blob: f262030d7517929428f0b3937643625b47a072c8 [file] [log] [blame]
Marc-André Lemburg0f00ba82005-10-21 14:35:35 +00001""" Python Character Mapping Codec generated from 'VENDORS/MICSFT/EBCDIC/CP875.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 Lemburg0f00ba82005-10-21 14:35:35 +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 Lemburg0f00ba82005-10-21 14:35:35 +000035 0x0004: 0x009c, # CONTROL
36 0x0005: 0x0009, # HORIZONTAL TABULATION
37 0x0006: 0x0086, # CONTROL
38 0x0007: 0x007f, # DELETE
39 0x0008: 0x0097, # CONTROL
40 0x0009: 0x008d, # CONTROL
41 0x000a: 0x008e, # CONTROL
42 0x0014: 0x009d, # CONTROL
43 0x0015: 0x0085, # CONTROL
44 0x0016: 0x0008, # BACKSPACE
45 0x0017: 0x0087, # CONTROL
46 0x001a: 0x0092, # CONTROL
47 0x001b: 0x008f, # CONTROL
48 0x0020: 0x0080, # CONTROL
49 0x0021: 0x0081, # CONTROL
50 0x0022: 0x0082, # CONTROL
51 0x0023: 0x0083, # CONTROL
52 0x0024: 0x0084, # CONTROL
53 0x0025: 0x000a, # LINE FEED
54 0x0026: 0x0017, # END OF TRANSMISSION BLOCK
55 0x0027: 0x001b, # ESCAPE
56 0x0028: 0x0088, # CONTROL
57 0x0029: 0x0089, # CONTROL
58 0x002a: 0x008a, # CONTROL
59 0x002b: 0x008b, # CONTROL
60 0x002c: 0x008c, # CONTROL
61 0x002d: 0x0005, # ENQUIRY
62 0x002e: 0x0006, # ACKNOWLEDGE
63 0x002f: 0x0007, # BELL
64 0x0030: 0x0090, # CONTROL
65 0x0031: 0x0091, # CONTROL
66 0x0032: 0x0016, # SYNCHRONOUS IDLE
67 0x0033: 0x0093, # CONTROL
68 0x0034: 0x0094, # CONTROL
69 0x0035: 0x0095, # CONTROL
70 0x0036: 0x0096, # CONTROL
71 0x0037: 0x0004, # END OF TRANSMISSION
72 0x0038: 0x0098, # CONTROL
73 0x0039: 0x0099, # CONTROL
74 0x003a: 0x009a, # CONTROL
75 0x003b: 0x009b, # CONTROL
76 0x003c: 0x0014, # DEVICE CONTROL FOUR
77 0x003d: 0x0015, # NEGATIVE ACKNOWLEDGE
78 0x003e: 0x009e, # CONTROL
79 0x003f: 0x001a, # SUBSTITUTE
80 0x0040: 0x0020, # SPACE
81 0x0041: 0x0391, # GREEK CAPITAL LETTER ALPHA
82 0x0042: 0x0392, # GREEK CAPITAL LETTER BETA
83 0x0043: 0x0393, # GREEK CAPITAL LETTER GAMMA
84 0x0044: 0x0394, # GREEK CAPITAL LETTER DELTA
85 0x0045: 0x0395, # GREEK CAPITAL LETTER EPSILON
86 0x0046: 0x0396, # GREEK CAPITAL LETTER ZETA
87 0x0047: 0x0397, # GREEK CAPITAL LETTER ETA
88 0x0048: 0x0398, # GREEK CAPITAL LETTER THETA
89 0x0049: 0x0399, # GREEK CAPITAL LETTER IOTA
90 0x004a: 0x005b, # LEFT SQUARE BRACKET
91 0x004b: 0x002e, # FULL STOP
92 0x004c: 0x003c, # LESS-THAN SIGN
93 0x004d: 0x0028, # LEFT PARENTHESIS
94 0x004e: 0x002b, # PLUS SIGN
95 0x004f: 0x0021, # EXCLAMATION MARK
96 0x0050: 0x0026, # AMPERSAND
97 0x0051: 0x039a, # GREEK CAPITAL LETTER KAPPA
98 0x0052: 0x039b, # GREEK CAPITAL LETTER LAMDA
99 0x0053: 0x039c, # GREEK CAPITAL LETTER MU
100 0x0054: 0x039d, # GREEK CAPITAL LETTER NU
101 0x0055: 0x039e, # GREEK CAPITAL LETTER XI
102 0x0056: 0x039f, # GREEK CAPITAL LETTER OMICRON
103 0x0057: 0x03a0, # GREEK CAPITAL LETTER PI
104 0x0058: 0x03a1, # GREEK CAPITAL LETTER RHO
105 0x0059: 0x03a3, # GREEK CAPITAL LETTER SIGMA
106 0x005a: 0x005d, # RIGHT SQUARE BRACKET
107 0x005b: 0x0024, # DOLLAR SIGN
108 0x005c: 0x002a, # ASTERISK
109 0x005d: 0x0029, # RIGHT PARENTHESIS
110 0x005e: 0x003b, # SEMICOLON
111 0x005f: 0x005e, # CIRCUMFLEX ACCENT
112 0x0060: 0x002d, # HYPHEN-MINUS
113 0x0061: 0x002f, # SOLIDUS
114 0x0062: 0x03a4, # GREEK CAPITAL LETTER TAU
115 0x0063: 0x03a5, # GREEK CAPITAL LETTER UPSILON
116 0x0064: 0x03a6, # GREEK CAPITAL LETTER PHI
117 0x0065: 0x03a7, # GREEK CAPITAL LETTER CHI
118 0x0066: 0x03a8, # GREEK CAPITAL LETTER PSI
119 0x0067: 0x03a9, # GREEK CAPITAL LETTER OMEGA
120 0x0068: 0x03aa, # GREEK CAPITAL LETTER IOTA WITH DIALYTIKA
121 0x0069: 0x03ab, # GREEK CAPITAL LETTER UPSILON WITH DIALYTIKA
122 0x006a: 0x007c, # VERTICAL LINE
123 0x006b: 0x002c, # COMMA
124 0x006c: 0x0025, # PERCENT SIGN
125 0x006d: 0x005f, # LOW LINE
126 0x006e: 0x003e, # GREATER-THAN SIGN
127 0x006f: 0x003f, # QUESTION MARK
128 0x0070: 0x00a8, # DIAERESIS
129 0x0071: 0x0386, # GREEK CAPITAL LETTER ALPHA WITH TONOS
130 0x0072: 0x0388, # GREEK CAPITAL LETTER EPSILON WITH TONOS
131 0x0073: 0x0389, # GREEK CAPITAL LETTER ETA WITH TONOS
132 0x0074: 0x00a0, # NO-BREAK SPACE
133 0x0075: 0x038a, # GREEK CAPITAL LETTER IOTA WITH TONOS
134 0x0076: 0x038c, # GREEK CAPITAL LETTER OMICRON WITH TONOS
135 0x0077: 0x038e, # GREEK CAPITAL LETTER UPSILON WITH TONOS
136 0x0078: 0x038f, # GREEK CAPITAL LETTER OMEGA WITH TONOS
137 0x0079: 0x0060, # GRAVE ACCENT
138 0x007a: 0x003a, # COLON
139 0x007b: 0x0023, # NUMBER SIGN
140 0x007c: 0x0040, # COMMERCIAL AT
141 0x007d: 0x0027, # APOSTROPHE
142 0x007e: 0x003d, # EQUALS SIGN
143 0x007f: 0x0022, # QUOTATION MARK
144 0x0080: 0x0385, # GREEK DIALYTIKA TONOS
145 0x0081: 0x0061, # LATIN SMALL LETTER A
146 0x0082: 0x0062, # LATIN SMALL LETTER B
147 0x0083: 0x0063, # LATIN SMALL LETTER C
148 0x0084: 0x0064, # LATIN SMALL LETTER D
149 0x0085: 0x0065, # LATIN SMALL LETTER E
150 0x0086: 0x0066, # LATIN SMALL LETTER F
151 0x0087: 0x0067, # LATIN SMALL LETTER G
152 0x0088: 0x0068, # LATIN SMALL LETTER H
153 0x0089: 0x0069, # LATIN SMALL LETTER I
154 0x008a: 0x03b1, # GREEK SMALL LETTER ALPHA
155 0x008b: 0x03b2, # GREEK SMALL LETTER BETA
156 0x008c: 0x03b3, # GREEK SMALL LETTER GAMMA
157 0x008d: 0x03b4, # GREEK SMALL LETTER DELTA
158 0x008e: 0x03b5, # GREEK SMALL LETTER EPSILON
159 0x008f: 0x03b6, # GREEK SMALL LETTER ZETA
160 0x0090: 0x00b0, # DEGREE SIGN
161 0x0091: 0x006a, # LATIN SMALL LETTER J
162 0x0092: 0x006b, # LATIN SMALL LETTER K
163 0x0093: 0x006c, # LATIN SMALL LETTER L
164 0x0094: 0x006d, # LATIN SMALL LETTER M
165 0x0095: 0x006e, # LATIN SMALL LETTER N
166 0x0096: 0x006f, # LATIN SMALL LETTER O
167 0x0097: 0x0070, # LATIN SMALL LETTER P
168 0x0098: 0x0071, # LATIN SMALL LETTER Q
169 0x0099: 0x0072, # LATIN SMALL LETTER R
170 0x009a: 0x03b7, # GREEK SMALL LETTER ETA
171 0x009b: 0x03b8, # GREEK SMALL LETTER THETA
172 0x009c: 0x03b9, # GREEK SMALL LETTER IOTA
173 0x009d: 0x03ba, # GREEK SMALL LETTER KAPPA
174 0x009e: 0x03bb, # GREEK SMALL LETTER LAMDA
175 0x009f: 0x03bc, # GREEK SMALL LETTER MU
176 0x00a0: 0x00b4, # ACUTE ACCENT
177 0x00a1: 0x007e, # TILDE
178 0x00a2: 0x0073, # LATIN SMALL LETTER S
179 0x00a3: 0x0074, # LATIN SMALL LETTER T
180 0x00a4: 0x0075, # LATIN SMALL LETTER U
181 0x00a5: 0x0076, # LATIN SMALL LETTER V
182 0x00a6: 0x0077, # LATIN SMALL LETTER W
183 0x00a7: 0x0078, # LATIN SMALL LETTER X
184 0x00a8: 0x0079, # LATIN SMALL LETTER Y
185 0x00a9: 0x007a, # LATIN SMALL LETTER Z
186 0x00aa: 0x03bd, # GREEK SMALL LETTER NU
187 0x00ab: 0x03be, # GREEK SMALL LETTER XI
188 0x00ac: 0x03bf, # GREEK SMALL LETTER OMICRON
189 0x00ad: 0x03c0, # GREEK SMALL LETTER PI
190 0x00ae: 0x03c1, # GREEK SMALL LETTER RHO
191 0x00af: 0x03c3, # GREEK SMALL LETTER SIGMA
192 0x00b0: 0x00a3, # POUND SIGN
193 0x00b1: 0x03ac, # GREEK SMALL LETTER ALPHA WITH TONOS
194 0x00b2: 0x03ad, # GREEK SMALL LETTER EPSILON WITH TONOS
195 0x00b3: 0x03ae, # GREEK SMALL LETTER ETA WITH TONOS
196 0x00b4: 0x03ca, # GREEK SMALL LETTER IOTA WITH DIALYTIKA
197 0x00b5: 0x03af, # GREEK SMALL LETTER IOTA WITH TONOS
198 0x00b6: 0x03cc, # GREEK SMALL LETTER OMICRON WITH TONOS
199 0x00b7: 0x03cd, # GREEK SMALL LETTER UPSILON WITH TONOS
200 0x00b8: 0x03cb, # GREEK SMALL LETTER UPSILON WITH DIALYTIKA
201 0x00b9: 0x03ce, # GREEK SMALL LETTER OMEGA WITH TONOS
202 0x00ba: 0x03c2, # GREEK SMALL LETTER FINAL SIGMA
203 0x00bb: 0x03c4, # GREEK SMALL LETTER TAU
204 0x00bc: 0x03c5, # GREEK SMALL LETTER UPSILON
205 0x00bd: 0x03c6, # GREEK SMALL LETTER PHI
206 0x00be: 0x03c7, # GREEK SMALL LETTER CHI
207 0x00bf: 0x03c8, # GREEK SMALL LETTER PSI
208 0x00c0: 0x007b, # LEFT CURLY BRACKET
209 0x00c1: 0x0041, # LATIN CAPITAL LETTER A
210 0x00c2: 0x0042, # LATIN CAPITAL LETTER B
211 0x00c3: 0x0043, # LATIN CAPITAL LETTER C
212 0x00c4: 0x0044, # LATIN CAPITAL LETTER D
213 0x00c5: 0x0045, # LATIN CAPITAL LETTER E
214 0x00c6: 0x0046, # LATIN CAPITAL LETTER F
215 0x00c7: 0x0047, # LATIN CAPITAL LETTER G
216 0x00c8: 0x0048, # LATIN CAPITAL LETTER H
217 0x00c9: 0x0049, # LATIN CAPITAL LETTER I
218 0x00ca: 0x00ad, # SOFT HYPHEN
219 0x00cb: 0x03c9, # GREEK SMALL LETTER OMEGA
220 0x00cc: 0x0390, # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND TONOS
221 0x00cd: 0x03b0, # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND TONOS
222 0x00ce: 0x2018, # LEFT SINGLE QUOTATION MARK
223 0x00cf: 0x2015, # HORIZONTAL BAR
224 0x00d0: 0x007d, # RIGHT CURLY BRACKET
225 0x00d1: 0x004a, # LATIN CAPITAL LETTER J
226 0x00d2: 0x004b, # LATIN CAPITAL LETTER K
227 0x00d3: 0x004c, # LATIN CAPITAL LETTER L
228 0x00d4: 0x004d, # LATIN CAPITAL LETTER M
229 0x00d5: 0x004e, # LATIN CAPITAL LETTER N
230 0x00d6: 0x004f, # LATIN CAPITAL LETTER O
231 0x00d7: 0x0050, # LATIN CAPITAL LETTER P
232 0x00d8: 0x0051, # LATIN CAPITAL LETTER Q
233 0x00d9: 0x0052, # LATIN CAPITAL LETTER R
234 0x00da: 0x00b1, # PLUS-MINUS SIGN
235 0x00db: 0x00bd, # VULGAR FRACTION ONE HALF
236 0x00dc: 0x001a, # SUBSTITUTE
237 0x00dd: 0x0387, # GREEK ANO TELEIA
238 0x00de: 0x2019, # RIGHT SINGLE QUOTATION MARK
239 0x00df: 0x00a6, # BROKEN BAR
240 0x00e0: 0x005c, # REVERSE SOLIDUS
241 0x00e1: 0x001a, # SUBSTITUTE
242 0x00e2: 0x0053, # LATIN CAPITAL LETTER S
243 0x00e3: 0x0054, # LATIN CAPITAL LETTER T
244 0x00e4: 0x0055, # LATIN CAPITAL LETTER U
245 0x00e5: 0x0056, # LATIN CAPITAL LETTER V
246 0x00e6: 0x0057, # LATIN CAPITAL LETTER W
247 0x00e7: 0x0058, # LATIN CAPITAL LETTER X
248 0x00e8: 0x0059, # LATIN CAPITAL LETTER Y
249 0x00e9: 0x005a, # LATIN CAPITAL LETTER Z
250 0x00ea: 0x00b2, # SUPERSCRIPT TWO
251 0x00eb: 0x00a7, # SECTION SIGN
252 0x00ec: 0x001a, # SUBSTITUTE
253 0x00ed: 0x001a, # SUBSTITUTE
254 0x00ee: 0x00ab, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
255 0x00ef: 0x00ac, # NOT SIGN
256 0x00f0: 0x0030, # DIGIT ZERO
257 0x00f1: 0x0031, # DIGIT ONE
258 0x00f2: 0x0032, # DIGIT TWO
259 0x00f3: 0x0033, # DIGIT THREE
260 0x00f4: 0x0034, # DIGIT FOUR
261 0x00f5: 0x0035, # DIGIT FIVE
262 0x00f6: 0x0036, # DIGIT SIX
263 0x00f7: 0x0037, # DIGIT SEVEN
264 0x00f8: 0x0038, # DIGIT EIGHT
265 0x00f9: 0x0039, # DIGIT NINE
266 0x00fa: 0x00b3, # SUPERSCRIPT THREE
267 0x00fb: 0x00a9, # COPYRIGHT SIGN
268 0x00fc: 0x001a, # SUBSTITUTE
269 0x00fd: 0x001a, # SUBSTITUTE
270 0x00fe: 0x00bb, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
271 0x00ff: 0x009f, # CONTROL
Marc-André Lemburga866df82001-01-03 21:29:14 +0000272})
Guido van Rossum0229bf62000-03-10 23:17:24 +0000273
Marc-André Lemburg0f00ba82005-10-21 14:35:35 +0000274### Decoding Table
275
276decoding_table = (
277 u'\x00' # 0x0000 -> NULL
278 u'\x01' # 0x0001 -> START OF HEADING
279 u'\x02' # 0x0002 -> START OF TEXT
280 u'\x03' # 0x0003 -> END OF TEXT
281 u'\x9c' # 0x0004 -> CONTROL
282 u'\t' # 0x0005 -> HORIZONTAL TABULATION
283 u'\x86' # 0x0006 -> CONTROL
284 u'\x7f' # 0x0007 -> DELETE
285 u'\x97' # 0x0008 -> CONTROL
286 u'\x8d' # 0x0009 -> CONTROL
287 u'\x8e' # 0x000a -> CONTROL
288 u'\x0b' # 0x000b -> VERTICAL TABULATION
289 u'\x0c' # 0x000c -> FORM FEED
290 u'\r' # 0x000d -> CARRIAGE RETURN
291 u'\x0e' # 0x000e -> SHIFT OUT
292 u'\x0f' # 0x000f -> SHIFT IN
293 u'\x10' # 0x0010 -> DATA LINK ESCAPE
294 u'\x11' # 0x0011 -> DEVICE CONTROL ONE
295 u'\x12' # 0x0012 -> DEVICE CONTROL TWO
296 u'\x13' # 0x0013 -> DEVICE CONTROL THREE
297 u'\x9d' # 0x0014 -> CONTROL
298 u'\x85' # 0x0015 -> CONTROL
299 u'\x08' # 0x0016 -> BACKSPACE
300 u'\x87' # 0x0017 -> CONTROL
301 u'\x18' # 0x0018 -> CANCEL
302 u'\x19' # 0x0019 -> END OF MEDIUM
303 u'\x92' # 0x001a -> CONTROL
304 u'\x8f' # 0x001b -> CONTROL
305 u'\x1c' # 0x001c -> FILE SEPARATOR
306 u'\x1d' # 0x001d -> GROUP SEPARATOR
307 u'\x1e' # 0x001e -> RECORD SEPARATOR
308 u'\x1f' # 0x001f -> UNIT SEPARATOR
309 u'\x80' # 0x0020 -> CONTROL
310 u'\x81' # 0x0021 -> CONTROL
311 u'\x82' # 0x0022 -> CONTROL
312 u'\x83' # 0x0023 -> CONTROL
313 u'\x84' # 0x0024 -> CONTROL
314 u'\n' # 0x0025 -> LINE FEED
315 u'\x17' # 0x0026 -> END OF TRANSMISSION BLOCK
316 u'\x1b' # 0x0027 -> ESCAPE
317 u'\x88' # 0x0028 -> CONTROL
318 u'\x89' # 0x0029 -> CONTROL
319 u'\x8a' # 0x002a -> CONTROL
320 u'\x8b' # 0x002b -> CONTROL
321 u'\x8c' # 0x002c -> CONTROL
322 u'\x05' # 0x002d -> ENQUIRY
323 u'\x06' # 0x002e -> ACKNOWLEDGE
324 u'\x07' # 0x002f -> BELL
325 u'\x90' # 0x0030 -> CONTROL
326 u'\x91' # 0x0031 -> CONTROL
327 u'\x16' # 0x0032 -> SYNCHRONOUS IDLE
328 u'\x93' # 0x0033 -> CONTROL
329 u'\x94' # 0x0034 -> CONTROL
330 u'\x95' # 0x0035 -> CONTROL
331 u'\x96' # 0x0036 -> CONTROL
332 u'\x04' # 0x0037 -> END OF TRANSMISSION
333 u'\x98' # 0x0038 -> CONTROL
334 u'\x99' # 0x0039 -> CONTROL
335 u'\x9a' # 0x003a -> CONTROL
336 u'\x9b' # 0x003b -> CONTROL
337 u'\x14' # 0x003c -> DEVICE CONTROL FOUR
338 u'\x15' # 0x003d -> NEGATIVE ACKNOWLEDGE
339 u'\x9e' # 0x003e -> CONTROL
340 u'\x1a' # 0x003f -> SUBSTITUTE
341 u' ' # 0x0040 -> SPACE
342 u'\u0391' # 0x0041 -> GREEK CAPITAL LETTER ALPHA
343 u'\u0392' # 0x0042 -> GREEK CAPITAL LETTER BETA
344 u'\u0393' # 0x0043 -> GREEK CAPITAL LETTER GAMMA
345 u'\u0394' # 0x0044 -> GREEK CAPITAL LETTER DELTA
346 u'\u0395' # 0x0045 -> GREEK CAPITAL LETTER EPSILON
347 u'\u0396' # 0x0046 -> GREEK CAPITAL LETTER ZETA
348 u'\u0397' # 0x0047 -> GREEK CAPITAL LETTER ETA
349 u'\u0398' # 0x0048 -> GREEK CAPITAL LETTER THETA
350 u'\u0399' # 0x0049 -> GREEK CAPITAL LETTER IOTA
351 u'[' # 0x004a -> LEFT SQUARE BRACKET
352 u'.' # 0x004b -> FULL STOP
353 u'<' # 0x004c -> LESS-THAN SIGN
354 u'(' # 0x004d -> LEFT PARENTHESIS
355 u'+' # 0x004e -> PLUS SIGN
356 u'!' # 0x004f -> EXCLAMATION MARK
357 u'&' # 0x0050 -> AMPERSAND
358 u'\u039a' # 0x0051 -> GREEK CAPITAL LETTER KAPPA
359 u'\u039b' # 0x0052 -> GREEK CAPITAL LETTER LAMDA
360 u'\u039c' # 0x0053 -> GREEK CAPITAL LETTER MU
361 u'\u039d' # 0x0054 -> GREEK CAPITAL LETTER NU
362 u'\u039e' # 0x0055 -> GREEK CAPITAL LETTER XI
363 u'\u039f' # 0x0056 -> GREEK CAPITAL LETTER OMICRON
364 u'\u03a0' # 0x0057 -> GREEK CAPITAL LETTER PI
365 u'\u03a1' # 0x0058 -> GREEK CAPITAL LETTER RHO
366 u'\u03a3' # 0x0059 -> GREEK CAPITAL LETTER SIGMA
367 u']' # 0x005a -> RIGHT SQUARE BRACKET
368 u'$' # 0x005b -> DOLLAR SIGN
369 u'*' # 0x005c -> ASTERISK
370 u')' # 0x005d -> RIGHT PARENTHESIS
371 u';' # 0x005e -> SEMICOLON
372 u'^' # 0x005f -> CIRCUMFLEX ACCENT
373 u'-' # 0x0060 -> HYPHEN-MINUS
374 u'/' # 0x0061 -> SOLIDUS
375 u'\u03a4' # 0x0062 -> GREEK CAPITAL LETTER TAU
376 u'\u03a5' # 0x0063 -> GREEK CAPITAL LETTER UPSILON
377 u'\u03a6' # 0x0064 -> GREEK CAPITAL LETTER PHI
378 u'\u03a7' # 0x0065 -> GREEK CAPITAL LETTER CHI
379 u'\u03a8' # 0x0066 -> GREEK CAPITAL LETTER PSI
380 u'\u03a9' # 0x0067 -> GREEK CAPITAL LETTER OMEGA
381 u'\u03aa' # 0x0068 -> GREEK CAPITAL LETTER IOTA WITH DIALYTIKA
382 u'\u03ab' # 0x0069 -> GREEK CAPITAL LETTER UPSILON WITH DIALYTIKA
383 u'|' # 0x006a -> VERTICAL LINE
384 u',' # 0x006b -> COMMA
385 u'%' # 0x006c -> PERCENT SIGN
386 u'_' # 0x006d -> LOW LINE
387 u'>' # 0x006e -> GREATER-THAN SIGN
388 u'?' # 0x006f -> QUESTION MARK
389 u'\xa8' # 0x0070 -> DIAERESIS
390 u'\u0386' # 0x0071 -> GREEK CAPITAL LETTER ALPHA WITH TONOS
391 u'\u0388' # 0x0072 -> GREEK CAPITAL LETTER EPSILON WITH TONOS
392 u'\u0389' # 0x0073 -> GREEK CAPITAL LETTER ETA WITH TONOS
393 u'\xa0' # 0x0074 -> NO-BREAK SPACE
394 u'\u038a' # 0x0075 -> GREEK CAPITAL LETTER IOTA WITH TONOS
395 u'\u038c' # 0x0076 -> GREEK CAPITAL LETTER OMICRON WITH TONOS
396 u'\u038e' # 0x0077 -> GREEK CAPITAL LETTER UPSILON WITH TONOS
397 u'\u038f' # 0x0078 -> GREEK CAPITAL LETTER OMEGA WITH TONOS
398 u'`' # 0x0079 -> GRAVE ACCENT
399 u':' # 0x007a -> COLON
400 u'#' # 0x007b -> NUMBER SIGN
401 u'@' # 0x007c -> COMMERCIAL AT
402 u"'" # 0x007d -> APOSTROPHE
403 u'=' # 0x007e -> EQUALS SIGN
404 u'"' # 0x007f -> QUOTATION MARK
405 u'\u0385' # 0x0080 -> GREEK DIALYTIKA TONOS
406 u'a' # 0x0081 -> LATIN SMALL LETTER A
407 u'b' # 0x0082 -> LATIN SMALL LETTER B
408 u'c' # 0x0083 -> LATIN SMALL LETTER C
409 u'd' # 0x0084 -> LATIN SMALL LETTER D
410 u'e' # 0x0085 -> LATIN SMALL LETTER E
411 u'f' # 0x0086 -> LATIN SMALL LETTER F
412 u'g' # 0x0087 -> LATIN SMALL LETTER G
413 u'h' # 0x0088 -> LATIN SMALL LETTER H
414 u'i' # 0x0089 -> LATIN SMALL LETTER I
415 u'\u03b1' # 0x008a -> GREEK SMALL LETTER ALPHA
416 u'\u03b2' # 0x008b -> GREEK SMALL LETTER BETA
417 u'\u03b3' # 0x008c -> GREEK SMALL LETTER GAMMA
418 u'\u03b4' # 0x008d -> GREEK SMALL LETTER DELTA
419 u'\u03b5' # 0x008e -> GREEK SMALL LETTER EPSILON
420 u'\u03b6' # 0x008f -> GREEK SMALL LETTER ZETA
421 u'\xb0' # 0x0090 -> DEGREE SIGN
422 u'j' # 0x0091 -> LATIN SMALL LETTER J
423 u'k' # 0x0092 -> LATIN SMALL LETTER K
424 u'l' # 0x0093 -> LATIN SMALL LETTER L
425 u'm' # 0x0094 -> LATIN SMALL LETTER M
426 u'n' # 0x0095 -> LATIN SMALL LETTER N
427 u'o' # 0x0096 -> LATIN SMALL LETTER O
428 u'p' # 0x0097 -> LATIN SMALL LETTER P
429 u'q' # 0x0098 -> LATIN SMALL LETTER Q
430 u'r' # 0x0099 -> LATIN SMALL LETTER R
431 u'\u03b7' # 0x009a -> GREEK SMALL LETTER ETA
432 u'\u03b8' # 0x009b -> GREEK SMALL LETTER THETA
433 u'\u03b9' # 0x009c -> GREEK SMALL LETTER IOTA
434 u'\u03ba' # 0x009d -> GREEK SMALL LETTER KAPPA
435 u'\u03bb' # 0x009e -> GREEK SMALL LETTER LAMDA
436 u'\u03bc' # 0x009f -> GREEK SMALL LETTER MU
437 u'\xb4' # 0x00a0 -> ACUTE ACCENT
438 u'~' # 0x00a1 -> TILDE
439 u's' # 0x00a2 -> LATIN SMALL LETTER S
440 u't' # 0x00a3 -> LATIN SMALL LETTER T
441 u'u' # 0x00a4 -> LATIN SMALL LETTER U
442 u'v' # 0x00a5 -> LATIN SMALL LETTER V
443 u'w' # 0x00a6 -> LATIN SMALL LETTER W
444 u'x' # 0x00a7 -> LATIN SMALL LETTER X
445 u'y' # 0x00a8 -> LATIN SMALL LETTER Y
446 u'z' # 0x00a9 -> LATIN SMALL LETTER Z
447 u'\u03bd' # 0x00aa -> GREEK SMALL LETTER NU
448 u'\u03be' # 0x00ab -> GREEK SMALL LETTER XI
449 u'\u03bf' # 0x00ac -> GREEK SMALL LETTER OMICRON
450 u'\u03c0' # 0x00ad -> GREEK SMALL LETTER PI
451 u'\u03c1' # 0x00ae -> GREEK SMALL LETTER RHO
452 u'\u03c3' # 0x00af -> GREEK SMALL LETTER SIGMA
453 u'\xa3' # 0x00b0 -> POUND SIGN
454 u'\u03ac' # 0x00b1 -> GREEK SMALL LETTER ALPHA WITH TONOS
455 u'\u03ad' # 0x00b2 -> GREEK SMALL LETTER EPSILON WITH TONOS
456 u'\u03ae' # 0x00b3 -> GREEK SMALL LETTER ETA WITH TONOS
457 u'\u03ca' # 0x00b4 -> GREEK SMALL LETTER IOTA WITH DIALYTIKA
458 u'\u03af' # 0x00b5 -> GREEK SMALL LETTER IOTA WITH TONOS
459 u'\u03cc' # 0x00b6 -> GREEK SMALL LETTER OMICRON WITH TONOS
460 u'\u03cd' # 0x00b7 -> GREEK SMALL LETTER UPSILON WITH TONOS
461 u'\u03cb' # 0x00b8 -> GREEK SMALL LETTER UPSILON WITH DIALYTIKA
462 u'\u03ce' # 0x00b9 -> GREEK SMALL LETTER OMEGA WITH TONOS
463 u'\u03c2' # 0x00ba -> GREEK SMALL LETTER FINAL SIGMA
464 u'\u03c4' # 0x00bb -> GREEK SMALL LETTER TAU
465 u'\u03c5' # 0x00bc -> GREEK SMALL LETTER UPSILON
466 u'\u03c6' # 0x00bd -> GREEK SMALL LETTER PHI
467 u'\u03c7' # 0x00be -> GREEK SMALL LETTER CHI
468 u'\u03c8' # 0x00bf -> GREEK SMALL LETTER PSI
469 u'{' # 0x00c0 -> LEFT CURLY BRACKET
470 u'A' # 0x00c1 -> LATIN CAPITAL LETTER A
471 u'B' # 0x00c2 -> LATIN CAPITAL LETTER B
472 u'C' # 0x00c3 -> LATIN CAPITAL LETTER C
473 u'D' # 0x00c4 -> LATIN CAPITAL LETTER D
474 u'E' # 0x00c5 -> LATIN CAPITAL LETTER E
475 u'F' # 0x00c6 -> LATIN CAPITAL LETTER F
476 u'G' # 0x00c7 -> LATIN CAPITAL LETTER G
477 u'H' # 0x00c8 -> LATIN CAPITAL LETTER H
478 u'I' # 0x00c9 -> LATIN CAPITAL LETTER I
479 u'\xad' # 0x00ca -> SOFT HYPHEN
480 u'\u03c9' # 0x00cb -> GREEK SMALL LETTER OMEGA
481 u'\u0390' # 0x00cc -> GREEK SMALL LETTER IOTA WITH DIALYTIKA AND TONOS
482 u'\u03b0' # 0x00cd -> GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND TONOS
483 u'\u2018' # 0x00ce -> LEFT SINGLE QUOTATION MARK
484 u'\u2015' # 0x00cf -> HORIZONTAL BAR
485 u'}' # 0x00d0 -> RIGHT CURLY BRACKET
486 u'J' # 0x00d1 -> LATIN CAPITAL LETTER J
487 u'K' # 0x00d2 -> LATIN CAPITAL LETTER K
488 u'L' # 0x00d3 -> LATIN CAPITAL LETTER L
489 u'M' # 0x00d4 -> LATIN CAPITAL LETTER M
490 u'N' # 0x00d5 -> LATIN CAPITAL LETTER N
491 u'O' # 0x00d6 -> LATIN CAPITAL LETTER O
492 u'P' # 0x00d7 -> LATIN CAPITAL LETTER P
493 u'Q' # 0x00d8 -> LATIN CAPITAL LETTER Q
494 u'R' # 0x00d9 -> LATIN CAPITAL LETTER R
495 u'\xb1' # 0x00da -> PLUS-MINUS SIGN
496 u'\xbd' # 0x00db -> VULGAR FRACTION ONE HALF
497 u'\x1a' # 0x00dc -> SUBSTITUTE
498 u'\u0387' # 0x00dd -> GREEK ANO TELEIA
499 u'\u2019' # 0x00de -> RIGHT SINGLE QUOTATION MARK
500 u'\xa6' # 0x00df -> BROKEN BAR
501 u'\\' # 0x00e0 -> REVERSE SOLIDUS
502 u'\x1a' # 0x00e1 -> SUBSTITUTE
503 u'S' # 0x00e2 -> LATIN CAPITAL LETTER S
504 u'T' # 0x00e3 -> LATIN CAPITAL LETTER T
505 u'U' # 0x00e4 -> LATIN CAPITAL LETTER U
506 u'V' # 0x00e5 -> LATIN CAPITAL LETTER V
507 u'W' # 0x00e6 -> LATIN CAPITAL LETTER W
508 u'X' # 0x00e7 -> LATIN CAPITAL LETTER X
509 u'Y' # 0x00e8 -> LATIN CAPITAL LETTER Y
510 u'Z' # 0x00e9 -> LATIN CAPITAL LETTER Z
511 u'\xb2' # 0x00ea -> SUPERSCRIPT TWO
512 u'\xa7' # 0x00eb -> SECTION SIGN
513 u'\x1a' # 0x00ec -> SUBSTITUTE
514 u'\x1a' # 0x00ed -> SUBSTITUTE
515 u'\xab' # 0x00ee -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
516 u'\xac' # 0x00ef -> NOT SIGN
517 u'0' # 0x00f0 -> DIGIT ZERO
518 u'1' # 0x00f1 -> DIGIT ONE
519 u'2' # 0x00f2 -> DIGIT TWO
520 u'3' # 0x00f3 -> DIGIT THREE
521 u'4' # 0x00f4 -> DIGIT FOUR
522 u'5' # 0x00f5 -> DIGIT FIVE
523 u'6' # 0x00f6 -> DIGIT SIX
524 u'7' # 0x00f7 -> DIGIT SEVEN
525 u'8' # 0x00f8 -> DIGIT EIGHT
526 u'9' # 0x00f9 -> DIGIT NINE
527 u'\xb3' # 0x00fa -> SUPERSCRIPT THREE
528 u'\xa9' # 0x00fb -> COPYRIGHT SIGN
529 u'\x1a' # 0x00fc -> SUBSTITUTE
530 u'\x1a' # 0x00fd -> SUBSTITUTE
531 u'\xbb' # 0x00fe -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
532 u'\x9f' # 0x00ff -> CONTROL
533)
534
Guido van Rossum0229bf62000-03-10 23:17:24 +0000535### Encoding Map
536
Marc-André Lemburg0f00ba82005-10-21 14:35:35 +0000537encoding_map = {
538 0x0000: 0x0000, # NULL
539 0x0001: 0x0001, # START OF HEADING
540 0x0002: 0x0002, # START OF TEXT
541 0x0003: 0x0003, # END OF TEXT
542 0x0004: 0x0037, # END OF TRANSMISSION
543 0x0005: 0x002d, # ENQUIRY
544 0x0006: 0x002e, # ACKNOWLEDGE
545 0x0007: 0x002f, # BELL
546 0x0008: 0x0016, # BACKSPACE
547 0x0009: 0x0005, # HORIZONTAL TABULATION
548 0x000a: 0x0025, # LINE FEED
549 0x000b: 0x000b, # VERTICAL TABULATION
550 0x000c: 0x000c, # FORM FEED
551 0x000d: 0x000d, # CARRIAGE RETURN
552 0x000e: 0x000e, # SHIFT OUT
553 0x000f: 0x000f, # SHIFT IN
554 0x0010: 0x0010, # DATA LINK ESCAPE
555 0x0011: 0x0011, # DEVICE CONTROL ONE
556 0x0012: 0x0012, # DEVICE CONTROL TWO
557 0x0013: 0x0013, # DEVICE CONTROL THREE
558 0x0014: 0x003c, # DEVICE CONTROL FOUR
559 0x0015: 0x003d, # NEGATIVE ACKNOWLEDGE
560 0x0016: 0x0032, # SYNCHRONOUS IDLE
561 0x0017: 0x0026, # END OF TRANSMISSION BLOCK
562 0x0018: 0x0018, # CANCEL
563 0x0019: 0x0019, # END OF MEDIUM
564 0x001a: None, # SUBSTITUTE
565 0x001b: 0x0027, # ESCAPE
566 0x001c: 0x001c, # FILE SEPARATOR
567 0x001d: 0x001d, # GROUP SEPARATOR
568 0x001e: 0x001e, # RECORD SEPARATOR
569 0x001f: 0x001f, # UNIT SEPARATOR
570 0x0020: 0x0040, # SPACE
571 0x0021: 0x004f, # EXCLAMATION MARK
572 0x0022: 0x007f, # QUOTATION MARK
573 0x0023: 0x007b, # NUMBER SIGN
574 0x0024: 0x005b, # DOLLAR SIGN
575 0x0025: 0x006c, # PERCENT SIGN
576 0x0026: 0x0050, # AMPERSAND
577 0x0027: 0x007d, # APOSTROPHE
578 0x0028: 0x004d, # LEFT PARENTHESIS
579 0x0029: 0x005d, # RIGHT PARENTHESIS
580 0x002a: 0x005c, # ASTERISK
581 0x002b: 0x004e, # PLUS SIGN
582 0x002c: 0x006b, # COMMA
583 0x002d: 0x0060, # HYPHEN-MINUS
584 0x002e: 0x004b, # FULL STOP
585 0x002f: 0x0061, # SOLIDUS
586 0x0030: 0x00f0, # DIGIT ZERO
587 0x0031: 0x00f1, # DIGIT ONE
588 0x0032: 0x00f2, # DIGIT TWO
589 0x0033: 0x00f3, # DIGIT THREE
590 0x0034: 0x00f4, # DIGIT FOUR
591 0x0035: 0x00f5, # DIGIT FIVE
592 0x0036: 0x00f6, # DIGIT SIX
593 0x0037: 0x00f7, # DIGIT SEVEN
594 0x0038: 0x00f8, # DIGIT EIGHT
595 0x0039: 0x00f9, # DIGIT NINE
596 0x003a: 0x007a, # COLON
597 0x003b: 0x005e, # SEMICOLON
598 0x003c: 0x004c, # LESS-THAN SIGN
599 0x003d: 0x007e, # EQUALS SIGN
600 0x003e: 0x006e, # GREATER-THAN SIGN
601 0x003f: 0x006f, # QUESTION MARK
602 0x0040: 0x007c, # COMMERCIAL AT
603 0x0041: 0x00c1, # LATIN CAPITAL LETTER A
604 0x0042: 0x00c2, # LATIN CAPITAL LETTER B
605 0x0043: 0x00c3, # LATIN CAPITAL LETTER C
606 0x0044: 0x00c4, # LATIN CAPITAL LETTER D
607 0x0045: 0x00c5, # LATIN CAPITAL LETTER E
608 0x0046: 0x00c6, # LATIN CAPITAL LETTER F
609 0x0047: 0x00c7, # LATIN CAPITAL LETTER G
610 0x0048: 0x00c8, # LATIN CAPITAL LETTER H
611 0x0049: 0x00c9, # LATIN CAPITAL LETTER I
612 0x004a: 0x00d1, # LATIN CAPITAL LETTER J
613 0x004b: 0x00d2, # LATIN CAPITAL LETTER K
614 0x004c: 0x00d3, # LATIN CAPITAL LETTER L
615 0x004d: 0x00d4, # LATIN CAPITAL LETTER M
616 0x004e: 0x00d5, # LATIN CAPITAL LETTER N
617 0x004f: 0x00d6, # LATIN CAPITAL LETTER O
618 0x0050: 0x00d7, # LATIN CAPITAL LETTER P
619 0x0051: 0x00d8, # LATIN CAPITAL LETTER Q
620 0x0052: 0x00d9, # LATIN CAPITAL LETTER R
621 0x0053: 0x00e2, # LATIN CAPITAL LETTER S
622 0x0054: 0x00e3, # LATIN CAPITAL LETTER T
623 0x0055: 0x00e4, # LATIN CAPITAL LETTER U
624 0x0056: 0x00e5, # LATIN CAPITAL LETTER V
625 0x0057: 0x00e6, # LATIN CAPITAL LETTER W
626 0x0058: 0x00e7, # LATIN CAPITAL LETTER X
627 0x0059: 0x00e8, # LATIN CAPITAL LETTER Y
628 0x005a: 0x00e9, # LATIN CAPITAL LETTER Z
629 0x005b: 0x004a, # LEFT SQUARE BRACKET
630 0x005c: 0x00e0, # REVERSE SOLIDUS
631 0x005d: 0x005a, # RIGHT SQUARE BRACKET
632 0x005e: 0x005f, # CIRCUMFLEX ACCENT
633 0x005f: 0x006d, # LOW LINE
634 0x0060: 0x0079, # GRAVE ACCENT
635 0x0061: 0x0081, # LATIN SMALL LETTER A
636 0x0062: 0x0082, # LATIN SMALL LETTER B
637 0x0063: 0x0083, # LATIN SMALL LETTER C
638 0x0064: 0x0084, # LATIN SMALL LETTER D
639 0x0065: 0x0085, # LATIN SMALL LETTER E
640 0x0066: 0x0086, # LATIN SMALL LETTER F
641 0x0067: 0x0087, # LATIN SMALL LETTER G
642 0x0068: 0x0088, # LATIN SMALL LETTER H
643 0x0069: 0x0089, # LATIN SMALL LETTER I
644 0x006a: 0x0091, # LATIN SMALL LETTER J
645 0x006b: 0x0092, # LATIN SMALL LETTER K
646 0x006c: 0x0093, # LATIN SMALL LETTER L
647 0x006d: 0x0094, # LATIN SMALL LETTER M
648 0x006e: 0x0095, # LATIN SMALL LETTER N
649 0x006f: 0x0096, # LATIN SMALL LETTER O
650 0x0070: 0x0097, # LATIN SMALL LETTER P
651 0x0071: 0x0098, # LATIN SMALL LETTER Q
652 0x0072: 0x0099, # LATIN SMALL LETTER R
653 0x0073: 0x00a2, # LATIN SMALL LETTER S
654 0x0074: 0x00a3, # LATIN SMALL LETTER T
655 0x0075: 0x00a4, # LATIN SMALL LETTER U
656 0x0076: 0x00a5, # LATIN SMALL LETTER V
657 0x0077: 0x00a6, # LATIN SMALL LETTER W
658 0x0078: 0x00a7, # LATIN SMALL LETTER X
659 0x0079: 0x00a8, # LATIN SMALL LETTER Y
660 0x007a: 0x00a9, # LATIN SMALL LETTER Z
661 0x007b: 0x00c0, # LEFT CURLY BRACKET
662 0x007c: 0x006a, # VERTICAL LINE
663 0x007d: 0x00d0, # RIGHT CURLY BRACKET
664 0x007e: 0x00a1, # TILDE
665 0x007f: 0x0007, # DELETE
666 0x0080: 0x0020, # CONTROL
667 0x0081: 0x0021, # CONTROL
668 0x0082: 0x0022, # CONTROL
669 0x0083: 0x0023, # CONTROL
670 0x0084: 0x0024, # CONTROL
671 0x0085: 0x0015, # CONTROL
672 0x0086: 0x0006, # CONTROL
673 0x0087: 0x0017, # CONTROL
674 0x0088: 0x0028, # CONTROL
675 0x0089: 0x0029, # CONTROL
676 0x008a: 0x002a, # CONTROL
677 0x008b: 0x002b, # CONTROL
678 0x008c: 0x002c, # CONTROL
679 0x008d: 0x0009, # CONTROL
680 0x008e: 0x000a, # CONTROL
681 0x008f: 0x001b, # CONTROL
682 0x0090: 0x0030, # CONTROL
683 0x0091: 0x0031, # CONTROL
684 0x0092: 0x001a, # CONTROL
685 0x0093: 0x0033, # CONTROL
686 0x0094: 0x0034, # CONTROL
687 0x0095: 0x0035, # CONTROL
688 0x0096: 0x0036, # CONTROL
689 0x0097: 0x0008, # CONTROL
690 0x0098: 0x0038, # CONTROL
691 0x0099: 0x0039, # CONTROL
692 0x009a: 0x003a, # CONTROL
693 0x009b: 0x003b, # CONTROL
694 0x009c: 0x0004, # CONTROL
695 0x009d: 0x0014, # CONTROL
696 0x009e: 0x003e, # CONTROL
697 0x009f: 0x00ff, # CONTROL
698 0x00a0: 0x0074, # NO-BREAK SPACE
699 0x00a3: 0x00b0, # POUND SIGN
700 0x00a6: 0x00df, # BROKEN BAR
701 0x00a7: 0x00eb, # SECTION SIGN
702 0x00a8: 0x0070, # DIAERESIS
703 0x00a9: 0x00fb, # COPYRIGHT SIGN
704 0x00ab: 0x00ee, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
705 0x00ac: 0x00ef, # NOT SIGN
706 0x00ad: 0x00ca, # SOFT HYPHEN
707 0x00b0: 0x0090, # DEGREE SIGN
708 0x00b1: 0x00da, # PLUS-MINUS SIGN
709 0x00b2: 0x00ea, # SUPERSCRIPT TWO
710 0x00b3: 0x00fa, # SUPERSCRIPT THREE
711 0x00b4: 0x00a0, # ACUTE ACCENT
712 0x00bb: 0x00fe, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
713 0x00bd: 0x00db, # VULGAR FRACTION ONE HALF
714 0x0385: 0x0080, # GREEK DIALYTIKA TONOS
715 0x0386: 0x0071, # GREEK CAPITAL LETTER ALPHA WITH TONOS
716 0x0387: 0x00dd, # GREEK ANO TELEIA
717 0x0388: 0x0072, # GREEK CAPITAL LETTER EPSILON WITH TONOS
718 0x0389: 0x0073, # GREEK CAPITAL LETTER ETA WITH TONOS
719 0x038a: 0x0075, # GREEK CAPITAL LETTER IOTA WITH TONOS
720 0x038c: 0x0076, # GREEK CAPITAL LETTER OMICRON WITH TONOS
721 0x038e: 0x0077, # GREEK CAPITAL LETTER UPSILON WITH TONOS
722 0x038f: 0x0078, # GREEK CAPITAL LETTER OMEGA WITH TONOS
723 0x0390: 0x00cc, # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND TONOS
724 0x0391: 0x0041, # GREEK CAPITAL LETTER ALPHA
725 0x0392: 0x0042, # GREEK CAPITAL LETTER BETA
726 0x0393: 0x0043, # GREEK CAPITAL LETTER GAMMA
727 0x0394: 0x0044, # GREEK CAPITAL LETTER DELTA
728 0x0395: 0x0045, # GREEK CAPITAL LETTER EPSILON
729 0x0396: 0x0046, # GREEK CAPITAL LETTER ZETA
730 0x0397: 0x0047, # GREEK CAPITAL LETTER ETA
731 0x0398: 0x0048, # GREEK CAPITAL LETTER THETA
732 0x0399: 0x0049, # GREEK CAPITAL LETTER IOTA
733 0x039a: 0x0051, # GREEK CAPITAL LETTER KAPPA
734 0x039b: 0x0052, # GREEK CAPITAL LETTER LAMDA
735 0x039c: 0x0053, # GREEK CAPITAL LETTER MU
736 0x039d: 0x0054, # GREEK CAPITAL LETTER NU
737 0x039e: 0x0055, # GREEK CAPITAL LETTER XI
738 0x039f: 0x0056, # GREEK CAPITAL LETTER OMICRON
739 0x03a0: 0x0057, # GREEK CAPITAL LETTER PI
740 0x03a1: 0x0058, # GREEK CAPITAL LETTER RHO
741 0x03a3: 0x0059, # GREEK CAPITAL LETTER SIGMA
742 0x03a4: 0x0062, # GREEK CAPITAL LETTER TAU
743 0x03a5: 0x0063, # GREEK CAPITAL LETTER UPSILON
744 0x03a6: 0x0064, # GREEK CAPITAL LETTER PHI
745 0x03a7: 0x0065, # GREEK CAPITAL LETTER CHI
746 0x03a8: 0x0066, # GREEK CAPITAL LETTER PSI
747 0x03a9: 0x0067, # GREEK CAPITAL LETTER OMEGA
748 0x03aa: 0x0068, # GREEK CAPITAL LETTER IOTA WITH DIALYTIKA
749 0x03ab: 0x0069, # GREEK CAPITAL LETTER UPSILON WITH DIALYTIKA
750 0x03ac: 0x00b1, # GREEK SMALL LETTER ALPHA WITH TONOS
751 0x03ad: 0x00b2, # GREEK SMALL LETTER EPSILON WITH TONOS
752 0x03ae: 0x00b3, # GREEK SMALL LETTER ETA WITH TONOS
753 0x03af: 0x00b5, # GREEK SMALL LETTER IOTA WITH TONOS
754 0x03b0: 0x00cd, # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND TONOS
755 0x03b1: 0x008a, # GREEK SMALL LETTER ALPHA
756 0x03b2: 0x008b, # GREEK SMALL LETTER BETA
757 0x03b3: 0x008c, # GREEK SMALL LETTER GAMMA
758 0x03b4: 0x008d, # GREEK SMALL LETTER DELTA
759 0x03b5: 0x008e, # GREEK SMALL LETTER EPSILON
760 0x03b6: 0x008f, # GREEK SMALL LETTER ZETA
761 0x03b7: 0x009a, # GREEK SMALL LETTER ETA
762 0x03b8: 0x009b, # GREEK SMALL LETTER THETA
763 0x03b9: 0x009c, # GREEK SMALL LETTER IOTA
764 0x03ba: 0x009d, # GREEK SMALL LETTER KAPPA
765 0x03bb: 0x009e, # GREEK SMALL LETTER LAMDA
766 0x03bc: 0x009f, # GREEK SMALL LETTER MU
767 0x03bd: 0x00aa, # GREEK SMALL LETTER NU
768 0x03be: 0x00ab, # GREEK SMALL LETTER XI
769 0x03bf: 0x00ac, # GREEK SMALL LETTER OMICRON
770 0x03c0: 0x00ad, # GREEK SMALL LETTER PI
771 0x03c1: 0x00ae, # GREEK SMALL LETTER RHO
772 0x03c2: 0x00ba, # GREEK SMALL LETTER FINAL SIGMA
773 0x03c3: 0x00af, # GREEK SMALL LETTER SIGMA
774 0x03c4: 0x00bb, # GREEK SMALL LETTER TAU
775 0x03c5: 0x00bc, # GREEK SMALL LETTER UPSILON
776 0x03c6: 0x00bd, # GREEK SMALL LETTER PHI
777 0x03c7: 0x00be, # GREEK SMALL LETTER CHI
778 0x03c8: 0x00bf, # GREEK SMALL LETTER PSI
779 0x03c9: 0x00cb, # GREEK SMALL LETTER OMEGA
780 0x03ca: 0x00b4, # GREEK SMALL LETTER IOTA WITH DIALYTIKA
781 0x03cb: 0x00b8, # GREEK SMALL LETTER UPSILON WITH DIALYTIKA
782 0x03cc: 0x00b6, # GREEK SMALL LETTER OMICRON WITH TONOS
783 0x03cd: 0x00b7, # GREEK SMALL LETTER UPSILON WITH TONOS
784 0x03ce: 0x00b9, # GREEK SMALL LETTER OMEGA WITH TONOS
785 0x2015: 0x00cf, # HORIZONTAL BAR
786 0x2018: 0x00ce, # LEFT SINGLE QUOTATION MARK
787 0x2019: 0x00de, # RIGHT SINGLE QUOTATION MARK
788}