mirror of
https://github.com/unicode-org/icu.git
synced 2025-04-08 06:53:45 +00:00
ICU-3346 support simple (single-character) conversion extensions
X-SVN-Rev: 13656
This commit is contained in:
Markus Scherer
parent
506bc1495f
commit
2e6b59aa7d
3 changed files with 20 additions and 39 deletions
|
|
@ -1595,14 +1595,11 @@ UConverter_toUnicode_ISO_2022_JP_OFFSETS_LOGIC(UConverterToUnicodeArgs *args,
|
|||
continue;
|
||||
}
|
||||
else{
|
||||
const char *pBuf;
|
||||
|
||||
tempBuf[0] = (char) args->converter->toUnicodeStatus;
|
||||
tempBuf[1] = (char) mySourceChar;
|
||||
mySourceChar+= (args->converter->toUnicodeStatus)<<8;
|
||||
*toUnicodeStatus= 0;
|
||||
pBuf = tempBuf;
|
||||
targetUniChar = _MBCSSimpleGetNextUChar(myData->currentConverter->sharedData, &pBuf, tempBuf+2, args->converter->useFallback);
|
||||
targetUniChar = _MBCSSimpleGetNextUChar(myData->currentConverter->sharedData, tempBuf, 2, args->converter->useFallback);
|
||||
}
|
||||
break;
|
||||
|
||||
|
|
@ -1917,8 +1914,7 @@ UConverter_toUnicode_ISO_2022_KR_OFFSETS_LOGIC_IBM(UConverterToUnicodeArgs *args
|
|||
static void
|
||||
UConverter_toUnicode_ISO_2022_KR_OFFSETS_LOGIC(UConverterToUnicodeArgs *args,
|
||||
UErrorCode* err){
|
||||
char tempBuf[3];
|
||||
const char* pBuf;
|
||||
char tempBuf[2];
|
||||
const char *mySource = ( char *) args->source;
|
||||
UChar *myTarget = args->target;
|
||||
const char *mySourceLimit = args->sourceLimit;
|
||||
|
|
@ -1995,19 +1991,17 @@ UConverter_toUnicode_ISO_2022_KR_OFFSETS_LOGIC(UConverterToUnicodeArgs *args,
|
|||
tempBuf[1] = (char) (mySourceChar+0x80);
|
||||
mySourceChar = (UChar)(mySourceChar + (args->converter->toUnicodeStatus<<8));
|
||||
args->converter->toUnicodeStatus =0x00;
|
||||
pBuf = tempBuf;
|
||||
targetUniChar = _MBCSSimpleGetNextUChar(sharedData,
|
||||
&pBuf,(pBuf+2),useFallback);
|
||||
targetUniChar = _MBCSSimpleGetNextUChar(sharedData, tempBuf, 2, useFallback);
|
||||
}
|
||||
}
|
||||
else{
|
||||
if(args->converter->fromUnicodeStatus == 0x00){
|
||||
targetUniChar = _MBCS_SINGLE_SIMPLE_GET_NEXT_BMP(sharedData, mySourceChar);
|
||||
targetUniChar = _MBCSSimpleGetNextUChar(sharedData, mySource - 1, 1, useFallback);
|
||||
|
||||
}
|
||||
|
||||
}
|
||||
if(targetUniChar != missingCharMarker){
|
||||
if(targetUniChar < 0xfffe){
|
||||
if(args->offsets)
|
||||
args->offsets[myTarget - args->target]= mySource - args->source - 1-(myData->currentType==DBCS);
|
||||
*(myTarget++)=(UChar)targetUniChar;
|
||||
|
|
@ -2432,10 +2426,8 @@ UConverter_toUnicode_ISO_2022_CN_OFFSETS_LOGIC(UConverterToUnicodeArgs *args,
|
|||
UErrorCode* err){
|
||||
char tempBuf[3];
|
||||
int plane=0;
|
||||
const char* pBuf;
|
||||
const char *mySource = ( char *) args->source;
|
||||
UChar *myTarget = args->target;
|
||||
char *tempLimit = &tempBuf[3];
|
||||
const char *mySourceLimit = args->sourceLimit;
|
||||
uint32_t targetUniChar = 0x0000;
|
||||
uint32_t mySourceChar = 0x0000;
|
||||
|
|
@ -2494,22 +2486,22 @@ UConverter_toUnicode_ISO_2022_CN_OFFSETS_LOGIC(UConverterToUnicodeArgs *args,
|
|||
continue;
|
||||
}
|
||||
else{
|
||||
int32_t tempBufLen;
|
||||
if(plane >0){
|
||||
tempBuf[0] = (char) (0x80+plane);
|
||||
tempBuf[1] = (char) (args->converter->toUnicodeStatus);
|
||||
tempBuf[2] = (char) (mySourceChar);
|
||||
tempLimit = &tempBuf[2]+1;
|
||||
tempBufLen = 3;
|
||||
|
||||
}else{
|
||||
tempBuf[0] = (char) args->converter->toUnicodeStatus;
|
||||
tempBuf[1] = (char) mySourceChar;
|
||||
tempLimit = &tempBuf[2];
|
||||
tempBufLen = 2;
|
||||
}
|
||||
mySourceChar+= (uint32_t) args->converter->toUnicodeStatus<<8;
|
||||
args->converter->toUnicodeStatus = 0;
|
||||
pBuf = tempBuf;
|
||||
if(myData->currentConverter!=NULL){
|
||||
targetUniChar = _MBCSSimpleGetNextUChar(myData->currentConverter->sharedData, &pBuf, tempLimit, FALSE);
|
||||
targetUniChar = _MBCSSimpleGetNextUChar(myData->currentConverter->sharedData, tempBuf, tempBufLen, FALSE);
|
||||
}else{
|
||||
*err=U_INVALID_CHAR_FOUND;
|
||||
break;
|
||||
|
|
|
|||
|
|
@ -1037,12 +1037,12 @@ _LMBCSGetNextUCharWorker(UConverterToUnicodeArgs* args,
|
|||
if (*args->source == group) {
|
||||
/* single byte */
|
||||
++args->source;
|
||||
uniChar = _MBCSSimpleGetNextUChar(cnv->sharedData, &args->source, args->source + 1, FALSE);
|
||||
uniChar = _MBCSSimpleGetNextUChar(cnv->sharedData, args->source, 1, FALSE);
|
||||
++args->source;
|
||||
} else {
|
||||
/* double byte */
|
||||
const char *newLimit = args->source + 2;
|
||||
uniChar = _MBCSSimpleGetNextUChar(cnv->sharedData, &args->source, newLimit, FALSE);
|
||||
args->source = newLimit; /* set the correct limit even in case of an error */
|
||||
uniChar = _MBCSSimpleGetNextUChar(cnv->sharedData, args->source, 2, FALSE);
|
||||
args->source += 2;
|
||||
}
|
||||
}
|
||||
else { /* single byte conversion */
|
||||
|
|
@ -1058,7 +1058,6 @@ _LMBCSGetNextUCharWorker(UConverterToUnicodeArgs* args,
|
|||
/* The non-optimizable oddballs where there is an explicit byte
|
||||
* AND the second byte is not in the upper ascii range
|
||||
*/
|
||||
const char *s;
|
||||
char bytes[2];
|
||||
|
||||
extraInfo = (UConverterDataLMBCS *) args->converter->extraInfo;
|
||||
|
|
@ -1067,8 +1066,7 @@ _LMBCSGetNextUCharWorker(UConverterToUnicodeArgs* args,
|
|||
/* Lookup value must include opt group */
|
||||
bytes[0] = group;
|
||||
bytes[1] = CurByte;
|
||||
s = bytes;
|
||||
uniChar = _MBCSSimpleGetNextUChar(cnv->sharedData, &s, bytes + 2, FALSE);
|
||||
uniChar = _MBCSSimpleGetNextUChar(cnv->sharedData, bytes, 2, FALSE);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
|
@ -1084,16 +1082,14 @@ _LMBCSGetNextUCharWorker(UConverterToUnicodeArgs* args,
|
|||
CHECK_SOURCE_LIMIT(0);
|
||||
|
||||
/* let the MBCS conversion consume CurByte again */
|
||||
--args->source;
|
||||
uniChar = _MBCSSimpleGetNextUChar(cnv->sharedData, &args->source, args->source + 1, FALSE);
|
||||
uniChar = _MBCSSimpleGetNextUChar(cnv->sharedData, args->source - 1, 1, FALSE);
|
||||
}
|
||||
else
|
||||
{
|
||||
CHECK_SOURCE_LIMIT(1);
|
||||
/* let the MBCS conversion consume CurByte again */
|
||||
--args->source;
|
||||
/* since we know that we start at a lead byte, args->source _will_ be incremented by 2 */
|
||||
uniChar = _MBCSSimpleGetNextUChar(cnv->sharedData, &args->source, args->source + 2, FALSE);
|
||||
uniChar = _MBCSSimpleGetNextUChar(cnv->sharedData, args->source - 1, 2, FALSE);
|
||||
++args->source;
|
||||
}
|
||||
}
|
||||
else /* single byte conversion */
|
||||
|
|
|
|||
|
|
@ -142,11 +142,9 @@ _HZReset(UConverter *cnv, UConverterResetChoice choice){
|
|||
static void
|
||||
UConverter_toUnicode_HZ_OFFSETS_LOGIC(UConverterToUnicodeArgs *args,
|
||||
UErrorCode* err){
|
||||
char tempBuf[3];
|
||||
const char* pBuf;
|
||||
char tempBuf[2];
|
||||
const char *mySource = ( char *) args->source;
|
||||
UChar *myTarget = args->target;
|
||||
char *tempLimit = &tempBuf[3];
|
||||
const char *mySourceLimit = args->sourceLimit;
|
||||
UChar32 targetUniChar = 0x0000;
|
||||
UChar mySourceChar = 0x0000;
|
||||
|
|
@ -234,19 +232,14 @@ UConverter_toUnicode_HZ_OFFSETS_LOGIC(UConverterToUnicodeArgs *args,
|
|||
tempBuf[1] = (char) (mySourceChar+0x80);
|
||||
mySourceChar= (UChar)(((args->converter->toUnicodeStatus+0x80) << 8) | ((mySourceChar & 0x00ff)+0x80));
|
||||
args->converter->toUnicodeStatus =0x00;
|
||||
pBuf = &tempBuf[0];
|
||||
tempLimit = &tempBuf[2]+1;
|
||||
targetUniChar = _MBCSSimpleGetNextUChar(myData->gbConverter->sharedData,
|
||||
&pBuf,tempLimit,args->converter->useFallback);
|
||||
tempBuf, 2, args->converter->useFallback);
|
||||
}
|
||||
}
|
||||
else{
|
||||
if(args->converter->fromUnicodeStatus == 0x00){
|
||||
tempBuf[0] = (char) mySourceChar;
|
||||
pBuf = &tempBuf[0];
|
||||
tempLimit = &tempBuf[1];
|
||||
targetUniChar = _MBCSSimpleGetNextUChar(myData->gbConverter->sharedData,
|
||||
&pBuf,tempLimit,args->converter->useFallback);
|
||||
mySource - 1, 1, args->converter->useFallback);
|
||||
}
|
||||
else{
|
||||
goto SAVE_STATE;
|
||||
|
|
|
|||
Loading…
Add table
Reference in a new issue