/
encoding.py
323 lines (287 loc) · 10.4 KB
/
encoding.py
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
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
# -*- coding: utf-8 -*-
#
# Copyright © Spyder Project Contributors
# Licensed under the terms of the MIT License
# (see spyder/__init__.py for details)
"""
Text encoding utilities, text file I/O
Functions 'get_coding', 'decode', 'encode' and 'to_unicode' come from Eric4
source code (Utilities/__init___.py) Copyright © 2003-2009 Detlev Offenbach
"""
# Standard library imports
from codecs import BOM_UTF8, BOM_UTF16, BOM_UTF32
import tempfile
import locale
import re
import os
import os.path as osp
import pathlib
import sys
import time
import errno
# Third-party imports
from chardet.universaldetector import UniversalDetector
from atomicwrites import atomic_write
# Local imports
from spyder.py3compat import (is_string, to_text_string, is_binary_string,
is_text_string)
from spyder.utils.external.binaryornot.check import is_binary
PREFERRED_ENCODING = locale.getpreferredencoding()
def transcode(text, input=PREFERRED_ENCODING, output=PREFERRED_ENCODING):
"""Transcode a text string"""
try:
return text.decode("cp437").encode("cp1252")
except UnicodeError:
try:
return text.decode("cp437").encode(output)
except UnicodeError:
return text
#------------------------------------------------------------------------------
# Functions for encoding and decoding bytes that come from
# the *file system*.
#------------------------------------------------------------------------------
# The default encoding for file paths and environment variables should be set
# to match the default encoding that the OS is using.
def getfilesystemencoding():
"""
Query the filesystem for the encoding used to encode filenames
and environment variables.
"""
encoding = sys.getfilesystemencoding()
if encoding is None:
# Must be Linux or Unix and nl_langinfo(CODESET) failed.
encoding = PREFERRED_ENCODING
return encoding
FS_ENCODING = getfilesystemencoding()
def to_unicode_from_fs(string):
"""
Return a unicode version of string decoded using the file system encoding.
"""
if not is_string(string): # string is a QString
string = to_text_string(string.toUtf8(), 'utf-8')
else:
if is_binary_string(string):
try:
unic = string.decode(FS_ENCODING)
except (UnicodeError, TypeError):
pass
else:
return unic
return string
def to_fs_from_unicode(unic):
"""
Return a byte string version of unic encoded using the file
system encoding.
"""
if is_text_string(unic):
try:
string = unic.encode(FS_ENCODING)
except (UnicodeError, TypeError):
pass
else:
return string
return unic
#------------------------------------------------------------------------------
# Functions for encoding and decoding *text data* itself, usually originating
# from or destined for the *contents* of a file.
#------------------------------------------------------------------------------
# Codecs for working with files and text.
CODING_RE = re.compile(r"coding[:=]\s*([-\w_.]+)")
CODECS = ['utf-8', 'iso8859-1', 'iso8859-15', 'ascii', 'koi8-r', 'cp1251',
'koi8-u', 'iso8859-2', 'iso8859-3', 'iso8859-4', 'iso8859-5',
'iso8859-6', 'iso8859-7', 'iso8859-8', 'iso8859-9',
'iso8859-10', 'iso8859-13', 'iso8859-14', 'latin-1',
'utf-16']
def get_coding(text, force_chardet=False):
"""
Function to get the coding of a text.
@param text text to inspect (string)
@return coding string
"""
if not force_chardet:
for line in text.splitlines()[:2]:
try:
result = CODING_RE.search(to_text_string(line))
except UnicodeDecodeError:
# This could fail because to_text_string assume the text
# is utf8-like and we don't know the encoding to give
# it to to_text_string
pass
else:
if result:
codec = result.group(1)
# sometimes we find a false encoding that can
# result in errors
if codec in CODECS:
return codec
# Fallback using chardet
if is_binary_string(text):
detector = UniversalDetector()
for line in text.splitlines()[:2]:
detector.feed(line)
if detector.done: break
detector.close()
return detector.result['encoding']
return None
def decode(text):
"""
Function to decode a text.
@param text text to decode (string)
@return decoded text and encoding
"""
try:
if text.startswith(BOM_UTF8):
# UTF-8 with BOM
return to_text_string(text[len(BOM_UTF8):], 'utf-8'), 'utf-8-bom'
elif text.startswith(BOM_UTF16):
# UTF-16 with BOM
return to_text_string(text[len(BOM_UTF16):], 'utf-16'), 'utf-16'
elif text.startswith(BOM_UTF32):
# UTF-32 with BOM
return to_text_string(text[len(BOM_UTF32):], 'utf-32'), 'utf-32'
coding = get_coding(text)
if coding:
return to_text_string(text, coding), coding
except (UnicodeError, LookupError):
pass
# Assume UTF-8
try:
return to_text_string(text, 'utf-8'), 'utf-8-guessed'
except (UnicodeError, LookupError):
pass
# Assume Latin-1 (behaviour before 3.7.1)
return to_text_string(text, "latin-1"), 'latin-1-guessed'
def encode(text, orig_coding):
"""
Function to encode a text.
@param text text to encode (string)
@param orig_coding type of the original coding (string)
@return encoded text and encoding
"""
if orig_coding == 'utf-8-bom':
return BOM_UTF8 + text.encode("utf-8"), 'utf-8-bom'
# Try saving with original encoding
if orig_coding:
try:
return text.encode(orig_coding), orig_coding
except (UnicodeError, LookupError):
pass
# Try declared coding spec
coding = get_coding(text)
if coding:
try:
return text.encode(coding), coding
except (UnicodeError, LookupError):
raise RuntimeError("Incorrect encoding (%s)" % coding)
if orig_coding and orig_coding.endswith('-default') or \
orig_coding.endswith('-guessed'):
coding = orig_coding.replace("-default", "")
coding = orig_coding.replace("-guessed", "")
try:
return text.encode(coding), coding
except (UnicodeError, LookupError):
pass
# Save as UTF-8 without BOM
return text.encode('utf-8'), 'utf-8'
def to_unicode(string):
"""Convert a string to unicode"""
if not is_text_string(string):
for codec in CODECS:
try:
unic = to_text_string(string, codec)
except UnicodeError:
pass
except TypeError:
break
else:
return unic
return string
def write(text, filename, encoding='utf-8', mode='wb'):
"""
Write 'text' to file ('filename') assuming 'encoding' in an atomic way
Return (eventually new) encoding
"""
text, encoding = encode(text, encoding)
if os.name == 'nt':
try:
absolute_path_filename = pathlib.Path(filename).resolve()
if absolute_path_filename.exists():
absolute_filename = to_text_string(absolute_path_filename)
else:
absolute_filename = osp.realpath(filename)
except (OSError, RuntimeError):
absolute_filename = osp.realpath(filename)
else:
absolute_filename = osp.realpath(filename)
if 'a' in mode:
with open(absolute_filename, mode) as textfile:
textfile.write(text)
else:
# Based in the solution at untitaker/python-atomicwrites#42.
# Needed to fix file permissions overwriting.
# See spyder-ide/spyder#9381.
try:
file_stat = os.stat(absolute_filename)
original_mode = file_stat.st_mode
creation = file_stat.st_atime
except FileNotFoundError:
# Creating a new file, emulate what os.open() does
umask = os.umask(0)
os.umask(umask)
# Set base permission of a file to standard permissions.
# See #spyder-ide/spyder#14112.
original_mode = 0o666 & ~umask
creation = time.time()
try:
# fixes issues with scripts in Dropbox leaving
# temporary files in the folder, see spyder-ide/spyder#13041
tempfolder = None
if 'dropbox' in absolute_filename.lower():
tempfolder = tempfile.gettempdir()
with atomic_write(absolute_filename, overwrite=True,
mode=mode, dir=tempfolder) as textfile:
textfile.write(text)
except OSError as error:
# Some filesystems don't support the option to sync directories
# See untitaker/python-atomicwrites#17
if error.errno != errno.EINVAL:
with open(absolute_filename, mode) as textfile:
textfile.write(text)
try:
os.chmod(absolute_filename, original_mode)
file_stat = os.stat(absolute_filename)
# Preserve creation timestamps
os.utime(absolute_filename, (creation, file_stat.st_mtime))
except OSError:
# Prevent error when chmod/utime is not allowed
# See spyder-ide/spyder#11308
pass
return encoding
def writelines(lines, filename, encoding='utf-8', mode='wb'):
"""
Write 'lines' to file ('filename') assuming 'encoding'
Return (eventually new) encoding
"""
return write(os.linesep.join(lines), filename, encoding, mode)
def read(filename, encoding='utf-8'):
"""
Read text from file ('filename')
Return text and encoding
"""
text, encoding = decode( open(filename, 'rb').read() )
return text, encoding
def readlines(filename, encoding='utf-8'):
"""
Read lines from file ('filename')
Return lines and encoding
"""
text, encoding = read(filename, encoding)
return text.split(os.linesep), encoding
def is_text_file(filename):
"""
Test if the given path is a text-like file.
"""
try:
return not is_binary(filename)
except (OSError, IOError):
return False