codepage.h

This software performs code conversion of Chinese characters, including GB2312/GBK and BIG5. It a

// codepage.h

#ifndef CODEPAGE_H
#define CODEPAGE_H


// Codepage definitions

// See <winnls.h>
// http://msdn.microsoft.com/library/en-us/intl/unicode_81rn.asp


// DOS
#define CP_US                             437      // 暷崙 (MS-DOS) as known as OEM
#define CP_ARABIC_ASMO_708                708      // 傾儔價傾岅 (ASMO 708)
#define CP_ARABIC_ASMO_449P               709      // 傾儔價傾岅 (ASMO 449+, BCON V4)
#define CP_ARABIC_TP                      710      // 傾儔價傾岅 (Transparent Arabic)
#define CP_ARABIC_NAFITHA                 711      // 傾儔價傾岅 (Nafitha Enhanced)
#define CP_ARABIC_SAKHR                   714      // 傾儔價傾岅 (Sakhr)
#define CP_ARABIC_TP_ASMO                 720      // 傾儔價傾岅 (Transparent ASMO)
#define CP_ARABIC_NAFITHA_INT             721      // 傾儔價傾岅 (Nafitha International)
#define CP_GREEK                          737      // 僊儕僔儍岅 (IBM)
#define CP_BALTIC                         775      // 僶儖僩岅 (MS-DOS)             // Latin 7
#define CP_ARABIC_MUSSAED                 786      // 傾儔價傾岅 (Mussaed Al Arabi)
#define CP_WIN31_EUROPEAN                 819      // 惣儓乕儘僢僷尵岅 (Windows 3.1) = CP_ISO_EUROPEAN
#define CP_EUROPEAN                       850      // 儓乕儘僢僷懡尵岅 (MS-DOS)     // Latin 1
#define CP_GREEK_OLD                      851      // 僊儕僔儍岅 (IBM) - obsolete
#define CP_CENTRAL_EUROPEAN               852      // 拞墰儓乕儘僢僷懡尵岅 (MS-DOS) // Latin 2
#define CP_TURKISH_OLD                    853      // 僩儖僐岅 (MS-DOS)             // Latin 3
#define CP_CYRILLIC                       855      // 僉儕儖岅 (IBM) - obsolete
#define CP_HEBREW_OLD                     856      // 僿僽儔僀岅 (IBM)
#define CP_TURKISH                        857      // 僩儖僐岅 (IBM)                // Latin 5
#define CP_EUROPEAN_EURO                  858      // 儓乕儘僢僷懡尵岅亄儐乕儘婰崋(IBM)
#define CP_PORTUGUESE                     860      // 億儖僩僈儖岅 (MS-DOS)
#define CP_ICELANDIC                      861      // 傾僀僗儔儞僪岅 (MS-DOS)
#define CP_HEBREW                         862      // 僿僽儔僀岅 (MS-DOS)
#define CP_CANADIAN_FRENCH                863      // 僇僫僟宯僼儔儞僗岅 (MS-DOS)
#define CP_ARABIC                         864      // 傾儔價傾岅 (MS-DOS)
#define CP_NORDIC                         865      // 杒墷岅 (MS-DOS)
#define CP_RUSSIAN                        866      // 儘僔傾岅 (MS-DOS)
#define CP_MODERN_GREEK                   869      // 尰戙僊儕僔儍岅 (IBM)
#define CP_THAI                           874      // 僞僀岅
#define CP_CZECH                          895      // 僠僃僐岅 (Kamenicky CS)
#define CP_JAPANESE                       932      // 擔杮岅 (Shift-JIS)
#define CP_CHINESE_SIMPLIFIED             936      // 拞崙岅娙懱帤 (GB2312)
#define CP_KOREAN                         949      // 娯崙岅 (UHC)
#define CP_CHINESE_TRADITIONAL            950      // 拞崙岅斏懱帤 (BIG5)

// UTF-16
#define CP_UTF16                          1200     // Unicode UTF-16
#define CP_UTF16_BE                       1201     // Unicode UTF-16 (Big Endian)

// Windows
#define CP_ANSI_CENTRAL_EUROPEAN          1250     // 拞墰儓乕儘僢僷岅 (Windows)
#define CP_ANSI_CYRILLIC                  1251     // 僉儕儖岅 (Windows)
#define CP_ANSI_EUROPEAN                  1252     // 儓乕儘僢僷岅 (Windows)
#define CP_ANSI_GREEK                     1253     // 僊儕僔傾岅 (Windows)
#define CP_ANSI_TURKISH                   1254     // 僩儖僐岅 (Windows)
#define CP_ANSI_HEBREW                    1255     // 僿僽儔僀岅 (Windows)
#define CP_ANSI_ARABIC                    1256     // 傾儔價傾岅 (Windows)
#define CP_ANSI_BALTIC                    1257     // 僶儖僩岅 (Windows)
#define CP_ANSI_VIETNAMESE                1258     // 儀僩僫儉岅 (Windows)

#define CP_KOREAN_JOHAB                   1361     // 娯崙岅 (Johab)

// Macintosh
#define CP_MAC_EUROPEAN                   10000
#define CP_MAC_JAPANESE                   10001
#define CP_MAC_CHINESE_TRADITIONAL        10002
#define CP_MAC_KOREAN                     10003
#define CP_MAC_ARABIC                     10004
#define CP_MAC_HEBREW                     10005
#define CP_MAC_GREEK                      10006
#define CP_MAC_CYRILLIC                   10007
#define CP_MAC_CHINESE_SIMPLIFIED         10008
#define CP_MAC_ROMANIAN                   10010
#define CP_MAC_UKRAINIAN                  10017
#define CP_MAC_THAI                       10021
#define CP_MAC_CENTRAL_EUROPEAN           10029
#define CP_MAC_ICELANDIC                  10079
#define CP_MAC_TURKISH                    10081
#define CP_MAC_CROATIAN                   10082

// Taiwan
#define CP_CHINESE_TRADITIONAL_CNS        20000    // 捠梡狴
#define CP_CHINESE_TRADITIONAL_TCA        20001    // 岞夛狴
#define CP_CHINESE_TRADITIONAL_ETEN       20002    // 樳揤狴
#define CP_CHINESE_TRADITIONAL_IBM5550    20003    // IBM5550
#define CP_CHINESE_TRADITIONAL_TELETEXT   20004    // 揹怣狴
#define CP_CHINESE_TRADITIONAL_WANG       20005    // 墹埨狴

// What is IA5 ?
#define CP_IA5_WESTERN_EUROPEAN           20105    // 7-bit
#define CP_IA5_GERMAN                     20106    // 7-bit
#define CP_IA5_SWEDISH                    20107    // 7-bit
#define CP_IA5_NORWEGIAN                  20108    // 7-bit

#define CP_US_ASCII                       20127    // 暷崙 ASCII 7-bit
#define CP_T61                            20261    // TeleText
#define CP_ISO_6937                       20269    // Non-Spacing Accent

// EUC
#define CP_EUC_JAPANESE_MS                20932    // 擔杮岅 (MS撈帺偺EUC晽)
#define CP_EUC_CHINESE_SIMPLIFIED         20936    // 拞崙岅娙懱帤
#define CP_EUC_KOREAN                     20949    // 娯崙岅 (亖CP51949)

#define CP_EXT_ALPHA_LOWERCASE            21027    // Ext Alpha Lowercase (deprecated)
#define CP_EUROPA                         29001    // ?

// KOI8
#define CP_CYRILLIC_KOI8R                 20866    // 僉儕儖岅 (KOI8-R)
#define CP_CYRILLIC_KOI8U                 21866    // 僉儕儖岅 (KOI8-U)

// ISO
#define CP_ISO_EUROPEAN                   28591    // 惣儓乕儘僢僷岅 (ISO-8859-1)   // Latin 1
#define CP_ISO_CENTRAL_EUROPEAN           28592    // 拞墰儓乕儘僢僷岅 (ISO-8859-2) // Latin 2
#define CP_ISO_TURKISH_OLD                28593    //          (ISO-8859-3)         // Latin 3
#define CP_ISO_BALTIC                     28594    // 僶儖僩岅 (ISO-8859-4)         // Latin 4
#define CP_ISO_CYRILLIC                   28595    // 僉儕儖岅 (ISO-8859-5)
#define CP_ISO_ARABIC                     28596    // 傾儔價傾岅 (ISO-8859-6)
#define CP_ISO_GREEK                      28597    // 僊儕僔傾岅 (ISO-8859-7)
#define CP_ISO_HEBREW_VISUAL              28598    // 僿僽儔僀岅 (ISO-8859-8) 帇妎弴
#define CP_ISO_TURKISH                    28599    // 僩儖僐岅 (ISO-8859-9)         // Latin 5
#define CP_ISO_NORDIC                     28600    // 杒墷岅 (ISO-8859-10)          // Latin 6
#define CP_ISO_THAI                       28601    // 僞僀岅 (ISO-8859-11)
#define CP_ISO_BALTIC_EX                  28603    // 僶儖僩岅 (ISO-8859-13)        // Latin 7
#define CP_ISO_CELTIC                     28604    // 働儖僩岅 (ISO-8859-14)        // Latin 8
#define CP_ISO_EUROPEAN_EX                28605    // 惣儓乕儘僢僷岅 (ISO-8859-15)  // Latin 9
#define CP_ISO_ROMANIAN                   28606    // 儖乕儅僯傾岅 (ISO-8859-16)    // Latin 10

#define CP_ISO_HEBREW_LOGICAL             38598    // 僿僽儔僀岅 (ISO-8859-8) 榑棟弴

// ISO-2022
#define CP_ISO_JAPANESE                   50220    // 擔杮岅 (ISO-2022-JP)
#define CP_ISO_JAPANESE_AND_KANA          50221    // 擔杮岅 (JIS-Allow 1 byte Kana)
#define CP_ISO_JAPANESE_AND_KANA_SIO      50222    // 擔杮岅 (JIS-Allow 1 byte Kana - SO/SI)
#define CP_ISO_KOREAN                     50225    // 娯崙岅 (ISO-2022-KR)
#define CP_ISO_CHINESE_SIMPLIFIED         50227    // 拞崙岅娙懱帤 (ISO-2022)
#define CP_ISO_CHINESE_TRADITIONAL        50229    // 拞崙岅斏懱帤 (ISO-2022)

// EUC
#define CP_EUC_JAPANESE                   51932    // 擔杮岅 (EUC)
#define CP_CHINESE_SIMPLIFIED_2           51936    // 拞崙岅娙懱帤 (亖CP936)
#define CP_EUC_KOREAN_2                   51949    // 娯崙岅 (亖CP20949)
#define CP_CHINESE_TRADITIONAL_2          51950    // 拞崙岅斏懱帤 (佮CP950)

#define CP_HZ_CHINESE_SIMPLIFIED          52936    // 拞崙岅娙懱帤 (HZ)
#define CP_CHINESE_SIMPLIFIED_EX          54936    // 拞崙岅娙懱帤 (GB18030)

// ISCII