import win.ui;
/*DSG{{*/
var winform = win.form(text="代码页编码乱码暴力猜解工具";right=1038;bottom=703)
winform.add(
button={cls="button";text="Button";left=858;top=530;right=955;bottom=593;z=2};
edit={cls="edit";left=10;top=8;right=713;bottom=431;autohscroll=false;edge=1;multiline=1;vscroll=1;z=1};
edit2={cls="edit";left=10;top=438;right=713;bottom=691;autohscroll=false;edge=1;multiline=1;vscroll=1;z=3}
)
/*}}*/
//原创分享:简码编程 www.jianma123.com
import web.json;
var codePageList = /***
37 IBM037 IBM EBCDIC (US-Canada)
437 IBM437 OEM United States
500 IBM500 IBM EBCDIC (International)
708 ASMO-708 Arabic (ASMO 708)
720 DOS-720 Arabic (DOS)
737 ibm737 Greek (DOS)
775 ibm775 Baltic (DOS)
850 ibm850 Western European (DOS)
852 ibm852 Central European (DOS)
855 IBM855 OEM Cyrillic
857 ibm857 Turkish (DOS)
858 IBM00858 OEM Multilingual Latin I
860 IBM860 Portuguese (DOS)
861 ibm861 Icelandic (DOS)
862 DOS-862 Hebrew (DOS)
863 IBM863 French Canadian (DOS)
864 IBM864 Arabic (864)
865 IBM865 Nordic (DOS)
866 cp866 Cyrillic (DOS)
869 ibm869 Greek, Modern (DOS)
870 IBM870 IBM EBCDIC (Multilingual Latin-2)
874 windows-874 Thai (Windows)
875 cp875 IBM EBCDIC (Greek Modern)
932 shift_jis Japanese (Shift-JIS)
936 gb2312 Chinese Simplified (GB2312)
949 ks_c_5601-1987 Korean
950 big5 Chinese Traditional (Big5)
1026 IBM1026 IBM EBCDIC (Turkish Latin-5)
1047 IBM01047 IBM Latin-1
1140 IBM01140 IBM EBCDIC (US-Canada-Euro)
1141 IBM01141 IBM EBCDIC (Germany-Euro)
1142 IBM01142 IBM EBCDIC (Denmark-Norway-Euro)
1143 IBM01143 IBM EBCDIC (Finland-Sweden-Euro)
1144 IBM01144 IBM EBCDIC (Italy-Euro)
1145 IBM01145 IBM EBCDIC (Spain-Euro)
1146 IBM01146 IBM EBCDIC (UK-Euro)
1147 IBM01147 IBM EBCDIC (France-Euro)
1148 IBM01148 IBM EBCDIC (International-Euro)
1149 IBM01149 IBM EBCDIC (Icelandic-Euro)
1200 utf-16 Unicode
1201 unicodeFFFE Unicode (Big-Endian)
1250 windows-1250 Central European (Windows)
1251 windows-1251 Cyrillic (Windows)
1252 Windows-1252 Western European (Windows)
1253 windows-1253 Greek (Windows)
1254 windows-1254 Turkish (Windows)
1255 windows-1255 Hebrew (Windows)
1256 windows-1256 Arabic (Windows)
1257 windows-1257 Baltic (Windows)
1258 windows-1258 Vietnamese (Windows)
1361 Johab Korean (Johab)
10000 macintosh Western European (Mac)
10001 x-mac-japanese Japanese (Mac)
10002 x-mac-chinesetrad Chinese Traditional (Mac)
10003 x-mac-korean Korean (Mac)
10004 x-mac-arabic Arabic (Mac)
10005 x-mac-hebrew Hebrew (Mac)
10006 x-mac-greek Greek (Mac)
10007 x-mac-cyrillic Cyrillic (Mac)
10008 x-mac-chinesesimp Chinese Simplified (Mac)
10010 x-mac-romanian Romanian (Mac)
10017 x-mac-ukrainian Ukrainian (Mac)
10021 x-mac-thai Thai (Mac)
10029 x-mac-ce Central European (Mac)
10079 x-mac-icelandic Icelandic (Mac)
10081 x-mac-turkish Turkish (Mac)
10082 x-mac-croatian Croatian (Mac)
20000 x-Chinese-CNS Chinese Traditional (CNS)
20001 x-cp20001 TCA Taiwan
20002 x-Chinese-Eten Chinese Traditional (Eten)
20003 x-cp20003 IBM5550 Taiwan
20004 x-cp20004 TeleText Taiwan
20005 x-cp20005 Wang Taiwan
20105 x-IA5 Western European (IA5)
20106 x-IA5-German German (IA5)
20107 x-IA5-Swedish Swedish (IA5)
20108 x-IA5-Norwegian Norwegian (IA5)
20127 us-ascii US-ASCII
20261 x-cp20261 T.61
20269 x-cp20269 ISO-6937
20273 IBM273 IBM EBCDIC (Germany)
20277 IBM277 IBM EBCDIC (Denmark-Norway)
20278 IBM278 IBM EBCDIC (Finland-Sweden)
20280 IBM280 IBM EBCDIC (Italy)
20284 IBM284 IBM EBCDIC (Spain)
20285 IBM285 IBM EBCDIC (UK)
20290 IBM290 IBM EBCDIC (Japanese katakana)
20297 IBM297 IBM EBCDIC (France)
20420 IBM420 IBM EBCDIC (Arabic)
20423 IBM423 IBM EBCDIC (Greek)
20424 IBM424 IBM EBCDIC (Hebrew)
20833 x-EBCDIC-KoreanExtended IBM EBCDIC (Korean Extended)
20838 IBM-Thai IBM EBCDIC (Thai)
20866 koi8-r Cyrillic (KOI8-R)
20871 IBM871 IBM EBCDIC (Icelandic)
20880 IBM880 IBM EBCDIC (Cyrillic Russian)
20905 IBM905 IBM EBCDIC (Turkish)
20924 IBM00924 IBM Latin-1
20932 EUC-JP Japanese (JIS 0208-1990 and 0212-1990)
20936 x-cp20936 Chinese Simplified (GB2312-80)
20949 x-cp20949 Korean Wansung
21025 cp1025 IBM EBCDIC (Cyrillic Serbian-Bulgarian)
21866 koi8-u Cyrillic (KOI8-U)
28591 iso-8859-1 Western European (ISO)
28592 iso-8859-2 Central European (ISO)
28593 iso-8859-3 Latin 3 (ISO)
28594 iso-8859-4 Baltic (ISO)
28595 iso-8859-5 Cyrillic (ISO)
28596 iso-8859-6 Arabic (ISO)
28597 iso-8859-7 Greek (ISO)
28598 iso-8859-8 Hebrew (ISO-Visual)
28599 iso-8859-9 Turkish (ISO)
28603 iso-8859-13 Estonian (ISO)
28605 iso-8859-15 Latin 9 (ISO)
29001 x-Europa Europa
38598 iso-8859-8-i Hebrew (ISO-Logical)
50220 iso-2022-jp Japanese (JIS)
50221 csISO2022JP Japanese (JIS-Allow 1 byte Kana)
50222 iso-2022-jp Japanese (JIS-Allow 1 byte Kana - SO/SI)
50225 iso-2022-kr Korean (ISO)
50227 x-cp50227 Chinese Simplified (ISO-2022)
51932 euc-jp Japanese (EUC)
51936 EUC-CN Chinese Simplified (EUC)
51949 euc-kr Korean (EUC)
52936 hz-gb-2312 Chinese Simplified (HZ)
54936 GB18030 Chinese Simplified (GB18030)
57002 x-iscii-de ISCII Devanagari
57003 x-iscii-be ISCII Bengali
57004 x-iscii-ta ISCII Tamil
57005 x-iscii-te ISCII Telugu
57006 x-iscii-as ISCII Assamese
57007 x-iscii-or ISCII Oriya
57008 x-iscii-ka ISCII Kannada
57009 x-iscii-ma ISCII Malayalam
57010 x-iscii-gu ISCII Gujarati
57011 x-iscii-pa ISCII Punjabi
65000 utf-7 Unicode (UTF-7)
65001 utf-8 Unicode (UTF-8)
65005 utf-32 Unicode (UTF-32)
65006 utf-32BE Unicode (UTF-32 Big-Endian)
***/
var sourceStr = /***
11.11æ¥æ°çå款22906
11.10æ¥æ°çå款34224
11.15æ¥æ°çå款22726
***/
/***
可以在输出的文件里搜索查找明文看是否有成功转换的,此乱码明文为:
11.11日民生回款22906
11.10日民生回款34224
11.15日民生回款22726
***/
winform.button.oncommand = function(id,event){
var listTab = string.split(codePageList,'<\r\n>');
var count = table.count(listTab);
var pageTab = {}
for(i=1;count;1){
table.push(pageTab,(tonumber(string.split(listTab[i],'\t')[1])));
}
//winform.edit.print("pageTab:",pageTab);
var count2 = table.count(pageTab);
var num = 1;
var allResultTab = {};
for(i=1;count2;1){//count2
for(k=1;count2;1){//count2
var fromCode = pageTab[i];
var toCode = pageTab[k];
//fromCode:65001 toCode:28591 时应该会成功
var headStr = string.concat("num:",num," i:",i," k:",k," fromCode:",fromCode," toCode:",toCode);
//winform.edit.print(headStr);
var resultStr = string.fromto(sourceStr,fromCode,toCode);
//有些转换后在AAR里 edit.text=resultStr 仍然是乱码但用 edit.print(resultStr) 输出就正常
//要用一个正常非空的ASCII字符在前面或后面连接,AAR底层才会把它识别并转成正常可阅读文本
//经过连接处理后,保存文件或 edit.text=resultStr 都正常了
//空字符串和null都不行,必须有任意一个非空的ascii字符,为了不影响视觉,所以用空格
resultStr = resultStr ++ " ";
//显示特定的转换出来看下
if(fromCode==65001 and toCode==28591){
winform.edit2.text = resultStr;
}
table.push(allResultTab,string.concat(headStr,'\r\n',resultStr));
num++;
}
}
var allResultStr = string.join(allResultTab,'\r\n\r\n');
//winform.edit.print(allResultStr);
//注意保存的文件格式要UTF8编码才能看到明文
string.save("C:\Users\Administrator\Desktop\乱码暴力猜解结果.txt",allResultStr);
winform.edit.print("完成");
}
winform.show();
win.loopMessage();