2 # Copyright (c) 2007-2009 Heikki Hokkanen <hoxu@users.sf.net> & others (see doc/author.txt)
15 GNUPLOT_COMMON
= 'set terminal png transparent\nset size 0.5,0.5\n'
16 MAX_EXT_LENGTH
= 10 # maximum file extension length
18 exectime_internal
= 0.0
19 exectime_external
= 0.0
20 time_start
= time
.time()
22 # By default, gnuplot is searched from path, but can be overridden with the
23 # environment variable "GNUPLOT"
24 gnuplot_cmd
= 'gnuplot'
25 if 'GNUPLOT' in os
.environ
:
26 gnuplot_cmd
= os
.environ
['GNUPLOT']
28 def getpipeoutput(cmds
, quiet
= False):
29 global exectime_external
32 print '>> ' + ' | '.join(cmds
),
34 p0
= subprocess
.Popen(cmds
[0], stdout
= subprocess
.PIPE
, shell
= True)
37 p
= subprocess
.Popen(x
, stdin
= p0
.stdout
, stdout
= subprocess
.PIPE
, shell
= True)
39 output
= p
.communicate()[0]
42 print '\r[%.5f] >> %s' % (end
- start
, ' | '.join(cmds
))
43 exectime_external
+= (end
- start
)
44 return output
.rstrip('\n')
46 def getkeyssortedbyvalues(dict):
47 return map(lambda el
: el
[1], sorted(map(lambda el
: (el
[1], el
[0]), dict.items())))
49 # dict['author'] = { 'commits': 512 } - ...key(dict, 'commits')
50 def getkeyssortedbyvaluekey(d
, key
):
51 return map(lambda el
: el
[1], sorted(map(lambda el
: (d
[el
][key
], el
), d
.keys())))
57 VERSION
= getpipeoutput(["git rev-parse --short HEAD"]).split('\n')[0]
61 """Manages data collection from a revision control repository."""
63 self
.stamp_created
= time
.time()
67 # This should be the main function to extract data from the repository.
68 def collect(self
, dir):
70 self
.projectname
= os
.path
.basename(os
.path
.abspath(dir))
74 def loadCache(self
, cachefile
):
75 if not os
.path
.exists(cachefile
):
77 print 'Loading cache...'
80 self
.cache
= pickle
.loads(zlib
.decompress(f
.read()))
82 # temporary hack to upgrade non-compressed caches
84 self
.cache
= pickle
.load(f
)
88 # Produce any additional statistics from the extracted data.
93 # : get a dictionary of author
94 def getAuthorInfo(self
, author
):
97 def getActivityByDayOfWeek(self
):
100 def getActivityByHourOfDay(self
):
104 # Get a list of authors
105 def getAuthors(self
):
108 def getFirstCommitDate(self
):
109 return datetime
.datetime
.now()
111 def getLastCommitDate(self
):
112 return datetime
.datetime
.now()
114 def getStampCreated(self
):
115 return self
.stamp_created
120 def getTotalAuthors(self
):
123 def getTotalCommits(self
):
126 def getTotalFiles(self
):
129 def getTotalLOC(self
):
133 # Save cacheable data
134 def saveCache(self
, filename
):
135 print 'Saving cache...'
136 f
= open(cachefile
, 'w')
137 #pickle.dump(self.cache, f)
138 data
= zlib
.compress(pickle
.dumps(self
.cache
))
142 class GitDataCollector(DataCollector
):
143 def collect(self
, dir):
144 DataCollector
.collect(self
, dir)
147 self
.total_authors
= int(getpipeoutput(['git log', 'git shortlog -s', 'wc -l']))
149 self
.total_authors
= 0
150 #self.total_lines = int(getoutput('git-ls-files -z |xargs -0 cat |wc -l'))
152 self
.activity_by_hour_of_day
= {} # hour -> commits
153 self
.activity_by_day_of_week
= {} # day -> commits
154 self
.activity_by_month_of_year
= {} # month [1-12] -> commits
155 self
.activity_by_hour_of_week
= {} # weekday -> hour -> commits
156 self
.activity_by_hour_of_day_busiest
= 0
157 self
.activity_by_hour_of_week_busiest
= 0
159 self
.authors
= {} # name -> {commits, first_commit_stamp, last_commit_stamp}
161 # author of the month
162 self
.author_of_month
= {} # month -> author -> commits
163 self
.author_of_year
= {} # year -> author -> commits
164 self
.commits_by_month
= {} # month -> commits
165 self
.commits_by_year
= {} # year -> commits
166 self
.first_commit_stamp
= 0
167 self
.last_commit_stamp
= 0
171 lines
= getpipeoutput(['git show-ref --tags']).split('\n')
175 (hash, tag
) = line
.split(' ')
177 tag
= tag
.replace('refs/tags/', '')
178 output
= getpipeoutput(['git log "%s" --pretty=format:"%%at %%an" -n 1' % hash])
180 parts
= output
.split(' ')
183 stamp
= int(parts
[0])
186 self
.tags
[tag
] = { 'stamp': stamp
, 'hash' : hash, 'date' : datetime
.datetime
.fromtimestamp(stamp
).strftime('%Y-%m-%d'), 'commits': 0, 'authors': {} }
188 # collect info on tags, starting from latest
189 tags_sorted_by_date_desc
= map(lambda el
: el
[1], reversed(sorted(map(lambda el
: (el
[1]['date'], el
[0]), data
.tags
.items()))))
191 for tag
in reversed(tags_sorted_by_date_desc
):
192 cmd
= 'git shortlog -s "%s"' % tag
194 cmd
+= ' "^%s"' % prev
195 output
= getpipeoutput([cmd
])
199 for line
in output
.split('\n'):
200 parts
= re
.split('\s+', line
, 2)
201 commits
= int(parts
[1])
203 self
.tags
[tag
]['commits'] += commits
204 self
.tags
[tag
]['authors'][author
] = commits
206 # Collect revision statistics
207 # Outputs "<stamp> <author>"
208 lines
= getpipeoutput(['git rev-list --pretty=format:"%at %an" HEAD', 'grep -v ^commit']).split('\n')
210 # linux-2.6 says "<unknown>" for one line O_o
211 parts
= line
.split(' ')
214 stamp
= int(parts
[0])
218 author
= ' '.join(parts
[1:])
219 date
= datetime
.datetime
.fromtimestamp(float(stamp
))
221 # First and last commit stamp
222 if self
.last_commit_stamp
== 0:
223 self
.last_commit_stamp
= stamp
224 self
.first_commit_stamp
= stamp
229 if hour
in self
.activity_by_hour_of_day
:
230 self
.activity_by_hour_of_day
[hour
] += 1
232 self
.activity_by_hour_of_day
[hour
] = 1
234 if self
.activity_by_hour_of_day
[hour
] > self
.activity_by_hour_of_day_busiest
:
235 self
.activity_by_hour_of_day_busiest
= self
.activity_by_hour_of_day
[hour
]
239 if day
in self
.activity_by_day_of_week
:
240 self
.activity_by_day_of_week
[day
] += 1
242 self
.activity_by_day_of_week
[day
] = 1
245 if day
not in self
.activity_by_hour_of_week
:
246 self
.activity_by_hour_of_week
[day
] = {}
247 if hour
not in self
.activity_by_hour_of_week
[day
]:
248 self
.activity_by_hour_of_week
[day
][hour
] = 1
250 self
.activity_by_hour_of_week
[day
][hour
] += 1
252 if self
.activity_by_hour_of_week
[day
][hour
] > self
.activity_by_hour_of_week_busiest
:
253 self
.activity_by_hour_of_week_busiest
= self
.activity_by_hour_of_week
[day
][hour
]
257 if month
in self
.activity_by_month_of_year
:
258 self
.activity_by_month_of_year
[month
] += 1
260 self
.activity_by_month_of_year
[month
] = 1
263 if author
not in self
.authors
:
264 self
.authors
[author
] = {}
266 if 'last_commit_stamp' not in self
.authors
[author
]:
267 self
.authors
[author
]['last_commit_stamp'] = stamp
268 self
.authors
[author
]['first_commit_stamp'] = stamp
269 if 'commits' in self
.authors
[author
]:
270 self
.authors
[author
]['commits'] += 1
272 self
.authors
[author
]['commits'] = 1
274 # author of the month/year
275 yymm
= datetime
.datetime
.fromtimestamp(stamp
).strftime('%Y-%m')
276 if yymm
in self
.author_of_month
:
277 if author
in self
.author_of_month
[yymm
]:
278 self
.author_of_month
[yymm
][author
] += 1
280 self
.author_of_month
[yymm
][author
] = 1
282 self
.author_of_month
[yymm
] = {}
283 self
.author_of_month
[yymm
][author
] = 1
284 if yymm
in self
.commits_by_month
:
285 self
.commits_by_month
[yymm
] += 1
287 self
.commits_by_month
[yymm
] = 1
289 yy
= datetime
.datetime
.fromtimestamp(stamp
).year
290 if yy
in self
.author_of_year
:
291 if author
in self
.author_of_year
[yy
]:
292 self
.author_of_year
[yy
][author
] += 1
294 self
.author_of_year
[yy
][author
] = 1
296 self
.author_of_year
[yy
] = {}
297 self
.author_of_year
[yy
][author
] = 1
298 if yy
in self
.commits_by_year
:
299 self
.commits_by_year
[yy
] += 1
301 self
.commits_by_year
[yy
] = 1
303 # TODO Optimize this, it's the worst bottleneck
304 # outputs "<stamp> <files>" for each revision
305 self
.files_by_stamp
= {} # stamp -> files
306 revlines
= getpipeoutput(['git rev-list --pretty=format:"%at %T" HEAD', 'grep -v ^commit']).strip().split('\n')
308 for revline
in revlines
:
309 time
, rev
= revline
.split(' ')
310 linecount
= self
.getFilesInCommit(rev
)
311 lines
.append('%d %d' % (int(time
), linecount
))
313 self
.total_commits
= len(lines
)
315 parts
= line
.split(' ')
318 (stamp
, files
) = parts
[0:2]
320 self
.files_by_stamp
[int(stamp
)] = int(files
)
322 print 'Warning: failed to parse line "%s"' % line
325 self
.extensions
= {} # extension -> files, lines
326 lines
= getpipeoutput(['git ls-tree -r -z HEAD']).split('\000')
327 self
.total_files
= len(lines
)
331 parts
= re
.split('\s+', line
, 4)
335 if filename
.find('.') == -1 or filename
.rfind('.') == 0:
338 ext
= filename
[(filename
.rfind('.') + 1):]
339 if len(ext
) > MAX_EXT_LENGTH
:
342 if ext
not in self
.extensions
:
343 self
.extensions
[ext
] = {'files': 0, 'lines': 0}
345 self
.extensions
[ext
]['files'] += 1
347 self
.extensions
[ext
]['lines'] += int(getpipeoutput(['git cat-file blob %s' % sha1
, 'wc -l']).split()[0])
349 print 'Warning: Could not count lines for file "%s"' % line
353 # N files changed, N insertions (+), N deletions(-)
355 self
.changes_by_date
= {} # stamp -> { files, ins, del }
356 lines
= getpipeoutput(['git log --shortstat --pretty=format:"%at %an"']).split('\n')
358 files
= 0; inserted
= 0; deleted
= 0; total_lines
= 0
364 if line
.find('files changed,') == -1:
368 (stamp
, author
) = (int(line
[:pos
]), line
[pos
+1:])
369 self
.changes_by_date
[stamp
] = { 'files': files
, 'ins': inserted
, 'del': deleted
, 'lines': total_lines
}
371 print 'Warning: unexpected line "%s"' % line
373 print 'Warning: unexpected line "%s"' % line
375 numbers
= re
.findall('\d+', line
)
376 if len(numbers
) == 3:
377 (files
, inserted
, deleted
) = map(lambda el
: int(el
), numbers
)
378 total_lines
+= inserted
379 total_lines
-= deleted
381 print 'Warning: failed to handle line "%s"' % line
382 (files
, inserted
, deleted
) = (0, 0, 0)
383 #self.changes_by_date[stamp] = { 'files': files, 'ins': inserted, 'del': deleted }
384 self
.total_lines
= total_lines
388 # name -> {place_by_commits, commits_frac, date_first, date_last, timedelta}
389 authors_by_commits
= getkeyssortedbyvaluekey(self
.authors
, 'commits')
390 authors_by_commits
.reverse() # most first
391 for i
, name
in enumerate(authors_by_commits
):
392 self
.authors
[name
]['place_by_commits'] = i
+ 1
394 for name
in self
.authors
.keys():
395 a
= self
.authors
[name
]
396 a
['commits_frac'] = (100 * float(a
['commits'])) / self
.getTotalCommits()
397 date_first
= datetime
.datetime
.fromtimestamp(a
['first_commit_stamp'])
398 date_last
= datetime
.datetime
.fromtimestamp(a
['last_commit_stamp'])
399 delta
= date_last
- date_first
400 a
['date_first'] = date_first
.strftime('%Y-%m-%d')
401 a
['date_last'] = date_last
.strftime('%Y-%m-%d')
402 a
['timedelta'] = delta
404 def getActivityByDayOfWeek(self
):
405 return self
.activity_by_day_of_week
407 def getActivityByHourOfDay(self
):
408 return self
.activity_by_hour_of_day
410 def getAuthorInfo(self
, author
):
411 return self
.authors
[author
]
413 def getAuthors(self
):
414 return self
.authors
.keys()
416 def getCommitDeltaDays(self
):
417 return (self
.last_commit_stamp
- self
.first_commit_stamp
) / 86400
419 def getFilesInCommit(self
, rev
):
421 res
= self
.cache
['files_in_tree'][rev
]
423 res
= int(getpipeoutput(['git ls-tree -r --name-only "%s"' % rev
, 'wc -l']).split('\n')[0])
424 if 'files_in_tree' not in self
.cache
:
425 self
.cache
['files_in_tree'] = {}
426 self
.cache
['files_in_tree'][rev
] = res
430 def getFirstCommitDate(self
):
431 return datetime
.datetime
.fromtimestamp(self
.first_commit_stamp
)
433 def getLastCommitDate(self
):
434 return datetime
.datetime
.fromtimestamp(self
.last_commit_stamp
)
437 lines
= getpipeoutput(['git show-ref --tags', 'cut -d/ -f3'])
438 return lines
.split('\n')
440 def getTagDate(self
, tag
):
441 return self
.revToDate('tags/' + tag
)
443 def getTotalAuthors(self
):
444 return self
.total_authors
446 def getTotalCommits(self
):
447 return self
.total_commits
449 def getTotalFiles(self
):
450 return self
.total_files
452 def getTotalLOC(self
):
453 return self
.total_lines
455 def revToDate(self
, rev
):
456 stamp
= int(getpipeoutput(['git log --pretty=format:%%at "%s" -n 1' % rev
]))
457 return datetime
.datetime
.fromtimestamp(stamp
).strftime('%Y-%m-%d')
460 """Creates the actual report based on given data."""
464 def create(self
, data
, path
):
468 def html_linkify(text
):
469 return text
.lower().replace(' ', '_')
471 def html_header(level
, text
):
472 name
= html_linkify(text
)
473 return '\n<h%d><a href="#%s" name="%s">%s</a></h%d>\n\n' % (level
, name
, name
, text
, level
)
475 class HTMLReportCreator(ReportCreator
):
476 def create(self
, data
, path
):
477 ReportCreator
.create(self
, data
, path
)
478 self
.title
= data
.projectname
480 # copy static files if they do not exist
481 for file in ('gitstats.css', 'sortable.js', 'arrow-up.gif', 'arrow-down.gif', 'arrow-none.gif'):
482 basedir
= os
.path
.dirname(os
.path
.abspath(__file__
))
483 shutil
.copyfile(basedir
+ '/' + file, path
+ '/' + file)
485 f
= open(path
+ "/index.html", 'w')
486 format
= '%Y-%m-%d %H:%M:%S'
489 f
.write('<h1>GitStats - %s</h1>' % data
.projectname
)
494 f
.write('<dt>Project name</dt><dd>%s</dd>' % (data
.projectname
))
495 f
.write('<dt>Generated</dt><dd>%s (in %d seconds)</dd>' % (datetime
.datetime
.now().strftime(format
), time
.time() - data
.getStampCreated()))
496 f
.write('<dt>Generator</dt><dd><a href="http://gitstats.sourceforge.net/">GitStats</a> (version %s)</dd>' % getversion())
497 f
.write('<dt>Report Period</dt><dd>%s to %s (%d days)</dd>' % (data
.getFirstCommitDate().strftime(format
), data
.getLastCommitDate().strftime(format
), data
.getCommitDeltaDays()))
498 f
.write('<dt>Total Files</dt><dd>%s</dd>' % data
.getTotalFiles())
499 f
.write('<dt>Total Lines of Code</dt><dd>%s</dd>' % data
.getTotalLOC())
500 f
.write('<dt>Total Commits</dt><dd>%s</dd>' % data
.getTotalCommits())
501 f
.write('<dt>Authors</dt><dd>%s</dd>' % data
.getTotalAuthors())
504 f
.write('</body>\n</html>')
509 f
= open(path
+ '/activity.html', 'w')
511 f
.write('<h1>Activity</h1>')
514 #f.write('<h2>Last 30 days</h2>')
516 #f.write('<h2>Last 12 months</h2>')
519 f
.write(html_header(2, 'Hour of Day'))
520 hour_of_day
= data
.getActivityByHourOfDay()
521 f
.write('<table><tr><th>Hour</th>')
522 for i
in range(0, 24):
523 f
.write('<th>%d</th>' % i
)
524 f
.write('</tr>\n<tr><th>Commits</th>')
525 fp
= open(path
+ '/hour_of_day.dat', 'w')
526 for i
in range(0, 24):
528 r
= 127 + int((float(hour_of_day
[i
]) / data
.activity_by_hour_of_day_busiest
) * 128)
529 f
.write('<td style="background-color: rgb(%d, 0, 0)">%d</td>' % (r
, hour_of_day
[i
]))
530 fp
.write('%d %d\n' % (i
, hour_of_day
[i
]))
532 f
.write('<td>0</td>')
533 fp
.write('%d 0\n' % i
)
535 f
.write('</tr>\n<tr><th>%</th>')
536 totalcommits
= data
.getTotalCommits()
537 for i
in range(0, 24):
539 r
= 127 + int((float(hour_of_day
[i
]) / data
.activity_by_hour_of_day_busiest
) * 128)
540 f
.write('<td style="background-color: rgb(%d, 0, 0)">%.2f</td>' % (r
, (100.0 * hour_of_day
[i
]) / totalcommits
))
542 f
.write('<td>0.00</td>')
543 f
.write('</tr></table>')
544 f
.write('<img src="hour_of_day.png" alt="Hour of Day" />')
545 fg
= open(path
+ '/hour_of_day.dat', 'w')
546 for i
in range(0, 24):
548 fg
.write('%d %d\n' % (i
+ 1, hour_of_day
[i
]))
550 fg
.write('%d 0\n' % (i
+ 1))
554 f
.write(html_header(2, 'Day of Week'))
555 day_of_week
= data
.getActivityByDayOfWeek()
556 f
.write('<div class="vtable"><table>')
557 f
.write('<tr><th>Day</th><th>Total (%)</th></tr>')
558 fp
= open(path
+ '/day_of_week.dat', 'w')
559 for d
in range(0, 7):
562 commits
= day_of_week
[d
]
563 fp
.write('%d %d\n' % (d
+ 1, commits
))
565 f
.write('<th>%d</th>' % (d
+ 1))
567 f
.write('<td>%d (%.2f%%)</td>' % (day_of_week
[d
], (100.0 * day_of_week
[d
]) / totalcommits
))
569 f
.write('<td>0</td>')
571 f
.write('</table></div>')
572 f
.write('<img src="day_of_week.png" alt="Day of Week" />')
576 f
.write(html_header(2, 'Hour of Week'))
579 f
.write('<tr><th>Weekday</th>')
580 for hour
in range(0, 24):
581 f
.write('<th>%d</th>' % (hour
))
584 for weekday
in range(0, 7):
585 f
.write('<tr><th>%d</th>' % (weekday
+ 1))
586 for hour
in range(0, 24):
588 commits
= data
.activity_by_hour_of_week
[weekday
][hour
]
593 r
= 127 + int((float(commits
) / data
.activity_by_hour_of_week_busiest
) * 128)
594 f
.write(' style="background-color: rgb(%d, 0, 0)"' % r
)
595 f
.write('>%d</td>' % commits
)
603 f
.write(html_header(2, 'Month of Year'))
604 f
.write('<div class="vtable"><table>')
605 f
.write('<tr><th>Month</th><th>Commits (%)</th></tr>')
606 fp
= open (path
+ '/month_of_year.dat', 'w')
607 for mm
in range(1, 13):
609 if mm
in data
.activity_by_month_of_year
:
610 commits
= data
.activity_by_month_of_year
[mm
]
611 f
.write('<tr><td>%d</td><td>%d (%.2f %%)</td></tr>' % (mm
, commits
, (100.0 * commits
) / data
.getTotalCommits()))
612 fp
.write('%d %d\n' % (mm
, commits
))
614 f
.write('</table></div>')
615 f
.write('<img src="month_of_year.png" alt="Month of Year" />')
617 # Commits by year/month
618 f
.write(html_header(2, 'Commits by year/month'))
619 f
.write('<div class="vtable"><table><tr><th>Month</th><th>Commits</th></tr>')
620 for yymm
in reversed(sorted(data
.commits_by_month
.keys())):
621 f
.write('<tr><td>%s</td><td>%d</td></tr>' % (yymm
, data
.commits_by_month
[yymm
]))
622 f
.write('</table></div>')
623 f
.write('<img src="commits_by_year_month.png" alt="Commits by year/month" />')
624 fg
= open(path
+ '/commits_by_year_month.dat', 'w')
625 for yymm
in sorted(data
.commits_by_month
.keys()):
626 fg
.write('%s %s\n' % (yymm
, data
.commits_by_month
[yymm
]))
630 f
.write(html_header(2, 'Commits by Year'))
631 f
.write('<div class="vtable"><table><tr><th>Year</th><th>Commits (% of all)</th></tr>')
632 for yy
in reversed(sorted(data
.commits_by_year
.keys())):
633 f
.write('<tr><td>%s</td><td>%d (%.2f%%)</td></tr>' % (yy
, data
.commits_by_year
[yy
], (100.0 * data
.commits_by_year
[yy
]) / data
.getTotalCommits()))
634 f
.write('</table></div>')
635 f
.write('<img src="commits_by_year.png" alt="Commits by Year" />')
636 fg
= open(path
+ '/commits_by_year.dat', 'w')
637 for yy
in sorted(data
.commits_by_year
.keys()):
638 fg
.write('%d %d\n' % (yy
, data
.commits_by_year
[yy
]))
641 f
.write('</body></html>')
646 f
= open(path
+ '/authors.html', 'w')
649 f
.write('<h1>Authors</h1>')
652 # Authors :: List of authors
653 f
.write(html_header(2, 'List of Authors'))
655 f
.write('<table class="authors sortable" id="authors">')
656 f
.write('<tr><th>Author</th><th>Commits (%)</th><th>First commit</th><th>Last commit</th><th class="unsortable">Age</th><th># by commits</th></tr>')
657 for author
in sorted(data
.getAuthors()):
658 info
= data
.getAuthorInfo(author
)
659 f
.write('<tr><td>%s</td><td>%d (%.2f%%)</td><td>%s</td><td>%s</td><td>%s</td><td>%d</td></tr>' % (author
, info
['commits'], info
['commits_frac'], info
['date_first'], info
['date_last'], info
['timedelta'], info
['place_by_commits']))
662 # Authors :: Author of Month
663 f
.write(html_header(2, 'Author of Month'))
664 f
.write('<table class="sortable" id="aom">')
665 f
.write('<tr><th>Month</th><th>Author</th><th>Commits (%)</th><th class="unsortable">Next top 5</th></tr>')
666 for yymm
in reversed(sorted(data
.author_of_month
.keys())):
667 authordict
= data
.author_of_month
[yymm
]
668 authors
= getkeyssortedbyvalues(authordict
)
670 commits
= data
.author_of_month
[yymm
][authors
[0]]
671 next
= ', '.join(authors
[1:5])
672 f
.write('<tr><td>%s</td><td>%s</td><td>%d (%.2f%% of %d)</td><td>%s</td></tr>' % (yymm
, authors
[0], commits
, (100 * commits
) / data
.commits_by_month
[yymm
], data
.commits_by_month
[yymm
], next
))
676 f
.write(html_header(2, 'Author of Year'))
677 f
.write('<table class="sortable" id="aoy"><tr><th>Year</th><th>Author</th><th>Commits (%)</th><th class="unsortable">Next top 5</th></tr>')
678 for yy
in reversed(sorted(data
.author_of_year
.keys())):
679 authordict
= data
.author_of_year
[yy
]
680 authors
= getkeyssortedbyvalues(authordict
)
682 commits
= data
.author_of_year
[yy
][authors
[0]]
683 next
= ', '.join(authors
[1:5])
684 f
.write('<tr><td>%s</td><td>%s</td><td>%d (%.2f%% of %d)</td><td>%s</td></tr>' % (yy
, authors
[0], commits
, (100 * commits
) / data
.commits_by_year
[yy
], data
.commits_by_year
[yy
], next
))
687 f
.write('</body></html>')
692 f
= open(path
+ '/files.html', 'w')
694 f
.write('<h1>Files</h1>')
698 f
.write('<dt>Total files</dt><dd>%d</dd>' % data
.getTotalFiles())
699 f
.write('<dt>Total lines</dt><dd>%d</dd>' % data
.getTotalLOC())
700 f
.write('<dt>Average file size</dt><dd>%.2f bytes</dd>' % ((100.0 * data
.getTotalLOC()) / data
.getTotalFiles()))
703 # Files :: File count by date
704 f
.write(html_header(2, 'File count by date'))
706 fg
= open(path
+ '/files_by_date.dat', 'w')
707 for stamp
in sorted(data
.files_by_stamp
.keys()):
708 fg
.write('%s %d\n' % (datetime
.datetime
.fromtimestamp(stamp
).strftime('%Y-%m-%d'), data
.files_by_stamp
[stamp
]))
711 f
.write('<img src="files_by_date.png" alt="Files by Date" />')
713 #f.write('<h2>Average file size by date</h2>')
715 # Files :: Extensions
716 f
.write(html_header(2, 'Extensions'))
717 f
.write('<table class="sortable" id="ext"><tr><th>Extension</th><th>Files (%)</th><th>Lines (%)</th><th>Lines/file</th></tr>')
718 for ext
in sorted(data
.extensions
.keys()):
719 files
= data
.extensions
[ext
]['files']
720 lines
= data
.extensions
[ext
]['lines']
721 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
))
724 f
.write('</body></html>')
729 f
= open(path
+ '/lines.html', 'w')
731 f
.write('<h1>Lines</h1>')
735 f
.write('<dt>Total lines</dt><dd>%d</dd>' % data
.getTotalLOC())
738 f
.write(html_header(2, 'Lines of Code'))
739 f
.write('<img src="lines_of_code.png" />')
741 fg
= open(path
+ '/lines_of_code.dat', 'w')
742 for stamp
in sorted(data
.changes_by_date
.keys()):
743 fg
.write('%d %d\n' % (stamp
, data
.changes_by_date
[stamp
]['lines']))
746 f
.write('</body></html>')
751 f
= open(path
+ '/tags.html', 'w')
753 f
.write('<h1>Tags</h1>')
757 f
.write('<dt>Total tags</dt><dd>%d</dd>' % len(data
.tags
))
758 if len(data
.tags
) > 0:
759 f
.write('<dt>Average commits per tag</dt><dd>%.2f</dd>' % (data
.getTotalCommits() / len(data
.tags
)))
763 f
.write('<tr><th>Name</th><th>Date</th><th>Commits</th><th>Authors</th></tr>')
764 # sort the tags by date desc
765 tags_sorted_by_date_desc
= map(lambda el
: el
[1], reversed(sorted(map(lambda el
: (el
[1]['date'], el
[0]), data
.tags
.items()))))
766 for tag
in tags_sorted_by_date_desc
:
768 authors_by_commits
= getkeyssortedbyvalues(data
.tags
[tag
]['authors'])
769 for i
in reversed(authors_by_commits
):
770 authorinfo
.append('%s (%d)' % (i
, data
.tags
[tag
]['authors'][i
]))
771 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
)))
774 f
.write('</body></html>')
777 self
.createGraphs(path
)
779 def createGraphs(self
, path
):
780 print 'Generating graphs...'
783 f
= open(path
+ '/hour_of_day.plot', 'w')
784 f
.write(GNUPLOT_COMMON
)
787 set output 'hour_of_day.png'
789 set xrange [0.5:24.5]
792 plot 'hour_of_day.dat' using 1:2:(0.5) w boxes fs solid
797 f
= open(path
+ '/day_of_week.plot', 'w')
798 f
.write(GNUPLOT_COMMON
)
801 set output 'day_of_week.png'
806 plot 'day_of_week.dat' using 1:2:(0.5) w boxes fs solid
811 f
= open(path
+ '/month_of_year.plot', 'w')
812 f
.write(GNUPLOT_COMMON
)
815 set output 'month_of_year.png'
817 set xrange [0.5:12.5]
820 plot 'month_of_year.dat' using 1:2:(0.5) w boxes fs solid
824 # commits_by_year_month
825 f
= open(path
+ '/commits_by_year_month.plot', 'w')
826 f
.write(GNUPLOT_COMMON
)
829 set output 'commits_by_year_month.png'
834 set xtics rotate by 90 15768000
837 plot 'commits_by_year_month.dat' using 1:2:(0.5) w boxes fs solid
842 f
= open(path
+ '/commits_by_year.plot', 'w')
843 f
.write(GNUPLOT_COMMON
)
846 set output 'commits_by_year.png'
851 plot 'commits_by_year.dat' using 1:2:(0.5) w boxes fs solid
856 f
= open(path
+ '/files_by_date.plot', 'w')
857 f
.write(GNUPLOT_COMMON
)
860 set output 'files_by_date.png'
863 set timefmt "%Y-%m-%d"
864 set format x "%Y-%m-%d"
866 set xtics rotate by 90
868 plot 'files_by_date.dat' using 1:2 w steps
873 f
= open(path
+ '/lines_of_code.plot', 'w')
874 f
.write(GNUPLOT_COMMON
)
877 set output 'lines_of_code.png'
881 set format x "%Y-%m-%d"
883 set xtics rotate by 90
885 plot 'lines_of_code.dat' using 1:2 w lines
890 files
= glob
.glob(path
+ '/*.plot')
892 out
= getpipeoutput([gnuplot_cmd
+ ' "%s"' % f
])
896 def printHeader(self
, f
, title
= ''):
898 """<?xml version="1.0" encoding="UTF-8"?>
899 <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN" "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
900 <html xmlns="http://www.w3.org/1999/xhtml">
902 <title>GitStats - %s</title>
903 <link rel="stylesheet" href="gitstats.css" type="text/css" />
904 <meta name="generator" content="GitStats %s" />
905 <script type="text/javascript" src="sortable.js"></script>
908 """ % (self
.title
, getversion()))
910 def printNav(self
, f
):
914 <li><a href="index.html">General</a></li>
915 <li><a href="activity.html">Activity</a></li>
916 <li><a href="authors.html">Authors</a></li>
917 <li><a href="files.html">Files</a></li>
918 <li><a href="lines.html">Lines</a></li>
919 <li><a href="tags.html">Tags</a></li>
926 Usage: gitstats [options] <gitpath> <outputpath>
931 if len(sys
.argv
) < 3:
935 gitpath
= sys
.argv
[1]
936 outputpath
= os
.path
.abspath(sys
.argv
[2])
940 os
.makedirs(outputpath
)
943 if not os
.path
.isdir(outputpath
):
944 print 'FATAL: Output path is not a directory or does not exist'
947 print 'Git path: %s' % gitpath
948 print 'Output path: %s' % outputpath
952 cachefile
= os
.path
.join(outputpath
, 'gitstats.cache')
954 print 'Collecting data...'
955 data
= GitDataCollector()
956 data
.loadCache(cachefile
)
957 data
.collect(gitpath
)
958 print 'Refining data...'
959 data
.saveCache(cachefile
)
964 print 'Generating report...'
965 report
= HTMLReportCreator()
966 report
.create(data
, outputpath
)
968 time_end
= time
.time()
969 exectime_internal
= time_end
- time_start
970 print 'Execution time %.5f secs, %.5f secs (%.2f %%) in external commands)' % (exectime_internal
, exectime_external
, (100.0 * exectime_external
) / exectime_internal
)