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.io.Reader;
22 import java.text.DateFormat;
23 import java.text.ParseException;
24 import java.util.Date;
25 import java.util.Properties;
28 * HTML Parser that is based on Lucene's demo HTML parser.
30 public class DemoHTMLParser implements org.apache.lucene.benchmark.byTask.feeds.HTMLParser {
32 public DocData parse(DocData docData, String name, Date date, String title, Reader reader, DateFormat dateFormat) throws IOException, InterruptedException {
33 org.apache.lucene.benchmark.byTask.feeds.demohtml.HTMLParser p = new org.apache.lucene.benchmark.byTask.feeds.demohtml.HTMLParser(reader);
41 Properties props = p.getMetaTags();
43 Reader r = p.getReader();
44 char c[] = new char[1024];
45 StringBuilder bodyBuf = new StringBuilder();
47 while ((n = r.read(c)) >= 0) {
49 bodyBuf.append(c,0,n);
53 if (date == null && props.getProperty("date")!=null) {
55 date = dateFormat.parse(props.getProperty("date").trim());
56 } catch (ParseException e) {
57 // do not fail test just because a date could not be parsed
58 System.out.println("ignoring date parse exception (assigning 'now') for: "+props.getProperty("date"));
59 date = new Date(); // now
64 docData.setName(name);
65 docData.setBody(bodyBuf.toString());
66 docData.setTitle(title);
67 docData.setProps(props);
68 docData.setDate(date);