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
|
#!/usr/bin/env python3
# Run with directory arguments from any directory, with no special setup
# required.
import os
from pathlib import Path
import re
import sys
from typing import Sequence
VERBOSE = False
copyrights = set()
def warn(s):
sys.stderr.write("warning: %s\n" % s)
def warn_verbose(s):
if VERBOSE:
warn(s)
def is_interesting(path_str: str) -> bool:
path = Path(path_str.lower())
uninteresting_extensions = [
".bp",
".map",
".md",
".mk",
".py",
".pyc",
".swp",
".txt",
]
if path.suffix in uninteresting_extensions:
return False
if path.name in {"notice", "readme", "pylintrc"}:
return False
# Backup files for some editors.
if path.match("*~"):
return False
return True
def is_auto_generated(content):
if "Generated by gensyscalls.py" in content or "generated by genserv.py" in content:
return True
if "This header was automatically generated from a Linux kernel header" in content:
return True
return False
def is_copyright_end(line: str, first_line_was_hash: bool) -> bool:
endings = [
" $FreeBSD: ",
"$Citrus$",
"$FreeBSD$",
"*/",
"From: @(#)",
# OpenBSD likes to say where stuff originally came from:
"Original version ID:",
"\t$Citrus: ",
"\t$NetBSD: ",
"\t$OpenBSD: ",
"\t@(#)",
"\tcitrus Id: ",
"\tfrom: @(#)",
"from OpenBSD:",
]
if first_line_was_hash and not line:
return True
for ending in endings:
if ending in line:
return True
return False
def extract_copyright_at(lines: Sequence[str], i: int) -> int:
first_line_was_hash = lines[i].startswith("#")
# Do we need to back up to find the start of the copyright header?
start = i
if not first_line_was_hash:
while start > 0:
if "/*" in lines[start - 1]:
break
start -= 1
# Read comment lines until we hit something that terminates a
# copyright header.
while i < len(lines):
if is_copyright_end(lines[i], first_line_was_hash):
break
i += 1
end = i
# Trim trailing cruft.
while end > 0:
line = lines[end - 1]
if line not in {
" *", " * ===================================================="
}:
break
end -= 1
# Remove C/assembler comment formatting, pulling out just the text.
clean_lines = []
for line in lines[start:end]:
line = line.replace("\t", " ")
line = line.replace("/* ", "")
line = re.sub(r"^ \* ", "", line)
line = line.replace("** ", "")
line = line.replace("# ", "")
if "SPDX-License-Identifier:" in line:
continue
if line.startswith("++Copyright++"):
continue
line = line.replace("--Copyright--", "")
line = line.rstrip()
# These come last and take care of "blank" comment lines.
if line in {"#", " *", "**", "-"}:
line = ""
clean_lines.append(line)
# Trim blank lines from head and tail.
while clean_lines[0] == "":
clean_lines = clean_lines[1:]
while clean_lines[len(clean_lines) - 1] == "":
clean_lines = clean_lines[0:(len(clean_lines) - 1)]
copyrights.add("\n".join(clean_lines))
return i
def do_file(path: str) -> None:
raw = Path(path).read_bytes()
try:
content = raw.decode("utf-8")
except UnicodeDecodeError:
warn("bad UTF-8 in %s" % path)
content = raw.decode("iso-8859-1")
lines = content.split("\n")
if len(lines) <= 4:
warn_verbose("ignoring short file %s" % path)
return
if is_auto_generated(content):
warn_verbose("ignoring auto-generated file %s" % path)
return
if not "Copyright" in content:
if "public domain" in content.lower():
warn_verbose("ignoring public domain file %s" % path)
return
warn('no copyright notice found in "%s" (%d lines)' %
(path, len(lines)))
return
# Manually iterate because extract_copyright_at tells us how many lines to
# skip.
i = 0
while i < len(lines):
if "Copyright" in lines[i] and not "@(#) Copyright" in lines[i]:
i = extract_copyright_at(lines, i)
else:
i += 1
def do_dir(arg):
for directory, sub_directories, filenames in os.walk(arg):
if ".git" in sub_directories:
sub_directories.remove(".git")
sub_directories = sorted(sub_directories)
for filename in sorted(filenames):
path = os.path.join(directory, filename)
if is_interesting(path):
do_file(path)
def main() -> None:
args = sys.argv[1:]
if len(args) == 0:
args = ["."]
for arg in args:
if os.path.isdir(arg):
do_dir(arg)
else:
do_file(arg)
for notice in sorted(copyrights):
print(notice)
print()
print("-" * 67)
print()
if __name__ == "__main__":
main()
|
