Get code int value for different encoding
http://msdn.microsoft.com/en-us/library/system.text.encodinginfo.getencoding%28v=vs.110%29.aspx
using System;
using System.Text; public class SamplesEncoding { public static void Main() { // Print the header.
Console.Write( "Info.CodePage " );
Console.Write( "Info.Name " );
Console.Write( "Info.DisplayName" );
Console.WriteLine(); // Display the EncodingInfo names for every encoding, and compare with the equivalent Encoding names.
foreach( EncodingInfo ei in Encoding.GetEncodings() ) {
Encoding e = ei.GetEncoding(); Console.Write( "{0,-15}", ei.CodePage );
if ( ei.CodePage == e.CodePage )
Console.Write( " " );
else
Console.Write( "*** " ); Console.Write( "{0,-25}", ei.Name );
if ( ei.CodePage == e.CodePage )
Console.Write( " " );
else
Console.Write( "*** " ); Console.Write( "{0,-25}", ei.DisplayName );
if ( ei.CodePage == e.CodePage )
Console.Write( " " );
else
Console.Write( "*** " ); Console.WriteLine(); // Below is an example regarding getting a Japanese string from ANSII format txt file.
// That is to say, Japanese chars are input on Japanese OS and saved as txt format,
// the file is opened on English OS.
// Encoding.GetEncoding(932).GetString(bytesConverted);
} } } /*
This code produces the following output. Info.CodePage Info.Name Info.DisplayName
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)
12000 utf-32 Unicode (UTF-32)
12001 utf-32BE Unicode (UTF-32 Big-Endian)
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) */
Get code int value for different encoding的更多相关文章
- 善用VS中的Code Snippet来提高开发效率
http://www.cnblogs.com/anderslly/archive/2009/02/16/vs2008-code-snippets.html http://www.cnblogs.com ...
- 字符在内存中最终的表示形式是什么？是某种字符编码还是码位(Code Point)？
字符在内存中最终的表示形式是什么?是某种字符编码还是码位(Code Point)? 根据我的了解,编码中有三个核心概念:1. 字符集(Character Set),可以说是一个抽象概念,字符的合集2. ...
- Int，Long比较重使用equal替换==
首先,==有很多限制,如Integer 类型的值在[-128,127] 期间,Integer 用 “==”是可以的(参考),超过范围则不行,那么使用equal则代替则完全ok public stati ...
- 使用DataOutputStream写入int类型数字不能显示
前段时间做Android系统项目需要使用DataOutputStream数据流向文件里写入数据,写入的有String类型和int类型.写入之后在代码中使用DataInputStream读出是没有问题的 ...
- Symantec Backup Exec 报"Access denied to directory xxx" Error Code E0008488
使用Symantec Backup Exec将几台Linux服务器上的RMAN备份收带时,偶尔会遇到作业备份失败的情况,检查Job History,就会发现有“Access denied to dir ...
- java Integer和int的拆箱与装箱
官网:http://docs.oracle.com/javase/tutorial/java/data/autoboxing.html 1.赋值: a. 把int类型赋值给Integer类型:JVM会 ...
- 善用VS中的Code Snippet来提高开发效率 分类： C# 2015-01-22 11:06 69人阅读 评论(0) 收藏
前言 在谈谈VS中的模板中,我介绍了如何创建项目/项模板,这种方式可以在创建项目时省却不少重复性的工作,从而提高开发效率.在创建好了项目和文件后,就得开始具体的编码了,这时又有了新的重复性工作,就是 ...
- 将String类型的数字字符转换成int
java.lang.Integer.parseInt(String) public static int parseInt(String s) throws NumberFormatException ...
- UVa 740 - Baudot Data Communication Code
称号:目前编码,他们shift键被按下,并提出,对应的两个编码,其中,2相应的编码shift操作. 给你适当的编码值.寻求相应的字符串. 分析:模拟.字符串. 简单题,标记shift的升降分类处理就可 ...
随机推荐
- 【ZZ】C 语言中的指针和内存泄漏 & 编写高效的C程序与C代码优化
C 语言中的指针和内存泄漏 http://www.ibm.com/developerworks/cn/aix/library/au-toughgame/ 本文讨论了几种在使用动态内存分配时可以避免的陷 ...
- apue.h
[root@localhost unix_env_advance_prog]# cat apue.h #ifndef _APUE_H #define _APUE_H #define _XOPEN_SO ...
- HTTP协议理解
HTTP(Hyper Text Transfer Protocol)超文本传输协议,是一种请求响应式协议,类似两国会晤中需要遵守的规则.那么,其中有什么内容特点呢? HTTP特点: 1)支持客户端/服 ...
- SandBox+NSBundle
1.iOS的文件系统 1.1.SandBox(沙箱.沙盒) 在iOS中,任何一个App都存放在自己的一个称之为SandBox中 1)SandBox的组成 a.Bundle Container:放应用程 ...
- mysql开启外联方法
1.修改Mysql配置文件 /etc/mysql/my.cnf 注释掉 bind-address = 127.0.0.1 2.重启Mysql /etc/init.d/mysql restart 3.r ...
- LeetCode 213
House Robber II Note: This is an extension of House Robber. After robbing those houses on that stree ...
- [改善Java代码]建议采用的顺序是 List<T>、List<?>、List<Object>
建议98:建议采用的顺序是 List<T>.List<?>.List<Object> List<T>.List<?>.List<Obj ...
- 【Stirling Number I】
hdu 4372 Count the Buildings 推荐这位小哥的,我觉得人家说的灰常的好. 注意数据范围,n,f,b均在(0,2000]范围内,而第一斯特林数的数组范围却是s[2000+5][ ...
- Java集合类 java.util包
概述 软件包 类 使用 树 已过时 索引 帮助 JavaTM Platform Standard Ed. 6 上一个软件包 下一个软件包 框架 无框架 ...
- request对象实现请求转发
request对象实现请求转发,请求转发指一个web资源收到客户端请求后,通知服务器去调用另外一个web资源进行处理.request对象提供了一个getRequestDispatcher方法,该方法返 ...