2000-02-03 19:54:49 +00:00
|
|
|
/*
|
|
|
|
*******************************************************************************
|
|
|
|
*
|
2004-05-18 22:01:41 +00:00
|
|
|
* Copyright (C) 1999-2004, International Business Machines
|
2000-02-03 19:54:49 +00:00
|
|
|
* 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
|
2000-12-08 18:43:57 +00:00
|
|
|
*/
|
|
|
|
|
|
|
|
/**
|
2002-09-30 04:00:17 +00:00
|
|
|
* \file
|
2004-06-03 21:37:47 +00:00
|
|
|
* \brief C API: Code point macros
|
2002-09-30 04:00:17 +00:00
|
|
|
*
|
2004-06-03 21:37:47 +00:00
|
|
|
* 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.
|
2002-09-30 04:00:17 +00:00
|
|
|
*
|
|
|
|
* 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
|
2005-02-18 00:19:33 +00:00
|
|
|
* (http://icu.sourceforge.net/userguide/strings.html).
|
2002-09-30 04:00:17 +00:00
|
|
|
*
|
|
|
|
* <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.
|
|
|
|
*
|
2004-03-26 19:42:04 +00:00
|
|
|
* @stable ICU 2.4
|
2002-09-30 04:00:17 +00:00
|
|
|
*/
|
2000-02-03 19:54:49 +00:00
|
|
|
|
|
|
|
#ifndef __UTF_H__
|
|
|
|
#define __UTF_H__
|
|
|
|
|
2004-03-26 19:42:04 +00:00
|
|
|
#include "unicode/utypes.h"
|
2000-02-03 19:54:49 +00:00
|
|
|
/* include the utfXX.h after the following definitions */
|
|
|
|
|
|
|
|
/* single-code point definitions -------------------------------------------- */
|
|
|
|
|
2002-09-20 22:00:21 +00:00
|
|
|
/**
|
|
|
|
* 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
|
2002-09-30 04:00:17 +00:00
|
|
|
* could be indicated with U_SENTINEL.
|
2002-09-20 22:00:21 +00:00
|
|
|
*
|
|
|
|
* 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().
|
|
|
|
*
|
2002-09-30 04:00:17 +00:00
|
|
|
* @return -1
|
2002-09-20 22:00:21 +00:00
|
|
|
* @see UChar32
|
2004-03-26 19:42:04 +00:00
|
|
|
* @stable ICU 2.4
|
2002-09-20 22:00:21 +00:00
|
|
|
*/
|
2002-09-30 04:00:17 +00:00
|
|
|
#define U_SENTINEL (-1)
|
2000-02-03 19:54:49 +00:00
|
|
|
|
2002-02-15 21:08:29 +00:00
|
|
|
/**
|
2002-09-30 04:00:17 +00:00
|
|
|
* Is this code point a Unicode noncharacter?
|
|
|
|
* @param c 32-bit code point
|
|
|
|
* @return TRUE or FALSE
|
2004-03-26 19:42:04 +00:00
|
|
|
* @stable ICU 2.4
|
2002-02-15 21:08:29 +00:00
|
|
|
*/
|
2002-09-30 04:00:17 +00:00
|
|
|
#define U_IS_UNICODE_NONCHAR(c) \
|
2002-07-02 00:48:46 +00:00
|
|
|
((c)>=0xfdd0 && \
|
|
|
|
((uint32_t)(c)<=0xfdef || ((c)&0xfffe)==0xfffe) && \
|
|
|
|
(uint32_t)(c)<=0x10ffff)
|
2002-02-15 21:08:29 +00:00
|
|
|
|
2000-12-12 20:31:47 +00:00
|
|
|
/**
|
2002-09-30 04:00:17 +00:00
|
|
|
* Is c a Unicode code point value (0..U+10ffff)
|
|
|
|
* that can be assigned a character?
|
2001-10-12 18:53:26 +00:00
|
|
|
*
|
2002-02-15 21:08:29 +00:00
|
|
|
* Code points that are not characters include:
|
2001-10-12 18:53:26 +00:00
|
|
|
* - 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.
|
2002-09-30 04:00:17 +00:00
|
|
|
*
|
|
|
|
* @param c 32-bit code point
|
|
|
|
* @return TRUE or FALSE
|
2004-03-26 19:42:04 +00:00
|
|
|
* @stable ICU 2.4
|
2000-02-03 19:54:49 +00:00
|
|
|
*/
|
2002-09-30 04:00:17 +00:00
|
|
|
#define U_IS_UNICODE_CHAR(c) \
|
2001-10-12 18:53:26 +00:00
|
|
|
((uint32_t)(c)<0xd800 || \
|
|
|
|
((uint32_t)(c)>0xdfff && \
|
|
|
|
(uint32_t)(c)<=0x10ffff && \
|
2002-09-30 04:00:17 +00:00
|
|
|
!U_IS_UNICODE_NONCHAR(c)))
|
2000-02-03 19:54:49 +00:00
|
|
|
|
2004-03-26 19:42:04 +00:00
|
|
|
#ifndef U_HIDE_DRAFT_API
|
|
|
|
|
2003-10-31 19:17:00 +00:00
|
|
|
/**
|
|
|
|
* 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)
|
|
|
|
|
2004-03-26 19:42:04 +00:00
|
|
|
#endif /*U_HIDE_DRAFT_API*/
|
|
|
|
|
2000-12-12 20:31:47 +00:00
|
|
|
/**
|
2002-09-30 04:00:17 +00:00
|
|
|
* Is this code point a lead surrogate (U+d800..U+dbff)?
|
|
|
|
* @param c 32-bit code point
|
|
|
|
* @return TRUE or FALSE
|
2004-03-26 19:42:04 +00:00
|
|
|
* @stable ICU 2.4
|
2000-12-12 20:31:47 +00:00
|
|
|
*/
|
2002-09-30 04:00:17 +00:00
|
|
|
#define U_IS_LEAD(c) (((c)&0xfffffc00)==0xd800)
|
2000-12-12 20:31:47 +00:00
|
|
|
|
|
|
|
/**
|
2002-09-30 04:00:17 +00:00
|
|
|
* Is this code point a trail surrogate (U+dc00..U+dfff)?
|
|
|
|
* @param c 32-bit code point
|
|
|
|
* @return TRUE or FALSE
|
2004-03-26 19:42:04 +00:00
|
|
|
* @stable ICU 2.4
|
2000-12-12 20:31:47 +00:00
|
|
|
*/
|
2002-09-30 04:00:17 +00:00
|
|
|
#define U_IS_TRAIL(c) (((c)&0xfffffc00)==0xdc00)
|
2000-12-12 20:31:47 +00:00
|
|
|
|
|
|
|
/**
|
2002-09-30 04:00:17 +00:00
|
|
|
* Is this code point a surrogate (U+d800..U+dfff)?
|
|
|
|
* @param c 32-bit code point
|
|
|
|
* @return TRUE or FALSE
|
2004-03-26 19:42:04 +00:00
|
|
|
* @stable ICU 2.4
|
2000-12-12 20:31:47 +00:00
|
|
|
*/
|
2002-09-30 04:00:17 +00:00
|
|
|
#define U_IS_SURROGATE(c) (((c)&0xfffff800)==0xd800)
|
2000-12-12 20:31:47 +00:00
|
|
|
|
|
|
|
/**
|
2002-09-30 04:00:17 +00:00
|
|
|
* 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
|
2004-03-26 19:42:04 +00:00
|
|
|
* @stable ICU 2.4
|
2000-12-12 20:31:47 +00:00
|
|
|
*/
|
2002-09-30 04:00:17 +00:00
|
|
|
#define U_IS_SURROGATE_LEAD(c) (((c)&0x400)==0)
|
2000-12-12 20:31:47 +00:00
|
|
|
|
2002-09-30 04:00:17 +00:00
|
|
|
/* include the utfXX.h ------------------------------------------------------ */
|
2000-02-03 19:54:49 +00:00
|
|
|
|
2002-09-30 04:00:17 +00:00
|
|
|
#include "unicode/utf8.h"
|
|
|
|
#include "unicode/utf16.h"
|
2000-02-03 19:54:49 +00:00
|
|
|
|
2002-09-30 04:00:17 +00:00
|
|
|
/* utf_old.h contains deprecated, pre-ICU 2.4 definitions */
|
|
|
|
#include "unicode/utf_old.h"
|
2000-02-03 19:54:49 +00:00
|
|
|
|
|
|
|
#endif
|