def load_reviewers(filename):
reviewers_by_date = defaultdict(set)
with open(filename, 'rb') as f:
for line in f:
if line:
review_data = json.loads(line)
else:
continue
if 'comments' not in review_data:
continue
for review_comment in review_data['comments']:
when = review_comment['timestamp']
when = datetime.datetime.utcfromtimestamp(when).strftime(
'%Y-%m-%d')
reviewer = review_comment['reviewer']
if 'email' not in reviewer:
continue
email = '<%s>' % reviewer['email']
name_email = '%s %s' % (reviewer['name'], email)
# name_email = name_email.decode('utf8')
name_email = '%s %s' % (map_one_person(name_email), email)
if name_email.lower() in excluded_authors:
continue
reviewers_by_date[when].add(name_email)
return reviewers_by_date
def load_reviewers(filename):
reviewers_by_date = defaultdict(set)
with open(filename, 'rb') as f:
for line in f:
if line:
review_data = json.loads(line)
else:
continue
if 'comments' not in review_data:
continue
for review_comment in review_data['comments']:
when = review_comment['timestamp']
when = datetime.datetime.utcfromtimestamp(when).strftime('%Y-%m-%d')
reviewer = review_comment['reviewer']
if 'email' not in reviewer:
continue
email = '<%s>' % reviewer['email']
name_email = '%s %s' % (reviewer['name'], email)
# name_email = name_email.decode('utf8')
name_email = '%s %s' % (map_one_person(name_email), email)
if name_email.lower() in excluded_authors:
continue
reviewers_by_date[when].add(name_email)
return reviewers_by_date
# (days, (rolling_avg_span, ...))
(30, (180, 365)),
(7, (30, 180)),
]
actives = {x: [] for (x, _) in actives_windows}
rolling_sets = {x: RollingSet(x) for (x, _) in actives_windows}
actives_avg = {x: defaultdict(list) for (x, _) in actives_windows}
for date in date_range(global_first_date, global_last_date):
contribs = contribs_by_date.get(date, set())
reviews = reviewers_by_date.get(date, set())
mapped_contribs = set()
for person in contribs:
name, email = person.split('<', 1)
email = '<' + email
p = '%s %s' % (map_one_person(person), email)
if p.lower() in excluded_authors:
continue
mapped_contribs.add(name)
mapped_reviews = set()
for person in reviews:
name, email = person.split('<', 1)
email = '<' + email
p = '%s %s' % (map_one_person(person), email)
if p.lower() in excluded_authors:
continue
mapped_reviews.add(name)
people_by_date[date]['contribs'] = mapped_contribs
people_by_date[date]['reviews'] = mapped_reviews
unique_reviewer_set.update(mapped_reviews)
date_obj = datetime.datetime.strptime(date, '%Y-%m-%d')
return contribs_by_date, authors_by_count
def save_commits(data):
with open(COMMITS_FILENAME, 'wb') as f:
json.dump(data, f)
if __name__ == '__main__':
people_by_date = collections.defaultdict(list)
dates_by_person = collections.defaultdict(list)
for line in sys.stdin.readlines():
if not line.strip():
continue
name, email, timestamp = line.strip().split('|')
person = ('%s %s' % (name, email)).decode('utf8')
person = '%s %s' % (map_one_person(person), email)
if person.lower() in excluded_authors:
continue
ts = dateutil.parser.parse(timestamp).strftime('%Y-%m-%d')
people_by_date[ts].append(person)
dates_by_person[person].append(ts)
# fill in any missing days
first_date = min(people_by_date.keys())
for day in date_range(first_date, datetime.datetime.now()):
if day not in people_by_date:
people_by_date[day] = []
save_commits((people_by_date, dates_by_person))
