1/*
2 * Copyright (C) 2013 Google Inc. All rights reserved.
3 *
4 * Redistribution and use in source and binary forms, with or without
5 * modification, are permitted provided that the following conditions are
6 * met:
7 *
8 *     * Redistributions of source code must retain the above copyright
9 * notice, this list of conditions and the following disclaimer.
10 *     * Redistributions in binary form must reproduce the above
11 * copyright notice, this list of conditions and the following disclaimer
12 * in the documentation and/or other materials provided with the
13 * distribution.
14 *     * Neither the name of Google Inc. nor the names of its
15 * contributors may be used to endorse or promote products derived from
16 * this software without specific prior written permission.
17 *
18 * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
19 * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
20 * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
21 * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
22 * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
23 * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
24 * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
25 * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
26 * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
27 * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
28 * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
29 */
30
31#ifndef StringUTF8Adaptor_h
32#define StringUTF8Adaptor_h
33
34#include "wtf/text/CString.h"
35#include "wtf/text/TextEncoding.h"
36#include "wtf/text/WTFString.h"
37
38namespace WTF {
39
40// This class lets you get UTF-8 data out of a String without mallocing a
41// separate buffer to hold the data if the String happens to be 8 bit and
42// contain only ASCII characters.
43class StringUTF8Adaptor {
44public:
45    enum ShouldNormalize {
46        DoNotNormalize,
47        Normalize
48    };
49
50    explicit StringUTF8Adaptor(const String& string, ShouldNormalize normalize = DoNotNormalize, UnencodableHandling handling = EntitiesForUnencodables)
51        : m_data(0)
52        , m_length(0)
53    {
54        if (string.isEmpty())
55            return;
56        // Unfortunately, 8 bit WTFStrings are encoded in Latin-1 and GURL uses UTF-8
57        // when processing 8 bit strings. If |relative| is entirely ASCII, we luck out
58        // and can avoid mallocing a new buffer to hold the UTF-8 data because UTF-8
59        // and Latin-1 use the same code units for ASCII code points.
60        if (string.is8Bit() && string.containsOnlyASCII()) {
61            m_data = reinterpret_cast<const char*>(string.characters8());
62            m_length = string.length();
63        } else {
64            if (normalize == Normalize)
65                m_utf8Buffer = UTF8Encoding().normalizeAndEncode(string, handling);
66            else
67                m_utf8Buffer = string.utf8();
68            m_data = m_utf8Buffer.data();
69            m_length = m_utf8Buffer.length();
70        }
71    }
72
73    const char* data() const { return m_data; }
74    size_t length() const { return m_length; }
75
76private:
77    CString m_utf8Buffer;
78    const char* m_data;
79    size_t m_length;
80};
81
82} // namespace WTF
83
84using WTF::StringUTF8Adaptor;
85
86#endif // StringUTF8Adaptor_h
87