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
|
# encoding: utf-8
from __future__ import print_function
# NOTE: run this script with LANG=en_US.UTF-8
import sys
from collections import defaultdict
import operator
import re
import subprocess
author_re = re.compile('(.*) <.*>')
pair_programming_re = re.compile(r'^\((.*?)\)')
excluded = set(["pypy", "convert-repo", "hgattic", 'Miss Islington (bot)',
"remote-hg", "Unknown"])
alias = {
'Anders Chrigstrom': ['arre'],
'Antonio Cuni': ['antocuni', 'anto', 'antonio'],
'Armin Rigo': ['arigo', 'arfigo', 'armin', 'arigato'],
'Maciej Fijałkowski': ['fijal', 'Maciej Fijalkowski'],
'Carl Friedrich Bolz-Tereick': ['Carl Friedrich Bolz', 'cfbolz', 'cf',
'cbolz', 'CF Bolz-Tereick'],
'Samuele Pedroni': ['pedronis', 'samuele', 'samule'],
'Richard Plangger': ['planrich', 'plan_rich'],
'Remi Meier': ['remi'],
'Michael Hudson-Doyle': ['mwh', 'Michael Hudson', 'michaelh'],
'Holger Krekel': ['hpk', 'holger krekel', 'holger', 'hufpk'],
"Amaury Forgeot d'Arc": ['afa', 'amauryfa@gmail.com', 'amaury'],
'Alex Gaynor': ['alex', 'agaynor'],
'David Schneider': ['bivab', 'david'],
'Christian Tismer': ['chris', 'christian', 'tismer',
'tismer@christia-wjtqxl.localdomain'],
'Benjamin Peterson': ['benjamin'],
'Håkan Ardö': ['hakan', 'hakanardo', 'Hakan Ardo'],
'Niklaus Haldimann': ['nik'],
'Alexander Schremmer': ['xoraxax'],
'Anders Hammarquist': ['iko'],
'David Edelsohn': ['edelsoh', 'edelsohn','opassembler.py'],
'Niko Matsakis': ['niko'],
'Jakub Gustak': ['jlg'],
'Guido Wesdorp': ['guido'],
'Michael Foord': ['mfoord'],
'Mark Pearse': ['mwp'],
'Eric van Riet Paap': ['ericvrp'],
'Jacob Hallen': ['jacob', 'jakob', 'jacob hallen'],
'Anders Lehmann': ['ale', 'anders'],
'Vanessa Freudenberg': ['bert', 'Bert Freudenberg'],
'Boris Feigin': ['boris', 'boria'],
'Valentino Volonghi': ['valentino', 'dialtone'],
'Aurelien Campeas': ['aurelien', 'aureliene'],
'Adrien Di Mascio': ['adim'],
'Jacek Generowicz': ['Jacek', 'jacek'],
'Jim Hunziker': ['landtuna@gmail.com'],
'Kristjan Valur Jonsson': ['kristjan@kristjan-lp.ccp.ad.local'],
'Laura Creighton': ['lac'],
'Aaron Iles': ['aliles'],
'Ludovic Aubry': ['ludal', 'ludovic'],
'Lukas Diekmann': ['l.diekmann', 'ldiekmann'],
'Matti Picus': ['Matti Picus matti.picus@gmail.com',
'matthp', 'mattip', 'mattip>', 'matti'],
'Michael Cheng': ['mikefc'],
'Richard Emslie': ['rxe'],
'Roberto De Ioris': ['roberto@goyle','roberto@mrspurr'],
'Sven Hager': ['hager'],
'Tomo Cocoa': ['cocoatomo'],
'Romain Guillebert': ['rguillebert', 'rguillbert', 'romain', 'Guillebert Romain'],
'Ronan Lamy': ['ronan'],
'Edd Barrett': ['edd'],
'Manuel Jacob': ['mjacob'],
'Rami Chowdhury': ['necaris'],
'Stanislaw Halik': ['Stanislaw Halik', 'w31rd0'],
'Wenzhu Man': ['wenzhu man', 'wenzhuman'],
'Anton Gulenko': ['anton gulenko', 'anton_gulenko'],
'Richard Lancaster': ['richardlancaster'],
'William Leslie': ['William ML Leslie'],
'Spenser Bauman': ['Spenser Andrew Bauman'],
'Raffael Tfirst': ['raffael.tfirst@gmail.com'],
'timo': ['timo@eistee.fritz.box'],
'Jasper Schulz': ['Jasper.Schulz', 'jbs'],
'Aaron Gallagher': ['"Aaron Gallagher'],
'Yasir Suhail': ['yasirs'],
'Squeaky': ['squeaky'],
"Dodan Mihai": ['mihai.dodan@gmail.com'],
'Wim Lavrijsen': ['wlav'],
'Toon Verwaest': ['toon', 'tverwaes'], #
'Seo Sanghyeon': ['sanxiyn'],
'Leonardo Santagada': ['santagada'],
'Laurence Tratt': ['ltratt'],
'Pieter Zieschang': ['pzieschang', 'p_zieschang@yahoo.de'],
'John Witulski': ['witulski'],
'Andrew Lawrence': ['andrew.lawrence@siemens.com', 'andrewjlawrence'],
'Batuhan Taskaya': ['isidentical'],
'Ondrej Baranovič': ['nulano', 'Nulano'],
'Brad Kish': ['rtkbkish'],
'Michał Górny': ['mgorny'],
'David Hewitt': ['davidhewitt'],
'Adrian Kuhn': ['akuhn'],
'David Malcolm': ['dmalcolm'],
'Simon Cross': ['hodgestar'],
'Łukasz Langa': ['ambv'],
'Wenzel Jakob': ['Jakob Wenzel'],
'Maxwell Bernstein': ['Max Bernstein'],
'Paul Gey': ['narpfel'],
'Bartosz Skowron': ['getxsick'],
'Beatrice During': ['bea'],
'Mikael Schönenberg': ['micke'],
'Oscar Nierstrasz': ['oscar'],
'Tim Felgentreff': ['timfel'],
'Tadeu Zagallo': ['tadeuzagallo'],
}
alias_map = {}
for name, nicks in alias.items():
for nick in nicks:
alias_map[nick] = name
def get_canonical_author(name):
match = author_re.match(name)
if match:
name = match.group(1)
return alias_map.get(name, name)
ignored_nicknames = defaultdict(int)
def get_more_authors(log):
match = pair_programming_re.match(log)
if not match:
return set()
ignore_words = ['around', 'consulting', 'yesterday', 'for a bit', 'thanks',
'in-progress', 'bits of', 'even a little', 'floating',
'a bit', 'reviewing', 'looking', 'advising', 'partly', 'ish',
'watching', 'mostly', 'jumping', 'twitch', 's390x']
sep_words = ['and', ';', '+', '/', 'with special by']
nicknames = match.group(1)
for word in ignore_words:
nicknames = nicknames.replace(word, '')
for word in sep_words:
nicknames = nicknames.replace(word, ',')
nicknames = [nick.strip().lower() for nick in nicknames.split(',')]
authors = set()
for nickname in nicknames:
if not nickname:
continue
author = alias_map.get(nickname)
if not author:
ignored_nicknames[nickname] += 1
else:
authors.add(author)
return authors
def main(show_numbers):
txt = subprocess.check_output(["git", "log", "--all", "--no-merges", '--format="%aN#<%aE>#%s"'], text=True)
authors_count = defaultdict(int)
with open("/tmp/authors", "wt", encoding="utf8") as fid:
fid.write(txt)
for line in txt.split('\n'):
if "#" not in line:
continue
if "#Notes added by" in line:
continue
author_src, author_mail, description = line.strip('"').split("#", 2)
authors = set()
authors.add(get_canonical_author(author_src))
authors.update(get_more_authors(description))
for author in authors:
if author not in excluded:
authors_count[author] += 1
# enable the next lines to get the list of nicknamed which could not be
# parsed from description
if 0:
items = list(ignored_nicknames.items())
items.sort(key=operator.itemgetter(1), reverse=True)
for name, n in items:
if show_numbers:
print("%5d '%s'" % (n, name))
else:
print("'%s'" % name)
return
items = list(authors_count.items())
items.sort(key=operator.itemgetter(1), reverse=True)
for name, n in items:
if show_numbers:
print('%5d %s' % (n, name))
else:
print(' ' + name)
if __name__ == '__main__':
show_numbers = '-n' in sys.argv
main(show_numbers)
|
