src/test/java/org/apache/tika/parser/microsoft/WordParserTest.java

   1 /**
   2  * Licensed to the Apache Software Foundation (ASF) under one or more
   3  * contributor license agreements.  See the NOTICE file distributed with
   4  * this work for additional information regarding copyright ownership.
   5  * The ASF licenses this file to You under the Apache License, Version 2.0
   6  * (the "License"); you may not use this file except in compliance with
   7  * the License.  You may obtain a copy of the License at
   8  *
   9  *     http://www.apache.org/licenses/LICENSE-2.0
  10  *
  11  * Unless required by applicable law or agreed to in writing, software
  12  * distributed under the License is distributed on an "AS IS" BASIS,
  13  * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
  14  * See the License for the specific language governing permissions and
  15  * limitations under the License.
  16  */
  17 package org.apache.tika.parser.microsoft;
  18
  19 import java.io.InputStream;
  20
  21 import org.apache.tika.metadata.Metadata;
  22 import org.apache.tika.sax.BodyContentHandler;
  23 import org.xml.sax.ContentHandler;
  24
  25 import junit.framework.TestCase;
  26
  27 public class WordParserTest extends TestCase {
  28
  29     public void testWordParser() throws Exception {
  30         InputStream input = WordParserTest.class.getResourceAsStream(
  31                 "/test-documents/testWORD.doc");
  32         try {
  33             ContentHandler handler = new BodyContentHandler();
  34             Metadata metadata = new Metadata();
  35             new OfficeParser().parse(input, handler, metadata);
  36
  37             assertEquals(
  38                     "application/msword",
  39                     metadata.get(Metadata.CONTENT_TYPE));
  40             assertEquals("Sample Word Document", metadata.get(Metadata.TITLE));
  41             assertEquals("Keith Bennett", metadata.get(Metadata.AUTHOR));
  42             assertTrue(handler.toString().contains("Sample Word Document"));
  43         } finally {
  44             input.close();
  45         }
  46     }
  47
  48 }