blob: c4fe1208baa6fe10e8185e99b16959b06333fc54 [file] [log] [blame]
Marc-André Lemburga1129f42005-10-21 13:49:12 +00001""" Python Character Mapping Codec generated from 'VENDORS/APPLE/GREEK.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: 0x00c4, # LATIN CAPITAL LETTER A WITH DIAERESIS
36 0x0081: 0x00b9, # SUPERSCRIPT ONE
37 0x0082: 0x00b2, # SUPERSCRIPT TWO
38 0x0083: 0x00c9, # LATIN CAPITAL LETTER E WITH ACUTE
39 0x0084: 0x00b3, # SUPERSCRIPT THREE
40 0x0085: 0x00d6, # LATIN CAPITAL LETTER O WITH DIAERESIS
41 0x0086: 0x00dc, # LATIN CAPITAL LETTER U WITH DIAERESIS
42 0x0087: 0x0385, # GREEK DIALYTIKA TONOS
43 0x0088: 0x00e0, # LATIN SMALL LETTER A WITH GRAVE
44 0x0089: 0x00e2, # LATIN SMALL LETTER A WITH CIRCUMFLEX
45 0x008a: 0x00e4, # LATIN SMALL LETTER A WITH DIAERESIS
46 0x008b: 0x0384, # GREEK TONOS
47 0x008c: 0x00a8, # DIAERESIS
48 0x008d: 0x00e7, # LATIN SMALL LETTER C WITH CEDILLA
49 0x008e: 0x00e9, # LATIN SMALL LETTER E WITH ACUTE
50 0x008f: 0x00e8, # LATIN SMALL LETTER E WITH GRAVE
51 0x0090: 0x00ea, # LATIN SMALL LETTER E WITH CIRCUMFLEX
52 0x0091: 0x00eb, # LATIN SMALL LETTER E WITH DIAERESIS
53 0x0092: 0x00a3, # POUND SIGN
54 0x0093: 0x2122, # TRADE MARK SIGN
55 0x0094: 0x00ee, # LATIN SMALL LETTER I WITH CIRCUMFLEX
56 0x0095: 0x00ef, # LATIN SMALL LETTER I WITH DIAERESIS
57 0x0096: 0x2022, # BULLET
58 0x0097: 0x00bd, # VULGAR FRACTION ONE HALF
59 0x0098: 0x2030, # PER MILLE SIGN
60 0x0099: 0x00f4, # LATIN SMALL LETTER O WITH CIRCUMFLEX
61 0x009a: 0x00f6, # LATIN SMALL LETTER O WITH DIAERESIS
62 0x009b: 0x00a6, # BROKEN BAR
63 0x009c: 0x20ac, # EURO SIGN # before Mac OS 9.2.2, was SOFT HYPHEN
64 0x009d: 0x00f9, # LATIN SMALL LETTER U WITH GRAVE
65 0x009e: 0x00fb, # LATIN SMALL LETTER U WITH CIRCUMFLEX
66 0x009f: 0x00fc, # LATIN SMALL LETTER U WITH DIAERESIS
67 0x00a0: 0x2020, # DAGGER
68 0x00a1: 0x0393, # GREEK CAPITAL LETTER GAMMA
69 0x00a2: 0x0394, # GREEK CAPITAL LETTER DELTA
70 0x00a3: 0x0398, # GREEK CAPITAL LETTER THETA
71 0x00a4: 0x039b, # GREEK CAPITAL LETTER LAMDA
72 0x00a5: 0x039e, # GREEK CAPITAL LETTER XI
73 0x00a6: 0x03a0, # GREEK CAPITAL LETTER PI
74 0x00a7: 0x00df, # LATIN SMALL LETTER SHARP S
75 0x00a8: 0x00ae, # REGISTERED SIGN
76 0x00aa: 0x03a3, # GREEK CAPITAL LETTER SIGMA
77 0x00ab: 0x03aa, # GREEK CAPITAL LETTER IOTA WITH DIALYTIKA
78 0x00ac: 0x00a7, # SECTION SIGN
79 0x00ad: 0x2260, # NOT EQUAL TO
80 0x00ae: 0x00b0, # DEGREE SIGN
81 0x00af: 0x00b7, # MIDDLE DOT
82 0x00b0: 0x0391, # GREEK CAPITAL LETTER ALPHA
83 0x00b2: 0x2264, # LESS-THAN OR EQUAL TO
84 0x00b3: 0x2265, # GREATER-THAN OR EQUAL TO
85 0x00b4: 0x00a5, # YEN SIGN
86 0x00b5: 0x0392, # GREEK CAPITAL LETTER BETA
87 0x00b6: 0x0395, # GREEK CAPITAL LETTER EPSILON
88 0x00b7: 0x0396, # GREEK CAPITAL LETTER ZETA
89 0x00b8: 0x0397, # GREEK CAPITAL LETTER ETA
90 0x00b9: 0x0399, # GREEK CAPITAL LETTER IOTA
91 0x00ba: 0x039a, # GREEK CAPITAL LETTER KAPPA
92 0x00bb: 0x039c, # GREEK CAPITAL LETTER MU
93 0x00bc: 0x03a6, # GREEK CAPITAL LETTER PHI
94 0x00bd: 0x03ab, # GREEK CAPITAL LETTER UPSILON WITH DIALYTIKA
95 0x00be: 0x03a8, # GREEK CAPITAL LETTER PSI
96 0x00bf: 0x03a9, # GREEK CAPITAL LETTER OMEGA
97 0x00c0: 0x03ac, # GREEK SMALL LETTER ALPHA WITH TONOS
98 0x00c1: 0x039d, # GREEK CAPITAL LETTER NU
99 0x00c2: 0x00ac, # NOT SIGN
100 0x00c3: 0x039f, # GREEK CAPITAL LETTER OMICRON
101 0x00c4: 0x03a1, # GREEK CAPITAL LETTER RHO
102 0x00c5: 0x2248, # ALMOST EQUAL TO
103 0x00c6: 0x03a4, # GREEK CAPITAL LETTER TAU
104 0x00c7: 0x00ab, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
105 0x00c8: 0x00bb, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
106 0x00c9: 0x2026, # HORIZONTAL ELLIPSIS
107 0x00ca: 0x00a0, # NO-BREAK SPACE
108 0x00cb: 0x03a5, # GREEK CAPITAL LETTER UPSILON
109 0x00cc: 0x03a7, # GREEK CAPITAL LETTER CHI
110 0x00cd: 0x0386, # GREEK CAPITAL LETTER ALPHA WITH TONOS
111 0x00ce: 0x0388, # GREEK CAPITAL LETTER EPSILON WITH TONOS
112 0x00cf: 0x0153, # LATIN SMALL LIGATURE OE
113 0x00d0: 0x2013, # EN DASH
114 0x00d1: 0x2015, # HORIZONTAL BAR
115 0x00d2: 0x201c, # LEFT DOUBLE QUOTATION MARK
116 0x00d3: 0x201d, # RIGHT DOUBLE QUOTATION MARK
117 0x00d4: 0x2018, # LEFT SINGLE QUOTATION MARK
118 0x00d5: 0x2019, # RIGHT SINGLE QUOTATION MARK
119 0x00d6: 0x00f7, # DIVISION SIGN
120 0x00d7: 0x0389, # GREEK CAPITAL LETTER ETA WITH TONOS
121 0x00d8: 0x038a, # GREEK CAPITAL LETTER IOTA WITH TONOS
122 0x00d9: 0x038c, # GREEK CAPITAL LETTER OMICRON WITH TONOS
123 0x00da: 0x038e, # GREEK CAPITAL LETTER UPSILON WITH TONOS
124 0x00db: 0x03ad, # GREEK SMALL LETTER EPSILON WITH TONOS
125 0x00dc: 0x03ae, # GREEK SMALL LETTER ETA WITH TONOS
126 0x00dd: 0x03af, # GREEK SMALL LETTER IOTA WITH TONOS
127 0x00de: 0x03cc, # GREEK SMALL LETTER OMICRON WITH TONOS
128 0x00df: 0x038f, # GREEK CAPITAL LETTER OMEGA WITH TONOS
129 0x00e0: 0x03cd, # GREEK SMALL LETTER UPSILON WITH TONOS
130 0x00e1: 0x03b1, # GREEK SMALL LETTER ALPHA
131 0x00e2: 0x03b2, # GREEK SMALL LETTER BETA
132 0x00e3: 0x03c8, # GREEK SMALL LETTER PSI
133 0x00e4: 0x03b4, # GREEK SMALL LETTER DELTA
134 0x00e5: 0x03b5, # GREEK SMALL LETTER EPSILON
135 0x00e6: 0x03c6, # GREEK SMALL LETTER PHI
136 0x00e7: 0x03b3, # GREEK SMALL LETTER GAMMA
137 0x00e8: 0x03b7, # GREEK SMALL LETTER ETA
138 0x00e9: 0x03b9, # GREEK SMALL LETTER IOTA
139 0x00ea: 0x03be, # GREEK SMALL LETTER XI
140 0x00eb: 0x03ba, # GREEK SMALL LETTER KAPPA
141 0x00ec: 0x03bb, # GREEK SMALL LETTER LAMDA
142 0x00ed: 0x03bc, # GREEK SMALL LETTER MU
143 0x00ee: 0x03bd, # GREEK SMALL LETTER NU
144 0x00ef: 0x03bf, # GREEK SMALL LETTER OMICRON
145 0x00f0: 0x03c0, # GREEK SMALL LETTER PI
146 0x00f1: 0x03ce, # GREEK SMALL LETTER OMEGA WITH TONOS
147 0x00f2: 0x03c1, # GREEK SMALL LETTER RHO
148 0x00f3: 0x03c3, # GREEK SMALL LETTER SIGMA
149 0x00f4: 0x03c4, # GREEK SMALL LETTER TAU
150 0x00f5: 0x03b8, # GREEK SMALL LETTER THETA
151 0x00f6: 0x03c9, # GREEK SMALL LETTER OMEGA
152 0x00f7: 0x03c2, # GREEK SMALL LETTER FINAL SIGMA
153 0x00f8: 0x03c7, # GREEK SMALL LETTER CHI
154 0x00f9: 0x03c5, # GREEK SMALL LETTER UPSILON
155 0x00fa: 0x03b6, # GREEK SMALL LETTER ZETA
156 0x00fb: 0x03ca, # GREEK SMALL LETTER IOTA WITH DIALYTIKA
157 0x00fc: 0x03cb, # GREEK SMALL LETTER UPSILON WITH DIALYTIKA
158 0x00fd: 0x0390, # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND TONOS
159 0x00fe: 0x03b0, # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND TONOS
160 0x00ff: 0x00ad, # SOFT HYPHEN # before Mac OS 9.2.2, was undefined
Marc-André Lemburga866df82001-01-03 21:29:14 +0000161})
Guido van Rossum0229bf62000-03-10 23:17:24 +0000162
Marc-André Lemburga1129f42005-10-21 13:49:12 +0000163### Decoding Table
164
165decoding_table = (
166 u'\x00' # 0x0000 -> CONTROL CHARACTER
167 u'\x01' # 0x0001 -> CONTROL CHARACTER
168 u'\x02' # 0x0002 -> CONTROL CHARACTER
169 u'\x03' # 0x0003 -> CONTROL CHARACTER
170 u'\x04' # 0x0004 -> CONTROL CHARACTER
171 u'\x05' # 0x0005 -> CONTROL CHARACTER
172 u'\x06' # 0x0006 -> CONTROL CHARACTER
173 u'\x07' # 0x0007 -> CONTROL CHARACTER
174 u'\x08' # 0x0008 -> CONTROL CHARACTER
175 u'\t' # 0x0009 -> CONTROL CHARACTER
176 u'\n' # 0x000a -> CONTROL CHARACTER
177 u'\x0b' # 0x000b -> CONTROL CHARACTER
178 u'\x0c' # 0x000c -> CONTROL CHARACTER
179 u'\r' # 0x000d -> CONTROL CHARACTER
180 u'\x0e' # 0x000e -> CONTROL CHARACTER
181 u'\x0f' # 0x000f -> CONTROL CHARACTER
182 u'\x10' # 0x0010 -> CONTROL CHARACTER
183 u'\x11' # 0x0011 -> CONTROL CHARACTER
184 u'\x12' # 0x0012 -> CONTROL CHARACTER
185 u'\x13' # 0x0013 -> CONTROL CHARACTER
186 u'\x14' # 0x0014 -> CONTROL CHARACTER
187 u'\x15' # 0x0015 -> CONTROL CHARACTER
188 u'\x16' # 0x0016 -> CONTROL CHARACTER
189 u'\x17' # 0x0017 -> CONTROL CHARACTER
190 u'\x18' # 0x0018 -> CONTROL CHARACTER
191 u'\x19' # 0x0019 -> CONTROL CHARACTER
192 u'\x1a' # 0x001a -> CONTROL CHARACTER
193 u'\x1b' # 0x001b -> CONTROL CHARACTER
194 u'\x1c' # 0x001c -> CONTROL CHARACTER
195 u'\x1d' # 0x001d -> CONTROL CHARACTER
196 u'\x1e' # 0x001e -> CONTROL CHARACTER
197 u'\x1f' # 0x001f -> CONTROL CHARACTER
198 u' ' # 0x0020 -> SPACE
199 u'!' # 0x0021 -> EXCLAMATION MARK
200 u'"' # 0x0022 -> QUOTATION MARK
201 u'#' # 0x0023 -> NUMBER SIGN
202 u'$' # 0x0024 -> DOLLAR SIGN
203 u'%' # 0x0025 -> PERCENT SIGN
204 u'&' # 0x0026 -> AMPERSAND
205 u"'" # 0x0027 -> APOSTROPHE
206 u'(' # 0x0028 -> LEFT PARENTHESIS
207 u')' # 0x0029 -> RIGHT PARENTHESIS
208 u'*' # 0x002a -> ASTERISK
209 u'+' # 0x002b -> PLUS SIGN
210 u',' # 0x002c -> COMMA
211 u'-' # 0x002d -> HYPHEN-MINUS
212 u'.' # 0x002e -> FULL STOP
213 u'/' # 0x002f -> SOLIDUS
214 u'0' # 0x0030 -> DIGIT ZERO
215 u'1' # 0x0031 -> DIGIT ONE
216 u'2' # 0x0032 -> DIGIT TWO
217 u'3' # 0x0033 -> DIGIT THREE
218 u'4' # 0x0034 -> DIGIT FOUR
219 u'5' # 0x0035 -> DIGIT FIVE
220 u'6' # 0x0036 -> DIGIT SIX
221 u'7' # 0x0037 -> DIGIT SEVEN
222 u'8' # 0x0038 -> DIGIT EIGHT
223 u'9' # 0x0039 -> DIGIT NINE
224 u':' # 0x003a -> COLON
225 u';' # 0x003b -> SEMICOLON
226 u'<' # 0x003c -> LESS-THAN SIGN
227 u'=' # 0x003d -> EQUALS SIGN
228 u'>' # 0x003e -> GREATER-THAN SIGN
229 u'?' # 0x003f -> QUESTION MARK
230 u'@' # 0x0040 -> COMMERCIAL AT
231 u'A' # 0x0041 -> LATIN CAPITAL LETTER A
232 u'B' # 0x0042 -> LATIN CAPITAL LETTER B
233 u'C' # 0x0043 -> LATIN CAPITAL LETTER C
234 u'D' # 0x0044 -> LATIN CAPITAL LETTER D
235 u'E' # 0x0045 -> LATIN CAPITAL LETTER E
236 u'F' # 0x0046 -> LATIN CAPITAL LETTER F
237 u'G' # 0x0047 -> LATIN CAPITAL LETTER G
238 u'H' # 0x0048 -> LATIN CAPITAL LETTER H
239 u'I' # 0x0049 -> LATIN CAPITAL LETTER I
240 u'J' # 0x004a -> LATIN CAPITAL LETTER J
241 u'K' # 0x004b -> LATIN CAPITAL LETTER K
242 u'L' # 0x004c -> LATIN CAPITAL LETTER L
243 u'M' # 0x004d -> LATIN CAPITAL LETTER M
244 u'N' # 0x004e -> LATIN CAPITAL LETTER N
245 u'O' # 0x004f -> LATIN CAPITAL LETTER O
246 u'P' # 0x0050 -> LATIN CAPITAL LETTER P
247 u'Q' # 0x0051 -> LATIN CAPITAL LETTER Q
248 u'R' # 0x0052 -> LATIN CAPITAL LETTER R
249 u'S' # 0x0053 -> LATIN CAPITAL LETTER S
250 u'T' # 0x0054 -> LATIN CAPITAL LETTER T
251 u'U' # 0x0055 -> LATIN CAPITAL LETTER U
252 u'V' # 0x0056 -> LATIN CAPITAL LETTER V
253 u'W' # 0x0057 -> LATIN CAPITAL LETTER W
254 u'X' # 0x0058 -> LATIN CAPITAL LETTER X
255 u'Y' # 0x0059 -> LATIN CAPITAL LETTER Y
256 u'Z' # 0x005a -> LATIN CAPITAL LETTER Z
257 u'[' # 0x005b -> LEFT SQUARE BRACKET
258 u'\\' # 0x005c -> REVERSE SOLIDUS
259 u']' # 0x005d -> RIGHT SQUARE BRACKET
260 u'^' # 0x005e -> CIRCUMFLEX ACCENT
261 u'_' # 0x005f -> LOW LINE
262 u'`' # 0x0060 -> GRAVE ACCENT
263 u'a' # 0x0061 -> LATIN SMALL LETTER A
264 u'b' # 0x0062 -> LATIN SMALL LETTER B
265 u'c' # 0x0063 -> LATIN SMALL LETTER C
266 u'd' # 0x0064 -> LATIN SMALL LETTER D
267 u'e' # 0x0065 -> LATIN SMALL LETTER E
268 u'f' # 0x0066 -> LATIN SMALL LETTER F
269 u'g' # 0x0067 -> LATIN SMALL LETTER G
270 u'h' # 0x0068 -> LATIN SMALL LETTER H
271 u'i' # 0x0069 -> LATIN SMALL LETTER I
272 u'j' # 0x006a -> LATIN SMALL LETTER J
273 u'k' # 0x006b -> LATIN SMALL LETTER K
274 u'l' # 0x006c -> LATIN SMALL LETTER L
275 u'm' # 0x006d -> LATIN SMALL LETTER M
276 u'n' # 0x006e -> LATIN SMALL LETTER N
277 u'o' # 0x006f -> LATIN SMALL LETTER O
278 u'p' # 0x0070 -> LATIN SMALL LETTER P
279 u'q' # 0x0071 -> LATIN SMALL LETTER Q
280 u'r' # 0x0072 -> LATIN SMALL LETTER R
281 u's' # 0x0073 -> LATIN SMALL LETTER S
282 u't' # 0x0074 -> LATIN SMALL LETTER T
283 u'u' # 0x0075 -> LATIN SMALL LETTER U
284 u'v' # 0x0076 -> LATIN SMALL LETTER V
285 u'w' # 0x0077 -> LATIN SMALL LETTER W
286 u'x' # 0x0078 -> LATIN SMALL LETTER X
287 u'y' # 0x0079 -> LATIN SMALL LETTER Y
288 u'z' # 0x007a -> LATIN SMALL LETTER Z
289 u'{' # 0x007b -> LEFT CURLY BRACKET
290 u'|' # 0x007c -> VERTICAL LINE
291 u'}' # 0x007d -> RIGHT CURLY BRACKET
292 u'~' # 0x007e -> TILDE
293 u'\x7f' # 0x007f -> CONTROL CHARACTER
294 u'\xc4' # 0x0080 -> LATIN CAPITAL LETTER A WITH DIAERESIS
295 u'\xb9' # 0x0081 -> SUPERSCRIPT ONE
296 u'\xb2' # 0x0082 -> SUPERSCRIPT TWO
297 u'\xc9' # 0x0083 -> LATIN CAPITAL LETTER E WITH ACUTE
298 u'\xb3' # 0x0084 -> SUPERSCRIPT THREE
299 u'\xd6' # 0x0085 -> LATIN CAPITAL LETTER O WITH DIAERESIS
300 u'\xdc' # 0x0086 -> LATIN CAPITAL LETTER U WITH DIAERESIS
301 u'\u0385' # 0x0087 -> GREEK DIALYTIKA TONOS
302 u'\xe0' # 0x0088 -> LATIN SMALL LETTER A WITH GRAVE
303 u'\xe2' # 0x0089 -> LATIN SMALL LETTER A WITH CIRCUMFLEX
304 u'\xe4' # 0x008a -> LATIN SMALL LETTER A WITH DIAERESIS
305 u'\u0384' # 0x008b -> GREEK TONOS
306 u'\xa8' # 0x008c -> DIAERESIS
307 u'\xe7' # 0x008d -> LATIN SMALL LETTER C WITH CEDILLA
308 u'\xe9' # 0x008e -> LATIN SMALL LETTER E WITH ACUTE
309 u'\xe8' # 0x008f -> LATIN SMALL LETTER E WITH GRAVE
310 u'\xea' # 0x0090 -> LATIN SMALL LETTER E WITH CIRCUMFLEX
311 u'\xeb' # 0x0091 -> LATIN SMALL LETTER E WITH DIAERESIS
312 u'\xa3' # 0x0092 -> POUND SIGN
313 u'\u2122' # 0x0093 -> TRADE MARK SIGN
314 u'\xee' # 0x0094 -> LATIN SMALL LETTER I WITH CIRCUMFLEX
315 u'\xef' # 0x0095 -> LATIN SMALL LETTER I WITH DIAERESIS
316 u'\u2022' # 0x0096 -> BULLET
317 u'\xbd' # 0x0097 -> VULGAR FRACTION ONE HALF
318 u'\u2030' # 0x0098 -> PER MILLE SIGN
319 u'\xf4' # 0x0099 -> LATIN SMALL LETTER O WITH CIRCUMFLEX
320 u'\xf6' # 0x009a -> LATIN SMALL LETTER O WITH DIAERESIS
321 u'\xa6' # 0x009b -> BROKEN BAR
322 u'\u20ac' # 0x009c -> EURO SIGN # before Mac OS 9.2.2, was SOFT HYPHEN
323 u'\xf9' # 0x009d -> LATIN SMALL LETTER U WITH GRAVE
324 u'\xfb' # 0x009e -> LATIN SMALL LETTER U WITH CIRCUMFLEX
325 u'\xfc' # 0x009f -> LATIN SMALL LETTER U WITH DIAERESIS
326 u'\u2020' # 0x00a0 -> DAGGER
327 u'\u0393' # 0x00a1 -> GREEK CAPITAL LETTER GAMMA
328 u'\u0394' # 0x00a2 -> GREEK CAPITAL LETTER DELTA
329 u'\u0398' # 0x00a3 -> GREEK CAPITAL LETTER THETA
330 u'\u039b' # 0x00a4 -> GREEK CAPITAL LETTER LAMDA
331 u'\u039e' # 0x00a5 -> GREEK CAPITAL LETTER XI
332 u'\u03a0' # 0x00a6 -> GREEK CAPITAL LETTER PI
333 u'\xdf' # 0x00a7 -> LATIN SMALL LETTER SHARP S
334 u'\xae' # 0x00a8 -> REGISTERED SIGN
335 u'\xa9' # 0x00a9 -> COPYRIGHT SIGN
336 u'\u03a3' # 0x00aa -> GREEK CAPITAL LETTER SIGMA
337 u'\u03aa' # 0x00ab -> GREEK CAPITAL LETTER IOTA WITH DIALYTIKA
338 u'\xa7' # 0x00ac -> SECTION SIGN
339 u'\u2260' # 0x00ad -> NOT EQUAL TO
340 u'\xb0' # 0x00ae -> DEGREE SIGN
341 u'\xb7' # 0x00af -> MIDDLE DOT
342 u'\u0391' # 0x00b0 -> GREEK CAPITAL LETTER ALPHA
343 u'\xb1' # 0x00b1 -> PLUS-MINUS SIGN
344 u'\u2264' # 0x00b2 -> LESS-THAN OR EQUAL TO
345 u'\u2265' # 0x00b3 -> GREATER-THAN OR EQUAL TO
346 u'\xa5' # 0x00b4 -> YEN SIGN
347 u'\u0392' # 0x00b5 -> GREEK CAPITAL LETTER BETA
348 u'\u0395' # 0x00b6 -> GREEK CAPITAL LETTER EPSILON
349 u'\u0396' # 0x00b7 -> GREEK CAPITAL LETTER ZETA
350 u'\u0397' # 0x00b8 -> GREEK CAPITAL LETTER ETA
351 u'\u0399' # 0x00b9 -> GREEK CAPITAL LETTER IOTA
352 u'\u039a' # 0x00ba -> GREEK CAPITAL LETTER KAPPA
353 u'\u039c' # 0x00bb -> GREEK CAPITAL LETTER MU
354 u'\u03a6' # 0x00bc -> GREEK CAPITAL LETTER PHI
355 u'\u03ab' # 0x00bd -> GREEK CAPITAL LETTER UPSILON WITH DIALYTIKA
356 u'\u03a8' # 0x00be -> GREEK CAPITAL LETTER PSI
357 u'\u03a9' # 0x00bf -> GREEK CAPITAL LETTER OMEGA
358 u'\u03ac' # 0x00c0 -> GREEK SMALL LETTER ALPHA WITH TONOS
359 u'\u039d' # 0x00c1 -> GREEK CAPITAL LETTER NU
360 u'\xac' # 0x00c2 -> NOT SIGN
361 u'\u039f' # 0x00c3 -> GREEK CAPITAL LETTER OMICRON
362 u'\u03a1' # 0x00c4 -> GREEK CAPITAL LETTER RHO
363 u'\u2248' # 0x00c5 -> ALMOST EQUAL TO
364 u'\u03a4' # 0x00c6 -> GREEK CAPITAL LETTER TAU
365 u'\xab' # 0x00c7 -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
366 u'\xbb' # 0x00c8 -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
367 u'\u2026' # 0x00c9 -> HORIZONTAL ELLIPSIS
368 u'\xa0' # 0x00ca -> NO-BREAK SPACE
369 u'\u03a5' # 0x00cb -> GREEK CAPITAL LETTER UPSILON
370 u'\u03a7' # 0x00cc -> GREEK CAPITAL LETTER CHI
371 u'\u0386' # 0x00cd -> GREEK CAPITAL LETTER ALPHA WITH TONOS
372 u'\u0388' # 0x00ce -> GREEK CAPITAL LETTER EPSILON WITH TONOS
373 u'\u0153' # 0x00cf -> LATIN SMALL LIGATURE OE
374 u'\u2013' # 0x00d0 -> EN DASH
375 u'\u2015' # 0x00d1 -> HORIZONTAL BAR
376 u'\u201c' # 0x00d2 -> LEFT DOUBLE QUOTATION MARK
377 u'\u201d' # 0x00d3 -> RIGHT DOUBLE QUOTATION MARK
378 u'\u2018' # 0x00d4 -> LEFT SINGLE QUOTATION MARK
379 u'\u2019' # 0x00d5 -> RIGHT SINGLE QUOTATION MARK
380 u'\xf7' # 0x00d6 -> DIVISION SIGN
381 u'\u0389' # 0x00d7 -> GREEK CAPITAL LETTER ETA WITH TONOS
382 u'\u038a' # 0x00d8 -> GREEK CAPITAL LETTER IOTA WITH TONOS
383 u'\u038c' # 0x00d9 -> GREEK CAPITAL LETTER OMICRON WITH TONOS
384 u'\u038e' # 0x00da -> GREEK CAPITAL LETTER UPSILON WITH TONOS
385 u'\u03ad' # 0x00db -> GREEK SMALL LETTER EPSILON WITH TONOS
386 u'\u03ae' # 0x00dc -> GREEK SMALL LETTER ETA WITH TONOS
387 u'\u03af' # 0x00dd -> GREEK SMALL LETTER IOTA WITH TONOS
388 u'\u03cc' # 0x00de -> GREEK SMALL LETTER OMICRON WITH TONOS
389 u'\u038f' # 0x00df -> GREEK CAPITAL LETTER OMEGA WITH TONOS
390 u'\u03cd' # 0x00e0 -> GREEK SMALL LETTER UPSILON WITH TONOS
391 u'\u03b1' # 0x00e1 -> GREEK SMALL LETTER ALPHA
392 u'\u03b2' # 0x00e2 -> GREEK SMALL LETTER BETA
393 u'\u03c8' # 0x00e3 -> GREEK SMALL LETTER PSI
394 u'\u03b4' # 0x00e4 -> GREEK SMALL LETTER DELTA
395 u'\u03b5' # 0x00e5 -> GREEK SMALL LETTER EPSILON
396 u'\u03c6' # 0x00e6 -> GREEK SMALL LETTER PHI
397 u'\u03b3' # 0x00e7 -> GREEK SMALL LETTER GAMMA
398 u'\u03b7' # 0x00e8 -> GREEK SMALL LETTER ETA
399 u'\u03b9' # 0x00e9 -> GREEK SMALL LETTER IOTA
400 u'\u03be' # 0x00ea -> GREEK SMALL LETTER XI
401 u'\u03ba' # 0x00eb -> GREEK SMALL LETTER KAPPA
402 u'\u03bb' # 0x00ec -> GREEK SMALL LETTER LAMDA
403 u'\u03bc' # 0x00ed -> GREEK SMALL LETTER MU
404 u'\u03bd' # 0x00ee -> GREEK SMALL LETTER NU
405 u'\u03bf' # 0x00ef -> GREEK SMALL LETTER OMICRON
406 u'\u03c0' # 0x00f0 -> GREEK SMALL LETTER PI
407 u'\u03ce' # 0x00f1 -> GREEK SMALL LETTER OMEGA WITH TONOS
408 u'\u03c1' # 0x00f2 -> GREEK SMALL LETTER RHO
409 u'\u03c3' # 0x00f3 -> GREEK SMALL LETTER SIGMA
410 u'\u03c4' # 0x00f4 -> GREEK SMALL LETTER TAU
411 u'\u03b8' # 0x00f5 -> GREEK SMALL LETTER THETA
412 u'\u03c9' # 0x00f6 -> GREEK SMALL LETTER OMEGA
413 u'\u03c2' # 0x00f7 -> GREEK SMALL LETTER FINAL SIGMA
414 u'\u03c7' # 0x00f8 -> GREEK SMALL LETTER CHI
415 u'\u03c5' # 0x00f9 -> GREEK SMALL LETTER UPSILON
416 u'\u03b6' # 0x00fa -> GREEK SMALL LETTER ZETA
417 u'\u03ca' # 0x00fb -> GREEK SMALL LETTER IOTA WITH DIALYTIKA
418 u'\u03cb' # 0x00fc -> GREEK SMALL LETTER UPSILON WITH DIALYTIKA
419 u'\u0390' # 0x00fd -> GREEK SMALL LETTER IOTA WITH DIALYTIKA AND TONOS
420 u'\u03b0' # 0x00fe -> GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND TONOS
421 u'\xad' # 0x00ff -> SOFT HYPHEN # before Mac OS 9.2.2, was undefined
422)
423
Guido van Rossum0229bf62000-03-10 23:17:24 +0000424### Encoding Map
425
Marc-André Lemburga1129f42005-10-21 13:49:12 +0000426encoding_map = {
427 0x0000: 0x0000, # CONTROL CHARACTER
428 0x0001: 0x0001, # CONTROL CHARACTER
429 0x0002: 0x0002, # CONTROL CHARACTER
430 0x0003: 0x0003, # CONTROL CHARACTER
431 0x0004: 0x0004, # CONTROL CHARACTER
432 0x0005: 0x0005, # CONTROL CHARACTER
433 0x0006: 0x0006, # CONTROL CHARACTER
434 0x0007: 0x0007, # CONTROL CHARACTER
435 0x0008: 0x0008, # CONTROL CHARACTER
436 0x0009: 0x0009, # CONTROL CHARACTER
437 0x000a: 0x000a, # CONTROL CHARACTER
438 0x000b: 0x000b, # CONTROL CHARACTER
439 0x000c: 0x000c, # CONTROL CHARACTER
440 0x000d: 0x000d, # CONTROL CHARACTER
441 0x000e: 0x000e, # CONTROL CHARACTER
442 0x000f: 0x000f, # CONTROL CHARACTER
443 0x0010: 0x0010, # CONTROL CHARACTER
444 0x0011: 0x0011, # CONTROL CHARACTER
445 0x0012: 0x0012, # CONTROL CHARACTER
446 0x0013: 0x0013, # CONTROL CHARACTER
447 0x0014: 0x0014, # CONTROL CHARACTER
448 0x0015: 0x0015, # CONTROL CHARACTER
449 0x0016: 0x0016, # CONTROL CHARACTER
450 0x0017: 0x0017, # CONTROL CHARACTER
451 0x0018: 0x0018, # CONTROL CHARACTER
452 0x0019: 0x0019, # CONTROL CHARACTER
453 0x001a: 0x001a, # CONTROL CHARACTER
454 0x001b: 0x001b, # CONTROL CHARACTER
455 0x001c: 0x001c, # CONTROL CHARACTER
456 0x001d: 0x001d, # CONTROL CHARACTER
457 0x001e: 0x001e, # CONTROL CHARACTER
458 0x001f: 0x001f, # CONTROL CHARACTER
459 0x0020: 0x0020, # SPACE
460 0x0021: 0x0021, # EXCLAMATION MARK
461 0x0022: 0x0022, # QUOTATION MARK
462 0x0023: 0x0023, # NUMBER SIGN
463 0x0024: 0x0024, # DOLLAR SIGN
464 0x0025: 0x0025, # PERCENT SIGN
465 0x0026: 0x0026, # AMPERSAND
466 0x0027: 0x0027, # APOSTROPHE
467 0x0028: 0x0028, # LEFT PARENTHESIS
468 0x0029: 0x0029, # RIGHT PARENTHESIS
469 0x002a: 0x002a, # ASTERISK
470 0x002b: 0x002b, # PLUS SIGN
471 0x002c: 0x002c, # COMMA
472 0x002d: 0x002d, # HYPHEN-MINUS
473 0x002e: 0x002e, # FULL STOP
474 0x002f: 0x002f, # SOLIDUS
475 0x0030: 0x0030, # DIGIT ZERO
476 0x0031: 0x0031, # DIGIT ONE
477 0x0032: 0x0032, # DIGIT TWO
478 0x0033: 0x0033, # DIGIT THREE
479 0x0034: 0x0034, # DIGIT FOUR
480 0x0035: 0x0035, # DIGIT FIVE
481 0x0036: 0x0036, # DIGIT SIX
482 0x0037: 0x0037, # DIGIT SEVEN
483 0x0038: 0x0038, # DIGIT EIGHT
484 0x0039: 0x0039, # DIGIT NINE
485 0x003a: 0x003a, # COLON
486 0x003b: 0x003b, # SEMICOLON
487 0x003c: 0x003c, # LESS-THAN SIGN
488 0x003d: 0x003d, # EQUALS SIGN
489 0x003e: 0x003e, # GREATER-THAN SIGN
490 0x003f: 0x003f, # QUESTION MARK
491 0x0040: 0x0040, # COMMERCIAL AT
492 0x0041: 0x0041, # LATIN CAPITAL LETTER A
493 0x0042: 0x0042, # LATIN CAPITAL LETTER B
494 0x0043: 0x0043, # LATIN CAPITAL LETTER C
495 0x0044: 0x0044, # LATIN CAPITAL LETTER D
496 0x0045: 0x0045, # LATIN CAPITAL LETTER E
497 0x0046: 0x0046, # LATIN CAPITAL LETTER F
498 0x0047: 0x0047, # LATIN CAPITAL LETTER G
499 0x0048: 0x0048, # LATIN CAPITAL LETTER H
500 0x0049: 0x0049, # LATIN CAPITAL LETTER I
501 0x004a: 0x004a, # LATIN CAPITAL LETTER J
502 0x004b: 0x004b, # LATIN CAPITAL LETTER K
503 0x004c: 0x004c, # LATIN CAPITAL LETTER L
504 0x004d: 0x004d, # LATIN CAPITAL LETTER M
505 0x004e: 0x004e, # LATIN CAPITAL LETTER N
506 0x004f: 0x004f, # LATIN CAPITAL LETTER O
507 0x0050: 0x0050, # LATIN CAPITAL LETTER P
508 0x0051: 0x0051, # LATIN CAPITAL LETTER Q
509 0x0052: 0x0052, # LATIN CAPITAL LETTER R
510 0x0053: 0x0053, # LATIN CAPITAL LETTER S
511 0x0054: 0x0054, # LATIN CAPITAL LETTER T
512 0x0055: 0x0055, # LATIN CAPITAL LETTER U
513 0x0056: 0x0056, # LATIN CAPITAL LETTER V
514 0x0057: 0x0057, # LATIN CAPITAL LETTER W
515 0x0058: 0x0058, # LATIN CAPITAL LETTER X
516 0x0059: 0x0059, # LATIN CAPITAL LETTER Y
517 0x005a: 0x005a, # LATIN CAPITAL LETTER Z
518 0x005b: 0x005b, # LEFT SQUARE BRACKET
519 0x005c: 0x005c, # REVERSE SOLIDUS
520 0x005d: 0x005d, # RIGHT SQUARE BRACKET
521 0x005e: 0x005e, # CIRCUMFLEX ACCENT
522 0x005f: 0x005f, # LOW LINE
523 0x0060: 0x0060, # GRAVE ACCENT
524 0x0061: 0x0061, # LATIN SMALL LETTER A
525 0x0062: 0x0062, # LATIN SMALL LETTER B
526 0x0063: 0x0063, # LATIN SMALL LETTER C
527 0x0064: 0x0064, # LATIN SMALL LETTER D
528 0x0065: 0x0065, # LATIN SMALL LETTER E
529 0x0066: 0x0066, # LATIN SMALL LETTER F
530 0x0067: 0x0067, # LATIN SMALL LETTER G
531 0x0068: 0x0068, # LATIN SMALL LETTER H
532 0x0069: 0x0069, # LATIN SMALL LETTER I
533 0x006a: 0x006a, # LATIN SMALL LETTER J
534 0x006b: 0x006b, # LATIN SMALL LETTER K
535 0x006c: 0x006c, # LATIN SMALL LETTER L
536 0x006d: 0x006d, # LATIN SMALL LETTER M
537 0x006e: 0x006e, # LATIN SMALL LETTER N
538 0x006f: 0x006f, # LATIN SMALL LETTER O
539 0x0070: 0x0070, # LATIN SMALL LETTER P
540 0x0071: 0x0071, # LATIN SMALL LETTER Q
541 0x0072: 0x0072, # LATIN SMALL LETTER R
542 0x0073: 0x0073, # LATIN SMALL LETTER S
543 0x0074: 0x0074, # LATIN SMALL LETTER T
544 0x0075: 0x0075, # LATIN SMALL LETTER U
545 0x0076: 0x0076, # LATIN SMALL LETTER V
546 0x0077: 0x0077, # LATIN SMALL LETTER W
547 0x0078: 0x0078, # LATIN SMALL LETTER X
548 0x0079: 0x0079, # LATIN SMALL LETTER Y
549 0x007a: 0x007a, # LATIN SMALL LETTER Z
550 0x007b: 0x007b, # LEFT CURLY BRACKET
551 0x007c: 0x007c, # VERTICAL LINE
552 0x007d: 0x007d, # RIGHT CURLY BRACKET
553 0x007e: 0x007e, # TILDE
554 0x007f: 0x007f, # CONTROL CHARACTER
555 0x00a0: 0x00ca, # NO-BREAK SPACE
556 0x00a3: 0x0092, # POUND SIGN
557 0x00a5: 0x00b4, # YEN SIGN
558 0x00a6: 0x009b, # BROKEN BAR
559 0x00a7: 0x00ac, # SECTION SIGN
560 0x00a8: 0x008c, # DIAERESIS
561 0x00a9: 0x00a9, # COPYRIGHT SIGN
562 0x00ab: 0x00c7, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
563 0x00ac: 0x00c2, # NOT SIGN
564 0x00ad: 0x00ff, # SOFT HYPHEN # before Mac OS 9.2.2, was undefined
565 0x00ae: 0x00a8, # REGISTERED SIGN
566 0x00b0: 0x00ae, # DEGREE SIGN
567 0x00b1: 0x00b1, # PLUS-MINUS SIGN
568 0x00b2: 0x0082, # SUPERSCRIPT TWO
569 0x00b3: 0x0084, # SUPERSCRIPT THREE
570 0x00b7: 0x00af, # MIDDLE DOT
571 0x00b9: 0x0081, # SUPERSCRIPT ONE
572 0x00bb: 0x00c8, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
573 0x00bd: 0x0097, # VULGAR FRACTION ONE HALF
574 0x00c4: 0x0080, # LATIN CAPITAL LETTER A WITH DIAERESIS
575 0x00c9: 0x0083, # LATIN CAPITAL LETTER E WITH ACUTE
576 0x00d6: 0x0085, # LATIN CAPITAL LETTER O WITH DIAERESIS
577 0x00dc: 0x0086, # LATIN CAPITAL LETTER U WITH DIAERESIS
578 0x00df: 0x00a7, # LATIN SMALL LETTER SHARP S
579 0x00e0: 0x0088, # LATIN SMALL LETTER A WITH GRAVE
580 0x00e2: 0x0089, # LATIN SMALL LETTER A WITH CIRCUMFLEX
581 0x00e4: 0x008a, # LATIN SMALL LETTER A WITH DIAERESIS
582 0x00e7: 0x008d, # LATIN SMALL LETTER C WITH CEDILLA
583 0x00e8: 0x008f, # LATIN SMALL LETTER E WITH GRAVE
584 0x00e9: 0x008e, # LATIN SMALL LETTER E WITH ACUTE
585 0x00ea: 0x0090, # LATIN SMALL LETTER E WITH CIRCUMFLEX
586 0x00eb: 0x0091, # LATIN SMALL LETTER E WITH DIAERESIS
587 0x00ee: 0x0094, # LATIN SMALL LETTER I WITH CIRCUMFLEX
588 0x00ef: 0x0095, # LATIN SMALL LETTER I WITH DIAERESIS
589 0x00f4: 0x0099, # LATIN SMALL LETTER O WITH CIRCUMFLEX
590 0x00f6: 0x009a, # LATIN SMALL LETTER O WITH DIAERESIS
591 0x00f7: 0x00d6, # DIVISION SIGN
592 0x00f9: 0x009d, # LATIN SMALL LETTER U WITH GRAVE
593 0x00fb: 0x009e, # LATIN SMALL LETTER U WITH CIRCUMFLEX
594 0x00fc: 0x009f, # LATIN SMALL LETTER U WITH DIAERESIS
595 0x0153: 0x00cf, # LATIN SMALL LIGATURE OE
596 0x0384: 0x008b, # GREEK TONOS
597 0x0385: 0x0087, # GREEK DIALYTIKA TONOS
598 0x0386: 0x00cd, # GREEK CAPITAL LETTER ALPHA WITH TONOS
599 0x0388: 0x00ce, # GREEK CAPITAL LETTER EPSILON WITH TONOS
600 0x0389: 0x00d7, # GREEK CAPITAL LETTER ETA WITH TONOS
601 0x038a: 0x00d8, # GREEK CAPITAL LETTER IOTA WITH TONOS
602 0x038c: 0x00d9, # GREEK CAPITAL LETTER OMICRON WITH TONOS
603 0x038e: 0x00da, # GREEK CAPITAL LETTER UPSILON WITH TONOS
604 0x038f: 0x00df, # GREEK CAPITAL LETTER OMEGA WITH TONOS
605 0x0390: 0x00fd, # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND TONOS
606 0x0391: 0x00b0, # GREEK CAPITAL LETTER ALPHA
607 0x0392: 0x00b5, # GREEK CAPITAL LETTER BETA
608 0x0393: 0x00a1, # GREEK CAPITAL LETTER GAMMA
609 0x0394: 0x00a2, # GREEK CAPITAL LETTER DELTA
610 0x0395: 0x00b6, # GREEK CAPITAL LETTER EPSILON
611 0x0396: 0x00b7, # GREEK CAPITAL LETTER ZETA
612 0x0397: 0x00b8, # GREEK CAPITAL LETTER ETA
613 0x0398: 0x00a3, # GREEK CAPITAL LETTER THETA
614 0x0399: 0x00b9, # GREEK CAPITAL LETTER IOTA
615 0x039a: 0x00ba, # GREEK CAPITAL LETTER KAPPA
616 0x039b: 0x00a4, # GREEK CAPITAL LETTER LAMDA
617 0x039c: 0x00bb, # GREEK CAPITAL LETTER MU
618 0x039d: 0x00c1, # GREEK CAPITAL LETTER NU
619 0x039e: 0x00a5, # GREEK CAPITAL LETTER XI
620 0x039f: 0x00c3, # GREEK CAPITAL LETTER OMICRON
621 0x03a0: 0x00a6, # GREEK CAPITAL LETTER PI
622 0x03a1: 0x00c4, # GREEK CAPITAL LETTER RHO
623 0x03a3: 0x00aa, # GREEK CAPITAL LETTER SIGMA
624 0x03a4: 0x00c6, # GREEK CAPITAL LETTER TAU
625 0x03a5: 0x00cb, # GREEK CAPITAL LETTER UPSILON
626 0x03a6: 0x00bc, # GREEK CAPITAL LETTER PHI
627 0x03a7: 0x00cc, # GREEK CAPITAL LETTER CHI
628 0x03a8: 0x00be, # GREEK CAPITAL LETTER PSI
629 0x03a9: 0x00bf, # GREEK CAPITAL LETTER OMEGA
630 0x03aa: 0x00ab, # GREEK CAPITAL LETTER IOTA WITH DIALYTIKA
631 0x03ab: 0x00bd, # GREEK CAPITAL LETTER UPSILON WITH DIALYTIKA
632 0x03ac: 0x00c0, # GREEK SMALL LETTER ALPHA WITH TONOS
633 0x03ad: 0x00db, # GREEK SMALL LETTER EPSILON WITH TONOS
634 0x03ae: 0x00dc, # GREEK SMALL LETTER ETA WITH TONOS
635 0x03af: 0x00dd, # GREEK SMALL LETTER IOTA WITH TONOS
636 0x03b0: 0x00fe, # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND TONOS
637 0x03b1: 0x00e1, # GREEK SMALL LETTER ALPHA
638 0x03b2: 0x00e2, # GREEK SMALL LETTER BETA
639 0x03b3: 0x00e7, # GREEK SMALL LETTER GAMMA
640 0x03b4: 0x00e4, # GREEK SMALL LETTER DELTA
641 0x03b5: 0x00e5, # GREEK SMALL LETTER EPSILON
642 0x03b6: 0x00fa, # GREEK SMALL LETTER ZETA
643 0x03b7: 0x00e8, # GREEK SMALL LETTER ETA
644 0x03b8: 0x00f5, # GREEK SMALL LETTER THETA
645 0x03b9: 0x00e9, # GREEK SMALL LETTER IOTA
646 0x03ba: 0x00eb, # GREEK SMALL LETTER KAPPA
647 0x03bb: 0x00ec, # GREEK SMALL LETTER LAMDA
648 0x03bc: 0x00ed, # GREEK SMALL LETTER MU
649 0x03bd: 0x00ee, # GREEK SMALL LETTER NU
650 0x03be: 0x00ea, # GREEK SMALL LETTER XI
651 0x03bf: 0x00ef, # GREEK SMALL LETTER OMICRON
652 0x03c0: 0x00f0, # GREEK SMALL LETTER PI
653 0x03c1: 0x00f2, # GREEK SMALL LETTER RHO
654 0x03c2: 0x00f7, # GREEK SMALL LETTER FINAL SIGMA
655 0x03c3: 0x00f3, # GREEK SMALL LETTER SIGMA
656 0x03c4: 0x00f4, # GREEK SMALL LETTER TAU
657 0x03c5: 0x00f9, # GREEK SMALL LETTER UPSILON
658 0x03c6: 0x00e6, # GREEK SMALL LETTER PHI
659 0x03c7: 0x00f8, # GREEK SMALL LETTER CHI
660 0x03c8: 0x00e3, # GREEK SMALL LETTER PSI
661 0x03c9: 0x00f6, # GREEK SMALL LETTER OMEGA
662 0x03ca: 0x00fb, # GREEK SMALL LETTER IOTA WITH DIALYTIKA
663 0x03cb: 0x00fc, # GREEK SMALL LETTER UPSILON WITH DIALYTIKA
664 0x03cc: 0x00de, # GREEK SMALL LETTER OMICRON WITH TONOS
665 0x03cd: 0x00e0, # GREEK SMALL LETTER UPSILON WITH TONOS
666 0x03ce: 0x00f1, # GREEK SMALL LETTER OMEGA WITH TONOS
667 0x2013: 0x00d0, # EN DASH
668 0x2015: 0x00d1, # HORIZONTAL BAR
669 0x2018: 0x00d4, # LEFT SINGLE QUOTATION MARK
670 0x2019: 0x00d5, # RIGHT SINGLE QUOTATION MARK
671 0x201c: 0x00d2, # LEFT DOUBLE QUOTATION MARK
672 0x201d: 0x00d3, # RIGHT DOUBLE QUOTATION MARK
673 0x2020: 0x00a0, # DAGGER
674 0x2022: 0x0096, # BULLET
675 0x2026: 0x00c9, # HORIZONTAL ELLIPSIS
676 0x2030: 0x0098, # PER MILLE SIGN
677 0x20ac: 0x009c, # EURO SIGN # before Mac OS 9.2.2, was SOFT HYPHEN
678 0x2122: 0x0093, # TRADE MARK SIGN
679 0x2248: 0x00c5, # ALMOST EQUAL TO
680 0x2260: 0x00ad, # NOT EQUAL TO
681 0x2264: 0x00b2, # LESS-THAN OR EQUAL TO
682 0x2265: 0x00b3, # GREATER-THAN OR EQUAL TO
683}