2000-01-15 02:00:06 +00:00
|
|
|
/********************************************************************
|
|
|
|
* COPYRIGHT:
|
|
|
|
* Copyright (c) 1997-1999, International Business Machines Corporation and
|
|
|
|
* others. All Rights Reserved.
|
|
|
|
********************************************************************/
|
|
|
|
/********************************************************************************
|
1999-08-16 21:50:52 +00:00
|
|
|
*
|
|
|
|
* File CCONVTST.C
|
|
|
|
*
|
|
|
|
* Modification History:
|
|
|
|
* Name Description
|
|
|
|
* Steven R. Loomis 7/8/1999 Adding input buffer test
|
|
|
|
*********************************************************************************
|
|
|
|
*/
|
|
|
|
#include <stdio.h>
|
|
|
|
#include <stdlib.h>
|
|
|
|
#include <string.h>
|
|
|
|
#include <ctype.h>
|
2000-07-21 23:28:07 +00:00
|
|
|
#include "cstring.h"
|
1999-12-28 23:57:50 +00:00
|
|
|
#include "unicode/uloc.h"
|
|
|
|
#include "unicode/ucnv.h"
|
|
|
|
#include "unicode/ucnv_err.h"
|
1999-08-16 21:50:52 +00:00
|
|
|
#include "cintltst.h"
|
1999-12-28 23:57:50 +00:00
|
|
|
#include "unicode/utypes.h"
|
|
|
|
#include "unicode/ustring.h"
|
1999-08-16 21:50:52 +00:00
|
|
|
|
1999-12-04 02:31:40 +00:00
|
|
|
static void printSeq(const unsigned char* a, int len);
|
1999-08-16 21:50:52 +00:00
|
|
|
static void printUSeq(const UChar* a, int len);
|
2000-06-22 01:18:30 +00:00
|
|
|
static void TestNextUChar(UConverter* cnv, const char* source, const char* limit, const uint32_t results[], const char* message);
|
2000-06-22 23:46:02 +00:00
|
|
|
static void TestNextUCharError(UConverter* cnv, const char* source, const char* limit, UErrorCode expected, const char* message);
|
1999-08-16 21:50:52 +00:00
|
|
|
|
|
|
|
void TestNewConvertWithBufferSizes(int32_t osize, int32_t isize) ;
|
1999-12-22 22:57:04 +00:00
|
|
|
void TestConverterTypesAndStarters(void);
|
2000-01-08 00:54:57 +00:00
|
|
|
void TestAmbiguous(void);
|
2000-01-19 19:00:53 +00:00
|
|
|
void TestUTF8(void);
|
2000-06-22 01:18:30 +00:00
|
|
|
void TestUTF16BE(void);
|
|
|
|
void TestUTF16LE(void);
|
|
|
|
void TestLATIN1(void);
|
|
|
|
void TestSBCS(void);
|
|
|
|
void TestDBCS(void);
|
|
|
|
void TestMBCS(void);
|
|
|
|
void TestISO_2022(void);
|
|
|
|
void TestEBCDIC_STATEFUL(void);
|
2000-03-31 16:53:09 +00:00
|
|
|
void TestLMBCS(void);
|
2000-02-05 00:01:54 +00:00
|
|
|
void TestJitterbug255(void);
|
2000-04-18 21:57:47 +00:00
|
|
|
void TestEBCDICUS4XML(void);
|
1999-08-16 21:50:52 +00:00
|
|
|
|
|
|
|
#define NEW_MAX_BUFFER 999
|
|
|
|
|
|
|
|
static int32_t gInBufferSize = 0;
|
|
|
|
static int32_t gOutBufferSize = 0;
|
|
|
|
static char gNuConvTestName[1024];
|
|
|
|
|
|
|
|
#define nct_min(x,y) ((x<y) ? x : y)
|
|
|
|
|
1999-12-04 02:31:40 +00:00
|
|
|
void printSeq(const unsigned char* a, int len)
|
1999-08-16 21:50:52 +00:00
|
|
|
{
|
2000-02-05 00:01:54 +00:00
|
|
|
int i=0;
|
2000-07-13 00:28:06 +00:00
|
|
|
log_verbose("{");
|
|
|
|
while (i<len) log_verbose("%2x ", a[i++]);
|
2000-02-05 00:01:54 +00:00
|
|
|
log_verbose("}\n");
|
1999-08-16 21:50:52 +00:00
|
|
|
}
|
|
|
|
void printUSeq(const UChar* a, int len)
|
|
|
|
{
|
2000-02-05 00:01:54 +00:00
|
|
|
int i=0;
|
2000-07-13 00:28:06 +00:00
|
|
|
log_verbose("{U+");
|
|
|
|
while (i<len) log_verbose("%4x ", a[i++]);
|
2000-02-05 00:01:54 +00:00
|
|
|
log_verbose("}\n");
|
1999-08-16 21:50:52 +00:00
|
|
|
}
|
|
|
|
|
1999-12-04 02:31:40 +00:00
|
|
|
void printSeqErr(const unsigned char* a, int len)
|
1999-08-16 21:50:52 +00:00
|
|
|
{
|
2000-02-05 00:01:54 +00:00
|
|
|
int i=0;
|
2000-07-13 00:28:06 +00:00
|
|
|
fprintf(stderr, "{");
|
|
|
|
while (i<len) fprintf(stderr, "%2x ", a[i++]);
|
2000-02-05 00:01:54 +00:00
|
|
|
fprintf(stderr, "}\n");
|
1999-08-16 21:50:52 +00:00
|
|
|
}
|
|
|
|
void printUSeqErr(const UChar* a, int len)
|
|
|
|
{
|
2000-02-05 00:01:54 +00:00
|
|
|
int i=0;
|
2000-07-13 00:28:06 +00:00
|
|
|
fprintf(stderr, "{U+");
|
|
|
|
while (i<len) fprintf(stderr, "%4x ", a[i++]);
|
2000-02-05 00:01:54 +00:00
|
|
|
fprintf(stderr,"}\n");
|
1999-08-16 21:50:52 +00:00
|
|
|
}
|
2000-06-22 01:18:30 +00:00
|
|
|
void
|
|
|
|
TestNextUChar(UConverter* cnv, const char* source, const char* limit, const uint32_t results[], const char* message)
|
|
|
|
{
|
|
|
|
const char* s0;
|
2000-06-29 01:48:34 +00:00
|
|
|
const char* s=(char*)source;
|
2000-06-22 01:18:30 +00:00
|
|
|
const uint32_t *r=results;
|
|
|
|
UErrorCode errorCode=U_ZERO_ERROR;
|
|
|
|
uint32_t c;
|
1999-08-16 21:50:52 +00:00
|
|
|
|
2000-06-22 01:18:30 +00:00
|
|
|
while(s<limit) {
|
|
|
|
s0=s;
|
|
|
|
c=ucnv_getNextUChar(cnv, &s, limit, &errorCode);
|
|
|
|
if(U_FAILURE(errorCode)) {
|
|
|
|
log_err("%s ucnv_getNextUChar() failed: %s\n", message, u_errorName(errorCode));
|
|
|
|
break;
|
|
|
|
} else if((uint32_t)(s-s0)!=*r || c!=(UChar32)*(r+1)) {
|
|
|
|
log_err("%s ucnv_getNextUChar() result %lx from %d bytes, should have been %lx from %d bytes.\n",
|
|
|
|
message, c, (s-s0), *(r+1), *r);
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
r+=2;
|
|
|
|
}
|
|
|
|
}
|
2000-06-22 23:46:02 +00:00
|
|
|
void
|
|
|
|
TestNextUCharError(UConverter* cnv, const char* source, const char* limit, UErrorCode expected, const char* message)
|
|
|
|
{
|
2000-06-29 01:48:34 +00:00
|
|
|
const char* s=(char*)source;
|
2000-06-22 23:46:02 +00:00
|
|
|
UErrorCode errorCode=U_ZERO_ERROR;
|
|
|
|
uint32_t c;
|
|
|
|
c=ucnv_getNextUChar(cnv, &s, limit, &errorCode);
|
|
|
|
if(errorCode != expected){
|
|
|
|
log_err("FAIL: Expected:%s when %s-----Got:%s\n", myErrorName(expected), message, myErrorName(errorCode));
|
|
|
|
}
|
2000-07-13 00:28:06 +00:00
|
|
|
if(c != 0xFFFD && c != 0xffff){
|
|
|
|
log_err("FAIL: Expected return value of 0xfffd or 0xffff when %s-----Got 0x%lx\n", message, c);
|
2000-06-22 23:46:02 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
}
|
1999-12-22 22:57:04 +00:00
|
|
|
void TestInBufSizes(void)
|
1999-08-16 21:50:52 +00:00
|
|
|
{
|
|
|
|
TestNewConvertWithBufferSizes(NEW_MAX_BUFFER,1);
|
2000-06-29 02:53:29 +00:00
|
|
|
#if 1
|
1999-08-16 21:50:52 +00:00
|
|
|
TestNewConvertWithBufferSizes(NEW_MAX_BUFFER,2);
|
|
|
|
TestNewConvertWithBufferSizes(NEW_MAX_BUFFER,3);
|
|
|
|
TestNewConvertWithBufferSizes(NEW_MAX_BUFFER,4);
|
|
|
|
TestNewConvertWithBufferSizes(NEW_MAX_BUFFER,5);
|
|
|
|
TestNewConvertWithBufferSizes(NEW_MAX_BUFFER,6);
|
|
|
|
TestNewConvertWithBufferSizes(1,1);
|
|
|
|
TestNewConvertWithBufferSizes(2,3);
|
|
|
|
TestNewConvertWithBufferSizes(3,2);
|
2000-06-29 02:53:29 +00:00
|
|
|
#endif
|
1999-08-16 21:50:52 +00:00
|
|
|
}
|
|
|
|
|
1999-12-22 22:57:04 +00:00
|
|
|
void TestOutBufSizes(void)
|
1999-08-16 21:50:52 +00:00
|
|
|
{
|
2000-06-29 02:53:29 +00:00
|
|
|
#if 1
|
1999-08-16 21:50:52 +00:00
|
|
|
TestNewConvertWithBufferSizes(NEW_MAX_BUFFER,NEW_MAX_BUFFER);
|
|
|
|
TestNewConvertWithBufferSizes(1,NEW_MAX_BUFFER);
|
|
|
|
TestNewConvertWithBufferSizes(2,NEW_MAX_BUFFER);
|
|
|
|
TestNewConvertWithBufferSizes(3,NEW_MAX_BUFFER);
|
|
|
|
TestNewConvertWithBufferSizes(4,NEW_MAX_BUFFER);
|
|
|
|
TestNewConvertWithBufferSizes(5,NEW_MAX_BUFFER);
|
2000-07-19 20:14:27 +00:00
|
|
|
|
2000-06-29 02:53:29 +00:00
|
|
|
#endif
|
1999-08-16 21:50:52 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
void addTestNewConvert(TestNode** root)
|
|
|
|
{
|
|
|
|
addTest(root, &TestInBufSizes, "tsconv/nucnvtst/TestInBufSizes");
|
|
|
|
addTest(root, &TestOutBufSizes, "tsconv/nucnvtst/TestOutBufSizes");
|
|
|
|
addTest(root, &TestConverterTypesAndStarters, "tsconv/nucnvtst/TestConverterTypesAndStarters");
|
2000-01-08 00:54:57 +00:00
|
|
|
addTest(root, &TestAmbiguous, "tsconv/nucnvtst/TestAmbiguous");
|
2000-01-19 19:00:53 +00:00
|
|
|
addTest(root, &TestUTF8, "tsconv/nucnvtst/TestUTF8");
|
2000-06-22 01:18:30 +00:00
|
|
|
addTest(root, &TestUTF16BE, "tsconv/nucnvtst/TestUTF16BE");
|
|
|
|
addTest(root, &TestUTF16LE, "tsconv/nucnvtst/TestUTF16LE");
|
|
|
|
addTest(root, &TestLATIN1, "tsconv/nucnvtst/TestLATIN1");
|
|
|
|
addTest(root, &TestSBCS, "tsconv/nucnvtst/TestSBCS");
|
|
|
|
addTest(root, &TestDBCS, "tsconv/nucnvtst/TestDBCS");
|
|
|
|
addTest(root, &TestMBCS, "tsconv/nucnvtst/TestMBCS");
|
|
|
|
addTest(root, &TestISO_2022, "tsconv/nucnvtst/TestISO_2022");
|
|
|
|
addTest(root, &TestEBCDIC_STATEFUL, "tsconv/nucnvtst/TestEBCDIC_STATEFUL");
|
2000-03-31 16:53:09 +00:00
|
|
|
addTest(root, &TestLMBCS, "tsconv/nucnvtst/TestLMBCS");
|
2000-02-05 00:01:54 +00:00
|
|
|
addTest(root, &TestJitterbug255, "tsconv/nucnvtst/TestJitterbug255");
|
2000-04-18 21:57:47 +00:00
|
|
|
addTest(root, &TestEBCDICUS4XML, "tsconv/nucnvtst/TestEBCDICUS4XML");
|
1999-08-16 21:50:52 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
/* Note that this test already makes use of statics, so it's not really
|
|
|
|
multithread safe.
|
|
|
|
This convenience function lets us make the error messages actually useful.
|
|
|
|
*/
|
|
|
|
|
|
|
|
void setNuConvTestName(const char *codepage, const char *direction)
|
|
|
|
{
|
|
|
|
sprintf(gNuConvTestName, "[Testing %s %s Unicode, InputBufSiz=%d, OutputBufSiz=%d]",
|
2000-02-05 00:01:54 +00:00
|
|
|
codepage,
|
|
|
|
direction,
|
|
|
|
gInBufferSize,
|
|
|
|
gOutBufferSize);
|
1999-08-16 21:50:52 +00:00
|
|
|
}
|
|
|
|
|
2000-08-11 03:35:25 +00:00
|
|
|
UBool testConvertFromU( const UChar *source, int sourceLen, const uint8_t *expect, int expectLen,
|
2000-02-05 00:01:54 +00:00
|
|
|
const char *codepage, int32_t *expectOffsets)
|
1999-08-16 21:50:52 +00:00
|
|
|
{
|
2000-02-05 00:01:54 +00:00
|
|
|
UErrorCode status = U_ZERO_ERROR;
|
|
|
|
UConverter *conv = 0;
|
2000-08-11 03:35:25 +00:00
|
|
|
uint8_t junkout[NEW_MAX_BUFFER]; /* FIX */
|
2000-02-05 00:01:54 +00:00
|
|
|
int32_t junokout[NEW_MAX_BUFFER]; /* FIX */
|
2000-08-11 03:35:25 +00:00
|
|
|
uint8_t *p;
|
2000-02-05 00:01:54 +00:00
|
|
|
const UChar *src;
|
2000-08-11 03:35:25 +00:00
|
|
|
uint8_t *end;
|
|
|
|
uint8_t *targ;
|
2000-02-05 00:01:54 +00:00
|
|
|
int32_t *offs;
|
|
|
|
int i;
|
|
|
|
int32_t realBufferSize;
|
2000-08-11 03:35:25 +00:00
|
|
|
uint8_t *realBufferEnd;
|
2000-02-05 00:01:54 +00:00
|
|
|
const UChar *realSourceEnd;
|
|
|
|
const UChar *sourceLimit;
|
2000-05-18 22:08:39 +00:00
|
|
|
UBool checkOffsets = TRUE;
|
|
|
|
UBool doFlush;
|
2000-02-05 00:01:54 +00:00
|
|
|
|
|
|
|
for(i=0;i<NEW_MAX_BUFFER;i++)
|
2000-08-11 03:35:25 +00:00
|
|
|
junkout[i] = 0xF0;
|
2000-02-05 00:01:54 +00:00
|
|
|
for(i=0;i<NEW_MAX_BUFFER;i++)
|
|
|
|
junokout[i] = 0xFF;
|
|
|
|
|
|
|
|
setNuConvTestName(codepage, "FROM");
|
|
|
|
|
|
|
|
log_verbose("\n========= %s\n", gNuConvTestName);
|
|
|
|
|
|
|
|
conv = ucnv_open(codepage, &status);
|
|
|
|
if(U_FAILURE(status))
|
|
|
|
{
|
|
|
|
log_err("Couldn't open converter %s\n",codepage);
|
|
|
|
return FALSE;
|
|
|
|
}
|
|
|
|
|
|
|
|
log_verbose("Converter opened..\n");
|
|
|
|
|
|
|
|
src = source;
|
|
|
|
targ = junkout;
|
|
|
|
offs = junokout;
|
|
|
|
|
|
|
|
realBufferSize = (sizeof(junkout)/sizeof(junkout[0]));
|
|
|
|
realBufferEnd = junkout + realBufferSize;
|
|
|
|
realSourceEnd = source + sourceLen;
|
|
|
|
|
|
|
|
if ( gOutBufferSize != realBufferSize )
|
|
|
|
checkOffsets = FALSE;
|
1999-08-16 21:50:52 +00:00
|
|
|
|
2000-02-05 00:01:54 +00:00
|
|
|
if( gInBufferSize != NEW_MAX_BUFFER )
|
|
|
|
checkOffsets = FALSE;
|
1999-08-16 21:50:52 +00:00
|
|
|
|
2000-02-05 00:01:54 +00:00
|
|
|
do
|
|
|
|
{
|
|
|
|
end = nct_min(targ + gOutBufferSize, realBufferEnd);
|
|
|
|
sourceLimit = nct_min(src + gInBufferSize, realSourceEnd);
|
1999-08-16 21:50:52 +00:00
|
|
|
|
2000-08-11 03:35:25 +00:00
|
|
|
doFlush = (UBool)(sourceLimit == realSourceEnd);
|
1999-08-16 21:50:52 +00:00
|
|
|
|
2000-02-05 00:01:54 +00:00
|
|
|
if(targ == realBufferEnd)
|
|
|
|
{
|
|
|
|
log_err("Error, overflowed the real buffer while about to call fromUnicode! targ=%08lx %s", targ, gNuConvTestName);
|
|
|
|
return FALSE;
|
|
|
|
}
|
|
|
|
log_verbose("calling fromUnicode @ SOURCE:%08lx to %08lx TARGET: %08lx to %08lx, flush=%s\n", src,sourceLimit, targ,end, doFlush?"TRUE":"FALSE");
|
|
|
|
|
1999-08-16 21:50:52 +00:00
|
|
|
|
2000-02-05 00:01:54 +00:00
|
|
|
status = U_ZERO_ERROR;
|
1999-08-16 21:50:52 +00:00
|
|
|
|
2000-02-05 00:01:54 +00:00
|
|
|
ucnv_fromUnicode (conv,
|
2000-08-11 03:35:25 +00:00
|
|
|
(char **)&targ,
|
|
|
|
(const int8_t*)end,
|
2000-02-05 00:01:54 +00:00
|
|
|
&src,
|
|
|
|
sourceLimit,
|
|
|
|
checkOffsets ? offs : NULL,
|
|
|
|
doFlush, /* flush if we're at the end of the input data */
|
|
|
|
&status);
|
2000-07-13 18:59:50 +00:00
|
|
|
} while ( (status == U_INDEX_OUTOFBOUNDS_ERROR) || (U_SUCCESS(status) && sourceLimit < realSourceEnd) );
|
2000-02-05 00:01:54 +00:00
|
|
|
|
|
|
|
if(U_FAILURE(status))
|
|
|
|
{
|
2000-07-19 20:14:27 +00:00
|
|
|
log_err("Problem doing fromUnicode to %s, errcode %s %s\n", codepage, myErrorName(status), gNuConvTestName);
|
2000-02-05 00:01:54 +00:00
|
|
|
return FALSE;
|
|
|
|
}
|
|
|
|
|
|
|
|
log_verbose("\nConversion done [%d uchars in -> %d chars out]. \nResult :",
|
|
|
|
sourceLen, targ-junkout);
|
|
|
|
if(VERBOSITY)
|
|
|
|
{
|
2000-08-11 03:35:25 +00:00
|
|
|
uint8_t junk[9999];
|
|
|
|
uint8_t offset_str[9999];
|
|
|
|
uint8_t *p;
|
|
|
|
|
2000-02-05 00:01:54 +00:00
|
|
|
junk[0] = 0;
|
|
|
|
offset_str[0] = 0;
|
|
|
|
for(p = junkout;p<targ;p++)
|
|
|
|
{
|
2000-08-11 03:35:25 +00:00
|
|
|
sprintf((char *)junk + strlen(junk), "0x%02x, ", (0xFF & *p));
|
|
|
|
sprintf((char *)offset_str + strlen(offset_str), "0x%02x, ", 0xFF & junokout[p-junkout]);
|
2000-02-05 00:01:54 +00:00
|
|
|
}
|
2000-08-11 03:35:25 +00:00
|
|
|
|
|
|
|
log_verbose((char *)junk);
|
|
|
|
printSeq((const uint8_t *)expect, expectLen);
|
2000-02-05 00:01:54 +00:00
|
|
|
if ( checkOffsets )
|
|
|
|
{
|
|
|
|
log_verbose("\nOffsets:");
|
2000-08-11 03:35:25 +00:00
|
|
|
log_verbose((const char *)offset_str);
|
2000-02-05 00:01:54 +00:00
|
|
|
}
|
|
|
|
log_verbose("\n");
|
|
|
|
}
|
|
|
|
ucnv_close(conv);
|
|
|
|
|
|
|
|
|
|
|
|
if(expectLen != targ-junkout)
|
|
|
|
{
|
|
|
|
log_err("Expected %d chars out, got %d %s\n", expectLen, targ-junkout, gNuConvTestName);
|
2000-06-22 01:18:30 +00:00
|
|
|
log_verbose("Expected %d chars out, got %d %s\n", expectLen, targ-junkout, gNuConvTestName);
|
2000-07-19 20:14:27 +00:00
|
|
|
printf("\nGot:");
|
2000-08-11 03:35:25 +00:00
|
|
|
printSeqErr(junkout, targ-junkout);
|
2000-07-19 20:14:27 +00:00
|
|
|
printf("\nExpected:");
|
2000-08-11 03:35:25 +00:00
|
|
|
printSeqErr(expect, expectLen);
|
2000-02-05 00:01:54 +00:00
|
|
|
return FALSE;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (checkOffsets && (expectOffsets != 0) )
|
|
|
|
{
|
|
|
|
log_verbose("comparing %d offsets..\n", targ-junkout);
|
2000-06-22 01:18:30 +00:00
|
|
|
if(memcmp(junokout,expectOffsets,(targ-junkout) * sizeof(int32_t) )){
|
2000-02-05 00:01:54 +00:00
|
|
|
log_err("did not get the expected offsets. %s", gNuConvTestName);
|
2000-06-22 01:18:30 +00:00
|
|
|
log_err("Got : ");
|
2000-08-11 03:35:25 +00:00
|
|
|
printSeqErr(junkout, targ-junkout);
|
|
|
|
for(p=junkout;p<targ;p++)
|
|
|
|
log_err("%d, ", junokout[p-junkout]);
|
|
|
|
log_err("\nExpected: ");
|
|
|
|
for(i=0; i<(targ-junkout); i++)
|
|
|
|
log_err("%d,", expectOffsets[i]);
|
2000-06-22 01:18:30 +00:00
|
|
|
}
|
2000-02-05 00:01:54 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
log_verbose("comparing..\n");
|
|
|
|
if(!memcmp(junkout, expect, expectLen))
|
|
|
|
{
|
|
|
|
log_verbose("Matches!\n");
|
|
|
|
return TRUE;
|
|
|
|
}
|
|
|
|
else
|
2000-08-11 03:35:25 +00:00
|
|
|
{
|
2000-02-05 00:01:54 +00:00
|
|
|
log_err("String does not match. %s\n", gNuConvTestName);
|
2000-07-13 00:28:06 +00:00
|
|
|
printUSeqErr(source, sourceLen);
|
2000-07-19 20:14:27 +00:00
|
|
|
printf("\nGot:");
|
2000-06-28 22:26:59 +00:00
|
|
|
printSeqErr((const unsigned char *)junkout, expectLen);
|
2000-07-19 20:14:27 +00:00
|
|
|
printf("\nExpected:");
|
2000-06-28 22:26:59 +00:00
|
|
|
printSeqErr((const unsigned char *)expect, expectLen);
|
2000-02-05 00:01:54 +00:00
|
|
|
|
|
|
|
return FALSE;
|
|
|
|
}
|
1999-08-16 21:50:52 +00:00
|
|
|
}
|
|
|
|
|
2000-08-11 03:35:25 +00:00
|
|
|
UBool testConvertToU( const uint8_t *source, int sourcelen, const UChar *expect, int expectlen,
|
2000-02-05 00:01:54 +00:00
|
|
|
const char *codepage, int32_t *expectOffsets)
|
1999-08-16 21:50:52 +00:00
|
|
|
{
|
2000-02-05 00:01:54 +00:00
|
|
|
UErrorCode status = U_ZERO_ERROR;
|
|
|
|
UConverter *conv = 0;
|
|
|
|
UChar junkout[NEW_MAX_BUFFER]; /* FIX */
|
|
|
|
int32_t junokout[NEW_MAX_BUFFER]; /* FIX */
|
2000-08-11 03:35:25 +00:00
|
|
|
const uint8_t *src;
|
|
|
|
const uint8_t *realSourceEnd;
|
|
|
|
const uint8_t *srcLimit;
|
2000-06-22 01:18:30 +00:00
|
|
|
UChar *p;
|
2000-02-05 00:01:54 +00:00
|
|
|
UChar *targ;
|
|
|
|
UChar *end;
|
|
|
|
int32_t *offs;
|
|
|
|
int i;
|
2000-05-18 22:08:39 +00:00
|
|
|
UBool checkOffsets = TRUE;
|
2000-02-05 00:01:54 +00:00
|
|
|
|
|
|
|
int32_t realBufferSize;
|
|
|
|
UChar *realBufferEnd;
|
|
|
|
|
|
|
|
|
|
|
|
for(i=0;i<NEW_MAX_BUFFER;i++)
|
|
|
|
junkout[i] = 0xFFFE;
|
|
|
|
|
|
|
|
for(i=0;i<NEW_MAX_BUFFER;i++)
|
|
|
|
junokout[i] = -1;
|
|
|
|
|
|
|
|
setNuConvTestName(codepage, "TO");
|
|
|
|
|
|
|
|
log_verbose("\n========= %s\n", gNuConvTestName);
|
|
|
|
|
|
|
|
conv = ucnv_open(codepage, &status);
|
|
|
|
if(U_FAILURE(status))
|
|
|
|
{
|
|
|
|
log_err("Couldn't open converter %s\n",gNuConvTestName);
|
|
|
|
return FALSE;
|
|
|
|
}
|
|
|
|
|
|
|
|
log_verbose("Converter opened..\n");
|
|
|
|
|
|
|
|
src = source;
|
|
|
|
targ = junkout;
|
|
|
|
offs = junokout;
|
|
|
|
|
|
|
|
realBufferSize = (sizeof(junkout)/sizeof(junkout[0]));
|
|
|
|
realBufferEnd = junkout + realBufferSize;
|
|
|
|
realSourceEnd = src + sourcelen;
|
|
|
|
|
|
|
|
if ( gOutBufferSize != realBufferSize )
|
|
|
|
checkOffsets = FALSE;
|
|
|
|
|
|
|
|
if( gInBufferSize != NEW_MAX_BUFFER )
|
|
|
|
checkOffsets = FALSE;
|
|
|
|
|
|
|
|
do
|
|
|
|
{
|
|
|
|
end = nct_min( targ + gOutBufferSize, realBufferEnd);
|
|
|
|
srcLimit = nct_min(realSourceEnd, src + gInBufferSize);
|
|
|
|
|
|
|
|
if(targ == realBufferEnd)
|
|
|
|
{
|
|
|
|
log_err("Error, the end would overflow the real output buffer while about to call toUnicode! tarjey=%08lx %s",targ,gNuConvTestName);
|
|
|
|
return FALSE;
|
|
|
|
}
|
|
|
|
log_verbose("calling toUnicode @ %08lx to %08lx\n", targ,end);
|
|
|
|
|
|
|
|
/* oldTarg = targ; */
|
|
|
|
|
|
|
|
status = U_ZERO_ERROR;
|
|
|
|
|
|
|
|
ucnv_toUnicode (conv,
|
|
|
|
&targ,
|
|
|
|
end,
|
2000-08-11 03:35:25 +00:00
|
|
|
(const char **)&src,
|
|
|
|
(const char *)srcLimit,
|
2000-02-05 00:01:54 +00:00
|
|
|
checkOffsets ? offs : NULL,
|
2000-05-18 22:08:39 +00:00
|
|
|
(UBool)(srcLimit == realSourceEnd), /* flush if we're at the end of hte source data */
|
2000-02-05 00:01:54 +00:00
|
|
|
&status);
|
|
|
|
|
|
|
|
/* offs += (targ-oldTarg); */
|
|
|
|
|
2000-07-13 17:58:28 +00:00
|
|
|
} while ( (status == U_INDEX_OUTOFBOUNDS_ERROR) || (U_SUCCESS(status) && (srcLimit < realSourceEnd)) ); /* while we just need another buffer */
|
2000-02-05 00:01:54 +00:00
|
|
|
|
|
|
|
if(U_FAILURE(status))
|
|
|
|
{
|
2000-07-19 20:14:27 +00:00
|
|
|
log_err("Problem doing %s toUnicode, errcode %s %s\n", codepage, myErrorName(status), gNuConvTestName);
|
2000-02-05 00:01:54 +00:00
|
|
|
return FALSE;
|
|
|
|
}
|
|
|
|
|
|
|
|
log_verbose("\nConversion done. %d bytes -> %d chars.\nResult :",
|
|
|
|
sourcelen, targ-junkout);
|
|
|
|
if(VERBOSITY)
|
|
|
|
{
|
|
|
|
char junk[9999];
|
|
|
|
char offset_str[9999];
|
|
|
|
|
|
|
|
UChar *p;
|
|
|
|
|
|
|
|
junk[0] = 0;
|
|
|
|
offset_str[0] = 0;
|
|
|
|
|
|
|
|
for(p = junkout;p<targ;p++)
|
|
|
|
{
|
|
|
|
sprintf(junk + strlen(junk), "0x%04x, ", (0xFFFF) & (unsigned int)*p);
|
|
|
|
sprintf(offset_str + strlen(offset_str), "0x%04x, ", (0xFFFF) & (unsigned int)junokout[p-junkout]);
|
|
|
|
}
|
|
|
|
|
|
|
|
log_verbose(junk);
|
|
|
|
|
|
|
|
if ( checkOffsets )
|
|
|
|
{
|
|
|
|
log_verbose("\nOffsets:");
|
|
|
|
log_verbose(offset_str);
|
|
|
|
}
|
|
|
|
log_verbose("\n");
|
|
|
|
}
|
|
|
|
ucnv_close(conv);
|
|
|
|
|
|
|
|
log_verbose("comparing %d uchars (%d bytes)..\n",expectlen,expectlen*2);
|
|
|
|
|
|
|
|
if (checkOffsets && (expectOffsets != 0))
|
|
|
|
{
|
2000-06-22 01:18:30 +00:00
|
|
|
if(memcmp(junokout,expectOffsets,(targ-junkout) * sizeof(int32_t))){
|
|
|
|
|
2000-02-05 00:01:54 +00:00
|
|
|
log_err("did not get the expected offsets. %s",gNuConvTestName);
|
2000-06-22 01:18:30 +00:00
|
|
|
for(p=junkout;p<targ;p++)
|
2000-08-11 03:35:25 +00:00
|
|
|
log_err("%d, ", junokout[p-junkout]);
|
|
|
|
log_err("\nExpected: ");
|
|
|
|
for(i=0; i<(targ-junkout); i++)
|
|
|
|
log_err("%d,", expectOffsets[i]);
|
|
|
|
log_err("");
|
|
|
|
for(i=0; i<(targ-junkout); i++)
|
|
|
|
log_err("%X,", junkout[i]);
|
|
|
|
log_err("");
|
|
|
|
for(i=0; i<(src-source); i++)
|
|
|
|
log_err("%X,", (unsigned char)source[i]);
|
|
|
|
}
|
2000-02-05 00:01:54 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
if(!memcmp(junkout, expect, expectlen*2))
|
|
|
|
{
|
|
|
|
log_verbose("Matches!\n");
|
|
|
|
return TRUE;
|
|
|
|
}
|
|
|
|
else
|
|
|
|
{
|
|
|
|
log_err("String does not match. %s\n", gNuConvTestName);
|
2000-06-22 01:18:30 +00:00
|
|
|
log_verbose("String does not match. %s\n", gNuConvTestName);
|
2000-07-19 20:14:27 +00:00
|
|
|
printf("\nGot:");
|
2000-08-11 03:35:25 +00:00
|
|
|
printUSeq(junkout, expectlen);
|
2000-07-19 20:14:27 +00:00
|
|
|
printf("\nExpected:");
|
2000-02-05 00:01:54 +00:00
|
|
|
printUSeq(expect, expectlen);
|
|
|
|
return FALSE;
|
|
|
|
}
|
1999-08-16 21:50:52 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
void TestNewConvertWithBufferSizes(int32_t outsize, int32_t insize )
|
|
|
|
{
|
|
|
|
/** test chars #1 */
|
2000-02-05 00:01:54 +00:00
|
|
|
/* 1 2 3 1Han 2Han 3Han . */
|
|
|
|
UChar sampleText[] =
|
2000-06-22 01:18:30 +00:00
|
|
|
{ 0x0031, 0x0032, 0x0033, 0x0000, 0x4e00, 0x4e8c, 0x4e09, 0x002E };
|
1999-08-16 21:50:52 +00:00
|
|
|
|
2000-02-05 00:01:54 +00:00
|
|
|
|
2000-08-11 03:35:25 +00:00
|
|
|
const uint8_t expectedUTF8[] =
|
|
|
|
{ 0x31, 0x32, 0x33, 0x00, 0xe4, 0xb8, 0x80, 0xe4, 0xba, 0x8c, 0xe4, 0xb8, 0x89, 0x2E };
|
2000-02-05 00:01:54 +00:00
|
|
|
int32_t toUTF8Offs[] =
|
2000-08-11 03:35:25 +00:00
|
|
|
{ 0x00, 0x01, 0x02, 0x03, 0x04, 0x04, 0x04, 0x05, 0x05, 0x05, 0x06, 0x06, 0x06, 0x07};
|
2000-06-22 01:18:30 +00:00
|
|
|
int32_t fmUTF8Offs[] =
|
|
|
|
{ 0x0000, 0x0001, 0x0002, 0x0003, 0x0004, 0x0007, 0x000a, 0x000d };
|
|
|
|
|
2000-02-05 00:01:54 +00:00
|
|
|
/* Same as UTF8, but with ^[%B preceeding */
|
2000-08-11 03:35:25 +00:00
|
|
|
const uint8_t expectedISO2022[] =
|
|
|
|
{ 0x1b, 0x25, 0x42, 0x31, 0x32, 0x33, 0x00, 0xe4, 0xb8, 0x80, 0xe4, 0xba, 0x8c, 0xe4, 0xb8, 0x89, 0x2E };
|
2000-02-05 00:01:54 +00:00
|
|
|
int32_t toISO2022Offs[] =
|
2000-08-11 03:35:25 +00:00
|
|
|
{ 0xff, 0xff, 0xff, 0x00, 0x01, 0x02, 0x03, 0x04, 0x04,
|
|
|
|
0x04, 0x05, 0x05, 0x05, 0x06, 0x06, 0x06, 0x07 }; /* right? */
|
2000-06-22 01:18:30 +00:00
|
|
|
int32_t fmISO2022Offs[] =
|
|
|
|
{ 0x0003, 0x0004, 0x0005, 0x0006, 0x0007, 0x000a, 0x000d, 0x0010 }; /* is this right? */
|
|
|
|
|
|
|
|
/* 1 2 3 0, <SO> h1 h2 h3 <SI> . EBCDIC_STATEFUL */
|
2000-08-11 03:35:25 +00:00
|
|
|
const uint8_t expectedIBM930[] =
|
|
|
|
{ 0xF1, 0xF2, 0xF3, 0x00, 0x0E, 0x45, 0x41, 0x45, 0x42, 0x45, 0x43, 0x0F, 0x4B };
|
2000-02-05 00:01:54 +00:00
|
|
|
int32_t toIBM930Offs[] =
|
2000-08-11 03:35:25 +00:00
|
|
|
{ 0x00, 0x01, 0x02, 0x03, 0x04, 0x04, 0x04, 0x05, 0x05, 0x06, 0x06, 0x07, 0x07, };
|
2000-06-22 01:18:30 +00:00
|
|
|
int32_t fmIBM930Offs[] =
|
|
|
|
{ 0x0000, 0x0001, 0x0002, 0x0003, 0x0005, 0x0007, 0x0009, 0x000c};
|
|
|
|
|
|
|
|
/* 1 2 3 0 h1 h2 h3 . MBCS*/
|
2000-08-11 03:35:25 +00:00
|
|
|
const uint8_t expectedIBM943[] =
|
|
|
|
{ 0x31, 0x32, 0x33, 0x00, 0x88, 0xea, 0x93, 0xf1, 0x8e, 0x4f, 0x2e };
|
2000-02-05 00:01:54 +00:00
|
|
|
int32_t toIBM943Offs [] =
|
2000-08-11 03:35:25 +00:00
|
|
|
{ 0x00, 0x01, 0x02, 0x03, 0x04, 0x04, 0x05, 0x05, 0x06, 0x06, 0x07 };
|
2000-06-22 01:18:30 +00:00
|
|
|
int32_t fmIBM943Offs[] =
|
|
|
|
{ 0x0000, 0x0001, 0x0002, 0x0003, 0x0004, 0x0006, 0x0008, 0x000a};
|
|
|
|
|
|
|
|
/* 1 2 3 0 h1 h2 h3 . DBCS*/
|
2000-08-11 03:35:25 +00:00
|
|
|
const uint8_t expectedIBM835[] =
|
|
|
|
{ 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0x4c, 0x41, 0x4c, 0x48, 0x4c, 0x55, 0xfe, 0xfe};
|
2000-06-26 22:16:32 +00:00
|
|
|
int32_t toIBM835Offs [] =
|
2000-08-11 03:35:25 +00:00
|
|
|
{ 0x00, 0x00, 0x01, 0x01, 0x02, 0x02, 0x03, 0x03, 0x04, 0x04, 0x05, 0x05, 0x06, 0x06, 0x07, 0x07};
|
2000-06-22 01:18:30 +00:00
|
|
|
|
|
|
|
/* 1 2 3 0 <?> <?> <?> . SBCS*/
|
2000-08-11 03:35:25 +00:00
|
|
|
const uint8_t expectedIBM920[] =
|
|
|
|
{ 0x31, 0x32, 0x33, 0x00, 0x1a, 0x1a, 0x1a, 0x2e };
|
2000-06-22 01:18:30 +00:00
|
|
|
int32_t toIBM920Offs [] =
|
2000-08-11 03:35:25 +00:00
|
|
|
{ 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07 };
|
2000-06-22 01:18:30 +00:00
|
|
|
|
|
|
|
/* 1 2 3 0 <?> <?> <?> . SBCS*/
|
2000-08-11 03:35:25 +00:00
|
|
|
const uint8_t expectedISO88593[] =
|
|
|
|
{ 0x31, 0x32, 0x33, 0x00, 0x1a, 0x1a, 0x1a, 0x2E };
|
2000-06-22 01:18:30 +00:00
|
|
|
int32_t toISO88593Offs[] =
|
2000-08-11 03:35:25 +00:00
|
|
|
{ 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07};
|
1999-08-16 21:50:52 +00:00
|
|
|
|
2000-06-22 01:18:30 +00:00
|
|
|
/* 1 2 3 0 <?> <?> <?> . LATIN_1*/
|
2000-08-11 03:35:25 +00:00
|
|
|
const uint8_t expectedLATIN1[] =
|
|
|
|
{ 0x31, 0x32, 0x33, 0x00, 0x1a, 0x1a, 0x1a, 0x2E };
|
2000-06-22 01:18:30 +00:00
|
|
|
int32_t toLATIN1Offs[] =
|
2000-08-11 03:35:25 +00:00
|
|
|
{ 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07};
|
2000-06-22 01:18:30 +00:00
|
|
|
|
|
|
|
|
2000-02-05 00:01:54 +00:00
|
|
|
/* etc */
|
2000-08-11 03:35:25 +00:00
|
|
|
const uint8_t expectedUTF16LE[] =
|
|
|
|
{ 0x31, 0x00, 0x32, 0x00, 0x33, 0x00, 0x00, 0x00, 0x00, 0x4e, 0x8c, 0x4e, 0x09, 0x4e, 0x2e, 0x00 };
|
2000-02-05 00:01:54 +00:00
|
|
|
int32_t toUTF16LEOffs[]=
|
2000-08-11 03:35:25 +00:00
|
|
|
{ 0x00, 0x00, 0x01, 0x01, 0x02, 0x02, 0x03, 0x03, 0x04, 0x04, 0x05, 0x05, 0x06, 0x06, 0x07, 0x07};
|
2000-06-22 01:18:30 +00:00
|
|
|
int32_t fmUTF16LEOffs[] =
|
|
|
|
{ 0x0000, 0x0002, 0x0004, 0x0006, 0x0008, 0x000a, 0x000c, 0x000e };
|
|
|
|
|
2000-08-11 03:35:25 +00:00
|
|
|
const uint8_t expectedUTF16BE[] =
|
|
|
|
{ 0x00, 0x31, 0x00, 0x32, 0x00, 0x33, 0x00, 0x00, 0x4e, 0x00, 0x4e, 0x8c, 0x4e, 0x09, 0x00, 0x2e };
|
2000-06-22 01:18:30 +00:00
|
|
|
int32_t toUTF16BEOffs[]=
|
2000-08-11 03:35:25 +00:00
|
|
|
{ 0x00, 0x00, 0x01, 0x01, 0x02, 0x02, 0x03, 0x03, 0x04, 0x04, 0x05, 0x05, 0x06, 0x06, 0x07, 0x07};
|
2000-06-22 01:18:30 +00:00
|
|
|
int32_t fmUTF16BEOffs[] =
|
|
|
|
{ 0x0000, 0x0002, 0x0004, 0x0006, 0x0008, 0x000a, 0x000c, 0x000e };
|
|
|
|
|
|
|
|
|
|
|
|
|
1999-08-16 21:50:52 +00:00
|
|
|
|
|
|
|
|
2000-06-28 17:01:52 +00:00
|
|
|
/** Test chars #2 **/
|
1999-08-16 21:50:52 +00:00
|
|
|
|
2000-02-05 00:01:54 +00:00
|
|
|
/* Sahha [health], slashed h's */
|
|
|
|
const UChar malteseUChars[] = { 0x0053, 0x0061, 0x0127, 0x0127, 0x0061 };
|
2000-08-11 03:35:25 +00:00
|
|
|
const uint8_t expectedMaltese913[] = { 0x53, 0x61, 0xB1, 0xB1, 0x61 };
|
2000-06-22 01:18:30 +00:00
|
|
|
|
|
|
|
/* LMBCS */
|
|
|
|
const UChar LMBCSUChars[] = { 0x0027, 0x010A, 0x0000, 0x0127, 0x2666 };
|
2000-08-11 03:35:25 +00:00
|
|
|
const uint8_t expectedLMBCS[] = { 0x27, 0x06, 0x04, 0x00, 0x01, 0x73, 0x01, 0x04 };
|
|
|
|
int32_t toLMBCSOffs[] = { 0x00, 0x01, 0x01, 0x02, 0x03, 0x03, 0x04, 0x04 };
|
2000-06-22 01:18:30 +00:00
|
|
|
int32_t fmLMBCSOffs[] = { 0x0000, 0x0001, 0x0003, 0x0004, 0x0006};
|
2000-02-05 00:01:54 +00:00
|
|
|
/*********************************** START OF CODE finally *************/
|
1999-08-16 21:50:52 +00:00
|
|
|
|
|
|
|
gInBufferSize = insize;
|
|
|
|
gOutBufferSize = outsize;
|
|
|
|
|
|
|
|
log_verbose("\n\n\nTesting conversions with InputBufferSize = %d, OutputBufferSize = %d\n", gInBufferSize, gOutBufferSize);
|
|
|
|
|
2000-02-05 00:01:54 +00:00
|
|
|
|
2000-06-29 02:53:29 +00:00
|
|
|
#if 1
|
2000-06-22 01:18:30 +00:00
|
|
|
/*UTF-8*/
|
2000-02-05 00:01:54 +00:00
|
|
|
if(!testConvertFromU(sampleText, sizeof(sampleText)/sizeof(sampleText[0]),
|
|
|
|
expectedUTF8, sizeof(expectedUTF8), "UTF8", toUTF8Offs ))
|
|
|
|
log_err("u-> UTF8 did not match.\n");
|
2000-07-19 20:14:27 +00:00
|
|
|
|
|
|
|
log_verbose("Test surrogate behaviour for UTF8\n");
|
|
|
|
{
|
|
|
|
const UChar testinput[]={ 0x20ac, 0xd801, 0xdc01, 0xdc01, 0xd801};
|
2000-08-11 03:35:25 +00:00
|
|
|
const uint8_t expectedUTF8[]= { 0xe2, 0x82, 0xac,
|
|
|
|
0xf0, 0x90, 0x90, 0x81,
|
|
|
|
0xed, 0xb0, 0x81, 0xed, 0xa0, 0x81
|
2000-07-19 20:14:27 +00:00
|
|
|
};
|
2000-07-20 20:08:40 +00:00
|
|
|
int32_t offsets[]={ 0, 0, 0, 1, 1, 1, 1, 3, 3, 3, 4, 4, 4 };
|
2000-07-19 20:14:27 +00:00
|
|
|
if(!testConvertFromU(testinput, sizeof(testinput)/sizeof(testinput[0]),
|
|
|
|
expectedUTF8, sizeof(expectedUTF8), "UTF8", offsets ))
|
|
|
|
log_err("u-> UTF8 did not match.\n");
|
|
|
|
|
|
|
|
}
|
2000-06-22 01:18:30 +00:00
|
|
|
/*ISO-2022*/
|
2000-07-22 00:08:14 +00:00
|
|
|
if(/* broken for icu 1.6, do not test */uprv_strcmp("1.6", U_ICU_VERSION) != 0 && !testConvertFromU(sampleText, sizeof(sampleText)/sizeof(sampleText[0]),
|
2000-02-05 00:01:54 +00:00
|
|
|
expectedISO2022, sizeof(expectedISO2022), "iso-2022", toISO2022Offs ))
|
|
|
|
log_err("u-> iso-2022 did not match.\n");
|
2000-06-22 01:18:30 +00:00
|
|
|
/*UTF16 LE*/
|
|
|
|
if(!testConvertFromU(sampleText, sizeof(sampleText)/sizeof(sampleText[0]),
|
|
|
|
expectedUTF16LE, sizeof(expectedUTF16LE), "utf-16le", toUTF16LEOffs ))
|
|
|
|
log_err("u-> utf-16le did not match.\n");
|
|
|
|
/*UTF16 BE*/
|
|
|
|
if(!testConvertFromU(sampleText, sizeof(sampleText)/sizeof(sampleText[0]),
|
|
|
|
expectedUTF16BE, sizeof(expectedUTF16BE), "utf-16be", toUTF16BEOffs ))
|
|
|
|
log_err("u-> utf-16be did not match.\n");
|
|
|
|
/*LATIN_1*/
|
|
|
|
if(!testConvertFromU(sampleText, sizeof(sampleText)/sizeof(sampleText[0]),
|
|
|
|
expectedLATIN1, sizeof(expectedLATIN1), "LATIN_1", toLATIN1Offs ))
|
|
|
|
log_err("u-> LATIN_1 did not match.\n");
|
|
|
|
/*EBCDIC_STATEFUL*/
|
2000-02-05 00:01:54 +00:00
|
|
|
if(!testConvertFromU(sampleText, sizeof(sampleText)/sizeof(sampleText[0]),
|
|
|
|
expectedIBM930, sizeof(expectedIBM930), "ibm-930", toIBM930Offs ))
|
|
|
|
log_err("u-> ibm-930 did not match.\n");
|
2000-06-28 17:01:52 +00:00
|
|
|
|
|
|
|
if(!testConvertFromU(sampleText, sizeof(sampleText)/sizeof(sampleText[0]),
|
|
|
|
expectedISO88593, sizeof(expectedISO88593), "iso-8859-3", toISO88593Offs ))
|
|
|
|
log_err("u-> iso-8859-3 did not match.\n");
|
|
|
|
|
2000-06-22 01:18:30 +00:00
|
|
|
/*MBCS*/
|
2000-06-28 17:01:52 +00:00
|
|
|
|
2000-02-05 00:01:54 +00:00
|
|
|
if(!testConvertFromU(sampleText, sizeof(sampleText)/sizeof(sampleText[0]),
|
|
|
|
expectedIBM943, sizeof(expectedIBM943), "ibm-943", toIBM943Offs ))
|
|
|
|
log_err("u-> ibm-943 [UCNV_MBCS] not match.\n");
|
2000-06-22 01:18:30 +00:00
|
|
|
/*DBCS*/
|
2000-02-05 00:01:54 +00:00
|
|
|
if(!testConvertFromU(sampleText, sizeof(sampleText)/sizeof(sampleText[0]),
|
2000-06-26 22:16:32 +00:00
|
|
|
expectedIBM835, sizeof(expectedIBM835), "ibm-835", toIBM835Offs ))
|
|
|
|
log_err("u-> ibm-835 [UCNV_DBCS] not match.\n");
|
2000-06-22 01:18:30 +00:00
|
|
|
/*SBCS*/
|
|
|
|
if(!testConvertFromU(sampleText, sizeof(sampleText)/sizeof(sampleText[0]),
|
|
|
|
expectedIBM920, sizeof(expectedIBM920), "ibm-920", toIBM920Offs ))
|
|
|
|
log_err("u-> ibm-920 [UCNV_SBCS] not match.\n");
|
|
|
|
/*SBCS*/
|
|
|
|
if(!testConvertFromU(sampleText, sizeof(sampleText)/sizeof(sampleText[0]),
|
|
|
|
expectedISO88593, sizeof(expectedISO88593), "iso-8859-3", toISO88593Offs ))
|
|
|
|
log_err("u-> iso-8859-3 did not match.\n");
|
1999-08-16 21:50:52 +00:00
|
|
|
|
2000-06-22 01:18:30 +00:00
|
|
|
|
1999-08-16 21:50:52 +00:00
|
|
|
/****/
|
2000-06-29 02:53:29 +00:00
|
|
|
#endif
|
1999-12-04 02:31:40 +00:00
|
|
|
|
2000-06-29 02:53:29 +00:00
|
|
|
#if 1
|
2000-06-22 01:18:30 +00:00
|
|
|
/*UTF-8*/
|
2000-02-05 00:01:54 +00:00
|
|
|
if(!testConvertToU(expectedUTF8, sizeof(expectedUTF8),
|
|
|
|
sampleText, sizeof(sampleText)/sizeof(sampleText[0]), "utf8", fmUTF8Offs ))
|
|
|
|
log_err("utf8 -> u did not match\n");
|
2000-06-22 01:18:30 +00:00
|
|
|
/*ISO-2022*/
|
2000-07-21 23:28:07 +00:00
|
|
|
if(/* broken for icu 1.6, do not test */uprv_strcmp("1.6", U_ICU_VERSION) != 0 && !testConvertToU(expectedISO2022, sizeof(expectedISO2022),
|
2000-02-05 00:01:54 +00:00
|
|
|
sampleText, sizeof(sampleText)/sizeof(sampleText[0]), "iso-2022", fmISO2022Offs ))
|
2000-07-14 20:40:05 +00:00
|
|
|
log_err("iso-2022 -> u did not match.\n");
|
2000-06-22 01:18:30 +00:00
|
|
|
/*UTF16 LE*/
|
|
|
|
if(!testConvertToU(expectedUTF16LE, sizeof(expectedUTF16LE),
|
|
|
|
sampleText, sizeof(sampleText)/sizeof(sampleText[0]), "utf-16le", fmUTF16LEOffs ))
|
2000-07-14 20:40:05 +00:00
|
|
|
log_err("utf-16le -> u did not match.\n");
|
2000-06-22 01:18:30 +00:00
|
|
|
/*UTF16 BE*/
|
|
|
|
if(!testConvertToU(expectedUTF16BE, sizeof(expectedUTF16BE),
|
|
|
|
sampleText, sizeof(sampleText)/sizeof(sampleText[0]), "utf-16be", fmUTF16BEOffs ))
|
2000-07-14 20:40:05 +00:00
|
|
|
log_err("utf-16be -> u did not match.\n");
|
2000-06-22 01:18:30 +00:00
|
|
|
/*EBCDIC_STATEFUL*/
|
2000-02-05 00:01:54 +00:00
|
|
|
if(!testConvertToU(expectedIBM930, sizeof(expectedIBM930),
|
|
|
|
sampleText, sizeof(sampleText)/sizeof(sampleText[0]), "ibm-930", fmIBM930Offs ))
|
2000-07-14 20:40:05 +00:00
|
|
|
log_err("ibm-930 -> u did not match.\n");
|
2000-06-22 01:18:30 +00:00
|
|
|
/*MBCS*/
|
2000-02-05 00:01:54 +00:00
|
|
|
if(!testConvertToU(expectedIBM943, sizeof(expectedIBM943),
|
|
|
|
sampleText, sizeof(sampleText)/sizeof(sampleText[0]), "ibm-943", fmIBM943Offs ))
|
2000-07-14 20:40:05 +00:00
|
|
|
log_err("ibm-943 -> u did not match.\n");
|
2000-06-28 17:01:52 +00:00
|
|
|
|
|
|
|
if(!testConvertToU(expectedUTF16LE, sizeof(expectedUTF16LE),
|
|
|
|
sampleText, sizeof(sampleText)/sizeof(sampleText[0]), "utf-16le", fmUTF16LEOffs ))
|
2000-07-14 20:40:05 +00:00
|
|
|
log_err("utf-16le -> u did not match.\n");
|
1999-12-04 02:31:40 +00:00
|
|
|
|
2000-02-05 00:01:54 +00:00
|
|
|
if(!testConvertToU(expectedMaltese913, sizeof(expectedMaltese913),
|
|
|
|
malteseUChars, sizeof(malteseUChars)/sizeof(malteseUChars[0]), "latin3", NULL))
|
|
|
|
log_err("latin3[813] -> u did not match\n");
|
1999-12-04 02:31:40 +00:00
|
|
|
|
2000-02-05 00:01:54 +00:00
|
|
|
if(!testConvertFromU(malteseUChars, sizeof(malteseUChars)/sizeof(malteseUChars[0]),
|
|
|
|
expectedMaltese913, sizeof(expectedMaltese913), "iso-8859-3", NULL ))
|
2000-06-22 01:18:30 +00:00
|
|
|
log_err("u-> latin3[813] did not match.\n");
|
|
|
|
|
2000-06-28 17:01:52 +00:00
|
|
|
/*LMBCS*/
|
2000-06-22 01:18:30 +00:00
|
|
|
if(!testConvertFromU(LMBCSUChars, sizeof(LMBCSUChars)/sizeof(LMBCSUChars[0]),
|
|
|
|
expectedLMBCS, sizeof(expectedLMBCS), "LMBCS-1", toLMBCSOffs ))
|
|
|
|
log_err("u-> LMBCS-1 did not match.\n");
|
|
|
|
if(!testConvertToU(expectedLMBCS, sizeof(expectedLMBCS),
|
|
|
|
LMBCSUChars, sizeof(LMBCSUChars)/sizeof(LMBCSUChars[0]), "LMBCS-1", fmLMBCSOffs ))
|
2000-07-14 20:40:05 +00:00
|
|
|
log_err("LMBCS-1 -> u did not match.\n");
|
2000-06-22 01:18:30 +00:00
|
|
|
|
|
|
|
}
|
|
|
|
|
1999-08-16 21:50:52 +00:00
|
|
|
|
|
|
|
void TestConverterTypesAndStarters()
|
|
|
|
{
|
2000-02-05 00:01:54 +00:00
|
|
|
UConverter* myConverter[3];
|
|
|
|
UErrorCode err = U_ZERO_ERROR;
|
2000-05-18 22:08:39 +00:00
|
|
|
UBool mystarters[256];
|
2000-02-05 00:01:54 +00:00
|
|
|
|
2000-08-11 03:35:25 +00:00
|
|
|
/* const UBool expectedKSCstarters[256] = {
|
2000-02-05 00:01:54 +00:00
|
|
|
FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE,
|
|
|
|
FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE,
|
|
|
|
FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE,
|
|
|
|
FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE,
|
|
|
|
FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE,
|
|
|
|
FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE,
|
|
|
|
FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE,
|
|
|
|
FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE,
|
|
|
|
FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE,
|
|
|
|
FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE,
|
|
|
|
FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE,
|
|
|
|
FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE,
|
|
|
|
FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE,
|
|
|
|
FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE,
|
|
|
|
FALSE, FALSE, FALSE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE,
|
|
|
|
TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE,
|
|
|
|
TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE,
|
|
|
|
TRUE, TRUE, TRUE, FALSE, FALSE, TRUE, TRUE, TRUE, TRUE, TRUE,
|
|
|
|
TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE,
|
|
|
|
TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE,
|
|
|
|
TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE,
|
|
|
|
TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE,
|
|
|
|
TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE,
|
|
|
|
TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE,
|
|
|
|
TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE,
|
2000-08-11 03:35:25 +00:00
|
|
|
TRUE, TRUE, TRUE, TRUE, TRUE, TRUE};*/
|
1999-08-16 21:50:52 +00:00
|
|
|
|
|
|
|
|
|
|
|
log_verbose("Testing KSC, ibm-930, ibm-878 for starters and their conversion types.");
|
|
|
|
|
2000-07-10 17:35:02 +00:00
|
|
|
myConverter[0] = ucnv_open("ksc", &err);
|
2000-02-05 00:01:54 +00:00
|
|
|
if (U_FAILURE(err))
|
2000-07-10 17:35:02 +00:00
|
|
|
log_err("Failed to create an ibm-ksc converter\n");
|
2000-02-05 00:01:54 +00:00
|
|
|
else
|
|
|
|
{
|
|
|
|
if (ucnv_getType(myConverter[0])!=UCNV_MBCS) log_err("ucnv_getType Failed for ibm-949\n");
|
|
|
|
else log_verbose("ucnv_getType ibm-949 ok\n");
|
|
|
|
|
|
|
|
if(myConverter[0]!=NULL)
|
|
|
|
ucnv_getStarters(myConverter[0], mystarters, &err);
|
|
|
|
|
|
|
|
/*if (memcmp(expectedKSCstarters, mystarters, sizeof(expectedKSCstarters)))
|
|
|
|
log_err("Failed ucnv_getStarters for ksc\n");
|
|
|
|
else
|
|
|
|
log_verbose("ucnv_getStarters ok\n");*/
|
|
|
|
|
|
|
|
}
|
|
|
|
|
|
|
|
myConverter[1] = ucnv_open("ibm-930", &err);
|
|
|
|
if (U_FAILURE(err))
|
|
|
|
log_err("Failed to create an ibm-930 converter\n");
|
|
|
|
else
|
|
|
|
{
|
|
|
|
if (ucnv_getType(myConverter[1])!=UCNV_EBCDIC_STATEFUL) log_err("ucnv_getType Failed for ibm-930\n");
|
|
|
|
else log_verbose("ucnv_getType ibm-930 ok\n");
|
|
|
|
}
|
|
|
|
|
|
|
|
myConverter[2] = ucnv_open("ibm-878", &err);
|
|
|
|
if (U_FAILURE(err))
|
|
|
|
log_err("Failed to create an ibm-815 converter\n");
|
|
|
|
else
|
|
|
|
{
|
|
|
|
if (ucnv_getType(myConverter[2])!=UCNV_SBCS) log_err("ucnv_getType Failed for ibm-815\n");
|
|
|
|
else log_verbose("ucnv_getType ibm-815 ok\n");
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
ucnv_close(myConverter[0]);
|
|
|
|
ucnv_close(myConverter[1]);
|
|
|
|
ucnv_close(myConverter[2]);
|
1999-08-16 21:50:52 +00:00
|
|
|
}
|
2000-01-08 00:54:57 +00:00
|
|
|
void TestAmbiguous()
|
|
|
|
{
|
|
|
|
UErrorCode status = U_ZERO_ERROR;
|
|
|
|
UConverter *ascii_cnv = 0, *sjis_cnv = 0;
|
2000-03-22 01:57:16 +00:00
|
|
|
const char target[] = {
|
|
|
|
/* "\\usr\\local\\share\\data\\icutest.txt" */
|
|
|
|
0x5c, 0x75, 0x73, 0x72,
|
|
|
|
0x5c, 0x6c, 0x6f, 0x63, 0x61, 0x6c,
|
|
|
|
0x5c, 0x73, 0x68, 0x61, 0x72, 0x65,
|
|
|
|
0x5c, 0x64, 0x61, 0x74, 0x61,
|
|
|
|
0x5c, 0x69, 0x63, 0x75, 0x74, 0x65, 0x73, 0x74, 0x2e, 0x74, 0x78, 0x74,
|
|
|
|
0
|
|
|
|
};
|
2000-01-08 00:54:57 +00:00
|
|
|
UChar *asciiResult = 0, *sjisResult = 0;
|
|
|
|
int32_t asciiLength = 0, sjisLength = 0;
|
|
|
|
|
|
|
|
sjis_cnv = ucnv_open("SJIS", &status);
|
|
|
|
if (U_FAILURE(status))
|
|
|
|
{
|
2000-02-05 00:01:54 +00:00
|
|
|
log_err("Failed to create a SJIS converter\n");
|
2000-01-08 00:54:57 +00:00
|
|
|
return;
|
|
|
|
}
|
|
|
|
ascii_cnv = ucnv_open("LATIN-1", &status);
|
|
|
|
if (U_FAILURE(status))
|
|
|
|
{
|
2000-02-05 00:01:54 +00:00
|
|
|
log_err("Failed to create a SJIS converter\n");
|
2000-01-08 00:54:57 +00:00
|
|
|
ucnv_close(sjis_cnv);
|
|
|
|
return;
|
|
|
|
}
|
|
|
|
/* convert target from SJIS to Unicode */
|
|
|
|
sjisLength = ucnv_toUChars(sjis_cnv, sjisResult, 0, target, strlen(target), &status);
|
|
|
|
status = U_ZERO_ERROR;
|
|
|
|
sjisResult = (UChar*)malloc(sizeof(UChar)* sjisLength);
|
|
|
|
ucnv_toUChars(sjis_cnv, sjisResult, sjisLength, target, strlen(target), &status);
|
|
|
|
if (U_FAILURE(status))
|
|
|
|
{
|
|
|
|
log_err("Failed to convert the SJIS string.\n");
|
|
|
|
ucnv_close(sjis_cnv);
|
|
|
|
ucnv_close(ascii_cnv);
|
|
|
|
return;
|
|
|
|
}
|
|
|
|
/* convert target from Latin-1 to Unicode */
|
|
|
|
asciiLength = ucnv_toUChars(ascii_cnv, asciiResult, 0, target, strlen(target), &status);
|
|
|
|
status = U_ZERO_ERROR;
|
|
|
|
asciiResult = (UChar*)malloc(sizeof(UChar)* asciiLength);
|
|
|
|
ucnv_toUChars(ascii_cnv, asciiResult, asciiLength, target, strlen(target), &status);
|
|
|
|
if (U_FAILURE(status))
|
|
|
|
{
|
|
|
|
log_err("Failed to convert the Latin-1 string.\n");
|
|
|
|
free(sjisResult);
|
|
|
|
ucnv_close(sjis_cnv);
|
|
|
|
ucnv_close(ascii_cnv);
|
|
|
|
return;
|
|
|
|
}
|
|
|
|
if (!ucnv_isAmbiguous(sjis_cnv))
|
|
|
|
{
|
|
|
|
log_err("SJIS converter should contain ambiguous character mappings.\n");
|
|
|
|
free(sjisResult);
|
|
|
|
free(asciiResult);
|
|
|
|
ucnv_close(sjis_cnv);
|
|
|
|
ucnv_close(ascii_cnv);
|
|
|
|
return;
|
|
|
|
}
|
|
|
|
if (u_strcmp(sjisResult, asciiResult) == 0)
|
|
|
|
{
|
|
|
|
log_err("File separators for SJIS don't need to be fixed.\n");
|
|
|
|
}
|
|
|
|
ucnv_fixFileSeparator(sjis_cnv, sjisResult, sjisLength);
|
|
|
|
if (u_strcmp(sjisResult, asciiResult) != 0)
|
|
|
|
{
|
|
|
|
log_err("Fixing file separator for SJIS failed.\n");
|
|
|
|
}
|
|
|
|
free(sjisResult);
|
|
|
|
free(asciiResult);
|
|
|
|
ucnv_close(sjis_cnv);
|
|
|
|
ucnv_close(ascii_cnv);
|
|
|
|
}
|
|
|
|
|
2000-06-02 00:04:34 +00:00
|
|
|
void
|
2000-06-22 01:18:30 +00:00
|
|
|
TestUTF8() {
|
2000-06-02 00:04:34 +00:00
|
|
|
/* test input */
|
|
|
|
static const uint8_t in[]={
|
2000-06-22 01:18:30 +00:00
|
|
|
0x61,
|
|
|
|
0xc0, 0x80,
|
|
|
|
0xe0, 0x80, 0x80,
|
|
|
|
0xf0, 0x80, 0x80, 0x80,
|
2000-07-19 20:14:27 +00:00
|
|
|
0xf4, 0x84, 0x8c, 0xa1,
|
|
|
|
0xf0, 0x90, 0x90, 0x81,
|
2000-06-02 00:04:34 +00:00
|
|
|
};
|
|
|
|
|
|
|
|
/* expected test results */
|
|
|
|
static const uint32_t results[]={
|
|
|
|
/* number of bytes read, code point */
|
|
|
|
1, 0x61,
|
2000-06-22 01:18:30 +00:00
|
|
|
2, 0,
|
|
|
|
3, 0,
|
|
|
|
4, 0,
|
2000-07-19 20:14:27 +00:00
|
|
|
4, 0x104321,
|
|
|
|
4, 0x10401,
|
2000-06-22 01:18:30 +00:00
|
|
|
};
|
|
|
|
|
|
|
|
const char *source=(const char *)in,*limit=(const char *)in+sizeof(in);
|
|
|
|
UErrorCode errorCode=U_ZERO_ERROR;
|
|
|
|
UConverter *cnv=ucnv_open("UTF-8", &errorCode);
|
|
|
|
if(U_FAILURE(errorCode)) {
|
|
|
|
log_err("Unable to open a UTF-8 converter: %s\n", u_errorName(errorCode));
|
|
|
|
}
|
|
|
|
TestNextUChar(cnv, source, limit, results, "UTF-8");
|
2000-06-22 23:46:02 +00:00
|
|
|
/*Test the condition when source > sourceLimit*/
|
|
|
|
TestNextUCharError(cnv, source, source, U_INDEX_OUTOFBOUNDS_ERROR, "sourceLimit < source");
|
2000-06-22 01:18:30 +00:00
|
|
|
ucnv_close(cnv);
|
|
|
|
}
|
|
|
|
void
|
|
|
|
TestUTF16BE() {
|
|
|
|
/* test input */
|
|
|
|
static const uint8_t in[]={
|
|
|
|
0x00, 0x61,
|
|
|
|
0x00, 0xc0,
|
|
|
|
0x00, 0x31,
|
|
|
|
0x00, 0xf4,
|
|
|
|
0xce, 0xfe,
|
2000-07-18 18:04:50 +00:00
|
|
|
0xd8, 0x01, 0xdc, 0x01,
|
2000-06-22 01:18:30 +00:00
|
|
|
|
2000-06-02 00:04:34 +00:00
|
|
|
};
|
|
|
|
|
2000-06-22 01:18:30 +00:00
|
|
|
/* expected test results */
|
|
|
|
static const uint32_t results[]={
|
|
|
|
/* number of bytes read, code point */
|
|
|
|
2, 0x61,
|
|
|
|
2, 0xc0,
|
|
|
|
2, 0x31,
|
|
|
|
2, 0xf4,
|
2000-07-18 18:04:50 +00:00
|
|
|
2, 0xcefe,
|
|
|
|
4, 0x10401,
|
2000-06-22 01:18:30 +00:00
|
|
|
|
|
|
|
};
|
2000-06-02 00:04:34 +00:00
|
|
|
|
2000-06-22 01:18:30 +00:00
|
|
|
const char *source=(const char *)in, *limit=(const char *)in+sizeof(in);
|
2000-06-02 00:04:34 +00:00
|
|
|
UErrorCode errorCode=U_ZERO_ERROR;
|
2000-06-22 01:18:30 +00:00
|
|
|
UConverter *cnv=ucnv_open("utf-16be", &errorCode);
|
|
|
|
if(U_FAILURE(errorCode)) {
|
|
|
|
log_err("Unable to open a UTF16-BE converter: %s\n", u_errorName(errorCode));
|
|
|
|
}
|
|
|
|
TestNextUChar(cnv, source, limit, results, "UTF-16BE");
|
2000-06-22 23:46:02 +00:00
|
|
|
/*Test the condition when source > sourceLimit*/
|
|
|
|
TestNextUCharError(cnv, source, source, U_INDEX_OUTOFBOUNDS_ERROR, "sourceLimit < source");
|
|
|
|
/*Test for the condition where there is an invalid character*/
|
|
|
|
{
|
|
|
|
static const uint8_t source2[]={0x61};
|
|
|
|
TestNextUCharError(cnv, (const char*)source2, (const char*)source2+sizeof(source2), U_TRUNCATED_CHAR_FOUND, "an invalid character");
|
|
|
|
}
|
|
|
|
/*Test for the condition where there is a surrogate pair*/
|
|
|
|
{
|
2000-07-18 18:04:50 +00:00
|
|
|
const uint8_t source2[]={0xd8, 0x01};
|
2000-08-11 03:35:25 +00:00
|
|
|
TestNextUCharError(cnv, (const char*)source2, (const char*)source2+sizeof(source2), U_TRUNCATED_CHAR_FOUND, "an truncated surrogate character");
|
2000-06-22 23:46:02 +00:00
|
|
|
}
|
2000-06-22 01:18:30 +00:00
|
|
|
ucnv_close(cnv);
|
|
|
|
}
|
|
|
|
void
|
|
|
|
TestUTF16LE() {
|
|
|
|
/* test input */
|
|
|
|
static const uint8_t in[]={
|
|
|
|
0x61, 0x00,
|
|
|
|
0x31, 0x00,
|
|
|
|
0x4e, 0x2e,
|
|
|
|
0x4e, 0x00,
|
2000-07-18 18:04:50 +00:00
|
|
|
0x01, 0xd8, 0x01, 0xdc,
|
2000-06-22 01:18:30 +00:00
|
|
|
};
|
2000-06-02 00:04:34 +00:00
|
|
|
|
2000-06-22 01:18:30 +00:00
|
|
|
/* expected test results */
|
|
|
|
static const uint32_t results[]={
|
|
|
|
/* number of bytes read, code point */
|
|
|
|
2, 0x61,
|
|
|
|
2, 0x31,
|
|
|
|
2, 0x2e4e,
|
|
|
|
2, 0x4e,
|
2000-07-18 18:04:50 +00:00
|
|
|
4, 0x10401,
|
2000-06-22 01:18:30 +00:00
|
|
|
};
|
|
|
|
|
|
|
|
const char *source=(const char *)in, *limit=(const char *)in+sizeof(in);
|
|
|
|
UErrorCode errorCode=U_ZERO_ERROR;
|
|
|
|
UConverter *cnv=ucnv_open("utf-16le", &errorCode);
|
2000-06-02 00:04:34 +00:00
|
|
|
if(U_FAILURE(errorCode)) {
|
2000-06-22 01:18:30 +00:00
|
|
|
log_err("Unable to open a UTF16-LE converter: %s\n", u_errorName(errorCode));
|
2000-06-02 00:04:34 +00:00
|
|
|
}
|
2000-06-22 01:18:30 +00:00
|
|
|
TestNextUChar(cnv, source, limit, results, "UTF-16LE");
|
2000-06-22 23:46:02 +00:00
|
|
|
/*Test the condition when source > sourceLimit*/
|
|
|
|
TestNextUCharError(cnv, source, source, U_INDEX_OUTOFBOUNDS_ERROR, "sourceLimit < source");
|
|
|
|
/*Test for the condition where there is an invalid character*/
|
|
|
|
{
|
|
|
|
static const uint8_t source2[]={0x61};
|
|
|
|
TestNextUCharError(cnv, (const char*)source2, (const char*)source2+sizeof(source2), U_TRUNCATED_CHAR_FOUND, "an invalid character");
|
|
|
|
}
|
2000-07-18 18:04:50 +00:00
|
|
|
/*Test for the condition where there is a surrogate character*/
|
|
|
|
{
|
|
|
|
static const uint8_t source2[]={0x01, 0xd8};
|
|
|
|
TestNextUCharError(cnv, (const char*)source2, (const char*)source2+sizeof(source2), U_TRUNCATED_CHAR_FOUND, "an truncated surrogate character");
|
|
|
|
}
|
2000-06-22 23:46:02 +00:00
|
|
|
|
2000-06-22 01:18:30 +00:00
|
|
|
ucnv_close(cnv);
|
|
|
|
}
|
|
|
|
void
|
|
|
|
TestLATIN1() {
|
|
|
|
/* test input */
|
|
|
|
static const uint8_t in[]={
|
|
|
|
0x61,
|
|
|
|
0x31,
|
|
|
|
0x32,
|
|
|
|
0xc0,
|
|
|
|
0xf0,
|
|
|
|
0xf4,
|
|
|
|
};
|
2000-06-02 00:04:34 +00:00
|
|
|
|
2000-06-22 01:18:30 +00:00
|
|
|
/* expected test results */
|
|
|
|
static const uint32_t results[]={
|
|
|
|
/* number of bytes read, code point */
|
|
|
|
1, 0x61,
|
|
|
|
1, 0x31,
|
|
|
|
1, 0x32,
|
2000-06-26 22:16:32 +00:00
|
|
|
1, 0xc0,
|
|
|
|
1, 0xf0,
|
|
|
|
1, 0xf4,
|
2000-06-22 01:18:30 +00:00
|
|
|
};
|
|
|
|
|
|
|
|
const char *source=(const char *)in;
|
|
|
|
const char *limit=(const char *)in+sizeof(in);
|
|
|
|
|
|
|
|
UErrorCode errorCode=U_ZERO_ERROR;
|
|
|
|
UConverter *cnv=ucnv_open("LATIN_1", &errorCode);
|
|
|
|
if(U_FAILURE(errorCode)) {
|
|
|
|
log_err("Unable to open a LATIN_1 converter: %s\n", u_errorName(errorCode));
|
2000-06-02 00:04:34 +00:00
|
|
|
}
|
2000-06-22 01:18:30 +00:00
|
|
|
TestNextUChar(cnv, source, limit, results, "LATIN_1");
|
2000-06-22 23:46:02 +00:00
|
|
|
/*Test the condition when source > sourceLimit*/
|
|
|
|
TestNextUCharError(cnv, source, source, U_INDEX_OUTOFBOUNDS_ERROR, "sourceLimit < source");
|
2000-06-22 01:18:30 +00:00
|
|
|
ucnv_close(cnv);
|
|
|
|
}
|
|
|
|
|
|
|
|
void
|
|
|
|
TestSBCS() {
|
|
|
|
/* test input */
|
|
|
|
static const uint8_t in[]={ 0x61, 0xc0, 0x80, 0xe0, 0xf0, 0xf4};
|
|
|
|
/* expected test results */
|
|
|
|
static const uint32_t results[]={
|
|
|
|
/* number of bytes read, code point */
|
|
|
|
1, 0x61,
|
|
|
|
1, 0xbf,
|
|
|
|
1, 0xc4,
|
|
|
|
1, 0x2021,
|
|
|
|
1, 0xf8fe,
|
|
|
|
1, 0x00d9
|
|
|
|
};
|
2000-06-02 00:04:34 +00:00
|
|
|
|
2000-06-22 01:18:30 +00:00
|
|
|
const char *source=(const char *)in, *limit=(const char *)in+sizeof(in);
|
|
|
|
UErrorCode errorCode=U_ZERO_ERROR;
|
|
|
|
UConverter *cnv=ucnv_open("ibm-1281", &errorCode);
|
|
|
|
if(U_FAILURE(errorCode)) {
|
|
|
|
log_err("Unable to open a SBCS(ibm-1281) converter: %s\n", u_errorName(errorCode));
|
|
|
|
}
|
|
|
|
TestNextUChar(cnv, source, limit, results, "SBCS(ibm-1281)");
|
2000-06-22 23:46:02 +00:00
|
|
|
/*Test the condition when source > sourceLimit*/
|
|
|
|
TestNextUCharError(cnv, source, source, U_INDEX_OUTOFBOUNDS_ERROR, "sourceLimit < source");
|
|
|
|
/*Test for Illegal character*//*
|
|
|
|
{
|
|
|
|
static const uint8_t input1[]={ 0xA1 };
|
|
|
|
const char* illegalsource=(const char*)input1;
|
|
|
|
TestNextUCharError(cnv, illegalsource, illegalsource+sizeof(illegalsource), U_INVALID_CHAR_FOUND, "source has a illegal characte");
|
|
|
|
}
|
|
|
|
*/
|
2000-07-06 23:01:50 +00:00
|
|
|
ucnv_close(cnv);
|
2000-06-02 00:04:34 +00:00
|
|
|
}
|
2000-06-22 23:46:02 +00:00
|
|
|
|
2000-06-22 01:18:30 +00:00
|
|
|
void
|
|
|
|
TestDBCS() {
|
|
|
|
/* test input */
|
|
|
|
static const uint8_t in[]={
|
|
|
|
0x44, 0x6a,
|
|
|
|
0xc4, 0x9c,
|
|
|
|
0x7a, 0x74,
|
|
|
|
0x46, 0xab,
|
|
|
|
0x42, 0x5b,
|
|
|
|
|
|
|
|
};
|
2000-06-02 00:04:34 +00:00
|
|
|
|
2000-06-22 01:18:30 +00:00
|
|
|
/* expected test results */
|
|
|
|
static const uint32_t results[]={
|
|
|
|
/* number of bytes read, code point */
|
|
|
|
2, 0x00a7,
|
|
|
|
2, 0xe1d2,
|
|
|
|
2, 0x6962,
|
|
|
|
2, 0xf842,
|
|
|
|
2, 0xffe5,
|
|
|
|
};
|
|
|
|
|
|
|
|
const char *source=(const char *)in, *limit=(const char *)in+sizeof(in);
|
|
|
|
UErrorCode errorCode=U_ZERO_ERROR;
|
|
|
|
|
|
|
|
UConverter *cnv=ucnv_open("ibm-9027", &errorCode);
|
|
|
|
if(U_FAILURE(errorCode)) {
|
|
|
|
log_err("Unable to open a DBCS(ibm-9027) converter: %s\n", u_errorName(errorCode));
|
|
|
|
}
|
|
|
|
TestNextUChar(cnv, source, limit, results, "DBCS(ibm-9027)");
|
2000-06-22 23:46:02 +00:00
|
|
|
/*Test the condition when source > sourceLimit*/
|
|
|
|
TestNextUCharError(cnv, source, source, U_INDEX_OUTOFBOUNDS_ERROR, "sourceLimit < source");
|
|
|
|
/*Test for the condition where we have a truncated char*/
|
|
|
|
{
|
|
|
|
static const uint8_t source1[]={0xc4};
|
|
|
|
TestNextUCharError(cnv, (const char*)source1, (const char*)source1+sizeof(source1), U_TRUNCATED_CHAR_FOUND, "a character is truncated");
|
|
|
|
}
|
|
|
|
/*Test for the condition where there is an invalid character*/
|
|
|
|
{
|
|
|
|
static const uint8_t source2[]={0x1a, 0x1b};
|
|
|
|
TestNextUCharError(cnv, (const char*)source2, (const char*)source2+sizeof(source2), U_ZERO_ERROR, "an invalid character");
|
|
|
|
}
|
2000-06-22 01:18:30 +00:00
|
|
|
ucnv_close(cnv);
|
|
|
|
}
|
2000-01-19 19:00:53 +00:00
|
|
|
void
|
2000-06-22 01:18:30 +00:00
|
|
|
TestMBCS() {
|
|
|
|
/* test input */
|
|
|
|
static const uint8_t in[]={
|
|
|
|
0x01,
|
|
|
|
0xa6, 0xa3,
|
|
|
|
0x00,
|
|
|
|
0xa6, 0xa1,
|
|
|
|
0x08,
|
|
|
|
0xc2, 0x76,
|
|
|
|
0xc2, 0x78,
|
2000-07-19 20:14:27 +00:00
|
|
|
|
2000-06-22 01:18:30 +00:00
|
|
|
};
|
|
|
|
|
|
|
|
/* expected test results */
|
|
|
|
static const uint32_t results[]={
|
|
|
|
/* number of bytes read, code point */
|
|
|
|
1, 0x0001,
|
|
|
|
2, 0x250c,
|
|
|
|
1, 0x0000,
|
|
|
|
2, 0x2500,
|
|
|
|
1, 0x0008,
|
|
|
|
2, 0xd60c,
|
2000-07-19 20:14:27 +00:00
|
|
|
2, 0xd60e,
|
2000-06-22 01:18:30 +00:00
|
|
|
};
|
|
|
|
|
|
|
|
const char *source=(const char *)in, *limit=(const char *)in+sizeof(in);
|
|
|
|
UErrorCode errorCode=U_ZERO_ERROR;
|
|
|
|
|
|
|
|
UConverter *cnv=ucnv_open("ibm-1363", &errorCode);
|
|
|
|
if(U_FAILURE(errorCode)) {
|
|
|
|
log_err("Unable to open a MBCS(ibm-1363) converter: %s\n", u_errorName(errorCode));
|
|
|
|
}
|
|
|
|
TestNextUChar(cnv, source, limit, results, "MBCS(ibm-1363)");
|
2000-06-22 23:46:02 +00:00
|
|
|
/*Test the condition when source > sourceLimit*/
|
|
|
|
TestNextUCharError(cnv, source, source, U_INDEX_OUTOFBOUNDS_ERROR, "sourceLimit < source");
|
|
|
|
/*Test for the condition where we have a truncated char*/
|
|
|
|
{
|
|
|
|
static const uint8_t source1[]={0xc4};
|
|
|
|
TestNextUCharError(cnv, (const char*)source1, (const char*)source1+sizeof(source1), U_TRUNCATED_CHAR_FOUND, "a character is truncated");
|
|
|
|
}
|
|
|
|
/*Test for the condition where there is an invalid character*/
|
|
|
|
{
|
|
|
|
static const uint8_t source2[]={0xa1, 0x01};
|
|
|
|
TestNextUCharError(cnv, (const char*)source2, (const char*)source2+sizeof(source2), U_ZERO_ERROR, "an invalid character");
|
|
|
|
}
|
2000-06-22 01:18:30 +00:00
|
|
|
ucnv_close(cnv);
|
|
|
|
}
|
|
|
|
void
|
|
|
|
TestISO_2022() {
|
2000-01-19 19:00:53 +00:00
|
|
|
/* test input */
|
|
|
|
static const uint8_t in[]={
|
2000-06-22 01:18:30 +00:00
|
|
|
0x1b, 0x25, 0x42, 0x31,
|
|
|
|
0x32,
|
2000-01-19 19:00:53 +00:00
|
|
|
0x61,
|
|
|
|
0xc0, 0x80,
|
|
|
|
0xe0, 0x80, 0x80,
|
2000-06-22 01:18:30 +00:00
|
|
|
0xf0, 0x80, 0x80, 0x80
|
|
|
|
|
2000-01-19 19:00:53 +00:00
|
|
|
};
|
|
|
|
|
|
|
|
/* expected test results */
|
|
|
|
static const uint32_t results[]={
|
|
|
|
/* number of bytes read, code point */
|
2000-06-22 01:18:30 +00:00
|
|
|
4, 0x0031,
|
|
|
|
1, 0x0032,
|
2000-01-19 19:00:53 +00:00
|
|
|
1, 0x61,
|
|
|
|
2, 0,
|
|
|
|
3, 0,
|
2000-06-22 01:18:30 +00:00
|
|
|
4, 0,
|
|
|
|
|
2000-01-19 19:00:53 +00:00
|
|
|
};
|
|
|
|
|
2000-06-22 01:18:30 +00:00
|
|
|
const char *source=(const char *)in, *limit=(const char *)in+sizeof(in);
|
2000-01-19 19:00:53 +00:00
|
|
|
UErrorCode errorCode=U_ZERO_ERROR;
|
2000-07-22 00:08:14 +00:00
|
|
|
UConverter *cnv;
|
|
|
|
|
|
|
|
if(/* broken for icu 1.6, do not test */uprv_strcmp("1.6", U_ICU_VERSION) == 0) {
|
|
|
|
return;
|
|
|
|
}
|
|
|
|
|
|
|
|
cnv=ucnv_open("iso-2022", &errorCode);
|
2000-01-19 19:00:53 +00:00
|
|
|
if(U_FAILURE(errorCode)) {
|
2000-06-22 01:18:30 +00:00
|
|
|
log_err("Unable to open a iso-2022 converter: %s\n", u_errorName(errorCode));
|
2000-07-21 23:58:01 +00:00
|
|
|
return;
|
2000-01-19 19:00:53 +00:00
|
|
|
}
|
2000-06-22 01:18:30 +00:00
|
|
|
TestNextUChar(cnv, source, limit, results, "iso-2022");
|
2000-06-22 23:46:02 +00:00
|
|
|
|
|
|
|
/*Test the condition when source > sourceLimit*/
|
|
|
|
TestNextUCharError(cnv, source, source-1, U_ILLEGAL_ARGUMENT_ERROR, "sourceLimit < source");
|
|
|
|
TestNextUCharError(cnv, source, source, U_INDEX_OUTOFBOUNDS_ERROR, "sourceLimit < source");
|
|
|
|
/*Test for the condition where we have a truncated char*/
|
|
|
|
{
|
|
|
|
static const uint8_t source1[]={0xc4};
|
|
|
|
TestNextUCharError(cnv, (const char*)source1, (const char*)source1+sizeof(source1), U_TRUNCATED_CHAR_FOUND, "a character is truncated");
|
|
|
|
}
|
|
|
|
/*Test for the condition where there is an invalid character*/
|
|
|
|
{
|
|
|
|
static const uint8_t source2[]={0xa1, 0x01};
|
|
|
|
TestNextUCharError(cnv, (const char*)source2, (const char*)source2+sizeof(source2), U_ZERO_ERROR, "an invalid character");
|
|
|
|
}
|
2000-06-22 01:18:30 +00:00
|
|
|
ucnv_close(cnv);
|
|
|
|
}
|
|
|
|
void
|
|
|
|
TestEBCDIC_STATEFUL() {
|
|
|
|
/* test input */
|
|
|
|
static const uint8_t in[]={
|
|
|
|
0x61,
|
|
|
|
0x1a,
|
|
|
|
0x0f, 0x4b,
|
|
|
|
0x42,
|
|
|
|
0x40,
|
|
|
|
0x36,
|
|
|
|
};
|
2000-01-19 19:00:53 +00:00
|
|
|
|
2000-06-22 01:18:30 +00:00
|
|
|
/* expected test results */
|
|
|
|
static const uint32_t results[]={
|
|
|
|
/* number of bytes read, code point */
|
|
|
|
1, 0x002f,
|
|
|
|
1, 0x0092,
|
|
|
|
2, 0x002e,
|
|
|
|
1, 0xff62,
|
|
|
|
1, 0x0020,
|
|
|
|
1, 0x0096,
|
|
|
|
|
|
|
|
};
|
2000-01-19 19:00:53 +00:00
|
|
|
|
2000-06-22 01:18:30 +00:00
|
|
|
const char *source=(const char *)in, *limit=(const char *)in+sizeof(in);
|
|
|
|
UErrorCode errorCode=U_ZERO_ERROR;
|
|
|
|
UConverter *cnv=ucnv_open("ibm-930", &errorCode);
|
|
|
|
if(U_FAILURE(errorCode)) {
|
|
|
|
log_err("Unable to open a EBCDIC_STATEFUL(ibm-930) converter: %s\n", u_errorName(errorCode));
|
|
|
|
}
|
|
|
|
TestNextUChar(cnv, source, limit, results, "EBCDIC_STATEFUL(ibm-930)");
|
2000-06-22 23:46:02 +00:00
|
|
|
/*Test the condition when source > sourceLimit*/
|
|
|
|
TestNextUCharError(cnv, source, source, U_INDEX_OUTOFBOUNDS_ERROR, "sourceLimit < source");
|
|
|
|
/*Test for the condition where source > sourcelimit after consuming the shift chracter */
|
|
|
|
{
|
|
|
|
static const uint8_t source1[]={0x0f};
|
|
|
|
TestNextUCharError(cnv, (const char*)source1, (const char*)source1+sizeof(source1), U_INDEX_OUTOFBOUNDS_ERROR, "a character is truncated");
|
|
|
|
}
|
|
|
|
/*Test for the condition where there is an invalid character*/
|
|
|
|
{
|
|
|
|
static const uint8_t source2[]={0x0f, 0xa1, 0x01};
|
|
|
|
TestNextUCharError(cnv, (const char*)source2, (const char*)source2+sizeof(source2), U_ZERO_ERROR, "an invalid character");
|
|
|
|
}
|
2000-01-19 19:00:53 +00:00
|
|
|
ucnv_close(cnv);
|
|
|
|
}
|
2000-03-31 16:53:09 +00:00
|
|
|
void
|
|
|
|
TestLMBCS() {
|
2000-06-28 17:01:52 +00:00
|
|
|
/* LMBCS-1 string */
|
2000-05-22 21:24:26 +00:00
|
|
|
static const uint8_t pszLMBCS[]={
|
2000-03-31 16:53:09 +00:00
|
|
|
0x61,
|
|
|
|
0x01, 0x29,
|
|
|
|
0x81,
|
|
|
|
0xA0,
|
|
|
|
0x0F, 0x27,
|
|
|
|
0x0F, 0x91,
|
|
|
|
0x14, 0x0a, 0x74,
|
|
|
|
0x14, 0xF6, 0x02,
|
2000-05-22 21:24:26 +00:00
|
|
|
0x14, 0xd8, 0x4d, 0x14, 0xdc, 0x56, /* UTF-16 surrogate pair */
|
2000-04-13 17:27:35 +00:00
|
|
|
0x10, 0x88, 0xA0,
|
2000-03-31 16:53:09 +00:00
|
|
|
};
|
|
|
|
|
2000-06-28 17:01:52 +00:00
|
|
|
/* Unicode UChar32 equivalents */
|
|
|
|
static const UChar32 pszUnicode32[]={
|
|
|
|
/* code point */
|
|
|
|
0x00000061,
|
|
|
|
0x00002013,
|
|
|
|
0x000000FC,
|
|
|
|
0x000000E1,
|
|
|
|
0x00000007,
|
|
|
|
0x00000091,
|
|
|
|
0x00000a74,
|
|
|
|
0x00000200,
|
|
|
|
0x00023456, /* code point for surrogate pair */
|
|
|
|
0x00005516
|
|
|
|
};
|
|
|
|
|
|
|
|
/* Unicode UChar equivalents */
|
|
|
|
static const UChar pszUnicode[]={
|
2000-05-22 21:24:26 +00:00
|
|
|
/* code point */
|
|
|
|
0x0061,
|
|
|
|
0x2013,
|
|
|
|
0x00FC,
|
|
|
|
0x00E1,
|
|
|
|
0x0007,
|
|
|
|
0x0091,
|
|
|
|
0x0a74,
|
|
|
|
0x0200,
|
2000-06-28 17:01:52 +00:00
|
|
|
0xD84D, /* low surrogate */
|
|
|
|
0xDC56, /* high surrogate */
|
2000-05-22 21:24:26 +00:00
|
|
|
0x5516
|
|
|
|
};
|
|
|
|
|
|
|
|
/* expected test results */
|
2000-06-28 17:01:52 +00:00
|
|
|
static const int offsets32[]={
|
|
|
|
/* number of bytes read, code point */
|
|
|
|
0,
|
|
|
|
1,
|
|
|
|
3,
|
|
|
|
4,
|
|
|
|
5,
|
|
|
|
7,
|
|
|
|
9,
|
|
|
|
12,
|
|
|
|
15,
|
|
|
|
21,
|
|
|
|
24
|
|
|
|
};
|
|
|
|
|
|
|
|
/* expected test results */
|
|
|
|
static const int offsets[]={
|
2000-03-31 16:53:09 +00:00
|
|
|
/* number of bytes read, code point */
|
2000-05-22 21:24:26 +00:00
|
|
|
0,
|
|
|
|
1,
|
|
|
|
3,
|
|
|
|
4,
|
|
|
|
5,
|
|
|
|
7,
|
|
|
|
9,
|
|
|
|
12,
|
|
|
|
15,
|
2000-06-28 17:01:52 +00:00
|
|
|
18,
|
2000-05-22 21:24:26 +00:00
|
|
|
21,
|
2000-06-28 17:01:52 +00:00
|
|
|
24
|
2000-03-31 16:53:09 +00:00
|
|
|
};
|
|
|
|
|
2000-05-22 21:24:26 +00:00
|
|
|
|
2000-06-28 17:01:52 +00:00
|
|
|
UConverter *cnv;
|
2000-03-31 16:53:09 +00:00
|
|
|
|
2000-06-28 17:01:52 +00:00
|
|
|
#define NAME_LMBCS_1 "LMBCS-1"
|
|
|
|
#define NAME_LMBCS_2 "LMBCS-2"
|
2000-03-31 16:53:09 +00:00
|
|
|
|
2000-06-28 17:01:52 +00:00
|
|
|
|
|
|
|
/* Some basic open/close/property tests on some LMBCS converters */
|
|
|
|
{
|
|
|
|
|
|
|
|
char expected_subchars[] = {0x3F}; /* ANSI Question Mark */
|
|
|
|
char new_subchars [] = {0x7F}; /* subst char used by SmartSuite..*/
|
|
|
|
char get_subchars [1];
|
|
|
|
const char * get_name;
|
|
|
|
UConverter *cnv1;
|
|
|
|
UConverter *cnv2;
|
|
|
|
|
|
|
|
int8_t len = sizeof(get_subchars);
|
|
|
|
|
|
|
|
UErrorCode errorCode=U_ZERO_ERROR;
|
|
|
|
|
|
|
|
/* Open */
|
|
|
|
cnv1=ucnv_open(NAME_LMBCS_1, &errorCode);
|
|
|
|
if(U_FAILURE(errorCode)) {
|
|
|
|
log_err("Unable to open a LMBCS-1 converter: %s\n", u_errorName(errorCode));
|
|
|
|
}
|
|
|
|
cnv2=ucnv_open(NAME_LMBCS_2, &errorCode);
|
|
|
|
if(U_FAILURE(errorCode)) {
|
|
|
|
log_err("Unable to open a LMBCS-2 converter: %s\n", u_errorName(errorCode));
|
|
|
|
}
|
|
|
|
|
|
|
|
/* Name */
|
|
|
|
get_name = ucnv_getName (cnv1, &errorCode);
|
|
|
|
if (strcmp(NAME_LMBCS_1,get_name)){
|
|
|
|
log_err("Unexpected converter name: %s\n", get_name);
|
|
|
|
}
|
|
|
|
get_name = ucnv_getName (cnv2, &errorCode);
|
|
|
|
if (strcmp(NAME_LMBCS_2,get_name)){
|
|
|
|
log_err("Unexpected converter name: %s\n", get_name);
|
|
|
|
}
|
|
|
|
|
|
|
|
/* substitution chars */
|
|
|
|
ucnv_getSubstChars (cnv1, get_subchars, &len, &errorCode);
|
|
|
|
if(U_FAILURE(errorCode)) {
|
|
|
|
log_err("Failure on get subst chars: %s\n", u_errorName(errorCode));
|
|
|
|
}
|
|
|
|
if (len!=1){
|
|
|
|
log_err("Unexpected length of sub chars\n");
|
|
|
|
}
|
|
|
|
if (get_subchars[0] != expected_subchars[0]){
|
|
|
|
log_err("Unexpected value of sub chars\n");
|
|
|
|
}
|
|
|
|
ucnv_setSubstChars (cnv2,new_subchars, len, &errorCode);
|
|
|
|
if(U_FAILURE(errorCode)) {
|
|
|
|
log_err("Failure on set subst chars: %s\n", u_errorName(errorCode));
|
|
|
|
}
|
|
|
|
ucnv_getSubstChars (cnv2, get_subchars, &len, &errorCode);
|
|
|
|
if(U_FAILURE(errorCode)) {
|
|
|
|
log_err("Failure on get subst chars: %s\n", u_errorName(errorCode));
|
|
|
|
}
|
|
|
|
if (len!=1){
|
|
|
|
log_err("Unexpected length of sub chars\n");
|
|
|
|
}
|
|
|
|
if (get_subchars[0] != new_subchars[0]){
|
|
|
|
log_err("Unexpected value of sub chars\n");
|
|
|
|
}
|
2000-07-06 23:01:50 +00:00
|
|
|
ucnv_close(cnv1);
|
|
|
|
ucnv_close(cnv2);
|
|
|
|
|
2000-03-31 16:53:09 +00:00
|
|
|
}
|
2000-06-28 17:01:52 +00:00
|
|
|
|
|
|
|
/* LMBCS to Unicode - offsets */
|
2000-03-31 16:53:09 +00:00
|
|
|
{
|
2000-06-28 17:01:52 +00:00
|
|
|
UErrorCode errorCode=U_ZERO_ERROR;
|
|
|
|
|
2000-08-11 03:35:25 +00:00
|
|
|
const uint8_t * pSource = pszLMBCS;
|
|
|
|
const uint8_t * sourceLimit = pszLMBCS + sizeof(pszLMBCS);
|
2000-06-28 17:01:52 +00:00
|
|
|
|
|
|
|
UChar Out [sizeof(pszUnicode)];
|
|
|
|
UChar * pOut = Out;
|
|
|
|
UChar * OutLimit = Out + sizeof(Out);
|
|
|
|
|
2000-07-28 03:18:30 +00:00
|
|
|
int32_t off [sizeof(offsets)];
|
2000-06-28 17:01:52 +00:00
|
|
|
|
|
|
|
/* last 'offset' in expected results is just the final size.
|
|
|
|
(Makes other tests easier). Compensate here: */
|
|
|
|
|
|
|
|
off[(sizeof(offsets)/sizeof(offsets[0]))-1] = sizeof(pszLMBCS);
|
|
|
|
|
2000-03-31 16:53:09 +00:00
|
|
|
|
2000-05-22 21:24:26 +00:00
|
|
|
|
2000-06-28 17:01:52 +00:00
|
|
|
cnv=ucnv_open("lmbcs", &errorCode); /* use generic name for LMBCS-1 */
|
|
|
|
if(U_FAILURE(errorCode)) {
|
|
|
|
log_err("Unable to open a LMBCS converter: %s\n", u_errorName(errorCode));
|
2000-03-31 16:53:09 +00:00
|
|
|
}
|
|
|
|
|
2000-08-11 03:35:25 +00:00
|
|
|
|
2000-06-28 17:01:52 +00:00
|
|
|
|
|
|
|
ucnv_toUnicode (cnv,
|
2000-08-11 03:35:25 +00:00
|
|
|
&pOut,
|
|
|
|
OutLimit,
|
|
|
|
(const char **)&pSource,
|
|
|
|
(const char *)sourceLimit,
|
|
|
|
off,
|
|
|
|
TRUE,
|
|
|
|
&errorCode);
|
|
|
|
|
2000-06-28 17:01:52 +00:00
|
|
|
|
|
|
|
if (memcmp(off,offsets,sizeof(offsets)))
|
|
|
|
{
|
|
|
|
log_err("LMBCS->Uni: Calculated offsets do not match expected results\n");
|
|
|
|
}
|
|
|
|
if (memcmp(Out,pszUnicode,sizeof(pszUnicode)))
|
|
|
|
{
|
|
|
|
log_err("LMBCS->Uni: Calculated codepoints do not match expected results\n");
|
|
|
|
}
|
|
|
|
ucnv_close(cnv);
|
2000-03-31 16:53:09 +00:00
|
|
|
}
|
2000-06-28 17:01:52 +00:00
|
|
|
{
|
|
|
|
/* LMBCS to Unicode - getNextUChar */
|
|
|
|
const char * sourceStart;
|
|
|
|
const char *source=(const char *)pszLMBCS;
|
|
|
|
const char *limit=(const char *)pszLMBCS+sizeof(pszLMBCS);
|
2000-07-28 04:09:39 +00:00
|
|
|
const UChar32 *results= pszUnicode32;
|
2000-06-28 17:01:52 +00:00
|
|
|
const int *off = offsets32;
|
2000-05-22 21:24:26 +00:00
|
|
|
|
2000-06-28 17:01:52 +00:00
|
|
|
UErrorCode errorCode=U_ZERO_ERROR;
|
|
|
|
uint32_t uniChar;
|
|
|
|
|
|
|
|
cnv=ucnv_open("LMBCS-1", &errorCode);
|
|
|
|
if(U_FAILURE(errorCode)) {
|
|
|
|
log_err("Unable to open a LMBCS-1 converter: %s\n", u_errorName(errorCode));
|
|
|
|
}
|
|
|
|
else
|
|
|
|
{
|
|
|
|
|
|
|
|
while(source<limit) {
|
|
|
|
sourceStart=source;
|
|
|
|
uniChar=ucnv_getNextUChar(cnv, &source, source + (off[1] - off[0]), &errorCode);
|
|
|
|
if(U_FAILURE(errorCode)) {
|
|
|
|
log_err("LMBCS-1 ucnv_getNextUChar() failed: %s\n", u_errorName(errorCode));
|
|
|
|
break;
|
|
|
|
} else if(source-sourceStart != off[1] - off[0] || uniChar != *results) {
|
|
|
|
log_err("LMBCS-1 ucnv_getNextUChar() result %lx from %d bytes, should have been %lx from %d bytes.\n",
|
|
|
|
uniChar, (source-sourceStart), *results, *off);
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
results++;
|
|
|
|
off++;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
ucnv_close(cnv);
|
|
|
|
}
|
|
|
|
{ /* test locale & optimization group operations: Unicode to LMBCS */
|
2000-05-22 21:24:26 +00:00
|
|
|
|
2000-06-28 17:01:52 +00:00
|
|
|
UErrorCode errorCode=U_ZERO_ERROR;
|
2000-05-22 21:24:26 +00:00
|
|
|
UConverter *cnv16he = ucnv_open("LMBCS-16,locale=he", &errorCode);
|
2000-06-28 17:01:52 +00:00
|
|
|
UConverter *cnv16jp = ucnv_open("LMBCS-16,locale=ja_JP", &errorCode);
|
|
|
|
UConverter *cnv01us = ucnv_open("LMBCS-1,locale=us_EN", &errorCode);
|
2000-05-22 21:24:26 +00:00
|
|
|
UChar uniString [] = {0x0192}; /* Latin Small letter f with hook */
|
2000-07-28 04:09:39 +00:00
|
|
|
const UChar * pUniOut = uniString;
|
|
|
|
UChar * pUniIn = uniString;
|
2000-08-11 03:35:25 +00:00
|
|
|
uint8_t lmbcsString [4];
|
|
|
|
const uint8_t * pLMBCSOut = lmbcsString;
|
|
|
|
uint8_t * pLMBCSIn = lmbcsString;
|
2000-05-22 21:24:26 +00:00
|
|
|
|
2000-06-28 17:01:52 +00:00
|
|
|
/* 0192 (hook) converts to both group 3 & group 1. input locale should differentiate */
|
2000-05-22 21:24:26 +00:00
|
|
|
ucnv_fromUnicode (cnv16he,
|
2000-08-11 03:35:25 +00:00
|
|
|
(char **)&pLMBCSIn, (const char *)(pLMBCSIn + sizeof(lmbcsString)/sizeof(lmbcsString[0])),
|
2000-07-28 04:09:39 +00:00
|
|
|
&pUniOut, pUniOut + sizeof(uniString)/sizeof(uniString[0]),
|
2000-05-22 21:24:26 +00:00
|
|
|
NULL, 1, &errorCode);
|
|
|
|
|
2000-08-11 03:35:25 +00:00
|
|
|
if (lmbcsString[0] != 0x3 || lmbcsString[1] != 0x83)
|
2000-05-22 21:24:26 +00:00
|
|
|
{
|
2000-06-28 17:01:52 +00:00
|
|
|
log_err("LMBCS-16,locale=he gives unexpected translation\n");
|
2000-05-22 21:24:26 +00:00
|
|
|
}
|
2000-08-11 03:35:25 +00:00
|
|
|
|
|
|
|
pLMBCSIn=lmbcsString;
|
2000-07-28 04:09:39 +00:00
|
|
|
pUniOut = uniString;
|
2000-05-22 21:24:26 +00:00
|
|
|
ucnv_fromUnicode (cnv01us,
|
2000-08-11 03:35:25 +00:00
|
|
|
(char **)&pLMBCSIn, (const char *)(lmbcsString + sizeof(lmbcsString)/sizeof(lmbcsString[0])),
|
2000-07-28 04:09:39 +00:00
|
|
|
&pUniOut, pUniOut + sizeof(uniString)/sizeof(uniString[0]),
|
2000-05-22 21:24:26 +00:00
|
|
|
NULL, 1, &errorCode);
|
2000-06-28 17:01:52 +00:00
|
|
|
|
2000-08-11 03:35:25 +00:00
|
|
|
if (lmbcsString[0] != 0x9F)
|
2000-05-22 21:24:26 +00:00
|
|
|
{
|
2000-06-28 17:01:52 +00:00
|
|
|
log_err("LMBCS-1,locale=US gives unexpected translation\n");
|
|
|
|
}
|
|
|
|
|
|
|
|
/* single byte char from mbcs char set */
|
2000-08-11 03:35:25 +00:00
|
|
|
lmbcsString[0] = 0xAE; /* 1/2 width katakana letter small Yo */
|
2000-07-28 04:09:39 +00:00
|
|
|
pLMBCSOut = lmbcsString;
|
|
|
|
pUniIn = uniString;
|
2000-06-28 17:01:52 +00:00
|
|
|
ucnv_toUnicode (cnv16jp,
|
2000-07-28 04:09:39 +00:00
|
|
|
&pUniIn, pUniIn + 1,
|
2000-08-11 03:35:25 +00:00
|
|
|
(char **)&pLMBCSOut, (const char *)(pLMBCSOut + 1),
|
2000-06-28 17:01:52 +00:00
|
|
|
NULL, 1, &errorCode);
|
2000-07-28 04:09:39 +00:00
|
|
|
if (U_FAILURE(errorCode) || pLMBCSOut != lmbcsString+1 || pUniIn != uniString+1 || uniString[0] != 0xFF6E)
|
2000-06-28 17:01:52 +00:00
|
|
|
{
|
|
|
|
log_err("Unexpected results from LMBCS-16 single byte char\n");
|
|
|
|
}
|
|
|
|
/* convert to group 1: should be 3 bytes */
|
2000-07-28 04:09:39 +00:00
|
|
|
pLMBCSIn = lmbcsString;
|
|
|
|
pUniOut = uniString;
|
2000-06-28 17:01:52 +00:00
|
|
|
ucnv_fromUnicode (cnv01us,
|
2000-08-11 03:35:25 +00:00
|
|
|
(char **)&pLMBCSIn, (const char *)(pLMBCSIn + 3),
|
2000-07-28 04:09:39 +00:00
|
|
|
&pUniOut, pUniOut + 1,
|
2000-06-28 17:01:52 +00:00
|
|
|
NULL, 1, &errorCode);
|
2000-07-28 04:09:39 +00:00
|
|
|
if (U_FAILURE(errorCode) || pLMBCSIn != lmbcsString+3 || pUniOut != uniString+1
|
2000-08-11 03:35:25 +00:00
|
|
|
|| lmbcsString[0] != 0x10 || lmbcsString[1] != 0x10 || lmbcsString[2] != 0xAE)
|
2000-06-28 17:01:52 +00:00
|
|
|
{
|
|
|
|
log_err("Unexpected results to LMBCS-1 single byte mbcs char\n");
|
|
|
|
}
|
2000-07-28 04:09:39 +00:00
|
|
|
pLMBCSOut = lmbcsString;
|
|
|
|
pUniIn = uniString;
|
2000-06-28 17:01:52 +00:00
|
|
|
ucnv_toUnicode (cnv01us,
|
2000-07-28 04:09:39 +00:00
|
|
|
&pUniIn, pUniIn + 1,
|
2000-08-11 03:35:25 +00:00
|
|
|
(char **)&pLMBCSOut, (const char *)(pLMBCSOut + 3),
|
2000-06-28 17:01:52 +00:00
|
|
|
NULL, 1, &errorCode);
|
2000-07-28 04:09:39 +00:00
|
|
|
if (U_FAILURE(errorCode) || pLMBCSOut != lmbcsString+3 || pUniIn != uniString+1 || uniString[0] != 0xFF6E)
|
2000-06-28 17:01:52 +00:00
|
|
|
{
|
|
|
|
log_err("Unexpected results from LMBCS-1 single byte mbcs char\n");
|
|
|
|
}
|
2000-07-28 04:09:39 +00:00
|
|
|
pLMBCSIn = lmbcsString;
|
|
|
|
pUniOut = uniString;
|
2000-06-28 17:01:52 +00:00
|
|
|
ucnv_fromUnicode (cnv16jp,
|
2000-08-11 03:35:25 +00:00
|
|
|
(char **)&pLMBCSIn, (const char *)(pLMBCSIn + 1),
|
2000-07-28 04:09:39 +00:00
|
|
|
&pUniOut, pUniOut + 1,
|
2000-06-28 17:01:52 +00:00
|
|
|
NULL, 1, &errorCode);
|
2000-08-11 03:35:25 +00:00
|
|
|
if (U_FAILURE(errorCode) || pLMBCSIn != lmbcsString+1 || pUniOut != uniString+1 || lmbcsString[0] != 0xAE)
|
2000-06-28 17:01:52 +00:00
|
|
|
{
|
|
|
|
log_err("Unexpected results to LMBCS-16 single byte mbcs char\n");
|
2000-05-22 21:24:26 +00:00
|
|
|
}
|
2000-06-28 17:01:52 +00:00
|
|
|
ucnv_close(cnv16he);
|
|
|
|
ucnv_close(cnv16jp);
|
|
|
|
ucnv_close(cnv01us);
|
|
|
|
}
|
|
|
|
{
|
|
|
|
/* Small source buffer testing, LMBCS -> Unicode */
|
|
|
|
|
|
|
|
UErrorCode errorCode=U_ZERO_ERROR;
|
|
|
|
|
2000-08-11 03:35:25 +00:00
|
|
|
const uint8_t * pSource = pszLMBCS;
|
|
|
|
const uint8_t * sourceLimit = pszLMBCS + sizeof(pszLMBCS);
|
2000-06-28 17:01:52 +00:00
|
|
|
int codepointCount = 0;
|
|
|
|
|
|
|
|
UChar Out [sizeof(pszUnicode)];
|
|
|
|
UChar * pOut = Out;
|
|
|
|
UChar * OutLimit = Out + sizeof(Out);
|
|
|
|
|
|
|
|
|
|
|
|
cnv = ucnv_open(NAME_LMBCS_1, &errorCode);
|
|
|
|
if(U_FAILURE(errorCode)) {
|
|
|
|
log_err("Unable to open a LMBCS-1 converter: %s\n", u_errorName(errorCode));
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
while ((pSource < sourceLimit) && U_SUCCESS (errorCode))
|
|
|
|
{
|
|
|
|
|
|
|
|
ucnv_toUnicode (cnv,
|
2000-08-11 03:35:25 +00:00
|
|
|
&pOut,
|
|
|
|
OutLimit,
|
|
|
|
(const char **)&pSource,
|
|
|
|
(const char *)(pSource+1), /* claim that this is a 1- byte buffer */
|
|
|
|
NULL,
|
|
|
|
FALSE, /* FALSE means there might be more chars in the next buffer */
|
|
|
|
&errorCode);
|
2000-06-28 17:01:52 +00:00
|
|
|
|
|
|
|
if (U_SUCCESS (errorCode))
|
2000-08-11 03:35:25 +00:00
|
|
|
{
|
|
|
|
if ((pSource - (const uint8_t *)pszLMBCS) == offsets [codepointCount+1])
|
2000-06-28 17:01:52 +00:00
|
|
|
{
|
|
|
|
/* we are on to the next code point: check value */
|
|
|
|
|
|
|
|
if (Out[0] != pszUnicode[codepointCount]){
|
|
|
|
log_err("LMBCS->Uni result %lx should have been %lx \n",
|
|
|
|
Out[0], pszUnicode[codepointCount]);
|
|
|
|
}
|
|
|
|
|
|
|
|
pOut = Out; /* reset for accumulating next code point */
|
|
|
|
codepointCount++;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
else
|
|
|
|
{
|
|
|
|
log_err("Unexpected Error on toUnicode: %s\n", u_errorName(errorCode));
|
|
|
|
}
|
|
|
|
}
|
|
|
|
{
|
|
|
|
/* limits & surrogate error testing */
|
|
|
|
UErrorCode errorCode=U_ZERO_ERROR;
|
|
|
|
|
2000-08-11 03:35:25 +00:00
|
|
|
uint8_t LIn [sizeof(pszLMBCS)];
|
|
|
|
const uint8_t * pLIn = LIn;
|
2000-06-28 17:01:52 +00:00
|
|
|
|
|
|
|
char LOut [sizeof(pszLMBCS)];
|
|
|
|
char * pLOut = LOut;
|
|
|
|
|
|
|
|
UChar UOut [sizeof(pszUnicode)];
|
|
|
|
UChar * pUOut = UOut;
|
|
|
|
|
|
|
|
UChar UIn [sizeof(pszUnicode)];
|
|
|
|
const UChar * pUIn = UIn;
|
|
|
|
|
2000-08-01 03:25:35 +00:00
|
|
|
int32_t off [sizeof(offsets)];
|
2000-06-28 17:01:52 +00:00
|
|
|
UChar32 uniChar;
|
|
|
|
|
|
|
|
/* negative source request should always return U_ILLEGAL_ARGUMENT_ERROR */
|
|
|
|
ucnv_fromUnicode(cnv, &pLOut,pLOut+1,&pUIn,pUIn-1,off,FALSE, &errorCode);
|
|
|
|
if (errorCode != U_ILLEGAL_ARGUMENT_ERROR)
|
|
|
|
{
|
|
|
|
log_err("Unexpected Error on negative source request to ucnv_fromUnicode: %s\n", u_errorName(errorCode));
|
|
|
|
}
|
|
|
|
errorCode=U_ZERO_ERROR;
|
2000-08-11 03:35:25 +00:00
|
|
|
ucnv_toUnicode(cnv, &pUOut,pUOut+1,(const char **)&pLIn,(const char *)(pLIn-1),off,FALSE, &errorCode);
|
2000-06-28 17:01:52 +00:00
|
|
|
if (errorCode != U_ILLEGAL_ARGUMENT_ERROR)
|
|
|
|
{
|
|
|
|
log_err("Unexpected Error on negative source request to ucnv_toUnicode: %s\n", u_errorName(errorCode));
|
|
|
|
}
|
|
|
|
errorCode=U_ZERO_ERROR;
|
|
|
|
|
2000-08-11 03:35:25 +00:00
|
|
|
uniChar = ucnv_getNextUChar(cnv, (const char **)&pLIn, (const char *)(pLIn-1), &errorCode);
|
2000-06-28 17:01:52 +00:00
|
|
|
if (errorCode != U_ILLEGAL_ARGUMENT_ERROR)
|
|
|
|
{
|
|
|
|
log_err("Unexpected Error on negative source request to ucnv_getNextUChar: %s\n", u_errorName(errorCode));
|
|
|
|
}
|
|
|
|
errorCode=U_ZERO_ERROR;
|
|
|
|
|
|
|
|
/* 0 byte source request - no error, no pointer movement */
|
2000-08-11 03:35:25 +00:00
|
|
|
ucnv_toUnicode(cnv, &pUOut,pUOut+1,(const char **)&pLIn,(const char *)pLIn,off,FALSE, &errorCode);
|
2000-06-28 17:01:52 +00:00
|
|
|
ucnv_fromUnicode(cnv, &pLOut,pLOut+1,&pUIn,pUIn,off,FALSE, &errorCode);
|
|
|
|
if(U_FAILURE(errorCode)) {
|
|
|
|
log_err("0 byte source request: unexpected error: %s\n", u_errorName(errorCode));
|
|
|
|
}
|
|
|
|
if ((pUOut != UOut) || (pUIn != UIn) || (pLOut != LOut) || (pLIn != LIn))
|
|
|
|
{
|
|
|
|
log_err("Unexpected pointer move in 0 byte source request \n");
|
|
|
|
}
|
2000-07-13 23:55:33 +00:00
|
|
|
/*0 byte source request - GetNextUChar : error & value == fffe or ffff */
|
2000-08-11 03:35:25 +00:00
|
|
|
uniChar = ucnv_getNextUChar(cnv, (const char **)&pLIn, (const char *)pLIn, &errorCode);
|
2000-06-28 17:01:52 +00:00
|
|
|
if (errorCode != U_ILLEGAL_ARGUMENT_ERROR)
|
|
|
|
{
|
|
|
|
log_err("Unexpected Error on 0-byte source request to ucnv_getnextUChar: %s\n", u_errorName(errorCode));
|
|
|
|
}
|
2000-07-13 23:55:33 +00:00
|
|
|
if (((uint32_t)uniChar - 0xfffe) > 1) /* not 0xfffe<=uniChar<=0xffff */
|
2000-06-28 17:01:52 +00:00
|
|
|
{
|
|
|
|
log_err("Unexpected value on 0-byte source request to ucnv_getnextUChar \n");
|
|
|
|
}
|
|
|
|
errorCode = 0;
|
|
|
|
|
|
|
|
/* running out of target room : U_INDEX_OUTOFBOUNDS_ERROR*/
|
|
|
|
|
|
|
|
pUIn = pszUnicode;
|
|
|
|
ucnv_fromUnicode(cnv, &pLOut,pLOut+offsets[4],&pUIn,pUIn+sizeof(pszUnicode),off,FALSE, &errorCode);
|
2000-07-13 15:35:39 +00:00
|
|
|
if (errorCode != U_INDEX_OUTOFBOUNDS_ERROR || pLOut != LOut + offsets[4] || pUIn != pszUnicode+4 )
|
2000-06-28 17:01:52 +00:00
|
|
|
{
|
|
|
|
log_err("Unexpected results on out of target room to ucnv_fromUnicode\n");
|
|
|
|
}
|
|
|
|
|
|
|
|
errorCode = 0;
|
|
|
|
|
|
|
|
pLIn = pszLMBCS;
|
2000-08-11 03:35:25 +00:00
|
|
|
ucnv_toUnicode(cnv, &pUOut,pUOut+4,(const char **)&pLIn,(const char *)(pLIn+sizeof(pszLMBCS)),off,FALSE, &errorCode);
|
|
|
|
if (errorCode != U_INDEX_OUTOFBOUNDS_ERROR || pUOut != UOut + 4 || pLIn != (const uint8_t *)pszLMBCS+offsets[4])
|
2000-06-28 17:01:52 +00:00
|
|
|
{
|
|
|
|
log_err("Unexpected results on out of target room to ucnv_toUnicode\n");
|
|
|
|
}
|
|
|
|
|
|
|
|
/* unpaired or chopped LMBCS surrogates */
|
|
|
|
|
|
|
|
/* OK high surrogate, Low surrogate is chopped */
|
|
|
|
LIn [0] = 0x14;
|
2000-08-11 03:35:25 +00:00
|
|
|
LIn [1] = 0xD8;
|
2000-06-28 17:01:52 +00:00
|
|
|
LIn [2] = 0x01;
|
|
|
|
LIn [3] = 0x14;
|
2000-08-11 03:35:25 +00:00
|
|
|
LIn [4] = 0xDC;
|
2000-06-28 17:01:52 +00:00
|
|
|
pLIn = LIn;
|
|
|
|
errorCode = 0;
|
|
|
|
pUOut = UOut;
|
|
|
|
|
2000-08-11 03:35:25 +00:00
|
|
|
ucnv_toUnicode(cnv, &pUOut,pUOut+sizeof(UOut),(const char **)&pLIn,(const char *)(pLIn+5),off,TRUE, &errorCode);
|
2000-06-28 17:01:52 +00:00
|
|
|
if (UOut[0] != 0xD801 || errorCode != U_TRUNCATED_CHAR_FOUND || pUOut != UOut + 1 || pLIn != LIn + 3)
|
|
|
|
{
|
|
|
|
log_err("Unexpected results on chopped low surrogate\n");
|
|
|
|
}
|
|
|
|
|
|
|
|
/* chopped at surrogate boundary */
|
|
|
|
LIn [0] = 0x14;
|
2000-08-11 03:35:25 +00:00
|
|
|
LIn [1] = 0xD8;
|
2000-06-28 17:01:52 +00:00
|
|
|
LIn [2] = 0x01;
|
|
|
|
pLIn = LIn;
|
|
|
|
errorCode = 0;
|
|
|
|
pUOut = UOut;
|
|
|
|
|
2000-08-11 03:35:25 +00:00
|
|
|
ucnv_toUnicode(cnv, &pUOut,pUOut+sizeof(UOut),(const char **)&pLIn,(const char *)(pLIn+3),off,TRUE, &errorCode);
|
2000-06-28 17:01:52 +00:00
|
|
|
if (UOut[0] != 0xD801 || U_FAILURE(errorCode) || pUOut != UOut + 1 || pLIn != LIn + 3)
|
|
|
|
{
|
|
|
|
log_err("Unexpected results on chopped at surrogate boundary \n");
|
|
|
|
}
|
|
|
|
|
|
|
|
/* unpaired surrogate plus valid Unichar */
|
|
|
|
LIn [0] = 0x14;
|
2000-08-11 03:35:25 +00:00
|
|
|
LIn [1] = 0xD8;
|
2000-06-28 17:01:52 +00:00
|
|
|
LIn [2] = 0x01;
|
|
|
|
LIn [3] = 0x14;
|
2000-08-11 03:35:25 +00:00
|
|
|
LIn [4] = 0xC9;
|
|
|
|
LIn [5] = 0xD0;
|
2000-06-28 17:01:52 +00:00
|
|
|
pLIn = LIn;
|
|
|
|
errorCode = 0;
|
|
|
|
pUOut = UOut;
|
|
|
|
|
2000-08-11 03:35:25 +00:00
|
|
|
ucnv_toUnicode(cnv, &pUOut,pUOut+sizeof(UOut),(const char **)&pLIn,(const char *)(pLIn+6),off,TRUE, &errorCode);
|
2000-06-28 17:01:52 +00:00
|
|
|
if (UOut[0] != 0xD801 || UOut[1] != 0xC9D0 || U_FAILURE(errorCode) || pUOut != UOut + 2 || pLIn != LIn + 6)
|
|
|
|
{
|
|
|
|
log_err("Unexpected results after unpaired surrogate plus valid Unichar \n");
|
|
|
|
}
|
|
|
|
|
|
|
|
/* unpaired surrogate plus chopped Unichar */
|
|
|
|
LIn [0] = 0x14;
|
2000-08-11 03:35:25 +00:00
|
|
|
LIn [1] = 0xD8;
|
2000-06-28 17:01:52 +00:00
|
|
|
LIn [2] = 0x01;
|
|
|
|
LIn [3] = 0x14;
|
2000-08-11 03:35:25 +00:00
|
|
|
LIn [4] = 0xC9;
|
2000-06-28 17:01:52 +00:00
|
|
|
|
|
|
|
pLIn = LIn;
|
|
|
|
errorCode = 0;
|
|
|
|
pUOut = UOut;
|
|
|
|
|
2000-08-11 03:35:25 +00:00
|
|
|
ucnv_toUnicode(cnv, &pUOut,pUOut+sizeof(UOut),(const char **)&pLIn,(const char *)(pLIn+5),off,TRUE, &errorCode);
|
2000-06-28 17:01:52 +00:00
|
|
|
if (UOut[0] != 0xD801 || errorCode != U_TRUNCATED_CHAR_FOUND || pUOut != UOut + 1 || pLIn != LIn + 3)
|
|
|
|
{
|
|
|
|
log_err("Unexpected results after unpaired surrogate plus chopped Unichar \n");
|
|
|
|
}
|
|
|
|
|
|
|
|
/* unpaired surrogate plus valid non-Unichar */
|
|
|
|
LIn [0] = 0x14;
|
2000-08-11 03:35:25 +00:00
|
|
|
LIn [1] = 0xD8;
|
2000-06-28 17:01:52 +00:00
|
|
|
LIn [2] = 0x01;
|
|
|
|
LIn [3] = 0x0F;
|
|
|
|
LIn [4] = 0x3B;
|
|
|
|
|
|
|
|
pLIn = LIn;
|
|
|
|
errorCode = 0;
|
|
|
|
pUOut = UOut;
|
|
|
|
|
2000-08-11 03:35:25 +00:00
|
|
|
ucnv_toUnicode(cnv, &pUOut,pUOut+sizeof(UOut),(const char **)&pLIn,(const char *)(pLIn+5),off,TRUE, &errorCode);
|
2000-06-28 17:01:52 +00:00
|
|
|
if (UOut[0] != 0xD801 || UOut[1] != 0x1B || U_FAILURE(errorCode) || pUOut != UOut + 2 || pLIn != LIn + 5)
|
|
|
|
{
|
|
|
|
log_err("Unexpected results after unpaired surrogate plus valid non-Unichar\n");
|
|
|
|
}
|
|
|
|
|
|
|
|
/* unpaired surrogate plus chopped non-Unichar */
|
|
|
|
LIn [0] = 0x14;
|
2000-08-11 03:35:25 +00:00
|
|
|
LIn [1] = 0xD8;
|
2000-06-28 17:01:52 +00:00
|
|
|
LIn [2] = 0x01;
|
|
|
|
LIn [3] = 0x0F;
|
|
|
|
|
|
|
|
pLIn = LIn;
|
|
|
|
errorCode = 0;
|
|
|
|
pUOut = UOut;
|
|
|
|
|
2000-08-11 03:35:25 +00:00
|
|
|
ucnv_toUnicode(cnv, &pUOut,pUOut+sizeof(UOut),(const char **)&pLIn,(const char *)(pLIn+4),off,TRUE, &errorCode);
|
2000-06-28 17:01:52 +00:00
|
|
|
|
|
|
|
if (UOut[0] != 0xD801 || errorCode != U_TRUNCATED_CHAR_FOUND || pUOut != UOut + 1 || pLIn != LIn + 3)
|
|
|
|
{
|
|
|
|
log_err("Unexpected results after unpaired surrogate plus chopped non-Unichar\n");
|
|
|
|
}
|
|
|
|
}
|
2000-05-22 21:24:26 +00:00
|
|
|
}
|
2000-06-28 17:01:52 +00:00
|
|
|
ucnv_close(cnv); /* final cleanup */
|
2000-03-31 16:53:09 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
|
2000-02-05 00:01:54 +00:00
|
|
|
void TestJitterbug255()
|
|
|
|
{
|
2000-08-11 03:35:25 +00:00
|
|
|
const uint8_t testBytes[] = { 0x95, 0xcf, 0x8a,
|
|
|
|
0xb7, 0x0d, 0x0a, 0x00 };
|
|
|
|
const uint8_t *testBuffer = testBytes;
|
|
|
|
const uint8_t *testEnd = (const uint8_t *)(testBytes+(strlen(testBytes)+1));
|
2000-02-05 00:01:54 +00:00
|
|
|
UErrorCode status = U_ZERO_ERROR;
|
2000-04-13 17:27:35 +00:00
|
|
|
UChar32 result;
|
2000-02-05 00:01:54 +00:00
|
|
|
UConverter *cnv = 0;
|
|
|
|
|
|
|
|
cnv = ucnv_open("shift-jis", &status);
|
|
|
|
if (U_FAILURE(status) || cnv == 0) {
|
|
|
|
log_err("Failed to open the converter for SJIS.\n");
|
|
|
|
return;
|
|
|
|
}
|
|
|
|
while (testBuffer != testEnd)
|
|
|
|
{
|
2000-08-11 03:35:25 +00:00
|
|
|
result = ucnv_getNextUChar (cnv, (const char **)&testBuffer, (const char *)testEnd , &status);
|
2000-02-05 00:01:54 +00:00
|
|
|
if (U_FAILURE(status))
|
|
|
|
{
|
|
|
|
log_err("Failed to convert the next UChar for SJIS.\n");
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
ucnv_close(cnv);
|
|
|
|
}
|
2000-04-18 21:57:47 +00:00
|
|
|
|
|
|
|
void TestEBCDICUS4XML()
|
|
|
|
{
|
|
|
|
UChar unicodes_x[] = {0x0000, 0x0000, 0x0000, 0x0000};
|
|
|
|
const UChar toUnicodeMaps_x[] = {0x000A, 0x000A, 0x000D, 0x0000};
|
|
|
|
const char fromUnicodeMaps_x[] = {0x25, 0x25, 0x0D, 0x00};
|
|
|
|
const char newLines_x[] = {0x25, 0x15, 0x0D, 0x00};
|
|
|
|
char target_x[] = {0x00, 0x00, 0x00, 0x00};
|
|
|
|
UChar *unicodes = unicodes_x;
|
|
|
|
const UChar *toUnicodeMaps = toUnicodeMaps_x;
|
|
|
|
char *target = target_x;
|
|
|
|
const char* fromUnicodeMaps = fromUnicodeMaps_x, *newLines = newLines_x;
|
|
|
|
UErrorCode status = U_ZERO_ERROR;
|
|
|
|
UConverter *cnv = 0;
|
|
|
|
|
|
|
|
cnv = ucnv_open("ebcdic-xml-us", &status);
|
|
|
|
if (U_FAILURE(status) || cnv == 0) {
|
|
|
|
log_err("Failed to open the converter for EBCDIC-XML-US.\n");
|
|
|
|
return;
|
|
|
|
}
|
|
|
|
ucnv_toUnicode(cnv, &unicodes, unicodes+3, (const char**)&newLines, newLines+3, NULL, TRUE, &status);
|
|
|
|
if (U_FAILURE(status) || memcmp(unicodes_x, toUnicodeMaps, sizeof(UChar)*3) != 0) {
|
|
|
|
log_err("To Unicode conversion failed in EBCDICUS4XML test.\n");
|
|
|
|
}
|
|
|
|
ucnv_fromUnicode(cnv, &target, target+3, (const UChar**)&toUnicodeMaps, toUnicodeMaps+3, NULL, TRUE, &status);
|
|
|
|
if (U_FAILURE(status) || memcmp(target_x, fromUnicodeMaps, sizeof(char)*3) != 0) {
|
|
|
|
log_err("From Unicode conversion failed in EBCDICUS4XML test.\n");
|
|
|
|
}
|
|
|
|
ucnv_close(cnv);
|
|
|
|
}
|
|
|
|
|
2000-06-22 01:18:30 +00:00
|
|
|
|
2000-06-29 02:53:29 +00:00
|
|
|
#endif
|