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
|
#!/usr/bin/env python3
# SPDX-License-Identifier: MPL-2.0
# Copyright ijl (2026)
import asyncio
import datetime
import re
import subprocess
from collections import defaultdict
from pathlib import Path
REPOSITORY = Path(__file__).parent.parent
LICENSE_APACHE = "(Apache-2.0 OR MIT)"
LICENSE_MPL2 = "MPL-2.0"
SPACES = re.compile(r"[ ]{2,}")
TO_INCLUDE = {
".github/**/*.yaml",
"bench/*.py",
"bench/run",
"integration/*",
"pysrc/orjson/*",
"script/*",
"src/**/*.rs",
"test/**/*.py",
}
TO_EXCLUDE = {
"integration/http",
"script/cargo",
"script/debug",
"script/develop",
"script/install-fedora",
"script/lint",
"script/profile",
"script/pybench",
"script/pytest",
"script/valgrind",
"src/ffi/atomiculong.rs",
}
def aggregate_files() -> list[Path]:
files = []
files.append(REPOSITORY / Path("build.rs"))
for pattern in TO_INCLUDE:
files.extend(REPOSITORY.glob(pattern))
files = {
each
for each in files
if not str(each).endswith(("py.typed", "__pycache__", ".txt"))
}
for filename in TO_EXCLUDE:
files.remove(REPOSITORY / Path(filename))
return sorted(list(files))
SKIP_FRAGMENTS = (
"# Copyright",
"# SPDX",
"#!/usr",
"// Copyright",
"// SPDX",
)
def get_contributor_and_date(line: str) -> tuple[str, datetime.date] | None:
if not line or "Not Committed Yet" in line:
return None
end = line.index(")")
diff = line[end + 2 :]
diff = SPACES.sub(r" ", diff)
# skip blank and ' };' etc
if len(diff) <= 3:
return None
# skip headers and imports
for fragment in SKIP_FRAGMENTS:
if diff.startswith(fragment):
return None
line = line[line.index("(") + 1 : end]
line = SPACES.sub(r" ", line)
segments = line.split(" ")[0:-2]
contributor = " ".join(segments[:-1])
date = datetime.date.fromtimestamp(int(segments[-1])).year
return (contributor, date)
def process_blame(filename: Path, blame: str) -> list[str, list[str]] | None:
file_license = "(Apache-2.0 OR MIT)"
contributors = defaultdict(list)
document = blame.split("\n")
for line in document:
ret = get_contributor_and_date(line)
if ret:
contributors[ret[0]].append(ret[1])
overall_earliest = 9999
overall_latest = 0
file_credit = []
for contributor, dates in contributors.items():
earliest = min(dates)
latest = max(dates)
overall_latest = max((latest, overall_latest))
overall_earliest = min((latest, overall_earliest))
num_lines = len(dates)
if earliest == latest:
file_credit.append((num_lines, f"{contributor} ({earliest})"))
else:
file_credit.append((num_lines, f"{contributor} ({earliest}-{latest})"))
if (len(contributors) == 1 and "ijl" in contributors) or overall_earliest == 2026:
file_license = LICENSE_MPL2
file_credit.sort(reverse=True)
return [file_license, file_credit]
async def handle_file(filename: str):
blame = await asyncio.create_subprocess_shell(
f"git blame -C -C -C -M --date=raw {filename}",
shell=True,
stdout=asyncio.subprocess.PIPE,
stderr=asyncio.subprocess.PIPE,
)
header = process_blame(filename, (await blame.stdout.read()).decode("utf-8"))
if header is None:
print(f"{filename.relative_to(REPOSITORY)} skipping")
return
if not header[1] and str(filename).endswith("__init__.py"):
return
if str(filename).endswith(".rs"):
prefix = "//"
else:
prefix = "#"
spdx = f"{prefix} SPDX-License-Identifier: {header[0]}"
credit = f"{prefix} Copyright {', '.join(each[1] for each in header[1])}"
contents = filename.read_bytes().decode("utf-8").split("\n")
if contents[0].startswith("#!"):
start_idx = 1
else:
start_idx = 0
if contents[start_idx].startswith(f"{prefix} SPDX-License-Identifier"):
contents[start_idx] = spdx
else:
contents.insert(start_idx, spdx)
if contents[start_idx + 1].startswith(f"{prefix} Copyright"):
contents[start_idx + 1] = credit
else:
contents.insert(start_idx + 1, credit)
# separate by blank line
first_line = start_idx + 2
while contents[first_line].startswith(prefix):
first_line += 1
if len(contents[first_line]) > 0:
contents.insert(first_line, "")
print(f"{filename.relative_to(REPOSITORY)} {spdx}")
filename.write_bytes("\n".join(contents).encode("utf-8"))
async def main():
async with asyncio.TaskGroup() as tg:
for filename in aggregate_files():
tg.create_task(handle_file(filename))
if __name__ == "__main__":
asyncio.run(main())
|
