Home | History | Annotate | Download | only in text 
      1 /*
      2  * Copyright (C) 2007, 2008 Apple, 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 COMPUTER, 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 COMPUTER, 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 #include "config.h"
     27 #include "wtf/text/TextCodecUserDefined.h"
     28 
     29 #include "wtf/PassOwnPtr.h"
     30 #include "wtf/text/CString.h"
     31 #include "wtf/text/StringBuffer.h"
     32 #include "wtf/text/StringBuilder.h"
     33 #include "wtf/text/WTFString.h"
     34 
     35 namespace WTF {
     36 
     37 void TextCodecUserDefined::registerEncodingNames(EncodingNameRegistrar registrar)
     38 {
     39     registrar("x-user-defined", "x-user-defined");
     40 }
     41 
     42 static PassOwnPtr<TextCodec> newStreamingTextDecoderUserDefined(const TextEncoding&, const void*)
     43 {
     44     return adoptPtr(new TextCodecUserDefined);
     45 }
     46 
     47 void TextCodecUserDefined::registerCodecs(TextCodecRegistrar registrar)
     48 {
     49     registrar("x-user-defined", newStreamingTextDecoderUserDefined, 0);
     50 }
     51 
     52 String TextCodecUserDefined::decode(const char* bytes, size_t length, FlushBehavior, bool, bool&)
     53 {
     54     StringBuilder result;
     55     result.reserveCapacity(length);
     56 
     57     for (size_t i = 0; i < length; ++i) {
     58         signed char c = bytes[i];
     59         result.append(static_cast<UChar>(c & 0xF7FF));
     60     }
     61 
     62     return result.toString();
     63 }
     64 
     65 template<typename CharType>
     66 static CString encodeComplexUserDefined(const CharType* characters, size_t length, UnencodableHandling handling)
     67 {
     68     Vector<char> result(length);
     69     char* bytes = result.data();
     70 
     71     size_t resultLength = 0;
     72     for (size_t i = 0; i < length; ) {
     73         UChar32 c;
     74         U16_NEXT(characters, i, length, c);
     75         signed char signedByte = c;
     76         if ((signedByte & 0xF7FF) == c)
     77             bytes[resultLength++] = signedByte;
     78         else {
     79             // No way to encode this character with x-user-defined.
     80             UnencodableReplacementArray replacement;
     81             int replacementLength = TextCodec::getUnencodableReplacement(c, handling, replacement);
     82             result.grow(resultLength + replacementLength + length - i);
     83             bytes = result.data();
     84             memcpy(bytes + resultLength, replacement, replacementLength);
     85             resultLength += replacementLength;
     86         }
     87     }
     88 
     89     return CString(bytes, resultLength);
     90 }
     91 
     92 template<typename CharType>
     93 CString TextCodecUserDefined::encodeCommon(const CharType* characters, size_t length, UnencodableHandling handling)
     94 {
     95     char* bytes;
     96     CString result = CString::newUninitialized(length, bytes);
     97 
     98     // Convert the string a fast way and simultaneously do an efficient check to see if it's all ASCII.
     99     UChar ored = 0;
    100     for (size_t i = 0; i < length; ++i) {
    101         UChar c = characters[i];
    102         bytes[i] = c;
    103         ored |= c;
    104     }
    105 
    106     if (!(ored & 0xFF80))
    107         return result;
    108 
    109     // If it wasn't all ASCII, call the function that handles more-complex cases.
    110     return encodeComplexUserDefined(characters, length, handling);
    111 }
    112 
    113 CString TextCodecUserDefined::encode(const UChar* characters, size_t length, UnencodableHandling handling)
    114 {
    115     return encodeCommon(characters, length, handling);
    116 }
    117 
    118 CString TextCodecUserDefined::encode(const LChar* characters, size_t length, UnencodableHandling handling)
    119 {
    120     return encodeCommon(characters, length, handling);
    121 }
    122 
    123 } // namespace WTF
    124