diff options
author | Steve Block <steveblock@google.com> | 2011-05-06 11:45:16 +0100 |
---|---|---|
committer | Steve Block <steveblock@google.com> | 2011-05-12 13:44:10 +0100 |
commit | cad810f21b803229eb11403f9209855525a25d57 (patch) | |
tree | 29a6fd0279be608e0fe9ffe9841f722f0f4e4269 /Source/WebCore/icu/unicode/utf.h | |
parent | 121b0cf4517156d0ac5111caf9830c51b69bae8f (diff) | |
download | external_webkit-cad810f21b803229eb11403f9209855525a25d57.zip external_webkit-cad810f21b803229eb11403f9209855525a25d57.tar.gz external_webkit-cad810f21b803229eb11403f9209855525a25d57.tar.bz2 |
Merge WebKit at r75315: Initial merge by git.
Change-Id: I570314b346ce101c935ed22a626b48c2af266b84
Diffstat (limited to 'Source/WebCore/icu/unicode/utf.h')
-rw-r--r-- | Source/WebCore/icu/unicode/utf.h | 221 |
1 files changed, 221 insertions, 0 deletions
diff --git a/Source/WebCore/icu/unicode/utf.h b/Source/WebCore/icu/unicode/utf.h new file mode 100644 index 0000000..201691d --- /dev/null +++ b/Source/WebCore/icu/unicode/utf.h @@ -0,0 +1,221 @@ +/* +******************************************************************************* +* +* 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 |