mirror of
https://github.com/unicode-org/icu.git
synced 2025-04-07 14:31:31 +00:00
ICU-311 Major rewrite of the callback APIs. Needs to be checked
in without more testing to make the 6/29/2000 API deadline. Lots of warnings still, offset handling is not implemented. More unit tests is required because the current implementation actually passes the tests. X-SVN-Rev: 1661
This commit is contained in:
parent
c68b0038be
commit
377889ccd9
24 changed files with 928 additions and 869 deletions
|
@ -71,7 +71,7 @@ LIBS = @LIBS@
|
|||
OBJECTS = chariter.o umutex.o compdata.o compitr.o convert.o \
|
||||
cpputils.o cstring.o dcmpdata.o digitlst.o filestrm.o umemstrm.o locid.o locmap.o \
|
||||
mutex.o normlzr.o putil.o resbund.o schriter.o scsu.o \
|
||||
uchar.o uchriter.o ucmp8.o ucmp16.o ucmp32.o ucnv.o ucnv_bld.o \
|
||||
uchar.o uchriter.o ucmp8.o ucmp16.o ucmp32.o ucnv.o ucnv_bld.o ucnv_cb.o \
|
||||
ucnv_cnv.o ucnv_err.o ucnv_io.o uhash.o uhash_us.o uloc.o unicode.o unistr.o \
|
||||
uresbund.o uresdata.o ustring.o rbdata.o ubidi.o ubidiln.o \
|
||||
bidi.o uvector.o udata.o unames.o utf_impl.o \
|
||||
|
|
|
@ -306,6 +306,10 @@ SOURCE=.\ucnv_bld.c
|
|||
# End Source File
|
||||
# Begin Source File
|
||||
|
||||
SOURCE=.\ucnv_cb.c
|
||||
# End Source File
|
||||
# Begin Source File
|
||||
|
||||
SOURCE=.\ucnv_cnv.c
|
||||
# End Source File
|
||||
# Begin Source File
|
||||
|
@ -884,29 +888,10 @@ InputPath=.\unicode\ucnv.h
|
|||
# Begin Source File
|
||||
|
||||
SOURCE=.\unicode\ucnv_bld.h
|
||||
# End Source File
|
||||
# Begin Source File
|
||||
|
||||
!IF "$(CFG)" == "common - Win32 Release"
|
||||
|
||||
# Begin Custom Build
|
||||
InputPath=.\unicode\ucnv_bld.h
|
||||
|
||||
"..\..\include\unicode\ucnv_bld.h" : $(SOURCE) "$(INTDIR)" "$(OUTDIR)"
|
||||
copy unicode\ucnv_bld.h ..\..\include\unicode
|
||||
|
||||
# End Custom Build
|
||||
|
||||
!ELSEIF "$(CFG)" == "common - Win32 Debug"
|
||||
|
||||
# Begin Custom Build
|
||||
InputPath=.\unicode\ucnv_bld.h
|
||||
|
||||
"..\..\include\unicode\ucnv_bld.h" : $(SOURCE) "$(INTDIR)" "$(OUTDIR)"
|
||||
copy unicode\ucnv_bld.h ..\..\include\unicode
|
||||
|
||||
# End Custom Build
|
||||
|
||||
!ENDIF
|
||||
|
||||
SOURCE=.\unicode\ucnv_cb.h
|
||||
# End Source File
|
||||
# Begin Source File
|
||||
|
||||
|
|
|
@ -16,7 +16,8 @@ class Mutex;
|
|||
#include "mutex.h"
|
||||
extern "C" {
|
||||
#include "ucnv_io.h"
|
||||
#include "unicode/ucnv_bld.h"
|
||||
#include "unicode/ucnv_err.h"
|
||||
#include "ucnv_bld.h"
|
||||
#include "unicode/ucnv.h"
|
||||
}
|
||||
#include "unicode/convert.h"
|
||||
|
@ -337,17 +338,23 @@ UnicodeConverterCPP::getMissingUnicodeAction() const
|
|||
|
||||
|
||||
void
|
||||
UnicodeConverterCPP::setMissingCharAction(UConverterToUCallback action,
|
||||
UnicodeConverterCPP::setMissingCharAction(UConverterToUCallback newAction,
|
||||
void *newContext,
|
||||
UConverterToUCallback oldAction,
|
||||
void **oldContext,
|
||||
UErrorCode& err)
|
||||
{
|
||||
ucnv_setToUCallBack(myUnicodeConverter, action, &err);
|
||||
ucnv_setToUCallBack(myUnicodeConverter, newAction, newContext, oldAction, oldContext, &err);
|
||||
}
|
||||
|
||||
void
|
||||
UnicodeConverterCPP::setMissingUnicodeAction(UConverterFromUCallback action,
|
||||
UnicodeConverterCPP::setMissingUnicodeAction(UConverterFromUCallback newAction,
|
||||
void* newContext,
|
||||
UConverterFromUCallback oldAction,
|
||||
void** oldContext,
|
||||
UErrorCode& err)
|
||||
{
|
||||
ucnv_setFromUCallBack(myUnicodeConverter, action, &err);
|
||||
ucnv_setFromUCallBack(myUnicodeConverter, newAction, newContext, oldAction, oldContext, &err);
|
||||
}
|
||||
|
||||
|
||||
|
|
|
@ -23,7 +23,6 @@
|
|||
#include "uhash.h"
|
||||
#include "ucmp16.h"
|
||||
#include "ucmp8.h"
|
||||
#include "unicode/ucnv_bld.h"
|
||||
#include "ucnv_io.h"
|
||||
#include "unicode/ucnv_err.h"
|
||||
#include "ucnv_cnv.h"
|
||||
|
@ -33,6 +32,7 @@
|
|||
#include "cstring.h"
|
||||
#include "unicode/ustring.h"
|
||||
#include "unicode/uloc.h"
|
||||
#include "ucnv_bld.h"
|
||||
|
||||
#define CHUNK_SIZE 5*1024
|
||||
|
||||
|
@ -394,32 +394,37 @@ UConverterFromUCallback ucnv_getFromUCallBack (const UConverter * converter)
|
|||
return converter->fromUCharErrorBehaviour;
|
||||
}
|
||||
|
||||
UConverterToUCallback ucnv_setToUCallBack (UConverter * converter,
|
||||
UConverterToUCallback action,
|
||||
void ucnv_setToUCallBack (UConverter * converter,
|
||||
UConverterToUCallback newAction,
|
||||
void* newContext,
|
||||
UConverterToUCallback oldAction,
|
||||
void** oldContext,
|
||||
UErrorCode * err)
|
||||
{
|
||||
UConverterToUCallback myReturn = NULL;
|
||||
|
||||
if (U_FAILURE (*err))
|
||||
return NULL;
|
||||
myReturn = converter->fromCharErrorBehaviour;
|
||||
converter->fromCharErrorBehaviour = action;
|
||||
|
||||
return myReturn;
|
||||
return;
|
||||
oldAction = converter->fromCharErrorBehaviour;
|
||||
converter->fromCharErrorBehaviour = newAction;
|
||||
oldContext = converter->toUContext;
|
||||
converter->toUContext = newContext;
|
||||
}
|
||||
|
||||
UConverterFromUCallback ucnv_setFromUCallBack (UConverter * converter,
|
||||
UConverterFromUCallback action,
|
||||
UErrorCode * err)
|
||||
void ucnv_setFromUCallBack (UConverter * converter,
|
||||
UConverterFromUCallback newAction,
|
||||
void* newContext,
|
||||
UConverterFromUCallback oldAction,
|
||||
void** oldContext,
|
||||
UErrorCode * err)
|
||||
{
|
||||
UConverterFromUCallback myReturn = NULL;
|
||||
|
||||
if (U_FAILURE (*err))
|
||||
return NULL;
|
||||
myReturn = converter->fromUCharErrorBehaviour;
|
||||
converter->fromUCharErrorBehaviour = action;
|
||||
|
||||
return myReturn;
|
||||
return;
|
||||
oldAction = converter->fromUCharErrorBehaviour;
|
||||
converter->fromUCharErrorBehaviour = newAction;
|
||||
oldContext = converter->fromUContext;
|
||||
converter->fromUContext = newContext;
|
||||
}
|
||||
void ucnv_fromUnicode (UConverter * _this,
|
||||
char **target,
|
||||
|
|
|
@ -10,13 +10,18 @@
|
|||
*
|
||||
* created on: 2000feb03
|
||||
* created by: Markus W. Scherer
|
||||
*
|
||||
* Change history:
|
||||
*
|
||||
* 06/29/2000 helena Major rewrite of the callback APIs.
|
||||
*/
|
||||
|
||||
#include "unicode/utypes.h"
|
||||
#include "cmemory.h"
|
||||
#include "ucmp16.h"
|
||||
#include "ucmp8.h"
|
||||
#include "unicode/ucnv_bld.h"
|
||||
#include "unicode/ucnv_err.h"
|
||||
#include "ucnv_bld.h"
|
||||
#include "unicode/ucnv.h"
|
||||
#include "ucnv_cnv.h"
|
||||
|
||||
|
@ -719,8 +724,8 @@ void T_UConverter_toUnicode_EBCDIC_STATEFUL (UConverter * _this,
|
|||
UBool flush,
|
||||
UErrorCode * err)
|
||||
{
|
||||
const char *mySource = *source;
|
||||
UChar *myTarget = *target;
|
||||
const char *mySource = *source, *srcTemp;
|
||||
UChar *myTarget = *target, *tgtTemp;
|
||||
int32_t mySourceIndex = 0;
|
||||
int32_t myTargetIndex = 0;
|
||||
int32_t targetLength = targetLimit - myTarget;
|
||||
|
@ -729,10 +734,11 @@ void T_UConverter_toUnicode_EBCDIC_STATEFUL (UConverter * _this,
|
|||
UChar targetUniChar = 0x0000;
|
||||
UChar mySourceChar = 0x0000;
|
||||
int32_t myMode = _this->mode;
|
||||
UConverterToUnicodeArgs args;
|
||||
|
||||
|
||||
myToUnicode = &_this->sharedData->table->dbcs.toUnicode;
|
||||
|
||||
args.sourceStart = *source;
|
||||
while (mySourceIndex < sourceLength)
|
||||
{
|
||||
if (myTargetIndex < targetLength)
|
||||
|
@ -783,19 +789,28 @@ void T_UConverter_toUnicode_EBCDIC_STATEFUL (UConverter * _this,
|
|||
_this->invalidCharBuffer[0] = (char) mySourceChar;
|
||||
}
|
||||
_this->mode = myMode;
|
||||
ToU_CALLBACK_MACRO(_this,
|
||||
myTarget,
|
||||
myTargetIndex,
|
||||
targetLimit,
|
||||
mySource,
|
||||
mySourceIndex,
|
||||
sourceLimit,
|
||||
offsets,
|
||||
flush,
|
||||
args.converter = _this;
|
||||
srcTemp = mySource + mySourceIndex;
|
||||
tgtTemp = myTarget + myTargetIndex;
|
||||
args.pTarget = &tgtTemp;
|
||||
args.targetLimit = targetLimit;
|
||||
args.pSource = &srcTemp;
|
||||
args.sourceLimit = sourceLimit;
|
||||
args.flush = flush;
|
||||
args.offsets = offsets+myTargetIndex;
|
||||
args.size = sizeof(args);
|
||||
|
||||
ToU_CALLBACK_MACRO(_this->toUContext,
|
||||
args,
|
||||
srcTemp,
|
||||
1,
|
||||
UCNV_UNASSIGNED,
|
||||
err);
|
||||
|
||||
if (U_FAILURE (*err)) break;
|
||||
_this->invalidCharLength = 0;
|
||||
myTargetIndex = *(args.pTarget) - myTarget;
|
||||
mySourceIndex = *(args.pSource) - mySource;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
@ -836,8 +851,8 @@ void T_UConverter_toUnicode_EBCDIC_STATEFUL_OFFSETS_LOGIC (UConverter * _this,
|
|||
UBool flush,
|
||||
UErrorCode * err)
|
||||
{
|
||||
const char *mySource = *source;
|
||||
UChar *myTarget = *target;
|
||||
const char *mySource = *source, *srcTemp;
|
||||
UChar *myTarget = *target, *tgtTemp;
|
||||
int32_t mySourceIndex = 0;
|
||||
int32_t myTargetIndex = 0;
|
||||
int32_t targetLength = targetLimit - myTarget;
|
||||
|
@ -847,9 +862,10 @@ void T_UConverter_toUnicode_EBCDIC_STATEFUL_OFFSETS_LOGIC (UConverter * _this,
|
|||
UChar mySourceChar = 0x0000;
|
||||
int32_t myMode = _this->mode;
|
||||
int32_t* originalOffsets = offsets;
|
||||
|
||||
UConverterToUnicodeArgs args;
|
||||
|
||||
myToUnicode = &_this->sharedData->table->dbcs.toUnicode;
|
||||
args.sourceStart = *source;
|
||||
|
||||
while (mySourceIndex < sourceLength)
|
||||
{
|
||||
|
@ -909,20 +925,29 @@ void T_UConverter_toUnicode_EBCDIC_STATEFUL_OFFSETS_LOGIC (UConverter * _this,
|
|||
_this->invalidCharBuffer[0] = (char) mySourceChar;
|
||||
}
|
||||
_this->mode = myMode;
|
||||
ToU_CALLBACK_OFFSETS_LOGIC_MACRO(_this,
|
||||
myTarget,
|
||||
myTargetIndex,
|
||||
targetLimit,
|
||||
mySource,
|
||||
mySourceIndex,
|
||||
sourceLimit,
|
||||
offsets,
|
||||
flush,
|
||||
err);
|
||||
|
||||
|
||||
args.converter = _this;
|
||||
srcTemp = mySource + mySourceIndex;
|
||||
tgtTemp = myTarget + myTargetIndex;
|
||||
args.pTarget = &tgtTemp;
|
||||
args.targetLimit = targetLimit;
|
||||
args.pSource = &srcTemp;
|
||||
args.sourceLimit = sourceLimit;
|
||||
args.flush = flush;
|
||||
args.offsets = offsets+myTargetIndex;
|
||||
args.size = sizeof(args);
|
||||
/* call back handles the offset array */
|
||||
ToU_CALLBACK_MACRO(_this->toUContext,
|
||||
args,
|
||||
srcTemp,
|
||||
1,
|
||||
UCNV_UNASSIGNED,
|
||||
err);
|
||||
|
||||
if (U_FAILURE (*err)) break;
|
||||
_this->invalidCharLength = 0;
|
||||
myTargetIndex = *(args.pTarget) - myTarget;
|
||||
mySourceIndex = *(args.pSource) - mySource;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
@ -964,8 +989,8 @@ void T_UConverter_fromUnicode_EBCDIC_STATEFUL (UConverter * _this,
|
|||
UErrorCode * err)
|
||||
|
||||
{
|
||||
const UChar *mySource = *source;
|
||||
char *myTarget = *target;
|
||||
const UChar *mySource = *source, *srcTemp;
|
||||
char *myTarget = *target, *tgtTemp;
|
||||
int32_t mySourceIndex = 0;
|
||||
int32_t myTargetIndex = 0;
|
||||
int32_t targetLength = targetLimit - myTarget;
|
||||
|
@ -976,8 +1001,10 @@ void T_UConverter_fromUnicode_EBCDIC_STATEFUL (UConverter * _this,
|
|||
UChar mySourceChar = 0x0000;
|
||||
UBool isTargetUCharDBCS = (UBool)_this->fromUnicodeStatus;
|
||||
UBool oldIsTargetUCharDBCS = isTargetUCharDBCS;
|
||||
UConverterFromUnicodeArgs args;
|
||||
|
||||
myFromUnicode = &_this->sharedData->table->dbcs.fromUnicode;
|
||||
|
||||
args.sourceStart = *source;
|
||||
/*writing the char to the output stream */
|
||||
while (mySourceIndex < sourceLength)
|
||||
{
|
||||
|
@ -1042,19 +1069,28 @@ void T_UConverter_fromUnicode_EBCDIC_STATEFUL (UConverter * _this,
|
|||
_this->invalidUCharLength = 1;
|
||||
|
||||
_this->fromUnicodeStatus = (int32_t)isTargetUCharDBCS;
|
||||
FromU_CALLBACK_MACRO(_this,
|
||||
myTarget,
|
||||
myTargetIndex,
|
||||
targetLimit,
|
||||
mySource,
|
||||
mySourceIndex,
|
||||
sourceLimit,
|
||||
offsets,
|
||||
flush,
|
||||
err);
|
||||
|
||||
srcTemp = mySource + mySourceIndex;
|
||||
tgtTemp = myTarget + myTargetIndex;
|
||||
args.converter = _this;
|
||||
args.pTarget = &tgtTemp;
|
||||
args.targetLimit = targetLimit;
|
||||
args.pSource = &srcTemp;
|
||||
args.sourceLimit = sourceLimit;
|
||||
args.flush = flush;
|
||||
args.offsets = offsets+myTargetIndex;
|
||||
args.size = sizeof(args);
|
||||
/* HSYS: to do: more smarts */
|
||||
FromU_CALLBACK_MACRO(args.converter->fromUContext,
|
||||
args,
|
||||
srcTemp,
|
||||
1,
|
||||
(UChar32) (*srcTemp),
|
||||
UCNV_UNASSIGNED,
|
||||
err);
|
||||
if (U_FAILURE (*err)) break;
|
||||
_this->invalidUCharLength = 0;
|
||||
myTargetIndex = *(args.pTarget) - myTarget;
|
||||
mySourceIndex = *(args.pSource) - mySource;
|
||||
}
|
||||
}
|
||||
else
|
||||
|
@ -1084,8 +1120,8 @@ void T_UConverter_fromUnicode_EBCDIC_STATEFUL_OFFSETS_LOGIC (UConverter * _this,
|
|||
UErrorCode * err)
|
||||
|
||||
{
|
||||
const UChar *mySource = *source;
|
||||
char *myTarget = *target;
|
||||
const UChar *mySource = *source, *srcTemp;
|
||||
char *myTarget = *target, *tgtTemp;
|
||||
int32_t mySourceIndex = 0;
|
||||
int32_t myTargetIndex = 0;
|
||||
int32_t targetLength = targetLimit - myTarget;
|
||||
|
@ -1097,9 +1133,10 @@ void T_UConverter_fromUnicode_EBCDIC_STATEFUL_OFFSETS_LOGIC (UConverter * _this,
|
|||
UBool isTargetUCharDBCS = (UBool)_this->fromUnicodeStatus;
|
||||
UBool oldIsTargetUCharDBCS = isTargetUCharDBCS;
|
||||
int32_t* originalOffsets = offsets;
|
||||
UConverterFromUnicodeArgs args;
|
||||
|
||||
myFromUnicode = &_this->sharedData->table->dbcs.fromUnicode;
|
||||
|
||||
args.sourceStart = *source;
|
||||
/*writing the char to the output stream */
|
||||
while (mySourceIndex < sourceLength)
|
||||
{
|
||||
|
@ -1168,19 +1205,29 @@ void T_UConverter_fromUnicode_EBCDIC_STATEFUL_OFFSETS_LOGIC (UConverter * _this,
|
|||
|
||||
/* Breaks out of the loop since behaviour was set to stop */
|
||||
_this->fromUnicodeStatus = (int32_t)isTargetUCharDBCS;
|
||||
FromU_CALLBACK_OFFSETS_LOGIC_MACRO(_this,
|
||||
myTarget,
|
||||
myTargetIndex,
|
||||
targetLimit,
|
||||
mySource,
|
||||
mySourceIndex,
|
||||
sourceLimit,
|
||||
offsets,
|
||||
flush,
|
||||
err);
|
||||
srcTemp = mySource + mySourceIndex;
|
||||
tgtTemp = myTarget + myTargetIndex;
|
||||
args.converter = _this;
|
||||
args.pTarget = &tgtTemp;
|
||||
args.targetLimit = targetLimit;
|
||||
args.pSource = &srcTemp;
|
||||
args.sourceLimit = sourceLimit;
|
||||
args.flush = flush;
|
||||
args.offsets = offsets+myTargetIndex;
|
||||
args.size = sizeof(args);
|
||||
/* HSYS: to do: more smarts, including offsets */
|
||||
FromU_CALLBACK_MACRO(args.converter->fromUContext,
|
||||
args,
|
||||
srcTemp,
|
||||
1,
|
||||
(UChar32) (*srcTemp),
|
||||
UCNV_UNASSIGNED,
|
||||
err);
|
||||
|
||||
if (U_FAILURE (*err)) break;
|
||||
_this->invalidUCharLength = 0;
|
||||
myTargetIndex = *(args.pTarget) - myTarget;
|
||||
mySourceIndex = *(args.pSource) - mySource;
|
||||
}
|
||||
}
|
||||
else
|
||||
|
@ -1207,6 +1254,7 @@ UChar32 T_UConverter_getNextUChar_EBCDIC_STATEFUL(UConverter* converter,
|
|||
{
|
||||
UChar myUChar;
|
||||
char const *sourceInitial = *source;
|
||||
UConverterToUnicodeArgs args;
|
||||
/*safe keeps a ptr to the beginning in case we need to step back*/
|
||||
|
||||
/*Input boundary check*/
|
||||
|
@ -1216,6 +1264,7 @@ UChar32 T_UConverter_getNextUChar_EBCDIC_STATEFUL(UConverter* converter,
|
|||
return 0xFFFD;
|
||||
}
|
||||
|
||||
args.sourceStart = *source;
|
||||
/*Checks to see if with have SI/SO shifters
|
||||
if we do we change the mode appropriately and we consume the byte*/
|
||||
if ((**source == UCNV_SI) || (**source == UCNV_SO))
|
||||
|
@ -1266,14 +1315,21 @@ UChar32 T_UConverter_getNextUChar_EBCDIC_STATEFUL(UConverter* converter,
|
|||
|
||||
/*It's is very likely that the ErrorFunctor will write to the
|
||||
*internal buffers */
|
||||
converter->fromCharErrorBehaviour(converter,
|
||||
&myUCharPtr,
|
||||
myUCharPtr + 1,
|
||||
&sourceFinal,
|
||||
sourceLimit,
|
||||
NULL,
|
||||
TRUE,
|
||||
err);
|
||||
args.converter = converter;
|
||||
args.pTarget = &myUCharPtr;
|
||||
args.targetLimit = myUCharPtr + 1;
|
||||
args.pSource = &sourceFinal;
|
||||
args.sourceLimit = sourceLimit;
|
||||
args.flush = TRUE;
|
||||
args.offsets = NULL;
|
||||
args.size = sizeof(args);
|
||||
|
||||
converter->fromCharErrorBehaviour(converter->toUContext,
|
||||
&args,
|
||||
sourceFinal,
|
||||
1,
|
||||
UCNV_UNASSIGNED,
|
||||
err);
|
||||
|
||||
/*makes the internal caching transparent to the user*/
|
||||
if (*err == U_INDEX_OUTOFBOUNDS_ERROR) *err = U_ZERO_ERROR;
|
||||
|
|
|
@ -16,6 +16,7 @@
|
|||
* Date Name Description
|
||||
*
|
||||
* 06/20/2000 helena OS/400 port changes; mostly typecast.
|
||||
* 06/29/2000 helena Major rewrite of the callback interface.
|
||||
*/
|
||||
|
||||
|
||||
|
@ -23,7 +24,7 @@
|
|||
#include "uhash.h"
|
||||
#include "ucmp16.h"
|
||||
#include "ucmp8.h"
|
||||
#include "unicode/ucnv_bld.h"
|
||||
#include "ucnv_bld.h"
|
||||
#include "unicode/ucnv_err.h"
|
||||
#include "ucnv_cnv.h"
|
||||
#include "ucnv_imp.h"
|
||||
|
|
|
@ -10,10 +10,12 @@
|
|||
* Implements all the low level conversion functions
|
||||
* T_UnicodeConverter_{to,from}Unicode_$ConversionType
|
||||
*
|
||||
* Change history:
|
||||
*
|
||||
* 06/29/2000 helena Major rewrite of the callback APIs.
|
||||
*/
|
||||
|
||||
#include "unicode/utypes.h"
|
||||
#include "unicode/ucnv_bld.h"
|
||||
#include "unicode/ucnv_err.h"
|
||||
#include "ucnv_cnv.h"
|
||||
#include "unicode/ucnv.h"
|
||||
|
|
|
@ -12,14 +12,15 @@
|
|||
*
|
||||
* Date Name Description
|
||||
* 05/09/00 helena Added implementation to handle fallback mappings.
|
||||
* 06/29/2000 helena Major rewrite of the callback APIs.
|
||||
*/
|
||||
|
||||
#ifndef UCNV_CNV_H
|
||||
#define UCNV_CNV_H
|
||||
|
||||
#include "unicode/utypes.h"
|
||||
#include "unicode/ucnv_bld.h"
|
||||
|
||||
#include "unicode/ucnv_err.h"
|
||||
#include "ucnv_bld.h"
|
||||
#include "ucmp8.h"
|
||||
#include "ucmp16.h"
|
||||
|
||||
|
@ -65,90 +66,35 @@ U_CDECL_BEGIN
|
|||
#define missingCharMarker 0xFFFF
|
||||
#define missingUCharMarker 0xFFFD
|
||||
|
||||
#define FromU_CALLBACK_MACRO(_this, myTarget, myTargetIndex, targetLimit, mySource, mySourceIndex, sourceLimit, offsets, flush, err) \
|
||||
if (_this->fromUCharErrorBehaviour == (UConverterFromUCallback) UCNV_FROM_U_CALLBACK_STOP) break;\
|
||||
#define FromU_CALLBACK_MACRO(context, args, codeUnits, length, codePoint, reason, err) \
|
||||
if (args.converter->fromUCharErrorBehaviour == (UConverterFromUCallback) UCNV_FROM_U_CALLBACK_STOP) break;\
|
||||
else \
|
||||
{ \
|
||||
char *myTargetCopy = myTarget + myTargetIndex; \
|
||||
const UChar *mySourceCopy = mySource + mySourceIndex; \
|
||||
/*copies current values for the ErrorFunctor to update */ \
|
||||
/*Calls the ErrorFunctor */ \
|
||||
_this->fromUCharErrorBehaviour (_this, \
|
||||
(char **) &myTargetCopy, \
|
||||
targetLimit, \
|
||||
(const UChar **) &mySourceCopy, \
|
||||
sourceLimit, \
|
||||
offsets, \
|
||||
flush, \
|
||||
args.converter->fromUCharErrorBehaviour ( context, \
|
||||
&args, \
|
||||
codeUnits, \
|
||||
length, \
|
||||
codePoint, \
|
||||
reason, \
|
||||
err); \
|
||||
/*Update the local Indexes so that the conversion can restart at the right points */ \
|
||||
mySourceIndex = (mySourceCopy - mySource) ; \
|
||||
myTargetIndex = (char*)myTargetCopy - (char*)myTarget ; \
|
||||
}
|
||||
|
||||
#define ToU_CALLBACK_MACRO(_this, myTarget, myTargetIndex, targetLimit, mySource, mySourceIndex, sourceLimit, offsets, flush, err) \
|
||||
if (_this->fromCharErrorBehaviour == (UConverterToUCallback) UCNV_TO_U_CALLBACK_STOP) break; \
|
||||
#define ToU_CALLBACK_MACRO(context, args, codePoints, length, reason, err) \
|
||||
if (args.converter->fromCharErrorBehaviour == (UConverterToUCallback) UCNV_TO_U_CALLBACK_STOP) break; \
|
||||
else \
|
||||
{ \
|
||||
UChar *myTargetCopy = myTarget + myTargetIndex; \
|
||||
const char *mySourceCopy = mySource + mySourceIndex; \
|
||||
/*Calls the ErrorFunctor */ \
|
||||
_this->fromCharErrorBehaviour (_this, \
|
||||
&myTargetCopy, \
|
||||
targetLimit, \
|
||||
(const char **) &mySourceCopy, \
|
||||
sourceLimit, \
|
||||
offsets, \
|
||||
flush, \
|
||||
args.converter->fromCharErrorBehaviour ( \
|
||||
context, \
|
||||
&args, \
|
||||
codePoints, \
|
||||
length, \
|
||||
reason, \
|
||||
err); \
|
||||
/*Update the local Indexes so that the conversion can restart at the right points */ \
|
||||
mySourceIndex = ((char*)mySourceCopy - (char*)mySource); \
|
||||
myTargetIndex = (myTargetCopy - myTarget); \
|
||||
}
|
||||
|
||||
#define FromU_CALLBACK_OFFSETS_LOGIC_MACRO(_this, myTarget, myTargetIndex, targetLimit, mySource, mySourceIndex, sourceLimit, offsets, flush, err) \
|
||||
if (_this->fromUCharErrorBehaviour == (UConverterFromUCallback) UCNV_FROM_U_CALLBACK_STOP) break;\
|
||||
else \
|
||||
{ \
|
||||
char *myTargetCopy = myTarget + myTargetIndex; \
|
||||
const UChar *mySourceCopy = mySource + mySourceIndex; \
|
||||
int32_t My_i = myTargetIndex; \
|
||||
/*copies current values for the ErrorFunctor to update */ \
|
||||
/*Calls the ErrorFunctor */ \
|
||||
_this->fromUCharErrorBehaviour (_this, \
|
||||
(char **) &myTargetCopy, \
|
||||
targetLimit, \
|
||||
(const UChar **) &mySourceCopy, \
|
||||
sourceLimit, \
|
||||
offsets + myTargetIndex, \
|
||||
flush, \
|
||||
err); \
|
||||
/*Update the local Indexes so that the conversion can restart at the right points */ \
|
||||
mySourceIndex = mySourceCopy - mySource ; \
|
||||
myTargetIndex = (char*)myTargetCopy - (char*)myTarget ; \
|
||||
for (;My_i < myTargetIndex;My_i++) offsets[My_i] += currentOffset ; \
|
||||
}
|
||||
|
||||
#define ToU_CALLBACK_OFFSETS_LOGIC_MACRO(_this, myTarget, myTargetIndex, targetLimit, mySource, mySourceIndex, sourceLimit, offsets, flush, err) \
|
||||
if (_this->fromCharErrorBehaviour == (UConverterToUCallback) UCNV_TO_U_CALLBACK_STOP) break; \
|
||||
else \
|
||||
{ \
|
||||
UChar *myTargetCopy = myTarget + myTargetIndex; \
|
||||
const char *mySourceCopy = mySource + mySourceIndex; \
|
||||
int32_t My_i = myTargetIndex; \
|
||||
_this->fromCharErrorBehaviour (_this, \
|
||||
&myTargetCopy, \
|
||||
targetLimit, \
|
||||
(const char **) &mySourceCopy, \
|
||||
sourceLimit, \
|
||||
offsets + myTargetIndex, \
|
||||
flush, \
|
||||
err); \
|
||||
/*Update the local Indexes so that the conversion can restart at the right points */ \
|
||||
mySourceIndex = (char *)mySourceCopy - (char*)mySource; \
|
||||
myTargetIndex = ((UChar*)myTargetCopy - (UChar*)myTarget); \
|
||||
for (;My_i < myTargetIndex;My_i++) {offsets[My_i] += currentOffset ; } \
|
||||
}
|
||||
|
||||
typedef void (*UConverterLoad) (UConverterSharedData *sharedData, const uint8_t *raw, UErrorCode *pErrorCode);
|
||||
typedef void (*UConverterUnload) (UConverterSharedData *sharedData);
|
||||
|
|
|
@ -9,11 +9,14 @@
|
|||
* ucnv_err.c
|
||||
* Implements error behaviour functions called by T_UConverter_{from,to}Unicode
|
||||
*
|
||||
*/
|
||||
*
|
||||
* Change history:
|
||||
*
|
||||
* 06/29/2000 helena Major rewrite of the callback APIs.
|
||||
*/
|
||||
|
||||
#include "ucmp8.h"
|
||||
#include "ucmp16.h"
|
||||
#include "unicode/ucnv_bld.h"
|
||||
#include "unicode/ucnv_err.h"
|
||||
#include "ucnv_cnv.h"
|
||||
#include "cmemory.h"
|
||||
|
@ -72,53 +75,54 @@ static void itou (UChar * buffer, int32_t i, int32_t radix, int32_t pad)
|
|||
}
|
||||
|
||||
/*Function Pointer STOPS at the ILLEGAL_SEQUENCE */
|
||||
void UCNV_FROM_U_CALLBACK_STOP (UConverter * _this,
|
||||
char **target,
|
||||
const char *targetLimit,
|
||||
const UChar ** source,
|
||||
const UChar * sourceLimit,
|
||||
int32_t *offsets,
|
||||
UBool flush,
|
||||
void UCNV_FROM_U_CALLBACK_STOP (
|
||||
void *context,
|
||||
UConverterFromUnicodeArgs *fromUArgs,
|
||||
const UChar* codeUnits,
|
||||
int32_t length,
|
||||
UChar32 codePoint,
|
||||
UConverterCallbackReason reason,
|
||||
UErrorCode * err)
|
||||
{
|
||||
reason = UCNV_ILLEGAL;
|
||||
return;
|
||||
}
|
||||
|
||||
|
||||
/*Function Pointer STOPS at the ILLEGAL_SEQUENCE */
|
||||
void UCNV_TO_U_CALLBACK_STOP (UConverter * _this,
|
||||
UChar ** target,
|
||||
const UChar * targetLimit,
|
||||
const char **source,
|
||||
const char *sourceLimit,
|
||||
int32_t *offsets,
|
||||
UBool flush,
|
||||
void UCNV_TO_U_CALLBACK_STOP (
|
||||
void *context,
|
||||
UConverterToUnicodeArgs *toUArgs,
|
||||
const char* codePoints,
|
||||
int32_t length,
|
||||
UConverterCallbackReason reason,
|
||||
UErrorCode * err)
|
||||
{
|
||||
reason = UCNV_ILLEGAL;
|
||||
return;
|
||||
}
|
||||
|
||||
void UCNV_FROM_U_CALLBACK_SKIP (UConverter * _this,
|
||||
char **target,
|
||||
const char *targetLimit,
|
||||
const UChar ** source,
|
||||
const UChar * sourceLimit,
|
||||
int32_t *offsets,
|
||||
UBool flush,
|
||||
void UCNV_FROM_U_CALLBACK_SKIP (
|
||||
void *context,
|
||||
UConverterFromUnicodeArgs *fromUArgs,
|
||||
const UChar* codeUnits,
|
||||
int32_t length,
|
||||
UChar32 codePoint,
|
||||
UConverterCallbackReason reason,
|
||||
UErrorCode * err)
|
||||
{
|
||||
if (CONVERSION_U_SUCCESS (*err)) return;
|
||||
*err = U_ZERO_ERROR;
|
||||
}
|
||||
|
||||
void UCNV_FROM_U_CALLBACK_SUBSTITUTE (UConverter * _this,
|
||||
char **target,
|
||||
const char *targetLimit,
|
||||
const UChar ** source,
|
||||
const UChar * sourceLimit,
|
||||
int32_t *offsets,
|
||||
UBool flush,
|
||||
UErrorCode * err)
|
||||
void UCNV_FROM_U_CALLBACK_SUBSTITUTE (
|
||||
void *context,
|
||||
UConverterFromUnicodeArgs *fromArgs,
|
||||
const UChar* codeUnits,
|
||||
int32_t length,
|
||||
UChar32 codePoint,
|
||||
UConverterCallbackReason reason,
|
||||
UErrorCode * err)
|
||||
{
|
||||
char togo[5];
|
||||
int32_t togoLen;
|
||||
|
@ -129,21 +133,21 @@ void UCNV_FROM_U_CALLBACK_SUBSTITUTE (UConverter * _this,
|
|||
|
||||
/*In case we're dealing with a modal converter a la UCNV_EBCDIC_STATEFUL,
|
||||
we need to make sure that the emitting of the substitution charater in the right mode*/
|
||||
uprv_memcpy(togo, _this->subChar, togoLen = _this->subCharLen);
|
||||
if (ucnv_getType(_this) == UCNV_EBCDIC_STATEFUL)
|
||||
uprv_memcpy(togo, fromArgs->converter->subChar, togoLen = fromArgs->converter->subCharLen);
|
||||
if (ucnv_getType(fromArgs->converter) == UCNV_EBCDIC_STATEFUL)
|
||||
{
|
||||
if ((_this->fromUnicodeStatus)&&(togoLen != 2))
|
||||
if ((fromArgs->converter->fromUnicodeStatus)&&(togoLen != 2))
|
||||
{
|
||||
togo[0] = UCNV_SI;
|
||||
togo[1] = _this->subChar[0];
|
||||
togo[1] = fromArgs->converter->subChar[0];
|
||||
togo[2] = UCNV_SO;
|
||||
togoLen = 3;
|
||||
}
|
||||
else if (!(_this->fromUnicodeStatus)&&(togoLen != 1))
|
||||
else if (!(fromArgs->converter->fromUnicodeStatus)&&(togoLen != 1))
|
||||
{
|
||||
togo[0] = UCNV_SO;
|
||||
togo[1] = _this->subChar[0];
|
||||
togo[2] = _this->subChar[1];
|
||||
togo[1] = fromArgs->converter->subChar[0];
|
||||
togo[2] = fromArgs->converter->subChar[1];
|
||||
togo[3] = UCNV_SI;
|
||||
togoLen = 4;
|
||||
}
|
||||
|
@ -151,16 +155,16 @@ void UCNV_FROM_U_CALLBACK_SUBSTITUTE (UConverter * _this,
|
|||
|
||||
/*if we have enough space on the output buffer we just copy
|
||||
the subchar there and update the pointer */
|
||||
if ((targetLimit - *target) >= togoLen)
|
||||
if ((fromArgs->targetLimit - *(fromArgs->pTarget)) >= togoLen)
|
||||
{
|
||||
uprv_memcpy (*target, togo, togoLen);
|
||||
*target += togoLen;
|
||||
uprv_memcpy (*(fromArgs->pTarget), togo, togoLen);
|
||||
*(fromArgs->pTarget) += togoLen;
|
||||
*err = U_ZERO_ERROR;
|
||||
if (offsets)
|
||||
if (fromArgs->offsets)
|
||||
{
|
||||
int i=0;
|
||||
for (i=0;i<togoLen;i++) offsets[i]=0;
|
||||
offsets += togoLen;
|
||||
for (i=0;i<togoLen;i++) fromArgs->offsets[i]=0;
|
||||
fromArgs->offsets += togoLen;
|
||||
}
|
||||
}
|
||||
else
|
||||
|
@ -170,18 +174,18 @@ void UCNV_FROM_U_CALLBACK_SUBSTITUTE (UConverter * _this,
|
|||
*copy the rest in the internal buffer, and increase the
|
||||
*length marker
|
||||
*/
|
||||
uprv_memcpy (*target, togo, (targetLimit - *target));
|
||||
if (offsets)
|
||||
uprv_memcpy (*(fromArgs->pTarget), togo, (fromArgs->targetLimit - *(fromArgs->pTarget)));
|
||||
if (fromArgs->offsets)
|
||||
{
|
||||
int i=0;
|
||||
for (i=0;i<(targetLimit - *target);i++) offsets[i]=0;
|
||||
offsets += (targetLimit - *target);
|
||||
for (i=0;i<(fromArgs->targetLimit - *(fromArgs->pTarget));i++) fromArgs->offsets[i]=0;
|
||||
fromArgs->offsets += (fromArgs->targetLimit - *(fromArgs->pTarget));
|
||||
}
|
||||
uprv_memcpy (_this->charErrorBuffer + _this->charErrorBufferLength,
|
||||
togo + (targetLimit - *target),
|
||||
togoLen - (targetLimit - *target));
|
||||
_this->charErrorBufferLength += togoLen - (targetLimit - *target);
|
||||
*target += (targetLimit - *target);
|
||||
uprv_memcpy (fromArgs->converter->charErrorBuffer + fromArgs->converter->charErrorBufferLength,
|
||||
togo + (fromArgs->targetLimit - *(fromArgs->pTarget)),
|
||||
togoLen - (fromArgs->targetLimit - *(fromArgs->pTarget)));
|
||||
fromArgs->converter->charErrorBufferLength += togoLen - (fromArgs->targetLimit - *(fromArgs->pTarget));
|
||||
*(fromArgs->pTarget) += (fromArgs->targetLimit - *(fromArgs->pTarget));
|
||||
*err = U_INDEX_OUTOFBOUNDS_ERROR;
|
||||
}
|
||||
|
||||
|
@ -194,13 +198,13 @@ void UCNV_FROM_U_CALLBACK_SUBSTITUTE (UConverter * _this,
|
|||
*escape sequence to the target codepage (if conversion failure happens then
|
||||
*we revert to substituting with subchar)
|
||||
*/
|
||||
void UCNV_FROM_U_CALLBACK_ESCAPE (UConverter * _this,
|
||||
char **target,
|
||||
const char *targetLimit,
|
||||
const UChar ** source,
|
||||
const UChar * sourceLimit,
|
||||
int32_t *offsets,
|
||||
UBool flush,
|
||||
void UCNV_FROM_U_CALLBACK_ESCAPE (
|
||||
void *context,
|
||||
UConverterFromUnicodeArgs *fromArgs,
|
||||
const UChar *codeUnits,
|
||||
int32_t length,
|
||||
UChar32 codePoint,
|
||||
UConverterCallbackReason reason,
|
||||
UErrorCode * err)
|
||||
{
|
||||
|
||||
|
@ -209,13 +213,13 @@ void UCNV_FROM_U_CALLBACK_ESCAPE (UConverter * _this,
|
|||
UChar codepoint[CODEPOINT_STRING_LENGTH];
|
||||
int32_t i = 0;
|
||||
/*Makes a bitwise copy of the converter passwd in */
|
||||
UConverter myConverter = *_this;
|
||||
UConverter myConverter = *(fromArgs->converter);
|
||||
char myTarget[VALUE_STRING_LENGTH];
|
||||
char *myTargetAlias = myTarget;
|
||||
const UChar *myValueSource = NULL;
|
||||
UErrorCode err2 = U_ZERO_ERROR;
|
||||
uint32_t myFromUnicodeStatus = _this->fromUnicodeStatus;
|
||||
|
||||
uint32_t myFromUnicodeStatus = fromArgs->converter->fromUnicodeStatus;
|
||||
UConverterFromUCallback original = NULL;
|
||||
|
||||
if (CONVERSION_U_SUCCESS (*err)) return;
|
||||
|
||||
|
@ -224,6 +228,9 @@ void UCNV_FROM_U_CALLBACK_ESCAPE (UConverter * _this,
|
|||
|
||||
ucnv_setFromUCallBack (&myConverter,
|
||||
(UConverterFromUCallback) UCNV_FROM_U_CALLBACK_STOP,
|
||||
NULL, /* To Do for HSYS: context is null? */
|
||||
original,
|
||||
NULL,
|
||||
&err2);
|
||||
if (U_FAILURE (err2))
|
||||
{
|
||||
|
@ -234,9 +241,9 @@ void UCNV_FROM_U_CALLBACK_ESCAPE (UConverter * _this,
|
|||
codepoint[0] = (UChar) UNICODE_PERCENT_SIGN_CODEPOINT; /* adding % */
|
||||
codepoint[1] = (UChar) UNICODE_U_CODEPOINT; /* adding U */
|
||||
|
||||
while (i < _this->invalidUCharLength)
|
||||
while (i < fromArgs->converter->invalidUCharLength)
|
||||
{
|
||||
itou (codepoint + 2, _this->invalidUCharBuffer[i++], 16, 4);
|
||||
itou (codepoint + 2, fromArgs->converter->invalidUCharBuffer[i++], 16, 4);
|
||||
uprv_memcpy (valueString + valueStringLength, codepoint, sizeof (UChar) * 6);
|
||||
valueStringLength += CODEPOINT_STRING_LENGTH - 1;
|
||||
}
|
||||
|
@ -255,13 +262,13 @@ void UCNV_FROM_U_CALLBACK_ESCAPE (UConverter * _this,
|
|||
|
||||
if (U_FAILURE (err2))
|
||||
{
|
||||
UCNV_FROM_U_CALLBACK_SUBSTITUTE (_this,
|
||||
target,
|
||||
targetLimit,
|
||||
source,
|
||||
sourceLimit,
|
||||
offsets,
|
||||
flush,
|
||||
UCNV_FROM_U_CALLBACK_SUBSTITUTE (
|
||||
NULL, /* TO do for HSYS: context */
|
||||
fromArgs,
|
||||
codeUnits,
|
||||
length,
|
||||
codePoint,
|
||||
reason,
|
||||
err);
|
||||
return;
|
||||
}
|
||||
|
@ -273,17 +280,17 @@ void UCNV_FROM_U_CALLBACK_ESCAPE (UConverter * _this,
|
|||
/*if we have enough space on the output buffer we just copy
|
||||
* the subchar there and update the pointer
|
||||
*/
|
||||
if ((targetLimit - *target) >= valueStringLength)
|
||||
if ((fromArgs->targetLimit - *(fromArgs->pTarget)) >= valueStringLength)
|
||||
{
|
||||
uprv_memcpy (*target, myTarget, valueStringLength);
|
||||
*target += valueStringLength;
|
||||
uprv_memcpy (*(fromArgs->pTarget), myTarget, valueStringLength);
|
||||
*(fromArgs->pTarget) += valueStringLength;
|
||||
*err = U_ZERO_ERROR;
|
||||
|
||||
if (offsets)
|
||||
if (fromArgs->offsets)
|
||||
{
|
||||
int j=0;
|
||||
for (j=0;j<valueStringLength;j++) offsets[j]=0;
|
||||
offsets += valueStringLength;
|
||||
for (j=0;j<valueStringLength;j++) fromArgs->offsets[j]=0;
|
||||
fromArgs->offsets += valueStringLength;
|
||||
}
|
||||
}
|
||||
else
|
||||
|
@ -294,18 +301,18 @@ void UCNV_FROM_U_CALLBACK_ESCAPE (UConverter * _this,
|
|||
*length marker
|
||||
*/
|
||||
|
||||
if (offsets)
|
||||
if (fromArgs->offsets)
|
||||
{
|
||||
int j=0;
|
||||
for (j=0;j<(targetLimit - *target);j++) offsets[j]=0;
|
||||
offsets += (targetLimit - *target);
|
||||
for (j=0;j<(fromArgs->targetLimit - *(fromArgs->pTarget));j++) fromArgs->offsets[j]=0;
|
||||
fromArgs->offsets += (fromArgs->targetLimit - *(fromArgs->pTarget));
|
||||
}
|
||||
uprv_memcpy (*target, myTarget, (targetLimit - *target));
|
||||
uprv_memcpy (_this->charErrorBuffer + _this->charErrorBufferLength,
|
||||
myTarget + (targetLimit - *target),
|
||||
valueStringLength - (targetLimit - *target));
|
||||
_this->charErrorBufferLength += valueStringLength - (targetLimit - *target);
|
||||
*target += (targetLimit - *target);
|
||||
uprv_memcpy (*(fromArgs->pTarget), myTarget, (fromArgs->targetLimit - *(fromArgs->pTarget)));
|
||||
uprv_memcpy (fromArgs->converter->charErrorBuffer + fromArgs->converter->charErrorBufferLength,
|
||||
myTarget + (fromArgs->targetLimit - *(fromArgs->pTarget)),
|
||||
valueStringLength - (fromArgs->targetLimit - *(fromArgs->pTarget)));
|
||||
fromArgs->converter->charErrorBufferLength += valueStringLength - (fromArgs->targetLimit - *(fromArgs->pTarget));
|
||||
*(fromArgs->pTarget) += (fromArgs->targetLimit - *(fromArgs->pTarget));
|
||||
*err = U_INDEX_OUTOFBOUNDS_ERROR;
|
||||
}
|
||||
|
||||
|
@ -314,42 +321,40 @@ void UCNV_FROM_U_CALLBACK_ESCAPE (UConverter * _this,
|
|||
|
||||
|
||||
|
||||
void UCNV_TO_U_CALLBACK_SKIP (UConverter * _this,
|
||||
UChar ** target,
|
||||
const UChar * targetLimit,
|
||||
const char **source,
|
||||
const char *sourceLimit,
|
||||
int32_t *offsets,
|
||||
UBool flush,
|
||||
void UCNV_TO_U_CALLBACK_SKIP (
|
||||
void *context,
|
||||
UConverterToUnicodeArgs *toArgs,
|
||||
const char* codeUnits,
|
||||
int32_t length,
|
||||
UConverterCallbackReason reason,
|
||||
UErrorCode * err)
|
||||
{
|
||||
if (CONVERSION_U_SUCCESS (*err)) return;
|
||||
*err = U_ZERO_ERROR;
|
||||
}
|
||||
|
||||
void UCNV_TO_U_CALLBACK_SUBSTITUTE (UConverter * _this,
|
||||
UChar ** target,
|
||||
const UChar * targetLimit,
|
||||
const char **source,
|
||||
const char *sourceLimit,
|
||||
int32_t *offsets,
|
||||
UBool flush,
|
||||
UErrorCode * err)
|
||||
void UCNV_TO_U_CALLBACK_SUBSTITUTE (
|
||||
void *context,
|
||||
UConverterToUnicodeArgs *toArgs,
|
||||
const char* codeUnits,
|
||||
int32_t length,
|
||||
UConverterCallbackReason reason,
|
||||
UErrorCode * err)
|
||||
{
|
||||
|
||||
if (CONVERSION_U_SUCCESS (*err)) return;
|
||||
|
||||
if ((targetLimit - *target) >= 1)
|
||||
if ((toArgs->targetLimit - *(toArgs->pTarget)) >= 1)
|
||||
{
|
||||
**target = 0xFFFD;
|
||||
(*target)++;
|
||||
if (offsets) *offsets = 0;
|
||||
**(toArgs->pTarget) = 0xFFFD;
|
||||
(*(toArgs->pTarget))++;
|
||||
if (toArgs->offsets) *(toArgs->offsets) = 0;
|
||||
*err = U_ZERO_ERROR;
|
||||
}
|
||||
else
|
||||
{
|
||||
_this->UCharErrorBuffer[_this->UCharErrorBufferLength] = 0xFFFD;
|
||||
_this->UCharErrorBufferLength++;
|
||||
toArgs->converter->UCharErrorBuffer[toArgs->converter->UCharErrorBufferLength] = 0xFFFD;
|
||||
toArgs->converter->UCharErrorBufferLength++;
|
||||
*err = U_INDEX_OUTOFBOUNDS_ERROR;
|
||||
}
|
||||
|
||||
|
@ -360,14 +365,13 @@ void UCNV_TO_U_CALLBACK_SUBSTITUTE (UConverter * _this,
|
|||
/*uses itou to get a unicode escape sequence of the offensive sequence,
|
||||
*and uses that as the substitution sequence
|
||||
*/
|
||||
void UCNV_TO_U_CALLBACK_ESCAPE (UConverter * _this,
|
||||
UChar ** target,
|
||||
const UChar * targetLimit,
|
||||
const char **source,
|
||||
const char *sourceLimit,
|
||||
int32_t *offsets,
|
||||
UBool flush,
|
||||
UErrorCode * err)
|
||||
void UCNV_TO_U_CALLBACK_ESCAPE (
|
||||
void *context,
|
||||
UConverterToUnicodeArgs *toArgs,
|
||||
const char* codeUnits,
|
||||
int32_t length,
|
||||
UConverterCallbackReason reason,
|
||||
UErrorCode * err)
|
||||
{
|
||||
UChar uniValueString[VALUE_STRING_LENGTH];
|
||||
int32_t valueStringLength = 0;
|
||||
|
@ -379,24 +383,24 @@ void UCNV_TO_U_CALLBACK_ESCAPE (UConverter * _this,
|
|||
codepoint[0] = (UChar) UNICODE_PERCENT_SIGN_CODEPOINT; /* adding % */
|
||||
codepoint[1] = (UChar) UNICODE_X_CODEPOINT; /* adding X */
|
||||
|
||||
while (i < _this->invalidCharLength)
|
||||
while (i < toArgs->converter->invalidCharLength)
|
||||
{
|
||||
itou (codepoint + 2, _this->invalidCharBuffer[i++], 16, 2);
|
||||
itou (codepoint + 2, toArgs->converter->invalidCharBuffer[i++], 16, 2);
|
||||
uprv_memcpy (uniValueString + valueStringLength, codepoint, sizeof (UChar) * 4);
|
||||
valueStringLength += 4;
|
||||
}
|
||||
|
||||
if ((targetLimit - *target) >= valueStringLength)
|
||||
if ((toArgs->targetLimit - *(toArgs->pTarget)) >= valueStringLength)
|
||||
{
|
||||
/*if we have enough space on the output buffer we just copy
|
||||
* the subchar there and update the pointer
|
||||
*/
|
||||
uprv_memcpy (*target, uniValueString, (sizeof (UChar)) * (valueStringLength));
|
||||
if (offsets)
|
||||
uprv_memcpy (*(toArgs->pTarget), uniValueString, (sizeof (UChar)) * (valueStringLength));
|
||||
if (toArgs->offsets)
|
||||
{
|
||||
for (i = 0; i < valueStringLength; i++) offsets[i] = 0;
|
||||
for (i = 0; i < valueStringLength; i++) toArgs->offsets[i] = 0;
|
||||
}
|
||||
*target += valueStringLength;
|
||||
*(toArgs->pTarget) += valueStringLength;
|
||||
|
||||
*err = U_ZERO_ERROR;
|
||||
}
|
||||
|
@ -407,18 +411,18 @@ void UCNV_TO_U_CALLBACK_ESCAPE (UConverter * _this,
|
|||
*copy the rest in the internal buffer, and increase the
|
||||
*length marker
|
||||
*/
|
||||
uprv_memcpy (*target, uniValueString, (sizeof (UChar)) * (targetLimit - *target));
|
||||
if (offsets)
|
||||
uprv_memcpy (*(toArgs->pTarget), uniValueString, (sizeof (UChar)) * (toArgs->targetLimit - *(toArgs->pTarget)));
|
||||
if (toArgs->offsets)
|
||||
{
|
||||
for (i = 0; i < (targetLimit - *target); i++) offsets[i] = 0;
|
||||
for (i = 0; i < (toArgs->targetLimit - *(toArgs->pTarget)); i++) toArgs->offsets[i] = 0;
|
||||
}
|
||||
|
||||
|
||||
uprv_memcpy (_this->UCharErrorBuffer,
|
||||
uniValueString + (targetLimit - *target),
|
||||
(sizeof (UChar)) * (valueStringLength - (targetLimit - *target)));
|
||||
_this->UCharErrorBufferLength += valueStringLength - (targetLimit - *target);
|
||||
*target += (targetLimit - *target);
|
||||
uprv_memcpy (toArgs->converter->UCharErrorBuffer,
|
||||
uniValueString + (toArgs->targetLimit - *(toArgs->pTarget)),
|
||||
(sizeof (UChar)) * (valueStringLength - (toArgs->targetLimit - *(toArgs->pTarget))));
|
||||
toArgs->converter->UCharErrorBufferLength += valueStringLength - (toArgs->targetLimit - *(toArgs->pTarget));
|
||||
*(toArgs->pTarget) += (toArgs->targetLimit - *(toArgs->pTarget));
|
||||
*err = U_INDEX_OUTOFBOUNDS_ERROR;
|
||||
}
|
||||
|
||||
|
|
|
@ -21,6 +21,7 @@
|
|||
#define UCNV_IMP_H
|
||||
|
||||
#include "unicode/utypes.h"
|
||||
#include "ucnv_bld.h"
|
||||
|
||||
#ifndef UHASH_H
|
||||
typedef struct _UHashtable UHashtable;
|
||||
|
|
|
@ -26,7 +26,8 @@
|
|||
#include "cmemory.h"
|
||||
#include "ucmp16.h"
|
||||
#include "ucmp8.h"
|
||||
#include "unicode/ucnv_bld.h"
|
||||
#include "unicode/ucnv_err.h"
|
||||
#include "ucnv_bld.h"
|
||||
#include "unicode/ucnv.h"
|
||||
#include "ucnv_cnv.h"
|
||||
|
||||
|
|
|
@ -10,12 +10,17 @@
|
|||
*
|
||||
* created on: 2000feb03
|
||||
* created by: Markus W. Scherer
|
||||
*
|
||||
* Change history:
|
||||
*
|
||||
* 06/29/2000 helena Major rewrite of the callback APIs.
|
||||
*/
|
||||
|
||||
#include "unicode/utypes.h"
|
||||
#include "ucmp16.h"
|
||||
#include "ucmp8.h"
|
||||
#include "unicode/ucnv_bld.h"
|
||||
#include "unicode/ucnv_err.h"
|
||||
#include "ucnv_bld.h"
|
||||
#include "unicode/ucnv.h"
|
||||
#include "ucnv_cnv.h"
|
||||
|
||||
|
@ -65,8 +70,8 @@ void T_UConverter_toUnicode_UTF8 (UConverter * _this,
|
|||
UBool flush,
|
||||
UErrorCode * err)
|
||||
{
|
||||
const unsigned char *mySource = (unsigned char *) *source;
|
||||
UChar *myTarget = *target;
|
||||
const unsigned char *mySource = (unsigned char *) *source, *srcTemp;
|
||||
UChar *myTarget = *target, *tgtTemp;
|
||||
int32_t mySourceIndex = 0;
|
||||
int32_t myTargetIndex = 0;
|
||||
int32_t targetLength = targetLimit - myTarget;
|
||||
|
@ -75,7 +80,9 @@ void T_UConverter_toUnicode_UTF8 (UConverter * _this,
|
|||
ch2 =0 ,
|
||||
i =0; /* Index into the current # of bytes consumed in the current sequence */
|
||||
uint32_t inBytes = 0; /* Total number of bytes in the current UTF8 sequence */
|
||||
UConverterToUnicodeArgs args;
|
||||
|
||||
args.sourceStart = *source;
|
||||
if (_this->toUnicodeStatus)
|
||||
{
|
||||
i = _this->invalidCharLength; /* restore # of bytes consumed */
|
||||
|
@ -170,18 +177,26 @@ void T_UConverter_toUnicode_UTF8 (UConverter * _this,
|
|||
printf("inbytes %d\n, _this->invalidCharLength = %d,\n mySource[mySourceIndex]=%X\n", inBytes, _this->invalidCharLength, mySource[mySourceIndex]);
|
||||
#endif
|
||||
/* Needed explicit cast for mySource on MVS to make compiler happy - JJD */
|
||||
ToU_CALLBACK_MACRO(_this,
|
||||
myTarget,
|
||||
myTargetIndex,
|
||||
targetLimit,
|
||||
(const char *)mySource,
|
||||
mySourceIndex,
|
||||
sourceLimit,
|
||||
offsets,
|
||||
flush,
|
||||
args.converter = _this;
|
||||
srcTemp = mySource + mySourceIndex;
|
||||
tgtTemp = myTarget + myTargetIndex;
|
||||
args.pTarget = &tgtTemp;
|
||||
args.targetLimit = targetLimit;
|
||||
args.pSource = &srcTemp;
|
||||
args.sourceLimit = sourceLimit;
|
||||
args.flush = flush;
|
||||
args.offsets = offsets+myTargetIndex;
|
||||
args.size = sizeof(args);
|
||||
ToU_CALLBACK_MACRO(_this->toUContext,
|
||||
args,
|
||||
srcTemp,
|
||||
1,
|
||||
UCNV_UNASSIGNED,
|
||||
err);
|
||||
if (U_FAILURE (*err)) break;
|
||||
_this->invalidCharLength = 0;
|
||||
myTargetIndex = *(args.pTarget) - myTarget;
|
||||
mySourceIndex = *(args.pSource) - mySource;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
@ -208,15 +223,17 @@ void T_UConverter_toUnicode_UTF8_OFFSETS_LOGIC (UConverter * _this,
|
|||
UBool flush,
|
||||
UErrorCode * err)
|
||||
{
|
||||
const unsigned char *mySource = (unsigned char *) *source;
|
||||
UChar *myTarget = *target;
|
||||
const unsigned char *mySource = (unsigned char *) *source, *srcTemp;
|
||||
UChar *myTarget = *target, *tgtTemp;
|
||||
int32_t mySourceIndex = 0;
|
||||
int32_t myTargetIndex = 0;
|
||||
int32_t targetLength = targetLimit - myTarget;
|
||||
int32_t sourceLength = sourceLimit - (char *) mySource;
|
||||
uint32_t ch = 0, ch2 = 0, i = 0;
|
||||
uint32_t inBytes = 0;
|
||||
UConverterToUnicodeArgs args;
|
||||
|
||||
args.sourceStart = *source;
|
||||
if (_this->toUnicodeStatus)
|
||||
{
|
||||
i = _this->invalidCharLength;
|
||||
|
@ -306,21 +323,30 @@ void T_UConverter_toUnicode_UTF8_OFFSETS_LOGIC (UConverter * _this,
|
|||
*err = U_ILLEGAL_CHAR_FOUND;
|
||||
_this->invalidCharLength = (int8_t)i;
|
||||
|
||||
args.converter = _this;
|
||||
srcTemp = mySource + mySourceIndex;
|
||||
tgtTemp = myTarget + myTargetIndex;
|
||||
args.pTarget = &tgtTemp;
|
||||
args.targetLimit = targetLimit;
|
||||
args.pSource = &srcTemp;
|
||||
args.sourceLimit = sourceLimit;
|
||||
args.flush = flush;
|
||||
args.offsets = offsets+myTargetIndex;
|
||||
args.size = sizeof(args);
|
||||
/* To do HSYS: more smarts here, including offsets */
|
||||
ToU_CALLBACK_MACRO(_this->toUContext,
|
||||
args,
|
||||
srcTemp,
|
||||
1,
|
||||
UCNV_UNASSIGNED,
|
||||
err);
|
||||
/* Needed explicit cast for mySource on MVS to make compiler happy - JJD */
|
||||
ToU_CALLBACK_OFFSETS_LOGIC_MACRO(_this,
|
||||
myTarget,
|
||||
myTargetIndex,
|
||||
targetLimit,
|
||||
(const char *)mySource,
|
||||
mySourceIndex,
|
||||
sourceLimit,
|
||||
offsets,
|
||||
flush,
|
||||
err);
|
||||
|
||||
|
||||
if (U_FAILURE (*err)) break;
|
||||
_this->invalidCharLength = 0;
|
||||
myTargetIndex = *(args.pTarget) - myTarget;
|
||||
mySourceIndex = *(args.pSource) - mySource;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
@ -574,8 +600,10 @@ UChar32 T_UConverter_getNextUChar_UTF8(UConverter* converter,
|
|||
uint8_t myByte;
|
||||
UChar32 ch;
|
||||
int8_t isLegalSequence = 1;
|
||||
UConverterToUnicodeArgs args;
|
||||
|
||||
/*Input boundary check*/
|
||||
args.sourceStart = *source;
|
||||
if ((*source) >= sourceLimit)
|
||||
{
|
||||
*err = U_INDEX_OUTOFBOUNDS_ERROR;
|
||||
|
@ -655,14 +683,21 @@ UChar32 T_UConverter_getNextUChar_UTF8(UConverter* converter,
|
|||
|
||||
/*It is very likely that the ErrorFunctor will write to the
|
||||
*internal buffers */
|
||||
converter->fromCharErrorBehaviour(converter,
|
||||
&myUCharPtr,
|
||||
myUCharPtr + 1,
|
||||
&sourceFinal,
|
||||
sourceLimit,
|
||||
NULL,
|
||||
TRUE,
|
||||
err);
|
||||
args.converter = converter;
|
||||
args.pTarget = &myUCharPtr;
|
||||
args.targetLimit = myUCharPtr + 1;
|
||||
args.pSource = &sourceFinal;
|
||||
args.sourceLimit = sourceLimit;
|
||||
args.flush = TRUE;
|
||||
args.offsets = NULL;
|
||||
args.size = sizeof(args);
|
||||
converter->fromCharErrorBehaviour(converter->toUContext,
|
||||
&args,
|
||||
sourceFinal,
|
||||
1,
|
||||
UCNV_UNASSIGNED,
|
||||
err);
|
||||
|
||||
|
||||
/*makes the internal caching transparent to the user*/
|
||||
if (*err == U_INDEX_OUTOFBOUNDS_ERROR) *err = U_ZERO_ERROR;
|
||||
|
|
|
@ -10,12 +10,16 @@
|
|||
*
|
||||
* created on: 2000feb07
|
||||
* created by: Markus W. Scherer
|
||||
* Change history:
|
||||
*
|
||||
* 06/29/2000 helena Major rewrite of the callback APIs.
|
||||
*/
|
||||
|
||||
#include "unicode/utypes.h"
|
||||
#include "ucmp16.h"
|
||||
#include "ucmp8.h"
|
||||
#include "unicode/ucnv_bld.h"
|
||||
#include "unicode/ucnv_err.h"
|
||||
#include "ucnv_bld.h"
|
||||
#include "unicode/ucnv.h"
|
||||
#include "ucnv_cnv.h"
|
||||
|
||||
|
@ -68,13 +72,15 @@ static void T_UConverter_fromUnicode_LATIN_1 (UConverter * _this,
|
|||
UBool flush,
|
||||
UErrorCode * err)
|
||||
{
|
||||
const UChar *mySource = *source;
|
||||
unsigned char *myTarget = (unsigned char *) *target;
|
||||
const UChar *mySource = *source, *srcTemp;
|
||||
unsigned char *myTarget = (unsigned char *) *target, *tgtTemp;
|
||||
int32_t mySourceIndex = 0;
|
||||
int32_t myTargetIndex = 0;
|
||||
int32_t targetLength = targetLimit - (char *) myTarget;
|
||||
int32_t sourceLength = sourceLimit - mySource;
|
||||
UConverterFromUnicodeArgs args;
|
||||
|
||||
args.sourceStart = *source;
|
||||
/*writing the char to the output stream */
|
||||
while (mySourceIndex < sourceLength)
|
||||
{
|
||||
|
@ -93,19 +99,29 @@ static void T_UConverter_fromUnicode_LATIN_1 (UConverter * _this,
|
|||
_this->invalidUCharLength = 1;
|
||||
|
||||
/* Needed explicit cast for myTarget on MVS to make compiler happy - JJD */
|
||||
FromU_CALLBACK_MACRO(_this,
|
||||
(char *)myTarget,
|
||||
myTargetIndex,
|
||||
targetLimit,
|
||||
mySource,
|
||||
mySourceIndex,
|
||||
sourceLimit,
|
||||
offsets,
|
||||
flush,
|
||||
err);
|
||||
srcTemp = mySource + mySourceIndex;
|
||||
tgtTemp = myTarget + myTargetIndex;
|
||||
args.converter = _this;
|
||||
args.pTarget = (char**)&tgtTemp;
|
||||
args.targetLimit = targetLimit;
|
||||
args.pSource = &srcTemp;
|
||||
args.sourceLimit = sourceLimit;
|
||||
args.flush = flush;
|
||||
args.offsets = offsets+myTargetIndex;
|
||||
args.size = sizeof(args);
|
||||
|
||||
FromU_CALLBACK_MACRO(args.converter->fromUContext,
|
||||
args,
|
||||
srcTemp,
|
||||
1,
|
||||
(UChar32) (*srcTemp),
|
||||
UCNV_UNASSIGNED,
|
||||
err);
|
||||
|
||||
if (U_FAILURE (*err)) break;
|
||||
_this->invalidUCharLength = 0;
|
||||
myTargetIndex = (unsigned char *) (*(args.pTarget)) - myTarget;
|
||||
mySourceIndex = *(args.pSource) - mySource;
|
||||
}
|
||||
}
|
||||
else
|
||||
|
|
|
@ -14,13 +14,15 @@
|
|||
* Change history:
|
||||
*
|
||||
* 05/09/00 helena Added implementation to handle fallback mappings.
|
||||
* 06/29/2000 helena Major rewrite of the callback APIs.
|
||||
*/
|
||||
|
||||
#include "unicode/utypes.h"
|
||||
#include "cmemory.h"
|
||||
#include "ucmp16.h"
|
||||
#include "ucmp8.h"
|
||||
#include "unicode/ucnv_bld.h"
|
||||
#include "unicode/ucnv_err.h"
|
||||
#include "ucnv_bld.h"
|
||||
#include "unicode/ucnv.h"
|
||||
#include "ucnv_cnv.h"
|
||||
|
||||
|
@ -76,8 +78,8 @@ static void T_UConverter_toUnicode_MBCS (UConverter * _this,
|
|||
UBool flush,
|
||||
UErrorCode * err)
|
||||
{
|
||||
const char *mySource = *source;
|
||||
UChar *myTarget = *target;
|
||||
const char *mySource = *source, *srcTemp;
|
||||
UChar *myTarget = *target, *tgtTemp;
|
||||
int32_t mySourceIndex = 0;
|
||||
int32_t myTargetIndex = 0;
|
||||
int32_t targetLength = targetLimit - myTarget;
|
||||
|
@ -86,10 +88,10 @@ static void T_UConverter_toUnicode_MBCS (UConverter * _this,
|
|||
UChar targetUniChar = 0x0000;
|
||||
UChar mySourceChar = 0x0000;
|
||||
UBool *myStarters = NULL;
|
||||
UConverterToUnicodeArgs args;
|
||||
|
||||
|
||||
|
||||
|
||||
args.sourceStart = *source;
|
||||
myToUnicode = &_this->sharedData->table->mbcs.toUnicode;
|
||||
myToUnicodeFallback = &_this->sharedData->table->mbcs.toUnicodeFallback;
|
||||
myStarters = _this->sharedData->table->mbcs.starters;
|
||||
|
@ -153,19 +155,30 @@ static void T_UConverter_toUnicode_MBCS (UConverter * _this,
|
|||
_this->invalidCharBuffer[0] = (char) mySourceChar;
|
||||
}
|
||||
|
||||
ToU_CALLBACK_MACRO(_this,
|
||||
myTarget,
|
||||
myTargetIndex,
|
||||
targetLimit,
|
||||
mySource,
|
||||
mySourceIndex,
|
||||
sourceLimit,
|
||||
offsets,
|
||||
flush,
|
||||
|
||||
args.converter = _this;
|
||||
srcTemp = mySource + mySourceIndex;
|
||||
tgtTemp = myTarget + myTargetIndex;
|
||||
args.pTarget = &tgtTemp;
|
||||
args.targetLimit = targetLimit;
|
||||
args.pSource = &srcTemp;
|
||||
args.sourceLimit = sourceLimit;
|
||||
args.flush = flush;
|
||||
args.offsets = offsets+myTargetIndex;
|
||||
args.size = sizeof(args);
|
||||
|
||||
/* to do hsys: add more smarts to the codeUnits and length later */
|
||||
ToU_CALLBACK_MACRO(_this->toUContext,
|
||||
args,
|
||||
srcTemp,
|
||||
1,
|
||||
UCNV_UNASSIGNED,
|
||||
err);
|
||||
|
||||
if (U_FAILURE (*err)) break;
|
||||
_this->invalidCharLength = 0;
|
||||
myTargetIndex = *(args.pTarget) - myTarget;
|
||||
mySourceIndex = *(args.pSource) - mySource;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
@ -205,8 +218,8 @@ static void T_UConverter_toUnicode_MBCS_OFFSETS_LOGIC (UConverter * _this,
|
|||
UBool flush,
|
||||
UErrorCode * err)
|
||||
{
|
||||
const char *mySource = *source;
|
||||
UChar *myTarget = *target;
|
||||
const char *mySource = *source, *srcTemp;
|
||||
UChar *myTarget = *target, *tgtTemp;
|
||||
int32_t mySourceIndex = 0;
|
||||
int32_t myTargetIndex = 0;
|
||||
int32_t targetLength = targetLimit - myTarget;
|
||||
|
@ -216,11 +229,13 @@ static void T_UConverter_toUnicode_MBCS_OFFSETS_LOGIC (UConverter * _this,
|
|||
UChar mySourceChar = 0x0000;
|
||||
UChar oldMySourceChar = 0x0000;
|
||||
UBool *myStarters = NULL;
|
||||
|
||||
UConverterToUnicodeArgs args;
|
||||
|
||||
args.sourceStart = *source;
|
||||
myToUnicode = &_this->sharedData->table->mbcs.toUnicode;
|
||||
myToUnicodeFallback = &_this->sharedData->table->mbcs.toUnicodeFallback;
|
||||
myStarters = _this->sharedData->table->mbcs.starters;
|
||||
|
||||
|
||||
while (mySourceIndex < sourceLength)
|
||||
{
|
||||
if (myTargetIndex < targetLength)
|
||||
|
@ -302,20 +317,29 @@ static void T_UConverter_toUnicode_MBCS_OFFSETS_LOGIC (UConverter * _this,
|
|||
_this->invalidCharLength = 1;
|
||||
_this->invalidCharBuffer[0] = (char) mySourceChar;
|
||||
}
|
||||
args.converter = _this;
|
||||
srcTemp = mySource + mySourceIndex;
|
||||
tgtTemp = myTarget + myTargetIndex;
|
||||
args.pTarget = &tgtTemp;
|
||||
args.targetLimit = targetLimit;
|
||||
args.pSource = &srcTemp;
|
||||
args.sourceLimit = sourceLimit;
|
||||
args.flush = flush;
|
||||
args.offsets = offsets+myTargetIndex;
|
||||
args.size = sizeof(args);
|
||||
|
||||
ToU_CALLBACK_OFFSETS_LOGIC_MACRO(_this,
|
||||
myTarget,
|
||||
myTargetIndex,
|
||||
targetLimit,
|
||||
mySource,
|
||||
mySourceIndex,
|
||||
sourceLimit,
|
||||
offsets,
|
||||
flush,
|
||||
err);
|
||||
/* to do hsys: add more smarts to the codeUnits and length later and offsets */
|
||||
ToU_CALLBACK_MACRO(_this->toUContext,
|
||||
args,
|
||||
srcTemp,
|
||||
1,
|
||||
UCNV_UNASSIGNED,
|
||||
err);
|
||||
|
||||
if (U_FAILURE (*err)) break;
|
||||
_this->invalidCharLength = 0;
|
||||
myTargetIndex = *(args.pTarget) - myTarget;
|
||||
mySourceIndex = *(args.pSource) - mySource;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
@ -356,8 +380,8 @@ static void T_UConverter_fromUnicode_MBCS (UConverter * _this,
|
|||
UErrorCode * err)
|
||||
|
||||
{
|
||||
const UChar *mySource = *source;
|
||||
char *myTarget = *target;
|
||||
const UChar *mySource = *source, *srcTemp;
|
||||
char *myTarget = *target, *tgtTemp;
|
||||
int32_t mySourceIndex = 0;
|
||||
int32_t myTargetIndex = 0;
|
||||
int32_t targetLength = targetLimit - myTarget;
|
||||
|
@ -365,7 +389,9 @@ static void T_UConverter_fromUnicode_MBCS (UConverter * _this,
|
|||
CompactShortArray *myFromUnicode = NULL, *myFromUnicodeFallback = NULL;
|
||||
UChar targetUniChar = 0x0000;
|
||||
UChar mySourceChar = 0x0000;
|
||||
UConverterFromUnicodeArgs args;
|
||||
|
||||
args.sourceStart = *source;
|
||||
myFromUnicode = &_this->sharedData->table->mbcs.fromUnicode;
|
||||
myFromUnicodeFallback = &_this->sharedData->table->mbcs.fromUnicodeFallback;
|
||||
|
||||
|
@ -431,18 +457,28 @@ static void T_UConverter_fromUnicode_MBCS (UConverter * _this,
|
|||
_this->invalidUCharBuffer[0] = (UChar) mySourceChar;
|
||||
_this->invalidUCharLength = 1;
|
||||
|
||||
FromU_CALLBACK_MACRO(_this,
|
||||
myTarget,
|
||||
myTargetIndex,
|
||||
targetLimit,
|
||||
mySource,
|
||||
mySourceIndex,
|
||||
sourceLimit,
|
||||
offsets,
|
||||
flush,
|
||||
err);
|
||||
|
||||
srcTemp = mySource + mySourceIndex;
|
||||
tgtTemp = myTarget + myTargetIndex;
|
||||
args.converter = _this;
|
||||
args.pTarget = &tgtTemp;
|
||||
args.targetLimit = targetLimit;
|
||||
args.pSource = &srcTemp;
|
||||
args.sourceLimit = sourceLimit;
|
||||
args.flush = flush;
|
||||
args.offsets = offsets+myTargetIndex;
|
||||
args.size = sizeof(args);
|
||||
/* Needed explicit cast for myTarget on MVS to make compiler happy - JJD */
|
||||
/* HSYS: to do: more smarts */
|
||||
FromU_CALLBACK_MACRO(args.converter->fromUContext,
|
||||
args,
|
||||
srcTemp,
|
||||
1,
|
||||
(UChar32) (*srcTemp),
|
||||
UCNV_UNASSIGNED,
|
||||
err);
|
||||
if (U_FAILURE (*err)) break;
|
||||
myTargetIndex = *(args.pTarget) - myTarget;
|
||||
mySourceIndex = *(args.pSource) - mySource;
|
||||
_this->invalidUCharLength = 0;
|
||||
}
|
||||
}
|
||||
|
@ -472,8 +508,8 @@ static void T_UConverter_fromUnicode_MBCS_OFFSETS_LOGIC (UConverter * _this,
|
|||
UErrorCode * err)
|
||||
|
||||
{
|
||||
const UChar *mySource = *source;
|
||||
char *myTarget = *target;
|
||||
const UChar *mySource = *source, *srcTemp;
|
||||
char *myTarget = *target, *tgtTemp;
|
||||
int32_t mySourceIndex = 0;
|
||||
int32_t myTargetIndex = 0;
|
||||
int32_t targetLength = targetLimit - myTarget;
|
||||
|
@ -481,7 +517,9 @@ static void T_UConverter_fromUnicode_MBCS_OFFSETS_LOGIC (UConverter * _this,
|
|||
CompactShortArray *myFromUnicode = NULL, *myFromUnicodeFallback = NULL;
|
||||
UChar targetUniChar = 0x0000;
|
||||
UChar mySourceChar = 0x0000;
|
||||
UConverterFromUnicodeArgs args;
|
||||
|
||||
args.sourceStart = *source;
|
||||
myFromUnicode = &_this->sharedData->table->mbcs.fromUnicode;
|
||||
myFromUnicodeFallback = &_this->sharedData->table->mbcs.fromUnicodeFallback;
|
||||
|
||||
|
@ -557,18 +595,30 @@ static void T_UConverter_fromUnicode_MBCS_OFFSETS_LOGIC (UConverter * _this,
|
|||
_this->invalidUCharBuffer[0] = (UChar) mySourceChar;
|
||||
_this->invalidUCharLength = 1;
|
||||
|
||||
FromU_CALLBACK_OFFSETS_LOGIC_MACRO(_this,
|
||||
myTarget,
|
||||
myTargetIndex,
|
||||
targetLimit,
|
||||
mySource,
|
||||
mySourceIndex,
|
||||
sourceLimit,
|
||||
offsets,
|
||||
flush,
|
||||
err);
|
||||
|
||||
srcTemp = mySource + mySourceIndex;
|
||||
tgtTemp = myTarget + myTargetIndex;
|
||||
args.converter = _this;
|
||||
args.pTarget = &tgtTemp;
|
||||
args.targetLimit = targetLimit;
|
||||
args.pSource = &srcTemp;
|
||||
args.sourceLimit = sourceLimit;
|
||||
args.flush = flush;
|
||||
args.offsets = offsets+myTargetIndex;
|
||||
args.size = sizeof(args);
|
||||
/* Needed explicit cast for myTarget on MVS to make compiler happy - JJD */
|
||||
/* HSYS: to do: more smarts including offsets*/
|
||||
FromU_CALLBACK_MACRO(args.converter->fromUContext,
|
||||
args,
|
||||
srcTemp,
|
||||
1,
|
||||
(UChar32) (*srcTemp),
|
||||
UCNV_UNASSIGNED,
|
||||
err);
|
||||
|
||||
if (U_FAILURE (*err)) break;
|
||||
myTargetIndex = *(args.pTarget) - myTarget;
|
||||
mySourceIndex = *(args.pSource) - mySource;
|
||||
_this->invalidUCharLength = 0;
|
||||
}
|
||||
}
|
||||
|
@ -595,6 +645,7 @@ static UChar32 T_UConverter_getNextUChar_MBCS(UConverter* converter,
|
|||
{
|
||||
UChar myUChar;
|
||||
char const *sourceInitial = *source;
|
||||
UConverterToUnicodeArgs args;
|
||||
/*safe keeps a ptr to the beginning in case we need to step back*/
|
||||
|
||||
/*Input boundary check*/
|
||||
|
@ -603,7 +654,7 @@ static UChar32 T_UConverter_getNextUChar_MBCS(UConverter* converter,
|
|||
*err = U_INDEX_OUTOFBOUNDS_ERROR;
|
||||
return 0xFFFD;
|
||||
}
|
||||
|
||||
args.sourceStart = *source;
|
||||
/*Checks to see if the byte is a lead*/
|
||||
if (converter->sharedData->table->mbcs.starters[(uint8_t)**source] == FALSE)
|
||||
{
|
||||
|
@ -654,15 +705,21 @@ static UChar32 T_UConverter_getNextUChar_MBCS(UConverter* converter,
|
|||
|
||||
/*It's is very likely that the ErrorFunctor will write to the
|
||||
*internal buffers */
|
||||
converter->fromCharErrorBehaviour(converter,
|
||||
&myUCharPtr,
|
||||
myUCharPtr + 1,
|
||||
&sourceFinal,
|
||||
sourceLimit,
|
||||
NULL,
|
||||
TRUE,
|
||||
err);
|
||||
|
||||
args.converter = converter;
|
||||
args.pTarget = &myUCharPtr;
|
||||
args.targetLimit = myUCharPtr + 1;
|
||||
args.pSource = &sourceFinal;
|
||||
args.sourceLimit = sourceLimit;
|
||||
args.flush = TRUE;
|
||||
args.offsets = NULL;
|
||||
args.size = sizeof(args);
|
||||
converter->fromCharErrorBehaviour(converter->toUContext,
|
||||
&args,
|
||||
sourceFinal,
|
||||
1,
|
||||
UCNV_UNASSIGNED,
|
||||
err);
|
||||
|
||||
/*makes the internal caching transparent to the user*/
|
||||
if (*err == U_INDEX_OUTOFBOUNDS_ERROR) *err = U_ZERO_ERROR;
|
||||
|
||||
|
|
|
@ -15,13 +15,15 @@
|
|||
*
|
||||
* 05/09/00 helena Added implementation to handle fallback mappings.
|
||||
* 06/20/2000 helena OS/400 port changes; mostly typecast.
|
||||
* 06/29/2000 helena Major rewrite of the callback APIs.
|
||||
*/
|
||||
|
||||
#include "unicode/utypes.h"
|
||||
#include "cmemory.h"
|
||||
#include "ucmp16.h"
|
||||
#include "ucmp8.h"
|
||||
#include "unicode/ucnv_bld.h"
|
||||
#include "unicode/ucnv_err.h"
|
||||
#include "ucnv_bld.h"
|
||||
#include "unicode/ucnv.h"
|
||||
#include "ucnv_cnv.h"
|
||||
|
||||
|
@ -66,17 +68,19 @@ void T_UConverter_toUnicode_SBCS (UConverter * _this,
|
|||
UBool flush,
|
||||
UErrorCode * err)
|
||||
{
|
||||
char *mySource = (char *) *source;
|
||||
UChar *myTarget = *target;
|
||||
char *mySource = (char *) *source, *srcTemp;
|
||||
UChar *myTarget = *target, *tgtTemp;
|
||||
int32_t mySourceIndex = 0;
|
||||
int32_t myTargetIndex = 0;
|
||||
int32_t targetLength = targetLimit - myTarget;
|
||||
int32_t sourceLength = sourceLimit - (char *) mySource;
|
||||
UChar *myToUnicode = NULL, *myToUnicodeFallback = NULL;
|
||||
UChar targetUniChar = 0x0000;
|
||||
UConverterToUnicodeArgs args;
|
||||
|
||||
myToUnicode = _this->sharedData->table->sbcs.toUnicode;
|
||||
myToUnicodeFallback = _this->sharedData->table->sbcs.toUnicodeFallback;
|
||||
args.sourceStart = *source;
|
||||
while (mySourceIndex < sourceLength)
|
||||
{
|
||||
|
||||
|
@ -109,18 +113,28 @@ void T_UConverter_toUnicode_SBCS (UConverter * _this,
|
|||
_this->invalidCharBuffer[0] = (char) mySource[mySourceIndex - 1];
|
||||
_this->invalidCharLength = 1;
|
||||
|
||||
ToU_CALLBACK_MACRO(_this,
|
||||
myTarget,
|
||||
myTargetIndex,
|
||||
targetLimit,
|
||||
mySource,
|
||||
mySourceIndex,
|
||||
sourceLimit,
|
||||
offsets,
|
||||
flush,
|
||||
args.converter = _this;
|
||||
srcTemp = mySource + mySourceIndex;
|
||||
tgtTemp = myTarget + myTargetIndex;
|
||||
args.pTarget = &tgtTemp;
|
||||
args.targetLimit = targetLimit;
|
||||
args.pSource = &srcTemp;
|
||||
args.sourceLimit = sourceLimit;
|
||||
args.flush = flush;
|
||||
args.offsets = offsets+myTargetIndex;
|
||||
args.size = sizeof(args);
|
||||
|
||||
/* to do hsys: add more smarts to the codeUnits and length later */
|
||||
ToU_CALLBACK_MACRO(_this->toUContext,
|
||||
args,
|
||||
srcTemp,
|
||||
1,
|
||||
UCNV_UNASSIGNED,
|
||||
err);
|
||||
|
||||
/* Hsys: calculate the source and target advancement */
|
||||
if (U_FAILURE (*err)) break;
|
||||
myTargetIndex = *(args.pTarget) - myTarget;
|
||||
mySourceIndex = *(args.pSource) - mySource;
|
||||
_this->invalidCharLength = 0;
|
||||
}
|
||||
}
|
||||
|
@ -147,18 +161,19 @@ void T_UConverter_fromUnicode_SBCS (UConverter * _this,
|
|||
UBool flush,
|
||||
UErrorCode * err)
|
||||
{
|
||||
const UChar *mySource = *source;
|
||||
unsigned char *myTarget = (unsigned char *) *target;
|
||||
const UChar *mySource = *source, *srcTemp;
|
||||
unsigned char *myTarget = (unsigned char *) *target, *tgtTemp;
|
||||
int32_t mySourceIndex = 0;
|
||||
int32_t myTargetIndex = 0;
|
||||
int32_t targetLength = targetLimit - (char *) myTarget;
|
||||
int32_t sourceLength = sourceLimit - mySource;
|
||||
CompactByteArray *myFromUnicode = NULL, *myFromUnicodeFallback = NULL;
|
||||
unsigned char targetChar = 0x00;
|
||||
UConverterFromUnicodeArgs args;
|
||||
|
||||
myFromUnicode = &_this->sharedData->table->sbcs.fromUnicode;
|
||||
myFromUnicodeFallback = &_this->sharedData->table->sbcs.fromUnicodeFallback;
|
||||
|
||||
args.sourceStart = *source;
|
||||
/*writing the char to the output stream */
|
||||
while (mySourceIndex < sourceLength)
|
||||
{
|
||||
|
@ -189,21 +204,31 @@ void T_UConverter_fromUnicode_SBCS (UConverter * _this,
|
|||
_this->invalidUCharBuffer[0] = (UChar)mySource[mySourceIndex - 1];
|
||||
_this->invalidUCharLength = 1;
|
||||
|
||||
srcTemp = mySource + mySourceIndex;
|
||||
tgtTemp = myTarget + myTargetIndex;
|
||||
args.converter = _this;
|
||||
args.pTarget = &tgtTemp;
|
||||
args.targetLimit = targetLimit;
|
||||
args.pSource = &srcTemp;
|
||||
args.sourceLimit = sourceLimit;
|
||||
args.flush = flush;
|
||||
args.offsets = offsets+myTargetIndex;
|
||||
args.size = sizeof(args);
|
||||
/* Needed explicit cast for myTarget on MVS to make compiler happy - JJD */
|
||||
FromU_CALLBACK_MACRO(_this,
|
||||
(char *)myTarget,
|
||||
myTargetIndex,
|
||||
targetLimit,
|
||||
mySource,
|
||||
mySourceIndex,
|
||||
sourceLimit,
|
||||
offsets,
|
||||
flush,
|
||||
err);
|
||||
/* HSYS: to do: more smarts */
|
||||
FromU_CALLBACK_MACRO(args.converter->fromUContext,
|
||||
args,
|
||||
srcTemp,
|
||||
1,
|
||||
(UChar32) (*srcTemp),
|
||||
UCNV_UNASSIGNED,
|
||||
err);
|
||||
if (U_FAILURE (*err))
|
||||
{
|
||||
break;
|
||||
}
|
||||
myTargetIndex = *(args.pTarget) - myTarget;
|
||||
mySourceIndex = *(args.pSource) - mySource;
|
||||
_this->invalidUCharLength = 0;
|
||||
}
|
||||
}
|
||||
|
@ -228,15 +253,17 @@ UChar32 T_UConverter_getNextUChar_SBCS(UConverter* converter,
|
|||
UErrorCode* err)
|
||||
{
|
||||
UChar myUChar;
|
||||
|
||||
UConverterToUnicodeArgs args;
|
||||
|
||||
if (U_FAILURE(*err)) return 0xFFFD;
|
||||
|
||||
if ((*source)+1 > sourceLimit)
|
||||
{
|
||||
*err = U_INDEX_OUTOFBOUNDS_ERROR;
|
||||
return 0xFFFD;
|
||||
}
|
||||
|
||||
|
||||
args.sourceStart = *source;
|
||||
/*Gets the corresponding codepoint*/
|
||||
myUChar = converter->sharedData->table->sbcs.toUnicode[(unsigned char)*((*source)++)];
|
||||
|
||||
|
@ -260,14 +287,20 @@ UChar32 T_UConverter_getNextUChar_SBCS(UConverter* converter,
|
|||
(*source)--;
|
||||
/*It's is very likely that the ErrorFunctor will write to the
|
||||
*internal buffers */
|
||||
converter->fromCharErrorBehaviour(converter,
|
||||
&myUCharPtr,
|
||||
myUCharPtr + 1,
|
||||
&sourceFinal,
|
||||
sourceLimit,
|
||||
NULL,
|
||||
TRUE,
|
||||
err);
|
||||
args.converter = converter;
|
||||
args.pTarget = &myUCharPtr;
|
||||
args.targetLimit = myUCharPtr + 1;
|
||||
args.pSource = &sourceFinal;
|
||||
args.sourceLimit = sourceLimit;
|
||||
args.flush = TRUE;
|
||||
args.offsets = NULL;
|
||||
args.size = sizeof(args);
|
||||
converter->fromCharErrorBehaviour(converter->toUContext,
|
||||
&args,
|
||||
sourceFinal,
|
||||
1,
|
||||
UCNV_UNASSIGNED,
|
||||
err);
|
||||
|
||||
/*makes the internal caching transparent to the user*/
|
||||
if (*err == U_INDEX_OUTOFBOUNDS_ERROR) *err = U_ZERO_ERROR;
|
||||
|
@ -354,8 +387,8 @@ void T_UConverter_toUnicode_DBCS (UConverter * _this,
|
|||
UBool flush,
|
||||
UErrorCode * err)
|
||||
{
|
||||
const char *mySource = ( char *) *source;
|
||||
UChar *myTarget = *target;
|
||||
const char *mySource = ( char *) *source, *srcTemp;
|
||||
UChar *myTarget = *target, *tgtTemp;
|
||||
int32_t mySourceIndex = 0;
|
||||
int32_t myTargetIndex = 0;
|
||||
int32_t targetLength = targetLimit - myTarget;
|
||||
|
@ -363,9 +396,11 @@ void T_UConverter_toUnicode_DBCS (UConverter * _this,
|
|||
CompactShortArray *myToUnicode = NULL, *myToUnicodeFallback = NULL;
|
||||
UChar targetUniChar = 0x0000;
|
||||
UChar mySourceChar = 0x0000;
|
||||
UConverterToUnicodeArgs args;
|
||||
|
||||
myToUnicode = &_this->sharedData->table->dbcs.toUnicode;
|
||||
myToUnicodeFallback = &_this->sharedData->table->dbcs.toUnicodeFallback;
|
||||
args.sourceStart = *source;
|
||||
|
||||
while (mySourceIndex < sourceLength)
|
||||
{
|
||||
|
@ -412,18 +447,28 @@ void T_UConverter_toUnicode_DBCS (UConverter * _this,
|
|||
_this->invalidCharBuffer[1] = (char) mySourceChar;
|
||||
_this->invalidCharLength = 2;
|
||||
|
||||
ToU_CALLBACK_MACRO(_this,
|
||||
myTarget,
|
||||
myTargetIndex,
|
||||
targetLimit,
|
||||
mySource,
|
||||
mySourceIndex,
|
||||
sourceLimit,
|
||||
offsets,
|
||||
flush,
|
||||
err);
|
||||
srcTemp = mySource + mySourceIndex;
|
||||
tgtTemp = myTarget + myTargetIndex;
|
||||
args.converter = _this;
|
||||
args.pTarget = &tgtTemp;
|
||||
args.targetLimit = targetLimit;
|
||||
args.pSource = &srcTemp;
|
||||
args.sourceLimit = sourceLimit;
|
||||
args.flush = flush;
|
||||
args.offsets = offsets+myTargetIndex;
|
||||
args.size = sizeof(args);
|
||||
|
||||
if (U_FAILURE (*err)) break;
|
||||
/* to do hsys: add more smarts to the codeUnits and length later */
|
||||
ToU_CALLBACK_MACRO(_this->toUContext,
|
||||
args,
|
||||
srcTemp,
|
||||
2,
|
||||
UCNV_UNASSIGNED,
|
||||
err);
|
||||
/* Hsys: calculate the source and target advancement */
|
||||
if (U_FAILURE (*err)) break;
|
||||
myTargetIndex = *(args.pTarget) - myTarget;
|
||||
mySourceIndex = *(args.pSource) - mySource;
|
||||
_this->invalidCharLength = 0;
|
||||
}
|
||||
}
|
||||
|
@ -465,8 +510,8 @@ void T_UConverter_fromUnicode_DBCS (UConverter * _this,
|
|||
UBool flush,
|
||||
UErrorCode * err)
|
||||
{
|
||||
const UChar *mySource = *source;
|
||||
unsigned char *myTarget = (unsigned char *) *target;
|
||||
const UChar *mySource = *source, *srcTemp;
|
||||
unsigned char *myTarget = (unsigned char *) *target, *tgtTemp;
|
||||
int32_t mySourceIndex = 0;
|
||||
int32_t myTargetIndex = 0;
|
||||
int32_t targetLength = targetLimit - (char *) myTarget;
|
||||
|
@ -474,9 +519,11 @@ void T_UConverter_fromUnicode_DBCS (UConverter * _this,
|
|||
CompactShortArray *myFromUnicode = NULL, *myFromUnicodeFallback = NULL;
|
||||
UChar targetUniChar = 0x0000;
|
||||
UChar mySourceChar = 0x0000;
|
||||
UConverterFromUnicodeArgs args;
|
||||
|
||||
myFromUnicode = &_this->sharedData->table->dbcs.fromUnicode;
|
||||
myFromUnicodeFallback = &_this->sharedData->table->dbcs.fromUnicodeFallback;
|
||||
args.sourceStart = *source;
|
||||
|
||||
/*writing the char to the output stream */
|
||||
while (mySourceIndex < sourceLength)
|
||||
|
@ -532,18 +579,30 @@ void T_UConverter_fromUnicode_DBCS (UConverter * _this,
|
|||
|
||||
|
||||
/* Needed explicit cast for myTarget on MVS to make compiler happy - JJD */
|
||||
FromU_CALLBACK_MACRO(_this,
|
||||
(char *)myTarget,
|
||||
myTargetIndex,
|
||||
targetLimit,
|
||||
mySource,
|
||||
mySourceIndex,
|
||||
sourceLimit,
|
||||
offsets,
|
||||
flush,
|
||||
err);
|
||||
|
||||
if (U_FAILURE (*err)) break;
|
||||
/* HSYS: to do: more smarts */
|
||||
srcTemp = mySource + mySourceIndex;
|
||||
tgtTemp = myTarget + myTargetIndex;
|
||||
args.converter = _this;
|
||||
args.pTarget = &tgtTemp;
|
||||
args.targetLimit = targetLimit;
|
||||
args.pSource = &srcTemp;
|
||||
args.sourceLimit = sourceLimit;
|
||||
args.flush = flush;
|
||||
args.offsets = offsets+myTargetIndex;
|
||||
args.size = sizeof(args);
|
||||
FromU_CALLBACK_MACRO(args.converter->fromUContext,
|
||||
args,
|
||||
srcTemp,
|
||||
1,
|
||||
(UChar32) (*srcTemp),
|
||||
UCNV_UNASSIGNED,
|
||||
err);
|
||||
if (U_FAILURE (*err))
|
||||
{
|
||||
break;
|
||||
}
|
||||
myTargetIndex = *(args.pTarget) - myTarget;
|
||||
mySourceIndex = *(args.pSource) - mySource;
|
||||
_this->invalidUCharLength = 0;
|
||||
}
|
||||
}
|
||||
|
@ -567,7 +626,9 @@ UChar32 T_UConverter_getNextUChar_DBCS(UConverter* converter,
|
|||
UErrorCode* err)
|
||||
{
|
||||
UChar myUChar;
|
||||
UConverterToUnicodeArgs args;
|
||||
|
||||
if (U_FAILURE(*err)) return 0xFFFD;
|
||||
/*Checks boundaries and set appropriate error codes*/
|
||||
if ((*source)+2 > sourceLimit)
|
||||
{
|
||||
|
@ -584,7 +645,8 @@ UChar32 T_UConverter_getNextUChar_DBCS(UConverter* converter,
|
|||
|
||||
return 0xFFFD;
|
||||
}
|
||||
|
||||
|
||||
args.sourceStart = *source;
|
||||
/*Gets the corresponding codepoint*/
|
||||
myUChar = ucmp16_getu((&converter->sharedData->table->dbcs.toUnicode),
|
||||
(uint16_t)(((UChar)((**source)) << 8) |((uint8_t)*((*source)+1))));
|
||||
|
@ -614,16 +676,22 @@ UChar32 T_UConverter_getNextUChar_DBCS(UConverter* converter,
|
|||
|
||||
*err = U_INVALID_CHAR_FOUND;
|
||||
|
||||
args.converter = converter;
|
||||
args.pTarget = &myUCharPtr;
|
||||
args.targetLimit = myUCharPtr + 1;
|
||||
args.pSource = &sourceFinal;
|
||||
args.sourceLimit = sourceLimit;
|
||||
args.flush = TRUE;
|
||||
args.offsets = NULL;
|
||||
args.size = sizeof(args);
|
||||
/*It's is very likely that the ErrorFunctor will write to the
|
||||
*internal buffers */
|
||||
converter->fromCharErrorBehaviour(converter,
|
||||
&myUCharPtr,
|
||||
myUCharPtr + 1,
|
||||
&sourceFinal,
|
||||
sourceLimit,
|
||||
NULL,
|
||||
TRUE,
|
||||
err);
|
||||
converter->fromCharErrorBehaviour(converter->toUContext,
|
||||
&args,
|
||||
sourceFinal,
|
||||
1,
|
||||
UCNV_UNASSIGNED,
|
||||
err);
|
||||
/*makes the internal caching transparent to the user*/
|
||||
if (*err == U_INDEX_OUTOFBOUNDS_ERROR) *err = U_ZERO_ERROR;
|
||||
|
||||
|
|
|
@ -3,6 +3,10 @@
|
|||
* Copyright (C) 1998-1999, International Business Machines
|
||||
* Corporation and others. All Rights Reserved.
|
||||
*
|
||||
*
|
||||
* Change history:
|
||||
*
|
||||
* 06/29/2000 helena Major rewrite of the callback APIs.
|
||||
*******************************************************************************/
|
||||
|
||||
#ifndef CONVERT_H
|
||||
|
@ -288,21 +292,34 @@ const char* getName( UErrorCode& err) const;
|
|||
/**
|
||||
* Sets the current setting action taken when a character from a codepage is
|
||||
* missing. (Currently STOP or SUBSTITUTE).
|
||||
* @param action the action constant if an equivalent codepage character is missing
|
||||
* @param newAction the action constant if an equivalent codepage character is missing
|
||||
* @param newContext the new toUnicode callback function state
|
||||
* @param oldAction the original action constant, saved for later restoration.
|
||||
* @param oldContext the old toUnicode callback function state
|
||||
* @param err the error status code
|
||||
* @stable
|
||||
*/
|
||||
void setMissingCharAction(UConverterToUCallback action,
|
||||
void setMissingCharAction(UConverterToUCallback newAction,
|
||||
void* newContext,
|
||||
UConverterToUCallback oldAction,
|
||||
void** oldContext,
|
||||
UErrorCode& err);
|
||||
|
||||
/**
|
||||
* Sets the current setting action taken when a unicode character is missing.
|
||||
* (currently T_UnicodeConverter_MissingUnicodeAction is either STOP or SUBSTITUTE,
|
||||
* SKIP, CLOSEST_MATCH, ESCAPE_SEQ may be added in the future).
|
||||
* @param action the action constant if an equivalent Unicode character is missing
|
||||
* @param newAction the action constant if an equivalent Unicode character is missing
|
||||
* @param newContext the new fromUnicode callback function state
|
||||
* @param oldAction the original action constant, saved for later restoration.
|
||||
* @param oldContext the old fromUnicode callback function state
|
||||
* @param err the error status code
|
||||
* @stable
|
||||
*/
|
||||
void setMissingUnicodeAction(UConverterFromUCallback action,
|
||||
void setMissingUnicodeAction(UConverterFromUCallback newAction,
|
||||
void* newContext,
|
||||
UConverterFromUCallback oldAction,
|
||||
void** oldContext,
|
||||
UErrorCode& err);
|
||||
/**
|
||||
* Returns the localized name of the UnicodeConverter, if for any reason it is
|
||||
|
|
|
@ -12,6 +12,7 @@
|
|||
* Date Name Description
|
||||
* 04/04/99 helena Fixed internal header inclusion.
|
||||
* 05/11/00 helena Added setFallback and usesFallback APIs.
|
||||
* 06/29/2000 helena Major rewrite of the callback APIs.
|
||||
*/
|
||||
|
||||
/**
|
||||
|
@ -25,27 +26,81 @@
|
|||
#define UCNV_H
|
||||
|
||||
#include "unicode/utypes.h"
|
||||
#include "unicode/ucnv_bld.h"
|
||||
#include "unicode/ucnv_err.h"
|
||||
|
||||
U_CDECL_BEGIN
|
||||
|
||||
typedef void (*UConverterToUCallback) (UConverter *,
|
||||
UChar **,
|
||||
const UChar *,
|
||||
const char **,
|
||||
const char *,
|
||||
int32_t* offsets,
|
||||
UBool,
|
||||
|
||||
#define UCNV_MAX_SUBCHAR_LEN 4
|
||||
#define UCNV_ERROR_BUFFER_LENGTH 20
|
||||
#define UCNV_MAX_AMBIGUOUSCCSIDS 5
|
||||
|
||||
#define UCNV_IMPLEMENTED_CONVERSION_TYPES 9
|
||||
/*Sentinel Value used to check the integrity of the binary data files */
|
||||
|
||||
#define UCNV_FILE_CHECK_MARKER 0xBEDA
|
||||
|
||||
/*maximum length of the converter names */
|
||||
#define UCNV_MAX_CONVERTER_NAME_LENGTH 60
|
||||
#define UCNV_MAX_FULL_FILE_NAME_LENGTH (600+UCNV_MAX_CONVERTER_NAME_LENGTH)
|
||||
|
||||
/*Pointer to the aforementioned file */
|
||||
#define UCNV_MAX_LINE_TEXT (UCNV_MAX_CONVERTER_NAME_LENGTH*400)
|
||||
|
||||
#define UCNV_SI 0x0F /*Shift in for EBDCDIC_STATEFUL and iso2022 states */
|
||||
#define UCNV_SO 0x0E /*Shift out for EBDCDIC_STATEFUL and iso2022 states */
|
||||
|
||||
typedef enum {
|
||||
UCNV_UNSUPPORTED_CONVERTER = -1,
|
||||
UCNV_SBCS = 0,
|
||||
UCNV_DBCS = 1,
|
||||
UCNV_MBCS = 2,
|
||||
UCNV_LATIN_1 = 3,
|
||||
UCNV_UTF8 = 4,
|
||||
UCNV_UTF16_BigEndian = 5,
|
||||
UCNV_UTF16_LittleEndian = 6,
|
||||
UCNV_EBCDIC_STATEFUL = 7,
|
||||
UCNV_ISO_2022 = 8,
|
||||
|
||||
UCNV_LMBCS_1 = 9,
|
||||
UCNV_LMBCS_2,
|
||||
UCNV_LMBCS_3,
|
||||
UCNV_LMBCS_4,
|
||||
UCNV_LMBCS_5,
|
||||
UCNV_LMBCS_6,
|
||||
UCNV_LMBCS_8,
|
||||
UCNV_LMBCS_11,
|
||||
UCNV_LMBCS_16,
|
||||
UCNV_LMBCS_17,
|
||||
UCNV_LMBCS_18,
|
||||
UCNV_LMBCS_19,
|
||||
UCNV_LMBCS_LAST = UCNV_LMBCS_19,
|
||||
|
||||
/* Number of converter types for which we have conversion routines. */
|
||||
UCNV_NUMBER_OF_SUPPORTED_CONVERTER_TYPES = UCNV_LMBCS_LAST+1
|
||||
|
||||
} UConverterType;
|
||||
|
||||
typedef enum {
|
||||
UCNV_UNKNOWN = -1,
|
||||
UCNV_IBM = 0
|
||||
} UConverterPlatform;
|
||||
|
||||
typedef void (*UConverterToUCallback) (
|
||||
void* context,
|
||||
UConverterToUnicodeArgs *args,
|
||||
const char *codePoints,
|
||||
int32_t length,
|
||||
UConverterCallbackReason reason,
|
||||
UErrorCode *);
|
||||
|
||||
typedef void (*UConverterFromUCallback) (UConverter *,
|
||||
char **,
|
||||
const char *,
|
||||
const UChar **,
|
||||
const UChar *,
|
||||
int32_t* offsets,
|
||||
UBool,
|
||||
typedef void (*UConverterFromUCallback) (
|
||||
void* context,
|
||||
UConverterFromUnicodeArgs *args,
|
||||
const UChar* codeUnits,
|
||||
int32_t length,
|
||||
UChar32 codePoint, /* HSYS: why can't just use the macros on the code units? */
|
||||
UConverterCallbackReason reason,
|
||||
UErrorCode *);
|
||||
|
||||
U_CDECL_END
|
||||
|
@ -384,30 +439,40 @@ U_CAPI UConverterFromUCallback U_EXPORT2
|
|||
* Gets the current callback function used by the converter when illegal or invalid sequence found.
|
||||
*
|
||||
* @param converter the unicode converter
|
||||
* @param action the callback function we want to set.
|
||||
* @param newAction the callback function we want to set.
|
||||
* @param newContext the new toUnicode callback function state
|
||||
* @param oldAction the previously assigned callback function pointer
|
||||
* @param oldContext the new toUnicode callback function state
|
||||
* @param err The error code status
|
||||
* @return the previously assigned callback function pointer
|
||||
* @see ucnv_getToUCallBack
|
||||
* @stable
|
||||
*/
|
||||
U_CAPI UConverterToUCallback U_EXPORT2
|
||||
U_CAPI void U_EXPORT2
|
||||
ucnv_setToUCallBack (UConverter * converter,
|
||||
UConverterToUCallback action,
|
||||
UConverterToUCallback newAction,
|
||||
void* newContext,
|
||||
UConverterToUCallback oldAction,
|
||||
void** oldContext,
|
||||
UErrorCode * err);
|
||||
|
||||
/**
|
||||
* Gets the current callback function used by the converter when illegal or invalid sequence found.
|
||||
*
|
||||
* @param converter the unicode converter
|
||||
* @param action the callback function we want to set.
|
||||
* @param newAction the callback function we want to set.
|
||||
* @param newContext the new fromUnicode callback function state
|
||||
* @param oldAction the previously assigned callback function pointer
|
||||
* @param oldContext the new fromUnicode callback function state
|
||||
* @param err The error code status
|
||||
* @return the previously assigned callback function pointer
|
||||
* @see ucnv_getFromUCallBack
|
||||
* @stable
|
||||
*/
|
||||
U_CAPI UConverterFromUCallback U_EXPORT2
|
||||
U_CAPI void U_EXPORT2
|
||||
ucnv_setFromUCallBack (UConverter * converter,
|
||||
UConverterFromUCallback action,
|
||||
UConverterFromUCallback newAction,
|
||||
void *newContext,
|
||||
UConverterFromUCallback oldAction,
|
||||
void **oldContext,
|
||||
UErrorCode * err);
|
||||
|
||||
|
||||
|
|
|
@ -1,268 +1 @@
|
|||
/*
|
||||
**********************************************************************
|
||||
* Copyright (C) 1999, International Business Machines
|
||||
* Corporation and others. All Rights Reserved.
|
||||
**********************************************************************
|
||||
*
|
||||
*
|
||||
* ucnv_bld.h:
|
||||
* Contains all internal and external data structure definitions
|
||||
* Created & Maitained by Bertrand A. Damiba
|
||||
*
|
||||
*
|
||||
*
|
||||
* ATTENTION:
|
||||
* ---------
|
||||
* Although the data structures in this file are open and stack allocatable
|
||||
* we reserve the right to hide them in further releases.
|
||||
*/
|
||||
|
||||
#ifndef UCNV_BLD_H
|
||||
#define UCNV_BLD_H
|
||||
|
||||
#include "unicode/utypes.h"
|
||||
|
||||
#define UCNV_MAX_SUBCHAR_LEN 4
|
||||
#define UCNV_ERROR_BUFFER_LENGTH 20
|
||||
#define UCNV_MAX_AMBIGUOUSCCSIDS 5
|
||||
|
||||
#define UCNV_IMPLEMENTED_CONVERSION_TYPES 9
|
||||
/*Sentinel Value used to check the integrity of the binary data files */
|
||||
|
||||
#define UCNV_FILE_CHECK_MARKER 0xBEDA
|
||||
|
||||
/*maximum length of the converter names */
|
||||
#define UCNV_MAX_CONVERTER_NAME_LENGTH 60
|
||||
#define UCNV_MAX_FULL_FILE_NAME_LENGTH (600+UCNV_MAX_CONVERTER_NAME_LENGTH)
|
||||
|
||||
/*Pointer to the aforementioned file */
|
||||
#define UCNV_MAX_LINE_TEXT (UCNV_MAX_CONVERTER_NAME_LENGTH*400)
|
||||
|
||||
#define UCNV_SI 0x0F /*Shift in for EBDCDIC_STATEFUL and iso2022 states */
|
||||
#define UCNV_SO 0x0E /*Shift out for EBDCDIC_STATEFUL and iso2022 states */
|
||||
|
||||
typedef enum {
|
||||
UCNV_UNSUPPORTED_CONVERTER = -1,
|
||||
UCNV_SBCS = 0,
|
||||
UCNV_DBCS = 1,
|
||||
UCNV_MBCS = 2,
|
||||
UCNV_LATIN_1 = 3,
|
||||
UCNV_UTF8 = 4,
|
||||
UCNV_UTF16_BigEndian = 5,
|
||||
UCNV_UTF16_LittleEndian = 6,
|
||||
UCNV_EBCDIC_STATEFUL = 7,
|
||||
UCNV_ISO_2022 = 8,
|
||||
|
||||
UCNV_LMBCS_1 = 9,
|
||||
UCNV_LMBCS_2,
|
||||
UCNV_LMBCS_3,
|
||||
UCNV_LMBCS_4,
|
||||
UCNV_LMBCS_5,
|
||||
UCNV_LMBCS_6,
|
||||
UCNV_LMBCS_8,
|
||||
UCNV_LMBCS_11,
|
||||
UCNV_LMBCS_16,
|
||||
UCNV_LMBCS_17,
|
||||
UCNV_LMBCS_18,
|
||||
UCNV_LMBCS_19,
|
||||
UCNV_LMBCS_LAST = UCNV_LMBCS_19,
|
||||
|
||||
/* Number of converter types for which we have conversion routines. */
|
||||
UCNV_NUMBER_OF_SUPPORTED_CONVERTER_TYPES = UCNV_LMBCS_LAST+1
|
||||
|
||||
} UConverterType;
|
||||
|
||||
/* ### move the following typedef and array into implementation files! */
|
||||
typedef struct
|
||||
{
|
||||
int32_t ccsid;
|
||||
UChar mismapped;
|
||||
UChar replacement;
|
||||
} UAmbiguousConverter;
|
||||
|
||||
static const UAmbiguousConverter UCNV_AMBIGUOUSCONVERTERS[UCNV_MAX_AMBIGUOUSCCSIDS] =
|
||||
{
|
||||
{ 943, 0x00A5, 0x005C },
|
||||
{ 949, 0x20A9, 0x005C },
|
||||
{ 1361, 0x20A9, 0x005C },
|
||||
{ 942, 0x00A5, 0x005C },
|
||||
{ 1363, 0x20A9, 0x005C }
|
||||
};
|
||||
|
||||
typedef enum {
|
||||
UCNV_UNKNOWN = -1,
|
||||
UCNV_IBM = 0
|
||||
} UConverterPlatform;
|
||||
|
||||
U_CDECL_BEGIN /* We must declare the following as 'extern "C"' so that if ucnv
|
||||
itself is compiled under C++, the linkage of the funcptrs will
|
||||
work.
|
||||
*/
|
||||
|
||||
union UConverterTable;
|
||||
typedef union UConverterTable UConverterTable;
|
||||
|
||||
struct UConverterImpl;
|
||||
typedef struct UConverterImpl UConverterImpl;
|
||||
|
||||
/* ###
|
||||
* Markus Scherer on 2000feb04:
|
||||
* I have change UConverter and UConverterSharedData; there may be more changes,
|
||||
* or we may decide to roll back the structure definitions to what they were
|
||||
* before, with the additional UConverterImpl field and the new semantics for
|
||||
* referenceCounter.
|
||||
*
|
||||
* Reasons for changes: Attempt at performance improvements, especially
|
||||
* a) decrease amount of internal, implicit padding by reordering the fields
|
||||
* b) save space by storing the internal name of the converter only with a
|
||||
* pointer instead of an array
|
||||
*
|
||||
* In addition to that, I added the UConverterImpl field for better
|
||||
* modularizing the code and making it more maintainable. It may actually
|
||||
* become slightly faster by doing this.
|
||||
*
|
||||
* I changed the UConverter.to|fromUnicodeStatus to be unsigned because
|
||||
* the defaultValues.toUnicodeStatus is unsigned, and it seemed to be a safer choice.
|
||||
*
|
||||
* Ultimately, I would prefer not to expose these definitions any more at all,
|
||||
* but this is suspect to discussions, proposals and design reviews.
|
||||
*
|
||||
* I would personally like to see more information hiding (with helper APIs),
|
||||
* useful state fields in UConverter that are reserved for the callbacks,
|
||||
* and directly included structures instead of pointers to allocated
|
||||
* memory, like for UConverterTable and its variant fields.
|
||||
*
|
||||
* Also, with the more C++-like converter implementation,
|
||||
* the conversionType does not need to be in UConverterSharedData any more:
|
||||
* it is in UConverterImpl and hardly used.
|
||||
*/
|
||||
|
||||
typedef struct {
|
||||
uint32_t structSize; /* Size of this structure */
|
||||
|
||||
char name [UCNV_MAX_CONVERTER_NAME_LENGTH]; /* internal name of the converter- invariant chars */
|
||||
|
||||
int32_t codepage; /* codepage # (now IBM-$codepage) */
|
||||
|
||||
int8_t platform; /* platform of the converter (only IBM now) */
|
||||
int8_t conversionType; /* conversion type */
|
||||
|
||||
int8_t minBytesPerChar; /* Minimum # bytes per char in this codepage */
|
||||
int8_t maxBytesPerChar; /* Maximum # bytes per char in this codepage */
|
||||
|
||||
int8_t subCharLen;
|
||||
|
||||
uint8_t subChar[UCNV_MAX_SUBCHAR_LEN];
|
||||
uint8_t hasToUnicodeFallback; /* UBool needs to be changed to UBool to be consistent across platform */
|
||||
uint8_t hasFromUnicodeFallback;
|
||||
uint8_t reserved[19]; /* to round out the structure */
|
||||
|
||||
} UConverterStaticData;
|
||||
|
||||
/*
|
||||
* Defines the UConverterSharedData struct,
|
||||
* the immutable, shared part of UConverter.
|
||||
*/
|
||||
typedef struct {
|
||||
uint32_t structSize; /* Size of this structure */
|
||||
uint32_t referenceCounter; /* used to count number of clients, 0xffffffff for static SharedData */
|
||||
|
||||
const void *dataMemory; /* from udata_openChoice() */
|
||||
UConverterTable *table; /* Pointer to conversion data */
|
||||
|
||||
const UConverterStaticData *staticData; /* pointer to the static (non changing) data. */
|
||||
UBool staticDataOwned; /* T if we own the staticData */
|
||||
const UConverterImpl *impl; /* vtable-style struct of mostly function pointers */
|
||||
|
||||
/*initial values of some members of the mutable part of object */
|
||||
uint32_t toUnicodeStatus;
|
||||
} UConverterSharedData;
|
||||
|
||||
|
||||
/* Defines a UConverter, the lightweight mutable part the user sees */
|
||||
|
||||
struct UConverter {
|
||||
uint32_t toUnicodeStatus; /* Used to internalize stream status information */
|
||||
uint32_t fromUnicodeStatus;
|
||||
int32_t mode;
|
||||
UBool useFallback;
|
||||
|
||||
int8_t subCharLen; /* length of the codepage specific character sequence */
|
||||
int8_t invalidCharLength;
|
||||
int8_t invalidUCharLength;
|
||||
int8_t charErrorBufferLength; /* number of valid bytes in charErrorBuffer */
|
||||
int8_t UCharErrorBufferLength; /* number of valid UChars in charErrorBuffer */
|
||||
|
||||
uint8_t subChar[UCNV_MAX_SUBCHAR_LEN]; /* codepage specific character sequence */
|
||||
char invalidCharBuffer[UCNV_MAX_SUBCHAR_LEN];
|
||||
uint8_t charErrorBuffer[UCNV_ERROR_BUFFER_LENGTH]; /* codepage output from Error functions */
|
||||
|
||||
UChar invalidUCharBuffer[3];
|
||||
UChar UCharErrorBuffer[UCNV_ERROR_BUFFER_LENGTH]; /* unicode output from Error functions */
|
||||
|
||||
/*
|
||||
* Error function pointer called when conversion issues
|
||||
* occur during a T_UConverter_fromUnicode call
|
||||
*/
|
||||
void (*fromUCharErrorBehaviour) (struct UConverter *,
|
||||
char **,
|
||||
const char *,
|
||||
const UChar **,
|
||||
const UChar *,
|
||||
int32_t* offsets,
|
||||
UBool,
|
||||
UErrorCode *);
|
||||
/*
|
||||
* Error function pointer called when conversion issues
|
||||
* occur during a T_UConverter_toUnicode call
|
||||
*/
|
||||
void (*fromCharErrorBehaviour) (struct UConverter *,
|
||||
UChar **,
|
||||
const UChar *,
|
||||
const char **,
|
||||
const char *,
|
||||
int32_t* offsets,
|
||||
UBool,
|
||||
UErrorCode *);
|
||||
|
||||
UConverterSharedData *sharedData; /* Pointer to the shared immutable part of the converter object */
|
||||
|
||||
/*
|
||||
* currently only used to point to a struct containing UConverter used by iso 2022;
|
||||
* could be used by clients writing their own call back function to pass context to them
|
||||
*/
|
||||
void *extraInfo;
|
||||
};
|
||||
|
||||
U_CDECL_END /* end of UConverter */
|
||||
|
||||
typedef struct UConverter UConverter;
|
||||
|
||||
|
||||
typedef struct
|
||||
{
|
||||
UConverter *currentConverter;
|
||||
uint8_t escSeq2022[10];
|
||||
int8_t escSeq2022Length;
|
||||
}
|
||||
UConverterDataISO2022;
|
||||
|
||||
|
||||
typedef struct
|
||||
{
|
||||
UConverter *OptGrpConverter[0x20]; /* Converter per Opt. grp. */
|
||||
uint8_t OptGroup; /* default Opt. grp. for this LMBCS session */
|
||||
uint8_t localeConverterIndex; /* reasonable locale match for index */
|
||||
|
||||
}
|
||||
UConverterDataLMBCS;
|
||||
|
||||
|
||||
#define CONVERTER_FILE_EXTENSION ".cnv"
|
||||
|
||||
#endif /* _UCNV_BLD */
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
#error Please do not include this file, it's now internal only.
|
||||
|
|
|
@ -34,52 +34,102 @@
|
|||
#ifndef UCNV_ERR_H
|
||||
#define UCNV_ERR_H
|
||||
|
||||
#include "unicode/ucnv.h"
|
||||
#include "unicode/utypes.h"
|
||||
|
||||
/**
|
||||
* The process condition code to be used with the callbacks.
|
||||
* UCNV_UNASSIGNED : the code point is unassigned.
|
||||
* UCNV_ILLEGAL : The code point is illegal. For example,\x81\x2E is illegal
|
||||
* because \x2E is not a valid trail byte for the \x81 lead byte in SJIS.
|
||||
* UCNV_IRREGULAR : The code point is not a regular sequence in the encoding.
|
||||
* For example,\xC0\E1 is irregular because the same character can be represented
|
||||
* as \x61.
|
||||
* UCNV_RESET : Whether the conversion operation has been reset.
|
||||
* UCNV_CLOSE : Whether the conversion operation has ended.
|
||||
*/
|
||||
typedef enum {
|
||||
UCNV_UNASSIGNED = 0,
|
||||
UCNV_ILLEGAL = 1,
|
||||
UCNV_IRREGULAR = 2,
|
||||
UCNV_RESET = 3,
|
||||
UCNV_CLOSE = 4,
|
||||
} UConverterCallbackReason;
|
||||
|
||||
/* Forward declaring the UConverter structure */
|
||||
struct UConverter;
|
||||
typedef struct UConverter UConverter;
|
||||
|
||||
/**
|
||||
* Functor STOPS at the ILLEGAL_SEQUENCE
|
||||
* @stable
|
||||
* The structure for the fromUnicode callback function parameter.
|
||||
*/
|
||||
U_CAPI void U_EXPORT2 UCNV_FROM_U_CALLBACK_STOP (UConverter * _this,
|
||||
char **target,
|
||||
const char *targetLimit,
|
||||
const UChar ** source,
|
||||
const UChar * sourceLimit,
|
||||
int32_t* offsets,
|
||||
UBool flush,
|
||||
UErrorCode * err);
|
||||
typedef struct {
|
||||
uint16_t size;
|
||||
UBool flush;
|
||||
UConverter *converter;
|
||||
const UChar *sourceStart;
|
||||
const UChar **pSource;
|
||||
const UChar *sourceLimit;
|
||||
char **pTarget;
|
||||
const char *targetLimit;
|
||||
int32_t *offsets; /* *offset = blah ; offset++; */
|
||||
} UConverterFromUnicodeArgs;
|
||||
|
||||
|
||||
/**
|
||||
* The structure for the toUnicode callback function parameter.
|
||||
*/
|
||||
typedef struct {
|
||||
uint16_t size;
|
||||
UBool flush;
|
||||
UConverter *converter;
|
||||
const char *sourceStart;
|
||||
const char **pSource;
|
||||
const char *sourceLimit;
|
||||
UChar **pTarget;
|
||||
const UChar *targetLimit;
|
||||
int32_t *offsets;
|
||||
} UConverterToUnicodeArgs;
|
||||
|
||||
|
||||
/**
|
||||
* Functor STOPS at the ILLEGAL_SEQUENCE
|
||||
* @stable
|
||||
*/
|
||||
U_CAPI void U_EXPORT2 UCNV_TO_U_CALLBACK_STOP (UConverter * _this,
|
||||
UChar ** target,
|
||||
const UChar * targetLimit,
|
||||
const char **source,
|
||||
const char *sourceLimit,
|
||||
int32_t* offsets,
|
||||
UBool flush,
|
||||
U_CAPI void U_EXPORT2 UCNV_FROM_U_CALLBACK_STOP (
|
||||
void *context,
|
||||
UConverterFromUnicodeArgs *fromUArgs,
|
||||
const UChar* codeUnits,
|
||||
int32_t length,
|
||||
UChar32 codePoint,
|
||||
UConverterCallbackReason reason,
|
||||
UErrorCode * err);
|
||||
|
||||
|
||||
|
||||
/**
|
||||
* Functor STOPS at the ILLEGAL_SEQUENCE
|
||||
* @stable
|
||||
*/
|
||||
U_CAPI void U_EXPORT2 UCNV_TO_U_CALLBACK_STOP (
|
||||
void *context,
|
||||
UConverterToUnicodeArgs *fromUArgs,
|
||||
const char* codeUnits,
|
||||
int32_t length,
|
||||
UConverterCallbackReason reason,
|
||||
UErrorCode * err);
|
||||
|
||||
/**
|
||||
* Functor SKIPs the ILLEGAL_SEQUENCE
|
||||
* @stable
|
||||
*/
|
||||
U_CAPI void U_EXPORT2 UCNV_FROM_U_CALLBACK_SKIP (UConverter * _this,
|
||||
char **target,
|
||||
const char *targetLimit,
|
||||
const UChar ** source,
|
||||
const UChar * sourceLimit,
|
||||
int32_t* offsets,
|
||||
UBool flush,
|
||||
UErrorCode * err);
|
||||
U_CAPI void U_EXPORT2 UCNV_FROM_U_CALLBACK_SKIP (
|
||||
void *context,
|
||||
UConverterFromUnicodeArgs *fromUArgs,
|
||||
const UChar* codeUnits,
|
||||
int32_t length,
|
||||
UChar32 codePoint,
|
||||
UConverterCallbackReason reason,
|
||||
UErrorCode * err);
|
||||
|
||||
/**
|
||||
* Functor Substitute the ILLEGAL SEQUENCE with the current substitution string assiciated with _this,
|
||||
|
@ -89,14 +139,14 @@ U_CAPI void U_EXPORT2 UCNV_FROM_U_CALLBACK_SKIP (UConverter * _this,
|
|||
* @stable
|
||||
*/
|
||||
|
||||
U_CAPI void U_EXPORT2 UCNV_FROM_U_CALLBACK_SUBSTITUTE (UConverter * _this,
|
||||
char **target,
|
||||
const char *targetLimit,
|
||||
const UChar ** source,
|
||||
const UChar * sourceLimit,
|
||||
int32_t* offsets,
|
||||
UBool flush,
|
||||
UErrorCode * err);
|
||||
U_CAPI void U_EXPORT2 UCNV_FROM_U_CALLBACK_SUBSTITUTE (
|
||||
void *context,
|
||||
UConverterFromUnicodeArgs *fromUArgs,
|
||||
const UChar* codeUnits,
|
||||
int32_t length,
|
||||
UChar32 codePoint,
|
||||
UConverterCallbackReason reason,
|
||||
UErrorCode * err);
|
||||
|
||||
/**
|
||||
* Functor Substitute the ILLEGAL SEQUENCE with a sequence escaped codepoints corresponding to the ILLEGAL
|
||||
|
@ -109,30 +159,28 @@ U_CAPI void U_EXPORT2 UCNV_FROM_U_CALLBACK_SUBSTITUTE (UConverter * _this,
|
|||
* @stable
|
||||
*/
|
||||
|
||||
U_CAPI void U_EXPORT2 UCNV_FROM_U_CALLBACK_ESCAPE (UConverter * _this,
|
||||
char **target,
|
||||
const char *targetLimit,
|
||||
const UChar ** source,
|
||||
const UChar * sourceLimit,
|
||||
int32_t* offsets,
|
||||
UBool flush,
|
||||
UErrorCode * err);
|
||||
U_CAPI void U_EXPORT2 UCNV_FROM_U_CALLBACK_ESCAPE (
|
||||
void *context,
|
||||
UConverterFromUnicodeArgs *fromUArgs,
|
||||
const UChar* codeUnits,
|
||||
int32_t length,
|
||||
UChar32 codePoint,
|
||||
UConverterCallbackReason reason,
|
||||
UErrorCode * err);
|
||||
|
||||
|
||||
/**
|
||||
* Functor SKIPs the ILLEGAL_SEQUENCE
|
||||
* @stable
|
||||
*/
|
||||
U_CAPI void U_EXPORT2 UCNV_TO_U_CALLBACK_SKIP (UConverter * _this,
|
||||
UChar ** target,
|
||||
const UChar * targetLimit,
|
||||
const char **source,
|
||||
const char *sourceLimit,
|
||||
int32_t* offsets,
|
||||
UBool flush,
|
||||
U_CAPI void U_EXPORT2 UCNV_TO_U_CALLBACK_SKIP (
|
||||
void *context,
|
||||
UConverterToUnicodeArgs *fromUArgs,
|
||||
const char* codeUnits,
|
||||
int32_t length,
|
||||
UConverterCallbackReason reason,
|
||||
UErrorCode * err);
|
||||
|
||||
|
||||
/**
|
||||
* Functor Substitute the ILLEGAL SEQUENCE with the current substitution string assiciated with _this,
|
||||
* in the event target buffer is too small, it will store the extra info in the UConverter, and err
|
||||
|
@ -140,14 +188,13 @@ U_CAPI void U_EXPORT2 UCNV_TO_U_CALLBACK_SKIP (UConverter * _this,
|
|||
* store the left over data in target, before transcoding the "source Stream"
|
||||
* @stable
|
||||
*/
|
||||
U_CAPI void U_EXPORT2 UCNV_TO_U_CALLBACK_SUBSTITUTE (UConverter * _this,
|
||||
UChar ** target,
|
||||
const UChar * targetLimit,
|
||||
const char **source,
|
||||
const char *sourceLimit,
|
||||
int32_t* offsets,
|
||||
UBool flush,
|
||||
UErrorCode * err);
|
||||
U_CAPI void U_EXPORT2 UCNV_TO_U_CALLBACK_SUBSTITUTE (
|
||||
void *context,
|
||||
UConverterToUnicodeArgs *fromUArgs,
|
||||
const char* codeUnits,
|
||||
int32_t length,
|
||||
UConverterCallbackReason reason,
|
||||
UErrorCode * err);
|
||||
|
||||
/**
|
||||
* Functor Substitute the ILLEGAL SEQUENCE with a sequence escaped codepoints corresponding to the
|
||||
|
@ -158,14 +205,12 @@ U_CAPI void U_EXPORT2 UCNV_TO_U_CALLBACK_SUBSTITUTE (UConverter * _this,
|
|||
* @stable
|
||||
*/
|
||||
|
||||
U_CAPI void U_EXPORT2 UCNV_TO_U_CALLBACK_ESCAPE (UConverter * _this,
|
||||
UChar ** target,
|
||||
const UChar * targetLimit,
|
||||
const char **source,
|
||||
const char *sourceLimit,
|
||||
int32_t* offsets,
|
||||
UBool flush,
|
||||
UErrorCode * err);
|
||||
|
||||
U_CAPI void U_EXPORT2 UCNV_TO_U_CALLBACK_ESCAPE (
|
||||
void *context,
|
||||
UConverterToUnicodeArgs *fromUArgs,
|
||||
const char* codeUnits,
|
||||
int32_t length,
|
||||
UConverterCallbackReason reason,
|
||||
UErrorCode * err);
|
||||
|
||||
#endif/*UCNV_ERR_H*/
|
||||
|
|
|
@ -197,6 +197,11 @@ void TestConvert()
|
|||
}
|
||||
};
|
||||
|
||||
UConverterFromUCallback oldFromUAction;
|
||||
UConverterToUCallback oldToUAction;
|
||||
void* oldFromUContext = NULL;
|
||||
void* oldToUContext = NULL;
|
||||
|
||||
/* flush the converter cache to get a consistent state before the flushing is tested */
|
||||
ucnv_flushCache();
|
||||
|
||||
|
@ -465,7 +470,7 @@ void TestConvert()
|
|||
MIA1 = ucnv_getFromUCallBack(myConverter);
|
||||
|
||||
log_verbose("\n---Testing ucnv_setFromUCallBack...\n");
|
||||
ucnv_setFromUCallBack(myConverter,otherUnicodeAction(MIA1), &err);
|
||||
ucnv_setFromUCallBack(myConverter, otherUnicodeAction(MIA1), NULL, oldFromUAction, &oldFromUContext, err);
|
||||
if (U_FAILURE(err))
|
||||
{ log_err("FAILURE! %s\n", myErrorName(err)); }
|
||||
|
||||
|
@ -475,7 +480,7 @@ void TestConvert()
|
|||
log_verbose("get From UCallBack ok\n");
|
||||
|
||||
log_verbose("\n---Testing getFromUCallBack Roundtrip...\n");
|
||||
ucnv_setFromUCallBack(myConverter,MIA1, &err);
|
||||
ucnv_setFromUCallBack(myConverter,MIA1, NULL, oldFromUAction, &oldFromUContext, &err);
|
||||
if (U_FAILURE(err))
|
||||
{ log_err("FAILURE! %s\n", myErrorName(err)); }
|
||||
|
||||
|
@ -490,7 +495,7 @@ void TestConvert()
|
|||
MIA2 = ucnv_getToUCallBack(myConverter);
|
||||
|
||||
log_verbose("\n---Testing setTo UCallBack...\n");
|
||||
ucnv_setToUCallBack(myConverter,otherCharAction(MIA2),&err);
|
||||
ucnv_setToUCallBack(myConverter,otherCharAction(MIA2), NULL, oldToUAction, &oldToUContext, &err);
|
||||
if (U_FAILURE(err))
|
||||
{ log_err("FAILURE! %s\n", myErrorName(err));}
|
||||
|
||||
|
@ -500,7 +505,7 @@ void TestConvert()
|
|||
log_verbose("To UCallBack ok\n");
|
||||
|
||||
log_verbose("\n---Testing setTo UCallBack Roundtrip...\n");
|
||||
ucnv_setToUCallBack(myConverter,MIA2, &err);
|
||||
ucnv_setToUCallBack(myConverter,MIA2, NULL, oldToUAction, &oldToUContext, &err);
|
||||
if (U_FAILURE(err))
|
||||
{ log_err("FAILURE! %s\n", myErrorName(err)); }
|
||||
|
||||
|
|
|
@ -435,6 +435,8 @@ UBool testConvertFromUnicode(const UChar *source, int sourceLen, const char *ex
|
|||
char junk[9999];
|
||||
char offset_str[9999];
|
||||
char *p;
|
||||
UConverterFromUCallback oldAction;
|
||||
void* oldContext = NULL;
|
||||
|
||||
|
||||
for(i=0;i<NEW_MAX_BUFFER;i++)
|
||||
|
@ -457,7 +459,7 @@ UBool testConvertFromUnicode(const UChar *source, int sourceLen, const char *ex
|
|||
/*----setting the callback routine----*/
|
||||
|
||||
|
||||
ucnv_setFromUCallBack (conv, /*action*/callback, &status);
|
||||
ucnv_setFromUCallBack (conv, /*action*/callback, NULL, oldAction, &oldContext, &status);
|
||||
if (U_FAILURE(status))
|
||||
{
|
||||
log_err("FAILURE in setting the callback Function! %s\n", myErrorName(status));
|
||||
|
@ -616,7 +618,9 @@ UBool testConvertToUnicode( const char *source, int sourcelen, const UChar *expe
|
|||
char junk[9999];
|
||||
char offset_str[9999];
|
||||
UChar *p;
|
||||
UConverterToUCallback action;
|
||||
UConverterToUCallback action;
|
||||
UConverterToUCallback oldAction;
|
||||
void* oldContext = NULL;
|
||||
|
||||
int32_t realBufferSize;
|
||||
UChar *realBufferEnd;
|
||||
|
@ -651,7 +655,7 @@ UBool testConvertToUnicode( const char *source, int sourcelen, const UChar *expe
|
|||
/*----setting the callback routine----*/
|
||||
|
||||
|
||||
ucnv_setToUCallBack (conv, callback, &status);
|
||||
ucnv_setToUCallBack (conv, callback, NULL, oldAction, &oldContext, &status);
|
||||
if (U_FAILURE(status))
|
||||
{
|
||||
log_err("FAILURE in setting the callback Function! %s\n", myErrorName(status));
|
||||
|
|
|
@ -171,6 +171,11 @@ void ConvertTest::TestConvert()
|
|||
(char)0xB0, (char)0xAD
|
||||
}
|
||||
};
|
||||
UConverterFromUCallback fromUAction;
|
||||
void* fromUContext = NULL;
|
||||
UConverterToUCallback toUAction;
|
||||
void* toUContext = NULL;
|
||||
|
||||
/*Calling all the UnicodeConverterCPP API and checking functionality*/
|
||||
|
||||
/*Tests UnicodeConverterCPP::getAvailableNames*/
|
||||
|
@ -357,14 +362,14 @@ void ConvertTest::TestConvert()
|
|||
|
||||
/*setMissingUnicodeAction*/
|
||||
logln("\n---Testing UnicodeConverterCPP::setMissingUnicodeAction...");
|
||||
myConverter->setMissingUnicodeAction(otherUnicodeAction(MIA1),err);
|
||||
myConverter->setMissingUnicodeAction(otherUnicodeAction(MIA1), NULL, fromUAction, &fromUContext, err);
|
||||
if (U_FAILURE(err)) errln ("FAILURE! " + (UnicodeString)myErrorName(err));
|
||||
if (myConverter->getMissingUnicodeAction() != otherUnicodeAction(MIA1)) logln("Missing action failed");
|
||||
else logln("Missing action ok");
|
||||
|
||||
|
||||
logln("\n---Testing UnicodeConverterCPP::setMissingUnicodeAction Roundtrip...");
|
||||
myConverter->setMissingUnicodeAction(MIA1, err);
|
||||
myConverter->setMissingUnicodeAction(MIA1, NULL, fromUAction, &fromUContext, err);
|
||||
if (U_FAILURE(err)) errln ("FAILURE! " + (UnicodeString)myErrorName(err));
|
||||
if (myConverter->getMissingUnicodeAction() != MIA1) errln("Missing action failed");
|
||||
else logln("Missing action ok");
|
||||
|
@ -372,13 +377,13 @@ void ConvertTest::TestConvert()
|
|||
|
||||
/*setMissingCharAction*/
|
||||
logln("\n---Testing UnicodeConverterCPP::setMissingCharAction...");
|
||||
myConverter->setMissingCharAction(otherCharAction(MIA2),err);
|
||||
myConverter->setMissingCharAction(otherCharAction(MIA2), NULL, toUAction, &toUContext, err);
|
||||
if (U_FAILURE(err)) errln ("FAILURE! " + (UnicodeString)myErrorName(err));
|
||||
if (myConverter->getMissingCharAction() != otherCharAction(MIA2)) errln("Missing action failed");
|
||||
else logln("Missing action ok");
|
||||
|
||||
logln("\n---Testing UnicodeConverterCPP::setMissingCharAction Roundtrip...");
|
||||
myConverter->setMissingCharAction(MIA2, err);
|
||||
myConverter->setMissingCharAction(MIA2, NULL, toUAction, &toUContext, err);
|
||||
if (U_FAILURE(err)) errln ("FAILURE! " + (UnicodeString)myErrorName(err));
|
||||
if (myConverter->getMissingCharAction() != MIA2) errln("Missing action failed");
|
||||
else logln("Missing action ok");
|
||||
|
|
|
@ -12,14 +12,15 @@
|
|||
* table (IBM NLTC ucmap format).
|
||||
*
|
||||
* 05/04/2000 helena Added fallback mapping into the picture...
|
||||
* 06/29/2000 helena Major rewrite of the callback APIs.
|
||||
*/
|
||||
|
||||
#include <stdio.h>
|
||||
#include "ucmp16.h"
|
||||
#include "ucmp8.h"
|
||||
#include "ucnv_io.h"
|
||||
#include "unicode/ucnv_bld.h"
|
||||
#include "unicode/ucnv_err.h"
|
||||
#include "ucnv_bld.h"
|
||||
#include "ucnv_imp.h"
|
||||
#include "ucnv_cnv.h"
|
||||
#include "cstring.h"
|
||||
|
|
|
@ -13,7 +13,7 @@
|
|||
|
||||
#include "unicode/utypes.h"
|
||||
#include "unicode/ucnv.h"
|
||||
#include "unicode/ucnv_bld.h"
|
||||
#include "ucnv_bld.h"
|
||||
|
||||
static const UConverterStaticData _SBCSStaticData={
|
||||
sizeof(UConverterStaticData),
|
||||
|
|
Loading…
Add table
Reference in a new issue