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.IOException;
20 import java.io.InputStream;
21
22 import org.apache.tika.exception.TikaException;
23 import org.apache.tika.metadata.Metadata;
24 import org.xml.sax.ContentHandler;
25 import org.xml.sax.SAXException;
26
27 /**
28 * Tika parser interface
29 */
30 public interface Parser {
31
32 /**
33 * Parses a document stream into a sequence of XHTML SAX events.
34 * Fills in related document metadata in the given metadata object.
35 * <p>
36 * The given document stream is consumed but not closed by this method.
37 * The responsibility to close the stream remains on the caller.
38 *
39 * @param stream the document stream (input)
40 * @param handler handler for the XHTML SAX events (output)
41 * @param metadata document metadata (input and output)
42 * @throws IOException if the document stream could not be read
43 * @throws SAXException if the SAX events could not be processed
44 * @throws TikaException if the document could not be parsed
45 */
46 void parse(InputStream stream, ContentHandler handler, Metadata metadata)
47 throws IOException, SAXException, TikaException;
48
49 }