blob: 68e61d396a1df3083e219b01d6de00a03f30bd59 [file] [log] [blame]
Marc-André Lemburga1129f42005-10-21 13:49:12 +00001""" Python Character Mapping Codec generated from 'VENDORS/MICSFT/WINDOWS/CP1253.TXT' with gencodec.py.
Guido van Rossum0229bf62000-03-10 23:17:24 +00002
3"""#"
4
5import codecs
6
7### Codec APIs
8
9class Codec(codecs.Codec):
10
11 def encode(self,input,errors='strict'):
12
13 return codecs.charmap_encode(input,errors,encoding_map)
Tim Peters469cdad2002-08-08 20:19:19 +000014
Guido van Rossum0229bf62000-03-10 23:17:24 +000015 def decode(self,input,errors='strict'):
16
Marc-André Lemburga1129f42005-10-21 13:49:12 +000017 return codecs.charmap_decode(input,errors,decoding_table)
18
Guido van Rossum0229bf62000-03-10 23:17:24 +000019class StreamWriter(Codec,codecs.StreamWriter):
20 pass
Tim Peters469cdad2002-08-08 20:19:19 +000021
Guido van Rossum0229bf62000-03-10 23:17:24 +000022class StreamReader(Codec,codecs.StreamReader):
23 pass
24
25### encodings module API
26
27def getregentry():
28
29 return (Codec().encode,Codec().decode,StreamReader,StreamWriter)
30
31### Decoding Map
32
Marc-André Lemburga866df82001-01-03 21:29:14 +000033decoding_map = codecs.make_identity_dict(range(256))
34decoding_map.update({
Marc-André Lemburga1129f42005-10-21 13:49:12 +000035 0x0080: 0x20ac, # EURO SIGN
36 0x0081: None, # UNDEFINED
37 0x0082: 0x201a, # SINGLE LOW-9 QUOTATION MARK
38 0x0083: 0x0192, # LATIN SMALL LETTER F WITH HOOK
39 0x0084: 0x201e, # DOUBLE LOW-9 QUOTATION MARK
40 0x0085: 0x2026, # HORIZONTAL ELLIPSIS
41 0x0086: 0x2020, # DAGGER
42 0x0087: 0x2021, # DOUBLE DAGGER
43 0x0088: None, # UNDEFINED
44 0x0089: 0x2030, # PER MILLE SIGN
45 0x008a: None, # UNDEFINED
46 0x008b: 0x2039, # SINGLE LEFT-POINTING ANGLE QUOTATION MARK
47 0x008c: None, # UNDEFINED
48 0x008d: None, # UNDEFINED
49 0x008e: None, # UNDEFINED
50 0x008f: None, # UNDEFINED
51 0x0090: None, # UNDEFINED
52 0x0091: 0x2018, # LEFT SINGLE QUOTATION MARK
53 0x0092: 0x2019, # RIGHT SINGLE QUOTATION MARK
54 0x0093: 0x201c, # LEFT DOUBLE QUOTATION MARK
55 0x0094: 0x201d, # RIGHT DOUBLE QUOTATION MARK
56 0x0095: 0x2022, # BULLET
57 0x0096: 0x2013, # EN DASH
58 0x0097: 0x2014, # EM DASH
59 0x0098: None, # UNDEFINED
60 0x0099: 0x2122, # TRADE MARK SIGN
61 0x009a: None, # UNDEFINED
62 0x009b: 0x203a, # SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
63 0x009c: None, # UNDEFINED
64 0x009d: None, # UNDEFINED
65 0x009e: None, # UNDEFINED
66 0x009f: None, # UNDEFINED
67 0x00a1: 0x0385, # GREEK DIALYTIKA TONOS
68 0x00a2: 0x0386, # GREEK CAPITAL LETTER ALPHA WITH TONOS
69 0x00aa: None, # UNDEFINED
70 0x00af: 0x2015, # HORIZONTAL BAR
71 0x00b4: 0x0384, # GREEK TONOS
72 0x00b8: 0x0388, # GREEK CAPITAL LETTER EPSILON WITH TONOS
73 0x00b9: 0x0389, # GREEK CAPITAL LETTER ETA WITH TONOS
74 0x00ba: 0x038a, # GREEK CAPITAL LETTER IOTA WITH TONOS
75 0x00bc: 0x038c, # GREEK CAPITAL LETTER OMICRON WITH TONOS
76 0x00be: 0x038e, # GREEK CAPITAL LETTER UPSILON WITH TONOS
77 0x00bf: 0x038f, # GREEK CAPITAL LETTER OMEGA WITH TONOS
78 0x00c0: 0x0390, # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND TONOS
79 0x00c1: 0x0391, # GREEK CAPITAL LETTER ALPHA
80 0x00c2: 0x0392, # GREEK CAPITAL LETTER BETA
81 0x00c3: 0x0393, # GREEK CAPITAL LETTER GAMMA
82 0x00c4: 0x0394, # GREEK CAPITAL LETTER DELTA
83 0x00c5: 0x0395, # GREEK CAPITAL LETTER EPSILON
84 0x00c6: 0x0396, # GREEK CAPITAL LETTER ZETA
85 0x00c7: 0x0397, # GREEK CAPITAL LETTER ETA
86 0x00c8: 0x0398, # GREEK CAPITAL LETTER THETA
87 0x00c9: 0x0399, # GREEK CAPITAL LETTER IOTA
88 0x00ca: 0x039a, # GREEK CAPITAL LETTER KAPPA
89 0x00cb: 0x039b, # GREEK CAPITAL LETTER LAMDA
90 0x00cc: 0x039c, # GREEK CAPITAL LETTER MU
91 0x00cd: 0x039d, # GREEK CAPITAL LETTER NU
92 0x00ce: 0x039e, # GREEK CAPITAL LETTER XI
93 0x00cf: 0x039f, # GREEK CAPITAL LETTER OMICRON
94 0x00d0: 0x03a0, # GREEK CAPITAL LETTER PI
95 0x00d1: 0x03a1, # GREEK CAPITAL LETTER RHO
96 0x00d2: None, # UNDEFINED
97 0x00d3: 0x03a3, # GREEK CAPITAL LETTER SIGMA
98 0x00d4: 0x03a4, # GREEK CAPITAL LETTER TAU
99 0x00d5: 0x03a5, # GREEK CAPITAL LETTER UPSILON
100 0x00d6: 0x03a6, # GREEK CAPITAL LETTER PHI
101 0x00d7: 0x03a7, # GREEK CAPITAL LETTER CHI
102 0x00d8: 0x03a8, # GREEK CAPITAL LETTER PSI
103 0x00d9: 0x03a9, # GREEK CAPITAL LETTER OMEGA
104 0x00da: 0x03aa, # GREEK CAPITAL LETTER IOTA WITH DIALYTIKA
105 0x00db: 0x03ab, # GREEK CAPITAL LETTER UPSILON WITH DIALYTIKA
106 0x00dc: 0x03ac, # GREEK SMALL LETTER ALPHA WITH TONOS
107 0x00dd: 0x03ad, # GREEK SMALL LETTER EPSILON WITH TONOS
108 0x00de: 0x03ae, # GREEK SMALL LETTER ETA WITH TONOS
109 0x00df: 0x03af, # GREEK SMALL LETTER IOTA WITH TONOS
110 0x00e0: 0x03b0, # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND TONOS
111 0x00e1: 0x03b1, # GREEK SMALL LETTER ALPHA
112 0x00e2: 0x03b2, # GREEK SMALL LETTER BETA
113 0x00e3: 0x03b3, # GREEK SMALL LETTER GAMMA
114 0x00e4: 0x03b4, # GREEK SMALL LETTER DELTA
115 0x00e5: 0x03b5, # GREEK SMALL LETTER EPSILON
116 0x00e6: 0x03b6, # GREEK SMALL LETTER ZETA
117 0x00e7: 0x03b7, # GREEK SMALL LETTER ETA
118 0x00e8: 0x03b8, # GREEK SMALL LETTER THETA
119 0x00e9: 0x03b9, # GREEK SMALL LETTER IOTA
120 0x00ea: 0x03ba, # GREEK SMALL LETTER KAPPA
121 0x00eb: 0x03bb, # GREEK SMALL LETTER LAMDA
122 0x00ec: 0x03bc, # GREEK SMALL LETTER MU
123 0x00ed: 0x03bd, # GREEK SMALL LETTER NU
124 0x00ee: 0x03be, # GREEK SMALL LETTER XI
125 0x00ef: 0x03bf, # GREEK SMALL LETTER OMICRON
126 0x00f0: 0x03c0, # GREEK SMALL LETTER PI
127 0x00f1: 0x03c1, # GREEK SMALL LETTER RHO
128 0x00f2: 0x03c2, # GREEK SMALL LETTER FINAL SIGMA
129 0x00f3: 0x03c3, # GREEK SMALL LETTER SIGMA
130 0x00f4: 0x03c4, # GREEK SMALL LETTER TAU
131 0x00f5: 0x03c5, # GREEK SMALL LETTER UPSILON
132 0x00f6: 0x03c6, # GREEK SMALL LETTER PHI
133 0x00f7: 0x03c7, # GREEK SMALL LETTER CHI
134 0x00f8: 0x03c8, # GREEK SMALL LETTER PSI
135 0x00f9: 0x03c9, # GREEK SMALL LETTER OMEGA
136 0x00fa: 0x03ca, # GREEK SMALL LETTER IOTA WITH DIALYTIKA
137 0x00fb: 0x03cb, # GREEK SMALL LETTER UPSILON WITH DIALYTIKA
138 0x00fc: 0x03cc, # GREEK SMALL LETTER OMICRON WITH TONOS
139 0x00fd: 0x03cd, # GREEK SMALL LETTER UPSILON WITH TONOS
140 0x00fe: 0x03ce, # GREEK SMALL LETTER OMEGA WITH TONOS
141 0x00ff: None, # UNDEFINED
Marc-André Lemburga866df82001-01-03 21:29:14 +0000142})
Guido van Rossum0229bf62000-03-10 23:17:24 +0000143
Marc-André Lemburga1129f42005-10-21 13:49:12 +0000144### Decoding Table
145
146decoding_table = (
147 u'\x00' # 0x0000 -> NULL
148 u'\x01' # 0x0001 -> START OF HEADING
149 u'\x02' # 0x0002 -> START OF TEXT
150 u'\x03' # 0x0003 -> END OF TEXT
151 u'\x04' # 0x0004 -> END OF TRANSMISSION
152 u'\x05' # 0x0005 -> ENQUIRY
153 u'\x06' # 0x0006 -> ACKNOWLEDGE
154 u'\x07' # 0x0007 -> BELL
155 u'\x08' # 0x0008 -> BACKSPACE
156 u'\t' # 0x0009 -> HORIZONTAL TABULATION
157 u'\n' # 0x000a -> LINE FEED
158 u'\x0b' # 0x000b -> VERTICAL TABULATION
159 u'\x0c' # 0x000c -> FORM FEED
160 u'\r' # 0x000d -> CARRIAGE RETURN
161 u'\x0e' # 0x000e -> SHIFT OUT
162 u'\x0f' # 0x000f -> SHIFT IN
163 u'\x10' # 0x0010 -> DATA LINK ESCAPE
164 u'\x11' # 0x0011 -> DEVICE CONTROL ONE
165 u'\x12' # 0x0012 -> DEVICE CONTROL TWO
166 u'\x13' # 0x0013 -> DEVICE CONTROL THREE
167 u'\x14' # 0x0014 -> DEVICE CONTROL FOUR
168 u'\x15' # 0x0015 -> NEGATIVE ACKNOWLEDGE
169 u'\x16' # 0x0016 -> SYNCHRONOUS IDLE
170 u'\x17' # 0x0017 -> END OF TRANSMISSION BLOCK
171 u'\x18' # 0x0018 -> CANCEL
172 u'\x19' # 0x0019 -> END OF MEDIUM
173 u'\x1a' # 0x001a -> SUBSTITUTE
174 u'\x1b' # 0x001b -> ESCAPE
175 u'\x1c' # 0x001c -> FILE SEPARATOR
176 u'\x1d' # 0x001d -> GROUP SEPARATOR
177 u'\x1e' # 0x001e -> RECORD SEPARATOR
178 u'\x1f' # 0x001f -> UNIT SEPARATOR
179 u' ' # 0x0020 -> SPACE
180 u'!' # 0x0021 -> EXCLAMATION MARK
181 u'"' # 0x0022 -> QUOTATION MARK
182 u'#' # 0x0023 -> NUMBER SIGN
183 u'$' # 0x0024 -> DOLLAR SIGN
184 u'%' # 0x0025 -> PERCENT SIGN
185 u'&' # 0x0026 -> AMPERSAND
186 u"'" # 0x0027 -> APOSTROPHE
187 u'(' # 0x0028 -> LEFT PARENTHESIS
188 u')' # 0x0029 -> RIGHT PARENTHESIS
189 u'*' # 0x002a -> ASTERISK
190 u'+' # 0x002b -> PLUS SIGN
191 u',' # 0x002c -> COMMA
192 u'-' # 0x002d -> HYPHEN-MINUS
193 u'.' # 0x002e -> FULL STOP
194 u'/' # 0x002f -> SOLIDUS
195 u'0' # 0x0030 -> DIGIT ZERO
196 u'1' # 0x0031 -> DIGIT ONE
197 u'2' # 0x0032 -> DIGIT TWO
198 u'3' # 0x0033 -> DIGIT THREE
199 u'4' # 0x0034 -> DIGIT FOUR
200 u'5' # 0x0035 -> DIGIT FIVE
201 u'6' # 0x0036 -> DIGIT SIX
202 u'7' # 0x0037 -> DIGIT SEVEN
203 u'8' # 0x0038 -> DIGIT EIGHT
204 u'9' # 0x0039 -> DIGIT NINE
205 u':' # 0x003a -> COLON
206 u';' # 0x003b -> SEMICOLON
207 u'<' # 0x003c -> LESS-THAN SIGN
208 u'=' # 0x003d -> EQUALS SIGN
209 u'>' # 0x003e -> GREATER-THAN SIGN
210 u'?' # 0x003f -> QUESTION MARK
211 u'@' # 0x0040 -> COMMERCIAL AT
212 u'A' # 0x0041 -> LATIN CAPITAL LETTER A
213 u'B' # 0x0042 -> LATIN CAPITAL LETTER B
214 u'C' # 0x0043 -> LATIN CAPITAL LETTER C
215 u'D' # 0x0044 -> LATIN CAPITAL LETTER D
216 u'E' # 0x0045 -> LATIN CAPITAL LETTER E
217 u'F' # 0x0046 -> LATIN CAPITAL LETTER F
218 u'G' # 0x0047 -> LATIN CAPITAL LETTER G
219 u'H' # 0x0048 -> LATIN CAPITAL LETTER H
220 u'I' # 0x0049 -> LATIN CAPITAL LETTER I
221 u'J' # 0x004a -> LATIN CAPITAL LETTER J
222 u'K' # 0x004b -> LATIN CAPITAL LETTER K
223 u'L' # 0x004c -> LATIN CAPITAL LETTER L
224 u'M' # 0x004d -> LATIN CAPITAL LETTER M
225 u'N' # 0x004e -> LATIN CAPITAL LETTER N
226 u'O' # 0x004f -> LATIN CAPITAL LETTER O
227 u'P' # 0x0050 -> LATIN CAPITAL LETTER P
228 u'Q' # 0x0051 -> LATIN CAPITAL LETTER Q
229 u'R' # 0x0052 -> LATIN CAPITAL LETTER R
230 u'S' # 0x0053 -> LATIN CAPITAL LETTER S
231 u'T' # 0x0054 -> LATIN CAPITAL LETTER T
232 u'U' # 0x0055 -> LATIN CAPITAL LETTER U
233 u'V' # 0x0056 -> LATIN CAPITAL LETTER V
234 u'W' # 0x0057 -> LATIN CAPITAL LETTER W
235 u'X' # 0x0058 -> LATIN CAPITAL LETTER X
236 u'Y' # 0x0059 -> LATIN CAPITAL LETTER Y
237 u'Z' # 0x005a -> LATIN CAPITAL LETTER Z
238 u'[' # 0x005b -> LEFT SQUARE BRACKET
239 u'\\' # 0x005c -> REVERSE SOLIDUS
240 u']' # 0x005d -> RIGHT SQUARE BRACKET
241 u'^' # 0x005e -> CIRCUMFLEX ACCENT
242 u'_' # 0x005f -> LOW LINE
243 u'`' # 0x0060 -> GRAVE ACCENT
244 u'a' # 0x0061 -> LATIN SMALL LETTER A
245 u'b' # 0x0062 -> LATIN SMALL LETTER B
246 u'c' # 0x0063 -> LATIN SMALL LETTER C
247 u'd' # 0x0064 -> LATIN SMALL LETTER D
248 u'e' # 0x0065 -> LATIN SMALL LETTER E
249 u'f' # 0x0066 -> LATIN SMALL LETTER F
250 u'g' # 0x0067 -> LATIN SMALL LETTER G
251 u'h' # 0x0068 -> LATIN SMALL LETTER H
252 u'i' # 0x0069 -> LATIN SMALL LETTER I
253 u'j' # 0x006a -> LATIN SMALL LETTER J
254 u'k' # 0x006b -> LATIN SMALL LETTER K
255 u'l' # 0x006c -> LATIN SMALL LETTER L
256 u'm' # 0x006d -> LATIN SMALL LETTER M
257 u'n' # 0x006e -> LATIN SMALL LETTER N
258 u'o' # 0x006f -> LATIN SMALL LETTER O
259 u'p' # 0x0070 -> LATIN SMALL LETTER P
260 u'q' # 0x0071 -> LATIN SMALL LETTER Q
261 u'r' # 0x0072 -> LATIN SMALL LETTER R
262 u's' # 0x0073 -> LATIN SMALL LETTER S
263 u't' # 0x0074 -> LATIN SMALL LETTER T
264 u'u' # 0x0075 -> LATIN SMALL LETTER U
265 u'v' # 0x0076 -> LATIN SMALL LETTER V
266 u'w' # 0x0077 -> LATIN SMALL LETTER W
267 u'x' # 0x0078 -> LATIN SMALL LETTER X
268 u'y' # 0x0079 -> LATIN SMALL LETTER Y
269 u'z' # 0x007a -> LATIN SMALL LETTER Z
270 u'{' # 0x007b -> LEFT CURLY BRACKET
271 u'|' # 0x007c -> VERTICAL LINE
272 u'}' # 0x007d -> RIGHT CURLY BRACKET
273 u'~' # 0x007e -> TILDE
274 u'\x7f' # 0x007f -> DELETE
275 u'\u20ac' # 0x0080 -> EURO SIGN
276 u'\ufffe' # 0x0081 -> UNDEFINED
277 u'\u201a' # 0x0082 -> SINGLE LOW-9 QUOTATION MARK
278 u'\u0192' # 0x0083 -> LATIN SMALL LETTER F WITH HOOK
279 u'\u201e' # 0x0084 -> DOUBLE LOW-9 QUOTATION MARK
280 u'\u2026' # 0x0085 -> HORIZONTAL ELLIPSIS
281 u'\u2020' # 0x0086 -> DAGGER
282 u'\u2021' # 0x0087 -> DOUBLE DAGGER
283 u'\ufffe' # 0x0088 -> UNDEFINED
284 u'\u2030' # 0x0089 -> PER MILLE SIGN
285 u'\ufffe' # 0x008a -> UNDEFINED
286 u'\u2039' # 0x008b -> SINGLE LEFT-POINTING ANGLE QUOTATION MARK
287 u'\ufffe' # 0x008c -> UNDEFINED
288 u'\ufffe' # 0x008d -> UNDEFINED
289 u'\ufffe' # 0x008e -> UNDEFINED
290 u'\ufffe' # 0x008f -> UNDEFINED
291 u'\ufffe' # 0x0090 -> UNDEFINED
292 u'\u2018' # 0x0091 -> LEFT SINGLE QUOTATION MARK
293 u'\u2019' # 0x0092 -> RIGHT SINGLE QUOTATION MARK
294 u'\u201c' # 0x0093 -> LEFT DOUBLE QUOTATION MARK
295 u'\u201d' # 0x0094 -> RIGHT DOUBLE QUOTATION MARK
296 u'\u2022' # 0x0095 -> BULLET
297 u'\u2013' # 0x0096 -> EN DASH
298 u'\u2014' # 0x0097 -> EM DASH
299 u'\ufffe' # 0x0098 -> UNDEFINED
300 u'\u2122' # 0x0099 -> TRADE MARK SIGN
301 u'\ufffe' # 0x009a -> UNDEFINED
302 u'\u203a' # 0x009b -> SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
303 u'\ufffe' # 0x009c -> UNDEFINED
304 u'\ufffe' # 0x009d -> UNDEFINED
305 u'\ufffe' # 0x009e -> UNDEFINED
306 u'\ufffe' # 0x009f -> UNDEFINED
307 u'\xa0' # 0x00a0 -> NO-BREAK SPACE
308 u'\u0385' # 0x00a1 -> GREEK DIALYTIKA TONOS
309 u'\u0386' # 0x00a2 -> GREEK CAPITAL LETTER ALPHA WITH TONOS
310 u'\xa3' # 0x00a3 -> POUND SIGN
311 u'\xa4' # 0x00a4 -> CURRENCY SIGN
312 u'\xa5' # 0x00a5 -> YEN SIGN
313 u'\xa6' # 0x00a6 -> BROKEN BAR
314 u'\xa7' # 0x00a7 -> SECTION SIGN
315 u'\xa8' # 0x00a8 -> DIAERESIS
316 u'\xa9' # 0x00a9 -> COPYRIGHT SIGN
317 u'\ufffe' # 0x00aa -> UNDEFINED
318 u'\xab' # 0x00ab -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
319 u'\xac' # 0x00ac -> NOT SIGN
320 u'\xad' # 0x00ad -> SOFT HYPHEN
321 u'\xae' # 0x00ae -> REGISTERED SIGN
322 u'\u2015' # 0x00af -> HORIZONTAL BAR
323 u'\xb0' # 0x00b0 -> DEGREE SIGN
324 u'\xb1' # 0x00b1 -> PLUS-MINUS SIGN
325 u'\xb2' # 0x00b2 -> SUPERSCRIPT TWO
326 u'\xb3' # 0x00b3 -> SUPERSCRIPT THREE
327 u'\u0384' # 0x00b4 -> GREEK TONOS
328 u'\xb5' # 0x00b5 -> MICRO SIGN
329 u'\xb6' # 0x00b6 -> PILCROW SIGN
330 u'\xb7' # 0x00b7 -> MIDDLE DOT
331 u'\u0388' # 0x00b8 -> GREEK CAPITAL LETTER EPSILON WITH TONOS
332 u'\u0389' # 0x00b9 -> GREEK CAPITAL LETTER ETA WITH TONOS
333 u'\u038a' # 0x00ba -> GREEK CAPITAL LETTER IOTA WITH TONOS
334 u'\xbb' # 0x00bb -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
335 u'\u038c' # 0x00bc -> GREEK CAPITAL LETTER OMICRON WITH TONOS
336 u'\xbd' # 0x00bd -> VULGAR FRACTION ONE HALF
337 u'\u038e' # 0x00be -> GREEK CAPITAL LETTER UPSILON WITH TONOS
338 u'\u038f' # 0x00bf -> GREEK CAPITAL LETTER OMEGA WITH TONOS
339 u'\u0390' # 0x00c0 -> GREEK SMALL LETTER IOTA WITH DIALYTIKA AND TONOS
340 u'\u0391' # 0x00c1 -> GREEK CAPITAL LETTER ALPHA
341 u'\u0392' # 0x00c2 -> GREEK CAPITAL LETTER BETA
342 u'\u0393' # 0x00c3 -> GREEK CAPITAL LETTER GAMMA
343 u'\u0394' # 0x00c4 -> GREEK CAPITAL LETTER DELTA
344 u'\u0395' # 0x00c5 -> GREEK CAPITAL LETTER EPSILON
345 u'\u0396' # 0x00c6 -> GREEK CAPITAL LETTER ZETA
346 u'\u0397' # 0x00c7 -> GREEK CAPITAL LETTER ETA
347 u'\u0398' # 0x00c8 -> GREEK CAPITAL LETTER THETA
348 u'\u0399' # 0x00c9 -> GREEK CAPITAL LETTER IOTA
349 u'\u039a' # 0x00ca -> GREEK CAPITAL LETTER KAPPA
350 u'\u039b' # 0x00cb -> GREEK CAPITAL LETTER LAMDA
351 u'\u039c' # 0x00cc -> GREEK CAPITAL LETTER MU
352 u'\u039d' # 0x00cd -> GREEK CAPITAL LETTER NU
353 u'\u039e' # 0x00ce -> GREEK CAPITAL LETTER XI
354 u'\u039f' # 0x00cf -> GREEK CAPITAL LETTER OMICRON
355 u'\u03a0' # 0x00d0 -> GREEK CAPITAL LETTER PI
356 u'\u03a1' # 0x00d1 -> GREEK CAPITAL LETTER RHO
357 u'\ufffe' # 0x00d2 -> UNDEFINED
358 u'\u03a3' # 0x00d3 -> GREEK CAPITAL LETTER SIGMA
359 u'\u03a4' # 0x00d4 -> GREEK CAPITAL LETTER TAU
360 u'\u03a5' # 0x00d5 -> GREEK CAPITAL LETTER UPSILON
361 u'\u03a6' # 0x00d6 -> GREEK CAPITAL LETTER PHI
362 u'\u03a7' # 0x00d7 -> GREEK CAPITAL LETTER CHI
363 u'\u03a8' # 0x00d8 -> GREEK CAPITAL LETTER PSI
364 u'\u03a9' # 0x00d9 -> GREEK CAPITAL LETTER OMEGA
365 u'\u03aa' # 0x00da -> GREEK CAPITAL LETTER IOTA WITH DIALYTIKA
366 u'\u03ab' # 0x00db -> GREEK CAPITAL LETTER UPSILON WITH DIALYTIKA
367 u'\u03ac' # 0x00dc -> GREEK SMALL LETTER ALPHA WITH TONOS
368 u'\u03ad' # 0x00dd -> GREEK SMALL LETTER EPSILON WITH TONOS
369 u'\u03ae' # 0x00de -> GREEK SMALL LETTER ETA WITH TONOS
370 u'\u03af' # 0x00df -> GREEK SMALL LETTER IOTA WITH TONOS
371 u'\u03b0' # 0x00e0 -> GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND TONOS
372 u'\u03b1' # 0x00e1 -> GREEK SMALL LETTER ALPHA
373 u'\u03b2' # 0x00e2 -> GREEK SMALL LETTER BETA
374 u'\u03b3' # 0x00e3 -> GREEK SMALL LETTER GAMMA
375 u'\u03b4' # 0x00e4 -> GREEK SMALL LETTER DELTA
376 u'\u03b5' # 0x00e5 -> GREEK SMALL LETTER EPSILON
377 u'\u03b6' # 0x00e6 -> GREEK SMALL LETTER ZETA
378 u'\u03b7' # 0x00e7 -> GREEK SMALL LETTER ETA
379 u'\u03b8' # 0x00e8 -> GREEK SMALL LETTER THETA
380 u'\u03b9' # 0x00e9 -> GREEK SMALL LETTER IOTA
381 u'\u03ba' # 0x00ea -> GREEK SMALL LETTER KAPPA
382 u'\u03bb' # 0x00eb -> GREEK SMALL LETTER LAMDA
383 u'\u03bc' # 0x00ec -> GREEK SMALL LETTER MU
384 u'\u03bd' # 0x00ed -> GREEK SMALL LETTER NU
385 u'\u03be' # 0x00ee -> GREEK SMALL LETTER XI
386 u'\u03bf' # 0x00ef -> GREEK SMALL LETTER OMICRON
387 u'\u03c0' # 0x00f0 -> GREEK SMALL LETTER PI
388 u'\u03c1' # 0x00f1 -> GREEK SMALL LETTER RHO
389 u'\u03c2' # 0x00f2 -> GREEK SMALL LETTER FINAL SIGMA
390 u'\u03c3' # 0x00f3 -> GREEK SMALL LETTER SIGMA
391 u'\u03c4' # 0x00f4 -> GREEK SMALL LETTER TAU
392 u'\u03c5' # 0x00f5 -> GREEK SMALL LETTER UPSILON
393 u'\u03c6' # 0x00f6 -> GREEK SMALL LETTER PHI
394 u'\u03c7' # 0x00f7 -> GREEK SMALL LETTER CHI
395 u'\u03c8' # 0x00f8 -> GREEK SMALL LETTER PSI
396 u'\u03c9' # 0x00f9 -> GREEK SMALL LETTER OMEGA
397 u'\u03ca' # 0x00fa -> GREEK SMALL LETTER IOTA WITH DIALYTIKA
398 u'\u03cb' # 0x00fb -> GREEK SMALL LETTER UPSILON WITH DIALYTIKA
399 u'\u03cc' # 0x00fc -> GREEK SMALL LETTER OMICRON WITH TONOS
400 u'\u03cd' # 0x00fd -> GREEK SMALL LETTER UPSILON WITH TONOS
401 u'\u03ce' # 0x00fe -> GREEK SMALL LETTER OMEGA WITH TONOS
402 u'\ufffe' # 0x00ff -> UNDEFINED
403)
404
Guido van Rossum0229bf62000-03-10 23:17:24 +0000405### Encoding Map
406
Marc-André Lemburga1129f42005-10-21 13:49:12 +0000407encoding_map = {
408 0x0000: 0x0000, # NULL
409 0x0001: 0x0001, # START OF HEADING
410 0x0002: 0x0002, # START OF TEXT
411 0x0003: 0x0003, # END OF TEXT
412 0x0004: 0x0004, # END OF TRANSMISSION
413 0x0005: 0x0005, # ENQUIRY
414 0x0006: 0x0006, # ACKNOWLEDGE
415 0x0007: 0x0007, # BELL
416 0x0008: 0x0008, # BACKSPACE
417 0x0009: 0x0009, # HORIZONTAL TABULATION
418 0x000a: 0x000a, # LINE FEED
419 0x000b: 0x000b, # VERTICAL TABULATION
420 0x000c: 0x000c, # FORM FEED
421 0x000d: 0x000d, # CARRIAGE RETURN
422 0x000e: 0x000e, # SHIFT OUT
423 0x000f: 0x000f, # SHIFT IN
424 0x0010: 0x0010, # DATA LINK ESCAPE
425 0x0011: 0x0011, # DEVICE CONTROL ONE
426 0x0012: 0x0012, # DEVICE CONTROL TWO
427 0x0013: 0x0013, # DEVICE CONTROL THREE
428 0x0014: 0x0014, # DEVICE CONTROL FOUR
429 0x0015: 0x0015, # NEGATIVE ACKNOWLEDGE
430 0x0016: 0x0016, # SYNCHRONOUS IDLE
431 0x0017: 0x0017, # END OF TRANSMISSION BLOCK
432 0x0018: 0x0018, # CANCEL
433 0x0019: 0x0019, # END OF MEDIUM
434 0x001a: 0x001a, # SUBSTITUTE
435 0x001b: 0x001b, # ESCAPE
436 0x001c: 0x001c, # FILE SEPARATOR
437 0x001d: 0x001d, # GROUP SEPARATOR
438 0x001e: 0x001e, # RECORD SEPARATOR
439 0x001f: 0x001f, # UNIT SEPARATOR
440 0x0020: 0x0020, # SPACE
441 0x0021: 0x0021, # EXCLAMATION MARK
442 0x0022: 0x0022, # QUOTATION MARK
443 0x0023: 0x0023, # NUMBER SIGN
444 0x0024: 0x0024, # DOLLAR SIGN
445 0x0025: 0x0025, # PERCENT SIGN
446 0x0026: 0x0026, # AMPERSAND
447 0x0027: 0x0027, # APOSTROPHE
448 0x0028: 0x0028, # LEFT PARENTHESIS
449 0x0029: 0x0029, # RIGHT PARENTHESIS
450 0x002a: 0x002a, # ASTERISK
451 0x002b: 0x002b, # PLUS SIGN
452 0x002c: 0x002c, # COMMA
453 0x002d: 0x002d, # HYPHEN-MINUS
454 0x002e: 0x002e, # FULL STOP
455 0x002f: 0x002f, # SOLIDUS
456 0x0030: 0x0030, # DIGIT ZERO
457 0x0031: 0x0031, # DIGIT ONE
458 0x0032: 0x0032, # DIGIT TWO
459 0x0033: 0x0033, # DIGIT THREE
460 0x0034: 0x0034, # DIGIT FOUR
461 0x0035: 0x0035, # DIGIT FIVE
462 0x0036: 0x0036, # DIGIT SIX
463 0x0037: 0x0037, # DIGIT SEVEN
464 0x0038: 0x0038, # DIGIT EIGHT
465 0x0039: 0x0039, # DIGIT NINE
466 0x003a: 0x003a, # COLON
467 0x003b: 0x003b, # SEMICOLON
468 0x003c: 0x003c, # LESS-THAN SIGN
469 0x003d: 0x003d, # EQUALS SIGN
470 0x003e: 0x003e, # GREATER-THAN SIGN
471 0x003f: 0x003f, # QUESTION MARK
472 0x0040: 0x0040, # COMMERCIAL AT
473 0x0041: 0x0041, # LATIN CAPITAL LETTER A
474 0x0042: 0x0042, # LATIN CAPITAL LETTER B
475 0x0043: 0x0043, # LATIN CAPITAL LETTER C
476 0x0044: 0x0044, # LATIN CAPITAL LETTER D
477 0x0045: 0x0045, # LATIN CAPITAL LETTER E
478 0x0046: 0x0046, # LATIN CAPITAL LETTER F
479 0x0047: 0x0047, # LATIN CAPITAL LETTER G
480 0x0048: 0x0048, # LATIN CAPITAL LETTER H
481 0x0049: 0x0049, # LATIN CAPITAL LETTER I
482 0x004a: 0x004a, # LATIN CAPITAL LETTER J
483 0x004b: 0x004b, # LATIN CAPITAL LETTER K
484 0x004c: 0x004c, # LATIN CAPITAL LETTER L
485 0x004d: 0x004d, # LATIN CAPITAL LETTER M
486 0x004e: 0x004e, # LATIN CAPITAL LETTER N
487 0x004f: 0x004f, # LATIN CAPITAL LETTER O
488 0x0050: 0x0050, # LATIN CAPITAL LETTER P
489 0x0051: 0x0051, # LATIN CAPITAL LETTER Q
490 0x0052: 0x0052, # LATIN CAPITAL LETTER R
491 0x0053: 0x0053, # LATIN CAPITAL LETTER S
492 0x0054: 0x0054, # LATIN CAPITAL LETTER T
493 0x0055: 0x0055, # LATIN CAPITAL LETTER U
494 0x0056: 0x0056, # LATIN CAPITAL LETTER V
495 0x0057: 0x0057, # LATIN CAPITAL LETTER W
496 0x0058: 0x0058, # LATIN CAPITAL LETTER X
497 0x0059: 0x0059, # LATIN CAPITAL LETTER Y
498 0x005a: 0x005a, # LATIN CAPITAL LETTER Z
499 0x005b: 0x005b, # LEFT SQUARE BRACKET
500 0x005c: 0x005c, # REVERSE SOLIDUS
501 0x005d: 0x005d, # RIGHT SQUARE BRACKET
502 0x005e: 0x005e, # CIRCUMFLEX ACCENT
503 0x005f: 0x005f, # LOW LINE
504 0x0060: 0x0060, # GRAVE ACCENT
505 0x0061: 0x0061, # LATIN SMALL LETTER A
506 0x0062: 0x0062, # LATIN SMALL LETTER B
507 0x0063: 0x0063, # LATIN SMALL LETTER C
508 0x0064: 0x0064, # LATIN SMALL LETTER D
509 0x0065: 0x0065, # LATIN SMALL LETTER E
510 0x0066: 0x0066, # LATIN SMALL LETTER F
511 0x0067: 0x0067, # LATIN SMALL LETTER G
512 0x0068: 0x0068, # LATIN SMALL LETTER H
513 0x0069: 0x0069, # LATIN SMALL LETTER I
514 0x006a: 0x006a, # LATIN SMALL LETTER J
515 0x006b: 0x006b, # LATIN SMALL LETTER K
516 0x006c: 0x006c, # LATIN SMALL LETTER L
517 0x006d: 0x006d, # LATIN SMALL LETTER M
518 0x006e: 0x006e, # LATIN SMALL LETTER N
519 0x006f: 0x006f, # LATIN SMALL LETTER O
520 0x0070: 0x0070, # LATIN SMALL LETTER P
521 0x0071: 0x0071, # LATIN SMALL LETTER Q
522 0x0072: 0x0072, # LATIN SMALL LETTER R
523 0x0073: 0x0073, # LATIN SMALL LETTER S
524 0x0074: 0x0074, # LATIN SMALL LETTER T
525 0x0075: 0x0075, # LATIN SMALL LETTER U
526 0x0076: 0x0076, # LATIN SMALL LETTER V
527 0x0077: 0x0077, # LATIN SMALL LETTER W
528 0x0078: 0x0078, # LATIN SMALL LETTER X
529 0x0079: 0x0079, # LATIN SMALL LETTER Y
530 0x007a: 0x007a, # LATIN SMALL LETTER Z
531 0x007b: 0x007b, # LEFT CURLY BRACKET
532 0x007c: 0x007c, # VERTICAL LINE
533 0x007d: 0x007d, # RIGHT CURLY BRACKET
534 0x007e: 0x007e, # TILDE
535 0x007f: 0x007f, # DELETE
536 0x00a0: 0x00a0, # NO-BREAK SPACE
537 0x00a3: 0x00a3, # POUND SIGN
538 0x00a4: 0x00a4, # CURRENCY SIGN
539 0x00a5: 0x00a5, # YEN SIGN
540 0x00a6: 0x00a6, # BROKEN BAR
541 0x00a7: 0x00a7, # SECTION SIGN
542 0x00a8: 0x00a8, # DIAERESIS
543 0x00a9: 0x00a9, # COPYRIGHT SIGN
544 0x00ab: 0x00ab, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
545 0x00ac: 0x00ac, # NOT SIGN
546 0x00ad: 0x00ad, # SOFT HYPHEN
547 0x00ae: 0x00ae, # REGISTERED SIGN
548 0x00b0: 0x00b0, # DEGREE SIGN
549 0x00b1: 0x00b1, # PLUS-MINUS SIGN
550 0x00b2: 0x00b2, # SUPERSCRIPT TWO
551 0x00b3: 0x00b3, # SUPERSCRIPT THREE
552 0x00b5: 0x00b5, # MICRO SIGN
553 0x00b6: 0x00b6, # PILCROW SIGN
554 0x00b7: 0x00b7, # MIDDLE DOT
555 0x00bb: 0x00bb, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
556 0x00bd: 0x00bd, # VULGAR FRACTION ONE HALF
557 0x0192: 0x0083, # LATIN SMALL LETTER F WITH HOOK
558 0x0384: 0x00b4, # GREEK TONOS
559 0x0385: 0x00a1, # GREEK DIALYTIKA TONOS
560 0x0386: 0x00a2, # GREEK CAPITAL LETTER ALPHA WITH TONOS
561 0x0388: 0x00b8, # GREEK CAPITAL LETTER EPSILON WITH TONOS
562 0x0389: 0x00b9, # GREEK CAPITAL LETTER ETA WITH TONOS
563 0x038a: 0x00ba, # GREEK CAPITAL LETTER IOTA WITH TONOS
564 0x038c: 0x00bc, # GREEK CAPITAL LETTER OMICRON WITH TONOS
565 0x038e: 0x00be, # GREEK CAPITAL LETTER UPSILON WITH TONOS
566 0x038f: 0x00bf, # GREEK CAPITAL LETTER OMEGA WITH TONOS
567 0x0390: 0x00c0, # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND TONOS
568 0x0391: 0x00c1, # GREEK CAPITAL LETTER ALPHA
569 0x0392: 0x00c2, # GREEK CAPITAL LETTER BETA
570 0x0393: 0x00c3, # GREEK CAPITAL LETTER GAMMA
571 0x0394: 0x00c4, # GREEK CAPITAL LETTER DELTA
572 0x0395: 0x00c5, # GREEK CAPITAL LETTER EPSILON
573 0x0396: 0x00c6, # GREEK CAPITAL LETTER ZETA
574 0x0397: 0x00c7, # GREEK CAPITAL LETTER ETA
575 0x0398: 0x00c8, # GREEK CAPITAL LETTER THETA
576 0x0399: 0x00c9, # GREEK CAPITAL LETTER IOTA
577 0x039a: 0x00ca, # GREEK CAPITAL LETTER KAPPA
578 0x039b: 0x00cb, # GREEK CAPITAL LETTER LAMDA
579 0x039c: 0x00cc, # GREEK CAPITAL LETTER MU
580 0x039d: 0x00cd, # GREEK CAPITAL LETTER NU
581 0x039e: 0x00ce, # GREEK CAPITAL LETTER XI
582 0x039f: 0x00cf, # GREEK CAPITAL LETTER OMICRON
583 0x03a0: 0x00d0, # GREEK CAPITAL LETTER PI
584 0x03a1: 0x00d1, # GREEK CAPITAL LETTER RHO
585 0x03a3: 0x00d3, # GREEK CAPITAL LETTER SIGMA
586 0x03a4: 0x00d4, # GREEK CAPITAL LETTER TAU
587 0x03a5: 0x00d5, # GREEK CAPITAL LETTER UPSILON
588 0x03a6: 0x00d6, # GREEK CAPITAL LETTER PHI
589 0x03a7: 0x00d7, # GREEK CAPITAL LETTER CHI
590 0x03a8: 0x00d8, # GREEK CAPITAL LETTER PSI
591 0x03a9: 0x00d9, # GREEK CAPITAL LETTER OMEGA
592 0x03aa: 0x00da, # GREEK CAPITAL LETTER IOTA WITH DIALYTIKA
593 0x03ab: 0x00db, # GREEK CAPITAL LETTER UPSILON WITH DIALYTIKA
594 0x03ac: 0x00dc, # GREEK SMALL LETTER ALPHA WITH TONOS
595 0x03ad: 0x00dd, # GREEK SMALL LETTER EPSILON WITH TONOS
596 0x03ae: 0x00de, # GREEK SMALL LETTER ETA WITH TONOS
597 0x03af: 0x00df, # GREEK SMALL LETTER IOTA WITH TONOS
598 0x03b0: 0x00e0, # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND TONOS
599 0x03b1: 0x00e1, # GREEK SMALL LETTER ALPHA
600 0x03b2: 0x00e2, # GREEK SMALL LETTER BETA
601 0x03b3: 0x00e3, # GREEK SMALL LETTER GAMMA
602 0x03b4: 0x00e4, # GREEK SMALL LETTER DELTA
603 0x03b5: 0x00e5, # GREEK SMALL LETTER EPSILON
604 0x03b6: 0x00e6, # GREEK SMALL LETTER ZETA
605 0x03b7: 0x00e7, # GREEK SMALL LETTER ETA
606 0x03b8: 0x00e8, # GREEK SMALL LETTER THETA
607 0x03b9: 0x00e9, # GREEK SMALL LETTER IOTA
608 0x03ba: 0x00ea, # GREEK SMALL LETTER KAPPA
609 0x03bb: 0x00eb, # GREEK SMALL LETTER LAMDA
610 0x03bc: 0x00ec, # GREEK SMALL LETTER MU
611 0x03bd: 0x00ed, # GREEK SMALL LETTER NU
612 0x03be: 0x00ee, # GREEK SMALL LETTER XI
613 0x03bf: 0x00ef, # GREEK SMALL LETTER OMICRON
614 0x03c0: 0x00f0, # GREEK SMALL LETTER PI
615 0x03c1: 0x00f1, # GREEK SMALL LETTER RHO
616 0x03c2: 0x00f2, # GREEK SMALL LETTER FINAL SIGMA
617 0x03c3: 0x00f3, # GREEK SMALL LETTER SIGMA
618 0x03c4: 0x00f4, # GREEK SMALL LETTER TAU
619 0x03c5: 0x00f5, # GREEK SMALL LETTER UPSILON
620 0x03c6: 0x00f6, # GREEK SMALL LETTER PHI
621 0x03c7: 0x00f7, # GREEK SMALL LETTER CHI
622 0x03c8: 0x00f8, # GREEK SMALL LETTER PSI
623 0x03c9: 0x00f9, # GREEK SMALL LETTER OMEGA
624 0x03ca: 0x00fa, # GREEK SMALL LETTER IOTA WITH DIALYTIKA
625 0x03cb: 0x00fb, # GREEK SMALL LETTER UPSILON WITH DIALYTIKA
626 0x03cc: 0x00fc, # GREEK SMALL LETTER OMICRON WITH TONOS
627 0x03cd: 0x00fd, # GREEK SMALL LETTER UPSILON WITH TONOS
628 0x03ce: 0x00fe, # GREEK SMALL LETTER OMEGA WITH TONOS
629 0x2013: 0x0096, # EN DASH
630 0x2014: 0x0097, # EM DASH
631 0x2015: 0x00af, # HORIZONTAL BAR
632 0x2018: 0x0091, # LEFT SINGLE QUOTATION MARK
633 0x2019: 0x0092, # RIGHT SINGLE QUOTATION MARK
634 0x201a: 0x0082, # SINGLE LOW-9 QUOTATION MARK
635 0x201c: 0x0093, # LEFT DOUBLE QUOTATION MARK
636 0x201d: 0x0094, # RIGHT DOUBLE QUOTATION MARK
637 0x201e: 0x0084, # DOUBLE LOW-9 QUOTATION MARK
638 0x2020: 0x0086, # DAGGER
639 0x2021: 0x0087, # DOUBLE DAGGER
640 0x2022: 0x0095, # BULLET
641 0x2026: 0x0085, # HORIZONTAL ELLIPSIS
642 0x2030: 0x0089, # PER MILLE SIGN
643 0x2039: 0x008b, # SINGLE LEFT-POINTING ANGLE QUOTATION MARK
644 0x203a: 0x009b, # SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
645 0x20ac: 0x0080, # EURO SIGN
646 0x2122: 0x0099, # TRADE MARK SIGN
647}