2000-01-15 02:00:06 +00:00
|
|
|
/********************************************************************
|
|
|
|
* COPYRIGHT:
|
2003-06-03 20:58:22 +00:00
|
|
|
* Copyright (c) 1997-2003, International Business Machines Corporation and
|
2000-01-15 02:00:06 +00:00
|
|
|
* others. All Rights Reserved.
|
|
|
|
********************************************************************/
|
|
|
|
/********************************************************************************
|
1999-08-16 21:50:52 +00:00
|
|
|
*
|
|
|
|
* File CALLCOLL.C
|
|
|
|
*
|
|
|
|
* Modification History:
|
|
|
|
* Name Description
|
1999-10-18 22:48:32 +00:00
|
|
|
* Madhu Katragadda Ported for C API
|
1999-08-16 21:50:52 +00:00
|
|
|
*********************************************************************************
|
|
|
|
*/
|
2000-03-22 23:17:42 +00:00
|
|
|
|
|
|
|
/*
|
|
|
|
* Important: This file is included into intltest/allcoll.cpp so that the
|
|
|
|
* test data is shared. This makes it easier to maintain the test data,
|
|
|
|
* especially since the Unicode data must be portable and quoted character
|
|
|
|
* literals will not work.
|
|
|
|
* If it is included, then there will be a #define INCLUDE_CALLCOLL_C
|
|
|
|
* that must prevent the actual code in here from being part of the
|
|
|
|
* allcoll.cpp compilation.
|
|
|
|
*/
|
|
|
|
|
1999-08-16 21:50:52 +00:00
|
|
|
/**
|
|
|
|
* CollationDummyTest is a third level test class. This tests creation of
|
|
|
|
* a customized collator object. For example, number 1 to be sorted
|
2001-10-29 17:56:00 +00:00
|
|
|
* equlivalent to word 'one'.
|
1999-08-16 21:50:52 +00:00
|
|
|
*/
|
2000-03-22 23:17:42 +00:00
|
|
|
|
2000-08-28 21:43:03 +00:00
|
|
|
#include <string.h>
|
|
|
|
#include <stdlib.h>
|
2002-09-20 17:54:45 +00:00
|
|
|
|
1999-12-28 23:57:50 +00:00
|
|
|
#include "unicode/utypes.h"
|
2002-09-20 17:54:45 +00:00
|
|
|
|
|
|
|
#if !UCONFIG_NO_COLLATION
|
|
|
|
|
1999-12-28 23:57:50 +00:00
|
|
|
#include "unicode/ucol.h"
|
|
|
|
#include "unicode/uloc.h"
|
2003-04-23 05:39:51 +00:00
|
|
|
#include "unicode/ucoleitr.h"
|
|
|
|
#include "unicode/ustring.h"
|
|
|
|
|
1999-08-16 21:50:52 +00:00
|
|
|
#include "cintltst.h"
|
|
|
|
#include "ccolltst.h"
|
|
|
|
#include "callcoll.h"
|
2003-04-23 05:39:51 +00:00
|
|
|
#include "calldata.h"
|
|
|
|
#include "cstring.h"
|
2001-04-07 00:24:06 +00:00
|
|
|
#include "cmemory.h"
|
2001-04-19 19:01:39 +00:00
|
|
|
#include "ucol_imp.h"
|
1999-12-22 22:57:04 +00:00
|
|
|
|
2001-03-22 04:16:49 +00:00
|
|
|
/* perform test with strength PRIMARY */
|
|
|
|
static void TestPrimary(void);
|
|
|
|
|
|
|
|
/* perform test with strength SECONDARY */
|
|
|
|
static void TestSecondary(void);
|
|
|
|
|
|
|
|
/* perform test with strength tertiary */
|
|
|
|
static void TestTertiary(void);
|
|
|
|
|
|
|
|
/*perform tests with strength Identical */
|
|
|
|
static void TestIdentical(void);
|
|
|
|
|
|
|
|
/* perform extra tests */
|
|
|
|
static void TestExtra(void);
|
|
|
|
|
|
|
|
/* Test jitterbug 581 */
|
|
|
|
static void TestJB581(void);
|
|
|
|
|
2001-10-29 17:56:00 +00:00
|
|
|
/* Test jitterbug 1401 */
|
|
|
|
static void TestJB1401(void);
|
|
|
|
|
2001-04-07 00:24:06 +00:00
|
|
|
/* Test [variable top] in the rule syntax */
|
|
|
|
static void TestVariableTop(void);
|
|
|
|
|
|
|
|
/* Test surrogates */
|
|
|
|
static void TestSurrogates(void);
|
|
|
|
|
2001-08-17 22:18:38 +00:00
|
|
|
static void TestInvalidRules(void);
|
|
|
|
|
2003-04-23 05:39:51 +00:00
|
|
|
static void TestJitterbug1098(void);
|
2000-03-22 23:17:42 +00:00
|
|
|
|
1999-08-16 21:50:52 +00:00
|
|
|
const UCollationResult results[] = {
|
|
|
|
UCOL_LESS,
|
2001-03-13 07:30:28 +00:00
|
|
|
UCOL_LESS, /*UCOL_GREATER,*/
|
1999-08-16 21:50:52 +00:00
|
|
|
UCOL_LESS,
|
|
|
|
UCOL_LESS,
|
|
|
|
UCOL_LESS,
|
|
|
|
UCOL_LESS,
|
|
|
|
UCOL_LESS,
|
|
|
|
UCOL_GREATER,
|
|
|
|
UCOL_GREATER,
|
|
|
|
UCOL_LESS, /* 10 */
|
|
|
|
UCOL_GREATER,
|
|
|
|
UCOL_LESS,
|
|
|
|
UCOL_GREATER,
|
|
|
|
UCOL_GREATER,
|
|
|
|
UCOL_LESS,
|
|
|
|
UCOL_LESS,
|
|
|
|
UCOL_LESS,
|
|
|
|
/* test primary > 17 */
|
|
|
|
UCOL_EQUAL,
|
|
|
|
UCOL_EQUAL,
|
|
|
|
UCOL_EQUAL, /* 20 */
|
|
|
|
UCOL_LESS,
|
|
|
|
UCOL_LESS,
|
|
|
|
UCOL_EQUAL,
|
|
|
|
UCOL_EQUAL,
|
|
|
|
UCOL_EQUAL,
|
|
|
|
UCOL_LESS,
|
|
|
|
/* test secondary > 26 */
|
|
|
|
UCOL_EQUAL,
|
|
|
|
UCOL_EQUAL,
|
|
|
|
UCOL_EQUAL,
|
|
|
|
UCOL_EQUAL,
|
|
|
|
UCOL_EQUAL, /* 30 */
|
|
|
|
UCOL_EQUAL,
|
|
|
|
UCOL_LESS,
|
|
|
|
UCOL_EQUAL, /* 34 */
|
|
|
|
UCOL_EQUAL,
|
|
|
|
UCOL_EQUAL,
|
|
|
|
UCOL_LESS /* 37 */
|
|
|
|
};
|
|
|
|
|
2001-11-07 03:23:55 +00:00
|
|
|
|
1999-08-16 21:50:52 +00:00
|
|
|
void addAllCollTest(TestNode** root)
|
|
|
|
{
|
|
|
|
|
|
|
|
|
|
|
|
addTest(root, &TestPrimary, "tscoll/callcoll/TestPrimary");
|
|
|
|
addTest(root, &TestSecondary, "tscoll/callcoll/TestSecondary");
|
|
|
|
addTest(root, &TestTertiary, "tscoll/callcoll/TestTertiary");
|
|
|
|
addTest(root, &TestIdentical, "tscoll/callcoll/TestIdentical");
|
|
|
|
addTest(root, &TestExtra, "tscoll/callcoll/TestExtra");
|
2000-10-13 20:14:51 +00:00
|
|
|
addTest(root, &TestJB581, "tscoll/callcoll/TestJB581");
|
2001-04-07 00:24:06 +00:00
|
|
|
addTest(root, &TestVariableTop, "tscoll/callcoll/TestVariableTop");
|
2001-08-17 22:18:38 +00:00
|
|
|
addTest(root, &TestSurrogates, "tscoll/callcoll/TestSurrogates");
|
|
|
|
addTest(root, &TestInvalidRules, "tscoll/callcoll/TestInvalidRules");
|
2001-10-29 17:56:00 +00:00
|
|
|
addTest(root, &TestJB1401, "tscoll/callcoll/TestJB1401");
|
2001-11-07 03:23:55 +00:00
|
|
|
addTest(root, &TestJitterbug1098, "tscoll/callcoll/TestJitterbug1098");
|
|
|
|
|
2001-10-29 17:56:00 +00:00
|
|
|
}
|
1999-08-16 21:50:52 +00:00
|
|
|
|
2003-02-20 01:12:45 +00:00
|
|
|
static UCollationResult compareUsingPartials(UCollator *coll, const UChar source[], int32_t sLen, const UChar target[], int32_t tLen, int32_t pieceSize, UErrorCode *status) {
|
|
|
|
int32_t partialSKResult = 0;
|
|
|
|
UCharIterator sIter, tIter;
|
|
|
|
uint32_t sState[2], tState[2];
|
|
|
|
int32_t sSize = pieceSize, tSize = pieceSize;
|
|
|
|
int32_t i = 0;
|
2003-03-04 06:31:46 +00:00
|
|
|
uint8_t sBuf[16384], tBuf[16384];
|
|
|
|
if(pieceSize > 16384) {
|
|
|
|
log_err("Partial sortkey size buffer too small. Please consider increasing the buffer!\n");
|
|
|
|
*status = U_BUFFER_OVERFLOW_ERROR;
|
|
|
|
return UCOL_EQUAL;
|
|
|
|
}
|
2003-02-20 01:12:45 +00:00
|
|
|
*status = U_ZERO_ERROR;
|
|
|
|
sState[0] = 0; sState[1] = 0;
|
|
|
|
tState[0] = 0; tState[1] = 0;
|
|
|
|
while(sSize == pieceSize && tSize == pieceSize && partialSKResult == 0) {
|
|
|
|
uiter_setString(&sIter, source, sLen);
|
|
|
|
uiter_setString(&tIter, target, tLen);
|
|
|
|
sSize = ucol_nextSortKeyPart(coll, &sIter, sState, sBuf, pieceSize, status);
|
|
|
|
tSize = ucol_nextSortKeyPart(coll, &tIter, tState, tBuf, pieceSize, status);
|
|
|
|
|
|
|
|
if(sState[0] != 0 || tState[0] != 0) {
|
|
|
|
log_verbose("State != 0 : %08X %08X\n", sState[0], tState[0]);
|
|
|
|
}
|
|
|
|
log_verbose("%i ", i++);
|
|
|
|
|
|
|
|
partialSKResult = memcmp(sBuf, tBuf, pieceSize);
|
|
|
|
}
|
|
|
|
|
|
|
|
if(partialSKResult < 0) {
|
|
|
|
return UCOL_LESS;
|
|
|
|
} else if(partialSKResult > 0) {
|
|
|
|
return UCOL_GREATER;
|
|
|
|
} else {
|
|
|
|
return UCOL_EQUAL;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2001-05-23 20:32:44 +00:00
|
|
|
static void doTestVariant(UCollator* myCollation, const UChar source[], const UChar target[], UCollationResult result)
|
1999-08-16 21:50:52 +00:00
|
|
|
{
|
2000-07-06 23:01:50 +00:00
|
|
|
int32_t sortklen1, sortklen2, sortklenmax, sortklenmin;
|
2001-03-07 22:27:50 +00:00
|
|
|
int temp=0, gSortklen1=0,gSortklen2=0;
|
2003-01-20 07:42:58 +00:00
|
|
|
UCollationResult compareResult, compareResulta, keyResult, compareResultIter = result;
|
2001-05-17 23:09:35 +00:00
|
|
|
uint8_t *sortKey1, *sortKey2, *sortKey1a, *sortKey2a;
|
2001-04-06 22:51:41 +00:00
|
|
|
uint32_t sLen = u_strlen(source);
|
|
|
|
uint32_t tLen = u_strlen(target);
|
2001-04-19 19:01:39 +00:00
|
|
|
char buffer[256];
|
|
|
|
uint32_t len;
|
2003-01-20 07:42:58 +00:00
|
|
|
UErrorCode status = U_ZERO_ERROR;
|
|
|
|
UColAttributeValue norm = ucol_getAttribute(myCollation, UCOL_NORMALIZATION_MODE, &status);
|
|
|
|
|
2003-02-20 01:12:45 +00:00
|
|
|
UCharIterator sIter, tIter;
|
|
|
|
uiter_setString(&sIter, source, sLen);
|
|
|
|
uiter_setString(&tIter, target, tLen);
|
|
|
|
compareResultIter = ucol_strcollIter(myCollation, &sIter, &tIter, &status);
|
|
|
|
if(compareResultIter != result) {
|
|
|
|
log_err("different results in iterative comparison for UTF-16 encoded strings. %s, %s\n", aescstrdup(source,-1), aescstrdup(target,-1));
|
2003-01-20 07:42:58 +00:00
|
|
|
}
|
2003-02-20 01:12:45 +00:00
|
|
|
|
2003-01-20 07:42:58 +00:00
|
|
|
/* convert the strings to UTF-8 and do try comparing with char iterator */
|
2003-02-20 01:12:45 +00:00
|
|
|
if(QUICK <= 0) { /*!QUICK*/
|
2003-01-20 07:42:58 +00:00
|
|
|
char utf8Source[256], utf8Target[256];
|
|
|
|
int32_t utf8SourceLen = 0, utf8TargetLen = 0;
|
|
|
|
u_strToUTF8(utf8Source, 256, &utf8SourceLen, source, sLen, &status);
|
|
|
|
if(U_FAILURE(status)) { /* probably buffer is not big enough */
|
|
|
|
log_verbose("Src UTF-8 buffer too small! Will not compare!\n");
|
|
|
|
} else {
|
|
|
|
u_strToUTF8(utf8Target, 256, &utf8TargetLen, target, tLen, &status);
|
|
|
|
if(U_SUCCESS(status)) { /* probably buffer is not big enough */
|
|
|
|
UCollationResult compareResultUTF8 = result, compareResultUTF8Norm = result;
|
2003-05-15 17:38:42 +00:00
|
|
|
/*UCharIterator sIter, tIter;*/
|
2003-01-29 21:33:29 +00:00
|
|
|
/*log_verbose("Strings converted to UTF-8:%s, %s\n", aescstrdup(source,-1), aescstrdup(target,-1));*/
|
2003-01-20 07:42:58 +00:00
|
|
|
uiter_setUTF8(&sIter, utf8Source, utf8SourceLen);
|
|
|
|
uiter_setUTF8(&tIter, utf8Target, utf8TargetLen);
|
|
|
|
/*uiter_setString(&sIter, source, sLen);
|
|
|
|
uiter_setString(&tIter, target, tLen);*/
|
|
|
|
compareResultUTF8 = ucol_strcollIter(myCollation, &sIter, &tIter, &status);
|
|
|
|
ucol_setAttribute(myCollation, UCOL_NORMALIZATION_MODE, UCOL_ON, &status);
|
|
|
|
sIter.move(&sIter, 0, UITER_START);
|
|
|
|
tIter.move(&tIter, 0, UITER_START);
|
|
|
|
compareResultUTF8Norm = ucol_strcollIter(myCollation, &sIter, &tIter, &status);
|
|
|
|
ucol_setAttribute(myCollation, UCOL_NORMALIZATION_MODE, norm, &status);
|
|
|
|
if(compareResultUTF8 != compareResultIter) {
|
2003-01-23 01:52:34 +00:00
|
|
|
log_err("different results in iterative comparison for UTF-16 and UTF-8 encoded strings. %s, %s\n", aescstrdup(source,-1), aescstrdup(target,-1));
|
2003-01-20 07:42:58 +00:00
|
|
|
}
|
|
|
|
if(compareResultUTF8 != compareResultUTF8Norm) {
|
2003-01-23 01:52:34 +00:00
|
|
|
log_err("different results in iterative when normalization is turned on with UTF-8 strings. %s, %s\n", aescstrdup(source,-1), aescstrdup(target,-1));
|
2003-01-20 07:42:58 +00:00
|
|
|
}
|
|
|
|
} else {
|
|
|
|
log_verbose("Target UTF-8 buffer too small! Did not compare!\n");
|
|
|
|
}
|
|
|
|
if(U_FAILURE(status)) {
|
|
|
|
log_verbose("UTF-8 strcoll failed! Ignoring result\n");
|
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2003-01-23 01:52:34 +00:00
|
|
|
/* testing the partial sortkeys */
|
2003-02-20 01:12:45 +00:00
|
|
|
if(1) { /*!QUICK*/
|
|
|
|
int32_t i = 0;
|
|
|
|
int32_t partialSizes[] = { 3, 1, 2, 4, 8, 20, 80 }; /* just size 3 in the quick mode */
|
|
|
|
int32_t partialSizesSize = 1;
|
|
|
|
if(QUICK <= 0) {
|
|
|
|
partialSizesSize = 7;
|
2003-01-23 01:52:34 +00:00
|
|
|
}
|
2003-02-20 01:12:45 +00:00
|
|
|
log_verbose("partial sortkey test piecesize=");
|
|
|
|
for(i = 0; i < partialSizesSize; i++) {
|
|
|
|
UCollationResult partialSKResult = result, partialNormalizedSKResult = result;
|
|
|
|
log_verbose("%i ", partialSizes[i]);
|
|
|
|
|
|
|
|
partialSKResult = compareUsingPartials(myCollation, source, sLen, target, tLen, partialSizes[i], &status);
|
|
|
|
if(partialSKResult != result) {
|
|
|
|
log_err("Partial sortkey comparison returned wrong result: %s, %s (size %i)\n",
|
|
|
|
aescstrdup(source,-1), aescstrdup(target,-1), partialSizes[i]);
|
|
|
|
}
|
2003-01-23 01:52:34 +00:00
|
|
|
|
2003-02-20 01:12:45 +00:00
|
|
|
if(QUICK <= 0 && norm != UCOL_ON) {
|
|
|
|
log_verbose("N ");
|
|
|
|
ucol_setAttribute(myCollation, UCOL_NORMALIZATION_MODE, UCOL_ON, &status);
|
|
|
|
partialNormalizedSKResult = compareUsingPartials(myCollation, source, sLen, target, tLen, partialSizes[i], &status);
|
|
|
|
ucol_setAttribute(myCollation, UCOL_NORMALIZATION_MODE, norm, &status);
|
|
|
|
if(partialSKResult != partialNormalizedSKResult) {
|
|
|
|
log_err("Partial sortkey comparison gets different result when normalization is on: %s, %s (size %i)\n",
|
|
|
|
aescstrdup(source,-1), aescstrdup(target,-1), partialSizes[i]);
|
|
|
|
}
|
|
|
|
}
|
2003-01-23 01:52:34 +00:00
|
|
|
}
|
2003-02-20 01:12:45 +00:00
|
|
|
log_verbose("\n");
|
2003-01-23 01:52:34 +00:00
|
|
|
}
|
|
|
|
|
1999-08-16 21:50:52 +00:00
|
|
|
|
2001-05-17 23:09:35 +00:00
|
|
|
compareResult = ucol_strcoll(myCollation, source, sLen, target, tLen);
|
|
|
|
compareResulta = ucol_strcoll(myCollation, source, -1, target, -1);
|
|
|
|
if (compareResult != compareResulta) {
|
|
|
|
log_err("ucol_strcoll result from null terminated and explicit length strings differs.\n");
|
|
|
|
}
|
|
|
|
|
2001-04-06 22:51:41 +00:00
|
|
|
sortklen1=ucol_getSortKey(myCollation, source, sLen, NULL, 0);
|
|
|
|
sortklen2=ucol_getSortKey(myCollation, target, tLen, NULL, 0);
|
2000-07-06 23:01:50 +00:00
|
|
|
|
|
|
|
sortklenmax = (sortklen1>sortklen2?sortklen1:sortklen2);
|
|
|
|
sortklenmin = (sortklen1<sortklen2?sortklen1:sortklen2);
|
|
|
|
|
2001-05-17 23:09:35 +00:00
|
|
|
sortKey1 =(uint8_t*)malloc(sizeof(uint8_t) * (sortklenmax+1));
|
|
|
|
sortKey1a=(uint8_t*)malloc(sizeof(uint8_t) * (sortklenmax+1));
|
|
|
|
ucol_getSortKey(myCollation, source, sLen, sortKey1, sortklen1+1);
|
|
|
|
ucol_getSortKey(myCollation, source, -1, sortKey1a, sortklen1+1);
|
1999-08-16 21:50:52 +00:00
|
|
|
|
2001-05-17 23:09:35 +00:00
|
|
|
sortKey2 =(uint8_t*)malloc(sizeof(uint8_t) * (sortklenmax+1));
|
|
|
|
sortKey2a=(uint8_t*)malloc(sizeof(uint8_t) * (sortklenmax+1));
|
|
|
|
ucol_getSortKey(myCollation, target, tLen, sortKey2, sortklen2+1);
|
|
|
|
ucol_getSortKey(myCollation, target, -1, sortKey2a, sortklen2+1);
|
|
|
|
|
|
|
|
/* Check that sort key generated with null terminated string is identical */
|
|
|
|
/* to that generted with a length specified. */
|
|
|
|
if (uprv_strcmp((const char *)sortKey1, (const char *)sortKey1a) != 0 ||
|
|
|
|
uprv_strcmp((const char *)sortKey2, (const char *)sortKey2a) != 0 ) {
|
|
|
|
log_err("Sort Keys from null terminated and explicit length strings differ.\n");
|
|
|
|
}
|
|
|
|
|
2001-03-09 02:28:41 +00:00
|
|
|
/*memcmp(sortKey1, sortKey2,sortklenmax);*/
|
|
|
|
temp= uprv_strcmp((const char *)sortKey1, (const char *)sortKey2);
|
|
|
|
gSortklen1 = uprv_strlen((const char *)sortKey1)+1;
|
|
|
|
gSortklen2 = uprv_strlen((const char *)sortKey2)+1;
|
2001-03-07 22:27:50 +00:00
|
|
|
if(sortklen1 != gSortklen1){
|
2001-03-10 00:51:07 +00:00
|
|
|
log_err("SortKey length does not match Expected: %i Got: %i\n",sortklen1, gSortklen1);
|
2001-04-19 19:01:39 +00:00
|
|
|
log_verbose("Generated sortkey: %s\n", ucol_sortKeyToString(myCollation, sortKey1, buffer, &len));
|
2001-03-07 22:27:50 +00:00
|
|
|
}
|
|
|
|
if(sortklen2!= gSortklen2){
|
2001-03-10 00:51:07 +00:00
|
|
|
log_err("SortKey length does not match Expected: %i Got: %i\n", sortklen2, gSortklen2);
|
2001-04-19 19:01:39 +00:00
|
|
|
log_verbose("Generated sortkey: %s\n", ucol_sortKeyToString(myCollation, sortKey2, buffer, &len));
|
2001-03-07 22:27:50 +00:00
|
|
|
}
|
|
|
|
|
2001-03-09 02:28:41 +00:00
|
|
|
if(temp < 0) {
|
|
|
|
keyResult=UCOL_LESS;
|
|
|
|
}
|
|
|
|
else if(temp > 0) {
|
|
|
|
keyResult= UCOL_GREATER;
|
|
|
|
}
|
|
|
|
else {
|
|
|
|
keyResult = UCOL_EQUAL;
|
|
|
|
}
|
2003-01-20 07:42:58 +00:00
|
|
|
reportCResult( source, target, sortKey1, sortKey2, compareResult, keyResult, compareResultIter, result );
|
2000-07-06 23:01:50 +00:00
|
|
|
free(sortKey1);
|
|
|
|
free(sortKey2);
|
2001-05-17 23:09:35 +00:00
|
|
|
free(sortKey1a);
|
|
|
|
free(sortKey2a);
|
|
|
|
|
1999-08-16 21:50:52 +00:00
|
|
|
}
|
|
|
|
|
2001-03-16 22:17:57 +00:00
|
|
|
void doTest(UCollator* myCollation, const UChar source[], const UChar target[], UCollationResult result)
|
|
|
|
{
|
2003-06-04 06:53:23 +00:00
|
|
|
if(myCollation) {
|
|
|
|
doTestVariant(myCollation, source, target, result);
|
|
|
|
if(result == UCOL_LESS) {
|
|
|
|
doTestVariant(myCollation, target, source, UCOL_GREATER);
|
|
|
|
} else if(result == UCOL_GREATER) {
|
|
|
|
doTestVariant(myCollation, target, source, UCOL_LESS);
|
|
|
|
} else {
|
|
|
|
doTestVariant(myCollation, target, source, UCOL_EQUAL);
|
|
|
|
}
|
2001-03-16 22:17:57 +00:00
|
|
|
} else {
|
2003-06-04 06:53:23 +00:00
|
|
|
log_data_err("No collator! Any data around?\n");
|
2001-03-16 22:17:57 +00:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2000-11-21 04:05:39 +00:00
|
|
|
static void TestTertiary()
|
1999-08-16 21:50:52 +00:00
|
|
|
{
|
|
|
|
int32_t len,i;
|
2001-03-23 23:50:28 +00:00
|
|
|
UChar *rules;
|
2001-03-27 02:19:56 +00:00
|
|
|
UCollator *myCollation;
|
1999-10-07 00:07:53 +00:00
|
|
|
UErrorCode status=U_ZERO_ERROR;
|
1999-08-16 21:50:52 +00:00
|
|
|
const char* str="& C < ch, cH, Ch, CH & Five, 5 & Four, 4 & one, 1 & Ampersand; '&' & Two, 2 ";
|
2001-03-23 23:50:28 +00:00
|
|
|
len = strlen(str);
|
|
|
|
rules=(UChar*)malloc(sizeof(UChar*) * (len+1));
|
|
|
|
u_uastrcpy(rules, str);
|
|
|
|
|
2001-09-22 01:17:26 +00:00
|
|
|
myCollation=ucol_openRules(rules, len, UCOL_OFF, UCOL_DEFAULT_STRENGTH, NULL, &status);
|
1999-10-18 22:48:32 +00:00
|
|
|
if(U_FAILURE(status)){
|
1999-08-16 21:50:52 +00:00
|
|
|
log_err("ERROR: in creation of rule based collator :%s\n", myErrorName(status));
|
|
|
|
}
|
|
|
|
|
|
|
|
ucol_setStrength(myCollation, UCOL_TERTIARY);
|
|
|
|
for (i = 0; i < 17 ; i++)
|
|
|
|
{
|
|
|
|
doTest(myCollation, testSourceCases[i], testTargetCases[i], results[i]);
|
|
|
|
}
|
|
|
|
free(rules);
|
|
|
|
ucol_close(myCollation);
|
|
|
|
myCollation = 0;
|
|
|
|
}
|
|
|
|
|
2000-11-21 04:05:39 +00:00
|
|
|
static void TestPrimary( )
|
1999-08-16 21:50:52 +00:00
|
|
|
{
|
|
|
|
int32_t len,i;
|
2001-03-23 23:50:28 +00:00
|
|
|
UChar *rules;
|
2001-03-27 02:19:56 +00:00
|
|
|
UCollator *myCollation;
|
1999-10-07 00:07:53 +00:00
|
|
|
UErrorCode status=U_ZERO_ERROR;
|
2001-03-23 23:50:28 +00:00
|
|
|
const char* str="& C < ch, cH, Ch, CH & Five, 5 & Four, 4 & one, 1 & Ampersand; '&' & Two, 2 ";
|
|
|
|
len = strlen(str);
|
|
|
|
rules=(UChar*)malloc(sizeof(UChar*) * (len+1));
|
|
|
|
u_uastrcpy(rules, str);
|
|
|
|
|
2001-09-22 01:17:26 +00:00
|
|
|
myCollation=ucol_openRules(rules, len, UCOL_OFF, UCOL_DEFAULT_STRENGTH,NULL, &status);
|
1999-10-18 22:48:32 +00:00
|
|
|
if(U_FAILURE(status)){
|
1999-08-16 21:50:52 +00:00
|
|
|
log_err("ERROR: in creation of rule based collator :%s\n", myErrorName(status));
|
|
|
|
}
|
|
|
|
ucol_setStrength(myCollation, UCOL_PRIMARY);
|
|
|
|
|
|
|
|
for (i = 17; i < 26 ; i++)
|
|
|
|
{
|
|
|
|
|
|
|
|
doTest(myCollation, testSourceCases[i], testTargetCases[i], results[i]);
|
|
|
|
}
|
|
|
|
free(rules);
|
|
|
|
ucol_close(myCollation);
|
|
|
|
myCollation = 0;
|
|
|
|
}
|
|
|
|
|
2000-11-21 04:05:39 +00:00
|
|
|
static void TestSecondary()
|
1999-08-16 21:50:52 +00:00
|
|
|
{
|
|
|
|
int32_t i;
|
|
|
|
int32_t len;
|
2001-03-23 23:50:28 +00:00
|
|
|
UChar *rules;
|
2001-03-27 02:19:56 +00:00
|
|
|
UCollator *myCollation;
|
1999-10-07 00:07:53 +00:00
|
|
|
UErrorCode status=U_ZERO_ERROR;
|
1999-08-16 21:50:52 +00:00
|
|
|
const char* str="& C < ch, cH, Ch, CH & Five, 5 & Four, 4 & one, 1 & Ampersand; '&' & Two, 2 ";
|
2001-03-23 23:50:28 +00:00
|
|
|
len = strlen(str);
|
|
|
|
rules=(UChar*)malloc(sizeof(UChar*) * (len+1));
|
|
|
|
u_uastrcpy(rules, str);
|
|
|
|
|
2001-09-22 01:17:26 +00:00
|
|
|
myCollation=ucol_openRules(rules, len, UCOL_OFF, UCOL_DEFAULT_STRENGTH,NULL, &status);
|
1999-10-18 22:48:32 +00:00
|
|
|
if(U_FAILURE(status)){
|
1999-08-16 21:50:52 +00:00
|
|
|
log_err("ERROR: in creation of rule based collator :%s\n", myErrorName(status));
|
|
|
|
}
|
|
|
|
ucol_setStrength(myCollation, UCOL_SECONDARY);
|
|
|
|
for (i = 26; i < 34 ; i++)
|
|
|
|
{
|
|
|
|
doTest(myCollation, testSourceCases[i], testTargetCases[i], results[i]);
|
|
|
|
}
|
|
|
|
free(rules);
|
|
|
|
ucol_close(myCollation);
|
|
|
|
myCollation = 0;
|
|
|
|
}
|
2000-11-21 04:05:39 +00:00
|
|
|
|
|
|
|
static void TestIdentical()
|
1999-08-16 21:50:52 +00:00
|
|
|
{
|
|
|
|
int32_t i;
|
|
|
|
int32_t len;
|
2001-03-23 23:50:28 +00:00
|
|
|
UChar *rules = 0;
|
2001-03-27 02:19:56 +00:00
|
|
|
UCollator *myCollation;
|
1999-10-07 00:07:53 +00:00
|
|
|
UErrorCode status=U_ZERO_ERROR;
|
1999-08-16 21:50:52 +00:00
|
|
|
const char* str="& C < ch, cH, Ch, CH & Five, 5 & Four, 4 & one, 1 & Ampersand; '&' & Two, 2 ";
|
2001-03-23 23:50:28 +00:00
|
|
|
len = strlen(str);
|
|
|
|
rules=(UChar*)malloc(sizeof(UChar*) * (len+1));
|
|
|
|
u_uastrcpy(rules, str);
|
1999-08-16 21:50:52 +00:00
|
|
|
|
2001-09-22 01:17:26 +00:00
|
|
|
myCollation=ucol_openRules(rules, len, UCOL_OFF, UCOL_IDENTICAL, NULL,&status);
|
1999-10-18 22:48:32 +00:00
|
|
|
if(U_FAILURE(status)){
|
1999-08-16 21:50:52 +00:00
|
|
|
log_err("ERROR: in creation of rule based collator :%s\n", myErrorName(status));
|
|
|
|
}
|
|
|
|
for(i= 34; i<37; i++)
|
|
|
|
{
|
|
|
|
doTest(myCollation, testSourceCases[i], testTargetCases[i], results[i]);
|
|
|
|
}
|
|
|
|
free(rules);
|
|
|
|
ucol_close(myCollation);
|
|
|
|
myCollation = 0;
|
|
|
|
}
|
2000-11-21 04:05:39 +00:00
|
|
|
|
|
|
|
static void TestExtra()
|
1999-08-16 21:50:52 +00:00
|
|
|
{
|
|
|
|
int32_t i, j;
|
|
|
|
int32_t len;
|
2001-03-23 23:50:28 +00:00
|
|
|
UChar *rules;
|
2001-03-27 02:19:56 +00:00
|
|
|
UCollator *myCollation;
|
1999-10-07 00:07:53 +00:00
|
|
|
UErrorCode status = U_ZERO_ERROR;
|
1999-08-16 21:50:52 +00:00
|
|
|
const char* str="& C < ch, cH, Ch, CH & Five, 5 & Four, 4 & one, 1 & Ampersand; '&' & Two, 2 ";
|
2001-03-23 23:50:28 +00:00
|
|
|
len = strlen(str);
|
|
|
|
rules=(UChar*)malloc(sizeof(UChar*) * (len+1));
|
|
|
|
u_uastrcpy(rules, str);
|
|
|
|
|
2001-09-22 01:17:26 +00:00
|
|
|
myCollation=ucol_openRules(rules, len, UCOL_OFF, UCOL_DEFAULT_STRENGTH,NULL, &status);
|
1999-10-18 22:48:32 +00:00
|
|
|
if(U_FAILURE(status)){
|
1999-08-16 21:50:52 +00:00
|
|
|
log_err("ERROR: in creation of rule based collator :%s\n", myErrorName(status));
|
|
|
|
}
|
|
|
|
ucol_setStrength(myCollation, UCOL_TERTIARY);
|
2000-03-22 23:17:42 +00:00
|
|
|
for (i = 0; i < COUNT_TEST_CASES-1 ; i++)
|
1999-08-16 21:50:52 +00:00
|
|
|
{
|
2000-03-22 23:17:42 +00:00
|
|
|
for (j = i + 1; j < COUNT_TEST_CASES; j += 1)
|
1999-08-16 21:50:52 +00:00
|
|
|
{
|
|
|
|
|
|
|
|
doTest(myCollation, testCases[i], testCases[j], UCOL_LESS);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
free(rules);
|
|
|
|
ucol_close(myCollation);
|
|
|
|
myCollation = 0;
|
|
|
|
}
|
2000-03-22 23:17:42 +00:00
|
|
|
|
2000-11-21 04:05:39 +00:00
|
|
|
static void TestJB581(void)
|
2000-10-13 20:14:51 +00:00
|
|
|
{
|
2000-11-21 04:05:39 +00:00
|
|
|
UChar dispName [100];
|
|
|
|
int32_t bufferLen = 0;
|
|
|
|
UChar source [100];
|
|
|
|
UChar target [100];
|
|
|
|
UCollationResult result = UCOL_EQUAL;
|
|
|
|
uint8_t sourceKeyArray [100];
|
|
|
|
uint8_t targetKeyArray [100];
|
|
|
|
int32_t sourceKeyOut = 0,
|
|
|
|
targetKeyOut = 0;
|
|
|
|
UCollator *myCollator = 0;
|
2000-10-13 20:14:51 +00:00
|
|
|
UErrorCode status = U_ZERO_ERROR;
|
|
|
|
|
2001-03-13 07:30:28 +00:00
|
|
|
/*u_uastrcpy(source, "This is a test.");*/
|
|
|
|
/*u_uastrcpy(target, "THISISATEST.");*/
|
|
|
|
u_uastrcpy(source, "THISISATEST.");
|
|
|
|
u_uastrcpy(target, "Thisisatest.");
|
2000-10-13 20:14:51 +00:00
|
|
|
|
|
|
|
myCollator = ucol_open("en_US", &status);
|
|
|
|
if (U_FAILURE(status)){
|
|
|
|
bufferLen = uloc_getDisplayName("en_US", 0, dispName, 100, &status);
|
|
|
|
/*Report the error with display name... */
|
|
|
|
log_err("ERROR: Failed to create the collator for : \"%s\"\n", dispName);
|
|
|
|
return;
|
|
|
|
}
|
|
|
|
result = ucol_strcoll(myCollator, source, -1, target, -1);
|
|
|
|
/* result is 1, secondary differences only for ignorable space characters*/
|
|
|
|
if (result != 1)
|
|
|
|
{
|
|
|
|
log_err("Comparing two strings with only secondary differences in C failed.\n");
|
|
|
|
}
|
|
|
|
/* To compare them with just primary differences */
|
|
|
|
ucol_setStrength(myCollator, UCOL_PRIMARY);
|
|
|
|
result = ucol_strcoll(myCollator, source, -1, target, -1);
|
|
|
|
/* result is 0 */
|
|
|
|
if (result != 0)
|
|
|
|
{
|
|
|
|
log_err("Comparing two strings with no differences in C failed.\n");
|
|
|
|
}
|
|
|
|
/* Now, do the same comparison with keys */
|
|
|
|
sourceKeyOut = ucol_getSortKey(myCollator, source, -1, sourceKeyArray, 100);
|
|
|
|
targetKeyOut = ucol_getSortKey(myCollator, target, -1, targetKeyArray, 100);
|
|
|
|
result = 0;
|
|
|
|
bufferLen = ((targetKeyOut > 100) ? 100 : targetKeyOut);
|
|
|
|
result = memcmp(sourceKeyArray, targetKeyArray, bufferLen);
|
|
|
|
if (result != 0)
|
|
|
|
{
|
|
|
|
log_err("Comparing two strings with sort keys in C failed.\n");
|
|
|
|
}
|
|
|
|
ucol_close(myCollator);
|
|
|
|
}
|
2001-04-07 00:24:06 +00:00
|
|
|
|
2001-10-29 17:56:00 +00:00
|
|
|
static void TestJB1401(void)
|
|
|
|
{
|
|
|
|
UCollator *myCollator = 0;
|
|
|
|
UErrorCode status = U_ZERO_ERROR;
|
|
|
|
static UChar NFD_UnsafeStartChars[] = {
|
|
|
|
0x0f73, /* Tibetan Vowel Sign II */
|
|
|
|
0x0f75, /* Tibetan Vowel Sign UU */
|
|
|
|
0x0f81, /* Tibetan Vowel Sign Reversed II */
|
|
|
|
0
|
|
|
|
};
|
|
|
|
int i;
|
|
|
|
|
|
|
|
|
|
|
|
myCollator = ucol_open("en_US", &status);
|
|
|
|
if (U_FAILURE(status)){
|
|
|
|
int32_t bufferLen = 0;
|
|
|
|
UChar dispName [100];
|
|
|
|
bufferLen = uloc_getDisplayName("en_US", 0, dispName, 100, &status);
|
|
|
|
/*Report the error with display name... */
|
|
|
|
log_err("ERROR: Failed to create the collator for : \"%s\"\n", dispName);
|
|
|
|
return;
|
|
|
|
}
|
|
|
|
ucol_setAttribute(myCollator, UCOL_NORMALIZATION_MODE, UCOL_ON, &status);
|
|
|
|
if (U_FAILURE(status)){
|
|
|
|
log_err("ERROR: Failed to set normalization mode ON for collator.\n");
|
|
|
|
return;
|
|
|
|
}
|
|
|
|
|
|
|
|
for (i=0; ; i++) {
|
|
|
|
UChar c;
|
|
|
|
UChar X[4];
|
|
|
|
UChar Y[20];
|
|
|
|
UChar Z[20];
|
|
|
|
|
|
|
|
/* Get the next funny character to be tested, and set up the
|
|
|
|
* three test strings X, Y, Z, consisting of an A-grave + test char,
|
|
|
|
* in original form, NFD, and then NFC form.
|
|
|
|
*/
|
|
|
|
c = NFD_UnsafeStartChars[i];
|
|
|
|
if (c==0) {break;}
|
|
|
|
|
|
|
|
X[0]=0xC0; X[1]=c; X[2]=0; /* \u00C0 is A Grave*/
|
|
|
|
|
|
|
|
unorm_normalize(X, -1, UNORM_NFD, 0, Y, 20, &status);
|
|
|
|
unorm_normalize(Y, -1, UNORM_NFC, 0, Z, 20, &status);
|
|
|
|
if (U_FAILURE(status)){
|
|
|
|
log_err("ERROR: Failed to normalize test of character %x\n", c);
|
|
|
|
return;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* Collation test. All three strings should be equal.
|
|
|
|
* doTest does both strcoll and sort keys, with params in both orders.
|
|
|
|
*/
|
|
|
|
doTest(myCollator, X, Y, UCOL_EQUAL);
|
|
|
|
doTest(myCollator, X, Z, UCOL_EQUAL);
|
|
|
|
doTest(myCollator, Y, Z, UCOL_EQUAL);
|
|
|
|
|
|
|
|
/* Run collation element iterators over the three strings. Results should be same for each.
|
|
|
|
*/
|
|
|
|
{
|
|
|
|
UCollationElements *ceiX, *ceiY, *ceiZ;
|
|
|
|
int32_t ceX, ceY, ceZ;
|
|
|
|
int j;
|
|
|
|
|
|
|
|
ceiX = ucol_openElements(myCollator, X, -1, &status);
|
|
|
|
ceiY = ucol_openElements(myCollator, Y, -1, &status);
|
|
|
|
ceiZ = ucol_openElements(myCollator, Z, -1, &status);
|
|
|
|
if (U_FAILURE(status)) {
|
|
|
|
log_err("ERROR: uucol_openElements failed.\n");
|
|
|
|
return;
|
|
|
|
}
|
|
|
|
|
|
|
|
for (j=0;; j++) {
|
|
|
|
ceX = ucol_next(ceiX, &status);
|
|
|
|
ceY = ucol_next(ceiY, &status);
|
|
|
|
ceZ = ucol_next(ceiZ, &status);
|
|
|
|
if (U_FAILURE(status)) {
|
|
|
|
log_err("ERROR: ucol_next failed for iteration #%d.\n", j);
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
if (ceX != ceY || ceY != ceZ) {
|
|
|
|
log_err("ERROR: ucol_next failed for iteration #%d.\n", j);
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
if (ceX == UCOL_NULLORDER) {
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
ucol_closeElements(ceiX);
|
|
|
|
ucol_closeElements(ceiY);
|
|
|
|
ucol_closeElements(ceiZ);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
ucol_close(myCollator);
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
|
2001-04-07 00:24:06 +00:00
|
|
|
/**
|
|
|
|
* Tests the [variable top] tag in rule syntax. Since the default [alternate]
|
|
|
|
* tag has the value shifted, any codepoints before [variable top] should give
|
|
|
|
* a primary ce of 0.
|
|
|
|
*/
|
|
|
|
static void TestVariableTop(void)
|
|
|
|
{
|
|
|
|
const char *str = "&z = [variable top]";
|
|
|
|
int len = strlen(str);
|
|
|
|
UChar *rules;
|
|
|
|
UCollator *myCollation;
|
|
|
|
UCollator *enCollation;
|
|
|
|
UErrorCode status = U_ZERO_ERROR;
|
|
|
|
UChar source[1];
|
|
|
|
UChar ch;
|
|
|
|
uint8_t result[20];
|
|
|
|
uint8_t expected[20];
|
|
|
|
|
|
|
|
rules = (UChar*)malloc(sizeof(UChar*) * (len + 1));
|
|
|
|
u_uastrcpy(rules, str);
|
|
|
|
|
|
|
|
enCollation = ucol_open("en_US", &status);
|
2001-09-22 01:17:26 +00:00
|
|
|
myCollation = ucol_openRules(rules, len, UCOL_OFF,
|
2001-08-16 00:58:53 +00:00
|
|
|
UCOL_PRIMARY,NULL, &status);
|
2001-04-07 00:24:06 +00:00
|
|
|
if (U_FAILURE(status)) {
|
|
|
|
log_err("ERROR: in creation of rule based collator :%s\n",
|
|
|
|
myErrorName(status));
|
|
|
|
return;
|
|
|
|
}
|
|
|
|
|
|
|
|
ucol_setStrength(enCollation, UCOL_PRIMARY);
|
|
|
|
ucol_setAttribute(enCollation, UCOL_ALTERNATE_HANDLING, UCOL_SHIFTED,
|
|
|
|
&status);
|
|
|
|
ucol_setAttribute(myCollation, UCOL_ALTERNATE_HANDLING, UCOL_SHIFTED,
|
|
|
|
&status);
|
|
|
|
|
|
|
|
if (ucol_getAttribute(myCollation, UCOL_ALTERNATE_HANDLING, &status) !=
|
|
|
|
UCOL_SHIFTED || U_FAILURE(status)) {
|
|
|
|
log_err("ERROR: ALTERNATE_HANDLING value can not be set to SHIFTED\n");
|
|
|
|
}
|
|
|
|
|
|
|
|
uprv_memset(expected, 0, 20);
|
|
|
|
|
|
|
|
/* space is supposed to be a variable */
|
|
|
|
source[0] = ' ';
|
|
|
|
len = ucol_getSortKey(enCollation, source, 1, result,
|
|
|
|
sizeof(result));
|
|
|
|
|
|
|
|
if (uprv_memcmp(expected, result, len) != 0) {
|
|
|
|
log_err("ERROR: SHIFTED alternate does not return 0 for primary of space\n");
|
|
|
|
}
|
|
|
|
|
|
|
|
ch = 'a';
|
|
|
|
while (ch < 'z') {
|
|
|
|
source[0] = ch;
|
|
|
|
len = ucol_getSortKey(myCollation, source, 1, result,
|
|
|
|
sizeof(result));
|
|
|
|
if (uprv_memcmp(expected, result, len) != 0) {
|
|
|
|
log_err("ERROR: SHIFTED alternate does not return 0 for primary of %c\n",
|
|
|
|
ch);
|
|
|
|
}
|
|
|
|
ch ++;
|
|
|
|
}
|
|
|
|
|
|
|
|
free(rules);
|
|
|
|
ucol_close(enCollation);
|
|
|
|
ucol_close(myCollation);
|
|
|
|
enCollation = NULL;
|
|
|
|
myCollation = NULL;
|
|
|
|
}
|
|
|
|
|
|
|
|
/**
|
2002-06-13 18:35:27 +00:00
|
|
|
* Tests surrogate support.
|
|
|
|
* NOTE: This test used \\uD801\\uDC01 pair, which is now assigned to Desseret
|
|
|
|
* Therefore, another (unassigned) code point was used for this test.
|
|
|
|
*/
|
2001-04-07 00:24:06 +00:00
|
|
|
static void TestSurrogates(void)
|
|
|
|
{
|
|
|
|
const char *str =
|
2002-06-13 18:35:27 +00:00
|
|
|
"&z<'\\uD800\\uDC00'<'\\uD800\\uDC0A\\u0308'<A";
|
2001-04-07 00:24:06 +00:00
|
|
|
int len = strlen(str);
|
|
|
|
int rlen = 0;
|
|
|
|
UChar *rules;
|
|
|
|
UCollator *myCollation;
|
|
|
|
UCollator *enCollation;
|
|
|
|
UErrorCode status = U_ZERO_ERROR;
|
|
|
|
UChar source[][4] =
|
2002-06-13 18:35:27 +00:00
|
|
|
{{'z', 0, 0}, {0xD800, 0xDC00, 0}, {0xD800, 0xDC0A, 0x0308, 0}, {0xD800, 0xDC02}};
|
2001-04-07 00:24:06 +00:00
|
|
|
UChar target[][4] =
|
2002-06-13 18:35:27 +00:00
|
|
|
{{0xD800, 0xDC00, 0}, {0xD800, 0xDC0A, 0x0308, 0}, {'A', 0, 0}, {0xD800, 0xDC03}};
|
2001-04-07 00:24:06 +00:00
|
|
|
int count = 0;
|
|
|
|
uint8_t enresult[20], myresult[20];
|
|
|
|
int enlen, mylen;
|
|
|
|
|
|
|
|
/* tests for open rules with surrogate rules */
|
|
|
|
rules = (UChar*)malloc(sizeof(UChar*) * (len + 1));
|
|
|
|
rlen = u_unescape(str, rules, len);
|
|
|
|
|
|
|
|
enCollation = ucol_open("en_US", &status);
|
2002-09-06 04:31:03 +00:00
|
|
|
myCollation = ucol_openRules(rules, rlen, UCOL_OFF,
|
2001-08-16 00:58:53 +00:00
|
|
|
UCOL_TERTIARY,NULL, &status);
|
2001-04-07 00:24:06 +00:00
|
|
|
if (U_FAILURE(status)) {
|
|
|
|
log_err("ERROR: in creation of rule based collator :%s\n",
|
|
|
|
myErrorName(status));
|
|
|
|
return;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
this test is to verify the supplementary sort key order in the english
|
|
|
|
collator
|
|
|
|
*/
|
|
|
|
log_verbose("start of english collation supplementary characters test\n");
|
|
|
|
while (count < 2) {
|
|
|
|
doTest(enCollation, source[count], target[count], UCOL_LESS);
|
|
|
|
count ++;
|
|
|
|
}
|
|
|
|
doTest(enCollation, source[count], target[count], UCOL_GREATER);
|
|
|
|
|
|
|
|
log_verbose("start of tailored collation supplementary characters test\n");
|
|
|
|
count = 0;
|
|
|
|
/* tests getting collation elements for surrogates for tailored rules */
|
2002-06-13 18:35:27 +00:00
|
|
|
while (count < 4) {
|
2001-04-07 00:24:06 +00:00
|
|
|
doTest(myCollation, source[count], target[count], UCOL_LESS);
|
|
|
|
count ++;
|
|
|
|
}
|
|
|
|
|
2002-06-13 18:35:27 +00:00
|
|
|
/* tests that \uD800\uDC02 still has the same value, not changed */
|
|
|
|
enlen = ucol_getSortKey(enCollation, source[3], 2, enresult, 20);
|
|
|
|
mylen = ucol_getSortKey(myCollation, source[3], 2, myresult, 20);
|
2001-04-26 22:57:06 +00:00
|
|
|
if (enlen != mylen ||
|
|
|
|
uprv_memcmp(enresult, myresult, enlen) != 0) {
|
2001-04-07 00:24:06 +00:00
|
|
|
log_verbose("Failed : non-tailored supplementary characters should have the same value\n");
|
|
|
|
}
|
|
|
|
|
|
|
|
free(rules);
|
|
|
|
ucol_close(enCollation);
|
|
|
|
ucol_close(myCollation);
|
|
|
|
enCollation = NULL;
|
|
|
|
myCollation = NULL;
|
|
|
|
}
|
|
|
|
|
2001-08-17 22:18:38 +00:00
|
|
|
/*
|
|
|
|
*### TODO: Add more invalid rules to test all different scenarios.
|
|
|
|
*
|
|
|
|
*/
|
|
|
|
static void
|
|
|
|
TestInvalidRules(){
|
|
|
|
#define MAX_ERROR_STATES 2
|
|
|
|
|
|
|
|
static const char* rulesArr[MAX_ERROR_STATES] = {
|
|
|
|
"& C < ch, cH, Ch[this should fail]<d",
|
|
|
|
"& C < ch, cH, & Ch[variable top]"
|
|
|
|
};
|
|
|
|
static const char* preContextArr[MAX_ERROR_STATES] = {
|
|
|
|
"his should fail",
|
|
|
|
"& C < ch, cH, ",
|
|
|
|
|
|
|
|
};
|
|
|
|
static const char* postContextArr[MAX_ERROR_STATES] = {
|
|
|
|
"<d",
|
|
|
|
" Ch[variable t"
|
|
|
|
};
|
2001-10-10 00:54:27 +00:00
|
|
|
int i;
|
|
|
|
|
|
|
|
for(i = 0;i<MAX_ERROR_STATES;i++){
|
2001-08-17 22:18:38 +00:00
|
|
|
UChar rules[1000] = { '\0' };
|
|
|
|
UChar preContextExp[1000] = { '\0' };
|
|
|
|
UChar postContextExp[1000] = { '\0' };
|
|
|
|
UParseError parseError;
|
|
|
|
UErrorCode status = U_ZERO_ERROR;
|
|
|
|
UCollator* coll=0;
|
2002-08-03 05:58:30 +00:00
|
|
|
u_charsToUChars(rulesArr[i],rules,uprv_strlen(rulesArr[i])+1);
|
|
|
|
u_charsToUChars(preContextArr[i],preContextExp,uprv_strlen(preContextArr[i])+1);
|
|
|
|
u_charsToUChars(postContextArr[i],postContextExp,uprv_strlen(postContextArr[i])+1);
|
2001-08-17 22:18:38 +00:00
|
|
|
/* clean up stuff in parseError */
|
|
|
|
u_memset(parseError.preContext,0x0000,U_PARSE_CONTEXT_LEN);
|
|
|
|
u_memset(parseError.postContext,0x0000,U_PARSE_CONTEXT_LEN);
|
|
|
|
/* open the rules and test */
|
2001-09-22 01:17:26 +00:00
|
|
|
coll = ucol_openRules(rules,u_strlen(rules),UCOL_OFF,UCOL_DEFAULT_STRENGTH,&parseError,&status);
|
2001-08-17 22:18:38 +00:00
|
|
|
if(u_strcmp(parseError.preContext,preContextExp)!=0){
|
|
|
|
log_err("preContext in UParseError for ucol_openRules does not match\n");
|
|
|
|
}
|
|
|
|
if(u_strcmp(parseError.postContext,postContextExp)!=0){
|
|
|
|
log_err("postContext in UParseError for ucol_openRules does not match\n");
|
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
2001-11-14 02:51:50 +00:00
|
|
|
|
2001-11-07 03:23:55 +00:00
|
|
|
static void
|
|
|
|
TestJitterbug1098(){
|
|
|
|
UChar rule[1000];
|
|
|
|
UCollator* c1 = NULL;
|
|
|
|
UErrorCode status = U_ZERO_ERROR;
|
|
|
|
UParseError parseError;
|
|
|
|
char preContext[200]={0};
|
|
|
|
char postContext[200]={0};
|
2001-11-14 02:51:50 +00:00
|
|
|
int i=0;
|
2001-11-07 03:23:55 +00:00
|
|
|
const char* rules[] = {
|
|
|
|
"&''<\\\\",
|
|
|
|
"&\\'<\\\\",
|
|
|
|
"&\\\"<'\\'",
|
|
|
|
"&'\"'<\\'",
|
|
|
|
'\0'
|
|
|
|
|
|
|
|
};
|
2001-11-14 02:51:50 +00:00
|
|
|
const UCollationResult results1098[] = {
|
2001-11-07 03:23:55 +00:00
|
|
|
UCOL_LESS,
|
|
|
|
UCOL_LESS,
|
|
|
|
UCOL_LESS,
|
|
|
|
UCOL_LESS,
|
|
|
|
};
|
|
|
|
const UChar input[][2]= {
|
|
|
|
{0x0027,0x005c},
|
|
|
|
{0x0027,0x005c},
|
|
|
|
{0x0022,0x005c},
|
|
|
|
{0x0022,0x0027},
|
|
|
|
};
|
|
|
|
UChar X[2] ={0};
|
|
|
|
UChar Y[2] ={0};
|
|
|
|
u_memset(parseError.preContext,0x0000,U_PARSE_CONTEXT_LEN);
|
|
|
|
u_memset(parseError.postContext,0x0000,U_PARSE_CONTEXT_LEN);
|
|
|
|
for(;rules[i]!=0;i++){
|
|
|
|
u_uastrcpy(rule, rules[i]);
|
|
|
|
c1 = ucol_openRules(rule, u_strlen(rule), UCOL_OFF, UCOL_DEFAULT_STRENGTH, &parseError, &status);
|
|
|
|
if(U_FAILURE(status)){
|
|
|
|
u_UCharsToChars(parseError.preContext,preContext,20);
|
|
|
|
u_UCharsToChars(parseError.postContext,postContext,20);
|
|
|
|
log_err("Could not parse the rules syntax. Error: %s ", u_errorName(status));
|
|
|
|
log_verbose("\n\tPre-Context: %s \n\tPost-Context:%s \n",preContext,postContext);
|
|
|
|
return;
|
|
|
|
}
|
|
|
|
X[0] = input[i][0];
|
|
|
|
Y[0] = input[i][1];
|
2001-11-14 02:51:50 +00:00
|
|
|
doTest(c1,X,Y,results1098[i]);
|
2001-11-07 03:23:55 +00:00
|
|
|
ucol_close(c1);
|
|
|
|
}
|
|
|
|
}
|
2001-08-17 22:18:38 +00:00
|
|
|
|
2002-09-20 17:54:45 +00:00
|
|
|
|
|
|
|
#endif /* #if !UCONFIG_NO_COLLATION */
|