1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
|
#Edited by Dan:
#Now takes raw encoding as arguments for Set/Get EncodedText.
#Also removed some uneeded code.
#***************************************************************************
#drDetectUTF_8
# Programmer: limodou
# E-mail: limodou@users.sourceforge.net
#
# Copyright 2004 limodou
#
# Distributed under the terms of the GPL (GNU Public License)
#
# DrPython is free software; you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation; either version 2 of the License, or
# (at your option) any later version.
#
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with this program; if not, write to the Free Software
# Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
import wx, re
def utf8Detect(text):
"""Detect if a string is utf-8 encoding"""
lastch=0
begin=0
BOM=True
BOMchs=(0xEF, 0xBB, 0xBF)
good=0
bad=0
for char in text:
ch=ord(char)
if begin<3:
BOM=(BOMchs[begin]==ch) and BOM
begin += 1
continue
if (begin==4) and (BOM==True):
break;
if (ch & 0xC0) == 0x80:
if (lastch & 0xC0) == 0xC0:
good += 1
elif (lastch &0x80) == 0:
bad += 1
elif (lastch & 0xC0) == 0xC0:
bad += 1
lastch = ch
#modi limodou 2004/04/16
#if all characters are ascii, its encoding also can be ascii encoding or default encoding
#in most cases, I think it's better that not recognizing it as utf-8 encoding
if (((begin == 4) and (BOM == True)) or
(good >= bad and good>0)):
return True
else:
return False
#/drDetectUTF_8
#***************************************************************************
#Autodetect: If the user has enabled autodetection,
#and the file has the proper special comment for encoding,
#return the encoding used (or None if nothing is found):
reencoding = re.compile(r'\#\s*-\*-.+-\*-')
def CheckForEncodingComment(text):
encodingmatch = reencoding.search(text)
if encodingmatch is not None:
t = encodingmatch.group()
i = t.find(':') + 1
encoding = t[i:].rstrip('-*-').strip()
return encoding
return None
#What if python is not built with unicode support, but wxPython is?
#So, here is a safe way to test for ascii.
def CheckAscii(text):
#Optimize this a little.
_ord = ord
for a in text:
n = _ord(a)
if (n < 0) or (n > 127):
return False
return True
def DecodeTextWith(text, encoding):
#Try the encoding
try:
text = text.encode(encoding)
return text
except:
pass
return None
def DecodeText(frame, text, encoding='<Default Encoding>'):
if wx.USE_UNICODE:
etext = None
if encoding != '<Default Encoding>':
etext = DecodeTextWith(text, encoding)
if etext is not None:
return etext
defaultencoding = len(frame.prefs.defaultencoding) > 0
if frame.prefs.autodetectencoding:
enco = CheckForEncodingComment(text)
if enco is not None:
etext = DecodeTextWith(text, enco)
if etext is not None:
return etext
if utf8Detect(text):
etext = DecodeTextWith(text, 'utf-8')
if etext is not None:
return etext
if defaultencoding:
etext = DecodeTextWith(text, frame.prefs.defaultencoding)
if etext is None:
frame.ShowMessage('There was an error using the encoding "%s".' % (frame.prefs.defaultencoding), 'Encoding Error')
else:
return etext
if CheckAscii(text):
return text
if etext is None:
raise Exception, 'Encoding Error!'
else:
return text
def EncodeTextWith(text, encoding):
#Try the encoding
try:
text = unicode(text, encoding)
return text
except:
pass
return None
def EncodeText(frame, text, encoding='<Default Encoding>', returnEncoding=False):
if wx.USE_UNICODE:
etext = None
if encoding != '<Default Encoding>':
etext = EncodeTextWith(text, encoding)
if etext is not None:
if returnEncoding:
return etext, encoding
else:
return etext
defaultencoding = len(frame.prefs.defaultencoding) > 0
if frame.prefs.autodetectencoding:
enco = CheckForEncodingComment(text)
if enco is not None:
etext = EncodeTextWith(text, enco)
if etext is not None:
if returnEncoding:
return etext, enco
else:
return etext
if utf8Detect(text):
etext = EncodeTextWith(text, 'utf-8')
if etext is not None:
if returnEncoding:
return etext, 'utf-8'
else:
return etext
if defaultencoding:
etext = EncodeTextWith(text, frame.prefs.defaultencoding)
if etext is None:
frame.ShowMessage('There was an error using the encoding "%s".' % (frame.prefs.defaultencoding), 'Encoding Error')
else:
if returnEncoding:
return etext, frame.prefs.defaultencoding
else:
return etext
if CheckAscii(text):
if returnEncoding:
return text, 'ascii'
else:
return text
if etext is None:
raise Exception, 'Encoding Error!'
else:
if returnEncoding:
return text, '<Default Encoding>'
else:
return text
|
