gitstats

   1 #!/usr/bin/env python
   2 # Copyright (c) 2007-2010 Heikki Hokkanen <hoxu@users.sf.net> & others (see doc/author.txt)
   3 # GPLv2 / GPLv3
   4 import datetime
   5 import getopt
   6 import glob
   7 import os
   8 import pickle
   9 import platform
  10 import re
  11 import shutil
  12 import subprocess
  13 import sys
  14 import time
  15 import zlib
  16
  17 GNUPLOT_COMMON = 'set terminal png transparent\nset size 1.0,0.5\n'
  18 ON_LINUX = (platform.system() == 'Linux')
  19 WEEKDAYS = ('Mon', 'Tue', 'Wed', 'Thu', 'Fri', 'Sat', 'Sun')
  20
  21 exectime_internal = 0.0
  22 exectime_external = 0.0
  23 time_start = time.time()
  24
  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']
  30
  31 conf = {
  32         'max_domains': 10,
  33         'max_ext_length': 10,
  34         'style': 'gitstats.css',
  35         'max_authors': 20,
  36         'authors_top': 5,
  37         'commit_begin': '',
  38         'commit_end': '',
  39 }
  40
  41 def getpipeoutput(cmds, quiet = False):
  42         global exectime_external
  43         start = time.time()
  44         if not quiet and ON_LINUX and os.isatty(1):
  45                 print '>> ' + ' | '.join(cmds),
  46                 sys.stdout.flush()
  47         p0 = subprocess.Popen(cmds[0], stdout = subprocess.PIPE, shell = True)
  48         p = p0
  49         for x in cmds[1:]:
  50                 p = subprocess.Popen(x, stdin = p0.stdout, stdout = subprocess.PIPE, shell = True)
  51                 p0 = p
  52         output = p.communicate()[0]
  53         end = time.time()
  54         if not quiet:
  55                 if ON_LINUX and os.isatty(1):
  56                         print '\r',
  57                 print '[%.5f] >> %s' % (end - start, ' | '.join(cmds))
  58         exectime_external += (end - start)
  59         return output.rstrip('\n')
  60
  61 def getcommitrange(defaultrange = '', end_only = False):
  62         if len(conf['commit_end']) > 0:
  63                 if end_only or len(conf['commit_begin']) == 0:
  64                         return conf['commit_end']
  65                 return '%s..%s' % (conf['commit_begin'], conf['commit_end'])
  66         return defaultrange
  67
  68 def getkeyssortedbyvalues(dict):
  69         return map(lambda el : el[1], sorted(map(lambda el : (el[1], el[0]), dict.items())))
  70
  71 # dict['author'] = { 'commits': 512 } - ...key(dict, 'commits')
  72 def getkeyssortedbyvaluekey(d, key):
  73         return map(lambda el : el[1], sorted(map(lambda el : (d[el][key], el), d.keys())))
  74
  75 VERSION = 0
  76 def getversion():
  77         global VERSION
  78         if VERSION == 0:
  79                 VERSION = getpipeoutput(["git rev-parse --short %s" % getcommitrange('HEAD')]).split('\n')[0]
  80         return VERSION
  81
  82 class DataCollector:
  83         """Manages data collection from a revision control repository."""
  84         def __init__(self):
  85                 self.stamp_created = time.time()
  86                 self.cache = {}
  87
  88         ##
  89         # This should be the main function to extract data from the repository.
  90         def collect(self, dir):
  91                 self.dir = dir
  92                 self.projectname = os.path.basename(os.path.abspath(dir))
  93
  94         ##
  95         # Load cacheable data
  96         def loadCache(self, cachefile):
  97                 if not os.path.exists(cachefile):
  98                         return
  99                 print 'Loading cache...'
 100                 f = open(cachefile, 'rb')
 101                 try:
 102                         self.cache = pickle.loads(zlib.decompress(f.read()))
 103                 except:
 104                         # temporary hack to upgrade non-compressed caches
 105                         f.seek(0)
 106                         self.cache = pickle.load(f)
 107                 f.close()
 108
 109         ##
 110         # Produce any additional statistics from the extracted data.
 111         def refine(self):
 112                 pass
 113
 114         ##
 115         # : get a dictionary of author
 116         def getAuthorInfo(self, author):
 117                 return None
 118
 119         def getActivityByDayOfWeek(self):
 120                 return {}
 121
 122         def getActivityByHourOfDay(self):
 123                 return {}
 124
 125         # : get a dictionary of domains
 126         def getDomainInfo(self, domain):
 127                 return None
 128
 129         ##
 130         # Get a list of authors
 131         def getAuthors(self):
 132                 return []
 133
 134         def getFirstCommitDate(self):
 135                 return datetime.datetime.now()
 136
 137         def getLastCommitDate(self):
 138                 return datetime.datetime.now()
 139
 140         def getStampCreated(self):
 141                 return self.stamp_created
 142
 143         def getTags(self):
 144                 return []
 145
 146         def getTotalAuthors(self):
 147                 return -1
 148
 149         def getTotalCommits(self):
 150                 return -1
 151
 152         def getTotalFiles(self):
 153                 return -1
 154
 155         def getTotalLOC(self):
 156                 return -1
 157
 158         ##
 159         # Save cacheable data
 160         def saveCache(self, cachefile):
 161                 print 'Saving cache...'
 162                 f = open(cachefile, 'wb')
 163                 #pickle.dump(self.cache, f)
 164                 data = zlib.compress(pickle.dumps(self.cache))
 165                 f.write(data)
 166                 f.close()
 167
 168 class GitDataCollector(DataCollector):
 169         def collect(self, dir):
 170                 DataCollector.collect(self, dir)
 171
 172                 try:
 173                         self.total_authors = int(getpipeoutput(['git shortlog -s %s' % getcommitrange(), 'wc -l']))
 174                 except:
 175                         self.total_authors = 0
 176                 #self.total_lines = int(getoutput('git-ls-files -z |xargs -0 cat |wc -l'))
 177
 178                 self.activity_by_hour_of_day = {} # hour -> commits
 179                 self.activity_by_day_of_week = {} # day -> commits
 180                 self.activity_by_month_of_year = {} # month [1-12] -> commits
 181                 self.activity_by_hour_of_week = {} # weekday -> hour -> commits
 182                 self.activity_by_hour_of_day_busiest = 0
 183                 self.activity_by_hour_of_week_busiest = 0
 184                 self.activity_by_year_week = {} # yy_wNN -> commits
 185                 self.activity_by_year_week_peak = 0
 186
 187                 self.authors = {} # name -> {commits, first_commit_stamp, last_commit_stamp, last_active_day, active_days, lines_added, lines_removed}
 188
 189                 # domains
 190                 self.domains = {} # domain -> commits
 191
 192                 # author of the month
 193                 self.author_of_month = {} # month -> author -> commits
 194                 self.author_of_year = {} # year -> author -> commits
 195                 self.commits_by_month = {} # month -> commits
 196                 self.commits_by_year = {} # year -> commits
 197                 self.first_commit_stamp = 0
 198                 self.last_commit_stamp = 0
 199                 self.last_active_day = None
 200                 self.active_days = set()
 201
 202                 # lines
 203                 self.total_lines = 0
 204                 self.total_lines_added = 0
 205                 self.total_lines_removed = 0
 206
 207                 # timezone
 208                 self.commits_by_timezone = {} # timezone -> commits
 209
 210                 # tags
 211                 self.tags = {}
 212                 lines = getpipeoutput(['git show-ref --tags']).split('\n')
 213                 for line in lines:
 214                         if len(line) == 0:
 215                                 continue
 216                         (hash, tag) = line.split(' ')
 217
 218                         tag = tag.replace('refs/tags/', '')
 219                         output = getpipeoutput(['git log "%s" --pretty=format:"%%at %%an" -n 1' % hash])
 220                         if len(output) > 0:
 221                                 parts = output.split(' ')
 222                                 stamp = 0
 223                                 try:
 224                                         stamp = int(parts[0])
 225                                 except ValueError:
 226                                         stamp = 0
 227                                 self.tags[tag] = { 'stamp': stamp, 'hash' : hash, 'date' : datetime.datetime.fromtimestamp(stamp).strftime('%Y-%m-%d'), 'commits': 0, 'authors': {} }
 228
 229                 # collect info on tags, starting from latest
 230                 tags_sorted_by_date_desc = map(lambda el : el[1], reversed(sorted(map(lambda el : (el[1]['date'], el[0]), self.tags.items()))))
 231                 prev = None
 232                 for tag in reversed(tags_sorted_by_date_desc):
 233                         cmd = 'git shortlog -s "%s"' % tag
 234                         if prev != None:
 235                                 cmd += ' "^%s"' % prev
 236                         output = getpipeoutput([cmd])
 237                         if len(output) == 0:
 238                                 continue
 239                         prev = tag
 240                         for line in output.split('\n'):
 241                                 parts = re.split('\s+', line, 2)
 242                                 commits = int(parts[1])
 243                                 author = parts[2]
 244                                 self.tags[tag]['commits'] += commits
 245                                 self.tags[tag]['authors'][author] = commits
 246
 247                 # Collect revision statistics
 248                 # Outputs "<stamp> <date> <time> <timezone> <author> '<' <mail> '>'"
 249                 lines = getpipeoutput(['git rev-list --pretty=format:"%%at %%ai %%an <%%aE>" %s' % getcommitrange('HEAD'), 'grep -v ^commit']).split('\n')
 250                 for line in lines:
 251                         parts = line.split(' ', 4)
 252                         author = ''
 253                         try:
 254                                 stamp = int(parts[0])
 255                         except ValueError:
 256                                 stamp = 0
 257                         timezone = parts[3]
 258                         author, mail = parts[4].split('<', 1)
 259                         author = author.rstrip()
 260                         mail = mail.rstrip('>')
 261                         domain = '?'
 262                         if mail.find('@') != -1:
 263                                 domain = mail.rsplit('@', 1)[1]
 264                         date = datetime.datetime.fromtimestamp(float(stamp))
 265
 266                         # First and last commit stamp
 267                         if self.last_commit_stamp == 0:
 268                                 self.last_commit_stamp = stamp
 269                         self.first_commit_stamp = stamp
 270
 271                         # activity
 272                         # hour
 273                         hour = date.hour
 274                         self.activity_by_hour_of_day[hour] = self.activity_by_hour_of_day.get(hour, 0) + 1
 275                         # most active hour?
 276                         if self.activity_by_hour_of_day[hour] > self.activity_by_hour_of_day_busiest:
 277                                 self.activity_by_hour_of_day_busiest = self.activity_by_hour_of_day[hour]
 278
 279                         # day of week
 280                         day = date.weekday()
 281                         self.activity_by_day_of_week[day] = self.activity_by_day_of_week.get(day, 0) + 1
 282
 283                         # domain stats
 284                         if domain not in self.domains:
 285                                 self.domains[domain] = {}
 286                         # commits
 287                         self.domains[domain]['commits'] = self.domains[domain].get('commits', 0) + 1
 288
 289                         # hour of week
 290                         if day not in self.activity_by_hour_of_week:
 291                                 self.activity_by_hour_of_week[day] = {}
 292                         self.activity_by_hour_of_week[day][hour] = self.activity_by_hour_of_week[day].get(hour, 0) + 1
 293                         # most active hour?
 294                         if self.activity_by_hour_of_week[day][hour] > self.activity_by_hour_of_week_busiest:
 295                                 self.activity_by_hour_of_week_busiest = self.activity_by_hour_of_week[day][hour]
 296
 297                         # month of year
 298                         month = date.month
 299                         self.activity_by_month_of_year[month] = self.activity_by_month_of_year.get(month, 0) + 1
 300
 301                         # yearly/weekly activity
 302                         yyw = date.strftime('%Y-%W')
 303                         self.activity_by_year_week[yyw] = self.activity_by_year_week.get(yyw, 0) + 1
 304                         if self.activity_by_year_week_peak < self.activity_by_year_week[yyw]:
 305                                 self.activity_by_year_week_peak = self.activity_by_year_week[yyw]
 306
 307                         # author stats
 308                         if author not in self.authors:
 309                                 self.authors[author] = {}
 310                         # commits
 311                         if 'last_commit_stamp' not in self.authors[author]:
 312                                 self.authors[author]['last_commit_stamp'] = stamp
 313                         self.authors[author]['first_commit_stamp'] = stamp
 314                         self.authors[author]['commits'] = self.authors[author].get('commits', 0) + 1
 315
 316                         # author of the month/year
 317                         yymm = date.strftime('%Y-%m')
 318                         if yymm in self.author_of_month:
 319                                 self.author_of_month[yymm][author] = self.author_of_month[yymm].get(author, 0) + 1
 320                         else:
 321                                 self.author_of_month[yymm] = {}
 322                                 self.author_of_month[yymm][author] = 1
 323                         self.commits_by_month[yymm] = self.commits_by_month.get(yymm, 0) + 1
 324
 325                         yy = date.year
 326                         if yy in self.author_of_year:
 327                                 self.author_of_year[yy][author] = self.author_of_year[yy].get(author, 0) + 1
 328                         else:
 329                                 self.author_of_year[yy] = {}
 330                                 self.author_of_year[yy][author] = 1
 331                         self.commits_by_year[yy] = self.commits_by_year.get(yy, 0) + 1
 332
 333                         # authors: active days
 334                         yymmdd = date.strftime('%Y-%m-%d')
 335                         if 'last_active_day' not in self.authors[author]:
 336                                 self.authors[author]['last_active_day'] = yymmdd
 337                                 self.authors[author]['active_days'] = 1
 338                         elif yymmdd != self.authors[author]['last_active_day']:
 339                                 self.authors[author]['last_active_day'] = yymmdd
 340                                 self.authors[author]['active_days'] += 1
 341
 342                         # project: active days
 343                         if yymmdd != self.last_active_day:
 344                                 self.last_active_day = yymmdd
 345                                 self.active_days.add(yymmdd)
 346
 347                         # timezone
 348                         self.commits_by_timezone[timezone] = self.commits_by_timezone.get(timezone, 0) + 1
 349
 350                 # TODO Optimize this, it's the worst bottleneck
 351                 # outputs "<stamp> <files>" for each revision
 352                 self.files_by_stamp = {} # stamp -> files
 353                 revlines = getpipeoutput(['git rev-list --pretty=format:"%%at %%T" %s' % getcommitrange('HEAD'), 'grep -v ^commit']).strip().split('\n')
 354                 lines = []
 355                 for revline in revlines:
 356                         time, rev = revline.split(' ')
 357                         linecount = self.getFilesInCommit(rev)
 358                         lines.append('%d %d' % (int(time), linecount))
 359
 360                 self.total_commits = len(lines)
 361                 for line in lines:
 362                         parts = line.split(' ')
 363                         if len(parts) != 2:
 364                                 continue
 365                         (stamp, files) = parts[0:2]
 366                         try:
 367                                 self.files_by_stamp[int(stamp)] = int(files)
 368                         except ValueError:
 369                                 print 'Warning: failed to parse line "%s"' % line
 370
 371                 # extensions
 372                 self.extensions = {} # extension -> files, lines
 373                 lines = getpipeoutput(['git ls-tree -r -z %s' % getcommitrange('HEAD', end_only = True)]).split('\000')
 374                 self.total_files = len(lines)
 375                 for line in lines:
 376                         if len(line) == 0:
 377                                 continue
 378                         parts = re.split('\s+', line, 4)
 379                         sha1 = parts[2]
 380                         filename = parts[3]
 381
 382                         if filename.find('.') == -1 or filename.rfind('.') == 0:
 383                                 ext = ''
 384                         else:
 385                                 ext = filename[(filename.rfind('.') + 1):]
 386                         if len(ext) > conf['max_ext_length']:
 387                                 ext = ''
 388
 389                         if ext not in self.extensions:
 390                                 self.extensions[ext] = {'files': 0, 'lines': 0}
 391
 392                         self.extensions[ext]['files'] += 1
 393                         try:
 394                                 self.extensions[ext]['lines'] += self.getLinesInBlob(sha1)
 395                         except:
 396                                 print 'Warning: Could not count lines for file "%s"' % line
 397
 398                 # line statistics
 399                 # outputs:
 400                 #  N files changed, N insertions (+), N deletions(-)
 401                 # <stamp> <author>
 402                 self.changes_by_date = {} # stamp -> { files, ins, del }
 403                 lines = getpipeoutput(['git log --shortstat --pretty=format:"%%at %%an" %s' % getcommitrange('HEAD')]).split('\n')
 404                 lines.reverse()
 405                 files = 0; inserted = 0; deleted = 0; total_lines = 0
 406                 author = None
 407                 for line in lines:
 408                         if len(line) == 0:
 409                                 continue
 410
 411                         # <stamp> <author>
 412                         if line.find('files changed,') == -1:
 413                                 pos = line.find(' ')
 414                                 if pos != -1:
 415                                         try:
 416                                                 (stamp, author) = (int(line[:pos]), line[pos+1:])
 417                                                 self.changes_by_date[stamp] = { 'files': files, 'ins': inserted, 'del': deleted, 'lines': total_lines }
 418                                                 if author not in self.authors:
 419                                                         self.authors[author] = { 'lines_added' : 0, 'lines_removed' : 0 }
 420                                                 self.authors[author]['lines_added'] = self.authors[author].get('lines_added', 0) + inserted
 421                                                 self.authors[author]['lines_removed'] = self.authors[author].get('lines_removed', 0) + deleted
 422                                                 files, inserted, deleted = 0, 0, 0
 423                                         except ValueError:
 424                                                 print 'Warning: unexpected line "%s"' % line
 425                                 else:
 426                                         print 'Warning: unexpected line "%s"' % line
 427                         else:
 428                                 numbers = re.findall('\d+', line)
 429                                 if len(numbers) == 3:
 430                                         (files, inserted, deleted) = map(lambda el : int(el), numbers)
 431                                         total_lines += inserted
 432                                         total_lines -= deleted
 433                                         self.total_lines_added += inserted
 434                                         self.total_lines_removed += deleted
 435                                 else:
 436                                         print 'Warning: failed to handle line "%s"' % line
 437                                         (files, inserted, deleted) = (0, 0, 0)
 438                                 #self.changes_by_date[stamp] = { 'files': files, 'ins': inserted, 'del': deleted }
 439                 self.total_lines = total_lines
 440
 441         def refine(self):
 442                 # authors
 443                 # name -> {place_by_commits, commits_frac, date_first, date_last, timedelta}
 444                 authors_by_commits = getkeyssortedbyvaluekey(self.authors, 'commits')
 445                 authors_by_commits.reverse() # most first
 446                 for i, name in enumerate(authors_by_commits):
 447                         self.authors[name]['place_by_commits'] = i + 1
 448
 449                 for name in self.authors.keys():
 450                         a = self.authors[name]
 451                         a['commits_frac'] = (100 * float(a['commits'])) / self.getTotalCommits()
 452                         date_first = datetime.datetime.fromtimestamp(a['first_commit_stamp'])
 453                         date_last = datetime.datetime.fromtimestamp(a['last_commit_stamp'])
 454                         delta = date_last - date_first
 455                         a['date_first'] = date_first.strftime('%Y-%m-%d')
 456                         a['date_last'] = date_last.strftime('%Y-%m-%d')
 457                         a['timedelta'] = delta
 458
 459         def getActiveDays(self):
 460                 return self.active_days
 461
 462         def getActivityByDayOfWeek(self):
 463                 return self.activity_by_day_of_week
 464
 465         def getActivityByHourOfDay(self):
 466                 return self.activity_by_hour_of_day
 467
 468         def getAuthorInfo(self, author):
 469                 return self.authors[author]
 470
 471         def getAuthors(self, limit = None):
 472                 res = getkeyssortedbyvaluekey(self.authors, 'commits')
 473                 res.reverse()
 474                 return res[:limit]
 475
 476         def getCommitDeltaDays(self):
 477                 return (self.last_commit_stamp - self.first_commit_stamp) / 86400 + 1
 478
 479         def getDomainInfo(self, domain):
 480                 return self.domains[domain]
 481
 482         def getDomains(self):
 483                 return self.domains.keys()
 484
 485         def getFilesInCommit(self, rev):
 486                 try:
 487                         res = self.cache['files_in_tree'][rev]
 488                 except:
 489                         res = int(getpipeoutput(['git ls-tree -r --name-only "%s"' % rev, 'wc -l']).split('\n')[0])
 490                         if 'files_in_tree' not in self.cache:
 491                                 self.cache['files_in_tree'] = {}
 492                         self.cache['files_in_tree'][rev] = res
 493
 494                 return res
 495
 496         def getFirstCommitDate(self):
 497                 return datetime.datetime.fromtimestamp(self.first_commit_stamp)
 498
 499         def getLastCommitDate(self):
 500                 return datetime.datetime.fromtimestamp(self.last_commit_stamp)
 501
 502         def getLinesInBlob(self, sha1):
 503                 try:
 504                         res = self.cache['lines_in_blob'][sha1]
 505                 except:
 506                         res = int(getpipeoutput(['git cat-file blob %s' % sha1, 'wc -l']).split()[0])
 507                         if 'lines_in_blob' not in self.cache:
 508                                 self.cache['lines_in_blob'] = {}
 509                         self.cache['lines_in_blob'][sha1] = res
 510                 return res
 511
 512         def getTags(self):
 513                 lines = getpipeoutput(['git show-ref --tags', 'cut -d/ -f3'])
 514                 return lines.split('\n')
 515
 516         def getTagDate(self, tag):
 517                 return self.revToDate('tags/' + tag)
 518
 519         def getTotalAuthors(self):
 520                 return self.total_authors
 521
 522         def getTotalCommits(self):
 523                 return self.total_commits
 524
 525         def getTotalFiles(self):
 526                 return self.total_files
 527
 528         def getTotalLOC(self):
 529                 return self.total_lines
 530
 531         def revToDate(self, rev):
 532                 stamp = int(getpipeoutput(['git log --pretty=format:%%at "%s" -n 1' % rev]))
 533                 return datetime.datetime.fromtimestamp(stamp).strftime('%Y-%m-%d')
 534
 535 class ReportCreator:
 536         """Creates the actual report based on given data."""
 537         def __init__(self):
 538                 pass
 539
 540         def create(self, data, path):
 541                 self.data = data
 542                 self.path = path
 543
 544 def html_linkify(text):
 545         return text.lower().replace(' ', '_')
 546
 547 def html_header(level, text):
 548         name = html_linkify(text)
 549         return '\n<h%d><a href="#%s" name="%s">%s</a></h%d>\n\n' % (level, name, name, text, level)
 550
 551 class HTMLReportCreator(ReportCreator):
 552         def create(self, data, path):
 553                 ReportCreator.create(self, data, path)
 554                 self.title = data.projectname
 555
 556                 # copy static files. Looks in the binary directory, ../share/gitstats and /usr/share/gitstats
 557                 binarypath = os.path.dirname(os.path.abspath(__file__))
 558                 secondarypath = os.path.join(binarypath, '..', 'share', 'gitstats')
 559                 basedirs = [binarypath, secondarypath, '/usr/share/gitstats']
 560                 for file in ('gitstats.css', 'sortable.js', 'arrow-up.gif', 'arrow-down.gif', 'arrow-none.gif'):
 561                         for base in basedirs:
 562                                 src = base + '/' + file
 563                                 if os.path.exists(src):
 564                                         shutil.copyfile(src, path + '/' + file)
 565                                         break
 566                         else:
 567                                 print 'Warning: "%s" not found, so not copied (searched: %s)' % (file, basedirs)
 568
 569                 f = open(path + "/index.html", 'w')
 570                 format = '%Y-%m-%d %H:%M:%S'
 571                 self.printHeader(f)
 572
 573                 f.write('<h1>GitStats - %s</h1>' % data.projectname)
 574
 575                 self.printNav(f)
 576
 577                 f.write('<dl>')
 578                 f.write('<dt>Project name</dt><dd>%s</dd>' % (data.projectname))
 579                 f.write('<dt>Generated</dt><dd>%s (in %d seconds)</dd>' % (datetime.datetime.now().strftime(format), time.time() - data.getStampCreated()))
 580                 f.write('<dt>Generator</dt><dd><a href="http://gitstats.sourceforge.net/">GitStats</a> (version %s)</dd>' % getversion())
 581                 f.write('<dt>Report Period</dt><dd>%s to %s</dd>' % (data.getFirstCommitDate().strftime(format), data.getLastCommitDate().strftime(format)))
 582                 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())))
 583                 f.write('<dt>Total Files</dt><dd>%s</dd>' % data.getTotalFiles())
 584                 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))
 585                 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()))
 586                 f.write('<dt>Authors</dt><dd>%s (average %.1f commits per author)</dd>' % (data.getTotalAuthors(), (1.0 * data.getTotalCommits()) / data.getTotalAuthors()))
 587                 f.write('</dl>')
 588
 589                 f.write('</body>\n</html>')
 590                 f.close()
 591
 592                 ###
 593                 # Activity
 594                 f = open(path + '/activity.html', 'w')
 595                 self.printHeader(f)
 596                 f.write('<h1>Activity</h1>')
 597                 self.printNav(f)
 598
 599                 #f.write('<h2>Last 30 days</h2>')
 600
 601                 #f.write('<h2>Last 12 months</h2>')
 602
 603                 # Weekly activity
 604                 WEEKS = 32
 605                 f.write(html_header(2, 'Weekly activity'))
 606                 f.write('<p>Last %d weeks</p>' % WEEKS)
 607
 608                 # generate weeks to show (previous N weeks from now)
 609                 now = datetime.datetime.now()
 610                 deltaweek = datetime.timedelta(7)
 611                 weeks = []
 612                 stampcur = now
 613                 for i in range(0, WEEKS):
 614                         weeks.insert(0, stampcur.strftime('%Y-%W'))
 615                         stampcur -= deltaweek
 616
 617                 # top row: commits & bar
 618                 f.write('<table class="noborders"><tr>')
 619                 for i in range(0, WEEKS):
 620                         commits = 0
 621                         if weeks[i] in data.activity_by_year_week:
 622                                 commits = data.activity_by_year_week[weeks[i]]
 623
 624                         percentage = 0
 625                         if weeks[i] in data.activity_by_year_week:
 626                                 percentage = float(data.activity_by_year_week[weeks[i]]) / data.activity_by_year_week_peak
 627                         height = max(1, int(200 * percentage))
 628                         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))
 629
 630                 # bottom row: year/week
 631                 f.write('</tr><tr>')
 632                 for i in range(0, WEEKS):
 633                         f.write('<td>%s</td>' % (WEEKS - i))
 634                 f.write('</tr></table>')
 635
 636                 # Hour of Day
 637                 f.write(html_header(2, 'Hour of Day'))
 638                 hour_of_day = data.getActivityByHourOfDay()
 639                 f.write('<table><tr><th>Hour</th>')
 640                 for i in range(0, 24):
 641                         f.write('<th>%d</th>' % i)
 642                 f.write('</tr>\n<tr><th>Commits</th>')
 643                 fp = open(path + '/hour_of_day.dat', 'w')
 644                 for i in range(0, 24):
 645                         if i in hour_of_day:
 646                                 r = 127 + int((float(hour_of_day[i]) / data.activity_by_hour_of_day_busiest) * 128)
 647                                 f.write('<td style="background-color: rgb(%d, 0, 0)">%d</td>' % (r, hour_of_day[i]))
 648                                 fp.write('%d %d\n' % (i, hour_of_day[i]))
 649                         else:
 650                                 f.write('<td>0</td>')
 651                                 fp.write('%d 0\n' % i)
 652                 fp.close()
 653                 f.write('</tr>\n<tr><th>%</th>')
 654                 totalcommits = data.getTotalCommits()
 655                 for i in range(0, 24):
 656                         if i in hour_of_day:
 657                                 r = 127 + int((float(hour_of_day[i]) / data.activity_by_hour_of_day_busiest) * 128)
 658                                 f.write('<td style="background-color: rgb(%d, 0, 0)">%.2f</td>' % (r, (100.0 * hour_of_day[i]) / totalcommits))
 659                         else:
 660                                 f.write('<td>0.00</td>')
 661                 f.write('</tr></table>')
 662                 f.write('<img src="hour_of_day.png" alt="Hour of Day" />')
 663                 fg = open(path + '/hour_of_day.dat', 'w')
 664                 for i in range(0, 24):
 665                         if i in hour_of_day:
 666                                 fg.write('%d %d\n' % (i + 1, hour_of_day[i]))
 667                         else:
 668                                 fg.write('%d 0\n' % (i + 1))
 669                 fg.close()
 670
 671                 # Day of Week
 672                 f.write(html_header(2, 'Day of Week'))
 673                 day_of_week = data.getActivityByDayOfWeek()
 674                 f.write('<div class="vtable"><table>')
 675                 f.write('<tr><th>Day</th><th>Total (%)</th></tr>')
 676                 fp = open(path + '/day_of_week.dat', 'w')
 677                 for d in range(0, 7):
 678                         commits = 0
 679                         if d in day_of_week:
 680                                 commits = day_of_week[d]
 681                         fp.write('%d %s %d\n' % (d + 1, WEEKDAYS[d], commits))
 682                         f.write('<tr>')
 683                         f.write('<th>%s</th>' % (WEEKDAYS[d]))
 684                         if d in day_of_week:
 685                                 f.write('<td>%d (%.2f%%)</td>' % (day_of_week[d], (100.0 * day_of_week[d]) / totalcommits))
 686                         else:
 687                                 f.write('<td>0</td>')
 688                         f.write('</tr>')
 689                 f.write('</table></div>')
 690                 f.write('<img src="day_of_week.png" alt="Day of Week" />')
 691                 fp.close()
 692
 693                 # Hour of Week
 694                 f.write(html_header(2, 'Hour of Week'))
 695                 f.write('<table>')
 696
 697                 f.write('<tr><th>Weekday</th>')
 698                 for hour in range(0, 24):
 699                         f.write('<th>%d</th>' % (hour))
 700                 f.write('</tr>')
 701
 702                 for weekday in range(0, 7):
 703                         f.write('<tr><th>%s</th>' % (WEEKDAYS[weekday]))
 704                         for hour in range(0, 24):
 705                                 try:
 706                                         commits = data.activity_by_hour_of_week[weekday][hour]
 707                                 except KeyError:
 708                                         commits = 0
 709                                 if commits != 0:
 710                                         f.write('<td')
 711                                         r = 127 + int((float(commits) / data.activity_by_hour_of_week_busiest) * 128)
 712                                         f.write(' style="background-color: rgb(%d, 0, 0)"' % r)
 713                                         f.write('>%d</td>' % commits)
 714                                 else:
 715                                         f.write('<td></td>')
 716                         f.write('</tr>')
 717
 718                 f.write('</table>')
 719
 720                 # Month of Year
 721                 f.write(html_header(2, 'Month of Year'))
 722                 f.write('<div class="vtable"><table>')
 723                 f.write('<tr><th>Month</th><th>Commits (%)</th></tr>')
 724                 fp = open (path + '/month_of_year.dat', 'w')
 725                 for mm in range(1, 13):
 726                         commits = 0
 727                         if mm in data.activity_by_month_of_year:
 728                                 commits = data.activity_by_month_of_year[mm]
 729                         f.write('<tr><td>%d</td><td>%d (%.2f %%)</td></tr>' % (mm, commits, (100.0 * commits) / data.getTotalCommits()))
 730                         fp.write('%d %d\n' % (mm, commits))
 731                 fp.close()
 732                 f.write('</table></div>')
 733                 f.write('<img src="month_of_year.png" alt="Month of Year" />')
 734
 735                 # Commits by year/month
 736                 f.write(html_header(2, 'Commits by year/month'))
 737                 f.write('<div class="vtable"><table><tr><th>Month</th><th>Commits</th></tr>')
 738                 for yymm in reversed(sorted(data.commits_by_month.keys())):
 739                         f.write('<tr><td>%s</td><td>%d</td></tr>' % (yymm, data.commits_by_month[yymm]))
 740                 f.write('</table></div>')
 741                 f.write('<img src="commits_by_year_month.png" alt="Commits by year/month" />')
 742                 fg = open(path + '/commits_by_year_month.dat', 'w')
 743                 for yymm in sorted(data.commits_by_month.keys()):
 744                         fg.write('%s %s\n' % (yymm, data.commits_by_month[yymm]))
 745                 fg.close()
 746
 747                 # Commits by year
 748                 f.write(html_header(2, 'Commits by Year'))
 749                 f.write('<div class="vtable"><table><tr><th>Year</th><th>Commits (% of all)</th></tr>')
 750                 for yy in reversed(sorted(data.commits_by_year.keys())):
 751                         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()))
 752                 f.write('</table></div>')
 753                 f.write('<img src="commits_by_year.png" alt="Commits by Year" />')
 754                 fg = open(path + '/commits_by_year.dat', 'w')
 755                 for yy in sorted(data.commits_by_year.keys()):
 756                         fg.write('%d %d\n' % (yy, data.commits_by_year[yy]))
 757                 fg.close()
 758
 759                 # Commits by timezone
 760                 f.write(html_header(2, 'Commits by Timezone'))
 761                 f.write('<table><tr>')
 762                 f.write('<th>Timezone</th><th>Commits</th>')
 763                 max_commits_on_tz = max(data.commits_by_timezone.values())
 764                 for i in sorted(data.commits_by_timezone.keys(), key = lambda n : int(n)):
 765                         commits = data.commits_by_timezone[i]
 766                         r = 127 + int((float(commits) / max_commits_on_tz) * 128)
 767                         f.write('<tr><th>%s</th><td style="background-color: rgb(%d, 0, 0)">%d</td></tr>' % (i, r, commits))
 768                 f.write('</tr></table>')
 769
 770                 f.write('</body></html>')
 771                 f.close()
 772
 773                 ###
 774                 # Authors
 775                 f = open(path + '/authors.html', 'w')
 776                 self.printHeader(f)
 777
 778                 f.write('<h1>Authors</h1>')
 779                 self.printNav(f)
 780
 781                 # Authors :: List of authors
 782                 f.write(html_header(2, 'List of Authors'))
 783
 784                 f.write('<table class="authors sortable" id="authors">')
 785                 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>')
 786                 for author in data.getAuthors(conf['max_authors']):
 787                         info = data.getAuthorInfo(author)
 788                         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'], info['active_days'], info['place_by_commits']))
 789                 f.write('</table>')
 790
 791                 allauthors = data.getAuthors()
 792                 if len(allauthors) > conf['max_authors']:
 793                         rest = allauthors[conf['max_authors']:]
 794                         f.write('<p class="moreauthors">These didn\'t make it to the top: %s</p>' % ', '.join(rest))
 795
 796                 # Authors :: Author of Month
 797                 f.write(html_header(2, 'Author of Month'))
 798                 f.write('<table class="sortable" id="aom">')
 799                 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'])
 800                 for yymm in reversed(sorted(data.author_of_month.keys())):
 801                         authordict = data.author_of_month[yymm]
 802                         authors = getkeyssortedbyvalues(authordict)
 803                         authors.reverse()
 804                         commits = data.author_of_month[yymm][authors[0]]
 805                         next = ', '.join(authors[1:conf['authors_top']+1])
 806                         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)))
 807
 808                 f.write('</table>')
 809
 810                 f.write(html_header(2, 'Author of Year'))
 811                 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'])
 812                 for yy in reversed(sorted(data.author_of_year.keys())):
 813                         authordict = data.author_of_year[yy]
 814                         authors = getkeyssortedbyvalues(authordict)
 815                         authors.reverse()
 816                         commits = data.author_of_year[yy][authors[0]]
 817                         next = ', '.join(authors[1:conf['authors_top']+1])
 818                         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)))
 819                 f.write('</table>')
 820
 821                 # Domains
 822                 f.write(html_header(2, 'Commits by Domains'))
 823                 domains_by_commits = getkeyssortedbyvaluekey(data.domains, 'commits')
 824                 domains_by_commits.reverse() # most first
 825                 f.write('<div class="vtable"><table>')
 826                 f.write('<tr><th>Domains</th><th>Total (%)</th></tr>')
 827                 fp = open(path + '/domains.dat', 'w')
 828                 n = 0
 829                 for domain in domains_by_commits:
 830                         if n == conf['max_domains']:
 831                                 break
 832                         commits = 0
 833                         n += 1
 834                         info = data.getDomainInfo(domain)
 835                         fp.write('%s %d %d\n' % (domain, n , info['commits']))
 836                         f.write('<tr><th>%s</th><td>%d (%.2f%%)</td></tr>' % (domain, info['commits'], (100.0 * info['commits'] / totalcommits)))
 837                 f.write('</table></div>')
 838                 f.write('<img src="domains.png" alt="Commits by Domains" />')
 839                 fp.close()
 840
 841                 f.write('</body></html>')
 842                 f.close()
 843
 844                 ###
 845                 # Files
 846                 f = open(path + '/files.html', 'w')
 847                 self.printHeader(f)
 848                 f.write('<h1>Files</h1>')
 849                 self.printNav(f)
 850
 851                 f.write('<dl>\n')
 852                 f.write('<dt>Total files</dt><dd>%d</dd>' % data.getTotalFiles())
 853                 f.write('<dt>Total lines</dt><dd>%d</dd>' % data.getTotalLOC())
 854                 f.write('<dt>Average file size</dt><dd>%.2f bytes</dd>' % ((100.0 * data.getTotalLOC()) / data.getTotalFiles()))
 855                 f.write('</dl>\n')
 856
 857                 # Files :: File count by date
 858                 f.write(html_header(2, 'File count by date'))
 859
 860                 # use set to get rid of duplicate/unnecessary entries
 861                 files_by_date = set()
 862                 for stamp in sorted(data.files_by_stamp.keys()):
 863                         files_by_date.add('%s %d' % (datetime.datetime.fromtimestamp(stamp).strftime('%Y-%m-%d'), data.files_by_stamp[stamp]))
 864
 865                 fg = open(path + '/files_by_date.dat', 'w')
 866                 for line in sorted(list(files_by_date)):
 867                         fg.write('%s\n' % line)
 868                 #for stamp in sorted(data.files_by_stamp.keys()):
 869                 #       fg.write('%s %d\n' % (datetime.datetime.fromtimestamp(stamp).strftime('%Y-%m-%d'), data.files_by_stamp[stamp]))
 870                 fg.close()
 871
 872                 f.write('<img src="files_by_date.png" alt="Files by Date" />')
 873
 874                 #f.write('<h2>Average file size by date</h2>')
 875
 876                 # Files :: Extensions
 877                 f.write(html_header(2, 'Extensions'))
 878                 f.write('<table class="sortable" id="ext"><tr><th>Extension</th><th>Files (%)</th><th>Lines (%)</th><th>Lines/file</th></tr>')
 879                 for ext in sorted(data.extensions.keys()):
 880                         files = data.extensions[ext]['files']
 881                         lines = data.extensions[ext]['lines']
 882                         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))
 883                 f.write('</table>')
 884
 885                 f.write('</body></html>')
 886                 f.close()
 887
 888                 ###
 889                 # Lines
 890                 f = open(path + '/lines.html', 'w')
 891                 self.printHeader(f)
 892                 f.write('<h1>Lines</h1>')
 893                 self.printNav(f)
 894
 895                 f.write('<dl>\n')
 896                 f.write('<dt>Total lines</dt><dd>%d</dd>' % data.getTotalLOC())
 897                 f.write('</dl>\n')
 898
 899                 f.write(html_header(2, 'Lines of Code'))
 900                 f.write('<img src="lines_of_code.png" />')
 901
 902                 fg = open(path + '/lines_of_code.dat', 'w')
 903                 for stamp in sorted(data.changes_by_date.keys()):
 904                         fg.write('%d %d\n' % (stamp, data.changes_by_date[stamp]['lines']))
 905                 fg.close()
 906
 907                 f.write('</body></html>')
 908                 f.close()
 909
 910                 ###
 911                 # tags.html
 912                 f = open(path + '/tags.html', 'w')
 913                 self.printHeader(f)
 914                 f.write('<h1>Tags</h1>')
 915                 self.printNav(f)
 916
 917                 f.write('<dl>')
 918                 f.write('<dt>Total tags</dt><dd>%d</dd>' % len(data.tags))
 919                 if len(data.tags) > 0:
 920                         f.write('<dt>Average commits per tag</dt><dd>%.2f</dd>' % (1.0 * data.getTotalCommits() / len(data.tags)))
 921                 f.write('</dl>')
 922
 923                 f.write('<table class="tags">')
 924                 f.write('<tr><th>Name</th><th>Date</th><th>Commits</th><th>Authors</th></tr>')
 925                 # sort the tags by date desc
 926                 tags_sorted_by_date_desc = map(lambda el : el[1], reversed(sorted(map(lambda el : (el[1]['date'], el[0]), data.tags.items()))))
 927                 for tag in tags_sorted_by_date_desc:
 928                         authorinfo = []
 929                         authors_by_commits = getkeyssortedbyvalues(data.tags[tag]['authors'])
 930                         for i in reversed(authors_by_commits):
 931                                 authorinfo.append('%s (%d)' % (i, data.tags[tag]['authors'][i]))
 932                         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)))
 933                 f.write('</table>')
 934
 935                 f.write('</body></html>')
 936                 f.close()
 937
 938                 self.createGraphs(path)
 939
 940         def createGraphs(self, path):
 941                 print 'Generating graphs...'
 942
 943                 # hour of day
 944                 f = open(path + '/hour_of_day.plot', 'w')
 945                 f.write(GNUPLOT_COMMON)
 946                 f.write(
 947 """
 948 set output 'hour_of_day.png'
 949 unset key
 950 set xrange [0.5:24.5]
 951 set xtics 4
 952 set grid y
 953 set ylabel "Commits"
 954 plot 'hour_of_day.dat' using 1:2:(0.5) w boxes fs solid
 955 """)
 956                 f.close()
 957
 958                 # day of week
 959                 f = open(path + '/day_of_week.plot', 'w')
 960                 f.write(GNUPLOT_COMMON)
 961                 f.write(
 962 """
 963 set output 'day_of_week.png'
 964 unset key
 965 set xrange [0.5:7.5]
 966 set xtics 1
 967 set grid y
 968 set ylabel "Commits"
 969 plot 'day_of_week.dat' using 1:3:(0.5):xtic(2) w boxes fs solid
 970 """)
 971                 f.close()
 972
 973                 # Domains
 974                 f = open(path + '/domains.plot', 'w')
 975                 f.write(GNUPLOT_COMMON)
 976                 f.write(
 977 """
 978 set output 'domains.png'
 979 unset key
 980 unset xtics
 981 set grid y
 982 set ylabel "Commits"
 983 plot 'domains.dat' using 2:3:(0.5) with boxes fs solid, '' using 2:3:1 with labels rotate by 45 offset 0,1
 984 """)
 985                 f.close()
 986
 987                 # Month of Year
 988                 f = open(path + '/month_of_year.plot', 'w')
 989                 f.write(GNUPLOT_COMMON)
 990                 f.write(
 991 """
 992 set output 'month_of_year.png'
 993 unset key
 994 set xrange [0.5:12.5]
 995 set xtics 1
 996 set grid y
 997 set ylabel "Commits"
 998 plot 'month_of_year.dat' using 1:2:(0.5) w boxes fs solid
 999 """)
1000                 f.close()
1001
1002                 # commits_by_year_month
1003                 f = open(path + '/commits_by_year_month.plot', 'w')
1004                 f.write(GNUPLOT_COMMON)
1005                 f.write(
1006 """
1007 set output 'commits_by_year_month.png'
1008 unset key
1009 set xdata time
1010 set timefmt "%Y-%m"
1011 set format x "%Y-%m"
1012 set xtics rotate by 90 15768000
1013 set bmargin 5
1014 set grid y
1015 set ylabel "Commits"
1016 plot 'commits_by_year_month.dat' using 1:2:(0.5) w boxes fs solid
1017 """)
1018                 f.close()
1019
1020                 # commits_by_year
1021                 f = open(path + '/commits_by_year.plot', 'w')
1022                 f.write(GNUPLOT_COMMON)
1023                 f.write(
1024 """
1025 set output 'commits_by_year.png'
1026 unset key
1027 set xtics 1 rotate by 90
1028 set grid y
1029 set ylabel "Commits"
1030 set yrange [0:]
1031 plot 'commits_by_year.dat' using 1:2:(0.5) w boxes fs solid
1032 """)
1033                 f.close()
1034
1035                 # Files by date
1036                 f = open(path + '/files_by_date.plot', 'w')
1037                 f.write(GNUPLOT_COMMON)
1038                 f.write(
1039 """
1040 set output 'files_by_date.png'
1041 unset key
1042 set xdata time
1043 set timefmt "%Y-%m-%d"
1044 set format x "%Y-%m-%d"
1045 set grid y
1046 set ylabel "Files"
1047 set xtics rotate by 90
1048 set ytics autofreq
1049 set bmargin 6
1050 plot 'files_by_date.dat' using 1:2 w steps
1051 """)
1052                 f.close()
1053
1054                 # Lines of Code
1055                 f = open(path + '/lines_of_code.plot', 'w')
1056                 f.write(GNUPLOT_COMMON)
1057                 f.write(
1058 """
1059 set output 'lines_of_code.png'
1060 unset key
1061 set xdata time
1062 set timefmt "%s"
1063 set format x "%Y-%m-%d"
1064 set grid y
1065 set ylabel "Lines"
1066 set xtics rotate by 90
1067 set bmargin 6
1068 plot 'lines_of_code.dat' using 1:2 w lines
1069 """)
1070                 f.close()
1071
1072                 os.chdir(path)
1073                 files = glob.glob(path + '/*.plot')
1074                 for f in files:
1075                         out = getpipeoutput([gnuplot_cmd + ' "%s"' % f])
1076                         if len(out) > 0:
1077                                 print out
1078
1079         def printHeader(self, f, title = ''):
1080                 f.write(
1081 """<?xml version="1.0" encoding="UTF-8"?>
1082 <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN" "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
1083 <html xmlns="http://www.w3.org/1999/xhtml">
1084 <head>
1085         <title>GitStats - %s</title>
1086         <link rel="stylesheet" href="%s" type="text/css" />
1087         <meta name="generator" content="GitStats %s" />
1088         <script type="text/javascript" src="sortable.js"></script>
1089 </head>
1090 <body>
1091 """ % (self.title, conf['style'], getversion()))
1092
1093         def printNav(self, f):
1094                 f.write("""
1095 <div class="nav">
1096 <ul>
1097 <li><a href="index.html">General</a></li>
1098 <li><a href="activity.html">Activity</a></li>
1099 <li><a href="authors.html">Authors</a></li>
1100 <li><a href="files.html">Files</a></li>
1101 <li><a href="lines.html">Lines</a></li>
1102 <li><a href="tags.html">Tags</a></li>
1103 </ul>
1104 </div>
1105 """)
1106
1107
1108 class GitStats:
1109         def run(self, args_orig):
1110                 optlist, args = getopt.getopt(args_orig, 'c:')
1111                 for o,v in optlist:
1112                         if o == '-c':
1113                                 key, value = v.split('=', 1)
1114                                 if key not in conf:
1115                                         raise 'Error: no such key "%s" in config' % key
1116                                 if isinstance(conf[key], int):
1117                                         conf[key] = int(value)
1118                                 else:
1119                                         conf[key] = value
1120
1121                 if len(args) < 2:
1122                         print """
1123 Usage: gitstats [options] <gitpath> <outputpath>
1124
1125 Options:
1126 -c key=value     Override configuration value
1127
1128 Default config values:
1129 %s
1130 """ % conf
1131                         sys.exit(0)
1132
1133                 gitpath = args[0]
1134                 outputpath = os.path.abspath(args[1])
1135                 rundir = os.getcwd()
1136
1137                 try:
1138                         os.makedirs(outputpath)
1139                 except OSError:
1140                         pass
1141                 if not os.path.isdir(outputpath):
1142                         print 'FATAL: Output path is not a directory or does not exist'
1143                         sys.exit(1)
1144
1145                 print 'Git path: %s' % gitpath
1146                 print 'Output path: %s' % outputpath
1147
1148                 os.chdir(gitpath)
1149
1150                 cachefile = os.path.join(outputpath, 'gitstats.cache')
1151
1152                 print 'Collecting data...'
1153                 data = GitDataCollector()
1154                 data.loadCache(cachefile)
1155                 data.collect(gitpath)
1156                 print 'Refining data...'
1157                 data.saveCache(cachefile)
1158                 data.refine()
1159
1160                 os.chdir(rundir)
1161
1162                 print 'Generating report...'
1163                 report = HTMLReportCreator()
1164                 report.create(data, outputpath)
1165
1166                 time_end = time.time()
1167                 exectime_internal = time_end - time_start
1168                 print 'Execution time %.5f secs, %.5f secs (%.2f %%) in external commands)' % (exectime_internal, exectime_external, (100.0 * exectime_external) / exectime_internal)
1169
1170 g = GitStats()
1171 g.run(sys.argv[1:])
1172