teramura / as3jcode Goto Github PK

as3jcode

I don't believe in ByteArray.readMultiByte/writeMultiByte

= Author

Lyo Kato, <[email protected]>

= License

MIT-License

= Usage

import org.coderepos.text.encoding.Jcode;

var utf8Bytes:ByteArray = new ByteArray();
utf8Bytes.writeUTFBytes("にほんご");

// convert to EUC-JP byte code
var eucBytes:ByteArray = Jcode.utf8_euc(utf8Bytes);

// convert to ISO-2022-JP byte code
var jisBytes:ByteArray = Jcode.utf8_jis(utf8Bytes);

// convert to Shift_JIS byte code
var jisBytes:ByteArray = Jcode.utf8_sjis(utf8Bytes);

// convert to UTF-16 byte code
var utf16Bytes:ByteArray = Jcode.utf8_utf16(utf8Bytes);

// with BOM that represents Big Endian
var utf16Bytes:ByteArray = Jcode.utf8_utf16be(utf8Bytes);

utf8Bytes  = Jcode.euc_utf8(eucBytes);
utf8nBytes = Jcode.euc_utf8n(eucBytes);
utf8Bytes  = Jcode.jis_utf8(jisBytes);
utf8nBytes = Jcode.jis_utf8n(jisBytes);
utf8Bytes  = Jcode.sjis_utf8(sjisBytes);
utf8nBytes = Jcode.sjis_utf8n(sjisBytes);

utf8Bytes  = Jcode.utf16_utf8(sjisBytes);
utf8nBytes = Jcode.utf16_utf8n(sjisBytes);

jisBytes  = Jcode.euc_jis(eucBytes);
sjisBytes = Jcode.euc_sjis(eucBytes);
eucBytes  = Jcode.jis_euc(jisBytes);
sjisBytes = Jcode.jis_sjis(jisBytes);
eucBytes  = Jcode.sjis_euc(sjisBytes);
jisBytes  = Jcode.sjis_jis(sjisBytes);


** Short circuit

*** Encoding from UTF-8 ActionScript native string

var utf8Bytes:ByteArray = new ByteArray();
utf8Bytes.writeUTFBytes("日本語");
var eucBytes:ByteArray = Jcode.utf8_euc(utf8Bytes);

instread of above 3 lines code, you can use to_xxx methods.

var eucBytes:ByteArray  = Jcode.to_euc("日本語");
var jisBytes:ByteArray  = Jcode.to_jis("日本語");
var sjisBytes:ByteArray = Jcode.to_sjis("日本語");

*** Decoding to UTF-8 ActionScript native string

var utf8String:String = Jcode.from_euc(eucBytes);
var utf8String:String = Jcode.from_jis(jisBytes);
var utf8String:String = Jcode.from_sjis(sjisBytes);

** Katakana

Hankaku to Zenkaku

var utf8String:String = Jcode.h2z("ｱｲｳｴｵ");
// utf8String should be "アイウエオ".

var origin:String = Jcode.z2h(utf8String);
// origin should be "ｱｲｳｴｵ";

** Validation

if (Jcode.is_hiragana(utf8string)) {

}

if (Jcode.is_zenkaku_katakana(utf8string)) {

}

if (Jcode.is_hankaku_katakana(utf8string)) {

}

// zenkaku and hankaku katakana
if (Jcode.is_katakana(utf8string)) {

}

= TODO

Zenkaku to Hankaku conversion (required?)
Support UTF-16LE, UTF-32, (UTF-7)