forked from pandas-dev/pandas
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathannounce.py
executable file
·249 lines (193 loc) · 6.57 KB
/
announce.py
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
#!/usr/bin/env python3
"""
Script to generate contributor and pull request lists
This script generates contributor and pull request lists for release
announcements using GitHub v3 protocol. Use requires an authentication token in
order to have sufficient bandwidth, you can get one following the directions at
`<https://help.github.com/articles/creating-an-access-token-for-command-line-use/>_
Don't add any scope, as the default is read access to public information. The
token may be stored in an environment variable as you only get one chance to
see it.
Usage::
$ ./scripts/announce.py <token> <revision range>
The output is utf8 rst.
Dependencies
------------
- gitpython
- pygithub
Some code was copied from scipy `tools/gh_lists.py` and `tools/authors.py`.
Examples
--------
From the bash command line with $GITHUB token.
$ ./scripts/announce.py $GITHUB v1.11.0..v1.11.1 > announce.rst
"""
import codecs
import os
import re
import textwrap
from git import Repo
# Contributors to be renamed.
CONTRIBUTOR_MAPPING = {"znkjnffrezna": "znetbgcubravk"}
UTF8Writer = codecs.getwriter("utf8")
this_repo = Repo(os.path.join(os.path.dirname(__file__), "..", ".."))
author_msg = """\
A total of %d people contributed patches to this release. People with a
"+" by their names contributed a patch for the first time.
"""
pull_request_msg = """\
A total of %d pull requests were merged for this release.
"""
def get_authors(revision_range):
"""
Finds and returns authors within the revision range.
Parameters
-----------
revision_range : str
Revision range to search for authors.
Returns
-------
list[str]
List of authors in the revision range.
"""
pat = "^.*\\t(.*)$"
lst_release, cur_release = (r.strip() for r in revision_range.split(".."))
if "|" in cur_release:
# e.g. v1.0.1|HEAD
maybe_tag, head = cur_release.split("|")
assert head == "HEAD"
if maybe_tag in this_repo.tags:
cur_release = maybe_tag
else:
cur_release = head
revision_range = f"{lst_release}..{cur_release}"
# authors, in current release and previous to current release.
# We need two passes over the log for cur and prev, one to get the
# "Co-authored by" commits, which come from backports by the bot,
# and one for regular commits.
xpr = re.compile(r"Co-authored-by: (?P<name>[^<]+) ")
cur = set(
xpr.findall(
this_repo.git.log("--grep=Co-authored", "--pretty=%b", revision_range)
)
)
cur |= set(re.findall(pat, this_repo.git.shortlog("-s", revision_range), re.M))
pre = set(
xpr.findall(this_repo.git.log("--grep=Co-authored", "--pretty=%b", lst_release))
)
pre |= set(re.findall(pat, this_repo.git.shortlog("-s", lst_release), re.M))
# Homu is the author of auto merges, clean him out.
cur.discard("Homu")
pre.discard("Homu")
# Rename contributors according to mapping.
for old_name, new_name in CONTRIBUTOR_MAPPING.items():
old_name_decoded = codecs.decode(old_name, "rot13")
new_name_decoded = codecs.decode(new_name, "rot13")
if old_name_decoded in pre:
pre.discard(old_name_decoded)
pre.add(new_name_decoded)
if old_name_decoded in cur:
cur.discard(old_name_decoded)
cur.add(new_name_decoded)
# Append '+' to new authors.
authors = [s + " +" for s in cur - pre] + list(cur & pre)
authors.sort()
return authors
def get_pull_requests(repo, revision_range):
"""
Finds and returns pull requests within the revision range.
Parameters
-----------
repo : github.Repository.Repository
GitHub repository object.
revision_range : str
Revision range to search for pull requests.
Returns
-------
list[github.PullRequest.PullRequest]
List of pull requests in the revision range.
"""
prnums = []
# From regular merges
merges = this_repo.git.log("--oneline", "--merges", revision_range)
issues = re.findall("Merge pull request \\#(\\d*)", merges)
prnums.extend(int(s) for s in issues)
# From Homu merges (Auto merges)
issues = re.findall("Auto merge of \\#(\\d*)", merges)
prnums.extend(int(s) for s in issues)
# From fast forward squash-merges
commits = this_repo.git.log(
"--oneline", "--no-merges", "--first-parent", revision_range
)
issues = re.findall("^.*\\(\\#(\\d+)\\)$", commits, re.M)
prnums.extend(int(s) for s in issues)
# get PR data from GitHub repo
prnums.sort()
prs = [repo.get_pull(n) for n in prnums]
return prs
def build_components(revision_range, heading="Contributors"):
"""
Builds components for the release announcement.
Parameters
-----------
revision_range : str
Revision range to search for authors.
heading : str
Heading for the announcement.
Returns
-------
dict[str, str]
Dictionary containing the components for the announcement.
"""
lst_release, cur_release = (r.strip() for r in revision_range.split(".."))
authors = get_authors(revision_range)
return {
"heading": heading,
"author_message": author_msg % len(authors),
"authors": authors,
}
def build_string(revision_range, heading="Contributors"):
"""
Builds a string for the release announcement.
Parameters
-----------
revision_range : str
Revision range to search for authors.
heading : str
Heading for the announcement.
Returns
-------
str
String for the release announcement.
"""
components = build_components(revision_range, heading=heading)
components["uline"] = "=" * len(components["heading"])
components["authors"] = "* " + "\n* ".join(components["authors"])
# Don't change this to an fstring. It breaks the formatting.
tpl = textwrap.dedent(
"""\
{heading}
{uline}
{author_message}
{authors}"""
).format(**components)
return tpl
def main(revision_range):
"""
Main function for generating author lists for release.
Parameters
-----------
revision_range : str
Revision range to search for authors.
Returns
-------
None
"""
# document authors
text = build_string(revision_range)
print(text)
if __name__ == "__main__":
from argparse import ArgumentParser
parser = ArgumentParser(description="Generate author lists for release")
parser.add_argument("revision_range", help="<revision>..<revision>")
args = parser.parse_args()
main(args.revision_range)