+// 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.SearchResult;
+import com.hughes.android.dictionary.engine.Index.IndexEntry;
+import com.hughes.util.CollectionUtil;
public class DictionaryTest extends TestCase {
- RandomAccessFile raf;
- Dictionary dict;
- Index deIndex;
-
- @Override
- public void setUp() {
- try {
- raf = new RandomAccessFile("testdata/de_en.dict", "r");
- dict = new Dictionary(raf);
- } catch (IOException e) {
- throw new RuntimeException(e);
- }
+ static final String TEST_OUTPUTS = com.hughes.android.dictionary.engine.DictionaryBuilderTest.TEST_OUTPUTS;
+ public static final String OUTPUTS = "data/outputs/";
- deIndex = dict.indices.get(0);
-}
-
@Override
- public void tearDown() {
- try {
- raf.close();
- } catch (IOException e) {
- throw new RuntimeException(e);
+ 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 {
- assertEquals("de", deIndex.shortName);
- assertEquals("de->en", deIndex.longName);
+ 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(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(TEST_OUTPUTS + "de-en.quickdic", "r");
+ final Dictionary dict = new Dictionary(raf);
+ final Index deIndex = dict.indices.get(0);
+
for (final Index.IndexEntry indexEntry : deIndex.sortedIndexEntries) {
System.out.println("testing: " + indexEntry.token);
- final Index.SearchResult searchResult = deIndex.findLongestSubstring(indexEntry.token, new AtomicBoolean(
+ final IndexEntry searchResult = deIndex.findInsertionPoint(indexEntry.token, new AtomicBoolean(
false));
- assertEquals(indexEntry.token.toLowerCase(), searchResult.insertionPoint.token.toLowerCase());
- assertEquals(indexEntry.token.toLowerCase(), searchResult.longestPrefix.token.toLowerCase());
+ assertEquals("Looked up: " + indexEntry.token, indexEntry.token.toLowerCase(), searchResult.token.toLowerCase());
}
// TODO: maybe if user types capitalization, use it.
- assertSearchResult("aaac", "aaac", deIndex.findLongestSubstring("aaac", new AtomicBoolean(false)));
- assertSearchResult("aaac", "aaac", deIndex.findLongestSubstring("AAAC", new AtomicBoolean(false)));
- assertSearchResult("aaac", "aaac", deIndex.findLongestSubstring("AAAc", new AtomicBoolean(false)));
- assertSearchResult("aaac", "aaac", deIndex.findLongestSubstring("aAac", new AtomicBoolean(false)));
+ assertSearchResult("aaac", "aaac", deIndex.findInsertionPoint("aaac", new AtomicBoolean(false)));
+ assertSearchResult("aaac", "aaac", deIndex.findInsertionPoint("AAAC", new AtomicBoolean(false)));
+ assertSearchResult("aaac", "aaac", deIndex.findInsertionPoint("AAAc", new AtomicBoolean(false)));
+ assertSearchResult("aaac", "aaac", deIndex.findInsertionPoint("aAac", new AtomicBoolean(false)));
// Before the beginning.
- assertSearchResult("40", "40" /* special case */, deIndex.findLongestSubstring("__", new AtomicBoolean(false)));
+ assertSearchResult("40", "40" /* special case */, deIndex.findInsertionPoint("", new AtomicBoolean(false)));
+ assertSearchResult("40", "40" /* special case */, deIndex.findInsertionPoint("__", new AtomicBoolean(false)));
// After the end.
- assertSearchResult("Zweckorientiertheit", "zählen", deIndex.findLongestSubstring("ZZZZZ", new AtomicBoolean(false)));
+ assertSearchResult("Zweckorientiertheit", "zählen", deIndex.findInsertionPoint("ZZZZZ", new AtomicBoolean(false)));
- assertSearchResult("ab", "aaac", deIndex.findLongestSubstring("aaaca", new AtomicBoolean(false)));
- assertSearchResult("machen", "machen", deIndex.findLongestSubstring("m", new AtomicBoolean(false)));
+ assertSearchResult("ab", "aaac", deIndex.findInsertionPoint("aaaca", new AtomicBoolean(false)));
+ assertSearchResult("machen", "machen", deIndex.findInsertionPoint("m", new AtomicBoolean(false)));
+ assertSearchResult("machen", "machen", deIndex.findInsertionPoint("macdddd", new AtomicBoolean(false)));
- assertSearchResult("überprüfe", "überprüfe", deIndex.findLongestSubstring("ueberprüfe", new AtomicBoolean(false)));
- assertSearchResult("überprüfe", "überprüfe", deIndex.findLongestSubstring("ueberpruefe", new AtomicBoolean(false)));
+ assertSearchResult("überprüfe", "überprüfe", deIndex.findInsertionPoint("ueberprüfe", new AtomicBoolean(false)));
+ assertSearchResult("überprüfe", "überprüfe", deIndex.findInsertionPoint("ueberpruefe", new AtomicBoolean(false)));
- assertSearchResult("überprüfe", "überprüfe", deIndex.findLongestSubstring("ueberpBLEH", new AtomicBoolean(false)));
- assertSearchResult("überprüfe", "überprüfe", deIndex.findLongestSubstring("überprBLEH", new AtomicBoolean(false)));
+ assertSearchResult("überprüfe", "überprüfe", deIndex.findInsertionPoint("ueberpBLEH", new AtomicBoolean(false)));
+ assertSearchResult("überprüfe", "überprüfe", deIndex.findInsertionPoint("überprBLEH", new AtomicBoolean(false)));
- assertSearchResult("überprüfen", "überprüfe", deIndex.findLongestSubstring("überprüfeBLEH", new AtomicBoolean(false)));
+ assertSearchResult("überprüfen", "überprüfe", deIndex.findInsertionPoint("überprüfeBLEH", new AtomicBoolean(false)));
+ // Check that search in lowercase works.
+ assertSearchResult("Alibi", "Alibi", deIndex.findInsertionPoint("alib", new AtomicBoolean(false)));
+ System.out.println(deIndex.findInsertionPoint("alib", new AtomicBoolean(false)).toString());
+
+ raf.close();
}
private void assertSearchResult(final String insertionPoint, final String longestPrefix,
- final SearchResult actual) {
- assertEquals(insertionPoint, actual.insertionPoint.token);
- assertEquals(longestPrefix, actual.longestPrefix.token);
+ final IndexEntry actual) {
+ assertEquals(insertionPoint, actual.token);
}
- public void testGermanTokenRows() {
+ public void testGermanTokenRows() 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);
+
// Pre-cache a few of these, just to make sure that's working.
for (int i = 0; i < deIndex.rows.size(); i += 7) {
deIndex.rows.get(i).getTokenRow(true);
// This will break if the Row cache isn't big enough.
assertEquals(lastTokenRow, row.getTokenRow(false));
}
+
+ raf.close();
}
- public void testGermanSort() {
- assertEquals("aüÄÄ", Language.de.textNorm("aueAeAE", false));
- final List<String> words = Arrays.asList(
- "er-ben",
- "erben",
- "Erben",
- "Erbse",
- "Erbsen",
- "essen",
- "Essen",
- "Grosformat",
- "Grosformats",
- "Grossformat",
- "Großformat",
- "Grossformats",
- "Großformats",
- "Großpoo",
- "Großpoos",
- "hulle",
- "Hulle",
- "hülle",
- "huelle",
- "Hülle",
- "Huelle",
- "Hum"
- );
- assertEquals(0, Language.de.sortComparator.compare("hülle", "huelle"));
- assertEquals(0, Language.de.sortComparator.compare("huelle", "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(-1, Language.de.sortComparator.compare("hülle", "Hülle"));
- assertEquals(0, Language.de.findComparator.compare("hülle", "Hülle"));
- assertEquals(-1, Language.de.findComparator.compare("hulle", "Hülle"));
+ assertSearchResult("Höschen", "Hos", deIndex.findInsertionPoint("Hos", new AtomicBoolean(false)));
+ assertSearchResult("Höschen", "hos", deIndex.findInsertionPoint("hos", new AtomicBoolean(false)));
-
- for (final String s : words) {
- System.out.println(s + "\t" + Language.de.textNorm(s, false));
- }
- final List<String> sorted = new ArrayList<String>(words);
-// Collections.shuffle(shuffled, new Random(0));
- Collections.sort(sorted, Language.de.sortComparator);
- 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();
}
- @SuppressWarnings("unchecked")
- public void testEnglishSort() {
+ 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);
- Collections.sort(sorted, Language.en.getSortCollator());
- for (int i = 0; i < words.size(); ++i) {
- if (i > 0) {
- assertTrue(Language.en.getSortCollator().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(Language.en.getSortCollator().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 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);
+
+ {
+ 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());
+ }
+
+ {
+ 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