-rw-r--r-- | qmake/tools/qregexp.cpp | 70 |
1 files changed, 39 insertions, 31 deletions
diff --git a/qmake/tools/qregexp.cpp b/qmake/tools/qregexp.cpp index 500efed..0c1f060 100644 --- a/qmake/tools/qregexp.cpp +++ b/qmake/tools/qregexp.cpp @@ -264,13 +264,13 @@ \i This matches any character (including newline). \row \i <b>\\d</b> - \i This matches a digit (see QChar::isDigit()). + \i This matches a digit (QChar::isDigit()). \row \i <b>\\D</b> \i This matches a non-digit. \row \i <b>\\s</b> - \i This matches a whitespace (see QChar::isSpace()). + \i This matches a whitespace (QChar::isSpace()). \row \i <b>\\S</b> \i This matches a non-whitespace. \row \i <b>\\w</b> - \i This matches a word character (see QChar::isLetterOrNumber()). + \i This matches a word character (QChar::isLetterOrNumber() or '_'). \row \i <b>\\W</b> \i This matches a non-word character. @@ -548,5 +548,12 @@ Perl's extended \c{/x} syntax is not supported, nor are - regexp comments (?#comment) or directives, e.g. (?i). + directives, e.g. (?i), or regexp comments, e.g. (?#comment). On + the other hand, C++'s rules for literal strings can be used to + achieve the same: + \code + QRegExp mark( "\\b" // word boundary + "[Mm]ark" // the word we want to match + ); + \endcode Both zero-width positive and zero-width negative lookahead @@ -678,9 +685,9 @@ \code - QRegExp rx( "*.html" ); // invalid regexp: * doesn't quantify anything - rx.setWildcard( TRUE ); // now it's a valid wildcard regexp - rx.search( "index.html" ); // returns 0 (matched at position 0) - rx.search( "default.htm" ); // returns -1 (no match) - rx.search( "readme.txt" ); // returns -1 (no match) + QRegExp rx( "*.html" ); // invalid regexp: * doesn't quantify anything + rx.setWildcard( TRUE ); // now it's a valid wildcard regexp + rx.exactMatch( "index.html" ); // returns TRUE + rx.exactMatch( "default.htm" ); // returns FALSE + rx.exactMatch( "readme.txt" ); // returns FALSE \endcode @@ -716,4 +723,9 @@ const int InftyRep = 1025; const int EOS = -1; +static bool isWord( QChar ch ) +{ + return ch.isLetterOrNumber() || ch == QChar( '_' ); +} + /* Merges two QMemArrays of ints and puts the result into the first one. @@ -1681,7 +1693,7 @@ bool QRegExpEngine::testAnchor( int i, int a, const int *capBegin ) bool after = FALSE; if ( mmPos + i != 0 ) - before = mmIn[mmPos + i - 1].isLetterOrNumber(); + before = isWord( mmIn[mmPos + i - 1] ); if ( mmPos + i != mmLen ) - after = mmIn[mmPos + i].isLetterOrNumber(); + after = isWord( mmIn[mmPos + i] ); if ( (a & Anchor_Word) != 0 && (before == after) ) return FALSE; @@ -2633,5 +2645,12 @@ int QRegExpEngine::getEscape() case 'W': // see QChar::isLetterOrNumber() - yyCharClass->addCategories( 0x7ff07f8f ); + yyCharClass->addCategories( 0x7fe07f8f ); + yyCharClass->addRange( 0x203f, 0x2040 ); + yyCharClass->addSingleton( 0x2040 ); + yyCharClass->addSingleton( 0x30fb ); + yyCharClass->addRange( 0xfe33, 0xfe34 ); + yyCharClass->addRange( 0xfe4d, 0xfe4f ); + yyCharClass->addSingleton( 0xff3f ); + yyCharClass->addSingleton( 0xff65 ); return Tok_CharClass; #endif @@ -2653,4 +2672,5 @@ int QRegExpEngine::getEscape() // see QChar::isLetterOrNumber() yyCharClass->addCategories( 0x000f8070 ); + yyCharClass->addSingleton( 0x005f ); // '_' return Tok_CharClass; #endif @@ -3184,5 +3204,6 @@ static QRegExpEngine *newEngine( const QString& pattern, bool caseSensitive ) if ( engineCache != 0 ) { #ifdef QT_THREAD_SUPPORT - QMutexLocker locker( qt_global_mutexpool->get( &engineCache ) ); + QMutexLocker locker( qt_global_mutexpool ? + qt_global_mutexpool->get( &engineCache ) : 0 ); #endif QRegExpEngine *eng = engineCache->take( pattern ); @@ -3200,9 +3221,10 @@ static QRegExpEngine *newEngine( const QString& pattern, bool caseSensitive ) static void derefEngine( QRegExpEngine *eng, const QString& pattern ) { - if ( eng != 0 && eng->deref() ) { -#ifndef QT_NO_REGEXP_OPTIM #ifdef QT_THREAD_SUPPORT - QMutexLocker locker( qt_global_mutexpool->get( &engineCache ) ); + QMutexLocker locker( qt_global_mutexpool ? + qt_global_mutexpool->get( &engineCache ) : 0 ); #endif + if ( eng != 0 && eng->deref() ) { +#ifndef QT_NO_REGEXP_OPTIM if ( engineCache == 0 ) { engineCache = new QCache<QRegExpEngine>; @@ -3566,11 +3588,4 @@ int QRegExp::match( const QString& str, int index, int *len, #endif // QT_NO_COMPAT -/*! - \overload - - This convenience function searches with a \c CaretMode of \c - CaretAtZero which is the most common usage. -*/ - int QRegExp::search( const QString& str, int offset ) const { @@ -3626,11 +3641,4 @@ int QRegExp::search( const QString& str, int offset, CaretMode caretMode ) const -/*! - \overload - - This convenience function searches with a \c CaretMode of \c - CaretAtZero which is the most common usage. -*/ - int QRegExp::searchRev( const QString& str, int offset ) const { @@ -3695,5 +3703,5 @@ int QRegExp::matchedLength() const #ifndef QT_NO_REGEXP_CAPTURE -/*! +/*! Returns the number of captures contained in the regular expression. */ |