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
|
#!/usr/bin/env python3
import argparse
import subprocess
from typing import Any
parser = argparse.ArgumentParser()
parser.add_argument(
"rev", metavar="revision", type=str, help="the revision", default="HEAD", nargs="?"
)
args = parser.parse_args()
authors: dict[str, Any] = dict()
max_lenght_author = 0
max_lenght_email = 0
def get_files(rev):
"""Returns a list of files for the repository, at the given path, for the given revision."""
tree = subprocess.run(
["git", "ls-tree", "--name-only", "-r", rev],
capture_output=True,
check=True,
encoding="utf-8",
)
return tree.stdout.splitlines()
def line_info(filename, rev):
"""Generates a set of commit blocks using `git blame` for a file.
Each block corresponds to the information about a single line of code."""
blame = subprocess.run(
["git", "blame", "-w", "--line-porcelain", rev, "--", filename],
capture_output=True,
encoding="utf-8",
check=True,
)
block = []
for line in blame.stdout.splitlines():
block.append(line)
if line.startswith("\t"):
yield block
block = []
files = get_files(args.rev)
for filename in files:
try:
for block in line_info(filename.rstrip(), args.rev):
author = ""
author_email = ""
commit = ""
skip = False
for i, val in enumerate(block):
if i == 0:
commit = val.split()[0]
continue
if val.startswith("author "):
author = " ".join(val.split()[1:])
continue
if val.startswith("author-mail"):
author_email = " ".join(val.split()[1:])
continue
if val.startswith("\t") and val == "\t":
skip = True
if skip:
continue
if authors.get(author, None) is None:
authors[author] = {
"email": author_email,
"commits": set(),
"files": set(),
"lines": 0,
}
authors[author]["commits"].add(commit)
authors[author]["files"].add(filename)
authors[author]["lines"] += 1
if len(author) > max_lenght_author:
max_lenght_author = len(author)
if len(author_email) > max_lenght_email:
max_lenght_email = len(author_email)
except Exception:
continue
for author, stats in authors.items():
email = stats["email"]
lines = stats["lines"]
commits = len(stats["commits"])
files = len(stats["files"])
print(
f"{author:{max_lenght_author}} {email:{max_lenght_email}} {lines:6} {commits:6} {files:6}"
)
|
