CFStringEncodingConverterExt.h

   1 /*
   2  * Copyright (c) 2009 Apple Inc. All rights reserved.
   3  *
   4  * @APPLE_LICENSE_HEADER_START@
   5  *
   6  * This file contains Original Code and/or Modifications of Original Code
   7  * as defined in and that are subject to the Apple Public Source License
   8  * Version 2.0 (the 'License'). You may not use this file except in
   9  * compliance with the License. Please obtain a copy of the License at
  10  * http://www.opensource.apple.com/apsl/ and read it before using this
  11  * file.
  12  *
  13  * The Original Code and all software distributed under the License are
  14  * distributed on an 'AS IS' basis, WITHOUT WARRANTY OF ANY KIND, EITHER
  15  * EXPRESS OR IMPLIED, AND APPLE HEREBY DISCLAIMS ALL SUCH WARRANTIES,
  16  * INCLUDING WITHOUT LIMITATION, ANY WARRANTIES OF MERCHANTABILITY,
  17  * FITNESS FOR A PARTICULAR PURPOSE, QUIET ENJOYMENT OR NON-INFRINGEMENT.
  18  * Please see the License for the specific language governing rights and
  19  * limitations under the License.
  20  *
  21  * @APPLE_LICENSE_HEADER_END@
  22  */
  23 /*      CFStringEncodingConverterExt.h
  24         Copyright (c) 1998-2009, Apple Inc. All rights reserved.
  25 */
  26
  27 #if !defined(__COREFOUNDATION_CFSTRINGENCODINGCONVERETEREXT__)
  28 #define __COREFOUNDATION_CFSTRINGENCODINGCONVERETEREXT__ 1
  29
  30 #include <CoreFoundation/CFStringEncodingConverter.h>
  31
  32 CF_EXTERN_C_BEGIN
  33
  34 #define MAX_DECOMPOSED_LENGTH (10)
  35
  36 enum {
  37     kCFStringEncodingConverterStandard = 0,
  38     kCFStringEncodingConverterCheapEightBit = 1,
  39     kCFStringEncodingConverterStandardEightBit = 2,
  40     kCFStringEncodingConverterCheapMultiByte = 3,
  41     kCFStringEncodingConverterPlatformSpecific = 4, // Other fields are ignored
  42     kCFStringEncodingConverterICU = 5 // Other fields are ignored
  43 };
  44
  45 /* kCFStringEncodingConverterStandard */
  46 typedef CFIndex (*CFStringEncodingToBytesProc)(uint32_t flags, const UniChar *characters, CFIndex numChars, uint8_t *bytes, CFIndex maxByteLen, CFIndex *usedByteLen);
  47 typedef CFIndex (*CFStringEncodingToUnicodeProc)(uint32_t flags, const uint8_t *bytes, CFIndex numBytes, UniChar *characters, CFIndex maxCharLen, CFIndex *usedCharLen);
  48 /* kCFStringEncodingConverterCheapEightBit */
  49 typedef bool (*CFStringEncodingCheapEightBitToBytesProc)(uint32_t flags, UniChar character, uint8_t *byte);
  50 typedef bool (*CFStringEncodingCheapEightBitToUnicodeProc)(uint32_t flags, uint8_t byte, UniChar *character);
  51 /* kCFStringEncodingConverterStandardEightBit */
  52 typedef uint16_t (*CFStringEncodingStandardEightBitToBytesProc)(uint32_t flags, const UniChar *characters, CFIndex numChars, uint8_t *byte);
  53 typedef uint16_t (*CFStringEncodingStandardEightBitToUnicodeProc)(uint32_t flags, uint8_t byte, UniChar *characters);
  54 /* kCFStringEncodingConverterCheapMultiByte */
  55 typedef uint16_t (*CFStringEncodingCheapMultiByteToBytesProc)(uint32_t flags, UniChar character, uint8_t *bytes);
  56 typedef uint16_t (*CFStringEncodingCheapMultiByteToUnicodeProc)(uint32_t flags, const uint8_t *bytes, CFIndex numBytes, UniChar *character);
  57
  58 typedef CFIndex (*CFStringEncodingToBytesLenProc)(uint32_t flags, const UniChar *characters, CFIndex numChars);
  59 typedef CFIndex (*CFStringEncodingToUnicodeLenProc)(uint32_t flags, const uint8_t *bytes, CFIndex numBytes);
  60
  61 typedef CFIndex (*CFStringEncodingToBytesPrecomposeProc)(uint32_t flags, const UniChar *character, CFIndex numChars, uint8_t *bytes, CFIndex maxByteLen, CFIndex *usedByteLen);
  62 typedef bool (*CFStringEncodingIsValidCombiningCharacterProc)(UniChar character);
  63
  64 typedef struct {
  65     void *toBytes;
  66     void *toUnicode;
  67     uint16_t maxBytesPerChar;
  68     uint16_t maxDecomposedCharLen;
  69     uint8_t encodingClass;
  70     uint32_t :24;
  71     CFStringEncodingToBytesLenProc toBytesLen;
  72     CFStringEncodingToUnicodeLenProc toUnicodeLen;
  73     CFStringEncodingToBytesFallbackProc toBytesFallback;
  74     CFStringEncodingToUnicodeFallbackProc toUnicodeFallback;
  75     CFStringEncodingToBytesPrecomposeProc toBytesPrecompose;
  76     CFStringEncodingIsValidCombiningCharacterProc isValidCombiningChar;
  77 } CFStringEncodingConverter;
  78
  79 extern const CFStringEncodingConverter *CFStringEncodingGetConverter(uint32_t encoding);
  80
  81 enum {
  82     kCFStringEncodingGetConverterSelector = 0,
  83     kCFStringEncodingIsDecomposableCharacterSelector = 1,
  84     kCFStringEncodingDecomposeCharacterSelector = 2,
  85     kCFStringEncodingIsValidLatin1CombiningCharacterSelector = 3,
  86     kCFStringEncodingPrecomposeLatin1CharacterSelector = 4
  87 };
  88
  89 extern const void *CFStringEncodingGetAddressForSelector(uint32_t selector);
  90
  91 #define BOOTSTRAPFUNC_NAME      CFStringEncodingBootstrap
  92 typedef const CFStringEncodingConverter* (*CFStringEncodingBootstrapProc)(uint32_t encoding, const void *getSelector);
  93
  94 /* Latin precomposition */
  95 /* This function does not precompose recursively nor to U+01E0 and U+01E1.
  96 */
  97 extern bool CFStringEncodingIsValidCombiningCharacterForLatin1(UniChar character);
  98 extern UniChar CFStringEncodingPrecomposeLatinCharacter(const UniChar *character, CFIndex numChars, CFIndex *usedChars);
  99
 100 /* Convenience functions for converter development */
 101 typedef struct _CFStringEncodingUnicodeTo8BitCharMap {
 102     UniChar _u;
 103     uint8_t _c;
 104     uint8_t :8;
 105 } CFStringEncodingUnicodeTo8BitCharMap;
 106
 107 /* Binary searches CFStringEncodingUnicodeTo8BitCharMap */
 108 CF_INLINE bool CFStringEncodingUnicodeTo8BitEncoding(const CFStringEncodingUnicodeTo8BitCharMap *theTable, CFIndex numElem, UniChar character, uint8_t *ch) {
 109     const CFStringEncodingUnicodeTo8BitCharMap *p, *q, *divider;
 110
 111     if ((character < theTable[0]._u) || (character > theTable[numElem-1]._u)) {
 112         return 0;
 113     }
 114     p = theTable;
 115     q = p + (numElem-1);
 116     while (p <= q) {
 117         divider = p + ((q - p) >> 1);   /* divide by 2 */
 118         if (character < divider->_u) { q = divider - 1; }
 119         else if (character > divider->_u) { p = divider + 1; }
 120         else { *ch = divider->_c; return 1; }
 121     }
 122     return 0;
 123 }
 124
 125
 126 CF_EXTERN_C_END
 127
 128 #endif /* ! __COREFOUNDATION_CFSTRINGENCODINGCONVERETEREXT__ */
 129