1010
1111class Codec (codecs .Codec ):
1212 def encode (self ,input ,errors = 'strict' ):
13- return codecs .charmap_encode (input ,errors ,encoding_map )
13+ return codecs .charmap_encode (input ,errors ,encoding_table )
1414
1515 def decode (self ,input ,errors = 'strict' ):
16- return codecs .charmap_decode (input ,errors ,decoding_map )
16+ return codecs .charmap_decode (input ,errors ,decoding_table )
1717
1818class IncrementalEncoder (codecs .IncrementalEncoder ):
1919 def encode (self , input , final = False ):
20- return codecs .charmap_encode (input ,self .errors ,encoding_map )[0 ]
20+ return codecs .charmap_encode (input ,self .errors ,encoding_table )[0 ]
2121
2222class IncrementalDecoder (codecs .IncrementalDecoder ):
2323 def decode (self , input , final = False ):
24- return codecs .charmap_decode (input ,self .errors ,decoding_map )[0 ]
24+ return codecs .charmap_decode (input ,self .errors ,decoding_table )[0 ]
2525
2626class StreamWriter (Codec ,codecs .StreamWriter ):
2727 pass
@@ -42,42 +42,268 @@ def getregentry():
4242 streamwriter = StreamWriter ,
4343 )
4444
45- ### Decoding Map
46-
47- decoding_map = codecs .make_identity_dict (range (256 ))
48-
49- # The PalmOS character set is mostly iso-8859-1 with some differences.
50- decoding_map .update ({
51- 0x0080 : 0x20ac , # EURO SIGN
52- 0x0082 : 0x201a , # SINGLE LOW-9 QUOTATION MARK
53- 0x0083 : 0x0192 , # LATIN SMALL LETTER F WITH HOOK
54- 0x0084 : 0x201e , # DOUBLE LOW-9 QUOTATION MARK
55- 0x0085 : 0x2026 , # HORIZONTAL ELLIPSIS
56- 0x0086 : 0x2020 , # DAGGER
57- 0x0087 : 0x2021 , # DOUBLE DAGGER
58- 0x0088 : 0x02c6 , # MODIFIER LETTER CIRCUMFLEX ACCENT
59- 0x0089 : 0x2030 , # PER MILLE SIGN
60- 0x008a : 0x0160 , # LATIN CAPITAL LETTER S WITH CARON
61- 0x008b : 0x2039 , # SINGLE LEFT-POINTING ANGLE QUOTATION MARK
62- 0x008c : 0x0152 , # LATIN CAPITAL LIGATURE OE
63- 0x008d : 0x2666 , # BLACK DIAMOND SUIT
64- 0x008e : 0x2663 , # BLACK CLUB SUIT
65- 0x008f : 0x2665 , # BLACK HEART SUIT
66- 0x0090 : 0x2660 , # BLACK SPADE SUIT
67- 0x0091 : 0x2018 , # LEFT SINGLE QUOTATION MARK
68- 0x0092 : 0x2019 , # RIGHT SINGLE QUOTATION MARK
69- 0x0093 : 0x201c , # LEFT DOUBLE QUOTATION MARK
70- 0x0094 : 0x201d , # RIGHT DOUBLE QUOTATION MARK
71- 0x0095 : 0x2022 , # BULLET
72- 0x0096 : 0x2013 , # EN DASH
73- 0x0097 : 0x2014 , # EM DASH
74- 0x0098 : 0x02dc , # SMALL TILDE
75- 0x0099 : 0x2122 , # TRADE MARK SIGN
76- 0x009a : 0x0161 , # LATIN SMALL LETTER S WITH CARON
77- 0x009c : 0x0153 , # LATIN SMALL LIGATURE OE
78- 0x009f : 0x0178 , # LATIN CAPITAL LETTER Y WITH DIAERESIS
79- })
80-
81- ### Encoding Map
82-
83- encoding_map = codecs .make_encoding_map (decoding_map )
45+
46+ ### Decoding Table
47+
48+ decoding_table = (
49+ '\x00 ' # 0x00 -> NULL
50+ '\x01 ' # 0x01 -> START OF HEADING
51+ '\x02 ' # 0x02 -> START OF TEXT
52+ '\x03 ' # 0x03 -> END OF TEXT
53+ '\x04 ' # 0x04 -> END OF TRANSMISSION
54+ '\x05 ' # 0x05 -> ENQUIRY
55+ '\x06 ' # 0x06 -> ACKNOWLEDGE
56+ '\x07 ' # 0x07 -> BELL
57+ '\x08 ' # 0x08 -> BACKSPACE
58+ '\t ' # 0x09 -> HORIZONTAL TABULATION
59+ '\n ' # 0x0A -> LINE FEED
60+ '\x0b ' # 0x0B -> VERTICAL TABULATION
61+ '\x0c ' # 0x0C -> FORM FEED
62+ '\r ' # 0x0D -> CARRIAGE RETURN
63+ '\x0e ' # 0x0E -> SHIFT OUT
64+ '\x0f ' # 0x0F -> SHIFT IN
65+ '\x10 ' # 0x10 -> DATA LINK ESCAPE
66+ '\x11 ' # 0x11 -> DEVICE CONTROL ONE
67+ '\x12 ' # 0x12 -> DEVICE CONTROL TWO
68+ '\x13 ' # 0x13 -> DEVICE CONTROL THREE
69+ '\x14 ' # 0x14 -> DEVICE CONTROL FOUR
70+ '\x15 ' # 0x15 -> NEGATIVE ACKNOWLEDGE
71+ '\x16 ' # 0x16 -> SYNCHRONOUS IDLE
72+ '\x17 ' # 0x17 -> END OF TRANSMISSION BLOCK
73+ '\x18 ' # 0x18 -> CANCEL
74+ '\x19 ' # 0x19 -> END OF MEDIUM
75+ '\x1a ' # 0x1A -> SUBSTITUTE
76+ '\x1b ' # 0x1B -> ESCAPE
77+ '\x1c ' # 0x1C -> FILE SEPARATOR
78+ '\x1d ' # 0x1D -> GROUP SEPARATOR
79+ '\x1e ' # 0x1E -> RECORD SEPARATOR
80+ '\x1f ' # 0x1F -> UNIT SEPARATOR
81+ ' ' # 0x20 -> SPACE
82+ '!' # 0x21 -> EXCLAMATION MARK
83+ '"' # 0x22 -> QUOTATION MARK
84+ '#' # 0x23 -> NUMBER SIGN
85+ '$' # 0x24 -> DOLLAR SIGN
86+ '%' # 0x25 -> PERCENT SIGN
87+ '&' # 0x26 -> AMPERSAND
88+ "'" # 0x27 -> APOSTROPHE
89+ '(' # 0x28 -> LEFT PARENTHESIS
90+ ')' # 0x29 -> RIGHT PARENTHESIS
91+ '*' # 0x2A -> ASTERISK
92+ '+' # 0x2B -> PLUS SIGN
93+ ',' # 0x2C -> COMMA
94+ '-' # 0x2D -> HYPHEN-MINUS
95+ '.' # 0x2E -> FULL STOP
96+ '/' # 0x2F -> SOLIDUS
97+ '0' # 0x30 -> DIGIT ZERO
98+ '1' # 0x31 -> DIGIT ONE
99+ '2' # 0x32 -> DIGIT TWO
100+ '3' # 0x33 -> DIGIT THREE
101+ '4' # 0x34 -> DIGIT FOUR
102+ '5' # 0x35 -> DIGIT FIVE
103+ '6' # 0x36 -> DIGIT SIX
104+ '7' # 0x37 -> DIGIT SEVEN
105+ '8' # 0x38 -> DIGIT EIGHT
106+ '9' # 0x39 -> DIGIT NINE
107+ ':' # 0x3A -> COLON
108+ ';' # 0x3B -> SEMICOLON
109+ '<' # 0x3C -> LESS-THAN SIGN
110+ '=' # 0x3D -> EQUALS SIGN
111+ '>' # 0x3E -> GREATER-THAN SIGN
112+ '?' # 0x3F -> QUESTION MARK
113+ '@' # 0x40 -> COMMERCIAL AT
114+ 'A' # 0x41 -> LATIN CAPITAL LETTER A
115+ 'B' # 0x42 -> LATIN CAPITAL LETTER B
116+ 'C' # 0x43 -> LATIN CAPITAL LETTER C
117+ 'D' # 0x44 -> LATIN CAPITAL LETTER D
118+ 'E' # 0x45 -> LATIN CAPITAL LETTER E
119+ 'F' # 0x46 -> LATIN CAPITAL LETTER F
120+ 'G' # 0x47 -> LATIN CAPITAL LETTER G
121+ 'H' # 0x48 -> LATIN CAPITAL LETTER H
122+ 'I' # 0x49 -> LATIN CAPITAL LETTER I
123+ 'J' # 0x4A -> LATIN CAPITAL LETTER J
124+ 'K' # 0x4B -> LATIN CAPITAL LETTER K
125+ 'L' # 0x4C -> LATIN CAPITAL LETTER L
126+ 'M' # 0x4D -> LATIN CAPITAL LETTER M
127+ 'N' # 0x4E -> LATIN CAPITAL LETTER N
128+ 'O' # 0x4F -> LATIN CAPITAL LETTER O
129+ 'P' # 0x50 -> LATIN CAPITAL LETTER P
130+ 'Q' # 0x51 -> LATIN CAPITAL LETTER Q
131+ 'R' # 0x52 -> LATIN CAPITAL LETTER R
132+ 'S' # 0x53 -> LATIN CAPITAL LETTER S
133+ 'T' # 0x54 -> LATIN CAPITAL LETTER T
134+ 'U' # 0x55 -> LATIN CAPITAL LETTER U
135+ 'V' # 0x56 -> LATIN CAPITAL LETTER V
136+ 'W' # 0x57 -> LATIN CAPITAL LETTER W
137+ 'X' # 0x58 -> LATIN CAPITAL LETTER X
138+ 'Y' # 0x59 -> LATIN CAPITAL LETTER Y
139+ 'Z' # 0x5A -> LATIN CAPITAL LETTER Z
140+ '[' # 0x5B -> LEFT SQUARE BRACKET
141+ '\\ ' # 0x5C -> REVERSE SOLIDUS
142+ ']' # 0x5D -> RIGHT SQUARE BRACKET
143+ '^' # 0x5E -> CIRCUMFLEX ACCENT
144+ '_' # 0x5F -> LOW LINE
145+ '`' # 0x60 -> GRAVE ACCENT
146+ 'a' # 0x61 -> LATIN SMALL LETTER A
147+ 'b' # 0x62 -> LATIN SMALL LETTER B
148+ 'c' # 0x63 -> LATIN SMALL LETTER C
149+ 'd' # 0x64 -> LATIN SMALL LETTER D
150+ 'e' # 0x65 -> LATIN SMALL LETTER E
151+ 'f' # 0x66 -> LATIN SMALL LETTER F
152+ 'g' # 0x67 -> LATIN SMALL LETTER G
153+ 'h' # 0x68 -> LATIN SMALL LETTER H
154+ 'i' # 0x69 -> LATIN SMALL LETTER I
155+ 'j' # 0x6A -> LATIN SMALL LETTER J
156+ 'k' # 0x6B -> LATIN SMALL LETTER K
157+ 'l' # 0x6C -> LATIN SMALL LETTER L
158+ 'm' # 0x6D -> LATIN SMALL LETTER M
159+ 'n' # 0x6E -> LATIN SMALL LETTER N
160+ 'o' # 0x6F -> LATIN SMALL LETTER O
161+ 'p' # 0x70 -> LATIN SMALL LETTER P
162+ 'q' # 0x71 -> LATIN SMALL LETTER Q
163+ 'r' # 0x72 -> LATIN SMALL LETTER R
164+ 's' # 0x73 -> LATIN SMALL LETTER S
165+ 't' # 0x74 -> LATIN SMALL LETTER T
166+ 'u' # 0x75 -> LATIN SMALL LETTER U
167+ 'v' # 0x76 -> LATIN SMALL LETTER V
168+ 'w' # 0x77 -> LATIN SMALL LETTER W
169+ 'x' # 0x78 -> LATIN SMALL LETTER X
170+ 'y' # 0x79 -> LATIN SMALL LETTER Y
171+ 'z' # 0x7A -> LATIN SMALL LETTER Z
172+ '{' # 0x7B -> LEFT CURLY BRACKET
173+ '|' # 0x7C -> VERTICAL LINE
174+ '}' # 0x7D -> RIGHT CURLY BRACKET
175+ '~' # 0x7E -> TILDE
176+ '\x7f ' # 0x7F -> DELETE
177+ '\u20ac ' # 0x80 -> EURO SIGN
178+ '\x81 ' # 0x81 -> <control>
179+ '\u201a ' # 0x82 -> SINGLE LOW-9 QUOTATION MARK
180+ '\u0192 ' # 0x83 -> LATIN SMALL LETTER F WITH HOOK
181+ '\u201e ' # 0x84 -> DOUBLE LOW-9 QUOTATION MARK
182+ '\u2026 ' # 0x85 -> HORIZONTAL ELLIPSIS
183+ '\u2020 ' # 0x86 -> DAGGER
184+ '\u2021 ' # 0x87 -> DOUBLE DAGGER
185+ '\u02c6 ' # 0x88 -> MODIFIER LETTER CIRCUMFLEX ACCENT
186+ '\u2030 ' # 0x89 -> PER MILLE SIGN
187+ '\u0160 ' # 0x8A -> LATIN CAPITAL LETTER S WITH CARON
188+ '\u2039 ' # 0x8B -> SINGLE LEFT-POINTING ANGLE QUOTATION MARK
189+ '\u0152 ' # 0x8C -> LATIN CAPITAL LIGATURE OE
190+ '\u2666 ' # 0x8D -> BLACK DIAMOND SUIT
191+ '\u2663 ' # 0x8E -> BLACK CLUB SUIT
192+ '\u2665 ' # 0x8F -> BLACK HEART SUIT
193+ '\u2660 ' # 0x90 -> BLACK SPADE SUIT
194+ '\u2018 ' # 0x91 -> LEFT SINGLE QUOTATION MARK
195+ '\u2019 ' # 0x92 -> RIGHT SINGLE QUOTATION MARK
196+ '\u201c ' # 0x93 -> LEFT DOUBLE QUOTATION MARK
197+ '\u201d ' # 0x94 -> RIGHT DOUBLE QUOTATION MARK
198+ '\u2022 ' # 0x95 -> BULLET
199+ '\u2013 ' # 0x96 -> EN DASH
200+ '\u2014 ' # 0x97 -> EM DASH
201+ '\u02dc ' # 0x98 -> SMALL TILDE
202+ '\u2122 ' # 0x99 -> TRADE MARK SIGN
203+ '\u0161 ' # 0x9A -> LATIN SMALL LETTER S WITH CARON
204+ '\x9b ' # 0x9B -> <control>
205+ '\u0153 ' # 0x9C -> LATIN SMALL LIGATURE OE
206+ '\x9d ' # 0x9D -> <control>
207+ '\x9e ' # 0x9E -> <control>
208+ '\u0178 ' # 0x9F -> LATIN CAPITAL LETTER Y WITH DIAERESIS
209+ '\xa0 ' # 0xA0 -> NO-BREAK SPACE
210+ '\xa1 ' # 0xA1 -> INVERTED EXCLAMATION MARK
211+ '\xa2 ' # 0xA2 -> CENT SIGN
212+ '\xa3 ' # 0xA3 -> POUND SIGN
213+ '\xa4 ' # 0xA4 -> CURRENCY SIGN
214+ '\xa5 ' # 0xA5 -> YEN SIGN
215+ '\xa6 ' # 0xA6 -> BROKEN BAR
216+ '\xa7 ' # 0xA7 -> SECTION SIGN
217+ '\xa8 ' # 0xA8 -> DIAERESIS
218+ '\xa9 ' # 0xA9 -> COPYRIGHT SIGN
219+ '\xaa ' # 0xAA -> FEMININE ORDINAL INDICATOR
220+ '\xab ' # 0xAB -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
221+ '\xac ' # 0xAC -> NOT SIGN
222+ '\xad ' # 0xAD -> SOFT HYPHEN
223+ '\xae ' # 0xAE -> REGISTERED SIGN
224+ '\xaf ' # 0xAF -> MACRON
225+ '\xb0 ' # 0xB0 -> DEGREE SIGN
226+ '\xb1 ' # 0xB1 -> PLUS-MINUS SIGN
227+ '\xb2 ' # 0xB2 -> SUPERSCRIPT TWO
228+ '\xb3 ' # 0xB3 -> SUPERSCRIPT THREE
229+ '\xb4 ' # 0xB4 -> ACUTE ACCENT
230+ '\xb5 ' # 0xB5 -> MICRO SIGN
231+ '\xb6 ' # 0xB6 -> PILCROW SIGN
232+ '\xb7 ' # 0xB7 -> MIDDLE DOT
233+ '\xb8 ' # 0xB8 -> CEDILLA
234+ '\xb9 ' # 0xB9 -> SUPERSCRIPT ONE
235+ '\xba ' # 0xBA -> MASCULINE ORDINAL INDICATOR
236+ '\xbb ' # 0xBB -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
237+ '\xbc ' # 0xBC -> VULGAR FRACTION ONE QUARTER
238+ '\xbd ' # 0xBD -> VULGAR FRACTION ONE HALF
239+ '\xbe ' # 0xBE -> VULGAR FRACTION THREE QUARTERS
240+ '\xbf ' # 0xBF -> INVERTED QUESTION MARK
241+ '\xc0 ' # 0xC0 -> LATIN CAPITAL LETTER A WITH GRAVE
242+ '\xc1 ' # 0xC1 -> LATIN CAPITAL LETTER A WITH ACUTE
243+ '\xc2 ' # 0xC2 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX
244+ '\xc3 ' # 0xC3 -> LATIN CAPITAL LETTER A WITH TILDE
245+ '\xc4 ' # 0xC4 -> LATIN CAPITAL LETTER A WITH DIAERESIS
246+ '\xc5 ' # 0xC5 -> LATIN CAPITAL LETTER A WITH RING ABOVE
247+ '\xc6 ' # 0xC6 -> LATIN CAPITAL LETTER AE
248+ '\xc7 ' # 0xC7 -> LATIN CAPITAL LETTER C WITH CEDILLA
249+ '\xc8 ' # 0xC8 -> LATIN CAPITAL LETTER E WITH GRAVE
250+ '\xc9 ' # 0xC9 -> LATIN CAPITAL LETTER E WITH ACUTE
251+ '\xca ' # 0xCA -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX
252+ '\xcb ' # 0xCB -> LATIN CAPITAL LETTER E WITH DIAERESIS
253+ '\xcc ' # 0xCC -> LATIN CAPITAL LETTER I WITH GRAVE
254+ '\xcd ' # 0xCD -> LATIN CAPITAL LETTER I WITH ACUTE
255+ '\xce ' # 0xCE -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX
256+ '\xcf ' # 0xCF -> LATIN CAPITAL LETTER I WITH DIAERESIS
257+ '\xd0 ' # 0xD0 -> LATIN CAPITAL LETTER ETH (Icelandic)
258+ '\xd1 ' # 0xD1 -> LATIN CAPITAL LETTER N WITH TILDE
259+ '\xd2 ' # 0xD2 -> LATIN CAPITAL LETTER O WITH GRAVE
260+ '\xd3 ' # 0xD3 -> LATIN CAPITAL LETTER O WITH ACUTE
261+ '\xd4 ' # 0xD4 -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX
262+ '\xd5 ' # 0xD5 -> LATIN CAPITAL LETTER O WITH TILDE
263+ '\xd6 ' # 0xD6 -> LATIN CAPITAL LETTER O WITH DIAERESIS
264+ '\xd7 ' # 0xD7 -> MULTIPLICATION SIGN
265+ '\xd8 ' # 0xD8 -> LATIN CAPITAL LETTER O WITH STROKE
266+ '\xd9 ' # 0xD9 -> LATIN CAPITAL LETTER U WITH GRAVE
267+ '\xda ' # 0xDA -> LATIN CAPITAL LETTER U WITH ACUTE
268+ '\xdb ' # 0xDB -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX
269+ '\xdc ' # 0xDC -> LATIN CAPITAL LETTER U WITH DIAERESIS
270+ '\xdd ' # 0xDD -> LATIN CAPITAL LETTER Y WITH ACUTE
271+ '\xde ' # 0xDE -> LATIN CAPITAL LETTER THORN (Icelandic)
272+ '\xdf ' # 0xDF -> LATIN SMALL LETTER SHARP S (German)
273+ '\xe0 ' # 0xE0 -> LATIN SMALL LETTER A WITH GRAVE
274+ '\xe1 ' # 0xE1 -> LATIN SMALL LETTER A WITH ACUTE
275+ '\xe2 ' # 0xE2 -> LATIN SMALL LETTER A WITH CIRCUMFLEX
276+ '\xe3 ' # 0xE3 -> LATIN SMALL LETTER A WITH TILDE
277+ '\xe4 ' # 0xE4 -> LATIN SMALL LETTER A WITH DIAERESIS
278+ '\xe5 ' # 0xE5 -> LATIN SMALL LETTER A WITH RING ABOVE
279+ '\xe6 ' # 0xE6 -> LATIN SMALL LETTER AE
280+ '\xe7 ' # 0xE7 -> LATIN SMALL LETTER C WITH CEDILLA
281+ '\xe8 ' # 0xE8 -> LATIN SMALL LETTER E WITH GRAVE
282+ '\xe9 ' # 0xE9 -> LATIN SMALL LETTER E WITH ACUTE
283+ '\xea ' # 0xEA -> LATIN SMALL LETTER E WITH CIRCUMFLEX
284+ '\xeb ' # 0xEB -> LATIN SMALL LETTER E WITH DIAERESIS
285+ '\xec ' # 0xEC -> LATIN SMALL LETTER I WITH GRAVE
286+ '\xed ' # 0xED -> LATIN SMALL LETTER I WITH ACUTE
287+ '\xee ' # 0xEE -> LATIN SMALL LETTER I WITH CIRCUMFLEX
288+ '\xef ' # 0xEF -> LATIN SMALL LETTER I WITH DIAERESIS
289+ '\xf0 ' # 0xF0 -> LATIN SMALL LETTER ETH (Icelandic)
290+ '\xf1 ' # 0xF1 -> LATIN SMALL LETTER N WITH TILDE
291+ '\xf2 ' # 0xF2 -> LATIN SMALL LETTER O WITH GRAVE
292+ '\xf3 ' # 0xF3 -> LATIN SMALL LETTER O WITH ACUTE
293+ '\xf4 ' # 0xF4 -> LATIN SMALL LETTER O WITH CIRCUMFLEX
294+ '\xf5 ' # 0xF5 -> LATIN SMALL LETTER O WITH TILDE
295+ '\xf6 ' # 0xF6 -> LATIN SMALL LETTER O WITH DIAERESIS
296+ '\xf7 ' # 0xF7 -> DIVISION SIGN
297+ '\xf8 ' # 0xF8 -> LATIN SMALL LETTER O WITH STROKE
298+ '\xf9 ' # 0xF9 -> LATIN SMALL LETTER U WITH GRAVE
299+ '\xfa ' # 0xFA -> LATIN SMALL LETTER U WITH ACUTE
300+ '\xfb ' # 0xFB -> LATIN SMALL LETTER U WITH CIRCUMFLEX
301+ '\xfc ' # 0xFC -> LATIN SMALL LETTER U WITH DIAERESIS
302+ '\xfd ' # 0xFD -> LATIN SMALL LETTER Y WITH ACUTE
303+ '\xfe ' # 0xFE -> LATIN SMALL LETTER THORN (Icelandic)
304+ '\xff ' # 0xFF -> LATIN SMALL LETTER Y WITH DIAERESIS
305+ )
306+
307+ ### Encoding table
308+ encoding_table = codecs .charmap_build (decoding_table )
309+
0 commit comments