Main Page   Class Hierarchy   Compound List   File List   Compound Members   File Members  

lang_enc.h

Go to the documentation of this file.
00001 //***************************************************************************
00002 // This source code is copyrighted 2002 by Google Inc.  All rights
00003 // reserved.  You are given a limited license to use this source code for
00004 // purposes of participating in the Google programming contest.  If you
00005 // choose to use or distribute the source code for any other purpose, you
00006 // must either (1) first obtain written approval from Google, or (2)
00007 // prominently display the foregoing copyright notice and the following
00008 // warranty and liability disclaimer on each copy used or distributed.
00009 // 
00010 // The source code and repository (the "Software") is provided "AS IS",
00011 // with no warranty, express or implied, including but not limited to the
00012 // implied warranties of merchantability and fitness for a particular
00013 // use.  In no event shall Google Inc. be liable for any damages, direct
00014 // or indirect, even if advised of the possibility of such damages.
00015 //***************************************************************************
00016 
00017 
00018 #ifndef _LANG_ENC_H_
00019 #define _LANG_ENC_H_
00020 
00021 #define LATIN1           ISO_8859_1
00022 #define LATIN2           ISO_8859_2
00023 #define LATIN3           ISO_8859_3
00024 #define LATIN4           ISO_8859_4
00025 #define CYRILLIC         ISO_8859_5
00026 #define ARABIC_ENCODING  ISO_8859_6
00027 #define GREEK_ENCODING   ISO_8859_7
00028 #define HEBREW_ENCODING  ISO_8859_8
00029 #define LATIN5           ISO_8859_9
00030 #define LATIN6           ISO_8859_10
00031 #define KOREAN_HANGUL    KOREAN_EUC_KR
00032 
00033 enum Language {  
00034   ENGLISH = 0,         
00035   DANISH,
00036   DUTCH,
00037   FINNISH,
00038   FRENCH,
00039   GERMAN,
00040   HEBREW,
00041   ITALIAN,
00042   JAPANESE,
00043   KOREAN,
00044   NORWEGIAN,
00045   POLISH,
00046   PORTUGUESE,
00047   RUSSIAN,
00048   SPANISH,
00049   SWEDISH,
00050   CHINESE,            
00051   CZECH,              
00052   GREEK,              
00053   ICELANDIC,          
00054   LATVIAN,            
00055   LITHUANIAN,         
00056   ROMANIAN,           
00057   HUNGARIAN,          
00058   ESTONIAN,           
00059   OTHER_UNKNOWN_LANGUAGE,
00060   UNKNOWN_LANGUAGE, 
00061   BULGARIAN,                 
00062   CROATIAN,
00063   SERBIAN,
00064   IRISH,
00065   GALICIAN,
00066   TAGALOG,
00067   TURKISH,
00068   UKRAINIAN,
00069   HINDI,
00070   MACEDONIAN,
00071   BENGALI,
00072   INDONESIAN,
00073   LATIN,
00074   MALAY,
00075   MALAYALAM,
00076   WELSH,
00077   NEPALI,
00078   TELUGU,
00079   ALBANIAN,
00080   TAMIL,
00081   THAI,
00082   ARABIC,
00083   CATALAN,
00084   ESPERANTO,
00085   BASQUE,
00086   INTERLINGUA,
00087   KANNADA,
00088   PUNJABI,
00089   SCOTS_GAELIC,
00090   SWAHILI,
00091   SLOVENIAN,
00092   MARATHI,
00093   MALTESE,
00094   VIETNAMESE,
00095   FRISIAN,
00096   SLOVAK,
00097   NUM_LANGUAGES,              // Always keep this at the end. It is not a 
00098                               // valid Language enum, it is only used to 
00099                               // indicate the total number of Languages.
00100 };
00101 
00102 enum Encoding {  
00103   ISO_8859_1 = 0,
00104   ISO_8859_2,
00105   ISO_8859_3,
00106   ISO_8859_4,
00107   ISO_8859_5,
00108   ISO_8859_6,
00109   ISO_8859_7,
00110   ISO_8859_8,
00111   ISO_8859_9,
00112   ISO_8859_10,
00113   JAPANESE_EUC_JP,
00114   JAPANESE_SHIFT_JIS,
00115   JAPANESE_JIS,
00116   CHINESE_BIG5,
00117   CHINESE_GB,
00118   CHINESE_EUC_CN,
00119   KOREAN_EUC_KR,
00120   UNICODE,
00121   CHINESE_EUC_DEC,
00122   CHINESE_CNS,
00123   CHINESE_BIG5_CP950,
00124   JAPANESE_CP932,
00125   UTF8,
00126   UNKNOWN_ENCODING,
00127   ASCII_7BIT,                // ISO_8859_1 with all characters <= 127.
00128                              // never returned by Document::encoding().
00129   RUSSIAN_KOI8_R,
00130   RUSSIAN_CP1251,
00131   MSFT_CP1252,
00132   RUSSIAN_KOI8_RU,
00133   MSFT_CP1250,
00134   ISO_8859_15,
00135   MSFT_CP1254,
00136   MSFT_CP1257,
00137   ISO_8859_11,
00138   MSFT_CP874,
00139   MSFT_CP1256,
00140   MSFT_CP1255,               // Logical Hebrew Microsoft
00141   ISO_8859_8_I,              // Iso Hebrew Logical
00142   HEBREW_VISUAL,             // Iso Hebrew Visual
00143 
00144   NUM_ENCODINGS              // Always keep this at the end. It is not a 
00145                              // valid Encoding enum, it is only used to 
00146                              // indicate the total number of Encodings.
00147 };
00148 
00149 #define kDefaultLanguage ENGLISH
00150 #define kDefaultEncoding LATIN1
00151 
00152 #endif // _LANG_ENC_H_

Generated on Wed May 29 11:37:14 2002 for MarkovPR by doxygen1.2.15