Repository navigation
Expand file tree
/
Copy pathcorrect_encoding.py
More file actions
executable file
·190 lines (146 loc) · 4.17 KB
/
Copy pathcorrect_encoding.py
File metadata and controls
executable file
·190 lines (146 loc) · 4.17 KB
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
# encoding:utf-8
"""
try to correct some mixed encoding problems in a text file (SQL dump)
HACK!
:copyleft: 2012 by Jens Diemer
:license: GNU GPL v3 or above
"""
import sys
import codecs
import pprint
import time
print "sys.getdefaultencoding():", sys.getdefaultencoding()
print "sys.stdout.encoding:", sys.stdout.encoding
print "-"*79
SQL_DUMP = "test.sql"
CONVERT_DATA = {
u'\xc3\xa4': u"ä",
u'\xc3\u201e': u"Ä",
u'\xc3\xb6': u"ö",
u'\xc3\u2013': u"Ö",
u'\xc3\xbc': u"ü",
u'\xc3\u0153': u"Ü",
u'\xc3\u0178': u"ß",
u'\xc3\xa4\xc3\u0178': u"äß",
u'\xc3\xb6\xc3\u0178': u"öß",
u'\xc3\xbc\xc3\u0178': u"üß",
}
SKIP_INFO = {
"utf-8":(
u"ä", u"Ä",
u"ö", u"Ö",
u"ü", u"Ü",
u"ß",
u"üß",
)
}
#SKIP_INFO = {}
POSSIBLE_CODECS = ("latin-1", "utf-8")
def get_nonascii_chars(content):
"""
>>> get_nonascii_chars(u'zur\\xc3\\xbcckf\\xc3\\xbchren.')
[u'\\xc3\\xbc', u'\\xc3\\xbc']
"""
chars = [u""]
in_nonascii = False
for char in content:
if ord(char) > 127:
chars[-1] += char
in_nonascii = True
continue
if in_nonascii:
in_nonascii = False
chars.append(u"")
if chars[-1] == u"":
chars = chars[:-1]
return chars
def correct_encoding(content):
content = content.split(u" ")
total_count = len(content)
print total_count
for index, part in enumerate(content):
try:
part.encode("ascii")
except UnicodeEncodeError, err:
# print "Unicode error: %s" % err
# print repr(part[err.start:err.end]), repr(part)
pass
else:
continue
chars = get_nonascii_chars(part)
# print chars
for char in chars:
if char not in CONVERT_DATA:
continue
new_char = CONVERT_DATA[char]
print repr(char), "->", new_char
print repr(part), "->",
part = part.replace(char, new_char)
print part
content[index] = part
print "%i/%i -> done." % (index, total_count)
content = " ".join(content)
return content
def extract_unicode_errors(content, skip_info):
def is_correct(char, skip_info):
for codec, chars in skip_info.items():
try:
test = char.encode(codec)
except UnicodeEncodeError:
continue
else:
if test in chars:
return True
return False
content = content.split(u" ")
total_count = len(content)
print total_count
non_ascii = {}
for part in content:
try:
part.encode("ascii")
except UnicodeEncodeError, err:
# print "Unicode error: %s" % err
# print repr(part[err.start:err.end]), repr(part)
pass
else:
continue
chars = get_nonascii_chars(part)
# print chars
for char in chars:
if is_correct(char, skip_info):
continue
if char not in non_ascii:
non_ascii[char] = [part]
else:
if part not in non_ascii[char]:
non_ascii[char].append(part)
return non_ascii
def display_unicode_errors(non_ascii_data):
for char, parts in non_ascii_data.items():
print repr(char),
if char in CONVERT_DATA:
print u"*** %s ***" % CONVERT_DATA[char]
for part in parts[:3]:
part = part.replace(char, CONVERT_DATA[char])
print "\t", part
else:
for part in parts[:3]:
print "\t", part
if __name__ == "__main__":
import doctest
print doctest.testmod(
# verbose=True
verbose=False
)
# sys.exit()
with open(SQL_DUMP, "rb") as f:
content = f.read()
non_ascii_data = extract_unicode_errors(content, SKIP_INFO)
display_unicode_errors(non_ascii_data)
# sys.exit()
content = correct_encoding(content)
print "write...",
with open(SQL_DUMP + "2", "wb") as f:
f.write(content)
print "done"