2 # Copyright (c) 2007-2011 Heikki Hokkanen <hoxu@users.sf.net> & others (see doc/author.txt)
17 GNUPLOT_COMMON
= 'set terminal png transparent size 640,240\nset size 1.0,1.0\n'
18 ON_LINUX
= (platform
.system() == 'Linux')
19 WEEKDAYS
= ('Mon', 'Tue', 'Wed', 'Thu', 'Fri', 'Sat', 'Sun')
21 exectime_internal
= 0.0
22 exectime_external
= 0.0
23 time_start
= time
.time()
25 # By default, gnuplot is searched from path, but can be overridden with the
26 # environment variable "GNUPLOT"
27 gnuplot_cmd
= 'gnuplot'
28 if 'GNUPLOT' in os
.environ
:
29 gnuplot_cmd
= os
.environ
['GNUPLOT']
34 'style': 'gitstats.css',
39 'linear_linestats': 1,
43 def getpipeoutput(cmds
, quiet
= False):
44 global exectime_external
46 if not quiet
and ON_LINUX
and os
.isatty(1):
47 print '>> ' + ' | '.join(cmds
),
49 p0
= subprocess
.Popen(cmds
[0], stdout
= subprocess
.PIPE
, shell
= True)
52 p
= subprocess
.Popen(x
, stdin
= p0
.stdout
, stdout
= subprocess
.PIPE
, shell
= True)
54 output
= p
.communicate()[0]
57 if ON_LINUX
and os
.isatty(1):
59 print '[%.5f] >> %s' % (end
- start
, ' | '.join(cmds
))
60 exectime_external
+= (end
- start
)
61 return output
.rstrip('\n')
63 def getcommitrange(defaultrange
= 'HEAD', end_only
= False):
64 if len(conf
['commit_end']) > 0:
65 if end_only
or len(conf
['commit_begin']) == 0:
66 return conf
['commit_end']
67 return '%s..%s' % (conf
['commit_begin'], conf
['commit_end'])
70 def getkeyssortedbyvalues(dict):
71 return map(lambda el
: el
[1], sorted(map(lambda el
: (el
[1], el
[0]), dict.items())))
73 # dict['author'] = { 'commits': 512 } - ...key(dict, 'commits')
74 def getkeyssortedbyvaluekey(d
, key
):
75 return map(lambda el
: el
[1], sorted(map(lambda el
: (d
[el
][key
], el
), d
.keys())))
81 VERSION
= getpipeoutput(["git rev-parse --short %s" % getcommitrange('HEAD')]).split('\n')[0]
85 return getpipeoutput(['git --version']).split('\n')[0]
87 def getgnuplotversion():
88 return getpipeoutput(['gnuplot --version']).split('\n')[0]
91 """Manages data collection from a revision control repository."""
93 self
.stamp_created
= time
.time()
95 self
.total_authors
= 0
96 self
.activity_by_hour_of_day
= {} # hour -> commits
97 self
.activity_by_day_of_week
= {} # day -> commits
98 self
.activity_by_month_of_year
= {} # month [1-12] -> commits
99 self
.activity_by_hour_of_week
= {} # weekday -> hour -> commits
100 self
.activity_by_hour_of_day_busiest
= 0
101 self
.activity_by_hour_of_week_busiest
= 0
102 self
.activity_by_year_week
= {} # yy_wNN -> commits
103 self
.activity_by_year_week_peak
= 0
105 self
.authors
= {} # name -> {commits, first_commit_stamp, last_commit_stamp, last_active_day, active_days, lines_added, lines_removed}
107 self
.total_commits
= 0
109 self
.authors_by_commits
= 0
112 self
.domains
= {} # domain -> commits
114 # author of the month
115 self
.author_of_month
= {} # month -> author -> commits
116 self
.author_of_year
= {} # year -> author -> commits
117 self
.commits_by_month
= {} # month -> commits
118 self
.commits_by_year
= {} # year -> commits
119 self
.lines_added_by_month
= {} # month -> lines added
120 self
.lines_added_by_year
= {} # year -> lines added
121 self
.lines_removed_by_month
= {} # month -> lines removed
122 self
.lines_removed_by_year
= {} # year -> lines removed
123 self
.first_commit_stamp
= 0
124 self
.last_commit_stamp
= 0
125 self
.last_active_day
= None
126 self
.active_days
= set()
130 self
.total_lines_added
= 0
131 self
.total_lines_removed
= 0
134 self
.commits_by_timezone
= {} # timezone -> commits
139 self
.files_by_stamp
= {} # stamp -> files
142 self
.extensions
= {} # extension -> files, lines
145 self
.changes_by_date
= {} # stamp -> { files, ins, del }
148 # This should be the main function to extract data from the repository.
149 def collect(self
, dir):
151 if len(conf
['project_name']) == 0:
152 self
.projectname
= os
.path
.basename(os
.path
.abspath(dir))
154 self
.projectname
= conf
['project_name']
157 # Load cacheable data
158 def loadCache(self
, cachefile
):
159 if not os
.path
.exists(cachefile
):
161 print 'Loading cache...'
162 f
= open(cachefile
, 'rb')
164 self
.cache
= pickle
.loads(zlib
.decompress(f
.read()))
166 # temporary hack to upgrade non-compressed caches
168 self
.cache
= pickle
.load(f
)
172 # Produce any additional statistics from the extracted data.
177 # : get a dictionary of author
178 def getAuthorInfo(self
, author
):
181 def getActivityByDayOfWeek(self
):
184 def getActivityByHourOfDay(self
):
187 # : get a dictionary of domains
188 def getDomainInfo(self
, domain
):
192 # Get a list of authors
193 def getAuthors(self
):
196 def getFirstCommitDate(self
):
197 return datetime
.datetime
.now()
199 def getLastCommitDate(self
):
200 return datetime
.datetime
.now()
202 def getStampCreated(self
):
203 return self
.stamp_created
208 def getTotalAuthors(self
):
211 def getTotalCommits(self
):
214 def getTotalFiles(self
):
217 def getTotalLOC(self
):
221 # Save cacheable data
222 def saveCache(self
, cachefile
):
223 print 'Saving cache...'
224 f
= open(cachefile
, 'wb')
225 #pickle.dump(self.cache, f)
226 data
= zlib
.compress(pickle
.dumps(self
.cache
))
230 class GitDataCollector(DataCollector
):
231 def collect(self
, dir):
232 DataCollector
.collect(self
, dir)
235 self
.total_authors
+= int(getpipeoutput(['git shortlog -s %s' % getcommitrange(), 'wc -l']))
237 self
.total_authors
= 0
238 #self.total_lines = int(getoutput('git-ls-files -z |xargs -0 cat |wc -l'))
241 lines
= getpipeoutput(['git show-ref --tags']).split('\n')
245 (hash, tag
) = line
.split(' ')
247 tag
= tag
.replace('refs/tags/', '')
248 output
= getpipeoutput(['git log "%s" --pretty=format:"%%at %%aN" -n 1' % hash])
250 parts
= output
.split(' ')
253 stamp
= int(parts
[0])
256 self
.tags
[tag
] = { 'stamp': stamp
, 'hash' : hash, 'date' : datetime
.datetime
.fromtimestamp(stamp
).strftime('%Y-%m-%d'), 'commits': 0, 'authors': {} }
258 # collect info on tags, starting from latest
259 tags_sorted_by_date_desc
= map(lambda el
: el
[1], reversed(sorted(map(lambda el
: (el
[1]['date'], el
[0]), self
.tags
.items()))))
261 for tag
in reversed(tags_sorted_by_date_desc
):
262 cmd
= 'git shortlog -s "%s"' % tag
264 cmd
+= ' "^%s"' % prev
265 output
= getpipeoutput([cmd
])
269 for line
in output
.split('\n'):
270 parts
= re
.split('\s+', line
, 2)
271 commits
= int(parts
[1])
273 self
.tags
[tag
]['commits'] = commits
274 self
.tags
[tag
]['authors'][author
] = commits
276 # Collect revision statistics
277 # Outputs "<stamp> <date> <time> <timezone> <author> '<' <mail> '>'"
278 lines
= getpipeoutput(['git rev-list --pretty=format:"%%at %%ai %%aN <%%aE>" %s' % getcommitrange('HEAD'), 'grep -v ^commit']).split('\n')
280 parts
= line
.split(' ', 4)
283 stamp
= int(parts
[0])
287 author
, mail
= parts
[4].split('<', 1)
288 author
= author
.rstrip()
289 mail
= mail
.rstrip('>')
291 if mail
.find('@') != -1:
292 domain
= mail
.rsplit('@', 1)[1]
293 date
= datetime
.datetime
.fromtimestamp(float(stamp
))
295 # First and last commit stamp (may be in any order because of cherry-picking and patches)
296 if stamp
> self
.last_commit_stamp
:
297 self
.last_commit_stamp
= stamp
298 if self
.first_commit_stamp
== 0 or stamp
< self
.first_commit_stamp
:
299 self
.first_commit_stamp
= stamp
304 self
.activity_by_hour_of_day
[hour
] = self
.activity_by_hour_of_day
.get(hour
, 0) + 1
306 if self
.activity_by_hour_of_day
[hour
] > self
.activity_by_hour_of_day_busiest
:
307 self
.activity_by_hour_of_day_busiest
= self
.activity_by_hour_of_day
[hour
]
311 self
.activity_by_day_of_week
[day
] = self
.activity_by_day_of_week
.get(day
, 0) + 1
314 if domain
not in self
.domains
:
315 self
.domains
[domain
] = {}
317 self
.domains
[domain
]['commits'] = self
.domains
[domain
].get('commits', 0) + 1
320 if day
not in self
.activity_by_hour_of_week
:
321 self
.activity_by_hour_of_week
[day
] = {}
322 self
.activity_by_hour_of_week
[day
][hour
] = self
.activity_by_hour_of_week
[day
].get(hour
, 0) + 1
324 if self
.activity_by_hour_of_week
[day
][hour
] > self
.activity_by_hour_of_week_busiest
:
325 self
.activity_by_hour_of_week_busiest
= self
.activity_by_hour_of_week
[day
][hour
]
329 self
.activity_by_month_of_year
[month
] = self
.activity_by_month_of_year
.get(month
, 0) + 1
331 # yearly/weekly activity
332 yyw
= date
.strftime('%Y-%W')
333 self
.activity_by_year_week
[yyw
] = self
.activity_by_year_week
.get(yyw
, 0) + 1
334 if self
.activity_by_year_week_peak
< self
.activity_by_year_week
[yyw
]:
335 self
.activity_by_year_week_peak
= self
.activity_by_year_week
[yyw
]
338 if author
not in self
.authors
:
339 self
.authors
[author
] = {}
340 # commits, note again that commits may be in any date order because of cherry-picking and patches
341 if 'last_commit_stamp' not in self
.authors
[author
]:
342 self
.authors
[author
]['last_commit_stamp'] = stamp
343 if stamp
> self
.authors
[author
]['last_commit_stamp']:
344 self
.authors
[author
]['last_commit_stamp'] = stamp
345 if 'first_commit_stamp' not in self
.authors
[author
]:
346 self
.authors
[author
]['first_commit_stamp'] = stamp
347 if stamp
< self
.authors
[author
]['first_commit_stamp']:
348 self
.authors
[author
]['first_commit_stamp'] = stamp
350 # author of the month/year
351 yymm
= date
.strftime('%Y-%m')
352 if yymm
in self
.author_of_month
:
353 self
.author_of_month
[yymm
][author
] = self
.author_of_month
[yymm
].get(author
, 0) + 1
355 self
.author_of_month
[yymm
] = {}
356 self
.author_of_month
[yymm
][author
] = 1
357 self
.commits_by_month
[yymm
] = self
.commits_by_month
.get(yymm
, 0) + 1
360 if yy
in self
.author_of_year
:
361 self
.author_of_year
[yy
][author
] = self
.author_of_year
[yy
].get(author
, 0) + 1
363 self
.author_of_year
[yy
] = {}
364 self
.author_of_year
[yy
][author
] = 1
365 self
.commits_by_year
[yy
] = self
.commits_by_year
.get(yy
, 0) + 1
367 # authors: active days
368 yymmdd
= date
.strftime('%Y-%m-%d')
369 if 'last_active_day' not in self
.authors
[author
]:
370 self
.authors
[author
]['last_active_day'] = yymmdd
371 self
.authors
[author
]['active_days'] = set([yymmdd
])
372 elif yymmdd
!= self
.authors
[author
]['last_active_day']:
373 self
.authors
[author
]['last_active_day'] = yymmdd
374 self
.authors
[author
]['active_days'].add(yymmdd
)
376 # project: active days
377 if yymmdd
!= self
.last_active_day
:
378 self
.last_active_day
= yymmdd
379 self
.active_days
.add(yymmdd
)
382 self
.commits_by_timezone
[timezone
] = self
.commits_by_timezone
.get(timezone
, 0) + 1
384 # TODO Optimize this, it's the worst bottleneck
385 # outputs "<stamp> <files>" for each revision
386 revlines
= getpipeoutput(['git rev-list --pretty=format:"%%at %%T" %s' % getcommitrange('HEAD'), 'grep -v ^commit']).strip().split('\n')
388 for revline
in revlines
:
389 time
, rev
= revline
.split(' ')
390 linecount
= self
.getFilesInCommit(rev
)
391 lines
.append('%d %d' % (int(time
), linecount
))
393 self
.total_commits
+= len(lines
)
395 parts
= line
.split(' ')
398 (stamp
, files
) = parts
[0:2]
400 self
.files_by_stamp
[int(stamp
)] = int(files
)
402 print 'Warning: failed to parse line "%s"' % line
405 lines
= getpipeoutput(['git ls-tree -r -z %s' % getcommitrange('HEAD', end_only
= True)]).split('\000')
406 self
.total_files
+= len(lines
)
410 parts
= re
.split('\s+', line
, 4)
414 filename
= fullpath
.split('/')[-1] # strip directories
415 if filename
.find('.') == -1 or filename
.rfind('.') == 0:
418 ext
= filename
[(filename
.rfind('.') + 1):]
419 if len(ext
) > conf
['max_ext_length']:
422 if ext
not in self
.extensions
:
423 self
.extensions
[ext
] = {'files': 0, 'lines': 0}
425 self
.extensions
[ext
]['files'] += 1
427 self
.extensions
[ext
]['lines'] += self
.getLinesInBlob(sha1
)
429 print 'Warning: Could not count lines for file "%s"' % line
433 # N files changed, N insertions (+), N deletions(-)
435 self
.changes_by_date
= {} # stamp -> { files, ins, del }
436 # computation of lines of code by date is better done
437 # on a linear history.
439 if conf
['linear_linestats']:
440 extra
= '--first-parent -m'
441 lines
= getpipeoutput(['git log --shortstat %s --pretty=format:"%%at %%aN" %s' % (extra
, getcommitrange('HEAD'))]).split('\n')
443 files
= 0; inserted
= 0; deleted
= 0; total_lines
= 0
450 if line
.find('files changed,') == -1:
454 (stamp
, author
) = (int(line
[:pos
]), line
[pos
+1:])
455 self
.changes_by_date
[stamp
] = { 'files': files
, 'ins': inserted
, 'del': deleted
, 'lines': total_lines
}
457 date
= datetime
.datetime
.fromtimestamp(stamp
)
458 yymm
= date
.strftime('%Y-%m')
459 self
.lines_added_by_month
[yymm
] = self
.lines_added_by_month
.get(yymm
, 0) + inserted
460 self
.lines_removed_by_month
[yymm
] = self
.lines_removed_by_month
.get(yymm
, 0) + deleted
463 self
.lines_added_by_year
[yy
] = self
.lines_added_by_year
.get(yy
,0) + inserted
464 self
.lines_removed_by_year
[yy
] = self
.lines_removed_by_year
.get(yy
, 0) + deleted
466 files
, inserted
, deleted
= 0, 0, 0
468 print 'Warning: unexpected line "%s"' % line
470 print 'Warning: unexpected line "%s"' % line
472 numbers
= re
.findall('\d+', line
)
473 if len(numbers
) == 3:
474 (files
, inserted
, deleted
) = map(lambda el
: int(el
), numbers
)
475 total_lines
+= inserted
476 total_lines
-= deleted
477 self
.total_lines_added
+= inserted
478 self
.total_lines_removed
+= deleted
481 print 'Warning: failed to handle line "%s"' % line
482 (files
, inserted
, deleted
) = (0, 0, 0)
483 #self.changes_by_date[stamp] = { 'files': files, 'ins': inserted, 'del': deleted }
484 self
.total_lines
= total_lines
486 # Per-author statistics
488 # defined for stamp, author only if author commited at this timestamp.
489 self
.changes_by_date_by_author
= {} # stamp -> author -> lines_added
491 # Similar to the above, but never use --first-parent
492 # (we need to walk through every commit to know who
493 # committed what, not just through mainline)
494 lines
= getpipeoutput(['git log --shortstat --date-order --pretty=format:"%%at %%aN" %s' % (getcommitrange('HEAD'))]).split('\n')
496 files
= 0; inserted
= 0; deleted
= 0
504 if line
.find('files changed,') == -1:
509 (stamp
, author
) = (int(line
[:pos
]), line
[pos
+1:])
511 # clock skew, keep old timestamp to avoid having ugly graph
513 if author
not in self
.authors
:
514 self
.authors
[author
] = { 'lines_added' : 0, 'lines_removed' : 0, 'commits' : 0}
515 self
.authors
[author
]['commits'] = self
.authors
[author
].get('commits', 0) + 1
516 self
.authors
[author
]['lines_added'] = self
.authors
[author
].get('lines_added', 0) + inserted
517 self
.authors
[author
]['lines_removed'] = self
.authors
[author
].get('lines_removed', 0) + deleted
518 if stamp
not in self
.changes_by_date_by_author
:
519 self
.changes_by_date_by_author
[stamp
] = {}
520 if author
not in self
.changes_by_date_by_author
[stamp
]:
521 self
.changes_by_date_by_author
[stamp
][author
] = {}
522 self
.changes_by_date_by_author
[stamp
][author
]['lines_added'] = self
.authors
[author
]['lines_added']
523 self
.changes_by_date_by_author
[stamp
][author
]['commits'] = self
.authors
[author
]['commits']
524 files
, inserted
, deleted
= 0, 0, 0
526 print 'Warning: unexpected line "%s"' % line
528 print 'Warning: unexpected line "%s"' % line
530 numbers
= re
.findall('\d+', line
)
531 if len(numbers
) == 3:
532 (files
, inserted
, deleted
) = map(lambda el
: int(el
), numbers
)
534 print 'Warning: failed to handle line "%s"' % line
535 (files
, inserted
, deleted
) = (0, 0, 0)
539 # name -> {place_by_commits, commits_frac, date_first, date_last, timedelta}
540 self
.authors_by_commits
= getkeyssortedbyvaluekey(self
.authors
, 'commits')
541 self
.authors_by_commits
.reverse() # most first
542 for i
, name
in enumerate(self
.authors_by_commits
):
543 self
.authors
[name
]['place_by_commits'] = i
+ 1
545 for name
in self
.authors
.keys():
546 a
= self
.authors
[name
]
547 a
['commits_frac'] = (100 * float(a
['commits'])) / self
.getTotalCommits()
548 date_first
= datetime
.datetime
.fromtimestamp(a
['first_commit_stamp'])
549 date_last
= datetime
.datetime
.fromtimestamp(a
['last_commit_stamp'])
550 delta
= date_last
- date_first
551 a
['date_first'] = date_first
.strftime('%Y-%m-%d')
552 a
['date_last'] = date_last
.strftime('%Y-%m-%d')
553 a
['timedelta'] = delta
554 if 'lines_added' not in a
: a
['lines_added'] = 0
555 if 'lines_removed' not in a
: a
['lines_removed'] = 0
557 def getActiveDays(self
):
558 return self
.active_days
560 def getActivityByDayOfWeek(self
):
561 return self
.activity_by_day_of_week
563 def getActivityByHourOfDay(self
):
564 return self
.activity_by_hour_of_day
566 def getAuthorInfo(self
, author
):
567 return self
.authors
[author
]
569 def getAuthors(self
, limit
= None):
570 res
= getkeyssortedbyvaluekey(self
.authors
, 'commits')
574 def getCommitDeltaDays(self
):
575 return (self
.last_commit_stamp
- self
.first_commit_stamp
) / 86400 + 1
577 def getDomainInfo(self
, domain
):
578 return self
.domains
[domain
]
580 def getDomains(self
):
581 return self
.domains
.keys()
583 def getFilesInCommit(self
, rev
):
585 res
= self
.cache
['files_in_tree'][rev
]
587 res
= int(getpipeoutput(['git ls-tree -r --name-only "%s"' % rev
, 'wc -l']).split('\n')[0])
588 if 'files_in_tree' not in self
.cache
:
589 self
.cache
['files_in_tree'] = {}
590 self
.cache
['files_in_tree'][rev
] = res
594 def getFirstCommitDate(self
):
595 return datetime
.datetime
.fromtimestamp(self
.first_commit_stamp
)
597 def getLastCommitDate(self
):
598 return datetime
.datetime
.fromtimestamp(self
.last_commit_stamp
)
600 def getLinesInBlob(self
, sha1
):
602 res
= self
.cache
['lines_in_blob'][sha1
]
604 res
= int(getpipeoutput(['git cat-file blob %s' % sha1
, 'wc -l']).split()[0])
605 if 'lines_in_blob' not in self
.cache
:
606 self
.cache
['lines_in_blob'] = {}
607 self
.cache
['lines_in_blob'][sha1
] = res
611 lines
= getpipeoutput(['git show-ref --tags', 'cut -d/ -f3'])
612 return lines
.split('\n')
614 def getTagDate(self
, tag
):
615 return self
.revToDate('tags/' + tag
)
617 def getTotalAuthors(self
):
618 return self
.total_authors
620 def getTotalCommits(self
):
621 return self
.total_commits
623 def getTotalFiles(self
):
624 return self
.total_files
626 def getTotalLOC(self
):
627 return self
.total_lines
629 def revToDate(self
, rev
):
630 stamp
= int(getpipeoutput(['git log --pretty=format:%%at "%s" -n 1' % rev
]))
631 return datetime
.datetime
.fromtimestamp(stamp
).strftime('%Y-%m-%d')
634 """Creates the actual report based on given data."""
638 def create(self
, data
, path
):
642 def html_linkify(text
):
643 return text
.lower().replace(' ', '_')
645 def html_header(level
, text
):
646 name
= html_linkify(text
)
647 return '\n<h%d><a href="#%s" name="%s">%s</a></h%d>\n\n' % (level
, name
, name
, text
, level
)
649 class HTMLReportCreator(ReportCreator
):
650 def create(self
, data
, path
):
651 ReportCreator
.create(self
, data
, path
)
652 self
.title
= data
.projectname
654 # copy static files. Looks in the binary directory, ../share/gitstats and /usr/share/gitstats
655 binarypath
= os
.path
.dirname(os
.path
.abspath(__file__
))
656 secondarypath
= os
.path
.join(binarypath
, '..', 'share', 'gitstats')
657 basedirs
= [binarypath
, secondarypath
, '/usr/share/gitstats']
658 for file in ('gitstats.css', 'sortable.js', 'arrow-up.gif', 'arrow-down.gif', 'arrow-none.gif'):
659 for base
in basedirs
:
660 src
= base
+ '/' + file
661 if os
.path
.exists(src
):
662 shutil
.copyfile(src
, path
+ '/' + file)
665 print 'Warning: "%s" not found, so not copied (searched: %s)' % (file, basedirs
)
667 f
= open(path
+ "/index.html", 'w')
668 format
= '%Y-%m-%d %H:%M:%S'
671 f
.write('<h1>GitStats - %s</h1>' % data
.projectname
)
676 f
.write('<dt>Project name</dt><dd>%s</dd>' % (data
.projectname
))
677 f
.write('<dt>Generated</dt><dd>%s (in %d seconds)</dd>' % (datetime
.datetime
.now().strftime(format
), time
.time() - data
.getStampCreated()))
678 f
.write('<dt>Generator</dt><dd><a href="http://gitstats.sourceforge.net/">GitStats</a> (version %s), %s, %s</dd>' % (getversion(), getgitversion(), getgnuplotversion()))
679 f
.write('<dt>Report Period</dt><dd>%s to %s</dd>' % (data
.getFirstCommitDate().strftime(format
), data
.getLastCommitDate().strftime(format
)))
680 f
.write('<dt>Age</dt><dd>%d days, %d active days (%3.2f%%)</dd>' % (data
.getCommitDeltaDays(), len(data
.getActiveDays()), (100.0 * len(data
.getActiveDays()) / data
.getCommitDeltaDays())))
681 f
.write('<dt>Total Files</dt><dd>%s</dd>' % data
.getTotalFiles())
682 f
.write('<dt>Total Lines of Code</dt><dd>%s (%d added, %d removed)</dd>' % (data
.getTotalLOC(), data
.total_lines_added
, data
.total_lines_removed
))
683 f
.write('<dt>Total Commits</dt><dd>%s (average %.1f commits per active day, %.1f per all days)</dd>' % (data
.getTotalCommits(), float(data
.getTotalCommits()) / len(data
.getActiveDays()), float(data
.getTotalCommits()) / data
.getCommitDeltaDays()))
684 f
.write('<dt>Authors</dt><dd>%s (average %.1f commits per author)</dd>' % (data
.getTotalAuthors(), (1.0 * data
.getTotalCommits()) / data
.getTotalAuthors()))
687 f
.write('</body>\n</html>')
692 f
= open(path
+ '/activity.html', 'w')
694 f
.write('<h1>Activity</h1>')
697 #f.write('<h2>Last 30 days</h2>')
699 #f.write('<h2>Last 12 months</h2>')
703 f
.write(html_header(2, 'Weekly activity'))
704 f
.write('<p>Last %d weeks</p>' % WEEKS
)
706 # generate weeks to show (previous N weeks from now)
707 now
= datetime
.datetime
.now()
708 deltaweek
= datetime
.timedelta(7)
711 for i
in range(0, WEEKS
):
712 weeks
.insert(0, stampcur
.strftime('%Y-%W'))
713 stampcur
-= deltaweek
715 # top row: commits & bar
716 f
.write('<table class="noborders"><tr>')
717 for i
in range(0, WEEKS
):
719 if weeks
[i
] in data
.activity_by_year_week
:
720 commits
= data
.activity_by_year_week
[weeks
[i
]]
723 if weeks
[i
] in data
.activity_by_year_week
:
724 percentage
= float(data
.activity_by_year_week
[weeks
[i
]]) / data
.activity_by_year_week_peak
725 height
= max(1, int(200 * percentage
))
726 f
.write('<td style="text-align: center; vertical-align: bottom">%d<div style="display: block; background-color: red; width: 20px; height: %dpx"></div></td>' % (commits
, height
))
728 # bottom row: year/week
730 for i
in range(0, WEEKS
):
731 f
.write('<td>%s</td>' % (WEEKS
- i
))
732 f
.write('</tr></table>')
735 f
.write(html_header(2, 'Hour of Day'))
736 hour_of_day
= data
.getActivityByHourOfDay()
737 f
.write('<table><tr><th>Hour</th>')
738 for i
in range(0, 24):
739 f
.write('<th>%d</th>' % i
)
740 f
.write('</tr>\n<tr><th>Commits</th>')
741 fp
= open(path
+ '/hour_of_day.dat', 'w')
742 for i
in range(0, 24):
744 r
= 127 + int((float(hour_of_day
[i
]) / data
.activity_by_hour_of_day_busiest
) * 128)
745 f
.write('<td style="background-color: rgb(%d, 0, 0)">%d</td>' % (r
, hour_of_day
[i
]))
746 fp
.write('%d %d\n' % (i
, hour_of_day
[i
]))
748 f
.write('<td>0</td>')
749 fp
.write('%d 0\n' % i
)
751 f
.write('</tr>\n<tr><th>%</th>')
752 totalcommits
= data
.getTotalCommits()
753 for i
in range(0, 24):
755 r
= 127 + int((float(hour_of_day
[i
]) / data
.activity_by_hour_of_day_busiest
) * 128)
756 f
.write('<td style="background-color: rgb(%d, 0, 0)">%.2f</td>' % (r
, (100.0 * hour_of_day
[i
]) / totalcommits
))
758 f
.write('<td>0.00</td>')
759 f
.write('</tr></table>')
760 f
.write('<img src="hour_of_day.png" alt="Hour of Day" />')
761 fg
= open(path
+ '/hour_of_day.dat', 'w')
762 for i
in range(0, 24):
764 fg
.write('%d %d\n' % (i
+ 1, hour_of_day
[i
]))
766 fg
.write('%d 0\n' % (i
+ 1))
770 f
.write(html_header(2, 'Day of Week'))
771 day_of_week
= data
.getActivityByDayOfWeek()
772 f
.write('<div class="vtable"><table>')
773 f
.write('<tr><th>Day</th><th>Total (%)</th></tr>')
774 fp
= open(path
+ '/day_of_week.dat', 'w')
775 for d
in range(0, 7):
778 commits
= day_of_week
[d
]
779 fp
.write('%d %s %d\n' % (d
+ 1, WEEKDAYS
[d
], commits
))
781 f
.write('<th>%s</th>' % (WEEKDAYS
[d
]))
783 f
.write('<td>%d (%.2f%%)</td>' % (day_of_week
[d
], (100.0 * day_of_week
[d
]) / totalcommits
))
785 f
.write('<td>0</td>')
787 f
.write('</table></div>')
788 f
.write('<img src="day_of_week.png" alt="Day of Week" />')
792 f
.write(html_header(2, 'Hour of Week'))
795 f
.write('<tr><th>Weekday</th>')
796 for hour
in range(0, 24):
797 f
.write('<th>%d</th>' % (hour
))
800 for weekday
in range(0, 7):
801 f
.write('<tr><th>%s</th>' % (WEEKDAYS
[weekday
]))
802 for hour
in range(0, 24):
804 commits
= data
.activity_by_hour_of_week
[weekday
][hour
]
809 r
= 127 + int((float(commits
) / data
.activity_by_hour_of_week_busiest
) * 128)
810 f
.write(' style="background-color: rgb(%d, 0, 0)"' % r
)
811 f
.write('>%d</td>' % commits
)
819 f
.write(html_header(2, 'Month of Year'))
820 f
.write('<div class="vtable"><table>')
821 f
.write('<tr><th>Month</th><th>Commits (%)</th></tr>')
822 fp
= open (path
+ '/month_of_year.dat', 'w')
823 for mm
in range(1, 13):
825 if mm
in data
.activity_by_month_of_year
:
826 commits
= data
.activity_by_month_of_year
[mm
]
827 f
.write('<tr><td>%d</td><td>%d (%.2f %%)</td></tr>' % (mm
, commits
, (100.0 * commits
) / data
.getTotalCommits()))
828 fp
.write('%d %d\n' % (mm
, commits
))
830 f
.write('</table></div>')
831 f
.write('<img src="month_of_year.png" alt="Month of Year" />')
833 # Commits by year/month
834 f
.write(html_header(2, 'Commits by year/month'))
835 f
.write('<div class="vtable"><table><tr><th>Month</th><th>Commits</th><th>Lines added</th><th>Lines removed</th></tr>')
836 for yymm
in reversed(sorted(data
.commits_by_month
.keys())):
837 f
.write('<tr><td>%s</td><td>%d</td><td>%d</td><td>%d</td></tr>' % (yymm
, data
.commits_by_month
[yymm
], data
.lines_added_by_month
[yymm
], data
.lines_removed_by_month
[yymm
]))
838 f
.write('</table></div>')
839 f
.write('<img src="commits_by_year_month.png" alt="Commits by year/month" />')
840 fg
= open(path
+ '/commits_by_year_month.dat', 'w')
841 for yymm
in sorted(data
.commits_by_month
.keys()):
842 fg
.write('%s %s\n' % (yymm
, data
.commits_by_month
[yymm
]))
846 f
.write(html_header(2, 'Commits by Year'))
847 f
.write('<div class="vtable"><table><tr><th>Year</th><th>Commits (% of all)</th><th>Lines added</th><th>Lines removed</th></tr>')
848 for yy
in reversed(sorted(data
.commits_by_year
.keys())):
849 f
.write('<tr><td>%s</td><td>%d (%.2f%%)</td><td>%d</td><td>%d</td></tr>' % (yy
, data
.commits_by_year
[yy
], (100.0 * data
.commits_by_year
[yy
]) / data
.getTotalCommits(), data
.lines_added_by_year
[yy
], data
.lines_removed_by_year
[yy
]))
850 f
.write('</table></div>')
851 f
.write('<img src="commits_by_year.png" alt="Commits by Year" />')
852 fg
= open(path
+ '/commits_by_year.dat', 'w')
853 for yy
in sorted(data
.commits_by_year
.keys()):
854 fg
.write('%d %d\n' % (yy
, data
.commits_by_year
[yy
]))
857 # Commits by timezone
858 f
.write(html_header(2, 'Commits by Timezone'))
859 f
.write('<table><tr>')
860 f
.write('<th>Timezone</th><th>Commits</th>')
861 max_commits_on_tz
= max(data
.commits_by_timezone
.values())
862 for i
in sorted(data
.commits_by_timezone
.keys(), key
= lambda n
: int(n
)):
863 commits
= data
.commits_by_timezone
[i
]
864 r
= 127 + int((float(commits
) / max_commits_on_tz
) * 128)
865 f
.write('<tr><th>%s</th><td style="background-color: rgb(%d, 0, 0)">%d</td></tr>' % (i
, r
, commits
))
866 f
.write('</tr></table>')
868 f
.write('</body></html>')
873 f
= open(path
+ '/authors.html', 'w')
876 f
.write('<h1>Authors</h1>')
879 # Authors :: List of authors
880 f
.write(html_header(2, 'List of Authors'))
882 f
.write('<table class="authors sortable" id="authors">')
883 f
.write('<tr><th>Author</th><th>Commits (%)</th><th>+ lines</th><th>- lines</th><th>First commit</th><th>Last commit</th><th class="unsortable">Age</th><th>Active days</th><th># by commits</th></tr>')
884 for author
in data
.getAuthors(conf
['max_authors']):
885 info
= data
.getAuthorInfo(author
)
886 f
.write('<tr><td>%s</td><td>%d (%.2f%%)</td><td>%d</td><td>%d</td><td>%s</td><td>%s</td><td>%s</td><td>%d</td><td>%d</td></tr>' % (author
, info
['commits'], info
['commits_frac'], info
['lines_added'], info
['lines_removed'], info
['date_first'], info
['date_last'], info
['timedelta'], len(info
['active_days']), info
['place_by_commits']))
889 allauthors
= data
.getAuthors()
890 if len(allauthors
) > conf
['max_authors']:
891 rest
= allauthors
[conf
['max_authors']:]
892 f
.write('<p class="moreauthors">These didn\'t make it to the top: %s</p>' % ', '.join(rest
))
894 f
.write(html_header(2, 'Cumulated Added Lines of Code per Author'))
895 f
.write('<img src="lines_of_code_by_author.png" alt="Lines of code per Author" />')
896 if len(allauthors
) > conf
['max_authors']:
897 f
.write('<p class="moreauthors">Only top %d authors shown</p>' % conf
['max_authors'])
899 f
.write(html_header(2, 'Commits per Author'))
900 f
.write('<img src="commits_by_author.png" alt="Commits per Author" />')
901 if len(allauthors
) > conf
['max_authors']:
902 f
.write('<p class="moreauthors">Only top %d authors shown</p>' % conf
['max_authors'])
904 fgl
= open(path
+ '/lines_of_code_by_author.dat', 'w')
905 fgc
= open(path
+ '/commits_by_author.dat', 'w')
907 lines_by_authors
= {} # cumulated added lines by
908 # author. to save memory,
909 # changes_by_date_by_author[stamp][author] is defined
910 # only at points where author commits.
911 # lines_by_authors allows us to generate all the
912 # points in the .dat file.
914 # Don't rely on getAuthors to give the same order each
915 # time. Be robust and keep the list in a variable.
916 commits_by_authors
= {} # cumulated added lines by
918 self
.authors_to_plot
= data
.getAuthors(conf
['max_authors'])
919 for author
in self
.authors_to_plot
:
920 lines_by_authors
[author
] = 0
921 commits_by_authors
[author
] = 0
922 for stamp
in sorted(data
.changes_by_date_by_author
.keys()):
923 fgl
.write('%d' % stamp
)
924 fgc
.write('%d' % stamp
)
925 for author
in self
.authors_to_plot
:
926 if author
in data
.changes_by_date_by_author
[stamp
].keys():
927 lines_by_authors
[author
] = data
.changes_by_date_by_author
[stamp
][author
]['lines_added']
928 commits_by_authors
[author
] = data
.changes_by_date_by_author
[stamp
][author
]['commits']
929 fgl
.write(' %d' % lines_by_authors
[author
])
930 fgc
.write(' %d' % commits_by_authors
[author
])
936 # Authors :: Author of Month
937 f
.write(html_header(2, 'Author of Month'))
938 f
.write('<table class="sortable" id="aom">')
939 f
.write('<tr><th>Month</th><th>Author</th><th>Commits (%%)</th><th class="unsortable">Next top %d</th><th>Number of authors</th></tr>' % conf
['authors_top'])
940 for yymm
in reversed(sorted(data
.author_of_month
.keys())):
941 authordict
= data
.author_of_month
[yymm
]
942 authors
= getkeyssortedbyvalues(authordict
)
944 commits
= data
.author_of_month
[yymm
][authors
[0]]
945 next
= ', '.join(authors
[1:conf
['authors_top']+1])
946 f
.write('<tr><td>%s</td><td>%s</td><td>%d (%.2f%% of %d)</td><td>%s</td><td>%d</td></tr>' % (yymm
, authors
[0], commits
, (100.0 * commits
) / data
.commits_by_month
[yymm
], data
.commits_by_month
[yymm
], next
, len(authors
)))
950 f
.write(html_header(2, 'Author of Year'))
951 f
.write('<table class="sortable" id="aoy"><tr><th>Year</th><th>Author</th><th>Commits (%%)</th><th class="unsortable">Next top %d</th><th>Number of authors</th></tr>' % conf
['authors_top'])
952 for yy
in reversed(sorted(data
.author_of_year
.keys())):
953 authordict
= data
.author_of_year
[yy
]
954 authors
= getkeyssortedbyvalues(authordict
)
956 commits
= data
.author_of_year
[yy
][authors
[0]]
957 next
= ', '.join(authors
[1:conf
['authors_top']+1])
958 f
.write('<tr><td>%s</td><td>%s</td><td>%d (%.2f%% of %d)</td><td>%s</td><td>%d</td></tr>' % (yy
, authors
[0], commits
, (100.0 * commits
) / data
.commits_by_year
[yy
], data
.commits_by_year
[yy
], next
, len(authors
)))
962 f
.write(html_header(2, 'Commits by Domains'))
963 domains_by_commits
= getkeyssortedbyvaluekey(data
.domains
, 'commits')
964 domains_by_commits
.reverse() # most first
965 f
.write('<div class="vtable"><table>')
966 f
.write('<tr><th>Domains</th><th>Total (%)</th></tr>')
967 fp
= open(path
+ '/domains.dat', 'w')
969 for domain
in domains_by_commits
:
970 if n
== conf
['max_domains']:
974 info
= data
.getDomainInfo(domain
)
975 fp
.write('%s %d %d\n' % (domain
, n
, info
['commits']))
976 f
.write('<tr><th>%s</th><td>%d (%.2f%%)</td></tr>' % (domain
, info
['commits'], (100.0 * info
['commits'] / totalcommits
)))
977 f
.write('</table></div>')
978 f
.write('<img src="domains.png" alt="Commits by Domains" />')
981 f
.write('</body></html>')
986 f
= open(path
+ '/files.html', 'w')
988 f
.write('<h1>Files</h1>')
992 f
.write('<dt>Total files</dt><dd>%d</dd>' % data
.getTotalFiles())
993 f
.write('<dt>Total lines</dt><dd>%d</dd>' % data
.getTotalLOC())
994 f
.write('<dt>Average file size</dt><dd>%.2f bytes</dd>' % ((100.0 * data
.getTotalLOC()) / data
.getTotalFiles()))
997 # Files :: File count by date
998 f
.write(html_header(2, 'File count by date'))
1000 # use set to get rid of duplicate/unnecessary entries
1001 files_by_date
= set()
1002 for stamp
in sorted(data
.files_by_stamp
.keys()):
1003 files_by_date
.add('%s %d' % (datetime
.datetime
.fromtimestamp(stamp
).strftime('%Y-%m-%d'), data
.files_by_stamp
[stamp
]))
1005 fg
= open(path
+ '/files_by_date.dat', 'w')
1006 for line
in sorted(list(files_by_date
)):
1007 fg
.write('%s\n' % line
)
1008 #for stamp in sorted(data.files_by_stamp.keys()):
1009 # fg.write('%s %d\n' % (datetime.datetime.fromtimestamp(stamp).strftime('%Y-%m-%d'), data.files_by_stamp[stamp]))
1012 f
.write('<img src="files_by_date.png" alt="Files by Date" />')
1014 #f.write('<h2>Average file size by date</h2>')
1016 # Files :: Extensions
1017 f
.write(html_header(2, 'Extensions'))
1018 f
.write('<table class="sortable" id="ext"><tr><th>Extension</th><th>Files (%)</th><th>Lines (%)</th><th>Lines/file</th></tr>')
1019 for ext
in sorted(data
.extensions
.keys()):
1020 files
= data
.extensions
[ext
]['files']
1021 lines
= data
.extensions
[ext
]['lines']
1022 f
.write('<tr><td>%s</td><td>%d (%.2f%%)</td><td>%d (%.2f%%)</td><td>%d</td></tr>' % (ext
, files
, (100.0 * files
) / data
.getTotalFiles(), lines
, (100.0 * lines
) / data
.getTotalLOC(), lines
/ files
))
1025 f
.write('</body></html>')
1030 f
= open(path
+ '/lines.html', 'w')
1032 f
.write('<h1>Lines</h1>')
1036 f
.write('<dt>Total lines</dt><dd>%d</dd>' % data
.getTotalLOC())
1039 f
.write(html_header(2, 'Lines of Code'))
1040 f
.write('<img src="lines_of_code.png" />')
1042 fg
= open(path
+ '/lines_of_code.dat', 'w')
1043 for stamp
in sorted(data
.changes_by_date
.keys()):
1044 fg
.write('%d %d\n' % (stamp
, data
.changes_by_date
[stamp
]['lines']))
1047 f
.write('</body></html>')
1052 f
= open(path
+ '/tags.html', 'w')
1054 f
.write('<h1>Tags</h1>')
1058 f
.write('<dt>Total tags</dt><dd>%d</dd>' % len(data
.tags
))
1059 if len(data
.tags
) > 0:
1060 f
.write('<dt>Average commits per tag</dt><dd>%.2f</dd>' % (1.0 * data
.getTotalCommits() / len(data
.tags
)))
1063 f
.write('<table class="tags">')
1064 f
.write('<tr><th>Name</th><th>Date</th><th>Commits</th><th>Authors</th></tr>')
1065 # sort the tags by date desc
1066 tags_sorted_by_date_desc
= map(lambda el
: el
[1], reversed(sorted(map(lambda el
: (el
[1]['date'], el
[0]), data
.tags
.items()))))
1067 for tag
in tags_sorted_by_date_desc
:
1069 self
.authors_by_commits
= getkeyssortedbyvalues(data
.tags
[tag
]['authors'])
1070 for i
in reversed(self
.authors_by_commits
):
1071 authorinfo
.append('%s (%d)' % (i
, data
.tags
[tag
]['authors'][i
]))
1072 f
.write('<tr><td>%s</td><td>%s</td><td>%d</td><td>%s</td></tr>' % (tag
, data
.tags
[tag
]['date'], data
.tags
[tag
]['commits'], ', '.join(authorinfo
)))
1075 f
.write('</body></html>')
1078 self
.createGraphs(path
)
1080 def createGraphs(self
, path
):
1081 print 'Generating graphs...'
1084 f
= open(path
+ '/hour_of_day.plot', 'w')
1085 f
.write(GNUPLOT_COMMON
)
1088 set output 'hour_of_day.png'
1090 set xrange [0.5:24.5]
1093 set ylabel "Commits"
1094 plot 'hour_of_day.dat' using 1:2:(0.5) w boxes fs solid
1099 f
= open(path
+ '/day_of_week.plot', 'w')
1100 f
.write(GNUPLOT_COMMON
)
1103 set output 'day_of_week.png'
1105 set xrange [0.5:7.5]
1108 set ylabel "Commits"
1109 plot 'day_of_week.dat' using 1:3:(0.5):xtic(2) w boxes fs solid
1114 f
= open(path
+ '/domains.plot', 'w')
1115 f
.write(GNUPLOT_COMMON
)
1118 set output 'domains.png'
1123 set ylabel "Commits"
1124 plot 'domains.dat' using 2:3:(0.5) with boxes fs solid, '' using 2:3:1 with labels rotate by 45 offset 0,1
1129 f
= open(path
+ '/month_of_year.plot', 'w')
1130 f
.write(GNUPLOT_COMMON
)
1133 set output 'month_of_year.png'
1135 set xrange [0.5:12.5]
1138 set ylabel "Commits"
1139 plot 'month_of_year.dat' using 1:2:(0.5) w boxes fs solid
1143 # commits_by_year_month
1144 f
= open(path
+ '/commits_by_year_month.plot', 'w')
1145 f
.write(GNUPLOT_COMMON
)
1148 set output 'commits_by_year_month.png'
1152 set format x "%Y-%m"
1156 set ylabel "Commits"
1157 plot 'commits_by_year_month.dat' using 1:2:(0.5) w boxes fs solid
1162 f
= open(path
+ '/commits_by_year.plot', 'w')
1163 f
.write(GNUPLOT_COMMON
)
1166 set output 'commits_by_year.png'
1170 set ylabel "Commits"
1172 plot 'commits_by_year.dat' using 1:2:(0.5) w boxes fs solid
1177 f
= open(path
+ '/files_by_date.plot', 'w')
1178 f
.write(GNUPLOT_COMMON
)
1181 set output 'files_by_date.png'
1184 set timefmt "%Y-%m-%d"
1185 set format x "%Y-%m-%d"
1191 plot 'files_by_date.dat' using 1:2 w steps
1196 f
= open(path
+ '/lines_of_code.plot', 'w')
1197 f
.write(GNUPLOT_COMMON
)
1200 set output 'lines_of_code.png'
1204 set format x "%Y-%m-%d"
1209 plot 'lines_of_code.dat' using 1:2 w lines
1213 # Lines of Code Added per author
1214 f
= open(path
+ '/lines_of_code_by_author.plot', 'w')
1215 f
.write(GNUPLOT_COMMON
)
1218 set terminal png transparent size 640,480
1219 set output 'lines_of_code_by_author.png'
1223 set format x "%Y-%m-%d"
1232 for a
in self
.authors_to_plot
:
1234 plots
.append("""'lines_of_code_by_author.dat' using 1:%d title "%s" w lines""" % (i
, a
.replace("\"", "\\\"")))
1235 f
.write(", ".join(plots
))
1240 # Commits per author
1241 f
= open(path
+ '/commits_by_author.plot', 'w')
1242 f
.write(GNUPLOT_COMMON
)
1245 set terminal png transparent size 640,480
1246 set output 'commits_by_author.png'
1250 set format x "%Y-%m-%d"
1252 set ylabel "Commits"
1259 for a
in self
.authors_to_plot
:
1261 plots
.append("""'commits_by_author.dat' using 1:%d title "%s" w lines""" % (i
, a
.replace("\"", "\\\"")))
1262 f
.write(", ".join(plots
))
1268 files
= glob
.glob(path
+ '/*.plot')
1270 out
= getpipeoutput([gnuplot_cmd
+ ' "%s"' % f
])
1274 def printHeader(self
, f
, title
= ''):
1276 """<?xml version="1.0" encoding="UTF-8"?>
1277 <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN" "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
1278 <html xmlns="http://www.w3.org/1999/xhtml">
1280 <title>GitStats - %s</title>
1281 <link rel="stylesheet" href="%s" type="text/css" />
1282 <meta name="generator" content="GitStats %s" />
1283 <script type="text/javascript" src="sortable.js"></script>
1286 """ % (self
.title
, conf
['style'], getversion()))
1288 def printNav(self
, f
):
1292 <li><a href="index.html">General</a></li>
1293 <li><a href="activity.html">Activity</a></li>
1294 <li><a href="authors.html">Authors</a></li>
1295 <li><a href="files.html">Files</a></li>
1296 <li><a href="lines.html">Lines</a></li>
1297 <li><a href="tags.html">Tags</a></li>
1304 def run(self
, args_orig
):
1305 optlist
, args
= getopt
.getopt(args_orig
, 'c:')
1308 key
, value
= v
.split('=', 1)
1310 raise KeyError('no such key "%s" in config' % key
)
1311 if isinstance(conf
[key
], int):
1312 conf
[key
] = int(value
)
1318 Usage: gitstats [options] <gitpath..> <outputpath>
1321 -c key=value Override configuration value
1323 Default config values:
1328 outputpath
= os
.path
.abspath(args
[-1])
1329 rundir
= os
.getcwd()
1332 os
.makedirs(outputpath
)
1335 if not os
.path
.isdir(outputpath
):
1336 print 'FATAL: Output path is not a directory or does not exist'
1339 print 'Output path: %s' % outputpath
1340 cachefile
= os
.path
.join(outputpath
, 'gitstats.cache')
1342 data
= GitDataCollector()
1343 data
.loadCache(cachefile
)
1345 for gitpath
in args
[0:-1]:
1346 print 'Git path: %s' % gitpath
1350 print 'Collecting data...'
1351 data
.collect(gitpath
)
1353 print 'Refining data...'
1354 data
.saveCache(cachefile
)
1359 print 'Generating report...'
1360 report
= HTMLReportCreator()
1361 report
.create(data
, outputpath
)
1363 time_end
= time
.time()
1364 exectime_internal
= time_end
- time_start
1365 print 'Execution time %.5f secs, %.5f secs (%.2f %%) in external commands)' % (exectime_internal
, exectime_external
, (100.0 * exectime_external
) / exectime_internal
)
1367 if __name__
=='__main__':