1 /* 2 * Copyright (C) 2013 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 are 6 * met: 7 * 8 * * Redistributions of source code must retain the above copyright 9 * notice, this list of conditions and the following disclaimer. 10 * * Redistributions in binary form must reproduce the above 11 * copyright notice, this list of conditions and the following disclaimer 12 * in the documentation and/or other materials provided with the 13 * distribution. 14 * * Neither the name of Google Inc. nor the names of its 15 * contributors may be used to endorse or promote products derived from 16 * this software without specific prior written permission. 17 * 18 * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS 19 * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT 20 * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR 21 * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT 22 * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, 23 * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT 24 * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, 25 * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY 26 * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT 27 * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE 28 * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. 29 */ 30 31 #include "config.h" 32 33 #include "modules/encoding/TextDecoder.h" 34 35 #include "bindings/v8/ExceptionState.h" 36 #include "core/dom/ExceptionCode.h" 37 #include "wtf/StringExtras.h" 38 #include "wtf/text/TextEncodingRegistry.h" 39 40 namespace WebCore { 41 42 TextDecoder* TextDecoder::create(const String& label, const Dictionary& options, ExceptionState& exceptionState) 43 { 44 const String& encodingLabel = label.isNull() ? String("utf-8") : label; 45 46 WTF::TextEncoding encoding(encodingLabel); 47 // The replacement encoding is not valid, but the Encoding API also 48 // rejects aliases of the replacement encoding. 49 if (!encoding.isValid() || !strcasecmp(encoding.name(), "replacement")) { 50 exceptionState.throwTypeError("The encoding label provided ('" + encodingLabel + "') is invalid."); 51 return 0; 52 } 53 54 bool fatal = false; 55 options.get("fatal", fatal); 56 57 bool ignoreBOM = false; 58 options.get("ignoreBOM", ignoreBOM); 59 60 return new TextDecoder(encoding, fatal, ignoreBOM); 61 } 62 63 64 TextDecoder::TextDecoder(const WTF::TextEncoding& encoding, bool fatal, bool ignoreBOM) 65 : m_encoding(encoding) 66 , m_codec(newTextCodec(encoding)) 67 , m_fatal(fatal) 68 , m_ignoreBOM(ignoreBOM) 69 , m_bomSeen(false) 70 { 71 } 72 73 TextDecoder::~TextDecoder() 74 { 75 } 76 77 String TextDecoder::encoding() const 78 { 79 String name = String(m_encoding.name()).lower(); 80 // Where possible, encoding aliases should be handled by changes to Chromium's ICU or Blink's WTF. 81 // The same codec is used, but WTF maintains a different name/identity for these. 82 if (name == "iso-8859-1" || name == "us-ascii") 83 return "windows-1252"; 84 return name; 85 } 86 87 String TextDecoder::decode(ArrayBufferView* input, const Dictionary& options, ExceptionState& exceptionState) 88 { 89 bool stream = false; 90 options.get("stream", stream); 91 92 const char* start = input ? static_cast<const char*>(input->baseAddress()) : 0; 93 size_t length = input ? input->byteLength() : 0; 94 95 WTF::FlushBehavior flush = stream ? WTF::DoNotFlush : WTF::DataEOF; 96 97 bool sawError = false; 98 String s = m_codec->decode(start, length, flush, m_fatal, sawError); 99 100 if (m_fatal && sawError) { 101 exceptionState.throwDOMException(EncodingError, "The encoded data was not valid."); 102 return String(); 103 } 104 105 if (!m_ignoreBOM && !m_bomSeen && !s.isEmpty()) { 106 m_bomSeen = true; 107 String name(m_encoding.name()); 108 if ((name == "UTF-8" || name == "UTF-16LE" || name == "UTF-16BE") && s[0] == 0xFEFF) 109 s.remove(0); 110 } 111 112 if (flush) 113 m_bomSeen = false; 114 115 return s; 116 } 117 118 } // namespace WebCore 119