Home | History | Annotate | Download | only in text 
      1 /*
      2  * Copyright (C) 2004, 2006 Apple Computer, Inc.  All rights reserved.
      3  * Copyright (C) 2006 Alexey Proskuryakov <ap (at) 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/Vector.h"
     34 #include "wtf/text/WTFString.h"
     35 #include "wtf/unicode/Unicode.h"
     36 
     37 namespace WTF {
     38 
     39 class TextEncoding;
     40 
     41 // Specifies what will happen when a character is encountered that is
     42 // not encodable in the character set.
     43 enum UnencodableHandling {
     44     // Substitutes the replacement character "?".
     45     QuestionMarksForUnencodables,
     46 
     47     // Encodes the character as an XML entity. For example, U+06DE
     48     // would be "&#1758;" (0x6DE = 1758 in octal).
     49     EntitiesForUnencodables,
     50 
     51     // Encodes the character as en entity as above, but escaped
     52     // non-alphanumeric characters. This is used in URLs.
     53     // For example, U+6DE would be "%26%231758%3B".
     54     URLEncodedEntitiesForUnencodables
     55 };
     56 
     57 typedef char UnencodableReplacementArray[32];
     58 
     59 enum FlushBehavior {
     60     // More bytes are coming, don't flush the codec.
     61     DoNotFlush = 0,
     62 
     63     // A fetch has hit EOF. Some codecs handle fetches differently, for compat reasons.
     64     FetchEOF,
     65 
     66     // Do a full flush of the codec.
     67     DataEOF
     68 };
     69 
     70 COMPILE_ASSERT(!DoNotFlush, DoNotFlush_is_falsy);
     71 COMPILE_ASSERT(FetchEOF, FetchEOF_is_truthy);
     72 COMPILE_ASSERT(DataEOF, DataEOF_is_truthy);
     73 
     74 
     75 class TextCodec {
     76     WTF_MAKE_NONCOPYABLE(TextCodec); WTF_MAKE_FAST_ALLOCATED;
     77 public:
     78     TextCodec() { }
     79     virtual ~TextCodec();
     80 
     81     String decode(const char* str, size_t length, FlushBehavior flush = DoNotFlush)
     82     {
     83         bool ignored;
     84         return decode(str, length, flush, false, ignored);
     85     }
     86 
     87     virtual String decode(const char*, size_t length, FlushBehavior, bool stopOnError, bool& sawError) = 0;
     88     virtual CString encode(const UChar*, size_t length, UnencodableHandling) = 0;
     89     virtual CString encode(const LChar*, size_t length, UnencodableHandling) = 0;
     90 
     91     // Fills a null-terminated string representation of the given
     92     // unencodable character into the given replacement buffer.
     93     // The length of the string (not including the null) will be returned.
     94     static int getUnencodableReplacement(unsigned codePoint, UnencodableHandling, UnencodableReplacementArray);
     95 };
     96 
     97 typedef void (*EncodingNameRegistrar)(const char* alias, const char* name);
     98 
     99 typedef PassOwnPtr<TextCodec> (*NewTextCodecFunction)(const TextEncoding&, const void* additionalData);
    100 typedef void (*TextCodecRegistrar)(const char* name, NewTextCodecFunction, const void* additionalData);
    101 
    102 } // namespace WTF
    103 
    104 using WTF::TextCodec;
    105 
    106 #endif // TextCodec_h
    107