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 FT docs in trec disks 4+5 collection format
26 public class TrecLATimesParser extends TrecDocParser {
28 private static final String DATE = "<DATE>";
29 private static final String DATE_END = "</DATE>";
30 private static final String DATE_NOISE = "day,"; // anything aftre the ','
32 private static final String SUBJECT = "<SUBJECT>";
33 private static final String SUBJECT_END = "</SUBJECT>";
34 private static final String HEADLINE = "<HEADLINE>";
35 private static final String HEADLINE_END = "</HEADLINE>";
38 public DocData parse(DocData docData, String name, TrecContentSource trecSrc,
39 StringBuilder docBuf, ParsePathType pathType) throws IOException, InterruptedException {
40 int mark = 0; // that much is skipped
44 String dateStr = extract(docBuf, DATE, DATE_END, -1, null);
45 if (dateStr != null) {
46 int d2a = dateStr.indexOf(DATE_NOISE);
48 dateStr = dateStr.substring(0,d2a+3); // we need the "day" part
50 dateStr = stripTags(dateStr,0).toString();
51 date = trecSrc.parseDate(dateStr.trim());
54 // title... first try with SUBJECT, them with HEADLINE
55 String title = extract(docBuf, SUBJECT, SUBJECT_END, -1, null);
57 title = extract(docBuf, HEADLINE, HEADLINE_END, -1, null);
60 title = stripTags(title,0).toString().trim();
64 docData.setName(name);
65 docData.setDate(date);
66 docData.setTitle(title);
67 docData.setBody(stripTags(docBuf, mark).toString());