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
- android:layout_weight总有你不知道的用法.
都知道weight是权重的意思. 在布局中起到非常重要的作用. 但是这玩意不能嵌套使用, 而且只能使用在LinearLayout中. 下面说说它的几种用法(以下例子全为横排 注意android:lay ...
- python-其他常用模块
本节大纲: 模块介绍 time &datetime模块 random shutil shelve xml处理 yaml处理 configparser hashlib subprocess lo ...
- CCTableView的使用和注意事项
#include "cocos-ext.h" using namespace cocos2d::extension; class TableViewTestLayer: publi ...
- dem30下载地址
http://www.gscloud.cn/listdata/listdata_new.shtml?from=&productId=311#Wzg4LFswLDEwLDEsMF0sW10sW1 ...
- 引用自定义的framework
关于静态库引用文件 如果希望你的工程能在未来能导出成静态库,那么在你编写的时候要遵循静态库引用原则,使用这种方式. 注意:这种引用方式必须在你的Products下静态库成黑色时候,才能编译通过. 使用 ...
- 求可能组合VB源码代写
输入1-20的整数n,把从1到n的n个整数摆成一个环,使得该环上任意相邻的两个数之和为素数.求出所有可能组合. 专业程序代写c++程序代写
- some words we should know
2010年,芬兰艺术家Mikko Kuorinki做了一件独特的艺术品. 他在赫尔辛基的奇亚斯玛当代艺术博物馆(Kiasma museum),找了一堵墙,装了一个175 x 320cm的木架子,上面用 ...
- javaweb学习总结二十一(servlet开发入门、servlet生命周期以及调用过程)
一:servlet开发入门 servlet是sun公司一门开发动态web资源的技术,下面编写一个servlet入门程序: 1:在tomcat服务器webapps目录下新建firstServlet目录, ...
- Ionic中弹窗
Ionic中弹窗有两种ionicModal和ionicPopup; $ionicModal是完整的页面: $ionicPopup是(Dialog)对话框样式的,直接用JavaScript设定对话框的一 ...
- [未完成][Mooc]关于线程的总结
进程和线程.Eclipse,QQ都是进程.是程序或者任务的执行过程,是动态性.持有资源(共享内存,共享文件)和线程. 这个资源就是内存. 每个程序在运行的时候都会分配一些内存. Eclipse中的源代 ...