2013-03-03 20:05:01 +00:00
|
|
|
|
2013-04-30 13:57:19 +00:00
|
|
|
# chardet - characted detection module, pure Javascript
|
2013-04-30 13:49:02 +00:00
|
|
|
|
2013-04-30 13:57:19 +00:00
|
|
|
Chardet is a character detection module for NodeJS written in pure Javascript.
|
|
|
|
|
Module is based on ICU project http://site.icu-project.org/, which uses character
|
|
|
|
|
occurency analysis to determine the most probable encoding.
|
|
|
|
|
|
|
|
|
|
## Installation
|
2013-04-30 13:49:02 +00:00
|
|
|
|
|
|
|
|
npm install chardet
|
|
|
|
|
|
2013-04-30 13:57:19 +00:00
|
|
|
## Usage
|
2013-04-30 13:49:02 +00:00
|
|
|
|
|
|
|
|
var chardet = require('chardet');
|
|
|
|
|
chardet.detect(new Buffer('hello there!'));
|
|
|
|
|
// or
|
|
|
|
|
chardet.detectFile('/path/to/file', function(err, encoding) {});
|
|
|
|
|
// or
|
|
|
|
|
chardet.detectFileSync('/path/to/file');
|
|
|
|
|
|
2013-04-30 13:57:19 +00:00
|
|
|
## Supported Encodings:
|
2013-04-30 13:49:02 +00:00
|
|
|
|
|
|
|
|
* UTF-8
|
|
|
|
|
* UTF-16 LE
|
|
|
|
|
* UTF-16 BE
|
|
|
|
|
* UTF-32 LE
|
|
|
|
|
* UTF-32 BE
|
|
|
|
|
* ISO-2022-JP
|
|
|
|
|
* ISO-2022-KR
|
|
|
|
|
* ISO-2022-CN
|
|
|
|
|
* Shift-JIS
|
|
|
|
|
* Big5
|
|
|
|
|
* EUC-JP
|
|
|
|
|
* EUC-KR
|
|
|
|
|
* GB18030
|
2013-05-01 14:57:54 +00:00
|
|
|
* ISO-8859-1
|
|
|
|
|
* ISO-8859-2
|
|
|
|
|
* ISO-8859-5
|
|
|
|
|
* ISO-8859-6
|
|
|
|
|
* ISO-8859-7
|
2013-05-04 09:27:28 +00:00
|
|
|
* ISO-8859-8
|
|
|
|
|
* ISO-8859-9
|
|
|
|
|
* windows-1250
|
|
|
|
|
* windows-1251
|
|
|
|
|
* windows-1252
|
|
|
|
|
* windows-1253
|
|
|
|
|
* windows-1254
|
|
|
|
|
* windows-1255
|
|
|
|
|
* windows-1256
|
|
|
|
|
* KOI8-R
|
2013-04-30 13:49:02 +00:00
|
|
|
|
|
|
|
|
Currently only these encodings are supported, more will be added soon.
|
