org.apache.lucene.benchmark.quality.trec.TrecTopicsReader Maven / Gradle / Ivy
Go to download
Show more of this group Show more artifacts with this name
Show all versions of lucene-benchmark Show documentation
Show all versions of lucene-benchmark Show documentation
Apache Lucene (module: benchmark)
/**
* Licensed to the Apache Software Foundation (ASF) under one or more
* contributor license agreements. See the NOTICE file distributed with
* this work for additional information regarding copyright ownership.
* The ASF licenses this file to You under the Apache License, Version 2.0
* (the "License"); you may not use this file except in compliance with
* the License. You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
package org.apache.lucene.benchmark.quality.trec;
import java.io.BufferedReader;
import java.io.IOException;
import java.util.ArrayList;
import java.util.Arrays;
import java.util.HashMap;
import org.apache.lucene.benchmark.quality.QualityQuery;
/**
* Read TREC topics.
*
* Expects this topic format -
*
* <top>
* <num> Number: nnn
*
* <title> title of the topic
*
* <desc> Description:
* description of the topic
*
* <narr> Narrative:
* "story" composed by assessors.
*
* </top>
*
* Comment lines starting with '#' are ignored.
*/
public class TrecTopicsReader {
private static final String newline = System.getProperty("line.separator");
/**
* Constructor for Trec's TopicsReader
*/
public TrecTopicsReader() {
super();
}
/**
* Read quality queries from trec format topics file.
* @param reader where queries are read from.
* @return the result quality queries.
* @throws IOException if cannot read the queries.
*/
public QualityQuery[] readQueries(BufferedReader reader) throws IOException {
ArrayList res = new ArrayList();
StringBuffer sb;
try {
while (null!=(sb=read(reader,"",null,false,false))) {
HashMap fields = new HashMap();
// id
sb = read(reader,"",null,true,false);
int k = sb.indexOf(":");
String id = sb.substring(k+1).trim();
// title
sb = read(reader,"",null,true,false);
k = sb.indexOf(">");
String title = sb.substring(k+1).trim();
// description
sb = read(reader,"",null,false,false);
sb = read(reader,"",null,false,true);
String descripion = sb.toString().trim();
// we got a topic!
fields.put("title",title);
fields.put("description",descripion);
QualityQuery topic = new QualityQuery(id,fields);
res.add(topic);
// skip narrative, get to end of doc
read(reader," ",null,false,false);
}
} finally {
reader.close();
}
// sort result array (by ID)
QualityQuery qq[] = (QualityQuery[]) res.toArray(new QualityQuery[0]);
Arrays.sort(qq);
return qq;
}
// read until finding a line that starts with the specified prefix
private StringBuffer read (BufferedReader reader, String prefix, StringBuffer sb, boolean collectMatchLine, boolean collectAll) throws IOException {
sb = (sb==null ? new StringBuffer() : sb);
String sep = "";
while (true) {
String line = reader.readLine();
if (line==null) {
return null;
}
if (line.startsWith(prefix)) {
if (collectMatchLine) {
sb.append(sep+line);
sep = newline;
}
break;
}
if (collectAll) {
sb.append(sep+line);
sep = newline;
}
}
//System.out.println("read: "+sb);
return sb;
}
}