1 package org.apache.maven.doxia.linkcheck;
2
3 /*
4 * Licensed to the Apache Software Foundation (ASF) under one
5 * or more contributor license agreements. See the NOTICE file
6 * distributed with this work for additional information
7 * regarding copyright ownership. The ASF licenses this file
8 * to you under the Apache License, Version 2.0 (the
9 * "License"); you may not use this file except in compliance
10 * with the License. You may obtain a copy of the License at
11 *
12 * http://www.apache.org/licenses/LICENSE-2.0
13 *
14 * Unless required by applicable law or agreed to in writing,
15 * software distributed under the License is distributed on an
16 * "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
17 * KIND, either express or implied. See the License for the
18 * specific language governing permissions and limitations
19 * under the License.
20 */
21
22 import java.io.File;
23 import java.io.IOException;
24 import java.io.Reader;
25 import java.util.Locale;
26 import java.util.Set;
27 import java.util.TreeSet;
28 import java.util.regex.Matcher;
29 import java.util.regex.Pattern;
30
31 import org.codehaus.plexus.util.IOUtil;
32 import org.codehaus.plexus.util.ReaderFactory;
33
34 /**
35 * Link matcher. Reads the contents of a file and tries to match the following:
36 * <pre>
37 * <a href="".../>
38 * <link href="".../>
39 * <img src="".../>
40 * <script src="".../>
41 * </pre>
42 *
43 * @author <a href="mailto:mac@apache.org">Ignacio G. Mac Dowell </a>
44 * @version $Id: LinkMatcher.java 800044 2009-08-02 12:28:50Z vsiveton $
45 */
46 class LinkMatcher
47 {
48 /** Regexp for link matching. */
49 private static final Pattern MATCH_PATTERN =
50 Pattern.compile( "<(?>link|a|img|script)[^>]*?(?>href|src)\\s*?=\\s*?[\\\"'](.*?)[\\\"'][^>]*?",
51 Pattern.CASE_INSENSITIVE );
52
53 /** No need to create a new object each time a file is processed. Just clear it. */
54 private static final Set LINK_LIST = new TreeSet();
55
56 private LinkMatcher()
57 {
58 // nop
59 }
60
61 /**
62 * Reads a file and returns its contents without any XML comments.
63 *
64 * @param file the file we are reading
65 * @param encoding the encoding file used
66 * @return a StringBuffer with file's contents.
67 * @throws IOException if something goes wrong.
68 * @see ReaderFactory#newReader(File, String)
69 * @see IOUtil#toString(Reader)
70 */
71 private static String toString( File file, String encoding )
72 throws IOException
73 {
74 String content;
75 Reader reader = null;
76 try
77 {
78 reader = ReaderFactory.newReader( file, encoding );
79
80 content = IOUtil.toString( reader );
81 }
82 finally
83 {
84 IOUtil.close( reader );
85 }
86
87 // some link could be in comments, remove them
88 return content.replaceAll( "(?s)<!--.*?-->", "" );
89 }
90
91 /**
92 * Performs the actual matching.
93 *
94 * @param file the file to check
95 * @param encoding the encoding file used
96 * @return a set with all links to check
97 * @throws IOException if something goes wrong
98 */
99 static Set match( File file, String encoding )
100 throws IOException
101 {
102 LINK_LIST.clear();
103
104 final Matcher m = MATCH_PATTERN.matcher( toString( file, encoding ) );
105
106 String link;
107
108 while ( m.find() )
109 {
110 link = m.group( 1 ).trim();
111
112 if ( link.length() < 1 )
113 {
114 continue;
115 }
116 else if ( link.toLowerCase( Locale.ENGLISH ).indexOf( "javascript" ) != -1 )
117 {
118 continue;
119 }
120 // TODO: Review dead code and delete if not needed
121 // else if (link.toLowerCase( Locale.ENGLISH ).indexOf("mailto:") != -1) {
122 // continue;
123 // }
124
125 LINK_LIST.add( link );
126 }
127
128 return LINK_LIST;
129 }
130 }