Java > Open Source Codes > org > ejbca > util > HTMLTools


1 /*
2  * ====================================================================
3  * Copyright (c) 1995-1999 Purple Technology, Inc. All rights
4  * reserved.
5  *
6  * PLAIN LANGUAGE LICENSE: Do whatever you like with this code, free
7  * of charge, just give credit where credit is due. If you improve it,
8  * please send your improvements to alex@purpletech.com. Check
9  * http://www.purpletech.com/code/ for the latest version and news.
10  *
11  * LEGAL LANGUAGE LICENSE: Redistribution and use in source and binary
12  * forms, with or without modification, are permitted provided that
13  * the following conditions are met:
14  *
15  * 1. Redistributions of source code must retain the above copyright
16  * notice, this list of conditions and the following disclaimer.
17  *
18  * 2. Redistributions in binary form must reproduce the above
19  * copyright notice, this list of conditions and the following
20  * disclaimer in the documentation and/or other materials provided
21  * with the distribution.
22  *
23  * 3. The names of the authors and the names "Purple Technology,"
24  * "Purple Server" and "Purple Chat" must not be used to endorse or
25  * promote products derived from this software without prior written
26  * permission. For written permission, please contact
27  * server@purpletech.com.
28  *
29  * THIS SOFTWARE IS PROVIDED BY THE AUTHORS AND PURPLE TECHNOLOGY ``AS
30  * IS'' AND ANY EXPRESSED OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
31  * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
32  * FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE
33  * AUTHORS OR PURPLE TECHNOLOGY BE LIABLE FOR ANY DIRECT, INDIRECT,
34  * INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
35  * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
36  * SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
37  * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT,
38  * STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
39  * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED
40  * OF THE POSSIBILITY OF SUCH DAMAGE.
41  *
42  * ====================================================================
43  *
44  **/
45 package org.ejbca.util;
46
47 import java.util.HashMap ;
48 import java.util.Map ;
49
50 public class HTMLTools {
51 // see http://hotwired.lycos.com/webmonkey/reference/special_characters/
52 static Object [][] entities = {
53        // {"#39", new Integer(39)}, // ' - apostrophe
54 {"quot", new Integer (34)}, // " - double-quote
55 {"amp", new Integer (38)}, // & - ampersand
56 {"lt", new Integer (60)}, // < - less-than
57 {"gt", new Integer (62)}, // > - greater-than
58 {"nbsp", new Integer (160)}, // non-breaking space
59 {"copy", new Integer (169)}, // © - copyright
60 {"reg", new Integer (174)}, // ® - registered trademark
61 {"Agrave", new Integer (192)}, // À - uppercase A, grave accent
62 {"Aacute", new Integer (193)}, // Ã? - uppercase A, acute accent
63 {"Acirc", new Integer (194)}, // Â - uppercase A, circumflex accent
64 {"Atilde", new Integer (195)}, // Ã - uppercase A, tilde
65 {"Auml", new Integer (196)}, // Ä - uppercase A, umlaut
66 {"Aring", new Integer (197)}, // Ã… - uppercase A, ring
67 {"AElig", new Integer (198)}, // Æ - uppercase AE
68 {"Ccedil", new Integer (199)}, // Ç - uppercase C, cedilla
69 {"Egrave", new Integer (200)}, // È - uppercase E, grave accent
70 {"Eacute", new Integer (201)}, // É - uppercase E, acute accent
71 {"Ecirc", new Integer (202)}, // Ê - uppercase E, circumflex accent
72 {"Euml", new Integer (203)}, // Ë - uppercase E, umlaut
73 {"Igrave", new Integer (204)}, // Ì - uppercase I, grave accent
74 {"Iacute", new Integer (205)}, // Ã? - uppercase I, acute accent
75 {"Icirc", new Integer (206)}, // ÃŽ - uppercase I, circumflex accent
76 {"Iuml", new Integer (207)}, // Ã? - uppercase I, umlaut
77 {"ETH", new Integer (208)}, // Ã? - uppercase Eth, Icelandic
78 {"Ntilde", new Integer (209)}, // Ñ - uppercase N, tilde
79 {"Ograve", new Integer (210)}, // Ã’ - uppercase O, grave accent
80 {"Oacute", new Integer (211)}, // Ó - uppercase O, acute accent
81 {"Ocirc", new Integer (212)}, // Ô - uppercase O, circumflex accent
82 {"Otilde", new Integer (213)}, // Õ - uppercase O, tilde
83 {"Ouml", new Integer (214)}, // Ö - uppercase O, umlaut
84 {"Oslash", new Integer (216)}, // Ø - uppercase O, slash
85 {"Ugrave", new Integer (217)}, // Ù - uppercase U, grave accent
86 {"Uacute", new Integer (218)}, // Ú - uppercase U, acute accent
87 {"Ucirc", new Integer (219)}, // Û - uppercase U, circumflex accent
88 {"Uuml", new Integer (220)}, // Ü - uppercase U, umlaut
89 {"Yacute", new Integer (221)}, // Ã? - uppercase Y, acute accent
90 {"THORN", new Integer (222)}, // Þ - uppercase THORN, Icelandic
91 {"szlig", new Integer (223)}, // ß - lowercase sharps, German
92 {"agrave", new Integer (224)}, // à - lowercase a, grave accent
93 {"aacute", new Integer (225)}, // á - lowercase a, acute accent
94 {"acirc", new Integer (226)}, // â - lowercase a, circumflex accent
95 {"atilde", new Integer (227)}, // ã - lowercase a, tilde
96 {"auml", new Integer (228)}, // ä - lowercase a, umlaut
97 {"aring", new Integer (229)}, // å - lowercase a, ring
98 {"aelig", new Integer (230)}, // æ - lowercase ae
99 {"ccedil", new Integer (231)}, // ç - lowercase c, cedilla
100 {"egrave", new Integer (232)}, // è - lowercase e, grave accent
101 {"eacute", new Integer (233)}, // é - lowercase e, acute accent
102 {"ecirc", new Integer (234)}, // ê - lowercase e, circumflex accent
103 {"euml", new Integer (235)}, // ë - lowercase e, umlaut
104 {"igrave", new Integer (236)}, // ì - lowercase i, grave accent
105 {"iacute", new Integer (237)}, // í - lowercase i, acute accent
106 {"icirc", new Integer (238)}, // î - lowercase i, circumflex accent
107 {"iuml", new Integer (239)}, // ï - lowercase i, umlaut
108 {"igrave", new Integer (236)}, // ì - lowercase i, grave accent
109 {"iacute", new Integer (237)}, // í - lowercase i, acute accent
110 {"icirc", new Integer (238)}, // î - lowercase i, circumflex accent
111 {"iuml", new Integer (239)}, // ï - lowercase i, umlaut
112 {"eth", new Integer (240)}, // ð - lowercase eth, Icelandic
113 {"ntilde", new Integer (241)}, // ñ - lowercase n, tilde
114 {"ograve", new Integer (242)}, // ò - lowercase o, grave accent
115 {"oacute", new Integer (243)}, // ó - lowercase o, acute accent
116 {"ocirc", new Integer (244)}, // ô - lowercase o, circumflex accent
117 {"otilde", new Integer (245)}, // õ - lowercase o, tilde
118 {"ouml", new Integer (246)}, // ö - lowercase o, umlaut
119 {"oslash", new Integer (248)}, // ø - lowercase o, slash
120 {"ugrave", new Integer (249)}, // ù - lowercase u, grave accent
121 {"uacute", new Integer (250)}, // ú - lowercase u, acute accent
122 {"ucirc", new Integer (251)}, // û - lowercase u, circumflex accent
123 {"uuml", new Integer (252)}, // ü - lowercase u, umlaut
124 {"yacute", new Integer (253)}, // ý - lowercase y, acute accent
125 {"thorn", new Integer (254)}, // þ - lowercase thorn, Icelandic
126 {"yuml", new Integer (255)}, // ÿ - lowercase y, umlaut
127 {"euro", new Integer (8364)}, // Euro symbol
128 };
129     static Map e2i = new HashMap ();
130     static Map i2e = new HashMap ();
131     static {
132         for (int i=0; i<entities.length; ++i) {
133             e2i.put(entities[i][0], entities[i][1]);
134             i2e.put(entities[i][1], entities[i][0]);
135         }
136     }
137
138     /**
139      * Turns funky characters into HTML entity equivalents<p>
140      * e.g. <tt>"bread" & "butter"</tt> => <tt>&amp;quot;bread&amp;quot; &amp;amp; &amp;quot;butter&amp;quot;</tt>.
141      * Update: supports nearly all HTML entities, including funky accents. See the source code for more detail.
142      * @see #htmlunescape(String)
143      **/
144     public static String htmlescape(String s1)
145     {
146         if (s1 == null) return null;
147         StringBuffer buf = new StringBuffer ();
148         int i;
149         for (i=0; i<s1.length(); ++i) {
150             char ch = s1.charAt(i);
151             String entity = (String )i2e.get( new Integer (ch) );
152             if (entity == null) {
153                 if ((ch) > 128) {
154                     buf.append("&#" + ((int)ch) + ";");
155                 }
156                 else {
157                     buf.append(ch);
158                 }
159             }
160             else {
161                 buf.append("&" + entity + ";");
162             }
163         }
164         return buf.toString();
165     }
166
167     /**
168      * Given a string containing entity escapes, returns a string
169      * containing the actual Unicode characters corresponding to the
170      * escapes.
171      *
172      * Note: nasty bug fixed by Helge Tesgaard (and, in parallel, by
173      * Alex, but Helge deserves major props for emailing me the fix).
174      * 15-Feb-2002 Another bug fixed by Sean Brown <sean@boohai.com>
175      *
176      * @see #htmlescape(String)
177      **/
178     public static String htmlunescape(String s1) {
179         if (s1 == null) return null;
180         StringBuffer buf = new StringBuffer ();
181         int i;
182         for (i=0; i<s1.length(); ++i) {
183             char ch = s1.charAt(i);
184             if (ch == '&') {
185                 int semi = s1.indexOf(';', i+1);
186                 if (semi == -1) {
187                     buf.append(ch);
188                     continue;
189                 }
190                 String entity = s1.substring(i+1, semi);
191                 Integer iso;
192                 if (entity.charAt(0) == '#') {
193                     iso = new Integer (entity.substring(1));
194                 }
195                 else {
196                     iso = (Integer )e2i.get(entity);
197                 }
198                 if (iso == null) {
199                     buf.append("&" + entity + ";");
200                 }
201                 else {
202                     buf.append((char)(iso.intValue()));
203                 }
204                 i = semi;
205             }
206             else {
207                 buf.append(ch);
208             }
209         }
210         return buf.toString();
211     }
212 }
213

A to Z: JavaDoc & Examples

---

Daily Java News & Articles

---

Open Source Projects

---

Open Source Codes

---

Free Computer Books

---

Remove Frame

---

Popular Tags