src/test/java/org/apache/tika/parser/ParsingReaderTest.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;
  18
  19 import java.io.ByteArrayInputStream;
  20 import java.io.InputStream;
  21 import java.io.Reader;
  22
  23 import junit.framework.TestCase;
  24
  25 public class ParsingReaderTest extends TestCase {
  26
  27     public void testPlainText() throws Exception {
  28         String data = "test content";
  29         InputStream stream = new ByteArrayInputStream(data.getBytes("UTF-8"));
  30         Reader reader = new ParsingReader(stream, "test.txt");
  31         assertEquals('t', reader.read());
  32         assertEquals('e', reader.read());
  33         assertEquals('s', reader.read());
  34         assertEquals('t', reader.read());
  35         assertEquals(' ', reader.read());
  36         assertEquals('c', reader.read());
  37         assertEquals('o', reader.read());
  38         assertEquals('n', reader.read());
  39         assertEquals('t', reader.read());
  40         assertEquals('e', reader.read());
  41         assertEquals('n', reader.read());
  42         assertEquals('t', reader.read());
  43         assertEquals(-1, reader.read());
  44         reader.close();
  45         assertEquals(-1, stream.read());
  46     }
  47
  48     public void testXML() throws Exception {
  49         String data = "<p>test <span>content</span></p>";
  50         InputStream stream = new ByteArrayInputStream(data.getBytes("UTF-8"));
  51         Reader reader = new ParsingReader(stream, "test.xml");
  52         assertEquals('t', reader.read());
  53         assertEquals('e', reader.read());
  54         assertEquals('s', reader.read());
  55         assertEquals('t', reader.read());
  56         assertEquals(' ', reader.read());
  57         assertEquals('c', reader.read());
  58         assertEquals('o', reader.read());
  59         assertEquals('n', reader.read());
  60         assertEquals('t', reader.read());
  61         assertEquals('e', reader.read());
  62         assertEquals('n', reader.read());
  63         assertEquals('t', reader.read());
  64         assertEquals(-1, reader.read());
  65         reader.close();
  66         assertEquals(-1, stream.read());
  67     }
  68
  69 }