b |= *bi1 == *bi2;
b |= *bi1 == *bi3;
if (b) {
- errln((UnicodeString)"ERROR:1 RBBI's == and != operator failed.");
+ errln("%s:%d ERROR:1 RBBI's == and != operator failed.", __FILE__, __LINE__);
}
if(*bi2 == *biequal || *bi2 == *bi1 || *biequal == *bi3)
- errln((UnicodeString)"ERROR:2 RBBI's == and != operator failed.");
+ errln("%s:%d ERROR:2 RBBI's == and != operator failed.", __FILE__, __LINE__);
// Quick test of RulesBasedBreakIterator assignment -
RuleBasedBreakIterator biDefault, biDefault2;
if(U_FAILURE(status)){
- errln((UnicodeString)"FAIL : in construction of default iterator");
+ errln("%s:%d FAIL : in construction of default iterator", __FILE__, __LINE__);
return;
}
if (biDefault == *bix) {
- errln((UnicodeString)"ERROR: iterators should not compare ==");
+ errln("%s:%d ERROR: iterators should not compare ==", __FILE__, __LINE__);
return;
}
if (biDefault != biDefault2) {
- errln((UnicodeString)"ERROR: iterators should compare ==");
+ errln("%s:%d ERROR: iterators should compare ==", __FILE__, __LINE__);
return;
}
UnicodeString HelloString("Hello Kitty");
bix->setText(HelloString);
if (*bix == *bi2) {
- errln(UnicodeString("ERROR: strings should not be equal before assignment."));
+ errln("%s:%d ERROR: strings should not be equal before assignment.", __FILE__, __LINE__);
}
*bix = *bi2;
if (*bix != *bi2) {
- errln(UnicodeString("ERROR: strings should be equal before assignment."));
+ errln("%s:%d ERROR: strings should be equal before assignment.", __FILE__, __LINE__);
}
int bixnext = bix->next();
int bi2next = bi2->next();
if (! (bixnext == bi2next && bixnext == 7)) {
- errln(UnicodeString("ERROR: iterators behaved differently after assignment."));
+ errln("%s:%d ERROR: iterators behaved differently after assignment.", __FILE__, __LINE__);
}
delete bix;
if (bi2->next() != 8) {
- errln(UnicodeString("ERROR: iterator.next() failed after deleting copy."));
+ errln("%s:%d ERROR: iterator.next() failed after deleting copy.", __FILE__, __LINE__);
}
logln((UnicodeString)"Testing clone()");
- RuleBasedBreakIterator* bi1clone=(RuleBasedBreakIterator*)bi1->clone();
- RuleBasedBreakIterator* bi2clone=(RuleBasedBreakIterator*)bi2->clone();
+ RuleBasedBreakIterator* bi1clone = dynamic_cast<RuleBasedBreakIterator *>(bi1->clone());
+ RuleBasedBreakIterator* bi2clone = dynamic_cast<RuleBasedBreakIterator *>(bi2->clone());
if(*bi1clone != *bi1 || *bi1clone != *biequal ||
*bi1clone == *bi3 || *bi1clone == *bi2)
- errln((UnicodeString)"ERROR:1 RBBI's clone() method failed");
+ errln("%s:%d ERROR:1 RBBI's clone() method failed", __FILE__, __LINE__);
if(*bi2clone == *bi1 || *bi2clone == *biequal ||
*bi2clone == *bi3 || *bi2clone != *bi2)
- errln((UnicodeString)"ERROR:2 RBBI's clone() method failed");
+ errln("%s:%d ERROR:2 RBBI's clone() method failed", __FILE__, __LINE__);
if(bi1->getText() != bi1clone->getText() ||
bi2clone->getText() != bi2->getText() ||
*bi2clone == *bi1clone )
- errln((UnicodeString)"ERROR: RBBI's clone() method failed");
+ errln("%s:%d ERROR: RBBI's clone() method failed", __FILE__, __LINE__);
delete bi1clone;
delete bi2clone;
int32_t i;
i = bi->first();
if (i != 0) {
- errln("Incorrect value from bi->first(). Expected 0, got %d.", i);
+ errln("%s:%d Incorrect value from bi->first(). Expected 0, got %d.", __FILE__, __LINE__, i);
}
i = bi->last();
if (i != 10) {
- errln("Incorrect value from bi->last(). Expected 10, got %d", i);
+ errln("%s:%d Incorrect value from bi->last(). Expected 10, got %d", __FILE__, __LINE__, i);
}
//
bi->last();
i = bi->previous();
if (i != 9) {
- errln("Incorrect value from bi->last() at line %d. Expected 9, got %d", __LINE__, i);
+ errln("%s:%d Incorrect value from bi->last(). Expected 9, got %d", __FILE__, __LINE__, i);
}
bi->first();
i = bi->previous();
if (i != BreakIterator::DONE) {
- errln("Incorrect value from bi->previous() at line %d. Expected DONE, got %d", __LINE__, i);
+ errln("%s:%d Incorrect value from bi->previous(). Expected DONE, got %d", __FILE__, __LINE__, i);
}
//
bi->first();
i = bi->next();
if (i != 1) {
- errln("Incorrect value from bi->next() at line %d. Expected 1, got %d", __LINE__, i);
+ errln("%s:%d Incorrect value from bi->next(). Expected 1, got %d", __FILE__, __LINE__, i);
}
bi->last();
i = bi->next();
if (i != BreakIterator::DONE) {
- errln("Incorrect value from bi->next() at line %d. Expected DONE, got %d", __LINE__, i);
+ errln("%s:%d Incorrect value from bi->next(). Expected DONE, got %d", __FILE__, __LINE__, i);
}
bi->first();
i = bi->current();
if (i != 0) {
- errln("Incorrect value from bi->previous() at line %d. Expected 0, got %d", __LINE__, i);
+ errln("%s:%d Incorrect value from bi->previous(). Expected 0, got %d", __FILE__, __LINE__, i);
}
bi->next();
i = bi->current();
if (i != 1) {
- errln("Incorrect value from bi->previous() at line %d. Expected 1, got %d", __LINE__, i);
+ errln("%s:%d Incorrect value from bi->previous(). Expected 1, got %d", __FILE__, __LINE__, i);
}
bi->last();
bi->next();
i = bi->current();
if (i != 10) {
- errln("Incorrect value from bi->previous() at line %d. Expected 10, got %d", __LINE__, i);
+ errln("%s:%d Incorrect value from bi->previous(). Expected 10, got %d", __FILE__, __LINE__, i);
}
bi->first();
bi->previous();
i = bi->current();
if (i != 0) {
- errln("Incorrect value from bi->previous() at line %d. Expected 0, got %d", __LINE__, i);
+ errln("%s:%d Incorrect value from bi->previous(). Expected 0, got %d", __FILE__, __LINE__, i);
}
//
i = bi->following(4);
if (i != 5) {
- errln("Incorrect value from bi->following() at line %d. Expected 5, got %d", __LINE__, i);
+ errln("%s:%d Incorrect value from bi->following(). Expected 5, got %d", __FILE__, __LINE__, i);
}
i = bi->following(9);
if (i != 10) {
- errln("Incorrect value from bi->following() at line %d. Expected 10, got %d", __LINE__, i);
+ errln("%s:%d Incorrect value from bi->following(). Expected 10, got %d", __FILE__, __LINE__, i);
}
i = bi->following(10);
if (i != BreakIterator::DONE) {
- errln("Incorrect value from bi->following() at line %d. Expected DONE, got %d", __LINE__, i);
+ errln("%s:%d Incorrect value from bi->following(). Expected DONE, got %d", __FILE__, __LINE__, i);
}
//
i = bi->preceding(4);
if (i != 3) {
- errln("Incorrect value from bi->preceding() at line %d. Expected 3, got %d", __LINE__, i);
+ errln("%s:%d Incorrect value from bi->preceding(). Expected 3, got %d", __FILE__, __LINE__, i);
}
i = bi->preceding(10);
if (i != 9) {
- errln("Incorrect value from bi->preceding() at line %d. Expected 9, got %d", __LINE__, i);
+ errln("%s:%d Incorrect value from bi->preceding(). Expected 9, got %d", __FILE__, __LINE__, i);
}
i = bi->preceding(1);
if (i != 0) {
- errln("Incorrect value from bi->preceding() at line %d. Expected 0, got %d", __LINE__, i);
+ errln("%s:%d Incorrect value from bi->preceding(). Expected 0, got %d", __FILE__, __LINE__, i);
}
i = bi->preceding(0);
if (i != BreakIterator::DONE) {
- errln("Incorrect value from bi->preceding() at line %d. Expected DONE, got %d", __LINE__, i);
+ errln("%s:%d Incorrect value from bi->preceding(). Expected DONE, got %d", __FILE__, __LINE__, i);
}
//
bi->first();
if (bi->isBoundary(3) != TRUE) {
- errln("Incorrect value from bi->isBoudary() at line %d. Expected TRUE, got FALSE", __LINE__, i);
+ errln("%s:%d Incorrect value from bi->isBoudary(). Expected TRUE, got FALSE", __FILE__, __LINE__, i);
}
i = bi->current();
if (i != 3) {
- errln("Incorrect value from bi->current() at line %d. Expected 3, got %d", __LINE__, i);
+ errln("%s:%d Incorrect value from bi->current(). Expected 3, got %d", __FILE__, __LINE__, i);
}
if (bi->isBoundary(11) != FALSE) {
- errln("Incorrect value from bi->isBoudary() at line %d. Expected FALSE, got TRUE", __LINE__, i);
+ errln("%s:%d Incorrect value from bi->isBoudary(). Expected FALSE, got TRUE", __FILE__, __LINE__, i);
}
i = bi->current();
if (i != 10) {
- errln("Incorrect value from bi->current() at line %d. Expected 10, got %d", __LINE__, i);
+ errln("%s:%d Incorrect value from bi->current(). Expected 10, got %d", __FILE__, __LINE__, i);
}
//
bi->first();
i = bi->next(4);
if (i != 4) {
- errln("Incorrect value from bi->next() at line %d. Expected 4, got %d", __LINE__, i);
+ errln("%s:%d Incorrect value from bi->next(). Expected 4, got %d", __FILE__, __LINE__, i);
}
i = bi->next(6);
if (i != 10) {
- errln("Incorrect value from bi->next() at line %d. Expected 10, got %d", __LINE__, i);
+ errln("%s:%d Incorrect value from bi->next(). Expected 10, got %d", __FILE__, __LINE__, i);
}
bi->first();
i = bi->next(11);
if (i != BreakIterator::DONE) {
- errln("Incorrect value from bi->next() at line %d. Expected BreakIterator::DONE, got %d", __LINE__, i);
+ errln("%s:%d Incorrect value from bi->next(). Expected BreakIterator::DONE, got %d", __FILE__, __LINE__, i);
}
delete bi;
BreakIterator *bi = BreakIterator::createWordInstance(Locale::getEnglish(), status);
if(U_FAILURE(status)) {
- errcheckln(status, "Fail : in construction - %s", u_errorName(status));
+ errcheckln(status, "%s:%d Fail in construction - %s", __FILE__, __LINE__, u_errorName(status));
} else {
bi->setText(testString1);
// First test that the breaks are in the right spots.
int32_t pos, tag;
for (pos = bi->first(); pos != BreakIterator::DONE; pos = bi->next(), i++) {
if (pos != bounds1[i]) {
- errln("FAIL: unexpected word break at postion %d", pos);
+ errln("%s:%d FAIL: unexpected word break at postion %d", __FILE__, __LINE__, pos);
break;
}
tag = bi->getRuleStatus();
if (tag < tag_lo[i] || tag >= tag_hi[i]) {
- errln("FAIL: incorrect tag value %d at position %d", tag, pos);
+ errln("%s:%d FAIL: incorrect tag value %d at position %d", __FILE__, __LINE__, tag, pos);
break;
}
bi = BreakIterator::createLineInstance(Locale::getEnglish(), status);
if(U_FAILURE(status)) {
- errcheckln(status, "failed to create word break iterator. - %s", u_errorName(status));
+ errcheckln(status, "%s:%d failed to create line break iterator. - %s", __FILE__, __LINE__, u_errorName(status));
} else {
int32_t i = 0;
int32_t pos, tag;
success = FALSE; break;
}
if (success == FALSE) {
- errln("Fail: incorrect word break status or position. i=%d, pos=%d, tag=%d",
- i, pos, tag);
+ errln("%s:%d: incorrect line break status or position. i=%d, pos=%d, tag=%d",
+ __FILE__, __LINE__, i, pos, tag);
break;
}
pos = bi->next();
if (UBRK_LINE_SOFT >= UBRK_LINE_SOFT_LIMIT ||
UBRK_LINE_HARD >= UBRK_LINE_HARD_LIMIT ||
(UBRK_LINE_HARD > UBRK_LINE_SOFT && UBRK_LINE_HARD < UBRK_LINE_SOFT_LIMIT)) {
- errln("UBRK_LINE_* constants from header are inconsistent.");
+ errln("%s:%d UBRK_LINE_* constants from header are inconsistent.", __FILE__, __LINE__);
}
}
delete bi;
#if !UCONFIG_NO_FILE_IO
TESTCASE_AUTO(TestBug4153072);
#endif
- TESTCASE_AUTO(TestStatusReturn);
#if !UCONFIG_NO_FILE_IO
TESTCASE_AUTO(TestUnicodeFiles);
TESTCASE_AUTO(TestEmptyString);
RBBITest::~RBBITest() {
}
-//-----------------------------------------------------------------------------------
-//
-// Test for status {tag} return value from break rules.
-// TODO: a more thorough test.
-//
-//-----------------------------------------------------------------------------------
-void RBBITest::TestStatusReturn() {
- UnicodeString rulesString1("$Letters = [:L:];\n"
- "$Numbers = [:N:];\n"
- "$Letters+{1};\n"
- "$Numbers+{2};\n"
- "Help\\ /me\\!{4};\n"
- "[^$Letters $Numbers];\n"
- "!.*;\n", -1, US_INV);
- UnicodeString testString1 = "abc123..abc Help me Help me!";
- // 01234567890123456789012345678
- int32_t bounds1[] = {0, 3, 6, 7, 8, 11, 12, 16, 17, 19, 20, 25, 27, 28, -1};
- int32_t brkStatus[] = {0, 1, 2, 0, 0, 1, 0, 1, 0, 1, 0, 4, 1, 0, -1};
-
- UErrorCode status=U_ZERO_ERROR;
- UParseError parseError;
-
- LocalPointer <BreakIterator> bi(new RuleBasedBreakIterator(rulesString1, parseError, status));
- if(U_FAILURE(status)) {
- dataerrln("%s:%d error in break iterator construction - %s", __FILE__, __LINE__, u_errorName(status));
- return;
- }
- int32_t pos;
- int32_t i = 0;
- bi->setText(testString1);
- for (pos=bi->first(); pos!= BreakIterator::DONE; pos=bi->next()) {
- if (pos != bounds1[i]) {
- errln("%s:%d expected break at %d, got %d\n", __FILE__, __LINE__, bounds1[i], pos);
- break;
- }
-
- int tag = bi->getRuleStatus();
- if (tag != brkStatus[i]) {
- errln("%s:%d break at %d, expected tag %d, got tag %d\n", __FILE__, __LINE__, pos, brkStatus[i], tag);
- break;
- }
- i++;
- }
-}
-
static void printStringBreaks(UText *tstr, int expected[], int expectedCount) {
UErrorCode status = U_ZERO_ERROR;
UErrorCode status = U_ZERO_ERROR;
Locale locale("");
- UnicodeString rules;
TestParams tp(status);
RegexMatcher localeMatcher(UNICODE_STRING_SIMPLE("<locale *([\\p{L}\\p{Nd}_@&=-]*) *>"), 0, status);
dataerrln("Failure in file %s, line %d, status = \"%s\"", __FILE__, __LINE__, u_errorName(status));
}
-
//
// Open and read the test data file.
//
PARSE_COMMENT,
PARSE_TAG,
PARSE_DATA,
- PARSE_NUM
+ PARSE_NUM,
+ PARSE_RULES
}
parseState = PARSE_TAG;
int32_t column = 0;
int32_t charIdx = 0;
- int32_t tagValue = 0; // The numeric value of a <nnn> tag.
+ int32_t tagValue = 0; // The numeric value of a <nnn> tag.
+
+ UnicodeString rules; // Holds rules from a <rules> ... </rules> block
+ int32_t rulesFirstLine; // Line number of the start of current <rules> block
for (charIdx = 0; charIdx < len; ) {
status = U_ZERO_ERROR;
break;
}
+ if (testString.compare(charIdx-1, 7, "<rules>") == 0 ||
+ testString.compare(charIdx-1, 10, "<badrules>") == 0) {
+ /// charIdx += 6;
+ charIdx = testString.indexOf(0x3e, charIdx) + 1; // 0x3e == '>'
+ parseState = PARSE_RULES;
+ rules.remove();
+ rulesFirstLine = lineNum;
+ break;
+ }
+
// <locale loc_name>
localeMatcher.reset(testString);
if (localeMatcher.lookingAt(charIdx-1, status)) {
}
break;
+ case PARSE_RULES:
+ if (testString.compare(charIdx-1, 8, "</rules>") == 0) {
+ charIdx += 7;
+ parseState = PARSE_TAG;
+ delete tp.bi;
+ UParseError pe;
+ tp.bi = new RuleBasedBreakIterator(rules, pe, status);
+ skipTest = U_FAILURE(status);
+ if (U_FAILURE(status)) {
+ errln("file rbbitst.txt: %d - Error %s creating break iterator from rules.",
+ rulesFirstLine + pe.line - 1, u_errorName(status));
+ }
+ break;
+ }
+ if (testString.compare(charIdx-1, 11, "</badrules>") == 0) {
+ charIdx += 10;
+ parseState = PARSE_TAG;
+ UErrorCode ec = U_ZERO_ERROR;
+ UParseError pe;
+ RuleBasedBreakIterator bi(rules, pe, ec);
+ if (U_SUCCESS(ec)) {
+ errln("file rbbitst.txt: %d - Expected, but did not get, a failure creating break iterator from rules.",
+ rulesFirstLine + pe.line - 1);
+ }
+ break;
+ }
+ rules.append(c);
+ break;
+
case PARSE_DATA:
if (c == u'•') {
int32_t breakIdx = tp.dataToBreak.length();
-
if (testString.compare(charIdx-1, 2, "<>") == 0) {
charIdx++;
int32_t breakIdx = tp.dataToBreak.length();
if (U_FAILURE(status)) {
- dataerrln("ICU Error %s while parsing test file at line %d.",
+ errln("ICU Error %s while parsing test file at line %d.",
u_errorName(status), lineNum);
status = U_ZERO_ERROR;
goto end_test; // Stop the test
}
+ // Reached end of test file. Raise an error if parseState indicates that we are
+ // within a block that should have been terminated.
+
+ if (parseState == PARSE_RULES) {
+ errln("rbbitst.txt:%d <rules> block beginning at line %d is not closed.",
+ lineNum, rulesFirstLine);
+ }
+ if (parseState == PARSE_DATA) {
+ errln("rbbitst.txt:%d <data> block not closed.", lineNum);
+ }
+
+
end_test:
delete [] testFile;
#endif
for (i = bi->first(); i != BreakIterator::DONE; i = bi->next()) {
forward[count] = i;
if (count < expectedcount && expected[count] != i) {
- test->errln("break forward test failed: expected %d but got %d",
- expected[count], i);
+ test->errln("%s:%d break forward test failed: expected %d but got %d",
+ __FILE__, __LINE__, expected[count], i);
break;
}
count ++;
}
if (count != expectedcount) {
printStringBreaks(ustr, expected, expectedcount);
- test->errln("break forward test failed: missed %d match",
- expectedcount - count);
+ test->errln("%s:%d break forward test failed: missed %d match",
+ __FILE__, __LINE__, expectedcount - count);
return;
}
// testing boundaries
int j = expected[i - 1];
if (!bi->isBoundary(j)) {
printStringBreaks(ustr, expected, expectedcount);
- test->errln("isBoundary() failed. Expected boundary at position %d", j);
+ test->errln("%s:%d isBoundary() failed. Expected boundary at position %d",
+ __FILE__, __LINE__, j);
return;
}
for (j = expected[i - 1] + 1; j < expected[i]; j ++) {
if (bi->isBoundary(j)) {
printStringBreaks(ustr, expected, expectedcount);
- test->errln("isBoundary() failed. Not expecting boundary at position %d", j);
+ test->errln("%s:%d isBoundary() failed. Not expecting boundary at position %d",
+ __FILE__, __LINE__, j);
return;
}
}
count --;
if (forward[count] != i) {
printStringBreaks(ustr, expected, expectedcount);
- test->errln("happy break test previous() failed: expected %d but got %d",
- forward[count], i);
+ test->errln("%s:%d happy break test previous() failed: expected %d but got %d",
+ __FILE__, __LINE__, forward[count], i);
break;
}
}
// int j = expected[i] + 1;
int j = ustr.moveIndex32(expected[i], 1);
for (; j <= expected[i + 1]; j ++) {
- if (bi->preceding(j) != expected[i]) {
+ int32_t expectedPreceding = expected[i];
+ int32_t actualPreceding = bi->preceding(j);
+ if (actualPreceding != expectedPreceding) {
printStringBreaks(ustr, expected, expectedcount);
- test->errln("preceding(): Not expecting boundary at position %d", j);
+ test->errln("%s:%d preceding(%d): expected %d, got %d",
+ __FILE__, __LINE__, j, expectedPreceding, actualPreceding);
return;
}
}
Locale locale("en");
UErrorCode status = U_ZERO_ERROR;
// BreakIterator *bi = BreakIterator::createCharacterInstance(locale, status);
- BreakIterator *bi = BreakIterator::createWordInstance(locale, status);
+ LocalPointer<BreakIterator> bi(BreakIterator::createWordInstance(locale, status), status);
+ if (U_FAILURE(status)) {
+ errcheckln(status, "%s:%d Creation of break iterator failed %s",
+ __FILE__, __LINE__, u_errorName(status));
+ return;
+ }
UChar str[50];
static const char *strlist[] =
{
"\\u003b\\u0027\\u00b7\\u47a3",
};
int loop;
- if (U_FAILURE(status)) {
- errcheckln(status, "Creation of break iterator failed %s", u_errorName(status));
- return;
- }
for (loop = 0; loop < UPRV_LENGTHOF(strlist); loop ++) {
- // printf("looping %d\n", loop);
- u_unescape(strlist[loop], str, 20);
+ u_unescape(strlist[loop], str, UPRV_LENGTHOF(str));
UnicodeString ustr(str);
int forward[50];
int count = 0;
bi->setText(ustr);
- int prev = 0;
- int i;
- for (i = bi->first(); i != BreakIterator::DONE; i = bi->next()) {
- forward[count ++] = i;
- if (i > prev) {
- int j;
- for (j = prev + 1; j < i; j ++) {
- if (bi->isBoundary(j)) {
- printStringBreaks(ustr, forward, count);
- errln("happy boundary test failed: expected %d not a boundary",
- j);
- return;
- }
+ int prev = -1;
+ for (int32_t boundary = bi->first(); boundary != BreakIterator::DONE; boundary = bi->next()) {
+ ++count;
+ if (count >= UPRV_LENGTHOF(forward)) {
+ errln("%s:%d too many breaks found. (loop, count, boundary) = (%d, %d, %d)",
+ __FILE__, __LINE__, loop, count, boundary);
+ return;
+ }
+ forward[count] = boundary;
+ if (boundary <= prev) {
+ errln("%s:%d bi::next() did not advance. (loop, prev, boundary) = (%d, %d, %d)\n",
+ __FILE__, __LINE__, loop, prev, boundary);
+ break;
+ }
+ for (int32_t nonBoundary = prev + 1; nonBoundary < boundary; nonBoundary ++) {
+ if (bi->isBoundary(nonBoundary)) {
+ printStringBreaks(ustr, forward, count);
+ errln("%s:%d isBoundary(nonBoundary) failed. (loop, prev, nonBoundary, boundary) = (%d, %d, %d, %d)",
+ __FILE__, __LINE__, loop, prev, nonBoundary, boundary);
+ return;
}
}
- if (!bi->isBoundary(i)) {
+ if (!bi->isBoundary(boundary)) {
printStringBreaks(ustr, forward, count);
- errln("happy boundary test failed: expected %d a boundary",
- i);
+ errln("%s:%d happy boundary test failed: expected %d a boundary",
+ __FILE__, __LINE__, boundary);
return;
}
- prev = i;
+ prev = boundary;
}
}
- delete bi;
}
void RBBITest::TestLineBreaks(void)
void runIndexedTest( int32_t index, UBool exec, const char* &name, char* par = NULL );
- /**
- * Tests rule status return values
- **/
- void TestStatusReturn();
-
void TestEmptyString();
void TestGetAvailableLocales();
void TestGetDisplayName();
# <sent> any following data is for sentence break testing
# <line> any following data is for line break testing
# <char> any following data is for char break testing
-# <locale local_name> Switch to the named locale at the next occurence of <word>, <sent>, etc.
+# <rules> rules ... </rules> following data is tested against these rules.
+# Applies until a following occurence of <word>, <sent>, etc. or another <rules>
+# <locale locale_name> Switch to the named locale at the next occurence of <word>, <sent>, etc.
# <data> ... </data> test data. May span multiple lines.
# <> Break position, status == 0
# • Break position, status == 0 (Bullet, \u2022)
# Temp debugging tests
<locale en>
<word>
-<data><0>１•２•３•４•</data>
-# <data><0>ク<400>ライアン<400>トサーバー<400></data>
+<data><0>コンピューター<400>は<400>、<0>本質<400>的<400>に<400>は<400>数字<400>しか<400>扱う<400>こと<400>が<400>でき<400>ま<400>せん<400>。<0>\
+コンピューター<400>は<400>、<0>文字<400>や<400>記号<400>など<400>の<400>それぞれに<400>番号<400>を<400>割り振る<400>こと<400>によって<400>扱える<400>\
+よう<400>にし<400>ます<400>。<0>ユニ<400>コード<400>が<400>出来る<400>まで<400>は<400>、<0>これらの<400>番号<400>を<400>割り振る<400>仕組み<400>が<400>\
+何<400>百<400>種類<400>も<400>存在<400>しま<400>した<400>。<0>どの<400>一つ<400>を<400>とっても<400>、<0>十分<400>な<400>文字<400>を<400>含<400>\
+んで<400>は<400>いま<400>せん<400>で<400>した<400>。<0>例えば<400>、<0>欧州<400>連合<400>一つ<400>を<400>見<400>て<400>も<400>、<0>その<400>\
+すべて<400>の<400>言語<400>を<400>カバー<400>する<400>ため<400>に<400>は<400>、<0>いくつか<400>の<400>異なる<400>符号<400>化<400>の<400>仕組み<400>\
+が<400>必要<400>で<400>した<400>。<0>英語<400>の<400>よう<400>な<400>一つ<400>の<400>言語<400>に<400>限<400>って<400>も<400>、<0>一つ<400>だけ<400>\
+の<400>符号<400>化<400>の<400>仕組み<400>では<400>、<0>一般<400>的<400>に<400>使<400>われる<400>すべて<400>の<400>文字<400>、<0>句読点<400>、<0>\
+。<0></data>
+
+#<data><0>コンピューター<400>は<400>、<0>本質<400>的<400>に<400>は<400>数字<400>しか<400>扱う<400>こと<400>が<400>でき<400>ま<400>せん<400>。<0>\
## FILTERED BREAK TESTS
<data>•\U0001F468\u200D\u2695\uFE0F•\U0001F468\u200D\u2695•\U0001F468\U0001F3FD\u200D\u2695\uFE0F•\U0001F468\U0001F3FD\u200D\u2695\u0020•</data>
# woman astronaut, woman astronaut / fitz4
<data>•\U0001F469\u200D\U0001F680•\U0001F469\U0001F3FD\u200D\U0001F680\u0020•</data>
+
+
+####################################################################################
+#
+# Test rule status values
+#
+####################################################################################
+<rules> $Letters = [:L:];
+ $Numbers = [:N:];
+ $Letters+{1};
+ $Numbers+{2};
+ Help\ me\!{4};
+ [^$Letters $Numbers];
+ !.*;
+</rules>
+<data>•abc<1>123<2>.•.•abc<1> •Help<1> •me<1> •Help me!<4></data>
+
+# Test option to prohibit unquoted literals.
+
+<rules>
+!!forward;
+ Hello\ World;
+!!reverse;
+ .*;
+</rules>
+<data>•Hello World•</data>
+
+<badrules>
+!!quoted_literals_only;
+!!forward;
+ Hello\ World;
+!!reverse;
+ .*;
+</badrules>
+
+<rules>
+#TODO: uncomment this line when quoted_literals_only is implemented.
+#!!quoted_literals_only;
+!!forward;
+ 'Hello World';
+!!reverse;
+ .*;
+</rules>
+<data>•Hello World•</data>
+
projects / icu / commitdiff