kallithea Files · scripts/shortlog.py

Files @ 3c503044e9f1

Branch filter:

Location: kallithea/scripts/shortlog.py

3c503044e9f1 1.0 KiB text/x-python Show Annotation Show as Raw Download as Raw

mads

mysql: bump sqlalchemy.url MariaDB/MySQL charset to to 'utf8mb4' to get full UTF-8 support

The change in 210e76d69b62 only changed character_set_database, as shown by output after:

--- a/kallithea/model/base.py
+++ b/kallithea/model/base.py
@@ -46,3 +46,8 @@ def init_model(engine):
engine_str = obfuscate_url_pw(str(engine.url))
log.info("initializing db for %s", engine_str)
meta.Base.metadata.bind = engine
+
+ meta.Session.configure(bind=engine)
+ for a, b in meta.Session().execute('''show variables''').fetchall():
+ if 'character_set_' in a:
+ print(a, repr(b))

Before, with charset=utf8, the utf8mb3 charset was used all the way through the stack:

[kallithea.model.base] initializing db for mysql://kallithea-test:XXXXX@localhost/kallithea-test?charset=utf8
character_set_client 'utf8'
character_set_connection 'utf8'
character_set_database 'utf8mb4'
character_set_filesystem 'binary'
character_set_results 'utf8'
character_set_server 'latin1'
character_set_system 'utf8'

With explicit charset=utf8mb4:

[kallithea.model.base] initializing db for mysql://kallithea-test:XXXXX@localhost/kallithea-test?charset=utf8mb4
character_set_client 'utf8mb4'
character_set_connection 'utf8mb4'
character_set_database 'utf8mb4'
character_set_filesystem 'binary'
character_set_results 'utf8mb4'
character_set_server 'latin1'
character_set_system 'utf8'

#!/usr/bin/env python3
# -*- coding: utf-8 -*-

"""
Kallithea script for generating a quick overview of contributors and their
commit counts in a given revision set.
"""
import argparse
import os
from collections import Counter

import contributor_data


def main():

    parser = argparse.ArgumentParser(description='Generate a list of committers and commit counts.')
    parser.add_argument('revset',
                        help='revision set specifying the commits to count')
    args = parser.parse_args()

    repo_entries = [
        (contributor_data.name_fixes.get(name) or contributor_data.name_fixes.get(name.rsplit('<', 1)[0].strip()) or name).rsplit('<', 1)[0].strip()
        for name in (line.strip()
         for line in os.popen("""hg log -r '%s' -T '{author}\n'""" % args.revset).readlines())
        ]

    counter = Counter(repo_entries)
    for name, count in counter.most_common():
        if name == '':
            continue
        print('%4s %s' % (count, name))


if __name__ == '__main__':
    main()