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         'linear_linestats': 1,
  40 }
  41
  42 def getpipeoutput(cmds, quiet = False):
  43         global exectime_external
  44         start = time.time()
  45         if not quiet and ON_LINUX and os.isatty(1):
  46                 print '>> ' + ' | '.join(cmds),
  47                 sys.stdout.flush()
  48         p0 = subprocess.Popen(cmds[0], stdout = subprocess.PIPE, shell = True)
  49         p = p0
  50         for x in cmds[1:]:
  51                 p = subprocess.Popen(x, stdin = p0.stdout, stdout = subprocess.PIPE, shell = True)
  52                 p0 = p
  53         output = p.communicate()[0]
  54         end = time.time()
  55         if not quiet:
  56                 if ON_LINUX and os.isatty(1):
  57                         print '\r',
  58                 print '[%.5f] >> %s' % (end - start, ' | '.join(cmds))
  59         exectime_external += (end - start)
  60         return output.rstrip('\n')
  61
  62 def getcommitrange(defaultrange = 'HEAD', end_only = False):
  63         if len(conf['commit_end']) > 0:
  64                 if end_only or len(conf['commit_begin']) == 0:
  65                         return conf['commit_end']
  66                 return '%s..%s' % (conf['commit_begin'], conf['commit_end'])
  67         return defaultrange
  68
  69 def getkeyssortedbyvalues(dict):
  70         return map(lambda el : el[1], sorted(map(lambda el : (el[1], el[0]), dict.items())))
  71
  72 # dict['author'] = { 'commits': 512 } - ...key(dict, 'commits')
  73 def getkeyssortedbyvaluekey(d, key):
  74         return map(lambda el : el[1], sorted(map(lambda el : (d[el][key], el), d.keys())))
  75
  76 VERSION = 0
  77 def getversion():
  78         global VERSION
  79         if VERSION == 0:
  80                 VERSION = getpipeoutput(["git rev-parse --short %s" % getcommitrange('HEAD')]).split('\n')[0]
  81         return VERSION
  82
  83 class DataCollector:
  84         """Manages data collection from a revision control repository."""
  85         def __init__(self):
  86                 self.stamp_created = time.time()
  87                 self.cache = {}
  88
  89         ##
  90         # This should be the main function to extract data from the repository.
  91         def collect(self, dir):
  92                 self.dir = dir
  93                 self.projectname = os.path.basename(os.path.abspath(dir))
  94
  95         ##
  96         # Load cacheable data
  97         def loadCache(self, cachefile):
  98                 if not os.path.exists(cachefile):
  99                         return
 100                 print 'Loading cache...'
 101                 f = open(cachefile, 'rb')
 102                 try:
 103                         self.cache = pickle.loads(zlib.decompress(f.read()))
 104                 except:
 105                         # temporary hack to upgrade non-compressed caches
 106                         f.seek(0)
 107                         self.cache = pickle.load(f)
 108                 f.close()
 109
 110         ##
 111         # Produce any additional statistics from the extracted data.
 112         def refine(self):
 113                 pass
 114
 115         ##
 116         # : get a dictionary of author
 117         def getAuthorInfo(self, author):
 118                 return None
 119
 120         def getActivityByDayOfWeek(self):
 121                 return {}
 122
 123         def getActivityByHourOfDay(self):
 124                 return {}
 125
 126         # : get a dictionary of domains
 127         def getDomainInfo(self, domain):
 128                 return None
 129
 130         ##
 131         # Get a list of authors
 132         def getAuthors(self):
 133                 return []
 134
 135         def getFirstCommitDate(self):
 136                 return datetime.datetime.now()
 137
 138         def getLastCommitDate(self):
 139                 return datetime.datetime.now()
 140
 141         def getStampCreated(self):
 142                 return self.stamp_created
 143
 144         def getTags(self):
 145                 return []
 146
 147         def getTotalAuthors(self):
 148                 return -1
 149
 150         def getTotalCommits(self):
 151                 return -1
 152
 153         def getTotalFiles(self):
 154                 return -1
 155
 156         def getTotalLOC(self):
 157                 return -1
 158
 159         ##
 160         # Save cacheable data
 161         def saveCache(self, cachefile):
 162                 print 'Saving cache...'
 163                 f = open(cachefile, 'wb')
 164                 #pickle.dump(self.cache, f)
 165                 data = zlib.compress(pickle.dumps(self.cache))
 166                 f.write(data)
 167                 f.close()
 168
 169 class GitDataCollector(DataCollector):
 170         def collect(self, dir):
 171                 DataCollector.collect(self, dir)
 172
 173                 try:
 174                         self.total_authors = int(getpipeoutput(['git shortlog -s %s' % getcommitrange(), 'wc -l']))
 175                 except:
 176                         self.total_authors = 0
 177                 #self.total_lines = int(getoutput('git-ls-files -z |xargs -0 cat |wc -l'))
 178
 179                 self.activity_by_hour_of_day = {} # hour -> commits
 180                 self.activity_by_day_of_week = {} # day -> commits
 181                 self.activity_by_month_of_year = {} # month [1-12] -> commits
 182                 self.activity_by_hour_of_week = {} # weekday -> hour -> commits
 183                 self.activity_by_hour_of_day_busiest = 0
 184                 self.activity_by_hour_of_week_busiest = 0
 185                 self.activity_by_year_week = {} # yy_wNN -> commits
 186                 self.activity_by_year_week_peak = 0
 187
 188                 self.authors = {} # name -> {commits, first_commit_stamp, last_commit_stamp, last_active_day, active_days, lines_added, lines_removed}
 189
 190                 # domains
 191                 self.domains = {} # domain -> commits
 192
 193                 # author of the month
 194                 self.author_of_month = {} # month -> author -> commits
 195                 self.author_of_year = {} # year -> author -> commits
 196                 self.commits_by_month = {} # month -> commits
 197                 self.commits_by_year = {} # year -> commits
 198                 self.first_commit_stamp = 0
 199                 self.last_commit_stamp = 0
 200                 self.last_active_day = None
 201                 self.active_days = set()
 202
 203                 # lines
 204                 self.total_lines = 0
 205                 self.total_lines_added = 0
 206                 self.total_lines_removed = 0
 207
 208                 # timezone
 209                 self.commits_by_timezone = {} # timezone -> commits
 210
 211                 # tags
 212                 self.tags = {}
 213                 lines = getpipeoutput(['git show-ref --tags']).split('\n')
 214                 for line in lines:
 215                         if len(line) == 0:
 216                                 continue
 217                         (hash, tag) = line.split(' ')
 218
 219                         tag = tag.replace('refs/tags/', '')
 220                         output = getpipeoutput(['git log "%s" --pretty=format:"%%at %%aN" -n 1' % hash])
 221                         if len(output) > 0:
 222                                 parts = output.split(' ')
 223                                 stamp = 0
 224                                 try:
 225                                         stamp = int(parts[0])
 226                                 except ValueError:
 227                                         stamp = 0
 228                                 self.tags[tag] = { 'stamp': stamp, 'hash' : hash, 'date' : datetime.datetime.fromtimestamp(stamp).strftime('%Y-%m-%d'), 'commits': 0, 'authors': {} }
 229
 230                 # collect info on tags, starting from latest
 231                 tags_sorted_by_date_desc = map(lambda el : el[1], reversed(sorted(map(lambda el : (el[1]['date'], el[0]), self.tags.items()))))
 232                 prev = None
 233                 for tag in reversed(tags_sorted_by_date_desc):
 234                         cmd = 'git shortlog -s "%s"' % tag
 235                         if prev != None:
 236                                 cmd += ' "^%s"' % prev
 237                         output = getpipeoutput([cmd])
 238                         if len(output) == 0:
 239                                 continue
 240                         prev = tag
 241                         for line in output.split('\n'):
 242                                 parts = re.split('\s+', line, 2)
 243                                 commits = int(parts[1])
 244                                 author = parts[2]
 245                                 self.tags[tag]['commits'] += commits
 246                                 self.tags[tag]['authors'][author] = commits
 247
 248                 # Collect revision statistics
 249                 # Outputs "<stamp> <date> <time> <timezone> <author> '<' <mail> '>'"
 250                 lines = getpipeoutput(['git rev-list --pretty=format:"%%at %%ai %%aN <%%aE>" %s' % getcommitrange('HEAD'), 'grep -v ^commit']).split('\n')
 251                 for line in lines:
 252                         parts = line.split(' ', 4)
 253                         author = ''
 254                         try:
 255                                 stamp = int(parts[0])
 256                         except ValueError:
 257                                 stamp = 0
 258                         timezone = parts[3]
 259                         author, mail = parts[4].split('<', 1)
 260                         author = author.rstrip()
 261                         mail = mail.rstrip('>')
 262                         domain = '?'
 263                         if mail.find('@') != -1:
 264                                 domain = mail.rsplit('@', 1)[1]
 265                         date = datetime.datetime.fromtimestamp(float(stamp))
 266
 267                         # First and last commit stamp
 268                         if self.last_commit_stamp == 0:
 269                                 self.last_commit_stamp = stamp
 270                         self.first_commit_stamp = stamp
 271
 272                         # activity
 273                         # hour
 274                         hour = date.hour
 275                         self.activity_by_hour_of_day[hour] = self.activity_by_hour_of_day.get(hour, 0) + 1
 276                         # most active hour?
 277                         if self.activity_by_hour_of_day[hour] > self.activity_by_hour_of_day_busiest:
 278                                 self.activity_by_hour_of_day_busiest = self.activity_by_hour_of_day[hour]
 279
 280                         # day of week
 281                         day = date.weekday()
 282                         self.activity_by_day_of_week[day] = self.activity_by_day_of_week.get(day, 0) + 1
 283
 284                         # domain stats
 285                         if domain not in self.domains:
 286                                 self.domains[domain] = {}
 287                         # commits
 288                         self.domains[domain]['commits'] = self.domains[domain].get('commits', 0) + 1
 289
 290                         # hour of week
 291                         if day not in self.activity_by_hour_of_week:
 292                                 self.activity_by_hour_of_week[day] = {}
 293                         self.activity_by_hour_of_week[day][hour] = self.activity_by_hour_of_week[day].get(hour, 0) + 1
 294                         # most active hour?
 295                         if self.activity_by_hour_of_week[day][hour] > self.activity_by_hour_of_week_busiest:
 296                                 self.activity_by_hour_of_week_busiest = self.activity_by_hour_of_week[day][hour]
 297
 298                         # month of year
 299                         month = date.month
 300                         self.activity_by_month_of_year[month] = self.activity_by_month_of_year.get(month, 0) + 1
 301
 302                         # yearly/weekly activity
 303                         yyw = date.strftime('%Y-%W')
 304                         self.activity_by_year_week[yyw] = self.activity_by_year_week.get(yyw, 0) + 1
 305                         if self.activity_by_year_week_peak < self.activity_by_year_week[yyw]:
 306                                 self.activity_by_year_week_peak = self.activity_by_year_week[yyw]
 307
 308                         # author stats
 309                         if author not in self.authors:
 310                                 self.authors[author] = {}
 311                         # commits
 312                         if 'last_commit_stamp' not in self.authors[author]:
 313                                 self.authors[author]['last_commit_stamp'] = stamp
 314                         self.authors[author]['first_commit_stamp'] = stamp
 315                         self.authors[author]['commits'] = self.authors[author].get('commits', 0) + 1
 316
 317                         # author of the month/year
 318                         yymm = date.strftime('%Y-%m')
 319                         if yymm in self.author_of_month:
 320                                 self.author_of_month[yymm][author] = self.author_of_month[yymm].get(author, 0) + 1
 321                         else:
 322                                 self.author_of_month[yymm] = {}
 323                                 self.author_of_month[yymm][author] = 1
 324                         self.commits_by_month[yymm] = self.commits_by_month.get(yymm, 0) + 1
 325
 326                         yy = date.year
 327                         if yy in self.author_of_year:
 328                                 self.author_of_year[yy][author] = self.author_of_year[yy].get(author, 0) + 1
 329                         else:
 330                                 self.author_of_year[yy] = {}
 331                                 self.author_of_year[yy][author] = 1
 332                         self.commits_by_year[yy] = self.commits_by_year.get(yy, 0) + 1
 333
 334                         # authors: active days
 335                         yymmdd = date.strftime('%Y-%m-%d')
 336                         if 'last_active_day' not in self.authors[author]:
 337                                 self.authors[author]['last_active_day'] = yymmdd
 338                                 self.authors[author]['active_days'] = 1
 339                         elif yymmdd != self.authors[author]['last_active_day']:
 340                                 self.authors[author]['last_active_day'] = yymmdd
 341                                 self.authors[author]['active_days'] += 1
 342
 343                         # project: active days
 344                         if yymmdd != self.last_active_day:
 345                                 self.last_active_day = yymmdd
 346                                 self.active_days.add(yymmdd)
 347
 348                         # timezone
 349                         self.commits_by_timezone[timezone] = self.commits_by_timezone.get(timezone, 0) + 1
 350
 351                 # TODO Optimize this, it's the worst bottleneck
 352                 # outputs "<stamp> <files>" for each revision
 353                 self.files_by_stamp = {} # stamp -> files
 354                 revlines = getpipeoutput(['git rev-list --pretty=format:"%%at %%T" %s' % getcommitrange('HEAD'), 'grep -v ^commit']).strip().split('\n')
 355                 lines = []
 356                 for revline in revlines:
 357                         time, rev = revline.split(' ')
 358                         linecount = self.getFilesInCommit(rev)
 359                         lines.append('%d %d' % (int(time), linecount))
 360
 361                 self.total_commits = len(lines)
 362                 for line in lines:
 363                         parts = line.split(' ')
 364                         if len(parts) != 2:
 365                                 continue
 366                         (stamp, files) = parts[0:2]
 367                         try:
 368                                 self.files_by_stamp[int(stamp)] = int(files)
 369                         except ValueError:
 370                                 print 'Warning: failed to parse line "%s"' % line
 371
 372                 # extensions
 373                 self.extensions = {} # extension -> files, lines
 374                 lines = getpipeoutput(['git ls-tree -r -z %s' % getcommitrange('HEAD', end_only = True)]).split('\000')
 375                 self.total_files = len(lines)
 376                 for line in lines:
 377                         if len(line) == 0:
 378                                 continue
 379                         parts = re.split('\s+', line, 4)
 380                         sha1 = parts[2]
 381                         filename = parts[3]
 382
 383                         if filename.find('.') == -1 or filename.rfind('.') == 0:
 384                                 ext = ''
 385                         else:
 386                                 ext = filename[(filename.rfind('.') + 1):]
 387                         if len(ext) > conf['max_ext_length']:
 388                                 ext = ''
 389
 390                         if ext not in self.extensions:
 391                                 self.extensions[ext] = {'files': 0, 'lines': 0}
 392
 393                         self.extensions[ext]['files'] += 1
 394                         try:
 395                                 self.extensions[ext]['lines'] += self.getLinesInBlob(sha1)
 396                         except:
 397                                 print 'Warning: Could not count lines for file "%s"' % line
 398
 399                 # line statistics
 400                 # outputs:
 401                 #  N files changed, N insertions (+), N deletions(-)
 402                 # <stamp> <author>
 403                 self.changes_by_date = {} # stamp -> { files, ins, del }
 404                 extra = ''
 405                 if conf['linear_linestats']:
 406                         extra = '--first-parent -m'
 407                 lines = getpipeoutput(['git log --shortstat %s --pretty=format:"%%at %%aN" %s' % (extra, getcommitrange('HEAD'))]).split('\n')
 408                 lines.reverse()
 409                 files = 0; inserted = 0; deleted = 0; total_lines = 0
 410                 author = None
 411                 for line in lines:
 412                         if len(line) == 0:
 413                                 continue
 414
 415                         # <stamp> <author>
 416                         if line.find('files changed,') == -1:
 417                                 pos = line.find(' ')
 418                                 if pos != -1:
 419                                         try:
 420                                                 (stamp, author) = (int(line[:pos]), line[pos+1:])
 421                                                 self.changes_by_date[stamp] = { 'files': files, 'ins': inserted, 'del': deleted, 'lines': total_lines }
 422                                                 if author not in self.authors:
 423                                                         self.authors[author] = { 'lines_added' : 0, 'lines_removed' : 0 }
 424                                                 self.authors[author]['lines_added'] = self.authors[author].get('lines_added', 0) + inserted
 425                                                 self.authors[author]['lines_removed'] = self.authors[author].get('lines_removed', 0) + deleted
 426                                                 files, inserted, deleted = 0, 0, 0
 427                                         except ValueError:
 428                                                 print 'Warning: unexpected line "%s"' % line
 429                                 else:
 430                                         print 'Warning: unexpected line "%s"' % line
 431                         else:
 432                                 numbers = re.findall('\d+', line)
 433                                 if len(numbers) == 3:
 434                                         (files, inserted, deleted) = map(lambda el : int(el), numbers)
 435                                         total_lines += inserted
 436                                         total_lines -= deleted
 437                                         self.total_lines_added += inserted
 438                                         self.total_lines_removed += deleted
 439                                 else:
 440                                         print 'Warning: failed to handle line "%s"' % line
 441                                         (files, inserted, deleted) = (0, 0, 0)
 442                                 #self.changes_by_date[stamp] = { 'files': files, 'ins': inserted, 'del': deleted }
 443                 self.total_lines = total_lines
 444
 445         def refine(self):
 446                 # authors
 447                 # name -> {place_by_commits, commits_frac, date_first, date_last, timedelta}
 448                 authors_by_commits = getkeyssortedbyvaluekey(self.authors, 'commits')
 449                 authors_by_commits.reverse() # most first
 450                 for i, name in enumerate(authors_by_commits):
 451                         self.authors[name]['place_by_commits'] = i + 1
 452
 453                 for name in self.authors.keys():
 454                         a = self.authors[name]
 455                         a['commits_frac'] = (100 * float(a['commits'])) / self.getTotalCommits()
 456                         date_first = datetime.datetime.fromtimestamp(a['first_commit_stamp'])
 457                         date_last = datetime.datetime.fromtimestamp(a['last_commit_stamp'])
 458                         delta = date_last - date_first
 459                         a['date_first'] = date_first.strftime('%Y-%m-%d')
 460                         a['date_last'] = date_last.strftime('%Y-%m-%d')
 461                         a['timedelta'] = delta
 462                         if 'lines_added' not in a: a['lines_added'] = 0
 463                         if 'lines_removed' not in a: a['lines_removed'] = 0
 464
 465         def getActiveDays(self):
 466                 return self.active_days
 467
 468         def getActivityByDayOfWeek(self):
 469                 return self.activity_by_day_of_week
 470
 471         def getActivityByHourOfDay(self):
 472                 return self.activity_by_hour_of_day
 473
 474         def getAuthorInfo(self, author):
 475                 return self.authors[author]
 476
 477         def getAuthors(self, limit = None):
 478                 res = getkeyssortedbyvaluekey(self.authors, 'commits')
 479                 res.reverse()
 480                 return res[:limit]
 481
 482         def getCommitDeltaDays(self):
 483                 return (self.last_commit_stamp - self.first_commit_stamp) / 86400 + 1
 484
 485         def getDomainInfo(self, domain):
 486                 return self.domains[domain]
 487
 488         def getDomains(self):
 489                 return self.domains.keys()
 490
 491         def getFilesInCommit(self, rev):
 492                 try:
 493                         res = self.cache['files_in_tree'][rev]
 494                 except:
 495                         res = int(getpipeoutput(['git ls-tree -r --name-only "%s"' % rev, 'wc -l']).split('\n')[0])
 496                         if 'files_in_tree' not in self.cache:
 497                                 self.cache['files_in_tree'] = {}
 498                         self.cache['files_in_tree'][rev] = res
 499
 500                 return res
 501
 502         def getFirstCommitDate(self):
 503                 return datetime.datetime.fromtimestamp(self.first_commit_stamp)
 504
 505         def getLastCommitDate(self):
 506                 return datetime.datetime.fromtimestamp(self.last_commit_stamp)
 507
 508         def getLinesInBlob(self, sha1):
 509                 try:
 510                         res = self.cache['lines_in_blob'][sha1]
 511                 except:
 512                         res = int(getpipeoutput(['git cat-file blob %s' % sha1, 'wc -l']).split()[0])
 513                         if 'lines_in_blob' not in self.cache:
 514                                 self.cache['lines_in_blob'] = {}
 515                         self.cache['lines_in_blob'][sha1] = res
 516                 return res
 517
 518         def getTags(self):
 519                 lines = getpipeoutput(['git show-ref --tags', 'cut -d/ -f3'])
 520                 return lines.split('\n')
 521
 522         def getTagDate(self, tag):
 523                 return self.revToDate('tags/' + tag)
 524
 525         def getTotalAuthors(self):
 526                 return self.total_authors
 527
 528         def getTotalCommits(self):
 529                 return self.total_commits
 530
 531         def getTotalFiles(self):
 532                 return self.total_files
 533
 534         def getTotalLOC(self):
 535                 return self.total_lines
 536
 537         def revToDate(self, rev):
 538                 stamp = int(getpipeoutput(['git log --pretty=format:%%at "%s" -n 1' % rev]))
 539                 return datetime.datetime.fromtimestamp(stamp).strftime('%Y-%m-%d')
 540
 541 class ReportCreator:
 542         """Creates the actual report based on given data."""
 543         def __init__(self):
 544                 pass
 545
 546         def create(self, data, path):
 547                 self.data = data
 548                 self.path = path
 549
 550 def html_linkify(text):
 551         return text.lower().replace(' ', '_')
 552
 553 def html_header(level, text):
 554         name = html_linkify(text)
 555         return '\n<h%d><a href="#%s" name="%s">%s</a></h%d>\n\n' % (level, name, name, text, level)
 556
 557 class HTMLReportCreator(ReportCreator):
 558         def create(self, data, path):
 559                 ReportCreator.create(self, data, path)
 560                 self.title = data.projectname
 561
 562                 # copy static files. Looks in the binary directory, ../share/gitstats and /usr/share/gitstats
 563                 binarypath = os.path.dirname(os.path.abspath(__file__))
 564                 secondarypath = os.path.join(binarypath, '..', 'share', 'gitstats')
 565                 basedirs = [binarypath, secondarypath, '/usr/share/gitstats']
 566                 for file in ('gitstats.css', 'sortable.js', 'arrow-up.gif', 'arrow-down.gif', 'arrow-none.gif'):
 567                         for base in basedirs:
 568                                 src = base + '/' + file
 569                                 if os.path.exists(src):
 570                                         shutil.copyfile(src, path + '/' + file)
 571                                         break
 572                         else:
 573                                 print 'Warning: "%s" not found, so not copied (searched: %s)' % (file, basedirs)
 574
 575                 f = open(path + "/index.html", 'w')
 576                 format = '%Y-%m-%d %H:%M:%S'
 577                 self.printHeader(f)
 578
 579                 f.write('<h1>GitStats - %s</h1>' % data.projectname)
 580
 581                 self.printNav(f)
 582
 583                 f.write('<dl>')
 584                 f.write('<dt>Project name</dt><dd>%s</dd>' % (data.projectname))
 585                 f.write('<dt>Generated</dt><dd>%s (in %d seconds)</dd>' % (datetime.datetime.now().strftime(format), time.time() - data.getStampCreated()))
 586                 f.write('<dt>Generator</dt><dd><a href="http://gitstats.sourceforge.net/">GitStats</a> (version %s)</dd>' % getversion())
 587                 f.write('<dt>Report Period</dt><dd>%s to %s</dd>' % (data.getFirstCommitDate().strftime(format), data.getLastCommitDate().strftime(format)))
 588                 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())))
 589                 f.write('<dt>Total Files</dt><dd>%s</dd>' % data.getTotalFiles())
 590                 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))
 591                 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()))
 592                 f.write('<dt>Authors</dt><dd>%s (average %.1f commits per author)</dd>' % (data.getTotalAuthors(), (1.0 * data.getTotalCommits()) / data.getTotalAuthors()))
 593                 f.write('</dl>')
 594
 595                 f.write('</body>\n</html>')
 596                 f.close()
 597
 598                 ###
 599                 # Activity
 600                 f = open(path + '/activity.html', 'w')
 601                 self.printHeader(f)
 602                 f.write('<h1>Activity</h1>')
 603                 self.printNav(f)
 604
 605                 #f.write('<h2>Last 30 days</h2>')
 606
 607                 #f.write('<h2>Last 12 months</h2>')
 608
 609                 # Weekly activity
 610                 WEEKS = 32
 611                 f.write(html_header(2, 'Weekly activity'))
 612                 f.write('<p>Last %d weeks</p>' % WEEKS)
 613
 614                 # generate weeks to show (previous N weeks from now)
 615                 now = datetime.datetime.now()
 616                 deltaweek = datetime.timedelta(7)
 617                 weeks = []
 618                 stampcur = now
 619                 for i in range(0, WEEKS):
 620                         weeks.insert(0, stampcur.strftime('%Y-%W'))
 621                         stampcur -= deltaweek
 622
 623                 # top row: commits & bar
 624                 f.write('<table class="noborders"><tr>')
 625                 for i in range(0, WEEKS):
 626                         commits = 0
 627                         if weeks[i] in data.activity_by_year_week:
 628                                 commits = data.activity_by_year_week[weeks[i]]
 629
 630                         percentage = 0
 631                         if weeks[i] in data.activity_by_year_week:
 632                                 percentage = float(data.activity_by_year_week[weeks[i]]) / data.activity_by_year_week_peak
 633                         height = max(1, int(200 * percentage))
 634                         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))
 635
 636                 # bottom row: year/week
 637                 f.write('</tr><tr>')
 638                 for i in range(0, WEEKS):
 639                         f.write('<td>%s</td>' % (WEEKS - i))
 640                 f.write('</tr></table>')
 641
 642                 # Hour of Day
 643                 f.write(html_header(2, 'Hour of Day'))
 644                 hour_of_day = data.getActivityByHourOfDay()
 645                 f.write('<table><tr><th>Hour</th>')
 646                 for i in range(0, 24):
 647                         f.write('<th>%d</th>' % i)
 648                 f.write('</tr>\n<tr><th>Commits</th>')
 649                 fp = open(path + '/hour_of_day.dat', 'w')
 650                 for i in range(0, 24):
 651                         if i in hour_of_day:
 652                                 r = 127 + int((float(hour_of_day[i]) / data.activity_by_hour_of_day_busiest) * 128)
 653                                 f.write('<td style="background-color: rgb(%d, 0, 0)">%d</td>' % (r, hour_of_day[i]))
 654                                 fp.write('%d %d\n' % (i, hour_of_day[i]))
 655                         else:
 656                                 f.write('<td>0</td>')
 657                                 fp.write('%d 0\n' % i)
 658                 fp.close()
 659                 f.write('</tr>\n<tr><th>%</th>')
 660                 totalcommits = data.getTotalCommits()
 661                 for i in range(0, 24):
 662                         if i in hour_of_day:
 663                                 r = 127 + int((float(hour_of_day[i]) / data.activity_by_hour_of_day_busiest) * 128)
 664                                 f.write('<td style="background-color: rgb(%d, 0, 0)">%.2f</td>' % (r, (100.0 * hour_of_day[i]) / totalcommits))
 665                         else:
 666                                 f.write('<td>0.00</td>')
 667                 f.write('</tr></table>')
 668                 f.write('<img src="hour_of_day.png" alt="Hour of Day" />')
 669                 fg = open(path + '/hour_of_day.dat', 'w')
 670                 for i in range(0, 24):
 671                         if i in hour_of_day:
 672                                 fg.write('%d %d\n' % (i + 1, hour_of_day[i]))
 673                         else:
 674                                 fg.write('%d 0\n' % (i + 1))
 675                 fg.close()
 676
 677                 # Day of Week
 678                 f.write(html_header(2, 'Day of Week'))
 679                 day_of_week = data.getActivityByDayOfWeek()
 680                 f.write('<div class="vtable"><table>')
 681                 f.write('<tr><th>Day</th><th>Total (%)</th></tr>')
 682                 fp = open(path + '/day_of_week.dat', 'w')
 683                 for d in range(0, 7):
 684                         commits = 0
 685                         if d in day_of_week:
 686                                 commits = day_of_week[d]
 687                         fp.write('%d %s %d\n' % (d + 1, WEEKDAYS[d], commits))
 688                         f.write('<tr>')
 689                         f.write('<th>%s</th>' % (WEEKDAYS[d]))
 690                         if d in day_of_week:
 691                                 f.write('<td>%d (%.2f%%)</td>' % (day_of_week[d], (100.0 * day_of_week[d]) / totalcommits))
 692                         else:
 693                                 f.write('<td>0</td>')
 694                         f.write('</tr>')
 695                 f.write('</table></div>')
 696                 f.write('<img src="day_of_week.png" alt="Day of Week" />')
 697                 fp.close()
 698
 699                 # Hour of Week
 700                 f.write(html_header(2, 'Hour of Week'))
 701                 f.write('<table>')
 702
 703                 f.write('<tr><th>Weekday</th>')
 704                 for hour in range(0, 24):
 705                         f.write('<th>%d</th>' % (hour))
 706                 f.write('</tr>')
 707
 708                 for weekday in range(0, 7):
 709                         f.write('<tr><th>%s</th>' % (WEEKDAYS[weekday]))
 710                         for hour in range(0, 24):
 711                                 try:
 712                                         commits = data.activity_by_hour_of_week[weekday][hour]
 713                                 except KeyError:
 714                                         commits = 0
 715                                 if commits != 0:
 716                                         f.write('<td')
 717                                         r = 127 + int((float(commits) / data.activity_by_hour_of_week_busiest) * 128)
 718                                         f.write(' style="background-color: rgb(%d, 0, 0)"' % r)
 719                                         f.write('>%d</td>' % commits)
 720                                 else:
 721                                         f.write('<td></td>')
 722                         f.write('</tr>')
 723
 724                 f.write('</table>')
 725
 726                 # Month of Year
 727                 f.write(html_header(2, 'Month of Year'))
 728                 f.write('<div class="vtable"><table>')
 729                 f.write('<tr><th>Month</th><th>Commits (%)</th></tr>')
 730                 fp = open (path + '/month_of_year.dat', 'w')
 731                 for mm in range(1, 13):
 732                         commits = 0
 733                         if mm in data.activity_by_month_of_year:
 734                                 commits = data.activity_by_month_of_year[mm]
 735                         f.write('<tr><td>%d</td><td>%d (%.2f %%)</td></tr>' % (mm, commits, (100.0 * commits) / data.getTotalCommits()))
 736                         fp.write('%d %d\n' % (mm, commits))
 737                 fp.close()
 738                 f.write('</table></div>')
 739                 f.write('<img src="month_of_year.png" alt="Month of Year" />')
 740
 741                 # Commits by year/month
 742                 f.write(html_header(2, 'Commits by year/month'))
 743                 f.write('<div class="vtable"><table><tr><th>Month</th><th>Commits</th></tr>')
 744                 for yymm in reversed(sorted(data.commits_by_month.keys())):
 745                         f.write('<tr><td>%s</td><td>%d</td></tr>' % (yymm, data.commits_by_month[yymm]))
 746                 f.write('</table></div>')
 747                 f.write('<img src="commits_by_year_month.png" alt="Commits by year/month" />')
 748                 fg = open(path + '/commits_by_year_month.dat', 'w')
 749                 for yymm in sorted(data.commits_by_month.keys()):
 750                         fg.write('%s %s\n' % (yymm, data.commits_by_month[yymm]))
 751                 fg.close()
 752
 753                 # Commits by year
 754                 f.write(html_header(2, 'Commits by Year'))
 755                 f.write('<div class="vtable"><table><tr><th>Year</th><th>Commits (% of all)</th></tr>')
 756                 for yy in reversed(sorted(data.commits_by_year.keys())):
 757                         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()))
 758                 f.write('</table></div>')
 759                 f.write('<img src="commits_by_year.png" alt="Commits by Year" />')
 760                 fg = open(path + '/commits_by_year.dat', 'w')
 761                 for yy in sorted(data.commits_by_year.keys()):
 762                         fg.write('%d %d\n' % (yy, data.commits_by_year[yy]))
 763                 fg.close()
 764
 765                 # Commits by timezone
 766                 f.write(html_header(2, 'Commits by Timezone'))
 767                 f.write('<table><tr>')
 768                 f.write('<th>Timezone</th><th>Commits</th>')
 769                 max_commits_on_tz = max(data.commits_by_timezone.values())
 770                 for i in sorted(data.commits_by_timezone.keys(), key = lambda n : int(n)):
 771                         commits = data.commits_by_timezone[i]
 772                         r = 127 + int((float(commits) / max_commits_on_tz) * 128)
 773                         f.write('<tr><th>%s</th><td style="background-color: rgb(%d, 0, 0)">%d</td></tr>' % (i, r, commits))
 774                 f.write('</tr></table>')
 775
 776                 f.write('</body></html>')
 777                 f.close()
 778
 779                 ###
 780                 # Authors
 781                 f = open(path + '/authors.html', 'w')
 782                 self.printHeader(f)
 783
 784                 f.write('<h1>Authors</h1>')
 785                 self.printNav(f)
 786
 787                 # Authors :: List of authors
 788                 f.write(html_header(2, 'List of Authors'))
 789
 790                 f.write('<table class="authors sortable" id="authors">')
 791                 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>')
 792                 for author in data.getAuthors(conf['max_authors']):
 793                         info = data.getAuthorInfo(author)
 794                         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']))
 795                 f.write('</table>')
 796
 797                 allauthors = data.getAuthors()
 798                 if len(allauthors) > conf['max_authors']:
 799                         rest = allauthors[conf['max_authors']:]
 800                         f.write('<p class="moreauthors">These didn\'t make it to the top: %s</p>' % ', '.join(rest))
 801
 802                 # Authors :: Author of Month
 803                 f.write(html_header(2, 'Author of Month'))
 804                 f.write('<table class="sortable" id="aom">')
 805                 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'])
 806                 for yymm in reversed(sorted(data.author_of_month.keys())):
 807                         authordict = data.author_of_month[yymm]
 808                         authors = getkeyssortedbyvalues(authordict)
 809                         authors.reverse()
 810                         commits = data.author_of_month[yymm][authors[0]]
 811                         next = ', '.join(authors[1:conf['authors_top']+1])
 812                         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)))
 813
 814                 f.write('</table>')
 815
 816                 f.write(html_header(2, 'Author of Year'))
 817                 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'])
 818                 for yy in reversed(sorted(data.author_of_year.keys())):
 819                         authordict = data.author_of_year[yy]
 820                         authors = getkeyssortedbyvalues(authordict)
 821                         authors.reverse()
 822                         commits = data.author_of_year[yy][authors[0]]
 823                         next = ', '.join(authors[1:conf['authors_top']+1])
 824                         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)))
 825                 f.write('</table>')
 826
 827                 # Domains
 828                 f.write(html_header(2, 'Commits by Domains'))
 829                 domains_by_commits = getkeyssortedbyvaluekey(data.domains, 'commits')
 830                 domains_by_commits.reverse() # most first
 831                 f.write('<div class="vtable"><table>')
 832                 f.write('<tr><th>Domains</th><th>Total (%)</th></tr>')
 833                 fp = open(path + '/domains.dat', 'w')
 834                 n = 0
 835                 for domain in domains_by_commits:
 836                         if n == conf['max_domains']:
 837                                 break
 838                         commits = 0
 839                         n += 1
 840                         info = data.getDomainInfo(domain)
 841                         fp.write('%s %d %d\n' % (domain, n , info['commits']))
 842                         f.write('<tr><th>%s</th><td>%d (%.2f%%)</td></tr>' % (domain, info['commits'], (100.0 * info['commits'] / totalcommits)))
 843                 f.write('</table></div>')
 844                 f.write('<img src="domains.png" alt="Commits by Domains" />')
 845                 fp.close()
 846
 847                 f.write('</body></html>')
 848                 f.close()
 849
 850                 ###
 851                 # Files
 852                 f = open(path + '/files.html', 'w')
 853                 self.printHeader(f)
 854                 f.write('<h1>Files</h1>')
 855                 self.printNav(f)
 856
 857                 f.write('<dl>\n')
 858                 f.write('<dt>Total files</dt><dd>%d</dd>' % data.getTotalFiles())
 859                 f.write('<dt>Total lines</dt><dd>%d</dd>' % data.getTotalLOC())
 860                 f.write('<dt>Average file size</dt><dd>%.2f bytes</dd>' % ((100.0 * data.getTotalLOC()) / data.getTotalFiles()))
 861                 f.write('</dl>\n')
 862
 863                 # Files :: File count by date
 864                 f.write(html_header(2, 'File count by date'))
 865
 866                 # use set to get rid of duplicate/unnecessary entries
 867                 files_by_date = set()
 868                 for stamp in sorted(data.files_by_stamp.keys()):
 869                         files_by_date.add('%s %d' % (datetime.datetime.fromtimestamp(stamp).strftime('%Y-%m-%d'), data.files_by_stamp[stamp]))
 870
 871                 fg = open(path + '/files_by_date.dat', 'w')
 872                 for line in sorted(list(files_by_date)):
 873                         fg.write('%s\n' % line)
 874                 #for stamp in sorted(data.files_by_stamp.keys()):
 875                 #       fg.write('%s %d\n' % (datetime.datetime.fromtimestamp(stamp).strftime('%Y-%m-%d'), data.files_by_stamp[stamp]))
 876                 fg.close()
 877
 878                 f.write('<img src="files_by_date.png" alt="Files by Date" />')
 879
 880                 #f.write('<h2>Average file size by date</h2>')
 881
 882                 # Files :: Extensions
 883                 f.write(html_header(2, 'Extensions'))
 884                 f.write('<table class="sortable" id="ext"><tr><th>Extension</th><th>Files (%)</th><th>Lines (%)</th><th>Lines/file</th></tr>')
 885                 for ext in sorted(data.extensions.keys()):
 886                         files = data.extensions[ext]['files']
 887                         lines = data.extensions[ext]['lines']
 888                         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))
 889                 f.write('</table>')
 890
 891                 f.write('</body></html>')
 892                 f.close()
 893
 894                 ###
 895                 # Lines
 896                 f = open(path + '/lines.html', 'w')
 897                 self.printHeader(f)
 898                 f.write('<h1>Lines</h1>')
 899                 self.printNav(f)
 900
 901                 f.write('<dl>\n')
 902                 f.write('<dt>Total lines</dt><dd>%d</dd>' % data.getTotalLOC())
 903                 f.write('</dl>\n')
 904
 905                 f.write(html_header(2, 'Lines of Code'))
 906                 f.write('<img src="lines_of_code.png" />')
 907
 908                 fg = open(path + '/lines_of_code.dat', 'w')
 909                 for stamp in sorted(data.changes_by_date.keys()):
 910                         fg.write('%d %d\n' % (stamp, data.changes_by_date[stamp]['lines']))
 911                 fg.close()
 912
 913                 f.write('</body></html>')
 914                 f.close()
 915
 916                 ###
 917                 # tags.html
 918                 f = open(path + '/tags.html', 'w')
 919                 self.printHeader(f)
 920                 f.write('<h1>Tags</h1>')
 921                 self.printNav(f)
 922
 923                 f.write('<dl>')
 924                 f.write('<dt>Total tags</dt><dd>%d</dd>' % len(data.tags))
 925                 if len(data.tags) > 0:
 926                         f.write('<dt>Average commits per tag</dt><dd>%.2f</dd>' % (1.0 * data.getTotalCommits() / len(data.tags)))
 927                 f.write('</dl>')
 928
 929                 f.write('<table class="tags">')
 930                 f.write('<tr><th>Name</th><th>Date</th><th>Commits</th><th>Authors</th></tr>')
 931                 # sort the tags by date desc
 932                 tags_sorted_by_date_desc = map(lambda el : el[1], reversed(sorted(map(lambda el : (el[1]['date'], el[0]), data.tags.items()))))
 933                 for tag in tags_sorted_by_date_desc:
 934                         authorinfo = []
 935                         authors_by_commits = getkeyssortedbyvalues(data.tags[tag]['authors'])
 936                         for i in reversed(authors_by_commits):
 937                                 authorinfo.append('%s (%d)' % (i, data.tags[tag]['authors'][i]))
 938                         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)))
 939                 f.write('</table>')
 940
 941                 f.write('</body></html>')
 942                 f.close()
 943
 944                 self.createGraphs(path)
 945
 946         def createGraphs(self, path):
 947                 print 'Generating graphs...'
 948
 949                 # hour of day
 950                 f = open(path + '/hour_of_day.plot', 'w')
 951                 f.write(GNUPLOT_COMMON)
 952                 f.write(
 953 """
 954 set output 'hour_of_day.png'
 955 unset key
 956 set xrange [0.5:24.5]
 957 set xtics 4
 958 set grid y
 959 set ylabel "Commits"
 960 plot 'hour_of_day.dat' using 1:2:(0.5) w boxes fs solid
 961 """)
 962                 f.close()
 963
 964                 # day of week
 965                 f = open(path + '/day_of_week.plot', 'w')
 966                 f.write(GNUPLOT_COMMON)
 967                 f.write(
 968 """
 969 set output 'day_of_week.png'
 970 unset key
 971 set xrange [0.5:7.5]
 972 set xtics 1
 973 set grid y
 974 set ylabel "Commits"
 975 plot 'day_of_week.dat' using 1:3:(0.5):xtic(2) w boxes fs solid
 976 """)
 977                 f.close()
 978
 979                 # Domains
 980                 f = open(path + '/domains.plot', 'w')
 981                 f.write(GNUPLOT_COMMON)
 982                 f.write(
 983 """
 984 set output 'domains.png'
 985 unset key
 986 unset xtics
 987 set yrange [0:]
 988 set grid y
 989 set ylabel "Commits"
 990 plot 'domains.dat' using 2:3:(0.5) with boxes fs solid, '' using 2:3:1 with labels rotate by 45 offset 0,1
 991 """)
 992                 f.close()
 993
 994                 # Month of Year
 995                 f = open(path + '/month_of_year.plot', 'w')
 996                 f.write(GNUPLOT_COMMON)
 997                 f.write(
 998 """
 999 set output 'month_of_year.png'
1000 unset key
1001 set xrange [0.5:12.5]
1002 set xtics 1
1003 set grid y
1004 set ylabel "Commits"
1005 plot 'month_of_year.dat' using 1:2:(0.5) w boxes fs solid
1006 """)
1007                 f.close()
1008
1009                 # commits_by_year_month
1010                 f = open(path + '/commits_by_year_month.plot', 'w')
1011                 f.write(GNUPLOT_COMMON)
1012                 f.write(
1013 """
1014 set output 'commits_by_year_month.png'
1015 unset key
1016 set xdata time
1017 set timefmt "%Y-%m"
1018 set format x "%Y-%m"
1019 set xtics rotate by 90 15768000
1020 set bmargin 5
1021 set grid y
1022 set ylabel "Commits"
1023 plot 'commits_by_year_month.dat' using 1:2:(0.5) w boxes fs solid
1024 """)
1025                 f.close()
1026
1027                 # commits_by_year
1028                 f = open(path + '/commits_by_year.plot', 'w')
1029                 f.write(GNUPLOT_COMMON)
1030                 f.write(
1031 """
1032 set output 'commits_by_year.png'
1033 unset key
1034 set xtics 1 rotate by 90
1035 set grid y
1036 set ylabel "Commits"
1037 set yrange [0:]
1038 plot 'commits_by_year.dat' using 1:2:(0.5) w boxes fs solid
1039 """)
1040                 f.close()
1041
1042                 # Files by date
1043                 f = open(path + '/files_by_date.plot', 'w')
1044                 f.write(GNUPLOT_COMMON)
1045                 f.write(
1046 """
1047 set output 'files_by_date.png'
1048 unset key
1049 set xdata time
1050 set timefmt "%Y-%m-%d"
1051 set format x "%Y-%m-%d"
1052 set grid y
1053 set ylabel "Files"
1054 set xtics rotate by 90
1055 set ytics autofreq
1056 set bmargin 6
1057 plot 'files_by_date.dat' using 1:2 w steps
1058 """)
1059                 f.close()
1060
1061                 # Lines of Code
1062                 f = open(path + '/lines_of_code.plot', 'w')
1063                 f.write(GNUPLOT_COMMON)
1064                 f.write(
1065 """
1066 set output 'lines_of_code.png'
1067 unset key
1068 set xdata time
1069 set timefmt "%s"
1070 set format x "%Y-%m-%d"
1071 set grid y
1072 set ylabel "Lines"
1073 set xtics rotate by 90
1074 set bmargin 6
1075 plot 'lines_of_code.dat' using 1:2 w lines
1076 """)
1077                 f.close()
1078
1079                 os.chdir(path)
1080                 files = glob.glob(path + '/*.plot')
1081                 for f in files:
1082                         out = getpipeoutput([gnuplot_cmd + ' "%s"' % f])
1083                         if len(out) > 0:
1084                                 print out
1085
1086         def printHeader(self, f, title = ''):
1087                 f.write(
1088 """<?xml version="1.0" encoding="UTF-8"?>
1089 <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN" "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
1090 <html xmlns="http://www.w3.org/1999/xhtml">
1091 <head>
1092         <title>GitStats - %s</title>
1093         <link rel="stylesheet" href="%s" type="text/css" />
1094         <meta name="generator" content="GitStats %s" />
1095         <script type="text/javascript" src="sortable.js"></script>
1096 </head>
1097 <body>
1098 """ % (self.title, conf['style'], getversion()))
1099
1100         def printNav(self, f):
1101                 f.write("""
1102 <div class="nav">
1103 <ul>
1104 <li><a href="index.html">General</a></li>
1105 <li><a href="activity.html">Activity</a></li>
1106 <li><a href="authors.html">Authors</a></li>
1107 <li><a href="files.html">Files</a></li>
1108 <li><a href="lines.html">Lines</a></li>
1109 <li><a href="tags.html">Tags</a></li>
1110 </ul>
1111 </div>
1112 """)
1113
1114
1115 class GitStats:
1116         def run(self, args_orig):
1117                 optlist, args = getopt.getopt(args_orig, 'c:')
1118                 for o,v in optlist:
1119                         if o == '-c':
1120                                 key, value = v.split('=', 1)
1121                                 if key not in conf:
1122                                         raise KeyError('no such key "%s" in config' % key)
1123                                 if isinstance(conf[key], int):
1124                                         conf[key] = int(value)
1125                                 else:
1126                                         conf[key] = value
1127
1128                 if len(args) < 2:
1129                         print """
1130 Usage: gitstats [options] <gitpath> <outputpath>
1131
1132 Options:
1133 -c key=value     Override configuration value
1134
1135 Default config values:
1136 %s
1137 """ % conf
1138                         sys.exit(0)
1139
1140                 gitpath = args[0]
1141                 outputpath = os.path.abspath(args[1])
1142                 rundir = os.getcwd()
1143
1144                 try:
1145                         os.makedirs(outputpath)
1146                 except OSError:
1147                         pass
1148                 if not os.path.isdir(outputpath):
1149                         print 'FATAL: Output path is not a directory or does not exist'
1150                         sys.exit(1)
1151
1152                 print 'Git path: %s' % gitpath
1153                 print 'Output path: %s' % outputpath
1154
1155                 os.chdir(gitpath)
1156
1157                 cachefile = os.path.join(outputpath, 'gitstats.cache')
1158
1159                 print 'Collecting data...'
1160                 data = GitDataCollector()
1161                 data.loadCache(cachefile)
1162                 data.collect(gitpath)
1163                 print 'Refining data...'
1164                 data.saveCache(cachefile)
1165                 data.refine()
1166
1167                 os.chdir(rundir)
1168
1169                 print 'Generating report...'
1170                 report = HTMLReportCreator()
1171                 report.create(data, outputpath)
1172
1173                 time_end = time.time()
1174                 exectime_internal = time_end - time_start
1175                 print 'Execution time %.5f secs, %.5f secs (%.2f %%) in external commands)' % (exectime_internal, exectime_external, (100.0 * exectime_external) / exectime_internal)
1176
1177 if __name__=='__main__':
1178         g = GitStats()
1179         g.run(sys.argv[1:])
1180