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.
		
		
		
		
		
			
		
			
				
					
					
						
							177 lines
						
					
					
						
							4.9 KiB
						
					
					
				
			
		
		
	
	
							177 lines
						
					
					
						
							4.9 KiB
						
					
					
				"use strict"; | 
						|
var Buffer = require("safer-buffer").Buffer; | 
						|
 | 
						|
// Note: UTF16-LE (or UCS2) codec is Node.js native. See encodings/internal.js | 
						|
 | 
						|
// == UTF16-BE codec. ========================================================== | 
						|
 | 
						|
exports.utf16be = Utf16BECodec; | 
						|
function Utf16BECodec() { | 
						|
} | 
						|
 | 
						|
Utf16BECodec.prototype.encoder = Utf16BEEncoder; | 
						|
Utf16BECodec.prototype.decoder = Utf16BEDecoder; | 
						|
Utf16BECodec.prototype.bomAware = true; | 
						|
 | 
						|
 | 
						|
// -- Encoding | 
						|
 | 
						|
function Utf16BEEncoder() { | 
						|
} | 
						|
 | 
						|
Utf16BEEncoder.prototype.write = function(str) { | 
						|
    var buf = Buffer.from(str, 'ucs2'); | 
						|
    for (var i = 0; i < buf.length; i += 2) { | 
						|
        var tmp = buf[i]; buf[i] = buf[i+1]; buf[i+1] = tmp; | 
						|
    } | 
						|
    return buf; | 
						|
} | 
						|
 | 
						|
Utf16BEEncoder.prototype.end = function() { | 
						|
} | 
						|
 | 
						|
 | 
						|
// -- Decoding | 
						|
 | 
						|
function Utf16BEDecoder() { | 
						|
    this.overflowByte = -1; | 
						|
} | 
						|
 | 
						|
Utf16BEDecoder.prototype.write = function(buf) { | 
						|
    if (buf.length == 0) | 
						|
        return ''; | 
						|
 | 
						|
    var buf2 = Buffer.alloc(buf.length + 1), | 
						|
        i = 0, j = 0; | 
						|
 | 
						|
    if (this.overflowByte !== -1) { | 
						|
        buf2[0] = buf[0]; | 
						|
        buf2[1] = this.overflowByte; | 
						|
        i = 1; j = 2; | 
						|
    } | 
						|
 | 
						|
    for (; i < buf.length-1; i += 2, j+= 2) { | 
						|
        buf2[j] = buf[i+1]; | 
						|
        buf2[j+1] = buf[i]; | 
						|
    } | 
						|
 | 
						|
    this.overflowByte = (i == buf.length-1) ? buf[buf.length-1] : -1; | 
						|
 | 
						|
    return buf2.slice(0, j).toString('ucs2'); | 
						|
} | 
						|
 | 
						|
Utf16BEDecoder.prototype.end = function() { | 
						|
} | 
						|
 | 
						|
 | 
						|
// == UTF-16 codec ============================================================= | 
						|
// Decoder chooses automatically from UTF-16LE and UTF-16BE using BOM and space-based heuristic. | 
						|
// Defaults to UTF-16LE, as it's prevalent and default in Node. | 
						|
// http://en.wikipedia.org/wiki/UTF-16 and http://encoding.spec.whatwg.org/#utf-16le | 
						|
// Decoder default can be changed: iconv.decode(buf, 'utf16', {defaultEncoding: 'utf-16be'}); | 
						|
 | 
						|
// Encoder uses UTF-16LE and prepends BOM (which can be overridden with addBOM: false). | 
						|
 | 
						|
exports.utf16 = Utf16Codec; | 
						|
function Utf16Codec(codecOptions, iconv) { | 
						|
    this.iconv = iconv; | 
						|
} | 
						|
 | 
						|
Utf16Codec.prototype.encoder = Utf16Encoder; | 
						|
Utf16Codec.prototype.decoder = Utf16Decoder; | 
						|
 | 
						|
 | 
						|
// -- Encoding (pass-through) | 
						|
 | 
						|
function Utf16Encoder(options, codec) { | 
						|
    options = options || {}; | 
						|
    if (options.addBOM === undefined) | 
						|
        options.addBOM = true; | 
						|
    this.encoder = codec.iconv.getEncoder('utf-16le', options); | 
						|
} | 
						|
 | 
						|
Utf16Encoder.prototype.write = function(str) { | 
						|
    return this.encoder.write(str); | 
						|
} | 
						|
 | 
						|
Utf16Encoder.prototype.end = function() { | 
						|
    return this.encoder.end(); | 
						|
} | 
						|
 | 
						|
 | 
						|
// -- Decoding | 
						|
 | 
						|
function Utf16Decoder(options, codec) { | 
						|
    this.decoder = null; | 
						|
    this.initialBytes = []; | 
						|
    this.initialBytesLen = 0; | 
						|
 | 
						|
    this.options = options || {}; | 
						|
    this.iconv = codec.iconv; | 
						|
} | 
						|
 | 
						|
Utf16Decoder.prototype.write = function(buf) { | 
						|
    if (!this.decoder) { | 
						|
        // Codec is not chosen yet. Accumulate initial bytes. | 
						|
        this.initialBytes.push(buf); | 
						|
        this.initialBytesLen += buf.length; | 
						|
         | 
						|
        if (this.initialBytesLen < 16) // We need more bytes to use space heuristic (see below) | 
						|
            return ''; | 
						|
 | 
						|
        // We have enough bytes -> detect endianness. | 
						|
        var buf = Buffer.concat(this.initialBytes), | 
						|
            encoding = detectEncoding(buf, this.options.defaultEncoding); | 
						|
        this.decoder = this.iconv.getDecoder(encoding, this.options); | 
						|
        this.initialBytes.length = this.initialBytesLen = 0; | 
						|
    } | 
						|
 | 
						|
    return this.decoder.write(buf); | 
						|
} | 
						|
 | 
						|
Utf16Decoder.prototype.end = function() { | 
						|
    if (!this.decoder) { | 
						|
        var buf = Buffer.concat(this.initialBytes), | 
						|
            encoding = detectEncoding(buf, this.options.defaultEncoding); | 
						|
        this.decoder = this.iconv.getDecoder(encoding, this.options); | 
						|
 | 
						|
        var res = this.decoder.write(buf), | 
						|
            trail = this.decoder.end(); | 
						|
 | 
						|
        return trail ? (res + trail) : res; | 
						|
    } | 
						|
    return this.decoder.end(); | 
						|
} | 
						|
 | 
						|
function detectEncoding(buf, defaultEncoding) { | 
						|
    var enc = defaultEncoding || 'utf-16le'; | 
						|
 | 
						|
    if (buf.length >= 2) { | 
						|
        // Check BOM. | 
						|
        if (buf[0] == 0xFE && buf[1] == 0xFF) // UTF-16BE BOM | 
						|
            enc = 'utf-16be'; | 
						|
        else if (buf[0] == 0xFF && buf[1] == 0xFE) // UTF-16LE BOM | 
						|
            enc = 'utf-16le'; | 
						|
        else { | 
						|
            // No BOM found. Try to deduce encoding from initial content. | 
						|
            // Most of the time, the content has ASCII chars (U+00**), but the opposite (U+**00) is uncommon. | 
						|
            // So, we count ASCII as if it was LE or BE, and decide from that. | 
						|
            var asciiCharsLE = 0, asciiCharsBE = 0, // Counts of chars in both positions | 
						|
                _len = Math.min(buf.length - (buf.length % 2), 64); // Len is always even. | 
						|
 | 
						|
            for (var i = 0; i < _len; i += 2) { | 
						|
                if (buf[i] === 0 && buf[i+1] !== 0) asciiCharsBE++; | 
						|
                if (buf[i] !== 0 && buf[i+1] === 0) asciiCharsLE++; | 
						|
            } | 
						|
 | 
						|
            if (asciiCharsBE > asciiCharsLE) | 
						|
                enc = 'utf-16be'; | 
						|
            else if (asciiCharsBE < asciiCharsLE) | 
						|
                enc = 'utf-16le'; | 
						|
        } | 
						|
    } | 
						|
 | 
						|
    return enc; | 
						|
} | 
						|
 | 
						|
 | 
						|
 |