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 FR94 docs in trec disks 4+5 collection format
26 public class TrecFR94Parser extends TrecDocParser {
28 private static final String TEXT = "<TEXT>";
29 private static final int TEXT_LENGTH = TEXT.length();
30 private static final String TEXT_END = "</TEXT>";
32 private static final String DATE = "<DATE>";
33 private static final String[] DATE_NOISE_PREFIXES = {
35 "date:", //TODO improve date extraction for this format
38 private static final String DATE_END = "</DATE>";
40 //TODO can we also extract title for this format?
43 public DocData parse(DocData docData, String name, TrecContentSource trecSrc,
44 StringBuilder docBuf, ParsePathType pathType) throws IOException, InterruptedException {
45 int mark = 0; // that much is skipped
46 // optionally skip some of the text, set date (no title?)
48 int h1 = docBuf.indexOf(TEXT);
50 int h2 = docBuf.indexOf(TEXT_END,h1);
51 mark = h1+TEXT_LENGTH;
53 String dateStr = extract(docBuf, DATE, DATE_END, h2, DATE_NOISE_PREFIXES);
54 if (dateStr != null) {
55 dateStr = stripTags(dateStr,0).toString();
56 date = trecSrc.parseDate(dateStr.trim());
60 docData.setName(name);
61 docData.setDate(date);
62 docData.setBody(stripTags(docBuf, mark).toString());