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.util.Date;
26
* HTML Parsing Interface for test purposes
28
public interface HTMLParser {
31
* Parse the input Reader and return DocData.
32
* The provided name,title,date are used for the result, unless when they're null,
33
* in which case an attempt is made to set them from the parsed data.
34
* @param docData result reused
35
* @param name name of the result doc data.
36
* @param date date of the result doc data. If null, attempt to set by parsed data.
37
* @param title title of the result doc data. If null, attempt to set by parsed data.
38
* @param reader reader of html text to parse.
39
* @param dateFormat date formatter to use for extracting the date.
40
* @return Parsed doc data.
42
* @throws InterruptedException
44
public DocData parse(DocData docData, String name, Date date, String title, Reader reader, DateFormat dateFormat) throws IOException, InterruptedException;