src/test/java/org/apache/tika/parser/microsoft/ExcelParserTest.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 junit.framework.TestCase;
  22
  23 import org.apache.tika.metadata.Metadata;
  24 import org.apache.tika.sax.BodyContentHandler;
  25 import org.xml.sax.ContentHandler;
  26
  27 public class ExcelParserTest extends TestCase {
  28
  29     public void testExcelParser() throws Exception {
  30         InputStream input = ExcelParserTest.class.getResourceAsStream(
  31                 "/test-documents/testEXCEL.xls");
  32         try {
  33             Metadata metadata = new Metadata();
  34             ContentHandler handler = new BodyContentHandler();
  35             new OfficeParser().parse(input, handler, metadata);
  36
  37             assertEquals(
  38                     "application/vnd.ms-excel",
  39                     metadata.get(Metadata.CONTENT_TYPE));
  40             assertEquals("Simple Excel document", metadata.get(Metadata.TITLE));
  41             assertEquals("Keith Bennett", metadata.get(Metadata.AUTHOR));
  42             String content = handler.toString();
  43             assertTrue(content.contains("Sample Excel Worksheet"));
  44             assertTrue(content.contains("Numbers and their Squares"));
  45             assertTrue(content.contains("9"));
  46             assertFalse(content.contains("9.0"));
  47             assertTrue(content.contains("196"));
  48             assertFalse(content.contains("196.0"));
  49         } finally {
  50             input.close();
  51         }
  52     }
  53
  54 }