|
1 /** |
|
2 * Copyright (c) 2012, Ben Fortuna |
|
3 * All rights reserved. |
|
4 * |
|
5 * Redistribution and use in source and binary forms, with or without |
|
6 * modification, are permitted provided that the following conditions |
|
7 * are met: |
|
8 * |
|
9 * o Redistributions of source code must retain the above copyright |
|
10 * notice, this list of conditions and the following disclaimer. |
|
11 * |
|
12 * o Redistributions in binary form must reproduce the above copyright |
|
13 * notice, this list of conditions and the following disclaimer in the |
|
14 * documentation and/or other materials provided with the distribution. |
|
15 * |
|
16 * o Neither the name of Ben Fortuna nor the names of any other contributors |
|
17 * may be used to endorse or promote products derived from this software |
|
18 * without specific prior written permission. |
|
19 * |
|
20 * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS |
|
21 * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT |
|
22 * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR |
|
23 * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR |
|
24 * CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, |
|
25 * EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, |
|
26 * PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR |
|
27 * PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF |
|
28 * LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING |
|
29 * NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS |
|
30 * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. |
|
31 */ |
|
32 package net.fortuna.ical4j.util; |
|
33 |
|
34 import java.net.URI; |
|
35 import java.net.URISyntaxException; |
|
36 import java.util.regex.Pattern; |
|
37 |
|
38 /** |
|
39 * $Id$ |
|
40 * |
|
41 * Created on 11/09/2005 |
|
42 * |
|
43 * Utility methods for working with URIs. |
|
44 * @author Ben Fortuna |
|
45 */ |
|
46 public final class Uris { |
|
47 |
|
48 /** |
|
49 * URI Scheme used when relaxed parsing is enabled and the given input stream lead to an invalid URI. |
|
50 */ |
|
51 public static final String INVALID_SCHEME = "net.fortunal.ical4j.invalid"; |
|
52 |
|
53 private static final Pattern CID_PATTERN = Pattern.compile("(?i)^cid:.*"); |
|
54 private static final Pattern NOTES_CID_REPLACEMENT_PATTERN = Pattern.compile("[<>]"); |
|
55 |
|
56 /** |
|
57 * Constructor made private to enforce static nature. |
|
58 */ |
|
59 private Uris() { |
|
60 } |
|
61 |
|
62 /** |
|
63 * Encodes the specified URI string using the UTF-8 charset. In the event that an exception is thrown, the specifed |
|
64 * URI string is returned unmodified. |
|
65 * @param s a URI string |
|
66 * @return an encoded URI string |
|
67 */ |
|
68 public static String encode(final String s) { |
|
69 /* |
|
70 * try { return URLEncoder.encode(s, ENCODING_CHARSET); } catch (UnsupportedEncodingException use) { |
|
71 * log.error("Error ocurred encoding URI [" + s + "]", use); } |
|
72 */ |
|
73 |
|
74 /* |
|
75 * Lotus Notes does not correctly strip angle brackets from cid uris. From RFC2392: A "cid" URL is converted to |
|
76 * the corresponding Content-ID message header [MIME] by removing the "cid:" prefix, converting the % encoded |
|
77 * character to their equivalent US-ASCII characters, and enclosing the remaining parts with an angle bracket |
|
78 * pair, "<" and ">". For example, "cid:foo4%25foo1@bar.net" corresponds to Content-ID: <foo4%25foo1@bar.net> |
|
79 * Reversing the process and converting URL special characters to their % encodings produces the original cid. A |
|
80 * "mid" URL is converted to a Message-ID or Message-ID/Content-ID pair in a similar fashion. |
|
81 */ |
|
82 if (CompatibilityHints.isHintEnabled(CompatibilityHints.KEY_NOTES_COMPATIBILITY) |
|
83 && CID_PATTERN.matcher(s).matches()) { |
|
84 |
|
85 return NOTES_CID_REPLACEMENT_PATTERN.matcher(s).replaceAll(""); |
|
86 } |
|
87 return s; |
|
88 } |
|
89 |
|
90 /** |
|
91 * Decodes the specified URI string using the UTF-8 charset. In the event that an exception is thrown, the specifed |
|
92 * URI string is returned unmodified. |
|
93 * @param s a URI string |
|
94 * @return an encoded URI string |
|
95 */ |
|
96 public static String decode(final String s) { |
|
97 /* |
|
98 * try { return URLDecoder.decode(s, ENCODING_CHARSET); } catch (UnsupportedEncodingException use) { |
|
99 * log.error("Error ocurred decoding URI [" + s + "]", use); } |
|
100 */ |
|
101 return s; |
|
102 } |
|
103 |
|
104 /** |
|
105 * Attempts to create a URI instance and will optionally swallow any resulting URISyntaxException depending on |
|
106 * configured {@link CompatibilityHints}. Will also automatically attempt encoding of the string representation for |
|
107 * greater compatibility. |
|
108 * <p>When relaxed parsing is enabled and if the string representation is not valid, a second URI creation attempt is made |
|
109 * by extracting the scheme from the scheme specific part and URI encoding that later part. For example, |
|
110 * "mailto: joe smith@example.com" becomes "mailto:joe%20smith@example.com".<p> |
|
111 * <p>If the second attempts also leads to a {@code URISyntaxException}, an opaque URI is constructed with a scheme |
|
112 * of {@code Uris.INVALID_SCHEME} and a value corresponding to the initial representation.</p> |
|
113 * |
|
114 * @param s a string representation of a URI. |
|
115 * @return a URI instance, which may not correspond to the URI string if a valid |
|
116 * URI string is not specified and relaxed parsing is enabled. |
|
117 * @throws URISyntaxException if a valid URI string is not specified and relaxed parsing is disabled |
|
118 */ |
|
119 public static URI create(final String s) throws URISyntaxException { |
|
120 try { |
|
121 return new URI(encode(s)); |
|
122 } |
|
123 catch (URISyntaxException use) { |
|
124 if (CompatibilityHints |
|
125 .isHintEnabled(CompatibilityHints.KEY_RELAXED_PARSING)) { |
|
126 String encoded = encode(s); |
|
127 int index = encoded.indexOf(':'); |
|
128 if (index != -1 && index < encoded.length() -1) { |
|
129 try { |
|
130 return new URI(encoded.substring(0, index), encoded.substring(index + 1), null); |
|
131 } catch (URISyntaxException use2) { |
|
132 } |
|
133 } |
|
134 try { |
|
135 return new URI(INVALID_SCHEME, s, null); |
|
136 } catch (URISyntaxException use2) { |
|
137 // should not happen as we are building an opaque URI |
|
138 throw new IllegalArgumentException("Could not build URI from " + s); |
|
139 } |
|
140 } |
|
141 throw use; |
|
142 } |
|
143 } |
|
144 } |