1/*
2 * Copyright (C) 2004, 2006 Apple Computer, Inc.  All rights reserved.
3 * Copyright (C) 2006 Alexey Proskuryakov <ap@nypop.com>
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 * 1. Redistributions of source code must retain the above copyright
9 *    notice, this list of conditions and the following disclaimer.
10 * 2. Redistributions in binary form must reproduce the above copyright
11 *    notice, this list of conditions and the following disclaimer in the
12 *    documentation and/or other materials provided with the distribution.
13 *
14 * THIS SOFTWARE IS PROVIDED BY APPLE COMPUTER, INC. ``AS IS'' AND ANY
15 * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
16 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
17 * PURPOSE ARE DISCLAIMED.  IN NO EVENT SHALL APPLE COMPUTER, INC. OR
18 * CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
19 * EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
20 * PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
21 * PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY
22 * OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
23 * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
24 * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
25 */
26
27#ifndef TextCodec_h
28#define TextCodec_h
29
30#include "wtf/Forward.h"
31#include "wtf/Noncopyable.h"
32#include "wtf/PassOwnPtr.h"
33#include "wtf/text/WTFString.h"
34#include "wtf/unicode/Unicode.h"
35
36namespace WTF {
37
38class TextEncoding;
39
40// Specifies what will happen when a character is encountered that is
41// not encodable in the character set.
42enum UnencodableHandling {
43    // Substitutes the replacement character "?".
44    QuestionMarksForUnencodables,
45
46    // Encodes the character as an XML entity. For example, U+06DE
47    // would be "&#1758;" (0x6DE = 1758 in octal).
48    EntitiesForUnencodables,
49
50    // Encodes the character as en entity as above, but escaped
51    // non-alphanumeric characters. This is used in URLs.
52    // For example, U+6DE would be "%26%231758%3B".
53    URLEncodedEntitiesForUnencodables
54};
55
56typedef char UnencodableReplacementArray[32];
57
58enum FlushBehavior {
59    // More bytes are coming, don't flush the codec.
60    DoNotFlush = 0,
61
62    // A fetch has hit EOF. Some codecs handle fetches differently, for compat reasons.
63    FetchEOF,
64
65    // Do a full flush of the codec.
66    DataEOF
67};
68
69COMPILE_ASSERT(!DoNotFlush, DoNotFlush_is_falsy);
70COMPILE_ASSERT(FetchEOF, FetchEOF_is_truthy);
71COMPILE_ASSERT(DataEOF, DataEOF_is_truthy);
72
73
74class TextCodec {
75    WTF_MAKE_NONCOPYABLE(TextCodec); WTF_MAKE_FAST_ALLOCATED;
76public:
77    TextCodec() { }
78    virtual ~TextCodec();
79
80    String decode(const char* str, size_t length, FlushBehavior flush = DoNotFlush)
81    {
82        bool ignored;
83        return decode(str, length, flush, false, ignored);
84    }
85
86    virtual String decode(const char*, size_t length, FlushBehavior, bool stopOnError, bool& sawError) = 0;
87    virtual CString encode(const UChar*, size_t length, UnencodableHandling) = 0;
88    virtual CString encode(const LChar*, size_t length, UnencodableHandling) = 0;
89
90    // Fills a null-terminated string representation of the given
91    // unencodable character into the given replacement buffer.
92    // The length of the string (not including the null) will be returned.
93    static int getUnencodableReplacement(unsigned codePoint, UnencodableHandling, UnencodableReplacementArray);
94};
95
96typedef void (*EncodingNameRegistrar)(const char* alias, const char* name);
97
98typedef PassOwnPtr<TextCodec> (*NewTextCodecFunction)(const TextEncoding&, const void* additionalData);
99typedef void (*TextCodecRegistrar)(const char* name, NewTextCodecFunction, const void* additionalData);
100
101} // namespace WTF
102
103using WTF::TextCodec;
104
105#endif // TextCodec_h
106