/****************************************************************************

**

** All rights reserved.

** Contact: Nokia Corporation (qt-info@nokia.com)

**

** This file is part of the test suite of the Qt Toolkit.

**

** $QT_BEGIN_LICENSE:LGPL$

** No Commercial Usage

** This file contains pre-release code and may not be distributed.

** You may use this file in accordance with the terms and conditions

** contained in the Technology Preview License Agreement accompanying

** this package.

**

** 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 1.1, included in the file LGPL_EXCEPTION.txt in this package.

**

** If you have questions regarding the use of this file, please contact

** Nokia at qt-info@nokia.com.

**

**

**

**

**

**

**

**

** $QT_END_LICENSE$

**

****************************************************************************/

#include <QtTest/QtTest>

#include <qtextcodec.h>

#include <qfile.h>

#include <qtextdocument.h>

#include <time.h>

#include <qprocess.h>

#ifdef Q_OS_SYMBIAN

#define SRCDIR ""

#endif

class tst_QTextCodec : public QObject

{

    Q_OBJECT

private slots:

    void toUnicode_data();

    void toUnicode();

    void codecForName_data();

    void codecForName();

    void fromUnicode_data();

    void fromUnicode();

    void toUnicode_codecForHtml();

    void toUnicode_incremental();

    void codecForLocale();

    void asciiToIscii() const;

    void flagCodepointFFFF() const;

    void flagF7808080() const;

    void flagEFBFBF() const;

    void decode0D() const;

    void codecForIndex() const;

    void aliasForUTF16() const;

    void mibForTSCII() const;

    void utf8Codec_data();

    void utf8Codec();

    void utf8bom_data();

    void utf8bom();

    void utfHeaders_data();

    void utfHeaders();

    void codecForHtml();

    void codecForUtfText_data();

    void codecForUtfText();

#ifdef Q_OS_UNIX

    void toLocal8Bit();

#endif

};

void tst_QTextCodec::toUnicode_data()

{

    QTest::addColumn<QString>("fileName");

    QTest::addColumn<QString>("codecName");

    QTest::newRow( "korean-eucKR" ) << SRCDIR "korean.txt" << "eucKR";

    QTest::newRow( "UTF-8" ) << SRCDIR "utf8.txt" << "UTF-8";

}

void tst_QTextCodec::toUnicode()

{

    QFETCH( QString, fileName );

    QFETCH( QString, codecName );

    QFile file( fileName );

    if ( file.open( QIODevice::ReadOnly ) ) {

        QByteArray ba = file.readAll();

        QTextCodec *c = QTextCodec::codecForName( codecName.toLatin1() );

        QVERIFY(c != 0);

        QString uniString = c->toUnicode( ba );

        if (codecName == QLatin1String("UTF-8")) {

            QCOMPARE(uniString, QString::fromUtf8(ba));

            QCOMPARE(ba, uniString.toUtf8());

        }

        QCOMPARE( ba, c->fromUnicode( uniString ) );

        if (codecName == QLatin1String("eucKR")) {

            char ch = '\0';

            QVERIFY(c->toUnicode(&ch, 1).isEmpty());

            QVERIFY(c->toUnicode(&ch, 1).isNull());

        }

    } else {

        QFAIL(qPrintable("File could not be opened: " + file.errorString()));

    }

}

void tst_QTextCodec::codecForName_data()

{

    QTest::addColumn<QString>("hint");

    QTest::addColumn<QString>("actualCodecName");

    QTest::newRow("data1") << "iso88591" << "ISO-8859-1";

    QTest::newRow("data2") << "iso88592" << "ISO-8859-2";

    QTest::newRow("data3") << " IsO(8)8/5*9-2 " << "ISO-8859-2";

    QTest::newRow("data4") << " IsO(8)8/5*2-9 " << "";

    QTest::newRow("data5") << "latin2" << "ISO-8859-2";

}

void tst_QTextCodec::codecForName()

{

    QFETCH(QString, hint);

    QFETCH(QString, actualCodecName);

    QTextCodec *codec = QTextCodec::codecForName(hint.toLatin1());

    if (actualCodecName.isEmpty()) {

        QVERIFY(codec == 0);

    } else {

        QVERIFY(codec != 0);

        QCOMPARE(QString(codec->name()), actualCodecName);

    }

}

void tst_QTextCodec::fromUnicode_data()

{

    QTest::addColumn<QString>("codecName");

    QTest::addColumn<bool>("eightBit");

    QTest::newRow("data1") << "ISO-8859-1" << true;

    QTest::newRow("data2") << "ISO-8859-2" << true;

    QTest::newRow("data3") << "ISO-8859-3" << true;

    QTest::newRow("data4") << "ISO-8859-4" << true;

    QTest::newRow("data5") << "ISO-8859-5" << true;

    QTest::newRow("data6") << "ISO-8859-6" << true;

    QTest::newRow("data7") << "ISO-8859-7" << true;

    QTest::newRow("data8") << "ISO-8859-8" << true;

    QTest::newRow("data9") << "ISO-8859-9" << true;

    QTest::newRow("data10") << "ISO-8859-10" << true;

    QTest::newRow("data13") << "ISO-8859-13" << true;

    QTest::newRow("data14") << "ISO-8859-14" << true;

    QTest::newRow("data15") << "ISO-8859-15" << true;

    QTest::newRow("data16") << "ISO-8859-16" << true;

    QTest::newRow("data18") << "IBM850" << true;

    QTest::newRow("data19") << "IBM874" << true;

    QTest::newRow("data20") << "IBM866" << true;

    QTest::newRow("data21") << "windows-1250" << true;

    QTest::newRow("data22") << "windows-1251" << true;

    QTest::newRow("data23") << "windows-1252" << true;

    QTest::newRow("data24") << "windows-1253" << true;

    QTest::newRow("data25") << "windows-1254" << true;

    QTest::newRow("data26") << "windows-1255" << true;

    QTest::newRow("data27") << "windows-1256" << true;

    QTest::newRow("data28") << "windows-1257" << true;

    QTest::newRow("data28") << "windows-1258" << true;

    QTest::newRow("data29") << "Apple Roman" << true;

    QTest::newRow("data29") << "WINSAMI2" << true;

    QTest::newRow("data30") << "TIS-620" << true;

    QTest::newRow("data31") << "roman8" << true;

    QTest::newRow("data32") << "SJIS" << false;

    QTest::newRow("data33") << "EUC-KR" << false;

}

void tst_QTextCodec::fromUnicode()

{

    QFETCH(QString, codecName);

    QFETCH(bool, eightBit);

    QTextCodec *codec = QTextCodec::codecForName(codecName.toLatin1());

    QVERIFY(codec != 0);

    // Check if the reverse lookup is what we expect

    if (eightBit) {

        char chars[128];

        for (int i = 0; i < 128; ++i)

            chars[i] = i + 128;

        QString s = codec->toUnicode(chars, 128);

        QByteArray c = codec->fromUnicode(s);

        int numberOfQuestionMarks = 0;

        for (int i = 0; i < 128; ++i) {

            if (c.at(i) == '?')

                ++numberOfQuestionMarks;

            else

                QCOMPARE(c.at(i), char(i + 128));

        }

        QVERIFY(numberOfQuestionMarks != 128);

    }

    /*

        If the encoding is a superset of ASCII, test that the byte

        array is correct (no off by one, no trailing '\0').

    */

    QByteArray result = codec->fromUnicode(QString("abc"));

    if (result.startsWith("a")) {

        QCOMPARE(result.size(), 3);

        QCOMPARE(result, QByteArray("abc"));

    } else {

        QVERIFY(true);

    }

}

void tst_QTextCodec::toUnicode_codecForHtml()

{

    QFile file(QString(SRCDIR "QT4-crashtest.txt"));

    QVERIFY(file.open(QFile::ReadOnly));

    QByteArray data = file.readAll();

    QTextCodec *codec = Qt::codecForHtml(data);

    codec->toUnicode(data); // this line crashes

}

void tst_QTextCodec::toUnicode_incremental()

{

    QByteArray ba;

    ba += char(0xf0);

    ba += char(0x90);

    ba += char(0x80);

    ba += char(0x80);

    ba += char(0xf4);

    ba += char(0x8f);

    ba += char(0xbf);

    ba += char(0xbd);

    QString expected = QString::fromUtf8(ba);

    QString incremental;

    QTextDecoder *utf8Decoder = QTextCodec::codecForMib(106)->makeDecoder();

    QString actual;

    for (int i = 0; i < ba.size(); ++i)

        utf8Decoder->toUnicode(&actual, ba.constData() + i, 1);

    QCOMPARE(actual, expected);

    delete utf8Decoder;

}

void tst_QTextCodec::codecForLocale()

{

    QTextCodec *codec = QTextCodec::codecForLocale();

    QVERIFY(codec != 0);

#if defined(Q_OS_UNIX)

    // get a time string that is locale-encoded

    QByteArray originalLocaleEncodedTimeString;

    originalLocaleEncodedTimeString.resize(1024);

    time_t t;

    time(&t);

    int r = strftime(originalLocaleEncodedTimeString.data(),

                     originalLocaleEncodedTimeString.size(),

                     "%A%a%B%b%Z",

                     localtime(&t));

    if (r == 0)

        QSKIP("strftime() failed", SkipAll);

    originalLocaleEncodedTimeString.resize(r);

    QString unicodeTimeString = codec->toUnicode(originalLocaleEncodedTimeString);

    QByteArray localeEncodedTimeString = codec->fromUnicode(unicodeTimeString);

    QCOMPARE(localeEncodedTimeString, originalLocaleEncodedTimeString);

#else

    QSKIP("This test is not implemented on Windows", SkipAll);

#endif

    // find a codec that is not the codecForLocale()

    QTextCodec *codec2 = 0;

    foreach (int mib, QTextCodec::availableMibs()) {

        if (mib != codec->mibEnum()) {

            codec2 = QTextCodec::codecForMib(mib);

            if (codec2)

                break;

        }

    }

    if (!codec2) {

        QSKIP("Could not find a codec that is not already the codecForLocale()", SkipAll);

    }

    // set it, codecForLocale() should return it now

    QTextCodec::setCodecForLocale(codec2);

    QCOMPARE(QTextCodec::codecForLocale(), codec2);

    // reset back to the default

    QTextCodec::setCodecForLocale(0);

    QCOMPARE(QTextCodec::codecForLocale(), codec);

}

void tst_QTextCodec::asciiToIscii() const

{

    /* Add all low, 7-bit ASCII characters. */

    QString ascii;

    const int len = 0xA0 - 1;

    ascii.resize(len);

    for(int i = 0; i < len; ++i)

        ascii[i] = QChar(i + 1);

    static const char *const isciiCodecs[] =

    {

        "Iscii-Mlm",

        "Iscii-Knd",

        "Iscii-Tlg",

        "Iscii-Tml",

        "Iscii-Ori",

        "Iscii-Gjr",

        "Iscii-Pnj",

        "Iscii-Bng",

        "Iscii-Dev"

    };

    const int isciiCodecsLen = sizeof(isciiCodecs) / sizeof(const char *);

    for(int i = 0; i < isciiCodecsLen; ++i) {

        /* For each codec. */

        const QTextCodec *const textCodec = QTextCodec::codecForName(isciiCodecs[i]);

        Q_ASSERT(textCodec);

        for(int i2 = 0; i2 < len; ++i2) {

            /* For each character in ascii. */

            const QChar c(ascii[i2]);

            QVERIFY2(textCodec->canEncode(c), qPrintable(QString::fromLatin1("Failed to encode %1 with encoding %2")

                                                         .arg(QString::number(c.unicode()), QString::fromLatin1(textCodec->name().constData()))));

        }

        QVERIFY2(textCodec->canEncode(ascii), qPrintable(QString::fromLatin1("Failed for full string with encoding %1")

                                                         .arg(QString::fromLatin1(textCodec->name().constData()))));

    }

}

void tst_QTextCodec::flagCodepointFFFF() const

{

    // This is an invalid Unicode codepoint.

    const QChar ch(0xFFFF);

    QString input(ch);

    QTextCodec *const codec = QTextCodec::codecForMib(106); // UTF-8

    Q_ASSERT(codec);

    const QByteArray asDecoded(codec->fromUnicode(input));

    QTextCodec::ConverterState state(QTextCodec::ConvertInvalidToNull);

    QVERIFY(codec->toUnicode(asDecoded.constData(), asDecoded.length(), &state) == QChar(0));

    QVERIFY(codec->toUnicode(asDecoded) == QChar(0xfffd));

}

void tst_QTextCodec::flagF7808080() const

{

    /* This test case stems from test not-wf-sa-170, tests/qxmlstream/XML-Test-Suite/xmlconf/xmltest/not-wf/sa/166.xml,

     * whose description reads:

     *

     * "Four byte UTF-8 encodings can encode UCS-4 characters

     *  which are beyond the range of legal XML characters

     *  (and can't be expressed in Unicode surrogate pairs).

     *  This document holds such a character."

     *

     *  In binary, this is:

     *  11110111100000001000000010000000

     *  *       *       *       *

     *  11110www10xxxxxx10yyyyyy10zzzzzz

     *

     *  With multibyte logic removed it is the codepoint 0x1C0000.

     */

    QByteArray input;

    input.resize(4);

    input[0] = char(0xF7);

    input[1] = char(0x80);

    input[2] = char(0x80);

    input[3] = char(0x80);

    QTextCodec *const codec = QTextCodec::codecForMib(106); // UTF-8

    Q_ASSERT(codec);

    //QVERIFY(!codec->canEncode(QChar(0x1C0000)));

    QTextCodec::ConverterState state(QTextCodec::ConvertInvalidToNull);

    QVERIFY(codec->toUnicode(input.constData(), input.length(), &state) == QChar(0));

}

void tst_QTextCodec::flagEFBFBF() const

{

    QByteArray invalidInput;

    invalidInput.resize(3);

    invalidInput[0] = char(0xEF);

    invalidInput[1] = char(0xBF);

    invalidInput[2] = char(0xBF);

    const QTextCodec *const codec = QTextCodec::codecForMib(106); // UTF-8

    Q_ASSERT(codec);

    {

        //QVERIFY(!codec->canEncode(QChar(0xFFFF)));

        QTextCodec::ConverterState state(QTextCodec::ConvertInvalidToNull);

        QVERIFY(codec->toUnicode(invalidInput.constData(), invalidInput.length(), &state) == QChar(0));

        QByteArray start("<?pi ");

        start.append(invalidInput);

        start.append("?>");

    }

    /* When 0xEFBFBF is preceeded by what seems to be an arbitrary character,

     * QTextCodec fails to flag it. */

    {

        QEXPECT_FAIL("", "This is a bug and needs to be fixed.", Continue);

        QByteArray start("B");

        start.append(invalidInput);

        QTextCodec::ConverterState state(QTextCodec::ConvertInvalidToNull);

        QVERIFY(codec->toUnicode(start.constData(), start.length(), &state) == QChar(0));

    }

}

void tst_QTextCodec::decode0D() const

{

    QByteArray input;

    input.resize(3);

    input[0] = 'A';

    input[1] = '\r';

    input[2] = 'B';

    QCOMPARE(QString::fromUtf8(input.constData()).toUtf8(), input);

}

void tst_QTextCodec::codecForIndex() const

{

}

void tst_QTextCodec::aliasForUTF16() const

{

    QVERIFY(QTextCodec::codecForName("UTF-16")->aliases().isEmpty());

}

void tst_QTextCodec::mibForTSCII() const

{

    QCOMPARE(QTextCodec::codecForName("TSCII")->mibEnum(), 2107);

}

static QString fromInvalidUtf8Sequence(const QByteArray &ba)

{

    return QString().fill(QChar::ReplacementCharacter, ba.size());

}

// copied from tst_QString::fromUtf8_data()

void tst_QTextCodec::utf8Codec_data()

{

    QTest::addColumn<QByteArray>("utf8");

    QTest::addColumn<QString>("res");

    QTest::addColumn<int>("len");

    QString str;

    QTest::newRow("str0") << QByteArray("abcdefgh") << QString("abcdefgh") << -1;

    QTest::newRow("str0-len") << QByteArray("abcdefgh") << QString("abc") << 3;

    QTest::newRow("str1") << QByteArray("\303\266\303\244\303\274\303\226\303\204\303\234\303\270\303\246\303\245\303\230\303\206\303\205") << QString("\366\344\374\326\304\334\370\346\345\330\306\305") << -1;

    QTest::newRow("str1-len") << QByteArray("\303\266\303\244\303\274\303\226\303\204\303\234\303\270\303\246\303\245\303\230\303\206\303\205") << QString("\366\344\374\326\304") << 10;

    str += QChar(0x05e9);

    str += QChar(0x05d3);

    str += QChar(0x05d2);

    QTest::newRow("str2") << QByteArray("\327\251\327\223\327\222") << str << -1;

    str = QChar(0x05e9);

    QTest::newRow("str2-len") << QByteArray("\327\251\327\223\327\222") << str << 2;

    str = QChar(0x20ac);

    str += " some text";

    QTest::newRow("str3") << QByteArray("\342\202\254 some text") << str << -1;

    str = QChar(0x20ac);

    str += " some ";

    QTest::newRow("str3-len") << QByteArray("\342\202\254 some text") << str << 9;

    str = "hello";

    str += QChar::ReplacementCharacter;

    str += QChar(0x68);

    str += QChar::ReplacementCharacter;

    str += QChar::ReplacementCharacter;

    str += QChar::ReplacementCharacter;

    str += QChar::ReplacementCharacter;

    str += QChar(0x61);

    str += QChar::ReplacementCharacter;

    QTest::newRow("invalid utf8") << QByteArray("hello\344h\344\344\366\344a\304") << str << -1;

    QTest::newRow("invalid utf8-len") << QByteArray("hello\344h\344\344\366\344a\304") << QString("hello") << 5;

    str = "Prohl";

    str += QChar::ReplacementCharacter;

    str += QChar::ReplacementCharacter;

    str += "e";