CFPlatformConverters.c

/*
 * Copyright (c) 2009-2012 Brent Fulgham <bfulgham@gmail.org>. All rights reserved.
 *
 * This source code is a modified version of the CoreFoundation sources released by Apple Inc. under
 * the terms of the APSL version 2.0 (see below).
 *
 * For information about changes from the original Apple source release can be found by reviewing the
 * source control system for the project at https://sourceforge.net/svn/?group_id=246198.
 *
 * The original license information is as follows:
 *
 * Copyright (c) 2012 Apple Inc. All rights reserved.
 *
 * @APPLE_LICENSE_HEADER_START@
 * 
 * This file contains Original Code and/or Modifications of Original Code
 * as defined in and that are subject to the Apple Public Source License
 * Version 2.0 (the 'License'). You may not use this file except in
 * compliance with the License. Please obtain a copy of the License at
 * http://www.opensource.apple.com/apsl/ and read it before using this
 * file.
 * 
 * The Original Code and all software distributed under the License are
 * distributed on an 'AS IS' basis, WITHOUT WARRANTY OF ANY KIND, EITHER
 * EXPRESS OR IMPLIED, AND APPLE HEREBY DISCLAIMS ALL SUCH WARRANTIES,
 * INCLUDING WITHOUT LIMITATION, ANY WARRANTIES OF MERCHANTABILITY,
 * FITNESS FOR A PARTICULAR PURPOSE, QUIET ENJOYMENT OR NON-INFRINGEMENT.
 * Please see the License for the specific language governing rights and
 * limitations under the License.
 * 
 * @APPLE_LICENSE_HEADER_END@
 */

/* CFPlatformConverters.c
 Copyright (c) 1998-2011, Apple Inc. All rights reserved.
 Responsibility: Aki Inoue
*/

#include<CoreFoundation/CoreFoundation_Prefix.h>
#include"CFInternal.h"
#include<CoreFoundation/CFString.h>
#include<CoreFoundation/CFStringEncodingConverterExt.h>
#include<CoreFoundation/CFStringEncodingExt.h>
#include<CoreFoundation/CFPreferences.h>
#include<CoreFoundation/CFUniChar.h>
#include<CoreFoundation/CFUnicodeDecomposition.h>
#include"CFStringEncodingConverterPriv.h"
#include<CoreFoundation/CFICUConverters.h>


CF_INLINEbool__CFIsPlatformConverterAvailable(intencoding) {

#ifDEPLOYMENT_TARGET_WINDOWS
return (IsValidCodePage(CFStringConvertEncodingToWindowsCodepage(encoding)) ? true : false);
#else
return false;
#endif
}

staticconstCFStringEncodingConverter__CFICUBootstrap= {
NULL/* toBytes */, NULL/* toUnicode */, 6/* maxBytesPerChar */, 4/* maxDecomposedCharLen */,
kCFStringEncodingConverterICU/* encodingClass */,
NULL/* toBytesLen */, NULL/* toUnicodeLen */, NULL/* toBytesFallback */,
NULL/* toUnicodeFallback */, NULL/* toBytesPrecompose */, NULL, /* isValidCombiningChar */
};

staticconstCFStringEncodingConverter__CFPlatformBootstrap= {
NULL/* toBytes */, NULL/* toUnicode */, 6/* maxBytesPerChar */, 4/* maxDecomposedCharLen */,
kCFStringEncodingConverterPlatformSpecific/* encodingClass */,
NULL/* toBytesLen */, NULL/* toUnicodeLen */, NULL/* toBytesFallback */,
NULL/* toUnicodeFallback */, NULL/* toBytesPrecompose */, NULL, /* isValidCombiningChar */
};

__private_extern__constCFStringEncodingConverter*__CFStringEncodingGetExternalConverter(uint32_tencoding) {

return (__CFIsPlatformConverterAvailable(encoding) ? &__CFPlatformBootstrap : (__CFStringEncodingGetICUName(encoding) ? &__CFICUBootstrap : NULL)); // we prefer Text Encoding Converter ICU since it's more reliable
}

#ifDEPLOYMENT_TARGET_MACOSX||DEPLOYMENT_TARGET_EMBEDDED
__private_extern__CFStringEncoding*__CFStringEncodingCreateListOfAvailablePlatformConverters(CFAllocatorRefallocator, CFIndex*numberOfConverters) {

returnNULL;
}
#elifDEPLOYMENT_TARGET_WINDOWS

#include<tchar.h>

staticuint32_t__CFWin32EncodingIndex=0;
staticCFStringEncoding*__CFWin32EncodingList=NULL;

staticcharCALLBACK__CFWin32EnumCodePageProc(LPTSTRstring) {
uint32_tencoding=CFStringConvertWindowsCodepageToEncoding(_tcstoul(string, NULL, 10));
CFIndexidx;

if (encoding!=kCFStringEncodingInvalidId) { // We list only encodings we know
if (__CFWin32EncodingList) {
for (idx=0;idx< (CFIndex)__CFWin32EncodingIndex;idx++) if (__CFWin32EncodingList[idx] ==encoding) break;
if (idx!=__CFWin32EncodingIndex) return true;
__CFWin32EncodingList[__CFWin32EncodingIndex] =encoding;
 }
++__CFWin32EncodingIndex;
 }
return true;
}

__private_extern__CFStringEncoding*__CFStringEncodingCreateListOfAvailablePlatformConverters(CFAllocatorRefallocator, CFIndex*numberOfConverters) {
CFStringEncoding*encodings;

EnumSystemCodePages((CODEPAGE_ENUMPROC)&__CFWin32EnumCodePageProc, CP_INSTALLED);
__CFWin32EncodingList= (uint32_t*)CFAllocatorAllocate(allocator, sizeof(uint32_t) *__CFWin32EncodingIndex, 0);
EnumSystemCodePages((CODEPAGE_ENUMPROC)&__CFWin32EnumCodePageProc, CP_INSTALLED);

*numberOfConverters=__CFWin32EncodingIndex;
encodings=__CFWin32EncodingList;

__CFWin32EncodingIndex=0;
__CFWin32EncodingList=NULL;

returnencodings;
}
#else
__private_extern__CFStringEncoding*__CFStringEncodingCreateListOfAvailablePlatformConverters(CFAllocatorRefallocator, CFIndex*numberOfConverters) { returnNULL; }
#endif

__private_extern__CFIndex__CFStringEncodingPlatformUnicodeToBytes(uint32_tencoding, uint32_tflags, constUniChar*characters, CFIndexnumChars, CFIndex*usedCharLen, uint8_t*bytes, CFIndexmaxByteLen, CFIndex*usedByteLen) {

#ifDEPLOYMENT_TARGET_WINDOWS
WORDdwFlags=0;
CFIndexusedLen;

if ((kCFStringEncodingUTF7!=encoding) && (kCFStringEncodingGB_18030_2000!=encoding) && (0x0800!= (encoding&0x0F00))) { // not UTF-7/GB18030/ISO-2022-*
dwFlags |= (flags& (kCFStringEncodingAllowLossyConversion|kCFStringEncodingSubstituteCombinings) ? WC_DEFAULTCHAR : 0);
dwFlags |= (flags&kCFStringEncodingComposeCombinings ? WC_COMPOSITECHECK : 0);
dwFlags |= (flags&kCFStringEncodingIgnoreCombinings ? WC_DISCARDNS : 0);
 }

if ((usedLen=WideCharToMultiByte(CFStringConvertEncodingToWindowsCodepage(encoding), dwFlags, (LPCWSTR)characters, numChars, (LPSTR)bytes, maxByteLen, NULL, NULL)) ==0) {
if (GetLastError() ==ERROR_INSUFFICIENT_BUFFER) {
CPINFOcpInfo;

if (!GetCPInfo(CFStringConvertEncodingToWindowsCodepage(encoding), &cpInfo)) {
cpInfo.MaxCharSize=1; // Is this right ???
 }
if (cpInfo.MaxCharSize==1) {
numChars=maxByteLen;
 } else {
usedLen=WideCharToMultiByte(CFStringConvertEncodingToWindowsCodepage(encoding), dwFlags, (LPCWSTR)characters, numChars, NULL, 0, NULL, NULL);
usedLen-=maxByteLen;
numChars= (numChars>usedLen ? numChars-usedLen : 1);
 }
if (WideCharToMultiByte(CFStringConvertEncodingToWindowsCodepage(encoding), dwFlags, (LPCWSTR)characters, numChars, (LPSTR)bytes, maxByteLen, NULL, NULL) ==0) {
if (usedCharLen) *usedCharLen=0;
if (usedByteLen) *usedByteLen=0;
 } else {
CFIndexlastUsedLen=0;

while ((usedLen=WideCharToMultiByte(CFStringConvertEncodingToWindowsCodepage(encoding), dwFlags, (LPCWSTR)characters, ++numChars, (LPSTR)bytes, maxByteLen, NULL, NULL))) lastUsedLen=usedLen;
if (usedCharLen) *usedCharLen= (numChars-1);
if (usedByteLen) *usedByteLen=lastUsedLen;
 }

returnkCFStringEncodingInsufficientOutputBufferLength;
 } else {
returnkCFStringEncodingInvalidInputStream;
 }
 } else {
if (usedCharLen) *usedCharLen=numChars;
if (usedByteLen) *usedByteLen=usedLen;
returnkCFStringEncodingConversionSuccess;
 }
#endif/* DEPLOYMENT_TARGET_WINDOWS */

returnkCFStringEncodingConverterUnavailable;
}

__private_extern__CFIndex__CFStringEncodingPlatformBytesToUnicode(uint32_tencoding, uint32_tflags, constuint8_t*bytes, CFIndexnumBytes, CFIndex*usedByteLen, UniChar*characters, CFIndexmaxCharLen, CFIndex*usedCharLen) {

#ifDEPLOYMENT_TARGET_WINDOWS
WORDdwFlags=0;
CFIndexusedLen;

if ((kCFStringEncodingUTF7!=encoding) && (kCFStringEncodingGB_18030_2000!=encoding) && (0x0800!= (encoding&0x0F00))) { // not UTF-7/GB18030/ISO-2022-*
dwFlags |= (flags& (kCFStringEncodingAllowLossyConversion|kCFStringEncodingSubstituteCombinings) ? 0 : MB_ERR_INVALID_CHARS);
dwFlags |= (flags& (kCFStringEncodingUseCanonical|kCFStringEncodingUseHFSPlusCanonical) ? MB_COMPOSITE : MB_PRECOMPOSED);
 }

if ((usedLen=MultiByteToWideChar(CFStringConvertEncodingToWindowsCodepage(encoding), dwFlags, (LPCSTR)bytes, numBytes, (LPWSTR)characters, maxCharLen) ==0)) {
if (GetLastError() ==ERROR_INSUFFICIENT_BUFFER) {
CPINFOcpInfo;

if (!GetCPInfo(CFStringConvertEncodingToWindowsCodepage(encoding), &cpInfo)) {
cpInfo.MaxCharSize=1; // Is this right ???
 }
if (cpInfo.MaxCharSize==1) {
numBytes=maxCharLen;
 } else {
usedLen=MultiByteToWideChar(CFStringConvertEncodingToWindowsCodepage(encoding), dwFlags, (LPCSTR)bytes, numBytes, (LPWSTR)characters, maxCharLen);
usedLen-=maxCharLen;
numBytes= (numBytes>usedLen ? numBytes-usedLen : 1);
 }
while ((usedLen=MultiByteToWideChar(CFStringConvertEncodingToWindowsCodepage(encoding), dwFlags, (LPCSTR)bytes, numBytes, (LPWSTR)characters, maxCharLen)) ==0) {
if ((--numBytes) ==0) break;
 }
if (usedCharLen) *usedCharLen=usedLen;
if (usedByteLen) *usedByteLen=numBytes;

returnkCFStringEncodingInsufficientOutputBufferLength;
 } else {
returnkCFStringEncodingInvalidInputStream;
 }
 } else {
if (usedCharLen) *usedCharLen=usedLen;
if (usedByteLen) *usedByteLen=numBytes;
returnkCFStringEncodingConversionSuccess;
 }
#endif/* DEPLOYMENT_TARGET_WINDOWS */

returnkCFStringEncodingConverterUnavailable;
}

__private_extern__CFIndex__CFStringEncodingPlatformCharLengthForBytes(uint32_tencoding, uint32_tflags, constuint8_t*bytes, CFIndexnumBytes) {
CFIndexusedCharLen;
return (__CFStringEncodingPlatformBytesToUnicode(encoding, flags, bytes, numBytes, NULL, NULL, 0, &usedCharLen) ==kCFStringEncodingConversionSuccess ? usedCharLen : 0);
}

__private_extern__CFIndex__CFStringEncodingPlatformByteLengthForCharacters(uint32_tencoding, uint32_tflags, constUniChar*characters, CFIndexnumChars) {
CFIndexusedByteLen;
return (__CFStringEncodingPlatformUnicodeToBytes(encoding, flags, characters, numChars, NULL, NULL, 0, &usedByteLen) ==kCFStringEncodingConversionSuccess ? usedByteLen : 0);
}

#undef __CFCarbonCore_GetTextEncodingBase0