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
|
#!/usr/bin/python
# Run with directory arguments from any directory, with no special setup required.
# Or:
# for i in libc libdl libm linker libstdc++ ; do ./libc/tools/generate-NOTICE.py $i > $i/NOTICE ; done
import ftplib
import hashlib
import os
import re
import shutil
import string
import subprocess
import sys
import tarfile
import tempfile
def IsUninteresting(path):
path = path.lower()
if path.endswith(".mk") or path.endswith(".py") or path.endswith(".pyc") or path.endswith(".txt") or path.endswith(".3"):
return True
if path.endswith("/notice") or path.endswith("/readme") or path.endswith("/caveats"):
return True
if path.endswith("/tzdata") or path.endswith("/zoneinfo/generate"):
return True
return False
def IsAutoGenerated(content):
if "Generated by gensyscalls.py" in content or "generated by genserv.py" in content:
return True
if "This header was automatically generated from a Linux kernel header" in content:
return True
return False
copyrights = set()
def ExtractCopyrightAt(lines, i):
hash = lines[i].startswith("#")
# Do we need to back up to find the start of the copyright header?
start = i
if not hash:
while start > 0:
if "/*" in lines[start - 1]:
break
start -= 1
# Read comment lines until we hit something that terminates a
# copyright header.
while i < len(lines):
if "*/" in lines[i]:
break
if hash and len(lines[i]) == 0:
break
if "\t@(#)" in lines[i] or "\tfrom: @(#)" in lines[i] or "From: @(#)" in lines[i] or "from OpenBSD:" in lines[i]:
break
if "\tcitrus Id: " in lines[i]:
break
if "\t$Citrus: " in lines[i] or "\t$OpenBSD: " in lines[i] or " $FreeBSD: " in lines[i] or "\t$NetBSD: " in lines[i]:
break
if "$FreeBSD$" in lines[i] or "$Citrus$" in lines[i]:
break
# OpenBSD likes to say where stuff originally came from:
if "Original version ID:" in lines[i]:
break
i += 1
end = i
# Trim trailing cruft.
while end > 0:
if lines[end - 1] != " *" and lines[end - 1] != " * ====================================================":
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("^ \* ", "", line)
line = line.replace("** ", "")
line = line.replace("# ", "")
if line.startswith("++Copyright++"):
continue
line = line.replace("--Copyright--", "")
line = line.rstrip()
# These come last and take care of "blank" comment lines.
if line == "#" or line == " *" or line == "**" or line == "-":
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)]
copyright = "\n".join(clean_lines)
copyrights.add(copyright)
return i
args = sys.argv[1:]
if len(args) == 0:
args = [ "." ]
for arg in args:
sys.stderr.write('Searching for source files in "%s"...\n' % 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 IsUninteresting(path):
#print "ignoring uninteresting file %s" % path
continue
try:
content = open(path, 'r').read().decode('utf-8')
except:
sys.stderr.write('warning: bad UTF-8 in %s\n' % path)
content = open(path, 'r').read().decode('iso-8859-1')
lines = content.split("\n")
if len(lines) <= 4:
#print "ignoring short file %s" % path
continue
if IsAutoGenerated(content):
#print "ignoring auto-generated file %s" % path
continue
if not "Copyright" in content:
if "public domain" in content.lower():
#print "ignoring public domain file %s" % path
continue
sys.stderr.write('warning: no copyright notice found in "%s" (%d lines)\n' % (path, len(lines)))
continue
i = 0
while i < len(lines):
if "Copyright" in lines[i] and not "@(#) Copyright" in lines[i]:
i = ExtractCopyrightAt(lines, i)
i += 1
#print path
for copyright in sorted(copyrights):
print copyright.encode('utf-8')
print
print '-------------------------------------------------------------------'
print
sys.exit(0)
|
