blob: 358cfe96be0492b3d2b12fd478329077f61f8ca6 [file] [log] [blame]
Marc-André Lemburga1129f42005-10-21 13:49:12 +00001""" Python Character Mapping Codec generated from 'VENDORS/MISC/CP856.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: 0x05d0, # HEBREW LETTER ALEF
36 0x0081: 0x05d1, # HEBREW LETTER BET
37 0x0082: 0x05d2, # HEBREW LETTER GIMEL
38 0x0083: 0x05d3, # HEBREW LETTER DALET
39 0x0084: 0x05d4, # HEBREW LETTER HE
40 0x0085: 0x05d5, # HEBREW LETTER VAV
41 0x0086: 0x05d6, # HEBREW LETTER ZAYIN
42 0x0087: 0x05d7, # HEBREW LETTER HET
43 0x0088: 0x05d8, # HEBREW LETTER TET
44 0x0089: 0x05d9, # HEBREW LETTER YOD
45 0x008a: 0x05da, # HEBREW LETTER FINAL KAF
46 0x008b: 0x05db, # HEBREW LETTER KAF
47 0x008c: 0x05dc, # HEBREW LETTER LAMED
48 0x008d: 0x05dd, # HEBREW LETTER FINAL MEM
49 0x008e: 0x05de, # HEBREW LETTER MEM
50 0x008f: 0x05df, # HEBREW LETTER FINAL NUN
51 0x0090: 0x05e0, # HEBREW LETTER NUN
52 0x0091: 0x05e1, # HEBREW LETTER SAMEKH
53 0x0092: 0x05e2, # HEBREW LETTER AYIN
54 0x0093: 0x05e3, # HEBREW LETTER FINAL PE
55 0x0094: 0x05e4, # HEBREW LETTER PE
56 0x0095: 0x05e5, # HEBREW LETTER FINAL TSADI
57 0x0096: 0x05e6, # HEBREW LETTER TSADI
58 0x0097: 0x05e7, # HEBREW LETTER QOF
59 0x0098: 0x05e8, # HEBREW LETTER RESH
60 0x0099: 0x05e9, # HEBREW LETTER SHIN
61 0x009a: 0x05ea, # HEBREW LETTER TAV
62 0x009b: None, # UNDEFINED
63 0x009c: 0x00a3, # POUND SIGN
64 0x009d: None, # UNDEFINED
65 0x009e: 0x00d7, # MULTIPLICATION SIGN
66 0x009f: None, # UNDEFINED
67 0x00a0: None, # UNDEFINED
68 0x00a1: None, # UNDEFINED
69 0x00a2: None, # UNDEFINED
70 0x00a3: None, # UNDEFINED
71 0x00a4: None, # UNDEFINED
72 0x00a5: None, # UNDEFINED
73 0x00a6: None, # UNDEFINED
74 0x00a7: None, # UNDEFINED
75 0x00a8: None, # UNDEFINED
76 0x00a9: 0x00ae, # REGISTERED SIGN
77 0x00aa: 0x00ac, # NOT SIGN
78 0x00ab: 0x00bd, # VULGAR FRACTION ONE HALF
79 0x00ac: 0x00bc, # VULGAR FRACTION ONE QUARTER
80 0x00ad: None, # UNDEFINED
81 0x00ae: 0x00ab, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
82 0x00af: 0x00bb, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
83 0x00b0: 0x2591, # LIGHT SHADE
84 0x00b1: 0x2592, # MEDIUM SHADE
85 0x00b2: 0x2593, # DARK SHADE
86 0x00b3: 0x2502, # BOX DRAWINGS LIGHT VERTICAL
87 0x00b4: 0x2524, # BOX DRAWINGS LIGHT VERTICAL AND LEFT
88 0x00b5: None, # UNDEFINED
89 0x00b6: None, # UNDEFINED
90 0x00b7: None, # UNDEFINED
91 0x00b8: 0x00a9, # COPYRIGHT SIGN
92 0x00b9: 0x2563, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT
93 0x00ba: 0x2551, # BOX DRAWINGS DOUBLE VERTICAL
94 0x00bb: 0x2557, # BOX DRAWINGS DOUBLE DOWN AND LEFT
95 0x00bc: 0x255d, # BOX DRAWINGS DOUBLE UP AND LEFT
96 0x00bd: 0x00a2, # CENT SIGN
97 0x00be: 0x00a5, # YEN SIGN
98 0x00bf: 0x2510, # BOX DRAWINGS LIGHT DOWN AND LEFT
99 0x00c0: 0x2514, # BOX DRAWINGS LIGHT UP AND RIGHT
100 0x00c1: 0x2534, # BOX DRAWINGS LIGHT UP AND HORIZONTAL
101 0x00c2: 0x252c, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
102 0x00c3: 0x251c, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT
103 0x00c4: 0x2500, # BOX DRAWINGS LIGHT HORIZONTAL
104 0x00c5: 0x253c, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
105 0x00c6: None, # UNDEFINED
106 0x00c7: None, # UNDEFINED
107 0x00c8: 0x255a, # BOX DRAWINGS DOUBLE UP AND RIGHT
108 0x00c9: 0x2554, # BOX DRAWINGS DOUBLE DOWN AND RIGHT
109 0x00ca: 0x2569, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL
110 0x00cb: 0x2566, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
111 0x00cc: 0x2560, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
112 0x00cd: 0x2550, # BOX DRAWINGS DOUBLE HORIZONTAL
113 0x00ce: 0x256c, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
114 0x00cf: 0x00a4, # CURRENCY SIGN
115 0x00d0: None, # UNDEFINED
116 0x00d1: None, # UNDEFINED
117 0x00d2: None, # UNDEFINED
118 0x00d3: None, # UNDEFINEDS
119 0x00d4: None, # UNDEFINED
120 0x00d5: None, # UNDEFINED
121 0x00d6: None, # UNDEFINEDE
122 0x00d7: None, # UNDEFINED
123 0x00d8: None, # UNDEFINED
124 0x00d9: 0x2518, # BOX DRAWINGS LIGHT UP AND LEFT
125 0x00da: 0x250c, # BOX DRAWINGS LIGHT DOWN AND RIGHT
126 0x00db: 0x2588, # FULL BLOCK
127 0x00dc: 0x2584, # LOWER HALF BLOCK
128 0x00dd: 0x00a6, # BROKEN BAR
129 0x00de: None, # UNDEFINED
130 0x00df: 0x2580, # UPPER HALF BLOCK
131 0x00e0: None, # UNDEFINED
132 0x00e1: None, # UNDEFINED
133 0x00e2: None, # UNDEFINED
134 0x00e3: None, # UNDEFINED
135 0x00e4: None, # UNDEFINED
136 0x00e5: None, # UNDEFINED
137 0x00e6: 0x00b5, # MICRO SIGN
138 0x00e7: None, # UNDEFINED
139 0x00e8: None, # UNDEFINED
140 0x00e9: None, # UNDEFINED
141 0x00ea: None, # UNDEFINED
142 0x00eb: None, # UNDEFINED
143 0x00ec: None, # UNDEFINED
144 0x00ed: None, # UNDEFINED
145 0x00ee: 0x00af, # MACRON
146 0x00ef: 0x00b4, # ACUTE ACCENT
147 0x00f0: 0x00ad, # SOFT HYPHEN
148 0x00f1: 0x00b1, # PLUS-MINUS SIGN
149 0x00f2: 0x2017, # DOUBLE LOW LINE
150 0x00f3: 0x00be, # VULGAR FRACTION THREE QUARTERS
151 0x00f4: 0x00b6, # PILCROW SIGN
152 0x00f5: 0x00a7, # SECTION SIGN
153 0x00f6: 0x00f7, # DIVISION SIGN
154 0x00f7: 0x00b8, # CEDILLA
155 0x00f8: 0x00b0, # DEGREE SIGN
156 0x00f9: 0x00a8, # DIAERESIS
157 0x00fa: 0x00b7, # MIDDLE DOT
158 0x00fb: 0x00b9, # SUPERSCRIPT ONE
159 0x00fc: 0x00b3, # SUPERSCRIPT THREE
160 0x00fd: 0x00b2, # SUPERSCRIPT TWO
161 0x00fe: 0x25a0, # BLACK SQUARE
162 0x00ff: 0x00a0, # NO-BREAK SPACE
Marc-André Lemburga866df82001-01-03 21:29:14 +0000163})
Guido van Rossum0229bf62000-03-10 23:17:24 +0000164
Marc-André Lemburga1129f42005-10-21 13:49:12 +0000165### Decoding Table
166
167decoding_table = (
168 u'\x00' # 0x0000 -> NULL
169 u'\x01' # 0x0001 -> START OF HEADING
170 u'\x02' # 0x0002 -> START OF TEXT
171 u'\x03' # 0x0003 -> END OF TEXT
172 u'\x04' # 0x0004 -> END OF TRANSMISSION
173 u'\x05' # 0x0005 -> ENQUIRY
174 u'\x06' # 0x0006 -> ACKNOWLEDGE
175 u'\x07' # 0x0007 -> BELL
176 u'\x08' # 0x0008 -> BACKSPACE
177 u'\t' # 0x0009 -> HORIZONTAL TABULATION
178 u'\n' # 0x000a -> LINE FEED
179 u'\x0b' # 0x000b -> VERTICAL TABULATION
180 u'\x0c' # 0x000c -> FORM FEED
181 u'\r' # 0x000d -> CARRIAGE RETURN
182 u'\x0e' # 0x000e -> SHIFT OUT
183 u'\x0f' # 0x000f -> SHIFT IN
184 u'\x10' # 0x0010 -> DATA LINK ESCAPE
185 u'\x11' # 0x0011 -> DEVICE CONTROL ONE
186 u'\x12' # 0x0012 -> DEVICE CONTROL TWO
187 u'\x13' # 0x0013 -> DEVICE CONTROL THREE
188 u'\x14' # 0x0014 -> DEVICE CONTROL FOUR
189 u'\x15' # 0x0015 -> NEGATIVE ACKNOWLEDGE
190 u'\x16' # 0x0016 -> SYNCHRONOUS IDLE
191 u'\x17' # 0x0017 -> END OF TRANSMISSION BLOCK
192 u'\x18' # 0x0018 -> CANCEL
193 u'\x19' # 0x0019 -> END OF MEDIUM
194 u'\x1a' # 0x001a -> SUBSTITUTE
195 u'\x1b' # 0x001b -> ESCAPE
196 u'\x1c' # 0x001c -> FILE SEPARATOR
197 u'\x1d' # 0x001d -> GROUP SEPARATOR
198 u'\x1e' # 0x001e -> RECORD SEPARATOR
199 u'\x1f' # 0x001f -> UNIT SEPARATOR
200 u' ' # 0x0020 -> SPACE
201 u'!' # 0x0021 -> EXCLAMATION MARK
202 u'"' # 0x0022 -> QUOTATION MARK
203 u'#' # 0x0023 -> NUMBER SIGN
204 u'$' # 0x0024 -> DOLLAR SIGN
205 u'%' # 0x0025 -> PERCENT SIGN
206 u'&' # 0x0026 -> AMPERSAND
207 u"'" # 0x0027 -> APOSTROPHE
208 u'(' # 0x0028 -> LEFT PARENTHESIS
209 u')' # 0x0029 -> RIGHT PARENTHESIS
210 u'*' # 0x002a -> ASTERISK
211 u'+' # 0x002b -> PLUS SIGN
212 u',' # 0x002c -> COMMA
213 u'-' # 0x002d -> HYPHEN-MINUS
214 u'.' # 0x002e -> FULL STOP
215 u'/' # 0x002f -> SOLIDUS
216 u'0' # 0x0030 -> DIGIT ZERO
217 u'1' # 0x0031 -> DIGIT ONE
218 u'2' # 0x0032 -> DIGIT TWO
219 u'3' # 0x0033 -> DIGIT THREE
220 u'4' # 0x0034 -> DIGIT FOUR
221 u'5' # 0x0035 -> DIGIT FIVE
222 u'6' # 0x0036 -> DIGIT SIX
223 u'7' # 0x0037 -> DIGIT SEVEN
224 u'8' # 0x0038 -> DIGIT EIGHT
225 u'9' # 0x0039 -> DIGIT NINE
226 u':' # 0x003a -> COLON
227 u';' # 0x003b -> SEMICOLON
228 u'<' # 0x003c -> LESS-THAN SIGN
229 u'=' # 0x003d -> EQUALS SIGN
230 u'>' # 0x003e -> GREATER-THAN SIGN
231 u'?' # 0x003f -> QUESTION MARK
232 u'@' # 0x0040 -> COMMERCIAL AT
233 u'A' # 0x0041 -> LATIN CAPITAL LETTER A
234 u'B' # 0x0042 -> LATIN CAPITAL LETTER B
235 u'C' # 0x0043 -> LATIN CAPITAL LETTER C
236 u'D' # 0x0044 -> LATIN CAPITAL LETTER D
237 u'E' # 0x0045 -> LATIN CAPITAL LETTER E
238 u'F' # 0x0046 -> LATIN CAPITAL LETTER F
239 u'G' # 0x0047 -> LATIN CAPITAL LETTER G
240 u'H' # 0x0048 -> LATIN CAPITAL LETTER H
241 u'I' # 0x0049 -> LATIN CAPITAL LETTER I
242 u'J' # 0x004a -> LATIN CAPITAL LETTER J
243 u'K' # 0x004b -> LATIN CAPITAL LETTER K
244 u'L' # 0x004c -> LATIN CAPITAL LETTER L
245 u'M' # 0x004d -> LATIN CAPITAL LETTER M
246 u'N' # 0x004e -> LATIN CAPITAL LETTER N
247 u'O' # 0x004f -> LATIN CAPITAL LETTER O
248 u'P' # 0x0050 -> LATIN CAPITAL LETTER P
249 u'Q' # 0x0051 -> LATIN CAPITAL LETTER Q
250 u'R' # 0x0052 -> LATIN CAPITAL LETTER R
251 u'S' # 0x0053 -> LATIN CAPITAL LETTER S
252 u'T' # 0x0054 -> LATIN CAPITAL LETTER T
253 u'U' # 0x0055 -> LATIN CAPITAL LETTER U
254 u'V' # 0x0056 -> LATIN CAPITAL LETTER V
255 u'W' # 0x0057 -> LATIN CAPITAL LETTER W
256 u'X' # 0x0058 -> LATIN CAPITAL LETTER X
257 u'Y' # 0x0059 -> LATIN CAPITAL LETTER Y
258 u'Z' # 0x005a -> LATIN CAPITAL LETTER Z
259 u'[' # 0x005b -> LEFT SQUARE BRACKET
260 u'\\' # 0x005c -> REVERSE SOLIDUS
261 u']' # 0x005d -> RIGHT SQUARE BRACKET
262 u'^' # 0x005e -> CIRCUMFLEX ACCENT
263 u'_' # 0x005f -> LOW LINE
264 u'`' # 0x0060 -> GRAVE ACCENT
265 u'a' # 0x0061 -> LATIN SMALL LETTER A
266 u'b' # 0x0062 -> LATIN SMALL LETTER B
267 u'c' # 0x0063 -> LATIN SMALL LETTER C
268 u'd' # 0x0064 -> LATIN SMALL LETTER D
269 u'e' # 0x0065 -> LATIN SMALL LETTER E
270 u'f' # 0x0066 -> LATIN SMALL LETTER F
271 u'g' # 0x0067 -> LATIN SMALL LETTER G
272 u'h' # 0x0068 -> LATIN SMALL LETTER H
273 u'i' # 0x0069 -> LATIN SMALL LETTER I
274 u'j' # 0x006a -> LATIN SMALL LETTER J
275 u'k' # 0x006b -> LATIN SMALL LETTER K
276 u'l' # 0x006c -> LATIN SMALL LETTER L
277 u'm' # 0x006d -> LATIN SMALL LETTER M
278 u'n' # 0x006e -> LATIN SMALL LETTER N
279 u'o' # 0x006f -> LATIN SMALL LETTER O
280 u'p' # 0x0070 -> LATIN SMALL LETTER P
281 u'q' # 0x0071 -> LATIN SMALL LETTER Q
282 u'r' # 0x0072 -> LATIN SMALL LETTER R
283 u's' # 0x0073 -> LATIN SMALL LETTER S
284 u't' # 0x0074 -> LATIN SMALL LETTER T
285 u'u' # 0x0075 -> LATIN SMALL LETTER U
286 u'v' # 0x0076 -> LATIN SMALL LETTER V
287 u'w' # 0x0077 -> LATIN SMALL LETTER W
288 u'x' # 0x0078 -> LATIN SMALL LETTER X
289 u'y' # 0x0079 -> LATIN SMALL LETTER Y
290 u'z' # 0x007a -> LATIN SMALL LETTER Z
291 u'{' # 0x007b -> LEFT CURLY BRACKET
292 u'|' # 0x007c -> VERTICAL LINE
293 u'}' # 0x007d -> RIGHT CURLY BRACKET
294 u'~' # 0x007e -> TILDE
295 u'\x7f' # 0x007f -> DELETE
296 u'\u05d0' # 0x0080 -> HEBREW LETTER ALEF
297 u'\u05d1' # 0x0081 -> HEBREW LETTER BET
298 u'\u05d2' # 0x0082 -> HEBREW LETTER GIMEL
299 u'\u05d3' # 0x0083 -> HEBREW LETTER DALET
300 u'\u05d4' # 0x0084 -> HEBREW LETTER HE
301 u'\u05d5' # 0x0085 -> HEBREW LETTER VAV
302 u'\u05d6' # 0x0086 -> HEBREW LETTER ZAYIN
303 u'\u05d7' # 0x0087 -> HEBREW LETTER HET
304 u'\u05d8' # 0x0088 -> HEBREW LETTER TET
305 u'\u05d9' # 0x0089 -> HEBREW LETTER YOD
306 u'\u05da' # 0x008a -> HEBREW LETTER FINAL KAF
307 u'\u05db' # 0x008b -> HEBREW LETTER KAF
308 u'\u05dc' # 0x008c -> HEBREW LETTER LAMED
309 u'\u05dd' # 0x008d -> HEBREW LETTER FINAL MEM
310 u'\u05de' # 0x008e -> HEBREW LETTER MEM
311 u'\u05df' # 0x008f -> HEBREW LETTER FINAL NUN
312 u'\u05e0' # 0x0090 -> HEBREW LETTER NUN
313 u'\u05e1' # 0x0091 -> HEBREW LETTER SAMEKH
314 u'\u05e2' # 0x0092 -> HEBREW LETTER AYIN
315 u'\u05e3' # 0x0093 -> HEBREW LETTER FINAL PE
316 u'\u05e4' # 0x0094 -> HEBREW LETTER PE
317 u'\u05e5' # 0x0095 -> HEBREW LETTER FINAL TSADI
318 u'\u05e6' # 0x0096 -> HEBREW LETTER TSADI
319 u'\u05e7' # 0x0097 -> HEBREW LETTER QOF
320 u'\u05e8' # 0x0098 -> HEBREW LETTER RESH
321 u'\u05e9' # 0x0099 -> HEBREW LETTER SHIN
322 u'\u05ea' # 0x009a -> HEBREW LETTER TAV
323 u'\ufffe' # 0x009b -> UNDEFINED
324 u'\xa3' # 0x009c -> POUND SIGN
325 u'\ufffe' # 0x009d -> UNDEFINED
326 u'\xd7' # 0x009e -> MULTIPLICATION SIGN
327 u'\ufffe' # 0x009f -> UNDEFINED
328 u'\ufffe' # 0x00a0 -> UNDEFINED
329 u'\ufffe' # 0x00a1 -> UNDEFINED
330 u'\ufffe' # 0x00a2 -> UNDEFINED
331 u'\ufffe' # 0x00a3 -> UNDEFINED
332 u'\ufffe' # 0x00a4 -> UNDEFINED
333 u'\ufffe' # 0x00a5 -> UNDEFINED
334 u'\ufffe' # 0x00a6 -> UNDEFINED
335 u'\ufffe' # 0x00a7 -> UNDEFINED
336 u'\ufffe' # 0x00a8 -> UNDEFINED
337 u'\xae' # 0x00a9 -> REGISTERED SIGN
338 u'\xac' # 0x00aa -> NOT SIGN
339 u'\xbd' # 0x00ab -> VULGAR FRACTION ONE HALF
340 u'\xbc' # 0x00ac -> VULGAR FRACTION ONE QUARTER
341 u'\ufffe' # 0x00ad -> UNDEFINED
342 u'\xab' # 0x00ae -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
343 u'\xbb' # 0x00af -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
344 u'\u2591' # 0x00b0 -> LIGHT SHADE
345 u'\u2592' # 0x00b1 -> MEDIUM SHADE
346 u'\u2593' # 0x00b2 -> DARK SHADE
347 u'\u2502' # 0x00b3 -> BOX DRAWINGS LIGHT VERTICAL
348 u'\u2524' # 0x00b4 -> BOX DRAWINGS LIGHT VERTICAL AND LEFT
349 u'\ufffe' # 0x00b5 -> UNDEFINED
350 u'\ufffe' # 0x00b6 -> UNDEFINED
351 u'\ufffe' # 0x00b7 -> UNDEFINED
352 u'\xa9' # 0x00b8 -> COPYRIGHT SIGN
353 u'\u2563' # 0x00b9 -> BOX DRAWINGS DOUBLE VERTICAL AND LEFT
354 u'\u2551' # 0x00ba -> BOX DRAWINGS DOUBLE VERTICAL
355 u'\u2557' # 0x00bb -> BOX DRAWINGS DOUBLE DOWN AND LEFT
356 u'\u255d' # 0x00bc -> BOX DRAWINGS DOUBLE UP AND LEFT
357 u'\xa2' # 0x00bd -> CENT SIGN
358 u'\xa5' # 0x00be -> YEN SIGN
359 u'\u2510' # 0x00bf -> BOX DRAWINGS LIGHT DOWN AND LEFT
360 u'\u2514' # 0x00c0 -> BOX DRAWINGS LIGHT UP AND RIGHT
361 u'\u2534' # 0x00c1 -> BOX DRAWINGS LIGHT UP AND HORIZONTAL
362 u'\u252c' # 0x00c2 -> BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
363 u'\u251c' # 0x00c3 -> BOX DRAWINGS LIGHT VERTICAL AND RIGHT
364 u'\u2500' # 0x00c4 -> BOX DRAWINGS LIGHT HORIZONTAL
365 u'\u253c' # 0x00c5 -> BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
366 u'\ufffe' # 0x00c6 -> UNDEFINED
367 u'\ufffe' # 0x00c7 -> UNDEFINED
368 u'\u255a' # 0x00c8 -> BOX DRAWINGS DOUBLE UP AND RIGHT
369 u'\u2554' # 0x00c9 -> BOX DRAWINGS DOUBLE DOWN AND RIGHT
370 u'\u2569' # 0x00ca -> BOX DRAWINGS DOUBLE UP AND HORIZONTAL
371 u'\u2566' # 0x00cb -> BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
372 u'\u2560' # 0x00cc -> BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
373 u'\u2550' # 0x00cd -> BOX DRAWINGS DOUBLE HORIZONTAL
374 u'\u256c' # 0x00ce -> BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
375 u'\xa4' # 0x00cf -> CURRENCY SIGN
376 u'\ufffe' # 0x00d0 -> UNDEFINED
377 u'\ufffe' # 0x00d1 -> UNDEFINED
378 u'\ufffe' # 0x00d2 -> UNDEFINED
379 u'\ufffe' # 0x00d3 -> UNDEFINEDS
380 u'\ufffe' # 0x00d4 -> UNDEFINED
381 u'\ufffe' # 0x00d5 -> UNDEFINED
382 u'\ufffe' # 0x00d6 -> UNDEFINEDE
383 u'\ufffe' # 0x00d7 -> UNDEFINED
384 u'\ufffe' # 0x00d8 -> UNDEFINED
385 u'\u2518' # 0x00d9 -> BOX DRAWINGS LIGHT UP AND LEFT
386 u'\u250c' # 0x00da -> BOX DRAWINGS LIGHT DOWN AND RIGHT
387 u'\u2588' # 0x00db -> FULL BLOCK
388 u'\u2584' # 0x00dc -> LOWER HALF BLOCK
389 u'\xa6' # 0x00dd -> BROKEN BAR
390 u'\ufffe' # 0x00de -> UNDEFINED
391 u'\u2580' # 0x00df -> UPPER HALF BLOCK
392 u'\ufffe' # 0x00e0 -> UNDEFINED
393 u'\ufffe' # 0x00e1 -> UNDEFINED
394 u'\ufffe' # 0x00e2 -> UNDEFINED
395 u'\ufffe' # 0x00e3 -> UNDEFINED
396 u'\ufffe' # 0x00e4 -> UNDEFINED
397 u'\ufffe' # 0x00e5 -> UNDEFINED
398 u'\xb5' # 0x00e6 -> MICRO SIGN
399 u'\ufffe' # 0x00e7 -> UNDEFINED
400 u'\ufffe' # 0x00e8 -> UNDEFINED
401 u'\ufffe' # 0x00e9 -> UNDEFINED
402 u'\ufffe' # 0x00ea -> UNDEFINED
403 u'\ufffe' # 0x00eb -> UNDEFINED
404 u'\ufffe' # 0x00ec -> UNDEFINED
405 u'\ufffe' # 0x00ed -> UNDEFINED
406 u'\xaf' # 0x00ee -> MACRON
407 u'\xb4' # 0x00ef -> ACUTE ACCENT
408 u'\xad' # 0x00f0 -> SOFT HYPHEN
409 u'\xb1' # 0x00f1 -> PLUS-MINUS SIGN
410 u'\u2017' # 0x00f2 -> DOUBLE LOW LINE
411 u'\xbe' # 0x00f3 -> VULGAR FRACTION THREE QUARTERS
412 u'\xb6' # 0x00f4 -> PILCROW SIGN
413 u'\xa7' # 0x00f5 -> SECTION SIGN
414 u'\xf7' # 0x00f6 -> DIVISION SIGN
415 u'\xb8' # 0x00f7 -> CEDILLA
416 u'\xb0' # 0x00f8 -> DEGREE SIGN
417 u'\xa8' # 0x00f9 -> DIAERESIS
418 u'\xb7' # 0x00fa -> MIDDLE DOT
419 u'\xb9' # 0x00fb -> SUPERSCRIPT ONE
420 u'\xb3' # 0x00fc -> SUPERSCRIPT THREE
421 u'\xb2' # 0x00fd -> SUPERSCRIPT TWO
422 u'\u25a0' # 0x00fe -> BLACK SQUARE
423 u'\xa0' # 0x00ff -> NO-BREAK SPACE
424)
425
Guido van Rossum0229bf62000-03-10 23:17:24 +0000426### Encoding Map
427
Marc-André Lemburga1129f42005-10-21 13:49:12 +0000428encoding_map = {
429 0x0000: 0x0000, # NULL
430 0x0001: 0x0001, # START OF HEADING
431 0x0002: 0x0002, # START OF TEXT
432 0x0003: 0x0003, # END OF TEXT
433 0x0004: 0x0004, # END OF TRANSMISSION
434 0x0005: 0x0005, # ENQUIRY
435 0x0006: 0x0006, # ACKNOWLEDGE
436 0x0007: 0x0007, # BELL
437 0x0008: 0x0008, # BACKSPACE
438 0x0009: 0x0009, # HORIZONTAL TABULATION
439 0x000a: 0x000a, # LINE FEED
440 0x000b: 0x000b, # VERTICAL TABULATION
441 0x000c: 0x000c, # FORM FEED
442 0x000d: 0x000d, # CARRIAGE RETURN
443 0x000e: 0x000e, # SHIFT OUT
444 0x000f: 0x000f, # SHIFT IN
445 0x0010: 0x0010, # DATA LINK ESCAPE
446 0x0011: 0x0011, # DEVICE CONTROL ONE
447 0x0012: 0x0012, # DEVICE CONTROL TWO
448 0x0013: 0x0013, # DEVICE CONTROL THREE
449 0x0014: 0x0014, # DEVICE CONTROL FOUR
450 0x0015: 0x0015, # NEGATIVE ACKNOWLEDGE
451 0x0016: 0x0016, # SYNCHRONOUS IDLE
452 0x0017: 0x0017, # END OF TRANSMISSION BLOCK
453 0x0018: 0x0018, # CANCEL
454 0x0019: 0x0019, # END OF MEDIUM
455 0x001a: 0x001a, # SUBSTITUTE
456 0x001b: 0x001b, # ESCAPE
457 0x001c: 0x001c, # FILE SEPARATOR
458 0x001d: 0x001d, # GROUP SEPARATOR
459 0x001e: 0x001e, # RECORD SEPARATOR
460 0x001f: 0x001f, # UNIT SEPARATOR
461 0x0020: 0x0020, # SPACE
462 0x0021: 0x0021, # EXCLAMATION MARK
463 0x0022: 0x0022, # QUOTATION MARK
464 0x0023: 0x0023, # NUMBER SIGN
465 0x0024: 0x0024, # DOLLAR SIGN
466 0x0025: 0x0025, # PERCENT SIGN
467 0x0026: 0x0026, # AMPERSAND
468 0x0027: 0x0027, # APOSTROPHE
469 0x0028: 0x0028, # LEFT PARENTHESIS
470 0x0029: 0x0029, # RIGHT PARENTHESIS
471 0x002a: 0x002a, # ASTERISK
472 0x002b: 0x002b, # PLUS SIGN
473 0x002c: 0x002c, # COMMA
474 0x002d: 0x002d, # HYPHEN-MINUS
475 0x002e: 0x002e, # FULL STOP
476 0x002f: 0x002f, # SOLIDUS
477 0x0030: 0x0030, # DIGIT ZERO
478 0x0031: 0x0031, # DIGIT ONE
479 0x0032: 0x0032, # DIGIT TWO
480 0x0033: 0x0033, # DIGIT THREE
481 0x0034: 0x0034, # DIGIT FOUR
482 0x0035: 0x0035, # DIGIT FIVE
483 0x0036: 0x0036, # DIGIT SIX
484 0x0037: 0x0037, # DIGIT SEVEN
485 0x0038: 0x0038, # DIGIT EIGHT
486 0x0039: 0x0039, # DIGIT NINE
487 0x003a: 0x003a, # COLON
488 0x003b: 0x003b, # SEMICOLON
489 0x003c: 0x003c, # LESS-THAN SIGN
490 0x003d: 0x003d, # EQUALS SIGN
491 0x003e: 0x003e, # GREATER-THAN SIGN
492 0x003f: 0x003f, # QUESTION MARK
493 0x0040: 0x0040, # COMMERCIAL AT
494 0x0041: 0x0041, # LATIN CAPITAL LETTER A
495 0x0042: 0x0042, # LATIN CAPITAL LETTER B
496 0x0043: 0x0043, # LATIN CAPITAL LETTER C
497 0x0044: 0x0044, # LATIN CAPITAL LETTER D
498 0x0045: 0x0045, # LATIN CAPITAL LETTER E
499 0x0046: 0x0046, # LATIN CAPITAL LETTER F
500 0x0047: 0x0047, # LATIN CAPITAL LETTER G
501 0x0048: 0x0048, # LATIN CAPITAL LETTER H
502 0x0049: 0x0049, # LATIN CAPITAL LETTER I
503 0x004a: 0x004a, # LATIN CAPITAL LETTER J
504 0x004b: 0x004b, # LATIN CAPITAL LETTER K
505 0x004c: 0x004c, # LATIN CAPITAL LETTER L
506 0x004d: 0x004d, # LATIN CAPITAL LETTER M
507 0x004e: 0x004e, # LATIN CAPITAL LETTER N
508 0x004f: 0x004f, # LATIN CAPITAL LETTER O
509 0x0050: 0x0050, # LATIN CAPITAL LETTER P
510 0x0051: 0x0051, # LATIN CAPITAL LETTER Q
511 0x0052: 0x0052, # LATIN CAPITAL LETTER R
512 0x0053: 0x0053, # LATIN CAPITAL LETTER S
513 0x0054: 0x0054, # LATIN CAPITAL LETTER T
514 0x0055: 0x0055, # LATIN CAPITAL LETTER U
515 0x0056: 0x0056, # LATIN CAPITAL LETTER V
516 0x0057: 0x0057, # LATIN CAPITAL LETTER W
517 0x0058: 0x0058, # LATIN CAPITAL LETTER X
518 0x0059: 0x0059, # LATIN CAPITAL LETTER Y
519 0x005a: 0x005a, # LATIN CAPITAL LETTER Z
520 0x005b: 0x005b, # LEFT SQUARE BRACKET
521 0x005c: 0x005c, # REVERSE SOLIDUS
522 0x005d: 0x005d, # RIGHT SQUARE BRACKET
523 0x005e: 0x005e, # CIRCUMFLEX ACCENT
524 0x005f: 0x005f, # LOW LINE
525 0x0060: 0x0060, # GRAVE ACCENT
526 0x0061: 0x0061, # LATIN SMALL LETTER A
527 0x0062: 0x0062, # LATIN SMALL LETTER B
528 0x0063: 0x0063, # LATIN SMALL LETTER C
529 0x0064: 0x0064, # LATIN SMALL LETTER D
530 0x0065: 0x0065, # LATIN SMALL LETTER E
531 0x0066: 0x0066, # LATIN SMALL LETTER F
532 0x0067: 0x0067, # LATIN SMALL LETTER G
533 0x0068: 0x0068, # LATIN SMALL LETTER H
534 0x0069: 0x0069, # LATIN SMALL LETTER I
535 0x006a: 0x006a, # LATIN SMALL LETTER J
536 0x006b: 0x006b, # LATIN SMALL LETTER K
537 0x006c: 0x006c, # LATIN SMALL LETTER L
538 0x006d: 0x006d, # LATIN SMALL LETTER M
539 0x006e: 0x006e, # LATIN SMALL LETTER N
540 0x006f: 0x006f, # LATIN SMALL LETTER O
541 0x0070: 0x0070, # LATIN SMALL LETTER P
542 0x0071: 0x0071, # LATIN SMALL LETTER Q
543 0x0072: 0x0072, # LATIN SMALL LETTER R
544 0x0073: 0x0073, # LATIN SMALL LETTER S
545 0x0074: 0x0074, # LATIN SMALL LETTER T
546 0x0075: 0x0075, # LATIN SMALL LETTER U
547 0x0076: 0x0076, # LATIN SMALL LETTER V
548 0x0077: 0x0077, # LATIN SMALL LETTER W
549 0x0078: 0x0078, # LATIN SMALL LETTER X
550 0x0079: 0x0079, # LATIN SMALL LETTER Y
551 0x007a: 0x007a, # LATIN SMALL LETTER Z
552 0x007b: 0x007b, # LEFT CURLY BRACKET
553 0x007c: 0x007c, # VERTICAL LINE
554 0x007d: 0x007d, # RIGHT CURLY BRACKET
555 0x007e: 0x007e, # TILDE
556 0x007f: 0x007f, # DELETE
557 0x00a0: 0x00ff, # NO-BREAK SPACE
558 0x00a2: 0x00bd, # CENT SIGN
559 0x00a3: 0x009c, # POUND SIGN
560 0x00a4: 0x00cf, # CURRENCY SIGN
561 0x00a5: 0x00be, # YEN SIGN
562 0x00a6: 0x00dd, # BROKEN BAR
563 0x00a7: 0x00f5, # SECTION SIGN
564 0x00a8: 0x00f9, # DIAERESIS
565 0x00a9: 0x00b8, # COPYRIGHT SIGN
566 0x00ab: 0x00ae, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
567 0x00ac: 0x00aa, # NOT SIGN
568 0x00ad: 0x00f0, # SOFT HYPHEN
569 0x00ae: 0x00a9, # REGISTERED SIGN
570 0x00af: 0x00ee, # MACRON
571 0x00b0: 0x00f8, # DEGREE SIGN
572 0x00b1: 0x00f1, # PLUS-MINUS SIGN
573 0x00b2: 0x00fd, # SUPERSCRIPT TWO
574 0x00b3: 0x00fc, # SUPERSCRIPT THREE
575 0x00b4: 0x00ef, # ACUTE ACCENT
576 0x00b5: 0x00e6, # MICRO SIGN
577 0x00b6: 0x00f4, # PILCROW SIGN
578 0x00b7: 0x00fa, # MIDDLE DOT
579 0x00b8: 0x00f7, # CEDILLA
580 0x00b9: 0x00fb, # SUPERSCRIPT ONE
581 0x00bb: 0x00af, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
582 0x00bc: 0x00ac, # VULGAR FRACTION ONE QUARTER
583 0x00bd: 0x00ab, # VULGAR FRACTION ONE HALF
584 0x00be: 0x00f3, # VULGAR FRACTION THREE QUARTERS
585 0x00d7: 0x009e, # MULTIPLICATION SIGN
586 0x00f7: 0x00f6, # DIVISION SIGN
587 0x05d0: 0x0080, # HEBREW LETTER ALEF
588 0x05d1: 0x0081, # HEBREW LETTER BET
589 0x05d2: 0x0082, # HEBREW LETTER GIMEL
590 0x05d3: 0x0083, # HEBREW LETTER DALET
591 0x05d4: 0x0084, # HEBREW LETTER HE
592 0x05d5: 0x0085, # HEBREW LETTER VAV
593 0x05d6: 0x0086, # HEBREW LETTER ZAYIN
594 0x05d7: 0x0087, # HEBREW LETTER HET
595 0x05d8: 0x0088, # HEBREW LETTER TET
596 0x05d9: 0x0089, # HEBREW LETTER YOD
597 0x05da: 0x008a, # HEBREW LETTER FINAL KAF
598 0x05db: 0x008b, # HEBREW LETTER KAF
599 0x05dc: 0x008c, # HEBREW LETTER LAMED
600 0x05dd: 0x008d, # HEBREW LETTER FINAL MEM
601 0x05de: 0x008e, # HEBREW LETTER MEM
602 0x05df: 0x008f, # HEBREW LETTER FINAL NUN
603 0x05e0: 0x0090, # HEBREW LETTER NUN
604 0x05e1: 0x0091, # HEBREW LETTER SAMEKH
605 0x05e2: 0x0092, # HEBREW LETTER AYIN
606 0x05e3: 0x0093, # HEBREW LETTER FINAL PE
607 0x05e4: 0x0094, # HEBREW LETTER PE
608 0x05e5: 0x0095, # HEBREW LETTER FINAL TSADI
609 0x05e6: 0x0096, # HEBREW LETTER TSADI
610 0x05e7: 0x0097, # HEBREW LETTER QOF
611 0x05e8: 0x0098, # HEBREW LETTER RESH
612 0x05e9: 0x0099, # HEBREW LETTER SHIN
613 0x05ea: 0x009a, # HEBREW LETTER TAV
614 0x2017: 0x00f2, # DOUBLE LOW LINE
615 0x2500: 0x00c4, # BOX DRAWINGS LIGHT HORIZONTAL
616 0x2502: 0x00b3, # BOX DRAWINGS LIGHT VERTICAL
617 0x250c: 0x00da, # BOX DRAWINGS LIGHT DOWN AND RIGHT
618 0x2510: 0x00bf, # BOX DRAWINGS LIGHT DOWN AND LEFT
619 0x2514: 0x00c0, # BOX DRAWINGS LIGHT UP AND RIGHT
620 0x2518: 0x00d9, # BOX DRAWINGS LIGHT UP AND LEFT
621 0x251c: 0x00c3, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT
622 0x2524: 0x00b4, # BOX DRAWINGS LIGHT VERTICAL AND LEFT
623 0x252c: 0x00c2, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
624 0x2534: 0x00c1, # BOX DRAWINGS LIGHT UP AND HORIZONTAL
625 0x253c: 0x00c5, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
626 0x2550: 0x00cd, # BOX DRAWINGS DOUBLE HORIZONTAL
627 0x2551: 0x00ba, # BOX DRAWINGS DOUBLE VERTICAL
628 0x2554: 0x00c9, # BOX DRAWINGS DOUBLE DOWN AND RIGHT
629 0x2557: 0x00bb, # BOX DRAWINGS DOUBLE DOWN AND LEFT
630 0x255a: 0x00c8, # BOX DRAWINGS DOUBLE UP AND RIGHT
631 0x255d: 0x00bc, # BOX DRAWINGS DOUBLE UP AND LEFT
632 0x2560: 0x00cc, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
633 0x2563: 0x00b9, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT
634 0x2566: 0x00cb, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
635 0x2569: 0x00ca, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL
636 0x256c: 0x00ce, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
637 0x2580: 0x00df, # UPPER HALF BLOCK
638 0x2584: 0x00dc, # LOWER HALF BLOCK
639 0x2588: 0x00db, # FULL BLOCK
640 0x2591: 0x00b0, # LIGHT SHADE
641 0x2592: 0x00b1, # MEDIUM SHADE
642 0x2593: 0x00b2, # DARK SHADE
643 0x25a0: 0x00fe, # BLACK SQUARE
644}