File indexing completed on 2024-10-06 04:31:46

 /* This file is part of the KDE project
 
    Copyright (C) 2008 Javier Goday <jgoday @ gmail.com>
    First Url regular expression taken from urlview tool by Michael Elkins <me@cs.hmc.edu>.
    Regular expression improved by FiNex.
    Improvements to regular expression and slotReadFile by Frantisek Ziacik
 
    This program is free software; you can redistribute it and/or
    modify it under the terms of the GNU General Public
    License as published by the Free Software Foundation; either
    version 2 of the License, or (at your option) any later version.
 */
 #include "linkimporter.h"
 
 #include <QDebug>
 #include <QDir>
 #include <QFile>
 #include <QIODevice>
 #include <QMap>
 #include <QRegularExpression>
 #include <QTextStream>
 
 #include <KIO/CopyJob>
 #include <KLocalizedString>
 #include <qregularexpression.h>
 
 // static QString REGULAR_EXPRESSION = "(((https?|ftp|gopher)://|(mailto|file|news):)[^’ <>\"]+|(www|web|w3).[-a-z0-9.]+)[^’ .,;<>\":]";
 //  static QString REGULAR_EXPRESSION = "((http|https|ftp|ftps)+([\\:\\w\\d:#@%/;$()~_?\\+-=\\\\.&])*)";
 static QString REGULAR_EXPRESSION =
     "(\\w+[:]//"
     ")?(((([\\w-]+[.]){1,}(ac|ad|ae|af|ag|ai|al|am|an|ao|aq|ar|as|at|au|aw|az|ba|bb|bd|be|bf|bg|bh|bi|bj|bm|bn|bo|br|bs|bt|bv|bw|by|bz|ca|cc|cd|cf|cg|ch|ci|ck|"
     "cl|cm|cn|co|com|cr|cs|cu|cv|cx|cy|cz|de|dj|dk|dm|do|dz|ec|edu|ee|eg|eh|er|es|et|eu|fi|fj|fk|fm|fo|fr|ga|gd|ge|gf|gg|gh|gi|gl|gm|gn|gov|gp|gq|gr|gs|gt|gu|"
     "gw|gy|hk|hm|hn|hr|ht|hu|id|ie|il|im|in|int|io|iq|ir|is|it|je|jm|jo|jp|ke|kg|kh|ki|km|kn|kp|kr|kw|ky|kz|la|lb|lc|li|lk|lr|ls|lt|lu|lv|ly|ma|mc|md|mg|mh|"
     "mil|mk|ml|mm|mn|mo|mp|mq|mr|ms|mt|mu|mv|mw|mx|my|mz|na|nc|ne|net|nf|ng|ni|nl|no|np|nr|nt|nu|nz|om|org|pa|pe|pf|pg|ph|pk|pl|pm|pn|pr|ps|pt|pw|py|qa|re|ro|"
     "ru|rw|sa|sb|sc|sd|se|sg|sh|si|sj|sk|sl|sm|sn|so|sr|sv|st|sy|sz|tc|td|tf|tg|th|tj|tk|tm|tn|to|tp|tr|tt|tv|tw|tz|ua|ug|uk|um|us|uy|uz|va|vc|ve|vg|vi|vn|vu|"
     "wf|ws|ye|yt|yu|za|zm|zw|aero|biz|coop|info|museum|name|pro|travel))|([0-9]+[.][0-9]+[.][0-9]+[.][0-9]+)))([:][0-9]*)?([?/][\\w~#\\-;%?@&=/.+]*)?(?!\\w)";
 
 LinkImporter::LinkImporter(const QUrl &url, QObject *parent)
     : QThread(parent)
     , m_url(url)
     , m_transfers()
     , m_tempFile()
 {
 }
 
 LinkImporter::LinkImporter(QObject *parent)
     : QThread(parent)
     , m_url()
     , m_transfers()
     , m_tempFile()
 {
 }
 
 LinkImporter::~LinkImporter()
 {
 }
 
 void LinkImporter::checkClipboard(const QString &clipboardContent)
 {
     static QRegularExpression rx(REGULAR_EXPRESSION);
 
     int regexPos = 1;
 
     QRegularExpressionMatch match = rx.match(clipboardContent);
 
     auto link = match.captured(regexPos);
     while (!link.isEmpty()) {
         addTransfer(link);
         regexPos++;
         link = match.captured(regexPos);
     }
 }
 
 void LinkImporter::run()
 {
     if (!m_url.isLocalFile() && !m_tempFile.isEmpty()) {
         slotReadFile(QUrl(m_tempFile));
     } else {
         slotReadFile(m_url);
     }
 
     quit();
 }
 
 void LinkImporter::copyRemoteFile()
 {
     m_tempFile = QString("%1/%2.tmp").arg(QDir::tempPath()).arg("importer_aux");
 
     QUrl aux(m_tempFile);
     KIO::CopyJob *job = KIO::copy(m_url, aux, KIO::HideProgressInfo);
 
     if (!job->exec()) {
         Q_EMIT error(ki18n("Error trying to get %1").subs(m_url.url()));
     }
 }
 
 void LinkImporter::slotReadFile(const QUrl &url)
 {
     static QRegularExpression rx(REGULAR_EXPRESSION);
     QFile file(url.toLocalFile());
 
     if (!file.open(QIODevice::ReadOnly | QIODevice::Text))
         return;
 
     QTextStream in(&file);
     quint64 size = file.size();
     quint64 position = 0;
 
     while (!in.atEnd()) {
         QString line = in.readLine();
         int regexPos = 0;
         quint64 lastPosition = position;
 
         auto match = rx.match(line);
 
         while (match.hasMatch()) {
             QString link = match.captured(0);
 
             addTransfer(link);
 
             regexPos += match.capturedLength(0);
             position = lastPosition + regexPos;
 
             Q_EMIT progress(position * 100 / size);
 
             match = rx.match(line, regexPos);
         }
 
         position += line.size();
 
         Q_EMIT progress(position * 100 / size);
     }
 
     if (!m_url.isLocalFile()) {
         file.remove();
     }
 }
 
 void LinkImporter::addTransfer(QString &link)
 {
     QUrl auxUrl;
 
     if (link.contains("://")) {
         auxUrl = QUrl(link);
     } else {
         auxUrl = QUrl(QString("http://") + link);
     }
 
     if (!link.isEmpty() && auxUrl.isValid() && m_transfers.indexOf(link) < 0 && !auxUrl.scheme().isEmpty() && !auxUrl.host().isEmpty()) {
         m_transfers << link;
     }
 }
 
 #include "moc_linkimporter.cpp"