blob: 7ee2a71b4d90922bc8adb77cd7661981542b3937 [file] [log] [blame]
Marc-André Lemburg75c9e832005-10-21 13:58:32 +00001""" Python Character Mapping Codec generated from 'VENDORS/APPLE/CENTEURO.TXT' with gencodec.py.
2
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)
14
15 def decode(self,input,errors='strict'):
16
17 return codecs.charmap_decode(input,errors,decoding_table)
18
19class StreamWriter(Codec,codecs.StreamWriter):
20 pass
21
22class 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
33decoding_map = codecs.make_identity_dict(range(256))
34decoding_map.update({
35 0x0080: 0x00c4, # LATIN CAPITAL LETTER A WITH DIAERESIS
36 0x0081: 0x0100, # LATIN CAPITAL LETTER A WITH MACRON
37 0x0082: 0x0101, # LATIN SMALL LETTER A WITH MACRON
38 0x0083: 0x00c9, # LATIN CAPITAL LETTER E WITH ACUTE
39 0x0084: 0x0104, # LATIN CAPITAL LETTER A WITH OGONEK
40 0x0085: 0x00d6, # LATIN CAPITAL LETTER O WITH DIAERESIS
41 0x0086: 0x00dc, # LATIN CAPITAL LETTER U WITH DIAERESIS
42 0x0087: 0x00e1, # LATIN SMALL LETTER A WITH ACUTE
43 0x0088: 0x0105, # LATIN SMALL LETTER A WITH OGONEK
44 0x0089: 0x010c, # LATIN CAPITAL LETTER C WITH CARON
45 0x008a: 0x00e4, # LATIN SMALL LETTER A WITH DIAERESIS
46 0x008b: 0x010d, # LATIN SMALL LETTER C WITH CARON
47 0x008c: 0x0106, # LATIN CAPITAL LETTER C WITH ACUTE
48 0x008d: 0x0107, # LATIN SMALL LETTER C WITH ACUTE
49 0x008e: 0x00e9, # LATIN SMALL LETTER E WITH ACUTE
50 0x008f: 0x0179, # LATIN CAPITAL LETTER Z WITH ACUTE
51 0x0090: 0x017a, # LATIN SMALL LETTER Z WITH ACUTE
52 0x0091: 0x010e, # LATIN CAPITAL LETTER D WITH CARON
53 0x0092: 0x00ed, # LATIN SMALL LETTER I WITH ACUTE
54 0x0093: 0x010f, # LATIN SMALL LETTER D WITH CARON
55 0x0094: 0x0112, # LATIN CAPITAL LETTER E WITH MACRON
56 0x0095: 0x0113, # LATIN SMALL LETTER E WITH MACRON
57 0x0096: 0x0116, # LATIN CAPITAL LETTER E WITH DOT ABOVE
58 0x0097: 0x00f3, # LATIN SMALL LETTER O WITH ACUTE
59 0x0098: 0x0117, # LATIN SMALL LETTER E WITH DOT ABOVE
60 0x0099: 0x00f4, # LATIN SMALL LETTER O WITH CIRCUMFLEX
61 0x009a: 0x00f6, # LATIN SMALL LETTER O WITH DIAERESIS
62 0x009b: 0x00f5, # LATIN SMALL LETTER O WITH TILDE
63 0x009c: 0x00fa, # LATIN SMALL LETTER U WITH ACUTE
64 0x009d: 0x011a, # LATIN CAPITAL LETTER E WITH CARON
65 0x009e: 0x011b, # LATIN SMALL LETTER E WITH CARON
66 0x009f: 0x00fc, # LATIN SMALL LETTER U WITH DIAERESIS
67 0x00a0: 0x2020, # DAGGER
68 0x00a1: 0x00b0, # DEGREE SIGN
69 0x00a2: 0x0118, # LATIN CAPITAL LETTER E WITH OGONEK
70 0x00a4: 0x00a7, # SECTION SIGN
71 0x00a5: 0x2022, # BULLET
72 0x00a6: 0x00b6, # PILCROW SIGN
73 0x00a7: 0x00df, # LATIN SMALL LETTER SHARP S
74 0x00a8: 0x00ae, # REGISTERED SIGN
75 0x00aa: 0x2122, # TRADE MARK SIGN
76 0x00ab: 0x0119, # LATIN SMALL LETTER E WITH OGONEK
77 0x00ac: 0x00a8, # DIAERESIS
78 0x00ad: 0x2260, # NOT EQUAL TO
79 0x00ae: 0x0123, # LATIN SMALL LETTER G WITH CEDILLA
80 0x00af: 0x012e, # LATIN CAPITAL LETTER I WITH OGONEK
81 0x00b0: 0x012f, # LATIN SMALL LETTER I WITH OGONEK
82 0x00b1: 0x012a, # LATIN CAPITAL LETTER I WITH MACRON
83 0x00b2: 0x2264, # LESS-THAN OR EQUAL TO
84 0x00b3: 0x2265, # GREATER-THAN OR EQUAL TO
85 0x00b4: 0x012b, # LATIN SMALL LETTER I WITH MACRON
86 0x00b5: 0x0136, # LATIN CAPITAL LETTER K WITH CEDILLA
87 0x00b6: 0x2202, # PARTIAL DIFFERENTIAL
88 0x00b7: 0x2211, # N-ARY SUMMATION
89 0x00b8: 0x0142, # LATIN SMALL LETTER L WITH STROKE
90 0x00b9: 0x013b, # LATIN CAPITAL LETTER L WITH CEDILLA
91 0x00ba: 0x013c, # LATIN SMALL LETTER L WITH CEDILLA
92 0x00bb: 0x013d, # LATIN CAPITAL LETTER L WITH CARON
93 0x00bc: 0x013e, # LATIN SMALL LETTER L WITH CARON
94 0x00bd: 0x0139, # LATIN CAPITAL LETTER L WITH ACUTE
95 0x00be: 0x013a, # LATIN SMALL LETTER L WITH ACUTE
96 0x00bf: 0x0145, # LATIN CAPITAL LETTER N WITH CEDILLA
97 0x00c0: 0x0146, # LATIN SMALL LETTER N WITH CEDILLA
98 0x00c1: 0x0143, # LATIN CAPITAL LETTER N WITH ACUTE
99 0x00c2: 0x00ac, # NOT SIGN
100 0x00c3: 0x221a, # SQUARE ROOT
101 0x00c4: 0x0144, # LATIN SMALL LETTER N WITH ACUTE
102 0x00c5: 0x0147, # LATIN CAPITAL LETTER N WITH CARON
103 0x00c6: 0x2206, # INCREMENT
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: 0x0148, # LATIN SMALL LETTER N WITH CARON
109 0x00cc: 0x0150, # LATIN CAPITAL LETTER O WITH DOUBLE ACUTE
110 0x00cd: 0x00d5, # LATIN CAPITAL LETTER O WITH TILDE
111 0x00ce: 0x0151, # LATIN SMALL LETTER O WITH DOUBLE ACUTE
112 0x00cf: 0x014c, # LATIN CAPITAL LETTER O WITH MACRON
113 0x00d0: 0x2013, # EN DASH
114 0x00d1: 0x2014, # EM DASH
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: 0x25ca, # LOZENGE
121 0x00d8: 0x014d, # LATIN SMALL LETTER O WITH MACRON
122 0x00d9: 0x0154, # LATIN CAPITAL LETTER R WITH ACUTE
123 0x00da: 0x0155, # LATIN SMALL LETTER R WITH ACUTE
124 0x00db: 0x0158, # LATIN CAPITAL LETTER R WITH CARON
125 0x00dc: 0x2039, # SINGLE LEFT-POINTING ANGLE QUOTATION MARK
126 0x00dd: 0x203a, # SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
127 0x00de: 0x0159, # LATIN SMALL LETTER R WITH CARON
128 0x00df: 0x0156, # LATIN CAPITAL LETTER R WITH CEDILLA
129 0x00e0: 0x0157, # LATIN SMALL LETTER R WITH CEDILLA
130 0x00e1: 0x0160, # LATIN CAPITAL LETTER S WITH CARON
131 0x00e2: 0x201a, # SINGLE LOW-9 QUOTATION MARK
132 0x00e3: 0x201e, # DOUBLE LOW-9 QUOTATION MARK
133 0x00e4: 0x0161, # LATIN SMALL LETTER S WITH CARON
134 0x00e5: 0x015a, # LATIN CAPITAL LETTER S WITH ACUTE
135 0x00e6: 0x015b, # LATIN SMALL LETTER S WITH ACUTE
136 0x00e7: 0x00c1, # LATIN CAPITAL LETTER A WITH ACUTE
137 0x00e8: 0x0164, # LATIN CAPITAL LETTER T WITH CARON
138 0x00e9: 0x0165, # LATIN SMALL LETTER T WITH CARON
139 0x00ea: 0x00cd, # LATIN CAPITAL LETTER I WITH ACUTE
140 0x00eb: 0x017d, # LATIN CAPITAL LETTER Z WITH CARON
141 0x00ec: 0x017e, # LATIN SMALL LETTER Z WITH CARON
142 0x00ed: 0x016a, # LATIN CAPITAL LETTER U WITH MACRON
143 0x00ee: 0x00d3, # LATIN CAPITAL LETTER O WITH ACUTE
144 0x00ef: 0x00d4, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX
145 0x00f0: 0x016b, # LATIN SMALL LETTER U WITH MACRON
146 0x00f1: 0x016e, # LATIN CAPITAL LETTER U WITH RING ABOVE
147 0x00f2: 0x00da, # LATIN CAPITAL LETTER U WITH ACUTE
148 0x00f3: 0x016f, # LATIN SMALL LETTER U WITH RING ABOVE
149 0x00f4: 0x0170, # LATIN CAPITAL LETTER U WITH DOUBLE ACUTE
150 0x00f5: 0x0171, # LATIN SMALL LETTER U WITH DOUBLE ACUTE
151 0x00f6: 0x0172, # LATIN CAPITAL LETTER U WITH OGONEK
152 0x00f7: 0x0173, # LATIN SMALL LETTER U WITH OGONEK
153 0x00f8: 0x00dd, # LATIN CAPITAL LETTER Y WITH ACUTE
154 0x00f9: 0x00fd, # LATIN SMALL LETTER Y WITH ACUTE
155 0x00fa: 0x0137, # LATIN SMALL LETTER K WITH CEDILLA
156 0x00fb: 0x017b, # LATIN CAPITAL LETTER Z WITH DOT ABOVE
157 0x00fc: 0x0141, # LATIN CAPITAL LETTER L WITH STROKE
158 0x00fd: 0x017c, # LATIN SMALL LETTER Z WITH DOT ABOVE
159 0x00fe: 0x0122, # LATIN CAPITAL LETTER G WITH CEDILLA
160 0x00ff: 0x02c7, # CARON
161})
162
163### 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'\u0100' # 0x0081 -> LATIN CAPITAL LETTER A WITH MACRON
296 u'\u0101' # 0x0082 -> LATIN SMALL LETTER A WITH MACRON
297 u'\xc9' # 0x0083 -> LATIN CAPITAL LETTER E WITH ACUTE
298 u'\u0104' # 0x0084 -> LATIN CAPITAL LETTER A WITH OGONEK
299 u'\xd6' # 0x0085 -> LATIN CAPITAL LETTER O WITH DIAERESIS
300 u'\xdc' # 0x0086 -> LATIN CAPITAL LETTER U WITH DIAERESIS
301 u'\xe1' # 0x0087 -> LATIN SMALL LETTER A WITH ACUTE
302 u'\u0105' # 0x0088 -> LATIN SMALL LETTER A WITH OGONEK
303 u'\u010c' # 0x0089 -> LATIN CAPITAL LETTER C WITH CARON
304 u'\xe4' # 0x008a -> LATIN SMALL LETTER A WITH DIAERESIS
305 u'\u010d' # 0x008b -> LATIN SMALL LETTER C WITH CARON
306 u'\u0106' # 0x008c -> LATIN CAPITAL LETTER C WITH ACUTE
307 u'\u0107' # 0x008d -> LATIN SMALL LETTER C WITH ACUTE
308 u'\xe9' # 0x008e -> LATIN SMALL LETTER E WITH ACUTE
309 u'\u0179' # 0x008f -> LATIN CAPITAL LETTER Z WITH ACUTE
310 u'\u017a' # 0x0090 -> LATIN SMALL LETTER Z WITH ACUTE
311 u'\u010e' # 0x0091 -> LATIN CAPITAL LETTER D WITH CARON
312 u'\xed' # 0x0092 -> LATIN SMALL LETTER I WITH ACUTE
313 u'\u010f' # 0x0093 -> LATIN SMALL LETTER D WITH CARON
314 u'\u0112' # 0x0094 -> LATIN CAPITAL LETTER E WITH MACRON
315 u'\u0113' # 0x0095 -> LATIN SMALL LETTER E WITH MACRON
316 u'\u0116' # 0x0096 -> LATIN CAPITAL LETTER E WITH DOT ABOVE
317 u'\xf3' # 0x0097 -> LATIN SMALL LETTER O WITH ACUTE
318 u'\u0117' # 0x0098 -> LATIN SMALL LETTER E WITH DOT ABOVE
319 u'\xf4' # 0x0099 -> LATIN SMALL LETTER O WITH CIRCUMFLEX
320 u'\xf6' # 0x009a -> LATIN SMALL LETTER O WITH DIAERESIS
321 u'\xf5' # 0x009b -> LATIN SMALL LETTER O WITH TILDE
322 u'\xfa' # 0x009c -> LATIN SMALL LETTER U WITH ACUTE
323 u'\u011a' # 0x009d -> LATIN CAPITAL LETTER E WITH CARON
324 u'\u011b' # 0x009e -> LATIN SMALL LETTER E WITH CARON
325 u'\xfc' # 0x009f -> LATIN SMALL LETTER U WITH DIAERESIS
326 u'\u2020' # 0x00a0 -> DAGGER
327 u'\xb0' # 0x00a1 -> DEGREE SIGN
328 u'\u0118' # 0x00a2 -> LATIN CAPITAL LETTER E WITH OGONEK
329 u'\xa3' # 0x00a3 -> POUND SIGN
330 u'\xa7' # 0x00a4 -> SECTION SIGN
331 u'\u2022' # 0x00a5 -> BULLET
332 u'\xb6' # 0x00a6 -> PILCROW SIGN
333 u'\xdf' # 0x00a7 -> LATIN SMALL LETTER SHARP S
334 u'\xae' # 0x00a8 -> REGISTERED SIGN
335 u'\xa9' # 0x00a9 -> COPYRIGHT SIGN
336 u'\u2122' # 0x00aa -> TRADE MARK SIGN
337 u'\u0119' # 0x00ab -> LATIN SMALL LETTER E WITH OGONEK
338 u'\xa8' # 0x00ac -> DIAERESIS
339 u'\u2260' # 0x00ad -> NOT EQUAL TO
340 u'\u0123' # 0x00ae -> LATIN SMALL LETTER G WITH CEDILLA
341 u'\u012e' # 0x00af -> LATIN CAPITAL LETTER I WITH OGONEK
342 u'\u012f' # 0x00b0 -> LATIN SMALL LETTER I WITH OGONEK
343 u'\u012a' # 0x00b1 -> LATIN CAPITAL LETTER I WITH MACRON
344 u'\u2264' # 0x00b2 -> LESS-THAN OR EQUAL TO
345 u'\u2265' # 0x00b3 -> GREATER-THAN OR EQUAL TO
346 u'\u012b' # 0x00b4 -> LATIN SMALL LETTER I WITH MACRON
347 u'\u0136' # 0x00b5 -> LATIN CAPITAL LETTER K WITH CEDILLA
348 u'\u2202' # 0x00b6 -> PARTIAL DIFFERENTIAL
349 u'\u2211' # 0x00b7 -> N-ARY SUMMATION
350 u'\u0142' # 0x00b8 -> LATIN SMALL LETTER L WITH STROKE
351 u'\u013b' # 0x00b9 -> LATIN CAPITAL LETTER L WITH CEDILLA
352 u'\u013c' # 0x00ba -> LATIN SMALL LETTER L WITH CEDILLA
353 u'\u013d' # 0x00bb -> LATIN CAPITAL LETTER L WITH CARON
354 u'\u013e' # 0x00bc -> LATIN SMALL LETTER L WITH CARON
355 u'\u0139' # 0x00bd -> LATIN CAPITAL LETTER L WITH ACUTE
356 u'\u013a' # 0x00be -> LATIN SMALL LETTER L WITH ACUTE
357 u'\u0145' # 0x00bf -> LATIN CAPITAL LETTER N WITH CEDILLA
358 u'\u0146' # 0x00c0 -> LATIN SMALL LETTER N WITH CEDILLA
359 u'\u0143' # 0x00c1 -> LATIN CAPITAL LETTER N WITH ACUTE
360 u'\xac' # 0x00c2 -> NOT SIGN
361 u'\u221a' # 0x00c3 -> SQUARE ROOT
362 u'\u0144' # 0x00c4 -> LATIN SMALL LETTER N WITH ACUTE
363 u'\u0147' # 0x00c5 -> LATIN CAPITAL LETTER N WITH CARON
364 u'\u2206' # 0x00c6 -> INCREMENT
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'\u0148' # 0x00cb -> LATIN SMALL LETTER N WITH CARON
370 u'\u0150' # 0x00cc -> LATIN CAPITAL LETTER O WITH DOUBLE ACUTE
371 u'\xd5' # 0x00cd -> LATIN CAPITAL LETTER O WITH TILDE
372 u'\u0151' # 0x00ce -> LATIN SMALL LETTER O WITH DOUBLE ACUTE
373 u'\u014c' # 0x00cf -> LATIN CAPITAL LETTER O WITH MACRON
374 u'\u2013' # 0x00d0 -> EN DASH
375 u'\u2014' # 0x00d1 -> EM DASH
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'\u25ca' # 0x00d7 -> LOZENGE
382 u'\u014d' # 0x00d8 -> LATIN SMALL LETTER O WITH MACRON
383 u'\u0154' # 0x00d9 -> LATIN CAPITAL LETTER R WITH ACUTE
384 u'\u0155' # 0x00da -> LATIN SMALL LETTER R WITH ACUTE
385 u'\u0158' # 0x00db -> LATIN CAPITAL LETTER R WITH CARON
386 u'\u2039' # 0x00dc -> SINGLE LEFT-POINTING ANGLE QUOTATION MARK
387 u'\u203a' # 0x00dd -> SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
388 u'\u0159' # 0x00de -> LATIN SMALL LETTER R WITH CARON
389 u'\u0156' # 0x00df -> LATIN CAPITAL LETTER R WITH CEDILLA
390 u'\u0157' # 0x00e0 -> LATIN SMALL LETTER R WITH CEDILLA
391 u'\u0160' # 0x00e1 -> LATIN CAPITAL LETTER S WITH CARON
392 u'\u201a' # 0x00e2 -> SINGLE LOW-9 QUOTATION MARK
393 u'\u201e' # 0x00e3 -> DOUBLE LOW-9 QUOTATION MARK
394 u'\u0161' # 0x00e4 -> LATIN SMALL LETTER S WITH CARON
395 u'\u015a' # 0x00e5 -> LATIN CAPITAL LETTER S WITH ACUTE
396 u'\u015b' # 0x00e6 -> LATIN SMALL LETTER S WITH ACUTE
397 u'\xc1' # 0x00e7 -> LATIN CAPITAL LETTER A WITH ACUTE
398 u'\u0164' # 0x00e8 -> LATIN CAPITAL LETTER T WITH CARON
399 u'\u0165' # 0x00e9 -> LATIN SMALL LETTER T WITH CARON
400 u'\xcd' # 0x00ea -> LATIN CAPITAL LETTER I WITH ACUTE
401 u'\u017d' # 0x00eb -> LATIN CAPITAL LETTER Z WITH CARON
402 u'\u017e' # 0x00ec -> LATIN SMALL LETTER Z WITH CARON
403 u'\u016a' # 0x00ed -> LATIN CAPITAL LETTER U WITH MACRON
404 u'\xd3' # 0x00ee -> LATIN CAPITAL LETTER O WITH ACUTE
405 u'\xd4' # 0x00ef -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX
406 u'\u016b' # 0x00f0 -> LATIN SMALL LETTER U WITH MACRON
407 u'\u016e' # 0x00f1 -> LATIN CAPITAL LETTER U WITH RING ABOVE
408 u'\xda' # 0x00f2 -> LATIN CAPITAL LETTER U WITH ACUTE
409 u'\u016f' # 0x00f3 -> LATIN SMALL LETTER U WITH RING ABOVE
410 u'\u0170' # 0x00f4 -> LATIN CAPITAL LETTER U WITH DOUBLE ACUTE
411 u'\u0171' # 0x00f5 -> LATIN SMALL LETTER U WITH DOUBLE ACUTE
412 u'\u0172' # 0x00f6 -> LATIN CAPITAL LETTER U WITH OGONEK
413 u'\u0173' # 0x00f7 -> LATIN SMALL LETTER U WITH OGONEK
414 u'\xdd' # 0x00f8 -> LATIN CAPITAL LETTER Y WITH ACUTE
415 u'\xfd' # 0x00f9 -> LATIN SMALL LETTER Y WITH ACUTE
416 u'\u0137' # 0x00fa -> LATIN SMALL LETTER K WITH CEDILLA
417 u'\u017b' # 0x00fb -> LATIN CAPITAL LETTER Z WITH DOT ABOVE
418 u'\u0141' # 0x00fc -> LATIN CAPITAL LETTER L WITH STROKE
419 u'\u017c' # 0x00fd -> LATIN SMALL LETTER Z WITH DOT ABOVE
420 u'\u0122' # 0x00fe -> LATIN CAPITAL LETTER G WITH CEDILLA
421 u'\u02c7' # 0x00ff -> CARON
422)
423
424### Encoding Map
425
426encoding_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: 0x00a3, # POUND SIGN
557 0x00a7: 0x00a4, # SECTION SIGN
558 0x00a8: 0x00ac, # DIAERESIS
559 0x00a9: 0x00a9, # COPYRIGHT SIGN
560 0x00ab: 0x00c7, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
561 0x00ac: 0x00c2, # NOT SIGN
562 0x00ae: 0x00a8, # REGISTERED SIGN
563 0x00b0: 0x00a1, # DEGREE SIGN
564 0x00b6: 0x00a6, # PILCROW SIGN
565 0x00bb: 0x00c8, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
566 0x00c1: 0x00e7, # LATIN CAPITAL LETTER A WITH ACUTE
567 0x00c4: 0x0080, # LATIN CAPITAL LETTER A WITH DIAERESIS
568 0x00c9: 0x0083, # LATIN CAPITAL LETTER E WITH ACUTE
569 0x00cd: 0x00ea, # LATIN CAPITAL LETTER I WITH ACUTE
570 0x00d3: 0x00ee, # LATIN CAPITAL LETTER O WITH ACUTE
571 0x00d4: 0x00ef, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX
572 0x00d5: 0x00cd, # LATIN CAPITAL LETTER O WITH TILDE
573 0x00d6: 0x0085, # LATIN CAPITAL LETTER O WITH DIAERESIS
574 0x00da: 0x00f2, # LATIN CAPITAL LETTER U WITH ACUTE
575 0x00dc: 0x0086, # LATIN CAPITAL LETTER U WITH DIAERESIS
576 0x00dd: 0x00f8, # LATIN CAPITAL LETTER Y WITH ACUTE
577 0x00df: 0x00a7, # LATIN SMALL LETTER SHARP S
578 0x00e1: 0x0087, # LATIN SMALL LETTER A WITH ACUTE
579 0x00e4: 0x008a, # LATIN SMALL LETTER A WITH DIAERESIS
580 0x00e9: 0x008e, # LATIN SMALL LETTER E WITH ACUTE
581 0x00ed: 0x0092, # LATIN SMALL LETTER I WITH ACUTE
582 0x00f3: 0x0097, # LATIN SMALL LETTER O WITH ACUTE
583 0x00f4: 0x0099, # LATIN SMALL LETTER O WITH CIRCUMFLEX
584 0x00f5: 0x009b, # LATIN SMALL LETTER O WITH TILDE
585 0x00f6: 0x009a, # LATIN SMALL LETTER O WITH DIAERESIS
586 0x00f7: 0x00d6, # DIVISION SIGN
587 0x00fa: 0x009c, # LATIN SMALL LETTER U WITH ACUTE
588 0x00fc: 0x009f, # LATIN SMALL LETTER U WITH DIAERESIS
589 0x00fd: 0x00f9, # LATIN SMALL LETTER Y WITH ACUTE
590 0x0100: 0x0081, # LATIN CAPITAL LETTER A WITH MACRON
591 0x0101: 0x0082, # LATIN SMALL LETTER A WITH MACRON
592 0x0104: 0x0084, # LATIN CAPITAL LETTER A WITH OGONEK
593 0x0105: 0x0088, # LATIN SMALL LETTER A WITH OGONEK
594 0x0106: 0x008c, # LATIN CAPITAL LETTER C WITH ACUTE
595 0x0107: 0x008d, # LATIN SMALL LETTER C WITH ACUTE
596 0x010c: 0x0089, # LATIN CAPITAL LETTER C WITH CARON
597 0x010d: 0x008b, # LATIN SMALL LETTER C WITH CARON
598 0x010e: 0x0091, # LATIN CAPITAL LETTER D WITH CARON
599 0x010f: 0x0093, # LATIN SMALL LETTER D WITH CARON
600 0x0112: 0x0094, # LATIN CAPITAL LETTER E WITH MACRON
601 0x0113: 0x0095, # LATIN SMALL LETTER E WITH MACRON
602 0x0116: 0x0096, # LATIN CAPITAL LETTER E WITH DOT ABOVE
603 0x0117: 0x0098, # LATIN SMALL LETTER E WITH DOT ABOVE
604 0x0118: 0x00a2, # LATIN CAPITAL LETTER E WITH OGONEK
605 0x0119: 0x00ab, # LATIN SMALL LETTER E WITH OGONEK
606 0x011a: 0x009d, # LATIN CAPITAL LETTER E WITH CARON
607 0x011b: 0x009e, # LATIN SMALL LETTER E WITH CARON
608 0x0122: 0x00fe, # LATIN CAPITAL LETTER G WITH CEDILLA
609 0x0123: 0x00ae, # LATIN SMALL LETTER G WITH CEDILLA
610 0x012a: 0x00b1, # LATIN CAPITAL LETTER I WITH MACRON
611 0x012b: 0x00b4, # LATIN SMALL LETTER I WITH MACRON
612 0x012e: 0x00af, # LATIN CAPITAL LETTER I WITH OGONEK
613 0x012f: 0x00b0, # LATIN SMALL LETTER I WITH OGONEK
614 0x0136: 0x00b5, # LATIN CAPITAL LETTER K WITH CEDILLA
615 0x0137: 0x00fa, # LATIN SMALL LETTER K WITH CEDILLA
616 0x0139: 0x00bd, # LATIN CAPITAL LETTER L WITH ACUTE
617 0x013a: 0x00be, # LATIN SMALL LETTER L WITH ACUTE
618 0x013b: 0x00b9, # LATIN CAPITAL LETTER L WITH CEDILLA
619 0x013c: 0x00ba, # LATIN SMALL LETTER L WITH CEDILLA
620 0x013d: 0x00bb, # LATIN CAPITAL LETTER L WITH CARON
621 0x013e: 0x00bc, # LATIN SMALL LETTER L WITH CARON
622 0x0141: 0x00fc, # LATIN CAPITAL LETTER L WITH STROKE
623 0x0142: 0x00b8, # LATIN SMALL LETTER L WITH STROKE
624 0x0143: 0x00c1, # LATIN CAPITAL LETTER N WITH ACUTE
625 0x0144: 0x00c4, # LATIN SMALL LETTER N WITH ACUTE
626 0x0145: 0x00bf, # LATIN CAPITAL LETTER N WITH CEDILLA
627 0x0146: 0x00c0, # LATIN SMALL LETTER N WITH CEDILLA
628 0x0147: 0x00c5, # LATIN CAPITAL LETTER N WITH CARON
629 0x0148: 0x00cb, # LATIN SMALL LETTER N WITH CARON
630 0x014c: 0x00cf, # LATIN CAPITAL LETTER O WITH MACRON
631 0x014d: 0x00d8, # LATIN SMALL LETTER O WITH MACRON
632 0x0150: 0x00cc, # LATIN CAPITAL LETTER O WITH DOUBLE ACUTE
633 0x0151: 0x00ce, # LATIN SMALL LETTER O WITH DOUBLE ACUTE
634 0x0154: 0x00d9, # LATIN CAPITAL LETTER R WITH ACUTE
635 0x0155: 0x00da, # LATIN SMALL LETTER R WITH ACUTE
636 0x0156: 0x00df, # LATIN CAPITAL LETTER R WITH CEDILLA
637 0x0157: 0x00e0, # LATIN SMALL LETTER R WITH CEDILLA
638 0x0158: 0x00db, # LATIN CAPITAL LETTER R WITH CARON
639 0x0159: 0x00de, # LATIN SMALL LETTER R WITH CARON
640 0x015a: 0x00e5, # LATIN CAPITAL LETTER S WITH ACUTE
641 0x015b: 0x00e6, # LATIN SMALL LETTER S WITH ACUTE
642 0x0160: 0x00e1, # LATIN CAPITAL LETTER S WITH CARON
643 0x0161: 0x00e4, # LATIN SMALL LETTER S WITH CARON
644 0x0164: 0x00e8, # LATIN CAPITAL LETTER T WITH CARON
645 0x0165: 0x00e9, # LATIN SMALL LETTER T WITH CARON
646 0x016a: 0x00ed, # LATIN CAPITAL LETTER U WITH MACRON
647 0x016b: 0x00f0, # LATIN SMALL LETTER U WITH MACRON
648 0x016e: 0x00f1, # LATIN CAPITAL LETTER U WITH RING ABOVE
649 0x016f: 0x00f3, # LATIN SMALL LETTER U WITH RING ABOVE
650 0x0170: 0x00f4, # LATIN CAPITAL LETTER U WITH DOUBLE ACUTE
651 0x0171: 0x00f5, # LATIN SMALL LETTER U WITH DOUBLE ACUTE
652 0x0172: 0x00f6, # LATIN CAPITAL LETTER U WITH OGONEK
653 0x0173: 0x00f7, # LATIN SMALL LETTER U WITH OGONEK
654 0x0179: 0x008f, # LATIN CAPITAL LETTER Z WITH ACUTE
655 0x017a: 0x0090, # LATIN SMALL LETTER Z WITH ACUTE
656 0x017b: 0x00fb, # LATIN CAPITAL LETTER Z WITH DOT ABOVE
657 0x017c: 0x00fd, # LATIN SMALL LETTER Z WITH DOT ABOVE
658 0x017d: 0x00eb, # LATIN CAPITAL LETTER Z WITH CARON
659 0x017e: 0x00ec, # LATIN SMALL LETTER Z WITH CARON
660 0x02c7: 0x00ff, # CARON
661 0x2013: 0x00d0, # EN DASH
662 0x2014: 0x00d1, # EM DASH
663 0x2018: 0x00d4, # LEFT SINGLE QUOTATION MARK
664 0x2019: 0x00d5, # RIGHT SINGLE QUOTATION MARK
665 0x201a: 0x00e2, # SINGLE LOW-9 QUOTATION MARK
666 0x201c: 0x00d2, # LEFT DOUBLE QUOTATION MARK
667 0x201d: 0x00d3, # RIGHT DOUBLE QUOTATION MARK
668 0x201e: 0x00e3, # DOUBLE LOW-9 QUOTATION MARK
669 0x2020: 0x00a0, # DAGGER
670 0x2022: 0x00a5, # BULLET
671 0x2026: 0x00c9, # HORIZONTAL ELLIPSIS
672 0x2039: 0x00dc, # SINGLE LEFT-POINTING ANGLE QUOTATION MARK
673 0x203a: 0x00dd, # SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
674 0x2122: 0x00aa, # TRADE MARK SIGN
675 0x2202: 0x00b6, # PARTIAL DIFFERENTIAL
676 0x2206: 0x00c6, # INCREMENT
677 0x2211: 0x00b7, # N-ARY SUMMATION
678 0x221a: 0x00c3, # SQUARE ROOT
679 0x2260: 0x00ad, # NOT EQUAL TO
680 0x2264: 0x00b2, # LESS-THAN OR EQUAL TO
681 0x2265: 0x00b3, # GREATER-THAN OR EQUAL TO
682 0x25ca: 0x00d7, # LOZENGE
683}