1 /* 2 ******************************************************************************* 3 * 4 * Copyright (C) 1999-2011, International Business Machines 5 * Corporation and others. All Rights Reserved. 6 * 7 ******************************************************************************* 8 * file name: utf.h 9 * encoding: US-ASCII 10 * tab size: 8 (not used) 11 * indentation:4 12 * 13 * created on: 1999sep09 14 * created by: Markus W. Scherer 15 */ 16 17 /** 18 * \file 19 * \brief C API: Code point macros 20 * 21 * This file defines macros for checking whether a code point is 22 * a surrogate or a non-character etc. 23 * 24 * The UChar and UChar32 data types for Unicode code units and code points 25 * are defined in umachine.h because they can be machine-dependent. 26 * 27 * If U_NO_DEFAULT_INCLUDE_UTF_HEADERS is 0 then utf.h is included by utypes.h 28 * and itself includes utf8.h and utf16.h after some 29 * common definitions. 30 * If U_NO_DEFAULT_INCLUDE_UTF_HEADERS is 1 then each of these headers must be 31 * included explicitly if their definitions are used. 32 * 33 * utf8.h and utf16.h define macros for efficiently getting code points 34 * in and out of UTF-8/16 strings. 35 * utf16.h macros have "U16_" prefixes. 36 * utf8.h defines similar macros with "U8_" prefixes for UTF-8 string handling. 37 * 38 * ICU mostly processes 16-bit Unicode strings. 39 * Most of the time, such strings are well-formed UTF-16. 40 * Single, unpaired surrogates must be handled as well, and are treated in ICU 41 * like regular code points where possible. 42 * (Pairs of surrogate code points are indistinguishable from supplementary 43 * code points encoded as pairs of supplementary code units.) 44 * 45 * In fact, almost all Unicode code points in normal text (>99%) 46 * are on the BMP (<=U+ffff) and even <=U+d7ff. 47 * ICU functions handle supplementary code points (U+10000..U+10ffff) 48 * but are optimized for the much more frequently occurring BMP code points. 49 * 50 * umachine.h defines UChar to be an unsigned 16-bit integer. 51 * Where available, UChar is defined to be a char16_t 52 * or a wchar_t (if that is an unsigned 16-bit type), otherwise uint16_t. 53 * 54 * UChar32 is defined to be a signed 32-bit integer (int32_t), large enough for a 21-bit 55 * Unicode code point (Unicode scalar value, 0..0x10ffff). 56 * Before ICU 2.4, the definition of UChar32 was similarly platform-dependent as 57 * the definition of UChar. For details see the documentation for UChar32 itself. 58 * 59 * utf.h defines a small number of C macros for single Unicode code points. 60 * These are simple checks for surrogates and non-characters. 61 * For actual Unicode character properties see uchar.h. 62 * 63 * By default, string operations must be done with error checking in case 64 * a string is not well-formed UTF-16. 65 * The macros will detect if a surrogate code unit is unpaired 66 * (lead unit without trail unit or vice versa) and just return the unit itself 67 * as the code point. 68 * 69 * The regular "safe" macros require that the initial, passed-in string index 70 * is within bounds. They only check the index when they read more than one 71 * code unit. This is usually done with code similar to the following loop: 72 * <pre>while(i<length) { 73 * U16_NEXT(s, i, length, c); 74 * // use c 75 * }</pre> 76 * 77 * When it is safe to assume that text is well-formed UTF-16 78 * (does not contain single, unpaired surrogates), then one can use 79 * U16_..._UNSAFE macros. 80 * These do not check for proper code unit sequences or truncated text and may 81 * yield wrong results or even cause a crash if they are used with "malformed" 82 * text. 83 * In practice, U16_..._UNSAFE macros will produce slightly less code but 84 * should not be faster because the processing is only different when a 85 * surrogate code unit is detected, which will be rare. 86 * 87 * Similarly for UTF-8, there are "safe" macros without a suffix, 88 * and U8_..._UNSAFE versions. 89 * The performance differences are much larger here because UTF-8 provides so 90 * many opportunities for malformed sequences. 91 * The unsafe UTF-8 macros are entirely implemented inside the macro definitions 92 * and are fast, while the safe UTF-8 macros call functions for all but the 93 * trivial (ASCII) cases. 94 * (ICU 3.6 optimizes U8_NEXT() and U8_APPEND() to handle most other common 95 * characters inline as well.) 96 * 97 * Unlike with UTF-16, malformed sequences cannot be expressed with distinct 98 * code point values (0..U+10ffff). They are indicated with negative values instead. 99 * 100 * For more information see the ICU User Guide Strings chapter 101 * (http://userguide.icu-project.org/strings). 102 * 103 * <em>Usage:</em> 104 * ICU coding guidelines for if() statements should be followed when using these macros. 105 * Compound statements (curly braces {}) must be used for if-else-while... 106 * bodies and all macro statements should be terminated with semicolon. 107 * 108 * @stable ICU 2.4 109 */ 110 111 #ifndef __UTF_H__ 112 #define __UTF_H__ 113 114 #include "unicode/umachine.h" 115 /* include the utfXX.h after the following definitions */ 116 117 /* single-code point definitions -------------------------------------------- */ 118 119 /** 120 * Is this code point a Unicode noncharacter? 121 * @param c 32-bit code point 122 * @return TRUE or FALSE 123 * @stable ICU 2.4 124 */ 125 #define U_IS_UNICODE_NONCHAR(c) \ 126 ((c)>=0xfdd0 && \ 127 ((uint32_t)(c)<=0xfdef || ((c)&0xfffe)==0xfffe) && \ 128 (uint32_t)(c)<=0x10ffff) 129 130 /** 131 * Is c a Unicode code point value (0..U+10ffff) 132 * that can be assigned a character? 133 * 134 * Code points that are not characters include: 135 * - single surrogate code points (U+d800..U+dfff, 2048 code points) 136 * - the last two code points on each plane (U+__fffe and U+__ffff, 34 code points) 137 * - U+fdd0..U+fdef (new with Unicode 3.1, 32 code points) 138 * - the highest Unicode code point value is U+10ffff 139 * 140 * This means that all code points below U+d800 are character code points, 141 * and that boundary is tested first for performance. 142 * 143 * @param c 32-bit code point 144 * @return TRUE or FALSE 145 * @stable ICU 2.4 146 */ 147 #define U_IS_UNICODE_CHAR(c) \ 148 ((uint32_t)(c)<0xd800 || \ 149 ((uint32_t)(c)>0xdfff && \ 150 (uint32_t)(c)<=0x10ffff && \ 151 !U_IS_UNICODE_NONCHAR(c))) 152 153 /** 154 * Is this code point a BMP code point (U+0000..U+ffff)? 155 * @param c 32-bit code point 156 * @return TRUE or FALSE 157 * @stable ICU 2.8 158 */ 159 #define U_IS_BMP(c) ((uint32_t)(c)<=0xffff) 160 161 /** 162 * Is this code point a supplementary code point (U+10000..U+10ffff)? 163 * @param c 32-bit code point 164 * @return TRUE or FALSE 165 * @stable ICU 2.8 166 */ 167 #define U_IS_SUPPLEMENTARY(c) ((uint32_t)((c)-0x10000)<=0xfffff) 168 169 /** 170 * Is this code point a lead surrogate (U+d800..U+dbff)? 171 * @param c 32-bit code point 172 * @return TRUE or FALSE 173 * @stable ICU 2.4 174 */ 175 #define U_IS_LEAD(c) (((c)&0xfffffc00)==0xd800) 176 177 /** 178 * Is this code point a trail surrogate (U+dc00..U+dfff)? 179 * @param c 32-bit code point 180 * @return TRUE or FALSE 181 * @stable ICU 2.4 182 */ 183 #define U_IS_TRAIL(c) (((c)&0xfffffc00)==0xdc00) 184 185 /** 186 * Is this code point a surrogate (U+d800..U+dfff)? 187 * @param c 32-bit code point 188 * @return TRUE or FALSE 189 * @stable ICU 2.4 190 */ 191 #define U_IS_SURROGATE(c) (((c)&0xfffff800)==0xd800) 192 193 /** 194 * Assuming c is a surrogate code point (U_IS_SURROGATE(c)), 195 * is it a lead surrogate? 196 * @param c 32-bit code point 197 * @return TRUE or FALSE 198 * @stable ICU 2.4 199 */ 200 #define U_IS_SURROGATE_LEAD(c) (((c)&0x400)==0) 201 202 /** 203 * Assuming c is a surrogate code point (U_IS_SURROGATE(c)), 204 * is it a trail surrogate? 205 * @param c 32-bit code point 206 * @return TRUE or FALSE 207 * @stable ICU 4.2 208 */ 209 #define U_IS_SURROGATE_TRAIL(c) (((c)&0x400)!=0) 210 211 /* include the utfXX.h ------------------------------------------------------ */ 212 213 #if !U_NO_DEFAULT_INCLUDE_UTF_HEADERS 214 215 #include "unicode/utf8.h" 216 #include "unicode/utf16.h" 217 218 /* utf_old.h contains deprecated, pre-ICU 2.4 definitions */ 219 #include "unicode/utf_old.h" 220 221 #endif /* !U_NO_DEFAULT_INCLUDE_UTF_HEADERS */ 222 223 #endif /* __UTF_H__ */ 224