+// Copyright 2011 Google Inc. All Rights Reserved.
+//
+// Licensed under the Apache License, Version 2.0 (the "License");
+// you may not use this file except in compliance with the License.
+// You may obtain a copy of the License at
+//
+// http://www.apache.org/licenses/LICENSE-2.0
+//
+// Unless required by applicable law or agreed to in writing, software
+// distributed under the License is distributed on an "AS IS" BASIS,
+// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+// See the License for the specific language governing permissions and
+// limitations under the License.
+
package com.hughes.android.dictionary.engine;
import java.io.IOException;
import java.io.RandomAccessFile;
-import java.util.ArrayList;
import java.util.Arrays;
-import java.util.Collections;
import java.util.List;
import java.util.concurrent.atomic.AtomicBoolean;
import junit.framework.TestCase;
import com.hughes.android.dictionary.engine.Index.IndexEntry;
-import com.ibm.icu.text.Transliterator;
+import com.hughes.util.CollectionUtil;
public class DictionaryTest extends TestCase {
+
+ static final String TEST_OUTPUTS = com.hughes.android.dictionary.engine.DictionaryBuilderTest.TEST_OUTPUTS;
+ public static final String OUTPUTS = "data/outputs/";
+
+ @Override
+ protected void setUp() {
+ while (!TransliteratorManager.init(null)) {
+ try {
+ Thread.sleep(10);
+ } catch (InterruptedException e) {
+ e.printStackTrace();
+ }
+ }
+ }
+
+ public void testEnItWiktionary() throws IOException {
+ final RandomAccessFile raf = new RandomAccessFile(OUTPUTS + "EN-IT_enwiktionary.quickdic", "r");
+ final Dictionary dict = new Dictionary(raf);
+ final Index enIndex = dict.indices.get(0);
+ final RowBase row = enIndex.rows.get(4);
+ assertEquals("The numeral 00\tzeranta (noun) {m|f|inv}", row.getRawText(false));
+
+ raf.close();
+ }
+
public void testGermanMetadata() throws IOException {
- final RandomAccessFile raf = new RandomAccessFile("testdata/de-en.quickdic", "r");
+ final RandomAccessFile raf = new RandomAccessFile(TEST_OUTPUTS + "de-en.quickdic", "r");
final Dictionary dict = new Dictionary(raf);
final Index deIndex = dict.indices.get(0);
- assertEquals("de", deIndex.shortName);
- assertEquals("de->en", deIndex.longName);
+ assertEquals("DE", deIndex.shortName);
+ assertEquals("DE->EN", deIndex.longName);
+
+ assertEquals(2, dict.sources.size());
+ assertEquals("chemnitz", dict.sources.get(0).name);
+ assertEquals("dictcc", dict.sources.get(1).name);
+
+ assertEquals("dictcc", dict.pairEntries.get(0).entrySource.name);
+ assertEquals("chemnitz", dict.pairEntries.get(1).entrySource.name);
raf.close();
}
public void testGermanIndex() throws IOException {
- final RandomAccessFile raf = new RandomAccessFile("testdata/de-en.dict", "r");
+ final RandomAccessFile raf = new RandomAccessFile(TEST_OUTPUTS + "de-en.quickdic", "r");
final Dictionary dict = new Dictionary(raf);
final Index deIndex = dict.indices.get(0);
System.out.println("testing: " + indexEntry.token);
final IndexEntry searchResult = deIndex.findInsertionPoint(indexEntry.token, new AtomicBoolean(
false));
- assertEquals(indexEntry.token.toLowerCase(), searchResult.token.toLowerCase());
+ assertEquals("Looked up: " + indexEntry.token, indexEntry.token.toLowerCase(), searchResult.token.toLowerCase());
}
// TODO: maybe if user types capitalization, use it.
}
public void testGermanTokenRows() throws IOException {
- final RandomAccessFile raf = new RandomAccessFile("testdata/de-en.quickdic", "r");
+ final RandomAccessFile raf = new RandomAccessFile(TEST_OUTPUTS + "de-en.quickdic", "r");
final Dictionary dict = new Dictionary(raf);
final Index deIndex = dict.indices.get(0);
raf.close();
}
- public void testGermanSort() {
- final Transliterator normalizer = Transliterator.createFromRules("", Language.de.getDefaultNormalizerRules(), Transliterator.FORWARD);
- assertEquals("aüääss", normalizer.transform("aueAeAEß"));
- final List<String> words = Arrays.asList(
- "er-ben",
- "erben",
- "Erben",
- "Erbse",
- "Erbsen",
- "essen",
- "Essen",
- "Grosformat",
- "Grosformats",
- "Grossformat",
- "Großformat",
- "Grossformats",
- "Großformats",
- "Großpoo",
- "Großpoos",
- "Hörvermögen",
- "Hörweite",
- "hos",
- "Höschen",
- "Hostel",
- "hulle",
- "Hulle",
- "huelle",
- "Huelle",
- "hülle",
- "Hülle",
- "Huellen",
- "Hüllen",
- "Hum"
- );
- final NormalizeComparator comparator = new NormalizeComparator(normalizer, Language.de.getCollator());
- assertEquals(1, comparator.compare("hülle", "huelle"));
- assertEquals(-1, comparator.compare("huelle", "hülle"));
-
- assertEquals(-1, comparator.compare("hülle", "Hülle"));
+ public void testChemnitz() throws IOException {
+ final RandomAccessFile raf = new RandomAccessFile(TEST_OUTPUTS + "de-en.quickdic", "r");
+ final Dictionary dict = new Dictionary(raf);
+ final Index deIndex = dict.indices.get(0);
- assertEquals("hülle", normalizer.transform("Hülle"));
- assertEquals("hulle", normalizer.transform("Hulle"));
+ assertSearchResult("Höschen", "Hos", deIndex.findInsertionPoint("Hos", new AtomicBoolean(false)));
+ assertSearchResult("Höschen", "hos", deIndex.findInsertionPoint("hos", new AtomicBoolean(false)));
-
- final List<String> sorted = new ArrayList<String>(words);
-// Collections.shuffle(shuffled, new Random(0));
- Collections.sort(sorted, comparator);
- System.out.println(sorted.toString());
- for (int i = 0; i < words.size(); ++i) {
- System.out.println(words.get(i) + "\t" + sorted.get(i));
- assertEquals(words.get(i), sorted.get(i));
- }
+ raf.close();
}
- public void testEnglishSort() {
- final Transliterator normalizer = Transliterator.createFromRules("", Language.en.getDefaultNormalizerRules(), Transliterator.FORWARD);
+ public void testMultiSearch() throws IOException {
+ final RandomAccessFile raf = new RandomAccessFile(TEST_OUTPUTS + "de-en.quickdic", "r");
+ final Dictionary dict = new Dictionary(raf);
+ final Index deIndex = dict.indices.get(0);
- final List<String> words = Arrays.asList(
- "pre-print",
- "preppie",
- "preppy",
- "preprocess");
-
- final List<String> sorted = new ArrayList<String>(words);
- final NormalizeComparator comparator = new NormalizeComparator(normalizer, Language.en.getCollator());
- Collections.sort(sorted, comparator);
- for (int i = 0; i < words.size(); ++i) {
- if (i > 0) {
- assertTrue(comparator.compare(words.get(i-1), words.get(i)) < 0);
- }
- System.out.println(words.get(i) + "\t" + sorted.get(i));
- assertEquals(words.get(i), sorted.get(i));
+ {
+ final List<RowBase> rows = deIndex.multiWordSearch(Arrays.asList("aaa", "aaab"), new AtomicBoolean(false));
+ System.out.println(CollectionUtil.join(rows, "\n "));
+ assertTrue(rows.toString(), rows.size() > 0);
}
- assertTrue(comparator.compare("pre-print", "preppy") < 0);
-
- }
-
- public void testLanguage() {
- assertEquals(Language.de, Language.lookup("de"));
- assertEquals(Language.en, Language.lookup("en"));
- assertEquals("es", Language.lookup("es").getSymbol());
+ raf.close();
}
- public void testTextNorm() {
- //final Transliterator transliterator = Transliterator.getInstance("Any-Latin; Upper; Lower; 'oe' > 'o'; NFD; [:Nonspacing Mark:] Remove; NFC", Transliterator.FORWARD);
- final Transliterator transliterator = Transliterator.createFromRules("", ":: Any-Latin; :: Upper; :: Lower; 'oe' > 'o'; :: NFD; :: [:Nonspacing Mark:] Remove; :: NFC ;", Transliterator.FORWARD);
- assertEquals("hoschen", transliterator.transliterate("Höschen"));
- assertEquals("hoschen", transliterator.transliterate("Hoeschen"));
- assertEquals("grosspoo", transliterator.transliterate("Großpoo"));
+ public void testMultiSearchBig() throws IOException {
+ final RandomAccessFile raf = new RandomAccessFile(OUTPUTS + "DE-EN_chemnitz_enwiktionary.quickdic", "r");
+ final Dictionary dict = new Dictionary(raf);
+ final Index enIndex = dict.indices.get(1);
- assertEquals("kyanpasu", transliterator.transliterate("キャンパス"));
- assertEquals("alphabetikos katalogos", transliterator.transliterate("Αλφαβητικός Κατάλογος"));
- assertEquals("biologiceskom", transliterator.transliterate("биологическом"));
- }
+ {
+ final List<RowBase> rows = enIndex.multiWordSearch(Arrays.asList("train", "station"), new AtomicBoolean(false));
+ System.out.println(CollectionUtil.join(rows, "\n "));
+ assertTrue(rows.toString(), rows.size() > 0);
+ assertEquals("Bahnhof {{de-noun|g=m|genitive=Bahnhofs|genitive2=Bahnhofes|plural=Bahnhöfe}}\ttrain station", rows.get(0).toString());
+ }
- public void testChemnitz() throws IOException {
- final RandomAccessFile raf = new RandomAccessFile("dictOutputs/de-en_chemnitz.quickdic", "r");
- final Dictionary dict = new Dictionary(raf);
- final Index deIndex = dict.indices.get(0);
-
- assertSearchResult("Höschen", "Hos", deIndex.findInsertionPoint("Hos", new AtomicBoolean(false)));
- assertSearchResult("Höschen", "hos", deIndex.findInsertionPoint("hos", new AtomicBoolean(false)));
+ {
+ final List<RowBase> rows = enIndex.multiWordSearch(Arrays.asList("a", "train", "station"), new AtomicBoolean(false));
+ System.out.println(CollectionUtil.join(rows, "\n "));
+ assertTrue(rows.toString(), rows.size() > 0);
+ assertEquals("Bahnhofsuhr {{de-noun|g=f|plural=Bahnhofsuhren}}\tstation clock (at a train station)", rows.get(0).toString());
+ }
+
+ {
+ final List<RowBase> rows = enIndex.multiWordSearch(Arrays.asList("a", "station"), new AtomicBoolean(false));
+ // TODO: bug, "a" isn't in stoplist for now...
+ System.out.println(CollectionUtil.join(rows, "\n "));
+ assertTrue(rows.toString(), rows.size() == 0);
+ //assertEquals("Bahnhofsuhr {{de-noun|g=f|plural=Bahnhofsuhren}}\tstation clock (at a train station)", rows.get(0).toString());
+ }
raf.close();
}
projects / DictionaryPC.git / blobdiff