1 package org.apache.lucene.analysis;
4 * Licensed to the Apache Software Foundation (ASF) under one or more
5 * contributor license agreements. See the NOTICE file distributed with
6 * this work for additional information regarding copyright ownership.
7 * The ASF licenses this file to You under the Apache License, Version 2.0
8 * (the "License"); you may not use this file except in compliance with
9 * the License. You may obtain a copy of the License at
11 * http://www.apache.org/licenses/LICENSE-2.0
13 * Unless required by applicable law or agreed to in writing, software
14 * distributed under the License is distributed on an "AS IS" BASIS,
15 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
16 * See the License for the specific language governing permissions and
17 * limitations under the License.
20 import java.io.BufferedReader;
22 import java.io.IOException;
23 import java.io.InputStream;
24 import java.io.InputStreamReader;
25 import java.util.zip.ZipFile;
27 import org.apache.lucene.analysis.Analyzer;
28 import org.junit.Assert;
30 /** Utility class for doing vocabulary-based stemming tests */
31 public class VocabularyAssert {
32 /** Run a vocabulary test against two data files. */
33 public static void assertVocabulary(Analyzer a, InputStream voc, InputStream out)
35 BufferedReader vocReader = new BufferedReader(
36 new InputStreamReader(voc, "UTF-8"));
37 BufferedReader outputReader = new BufferedReader(
38 new InputStreamReader(out, "UTF-8"));
39 String inputWord = null;
40 while ((inputWord = vocReader.readLine()) != null) {
41 String expectedWord = outputReader.readLine();
42 Assert.assertNotNull(expectedWord);
43 BaseTokenStreamTestCase.checkOneTermReuse(a, inputWord, expectedWord);
47 /** Run a vocabulary test against one file: tab separated. */
48 public static void assertVocabulary(Analyzer a, InputStream vocOut)
50 BufferedReader vocReader = new BufferedReader(
51 new InputStreamReader(vocOut, "UTF-8"));
52 String inputLine = null;
53 while ((inputLine = vocReader.readLine()) != null) {
54 if (inputLine.startsWith("#") || inputLine.trim().length() == 0)
55 continue; /* comment */
56 String words[] = inputLine.split("\t");
57 BaseTokenStreamTestCase.checkOneTermReuse(a, words[0], words[1]);
61 /** Run a vocabulary test against two data files inside a zip file */
62 public static void assertVocabulary(Analyzer a, File zipFile, String voc, String out)
64 ZipFile zip = new ZipFile(zipFile);
65 InputStream v = zip.getInputStream(zip.getEntry(voc));
66 InputStream o = zip.getInputStream(zip.getEntry(out));
67 assertVocabulary(a, v, o);
73 /** Run a vocabulary test against a tab-separated data file inside a zip file */
74 public static void assertVocabulary(Analyzer a, File zipFile, String vocOut)
76 ZipFile zip = new ZipFile(zipFile);
77 InputStream vo = zip.getInputStream(zip.getEntry(vocOut));
78 assertVocabulary(a, vo);