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
324
325
326
327#!/usr/bin/env python3
############################################################################
#
# SPDX-License-Identifier: Apache-2.0
#
# Licensed to the Apache Software Foundation (ASF) under one or more
# contributor license agreements. See the NOTICE file distributed with
# this work for additional information regarding copyright ownership. The
# ASF licenses this file to you under the Apache License, Version 2.0 (the
# "License"); you may not use this file except in compliance with the
# License. You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS, WITHOUT
# WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the
# License for the specific language governing permissions and limitations
# under the License.
#
############################################################################
import getopt
import json
import os
import re
import subprocess
import sys
import termcolor
committers_json = None
non_commiters_json = None
author_mappings_json = None
verbose_level = 0
color = True
def colored(s, c):
if color:
return termcolor.colored(s, c)
else:
return s
def commit_attributions(c):
regex = re.compile("(?i)(?:by|from|author|Co-authored-by):? +(.+)")
return re.findall(regex, c["message"]) + re.findall(regex, c["body"])
def get_headers(s):
return re.findall("(?i)/\*\*\*.+?(?:Copyright).+?\*\*\*+/", s, re.DOTALL)
def get_file(blob):
try:
return subprocess.check_output(
["git", "cat-file", "-p", blob], stderr=subprocess.DEVNULL
).decode()
except subprocess.CalledProcessError:
return None
def header_authors(header):
results = re.findall("[Aa]uthors?: +(.+?) *(?:Redistribution)", header, re.DOTALL)
results = [re.split("\n[ *]+", result) for result in results]
results = sum(results, []) # flatten
results = [
re.sub("[Cc]opyright:?( ?.[Cc].)? *([12][0-9]{3}[,-]? ?)", "", result)
for result in results
]
results = list(filter(lambda s: s != "", results)) # remove empty strings
return results
# Search for an author name in Apache's committers/non-committers
# database. It will return (apacheID,name) if there's a match or
# None if not. apacheID might be None if there's no Apache ID
# for author
def search_for_cla(name):
for k, v in committers_json["committers"].items():
if v == name:
return (k, v)
if name in non_committers_json["non_committers"]:
return (None, name)
return None
# Returns the same as above, but this takes an author
# (which may include an email include an email used
# to look for alternative author names for this person)
def author_has_cla(author):
if "@" in author:
matches = re.match("^(.+?)(?: +([^ ]+@[^ ]+ *))$", author)
if not matches:
return None # found an '@' but it wasn't an email, so this is most likely not really an author
name = matches.group(1)
email = matches.group(2).lstrip("<").rstrip(">")
else:
name = author.strip()
email = None
vvvprint("name: %s email: %s" % (name, email if email else "?"))
# first look for name directly
result = search_for_cla(name)
if result:
return result
# otherwise, get all available alternative names for author
# and look for each
if email and (email in author_mappings_json):
result = search_for_cla(author_mappings_json[email])
if result:
return result
# Nothing matched
return None
def header_copyrights(header):
results = re.findall(
" \* *[Cc]opyright:?(?: ?.[Cc].)? *(?:[12][0-9]{3}[,-]? ?)* *(.+)", header
)
return [re.sub("(. )?[Aa]ll rights reserved.?", "", result) for result in results]
def report_cla(author):
cla = author_has_cla(author)
if cla:
(apacheid, name) = cla
print(colored("✓", "green"), end=" ")
else:
apacheid = None
print(colored("✗", "red"), end=" ")
if apacheid:
print("%s (ID: %s)" % (author, apacheid))
else:
print(author)
def analyze(j):
complete_attributions = set()
complete_authors = set()
complete_copyrights = set()
vprint("file has %i commits" % len(j))
for commit in j:
authors = set()
vprint(colored("-", "yellow"))
vprint(colored("commit: ", "green") + commit["commit"])
vprint(colored("blob: ", "green") + commit["blob"])
vprint(colored("date: ", "green") + commit["date"])
vprint(
colored("author: ", "green")
+ ("%s <%s>" % (commit["author"], commit["author-email"]))
)
attributions = commit_attributions(commit)
if len(attributions) > 0:
vprint(colored("attributions:", "green"))
for attribution in attributions:
vprint(attribution)
complete_attributions |= set(attributions)
complete_authors |= set([commit["author"] + " " + commit["author-email"]])
# skip deletion commits
vprint(colored("blob:", "green"), end=" ")
if commit["blob"] == "0000000000000000000000000000000000000000":
vprint("zero (deletion)")
continue
file_contents = get_file(commit["blob"])
# skip inaccessible blobs (probably lived in a submodule)
if not file_contents:
vprint("inaccessible")
continue
else:
vprint("available")
headers = get_headers(file_contents)
vprint(colored("header authors:", "green"))
for header in headers:
ha = header_authors(header)
authors |= set(ha)
vprint(ha)
complete_authors |= set(authors)
vprint(colored("header copyrights:", "green"))
copyrights = set()
for header in headers:
hc = header_copyrights(header)
copyrights |= set(hc)
vprint(hc)
vprint(colored("commit description:", "green"))
vprint(commit["message"])
if commit["body"]:
vprint(colored("commit msg body:", "green"))
vprint(commit["body"])
vvprint(colored("headers:", "green"))
for header in headers:
vvprint(header)
complete_copyrights |= copyrights
vprint(colored("----\n", "yellow"))
print(colored("COMPLETE REPORT:", "blue"))
print(colored("attributions:", "green"))
if len(complete_attributions) == 0:
print("*none detected*")
else:
for attribution in complete_attributions:
report_cla(attribution)
print(colored("authors:", "green"))
for author in complete_authors:
report_cla(author)
print(colored("copyrights:", "green"))
print("\n".join(complete_copyrights))
def print_help():
print("Usage: check.py [-v] [-n] <JSON file>\n")
print(
" -v\tIncrease verbosity (add up to three times)\n"
" -n\tDo not use color for output"
)
def vprint(*args, **kwargs):
if verbose_level > 0:
print(*args, **kwargs)
def vvprint(*args, **kwargs):
if verbose_level > 1:
print(*args, **kwargs)
def vvvprint(*args, **kwargs):
if verbose_level > 2:
print(*args, **kwargs)
#####
# First try to load the CLAs JSONs:
try:
with open(
os.path.dirname(os.path.abspath(__file__)) + "/icla-info.json", "r"
) as file:
committers_json = json.load(file)
with open(
os.path.dirname(os.path.abspath(__file__)) + "/icla-info_noid.json", "r"
) as file:
non_committers_json = json.load(file)
except Exception:
print(
"Could not open CLA JSON files, please read README.md for download instructions"
)
sys.exit(2)
# Open author mappings JSON
with open(
os.path.dirname(os.path.abspath(__file__)) + "/author_mappings.json", "r"
) as file:
author_mappings_json = json.load(file)
try:
opts, args = getopt.getopt(sys.argv[1:], "hnv")
except getopt.GetoptError:
print_help()
sys.exit(2)
for opt, arg in opts:
if opt == "-h":
print_help()
sys.exit()
elif opt == "-v":
verbose_level = verbose_level + 1
elif opt == "-n":
color = False
if len(args) != 1:
print_help()
sys.exit(2)
f = args[0]
if not f:
print_help()
sys.exit(2)
if f == "-":
j = json.load(sys.stdin)
else:
with open(f, "r") as file:
j = json.load(file)
analyze(j)