -#define Format1AnchorTable Format1AnchorTable_3_2 -#define Format2AnchorTable Format2AnchorTable_3_2 -#define Format3AnchorTable Format3AnchorTable_3_2 -#define Formattable Formattable_3_2 -#define ForwardCharacterIterator ForwardCharacterIterator_3_2 -#define FractionalPartSubstitution FractionalPartSubstitution_3_2 -#define FunctionReplacer FunctionReplacer_3_2 -#define GDEFMarkFilter GDEFMarkFilter_3_2 -#define GXLayoutEngine GXLayoutEngine_3_2 -#define GlyphDefinitionTableHeader GlyphDefinitionTableHeader_3_2 -#define GlyphIterator GlyphIterator_3_2 -#define GlyphLookupTableHeader GlyphLookupTableHeader_3_2 -#define GlyphPositioningLookupProcessor GlyphPositioningLookupProcessor_3_2 -#define GlyphPositioningTableHeader GlyphPositioningTableHeader_3_2 -#define GlyphSubstitutionLookupProcessor GlyphSubstitutionLookupProcessor_3_2 -#define GlyphSubstitutionTableHeader GlyphSubstitutionTableHeader_3_2 -#define Grego Grego_3_2 -#define GregorianCalendar GregorianCalendar_3_2 -#define HanOpenTypeLayoutEngine HanOpenTypeLayoutEngine_3_2 -#define HebrewCalendar HebrewCalendar_3_2 -#define ICUBreakIteratorFactory ICUBreakIteratorFactory_3_2 -#define ICUBreakIteratorService ICUBreakIteratorService_3_2 -#define ICUCollatorFactory ICUCollatorFactory_3_2 -#define ICUCollatorService ICUCollatorService_3_2 -#define ICULayoutEngine ICULayoutEngine_3_2 -#define ICULocaleService ICULocaleService_3_2 -#define ICUNotifier ICUNotifier_3_2 -#define ICUNumberFormatFactory ICUNumberFormatFactory_3_2 -#define ICUNumberFormatService ICUNumberFormatService_3_2 -#define ICUResourceBundleFactory ICUResourceBundleFactory_3_2 -#define ICUService ICUService_3_2 -#define ICUServiceFactory ICUServiceFactory_3_2 -#define ICUServiceKey ICUServiceKey_3_2 -#define ICU_Utility ICU_Utility_3_2 -#define IndicClassTable IndicClassTable_3_2 -#define IndicOpenTypeLayoutEngine IndicOpenTypeLayoutEngine_3_2 -#define IndicRearrangementProcessor IndicRearrangementProcessor_3_2 -#define IndicReordering IndicReordering_3_2 -#define IntegralPartSubstitution IntegralPartSubstitution_3_2 -#define IslamicCalendar IslamicCalendar_3_2 -#define JapaneseCalendar JapaneseCalendar_3_2 -#define KeywordEnumeration KeywordEnumeration_3_2 -#define LECharMapper LECharMapper_3_2 -#define LEFontInstance LEFontInstance_3_2 -#define LEGlyphFilter LEGlyphFilter_3_2 -#define LEGlyphStorage LEGlyphStorage_3_2 -#define LEInsertionCallback LEInsertionCallback_3_2 -#define LEInsertionList LEInsertionList_3_2 -#define LXUtilities LXUtilities_3_2 -#define LayoutEngine LayoutEngine_3_2 -#define LigatureSubstitutionProcessor LigatureSubstitutionProcessor_3_2 -#define LigatureSubstitutionSubtable LigatureSubstitutionSubtable_3_2 -#define LocDataParser LocDataParser_3_2 -#define Locale Locale_3_2 -#define LocaleBased LocaleBased_3_2 -#define LocaleKey LocaleKey_3_2 -#define LocaleKeyFactory LocaleKeyFactory_3_2 -#define LocaleRuns LocaleRuns_3_2 -#define LocaleUtility LocaleUtility_3_2 -#define LocalizationInfo LocalizationInfo_3_2 -#define LookupListTable LookupListTable_3_2 -#define LookupProcessor LookupProcessor_3_2 -#define LookupSubtable LookupSubtable_3_2 -#define LookupTable LookupTable_3_2 -#define LowercaseTransliterator LowercaseTransliterator_3_2 -#define MPreFixups MPreFixups_3_2 -#define MarkArray MarkArray_3_2 -#define MarkToBasePositioningSubtable MarkToBasePositioningSubtable_3_2 -#define MarkToLigaturePositioningSubtable MarkToLigaturePositioningSubtable_3_2 -#define MarkToMarkPositioningSubtable MarkToMarkPositioningSubtable_3_2 -#define Math Math_3_2 -#define Measure Measure_3_2 -#define MeasureFormat MeasureFormat_3_2 -#define MeasureUnit MeasureUnit_3_2 -#define MessageFormat MessageFormat_3_2 -#define MessageFormatAdapter MessageFormatAdapter_3_2 -#define ModulusSubstitution ModulusSubstitution_3_2 -#define MoonRiseSetCoordFunc MoonRiseSetCoordFunc_3_2 -#define MoonTimeAngleFunc MoonTimeAngleFunc_3_2 -#define MorphSubtableHeader MorphSubtableHeader_3_2 -#define MorphTableHeader MorphTableHeader_3_2 -#define MultipleSubstitutionSubtable MultipleSubstitutionSubtable_3_2 -#define MultiplierSubstitution MultiplierSubstitution_3_2 -#define NFFactory NFFactory_3_2 -#define NFRule NFRule_3_2 -#define NFRuleSet NFRuleSet_3_2 -#define NFSubstitution NFSubstitution_3_2 -#define NameToEnum NameToEnum_3_2 -#define NameUnicodeTransliterator NameUnicodeTransliterator_3_2 -#define NonContextualGlyphSubstitutionProcessor NonContextualGlyphSubstitutionProcessor_3_2 -#define NonContiguousEnumToOffset NonContiguousEnumToOffset_3_2 -#define NormalizationTransliterator NormalizationTransliterator_3_2 -#define Normalizer Normalizer_3_2 -#define NullSubstitution NullSubstitution_3_2 -#define NullTransliterator NullTransliterator_3_2 -#define NumberFormat NumberFormat_3_2 -#define NumberFormatFactory NumberFormatFactory_3_2 -#define NumeratorSubstitution NumeratorSubstitution_3_2 -#define OlsonTimeZone OlsonTimeZone_3_2 -#define OpenTypeLayoutEngine OpenTypeLayoutEngine_3_2 -#define OpenTypeUtilities OpenTypeUtilities_3_2 -#define PairPositioningFormat1Subtable PairPositioningFormat1Subtable_3_2 -#define PairPositioningFormat2Subtable PairPositioningFormat2Subtable_3_2 -#define PairPositioningSubtable PairPositioningSubtable_3_2 -#define ParagraphLayout ParagraphLayout_3_2 -#define ParseData ParseData_3_2 -#define ParsePosition ParsePosition_3_2 -#define PropertyAliases PropertyAliases_3_2 -#define Quantifier Quantifier_3_2 -#define RBBIDataWrapper RBBIDataWrapper_3_2 -#define RBBINode RBBINode_3_2 -#define RBBIRuleBuilder RBBIRuleBuilder_3_2 -#define RBBIRuleScanner RBBIRuleScanner_3_2 -#define RBBISetBuilder RBBISetBuilder_3_2 -#define RBBIStateDescriptor RBBIStateDescriptor_3_2 -#define RBBISymbolTable RBBISymbolTable_3_2 -#define RBBISymbolTableEntry RBBISymbolTableEntry_3_2 -#define RBBITableBuilder RBBITableBuilder_3_2 -#define RangeDescriptor RangeDescriptor_3_2 -#define RegexCompile RegexCompile_3_2 -#define RegexMatcher RegexMatcher_3_2 -#define RegexPattern RegexPattern_3_2 -#define RegexStaticSets RegexStaticSets_3_2 -#define RemoveTransliterator RemoveTransliterator_3_2 -#define Replaceable Replaceable_3_2 -#define ReplaceableGlue ReplaceableGlue_3_2 -#define ResourceBundle ResourceBundle_3_2 -#define RiseSetCoordFunc RiseSetCoordFunc_3_2 -#define RuleBasedBreakIterator RuleBasedBreakIterator_3_2 -#define RuleBasedCollator RuleBasedCollator_3_2 -#define RuleBasedNumberFormat RuleBasedNumberFormat_3_2 -#define RuleBasedTransliterator RuleBasedTransliterator_3_2 -#define RuleCharacterIterator RuleCharacterIterator_3_2 -#define RuleHalf RuleHalf_3_2 -#define RunArray RunArray_3_2 -#define SameValueSubstitution SameValueSubstitution_3_2 -#define ScriptListTable ScriptListTable_3_2 -#define ScriptRunIterator ScriptRunIterator_3_2 -#define ScriptTable ScriptTable_3_2 -#define SearchIterator SearchIterator_3_2 -#define SegmentArrayProcessor SegmentArrayProcessor_3_2 -#define SegmentSingleProcessor SegmentSingleProcessor_3_2 -#define ServiceEnumeration ServiceEnumeration_3_2 -#define ServiceListener ServiceListener_3_2 -#define SimpleArrayProcessor SimpleArrayProcessor_3_2 -#define SimpleDateFormat SimpleDateFormat_3_2 -#define SimpleFactory SimpleFactory_3_2 -#define SimpleLocaleKeyFactory SimpleLocaleKeyFactory_3_2 -#define SimpleNumberFormatFactory SimpleNumberFormatFactory_3_2 -#define SimpleTimeZone SimpleTimeZone_3_2 -#define SinglePositioningFormat1Subtable SinglePositioningFormat1Subtable_3_2 -#define SinglePositioningFormat2Subtable SinglePositioningFormat2Subtable_3_2 -#define SinglePositioningSubtable SinglePositioningSubtable_3_2 -#define SingleSubstitutionFormat1Subtable SingleSubstitutionFormat1Subtable_3_2 -#define SingleSubstitutionFormat2Subtable SingleSubstitutionFormat2Subtable_3_2 -#define SingleSubstitutionSubtable SingleSubstitutionSubtable_3_2 -#define SingleTableProcessor SingleTableProcessor_3_2 -#define Spec Spec_3_2 -#define StateTableProcessor StateTableProcessor_3_2 -#define StringCharacterIterator StringCharacterIterator_3_2 -#define StringEnumeration StringEnumeration_3_2 -#define StringLocalizationInfo StringLocalizationInfo_3_2 -#define StringMatcher StringMatcher_3_2 -#define StringPair StringPair_3_2 -#define StringReplacer StringReplacer_3_2 -#define StringSearch StringSearch_3_2 -#define StyleRuns StyleRuns_3_2 -#define SubstitutionLookup SubstitutionLookup_3_2 -#define SubtableProcessor SubtableProcessor_3_2 -#define SunTimeAngleFunc SunTimeAngleFunc_3_2 -#define SymbolTable SymbolTable_3_2 -#define TZEnumeration TZEnumeration_3_2 -#define ThaiLayoutEngine ThaiLayoutEngine_3_2 -#define ThaiShaping ThaiShaping_3_2 -#define TimeZone TimeZone_3_2 -#define TitlecaseTransliterator TitlecaseTransliterator_3_2 -#define TransliterationRule TransliterationRule_3_2 -#define TransliterationRuleData TransliterationRuleData_3_2 -#define TransliterationRuleSet TransliterationRuleSet_3_2 -#define Transliterator Transliterator_3_2 -#define TransliteratorAlias TransliteratorAlias_3_2 -#define TransliteratorIDParser TransliteratorIDParser_3_2 -#define TransliteratorParser TransliteratorParser_3_2 -#define TransliteratorRegistry TransliteratorRegistry_3_2 -#define TrimmedArrayProcessor TrimmedArrayProcessor_3_2 -#define UCharCharacterIterator UCharCharacterIterator_3_2 -#define UMemory UMemory_3_2 -#define UObject UObject_3_2 -#define UStack UStack_3_2 -#define UStringEnumeration UStringEnumeration_3_2 -#define UVector UVector_3_2 -#define UVector32 UVector32_3_2 -#define UnescapeTransliterator UnescapeTransliterator_3_2 -#define UnicodeArabicOpenTypeLayoutEngine UnicodeArabicOpenTypeLayoutEngine_3_2 -#define UnicodeFilter UnicodeFilter_3_2 -#define UnicodeFunctor UnicodeFunctor_3_2 -#define UnicodeMatcher UnicodeMatcher_3_2 -#define UnicodeNameTransliterator UnicodeNameTransliterator_3_2 -#define UnicodeReplacer UnicodeReplacer_3_2 -#define UnicodeSet UnicodeSet_3_2 -#define UnicodeSetIterator UnicodeSetIterator_3_2 -#define UnicodeString UnicodeString_3_2 -#define UppercaseTransliterator UppercaseTransliterator_3_2 -#define ValueRecord ValueRecord_3_2 -#define ValueRuns ValueRuns_3_2 -#define locale_set_default_internal locale_set_default_internal_3_2 -#define uprv_parseCurrency uprv_parseCurrency_3_2 -#define util64_fromDouble util64_fromDouble_3_2 -#define util64_pow util64_pow_3_2 -#define util64_tou util64_tou_3_2 -#define util64_utoi util64_utoi_3_2 - -#endif -#endif - -#endif - -#endif diff --git a/WebKit/mac/icu/unicode/uscript.h b/WebKit/mac/icu/unicode/uscript.h deleted file mode 100644 index f31d748..0000000 --- a/WebKit/mac/icu/unicode/uscript.h +++ /dev/null @@ -1,148 +0,0 @@ -/* -********************************************************************** -* Copyright (C) 1997-2004, International Business Machines -* Corporation and others. All Rights Reserved. -********************************************************************** -* -* File USCRIPT.H -* -* Modification History: -* -* Date Name Description -* 07/06/2001 Ram Creation. -****************************************************************************** -*/ -#ifndef USCRIPT_H -#define USCRIPT_H -#include "unicode/utypes.h" - -/** - * Constants for Unicode script values from ScriptNames.txt . - * - * @stable ICU 2.2 - */ -typedef enum UScriptCode { - USCRIPT_INVALID_CODE = -1, - USCRIPT_COMMON = 0 , /* Zyyy */ - USCRIPT_INHERITED = 1, /* Qaai */ - USCRIPT_ARABIC = 2, /* Arab */ - USCRIPT_ARMENIAN = 3, /* Armn */ - USCRIPT_BENGALI = 4, /* Beng */ - USCRIPT_BOPOMOFO = 5, /* Bopo */ - USCRIPT_CHEROKEE = 6, /* Cher */ - USCRIPT_COPTIC = 7, /* Copt */ - USCRIPT_CYRILLIC = 8, /* Cyrl (Cyrs) */ - USCRIPT_DESERET = 9, /* Dsrt */ - USCRIPT_DEVANAGARI = 10, /* Deva */ - USCRIPT_ETHIOPIC = 11, /* Ethi */ - USCRIPT_GEORGIAN = 12, /* Geor (Geon, Geoa) */ - USCRIPT_GOTHIC = 13, /* Goth */ - USCRIPT_GREEK = 14, /* Grek */ - USCRIPT_GUJARATI = 15, /* Gujr */ - USCRIPT_GURMUKHI = 16, /* Guru */ - USCRIPT_HAN = 17, /* Hani */ - USCRIPT_HANGUL = 18, /* Hang */ - USCRIPT_HEBREW = 19, /* Hebr */ - USCRIPT_HIRAGANA = 20, /* Hira */ - USCRIPT_KANNADA = 21, /* Knda */ - USCRIPT_KATAKANA = 22, /* Kana */ - USCRIPT_KHMER = 23, /* Khmr */ - USCRIPT_LAO = 24, /* Laoo */ - USCRIPT_LATIN = 25, /* Latn (Latf, Latg) */ - USCRIPT_MALAYALAM = 26, /* Mlym */ - USCRIPT_MONGOLIAN = 27, /* Mong */ - USCRIPT_MYANMAR = 28, /* Mymr */ - USCRIPT_OGHAM = 29, /* Ogam */ - USCRIPT_OLD_ITALIC = 30, /* Ital */ - USCRIPT_ORIYA = 31, /* Orya */ - USCRIPT_RUNIC = 32, /* Runr */ - USCRIPT_SINHALA = 33, /* Sinh */ - USCRIPT_SYRIAC = 34, /* Syrc (Syrj, Syrn, Syre) */ - USCRIPT_TAMIL = 35, /* Taml */ - USCRIPT_TELUGU = 36, /* Telu */ - USCRIPT_THAANA = 37, /* Thaa */ - USCRIPT_THAI = 38, /* Thai */ - USCRIPT_TIBETAN = 39, /* Tibt */ - /** Canadian_Aboriginal script. @stable ICU 2.6 */ - USCRIPT_CANADIAN_ABORIGINAL = 40, /* Cans */ - /** Canadian_Aboriginal script (alias). @stable ICU 2.2 */ - USCRIPT_UCAS = USCRIPT_CANADIAN_ABORIGINAL, - USCRIPT_YI = 41, /* Yiii */ - USCRIPT_TAGALOG = 42, /* Tglg */ - USCRIPT_HANUNOO = 43, /* Hano */ - USCRIPT_BUHID = 44, /* Buhd */ - USCRIPT_TAGBANWA = 45, /* Tagb */ - - /* New scripts in Unicode 4 @stable ICU 2.6 */ - USCRIPT_BRAILLE, /* Brai */ - USCRIPT_CYPRIOT, /* Cprt */ - USCRIPT_LIMBU, /* Limb */ - USCRIPT_LINEAR_B, /* Linb */ - USCRIPT_OSMANYA, /* Osma */ - USCRIPT_SHAVIAN, /* Shaw */ - USCRIPT_TAI_LE, /* Tale */ - USCRIPT_UGARITIC, /* Ugar */ - - /** New script code in Unicode 4.0.1 @draft ICU 3.0 */ - USCRIPT_KATAKANA_OR_HIRAGANA,/*Hrkt */ - - USCRIPT_CODE_LIMIT -} UScriptCode; - -/** - * Gets script codes associated with the given locale or ISO 15924 abbreviation or name. - * Fills in USCRIPT_MALAYALAM given "Malayam" OR "Mlym". - * Fills in USCRIPT_LATIN given "en" OR "en_US" - * If required capacity is greater than capacity of the destination buffer then the error code - * is set to U_BUFFER_OVERFLOW_ERROR and the required capacity is returned - * - * <p>Note: To search by short or long script alias only, use - * u_getPropertyValueEnum(UCHAR_SCRIPT, alias) instead. This does - * a fast lookup with no access of the locale data. - * @param nameOrAbbrOrLocale name of the script, as given in - * PropertyValueAliases.txt, or ISO 15924 code or locale - * @param fillIn the UScriptCode buffer to fill in the script code - * @param capacity the capacity (size) fo UScriptCode buffer passed in. - * @param err the error status code. - * @return The number of script codes filled in the buffer passed in - * @stable ICU 2.4 - */ -U_STABLE int32_t U_EXPORT2 -uscript_getCode(const char* nameOrAbbrOrLocale,UScriptCode* fillIn,int32_t capacity,UErrorCode *err); - -/** - * Gets a script name associated with the given script code. - * Returns "Malayam" given USCRIPT_MALAYALAM - * @param scriptCode UScriptCode enum - * @return script long name as given in - * PropertyValueAliases.txt, or NULL if scriptCode is invalid - * @stable ICU 2.4 - */ -U_STABLE const char* U_EXPORT2 -uscript_getName(UScriptCode scriptCode); - -/** - * Gets a script name associated with the given script code. - * Returns "Mlym" given USCRIPT_MALAYALAM - * @param scriptCode UScriptCode enum - * @return script abbreviated name as given in - * PropertyValueAliases.txt, or NULL if scriptCode is invalid - * @stable ICU 2.4 - */ -U_STABLE const char* U_EXPORT2 -uscript_getShortName(UScriptCode scriptCode); - -/** - * Gets the script code associated with the given codepoint. - * Returns USCRIPT_MALAYALAM given 0x0D02 - * @param codepoint UChar32 codepoint - * @param err the error status code. - * @return The UScriptCode, or 0 if codepoint is invalid - * @stable ICU 2.4 - */ -U_STABLE UScriptCode U_EXPORT2 -uscript_getScript(UChar32 codepoint, UErrorCode *err); - -#endif - - diff --git a/WebKit/mac/icu/unicode/ustring.h b/WebKit/mac/icu/unicode/ustring.h deleted file mode 100644 index 6ebb6fb..0000000 --- a/WebKit/mac/icu/unicode/ustring.h +++ /dev/null @@ -1,1320 +0,0 @@ -/* -********************************************************************** -* Copyright (C) 1998-2004, International Business Machines -* Corporation and others. All Rights Reserved. -********************************************************************** -* -* File ustring.h -* -* Modification History: -* -* Date Name Description -* 12/07/98 bertrand Creation. -****************************************************************************** -*/ - -#ifndef USTRING_H -#define USTRING_H - -#include "unicode/utypes.h" -#include "unicode/putil.h" -#include "unicode/uiter.h" - -/** Simple declaration for u_strToTitle() to avoid including unicode/ubrk.h. @stable ICU 2.1*/ -#ifndef UBRK_TYPEDEF_UBREAK_ITERATOR -# define UBRK_TYPEDEF_UBREAK_ITERATOR - typedef void UBreakIterator; -#endif - -/** - * \file - * \brief C API: Unicode string handling functions - * - * These C API functions provide general Unicode string handling. - * - * Some functions are equivalent in name, signature, and behavior to the ANSI C <string.h> - * functions. (For example, they do not check for bad arguments like NULL string pointers.) - * In some cases, only the thread-safe variant of such a function is implemented here - * (see u_strtok_r()). - * - * Other functions provide more Unicode-specific functionality like locale-specific - * upper/lower-casing and string comparison in code point order. - * - * ICU uses 16-bit Unicode (UTF-16) in the form of arrays of UChar code units. - * UTF-16 encodes each Unicode code point with either one or two UChar code units. - * (This is the default form of Unicode, and a forward-compatible extension of the original, - * fixed-width form that was known as UCS-2. UTF-16 superseded UCS-2 with Unicode 2.0 - * in 1996.) - * - * Some APIs accept a 32-bit UChar32 value for a single code point. - * - * ICU also handles 16-bit Unicode text with unpaired surrogates. - * Such text is not well-formed UTF-16. - * Code-point-related functions treat unpaired surrogates as surrogate code points, - * i.e., as separate units. - * - * Although UTF-16 is a variable-width encoding form (like some legacy multi-byte encodings), - * it is much more efficient even for random access because the code unit values - * for single-unit characters vs. lead units vs. trail units are completely disjoint. - * This means that it is easy to determine character (code point) boundaries from - * random offsets in the string. - * - * Unicode (UTF-16) string processing is optimized for the single-unit case. - * Although it is important to support supplementary characters - * (which use pairs of lead/trail code units called "surrogates"), - * their occurrence is rare. Almost all characters in modern use require only - * a single UChar code unit (i.e., their code point values are <=0xffff). - * - * For more details see the User Guide Strings chapter (http://oss.software.ibm.com/icu/userguide/strings.html). - * For a discussion of the handling of unpaired surrogates see also - * Jitterbug 2145 and its icu mailing list proposal on 2002-sep-18. - */ - -/** - * Determine the length of an array of UChar. - * - * @param s The array of UChars, NULL (U+0000) terminated. - * @return The number of UChars in <code>chars</code>, minus the terminator. - * @stable ICU 2.0 - */ -U_STABLE int32_t U_EXPORT2 -u_strlen(const UChar *s); - -/** - * Count Unicode code points in the length UChar code units of the string. - * A code point may occupy either one or two UChar code units. - * Counting code points involves reading all code units. - * - * This functions is basically the inverse of the U16_FWD_N() macro (see utf.h). - * - * @param s The input string. - * @param length The number of UChar code units to be checked, or -1 to count all - * code points before the first NUL (U+0000). - * @return The number of code points in the specified code units. - * @stable ICU 2.0 - */ -U_STABLE int32_t U_EXPORT2 -u_countChar32(const UChar *s, int32_t length); - -/** - * Check if the string contains more Unicode code points than a certain number. - * This is more efficient than counting all code points in the entire string - * and comparing that number with a threshold. - * This function may not need to scan the string at all if the length is known - * (not -1 for NUL-termination) and falls within a certain range, and - * never needs to count more than 'number+1' code points. - * Logically equivalent to (u_countChar32(s, length)>number). - * A Unicode code point may occupy either one or two UChar code units. - * - * @param s The input string. - * @param length The length of the string, or -1 if it is NUL-terminated. - * @param number The number of code points in the string is compared against - * the 'number' parameter. - * @return Boolean value for whether the string contains more Unicode code points - * than 'number'. Same as (u_countChar32(s, length)>number). - * @stable ICU 2.4 - */ -U_STABLE UBool U_EXPORT2 -u_strHasMoreChar32Than(const UChar *s, int32_t length, int32_t number); - -/** - * Concatenate two ustrings. Appends a copy of <code>src</code>, - * including the null terminator, to <code>dst</code>. The initial copied - * character from <code>src</code> overwrites the null terminator in <code>dst</code>. - * - * @param dst The destination string. - * @param src The source string. - * @return A pointer to <code>dst</code>. - * @stable ICU 2.0 - */ -U_STABLE UChar* U_EXPORT2 -u_strcat(UChar *dst, - const UChar *src); - -/** - * Concatenate two ustrings. - * Appends at most <code>n</code> characters from <code>src</code> to <code>dst</code>. - * Adds a terminating NUL. - * If src is too long, then only <code>n-1</code> characters will be copied - * before the terminating NUL. - * If <code>n<=0</code> then dst is not modified. - * - * @param dst The destination string. - * @param src The source string. - * @param n The maximum number of characters to compare. - * @return A pointer to <code>dst</code>. - * @stable ICU 2.0 - */ -U_STABLE UChar* U_EXPORT2 -u_strncat(UChar *dst, - const UChar *src, - int32_t n); - -/** - * Find the first occurrence of a substring in a string. - * The substring is found at code point boundaries. - * That means that if the substring begins with - * a trail surrogate or ends with a lead surrogate, - * then it is found only if these surrogates stand alone in the text. - * Otherwise, the substring edge units would be matched against - * halves of surrogate pairs. - * - * @param s The string to search (NUL-terminated). - * @param substring The substring to find (NUL-terminated). - * @return A pointer to the first occurrence of <code>substring</code> in <code>s</code>, - * or <code>s</code> itself if the <code>substring</code> is empty, - * or <code>NULL</code> if <code>substring</code> is not in <code>s</code>. - * @stable ICU 2.0 - * - * @see u_strrstr - * @see u_strFindFirst - * @see u_strFindLast - */ -U_STABLE UChar * U_EXPORT2 -u_strstr(const UChar *s, const UChar *substring); - -/** - * Find the first occurrence of a substring in a string. - * The substring is found at code point boundaries. - * That means that if the substring begins with - * a trail surrogate or ends with a lead surrogate, - * then it is found only if these surrogates stand alone in the text. - * Otherwise, the substring edge units would be matched against - * halves of surrogate pairs. - * - * @param s The string to search. - * @param length The length of s (number of UChars), or -1 if it is NUL-terminated. - * @param substring The substring to find (NUL-terminated). - * @param subLength The length of substring (number of UChars), or -1 if it is NUL-terminated. - * @return A pointer to the first occurrence of <code>substring</code> in <code>s</code>, - * or <code>s</code> itself if the <code>substring</code> is empty, - * or <code>NULL</code> if <code>substring</code> is not in <code>s</code>. - * @stable ICU 2.4 - * - * @see u_strstr - * @see u_strFindLast - */ -U_STABLE UChar * U_EXPORT2 -u_strFindFirst(const UChar *s, int32_t length, const UChar *substring, int32_t subLength); - -/** - * Find the first occurrence of a BMP code point in a string. - * A surrogate code point is found only if its match in the text is not - * part of a surrogate pair. - * A NUL character is found at the string terminator. - * - * @param s The string to search (NUL-terminated). - * @param c The BMP code point to find. - * @return A pointer to the first occurrence of <code>c</code> in <code>s</code> - * or <code>NULL</code> if <code>c</code> is not in <code>s</code>. - * @stable ICU 2.0 - * - * @see u_strchr32 - * @see u_memchr - * @see u_strstr - * @see u_strFindFirst - */ -U_STABLE UChar * U_EXPORT2 -u_strchr(const UChar *s, UChar c); - -/** - * Find the first occurrence of a code point in a string. - * A surrogate code point is found only if its match in the text is not - * part of a surrogate pair. - * A NUL character is found at the string terminator. - * - * @param s The string to search (NUL-terminated). - * @param c The code point to find. - * @return A pointer to the first occurrence of <code>c</code> in <code>s</code> - * or <code>NULL</code> if <code>c</code> is not in <code>s</code>. - * @stable ICU 2.0 - * - * @see u_strchr - * @see u_memchr32 - * @see u_strstr - * @see u_strFindFirst - */ -U_STABLE UChar * U_EXPORT2 -u_strchr32(const UChar *s, UChar32 c); - -/** - * Find the last occurrence of a substring in a string. - * The substring is found at code point boundaries. - * That means that if the substring begins with - * a trail surrogate or ends with a lead surrogate, - * then it is found only if these surrogates stand alone in the text. - * Otherwise, the substring edge units would be matched against - * halves of surrogate pairs. - * - * @param s The string to search (NUL-terminated). - * @param substring The substring to find (NUL-terminated). - * @return A pointer to the last occurrence of <code>substring</code> in <code>s</code>, - * or <code>s</code> itself if the <code>substring</code> is empty, - * or <code>NULL</code> if <code>substring</code> is not in <code>s</code>. - * @stable ICU 2.4 - * - * @see u_strstr - * @see u_strFindFirst - * @see u_strFindLast - */ -U_STABLE UChar * U_EXPORT2 -u_strrstr(const UChar *s, const UChar *substring); - -/** - * Find the last occurrence of a substring in a string. - * The substring is found at code point boundaries. - * That means that if the substring begins with - * a trail surrogate or ends with a lead surrogate, - * then it is found only if these surrogates stand alone in the text. - * Otherwise, the substring edge units would be matched against - * halves of surrogate pairs. - * - * @param s The string to search. - * @param length The length of s (number of UChars), or -1 if it is NUL-terminated. - * @param substring The substring to find (NUL-terminated). - * @param subLength The length of substring (number of UChars), or -1 if it is NUL-terminated. - * @return A pointer to the last occurrence of <code>substring</code> in <code>s</code>, - * or <code>s</code> itself if the <code>substring</code> is empty, - * or <code>NULL</code> if <code>substring</code> is not in <code>s</code>. - * @stable ICU 2.4 - * - * @see u_strstr - * @see u_strFindLast - */ -U_STABLE UChar * U_EXPORT2 -u_strFindLast(const UChar *s, int32_t length, const UChar *substring, int32_t subLength); - -/** - * Find the last occurrence of a BMP code point in a string. - * A surrogate code point is found only if its match in the text is not - * part of a surrogate pair. - * A NUL character is found at the string terminator. - * - * @param s The string to search (NUL-terminated). - * @param c The BMP code point to find. - * @return A pointer to the last occurrence of <code>c</code> in <code>s</code> - * or <code>NULL</code> if <code>c</code> is not in <code>s</code>. - * @stable ICU 2.4 - * - * @see u_strrchr32 - * @see u_memrchr - * @see u_strrstr - * @see u_strFindLast - */ -U_STABLE UChar * U_EXPORT2 -u_strrchr(const UChar *s, UChar c); - -/** - * Find the last occurrence of a code point in a string. - * A surrogate code point is found only if its match in the text is not - * part of a surrogate pair. - * A NUL character is found at the string terminator. - * - * @param s The string to search (NUL-terminated). - * @param c The code point to find. - * @return A pointer to the last occurrence of <code>c</code> in <code>s</code> - * or <code>NULL</code> if <code>c</code> is not in <code>s</code>. - * @stable ICU 2.4 - * - * @see u_strrchr - * @see u_memchr32 - * @see u_strrstr - * @see u_strFindLast - */ -U_STABLE UChar * U_EXPORT2 -u_strrchr32(const UChar *s, UChar32 c); - -/** - * Locates the first occurrence in the string <code>string</code> of any of the characters - * in the string <code>matchSet</code>. - * Works just like C's strpbrk but with Unicode. - * - * @param string The string in which to search, NUL-terminated. - * @param matchSet A NUL-terminated string defining a set of code points - * for which to search in the text string. - * @return A pointer to the character in <code>string</code> that matches one of the - * characters in <code>matchSet</code>, or NULL if no such character is found. - * @stable ICU 2.0 - */ -U_STABLE UChar * U_EXPORT2 -u_strpbrk(const UChar *string, const UChar *matchSet); - -/** - * Returns the number of consecutive characters in <code>string</code>, - * beginning with the first, that do not occur somewhere in <code>matchSet</code>. - * Works just like C's strcspn but with Unicode. - * - * @param string The string in which to search, NUL-terminated. - * @param matchSet A NUL-terminated string defining a set of code points - * for which to search in the text string. - * @return The number of initial characters in <code>string</code> that do not - * occur in <code>matchSet</code>. - * @see u_strspn - * @stable ICU 2.0 - */ -U_STABLE int32_t U_EXPORT2 -u_strcspn(const UChar *string, const UChar *matchSet); - -/** - * Returns the number of consecutive characters in <code>string</code>, - * beginning with the first, that occur somewhere in <code>matchSet</code>. - * Works just like C's strspn but with Unicode. - * - * @param string The string in which to search, NUL-terminated. - * @param matchSet A NUL-terminated string defining a set of code points - * for which to search in the text string. - * @return The number of initial characters in <code>string</code> that do - * occur in <code>matchSet</code>. - * @see u_strcspn - * @stable ICU 2.0 - */ -U_STABLE int32_t U_EXPORT2 -u_strspn(const UChar *string, const UChar *matchSet); - -/** - * The string tokenizer API allows an application to break a string into - * tokens. Unlike strtok(), the saveState (the current pointer within the - * original string) is maintained in saveState. In the first call, the - * argument src is a pointer to the string. In subsequent calls to - * return successive tokens of that string, src must be specified as - * NULL. The value saveState is set by this function to maintain the - * function's position within the string, and on each subsequent call - * you must give this argument the same variable. This function does - * handle surrogate pairs. This function is similar to the strtok_r() - * the POSIX Threads Extension (1003.1c-1995) version. - * - * @param src String containing token(s). This string will be modified. - * After the first call to u_strtok_r(), this argument must - * be NULL to get to the next token. - * @param delim Set of delimiter characters (Unicode code points). - * @param saveState The current pointer within the original string, - * which is set by this function. The saveState - * parameter should the address of a local variable of type - * UChar *. (i.e. defined "Uhar *myLocalSaveState" and use - * &myLocalSaveState for this parameter). - * @return A pointer to the next token found in src, or NULL - * when there are no more tokens. - * @stable ICU 2.0 - */ -U_STABLE UChar * U_EXPORT2 -u_strtok_r(UChar *src, - const UChar *delim, - UChar **saveState); - -/** - * Compare two Unicode strings for bitwise equality (code unit order). - * - * @param s1 A string to compare. - * @param s2 A string to compare. - * @return 0 if <code>s1</code> and <code>s2</code> are bitwise equal; a negative - * value if <code>s1</code> is bitwise less than <code>s2,</code>; a positive - * value if <code>s1</code> is bitwise greater than <code>s2</code>. - * @stable ICU 2.0 - */ -U_STABLE int32_t U_EXPORT2 -u_strcmp(const UChar *s1, - const UChar *s2); - -/** - * Compare two Unicode strings in code point order. - * See u_strCompare for details. - * - * @param s1 A string to compare. - * @param s2 A string to compare. - * @return a negative/zero/positive integer corresponding to whether - * the first string is less than/equal to/greater than the second one - * in code point order - * @stable ICU 2.0 - */ -U_STABLE int32_t U_EXPORT2 -u_strcmpCodePointOrder(const UChar *s1, const UChar *s2); - -/** - * Compare two Unicode strings (binary order). - * - * The comparison can be done in code unit order or in code point order. - * They differ only in UTF-16 when - * comparing supplementary code points (U+10000..U+10ffff) - * to BMP code points near the end of the BMP (i.e., U+e000..U+ffff). - * In code unit order, high BMP code points sort after supplementary code points - * because they are stored as pairs of surrogates which are at U+d800..U+dfff. - * - * This functions works with strings of different explicitly specified lengths - * unlike the ANSI C-like u_strcmp() and u_memcmp() etc. - * NUL-terminated strings are possible with length arguments of -1. - * - * @param s1 First source string. - * @param length1 Length of first source string, or -1 if NUL-terminated. - * - * @param s2 Second source string. - * @param length2 Length of second source string, or -1 if NUL-terminated. - * - * @param codePointOrder Choose between code unit order (FALSE) - * and code point order (TRUE). - * - * @return <0 or 0 or >0 as usual for string comparisons - * - * @stable ICU 2.2 - */ -U_STABLE int32_t U_EXPORT2 -u_strCompare(const UChar *s1, int32_t length1, - const UChar *s2, int32_t length2, - UBool codePointOrder); - -/** - * Compare two Unicode strings (binary order) - * as presented by UCharIterator objects. - * Works otherwise just like u_strCompare(). - * - * Both iterators are reset to their start positions. - * When the function returns, it is undefined where the iterators - * have stopped. - * - * @param iter1 First source string iterator. - * @param iter2 Second source string iterator. - * @param codePointOrder Choose between code unit order (FALSE) - * and code point order (TRUE). - * - * @return <0 or 0 or >0 as usual for string comparisons - * - * @see u_strCompare - * - * @stable ICU 2.6 - */ -U_STABLE int32_t U_EXPORT2 -u_strCompareIter(UCharIterator *iter1, UCharIterator *iter2, UBool codePointOrder); - -#ifndef U_COMPARE_CODE_POINT_ORDER -/* see also unistr.h and unorm.h */ -/** - * Option bit for u_strCaseCompare, u_strcasecmp, unorm_compare, etc: - * Compare strings in code point order instead of code unit order. - * @stable ICU 2.2 - */ -#define U_COMPARE_CODE_POINT_ORDER 0x8000 -#endif - -/** - * Compare two strings case-insensitively using full case folding. - * This is equivalent to - * u_strCompare(u_strFoldCase(s1, options), - * u_strFoldCase(s2, options), - * (options&U_COMPARE_CODE_POINT_ORDER)!=0). - * - * The comparison can be done in UTF-16 code unit order or in code point order. - * They differ only when comparing supplementary code points (U+10000..U+10ffff) - * to BMP code points near the end of the BMP (i.e., U+e000..U+ffff). - * In code unit order, high BMP code points sort after supplementary code points - * because they are stored as pairs of surrogates which are at U+d800..U+dfff. - * - * This functions works with strings of different explicitly specified lengths - * unlike the ANSI C-like u_strcmp() and u_memcmp() etc. - * NUL-terminated strings are possible with length arguments of -1. - * - * @param s1 First source string. - * @param length1 Length of first source string, or -1 if NUL-terminated. - * - * @param s2 Second source string. - * @param length2 Length of second source string, or -1 if NUL-terminated. - * - * @param options A bit set of options: - * - U_FOLD_CASE_DEFAULT or 0 is used for default options: - * Comparison in code unit order with default case folding. - * - * - U_COMPARE_CODE_POINT_ORDER - * Set to choose code point order instead of code unit order - * (see u_strCompare for details). - * - * - U_FOLD_CASE_EXCLUDE_SPECIAL_I - * - * @param pErrorCode Must be a valid pointer to an error code value, - * which must not indicate a failure before the function call. - * - * @return <0 or 0 or >0 as usual for string comparisons - * - * @stable ICU 2.2 - */ -U_STABLE int32_t U_EXPORT2 -u_strCaseCompare(const UChar *s1, int32_t length1, - const UChar *s2, int32_t length2, - uint32_t options, - UErrorCode *pErrorCode); - -/** - * Compare two ustrings for bitwise equality. - * Compares at most <code>n</code> characters. - * - * @param ucs1 A string to compare. - * @param ucs2 A string to compare. - * @param n The maximum number of characters to compare. - * @return 0 if <code>s1</code> and <code>s2</code> are bitwise equal; a negative - * value if <code>s1</code> is bitwise less than <code>s2</code>; a positive - * value if <code>s1</code> is bitwise greater than <code>s2</code>. - * @stable ICU 2.0 - */ -U_STABLE int32_t U_EXPORT2 -u_strncmp(const UChar *ucs1, - const UChar *ucs2, - int32_t n); - -/** - * Compare two Unicode strings in code point order. - * This is different in UTF-16 from u_strncmp() if supplementary characters are present. - * For details, see u_strCompare(). - * - * @param s1 A string to compare. - * @param s2 A string to compare. - * @param n The maximum number of characters to compare. - * @return a negative/zero/positive integer corresponding to whether - * the first string is less than/equal to/greater than the second one - * in code point order - * @stable ICU 2.0 - */ -U_STABLE int32_t U_EXPORT2 -u_strncmpCodePointOrder(const UChar *s1, const UChar *s2, int32_t n); - -/** - * Compare two strings case-insensitively using full case folding. - * This is equivalent to u_strcmp(u_strFoldCase(s1, options), u_strFoldCase(s2, options)). - * - * @param s1 A string to compare. - * @param s2 A string to compare. - * @param options A bit set of options: - * - U_FOLD_CASE_DEFAULT or 0 is used for default options: - * Comparison in code unit order with default case folding. - * - * - U_COMPARE_CODE_POINT_ORDER - * Set to choose code point order instead of code unit order - * (see u_strCompare for details). - * - * - U_FOLD_CASE_EXCLUDE_SPECIAL_I - * - * @return A negative, zero, or positive integer indicating the comparison result. - * @stable ICU 2.0 - */ -U_STABLE int32_t U_EXPORT2 -u_strcasecmp(const UChar *s1, const UChar *s2, uint32_t options); - -/** - * Compare two strings case-insensitively using full case folding. - * This is equivalent to u_strcmp(u_strFoldCase(s1, at most n, options), - * u_strFoldCase(s2, at most n, options)). - * - * @param s1 A string to compare. - * @param s2 A string to compare. - * @param n The maximum number of characters each string to case-fold and then compare. - * @param options A bit set of options: - * - U_FOLD_CASE_DEFAULT or 0 is used for default options: - * Comparison in code unit order with default case folding. - * - * - U_COMPARE_CODE_POINT_ORDER - * Set to choose code point order instead of code unit order - * (see u_strCompare for details). - * - * - U_FOLD_CASE_EXCLUDE_SPECIAL_I - * - * @return A negative, zero, or positive integer indicating the comparison result. - * @stable ICU 2.0 - */ -U_STABLE int32_t U_EXPORT2 -u_strncasecmp(const UChar *s1, const UChar *s2, int32_t n, uint32_t options); - -/** - * Compare two strings case-insensitively using full case folding. - * This is equivalent to u_strcmp(u_strFoldCase(s1, n, options), - * u_strFoldCase(s2, n, options)). - * - * @param s1 A string to compare. - * @param s2 A string to compare. - * @param length The number of characters in each string to case-fold and then compare. - * @param options A bit set of options: - * - U_FOLD_CASE_DEFAULT or 0 is used for default options: - * Comparison in code unit order with default case folding. - * - * - U_COMPARE_CODE_POINT_ORDER - * Set to choose code point order instead of code unit order - * (see u_strCompare for details). - * - * - U_FOLD_CASE_EXCLUDE_SPECIAL_I - * - * @return A negative, zero, or positive integer indicating the comparison result. - * @stable ICU 2.0 - */ -U_STABLE int32_t U_EXPORT2 -u_memcasecmp(const UChar *s1, const UChar *s2, int32_t length, uint32_t options); - -/** - * Copy a ustring. Adds a null terminator. - * - * @param dst The destination string. - * @param src The source string. - * @return A pointer to <code>dst</code>. - * @stable ICU 2.0 - */ -U_STABLE UChar* U_EXPORT2 -u_strcpy(UChar *dst, - const UChar *src); - -/** - * Copy a ustring. - * Copies at most <code>n</code> characters. The result will be null terminated - * if the length of <code>src</code> is less than <code>n</code>. - * - * @param dst The destination string. - * @param src The source string. - * @param n The maximum number of characters to copy. - * @return A pointer to <code>dst</code>. - * @stable ICU 2.0 - */ -U_STABLE UChar* U_EXPORT2 -u_strncpy(UChar *dst, - const UChar *src, - int32_t n); - -#if !UCONFIG_NO_CONVERSION - -/** - * Copy a byte string encoded in the default codepage to a ustring. - * Adds a null terminator. - * Performs a host byte to UChar conversion - * - * @param dst The destination string. - * @param src The source string. - * @return A pointer to <code>dst</code>. - * @stable ICU 2.0 - */ -U_STABLE UChar* U_EXPORT2 u_uastrcpy(UChar *dst, - const char *src ); - -/** - * Copy a byte string encoded in the default codepage to a ustring. - * Copies at most <code>n</code> characters. The result will be null terminated - * if the length of <code>src</code> is less than <code>n</code>. - * Performs a host byte to UChar conversion - * - * @param dst The destination string. - * @param src The source string. - * @param n The maximum number of characters to copy. - * @return A pointer to <code>dst</code>. - * @stable ICU 2.0 - */ -U_STABLE UChar* U_EXPORT2 u_uastrncpy(UChar *dst, - const char *src, - int32_t n); - -/** - * Copy ustring to a byte string encoded in the default codepage. - * Adds a null terminator. - * Performs a UChar to host byte conversion - * - * @param dst The destination string. - * @param src The source string. - * @return A pointer to <code>dst</code>. - * @stable ICU 2.0 - */ -U_STABLE char* U_EXPORT2 u_austrcpy(char *dst, - const UChar *src ); - -/** - * Copy ustring to a byte string encoded in the default codepage. - * Copies at most <code>n</code> characters. The result will be null terminated - * if the length of <code>src</code> is less than <code>n</code>. - * Performs a UChar to host byte conversion - * - * @param dst The destination string. - * @param src The source string. - * @param n The maximum number of characters to copy. - * @return A pointer to <code>dst</code>. - * @stable ICU 2.0 - */ -U_STABLE char* U_EXPORT2 u_austrncpy(char *dst, - const UChar *src, - int32_t n ); - -#endif - -/** - * Synonym for memcpy(), but with UChars only. - * @param dest The destination string - * @param src The source string - * @param count The number of characters to copy - * @return A pointer to <code>dest</code> - * @stable ICU 2.0 - */ -U_STABLE UChar* U_EXPORT2 -u_memcpy(UChar *dest, const UChar *src, int32_t count); - -/** - * Synonym for memmove(), but with UChars only. - * @param dest The destination string - * @param src The source string - * @param count The number of characters to move - * @return A pointer to <code>dest</code> - * @stable ICU 2.0 - */ -U_STABLE UChar* U_EXPORT2 -u_memmove(UChar *dest, const UChar *src, int32_t count); - -/** - * Initialize <code>count</code> characters of <code>dest</code> to <code>c</code>. - * - * @param dest The destination string. - * @param c The character to initialize the string. - * @param count The maximum number of characters to set. - * @return A pointer to <code>dest</code>. - * @stable ICU 2.0 - */ -U_STABLE UChar* U_EXPORT2 -u_memset(UChar *dest, UChar c, int32_t count); - -/** - * Compare the first <code>count</code> UChars of each buffer. - * - * @param buf1 The first string to compare. - * @param buf2 The second string to compare. - * @param count The maximum number of UChars to compare. - * @return When buf1 < buf2, a negative number is returned. - * When buf1 == buf2, 0 is returned. - * When buf1 > buf2, a positive number is returned. - * @stable ICU 2.0 - */ -U_STABLE int32_t U_EXPORT2 -u_memcmp(const UChar *buf1, const UChar *buf2, int32_t count); - -/** - * Compare two Unicode strings in code point order. - * This is different in UTF-16 from u_memcmp() if supplementary characters are present. - * For details, see u_strCompare(). - * - * @param s1 A string to compare. - * @param s2 A string to compare. - * @param count The maximum number of characters to compare. - * @return a negative/zero/positive integer corresponding to whether - * the first string is less than/equal to/greater than the second one - * in code point order - * @stable ICU 2.0 - */ -U_STABLE int32_t U_EXPORT2 -u_memcmpCodePointOrder(const UChar *s1, const UChar *s2, int32_t count); - -/** - * Find the first occurrence of a BMP code point in a string. - * A surrogate code point is found only if its match in the text is not - * part of a surrogate pair. - * A NUL character is found at the string terminator. - * - * @param s The string to search (contains <code>count</code> UChars). - * @param c The BMP code point to find. - * @param count The length of the string. - * @return A pointer to the first occurrence of <code>c</code> in <code>s</code> - * or <code>NULL</code> if <code>c</code> is not in <code>s</code>. - * @stable ICU 2.0 - * - * @see u_strchr - * @see u_memchr32 - * @see u_strFindFirst - */ -U_STABLE UChar* U_EXPORT2 -u_memchr(const UChar *s, UChar c, int32_t count); - -/** - * Find the first occurrence of a code point in a string. - * A surrogate code point is found only if its match in the text is not - * part of a surrogate pair. - * A NUL character is found at the string terminator. - * - * @param s The string to search (contains <code>count</code> UChars). - * @param c The code point to find. - * @param count The length of the string. - * @return A pointer to the first occurrence of <code>c</code> in <code>s</code> - * or <code>NULL</code> if <code>c</code> is not in <code>s</code>. - * @stable ICU 2.0 - * - * @see u_strchr32 - * @see u_memchr - * @see u_strFindFirst - */ -U_STABLE UChar* U_EXPORT2 -u_memchr32(const UChar *s, UChar32 c, int32_t count); - -/** - * Find the last occurrence of a BMP code point in a string. - * A surrogate code point is found only if its match in the text is not - * part of a surrogate pair. - * A NUL character is found at the string terminator. - * - * @param s The string to search (contains <code>count</code> UChars). - * @param c The BMP code point to find. - * @param count The length of the string. - * @return A pointer to the last occurrence of <code>c</code> in <code>s</code> - * or <code>NULL</code> if <code>c</code> is not in <code>s</code>. - * @stable ICU 2.4 - * - * @see u_strrchr - * @see u_memrchr32 - * @see u_strFindLast - */ -U_STABLE UChar* U_EXPORT2 -u_memrchr(const UChar *s, UChar c, int32_t count); - -/** - * Find the last occurrence of a code point in a string. - * A surrogate code point is found only if its match in the text is not - * part of a surrogate pair. - * A NUL character is found at the string terminator. - * - * @param s The string to search (contains <code>count</code> UChars). - * @param c The code point to find. - * @param count The length of the string. - * @return A pointer to the last occurrence of <code>c</code> in <code>s</code> - * or <code>NULL</code> if <code>c</code> is not in <code>s</code>. - * @stable ICU 2.4 - * - * @see u_strrchr32 - * @see u_memrchr - * @see u_strFindLast - */ -U_STABLE UChar* U_EXPORT2 -u_memrchr32(const UChar *s, UChar32 c, int32_t count); - -/** - * Unicode String literals in C. - * We need one macro to declare a variable for the string - * and to statically preinitialize it if possible, - * and a second macro to dynamically intialize such a string variable if necessary. - * - * The macros are defined for maximum performance. - * They work only for strings that contain "invariant characters", i.e., - * only latin letters, digits, and some punctuation. - * See utypes.h for details. - * - * A pair of macros for a single string must be used with the same - * parameters. - * The string parameter must be a C string literal. - * The length of the string, not including the terminating - * <code>NUL</code>, must be specified as a constant. - * The U_STRING_DECL macro should be invoked exactly once for one - * such string variable before it is used. - * - * Usage: - * <pre> - *   U_STRING_DECL(ustringVar1, "Quick-Fox 2", 11); - *   U_STRING_DECL(ustringVar2, "jumps 5%", 8); - *   static UBool didInit=FALSE; - *   - *   int32_t function() { - *   if(!didInit) { - *   U_STRING_INIT(ustringVar1, "Quick-Fox 2", 11); - *   U_STRING_INIT(ustringVar2, "jumps 5%", 8); - *   didInit=TRUE; - *   } - *   return u_strcmp(ustringVar1, ustringVar2); - *   } - * </pre> - * @stable ICU 2.0 - */ -#if U_SIZEOF_WCHAR_T==U_SIZEOF_UCHAR && U_CHARSET_FAMILY==U_ASCII_FAMILY -# define U_STRING_DECL(var, cs, length) static const wchar_t var[(length)+1]={ L ## cs } - /**@stable ICU 2.0 */ -# define U_STRING_INIT(var, cs, length) -#elif U_SIZEOF_UCHAR==1 && U_CHARSET_FAMILY==U_ASCII_FAMILY -# define U_STRING_DECL(var, cs, length) static const UChar var[(length)+1]={ (const UChar *)cs } - /**@stable ICU 2.0 */ -# define U_STRING_INIT(var, cs, length) -#else -# define U_STRING_DECL(var, cs, length) static UChar var[(length)+1] - /**@stable ICU 2.0 */ -# define U_STRING_INIT(var, cs, length) u_charsToUChars(cs, var, length+1) -#endif - -/** - * Unescape a string of characters and write the resulting - * Unicode characters to the destination buffer. The following escape - * sequences are recognized: - * - * \\uhhhh 4 hex digits; h in [0-9A-Fa-f] - * \\Uhhhhhhhh 8 hex digits - * \\xhh 1-2 hex digits - * \\x{h...} 1-8 hex digits - * \\ooo 1-3 octal digits; o in [0-7] - * \\cX control-X; X is masked with 0x1F - * - * as well as the standard ANSI C escapes: - * - * \\a => U+0007, \\b => U+0008, \\t => U+0009, \\n => U+000A, - * \\v => U+000B, \\f => U+000C, \\r => U+000D, \\e => U+001B, - * \\" => U+0022, \\' => U+0027, \\? => U+003F, \\\\ => U+005C - * - * Anything else following a backslash is generically escaped. For - * example, "[a\\-z]" returns "[a-z]". - * - * If an escape sequence is ill-formed, this method returns an empty - * string. An example of an ill-formed sequence is "\\u" followed by - * fewer than 4 hex digits. - * - * The above characters are recognized in the compiler's codepage, - * that is, they are coded as 'u', '\\', etc. Characters that are - * not parts of escape sequences are converted using u_charsToUChars(). - * - * This function is similar to UnicodeString::unescape() but not - * identical to it. The latter takes a source UnicodeString, so it - * does escape recognition but no conversion. - * - * @param src a zero-terminated string of invariant characters - * @param dest pointer to buffer to receive converted and unescaped - * text and, if there is room, a zero terminator. May be NULL for - * preflighting, in which case no UChars will be written, but the - * return value will still be valid. On error, an empty string is - * stored here (if possible). - * @param destCapacity the number of UChars that may be written at - * dest. Ignored if dest == NULL. - * @return the length of unescaped string. - * @see u_unescapeAt - * @see UnicodeString#unescape() - * @see UnicodeString#unescapeAt() - * @stable ICU 2.0 - */ -U_STABLE int32_t U_EXPORT2 -u_unescape(const char *src, - UChar *dest, int32_t destCapacity); - -U_CDECL_BEGIN -/** - * Callback function for u_unescapeAt() that returns a character of - * the source text given an offset and a context pointer. The context - * pointer will be whatever is passed into u_unescapeAt(). - * - * @param offset pointer to the offset that will be passed to u_unescapeAt(). - * @param context an opaque pointer passed directly into u_unescapeAt() - * @return the character represented by the escape sequence at - * offset - * @see u_unescapeAt - * @stable ICU 2.0 - */ -typedef UChar (U_CALLCONV *UNESCAPE_CHAR_AT)(int32_t offset, void *context); -U_CDECL_END - -/** - * Unescape a single sequence. The character at offset-1 is assumed - * (without checking) to be a backslash. This method takes a callback - * pointer to a function that returns the UChar at a given offset. By - * varying this callback, ICU functions are able to unescape char* - * strings, UnicodeString objects, and UFILE pointers. - * - * If offset is out of range, or if the escape sequence is ill-formed, - * (UChar32)0xFFFFFFFF is returned. See documentation of u_unescape() - * for a list of recognized sequences. - * - * @param charAt callback function that returns a UChar of the source - * text given an offset and a context pointer. - * @param offset pointer to the offset that will be passed to charAt. - * The offset value will be updated upon return to point after the - * last parsed character of the escape sequence. On error the offset - * is unchanged. - * @param length the number of characters in the source text. The - * last character of the source text is considered to be at offset - * length-1. - * @param context an opaque pointer passed directly into charAt. - * @return the character represented by the escape sequence at - * offset, or (UChar32)0xFFFFFFFF on error. - * @see u_unescape() - * @see UnicodeString#unescape() - * @see UnicodeString#unescapeAt() - * @stable ICU 2.0 - */ -U_STABLE UChar32 U_EXPORT2 -u_unescapeAt(UNESCAPE_CHAR_AT charAt, - int32_t *offset, - int32_t length, - void *context); - -/** - * Uppercase the characters in a string. - * Casing is locale-dependent and context-sensitive. - * The result may be longer or shorter than the original. - * The source string and the destination buffer are allowed to overlap. - * - * @param dest A buffer for the result string. The result will be zero-terminated if - * the buffer is large enough. - * @param destCapacity The size of the buffer (number of UChars). If it is 0, then - * dest may be NULL and the function will only return the length of the result - * without writing any of the result string. - * @param src The original string - * @param srcLength The length of the original string. If -1, then src must be zero-terminated. - * @param locale The locale to consider, or "" for the root locale or NULL for the default locale. - * @param pErrorCode Must be a valid pointer to an error code value, - * which must not indicate a failure before the function call. - * @return The length of the result string. It may be greater than destCapacity. In that case, - * only some of the result was written to the destination buffer. - * @stable ICU 2.0 - */ -U_STABLE int32_t U_EXPORT2 -u_strToUpper(UChar *dest, int32_t destCapacity, - const UChar *src, int32_t srcLength, - const char *locale, - UErrorCode *pErrorCode); - -/** - * Lowercase the characters in a string. - * Casing is locale-dependent and context-sensitive. - * The result may be longer or shorter than the original. - * The source string and the destination buffer are allowed to overlap. - * - * @param dest A buffer for the result string. The result will be zero-terminated if - * the buffer is large enough. - * @param destCapacity The size of the buffer (number of UChars). If it is 0, then - * dest may be NULL and the function will only return the length of the result - * without writing any of the result string. - * @param src The original string - * @param srcLength The length of the original string. If -1, then src must be zero-terminated. - * @param locale The locale to consider, or "" for the root locale or NULL for the default locale. - * @param pErrorCode Must be a valid pointer to an error code value, - * which must not indicate a failure before the function call. - * @return The length of the result string. It may be greater than destCapacity. In that case, - * only some of the result was written to the destination buffer. - * @stable ICU 2.0 - */ -U_STABLE int32_t U_EXPORT2 -u_strToLower(UChar *dest, int32_t destCapacity, - const UChar *src, int32_t srcLength, - const char *locale, - UErrorCode *pErrorCode); - -#if !UCONFIG_NO_BREAK_ITERATION - -/** - * Titlecase a string. - * Casing is locale-dependent and context-sensitive. - * Titlecasing uses a break iterator to find the first characters of words - * that are to be titlecased. It titlecases those characters and lowercases - * all others. - * - * The titlecase break iterator can be provided to customize for arbitrary - * styles, using rules and dictionaries beyond the standard iterators. - * It may be more efficient to always provide an iterator to avoid - * opening and closing one for each string. - * The standard titlecase iterator for the root locale implements the - * algorithm of Unicode TR 21. - * - * This function uses only the first() and next() methods of the - * provided break iterator. - * - * The result may be longer or shorter than the original. - * The source string and the destination buffer are allowed to overlap. - * - * @param dest A buffer for the result string. The result will be zero-terminated if - * the buffer is large enough. - * @param destCapacity The size of the buffer (number of UChars). If it is 0, then - * dest may be NULL and the function will only return the length of the result - * without writing any of the result string. - * @param src The original string - * @param srcLength The length of the original string. If -1, then src must be zero-terminated. - * @param titleIter A break iterator to find the first characters of words - * that are to be titlecased. - * If none is provided (NULL), then a standard titlecase - * break iterator is opened. - * @param locale The locale to consider, or "" for the root locale or NULL for the default locale. - * @param pErrorCode Must be a valid pointer to an error code value, - * which must not indicate a failure before the function call. - * @return The length of the result string. It may be greater than destCapacity. In that case, - * only some of the result was written to the destination buffer. - * @stable ICU 2.1 - */ -U_STABLE int32_t U_EXPORT2 -u_strToTitle(UChar *dest, int32_t destCapacity, - const UChar *src, int32_t srcLength, - UBreakIterator *titleIter, - const char *locale, - UErrorCode *pErrorCode); - -#endif - -/** - * Case-fold the characters in a string. - * Case-folding is locale-independent and not context-sensitive, - * but there is an option for whether to include or exclude mappings for dotted I - * and dotless i that are marked with 'I' in CaseFolding.txt. - * The result may be longer or shorter than the original. - * The source string and the destination buffer are allowed to overlap. - * - * @param dest A buffer for the result string. The result will be zero-terminated if - * the buffer is large enough. - * @param destCapacity The size of the buffer (number of UChars). If it is 0, then - * dest may be NULL and the function will only return the length of the result - * without writing any of the result string. - * @param src The original string - * @param srcLength The length of the original string. If -1, then src must be zero-terminated. - * @param options Either U_FOLD_CASE_DEFAULT or U_FOLD_CASE_EXCLUDE_SPECIAL_I - * @param pErrorCode Must be a valid pointer to an error code value, - * which must not indicate a failure before the function call. - * @return The length of the result string. It may be greater than destCapacity. In that case, - * only some of the result was written to the destination buffer. - * @stable ICU 2.0 - */ -U_STABLE int32_t U_EXPORT2 -u_strFoldCase(UChar *dest, int32_t destCapacity, - const UChar *src, int32_t srcLength, - uint32_t options, - UErrorCode *pErrorCode); - -/** - * Converts a sequence of UChars to wchar_t units. - * - * @param dest A buffer for the result string. The result will be zero-terminated if - * the buffer is large enough. - * @param destCapacity The size of the buffer (number of wchar_t's). If it is 0, then - * dest may be NULL and the function will only return the length of the - * result without writing any of the result string (pre-flighting). - * @param pDestLength A pointer to receive the number of units written to the destination. If - * pDestLength!=NULL then *pDestLength is always set to the - * number of output units corresponding to the transformation of - * all the input units, even in case of a buffer overflow. - * @param src The original source string - * @param srcLength The length of the original string. If -1, then src must be zero-terminated. - * @param pErrorCode Must be a valid pointer to an error code value, - * which must not indicate a failure before the function call. - * @return The pointer to destination buffer. - * @stable ICU 2.0 - */ -U_STABLE wchar_t* U_EXPORT2 -u_strToWCS(wchar_t *dest, - int32_t destCapacity, - int32_t *pDestLength, - const UChar *src, - int32_t srcLength, - UErrorCode *pErrorCode); -/** - * Converts a sequence of wchar_t units to UChars - * - * @param dest A buffer for the result string. The result will be zero-terminated if - * the buffer is large enough. - * @param destCapacity The size of the buffer (number of UChars). If it is 0, then - * dest may be NULL and the function will only return the length of the - * result without writing any of the result string (pre-flighting). - * @param pDestLength A pointer to receive the number of units written to the destination. If - * pDestLength!=NULL then *pDestLength is always set to the - * number of output units corresponding to the transformation of - * all the input units, even in case of a buffer overflow. - * @param src The original source string - * @param srcLength The length of the original string. If -1, then src must be zero-terminated. - * @param pErrorCode Must be a valid pointer to an error code value, - * which must not indicate a failure before the function call. - * @return The pointer to destination buffer. - * @stable ICU 2.0 - */ -U_STABLE UChar* U_EXPORT2 -u_strFromWCS(UChar *dest, - int32_t destCapacity, - int32_t *pDestLength, - const wchar_t *src, - int32_t srcLength, - UErrorCode *pErrorCode); -/** - * Converts a sequence of UChars (UTF-16) to UTF-8 bytes - * - * @param dest A buffer for the result string. The result will be zero-terminated if - * the buffer is large enough. - * @param destCapacity The size of the buffer (number of chars). If it is 0, then - * dest may be NULL and the function will only return the length of the - * result without writing any of the result string (pre-flighting). - * @param pDestLength A pointer to receive the number of units written to the destination. If - * pDestLength!=NULL then *pDestLength is always set to the - * number of output units corresponding to the transformation of - * all the input units, even in case of a buffer overflow. - * @param src The original source string - * @param srcLength The length of the original string. If -1, then src must be zero-terminated. - * @param pErrorCode Must be a valid pointer to an error code value, - * which must not indicate a failure before the function call. - * @return The pointer to destination buffer. - * @stable ICU 2.0 - */ -U_STABLE char* U_EXPORT2 -u_strToUTF8(char *dest, - int32_t destCapacity, - int32_t *pDestLength, - const UChar *src, - int32_t srcLength, - UErrorCode *pErrorCode); - -/** - * Converts a sequence of UTF-8 bytes to UChars (UTF-16). - * - * @param dest A buffer for the result string. The result will be zero-terminated if - * the buffer is large enough. - * @param destCapacity The size of the buffer (number of UChars). If it is 0, then - * dest may be NULL and the function will only return the length of the - * result without writing any of the result string (pre-flighting). - * @param pDestLength A pointer to receive the number of units written to the destination. If - * pDestLength!=NULL then *pDestLength is always set to the - * number of output units corresponding to the transformation of - * all the input units, even in case of a buffer overflow. - * @param src The original source string - * @param srcLength The length of the original string. If -1, then src must be zero-terminated. - * @param pErrorCode Must be a valid pointer to an error code value, - * which must not indicate a failure before the function call. - * @return The pointer to destination buffer. - * @stable ICU 2.0 - */ -U_STABLE UChar* U_EXPORT2 -u_strFromUTF8(UChar *dest, - int32_t destCapacity, - int32_t *pDestLength, - const char *src, - int32_t srcLength, - UErrorCode *pErrorCode); - -/** - * Converts a sequence of UChars (UTF-16) to UTF32 units. - * - * @param dest A buffer for the result string. The result will be zero-terminated if - * the buffer is large enough. - * @param destCapacity The size of the buffer (number of UChar32s). If it is 0, then - * dest may be NULL and the function will only return the length of the - * result without writing any of the result string (pre-flighting). - * @param pDestLength A pointer to receive the number of units written to the destination. If - * pDestLength!=NULL then *pDestLength is always set to the - * number of output units corresponding to the transformation of - * all the input units, even in case of a buffer overflow. - * @param src The original source string - * @param srcLength The length of the original string. If -1, then src must be zero-terminated. - * @param pErrorCode Must be a valid pointer to an error code value, - * which must not indicate a failure before the function call. - * @return The pointer to destination buffer. - * @stable ICU 2.0 - */ -U_STABLE UChar32* U_EXPORT2 -u_strToUTF32(UChar32 *dest, - int32_t destCapacity, - int32_t *pDestLength, - const UChar *src, - int32_t srcLength, - UErrorCode *pErrorCode); - -/** - * Converts a sequence of UTF32 units to UChars (UTF-16) - * - * @param dest A buffer for the result string. The result will be zero-terminated if - * the buffer is large enough. - * @param destCapacity The size of the buffer (number of UChars). If it is 0, then - * dest may be NULL and the function will only return the length of the - * result without writing any of the result string (pre-flighting). - * @param pDestLength A pointer to receive the number of units written to the destination. If - * pDestLength!=NULL then *pDestLength is always set to the - * number of output units corresponding to the transformation of - * all the input units, even in case of a buffer overflow. - * @param src The original source string - * @param srcLength The length of the original string. If -1, then src must be zero-terminated. - * @param pErrorCode Must be a valid pointer to an error code value, - * which must not indicate a failure before the function call. - * @return The pointer to destination buffer. - * @stable ICU 2.0 - */ -U_STABLE UChar* U_EXPORT2 -u_strFromUTF32(UChar *dest, - int32_t destCapacity, - int32_t *pDestLength, - const UChar32 *src, - int32_t srcLength, - UErrorCode *pErrorCode); - -#endif diff --git a/WebKit/mac/icu/unicode/utf.h b/WebKit/mac/icu/unicode/utf.h deleted file mode 100644 index 201691d..0000000 --- a/WebKit/mac/icu/unicode/utf.h +++ /dev/null @@ -1,221 +0,0 @@ -/* -******************************************************************************* -* -* Copyright (C) 1999-2004, International Business Machines -* Corporation and others. All Rights Reserved. -* -******************************************************************************* -* file name: utf.h -* encoding: US-ASCII -* tab size: 8 (not used) -* indentation:4 -* -* created on: 1999sep09 -* created by: Markus W. Scherer -*/ - -/** - * \file - * \brief C API: Code point macros - * - * This file defines macros for checking whether a code point is - * a surrogate or a non-character etc. - * - * The UChar and UChar32 data types for Unicode code units and code points - * are defined in umachines.h because they can be machine-dependent. - * - * utf.h is included by utypes.h and itself includes utf8.h and utf16.h after some - * common definitions. Those files define macros for efficiently getting code points - * in and out of UTF-8/16 strings. - * utf16.h macros have "U16_" prefixes. - * utf8.h defines similar macros with "U8_" prefixes for UTF-8 string handling. - * - * ICU processes 16-bit Unicode strings. - * Most of the time, such strings are well-formed UTF-16. - * Single, unpaired surrogates must be handled as well, and are treated in ICU - * like regular code points where possible. - * (Pairs of surrogate code points are indistinguishable from supplementary - * code points encoded as pairs of supplementary code units.) - * - * In fact, almost all Unicode code points in normal text (>99%) - * are on the BMP (<=U+ffff) and even <=U+d7ff. - * ICU functions handle supplementary code points (U+10000..U+10ffff) - * but are optimized for the much more frequently occurring BMP code points. - * - * utf.h defines UChar to be an unsigned 16-bit integer. If this matches wchar_t, then - * UChar is defined to be exactly wchar_t, otherwise uint16_t. - * - * UChar32 is defined to be a signed 32-bit integer (int32_t), large enough for a 21-bit - * Unicode code point (Unicode scalar value, 0..0x10ffff). - * Before ICU 2.4, the definition of UChar32 was similarly platform-dependent as - * the definition of UChar. For details see the documentation for UChar32 itself. - * - * utf.h also defines a small number of C macros for single Unicode code points. - * These are simple checks for surrogates and non-characters. - * For actual Unicode character properties see uchar.h. - * - * By default, string operations must be done with error checking in case - * a string is not well-formed UTF-16. - * The macros will detect if a surrogate code unit is unpaired - * (lead unit without trail unit or vice versa) and just return the unit itself - * as the code point. - * (It is an accidental property of Unicode and UTF-16 that all - * malformed sequences can be expressed unambiguously with a distinct subrange - * of Unicode code points.) - * - * When it is safe to assume that text is well-formed UTF-16 - * (does not contain single, unpaired surrogates), then one can use - * U16_..._UNSAFE macros. - * These do not check for proper code unit sequences or truncated text and may - * yield wrong results or even cause a crash if they are used with "malformed" - * text. - * In practice, U16_..._UNSAFE macros will produce slightly less code but - * should not be faster because the processing is only different when a - * surrogate code unit is detected, which will be rare. - * - * Similarly for UTF-8, there are "safe" macros without a suffix, - * and U8_..._UNSAFE versions. - * The performance differences are much larger here because UTF-8 provides so - * many opportunities for malformed sequences. - * The unsafe UTF-8 macros are entirely implemented inside the macro definitions - * and are fast, while the safe UTF-8 macros call functions for all but the - * trivial (ASCII) cases. - * - * Unlike with UTF-16, malformed sequences cannot be expressed with distinct - * code point values (0..U+10ffff). They are indicated with negative values instead. - * - * For more information see the ICU User Guide Strings chapter - * (http://oss.software.ibm.com/icu/userguide/). - * - * <em>Usage:</em> - * ICU coding guidelines for if() statements should be followed when using these macros. - * Compound statements (curly braces {}) must be used for if-else-while... - * bodies and all macro statements should be terminated with semicolon. - * - * @stable ICU 2.4 - */ - -#ifndef __UTF_H__ -#define __UTF_H__ - -#include "unicode/utypes.h" -/* include the utfXX.h after the following definitions */ - -/* single-code point definitions -------------------------------------------- */ - -/** - * This value is intended for sentinel values for APIs that - * (take or) return single code points (UChar32). - * It is outside of the Unicode code point range 0..0x10ffff. - * - * For example, a "done" or "error" value in a new API - * could be indicated with U_SENTINEL. - * - * ICU APIs designed before ICU 2.4 usually define service-specific "done" - * values, mostly 0xffff. - * Those may need to be distinguished from - * actual U+ffff text contents by calling functions like - * CharacterIterator::hasNext() or UnicodeString::length(). - * - * @return -1 - * @see UChar32 - * @stable ICU 2.4 - */ -#define U_SENTINEL (-1) - -/** - * Is this code point a Unicode noncharacter? - * @param c 32-bit code point - * @return TRUE or FALSE - * @stable ICU 2.4 - */ -#define U_IS_UNICODE_NONCHAR(c) \ - ((c)>=0xfdd0 && \ - ((uint32_t)(c)<=0xfdef || ((c)&0xfffe)==0xfffe) && \ - (uint32_t)(c)<=0x10ffff) - -/** - * Is c a Unicode code point value (0..U+10ffff) - * that can be assigned a character? - * - * Code points that are not characters include: - * - single surrogate code points (U+d800..U+dfff, 2048 code points) - * - the last two code points on each plane (U+__fffe and U+__ffff, 34 code points) - * - U+fdd0..U+fdef (new with Unicode 3.1, 32 code points) - * - the highest Unicode code point value is U+10ffff - * - * This means that all code points below U+d800 are character code points, - * and that boundary is tested first for performance. - * - * @param c 32-bit code point - * @return TRUE or FALSE - * @stable ICU 2.4 - */ -#define U_IS_UNICODE_CHAR(c) \ - ((uint32_t)(c)<0xd800 || \ - ((uint32_t)(c)>0xdfff && \ - (uint32_t)(c)<=0x10ffff && \ - !U_IS_UNICODE_NONCHAR(c))) - -#ifndef U_HIDE_DRAFT_API - -/** - * Is this code point a BMP code point (U+0000..U+ffff)? - * @param c 32-bit code point - * @return TRUE or FALSE - * @draft ICU 2.8 - */ -#define U_IS_BMP(c) ((uint32_t)(c)<=0xffff) - -/** - * Is this code point a supplementary code point (U+10000..U+10ffff)? - * @param c 32-bit code point - * @return TRUE or FALSE - * @draft ICU 2.8 - */ -#define U_IS_SUPPLEMENTARY(c) ((uint32_t)((c)-0x10000)<=0xfffff) - -#endif /*U_HIDE_DRAFT_API*/ - -/** - * Is this code point a lead surrogate (U+d800..U+dbff)? - * @param c 32-bit code point - * @return TRUE or FALSE - * @stable ICU 2.4 - */ -#define U_IS_LEAD(c) (((c)&0xfffffc00)==0xd800) - -/** - * Is this code point a trail surrogate (U+dc00..U+dfff)? - * @param c 32-bit code point - * @return TRUE or FALSE - * @stable ICU 2.4 - */ -#define U_IS_TRAIL(c) (((c)&0xfffffc00)==0xdc00) - -/** - * Is this code point a surrogate (U+d800..U+dfff)? - * @param c 32-bit code point - * @return TRUE or FALSE - * @stable ICU 2.4 - */ -#define U_IS_SURROGATE(c) (((c)&0xfffff800)==0xd800) - -/** - * Assuming c is a surrogate code point (U_IS_SURROGATE(c)), - * is it a lead surrogate? - * @param c 32-bit code point - * @return TRUE or FALSE - * @stable ICU 2.4 - */ -#define U_IS_SURROGATE_LEAD(c) (((c)&0x400)==0) - -/* include the utfXX.h ------------------------------------------------------ */ - -#include "unicode/utf8.h" -#include "unicode/utf16.h" - -/* utf_old.h contains deprecated, pre-ICU 2.4 definitions */ -#include "unicode/utf_old.h" - -#endif diff --git a/WebKit/mac/icu/unicode/utf16.h b/WebKit/mac/icu/unicode/utf16.h deleted file mode 100644 index 7bf3872..0000000 --- a/WebKit/mac/icu/unicode/utf16.h +++ /dev/null @@ -1,605 +0,0 @@ -/* -******************************************************************************* -* -* Copyright (C) 1999-2004, International Business Machines -* Corporation and others. All Rights Reserved. -* -******************************************************************************* -* file name: utf16.h -* encoding: US-ASCII -* tab size: 8 (not used) -* indentation:4 -* -* created on: 1999sep09 -* created by: Markus W. Scherer -*/ - -/** - * \file - * \brief C API: 16-bit Unicode handling macros - * - * This file defines macros to deal with 16-bit Unicode (UTF-16) code units and strings. - * utf16.h is included by utf.h after unicode/umachine.h - * and some common definitions. - * - * For more information see utf.h and the ICU User Guide Strings chapter - * (http://oss.software.ibm.com/icu/userguide/). - * - * <em>Usage:</em> - * ICU coding guidelines for if() statements should be followed when using these macros. - * Compound statements (curly braces {}) must be used for if-else-while... - * bodies and all macro statements should be terminated with semicolon. - */ - -#ifndef __UTF16_H__ -#define __UTF16_H__ - -/* utf.h must be included first. */ -#ifndef __UTF_H__ -# include "unicode/utf.h" -#endif - -/* single-code point definitions -------------------------------------------- */ - -/** - * Does this code unit alone encode a code point (BMP, not a surrogate)? - * @param c 16-bit code unit - * @return TRUE or FALSE - * @stable ICU 2.4 - */ -#define U16_IS_SINGLE(c) !U_IS_SURROGATE(c) - -/** - * Is this code unit a lead surrogate (U+d800..U+dbff)? - * @param c 16-bit code unit - * @return TRUE or FALSE - * @stable ICU 2.4 - */ -#define U16_IS_LEAD(c) (((c)&0xfffffc00)==0xd800) - -/** - * Is this code unit a trail surrogate (U+dc00..U+dfff)? - * @param c 16-bit code unit - * @return TRUE or FALSE - * @stable ICU 2.4 - */ -#define U16_IS_TRAIL(c) (((c)&0xfffffc00)==0xdc00) - -/** - * Is this code unit a surrogate (U+d800..U+dfff)? - * @param c 16-bit code unit - * @return TRUE or FALSE - * @stable ICU 2.4 - */ -#define U16_IS_SURROGATE(c) U_IS_SURROGATE(c) - -/** - * Assuming c is a surrogate code point (U16_IS_SURROGATE(c)), - * is it a lead surrogate? - * @param c 16-bit code unit - * @return TRUE or FALSE - * @stable ICU 2.4 - */ -#define U16_IS_SURROGATE_LEAD(c) (((c)&0x400)==0) - -/** - * Helper constant for U16_GET_SUPPLEMENTARY. - * @internal - */ -#define U16_SURROGATE_OFFSET ((0xd800<<10UL)+0xdc00-0x10000) - -/** - * Get a supplementary code point value (U+10000..U+10ffff) - * from its lead and trail surrogates. - * The result is undefined if the input values are not - * lead and trail surrogates. - * - * @param lead lead surrogate (U+d800..U+dbff) - * @param trail trail surrogate (U+dc00..U+dfff) - * @return supplementary code point (U+10000..U+10ffff) - * @stable ICU 2.4 - */ -#define U16_GET_SUPPLEMENTARY(lead, trail) \ - (((UChar32)(lead)<<10UL)+(UChar32)(trail)-U16_SURROGATE_OFFSET) - - -/** - * Get the lead surrogate (0xd800..0xdbff) for a - * supplementary code point (0x10000..0x10ffff). - * @param supplementary 32-bit code point (U+10000..U+10ffff) - * @return lead surrogate (U+d800..U+dbff) for supplementary - * @stable ICU 2.4 - */ -#define U16_LEAD(supplementary) (UChar)(((supplementary)>>10)+0xd7c0) - -/** - * Get the trail surrogate (0xdc00..0xdfff) for a - * supplementary code point (0x10000..0x10ffff). - * @param supplementary 32-bit code point (U+10000..U+10ffff) - * @return trail surrogate (U+dc00..U+dfff) for supplementary - * @stable ICU 2.4 - */ -#define U16_TRAIL(supplementary) (UChar)(((supplementary)&0x3ff)|0xdc00) - -/** - * How many 16-bit code units are used to encode this Unicode code point? (1 or 2) - * The result is not defined if c is not a Unicode code point (U+0000..U+10ffff). - * @param c 32-bit code point - * @return 1 or 2 - * @stable ICU 2.4 - */ -#define U16_LENGTH(c) ((uint32_t)(c)<=0xffff ? 1 : 2) - -/** - * The maximum number of 16-bit code units per Unicode code point (U+0000..U+10ffff). - * @return 2 - * @stable ICU 2.4 - */ -#define U16_MAX_LENGTH 2 - -/** - * Get a code point from a string at a random-access offset, - * without changing the offset. - * "Unsafe" macro, assumes well-formed UTF-16. - * - * The offset may point to either the lead or trail surrogate unit - * for a supplementary code point, in which case the macro will read - * the adjacent matching surrogate as well. - * The result is undefined if the offset points to a single, unpaired surrogate. - * Iteration through a string is more efficient with U16_NEXT_UNSAFE or U16_NEXT. - * - * @param s const UChar * string - * @param i string offset - * @param c output UChar32 variable - * @see U16_GET - * @stable ICU 2.4 - */ -#define U16_GET_UNSAFE(s, i, c) { \ - (c)=(s)[i]; \ - if(U16_IS_SURROGATE(c)) { \ - if(U16_IS_SURROGATE_LEAD(c)) { \ - (c)=U16_GET_SUPPLEMENTARY((c), (s)[(i)+1]); \ - } else { \ - (c)=U16_GET_SUPPLEMENTARY((s)[(i)-1], (c)); \ - } \ - } \ -} - -/** - * Get a code point from a string at a random-access offset, - * without changing the offset. - * "Safe" macro, handles unpaired surrogates and checks for string boundaries. - * - * The offset may point to either the lead or trail surrogate unit - * for a supplementary code point, in which case the macro will read - * the adjacent matching surrogate as well. - * If the offset points to a single, unpaired surrogate, then that itself - * will be returned as the code point. - * Iteration through a string is more efficient with U16_NEXT_UNSAFE or U16_NEXT. - * - * @param s const UChar * string - * @param start starting string offset (usually 0) - * @param i string offset, start<=i<length - * @param length string length - * @param c output UChar32 variable - * @see U16_GET_UNSAFE - * @stable ICU 2.4 - */ -#define U16_GET(s, start, i, length, c) { \ - (c)=(s)[i]; \ - if(U16_IS_SURROGATE(c)) { \ - uint16_t __c2; \ - if(U16_IS_SURROGATE_LEAD(c)) { \ - if((i)+1<(length) && U16_IS_TRAIL(__c2=(s)[(i)+1])) { \ - (c)=U16_GET_SUPPLEMENTARY((c), __c2); \ - } \ - } else { \ - if((i)-1>=(start) && U16_IS_LEAD(__c2=(s)[(i)-1])) { \ - (c)=U16_GET_SUPPLEMENTARY(__c2, (c)); \ - } \ - } \ - } \ -} - -/* definitions with forward iteration --------------------------------------- */ - -/** - * Get a code point from a string at a code point boundary offset, - * and advance the offset to the next code point boundary. - * (Post-incrementing forward iteration.) - * "Unsafe" macro, assumes well-formed UTF-16. - * - * The offset may point to the lead surrogate unit - * for a supplementary code point, in which case the macro will read - * the following trail surrogate as well. - * If the offset points to a trail surrogate, then that itself - * will be returned as the code point. - * The result is undefined if the offset points to a single, unpaired lead surrogate. - * - * @param s const UChar * string - * @param i string offset - * @param c output UChar32 variable - * @see U16_NEXT - * @stable ICU 2.4 - */ -#define U16_NEXT_UNSAFE(s, i, c) { \ - (c)=(s)[(i)++]; \ - if(U16_IS_LEAD(c)) { \ - (c)=U16_GET_SUPPLEMENTARY((c), (s)[(i)++]); \ - } \ -} - -/** - * Get a code point from a string at a code point boundary offset, - * and advance the offset to the next code point boundary. - * (Post-incrementing forward iteration.) - * "Safe" macro, handles unpaired surrogates and checks for string boundaries. - * - * The offset may point to the lead surrogate unit - * for a supplementary code point, in which case the macro will read - * the following trail surrogate as well. - * If the offset points to a trail surrogate or - * to a single, unpaired lead surrogate, then that itself - * will be returned as the code point. - * - * @param s const UChar * string - * @param i string offset, i<length - * @param length string length - * @param c output UChar32 variable - * @see U16_NEXT_UNSAFE - * @stable ICU 2.4 - */ -#define U16_NEXT(s, i, length, c) { \ - (c)=(s)[(i)++]; \ - if(U16_IS_LEAD(c)) { \ - uint16_t __c2; \ - if((i)<(length) && U16_IS_TRAIL(__c2=(s)[(i)])) { \ - ++(i); \ - (c)=U16_GET_SUPPLEMENTARY((c), __c2); \ - } \ - } \ -} - -/** - * Append a code point to a string, overwriting 1 or 2 code units. - * The offset points to the current end of the string contents - * and is advanced (post-increment). - * "Unsafe" macro, assumes a valid code point and sufficient space in the string. - * Otherwise, the result is undefined. - * - * @param s const UChar * string buffer - * @param i string offset - * @param c code point to append - * @see U16_APPEND - * @stable ICU 2.4 - */ -#define U16_APPEND_UNSAFE(s, i, c) { \ - if((uint32_t)(c)<=0xffff) { \ - (s)[(i)++]=(uint16_t)(c); \ - } else { \ - (s)[(i)++]=(uint16_t)(((c)>>10)+0xd7c0); \ - (s)[(i)++]=(uint16_t)(((c)&0x3ff)|0xdc00); \ - } \ -} - -/** - * Append a code point to a string, overwriting 1 or 2 code units. - * The offset points to the current end of the string contents - * and is advanced (post-increment). - * "Safe" macro, checks for a valid code point. - * If a surrogate pair is written, checks for sufficient space in the string. - * If the code point is not valid or a trail surrogate does not fit, - * then isError is set to TRUE. - * - * @param s const UChar * string buffer - * @param i string offset, i<length - * @param capacity size of the string buffer - * @param c code point to append - * @param isError output UBool set to TRUE if an error occurs, otherwise not modified - * @see U16_APPEND_UNSAFE - * @stable ICU 2.4 - */ -#define U16_APPEND(s, i, capacity, c, isError) { \ - if((uint32_t)(c)<=0xffff) { \ - (s)[(i)++]=(uint16_t)(c); \ - } else if((uint32_t)(c)<=0x10ffff && (i)+1<(capacity)) { \ - (s)[(i)++]=(uint16_t)(((c)>>10)+0xd7c0); \ - (s)[(i)++]=(uint16_t)(((c)&0x3ff)|0xdc00); \ - } else /* c>0x10ffff or not enough space */ { \ - (isError)=TRUE; \ - } \ -} - -/** - * Advance the string offset from one code point boundary to the next. - * (Post-incrementing iteration.) - * "Unsafe" macro, assumes well-formed UTF-16. - * - * @param s const UChar * string - * @param i string offset - * @see U16_FWD_1 - * @stable ICU 2.4 - */ -#define U16_FWD_1_UNSAFE(s, i) { \ - if(U16_IS_LEAD((s)[(i)++])) { \ - ++(i); \ - } \ -} - -/** - * Advance the string offset from one code point boundary to the next. - * (Post-incrementing iteration.) - * "Safe" macro, handles unpaired surrogates and checks for string boundaries. - * - * @param s const UChar * string - * @param i string offset, i<length - * @param length string length - * @see U16_FWD_1_UNSAFE - * @stable ICU 2.4 - */ -#define U16_FWD_1(s, i, length) { \ - if(U16_IS_LEAD((s)[(i)++]) && (i)<(length) && U16_IS_TRAIL((s)[i])) { \ - ++(i); \ - } \ -} - -/** - * Advance the string offset from one code point boundary to the n-th next one, - * i.e., move forward by n code points. - * (Post-incrementing iteration.) - * "Unsafe" macro, assumes well-formed UTF-16. - * - * @param s const UChar * string - * @param i string offset - * @param n number of code points to skip - * @see U16_FWD_N - * @stable ICU 2.4 - */ -#define U16_FWD_N_UNSAFE(s, i, n) { \ - int32_t __N=(n); \ - while(__N>0) { \ - U16_FWD_1_UNSAFE(s, i); \ - --__N; \ - } \ -} - -/** - * Advance the string offset from one code point boundary to the n-th next one, - * i.e., move forward by n code points. - * (Post-incrementing iteration.) - * "Safe" macro, handles unpaired surrogates and checks for string boundaries. - * - * @param s const UChar * string - * @param i string offset, i<length - * @param length string length - * @param n number of code points to skip - * @see U16_FWD_N_UNSAFE - * @stable ICU 2.4 - */ -#define U16_FWD_N(s, i, length, n) { \ - int32_t __N=(n); \ - while(__N>0 && (i)<(length)) { \ - U16_FWD_1(s, i, length); \ - --__N; \ - } \ -} - -/** - * Adjust a random-access offset to a code point boundary - * at the start of a code point. - * If the offset points to the trail surrogate of a surrogate pair, - * then the offset is decremented. - * Otherwise, it is not modified. - * "Unsafe" macro, assumes well-formed UTF-16. - * - * @param s const UChar * string - * @param i string offset - * @see U16_SET_CP_START - * @stable ICU 2.4 - */ -#define U16_SET_CP_START_UNSAFE(s, i) { \ - if(U16_IS_TRAIL((s)[i])) { \ - --(i); \ - } \ -} - -/** - * Adjust a random-access offset to a code point boundary - * at the start of a code point. - * If the offset points to the trail surrogate of a surrogate pair, - * then the offset is decremented. - * Otherwise, it is not modified. - * "Safe" macro, handles unpaired surrogates and checks for string boundaries. - * - * @param s const UChar * string - * @param start starting string offset (usually 0) - * @param i string offset, start<=i - * @see U16_SET_CP_START_UNSAFE - * @stable ICU 2.4 - */ -#define U16_SET_CP_START(s, start, i) { \ - if(U16_IS_TRAIL((s)[i]) && (i)>(start) && U16_IS_LEAD((s)[(i)-1])) { \ - --(i); \ - } \ -} - -/* definitions with backward iteration -------------------------------------- */ - -/** - * Move the string offset from one code point boundary to the previous one - * and get the code point between them. - * (Pre-decrementing backward iteration.) - * "Unsafe" macro, assumes well-formed UTF-16. - * - * The input offset may be the same as the string length. - * If the offset is behind a trail surrogate unit - * for a supplementary code point, then the macro will read - * the preceding lead surrogate as well. - * If the offset is behind a lead surrogate, then that itself - * will be returned as the code point. - * The result is undefined if the offset is behind a single, unpaired trail surrogate. - * - * @param s const UChar * string - * @param i string offset - * @param c output UChar32 variable - * @see U16_PREV - * @stable ICU 2.4 - */ -#define U16_PREV_UNSAFE(s, i, c) { \ - (c)=(s)[--(i)]; \ - if(U16_IS_TRAIL(c)) { \ - (c)=U16_GET_SUPPLEMENTARY((s)[--(i)], (c)); \ - } \ -} - -/** - * Move the string offset from one code point boundary to the previous one - * and get the code point between them. - * (Pre-decrementing backward iteration.) - * "Safe" macro, handles unpaired surrogates and checks for string boundaries. - * - * The input offset may be the same as the string length. - * If the offset is behind a trail surrogate unit - * for a supplementary code point, then the macro will read - * the preceding lead surrogate as well. - * If the offset is behind a lead surrogate or behind a single, unpaired - * trail surrogate, then that itself - * will be returned as the code point. - * - * @param s const UChar * string - * @param start starting string offset (usually 0) - * @param i string offset, start<=i - * @param c output UChar32 variable - * @see U16_PREV_UNSAFE - * @stable ICU 2.4 - */ -#define U16_PREV(s, start, i, c) { \ - (c)=(s)[--(i)]; \ - if(U16_IS_TRAIL(c)) { \ - uint16_t __c2; \ - if((i)>(start) && U16_IS_LEAD(__c2=(s)[(i)-1])) { \ - --(i); \ - (c)=U16_GET_SUPPLEMENTARY(__c2, (c)); \ - } \ - } \ -} - -/** - * Move the string offset from one code point boundary to the previous one. - * (Pre-decrementing backward iteration.) - * The input offset may be the same as the string length. - * "Unsafe" macro, assumes well-formed UTF-16. - * - * @param s const UChar * string - * @param i string offset - * @see U16_BACK_1 - * @stable ICU 2.4 - */ -#define U16_BACK_1_UNSAFE(s, i) { \ - if(U16_IS_TRAIL((s)[--(i)])) { \ - --(i); \ - } \ -} - -/** - * Move the string offset from one code point boundary to the previous one. - * (Pre-decrementing backward iteration.) - * The input offset may be the same as the string length. - * "Safe" macro, handles unpaired surrogates and checks for string boundaries. - * - * @param s const UChar * string - * @param start starting string offset (usually 0) - * @param i string offset, start<=i - * @see U16_BACK_1_UNSAFE - * @stable ICU 2.4 - */ -#define U16_BACK_1(s, start, i) { \ - if(U16_IS_TRAIL((s)[--(i)]) && (i)>(start) && U16_IS_LEAD((s)[(i)-1])) { \ - --(i); \ - } \ -} - -/** - * Move the string offset from one code point boundary to the n-th one before it, - * i.e., move backward by n code points. - * (Pre-decrementing backward iteration.) - * The input offset may be the same as the string length. - * "Unsafe" macro, assumes well-formed UTF-16. - * - * @param s const UChar * string - * @param i string offset - * @param n number of code points to skip - * @see U16_BACK_N - * @stable ICU 2.4 - */ -#define U16_BACK_N_UNSAFE(s, i, n) { \ - int32_t __N=(n); \ - while(__N>0) { \ - U16_BACK_1_UNSAFE(s, i); \ - --__N; \ - } \ -} - -/** - * Move the string offset from one code point boundary to the n-th one before it, - * i.e., move backward by n code points. - * (Pre-decrementing backward iteration.) - * The input offset may be the same as the string length. - * "Safe" macro, handles unpaired surrogates and checks for string boundaries. - * - * @param s const UChar * string - * @param start start of string - * @param i string offset, i<length - * @param n number of code points to skip - * @see U16_BACK_N_UNSAFE - * @stable ICU 2.4 - */ -#define U16_BACK_N(s, start, i, n) { \ - int32_t __N=(n); \ - while(__N>0 && (i)>(start)) { \ - U16_BACK_1(s, start, i); \ - --__N; \ - } \ -} - -/** - * Adjust a random-access offset to a code point boundary after a code point. - * If the offset is behind the lead surrogate of a surrogate pair, - * then the offset is incremented. - * Otherwise, it is not modified. - * The input offset may be the same as the string length. - * "Unsafe" macro, assumes well-formed UTF-16. - * - * @param s const UChar * string - * @param i string offset - * @see U16_SET_CP_LIMIT - * @stable ICU 2.4 - */ -#define U16_SET_CP_LIMIT_UNSAFE(s, i) { \ - if(U16_IS_LEAD((s)[(i)-1])) { \ - ++(i); \ - } \ -} - -/** - * Adjust a random-access offset to a code point boundary after a code point. - * If the offset is behind the lead surrogate of a surrogate pair, - * then the offset is incremented. - * Otherwise, it is not modified. - * The input offset may be the same as the string length. - * "Safe" macro, handles unpaired surrogates and checks for string boundaries. - * - * @param s const UChar * string - * @param start starting string offset (usually 0) - * @param i string offset, start<=i<=length - * @param length string length - * @see U16_SET_CP_LIMIT_UNSAFE - * @stable ICU 2.4 - */ -#define U16_SET_CP_LIMIT(s, start, i, length) { \ - if((start)<(i) && (i)<(length) && U16_IS_LEAD((s)[(i)-1]) && U16_IS_TRAIL((s)[i])) { \ - ++(i); \ - } \ -} - -#endif diff --git a/WebKit/mac/icu/unicode/utf8.h b/WebKit/mac/icu/unicode/utf8.h deleted file mode 100644 index f83662b..0000000 --- a/WebKit/mac/icu/unicode/utf8.h +++ /dev/null @@ -1,627 +0,0 @@ -/* -******************************************************************************* -* -* Copyright (C) 1999-2004, International Business Machines -* Corporation and others. All Rights Reserved. -* -******************************************************************************* -* file name: utf8.h -* encoding: US-ASCII -* tab size: 8 (not used) -* indentation:4 -* -* created on: 1999sep13 -* created by: Markus W. Scherer -*/ - -/** - * \file - * \brief C API: 8-bit Unicode handling macros - * - * This file defines macros to deal with 8-bit Unicode (UTF-8) code units (bytes) and strings. - * utf8.h is included by utf.h after unicode/umachine.h - * and some common definitions. - * - * For more information see utf.h and the ICU User Guide Strings chapter - * (http://oss.software.ibm.com/icu/userguide/). - * - * <em>Usage:</em> - * ICU coding guidelines for if() statements should be followed when using these macros. - * Compound statements (curly braces {}) must be used for if-else-while... - * bodies and all macro statements should be terminated with semicolon. - */ - -#ifndef __UTF8_H__ -#define __UTF8_H__ - -/* utf.h must be included first. */ -#ifndef __UTF_H__ -# include "unicode/utf.h" -#endif - -/* internal definitions ----------------------------------------------------- */ - -/** - * \var utf8_countTrailBytes - * Internal array with numbers of trail bytes for any given byte used in - * lead byte position. - * @internal - */ -#ifdef U_UTF8_IMPL -U_INTERNAL const uint8_t -#elif defined(U_STATIC_IMPLEMENTATION) -U_CFUNC const uint8_t -#else -U_CFUNC U_IMPORT const uint8_t /* U_IMPORT2? */ /*U_IMPORT*/ -#endif -utf8_countTrailBytes[256]; - -/** - * Count the trail bytes for a UTF-8 lead byte. - * @internal - */ -#define U8_COUNT_TRAIL_BYTES(leadByte) (utf8_countTrailBytes[(uint8_t)leadByte]) - -/** - * Mask a UTF-8 lead byte, leave only the lower bits that form part of the code point value. - * @internal - */ -#define U8_MASK_LEAD_BYTE(leadByte, countTrailBytes) ((leadByte)&=(1<<(6-(countTrailBytes)))-1) - -/** - * Function for handling "next code point" with error-checking. - * @internal - */ -U_INTERNAL UChar32 U_EXPORT2 -utf8_nextCharSafeBody(const uint8_t *s, int32_t *pi, int32_t length, UChar32 c, UBool strict); - -/** - * Function for handling "append code point" with error-checking. - * @internal - */ -U_INTERNAL int32_t U_EXPORT2 -utf8_appendCharSafeBody(uint8_t *s, int32_t i, int32_t length, UChar32 c, UBool *pIsError); - -/** - * Function for handling "previous code point" with error-checking. - * @internal - */ -U_INTERNAL UChar32 U_EXPORT2 -utf8_prevCharSafeBody(const uint8_t *s, int32_t start, int32_t *pi, UChar32 c, UBool strict); - -/** - * Function for handling "skip backward one code point" with error-checking. - * @internal - */ -U_INTERNAL int32_t U_EXPORT2 -utf8_back1SafeBody(const uint8_t *s, int32_t start, int32_t i); - -/* single-code point definitions -------------------------------------------- */ - -/** - * Does this code unit (byte) encode a code point by itself (US-ASCII 0..0x7f)? - * @param c 8-bit code unit (byte) - * @return TRUE or FALSE - * @stable ICU 2.4 - */ -#define U8_IS_SINGLE(c) (((c)&0x80)==0) - -/** - * Is this code unit (byte) a UTF-8 lead byte? - * @param c 8-bit code unit (byte) - * @return TRUE or FALSE - * @stable ICU 2.4 - */ -#define U8_IS_LEAD(c) ((uint8_t)((c)-0xc0)<0x3e) - -/** - * Is this code unit (byte) a UTF-8 trail byte? - * @param c 8-bit code unit (byte) - * @return TRUE or FALSE - * @stable ICU 2.4 - */ -#define U8_IS_TRAIL(c) (((c)&0xc0)==0x80) - -/** - * How many code units (bytes) are used for the UTF-8 encoding - * of this Unicode code point? - * @param c 32-bit code point - * @return 1..4, or 0 if c is a surrogate or not a Unicode code point - * @stable ICU 2.4 - */ -#define U8_LENGTH(c) \ - ((uint32_t)(c)<=0x7f ? 1 : \ - ((uint32_t)(c)<=0x7ff ? 2 : \ - ((uint32_t)(c)<=0xd7ff ? 3 : \ - ((uint32_t)(c)<=0xdfff || (uint32_t)(c)>0x10ffff ? 0 : \ - ((uint32_t)(c)<=0xffff ? 3 : 4)\ - ) \ - ) \ - ) \ - ) - -/** - * The maximum number of UTF-8 code units (bytes) per Unicode code point (U+0000..U+10ffff). - * @return 4 - * @stable ICU 2.4 - */ -#define U8_MAX_LENGTH 4 - -/** - * Get a code point from a string at a random-access offset, - * without changing the offset. - * The offset may point to either the lead byte or one of the trail bytes - * for a code point, in which case the macro will read all of the bytes - * for the code point. - * The result is undefined if the offset points to an illegal UTF-8 - * byte sequence. - * Iteration through a string is more efficient with U8_NEXT_UNSAFE or U8_NEXT. - * - * @param s const uint8_t * string - * @param i string offset - * @param c output UChar32 variable - * @see U8_GET - * @stable ICU 2.4 - */ -#define U8_GET_UNSAFE(s, i, c) { \ - int32_t _u8_get_unsafe_index=(int32_t)(i); \ - U8_SET_CP_START_UNSAFE(s, _u8_get_unsafe_index); \ - U8_NEXT_UNSAFE(s, _u8_get_unsafe_index, c); \ -} - -/** - * Get a code point from a string at a random-access offset, - * without changing the offset. - * The offset may point to either the lead byte or one of the trail bytes - * for a code point, in which case the macro will read all of the bytes - * for the code point. - * If the offset points to an illegal UTF-8 byte sequence, then - * c is set to a negative value. - * Iteration through a string is more efficient with U8_NEXT_UNSAFE or U8_NEXT. - * - * @param s const uint8_t * string - * @param start starting string offset - * @param i string offset, start<=i<length - * @param length string length - * @param c output UChar32 variable, set to <0 in case of an error - * @see U8_GET_UNSAFE - * @stable ICU 2.4 - */ -#define U8_GET(s, start, i, length, c) { \ - int32_t _u8_get_index=(int32_t)(i); \ - U8_SET_CP_START(s, start, _u8_get_index); \ - U8_NEXT(s, _u8_get_index, length, c); \ -} - -/* definitions with forward iteration --------------------------------------- */ - -/** - * Get a code point from a string at a code point boundary offset, - * and advance the offset to the next code point boundary. - * (Post-incrementing forward iteration.) - * "Unsafe" macro, assumes well-formed UTF-8. - * - * The offset may point to the lead byte of a multi-byte sequence, - * in which case the macro will read the whole sequence. - * The result is undefined if the offset points to a trail byte - * or an illegal UTF-8 sequence. - * - * @param s const uint8_t * string - * @param i string offset - * @param c output UChar32 variable - * @see U8_NEXT - * @stable ICU 2.4 - */ -#define U8_NEXT_UNSAFE(s, i, c) { \ - (c)=(s)[(i)++]; \ - if((uint8_t)((c)-0xc0)<0x35) { \ - uint8_t __count=U8_COUNT_TRAIL_BYTES(c); \ - U8_MASK_LEAD_BYTE(c, __count); \ - switch(__count) { \ - /* each following branch falls through to the next one */ \ - case 3: \ - (c)=((c)<<6)|((s)[(i)++]&0x3f); \ - case 2: \ - (c)=((c)<<6)|((s)[(i)++]&0x3f); \ - case 1: \ - (c)=((c)<<6)|((s)[(i)++]&0x3f); \ - /* no other branches to optimize switch() */ \ - break; \ - } \ - } \ -} - -/** - * Get a code point from a string at a code point boundary offset, - * and advance the offset to the next code point boundary. - * (Post-incrementing forward iteration.) - * "Safe" macro, checks for illegal sequences and for string boundaries. - * - * The offset may point to the lead byte of a multi-byte sequence, - * in which case the macro will read the whole sequence. - * If the offset points to a trail byte or an illegal UTF-8 sequence, then - * c is set to a negative value. - * - * @param s const uint8_t * string - * @param i string offset, i<length - * @param length string length - * @param c output UChar32 variable, set to <0 in case of an error - * @see U8_NEXT_UNSAFE - * @stable ICU 2.4 - */ -#define U8_NEXT(s, i, length, c) { \ - (c)=(s)[(i)++]; \ - if(((uint8_t)(c))>=0x80) { \ - if(U8_IS_LEAD(c)) { \ - (c)=utf8_nextCharSafeBody((const uint8_t *)s, &(i), (int32_t)(length), c, -1); \ - } else { \ - (c)=U_SENTINEL; \ - } \ - } \ -} - -/** - * Append a code point to a string, overwriting 1 to 4 bytes. - * The offset points to the current end of the string contents - * and is advanced (post-increment). - * "Unsafe" macro, assumes a valid code point and sufficient space in the string. - * Otherwise, the result is undefined. - * - * @param s const uint8_t * string buffer - * @param i string offset - * @param c code point to append - * @see U8_APPEND - * @stable ICU 2.4 - */ -#define U8_APPEND_UNSAFE(s, i, c) { \ - if((uint32_t)(c)<=0x7f) { \ - (s)[(i)++]=(uint8_t)(c); \ - } else { \ - if((uint32_t)(c)<=0x7ff) { \ - (s)[(i)++]=(uint8_t)(((c)>>6)|0xc0); \ - } else { \ - if((uint32_t)(c)<=0xffff) { \ - (s)[(i)++]=(uint8_t)(((c)>>12)|0xe0); \ - } else { \ - (s)[(i)++]=(uint8_t)(((c)>>18)|0xf0); \ - (s)[(i)++]=(uint8_t)((((c)>>12)&0x3f)|0x80); \ - } \ - (s)[(i)++]=(uint8_t)((((c)>>6)&0x3f)|0x80); \ - } \ - (s)[(i)++]=(uint8_t)(((c)&0x3f)|0x80); \ - } \ -} - -/** - * Append a code point to a string, overwriting 1 or 2 code units. - * The offset points to the current end of the string contents - * and is advanced (post-increment). - * "Safe" macro, checks for a valid code point. - * If a non-ASCII code point is written, checks for sufficient space in the string. - * If the code point is not valid or trail bytes do not fit, - * then isError is set to TRUE. - * - * @param s const uint8_t * string buffer - * @param i string offset, i<length - * @param length size of the string buffer - * @param c code point to append - * @param isError output UBool set to TRUE if an error occurs, otherwise not modified - * @see U8_APPEND_UNSAFE - * @stable ICU 2.4 - */ -#define U8_APPEND(s, i, length, c, isError) { \ - if((uint32_t)(c)<=0x7f) { \ - (s)[(i)++]=(uint8_t)(c); \ - } else { \ - (i)=utf8_appendCharSafeBody(s, (int32_t)(i), (int32_t)(length), c, &(isError)); \ - } \ -} - -/** - * Advance the string offset from one code point boundary to the next. - * (Post-incrementing iteration.) - * "Unsafe" macro, assumes well-formed UTF-8. - * - * @param s const uint8_t * string - * @param i string offset - * @see U8_FWD_1 - * @stable ICU 2.4 - */ -#define U8_FWD_1_UNSAFE(s, i) { \ - (i)+=1+U8_COUNT_TRAIL_BYTES((s)[i]); \ -} - -/** - * Advance the string offset from one code point boundary to the next. - * (Post-incrementing iteration.) - * "Safe" macro, checks for illegal sequences and for string boundaries. - * - * @param s const uint8_t * string - * @param i string offset, i<length - * @param length string length - * @see U8_FWD_1_UNSAFE - * @stable ICU 2.4 - */ -#define U8_FWD_1(s, i, length) { \ - uint8_t __b=(s)[(i)++]; \ - if(U8_IS_LEAD(__b)) { \ - uint8_t __count=U8_COUNT_TRAIL_BYTES(__b); \ - if((i)+__count>(length)) { \ - __count=(uint8_t)((length)-(i)); \ - } \ - while(__count>0 && U8_IS_TRAIL((s)[i])) { \ - ++(i); \ - --__count; \ - } \ - } \ -} - -/** - * Advance the string offset from one code point boundary to the n-th next one, - * i.e., move forward by n code points. - * (Post-incrementing iteration.) - * "Unsafe" macro, assumes well-formed UTF-8. - * - * @param s const uint8_t * string - * @param i string offset - * @param n number of code points to skip - * @see U8_FWD_N - * @stable ICU 2.4 - */ -#define U8_FWD_N_UNSAFE(s, i, n) { \ - int32_t __N=(n); \ - while(__N>0) { \ - U8_FWD_1_UNSAFE(s, i); \ - --__N; \ - } \ -} - -/** - * Advance the string offset from one code point boundary to the n-th next one, - * i.e., move forward by n code points. - * (Post-incrementing iteration.) - * "Safe" macro, checks for illegal sequences and for string boundaries. - * - * @param s const uint8_t * string - * @param i string offset, i<length - * @param length string length - * @param n number of code points to skip - * @see U8_FWD_N_UNSAFE - * @stable ICU 2.4 - */ -#define U8_FWD_N(s, i, length, n) { \ - int32_t __N=(n); \ - while(__N>0 && (i)<(length)) { \ - U8_FWD_1(s, i, length); \ - --__N; \ - } \ -} - -/** - * Adjust a random-access offset to a code point boundary - * at the start of a code point. - * If the offset points to a UTF-8 trail byte, - * then the offset is moved backward to the corresponding lead byte. - * Otherwise, it is not modified. - * "Unsafe" macro, assumes well-formed UTF-8. - * - * @param s const uint8_t * string - * @param i string offset - * @see U8_SET_CP_START - * @stable ICU 2.4 - */ -#define U8_SET_CP_START_UNSAFE(s, i) { \ - while(U8_IS_TRAIL((s)[i])) { --(i); } \ -} - -/** - * Adjust a random-access offset to a code point boundary - * at the start of a code point. - * If the offset points to a UTF-8 trail byte, - * then the offset is moved backward to the corresponding lead byte. - * Otherwise, it is not modified. - * "Safe" macro, checks for illegal sequences and for string boundaries. - * - * @param s const uint8_t * string - * @param start starting string offset (usually 0) - * @param i string offset, start<=i - * @see U8_SET_CP_START_UNSAFE - * @stable ICU 2.4 - */ -#define U8_SET_CP_START(s, start, i) { \ - if(U8_IS_TRAIL((s)[(i)])) { \ - (i)=utf8_back1SafeBody(s, start, (int32_t)(i)); \ - } \ -} - -/* definitions with backward iteration -------------------------------------- */ - -/** - * Move the string offset from one code point boundary to the previous one - * and get the code point between them. - * (Pre-decrementing backward iteration.) - * "Unsafe" macro, assumes well-formed UTF-8. - * - * The input offset may be the same as the string length. - * If the offset is behind a multi-byte sequence, then the macro will read - * the whole sequence. - * If the offset is behind a lead byte, then that itself - * will be returned as the code point. - * The result is undefined if the offset is behind an illegal UTF-8 sequence. - * - * @param s const uint8_t * string - * @param i string offset - * @param c output UChar32 variable - * @see U8_PREV - * @stable ICU 2.4 - */ -#define U8_PREV_UNSAFE(s, i, c) { \ - (c)=(s)[--(i)]; \ - if(U8_IS_TRAIL(c)) { \ - uint8_t __b, __count=1, __shift=6; \ -\ - /* c is a trail byte */ \ - (c)&=0x3f; \ - for(;;) { \ - __b=(s)[--(i)]; \ - if(__b>=0xc0) { \ - U8_MASK_LEAD_BYTE(__b, __count); \ - (c)|=(UChar32)__b<<__shift; \ - break; \ - } else { \ - (c)|=(UChar32)(__b&0x3f)<<__shift; \ - ++__count; \ - __shift+=6; \ - } \ - } \ - } \ -} - -/** - * Move the string offset from one code point boundary to the previous one - * and get the code point between them. - * (Pre-decrementing backward iteration.) - * "Safe" macro, checks for illegal sequences and for string boundaries. - * - * The input offset may be the same as the string length. - * If the offset is behind a multi-byte sequence, then the macro will read - * the whole sequence. - * If the offset is behind a lead byte, then that itself - * will be returned as the code point. - * If the offset is behind an illegal UTF-8 sequence, then c is set to a negative value. - * - * @param s const uint8_t * string - * @param start starting string offset (usually 0) - * @param i string offset, start<=i - * @param c output UChar32 variable, set to <0 in case of an error - * @see U8_PREV_UNSAFE - * @stable ICU 2.4 - */ -#define U8_PREV(s, start, i, c) { \ - (c)=(s)[--(i)]; \ - if((c)>=0x80) { \ - if((c)<=0xbf) { \ - (c)=utf8_prevCharSafeBody(s, start, &(i), c, -1); \ - } else { \ - (c)=U_SENTINEL; \ - } \ - } \ -} - -/** - * Move the string offset from one code point boundary to the previous one. - * (Pre-decrementing backward iteration.) - * The input offset may be the same as the string length. - * "Unsafe" macro, assumes well-formed UTF-8. - * - * @param s const uint8_t * string - * @param i string offset - * @see U8_BACK_1 - * @stable ICU 2.4 - */ -#define U8_BACK_1_UNSAFE(s, i) { \ - while(U8_IS_TRAIL((s)[--(i)])) {} \ -} - -/** - * Move the string offset from one code point boundary to the previous one. - * (Pre-decrementing backward iteration.) - * The input offset may be the same as the string length. - * "Safe" macro, checks for illegal sequences and for string boundaries. - * - * @param s const uint8_t * string - * @param start starting string offset (usually 0) - * @param i string offset, start<=i - * @see U8_BACK_1_UNSAFE - * @stable ICU 2.4 - */ -#define U8_BACK_1(s, start, i) { \ - if(U8_IS_TRAIL((s)[--(i)])) { \ - (i)=utf8_back1SafeBody(s, start, (int32_t)(i)); \ - } \ -} - -/** - * Move the string offset from one code point boundary to the n-th one before it, - * i.e., move backward by n code points. - * (Pre-decrementing backward iteration.) - * The input offset may be the same as the string length. - * "Unsafe" macro, assumes well-formed UTF-8. - * - * @param s const uint8_t * string - * @param i string offset - * @param n number of code points to skip - * @see U8_BACK_N - * @stable ICU 2.4 - */ -#define U8_BACK_N_UNSAFE(s, i, n) { \ - int32_t __N=(n); \ - while(__N>0) { \ - U8_BACK_1_UNSAFE(s, i); \ - --__N; \ - } \ -} - -/** - * Move the string offset from one code point boundary to the n-th one before it, - * i.e., move backward by n code points. - * (Pre-decrementing backward iteration.) - * The input offset may be the same as the string length. - * "Safe" macro, checks for illegal sequences and for string boundaries. - * - * @param s const uint8_t * string - * @param start index of the start of the string - * @param i string offset, i<length - * @param n number of code points to skip - * @see U8_BACK_N_UNSAFE - * @stable ICU 2.4 - */ -#define U8_BACK_N(s, start, i, n) { \ - int32_t __N=(n); \ - while(__N>0 && (i)>(start)) { \ - U8_BACK_1(s, start, i); \ - --__N; \ - } \ -} - -/** - * Adjust a random-access offset to a code point boundary after a code point. - * If the offset is behind a partial multi-byte sequence, - * then the offset is incremented to behind the whole sequence. - * Otherwise, it is not modified. - * The input offset may be the same as the string length. - * "Unsafe" macro, assumes well-formed UTF-8. - * - * @param s const uint8_t * string - * @param i string offset - * @see U8_SET_CP_LIMIT - * @stable ICU 2.4 - */ -#define U8_SET_CP_LIMIT_UNSAFE(s, i) { \ - U8_BACK_1_UNSAFE(s, i); \ - U8_FWD_1_UNSAFE(s, i); \ -} - -/** - * Adjust a random-access offset to a code point boundary after a code point. - * If the offset is behind a partial multi-byte sequence, - * then the offset is incremented to behind the whole sequence. - * Otherwise, it is not modified. - * The input offset may be the same as the string length. - * "Safe" macro, checks for illegal sequences and for string boundaries. - * - * @param s const uint8_t * string - * @param start starting string offset (usually 0) - * @param i string offset, start<=i<=length - * @param length string length - * @see U8_SET_CP_LIMIT_UNSAFE - * @stable ICU 2.4 - */ -#define U8_SET_CP_LIMIT(s, start, i, length) { \ - if((start)<(i) && (i)<(length)) { \ - U8_BACK_1(s, start, i); \ - U8_FWD_1(s, i, length); \ - } \ -} - -#endif diff --git a/WebKit/mac/icu/unicode/utf_old.h b/WebKit/mac/icu/unicode/utf_old.h deleted file mode 100644 index 8504a03..0000000 --- a/WebKit/mac/icu/unicode/utf_old.h +++ /dev/null @@ -1 +0,0 @@ -/* This file is intentionally left blank. */ diff --git a/WebKit/mac/icu/unicode/utypes.h b/WebKit/mac/icu/unicode/utypes.h deleted file mode 100644 index e20cd79..0000000 --- a/WebKit/mac/icu/unicode/utypes.h +++ /dev/null @@ -1,745 +0,0 @@ -/* -********************************************************************** -* Copyright (C) 1996-2004, International Business Machines -* Corporation and others. All Rights Reserved. -********************************************************************** -* -* FILE NAME : UTYPES.H (formerly ptypes.h) -* -* Date Name Description -* 12/11/96 helena Creation. -* 02/27/97 aliu Added typedefs for UClassID, int8, int16, int32, -* uint8, uint16, and uint32. -* 04/01/97 aliu Added XP_CPLUSPLUS and modified to work under C as -* well as C++. -* Modified to use memcpy() for uprv_arrayCopy() fns. -* 04/14/97 aliu Added TPlatformUtilities. -* 05/07/97 aliu Added import/export specifiers (replacing the old -* broken EXT_CLASS). Added version number for our -* code. Cleaned up header. -* 6/20/97 helena Java class name change. -* 08/11/98 stephen UErrorCode changed from typedef to enum -* 08/12/98 erm Changed T_ANALYTIC_PACKAGE_VERSION to 3 -* 08/14/98 stephen Added uprv_arrayCopy() for int8_t, int16_t, int32_t -* 12/09/98 jfitz Added BUFFER_OVERFLOW_ERROR (bug 1100066) -* 04/20/99 stephen Cleaned up & reworked for autoconf. -* Renamed to utypes.h. -* 05/05/99 stephen Changed to use <inttypes.h> -* 12/07/99 helena Moved copyright notice string from ucnv_bld.h here. -******************************************************************************* -*/ - -#ifndef UTYPES_H -#define UTYPES_H - - -#include "unicode/umachine.h" -#include "unicode/utf.h" -#include "unicode/uversion.h" -#include "unicode/uconfig.h" - -#ifdef U_HIDE_DRAFT_API -#include "unicode/udraft.h" -#endif - -#ifdef U_HIDE_DEPRECATED_API -#include "unicode/udeprctd.h" -#endif - -#ifdef U_HIDE_DEPRECATED_API -#include "unicode/uobslete.h" -#endif - - -/*! - * \file - * \brief Basic definitions for ICU, for both C and C++ APIs - * - * This file defines basic types, constants, and enumerations directly or - * indirectly by including other header files, especially utf.h for the - * basic character and string definitions and umachine.h for consistent - * integer and other types. - */ - -/*===========================================================================*/ -/* char Character set family */ -/*===========================================================================*/ - -/** - * U_CHARSET_FAMILY is equal to this value when the platform is an ASCII based platform. - * @stable ICU 2.0 - */ -#define U_ASCII_FAMILY 0 - -/** - * U_CHARSET_FAMILY is equal to this value when the platform is an EBCDIC based platform. - * @stable ICU 2.0 - */ -#define U_EBCDIC_FAMILY 1 - -/** - * \def U_CHARSET_FAMILY - * - * <p>These definitions allow to specify the encoding of text - * in the char data type as defined by the platform and the compiler. - * It is enough to determine the code point values of "invariant characters", - * which are the ones shared by all encodings that are in use - * on a given platform.</p> - * - * <p>Those "invariant characters" should be all the uppercase and lowercase - * latin letters, the digits, the space, and "basic punctuation". - * Also, '\\n', '\\r', '\\t' should be available.</p> - * - * <p>The list of "invariant characters" is:<br> - * \code - * A-Z a-z 0-9 SPACE " % & ' ( ) * + , - . / : ; < = > ? _ - * \endcode - * <br> - * (52 letters + 10 numbers + 20 punc/sym/space = 82 total)</p> - * - * <p>This matches the IBM Syntactic Character Set (CS 640).</p> - * - * <p>In other words, all the graphic characters in 7-bit ASCII should - * be safely accessible except the following:</p> - * - * \code - * '\' <backslash> - * '[' <left bracket> - * ']' <right bracket> - * '{' <left brace> - * '}' <right brace> - * '^' <circumflex> - * '~' <tilde> - * '!' <exclamation mark> - * '#' <number sign> - * '|' <vertical line> - * '$' <dollar sign> - * '@' <commercial at> - * '`' <grave accent> - * \endcode - * @stable ICU 2.0 - */ - -#ifndef U_CHARSET_FAMILY -# define U_CHARSET_FAMILY 0 -#endif - -/*===========================================================================*/ -/* ICUDATA naming scheme */ -/*===========================================================================*/ - -/** - * \def U_ICUDATA_TYPE_LETTER - * - * This is a platform-dependent string containing one letter: - * - b for big-endian, ASCII-family platforms - * - l for little-endian, ASCII-family platforms - * - e for big-endian, EBCDIC-family platforms - * This letter is part of the common data file name. - * @stable ICU 2.0 - */ - -/** - * \def U_ICUDATA_TYPE_LITLETTER - * The non-string form of U_ICUDATA_TYPE_LETTER - * @stable ICU 2.0 - */ -#if U_CHARSET_FAMILY -# if U_IS_BIG_ENDIAN - /* EBCDIC - should always be BE */ -# define U_ICUDATA_TYPE_LETTER "e" -# define U_ICUDATA_TYPE_LITLETTER e -# else -# error "Don't know what to do with little endian EBCDIC!" -# define U_ICUDATA_TYPE_LETTER "x" -# define U_ICUDATA_TYPE_LITLETTER x -# endif -#else -# if U_IS_BIG_ENDIAN - /* Big-endian ASCII */ -# define U_ICUDATA_TYPE_LETTER "b" -# define U_ICUDATA_TYPE_LITLETTER b -# else - /* Little-endian ASCII */ -# define U_ICUDATA_TYPE_LETTER "l" -# define U_ICUDATA_TYPE_LITLETTER l -# endif -#endif - -/** - * A single string literal containing the icudata stub name. i.e. 'icudt18e' for - * ICU 1.8.x on EBCDIC, etc.. - * @stable ICU 2.0 - */ -#define U_ICUDATA_NAME "icudt" U_ICU_VERSION_SHORT U_ICUDATA_TYPE_LETTER - - -/** - * U_ICU_ENTRY_POINT is the name of the DLL entry point to the ICU data library. - * Defined as a literal, not a string. - * Tricky Preprocessor use - ## operator replaces macro paramters with the literal string - * from the corresponding macro invocation, _before_ other macro substitutions. - * Need a nested #defines to get the actual version numbers rather than - * the literal text U_ICU_VERSION_MAJOR_NUM into the name. - * The net result will be something of the form - * #define U_ICU_ENTRY_POINT icudt19_dat - * @stable ICU 2.4 - */ -#define U_ICUDATA_ENTRY_POINT U_DEF2_ICUDATA_ENTRY_POINT(U_ICU_VERSION_MAJOR_NUM, U_ICU_VERSION_MINOR_NUM) -/** - * @internal - */ -#define U_DEF2_ICUDATA_ENTRY_POINT(major, minor) U_DEF_ICUDATA_ENTRY_POINT(major, minor) -/** - * @internal - */ -#define U_DEF_ICUDATA_ENTRY_POINT(major, minor) icudt##major##minor##_dat - -/** - * \def U_CALLCONV - * Similar to U_CDECL_BEGIN/U_CDECL_END, this qualifier is necessary - * in callback function typedefs to make sure that the calling convention - * is compatible. - * - * This is only used for non-ICU-API functions. - * When a function is a public ICU API, - * you must use the U_CAPI and U_EXPORT2 qualifiers. - * @stable ICU 2.0 - */ -#if defined(OS390) && (__COMPILER_VER__ < 0x41020000) && defined(XP_CPLUSPLUS) -# define U_CALLCONV __cdecl -#else -# define U_CALLCONV U_EXPORT2 -#endif - -/** - * \def NULL - * Define NULL if necessary, to 0 for C++ and to ((void *)0) for C. - * @stable ICU 2.0 - */ -#ifndef NULL -#ifdef XP_CPLUSPLUS -#define NULL 0 -#else -#define NULL ((void *)0) -#endif -#endif - -/*===========================================================================*/ -/* Calendar/TimeZone data types */ -/*===========================================================================*/ - -/** - * Date and Time data type. - * This is a primitive data type that holds the date and time - * as the number of milliseconds since 1970-jan-01, 00:00 UTC. - * UTC leap seconds are ignored. - * @stable ICU 2.0 - */ -typedef double UDate; - -/** The number of milliseconds per second @stable ICU 2.0 */ -#define U_MILLIS_PER_SECOND (1000) -/** The number of milliseconds per minute @stable ICU 2.0 */ -#define U_MILLIS_PER_MINUTE (60000) -/** The number of milliseconds per hour @stable ICU 2.0 */ -#define U_MILLIS_PER_HOUR (3600000) -/** The number of milliseconds per day @stable ICU 2.0 */ -#define U_MILLIS_PER_DAY (86400000) - - -/*===========================================================================*/ -/* UClassID-based RTTI */ -/*===========================================================================*/ - -/** - * UClassID is used to identify classes without using RTTI, since RTTI - * is not yet supported by all C++ compilers. Each class hierarchy which needs - * to implement polymorphic clone() or operator==() defines two methods, - * described in detail below. UClassID values can be compared using - * operator==(). Nothing else should be done with them. - * - * \par - * getDynamicClassID() is declared in the base class of the hierarchy as - * a pure virtual. Each concrete subclass implements it in the same way: - * - * \code - * class Base { - * public: - * virtual UClassID getDynamicClassID() const = 0; - * } - * - * class Derived { - * public: - * virtual UClassID getDynamicClassID() const - * { return Derived::getStaticClassID(); } - * } - * \endcode - * - * Each concrete class implements getStaticClassID() as well, which allows - * clients to test for a specific type. - * - * \code - * class Derived { - * public: - * static UClassID U_EXPORT2 getStaticClassID(); - * private: - * static char fgClassID; - * } - * - * // In Derived.cpp: - * UClassID Derived::getStaticClassID() - * { return (UClassID)&Derived::fgClassID; } - * char Derived::fgClassID = 0; // Value is irrelevant - * \endcode - * @stable ICU 2.0 - */ -typedef void* UClassID; - -/*===========================================================================*/ -/* Shared library/DLL import-export API control */ -/*===========================================================================*/ - -/* - * Control of symbol import/export. - * ICU is separated into three libraries. - */ - -/* - * \def U_COMBINED_IMPLEMENTATION - * Set to export library symbols from inside the ICU library - * when all of ICU is in a single library. - * This can be set as a compiler option while building ICU, and it - * needs to be the first one tested to override U_COMMON_API, U_I18N_API, etc. - * @stable ICU 2.0 - */ - -/** - * \def U_DATA_API - * Set to export library symbols from inside the stubdata library, - * and to import them from outside. - * @draft ICU 3.0 - */ - -/** - * \def U_COMMON_API - * Set to export library symbols from inside the common library, - * and to import them from outside. - * @stable ICU 2.0 - */ - -/** - * \def U_I18N_API - * Set to export library symbols from inside the i18n library, - * and to import them from outside. - * @stable ICU 2.0 - */ - -/** - * \def U_LAYOUT_API - * Set to export library symbols from inside the layout engine library, - * and to import them from outside. - * @stable ICU 2.0 - */ - -/** - * \def U_LAYOUTEX_API - * Set to export library symbols from inside the layout extensions library, - * and to import them from outside. - * @stable ICU 2.6 - */ - -/** - * \def U_IO_API - * Set to export library symbols from inside the ustdio library, - * and to import them from outside. - * @stable ICU 2.0 - */ - -#if defined(U_COMBINED_IMPLEMENTATION) -#define U_DATA_API U_EXPORT -#define U_COMMON_API U_EXPORT -#define U_I18N_API U_EXPORT -#define U_LAYOUT_API U_EXPORT -#define U_LAYOUTEX_API U_EXPORT -#define U_IO_API U_EXPORT -#elif defined(U_STATIC_IMPLEMENTATION) -#define U_DATA_API -#define U_COMMON_API -#define U_I18N_API -#define U_LAYOUT_API -#define U_LAYOUTEX_API -#define U_IO_API -#elif defined(U_COMMON_IMPLEMENTATION) -#define U_DATA_API U_IMPORT -#define U_COMMON_API U_EXPORT -#define U_I18N_API U_IMPORT -#define U_LAYOUT_API U_IMPORT -#define U_LAYOUTEX_API U_IMPORT -#define U_IO_API U_IMPORT -#elif defined(U_I18N_IMPLEMENTATION) -#define U_DATA_API U_IMPORT -#define U_COMMON_API U_IMPORT -#define U_I18N_API U_EXPORT -#define U_LAYOUT_API U_IMPORT -#define U_LAYOUTEX_API U_IMPORT -#define U_IO_API U_IMPORT -#elif defined(U_LAYOUT_IMPLEMENTATION) -#define U_DATA_API U_IMPORT -#define U_COMMON_API U_IMPORT -#define U_I18N_API U_IMPORT -#define U_LAYOUT_API U_EXPORT -#define U_LAYOUTEX_API U_IMPORT -#define U_IO_API U_IMPORT -#elif defined(U_LAYOUTEX_IMPLEMENTATION) -#define U_DATA_API U_IMPORT -#define U_COMMON_API U_IMPORT -#define U_I18N_API U_IMPORT -#define U_LAYOUT_API U_IMPORT -#define U_LAYOUTEX_API U_EXPORT -#define U_IO_API U_IMPORT -#elif defined(U_IO_IMPLEMENTATION) -#define U_DATA_API U_IMPORT -#define U_COMMON_API U_IMPORT -#define U_I18N_API U_IMPORT -#define U_LAYOUT_API U_IMPORT -#define U_LAYOUTEX_API U_IMPORT -#define U_IO_API U_EXPORT -#else -#define U_DATA_API U_IMPORT -#define U_COMMON_API U_IMPORT -#define U_I18N_API U_IMPORT -#define U_LAYOUT_API U_IMPORT -#define U_LAYOUTEX_API U_IMPORT -#define U_IO_API U_IMPORT -#endif - -/** - * \def U_STANDARD_CPP_NAMESPACE - * Control of C++ Namespace - * @stable ICU 2.0 - */ -#ifdef __cplusplus -#define U_STANDARD_CPP_NAMESPACE :: -#else -#define U_STANDARD_CPP_NAMESPACE -#endif - - -/*===========================================================================*/ -/* Global delete operator */ -/*===========================================================================*/ - -/* - * The ICU4C library must not use the global new and delete operators. - * These operators here are defined to enable testing for this. - * See Jitterbug 2581 for details of why this is necessary. - * - * Verification that ICU4C's memory usage is correct, i.e., - * that global new/delete are not used: - * - * a) Check for imports of global new/delete (see uobject.cpp for details) - * b) Verify that new is never imported. - * c) Verify that delete is only imported from object code for interface/mixin classes. - * d) Add global delete and delete[] only for the ICU4C library itself - * and define them in a way that crashes or otherwise easily shows a problem. - * - * The following implements d). - * The operator implementations crash; this is intentional and used for library debugging. - * - * Note: This is currently only done on Windows because - * some Linux/Unix compilers have problems with defining global new/delete. - * On Windows, WIN32 is defined, and it is _MSC_Ver>=1200 for MSVC 6.0 and higher. - */ -#if defined(XP_CPLUSPLUS) && defined(WIN32) && (_MSC_Ver>=1200) && (defined(U_COMMON_IMPLEMENTATION) || defined(U_I18N_IMPLEMENTATION) || defined(U_LAYOUT_IMPLEMENTATION) || defined(U_USTDIO_IMPLEMENTATION)) - -/** - * Global operator new, defined only inside ICU4C, must not be used. - * Crashes intentionally. - * @internal - */ -inline void * -operator new(size_t /*size*/) { - char *q=NULL; - *q=5; /* break it */ - return q; -} - -/** - * Global operator new[], defined only inside ICU4C, must not be used. - * Crashes intentionally. - * @internal - */ -inline void * -operator new[](size_t /*size*/) { - char *q=NULL; - *q=5; /* break it */ - return q; -} - -/** - * Global operator delete, defined only inside ICU4C, must not be used. - * Crashes intentionally. - * @internal - */ -inline void -operator delete(void * /*p*/) { - char *q=NULL; - *q=5; /* break it */ -} - -/** - * Global operator delete[], defined only inside ICU4C, must not be used. - * Crashes intentionally. - * @internal - */ -inline void -operator delete[](void * /*p*/) { - char *q=NULL; - *q=5; /* break it */ -} - -#endif - -/*===========================================================================*/ -/* UErrorCode */ -/*===========================================================================*/ - -/** - * Error code to replace exception handling, so that the code is compatible with all C++ compilers, - * and to use the same mechanism for C and C++. - * - * \par - * ICU functions that take a reference (C++) or a pointer (C) to a UErrorCode - * first test if(U_FAILURE(errorCode)) { return immediately; } - * so that in a chain of such functions the first one that sets an error code - * causes the following ones to not perform any operations. - * - * \par - * Error codes should be tested using U_FAILURE() and U_SUCCESS(). - * @stable ICU 2.0 - */ -typedef enum UErrorCode { - /* The ordering of U_ERROR_INFO_START Vs U_USING_FALLBACK_WARNING looks weird - * and is that way because VC++ debugger displays first encountered constant, - * which is not the what the code is used for - */ - - U_USING_FALLBACK_WARNING = -128, /**< A resource bundle lookup returned a fallback result (not an error) */ - - U_ERROR_WARNING_START = -128, /**< Start of information results (semantically successful) */ - - U_USING_DEFAULT_WARNING = -127, /**< A resource bundle lookup returned a result from the root locale (not an error) */ - - U_SAFECLONE_ALLOCATED_WARNING = -126, /**< A SafeClone operation required allocating memory (informational only) */ - - U_STATE_OLD_WARNING = -125, /**< ICU has to use compatibility layer to construct the service. Expect performance/memory usage degradation. Consider upgrading */ - - U_STRING_NOT_TERMINATED_WARNING = -124,/**< An output string could not be NUL-terminated because output length==destCapacity. */ - - U_SORT_KEY_TOO_SHORT_WARNING = -123, /**< Number of levels requested in getBound is higher than the number of levels in the sort key */ - - U_AMBIGUOUS_ALIAS_WARNING = -122, /**< This converter alias can go to different converter implementations */ - - U_DIFFERENT_UCA_VERSION = -121, /**< ucol_open encountered a mismatch between UCA version and collator image version, so the collator was constructed from rules. No impact to further function */ - - U_ERROR_WARNING_LIMIT, /**< This must always be the last warning value to indicate the limit for UErrorCode warnings (last warning code +1) */ - - - U_ZERO_ERROR = 0, /**< No error, no warning. */ - - U_ILLEGAL_ARGUMENT_ERROR = 1, /**< Start of codes indicating failure */ - U_MISSING_RESOURCE_ERROR = 2, /**< The requested resource cannot be found */ - U_INVALID_FORMAT_ERROR = 3, /**< Data format is not what is expected */ - U_FILE_ACCESS_ERROR = 4, /**< The requested file cannot be found */ - U_INTERNAL_PROGRAM_ERROR = 5, /**< Indicates a bug in the library code */ - U_MESSAGE_PARSE_ERROR = 6, /**< Unable to parse a message (message format) */ - U_MEMORY_ALLOCATION_ERROR = 7, /**< Memory allocation error */ - U_INDEX_OUTOFBOUNDS_ERROR = 8, /**< Trying to access the index that is out of bounds */ - U_PARSE_ERROR = 9, /**< Equivalent to Java ParseException */ - U_INVALID_CHAR_FOUND = 10, /**< Character conversion: Unmappable input sequence. In other APIs: Invalid character. */ - U_TRUNCATED_CHAR_FOUND = 11, /**< Character conversion: Incomplete input sequence. */ - U_ILLEGAL_CHAR_FOUND = 12, /**< Character conversion: Illegal input sequence/combination of input units.. */ - U_INVALID_TABLE_FORMAT = 13, /**< Conversion table file found, but corrupted */ - U_INVALID_TABLE_FILE = 14, /**< Conversion table file not found */ - U_BUFFER_OVERFLOW_ERROR = 15, /**< A result would not fit in the supplied buffer */ - U_UNSUPPORTED_ERROR = 16, /**< Requested operation not supported in current context */ - U_RESOURCE_TYPE_MISMATCH = 17, /**< an operation is requested over a resource that does not support it */ - U_ILLEGAL_ESCAPE_SEQUENCE = 18, /**< ISO-2022 illlegal escape sequence */ - U_UNSUPPORTED_ESCAPE_SEQUENCE = 19, /**< ISO-2022 unsupported escape sequence */ - U_NO_SPACE_AVAILABLE = 20, /**< No space available for in-buffer expansion for Arabic shaping */ - U_CE_NOT_FOUND_ERROR = 21, /**< Currently used only while setting variable top, but can be used generally */ - U_PRIMARY_TOO_LONG_ERROR = 22, /**< User tried to set variable top to a primary that is longer than two bytes */ - U_STATE_TOO_OLD_ERROR = 23, /**< ICU cannot construct a service from this state, as it is no longer supported */ - U_TOO_MANY_ALIASES_ERROR = 24, /**< There are too many aliases in the path to the requested resource. - It is very possible that a circular alias definition has occured */ - U_ENUM_OUT_OF_SYNC_ERROR = 25, /**< UEnumeration out of sync with underlying collection */ - U_INVARIANT_CONVERSION_ERROR = 26, /**< Unable to convert a UChar* string to char* with the invariant converter. */ - U_INVALID_STATE_ERROR = 27, /**< Requested operation can not be completed with ICU in its current state */ - U_COLLATOR_VERSION_MISMATCH = 28, /**< Collator version is not compatible with the base version */ - U_USELESS_COLLATOR_ERROR = 29, /**< Collator is options only and no base is specified */ - - U_STANDARD_ERROR_LIMIT, /**< This must always be the last value to indicate the limit for standard errors */ - /* - * the error code range 0x10000 0x10100 are reserved for Transliterator - */ - U_BAD_VARIABLE_DEFINITION=0x10000,/**< Missing '$' or duplicate variable name */ - U_PARSE_ERROR_START = 0x10000, /**< Start of Transliterator errors */ - U_MALFORMED_RULE, /**< Elements of a rule are misplaced */ - U_MALFORMED_SET, /**< A UnicodeSet pattern is invalid*/ - U_MALFORMED_SYMBOL_REFERENCE, /**< UNUSED as of ICU 2.4 */ - U_MALFORMED_UNICODE_ESCAPE, /**< A Unicode escape pattern is invalid*/ - U_MALFORMED_VARIABLE_DEFINITION, /**< A variable definition is invalid */ - U_MALFORMED_VARIABLE_REFERENCE, /**< A variable reference is invalid */ - U_MISMATCHED_SEGMENT_DELIMITERS, /**< UNUSED as of ICU 2.4 */ - U_MISPLACED_ANCHOR_START, /**< A start anchor appears at an illegal position */ - U_MISPLACED_CURSOR_OFFSET, /**< A cursor offset occurs at an illegal position */ - U_MISPLACED_QUANTIFIER, /**< A quantifier appears after a segment close delimiter */ - U_MISSING_OPERATOR, /**< A rule contains no operator */ - U_MISSING_SEGMENT_CLOSE, /**< UNUSED as of ICU 2.4 */ - U_MULTIPLE_ANTE_CONTEXTS, /**< More than one ante context */ - U_MULTIPLE_CURSORS, /**< More than one cursor */ - U_MULTIPLE_POST_CONTEXTS, /**< More than one post context */ - U_TRAILING_BACKSLASH, /**< A dangling backslash */ - U_UNDEFINED_SEGMENT_REFERENCE, /**< A segment reference does not correspond to a defined segment */ - U_UNDEFINED_VARIABLE, /**< A variable reference does not correspond to a defined variable */ - U_UNQUOTED_SPECIAL, /**< A special character was not quoted or escaped */ - U_UNTERMINATED_QUOTE, /**< A closing single quote is missing */ - U_RULE_MASK_ERROR, /**< A rule is hidden by an earlier more general rule */ - U_MISPLACED_COMPOUND_FILTER, /**< A compound filter is in an invalid location */ - U_MULTIPLE_COMPOUND_FILTERS, /**< More than one compound filter */ - U_INVALID_RBT_SYNTAX, /**< A "::id" rule was passed to the RuleBasedTransliterator parser */ - U_INVALID_PROPERTY_PATTERN, /**< UNUSED as of ICU 2.4 */ - U_MALFORMED_PRAGMA, /**< A 'use' pragma is invlalid */ - U_UNCLOSED_SEGMENT, /**< A closing ')' is missing */ - U_ILLEGAL_CHAR_IN_SEGMENT, /**< UNUSED as of ICU 2.4 */ - U_VARIABLE_RANGE_EXHAUSTED, /**< Too many stand-ins generated for the given variable range */ - U_VARIABLE_RANGE_OVERLAP, /**< The variable range overlaps characters used in rules */ - U_ILLEGAL_CHARACTER, /**< A special character is outside its allowed context */ - U_INTERNAL_TRANSLITERATOR_ERROR, /**< Internal transliterator system error */ - U_INVALID_ID, /**< A "::id" rule specifies an unknown transliterator */ - U_INVALID_FUNCTION, /**< A "&fn()" rule specifies an unknown transliterator */ - U_PARSE_ERROR_LIMIT, /**< The limit for Transliterator errors */ - - /* - * the error code range 0x10100 0x10200 are reserved for formatting API parsing error - */ - U_UNEXPECTED_TOKEN=0x10100, /**< Syntax error in format pattern */ - U_FMT_PARSE_ERROR_START=0x10100, /**< Start of format library errors */ - U_MULTIPLE_DECIMAL_SEPARATORS, /**< More than one decimal separator in number pattern */ - U_MULTIPLE_DECIMAL_SEPERATORS = U_MULTIPLE_DECIMAL_SEPARATORS, /**< Typo: kept for backward compatibility. Use U_MULTIPLE_DECIMAL_SEPARATORS */ - U_MULTIPLE_EXPONENTIAL_SYMBOLS, /**< More than one exponent symbol in number pattern */ - U_MALFORMED_EXPONENTIAL_PATTERN, /**< Grouping symbol in exponent pattern */ - U_MULTIPLE_PERCENT_SYMBOLS, /**< More than one percent symbol in number pattern */ - U_MULTIPLE_PERMILL_SYMBOLS, /**< More than one permill symbol in number pattern */ - U_MULTIPLE_PAD_SPECIFIERS, /**< More than one pad symbol in number pattern */ - U_PATTERN_SYNTAX_ERROR, /**< Syntax error in format pattern */ - U_ILLEGAL_PAD_POSITION, /**< Pad symbol misplaced in number pattern */ - U_UNMATCHED_BRACES, /**< Braces do not match in message pattern */ - U_UNSUPPORTED_PROPERTY, /**< UNUSED as of ICU 2.4 */ - U_UNSUPPORTED_ATTRIBUTE, /**< UNUSED as of ICU 2.4 */ - U_FMT_PARSE_ERROR_LIMIT, /**< The limit for format library errors */ - - /* - * the error code range 0x10200 0x102ff are reserved for Break Iterator related error - */ - U_BRK_ERROR_START=0x10200, /**< Start of codes indicating Break Iterator failures */ - U_BRK_INTERNAL_ERROR, /**< An internal error (bug) was detected. */ - U_BRK_HEX_DIGITS_EXPECTED, /**< Hex digits expected as part of a escaped char in a rule. */ - U_BRK_SEMICOLON_EXPECTED, /**< Missing ';' at the end of a RBBI rule. */ - U_BRK_RULE_SYNTAX, /**< Syntax error in RBBI rule. */ - U_BRK_UNCLOSED_SET, /**< UnicodeSet witing an RBBI rule missing a closing ']'. */ - U_BRK_ASSIGN_ERROR, /**< Syntax error in RBBI rule assignment statement. */ - U_BRK_VARIABLE_REDFINITION, /**< RBBI rule $Variable redefined. */ - U_BRK_MISMATCHED_PAREN, /**< Mis-matched parentheses in an RBBI rule. */ - U_BRK_NEW_LINE_IN_QUOTED_STRING, /**< Missing closing quote in an RBBI rule. */ - U_BRK_UNDEFINED_VARIABLE, /**< Use of an undefined $Variable in an RBBI rule. */ - U_BRK_INIT_ERROR, /**< Initialization failure. Probable missing ICU Data. */ - U_BRK_RULE_EMPTY_SET, /**< Rule contains an empty Unicode Set. */ - U_BRK_UNRECOGNIZED_OPTION, /**< !!option in RBBI rules not recognized. */ - U_BRK_MALFORMED_RULE_TAG, /**< The {nnn} tag on a rule is mal formed */ - U_BRK_ERROR_LIMIT, /**< This must always be the last value to indicate the limit for Break Iterator failures */ - - /* - * The error codes in the range 0x10300-0x103ff are reserved for regular expression related errrs - */ - U_REGEX_ERROR_START=0x10300, /**< Start of codes indicating Regexp failures */ - U_REGEX_INTERNAL_ERROR, /**< An internal error (bug) was detected. */ - U_REGEX_RULE_SYNTAX, /**< Syntax error in regexp pattern. */ - U_REGEX_INVALID_STATE, /**< RegexMatcher in invalid state for requested operation */ - U_REGEX_BAD_ESCAPE_SEQUENCE, /**< Unrecognized backslash escape sequence in pattern */ - U_REGEX_PROPERTY_SYNTAX, /**< Incorrect Unicode property */ - U_REGEX_UNIMPLEMENTED, /**< Use of regexp feature that is not yet implemented. */ - U_REGEX_MISMATCHED_PAREN, /**< Incorrectly nested parentheses in regexp pattern. */ - U_REGEX_NUMBER_TOO_BIG, /**< Decimal number is too large. */ - U_REGEX_BAD_INTERVAL, /**< Error in {min,max} interval */ - U_REGEX_MAX_LT_MIN, /**< In {min,max}, max is less than min. */ - U_REGEX_INVALID_BACK_REF, /**< Back-reference to a non-existent capture group. */ - U_REGEX_INVALID_FLAG, /**< Invalid value for match mode flags. */ - U_REGEX_LOOK_BEHIND_LIMIT, /**< Look-Behind pattern matches must have a bounded maximum length. */ - U_REGEX_SET_CONTAINS_STRING, /**< Regexps cannot have UnicodeSets containing strings.*/ - U_REGEX_ERROR_LIMIT, /**< This must always be the last value to indicate the limit for regexp errors */ - - /* - * The error code in the range 0x10400-0x104ff are reserved for IDNA related error codes - */ - U_IDNA_ERROR_START=0x10400, - U_IDNA_PROHIBITED_ERROR, - U_IDNA_UNASSIGNED_ERROR, - U_IDNA_CHECK_BIDI_ERROR, - U_IDNA_STD3_ASCII_RULES_ERROR, - U_IDNA_ACE_PREFIX_ERROR, - U_IDNA_VERIFICATION_ERROR, - U_IDNA_LABEL_TOO_LONG_ERROR, - U_IDNA_ERROR_LIMIT, - /* - * Aliases for StringPrep - */ - U_STRINGPREP_PROHIBITED_ERROR = U_IDNA_PROHIBITED_ERROR, - U_STRINGPREP_UNASSIGNED_ERROR = U_IDNA_UNASSIGNED_ERROR, - U_STRINGPREP_CHECK_BIDI_ERROR = U_IDNA_CHECK_BIDI_ERROR, - - - U_ERROR_LIMIT=U_IDNA_ERROR_LIMIT /**< This must always be the last value to indicate the limit for UErrorCode (last error code +1) */ -} UErrorCode; - -/* Use the following to determine if an UErrorCode represents */ -/* operational success or failure. */ - -#ifdef XP_CPLUSPLUS - /** - * Does the error code indicate success? - * @stable ICU 2.0 - */ - static - inline UBool U_SUCCESS(UErrorCode code) { return (UBool)(code<=U_ZERO_ERROR); } - /** - * Does the error code indicate a failure? - * @stable ICU 2.0 - */ - static - inline UBool U_FAILURE(UErrorCode code) { return (UBool)(code>U_ZERO_ERROR); } -#else - /** - * Does the error code indicate success? - * @stable ICU 2.0 - */ -# define U_SUCCESS(x) ((x)<=U_ZERO_ERROR) - /** - * Does the error code indicate a failure? - * @stable ICU 2.0 - */ -# define U_FAILURE(x) ((x)>U_ZERO_ERROR) -#endif - -/** - * Return a string for a UErrorCode value. - * The string will be the same as the name of the error code constant - * in the UErrorCode enum above. - * @stable ICU 2.0 - */ -U_STABLE const char * U_EXPORT2 -u_errorName(UErrorCode code); - - -#endif /* _UTYPES */ diff --git a/WebKit/mac/icu/unicode/uversion.h b/WebKit/mac/icu/unicode/uversion.h deleted file mode 100644 index f9a7755..0000000 --- a/WebKit/mac/icu/unicode/uversion.h +++ /dev/null @@ -1,216 +0,0 @@ -/* -******************************************************************************* -* Copyright (C) 2000-2004, International Business Machines -* Corporation and others. All Rights Reserved. -******************************************************************************* -* -* file name: uversion.h -* encoding: US-ASCII -* tab size: 8 (not used) -* indentation:4 -* -* Created by: Vladimir Weinstein -* -* Contains all the important version numbers for ICU. -* Gets included by utypes.h and Windows .rc files -*/ - -/*===========================================================================*/ -/* Main ICU version information */ -/*===========================================================================*/ - -#ifndef UVERSION_H -#define UVERSION_H - -/** IMPORTANT: When updating version, the following things need to be done: */ -/** source/common/unicode/uversion.h - this file: update major, minor, */ -/** patchlevel, suffix, version, short version constants, namespace, */ -/** and copyright */ -/** source/common/common.dsp - update 'Output file name' on the link tab so */ -/** that it contains the new major/minor combination */ -/** source/i18n/i18n.dsp - same as for the common.dsp */ -/** source/layout/layout.dsp - same as for the common.dsp */ -/** source/stubdata/stubdata.dsp - same as for the common.dsp */ -/** source/extra/ustdio/ustdio.dsp - same as for the common.dsp */ -/** source/data/makedata.mak - change U_ICUDATA_NAME so that it contains */ -/** the new major/minor combination */ -/** source/tools/genren/genren.pl - use this script according to the README */ -/** in that folder */ - -#include "unicode/umachine.h" - -/** The standard copyright notice that gets compiled into each library. - * This value will change in the subsequent releases of ICU - * @stable ICU 2.4 - */ -#define U_COPYRIGHT_STRING \ - " Copyright (C) 2004, International Business Machines Corporation and others. All Rights Reserved. " - -/** Maximum length of the copyright string. - * @stable ICU 2.4 - */ -#define U_COPYRIGHT_STRING_LENGTH 128 - -/** The current ICU major version as an integer. - * This value will change in the subsequent releases of ICU - * @stable ICU 2.4 - */ -#define U_ICU_VERSION_MAJOR_NUM 3 - -/** The current ICU minor version as an integer. - * This value will change in the subsequent releases of ICU - * @stable ICU 2.6 - */ -#define U_ICU_VERSION_MINOR_NUM 2 - -/** The current ICU patchlevel version as an integer. - * This value will change in the subsequent releases of ICU - * @stable ICU 2.4 - */ -#define U_ICU_VERSION_PATCHLEVEL_NUM 0 - -/** Glued version suffix for renamers - * This value will change in the subsequent releases of ICU - * @stable ICU 2.6 - */ -#define U_ICU_VERSION_SUFFIX _3_2 - -/** The current ICU library version as a dotted-decimal string. The patchlevel - * only appears in this string if it non-zero. - * This value will change in the subsequent releases of ICU - * @stable ICU 2.4 - */ -#define U_ICU_VERSION "3.2" - -/** The current ICU library major/minor version as a string without dots, for library name suffixes. - * This value will change in the subsequent releases of ICU - * @stable ICU 2.6 - */ -#define U_ICU_VERSION_SHORT "32" - -/** An ICU version consists of up to 4 numbers from 0..255. - * @stable ICU 2.4 - */ -#define U_MAX_VERSION_LENGTH 4 - -/** In a string, ICU version fields are delimited by dots. - * @stable ICU 2.4 - */ -#define U_VERSION_DELIMITER '.' - -/** The maximum length of an ICU version string. - * @stable ICU 2.4 - */ -#define U_MAX_VERSION_STRING_LENGTH 20 - -/** The binary form of a version on ICU APIs is an array of 4 uint8_t. - * @stable ICU 2.4 - */ -typedef uint8_t UVersionInfo[U_MAX_VERSION_LENGTH]; - -#if U_HAVE_NAMESPACE && defined(XP_CPLUSPLUS) -#if U_DISABLE_RENAMING -#define U_ICU_NAMESPACE icu -namespace U_ICU_NAMESPACE { } -#else -#define U_ICU_NAMESPACE icu_3_2 -namespace U_ICU_NAMESPACE { } -namespace icu = U_ICU_NAMESPACE; -#endif -U_NAMESPACE_USE -#endif - - -/*===========================================================================*/ -/* General version helper functions. Definitions in putil.c */ -/*===========================================================================*/ - -/** - * Parse a string with dotted-decimal version information and - * fill in a UVersionInfo structure with the result. - * Definition of this function lives in putil.c - * - * @param versionArray The destination structure for the version information. - * @param versionString A string with dotted-decimal version information, - * with up to four non-negative number fields with - * values of up to 255 each. - * @stable ICU 2.4 - */ -U_STABLE void U_EXPORT2 -u_versionFromString(UVersionInfo versionArray, const char *versionString); - -/** - * Write a string with dotted-decimal version information according - * to the input UVersionInfo. - * Definition of this function lives in putil.c - * - * @param versionArray The version information to be written as a string. - * @param versionString A string buffer that will be filled in with - * a string corresponding to the numeric version - * information in versionArray. - * The buffer size must be at least U_MAX_VERSION_STRING_LENGTH. - * @stable ICU 2.4 - */ -U_STABLE void U_EXPORT2 -u_versionToString(UVersionInfo versionArray, char *versionString); - -/** - * Gets the ICU release version. The version array stores the version information - * for ICU. For example, release "1.3.31.2" is then represented as 0x01031F02. - * Definition of this function lives in putil.c - * - * @param versionArray the version # information, the result will be filled in - * @stable ICU 2.0 - */ -U_STABLE void U_EXPORT2 -u_getVersion(UVersionInfo versionArray); - - -/*=========================================================================== - * ICU collation framework version information - * Version info that can be obtained from a collator is affected by these - * numbers in a secret and magic way. Please use collator version as whole - *=========================================================================== - */ - -/** Collation runtime version (sort key generator, strcoll). - * If the version is different, sortkeys for the same string could be different - * version 2 was in ICU 1.8.1. changed is: compression intervals, French secondary - * compression, generating quad level always when strength is quad or more - * version 4 - ICU 2.2 - tracking UCA changes, ignore completely ignorables - * in contractions, ignore primary ignorables after shifted - * version 5 - ICU 2.8 - changed implicit generation code - * This value may change in the subsequent releases of ICU - * @stable ICU 2.4 - */ -#define UCOL_RUNTIME_VERSION 5 - -/** Builder code version. When this is different, same tailoring might result - * in assigning different collation elements to code points - * version 2 was in ICU 1.8.1. added support for prefixes, tweaked canonical - * closure. However, the tailorings should probably get same CEs assigned - * version 5 - ICU 2.2 - fixed some bugs, renamed some indirect values. - * version 6 - ICU 2.8 - fixed bug in builder that allowed 0xFF in primary values - * Backward compatible with the old rules. - * This value may change in the subsequent releases of ICU - * @stable ICU 2.4 - */ -#define UCOL_BUILDER_VERSION 6 - -/** *** Removed *** Instead we use the data we read from FractionalUCA.txt - * This is the version of FractionalUCA.txt tailoring rules - * Version 1 was in ICU 1.8.1. Version two contains canonical closure for - * supplementary code points - * Version 4 in ICU 2.2, following UCA=3.1.1d6, UCD=3.2.0 - * This value may change in the subsequent releases of ICU - * @stable ICU 2.4 - */ -/*#define UCOL_FRACTIONAL_UCA_VERSION 4*/ - -/** This is the version of the tailorings - * This value may change in the subsequent releases of ICU - * @stable ICU 2.4 - */ -#define UCOL_TAILORINGS_VERSION 1 - -#endif |