View Javadoc
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  
18  package org.apache.any23.mime.purifier;
19  
20  import java.io.IOException;
21  import java.io.InputStream;
22  
23  /**
24   * Implementation of {@link Purifier} that removes all the eventual blank
25   * characters at the header of a file that might prevents its <i>MIME Type</i> detection.
26   *
27   * @author Davide Palmisano ( dpalmisano@gmail.com )
28   */
29  public class WhiteSpacesPurifier implements Purifier {
30  
31      /**
32       * {@inheritDoc}
33       */
34      public void purify(InputStream inputStream) throws IOException {
35          if(!inputStream.markSupported())
36              throw new IllegalArgumentException("Provided InputStream does not support marks");
37  
38          // mark the current position
39          inputStream.mark(Integer.MAX_VALUE);
40          int byteRead = inputStream.read();
41          char charRead = (char) byteRead;
42          while(isBlank(charRead) && (byteRead != -1)) {
43              // if here means that the previos character must be removed, so mark.
44              inputStream.mark(Integer.MAX_VALUE);            
45              byteRead = inputStream.read();
46              charRead = (char) byteRead;
47          }
48          // if exit go back to the last valid mark.
49          inputStream.reset();
50      }
51      
52      private boolean isBlank(char c) {
53          return c == '\t' || c == '\n' || c == ' ' || c == '\r' || c == '\b' || c == '\f';
54      }
55  }