CFStringEncodingConverter.h

   1 /*
   2  * Copyright (c) 2013 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
  24 /*      CFStringEncodingConverter.h
  25         Copyright (c) 1998-2013, Apple Inc. All rights reserved.
  26 */
  27
  28 #if !defined(__COREFOUNDATION_CFSTRINGENCODINGCONVERTER__)
  29 #define __COREFOUNDATION_CFSTRINGENCODINGCONVERTER__ 1
  30
  31 #include <CoreFoundation/CFString.h>
  32
  33
  34 CF_EXTERN_C_BEGIN
  35
  36 /* Values for flags argument for the conversion functions below.  These can be combined, but the three NonSpacing behavior flags are exclusive.
  37 */
  38 // kCFStringEncodingBasicDirectionLeftToRight ~ kCFStringEncodingPrependBOM will probably be deprecated and superceded by kCFStringEncodingPartialInput flag
  39 enum {
  40     kCFStringEncodingAllowLossyConversion = (1UL << 0), // Uses fallback functions to substitutes non mappable chars
  41     kCFStringEncodingBasicDirectionLeftToRight = (1UL << 1), // Converted with original direction left-to-right.
  42     kCFStringEncodingBasicDirectionRightToLeft = (1UL << 2), // Converted with original direction right-to-left.
  43     kCFStringEncodingSubstituteCombinings = (1UL << 3), // Uses fallback function to combining chars.
  44     kCFStringEncodingComposeCombinings = (1UL << 4), // Checks mappable precomposed equivalents for decomposed sequences.  This is the default behavior.
  45     kCFStringEncodingIgnoreCombinings = (1UL << 5), // Ignores combining chars.
  46     kCFStringEncodingUseCanonical = (1UL << 6), // Always use canonical form
  47     kCFStringEncodingUseHFSPlusCanonical = (1UL << 7), // Always use canonical form but leaves 0x2000 ranges
  48     kCFStringEncodingPrependBOM = (1UL << 8), // Prepend BOM sequence (i.e. ISO2022KR)
  49     kCFStringEncodingDisableCorporateArea = (1UL << 9), // Disable the usage of 0xF8xx area for Apple proprietary chars in converting to UniChar, resulting loosely mapping.
  50     kCFStringEncodingASCIICompatibleConversion = (1UL << 10), // This flag forces strict ASCII compatible converion. i.e. MacJapanese 0x5C maps to Unicode 0x5C.
  51     kCFStringEncodingLenientUTF8Conversion = (1UL << 11), // 10.1 (Puma) compatible lenient UTF-8 conversion.
  52     kCFStringEncodingPartialInput = (1UL << 12), // input buffer is a part of stream
  53     kCFStringEncodingPartialOutput = (1UL << 13) // output buffer streaming
  54 };
  55
  56 /* Return values for CFStringEncodingUnicodeToBytes & CFStringEncodingBytesToUnicode functions
  57 */
  58 enum {
  59     kCFStringEncodingConversionSuccess = 0,
  60     kCFStringEncodingInvalidInputStream = 1,
  61     kCFStringEncodingInsufficientOutputBufferLength = 2,
  62     kCFStringEncodingConverterUnavailable = 3
  63 };
  64
  65 /* Macro to shift lossByte argument.
  66 */
  67 #define CFStringEncodingLossyByteToMask(lossByte)       ((uint32_t)(lossByte << 24)|kCFStringEncodingAllowLossyConversion)
  68 #define CFStringEncodingMaskToLossyByte(flags)          ((uint8_t)(flags >> 24))
  69
  70 /* Macros for streaming support
  71  */
  72 #define CFStringEncodingStreamIDMask                    (0x00FF0000)
  73 #define CFStringEncodingStreamIDFromMask(mask)    ((mask >> 16) & 0xFF)
  74 #define CFStringEncodingStreamIDToMask(identifier)            ((uint32_t)((identifier & 0xFF) << 16))
  75
  76 /* Converts characters into the specified encoding.  Returns the constants defined above.
  77 If maxByteLen is 0, bytes is ignored. You can pass lossyByte by passing the value in flags argument.
  78 i.e. CFStringEncodingUnicodeToBytes(encoding, CFStringEncodingLossyByteToMask(lossByte), ....)
  79 */
  80 CF_EXPORT uint32_t CFStringEncodingUnicodeToBytes(uint32_t encoding, uint32_t flags, const UniChar *characters, CFIndex numChars, CFIndex *usedCharLen, uint8_t *bytes, CFIndex maxByteLen, CFIndex *usedByteLen);
  81
  82 /* Converts bytes in the specified encoding into unicode.  Returns the constants defined above.
  83 maxCharLen & usdCharLen are in UniChar length, not byte length.
  84 If maxCharLen is 0, characters is ignored.
  85 */
  86 CF_EXPORT uint32_t CFStringEncodingBytesToUnicode(uint32_t encoding, uint32_t flags, const uint8_t *bytes, CFIndex numBytes, CFIndex *usedByteLen, UniChar *characters, CFIndex maxCharLen, CFIndex *usedCharLen);
  87
  88 /* Fallback functions used when allowLossy
  89 */
  90 typedef CFIndex (*CFStringEncodingToBytesFallbackProc)(const UniChar *characters, CFIndex numChars, uint8_t *bytes, CFIndex maxByteLen, CFIndex *usedByteLen);
  91 typedef CFIndex (*CFStringEncodingToUnicodeFallbackProc)(const uint8_t *bytes, CFIndex numBytes, UniChar *characters, CFIndex maxCharLen, CFIndex *usedCharLen);
  92
  93 CF_EXPORT bool CFStringEncodingIsValidEncoding(uint32_t encoding);
  94
  95 /* Returns kCFStringEncodingInvalidId terminated encoding list
  96 */
  97 CF_EXPORT const CFStringEncoding *CFStringEncodingListOfAvailableEncodings(void);
  98
  99 /* Returns required length of destination buffer for conversion.  These functions are faster than specifying 0 to maxByteLen (maxCharLen), but unnecessarily optimal length
 100 */
 101 CF_EXPORT CFIndex CFStringEncodingCharLengthForBytes(uint32_t encoding, uint32_t flags, const uint8_t *bytes, CFIndex numBytes);
 102 CF_EXPORT CFIndex CFStringEncodingByteLengthForCharacters(uint32_t encoding, uint32_t flags, const UniChar *characters, CFIndex numChars);
 103
 104 /* Can register functions used for lossy conversion.  Reregisters default procs if NULL
 105 */
 106 CF_EXPORT void CFStringEncodingRegisterFallbackProcedures(uint32_t encoding, CFStringEncodingToBytesFallbackProc toBytes, CFStringEncodingToUnicodeFallbackProc toUnicode);
 107
 108 CF_EXTERN_C_END
 109
 110 #endif /* ! __COREFOUNDATION_CFSTRINGENCODINGCONVERTER__ */
 111