File indexing completed on 2024-03-03 04:09:23

0001 /**
0002  * Copyright (C)  2019 Waqar Ahmed <waqar.17a@gmail.com>
0003  *
0004  * This library is free software; you can redistribute it and/or
0005  * modify it under the terms of the GNU Lesser General Public
0006  * License as published by the Free Software Foundation; either
0007  * version 2.1 of the License, or (at your option) any later version.
0008  *
0009  * This library is distributed in the hope that it will be useful,
0010  * but WITHOUT ANY WARRANTY; without even the implied warranty of
0011  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
0012  * Lesser General Public License for more details.
0013  *
0014  * You should have received a copy of the GNU Lesser General Public
0015  * License along with this library; if not, write to the Free Software
0016  * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
0017  * 02110-1301  USA
0018  */
0019 #include "guesslanguage.h"
0020 #include "speller.h"
0021 
0022 #include <QObject>
0023 #include <QStandardPaths>
0024 #include <QTest>
0025 
0026 class SonnetAutoDetectTest : public QObject
0027 {
0028     Q_OBJECT
0029 private Q_SLOTS:
0030     void initTestCase();
0031     void autodetect_data();
0032     void autodetect();
0033     void benchDistance_data();
0034     void benchDistance();
0035 };
0036 
0037 using namespace Sonnet;
0038 
0039 void SonnetAutoDetectTest::initTestCase()
0040 {
0041     QStandardPaths::setTestModeEnabled(true);
0042 
0043     Speller speller(QStringLiteral("en_US"));
0044 
0045     if (speller.availableBackends().empty()) {
0046         QSKIP("No backends available");
0047     }
0048 
0049     if (!speller.availableBackends().contains(QLatin1String("Hunspell"))) {
0050         QSKIP("Hunspell not available");
0051     }
0052 
0053     speller.setDefaultClient(QStringLiteral("Hunspell"));
0054     speller.setAttribute(Speller::AutoDetectLanguage, true);
0055 }
0056 
0057 void SonnetAutoDetectTest::autodetect_data()
0058 {
0059     QTest::addColumn<QString>("sentence");
0060     QTest::addColumn<QString>("correct_lang");
0061     QTest::addColumn<QStringList>("suggested_langs");
0062 
0063     QTest::newRow("English") << QStringLiteral("This is an English sentence.") << QStringLiteral("en_US")
0064                              << QStringList{QLatin1String("en_US"), QLatin1String("de_DE"), QLatin1String("ur_PK")};
0065     QTest::newRow("German") << QStringLiteral("Dies ist ein deutscher Satz.") << QStringLiteral("de_DE")
0066                             << QStringList{QLatin1String("hi_IN"), QLatin1String("pl_PL"), QLatin1String("de_DE_frami")};
0067     QTest::newRow("Malayam") << QStringLiteral("ഇന്ത്യയുടെ തെക്കു ഭാഗത്തു സ്ഥിതി ചെയ്യുന്ന ഒരു സംസ്ഥാനമാണ് കേരളം.") << QStringLiteral("ml_IN")
0068                              << QStringList{QLatin1String("ml_IN"), QLatin1String("ur_PK"), QLatin1String("en_US-large")};
0069 }
0070 
0071 void SonnetAutoDetectTest::autodetect()
0072 {
0073     QFETCH(QString, sentence);
0074     QFETCH(QString, correct_lang);
0075     QFETCH(QStringList, suggested_langs);
0076 
0077     // skip if the language is not available
0078     Speller speller;
0079     if (!speller.availableLanguages().contains(correct_lang)) {
0080         const QString msg = correct_lang + QStringLiteral(" not available");
0081         QSKIP(msg.toLocal8Bit().constData());
0082     }
0083 
0084     Sonnet::GuessLanguage gl;
0085     QString actual_lang = gl.identify(sentence, suggested_langs);
0086 
0087     // get chars till _, get the language code
0088     int us = correct_lang.indexOf(QLatin1Char('_'));
0089     const QString correctLangCode = correct_lang.left(us);
0090 
0091     us = actual_lang.indexOf(QLatin1Char('_'));
0092     const QString actualLangCode = actual_lang.left(us);
0093 
0094     qDebug() << "Actual: " << actual_lang;
0095     qDebug() << "Expected: " << correct_lang;
0096 
0097     QCOMPARE(actualLangCode, correctLangCode);
0098 }
0099 
0100 void SonnetAutoDetectTest::benchDistance_data()
0101 {
0102     QTest::addColumn<QString>("sentence");
0103     QTest::addColumn<QString>("correct_lang");
0104     QTest::addColumn<QStringList>("suggested_langs");
0105 
0106     QTest::newRow("English") << QStringLiteral("This is an English sentence.") << QStringLiteral("en_US")
0107                              << QStringList{QLatin1String("en_US"), QLatin1String("de_DE")};
0108     QTest::newRow("German") << QStringLiteral("Dies ist ein deutscher Satz.") << QStringLiteral("de_DE")
0109                             << QStringList{QLatin1String("pl_PL"), QLatin1String("de_DE_frami")};
0110     QTest::newRow("Malayam") << QStringLiteral("ഇന്ത്യയുടെ തെക്കു ഭാഗത്തു സ്ഥിതി ചെയ്യുന്ന ഒരു സംസ്ഥാനമാണ് കേരളം.") << QStringLiteral("ml_IN")
0111                              << QStringList{QLatin1String("ml_IN"), QLatin1String("en_US-large")};
0112 }
0113 
0114 void SonnetAutoDetectTest::benchDistance()
0115 {
0116     QFETCH(QString, sentence);
0117     QFETCH(QString, correct_lang);
0118     QFETCH(QStringList, suggested_langs);
0119 
0120     Sonnet::GuessLanguage gl;
0121 
0122     QBENCHMARK {
0123         QString actual_lang = gl.identify(sentence, suggested_langs);
0124     }
0125 }
0126 
0127 QTEST_GUILESS_MAIN(SonnetAutoDetectTest)
0128 
0129 #include "test_autodetect.moc"