1 /****************************************************************************
3 ** Copyright (C) 2012 Nokia Corporation and/or its subsidiary(-ies).
4 ** Contact: http://www.qt-project.org/
6 ** This file is part of the QtXmlPatterns module of the Qt Toolkit.
8 ** $QT_BEGIN_LICENSE:LGPL$
9 ** GNU Lesser General Public License Usage
10 ** This file may be used under the terms of the GNU Lesser General Public
11 ** License version 2.1 as published by the Free Software Foundation and
12 ** appearing in the file LICENSE.LGPL included in the packaging of this
13 ** file. Please review the following information to ensure the GNU Lesser
14 ** General Public License version 2.1 requirements will be met:
15 ** http://www.gnu.org/licenses/old-licenses/lgpl-2.1.html.
17 ** In addition, as a special exception, Nokia gives you certain additional
18 ** rights. These rights are described in the Nokia Qt LGPL Exception
19 ** version 1.1, included in the file LGPL_EXCEPTION.txt in this package.
21 ** GNU General Public License Usage
22 ** Alternatively, this file may be used under the terms of the GNU General
23 ** Public License version 3.0 as published by the Free Software Foundation
24 ** and appearing in the file LICENSE.GPL included in the packaging of this
25 ** file. Please review the following information to ensure the GNU General
26 ** Public License version 3.0 requirements will be met:
27 ** http://www.gnu.org/copyleft/gpl.html.
30 ** Alternatively, this file may be used in accordance with the terms and
31 ** conditions contained in a signed written agreement between you and Nokia.
40 ****************************************************************************/
44 #include "qpatternistlocale_p.h"
46 #include "qpatternplatform_p.h"
50 using namespace QPatternist;
55 * @short Used internally by PatternPlatform and describes
56 * a flag that affects how a pattern is treated.
58 * The member variables aren't declared @c const, in order
59 * to make the synthesized assignment operator and copy constructor work.
61 * @ingroup Patternist_utils
62 * @author Frans Englich <frans.englich@nokia.com>
67 typedef QMap<QChar, PatternFlag> Hash;
69 inline PatternFlag() : flag(PatternPlatform::NoFlags)
73 inline PatternFlag(const PatternPlatform::Flag opt,
74 const QString &descr) : flag(opt),
79 PatternPlatform::Flag flag;
82 static inline Hash flagDescriptions();
86 static inline PatternFlag::Hash flagDescriptions()
88 PatternFlag::Hash retval;
90 retval.insert(QChar(QLatin1Char('s')),
91 PatternFlag(PatternPlatform::DotAllMode,
92 QtXmlPatterns::tr("%1 matches newline characters").arg(formatKeyword(QLatin1Char('.')))));
94 retval.insert(QChar(QLatin1Char('m')),
95 PatternFlag(PatternPlatform::MultiLineMode,
96 QtXmlPatterns::tr("%1 and %2 match the start and end of a line.")
97 .arg(formatKeyword(QLatin1Char('^')))
98 .arg(formatKeyword(QLatin1Char('$')))));
100 retval.insert(QChar(QLatin1Char('i')),
101 PatternFlag(PatternPlatform::CaseInsensitive,
102 QtXmlPatterns::tr("Matches are case insensitive")));
104 retval.insert(QChar(QLatin1Char('x')),
105 PatternFlag(PatternPlatform::SimplifyWhitespace,
106 QtXmlPatterns::tr("Whitespace characters are removed, except when they appear "
107 "in character classes")));
112 PatternPlatform::PatternPlatform(const qint8 flagsPosition) : m_compiledParts(NoPart),
114 m_flagsPosition(flagsPosition)
118 const QRegExp PatternPlatform::pattern(const DynamicContext::Ptr &context) const
120 if(m_compiledParts == FlagsAndPattern) /* This is the most common case. */
122 Q_ASSERT(m_pattern.isValid());
126 QRegExp retvalPattern;
129 /* Compile the flags, if necessary. */
130 if(m_compiledParts.testFlag(FlagsPrecompiled))
134 const Expression::Ptr flagsOp(m_operands.value(m_flagsPosition));
137 flags = parseFlags(flagsOp->evaluateSingleton(context).stringValue(), context);
142 /* Compile the pattern, if necessary. */
143 if(m_compiledParts.testFlag(PatternPrecompiled))
144 retvalPattern = m_pattern;
147 retvalPattern = parsePattern(m_operands.at(1)->evaluateSingleton(context).stringValue(),
152 applyFlags(flags, retvalPattern);
154 Q_ASSERT(m_pattern.isValid());
155 return retvalPattern;
158 void PatternPlatform::applyFlags(const Flags flags, QRegExp &patternP)
160 Q_ASSERT(patternP.isValid());
164 if(flags & CaseInsensitive)
166 patternP.setCaseSensitivity(Qt::CaseInsensitive);
168 // TODO Apply the other flags, like 'x'.
171 QRegExp PatternPlatform::parsePattern(const QString &pattern,
172 const ReportContext::Ptr &context) const
174 return parsePattern(pattern, context, this);
177 QRegExp PatternPlatform::parsePattern(const QString &patternP,
178 const ReportContext::Ptr &context,
179 const SourceLocationReflection *const location)
181 if(patternP == QLatin1String("(.)\\3") ||
182 patternP == QLatin1String("\\3") ||
183 patternP == QLatin1String("(.)\\2"))
185 context->error(QLatin1String("We don't want to hang infinitely on K2-MatchesFunc-9, "
187 ReportContext::FOER0000, location);
191 QString rewrittenPattern(patternP);
193 /* We rewrite some well known patterns to QRegExp style here. Note that
194 * these character classes only works in the ASCII range, and fail for
195 * others. This support needs to be in QRegExp, since it's about checking
196 * QChar::category(). */
197 rewrittenPattern.replace(QLatin1String("[\\i-[:]]"), QLatin1String("[a-zA-Z_]"));
198 rewrittenPattern.replace(QLatin1String("[\\c-[:]]"), QLatin1String("[a-zA-Z0-9_\\-\\.]"));
200 QRegExp retval(rewrittenPattern, Qt::CaseSensitive, QRegExp::W3CXmlSchema11);
206 context->error(QtXmlPatterns::tr("%1 is an invalid regular expression pattern: %2")
207 .arg(formatExpression(patternP), retval.errorString()),
208 ReportContext::FORX0002, location);
213 PatternPlatform::Flags PatternPlatform::parseFlags(const QString &flags,
214 const DynamicContext::Ptr &context) const
220 const PatternFlag::Hash flagDescrs(flagDescriptions());
221 const int len = flags.length();
222 Flags retval = NoFlags;
224 for(int i = 0; i < len; ++i)
226 const QChar flag(flags.at(i));
227 const Flag specified = flagDescrs.value(flag).flag;
229 if(specified != NoFlags)
235 /* Generate a nice error message. */
236 QString message(QtXmlPatterns::tr("%1 is an invalid flag for regular expressions. Valid flags are:")
237 .arg(formatKeyword(flag)));
239 /* This is formatting, so don't bother translators with it. */
240 message.append(QLatin1Char('\n'));
242 const PatternFlag::Hash::const_iterator end(flagDescrs.constEnd());
243 PatternFlag::Hash::const_iterator it(flagDescrs.constBegin());
247 // TODO handle bidi correctly
248 // TODO format this with rich text(list/table)
249 message.append(formatKeyword(it.key()));
250 message.append(QLatin1String(" - "));
251 message.append(it.value().description);
255 message.append(QLatin1Char('\n'));
258 context->error(message, ReportContext::FORX0001, this);
265 Expression::Ptr PatternPlatform::compress(const StaticContext::Ptr &context)
267 const Expression::Ptr me(FunctionCall::compress(context));
271 if(m_operands.at(1)->is(IDStringValue))
273 const DynamicContext::Ptr dynContext(context->dynamicContext());
275 m_pattern = parsePattern(m_operands.at(1)->evaluateSingleton(dynContext).stringValue(),
277 m_compiledParts |= PatternPrecompiled;
280 const Expression::Ptr flagOperand(m_operands.value(m_flagsPosition));
285 m_compiledParts |= FlagsPrecompiled;
287 else if(flagOperand->is(IDStringValue))
289 const DynamicContext::Ptr dynContext(context->dynamicContext());
290 m_flags = parseFlags(flagOperand->evaluateSingleton(dynContext).stringValue(),
292 m_compiledParts |= FlagsPrecompiled;
295 if(m_compiledParts == FlagsAndPattern)
296 applyFlags(m_flags, m_pattern);