Last active
December 16, 2015 20:09
-
-
Save yuchi/5490028 to your computer and use it in GitHub Desktop.
Titanium SDK: a snippet to read a Stream into a string preserving UTF-8 characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
/** | |
* Titanium SDK - Stream UTF-8 reader | |
* ================================== | |
* | |
* a snippet to read a Stream into a string preserving UTF-8 characters | |
* | |
* Author: Pier Paolo Ramon | |
* Copyright 2013 SMC Treviso <http://www.smc.it> | |
* | |
*/ | |
var chunkSize = 1024; | |
var memoize = (typeof _ !== 'undefined') && _.memoize || function(func, hasher) { | |
var has = Object.prototype.hasOwnProperty; | |
var memo = {}; | |
hasher || (hasher = function (o) { return o; }); | |
return function() { | |
var key = hasher.apply(this, arguments); | |
return has.call(memo, key) ? memo[key] : (memo[key] = func.apply(this, arguments)); | |
}; | |
}; | |
}; | |
var firstByteToSequenceSize = memoize(function (firstByte) { | |
firstByte = firstByte.toString(2); | |
if (firstByte.slice(0, -5) === '110') { | |
return 2; | |
} | |
else if (firstByte.slice(0, -4) === '1110') { | |
return 3; | |
} | |
else if (firstByte.slice(0, -3) === '11110') { | |
return 4; | |
} | |
else if (firstByte.slice(0, -2) === '111110') { | |
return 5; | |
} | |
else if (firstByte.slice(0, -1) === '1111110') { | |
return 6; | |
} | |
else { | |
return NaN; | |
} | |
}); | |
var getContent = function (stream) { | |
var stringbuffer = []; | |
var chunkSize = 1024; | |
var buffer = Ti.createBuffer({ | |
type: Ti.Codec.CHARSET_UTF8, | |
length: chunkSize // bytes | |
}); | |
var bytesRead; | |
var number, spy, firstByte, sequence, toread; | |
var cutout; | |
var append; | |
var stringvalue; | |
var temp; | |
while ((bytesRead = stream.read(buffer)) >= 0) { | |
append = null; | |
cutout = 0; | |
if (bytesRead < chunkSize) { | |
cutout = chunkSize - bytesRead; | |
} | |
else { | |
spy = null; | |
firstByte = null; | |
toread = 0; | |
number = 1; | |
while ((spy = buffer[chunkSize - number]) >= 128) { | |
firstByte = spy; | |
number += 1; | |
if (spy >= 192) { | |
break; | |
} | |
} | |
number -= 1; | |
if (number > 0) { | |
sequence = firstByteToSequenceSize(firstByte); | |
toread = sequence - number; | |
if (toread < 0) { | |
throw new Error("Malformed UTF-8"); | |
} | |
if (toread > 0) { | |
cutout = number; | |
temp = Ti.createBuffer({ | |
type: Ti.Codec.CHARSET_UTF8, | |
length: sequence | |
}); | |
temp.copy(buffer, 0, chunkSize - number, number); | |
stream.read(temp, number, toread); | |
append = Ti.Codec.decodeString({ | |
source: temp, | |
type: Ti.Codec.CHARSET_UTF8 | |
}); | |
temp.release(); | |
temp = null; | |
} | |
} | |
} | |
if (cutout > 0) { | |
buffer.fill(0, chunkSize - cutout, cutout); | |
} | |
stringvalue = Ti.Codec.decodeString({ | |
source: buffer, | |
type: Ti.Codec.CHARSET_UTF8 | |
}); | |
if (cutout > 0) { | |
stringvalue = stringvalue.slice(0, -cutout); | |
} | |
if (append) { | |
stringbuffer.push(stringvalue, append); | |
} | |
else { | |
stringbuffer.push(stringvalue); | |
} | |
} | |
var content = stringbuffer.join(''); | |
buffer.release(); | |
stream.close(); | |
return content; | |
}; |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment