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.kiss;
19 import java.io.InputStream;
20 import java.util.ArrayList;
21 import java.util.Iterator;
22 import java.util.List;
24 import org.dom4j.Attribute;
25 import org.dom4j.Document;
26 import org.dom4j.DocumentException;
27 import org.dom4j.Element;
28 import org.dom4j.io.SAXReader;
29 import org.wamblee.conditions.AndCondition;
30 import org.wamblee.conditions.Condition;
31 import org.wamblee.conditions.PropertyRegexCondition;
34 * Parse the configuration of desired programs.
36 class ProgramConfigurationParser {
38 private static final String ELEM_PROGRAM = "program";
40 private static final String ELEM_PATTERN = "match";
42 private static final String ELEM_ACTION = "action";
44 private static final String ELEM_CATEGORY = "category";
46 private static final String ACTION_NOTIFY = "notify";
49 * Parses the condition used to match the desired programs.
52 * Input stream to parse from.
55 List<ProgramFilter> parse(InputStream aStream) {
56 List<ProgramFilter> filters = new ArrayList<ProgramFilter>();
58 SAXReader reader = new SAXReader();
59 Document document = reader.read(aStream);
61 Element root = document.getRootElement();
63 for (Iterator i = root.elementIterator(ELEM_PROGRAM); i.hasNext();) {
64 Element program = (Element) i.next();
66 Element categoryElem = program.element(ELEM_CATEGORY);
68 if ( categoryElem != null ) {
69 category = categoryElem.getText().trim();
72 Element actionElem = program.element(ELEM_ACTION);
73 ProgramAction action = new RecordProgramAction();
74 if (actionElem != null) {
75 if (actionElem.getText().equals(ACTION_NOTIFY)) {
76 action = new InterestingProgramAction(category);
80 List<Condition<Program>> regexConditions =
81 new ArrayList<Condition<Program>>();
82 for (Iterator j = program.elementIterator(ELEM_PATTERN); j.hasNext(); ) {
83 Element patternElem = (Element)j.next();
84 String fieldName = "name";
85 Attribute fieldAttribute = patternElem.attribute("field");
86 if ( fieldAttribute != null ) {
87 fieldName = fieldAttribute.getText();
89 String pattern = ".*(" + patternElem.getText()
91 regexConditions.add(new PropertyRegexCondition<Program>(fieldName, pattern, true));
93 Condition<Program> condition = new AndCondition<Program>(regexConditions);
94 filters.add(new ProgramFilter(condition, action));
97 } catch (DocumentException e) {
98 throw new RuntimeException("Error parsing program configuraiton", e);