1 /*
2  * Copyright (C) 2010 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
6  * are met:
7  * 1. Redistributions of source code must retain the above copyright
8  *    notice, this list of conditions and the following disclaimer.
9  * 2. Redistributions in binary form must reproduce the above copyright
10  *    notice, this list of conditions and the following disclaimer in the
11  *    documentation and/or other materials provided with the distribution.
12  *
13  * THIS SOFTWARE IS PROVIDED BY APPLE INC. ``AS IS'' AND ANY
14  * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
15  * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
16  * PURPOSE ARE DISCLAIMED.  IN NO EVENT SHALL APPLE INC. OR
17  * CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
18  * EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
19  * PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
20  * PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY
21  * OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
22  * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
23  * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
24  */
25 
26 #ifndef HTMLMetaCharsetParser_h
27 #define HTMLMetaCharsetParser_h
28 
29 #include "HTMLToken.h"
30 #include "SegmentedString.h"
31 #include "TextEncoding.h"
32 #include <wtf/Noncopyable.h>
33 
34 namespace WebCore {
35 
36 class HTMLTokenizer;
37 class TextCodec;
38 
39 class HTMLMetaCharsetParser {
40     WTF_MAKE_NONCOPYABLE(HTMLMetaCharsetParser);
41 public:
create()42     static PassOwnPtr<HTMLMetaCharsetParser> create() { return adoptPtr(new HTMLMetaCharsetParser()); }
43 
44     ~HTMLMetaCharsetParser();
45 
46     // Returns true if done checking, regardless whether an encoding is found.
47     bool checkForMetaCharset(const char*, size_t);
48 
encoding()49     const TextEncoding& encoding() { return m_encoding; }
50 
51     typedef Vector<pair<String, String> > AttributeList;
52     // The returned encoding might not be valid.
53     static TextEncoding encodingFromMetaAttributes(const AttributeList&
54 );
55 
56 private:
57     HTMLMetaCharsetParser();
58 
59     bool processMeta();
60     static String extractCharset(const String&);
61 
62     enum Mode {
63         None,
64         Charset,
65         Pragma,
66     };
67 
68     OwnPtr<HTMLTokenizer> m_tokenizer;
69     OwnPtr<TextCodec> m_assumedCodec;
70     SegmentedString m_input;
71     HTMLToken m_token;
72     bool m_inHeadSection;
73 
74     bool m_doneChecking;
75     TextEncoding m_encoding;
76 };
77 
78 }
79 #endif
80