X-Git-Url: http://gitweb.fperrin.net/?a=blobdiff_plain;f=src%2Fcom%2Fhughes%2Fandroid%2Fdictionary%2Fengine%2FDictionaryTest.java;h=f766e0ab50ace5d74ece89b47618f6dbb2fbaa72;hb=6e6661c2989066377a6a6693dafc0d65bfea4b82;hp=59bb031b4ec67a4c9113eca8f3c9dc946ef2cba7;hpb=749687bc77b2daf14d7a537b6f73073062e5d9f6;p=DictionaryPC.git

diff --git a/src/com/hughes/android/dictionary/engine/DictionaryTest.java b/src/com/hughes/android/dictionary/engine/DictionaryTest.java
index 59bb031..f766e0a 100644
--- a/src/com/hughes/android/dictionary/engine/DictionaryTest.java
+++ b/src/com/hughes/android/dictionary/engine/DictionaryTest.java
@@ -1,59 +1,131 @@
+// 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.Arrays;
+import java.util.List;
 import java.util.concurrent.atomic.AtomicBoolean;
 
 import junit.framework.TestCase;
 
+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 TokenRow row = deIndex.find(indexEntry.token, new AtomicBoolean(
+      final IndexEntry searchResult = deIndex.findInsertionPoint(indexEntry.token, new AtomicBoolean(
           false));
-      assertEquals(indexEntry.token.toLowerCase(), row.getToken().toLowerCase());
+      assertEquals("Looked up: " + indexEntry.token, indexEntry.token.toLowerCase(), searchResult.token.toLowerCase());
     }
 
-    assertEquals("aaac", deIndex.find("AAAC", new AtomicBoolean(false)).getToken());
-    assertEquals("aaac", deIndex.find("aaac", new AtomicBoolean(false)).getToken());
-    assertEquals("aaac", deIndex.find("AAAc", new AtomicBoolean(false)).getToken());
-    assertEquals("aaac", deIndex.find("aaac", new AtomicBoolean(false)).getToken());
+    // TODO: maybe if user types capitalization, use it.
+    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.findInsertionPoint("", new AtomicBoolean(false)));
+    assertSearchResult("40", "40" /* special case */, deIndex.findInsertionPoint("__", new AtomicBoolean(false)));
+    
+    // After the end.
+    assertSearchResult("Zweckorientiertheit", "zählen", deIndex.findInsertionPoint("ZZZZZ", 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.findInsertionPoint("ueberprüfe", new AtomicBoolean(false)));
+    assertSearchResult("überprüfe", "überprüfe", deIndex.findInsertionPoint("ueberpruefe", 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.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();
   }
   
-  public void testGermanTokenRows() {
+  private void assertSearchResult(final String insertionPoint, final String longestPrefix,
+      final IndexEntry actual) {
+    assertEquals(insertionPoint, actual.token);
+  }
+
+  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);
@@ -76,8 +148,47 @@ public class DictionaryTest extends TestCase {
       // This will break if the Row cache isn't big enough.
       assertEquals(lastTokenRow, row.getTokenRow(false));
     }
+    
+    raf.close();
+  }
+  
+  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);
+    
+    assertSearchResult("Höschen", "Hos", deIndex.findInsertionPoint("Hos", new AtomicBoolean(false)));
+    assertSearchResult("Höschen", "hos", deIndex.findInsertionPoint("hos", new AtomicBoolean(false)));
 
+    raf.close();
   }
 
+  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<RowBase> rows = deIndex.multiWordSearch(Arrays.asList("aaa", "aaab"), new AtomicBoolean(false));
+    System.out.println(CollectionUtil.join(rows, "\n  "));
+    assertTrue(rows.toString(), rows.size() > 0);
+    }
+    
+    raf.close();
+  }
+
+  public void testMultiSearchBig() 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 List<RowBase> rows = enIndex.multiWordSearch(Arrays.asList("space", "station"), new AtomicBoolean(false));
+    System.out.println(CollectionUtil.join(rows, "\n  "));
+    assertTrue(rows.toString(), rows.size() > 0);
+    }
+    
+    raf.close();
+  }
 
 }