source: trunk/tools/assistant/lib/qhelpsearchindexreader_default.cpp@ 109

/****************************************************************************
**
** Copyright (C) 2009 Nokia Corporation and/or its subsidiary(-ies).
** Contact: Qt Software Information ([email protected])
**
** This file is part of the Qt Assistant of the Qt Toolkit.
**
** $QT_BEGIN_LICENSE:LGPL$
** Commercial Usage
** Licensees holding valid Qt Commercial licenses may use this file in
** accordance with the Qt Commercial License Agreement provided with the
** Software or, alternatively, in accordance with the terms contained in
** a written agreement between you and Nokia.
**
** GNU Lesser General Public License Usage
** Alternatively, this file may be used under the terms of the GNU Lesser
** General Public License version 2.1 as published by the Free Software
** Foundation and appearing in the file LICENSE.LGPL included in the
** packaging of this file.  Please review the following information to
** ensure the GNU Lesser General Public License version 2.1 requirements
** will be met: http://www.gnu.org/licenses/old-licenses/lgpl-2.1.html.
**
** In addition, as a special exception, Nokia gives you certain
** additional rights. These rights are described in the Nokia Qt LGPL
** Exception version 1.0, included in the file LGPL_EXCEPTION.txt in this
** package.
**
** GNU General Public License Usage
** Alternatively, this file may be used under the terms of the GNU
** General Public License version 3.0 as published by the Free Software
** Foundation and appearing in the file LICENSE.GPL included in the
** packaging of this file.  Please review the following information to
** ensure the GNU General Public License version 3.0 requirements will be
** met: http://www.gnu.org/copyleft/gpl.html.
**
** If you are unsure which license is appropriate for your use, please
** contact the sales department at [email protected].
** $QT_END_LICENSE$
**
****************************************************************************/

#include "qhelpenginecore.h"
#include "qhelpsearchindexreader_default_p.h"

#include <QtCore/QDir>
#include <QtCore/QUrl>
#include <QtCore/QFile>
#include <QtCore/QVariant>
#include <QtCore/QFileInfo>
#include <QtCore/QDataStream>
#include <QtCore/QTextStream>

QT_BEGIN_NAMESPACE

namespace qt {
    namespace fulltextsearch {
        namespace std {

namespace {
    QStringList split( const QString &str )
    {
        QStringList lst;
        int j = 0;
        int i = str.indexOf(QLatin1Char('*'), j );

        if (str.startsWith(QLatin1String("*")))
            lst << QLatin1String("*");

        while ( i != -1 ) {
            if ( i > j && i <= (int)str.length() ) {
                lst << str.mid( j, i - j );
                lst << QLatin1String("*");
            }
            j = i + 1;
            i = str.indexOf(QLatin1Char('*'), j );
        }

        int l = str.length() - 1;
        if ( str.mid( j, l - j + 1 ).length() > 0 )
            lst << str.mid( j, l - j + 1 );

        return lst;
    }
}


Reader::Reader()
    : indexPath(QString())
    , indexFile(QString())
    , documentFile(QString())
{
    termList.clear();
    indexTable.clear();
    searchIndexTable.clear();
}

Reader::~Reader()
{
    reset();
    searchIndexTable.clear();
}

bool Reader::readIndex()
{
    if (indexTable.contains(indexFile))
        return true;

    QFile idxFile(indexFile);
    if (!idxFile.open(QFile::ReadOnly))
        return false;

    QString key;
    int numOfDocs;
    EntryTable entryTable;
    QVector<Document> docs;
    QDataStream dictStream(&idxFile);
    while (!dictStream.atEnd()) {
        dictStream >> key;
        dictStream >> numOfDocs;
        docs.resize(numOfDocs);
        dictStream >> docs;
        entryTable.insert(key, new Entry(docs));
    }
    idxFile.close();

    if (entryTable.isEmpty())
        return false;

    QFile docFile(documentFile);
    if (!docFile.open(QFile::ReadOnly))
        return false;

    QString title, url;
    DocumentList documentList;
    QDataStream docStream(&docFile);
    while (!docStream.atEnd()) {
        docStream >> title;
        docStream >> url;
        documentList.append(QStringList(title) << url);
    }
    docFile.close();

    if (documentList.isEmpty()) {
        cleanupIndex(entryTable);
        return false;
    }

    indexTable.insert(indexFile, Index(entryTable, documentList));
    return true;
}

bool Reader::initCheck() const
{
    return !searchIndexTable.isEmpty();
}

void Reader::setIndexPath(const QString &path)
{
    indexPath = path;
}

void Reader::filterFilesForAttributes(const QStringList &attributes)
{
    searchIndexTable.clear();
    for(IndexTable::ConstIterator it = indexTable.begin(); it != indexTable.end(); ++it) {
        const QString fileName = it.key();
        bool containsAll = true;
        QStringList split = fileName.split(QLatin1String("@"));
        foreach (const QString attribute, attributes) {
            if (!split.contains(attribute, Qt::CaseInsensitive)) {
                containsAll = false;
                break;
            }
        }

        if (containsAll)
            searchIndexTable.insert(fileName, it.value());
    }
}

void Reader::setIndexFile(const QString &namespaceName, const QString &attributes)
{
    QString extention = namespaceName + QLatin1String("@") + attributes;
    indexFile = indexPath + QLatin1String("/indexdb40.") + extention;
    documentFile = indexPath + QLatin1String("/indexdoc40.") + extention;
}

bool Reader::splitSearchTerm(const QString &searchTerm, QStringList *terms,
                                  QStringList *termSeq, QStringList *seqWords)
{
    QString term = searchTerm;

    term = term.simplified();
    term = term.replace(QLatin1String("\'"), QLatin1String("\""));
    term = term.replace(QLatin1String("`"), QLatin1String("\""));
    term = term.replace(QLatin1String("-"), QLatin1String(" "));
    term = term.replace(QRegExp(QLatin1String("\\s[\\S]?\\s")), QLatin1String(" "));

    *terms = term.split(QLatin1Char(' '));
    QStringList::iterator it = terms->begin();
    for (; it != terms->end(); ++it) {
        (*it) = (*it).simplified();
        (*it) = (*it).toLower();
        (*it) = (*it).replace(QLatin1String("\""), QLatin1String(""));
    }

    if (term.contains(QLatin1Char('\"'))) {
        if ((term.count(QLatin1Char('\"')))%2 == 0) {
            int beg = 0;
            int end = 0;
            QString s;
            beg = term.indexOf(QLatin1Char('\"'), beg);
            while (beg != -1) {
                beg++;
                end = term.indexOf(QLatin1Char('\"'), beg);
                s = term.mid(beg, end - beg);
                s = s.toLower();
                s = s.simplified();
                if (s.contains(QLatin1Char('*'))) {
                    qWarning("Full Text Search, using a wildcard within phrases is not allowed.");
                    return false;
                }
                *seqWords += s.split(QLatin1Char(' '));
                *termSeq << s;
                beg = term.indexOf(QLatin1Char('\"'), end + 1);
            }
        } else {
            qWarning("Full Text Search, the closing quotation mark is missing.");
            return false;
        }
    }

    return true;
}

void Reader::searchInIndex(const QStringList &terms)
{
    foreach (const QString term, terms) {
        QVector<Document> documents;

        for(IndexTable::ConstIterator it = searchIndexTable.begin();
            it != searchIndexTable.end(); ++it) {
            EntryTable entryTable = it.value().first;
            DocumentList documentList = it.value().second;

            if (term.contains(QLatin1Char('*')))
                documents = setupDummyTerm(getWildcardTerms(term, entryTable), entryTable);
            else if (entryTable.value(term))
                documents = entryTable.value(term)->documents;
            else
                continue;

            if (!documents.isEmpty()) {
                DocumentInfo info;
                QString title, url;
                QVector<DocumentInfo> documentsInfo;
                foreach(const Document doc, documents) {
                    info.docNumber = doc.docNumber;