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
|
#!/usr/bin/env python3
"""
Utility for inspecting files in various ways.
This tool is like the collection of tools found in a unix environment but are
cross platform and stable and suitable for our needs in the test suite.
This can be used instead of tools like:
[
dd
find
head
hexdump
ls
md5sum
readlink
sha1sum
stat
tail
test
readlink.py
md5sum.py
"""
import binascii
import glob
import hashlib
import optparse
import os
import re
import sys
def iterbytes(s):
for i in range(len(s)):
yield s[i : i + 1]
def visit(opts, filenames, outfile):
"""Process filenames in the way specified in opts, writing output to
outfile."""
for f in sorted(filenames):
isstdin = f == '-'
if not isstdin and not os.path.lexists(f):
outfile.write(b'%s: file not found\n' % f.encode('utf-8'))
continue
quiet = opts.quiet and not opts.recurse or isstdin
isdir = os.path.isdir(f)
islink = os.path.islink(f)
isfile = os.path.isfile(f) and not islink
dirfiles = None
content = None
facts = []
if isfile:
if opts.type:
facts.append(b'file')
needs_reading = (
opts.hexdump,
opts.dump,
opts.md5,
opts.sha1,
opts.raw_sha1,
opts.sha256,
)
if any(needs_reading):
with open(f, 'rb') as fobj:
content = fobj.read()
elif islink:
if opts.type:
facts.append(b'link')
content = os.readlink(f).encode('utf8')
elif isstdin:
content = getattr(sys.stdin, 'buffer', sys.stdin).read()
if opts.size:
facts.append(b'size=%d' % len(content))
elif isdir:
if opts.recurse or opts.type:
dirfiles = glob.glob(f + '/*')
facts.append(b'directory with %d files' % len(dirfiles))
elif opts.type:
facts.append(b'type unknown')
if not isstdin:
stat = os.lstat(f)
if opts.size and not isdir:
facts.append(b'size=%d' % stat.st_size)
if opts.mode and not islink:
facts.append(b'mode=%o' % (stat.st_mode & 0o777))
if opts.links:
facts.append(b'links=%d' % stat.st_nlink)
if opts.newer:
# mtime might be in whole seconds so newer file might be same
if stat.st_mtime >= os.stat(opts.newer).st_mtime:
facts.append(
b'newer than %s' % opts.newer.encode('utf8', 'replace')
)
else:
facts.append(
b'older than %s' % opts.newer.encode('utf8', 'replace')
)
if opts.line_count and content is not None:
facts.append(b'line-count=%d' % len(content.splitlines()))
if opts.md5 and content is not None:
h = hashlib.md5(content)
facts.append(b'md5=%s' % binascii.hexlify(h.digest())[: opts.bytes])
if opts.raw_sha1 and content is not None:
h = hashlib.sha1(content)
facts.append(b'raw-sha1=%s' % h.digest()[: opts.bytes])
if opts.sha1 and content is not None:
h = hashlib.sha1(content)
facts.append(
b'sha1=%s' % binascii.hexlify(h.digest())[: opts.bytes]
)
if opts.sha256 and content is not None:
h = hashlib.sha256(content)
facts.append(
b'sha256=%s' % binascii.hexlify(h.digest())[: opts.bytes]
)
if isstdin:
outfile.write(b', '.join(facts) + b'\n')
elif facts:
outfile.write(b'%s: %s\n' % (f.encode('utf-8'), b', '.join(facts)))
elif not quiet:
outfile.write(b'%s:\n' % f.encode('utf-8'))
if content is not None:
chunk = content
if not islink:
if opts.lines:
if opts.lines >= 0:
chunk = b''.join(chunk.splitlines(True)[: opts.lines])
else:
chunk = b''.join(chunk.splitlines(True)[opts.lines :])
if opts.bytes:
if opts.bytes >= 0:
chunk = chunk[: opts.bytes]
else:
chunk = chunk[opts.bytes :]
if opts.hexdump:
for i in range(0, len(chunk), 16):
s = chunk[i : i + 16]
outfile.write(
b'%04x: %-47s |%s|\n'
% (
i,
b' '.join(b'%02x' % ord(c) for c in iterbytes(s)),
re.sub(b'[^ -~]', b'.', s),
)
)
if opts.dump:
if not quiet:
outfile.write(b'>>>\n')
outfile.write(chunk)
if not quiet:
if chunk.endswith(b'\n'):
outfile.write(b'<<<\n')
else:
outfile.write(b'\n<<< no trailing newline\n')
if opts.recurse and dirfiles:
assert not isstdin
visit(opts, dirfiles, outfile)
if __name__ == "__main__":
parser = optparse.OptionParser("%prog [options] [filenames]")
parser.add_option(
"-t",
"--type",
action="store_true",
help="show file type (file or directory)",
)
parser.add_option(
"-m", "--mode", action="store_true", help="show file mode"
)
parser.add_option(
"-l", "--links", action="store_true", help="show number of links"
)
parser.add_option(
"-s", "--size", action="store_true", help="show size of file"
)
parser.add_option(
"", "--line-count", action="store_true", help="show line count of file"
)
parser.add_option(
"-n", "--newer", action="store", help="check if file is newer (or same)"
)
parser.add_option(
"-r", "--recurse", action="store_true", help="recurse into directories"
)
parser.add_option(
"-S",
"--sha1",
action="store_true",
help="show sha1 hash of the content",
)
parser.add_option(
"",
"--raw-sha1",
action="store_true",
help="show raw bytes of the sha1 hash of the content",
)
parser.add_option(
"",
"--sha256",
action="store_true",
help="show sha256 hash of the content",
)
parser.add_option(
"-M", "--md5", action="store_true", help="show md5 hash of the content"
)
parser.add_option(
"-D", "--dump", action="store_true", help="dump file content"
)
parser.add_option(
"-H", "--hexdump", action="store_true", help="hexdump file content"
)
parser.add_option(
"-B", "--bytes", type="int", help="number of characters to dump"
)
parser.add_option(
"-L", "--lines", type="int", help="number of lines to dump"
)
parser.add_option(
"-q", "--quiet", action="store_true", help="no default output"
)
(opts, filenames) = parser.parse_args(sys.argv[1:])
if not filenames:
filenames = ['-']
visit(opts, filenames, getattr(sys.stdout, 'buffer', sys.stdout))
|
