Skip to content

gitstats: add support for python3 #97

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
gktrk wants to merge 1 commit into
base: master
Choose a base branch
from
Open

gitstats: add support for python3 #97

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
97 changes: 50 additions & 47 deletions gitstats
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,6 +1,9 @@
#!/usr/bin/env python2
#!/usr/bin/env python
# Copyright (c) 2007-2014 Heikki Hokkanen <hoxu@users.sf.net> & others (see doc/AUTHOR)
# GPLv2 / GPLv3

from __future__ import print_function

import datetime
import getopt
import glob
Expand All @@ -15,7 +18,7 @@ import time
import zlib

if sys.version_info < (2, 6):
print >> sys.stderr, "Python 2.6 or higher is required for gitstats"
print("Python 2.6 or higher is required for gitstats", file=sys.stderr)
sys.exit(1)

from multiprocessing import Pool
Expand Down Expand Up @@ -54,21 +57,21 @@ def getpipeoutput(cmds, quiet = False):
global exectime_external
start = time.time()
if not quiet and ON_LINUX and os.isatty(1):
print '>> ' + ' | '.join(cmds),
print('>> ' + ' | '.join(cmds), end=' ')
sys.stdout.flush()
p = subprocess.Popen(cmds[0], stdout = subprocess.PIPE, shell = True)
p = subprocess.Popen(cmds[0], stdout = subprocess.PIPE, shell = True, universal_newlines = True)
processes=[p]
for x in cmds[1:]:
p = subprocess.Popen(x, stdin = p.stdout, stdout = subprocess.PIPE, shell = True)
p = subprocess.Popen(x, stdin = p.stdout, stdout = subprocess.PIPE, shell = True, universal_newlines = True)
processes.append(p)
output = p.communicate()[0]
for p in processes:
p.wait()
end = time.time()
if not quiet:
if ON_LINUX and os.isatty(1):
print '\r',
print '[%.5f] >> %s' % (end - start, ' | '.join(cmds))
print('\r', end=' ')
print('[%.5f] >> %s' % (end - start, ' | '.join(cmds)))
exectime_external += (end - start)
return output.rstrip('\n')

Expand All @@ -86,11 +89,11 @@ def getcommitrange(defaultrange = 'HEAD', end_only = False):
return defaultrange

def getkeyssortedbyvalues(dict):
return map(lambda el : el[1], sorted(map(lambda el : (el[1], el[0]), dict.items())))
return [el[1] for el in sorted([(el[1], el[0]) for el in list(dict.items())])]
Copy link

@penguinolog penguinolog Nov 4, 2020 •
edited
Loading

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more. 

	return [el[1] for el in sorted(((val, key) for key, val in dict.items()))]


# dict['author'] = { 'commits': 512 } - ...key(dict, 'commits')
def getkeyssortedbyvaluekey(d, key):
return map(lambda el : el[1], sorted(map(lambda el : (d[el][key], el), d.keys())))
return [el[1] for el in sorted([(d[el][key], el) for el in list(d.keys())])]
Copy link

@penguinolog penguinolog Nov 4, 2020

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more. 

	return [el[1] for el in sorted(((v[key], k) for k, v in d.items()))]


def getstatsummarycounts(line):
numbers = re.findall('\d+', line)
Expand Down Expand Up @@ -207,7 +210,7 @@ class DataCollector:
def loadCache(self, cachefile):
if not os.path.exists(cachefile):
return
print 'Loading cache...'
print('Loading cache...')
f = open(cachefile, 'rb')
try:
self.cache = pickle.loads(zlib.decompress(f.read()))
Expand Down Expand Up @@ -269,7 +272,7 @@ class DataCollector:
##
# Save cacheable data
def saveCache(self, cachefile):
print 'Saving cache...'
print('Saving cache...')
tempfile = cachefile + '.tmp'
f = open(tempfile, 'wb')
#pickle.dump(self.cache, f)
Expand Down Expand Up @@ -308,7 +311,7 @@ class GitDataCollector(DataCollector):
self.tags[tag] = { 'stamp': stamp, 'hash' : hash, 'date' : datetime.datetime.fromtimestamp(stamp).strftime('%Y-%m-%d'), 'commits': 0, 'authors': {} }

# collect info on tags, starting from latest
tags_sorted_by_date_desc = map(lambda el : el[1], reversed(sorted(map(lambda el : (el[1]['date'], el[0]), self.tags.items()))))
tags_sorted_by_date_desc = [el[1] for el in reversed(sorted([(el[1]['date'], el[0]) for el in list(self.tags.items())]))]
prev = None
for tag in reversed(tags_sorted_by_date_desc):
cmd = 'git shortlog -s "%s"' % tag
Expand Down Expand Up @@ -444,10 +447,10 @@ class GitDataCollector(DataCollector):
time, rev = revline.split(' ')
#if cache empty then add time and rev to list of new rev's
#otherwise try to read needed info from cache
if 'files_in_tree' not in self.cache.keys():
if 'files_in_tree' not in list(self.cache.keys()):
revs_to_read.append((time,rev))
continue
if rev in self.cache['files_in_tree'].keys():
if rev in list(self.cache['files_in_tree'].keys()):
lines.append('%d %d' % (int(time), self.cache['files_in_tree'][rev]))
else:
revs_to_read.append((time,rev))
Expand All @@ -474,7 +477,7 @@ class GitDataCollector(DataCollector):
try:
self.files_by_stamp[int(stamp)] = int(files)
except ValueError:
print 'Warning: failed to parse line "%s"' % line
print('Warning: failed to parse line "%s"' % line)

# extensions and size of files
lines = getpipeoutput(['git ls-tree -r -l -z %s' % getcommitrange('HEAD', end_only = True)]).split('\000')
Expand Down Expand Up @@ -505,10 +508,10 @@ class GitDataCollector(DataCollector):
self.extensions[ext]['files'] += 1
#if cache empty then add ext and blob id to list of new blob's
#otherwise try to read needed info from cache
if 'lines_in_blob' not in self.cache.keys():
if 'lines_in_blob' not in list(self.cache.keys()):
blobs_to_read.append((ext,blob_id))
continue
if blob_id in self.cache['lines_in_blob'].keys():
if blob_id in list(self.cache['lines_in_blob'].keys()):
self.extensions[ext]['lines'] += self.cache['lines_in_blob'][blob_id]
else:
blobs_to_read.append((ext,blob_id))
Expand Down Expand Up @@ -563,21 +566,21 @@ class GitDataCollector(DataCollector):

files, inserted, deleted = 0, 0, 0
except ValueError:
print 'Warning: unexpected line "%s"' % line
print('Warning: unexpected line "%s"' % line)
else:
print 'Warning: unexpected line "%s"' % line
print('Warning: unexpected line "%s"' % line)
else:
numbers = getstatsummarycounts(line)

if len(numbers) == 3:
(files, inserted, deleted) = map(lambda el : int(el), numbers)
(files, inserted, deleted) = [int(el) for el in numbers]
total_lines += inserted
total_lines -= deleted
self.total_lines_added += inserted
self.total_lines_removed += deleted

else:
print 'Warning: failed to handle line "%s"' % line
print('Warning: failed to handle line "%s"' % line)
(files, inserted, deleted) = (0, 0, 0)
#self.changes_by_date[stamp] = { 'files': files, 'ins': inserted, 'del': deleted }
self.total_lines += total_lines
Expand Down Expand Up @@ -622,16 +625,16 @@ class GitDataCollector(DataCollector):
self.changes_by_date_by_author[stamp][author]['commits'] = self.authors[author]['commits']
files, inserted, deleted = 0, 0, 0
except ValueError:
print 'Warning: unexpected line "%s"' % line
print('Warning: unexpected line "%s"' % line)
else:
print 'Warning: unexpected line "%s"' % line
print('Warning: unexpected line "%s"' % line)
else:
numbers = getstatsummarycounts(line);

if len(numbers) == 3:
(files, inserted, deleted) = map(lambda el : int(el), numbers)
(files, inserted, deleted) = [int(el) for el in numbers]
else:
print 'Warning: failed to handle line "%s"' % line
print('Warning: failed to handle line "%s"' % line)
(files, inserted, deleted) = (0, 0, 0)

def refine(self):
Expand All @@ -642,7 +645,7 @@ class GitDataCollector(DataCollector):
for i, name in enumerate(self.authors_by_commits):
self.authors[name]['place_by_commits'] = i + 1

for name in self.authors.keys():
for name in list(self.authors.keys()):
a = self.authors[name]
a['commits_frac'] = (100 * float(a['commits'])) / self.getTotalCommits()
date_first = datetime.datetime.fromtimestamp(a['first_commit_stamp'])
Expand Down Expand Up @@ -678,7 +681,7 @@ class GitDataCollector(DataCollector):
return self.domains[domain]

def getDomains(self):
return self.domains.keys()
return list(self.domains.keys())

def getFirstCommitDate(self):
return datetime.datetime.fromtimestamp(self.first_commit_stamp)
Expand Down Expand Up @@ -744,7 +747,7 @@ class HTMLReportCreator(ReportCreator):
shutil.copyfile(src, path + '/' + file)
break
else:
print 'Warning: "%s" not found, so not copied (searched: %s)' % (file, basedirs)
print('Warning: "%s" not found, so not copied (searched: %s)' % (file, basedirs))

f = open(path + "/index.html", 'w')
format = '%Y-%m-%d %H:%M:%S'
Expand Down Expand Up @@ -942,7 +945,7 @@ class HTMLReportCreator(ReportCreator):
f.write('<th>Timezone</th><th>Commits</th>')
f.write('</tr>')
max_commits_on_tz = max(data.commits_by_timezone.values())
for i in sorted(data.commits_by_timezone.keys(), key = lambda n : int(n)):
for i in sorted(list(data.commits_by_timezone.keys()), key = lambda n : int(n)):
Copy link

@penguinolog penguinolog Nov 4, 2020

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

use generator expression: more memory efficient & faster

commits = data.commits_by_timezone[i]
r = 127 + int((float(commits) / max_commits_on_tz) * 128)
f.write('<tr><th>%s</th><td style="background-color: rgb(%d, 0, 0)">%d</td></tr>' % (i, r, commits))
Expand Down Expand Up @@ -1006,7 +1009,7 @@ class HTMLReportCreator(ReportCreator):
fgl.write('%d' % stamp)
fgc.write('%d' % stamp)
for author in self.authors_to_plot:
if author in data.changes_by_date_by_author[stamp].keys():
if author in list(data.changes_by_date_by_author[stamp].keys()):
Copy link

@penguinolog penguinolog Nov 4, 2020

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more. 

if author in data.changes_by_date_by_author[stamp]:

keys is checked for in expression

lines_by_authors[author] = data.changes_by_date_by_author[stamp][author]['lines_added']
commits_by_authors[author] = data.changes_by_date_by_author[stamp][author]['commits']
fgl.write(' %d' % lines_by_authors[author])
Expand Down Expand Up @@ -1153,7 +1156,7 @@ class HTMLReportCreator(ReportCreator):
f.write('<table class="tags">')
f.write('<tr><th>Name</th><th>Date</th><th>Commits</th><th>Authors</th></tr>')
# sort the tags by date desc
tags_sorted_by_date_desc = map(lambda el : el[1], reversed(sorted(map(lambda el : (el[1]['date'], el[0]), data.tags.items()))))
tags_sorted_by_date_desc = [el[1] for el in reversed(sorted([(el[1]['date'], el[0]) for el in list(data.tags.items())]))]
Copy link

@penguinolog penguinolog Nov 4, 2020 •
edited
Loading

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more. 

tags_sorted_by_date_desc = [(el[1] for el in sorted((v['date'], k) for k, v in data.tags.items()), reverse=True)]

for tag in tags_sorted_by_date_desc:
authorinfo = []
self.authors_by_commits = getkeyssortedbyvalues(data.tags[tag]['authors'])
Expand All @@ -1168,7 +1171,7 @@ class HTMLReportCreator(ReportCreator):
self.createGraphs(path)

def createGraphs(self, path):
print 'Generating graphs...'
print('Generating graphs...')

# hour of day
f = open(path + '/hour_of_day.plot', 'w')
Expand Down Expand Up @@ -1370,7 +1373,7 @@ plot """
for f in files:
out = getpipeoutput([gnuplot_cmd + ' "%s"' % f])
if len(out) > 0:
print out
print(out)

def printHeader(self, f, title = ''):
f.write(
Expand Down Expand Up @@ -1401,7 +1404,7 @@ plot """
""")

def usage():
print """
print("""
Usage: gitstats [options] <gitpath..> <outputpath>

Options:
Expand All @@ -1411,7 +1414,7 @@ Default config values:
%s

Please see the manual page for more details.
""" % conf
""" % conf)


class GitStats:
Expand Down Expand Up @@ -1442,48 +1445,48 @@ class GitStats:
except OSError:
pass
if not os.path.isdir(outputpath):
print 'FATAL: Output path is not a directory or does not exist'
print('FATAL: Output path is not a directory or does not exist')
sys.exit(1)

if not getgnuplotversion():
print 'gnuplot not found'
print('gnuplot not found')
sys.exit(1)

print 'Output path: %s' % outputpath
print('Output path: %s' % outputpath)
cachefile = os.path.join(outputpath, 'gitstats.cache')

data = GitDataCollector()
data.loadCache(cachefile)

for gitpath in args[0:-1]:
print 'Git path: %s' % gitpath
print('Git path: %s' % gitpath)

prevdir = os.getcwd()
os.chdir(gitpath)

print 'Collecting data...'
print('Collecting data...')
data.collect(gitpath)

os.chdir(prevdir)

print 'Refining data...'
print('Refining data...')
data.saveCache(cachefile)
data.refine()

os.chdir(rundir)

print 'Generating report...'
print('Generating report...')
report = HTMLReportCreator()
report.create(data, outputpath)

time_end = time.time()
exectime_internal = time_end - time_start
print 'Execution time %.5f secs, %.5f secs (%.2f %%) in external commands)' % (exectime_internal, exectime_external, (100.0 * exectime_external) / exectime_internal)
print('Execution time %.5f secs, %.5f secs (%.2f %%) in external commands)' % (exectime_internal, exectime_external, (100.0 * exectime_external) / exectime_internal))
if sys.stdin.isatty():
print 'You may now run:'
print
print ' sensible-browser \'%s\'' % os.path.join(outputpath, 'index.html').replace("'", "'\\''")
print
print('You may now run:')
print()
print(' sensible-browser \'%s\'' % os.path.join(outputpath, 'index.html').replace("'", "'\\''"))
print()

if __name__=='__main__':
g = GitStats()
Expand Down