StringEncodings.subproj/CFStringEncodingConverter.h

   1 /*
   2  * Copyright (c) 2005 Apple Computer, 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 /*      CFStringEncodingConverter.h
  24         Copyright (c) 1998-2005, Apple, Inc. All rights reserved.
  25 */
  26
  27 #ifndef __CFSTRINGENCODINGCONVERTER__
  28 #define __CFSTRINGENCODINGCONVERTER__ 1
  29
  30 #include <CoreFoundation/CFString.h>
  31
  32
  33 #if defined(__cplusplus)
  34 extern "C" {
  35 #endif
  36
  37 /* Values for flags argument for the conversion functions below.  These can be combined, but the three NonSpacing behavior flags are exclusive.
  38 */
  39 enum {
  40     kCFStringEncodingAllowLossyConversion = 1, // Uses fallback functions to substitutes non mappable chars
  41     kCFStringEncodingBasicDirectionLeftToRight = (1 << 1), // Converted with original direction left-to-right.
  42     kCFStringEncodingBasicDirectionRightToLeft = (1 << 2), // Converted with original direction right-to-left.
  43     kCFStringEncodingSubstituteCombinings = (1 << 3), // Uses fallback function to combining chars.
  44     kCFStringEncodingComposeCombinings = (1 << 4), // Checks mappable precomposed equivalents for decomposed sequences.  This is the default behavior.
  45     kCFStringEncodingIgnoreCombinings = (1 << 5), // Ignores combining chars.
  46     kCFStringEncodingUseCanonical = (1 << 6), // Always use canonical form
  47     kCFStringEncodingUseHFSPlusCanonical = (1 << 7), // Always use canonical form but leaves 0x2000 ranges
  48     kCFStringEncodingPrependBOM = (1 << 8), // Prepend BOM sequence (i.e. ISO2022KR)
  49     kCFStringEncodingDisableCorporateArea = (1 << 9), // Disable the usage of 0xF8xx area for Apple proprietary chars in converting to UniChar, resulting loosely mapping.
  50     kCFStringEncodingASCIICompatibleConversion = (1 << 10), // This flag forces strict ASCII compatible converion. i.e. MacJapanese 0x5C maps to Unicode 0x5C.
  51     kCFStringEncodingLenientUTF8Conversion = (1 << 11) // 10.1 (Puma) compatible lenient UTF-8 conversion.
  52 };
  53
  54 /* Return values for CFStringEncodingUnicodeToBytes & CFStringEncodingBytesToUnicode functions
  55 */
  56 enum {
  57     kCFStringEncodingConversionSuccess = 0,
  58     kCFStringEncodingInvalidInputStream = 1,
  59     kCFStringEncodingInsufficientOutputBufferLength = 2,
  60     kCFStringEncodingConverterUnavailable = 3
  61 };
  62
  63 /* Macro to shift lossByte argument.
  64 */
  65 #define CFStringEncodingLossyByteToMask(lossByte)       ((UInt32)(lossByte << 24)|kCFStringEncodingAllowLossyConversion)
  66 #define CFStringEncodingMaskToLossyByte(flags)          ((UInt8)(flags >> 24))
  67
  68 /* Converts characters into the specified encoding.  Returns the constants defined above.
  69 If maxByteLen is 0, bytes is ignored. You can pass lossyByte by passing the value in flags argument.
  70 i.e. CFStringEncodingUnicodeToBytes(encoding, CFStringEncodingLossyByteToMask(lossByte), ....)
  71 */
  72 extern UInt32 CFStringEncodingUnicodeToBytes(UInt32 encoding, UInt32 flags, const UniChar *characters, UInt32 numChars, UInt32 *usedCharLen, UInt8 *bytes, UInt32 maxByteLen, UInt32 *usedByteLen);
  73
  74 /* Converts bytes in the specified encoding into unicode.  Returns the constants defined above.
  75 maxCharLen & usdCharLen are in UniChar length, not byte length.
  76 If maxCharLen is 0, characters is ignored.
  77 */
  78 extern UInt32 CFStringEncodingBytesToUnicode(UInt32 encoding, UInt32 flags, const UInt8 *bytes, UInt32 numBytes, UInt32 *usedByteLen, UniChar *characters, UInt32 maxCharLen, UInt32 *usedCharLen);
  79
  80 /* Fallback functions used when allowLossy
  81 */
  82 typedef UInt32 (*CFStringEncodingToBytesFallbackProc)(const UniChar *characters, UInt32 numChars, UInt8 *bytes, UInt32 maxByteLen, UInt32 *usedByteLen);
  83 typedef UInt32 (*CFStringEncodingToUnicodeFallbackProc)(const UInt8 *bytes, UInt32 numBytes, UniChar *characters, UInt32 maxCharLen, UInt32 *usedCharLen);
  84
  85 extern Boolean CFStringEncodingIsValidEncoding(UInt32 encoding);
  86
  87 /* Returns kCFStringEncodingInvalidId terminated encoding list
  88 */
  89 extern const UInt32 *CFStringEncodingListOfAvailableEncodings(void);
  90
  91 extern const char *CFStringEncodingName(UInt32 encoding);
  92
  93 /* Returns NULL-terminated list of IANA registered canonical names
  94 */
  95 extern const char **CFStringEncodingCanonicalCharsetNames(UInt32 encoding);
  96
  97 /* Returns required length of destination buffer for conversion.  These functions are faster than specifying 0 to maxByteLen (maxCharLen), but unnecessarily optimal length
  98 */
  99 extern UInt32 CFStringEncodingCharLengthForBytes(UInt32 encoding, UInt32 flags, const UInt8 *bytes, UInt32 numBytes);
 100 extern UInt32 CFStringEncodingByteLengthForCharacters(UInt32 encoding, UInt32 flags, const UniChar *characters, UInt32 numChars);
 101
 102 /* Can register functions used for lossy conversion.  Reregisters default procs if NULL
 103 */
 104 extern void CFStringEncodingRegisterFallbackProcedures(UInt32 encoding, CFStringEncodingToBytesFallbackProc toBytes, CFStringEncodingToUnicodeFallbackProc toUnicode);
 105
 106 #if defined(__cplusplus)
 107 }
 108 #endif
 109
 110 #endif /* __CFSTRINGENCODINGCONVERTER__ */
 111