1
package org.apache.lucene.benchmark.byTask.feeds;
4
* Licensed to the Apache Software Foundation (ASF) under one or more
5
* contributor license agreements. See the NOTICE file distributed with
6
* this work for additional information regarding copyright ownership.
7
* The ASF licenses this file to You under the Apache License, Version 2.0
8
* (the "License"); you may not use this file except in compliance with
9
* the License. You may obtain a copy of the License at
11
* http://www.apache.org/licenses/LICENSE-2.0
13
* Unless required by applicable law or agreed to in writing, software
14
* distributed under the License is distributed on an "AS IS" BASIS,
15
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
16
* See the License for the specific language governing permissions and
17
* limitations under the License.
20
import java.io.IOException;
21
import java.util.Date;
24
* Parser for the FBIS docs in trec disks 4+5 collection format
26
public class TrecFBISParser extends TrecDocParser {
28
private static final String HEADER = "<HEADER>";
29
private static final String HEADER_END = "</HEADER>";
30
private static final int HEADER_END_LENGTH = HEADER_END.length();
32
private static final String DATE1 = "<DATE1>";
33
private static final String DATE1_END = "</DATE1>";
35
private static final String TI = "<TI>";
36
private static final String TI_END = "</TI>";
39
public DocData parse(DocData docData, String name, TrecContentSource trecSrc,
40
StringBuilder docBuf, ParsePathType pathType) throws IOException, InterruptedException {
41
int mark = 0; // that much is skipped
42
// optionally skip some of the text, set date, title
45
int h1 = docBuf.indexOf(HEADER);
47
int h2 = docBuf.indexOf(HEADER_END,h1);
48
mark = h2+HEADER_END_LENGTH;
50
String dateStr = extract(docBuf, DATE1, DATE1_END, h2, null);
51
if (dateStr != null) {
52
date = trecSrc.parseDate(dateStr);
55
title = extract(docBuf, TI, TI_END, h2, null);
58
docData.setName(name);
59
docData.setDate(date);
60
docData.setTitle(title);
61
docData.setBody(stripTags(docBuf, mark).toString());