You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

190 lines
5.7 KiB

// 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.
function assertEncoding(encoding) {
if (encoding && !Buffer.isEncoding(encoding)) {
throw new Error('Unknown encoding: ' + encoding);
}
}
14 years ago
var StringDecoder = exports.StringDecoder = function(encoding) {
this.encoding = (encoding || 'utf8').toLowerCase().replace(/[-_]/, '');
assertEncoding(encoding);
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;
case 'base64':
// Base-64 stores 3 bytes in 4 chars, and pads the remainder.
this.surrogateSize = 3;
this.detectIncompleteChar = base64DetectIncompleteChar;
break;
default:
this.write = passThroughWrite;
return;
}
this.charBuffer = new Buffer(6);
this.charReceived = 0;
this.charLength = 0;
};
14 years ago
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
14 years ago
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;
14 years ago
// Figure out if one of the last i bytes of our buffer announces an
// incomplete char.
for (; i > 0; i--) {
14 years ago
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;
};
StringDecoder.prototype.end = function(buffer) {
var res = '';
if (buffer && buffer.length)
res = this.write(buffer);
if (this.charReceived) {
var cr = this.charReceived;
var buf = this.charBuffer;
var enc = this.encoding;
res += buf.slice(0, cr).toString(enc);
}
return res;
};
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;
}
function base64DetectIncompleteChar(buffer) {
var incomplete = this.charReceived = buffer.length % 3;
this.charLength = incomplete ? 3 : 0;
return incomplete;
}