Thomas Wouters | a977329 | 2006-04-21 09:43:23 +0000 | [diff] [blame] | 1 | """ Python Character Mapping Codec iso8859_5 generated from 'MAPPINGS/ISO8859/8859-5.TXT' with gencodec.py. |
Guido van Rossum | 0229bf6 | 2000-03-10 23:17:24 +0000 | [diff] [blame] | 2 | |
| 3 | """#" |
| 4 | |
| 5 | import codecs |
| 6 | |
| 7 | ### Codec APIs |
| 8 | |
| 9 | class Codec(codecs.Codec): |
| 10 | |
| 11 | def encode(self,input,errors='strict'): |
Thomas Wouters | 73e5a5b | 2006-06-08 15:35:45 +0000 | [diff] [blame] | 12 | return codecs.charmap_encode(input,errors,encoding_table) |
Tim Peters | 469cdad | 2002-08-08 20:19:19 +0000 | [diff] [blame] | 13 | |
Guido van Rossum | 0229bf6 | 2000-03-10 23:17:24 +0000 | [diff] [blame] | 14 | def decode(self,input,errors='strict'): |
Marc-André Lemburg | a1129f4 | 2005-10-21 13:49:12 +0000 | [diff] [blame] | 15 | return codecs.charmap_decode(input,errors,decoding_table) |
Tim Peters | 536cf99 | 2005-12-25 23:18:31 +0000 | [diff] [blame] | 16 | |
Thomas Wouters | a977329 | 2006-04-21 09:43:23 +0000 | [diff] [blame] | 17 | class IncrementalEncoder(codecs.IncrementalEncoder): |
| 18 | def encode(self, input, final=False): |
Thomas Wouters | 73e5a5b | 2006-06-08 15:35:45 +0000 | [diff] [blame] | 19 | return codecs.charmap_encode(input,self.errors,encoding_table)[0] |
Thomas Wouters | a977329 | 2006-04-21 09:43:23 +0000 | [diff] [blame] | 20 | |
| 21 | class IncrementalDecoder(codecs.IncrementalDecoder): |
| 22 | def decode(self, input, final=False): |
| 23 | return codecs.charmap_decode(input,self.errors,decoding_table)[0] |
| 24 | |
Guido van Rossum | 0229bf6 | 2000-03-10 23:17:24 +0000 | [diff] [blame] | 25 | class StreamWriter(Codec,codecs.StreamWriter): |
| 26 | pass |
Tim Peters | 469cdad | 2002-08-08 20:19:19 +0000 | [diff] [blame] | 27 | |
Guido van Rossum | 0229bf6 | 2000-03-10 23:17:24 +0000 | [diff] [blame] | 28 | class StreamReader(Codec,codecs.StreamReader): |
| 29 | pass |
| 30 | |
| 31 | ### encodings module API |
| 32 | |
| 33 | def getregentry(): |
Thomas Wouters | a977329 | 2006-04-21 09:43:23 +0000 | [diff] [blame] | 34 | return codecs.CodecInfo( |
| 35 | name='iso8859-5', |
| 36 | encode=Codec().encode, |
| 37 | decode=Codec().decode, |
| 38 | incrementalencoder=IncrementalEncoder, |
| 39 | incrementaldecoder=IncrementalDecoder, |
| 40 | streamreader=StreamReader, |
| 41 | streamwriter=StreamWriter, |
| 42 | ) |
Guido van Rossum | 0229bf6 | 2000-03-10 23:17:24 +0000 | [diff] [blame] | 43 | |
Guido van Rossum | 0229bf6 | 2000-03-10 23:17:24 +0000 | [diff] [blame] | 44 | |
Marc-André Lemburg | a1129f4 | 2005-10-21 13:49:12 +0000 | [diff] [blame] | 45 | ### Decoding Table |
| 46 | |
| 47 | decoding_table = ( |
Guido van Rossum | ef87d6e | 2007-05-02 19:09:54 +0000 | [diff] [blame] | 48 | '\x00' # 0x00 -> NULL |
| 49 | '\x01' # 0x01 -> START OF HEADING |
| 50 | '\x02' # 0x02 -> START OF TEXT |
| 51 | '\x03' # 0x03 -> END OF TEXT |
| 52 | '\x04' # 0x04 -> END OF TRANSMISSION |
| 53 | '\x05' # 0x05 -> ENQUIRY |
| 54 | '\x06' # 0x06 -> ACKNOWLEDGE |
| 55 | '\x07' # 0x07 -> BELL |
| 56 | '\x08' # 0x08 -> BACKSPACE |
| 57 | '\t' # 0x09 -> HORIZONTAL TABULATION |
| 58 | '\n' # 0x0A -> LINE FEED |
| 59 | '\x0b' # 0x0B -> VERTICAL TABULATION |
| 60 | '\x0c' # 0x0C -> FORM FEED |
| 61 | '\r' # 0x0D -> CARRIAGE RETURN |
| 62 | '\x0e' # 0x0E -> SHIFT OUT |
| 63 | '\x0f' # 0x0F -> SHIFT IN |
| 64 | '\x10' # 0x10 -> DATA LINK ESCAPE |
| 65 | '\x11' # 0x11 -> DEVICE CONTROL ONE |
| 66 | '\x12' # 0x12 -> DEVICE CONTROL TWO |
| 67 | '\x13' # 0x13 -> DEVICE CONTROL THREE |
| 68 | '\x14' # 0x14 -> DEVICE CONTROL FOUR |
| 69 | '\x15' # 0x15 -> NEGATIVE ACKNOWLEDGE |
| 70 | '\x16' # 0x16 -> SYNCHRONOUS IDLE |
| 71 | '\x17' # 0x17 -> END OF TRANSMISSION BLOCK |
| 72 | '\x18' # 0x18 -> CANCEL |
| 73 | '\x19' # 0x19 -> END OF MEDIUM |
| 74 | '\x1a' # 0x1A -> SUBSTITUTE |
| 75 | '\x1b' # 0x1B -> ESCAPE |
| 76 | '\x1c' # 0x1C -> FILE SEPARATOR |
| 77 | '\x1d' # 0x1D -> GROUP SEPARATOR |
| 78 | '\x1e' # 0x1E -> RECORD SEPARATOR |
| 79 | '\x1f' # 0x1F -> UNIT SEPARATOR |
| 80 | ' ' # 0x20 -> SPACE |
| 81 | '!' # 0x21 -> EXCLAMATION MARK |
| 82 | '"' # 0x22 -> QUOTATION MARK |
| 83 | '#' # 0x23 -> NUMBER SIGN |
| 84 | '$' # 0x24 -> DOLLAR SIGN |
| 85 | '%' # 0x25 -> PERCENT SIGN |
| 86 | '&' # 0x26 -> AMPERSAND |
| 87 | "'" # 0x27 -> APOSTROPHE |
| 88 | '(' # 0x28 -> LEFT PARENTHESIS |
| 89 | ')' # 0x29 -> RIGHT PARENTHESIS |
| 90 | '*' # 0x2A -> ASTERISK |
| 91 | '+' # 0x2B -> PLUS SIGN |
| 92 | ',' # 0x2C -> COMMA |
| 93 | '-' # 0x2D -> HYPHEN-MINUS |
| 94 | '.' # 0x2E -> FULL STOP |
| 95 | '/' # 0x2F -> SOLIDUS |
| 96 | '0' # 0x30 -> DIGIT ZERO |
| 97 | '1' # 0x31 -> DIGIT ONE |
| 98 | '2' # 0x32 -> DIGIT TWO |
| 99 | '3' # 0x33 -> DIGIT THREE |
| 100 | '4' # 0x34 -> DIGIT FOUR |
| 101 | '5' # 0x35 -> DIGIT FIVE |
| 102 | '6' # 0x36 -> DIGIT SIX |
| 103 | '7' # 0x37 -> DIGIT SEVEN |
| 104 | '8' # 0x38 -> DIGIT EIGHT |
| 105 | '9' # 0x39 -> DIGIT NINE |
| 106 | ':' # 0x3A -> COLON |
| 107 | ';' # 0x3B -> SEMICOLON |
| 108 | '<' # 0x3C -> LESS-THAN SIGN |
| 109 | '=' # 0x3D -> EQUALS SIGN |
| 110 | '>' # 0x3E -> GREATER-THAN SIGN |
| 111 | '?' # 0x3F -> QUESTION MARK |
| 112 | '@' # 0x40 -> COMMERCIAL AT |
| 113 | 'A' # 0x41 -> LATIN CAPITAL LETTER A |
| 114 | 'B' # 0x42 -> LATIN CAPITAL LETTER B |
| 115 | 'C' # 0x43 -> LATIN CAPITAL LETTER C |
| 116 | 'D' # 0x44 -> LATIN CAPITAL LETTER D |
| 117 | 'E' # 0x45 -> LATIN CAPITAL LETTER E |
| 118 | 'F' # 0x46 -> LATIN CAPITAL LETTER F |
| 119 | 'G' # 0x47 -> LATIN CAPITAL LETTER G |
| 120 | 'H' # 0x48 -> LATIN CAPITAL LETTER H |
| 121 | 'I' # 0x49 -> LATIN CAPITAL LETTER I |
| 122 | 'J' # 0x4A -> LATIN CAPITAL LETTER J |
| 123 | 'K' # 0x4B -> LATIN CAPITAL LETTER K |
| 124 | 'L' # 0x4C -> LATIN CAPITAL LETTER L |
| 125 | 'M' # 0x4D -> LATIN CAPITAL LETTER M |
| 126 | 'N' # 0x4E -> LATIN CAPITAL LETTER N |
| 127 | 'O' # 0x4F -> LATIN CAPITAL LETTER O |
| 128 | 'P' # 0x50 -> LATIN CAPITAL LETTER P |
| 129 | 'Q' # 0x51 -> LATIN CAPITAL LETTER Q |
| 130 | 'R' # 0x52 -> LATIN CAPITAL LETTER R |
| 131 | 'S' # 0x53 -> LATIN CAPITAL LETTER S |
| 132 | 'T' # 0x54 -> LATIN CAPITAL LETTER T |
| 133 | 'U' # 0x55 -> LATIN CAPITAL LETTER U |
| 134 | 'V' # 0x56 -> LATIN CAPITAL LETTER V |
| 135 | 'W' # 0x57 -> LATIN CAPITAL LETTER W |
| 136 | 'X' # 0x58 -> LATIN CAPITAL LETTER X |
| 137 | 'Y' # 0x59 -> LATIN CAPITAL LETTER Y |
| 138 | 'Z' # 0x5A -> LATIN CAPITAL LETTER Z |
| 139 | '[' # 0x5B -> LEFT SQUARE BRACKET |
| 140 | '\\' # 0x5C -> REVERSE SOLIDUS |
| 141 | ']' # 0x5D -> RIGHT SQUARE BRACKET |
| 142 | '^' # 0x5E -> CIRCUMFLEX ACCENT |
| 143 | '_' # 0x5F -> LOW LINE |
| 144 | '`' # 0x60 -> GRAVE ACCENT |
| 145 | 'a' # 0x61 -> LATIN SMALL LETTER A |
| 146 | 'b' # 0x62 -> LATIN SMALL LETTER B |
| 147 | 'c' # 0x63 -> LATIN SMALL LETTER C |
| 148 | 'd' # 0x64 -> LATIN SMALL LETTER D |
| 149 | 'e' # 0x65 -> LATIN SMALL LETTER E |
| 150 | 'f' # 0x66 -> LATIN SMALL LETTER F |
| 151 | 'g' # 0x67 -> LATIN SMALL LETTER G |
| 152 | 'h' # 0x68 -> LATIN SMALL LETTER H |
| 153 | 'i' # 0x69 -> LATIN SMALL LETTER I |
| 154 | 'j' # 0x6A -> LATIN SMALL LETTER J |
| 155 | 'k' # 0x6B -> LATIN SMALL LETTER K |
| 156 | 'l' # 0x6C -> LATIN SMALL LETTER L |
| 157 | 'm' # 0x6D -> LATIN SMALL LETTER M |
| 158 | 'n' # 0x6E -> LATIN SMALL LETTER N |
| 159 | 'o' # 0x6F -> LATIN SMALL LETTER O |
| 160 | 'p' # 0x70 -> LATIN SMALL LETTER P |
| 161 | 'q' # 0x71 -> LATIN SMALL LETTER Q |
| 162 | 'r' # 0x72 -> LATIN SMALL LETTER R |
| 163 | 's' # 0x73 -> LATIN SMALL LETTER S |
| 164 | 't' # 0x74 -> LATIN SMALL LETTER T |
| 165 | 'u' # 0x75 -> LATIN SMALL LETTER U |
| 166 | 'v' # 0x76 -> LATIN SMALL LETTER V |
| 167 | 'w' # 0x77 -> LATIN SMALL LETTER W |
| 168 | 'x' # 0x78 -> LATIN SMALL LETTER X |
| 169 | 'y' # 0x79 -> LATIN SMALL LETTER Y |
| 170 | 'z' # 0x7A -> LATIN SMALL LETTER Z |
| 171 | '{' # 0x7B -> LEFT CURLY BRACKET |
| 172 | '|' # 0x7C -> VERTICAL LINE |
| 173 | '}' # 0x7D -> RIGHT CURLY BRACKET |
| 174 | '~' # 0x7E -> TILDE |
| 175 | '\x7f' # 0x7F -> DELETE |
| 176 | '\x80' # 0x80 -> <control> |
| 177 | '\x81' # 0x81 -> <control> |
| 178 | '\x82' # 0x82 -> <control> |
| 179 | '\x83' # 0x83 -> <control> |
| 180 | '\x84' # 0x84 -> <control> |
| 181 | '\x85' # 0x85 -> <control> |
| 182 | '\x86' # 0x86 -> <control> |
| 183 | '\x87' # 0x87 -> <control> |
| 184 | '\x88' # 0x88 -> <control> |
| 185 | '\x89' # 0x89 -> <control> |
| 186 | '\x8a' # 0x8A -> <control> |
| 187 | '\x8b' # 0x8B -> <control> |
| 188 | '\x8c' # 0x8C -> <control> |
| 189 | '\x8d' # 0x8D -> <control> |
| 190 | '\x8e' # 0x8E -> <control> |
| 191 | '\x8f' # 0x8F -> <control> |
| 192 | '\x90' # 0x90 -> <control> |
| 193 | '\x91' # 0x91 -> <control> |
| 194 | '\x92' # 0x92 -> <control> |
| 195 | '\x93' # 0x93 -> <control> |
| 196 | '\x94' # 0x94 -> <control> |
| 197 | '\x95' # 0x95 -> <control> |
| 198 | '\x96' # 0x96 -> <control> |
| 199 | '\x97' # 0x97 -> <control> |
| 200 | '\x98' # 0x98 -> <control> |
| 201 | '\x99' # 0x99 -> <control> |
| 202 | '\x9a' # 0x9A -> <control> |
| 203 | '\x9b' # 0x9B -> <control> |
| 204 | '\x9c' # 0x9C -> <control> |
| 205 | '\x9d' # 0x9D -> <control> |
| 206 | '\x9e' # 0x9E -> <control> |
| 207 | '\x9f' # 0x9F -> <control> |
| 208 | '\xa0' # 0xA0 -> NO-BREAK SPACE |
| 209 | '\u0401' # 0xA1 -> CYRILLIC CAPITAL LETTER IO |
| 210 | '\u0402' # 0xA2 -> CYRILLIC CAPITAL LETTER DJE |
| 211 | '\u0403' # 0xA3 -> CYRILLIC CAPITAL LETTER GJE |
| 212 | '\u0404' # 0xA4 -> CYRILLIC CAPITAL LETTER UKRAINIAN IE |
| 213 | '\u0405' # 0xA5 -> CYRILLIC CAPITAL LETTER DZE |
| 214 | '\u0406' # 0xA6 -> CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN I |
| 215 | '\u0407' # 0xA7 -> CYRILLIC CAPITAL LETTER YI |
| 216 | '\u0408' # 0xA8 -> CYRILLIC CAPITAL LETTER JE |
| 217 | '\u0409' # 0xA9 -> CYRILLIC CAPITAL LETTER LJE |
| 218 | '\u040a' # 0xAA -> CYRILLIC CAPITAL LETTER NJE |
| 219 | '\u040b' # 0xAB -> CYRILLIC CAPITAL LETTER TSHE |
| 220 | '\u040c' # 0xAC -> CYRILLIC CAPITAL LETTER KJE |
| 221 | '\xad' # 0xAD -> SOFT HYPHEN |
| 222 | '\u040e' # 0xAE -> CYRILLIC CAPITAL LETTER SHORT U |
| 223 | '\u040f' # 0xAF -> CYRILLIC CAPITAL LETTER DZHE |
| 224 | '\u0410' # 0xB0 -> CYRILLIC CAPITAL LETTER A |
| 225 | '\u0411' # 0xB1 -> CYRILLIC CAPITAL LETTER BE |
| 226 | '\u0412' # 0xB2 -> CYRILLIC CAPITAL LETTER VE |
| 227 | '\u0413' # 0xB3 -> CYRILLIC CAPITAL LETTER GHE |
| 228 | '\u0414' # 0xB4 -> CYRILLIC CAPITAL LETTER DE |
| 229 | '\u0415' # 0xB5 -> CYRILLIC CAPITAL LETTER IE |
| 230 | '\u0416' # 0xB6 -> CYRILLIC CAPITAL LETTER ZHE |
| 231 | '\u0417' # 0xB7 -> CYRILLIC CAPITAL LETTER ZE |
| 232 | '\u0418' # 0xB8 -> CYRILLIC CAPITAL LETTER I |
| 233 | '\u0419' # 0xB9 -> CYRILLIC CAPITAL LETTER SHORT I |
| 234 | '\u041a' # 0xBA -> CYRILLIC CAPITAL LETTER KA |
| 235 | '\u041b' # 0xBB -> CYRILLIC CAPITAL LETTER EL |
| 236 | '\u041c' # 0xBC -> CYRILLIC CAPITAL LETTER EM |
| 237 | '\u041d' # 0xBD -> CYRILLIC CAPITAL LETTER EN |
| 238 | '\u041e' # 0xBE -> CYRILLIC CAPITAL LETTER O |
| 239 | '\u041f' # 0xBF -> CYRILLIC CAPITAL LETTER PE |
| 240 | '\u0420' # 0xC0 -> CYRILLIC CAPITAL LETTER ER |
| 241 | '\u0421' # 0xC1 -> CYRILLIC CAPITAL LETTER ES |
| 242 | '\u0422' # 0xC2 -> CYRILLIC CAPITAL LETTER TE |
| 243 | '\u0423' # 0xC3 -> CYRILLIC CAPITAL LETTER U |
| 244 | '\u0424' # 0xC4 -> CYRILLIC CAPITAL LETTER EF |
| 245 | '\u0425' # 0xC5 -> CYRILLIC CAPITAL LETTER HA |
| 246 | '\u0426' # 0xC6 -> CYRILLIC CAPITAL LETTER TSE |
| 247 | '\u0427' # 0xC7 -> CYRILLIC CAPITAL LETTER CHE |
| 248 | '\u0428' # 0xC8 -> CYRILLIC CAPITAL LETTER SHA |
| 249 | '\u0429' # 0xC9 -> CYRILLIC CAPITAL LETTER SHCHA |
| 250 | '\u042a' # 0xCA -> CYRILLIC CAPITAL LETTER HARD SIGN |
| 251 | '\u042b' # 0xCB -> CYRILLIC CAPITAL LETTER YERU |
| 252 | '\u042c' # 0xCC -> CYRILLIC CAPITAL LETTER SOFT SIGN |
| 253 | '\u042d' # 0xCD -> CYRILLIC CAPITAL LETTER E |
| 254 | '\u042e' # 0xCE -> CYRILLIC CAPITAL LETTER YU |
| 255 | '\u042f' # 0xCF -> CYRILLIC CAPITAL LETTER YA |
| 256 | '\u0430' # 0xD0 -> CYRILLIC SMALL LETTER A |
| 257 | '\u0431' # 0xD1 -> CYRILLIC SMALL LETTER BE |
| 258 | '\u0432' # 0xD2 -> CYRILLIC SMALL LETTER VE |
| 259 | '\u0433' # 0xD3 -> CYRILLIC SMALL LETTER GHE |
| 260 | '\u0434' # 0xD4 -> CYRILLIC SMALL LETTER DE |
| 261 | '\u0435' # 0xD5 -> CYRILLIC SMALL LETTER IE |
| 262 | '\u0436' # 0xD6 -> CYRILLIC SMALL LETTER ZHE |
| 263 | '\u0437' # 0xD7 -> CYRILLIC SMALL LETTER ZE |
| 264 | '\u0438' # 0xD8 -> CYRILLIC SMALL LETTER I |
| 265 | '\u0439' # 0xD9 -> CYRILLIC SMALL LETTER SHORT I |
| 266 | '\u043a' # 0xDA -> CYRILLIC SMALL LETTER KA |
| 267 | '\u043b' # 0xDB -> CYRILLIC SMALL LETTER EL |
| 268 | '\u043c' # 0xDC -> CYRILLIC SMALL LETTER EM |
| 269 | '\u043d' # 0xDD -> CYRILLIC SMALL LETTER EN |
| 270 | '\u043e' # 0xDE -> CYRILLIC SMALL LETTER O |
| 271 | '\u043f' # 0xDF -> CYRILLIC SMALL LETTER PE |
| 272 | '\u0440' # 0xE0 -> CYRILLIC SMALL LETTER ER |
| 273 | '\u0441' # 0xE1 -> CYRILLIC SMALL LETTER ES |
| 274 | '\u0442' # 0xE2 -> CYRILLIC SMALL LETTER TE |
| 275 | '\u0443' # 0xE3 -> CYRILLIC SMALL LETTER U |
| 276 | '\u0444' # 0xE4 -> CYRILLIC SMALL LETTER EF |
| 277 | '\u0445' # 0xE5 -> CYRILLIC SMALL LETTER HA |
| 278 | '\u0446' # 0xE6 -> CYRILLIC SMALL LETTER TSE |
| 279 | '\u0447' # 0xE7 -> CYRILLIC SMALL LETTER CHE |
| 280 | '\u0448' # 0xE8 -> CYRILLIC SMALL LETTER SHA |
| 281 | '\u0449' # 0xE9 -> CYRILLIC SMALL LETTER SHCHA |
| 282 | '\u044a' # 0xEA -> CYRILLIC SMALL LETTER HARD SIGN |
| 283 | '\u044b' # 0xEB -> CYRILLIC SMALL LETTER YERU |
| 284 | '\u044c' # 0xEC -> CYRILLIC SMALL LETTER SOFT SIGN |
| 285 | '\u044d' # 0xED -> CYRILLIC SMALL LETTER E |
| 286 | '\u044e' # 0xEE -> CYRILLIC SMALL LETTER YU |
| 287 | '\u044f' # 0xEF -> CYRILLIC SMALL LETTER YA |
| 288 | '\u2116' # 0xF0 -> NUMERO SIGN |
| 289 | '\u0451' # 0xF1 -> CYRILLIC SMALL LETTER IO |
| 290 | '\u0452' # 0xF2 -> CYRILLIC SMALL LETTER DJE |
| 291 | '\u0453' # 0xF3 -> CYRILLIC SMALL LETTER GJE |
| 292 | '\u0454' # 0xF4 -> CYRILLIC SMALL LETTER UKRAINIAN IE |
| 293 | '\u0455' # 0xF5 -> CYRILLIC SMALL LETTER DZE |
| 294 | '\u0456' # 0xF6 -> CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I |
| 295 | '\u0457' # 0xF7 -> CYRILLIC SMALL LETTER YI |
| 296 | '\u0458' # 0xF8 -> CYRILLIC SMALL LETTER JE |
| 297 | '\u0459' # 0xF9 -> CYRILLIC SMALL LETTER LJE |
| 298 | '\u045a' # 0xFA -> CYRILLIC SMALL LETTER NJE |
| 299 | '\u045b' # 0xFB -> CYRILLIC SMALL LETTER TSHE |
| 300 | '\u045c' # 0xFC -> CYRILLIC SMALL LETTER KJE |
| 301 | '\xa7' # 0xFD -> SECTION SIGN |
| 302 | '\u045e' # 0xFE -> CYRILLIC SMALL LETTER SHORT U |
| 303 | '\u045f' # 0xFF -> CYRILLIC SMALL LETTER DZHE |
Marc-André Lemburg | a1129f4 | 2005-10-21 13:49:12 +0000 | [diff] [blame] | 304 | ) |
| 305 | |
Thomas Wouters | 73e5a5b | 2006-06-08 15:35:45 +0000 | [diff] [blame] | 306 | ### Encoding table |
| 307 | encoding_table=codecs.charmap_build(decoding_table) |