node/lib/string_decoder.js at master · magicmonkey/node · GitHub

This repository was archived by the owner on Jun 7, 2020. It is now read-only.

History

156 lines (131 loc) · 4.91 KB

Raw

100

101

102

103

104

105

106

107

108

109

110

111

112

113

114

115

116

117

118

119

120

121

122

123

124

125

126

127

128

129

130

131

132

133

134

135

136

137

138

139

140

141

142

143

144

145

146

147

148

149

150

151

152

153

154

155

156

// Copyright Joyent, Inc. and other Node contributors.

// Permission is hereby granted, free of charge, to any person obtaining a

// copy of this software and associated documentation files (the

// "Software"), to deal in the Software without restriction, including

// without limitation the rights to use, copy, modify, merge, publish,

// distribute, sublicense, and/or sell copies of the Software, and to permit

// persons to whom the Software is furnished to do so, subject to the

// following conditions:

// The above copyright notice and this permission notice shall be included

// in all copies or substantial portions of the Software.

// THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS

// OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF

// MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN

// NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM,

// DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR

// OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE

// USE OR OTHER DEALINGS IN THE SOFTWARE.

var StringDecoder = exports.StringDecoder = function(encoding) {

this.encoding = (encoding || 'utf8').toLowerCase().replace(/[-_]/, '');

switch (this.encoding) {

case 'utf8':

// CESU-8 represents each of Surrogate Pair by 3-bytes

this.surrogateSize = 3;

break;

case 'ucs2':

case 'utf16le':

// UTF-16 represents each of Surrogate Pair by 2-bytes

this.surrogateSize = 2;

this.detectIncompleteChar = utf16DetectIncompleteChar;

break;

default:

this.write = passThroughWrite;

return;

}

this.charBuffer = new Buffer(6);

this.charReceived = 0;

this.charLength = 0;

};

StringDecoder.prototype.write = function(buffer) {

var charStr = '';

var offset = 0;

// if our last write ended with an incomplete multibyte character

while (this.charLength) {

// determine how many remaining bytes this buffer has to offer for this char

var i = (buffer.length >= this.charLength - this.charReceived) ?

this.charLength - this.charReceived :

buffer.length;

// add the new bytes to the char buffer

buffer.copy(this.charBuffer, this.charReceived, offset, i);

this.charReceived += (i - offset);

offset = i;

if (this.charReceived < this.charLength) {

// still not enough chars in this buffer? wait for more ...

return '';

}

// get the character that was split

charStr = this.charBuffer.slice(0, this.charLength).toString(this.encoding);

// lead surrogate (D800-DBFF) is also the incomplete character

var charCode = charStr.charCodeAt(charStr.length - 1);

if (charCode >= 0xD800 && charCode <= 0xDBFF) {

this.charLength += this.surrogateSize;

charStr = '';

continue;

}

this.charReceived = this.charLength = 0;

// if there are no more bytes in this buffer, just emit our char

if (i == buffer.length) return charStr;

// otherwise cut off the characters end from the beginning of this buffer

buffer = buffer.slice(i, buffer.length);

break;

}

var lenIncomplete = this.detectIncompleteChar(buffer);

var end = buffer.length;

if (this.charLength) {

// buffer the incomplete character bytes we got

buffer.copy(this.charBuffer, 0, buffer.length - lenIncomplete, end);

this.charReceived = lenIncomplete;

end -= lenIncomplete;

}

charStr += buffer.toString(this.encoding, 0, end);

var end = charStr.length - 1;

var charCode = charStr.charCodeAt(end);

// lead surrogate (D800-DBFF) is also the incomplete character

if (charCode >= 0xD800 && charCode <= 0xDBFF) {

var size = this.surrogateSize;

this.charLength += size;

this.charReceived += size;

this.charBuffer.copy(this.charBuffer, size, 0, size);

this.charBuffer.write(charStr.charAt(charStr.length - 1), this.encoding);

return charStr.substring(0, end);

}

// or just emit the charStr

return charStr;

};

StringDecoder.prototype.detectIncompleteChar = function(buffer) {

// determine how many bytes we have to check at the end of this buffer

var i = (buffer.length >= 3) ? 3 : buffer.length;

// Figure out if one of the last i bytes of our buffer announces an

// incomplete char.

for (; i > 0; i--) {

var c = buffer[buffer.length - i];

// See http://en.wikipedia.org/wiki/UTF-8#Description

// 110XXXXX

if (i == 1 && c >> 5 == 0x06) {

this.charLength = 2;

break;

}

// 1110XXXX

if (i <= 2 && c >> 4 == 0x0E) {

this.charLength = 3;

break;

}

// 11110XXX

if (i <= 3 && c >> 3 == 0x1E) {

this.charLength = 4;

break;

}

return i;

};

function passThroughWrite(buffer) {

return buffer.toString(this.encoding);

}

function utf16DetectIncompleteChar(buffer) {

var incomplete = this.charReceived = buffer.length % 2;

this.charLength = incomplete ? 2 : 0;

return incomplete;

}

node/lib/string_decoder.js at master · magicmonkey/node · GitHub

Expand file tree

Breadcrumbs

string_decoder.js

Latest commit

History

Breadcrumbs

string_decoder.js

File metadata and controls