2 * Copyright 2005 the original author or authors.
4 * Licensed under the Apache License, Version 2.0 (the "License");
5 * you may not use this file except in compliance with the License.
6 * You may obtain a copy of the License at
8 * http://www.apache.org/licenses/LICENSE-2.0
10 * Unless required by applicable law or agreed to in writing, software
11 * distributed under the License is distributed on an "AS IS" BASIS,
12 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
13 * See the License for the specific language governing permissions and
14 * limitations under the License.
17 package org.wamblee.crawler.impl;
19 import java.util.List;
21 import org.wamblee.crawler.Configuration;
22 import org.wamblee.crawler.PageRequest;
23 import org.wamblee.crawler.PageType;
26 * Implementation of the configuration for the crawler.
28 * @author Erik Brakkee
30 public class ConfigurationImpl implements Configuration {
32 private List<UrlConfig> _urlConfig;
34 private List<PageTypeConfig> _pageTypeConfig;
37 * Constructs the configuration.
38 * @param aUrlConfig List of URL configuration elements.
39 * @param aPageTypeConfig List of page type configuration elements.
41 public ConfigurationImpl(List<UrlConfig> aUrlConfig,
42 List<PageTypeConfig> aPageTypeConfig) {
43 _urlConfig = aUrlConfig;
44 _pageTypeConfig = aPageTypeConfig;
50 * @see org.wamblee.crawler.Configuration#getRequest(java.lang.String)
52 public PageRequest getRequest(String aUrl) {
54 for (UrlConfig config : _urlConfig) {
55 PageRequest request = config.getRequest(aUrl);
56 if (request != null) {
60 throw new RuntimeException("No configuration matched the URL '" + aUrl
67 * @see org.wamblee.crawler.Configuration#getRequest(org.wamblee.crawler.PageType)
69 public PageRequest getRequest(PageType aType) {
70 for (PageTypeConfig config : _pageTypeConfig) {
71 PageRequest request = config.getRequest(aType.getType());
72 if (request != null) {
76 throw new RuntimeException("No configuration matched type '" + aType