Skip to content

Commit 15272cb

Browse files
andrewbirdandrewbird
committed
GSM encoding, use dicts now that the mapping is unique
1 parent 9f85446 commit 15272cb

File tree

1 file changed

+167
-173
lines changed

1 file changed

+167
-173
lines changed

‎messaging/sms/gsm0338.py‎

Lines changed: 167 additions & 173 deletions
Original file line numberDiff line numberDiff line change
@@ -19,193 +19,187 @@
1919
# data from
2020
# http://snoops.roy202.org/testerman/browser/trunk/plugins/codecs/gsm0338.py
2121

22-
def_regular_mapping = [
23-
('\x00', u'\u0040'), # COMMERCIAL AT
24-
# ('\x00', u'\u0000'), # NULL (see note above)
25-
('\x01', u'\u00A3'), # POUND SIGN
26-
('\x02', u'\u0024'), # DOLLAR SIGN
27-
('\x03', u'\u00A5'), # YEN SIGN
28-
('\x04', u'\u00E8'), # LATIN SMALL LETTER E WITH GRAVE
29-
('\x05', u'\u00E9'), # LATIN SMALL LETTER E WITH ACUTE
30-
('\x06', u'\u00F9'), # LATIN SMALL LETTER U WITH GRAVE
31-
('\x07', u'\u00EC'), # LATIN SMALL LETTER I WITH GRAVE
32-
('\x08', u'\u00F2'), # LATIN SMALL LETTER O WITH GRAVE
33-
('\x09', u'\u00C7'), # LATIN CAPITAL LETTER C WITH CEDILLA
34-
# The Unicode page suggests this is a mistake, but
35-
# it's still in the latest version of the spec and
36-
# our implementation has to be exact.
22+
# default GSM 03.38 -> unicode
23+
def_regular_decode_dict = {
24+
'\x00': u'\u0040', # COMMERCIAL AT
25+
'\x01': u'\u00A3', # POUND SIGN
26+
'\x02': u'\u0024', # DOLLAR SIGN
27+
'\x03': u'\u00A5', # YEN SIGN
28+
'\x04': u'\u00E8', # LATIN SMALL LETTER E WITH GRAVE
29+
'\x05': u'\u00E9', # LATIN SMALL LETTER E WITH ACUTE
30+
'\x06': u'\u00F9', # LATIN SMALL LETTER U WITH GRAVE
31+
'\x07': u'\u00EC', # LATIN SMALL LETTER I WITH GRAVE
32+
'\x08': u'\u00F2', # LATIN SMALL LETTER O WITH GRAVE
33+
'\x09': u'\u00C7', # LATIN CAPITAL LETTER C WITH CEDILLA
34+
# The Unicode page suggests this is a mistake: but
35+
# it's still in the latest version of the spec and
36+
# our implementation has to be exact.
3737

38-
('\x0A', u'\u000A'), # LINE FEED
39-
('\x0B', u'\u00D8'), # LATIN CAPITAL LETTER O WITH STROKE
40-
('\x0C', u'\u00F8'), # LATIN SMALL LETTER O WITH STROKE
41-
('\x0D', u'\u000D'), # CARRIAGE RETURN
42-
('\x0E', u'\u00C5'), # LATIN CAPITAL LETTER A WITH RING ABOVE
43-
('\x0F', u'\u00E5'), # LATIN SMALL LETTER A WITH RING ABOVE
44-
('\x10', u'\u0394'), # GREEK CAPITAL LETTER DELTA
45-
('\x11', u'\u005F'), # LOW LINE
46-
('\x12', u'\u03A6'), # GREEK CAPITAL LETTER PHI
47-
('\x13', u'\u0393'), # GREEK CAPITAL LETTER GAMMA
48-
('\x14', u'\u039B'), # GREEK CAPITAL LETTER LAMDA
49-
('\x15', u'\u03A9'), # GREEK CAPITAL LETTER OMEGA
50-
('\x16', u'\u03A0'), # GREEK CAPITAL LETTER PI
51-
('\x17', u'\u03A8'), # GREEK CAPITAL LETTER PSI
52-
('\x18', u'\u03A3'), # GREEK CAPITAL LETTER SIGMA
53-
('\x19', u'\u0398'), # GREEK CAPITAL LETTER THETA
54-
('\x1A', u'\u039E'), # GREEK CAPITAL LETTER XI
55-
('\x1C', u'\u00C6'), # LATIN CAPITAL LETTER AE
56-
('\x1D', u'\u00E6'), # LATIN SMALL LETTER AE
57-
('\x1E', u'\u00DF'), # LATIN SMALL LETTER SHARP S (German)
58-
('\x1F', u'\u00C9'), # LATIN CAPITAL LETTER E WITH ACUTE
59-
('\x20', u'\u0020'), # SPACE
60-
('\x21', u'\u0021'), # EXCLAMATION MARK
61-
('\x22', u'\u0022'), # QUOTATION MARK
62-
('\x23', u'\u0023'), # NUMBER SIGN
63-
('\x24', u'\u00A4'), # CURRENCY SIGN
64-
('\x25', u'\u0025'), # PERCENT SIGN
65-
('\x26', u'\u0026'), # AMPERSAND
66-
('\x27', u'\u0027'), # APOSTROPHE
67-
('\x28', u'\u0028'), # LEFT PARENTHESIS
68-
('\x29', u'\u0029'), # RIGHT PARENTHESIS
69-
('\x2A', u'\u002A'), # ASTERISK
70-
('\x2B', u'\u002B'), # PLUS SIGN
71-
('\x2C', u'\u002C'), # COMMA
72-
('\x2D', u'\u002D'), # HYPHEN-MINUS
73-
('\x2E', u'\u002E'), # FULL STOP
74-
('\x2F', u'\u002F'), # SOLIDUS
75-
('\x30', u'\u0030'), # DIGIT ZERO
76-
('\x31', u'\u0031'), # DIGIT ONE
77-
('\x32', u'\u0032'), # DIGIT TWO
78-
('\x33', u'\u0033'), # DIGIT THREE
79-
('\x34', u'\u0034'), # DIGIT FOUR
80-
('\x35', u'\u0035'), # DIGIT FIVE
81-
('\x36', u'\u0036'), # DIGIT SIX
82-
('\x37', u'\u0037'), # DIGIT SEVEN
83-
('\x38', u'\u0038'), # DIGIT EIGHT
84-
('\x39', u'\u0039'), # DIGIT NINE
85-
('\x3A', u'\u003A'), # COLON
86-
('\x3B', u'\u003B'), # SEMICOLON
87-
('\x3C', u'\u003C'), # LESS-THAN SIGN
88-
('\x3D', u'\u003D'), # EQUALS SIGN
89-
('\x3E', u'\u003E'), # GREATER-THAN SIGN
90-
('\x3F', u'\u003F'), # QUESTION MARK
91-
('\x40', u'\u00A1'), # INVERTED EXCLAMATION MARK
92-
('\x41', u'\u0041'), # LATIN CAPITAL LETTER A
93-
('\x42', u'\u0042'), # LATIN CAPITAL LETTER B
94-
('\x43', u'\u0043'), # LATIN CAPITAL LETTER C
95-
('\x44', u'\u0044'), # LATIN CAPITAL LETTER D
96-
('\x45', u'\u0045'), # LATIN CAPITAL LETTER E
97-
('\x46', u'\u0046'), # LATIN CAPITAL LETTER F
98-
('\x47', u'\u0047'), # LATIN CAPITAL LETTER G
99-
('\x48', u'\u0048'), # LATIN CAPITAL LETTER H
100-
('\x49', u'\u0049'), # LATIN CAPITAL LETTER I
101-
('\x4A', u'\u004A'), # LATIN CAPITAL LETTER J
102-
('\x4B', u'\u004B'), # LATIN CAPITAL LETTER K
103-
('\x4C', u'\u004C'), # LATIN CAPITAL LETTER L
104-
('\x4D', u'\u004D'), # LATIN CAPITAL LETTER M
105-
('\x4E', u'\u004E'), # LATIN CAPITAL LETTER N
106-
('\x4F', u'\u004F'), # LATIN CAPITAL LETTER O
107-
('\x50', u'\u0050'), # LATIN CAPITAL LETTER P
108-
('\x51', u'\u0051'), # LATIN CAPITAL LETTER Q
109-
('\x52', u'\u0052'), # LATIN CAPITAL LETTER R
110-
('\x53', u'\u0053'), # LATIN CAPITAL LETTER S
111-
('\x54', u'\u0054'), # LATIN CAPITAL LETTER T
112-
('\x55', u'\u0055'), # LATIN CAPITAL LETTER U
113-
('\x56', u'\u0056'), # LATIN CAPITAL LETTER V
114-
('\x57', u'\u0057'), # LATIN CAPITAL LETTER W
115-
('\x58', u'\u0058'), # LATIN CAPITAL LETTER X
116-
('\x59', u'\u0059'), # LATIN CAPITAL LETTER Y
117-
('\x5A', u'\u005A'), # LATIN CAPITAL LETTER Z
118-
('\x5B', u'\u00C4'), # LATIN CAPITAL LETTER A WITH DIAERESIS
119-
('\x5C', u'\u00D6'), # LATIN CAPITAL LETTER O WITH DIAERESIS
120-
('\x5D', u'\u00D1'), # LATIN CAPITAL LETTER N WITH TILDE
121-
('\x5E', u'\u00DC'), # LATIN CAPITAL LETTER U WITH DIAERESIS
122-
('\x5F', u'\u00A7'), # SECTION SIGN
123-
('\x60', u'\u00BF'), # INVERTED QUESTION MARK
124-
('\x61', u'\u0061'), # LATIN SMALL LETTER A
125-
('\x62', u'\u0062'), # LATIN SMALL LETTER B
126-
('\x63', u'\u0063'), # LATIN SMALL LETTER C
127-
('\x64', u'\u0064'), # LATIN SMALL LETTER D
128-
('\x65', u'\u0065'), # LATIN SMALL LETTER E
129-
('\x66', u'\u0066'), # LATIN SMALL LETTER F
130-
('\x67', u'\u0067'), # LATIN SMALL LETTER G
131-
('\x68', u'\u0068'), # LATIN SMALL LETTER H
132-
('\x69', u'\u0069'), # LATIN SMALL LETTER I
133-
('\x6A', u'\u006A'), # LATIN SMALL LETTER J
134-
('\x6B', u'\u006B'), # LATIN SMALL LETTER K
135-
('\x6C', u'\u006C'), # LATIN SMALL LETTER L
136-
('\x6D', u'\u006D'), # LATIN SMALL LETTER M
137-
('\x6E', u'\u006E'), # LATIN SMALL LETTER N
138-
('\x6F', u'\u006F'), # LATIN SMALL LETTER O
139-
('\x70', u'\u0070'), # LATIN SMALL LETTER P
140-
('\x71', u'\u0071'), # LATIN SMALL LETTER Q
141-
('\x72', u'\u0072'), # LATIN SMALL LETTER R
142-
('\x73', u'\u0073'), # LATIN SMALL LETTER S
143-
('\x74', u'\u0074'), # LATIN SMALL LETTER T
144-
('\x75', u'\u0075'), # LATIN SMALL LETTER U
145-
('\x76', u'\u0076'), # LATIN SMALL LETTER V
146-
('\x77', u'\u0077'), # LATIN SMALL LETTER W
147-
('\x78', u'\u0078'), # LATIN SMALL LETTER X
148-
('\x79', u'\u0079'), # LATIN SMALL LETTER Y
149-
('\x7A', u'\u007A'), # LATIN SMALL LETTER Z
150-
('\x7B', u'\u00E4'), # LATIN SMALL LETTER A WITH DIAERESIS
151-
('\x7C', u'\u00F6'), # LATIN SMALL LETTER O WITH DIAERESIS
152-
('\x7D', u'\u00F1'), # LATIN SMALL LETTER N WITH TILDE
153-
('\x7E', u'\u00FC'), # LATIN SMALL LETTER U WITH DIAERESIS
154-
('\x7F', u'\u00E0'), # LATIN SMALL LETTER A WITH GRAVE
155-
]
38+
'\x0A': u'\u000A', # LINE FEED
39+
'\x0B': u'\u00D8', # LATIN CAPITAL LETTER O WITH STROKE
40+
'\x0C': u'\u00F8', # LATIN SMALL LETTER O WITH STROKE
41+
'\x0D': u'\u000D', # CARRIAGE RETURN
42+
'\x0E': u'\u00C5', # LATIN CAPITAL LETTER A WITH RING ABOVE
43+
'\x0F': u'\u00E5', # LATIN SMALL LETTER A WITH RING ABOVE
44+
'\x10': u'\u0394', # GREEK CAPITAL LETTER DELTA
45+
'\x11': u'\u005F', # LOW LINE
46+
'\x12': u'\u03A6', # GREEK CAPITAL LETTER PHI
47+
'\x13': u'\u0393', # GREEK CAPITAL LETTER GAMMA
48+
'\x14': u'\u039B', # GREEK CAPITAL LETTER LAMDA
49+
'\x15': u'\u03A9', # GREEK CAPITAL LETTER OMEGA
50+
'\x16': u'\u03A0', # GREEK CAPITAL LETTER PI
51+
'\x17': u'\u03A8', # GREEK CAPITAL LETTER PSI
52+
'\x18': u'\u03A3', # GREEK CAPITAL LETTER SIGMA
53+
'\x19': u'\u0398', # GREEK CAPITAL LETTER THETA
54+
'\x1A': u'\u039E', # GREEK CAPITAL LETTER XI
55+
'\x1C': u'\u00C6', # LATIN CAPITAL LETTER AE
56+
'\x1D': u'\u00E6', # LATIN SMALL LETTER AE
57+
'\x1E': u'\u00DF', # LATIN SMALL LETTER SHARP S (German)
58+
'\x1F': u'\u00C9', # LATIN CAPITAL LETTER E WITH ACUTE
59+
'\x20': u'\u0020', # SPACE
60+
'\x21': u'\u0021', # EXCLAMATION MARK
61+
'\x22': u'\u0022', # QUOTATION MARK
62+
'\x23': u'\u0023', # NUMBER SIGN
63+
'\x24': u'\u00A4', # CURRENCY SIGN
64+
'\x25': u'\u0025', # PERCENT SIGN
65+
'\x26': u'\u0026', # AMPERSAND
66+
'\x27': u'\u0027', # APOSTROPHE
67+
'\x28': u'\u0028', # LEFT PARENTHESIS
68+
'\x29': u'\u0029', # RIGHT PARENTHESIS
69+
'\x2A': u'\u002A', # ASTERISK
70+
'\x2B': u'\u002B', # PLUS SIGN
71+
'\x2C': u'\u002C', # COMMA
72+
'\x2D': u'\u002D', # HYPHEN-MINUS
73+
'\x2E': u'\u002E', # FULL STOP
74+
'\x2F': u'\u002F', # SOLIDUS
75+
'\x30': u'\u0030', # DIGIT ZERO
76+
'\x31': u'\u0031', # DIGIT ONE
77+
'\x32': u'\u0032', # DIGIT TWO
78+
'\x33': u'\u0033', # DIGIT THREE
79+
'\x34': u'\u0034', # DIGIT FOUR
80+
'\x35': u'\u0035', # DIGIT FIVE
81+
'\x36': u'\u0036', # DIGIT SIX
82+
'\x37': u'\u0037', # DIGIT SEVEN
83+
'\x38': u'\u0038', # DIGIT EIGHT
84+
'\x39': u'\u0039', # DIGIT NINE
85+
'\x3A': u'\u003A', # COLON
86+
'\x3B': u'\u003B', # SEMICOLON
87+
'\x3C': u'\u003C', # LESS-THAN SIGN
88+
'\x3D': u'\u003D', # EQUALS SIGN
89+
'\x3E': u'\u003E', # GREATER-THAN SIGN
90+
'\x3F': u'\u003F', # QUESTION MARK
91+
'\x40': u'\u00A1', # INVERTED EXCLAMATION MARK
92+
'\x41': u'\u0041', # LATIN CAPITAL LETTER A
93+
'\x42': u'\u0042', # LATIN CAPITAL LETTER B
94+
'\x43': u'\u0043', # LATIN CAPITAL LETTER C
95+
'\x44': u'\u0044', # LATIN CAPITAL LETTER D
96+
'\x45': u'\u0045', # LATIN CAPITAL LETTER E
97+
'\x46': u'\u0046', # LATIN CAPITAL LETTER F
98+
'\x47': u'\u0047', # LATIN CAPITAL LETTER G
99+
'\x48': u'\u0048', # LATIN CAPITAL LETTER H
100+
'\x49': u'\u0049', # LATIN CAPITAL LETTER I
101+
'\x4A': u'\u004A', # LATIN CAPITAL LETTER J
102+
'\x4B': u'\u004B', # LATIN CAPITAL LETTER K
103+
'\x4C': u'\u004C', # LATIN CAPITAL LETTER L
104+
'\x4D': u'\u004D', # LATIN CAPITAL LETTER M
105+
'\x4E': u'\u004E', # LATIN CAPITAL LETTER N
106+
'\x4F': u'\u004F', # LATIN CAPITAL LETTER O
107+
'\x50': u'\u0050', # LATIN CAPITAL LETTER P
108+
'\x51': u'\u0051', # LATIN CAPITAL LETTER Q
109+
'\x52': u'\u0052', # LATIN CAPITAL LETTER R
110+
'\x53': u'\u0053', # LATIN CAPITAL LETTER S
111+
'\x54': u'\u0054', # LATIN CAPITAL LETTER T
112+
'\x55': u'\u0055', # LATIN CAPITAL LETTER U
113+
'\x56': u'\u0056', # LATIN CAPITAL LETTER V
114+
'\x57': u'\u0057', # LATIN CAPITAL LETTER W
115+
'\x58': u'\u0058', # LATIN CAPITAL LETTER X
116+
'\x59': u'\u0059', # LATIN CAPITAL LETTER Y
117+
'\x5A': u'\u005A', # LATIN CAPITAL LETTER Z
118+
'\x5B': u'\u00C4', # LATIN CAPITAL LETTER A WITH DIAERESIS
119+
'\x5C': u'\u00D6', # LATIN CAPITAL LETTER O WITH DIAERESIS
120+
'\x5D': u'\u00D1', # LATIN CAPITAL LETTER N WITH TILDE
121+
'\x5E': u'\u00DC', # LATIN CAPITAL LETTER U WITH DIAERESIS
122+
'\x5F': u'\u00A7', # SECTION SIGN
123+
'\x60': u'\u00BF', # INVERTED QUESTION MARK
124+
'\x61': u'\u0061', # LATIN SMALL LETTER A
125+
'\x62': u'\u0062', # LATIN SMALL LETTER B
126+
'\x63': u'\u0063', # LATIN SMALL LETTER C
127+
'\x64': u'\u0064', # LATIN SMALL LETTER D
128+
'\x65': u'\u0065', # LATIN SMALL LETTER E
129+
'\x66': u'\u0066', # LATIN SMALL LETTER F
130+
'\x67': u'\u0067', # LATIN SMALL LETTER G
131+
'\x68': u'\u0068', # LATIN SMALL LETTER H
132+
'\x69': u'\u0069', # LATIN SMALL LETTER I
133+
'\x6A': u'\u006A', # LATIN SMALL LETTER J
134+
'\x6B': u'\u006B', # LATIN SMALL LETTER K
135+
'\x6C': u'\u006C', # LATIN SMALL LETTER L
136+
'\x6D': u'\u006D', # LATIN SMALL LETTER M
137+
'\x6E': u'\u006E', # LATIN SMALL LETTER N
138+
'\x6F': u'\u006F', # LATIN SMALL LETTER O
139+
'\x70': u'\u0070', # LATIN SMALL LETTER P
140+
'\x71': u'\u0071', # LATIN SMALL LETTER Q
141+
'\x72': u'\u0072', # LATIN SMALL LETTER R
142+
'\x73': u'\u0073', # LATIN SMALL LETTER S
143+
'\x74': u'\u0074', # LATIN SMALL LETTER T
144+
'\x75': u'\u0075', # LATIN SMALL LETTER U
145+
'\x76': u'\u0076', # LATIN SMALL LETTER V
146+
'\x77': u'\u0077', # LATIN SMALL LETTER W
147+
'\x78': u'\u0078', # LATIN SMALL LETTER X
148+
'\x79': u'\u0079', # LATIN SMALL LETTER Y
149+
'\x7A': u'\u007A', # LATIN SMALL LETTER Z
150+
'\x7B': u'\u00E4', # LATIN SMALL LETTER A WITH DIAERESIS
151+
'\x7C': u'\u00F6', # LATIN SMALL LETTER O WITH DIAERESIS
152+
'\x7D': u'\u00F1', # LATIN SMALL LETTER N WITH TILDE
153+
'\x7E': u'\u00FC', # LATIN SMALL LETTER U WITH DIAERESIS
154+
'\x7F': u'\u00E0', # LATIN SMALL LETTER A WITH GRAVE
155+
}
156156

157-
# Escaped characters
158-
def_escaped_mapping = [
159-
('\x0A', u'\u000C'), # FORM FEED
160-
('\x14', u'\u005E'), # CIRCUMFLEX ACCENT
161-
('\x28', u'\u007B'), # LEFT CURLY BRACKET
162-
('\x29', u'\u007D'), # RIGHT CURLY BRACKET
163-
('\x2F', u'\u005C'), # REVERSE SOLIDUS
164-
('\x3C', u'\u005B'), # LEFT SQUARE BRACKET
165-
('\x3D', u'\u007E'), # TILDE
166-
('\x3E', u'\u005D'), # RIGHT SQUARE BRACKET
167-
('\x40', u'\u007C'), # VERTICAL LINE
168-
('\x65', u'\u20AC'), # EURO SIGN
169-
]
157+
# default GSM 03.38 escaped characters -> unicode
158+
def_escape_decode_dict = {
159+
'\x0A': u'\u000C', # FORM FEED
160+
'\x14': u'\u005E', # CIRCUMFLEX ACCENT
161+
'\x28': u'\u007B', # LEFT CURLY BRACKET
162+
'\x29': u'\u007D', # RIGHT CURLY BRACKET
163+
'\x2F': u'\u005C', # REVERSE SOLIDUS
164+
'\x3C': u'\u005B', # LEFT SQUARE BRACKET
165+
'\x3D': u'\u007E', # TILDE
166+
'\x3E': u'\u005D', # RIGHT SQUARE BRACKET
167+
'\x40': u'\u007C', # VERTICAL LINE
168+
'\x65': u'\u20AC', # EURO SIGN
169+
}
170170

171171
# Replacement characters, default is question mark. Used when it is not too
172172
# important to ensure exact UTF-8 -> GSM -> UTF-8 equivilence, such as when
173173
# humans read and write SMS. But for USSD and other M2M applications it's
174174
# important to ensure the conversion is exact.
175-
def_replace_mapping = [
176-
('\x09', u'\u00E7'), # LATIN SMALL LETTER C WITH CEDILLA
175+
def_replace_encode_dict = {
176+
u'\u00E7': '\x09', # LATIN SMALL LETTER C WITH CEDILLA
177177

178-
('\x41', u'\u0391'), # GREEK CAPITAL LETTER ALPHA
179-
('\x42', u'\u0392'), # GREEK CAPITAL LETTER BETA
180-
('\x45', u'\u0395'), # GREEK CAPITAL LETTER EPSILON
181-
('\x48', u'\u0397'), # GREEK CAPITAL LETTER ETA
182-
('\x49', u'\u0399'), # GREEK CAPITAL LETTER IOTA
183-
('\x4B', u'\u039A'), # GREEK CAPITAL LETTER KAPPA
184-
('\x4D', u'\u039C'), # GREEK CAPITAL LETTER MU
185-
('\x4E', u'\u039D'), # GREEK CAPITAL LETTER NU
186-
('\x4F', u'\u039F'), # GREEK CAPITAL LETTER OMICRON
187-
('\x50', u'\u03A1'), # GREEK CAPITAL LETTER RHO
188-
('\x54', u'\u03A4'), # GREEK CAPITAL LETTER TAU
189-
('\x58', u'\u03A7'), # GREEK CAPITAL LETTER CHI
190-
('\x59', u'\u03A5'), # GREEK CAPITAL LETTER UPSILON
191-
('\x5A', u'\u0396'), # GREEK CAPITAL LETTER ZETA
192-
]
178+
u'\u0391': '\x41', # GREEK CAPITAL LETTER ALPHA
179+
u'\u0392': '\x42', # GREEK CAPITAL LETTER BETA
180+
u'\u0395': '\x45', # GREEK CAPITAL LETTER EPSILON
181+
u'\u0397': '\x48', # GREEK CAPITAL LETTER ETA
182+
u'\u0399': '\x49', # GREEK CAPITAL LETTER IOTA
183+
u'\u039A': '\x4B', # GREEK CAPITAL LETTER KAPPA
184+
u'\u039C': '\x4D', # GREEK CAPITAL LETTER MU
185+
u'\u039D': '\x4E', # GREEK CAPITAL LETTER NU
186+
u'\u039F': '\x4F', # GREEK CAPITAL LETTER OMICRON
187+
u'\u03A1': '\x50', # GREEK CAPITAL LETTER RHO
188+
u'\u03A4': '\x54', # GREEK CAPITAL LETTER TAU
189+
u'\u03A7': '\x58', # GREEK CAPITAL LETTER CHI
190+
u'\u03A5': '\x59', # GREEK CAPITAL LETTER UPSILON
191+
u'\u0396': '\x5A', # GREEK CAPITAL LETTER ZETA
192+
}
193193

194194
QUESTION_MARK = chr(0x3f)
195195

196196
# unicode -> default GSM 03.38
197-
def_regular_encode_dict = dict([(u, g) for g, u in def_regular_mapping])
197+
def_regular_encode_dict = \
198+
dict((u, g) for g, u in def_regular_decode_dict.iteritems())
198199

199200
# unicode -> default escaped GSM 03.38 characters
200-
def_escape_encode_dict = dict([(u, g) for g, u in def_escaped_mapping])
201-
202-
# unicode -> default replacement characters
203-
def_replace_encode_dict = dict([(u, g) for g, u in def_replace_mapping])
204-
205-
# default GSM 03.38 -> unicode
206-
# Note: We've removed the duplicates to be strict TS23.038 compliant
207-
def_regular_decode_dict = dict([(g, u) for g, u in def_regular_mapping])
208-
def_escape_decode_dict = dict([(g, u) for g, u in def_escaped_mapping])
201+
def_escape_encode_dict = \
202+
dict((u, g) for g, u in def_escape_decode_dict.iteritems())
209203

210204

211205
def encode(input_, errors='strict'):

0 commit comments

Comments
 (0)