feat: introduce Lucene-Hunspell spellchecker module

settings.gradle

@@ -21,5 +21,6 @@ include("machinetranslators:apertium",
         "aligner",
         "theme",
         "spellchecker:hunspell",
+        "spellchecker:lucene",
         "spellchecker:morfologik",
         "tipoftheday")

spellchecker/lucene/build.gradle

@@ -0,0 +1,40 @@
+plugins {
+    id 'java-library'
+}
+
+dependencies {
+    compileOnly(project.rootProject) {
+        exclude group: 'org.apache.lucene'
+        exclude group: 'org.languagetool'
+    }
+    if (providedLibsDir.directory) {
+        compileOnly fileTree(dir: providedLibsDir, includes: ['**/commons-io-*.jar'])
+        implementation fileTree(dir: providedLibsDir, includes: ['**/lucene-analyzers-common-8*.jar'])
+    } else {
+        compileOnly(libs.commons.io)
+        implementation 'org.apache.lucene:lucene-analyzers-common:8.11.3'
+    }
+    testImplementation(libs.junit4)
+    testImplementation(libs.assertj)
+    testImplementation(testFixtures(project.rootProject))
+    testImplementation(libs.commons.io)
+}
+
+jar {
+    archiveAppendix.set("spellchecker")
+    destinationDirectory.set(rootProject.layout.buildDirectory.dir("modules").get())
+    from configurations.runtimeClasspath.collect { it.isDirectory() ? it : zipTree(it) }
+    def pluginProp = loadProperties(file('plugin.properties'))
+    manifest {
+        attributes('License': 'GNU Public License version 3 or later',
+                'Implementation-Version': pluginProp.Version,
+                'OmegaT-Plugins': pluginProp.Class,
+                'Plugin-Author': pluginProp.Author,
+                'Plugin-Version': pluginProp.Version,
+                'Plugin-Name': pluginProp.Name,
+                'Plugin-Category': pluginProp.Category,
+                'Plugin-Description': pluginProp.Description
+        )
+    }
+    duplicatesStrategy = DuplicatesStrategy.INCLUDE
+}

spellchecker/lucene/plugin.properties

@@ -0,0 +1,31 @@
+#
+#  OmegaT - Computer Assisted Translation (CAT) tool
+#           with fuzzy matching, translation memory, keyword search,
+#           glossaries, and translation leveraging into updated projects.
+#
+#  Copyright (C) 2024 Hiroshi Miura
+#                Home page: https://www.omegat.org/
+#                Support center: https://omegat.org/support
+#
+#  This file is part of OmegaT.
+#
+#  OmegaT 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 3 of the License, or
+#  (at your option) any later version.
+#
+#  OmegaT is distributed in the hope that it will be useful,
+#  but WITHOUT ANY WARRANTY; without even the implied warranty of
+#  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+#  GNU General Public License for more details.
+#
+#  You should have received a copy of the GNU General Public License
+#  along with this program.  If not, see <https://www.gnu.org/licenses/>.
+#
+License=GNU Public License version 3 or later
+Author=OmegaT team
+Version=6.0.0
+Category=spellchecker
+Name=Default spell checker with Lucene Hunspell
+Class=org.omegat.spellchecker.lucene.HunSpellChecker
+Description=Lucene spellchecker module

spellchecker/lucene/src/main/java/org/omegat/spellchecker/lucene/LuceneHunSpellChecker.java

@@ -0,0 +1,134 @@
+/*******************************************************************************
+ * OmegaT - Computer Assisted Translation (CAT) tool
+ *          with fuzzy matching, translation memory, keyword search,
+ *          glossaries, and translation leveraging into updated projects.
+ *
+ * Copyright (C) 2024 Hiroshi Miura
+ *          Home page: https://www.omegat.org/
+ *          Support center: https://omegat.org/support
+ *
+ * This file is part of OmegaT.
+ *
+ * OmegaT 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 3 of the License, or
+ * (at your option) any later version.
+ *
+ * OmegaT is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <https://www.gnu.org/licenses/>.
+ ******************************************************************************/
+
+package org.omegat.spellchecker.lucene;
+
+import java.io.File;
+import java.io.FileInputStream;
+import java.io.IOException;
+import java.io.InputStream;
+import java.nio.file.Path;
+import java.text.ParseException;
+import java.util.List;
+import java.util.Optional;
+
+import org.apache.commons.io.FileUtils;
+import org.apache.lucene.analysis.hunspell.Dictionary;
+import org.apache.lucene.analysis.hunspell.Hunspell;
+import org.apache.lucene.store.NIOFSDirectory;
+
+import org.omegat.core.Core;
+import org.omegat.core.spellchecker.AbstractSpellChecker;
+import org.omegat.core.spellchecker.ISpellChecker;
+import org.omegat.core.spellchecker.ISpellCheckerProvider;
+import org.omegat.core.spellchecker.SpellCheckerManager;
+import org.omegat.util.Preferences;
+
+public class LuceneHunSpellChecker extends AbstractSpellChecker implements ISpellChecker {
+
+    /**
+     * affix file extension
+     */
+    public static final String SC_AFFIX_FILENAME = "index.aff";
+
+    /**
+     * dictionary file extension
+     */
+    public static final String SC_DICTIONARY_FILENAME = "index.dic";
+
+    /**
+     * Register plugins into OmegaT.
+     */
+    public static void loadPlugins() {
+        Core.registerSpellCheckClass(LuceneHunSpellChecker.class);
+    }
+
+    public static void unloadPlugins() {
+    }
+
+    public LuceneHunSpellChecker() {
+        super();
+    }
+
+    @Override
+    protected Optional<ISpellCheckerProvider> initializeWithLanguage(final String language) {
+        // check that the dict exists
+        String dictionaryDir = Preferences.getPreferenceDefault(Preferences.SPELLCHECKER_DICTIONARY_DIRECTORY,
+                SpellCheckerManager.DEFAULT_DICTIONARY_DIR.getPath());
+
+        File affixName = Path.of(dictionaryDir).resolve(Path.of(language)).resolve(SC_AFFIX_FILENAME).toFile();
+        File dictionaryName = Path.of(dictionaryDir).resolve(language).resolve(SC_DICTIONARY_FILENAME).toFile();
+
+        if (isInvalidFile(affixName) || isInvalidFile(dictionaryName)) {
+            return Optional.empty();
+        }
+
+        try {
+            ISpellCheckerProvider result = new LuceneProvider(dictionaryName, affixName);
+            return Optional.of(result);
+        } catch (Exception ex) {
+            ex.printStackTrace();
+        }
+        return Optional.empty();
+    }
+
+    private static final class LuceneProvider implements ISpellCheckerProvider {
+        private final InputStream dictInputStream;
+        private final InputStream affixInputStream;
+        private final Hunspell hunspell;
+
+        private LuceneProvider(File dictName, File affixName) throws IOException, ParseException {
+            Path tempDir = Path.of(FileUtils.getTempDirectoryPath());
+            dictInputStream = new FileInputStream(dictName);
+            affixInputStream = new FileInputStream(affixName);
+            Dictionary dict = new Dictionary(new NIOFSDirectory(tempDir), "omegat",
+                    affixInputStream, dictInputStream);
+            hunspell = new Hunspell(dict);
+        }
+
+        @Override
+        public boolean isCorrect(final String word) {
+            return hunspell.spell(word);
+        }
+
+        @Override
+        public List<String> suggest(final String word) {
+            return hunspell.suggest(word);
+        }
+
+        @Override
+        public void learnWord(final String word) {
+        }
+
+        @Override
+        public void destroy() {
+            try {
+                dictInputStream.close();
+                affixInputStream.close();
+            } catch (Exception ignored) {
+            }
+        }
+    }
+}

spellchecker/lucene/src/test/java/org/omegat/spellchecker/CopyrightTest.java

@@ -0,0 +1,104 @@
+/*******************************************************************************
+ * OmegaT - Computer Assisted Translation (CAT) tool
+ *          with fuzzy matching, translation memory, keyword search,
+ *          glossaries, and translation leveraging into updated projects.
+ *
+ * Copyright (C) 2008 Alex Buloichik
+ *          Home page: https://www.omegat.org/
+ *          Support center: https://omegat.org/support
+ *
+ * This file is part of OmegaT.
+ *
+ * OmegaT 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 3 of the License, or
+ * (at your option) any later version.
+ *
+ * OmegaT is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <https://www.gnu.org/licenses/>.
+ ******************************************************************************/
+
+package org.omegat.spellchecker;
+
+import static org.junit.Assert.assertTrue;
+
+import java.io.ByteArrayOutputStream;
+import java.io.File;
+import java.util.ArrayList;
+import java.util.List;
+
+import org.apache.commons.io.FileUtils;
+import org.junit.Test;
+
+/**
+ * Test for copyright notes exists in source files.
+ *
+ * @author Alex Buloichik
+ */
+public class CopyrightTest {
+    protected static final String[] MUST_EXIST = new String[]{
+            "OmegaT - Computer Assisted Translation (CAT) tool", "Copyright (C)",
+            "Home page: https://www.omegat.org/", "This file is part of OmegaT",
+            "OmegaT 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 3 of the License, or",
+            "(at your option) any later version.",
+            "OmegaT is distributed in the hope that it will be useful,",
+            "but WITHOUT ANY WARRANTY; without even the implied warranty of",
+            "MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the",
+            "GNU General Public License for more details.",
+            "You should have received a copy of the GNU General Public License",
+            "along with this program.  If not, see <https://www.gnu.org/licenses/>."};
+
+    @Test
+    public void testCopyright() throws Exception {
+        List<File> sourceFiles = new ArrayList<File>();
+        list(new File("src"), sourceFiles);
+        ByteArrayOutputStream fdata = new ByteArrayOutputStream();
+        for (File f : sourceFiles) {
+            if (f.getPath().replace('\\', '/').startsWith("src/gen/")) {
+                // skip jaxb generated files
+                continue;
+            }
+            FileUtils.copyFile(f, fdata);
+            String data = fdata.toString("ISO-8859-1");
+            checkNote(f, data);
+            fdata.reset();
+        }
+    }
+
+    protected void checkNote(File f, String data) {
+        int pos = data.indexOf("\npackage ");
+        if (pos > 0) {
+            data = data.substring(0, pos);
+        }
+        for (String con : MUST_EXIST) {
+            assertTrue("There is no copyright note in '" + f.getAbsolutePath() + "' : " + con,
+                    data.contains(con));
+        }
+    }
+
+    protected void list(File dir, List<File> files) {
+        for (File f : dir.listFiles()) {
+            String fn = f.getName();
+            if (f.getName().endsWith(".java")) {
+                files.add(f);
+            } else if (fn.equals("build.xml")) {
+                files.add(f);
+            } else if (fn.endsWith(".properties")) {
+                if (fn.startsWith("Version") || fn.startsWith("Bundle") || fn.startsWith("project")) {
+                    files.add(f);
+                }
+            } else if (fn.endsWith(".html")) {
+                files.add(f);
+            } else if (f.isDirectory()) {
+                list(f, files);
+            }
+        }
+    }
+}