1/*
2 * Copyright (c) 1999, 2012, Oracle and/or its affiliates. All rights reserved.
3 * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
4 *
5 * This code is free software; you can redistribute it and/or modify it
6 * under the terms of the GNU General Public License version 2 only, as
7 * published by the Free Software Foundation.  Oracle designates this
8 * particular file as subject to the "Classpath" exception as provided
9 * by Oracle in the LICENSE file that accompanied this code.
10 *
11 * This code is distributed in the hope that it will be useful, but WITHOUT
12 * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
13 * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
14 * version 2 for more details (a copy is included in the LICENSE file that
15 * accompanied this code).
16 *
17 * You should have received a copy of the GNU General Public License version
18 * 2 along with this work; if not, write to the Free Software Foundation,
19 * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.
20 *
21 * Please contact Oracle, 500 Oracle Parkway, Redwood Shores, CA 94065 USA
22 * or visit www.oracle.com if you need additional information or have any
23 * questions.
24 */
25
26package com.sun.jndi.toolkit.url;
27
28import java.net.MalformedURLException;
29import java.io.UnsupportedEncodingException;
30import java.net.URLDecoder;
31
32/**
33 * Utilities for dealing with URLs.
34 * @author Vincent Ryan
35 */
36
37final public class UrlUtil {
38
39    // To prevent creation of this static class
40    private UrlUtil() {
41    }
42
43    /**
44     * Decode a URI string (according to RFC 2396).
45     */
46    public static final String decode(String s) throws MalformedURLException {
47        try {
48            return decode(s, "8859_1");
49        } catch (UnsupportedEncodingException e) {
50            // ISO-Latin-1 should always be available?
51            throw new MalformedURLException("ISO-Latin-1 decoder unavailable");
52        }
53    }
54
55    /**
56     * Decode a URI string (according to RFC 2396).
57     *
58     * Three-character sequences '%xy', where 'xy' is the two-digit
59     * hexadecimal representation of the lower 8-bits of a character,
60     * are decoded into the character itself.
61     *
62     * The string is subsequently converted using the specified encoding
63     */
64    public static final String decode(String s, String enc)
65            throws MalformedURLException, UnsupportedEncodingException {
66        try {
67            return URLDecoder.decode(s, enc);
68        } catch (IllegalArgumentException iae) {
69            MalformedURLException mue = new MalformedURLException("Invalid URI encoding: " + s);
70            mue.initCause(iae);
71            throw mue;
72        }
73    }
74
75    /**
76     * Encode a string for inclusion in a URI (according to RFC 2396).
77     *
78     * Unsafe characters are escaped by encoding them in three-character
79     * sequences '%xy', where 'xy' is the two-digit hexadecimal representation
80     * of the lower 8-bits of the character.
81     *
82     * The question mark '?' character is also escaped, as required by RFC 2255.
83     *
84     * The string is first converted to the specified encoding.
85     * For LDAP (2255), the encoding must be UTF-8.
86     */
87    public static final String encode(String s, String enc)
88        throws UnsupportedEncodingException {
89
90        byte[] bytes = s.getBytes(enc);
91        int count = bytes.length;
92
93        /*
94         * From RFC 2396:
95         *
96         *     mark = "-" | "_" | "." | "!" | "~" | "*" | "'" | "(" | ")"
97         * reserved = ";" | "/" | ":" | "?" | "@" | "&" | "=" | "+" | "$" | ","
98         */
99        final String allowed = "=,+;.'-@&/$_()!~*:"; // '?' is omitted
100        char[] buf = new char[3 * count];
101        int j = 0;
102
103        for (int i = 0; i < count; i++) {
104            if ((bytes[i] >= 0x61 && bytes[i] <= 0x7A) || // a..z
105                (bytes[i] >= 0x41 && bytes[i] <= 0x5A) || // A..Z
106                (bytes[i] >= 0x30 && bytes[i] <= 0x39) || // 0..9
107                (allowed.indexOf(bytes[i]) >= 0)) {
108                buf[j++] = (char) bytes[i];
109            } else {
110                buf[j++] = '%';
111                buf[j++] = Character.forDigit(0xF & (bytes[i] >>> 4), 16);
112                buf[j++] = Character.forDigit(0xF & bytes[i], 16);
113            }
114        }
115        return new String(buf, 0, j);
116    }
117}
118