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 <stdio.h>
     30 #include "wtf/PassOwnPtr.h"
     31 #include "wtf/text/CString.h"
     32 #include "wtf/text/StringBuffer.h"
     33 #include "wtf/text/StringBuilder.h"
     34 #include "wtf/text/WTFString.h"
     35 
     36 namespace WTF {
     37 
     38 void TextCodecUserDefined::registerEncodingNames(EncodingNameRegistrar registrar)
     39 {
     40     registrar("x-user-defined", "x-user-defined");
     41 }
     42 
     43 static PassOwnPtr<TextCodec> newStreamingTextDecoderUserDefined(const TextEncoding&, const void*)
     44 {
     45     return adoptPtr(new TextCodecUserDefined);
     46 }
     47 
     48 void TextCodecUserDefined::registerCodecs(TextCodecRegistrar registrar)
     49 {
     50     registrar("x-user-defined", newStreamingTextDecoderUserDefined, 0);
     51 }
     52 
     53 String TextCodecUserDefined::decode(const char* bytes, size_t length, bool, bool, bool&)
     54 {
     55     StringBuilder result;
     56     result.reserveCapacity(length);
     57 
     58     for (size_t i = 0; i < length; ++i) {
     59         signed char c = bytes[i];
     60         result.append(static_cast<UChar>(c & 0xF7FF));
     61     }
     62 
     63     return result.toString();
     64 }
     65 
     66 template<typename CharType>
     67 static CString encodeComplexUserDefined(const CharType* characters, size_t length, UnencodableHandling handling)
     68 {
     69     Vector<char> result(length);
     70     char* bytes = result.data();
     71 
     72     size_t resultLength = 0;
     73     for (size_t i = 0; i < length; ) {
     74         UChar32 c;
     75         U16_NEXT(characters, i, length, c);
     76         signed char signedByte = c;
     77         if ((signedByte & 0xF7FF) == c)
     78             bytes[resultLength++] = signedByte;
     79         else {
     80             // No way to encode this character with x-user-defined.
     81             UnencodableReplacementArray replacement;
     82             int replacementLength = TextCodec::getUnencodableReplacement(c, handling, replacement);
     83             result.grow(resultLength + replacementLength + length - i);
     84             bytes = result.data();
     85             memcpy(bytes + resultLength, replacement, replacementLength);
     86             resultLength += replacementLength;
     87         }
     88     }
     89 
     90     return CString(bytes, resultLength);
     91 }
     92 
     93 template<typename CharType>
     94 CString TextCodecUserDefined::encodeCommon(const CharType* characters, size_t length, UnencodableHandling handling)
     95 {
     96     char* bytes;
     97     CString result = CString::newUninitialized(length, bytes);
     98 
     99     // Convert the string a fast way and simultaneously do an efficient check to see if it's all ASCII.
    100     UChar ored = 0;
    101     for (size_t i = 0; i < length; ++i) {
    102         UChar c = characters[i];
    103         bytes[i] = c;
    104         ored |= c;
    105     }
    106 
    107     if (!(ored & 0xFF80))
    108         return result;
    109 
    110     // If it wasn't all ASCII, call the function that handles more-complex cases.
    111     return encodeComplexUserDefined(characters, length, handling);
    112 }
    113 
    114 CString TextCodecUserDefined::encode(const UChar* characters, size_t length, UnencodableHandling handling)
    115 {
    116     return encodeCommon(characters, length, handling);
    117 }
    118 
    119 CString TextCodecUserDefined::encode(const LChar* characters, size_t length, UnencodableHandling handling)
    120 {
    121     return encodeCommon(characters, length, handling);
    122 }
    123 
    124 } // namespace WTF
    125