| -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 @@ -250,41 +250,41 @@ \row \i <b>\\n</b> \i This matches the ASCII line feed character (LF, 0x0A, Unix newline). \row \i <b>\\r</b> \i This matches the ASCII carriage return character (CR, 0x0D). \row \i <b>\\t</b> \i This matches the ASCII horizontal tab character (HT, 0x09). \row \i <b>\\v</b> \i This matches the ASCII vertical tab character (VT, 0x0B). \row \i <b>\\xhhhh</b> \i This matches the Unicode character corresponding to the hexadecimal number hhhh (between 0x0000 and 0xFFFF). \0ooo (i.e., \zero ooo) matches the ASCII/Latin-1 character corresponding to the octal number ooo (between 0 and 0377). \row \i <b>. (dot)</b> \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. \row \i <b>\\n</b> \i The n-th \link #capturing-text backreference \endlink, e.g. \1, \2, etc. \endtable \e {Note that the C++ compiler transforms backslashes in strings so to include a <b>\\</b> in a regexp you will need to enter it twice, i.e. <b>\\\\</b>.} \target sets-of-characters \section1 Sets of Characters Square brackets are used to match any character in the set of characters contained within the square brackets. All the character @@ -534,33 +534,40 @@ does not have an equivalent to Perl's \c{/m} option, but this can be emulated in various ways for example by splitting the input into lines or by looping with a regexp that searches for newlines. Because QRegExp is string oriented there are no \A, \Z or \z assertions. The \G assertion is not supported but can be emulated in a loop. Perl's $& is cap(0) or capturedTexts()[0]. There are no QRegExp equivalents for $`, $' or $+. Perl's capturing variables, $1, $2, ... correspond to cap(1) or capturedTexts()[1], cap(2) or capturedTexts()[2], etc. To substitute a pattern use QString::replace(). 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 assertions (?=pattern) and (?!pattern) are supported with the same syntax as Perl. Perl's lookbehind assertions, "independent" subexpressions and conditional expressions are not supported. Non-capturing parentheses are also supported, with the same (?:pattern) syntax. See QStringList::split() and QStringList::join() for equivalents to Perl's split and join functions. Note: because C++ transforms \\'s they must be written \e twice in code, e.g. <b>\\b</b> must be written <b>\\\\b</b>. \target code-examples @@ -664,37 +671,37 @@ address and country. Unfortunately the regexp is rather long and not very versatile -- the code will break if we add any more fields. A simpler and better solution is to look for the separator, '\t' in this case, and take the surrounding text. The QStringList split() function can take a separator string or regexp as an argument and split a string accordingly. \code QStringList field = QStringList::split( "\t", str ); \endcode Here field[0] is the company, field[1] the web address and so on. To imitate the matching of a shell we can use wildcard mode. \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 Wildcard matching can be convenient because of its simplicity, but any wildcard regexp can be defined using full regexps, e.g. <b>.*\.html$</b>. Notice that we can't match both \c .html and \c .htm files with a wildcard unless we use <b>*.htm*</b> which will also match 'test.html.bak'. A full regexp gives us the precision we need, <b>.*\\.html?$</b>. QRegExp can match case insensitively using setCaseSensitive(), and can use non-greedy matching, see setMinimal(). By default QRegExp uses full regexps but this can be changed with setWildcard(). Searching can be forward with search() or backward with searchRev(). Captured text can be accessed using capturedTexts() which returns a string list of all captured strings, or using cap() which returns the captured string for the given index. The @@ -702,32 +709,37 @@ string where the match was made (or -1 if there was no match). \sa QRegExpValidator QString QStringList \target member-function-documentation */ const int NumBadChars = 64; #define BadChar( ch ) ( (ch).unicode() % NumBadChars ) const int NoOccurrence = INT_MAX; const int EmptyCapture = INT_MAX; const int InftyLen = INT_MAX; 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. */ static void mergeInto( QMemArray<int> *a, const QMemArray<int>& b ) { int asize = a->size(); int bsize = b.size(); if ( asize == 0 ) { *a = b.copy(); #ifndef QT_NO_REGEXP_OPTIM } else if ( bsize == 1 && (*a)[asize - 1] < b[0] ) { a->resize( asize + 1 ); (*a)[asize] = b[0]; #endif } else if ( bsize >= 1 ) { int csize = asize + bsize; @@ -1667,35 +1679,35 @@ bool QRegExpEngine::testAnchor( int i, int a, const int *capBegin ) } #endif if ( (a & Anchor_Caret) != 0 ) { if ( mmPos + i != mmCaretPos ) return FALSE; } if ( (a & Anchor_Dollar) != 0 ) { if ( mmPos + i != mmLen ) return FALSE; } #ifndef QT_NO_REGEXP_ESCAPE if ( (a & (Anchor_Word | Anchor_NonWord)) != 0 ) { bool before = FALSE; 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; if ( (a & Anchor_NonWord) != 0 && (before != after) ) return FALSE; } #endif #ifndef QT_NO_REGEXP_LOOKAHEAD bool catchx = TRUE; if ( (a & Anchor_LookaheadMask) != 0 ) { QConstString cstr = QConstString( (QChar *) mmIn + mmPos + i, mmLen - mmPos - i ); for ( j = 0; j < (int) ahead.size(); j++ ) { if ( (a & (Anchor_FirstLookahead << j)) != 0 ) { catchx = ahead[j]->eng->match( cstr.string(), 0, TRUE, TRUE, mmCaretPos - mmPos - i )[0] == 0; @@ -2619,52 +2631,60 @@ int QRegExpEngine::getEscape() return Tok_NonWord; #endif #ifndef QT_NO_REGEXP_CCLASS case 'D': // see QChar::isDigit() yyCharClass->addCategories( 0x7fffffef ); return Tok_CharClass; case 'S': // see QChar::isSpace() yyCharClass->addCategories( 0x7ffff87f ); yyCharClass->addRange( 0x0000, 0x0008 ); yyCharClass->addRange( 0x000e, 0x001f ); yyCharClass->addRange( 0x007f, 0x009f ); return Tok_CharClass; 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 #ifndef QT_NO_REGEXP_ESCAPE case 'b': return Tok_Word; #endif #ifndef QT_NO_REGEXP_CCLASS case 'd': // see QChar::isDigit() yyCharClass->addCategories( 0x00000010 ); return Tok_CharClass; case 's': // see QChar::isSpace() yyCharClass->addCategories( 0x00000380 ); yyCharClass->addRange( 0x0009, 0x000d ); return Tok_CharClass; case 'w': // see QChar::isLetterOrNumber() yyCharClass->addCategories( 0x000f8070 ); + yyCharClass->addSingleton( 0x005f ); // '_' return Tok_CharClass; #endif #ifndef QT_NO_REGEXP_ESCAPE case 'x': val = 0; for ( i = 0; i < 4; i++ ) { low = QChar( yyCh ).lower(); if ( low >= '0' && low <= '9' ) val = ( val << 4 ) | ( low - '0' ); else if ( low >= 'a' && low <= 'f' ) val = ( val << 4 ) | ( low - 'a' + 10 ); else break; yyCh = getChar(); } return Tok_Char | val; @@ -3170,53 +3190,55 @@ struct QRegExpPrivate #endif QMemArray<int> captured; // what QRegExpEngine::search() returned last QRegExpPrivate() { captured.fill( -1, 2 ); } }; #ifndef QT_NO_REGEXP_OPTIM static QCache<QRegExpEngine> *engineCache = 0; static QSingleCleanupHandler<QCache<QRegExpEngine> > cleanup_cache; #endif static QRegExpEngine *newEngine( const QString& pattern, bool caseSensitive ) { #ifndef QT_NO_REGEXP_OPTIM 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 ); if ( eng == 0 || eng->caseSensitive() != caseSensitive ) { delete eng; } else { eng->ref(); return eng; } } #endif return new QRegExpEngine( pattern, 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>; engineCache->setAutoDelete( TRUE ); cleanup_cache.set( &engineCache ); } if ( !pattern.isNull() && engineCache->insert(pattern, eng, 4 + pattern.length() / 4) ) return; #else Q_UNUSED( pattern ); #endif delete eng; } } /*! @@ -3552,39 +3574,32 @@ bool QRegExp::exactMatch( const QString& str ) const regexp, if present. Otherwise, position 0 in \a str will match. Use search() and matchedLength() instead of this function. \sa QString::mid() QConstString */ int QRegExp::match( const QString& str, int index, int *len, bool indexIsStart ) const { int pos = search( str, index, indexIsStart ? CaretAtOffset : CaretAtZero ); if ( len != 0 ) *len = matchedLength(); return pos; } #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 { return search( str, offset, CaretAtZero ); } /*! Attempts to find a match in \a str from position \a offset (0 by default). If \a offset is -1, the search starts at the last character; if -2, at the next to last character; etc. Returns the position of the first match, or -1 if there was no match. The \a caretMode parameter can be used to instruct whether <b>^</b> should match at index 0 or at \a offset. @@ -3612,39 +3627,32 @@ int QRegExp::search( const QString& str, int offset ) const */ int QRegExp::search( const QString& str, int offset, CaretMode caretMode ) const { if ( offset < 0 ) offset += str.length(); #ifndef QT_NO_REGEXP_CAPTURE priv->t = str; priv->capturedCache.clear(); #endif priv->captured = eng->match( str, offset, priv->min, FALSE, caretIndex(offset, caretMode) ); return priv->captured[0]; } -/*! - \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 { return searchRev( str, offset, CaretAtZero ); } /*! Attempts to find a match backwards in \a str from position \a offset. If \a offset is -1 (the default), the search starts at the last character; if -2, at the next to last character; etc. Returns the position of the first match, or -1 if there was no match. The \a caretMode parameter can be used to instruct whether <b>^</b> should match at index 0 or at \a offset. @@ -3681,33 +3689,33 @@ int QRegExp::searchRev( const QString& str, int offset, } return -1; } /*! Returns the length of the last matched string, or -1 if there was no match. \sa exactMatch() search() searchRev() */ int QRegExp::matchedLength() const { return priv->captured[1]; } #ifndef QT_NO_REGEXP_CAPTURE -/*! +/*! Returns the number of captures contained in the regular expression. */ int QRegExp::numCaptures() const { return eng->numCaptures(); } /*! Returns a list of the captured text strings. The first string in the list is the entire matched string. Each subsequent list element contains a string that matched a (capturing) subexpression of the regexp. |