Andrew Kuchling | ad8156e | 2013-11-10 13:44:30 -0500 | [diff] [blame] | 1 | """ Python Character Mapping Codec cp273 generated from 'python-mappings/CP273.TXT' with gencodec.py. |
| 2 | |
| 3 | """#" |
| 4 | |
| 5 | import codecs |
| 6 | |
| 7 | ### Codec APIs |
| 8 | |
| 9 | class Codec(codecs.Codec): |
| 10 | |
| 11 | def encode(self,input,errors='strict'): |
| 12 | return codecs.charmap_encode(input,errors,encoding_table) |
| 13 | |
| 14 | def decode(self,input,errors='strict'): |
| 15 | return codecs.charmap_decode(input,errors,decoding_table) |
| 16 | |
| 17 | class IncrementalEncoder(codecs.IncrementalEncoder): |
| 18 | def encode(self, input, final=False): |
| 19 | return codecs.charmap_encode(input,self.errors,encoding_table)[0] |
| 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 | |
| 25 | class StreamWriter(Codec,codecs.StreamWriter): |
| 26 | pass |
| 27 | |
| 28 | class StreamReader(Codec,codecs.StreamReader): |
| 29 | pass |
| 30 | |
| 31 | ### encodings module API |
| 32 | |
| 33 | def getregentry(): |
| 34 | return codecs.CodecInfo( |
| 35 | name='cp273', |
| 36 | encode=Codec().encode, |
| 37 | decode=Codec().decode, |
| 38 | incrementalencoder=IncrementalEncoder, |
| 39 | incrementaldecoder=IncrementalDecoder, |
| 40 | streamreader=StreamReader, |
| 41 | streamwriter=StreamWriter, |
| 42 | ) |
| 43 | |
| 44 | |
| 45 | ### Decoding Table |
| 46 | |
| 47 | decoding_table = ( |
| 48 | '\x00' # 0x00 -> NULL (NUL) |
| 49 | '\x01' # 0x01 -> START OF HEADING (SOH) |
| 50 | '\x02' # 0x02 -> START OF TEXT (STX) |
| 51 | '\x03' # 0x03 -> END OF TEXT (ETX) |
| 52 | '\x9c' # 0x04 -> STRING TERMINATOR (ST) |
| 53 | '\t' # 0x05 -> CHARACTER TABULATION (HT) |
| 54 | '\x86' # 0x06 -> START OF SELECTED AREA (SSA) |
| 55 | '\x7f' # 0x07 -> DELETE (DEL) |
| 56 | '\x97' # 0x08 -> END OF GUARDED AREA (EPA) |
| 57 | '\x8d' # 0x09 -> REVERSE LINE FEED (RI) |
| 58 | '\x8e' # 0x0A -> SINGLE-SHIFT TWO (SS2) |
| 59 | '\x0b' # 0x0B -> LINE TABULATION (VT) |
| 60 | '\x0c' # 0x0C -> FORM FEED (FF) |
| 61 | '\r' # 0x0D -> CARRIAGE RETURN (CR) |
| 62 | '\x0e' # 0x0E -> SHIFT OUT (SO) |
| 63 | '\x0f' # 0x0F -> SHIFT IN (SI) |
| 64 | '\x10' # 0x10 -> DATALINK ESCAPE (DLE) |
| 65 | '\x11' # 0x11 -> DEVICE CONTROL ONE (DC1) |
| 66 | '\x12' # 0x12 -> DEVICE CONTROL TWO (DC2) |
| 67 | '\x13' # 0x13 -> DEVICE CONTROL THREE (DC3) |
| 68 | '\x9d' # 0x14 -> OPERATING SYSTEM COMMAND (OSC) |
| 69 | '\x85' # 0x15 -> NEXT LINE (NEL) |
| 70 | '\x08' # 0x16 -> BACKSPACE (BS) |
| 71 | '\x87' # 0x17 -> END OF SELECTED AREA (ESA) |
| 72 | '\x18' # 0x18 -> CANCEL (CAN) |
| 73 | '\x19' # 0x19 -> END OF MEDIUM (EM) |
| 74 | '\x92' # 0x1A -> PRIVATE USE TWO (PU2) |
| 75 | '\x8f' # 0x1B -> SINGLE-SHIFT THREE (SS3) |
| 76 | '\x1c' # 0x1C -> FILE SEPARATOR (IS4) |
| 77 | '\x1d' # 0x1D -> GROUP SEPARATOR (IS3) |
| 78 | '\x1e' # 0x1E -> RECORD SEPARATOR (IS2) |
| 79 | '\x1f' # 0x1F -> UNIT SEPARATOR (IS1) |
| 80 | '\x80' # 0x20 -> PADDING CHARACTER (PAD) |
| 81 | '\x81' # 0x21 -> HIGH OCTET PRESET (HOP) |
| 82 | '\x82' # 0x22 -> BREAK PERMITTED HERE (BPH) |
| 83 | '\x83' # 0x23 -> NO BREAK HERE (NBH) |
| 84 | '\x84' # 0x24 -> INDEX (IND) |
| 85 | '\n' # 0x25 -> LINE FEED (LF) |
| 86 | '\x17' # 0x26 -> END OF TRANSMISSION BLOCK (ETB) |
| 87 | '\x1b' # 0x27 -> ESCAPE (ESC) |
| 88 | '\x88' # 0x28 -> CHARACTER TABULATION SET (HTS) |
| 89 | '\x89' # 0x29 -> CHARACTER TABULATION WITH JUSTIFICATION (HTJ) |
| 90 | '\x8a' # 0x2A -> LINE TABULATION SET (VTS) |
| 91 | '\x8b' # 0x2B -> PARTIAL LINE FORWARD (PLD) |
| 92 | '\x8c' # 0x2C -> PARTIAL LINE BACKWARD (PLU) |
| 93 | '\x05' # 0x2D -> ENQUIRY (ENQ) |
| 94 | '\x06' # 0x2E -> ACKNOWLEDGE (ACK) |
| 95 | '\x07' # 0x2F -> BELL (BEL) |
| 96 | '\x90' # 0x30 -> DEVICE CONTROL STRING (DCS) |
| 97 | '\x91' # 0x31 -> PRIVATE USE ONE (PU1) |
| 98 | '\x16' # 0x32 -> SYNCHRONOUS IDLE (SYN) |
| 99 | '\x93' # 0x33 -> SET TRANSMIT STATE (STS) |
| 100 | '\x94' # 0x34 -> CANCEL CHARACTER (CCH) |
| 101 | '\x95' # 0x35 -> MESSAGE WAITING (MW) |
| 102 | '\x96' # 0x36 -> START OF GUARDED AREA (SPA) |
| 103 | '\x04' # 0x37 -> END OF TRANSMISSION (EOT) |
| 104 | '\x98' # 0x38 -> START OF STRING (SOS) |
| 105 | '\x99' # 0x39 -> SINGLE GRAPHIC CHARACTER INTRODUCER (SGCI) |
| 106 | '\x9a' # 0x3A -> SINGLE CHARACTER INTRODUCER (SCI) |
| 107 | '\x9b' # 0x3B -> CONTROL SEQUENCE INTRODUCER (CSI) |
| 108 | '\x14' # 0x3C -> DEVICE CONTROL FOUR (DC4) |
| 109 | '\x15' # 0x3D -> NEGATIVE ACKNOWLEDGE (NAK) |
| 110 | '\x9e' # 0x3E -> PRIVACY MESSAGE (PM) |
| 111 | '\x1a' # 0x3F -> SUBSTITUTE (SUB) |
| 112 | ' ' # 0x40 -> SPACE |
| 113 | '\xa0' # 0x41 -> NO-BREAK SPACE |
| 114 | '\xe2' # 0x42 -> LATIN SMALL LETTER A WITH CIRCUMFLEX |
| 115 | '{' # 0x43 -> LEFT CURLY BRACKET |
| 116 | '\xe0' # 0x44 -> LATIN SMALL LETTER A WITH GRAVE |
| 117 | '\xe1' # 0x45 -> LATIN SMALL LETTER A WITH ACUTE |
| 118 | '\xe3' # 0x46 -> LATIN SMALL LETTER A WITH TILDE |
| 119 | '\xe5' # 0x47 -> LATIN SMALL LETTER A WITH RING ABOVE |
| 120 | '\xe7' # 0x48 -> LATIN SMALL LETTER C WITH CEDILLA |
| 121 | '\xf1' # 0x49 -> LATIN SMALL LETTER N WITH TILDE |
| 122 | '\xc4' # 0x4A -> LATIN CAPITAL LETTER A WITH DIAERESIS |
| 123 | '.' # 0x4B -> FULL STOP |
| 124 | '<' # 0x4C -> LESS-THAN SIGN |
| 125 | '(' # 0x4D -> LEFT PARENTHESIS |
| 126 | '+' # 0x4E -> PLUS SIGN |
| 127 | '!' # 0x4F -> EXCLAMATION MARK |
| 128 | '&' # 0x50 -> AMPERSAND |
| 129 | '\xe9' # 0x51 -> LATIN SMALL LETTER E WITH ACUTE |
| 130 | '\xea' # 0x52 -> LATIN SMALL LETTER E WITH CIRCUMFLEX |
| 131 | '\xeb' # 0x53 -> LATIN SMALL LETTER E WITH DIAERESIS |
| 132 | '\xe8' # 0x54 -> LATIN SMALL LETTER E WITH GRAVE |
| 133 | '\xed' # 0x55 -> LATIN SMALL LETTER I WITH ACUTE |
| 134 | '\xee' # 0x56 -> LATIN SMALL LETTER I WITH CIRCUMFLEX |
| 135 | '\xef' # 0x57 -> LATIN SMALL LETTER I WITH DIAERESIS |
| 136 | '\xec' # 0x58 -> LATIN SMALL LETTER I WITH GRAVE |
| 137 | '~' # 0x59 -> TILDE |
| 138 | '\xdc' # 0x5A -> LATIN CAPITAL LETTER U WITH DIAERESIS |
| 139 | '$' # 0x5B -> DOLLAR SIGN |
| 140 | '*' # 0x5C -> ASTERISK |
| 141 | ')' # 0x5D -> RIGHT PARENTHESIS |
| 142 | ';' # 0x5E -> SEMICOLON |
| 143 | '^' # 0x5F -> CIRCUMFLEX ACCENT |
| 144 | '-' # 0x60 -> HYPHEN-MINUS |
| 145 | '/' # 0x61 -> SOLIDUS |
| 146 | '\xc2' # 0x62 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX |
| 147 | '[' # 0x63 -> LEFT SQUARE BRACKET |
| 148 | '\xc0' # 0x64 -> LATIN CAPITAL LETTER A WITH GRAVE |
| 149 | '\xc1' # 0x65 -> LATIN CAPITAL LETTER A WITH ACUTE |
| 150 | '\xc3' # 0x66 -> LATIN CAPITAL LETTER A WITH TILDE |
| 151 | '\xc5' # 0x67 -> LATIN CAPITAL LETTER A WITH RING ABOVE |
| 152 | '\xc7' # 0x68 -> LATIN CAPITAL LETTER C WITH CEDILLA |
| 153 | '\xd1' # 0x69 -> LATIN CAPITAL LETTER N WITH TILDE |
| 154 | '\xf6' # 0x6A -> LATIN SMALL LETTER O WITH DIAERESIS |
| 155 | ',' # 0x6B -> COMMA |
| 156 | '%' # 0x6C -> PERCENT SIGN |
| 157 | '_' # 0x6D -> LOW LINE |
| 158 | '>' # 0x6E -> GREATER-THAN SIGN |
| 159 | '?' # 0x6F -> QUESTION MARK |
| 160 | '\xf8' # 0x70 -> LATIN SMALL LETTER O WITH STROKE |
| 161 | '\xc9' # 0x71 -> LATIN CAPITAL LETTER E WITH ACUTE |
| 162 | '\xca' # 0x72 -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX |
| 163 | '\xcb' # 0x73 -> LATIN CAPITAL LETTER E WITH DIAERESIS |
| 164 | '\xc8' # 0x74 -> LATIN CAPITAL LETTER E WITH GRAVE |
| 165 | '\xcd' # 0x75 -> LATIN CAPITAL LETTER I WITH ACUTE |
| 166 | '\xce' # 0x76 -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX |
| 167 | '\xcf' # 0x77 -> LATIN CAPITAL LETTER I WITH DIAERESIS |
| 168 | '\xcc' # 0x78 -> LATIN CAPITAL LETTER I WITH GRAVE |
| 169 | '`' # 0x79 -> GRAVE ACCENT |
| 170 | ':' # 0x7A -> COLON |
| 171 | '#' # 0x7B -> NUMBER SIGN |
| 172 | '\xa7' # 0x7C -> SECTION SIGN |
| 173 | "'" # 0x7D -> APOSTROPHE |
| 174 | '=' # 0x7E -> EQUALS SIGN |
| 175 | '"' # 0x7F -> QUOTATION MARK |
| 176 | '\xd8' # 0x80 -> LATIN CAPITAL LETTER O WITH STROKE |
| 177 | 'a' # 0x81 -> LATIN SMALL LETTER A |
| 178 | 'b' # 0x82 -> LATIN SMALL LETTER B |
| 179 | 'c' # 0x83 -> LATIN SMALL LETTER C |
| 180 | 'd' # 0x84 -> LATIN SMALL LETTER D |
| 181 | 'e' # 0x85 -> LATIN SMALL LETTER E |
| 182 | 'f' # 0x86 -> LATIN SMALL LETTER F |
| 183 | 'g' # 0x87 -> LATIN SMALL LETTER G |
| 184 | 'h' # 0x88 -> LATIN SMALL LETTER H |
| 185 | 'i' # 0x89 -> LATIN SMALL LETTER I |
| 186 | '\xab' # 0x8A -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK |
| 187 | '\xbb' # 0x8B -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK |
| 188 | '\xf0' # 0x8C -> LATIN SMALL LETTER ETH (Icelandic) |
| 189 | '\xfd' # 0x8D -> LATIN SMALL LETTER Y WITH ACUTE |
| 190 | '\xfe' # 0x8E -> LATIN SMALL LETTER THORN (Icelandic) |
| 191 | '\xb1' # 0x8F -> PLUS-MINUS SIGN |
| 192 | '\xb0' # 0x90 -> DEGREE SIGN |
| 193 | 'j' # 0x91 -> LATIN SMALL LETTER J |
| 194 | 'k' # 0x92 -> LATIN SMALL LETTER K |
| 195 | 'l' # 0x93 -> LATIN SMALL LETTER L |
| 196 | 'm' # 0x94 -> LATIN SMALL LETTER M |
| 197 | 'n' # 0x95 -> LATIN SMALL LETTER N |
| 198 | 'o' # 0x96 -> LATIN SMALL LETTER O |
| 199 | 'p' # 0x97 -> LATIN SMALL LETTER P |
| 200 | 'q' # 0x98 -> LATIN SMALL LETTER Q |
| 201 | 'r' # 0x99 -> LATIN SMALL LETTER R |
| 202 | '\xaa' # 0x9A -> FEMININE ORDINAL INDICATOR |
| 203 | '\xba' # 0x9B -> MASCULINE ORDINAL INDICATOR |
| 204 | '\xe6' # 0x9C -> LATIN SMALL LETTER AE |
| 205 | '\xb8' # 0x9D -> CEDILLA |
| 206 | '\xc6' # 0x9E -> LATIN CAPITAL LETTER AE |
| 207 | '\xa4' # 0x9F -> CURRENCY SIGN |
| 208 | '\xb5' # 0xA0 -> MICRO SIGN |
| 209 | '\xdf' # 0xA1 -> LATIN SMALL LETTER SHARP S (German) |
| 210 | 's' # 0xA2 -> LATIN SMALL LETTER S |
| 211 | 't' # 0xA3 -> LATIN SMALL LETTER T |
| 212 | 'u' # 0xA4 -> LATIN SMALL LETTER U |
| 213 | 'v' # 0xA5 -> LATIN SMALL LETTER V |
| 214 | 'w' # 0xA6 -> LATIN SMALL LETTER W |
| 215 | 'x' # 0xA7 -> LATIN SMALL LETTER X |
| 216 | 'y' # 0xA8 -> LATIN SMALL LETTER Y |
| 217 | 'z' # 0xA9 -> LATIN SMALL LETTER Z |
| 218 | '\xa1' # 0xAA -> INVERTED EXCLAMATION MARK |
| 219 | '\xbf' # 0xAB -> INVERTED QUESTION MARK |
| 220 | '\xd0' # 0xAC -> LATIN CAPITAL LETTER ETH (Icelandic) |
| 221 | '\xdd' # 0xAD -> LATIN CAPITAL LETTER Y WITH ACUTE |
| 222 | '\xde' # 0xAE -> LATIN CAPITAL LETTER THORN (Icelandic) |
| 223 | '\xae' # 0xAF -> REGISTERED SIGN |
| 224 | '\xa2' # 0xB0 -> CENT SIGN |
| 225 | '\xa3' # 0xB1 -> POUND SIGN |
| 226 | '\xa5' # 0xB2 -> YEN SIGN |
| 227 | '\xb7' # 0xB3 -> MIDDLE DOT |
| 228 | '\xa9' # 0xB4 -> COPYRIGHT SIGN |
| 229 | '@' # 0xB5 -> COMMERCIAL AT |
| 230 | '\xb6' # 0xB6 -> PILCROW SIGN |
| 231 | '\xbc' # 0xB7 -> VULGAR FRACTION ONE QUARTER |
| 232 | '\xbd' # 0xB8 -> VULGAR FRACTION ONE HALF |
| 233 | '\xbe' # 0xB9 -> VULGAR FRACTION THREE QUARTERS |
| 234 | '\xac' # 0xBA -> NOT SIGN |
| 235 | '|' # 0xBB -> VERTICAL LINE |
| 236 | '\u203e' # 0xBC -> OVERLINE |
| 237 | '\xa8' # 0xBD -> DIAERESIS |
| 238 | '\xb4' # 0xBE -> ACUTE ACCENT |
| 239 | '\xd7' # 0xBF -> MULTIPLICATION SIGN |
| 240 | '\xe4' # 0xC0 -> LATIN SMALL LETTER A WITH DIAERESIS |
| 241 | 'A' # 0xC1 -> LATIN CAPITAL LETTER A |
| 242 | 'B' # 0xC2 -> LATIN CAPITAL LETTER B |
| 243 | 'C' # 0xC3 -> LATIN CAPITAL LETTER C |
| 244 | 'D' # 0xC4 -> LATIN CAPITAL LETTER D |
| 245 | 'E' # 0xC5 -> LATIN CAPITAL LETTER E |
| 246 | 'F' # 0xC6 -> LATIN CAPITAL LETTER F |
| 247 | 'G' # 0xC7 -> LATIN CAPITAL LETTER G |
| 248 | 'H' # 0xC8 -> LATIN CAPITAL LETTER H |
| 249 | 'I' # 0xC9 -> LATIN CAPITAL LETTER I |
| 250 | '\xad' # 0xCA -> SOFT HYPHEN |
| 251 | '\xf4' # 0xCB -> LATIN SMALL LETTER O WITH CIRCUMFLEX |
| 252 | '\xa6' # 0xCC -> BROKEN BAR |
| 253 | '\xf2' # 0xCD -> LATIN SMALL LETTER O WITH GRAVE |
| 254 | '\xf3' # 0xCE -> LATIN SMALL LETTER O WITH ACUTE |
| 255 | '\xf5' # 0xCF -> LATIN SMALL LETTER O WITH TILDE |
| 256 | '\xfc' # 0xD0 -> LATIN SMALL LETTER U WITH DIAERESIS |
| 257 | 'J' # 0xD1 -> LATIN CAPITAL LETTER J |
| 258 | 'K' # 0xD2 -> LATIN CAPITAL LETTER K |
| 259 | 'L' # 0xD3 -> LATIN CAPITAL LETTER L |
| 260 | 'M' # 0xD4 -> LATIN CAPITAL LETTER M |
| 261 | 'N' # 0xD5 -> LATIN CAPITAL LETTER N |
| 262 | 'O' # 0xD6 -> LATIN CAPITAL LETTER O |
| 263 | 'P' # 0xD7 -> LATIN CAPITAL LETTER P |
| 264 | 'Q' # 0xD8 -> LATIN CAPITAL LETTER Q |
| 265 | 'R' # 0xD9 -> LATIN CAPITAL LETTER R |
| 266 | '\xb9' # 0xDA -> SUPERSCRIPT ONE |
| 267 | '\xfb' # 0xDB -> LATIN SMALL LETTER U WITH CIRCUMFLEX |
| 268 | '}' # 0xDC -> RIGHT CURLY BRACKET |
| 269 | '\xf9' # 0xDD -> LATIN SMALL LETTER U WITH GRAVE |
| 270 | '\xfa' # 0xDE -> LATIN SMALL LETTER U WITH ACUTE |
| 271 | '\xff' # 0xDF -> LATIN SMALL LETTER Y WITH DIAERESIS |
| 272 | '\xd6' # 0xE0 -> LATIN CAPITAL LETTER O WITH DIAERESIS |
| 273 | '\xf7' # 0xE1 -> DIVISION SIGN |
| 274 | 'S' # 0xE2 -> LATIN CAPITAL LETTER S |
| 275 | 'T' # 0xE3 -> LATIN CAPITAL LETTER T |
| 276 | 'U' # 0xE4 -> LATIN CAPITAL LETTER U |
| 277 | 'V' # 0xE5 -> LATIN CAPITAL LETTER V |
| 278 | 'W' # 0xE6 -> LATIN CAPITAL LETTER W |
| 279 | 'X' # 0xE7 -> LATIN CAPITAL LETTER X |
| 280 | 'Y' # 0xE8 -> LATIN CAPITAL LETTER Y |
| 281 | 'Z' # 0xE9 -> LATIN CAPITAL LETTER Z |
| 282 | '\xb2' # 0xEA -> SUPERSCRIPT TWO |
| 283 | '\xd4' # 0xEB -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX |
| 284 | '\\' # 0xEC -> REVERSE SOLIDUS |
| 285 | '\xd2' # 0xED -> LATIN CAPITAL LETTER O WITH GRAVE |
| 286 | '\xd3' # 0xEE -> LATIN CAPITAL LETTER O WITH ACUTE |
| 287 | '\xd5' # 0xEF -> LATIN CAPITAL LETTER O WITH TILDE |
| 288 | '0' # 0xF0 -> DIGIT ZERO |
| 289 | '1' # 0xF1 -> DIGIT ONE |
| 290 | '2' # 0xF2 -> DIGIT TWO |
| 291 | '3' # 0xF3 -> DIGIT THREE |
| 292 | '4' # 0xF4 -> DIGIT FOUR |
| 293 | '5' # 0xF5 -> DIGIT FIVE |
| 294 | '6' # 0xF6 -> DIGIT SIX |
| 295 | '7' # 0xF7 -> DIGIT SEVEN |
| 296 | '8' # 0xF8 -> DIGIT EIGHT |
| 297 | '9' # 0xF9 -> DIGIT NINE |
| 298 | '\xb3' # 0xFA -> SUPERSCRIPT THREE |
| 299 | '\xdb' # 0xFB -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX |
| 300 | ']' # 0xFC -> RIGHT SQUARE BRACKET |
| 301 | '\xd9' # 0xFD -> LATIN CAPITAL LETTER U WITH GRAVE |
| 302 | '\xda' # 0xFE -> LATIN CAPITAL LETTER U WITH ACUTE |
| 303 | '\x9f' # 0xFF -> APPLICATION PROGRAM COMMAND (APC) |
| 304 | ) |
| 305 | |
| 306 | ### Encoding table |
| 307 | encoding_table=codecs.charmap_build(decoding_table) |