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
|
#!/usr/bin/env python
"""Test that untokenize always generates the expected output.
That is, the output of
untokenize.untokenize(tokenize.generate_tokens(file_input.readline))
is exactly equal to the input file.
"""
from __future__ import print_function
from __future__ import unicode_literals
import io
import os
import sys
import tokenize
import untokenize
try:
unicode
except NameError:
unicode = str
def open_with_encoding(filename, encoding, mode='r'):
"""Return opened file with a specific encoding."""
return io.open(filename, mode=mode, encoding=encoding,
newline='') # Preserve line endings
def detect_encoding(filename):
"""Return file encoding."""
try:
with open(filename, 'rb') as input_file:
from fissix.pgen2 import tokenize as lib2to3_tokenize
encoding = lib2to3_tokenize.detect_encoding(input_file.readline)[0]
# Check for correctness of encoding.
with open_with_encoding(filename, encoding) as input_file:
input_file.read()
return encoding
except (SyntaxError, LookupError, UnicodeDecodeError):
return 'latin-1'
def diff(before, after):
"""Return diff of two files."""
import difflib
return ''.join(difflib.unified_diff(
before.splitlines(True),
after.splitlines(True),
lineterm='\n'))
def run(filename):
"""Check untokenize with file.
Return True on success.
"""
with open_with_encoding(filename,
encoding=detect_encoding(filename)) as input_file:
source_code = input_file.read()
# Handle files with trailing whitespace, but no final newline.
# tokenize.generate_tokens() will not report the trailing whitespace in
# such a case.
if source_code.endswith((' ', '\t')):
source_code = source_code.rstrip()
string_io = io.StringIO(source_code)
generated = untokenize.untokenize(
tokenize.generate_tokens(string_io.readline))
if source_code == generated:
return True
else:
print('untokenize failed on ' + filename,
file=sys.stderr)
print(diff(source_code, generated),
file=sys.stderr)
def process_args():
"""Return processed arguments (options and positional arguments)."""
import argparse
parser = argparse.ArgumentParser()
parser.add_argument('files', nargs='*', help='files to format')
return parser.parse_args()
def check(args):
"""Run test recursively on directory of files.
Return False if the fix results in broken syntax.
"""
if args.files:
dir_paths = args.files
else:
dir_paths = [path for path in sys.path
if os.path.isdir(path)]
filenames = dir_paths
completed_filenames = set()
while filenames:
try:
name = os.path.realpath(filenames.pop(0))
if not os.path.exists(name):
# Invalid symlink.
continue
if name in completed_filenames:
print('---> Skipping previously tested ' + name,
file=sys.stderr)
continue
else:
completed_filenames.update(name)
if os.path.isdir(name):
for root, directories, children in os.walk(unicode(name)):
filenames += [os.path.join(root, f) for f in children
if f.endswith('.py') and
not f.startswith('.')]
directories[:] = [d for d in directories
if not d.startswith('.')]
else:
print('---> Testing with ' + name,
file=sys.stderr)
if not run(os.path.join(name)):
return False
except (IndentationError,
tokenize.TokenError,
UnicodeDecodeError,
UnicodeEncodeError) as exception:
print('---> Skipping bad file {0} ({1})'.format(name, exception),
file=sys.stderr)
continue
return True
def main():
"""Run main."""
return 0 if check(process_args()) else 1
if __name__ == '__main__':
try:
sys.exit(main())
except KeyboardInterrupt:
sys.exit(1)
|
