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.source;
19
20 import java.io.ByteArrayOutputStream;
21 import java.io.IOException;
22 import java.io.InputStream;
23
24 /**
25 * Creates local copies of {@link DocumentSource} by reading them into an in-memory buffer. This allows opening several
26 * input streams over the content at lower cost.
27 *
28 * @author Richard Cyganiak (richard@cyganiak.de)
29 */
30 public class MemCopyFactory implements LocalCopyFactory {
31
32 private static final int TEMP_SIZE = 10000;
33
34 public static byte[] toByteArray(InputStream in) throws IOException {
35 ByteArrayOutputStream out = new ByteArrayOutputStream();
36 byte[] temp = new byte[TEMP_SIZE];
37 while (true) {
38 int bytes = in.read(temp);
39 if (bytes == -1)
40 break;
41 out.write(temp, 0, bytes);
42 }
43 return out.toByteArray();
44 }
45
46 public DocumentSource createLocalCopy(final DocumentSource in) throws IOException {
47 return new ByteArrayDocumentSource(in.openInputStream(), in.getDocumentIRI(), in.getContentType());
48 }
49 }