TEST(Pattern_RegexPattern, Match)
{
RegexPattern const pattern { ".*adblock.*"_r };
auto const& uri = "http://adblock.org"_u;
EXPECT_TRUE(pattern.match(uri));
}
static jint Matcher_openImpl(JNIEnv* env, jclass, jint patternAddr) {
RegexPattern* pattern = reinterpret_cast<RegexPattern*>(static_cast<uintptr_t>(patternAddr));
UErrorCode status = U_ZERO_ERROR;
RegexMatcher* result = pattern->matcher(status);
maybeThrowIcuException(env, status);
return static_cast<jint>(reinterpret_cast<uintptr_t>(result));
}
U_CFUNC int32_t
getText(const UChar* source, int32_t srcLen,
UChar** dest, int32_t destCapacity,
UnicodeString patternString,
UErrorCode* status){
if(status == NULL || U_FAILURE(*status)){
return 0;
}
UnicodeString stringArray[MAX_SPLIT_STRINGS];
RegexPattern *pattern = RegexPattern::compile(UnicodeString("@"), 0, *status);
UnicodeString src (source,srcLen);
if (U_FAILURE(*status)) {
return 0;
}
pattern->split(src, stringArray, MAX_SPLIT_STRINGS, *status);
RegexMatcher matcher(patternString, UREGEX_DOTALL, *status);
if (U_FAILURE(*status)) {
return 0;
}
for(int32_t i=0; i<MAX_SPLIT_STRINGS; i++){
matcher.reset(stringArray[i]);
if(matcher.lookingAt(*status)){
UnicodeString out = matcher.group(1, *status);
return out.extract(*dest, destCapacity,*status);
}
}
return 0;
}
TEST(Pattern_RegexPattern, MatchWithDifferentCase2)
{
RegexPattern const pattern { ".*AdBlock.*"_r };
auto const& uri = "http://adblock.org"_u;
EXPECT_TRUE(pattern.match(uri));
}
U_CFUNC int32_t
getCount(const UChar* source, int32_t srcLen,
UParseCommentsOption option, UErrorCode *status){
if(status == NULL || U_FAILURE(*status)){
return 0;
}
UnicodeString stringArray[MAX_SPLIT_STRINGS];
RegexPattern *pattern = RegexPattern::compile("@", UREGEX_MULTILINE, *status);
UnicodeString src (source, srcLen);
if (U_FAILURE(*status)) {
return 0;
}
int32_t retLen = pattern->split(src, stringArray, MAX_SPLIT_STRINGS, *status);
RegexMatcher matcher(patternStrings[option], UREGEX_DOTALL, *status);
if (U_FAILURE(*status)) {
return 0;
}
int32_t count = 0;
for(int32_t i=0; i<retLen; i++){
matcher.reset(stringArray[i]);
if(matcher.lookingAt(*status)){
count++;
}
}
if(option == UPC_TRANSLATE && count > 1){
fprintf(stderr, "Multiple @translate tags cannot be supported.\n");
exit(U_UNSUPPORTED_ERROR);
}
return count;
}
TEST(Pattern_RegexPattern, CaseSensitiveMatch)
{
RegexPattern const pattern { ".*AdBlock.*"_r };
auto const& uri1 = "http://AdBlock.org"_u;
auto const& uri2 = "http://adblock.org"_u;
EXPECT_TRUE(pattern.match(uri1, true));
EXPECT_TRUE(pattern.match(uri2, false));
}
//---------------------------------------------------------------------
//
// matches Convenience function to test for a match, starting
// with a pattern string and a data string.
//
//---------------------------------------------------------------------
UBool U_EXPORT2 RegexPattern::matches(const UnicodeString ®ex,
const UnicodeString &input,
UParseError &pe,
UErrorCode &status) {
if (U_FAILURE(status)) {return FALSE;}
UBool retVal;
RegexPattern *pat = NULL;
RegexMatcher *matcher = NULL;
pat = RegexPattern::compile(regex, 0, pe, status);
matcher = pat->matcher(input, status);
retVal = matcher->matches(status);
delete matcher;
delete pat;
return retVal;
}
//
// matches, UText mode
//
UBool U_EXPORT2 RegexPattern::matches(UText *regex,
UText *input,
UParseError &pe,
UErrorCode &status) {
if (U_FAILURE(status)) {return FALSE;}
UBool retVal;
RegexPattern *pat = NULL;
RegexMatcher *matcher = NULL;
pat = RegexPattern::compile(regex, 0, pe, status);
matcher = pat->matcher(input, PATTERN_IS_UTEXT, status);
retVal = matcher->matches(status);
delete matcher;
delete pat;
return retVal;
}
U_CFUNC int32_t
getAt(const UChar* source, int32_t srcLen,
UChar** dest, int32_t destCapacity,
int32_t index,
UParseCommentsOption option,
UErrorCode* status){
if(status == NULL || U_FAILURE(*status)){
return 0;
}
UnicodeString stringArray[MAX_SPLIT_STRINGS];
RegexPattern *pattern = RegexPattern::compile(UnicodeString("@"), UREGEX_MULTILINE, *status);
UnicodeString src (source, srcLen);
if (U_FAILURE(*status)) {
return 0;
}
int32_t retLen = pattern->split(src, stringArray, MAX_SPLIT_STRINGS, *status);
UnicodeString patternString(patternStrings[option]);
RegexMatcher matcher(patternString, UREGEX_DOTALL, *status);
if (U_FAILURE(*status)) {
return 0;
}
int32_t count = 0;
for(int32_t i=0; i<retLen; i++){
matcher.reset(stringArray[i]);
if(matcher.lookingAt(*status)){
if(count == index){
UnicodeString out = matcher.group(1, *status);
return out.extract(*dest, destCapacity,*status);
}
count++;
}
}
return 0;
}
//
// matches, UText mode
//
UBool U_EXPORT2 RegexPattern::matches(UText *regex,
UText *input,
UParseError &pe,
UErrorCode &status) {
if (U_FAILURE(status)) {return FALSE;}
UBool retVal = FALSE;
RegexPattern *pat = NULL;
RegexMatcher *matcher = NULL;
pat = RegexPattern::compile(regex, 0, pe, status);
matcher = pat->matcher(status);
if (U_SUCCESS(status)) {
matcher->reset(input);
retVal = matcher->matches(status);
}
delete matcher;
delete pat;
return retVal;
}
U_CFUNC int32_t
getDescription( const UChar* source, int32_t srcLen,
UChar** dest, int32_t destCapacity,
UErrorCode* status){
if(status == NULL || U_FAILURE(*status)){
return 0;
}
UnicodeString stringArray[MAX_SPLIT_STRINGS];
RegexPattern *pattern = RegexPattern::compile(UnicodeString("@"), UREGEX_MULTILINE, *status);
UnicodeString src(source, srcLen);
if (U_FAILURE(*status)) {
return 0;
}
pattern->split(src, stringArray,MAX_SPLIT_STRINGS , *status);
if(stringArray[0].indexOf((UChar)AT_SIGN)==-1){
int32_t destLen = stringArray[0].extract(*dest, destCapacity, *status);
return trim(*dest, destLen, status);
}
return 0;
}
//------------------------------------------------------------------------------------------
//
// main for ugrep
//
// Structurally, all use of the ICU Regular Expression API is in main(),
// and all of the supporting stuff necessary to make a running program, but
// not directly related to regular expressions, is factored out into these other
// functions.
//
//------------------------------------------------------------------------------------------
int main(int argc, const char** argv) {
UBool matchFound = FALSE;
//
// Process the commmand line options.
//
processOptions(argc, argv);
//
// Create a RegexPattern object from the user supplied pattern string.
//
UErrorCode status = U_ZERO_ERROR; // All ICU operations report success or failure
// in a status variable.
UParseError parseErr; // In the event of a syntax error in the regex pattern,
// this struct will contain the position of the
// error.
RegexPattern *rePat = RegexPattern::compile(pattern, parseErr, status);
// Note that C++ is doing an automatic conversion
// of the (char *) pattern to a temporary
// UnicodeString object.
if (U_FAILURE(status)) {
fprintf(stderr, "ugrep: error in pattern: \"%s\" at position %d\n",
u_errorName(status), parseErr.offset);
exit(-1);
}
//
// Create a RegexMatcher from the newly created pattern.
//
UnicodeString empty;
RegexMatcher *matcher = rePat->matcher(empty, status);
if (U_FAILURE(status)) {
fprintf(stderr, "ugrep: error in creating RegexMatcher: \"%s\"\n",
u_errorName(status));
exit(-1);
}
//
// Loop, processing each of the input files.
//
for (int fileNum=firstFileNum; fileNum < argc; fileNum++) {
readFile(argv[fileNum]);
//
// Loop through the lines of a file, trying to match the regex pattern on each.
//
for (nextLine(0); lineStart<fileLen; nextLine(lineEnd)) {
UnicodeString s(FALSE, ucharBuf+lineStart, lineEnd-lineStart);
matcher->reset(s);
if (matcher->find()) {
matchFound = TRUE;
printMatch();
}
}
}
//
// Clean up
//
delete matcher;
delete rePat;
free(ucharBuf);
free(charBuf);
ucnv_close(outConverter);
u_cleanup(); // shut down ICU, release any cached data it owns.
return matchFound? 0: 1;
}
static PyObject *t_regexmatcher_pattern(t_regexmatcher *self)
{
const RegexPattern pattern = self->object->pattern();
return wrap_RegexPattern(pattern.clone(), T_OWNED);
}
