bbd825be7b249e5da7f03b64d5ddefc55a9e9213
[p5sagit/p5-mst-13.2.git] / Porting / checkAUTHORS.pl
1 #!/usr/bin/perl -w
2 use strict;
3 use Text::Wrap;
4 $Text::Wrap::columns = 80;
5 my ($committer, $patch, $log);
6 use Getopt::Long;
7
8 my ($rank, $percentage, $cumulative, $reverse, $ta, @authors, %authors,
9     %untraced, %patchers, %committers);
10 my $result = GetOptions ("rank" => \$rank,                  # rank authors
11                          "thanks-applied" => \$ta,          # ranks committers
12                          "acknowledged=s"   => \@authors ,  # authors files
13                          "percentage" => \$percentage,      # show as %age
14                          "cumulative" => \$cumulative,
15                          "reverse" => \$reverse,
16                         );
17
18 if (!$result or (($rank||0) + ($ta||0) + (@authors ? 1 : 0) != 1) or !@ARGV) {
19   die <<"EOS";
20 $0 --rank Changelogs                        # rank authors by patches
21 $0 --acknowledged <authors file> Changelogs # Display unacknowledged authors
22 $0 --thanks-applied Changelogs              # ranks committers
23 $0 --percentage ...                         # show rankings as percentages
24 $0 --cumulative ...                         # show rankings cumulatively
25 $0 --reverse ...                            # show rankings in reverse
26 Specify stdin as - if needs be. Remember that option names can be abbreviated.
27 EOS
28 }
29
30
31 my $prev = "";
32 my %map;
33
34 while (<DATA>) {
35     chomp;
36     s/\\100/\@/g;
37     $_ = lc;
38     if (my ($correct, $alias) = /^\s*([^#\s]\S*)\s+(.*\S)/) {
39         if ($correct eq '+') {$correct = $prev} else {$prev = $correct}
40         $map {$alias} = $correct;
41     }
42 }
43
44 #
45 # Email addresses for we do not have names.
46 #
47 $map {$_} = "?" for 
48     "alexander_bluhm\100genua.de",
49     "alexander_gernler\100genua.de",
50     "ammon\100rhythm.com",
51     "bah\100longitude.com",
52     "bbucklan\100jpl-devvax.jpl.nasa.gov",
53     "bilbo\100ua.fm",
54     "bob\100starlabs.net",
55     "bonefish\100cs.tu-berlin.de",
56     "bstrand\100switchmanagement.com",
57     "cygwin\100cygwin.com",
58     "david\100dhaller.de",
59     "dformosa\100dformosa.zeta.org.au",
60     "dgay\100acm.org",
61     "erik\100cs.uni-jena.de",
62     "glasser\100tang-eleven-seventy-nine.mit.edu",
63     "gml4410\100ggr.co.uk",
64     "grommel\100sears.com",
65     "ilya\100juil.nonet",
66     "info\100lingo.kiev.ua",
67     "jms\100mathras.comcast.net",
68     "kan\100dcit.cz",
69     "kaminsky\100math.huji.ac.il",
70     "knew-p5p\100pimb.org",
71     "kvr\100centrum.cz",
72     "mauzo\100csv.warwick.ac.uk",
73     "merijnb\100ms.com",
74     "mlelstv\100serpens.de",
75     "p.boven\100sara.nl",
76     "padre\100elte.hu",
77     "perlbug\100veggiechinese.net",
78     "pm\100capmon.dk",
79     "premchai21\100yahoo.com",
80     "pxm\100nubz.org",
81     "raf\100tradingpost.com.au",
82     "scott\100perlcode.org",
83     "smoketst\100hp46t243.cup.hp.com",
84     "yath-perlbug\100yath.de",
85 ;
86
87 #
88 # Email addresses for people that don't have an email address in AUTHORS
89 # Presumably deliberately?
90
91
92 $map {$_} = '!' for
93      # Iain Truskett has passed away.
94      "perl\100dellah.anu.edu.au",
95      "spoon\100dellah.org",
96      "spoon\100cpan.org",
97
98      # Ton Hospel
99      "me-02\100ton.iguana.be",
100      "perl-5.8.0\100ton.iguana.be",
101      "perl5-porters\100ton.iguana.be",
102
103      # Beau Cox
104      "beau\100beaucox.com",
105
106      # Randy W. Sims 
107      "ml-perl\100thepierianspring.org",
108
109      # Yuval Kogman
110      "nothingmuch\100woobling.org",
111
112 ;
113
114
115 if (@authors) {
116   my %raw;
117   foreach my $filename (@authors) {
118     open FH, "<$filename" or die "Can't open $filename: $!";
119     while (<FH>) {
120       next if /^\#/;
121       next if /^-- /;
122       if (/<([^>]+)>/) {
123         # Easy line.
124         $raw{$1}++;
125       } elsif (/^([-A-Za-z0-9 .\'À-ÖØöø-ÿ]+)[\t\n]/) {
126         # Name only
127         $untraced{$1}++;
128       } else {
129         chomp;
130         warn "Can't parse line '$_'";
131       }
132     }
133   }
134   foreach (keys %raw) {
135     print "E-mail $_ occurs $raw{$_} times\n" if $raw{$_} > 1;
136     $_ = lc $_;
137     $authors{$map{$_} || $_}++;
138   }
139   ++$authors{'!'};
140   ++$authors{'?'};
141 }
142
143 while (<>) {
144   next if /^-+/;
145   if (m!^\[\s+(\d+)\]\s+By:\s+(\S+)\s+on!) {
146     # new patch
147     my @new = ($1, $2);
148     &process ($committer, $patch, $log);
149     ($patch, $committer) = @new;
150     undef $log;
151   } elsif (s/^(\s+Log: )//) {
152     die "Duplicate Log:" if $log;
153     $log = $_;
154     my $prefix = " " x length $1;
155     LOG: while (<>) {
156       next if /^$/;
157       s/^\t/        /;
158       if (s/^$prefix//) {
159         $log .= $_;
160       } elsif (/^\s+Branch:/) {
161         last LOG;
162       } else {
163         chomp;
164         die "Malformed log end with '$_'";
165       }
166     }
167   }
168 }
169
170 &process ($committer, $patch, $log);
171
172 if ($rank) {
173   &display_ordered(\%patchers);
174 } elsif ($ta) {
175   &display_ordered(\%committers);
176 } elsif (%authors) {
177   my %missing;
178   foreach (sort keys %patchers) {
179     next if $authors{$_};
180     # Sort by number of patches, then name.
181     $missing{$patchers{$_}}->{$_}++;
182   }
183   foreach my $patches (sort {$b <=> $a} keys %missing) {
184     print "$patches patch(es)\n";
185     foreach my $author (sort keys %{$missing{$patches}}) {
186       print "  $author\n";
187     }
188   }
189 }
190
191 sub display_ordered {
192   my $what = shift;
193   my @sorted;
194   my $total;
195   while (my ($name, $count) = each %$what) {
196     push @{$sorted[$count]}, $name;
197     $total += $count;
198   }
199
200   my $i = @sorted;
201   return unless @sorted;
202   my $sum = 0;
203   foreach my $i ($reverse ? 0 .. $#sorted : reverse 0 .. $#sorted) {
204     next unless $sorted[$i];
205     my $prefix;
206     $sum += $i * @{$sorted[$i]};
207     # Value to display is either this one, or the cumulative sum.
208     my $value = $cumulative ? $sum : $i;
209     if ($percentage) {
210         $prefix = sprintf "%6.2f:\t", 100 * $value / $total;
211     } else {
212         $prefix = "$value:\t";
213     }
214     print wrap ($prefix, "\t", join (" ", sort @{$sorted[$i]}), "\n");
215   }
216 }
217
218 sub process {
219   my ($committer, $patch, $log) = @_;
220   return unless $committer;
221   my @authors = $log =~ /From:\s+.*?([^"\@ \t\n<>]+\@[^"\@ \t\n<>]+)/gm;
222
223   if (@authors) {
224     foreach (@authors) {
225       s/^<//;
226       s/>$//;
227       $_ = lc $_;
228       $patchers{$map{$_} || $_}++;
229     }
230     # print "$patch: @authors\n";
231     ++$committers{$committer};
232   } else {
233     # print "$patch: $committer\n";
234     # Not entirely fair as this means that the maint pumpking scores for
235     # everything intergrated that wasn't a third party patch in blead
236     $patchers{$committer}++;
237   }
238 }
239
240
241 __DATA__
242
243 #
244 # List of mappings. First entry the "correct" email address, as appears
245 # in the AUTHORS file. Second is any "alias" mapped to it.
246 #
247 # If the "correct" email address is a '+', the entry above is reused; 
248 # this for addresses with more than one alias.
249 #
250 # Note that all entries are in lowercase. Further, no '@' signs should
251 # appear; use \100 instead.
252 #
253 #
254 #  Committers.
255 #
256 adi                                     enache\100rdslink.ro
257 alanbur                                 alan.burlison\100sun.com
258 +                                       alan.burlison\100uk.sun.com
259 ams                                     ams\100wiw.org
260 chip                                    chip\100pobox.com
261 craigb                                  craig.berry\100psinetcs.com
262 +                                       craig.berry\100metamorgs.com
263 +                                       craig.berry\100signaltreesolutions.com
264 +                                       craigberry\100mac.com
265 davem                                   davem\100fdgroup.com
266 +                                       davem\100iabyn.nospamdeletethisbit.com
267 +                                       davem\100fdgroup.co.uk
268 +                                       davem\100fdisolutions.com
269 +                                       davem\100iabyn.com
270 demerphq                                demerphq\100gmail.com
271 +                                       yves.orton\100de.mci.com
272 +                                       yves.orton\100mciworldcom.de
273 doughera                                doughera\100lafayette.edu
274 gbarr                                   gbarr\100pobox.com
275 gisle                                   gisle\100activestate.com
276 +                                       gisle\100aas.no
277 gsar                                    gsar\100activestate.com
278 +                                       gsar\100cpan.org
279 hv                                      hv\100crypt.compulink.co.uk
280 +                                       hv\100crypt.org
281 jhi                                     jhi\100iki.fi
282 +                                       jhietaniemi\100gmail.com
283 +                                       jhi\100kosh.hut.fi
284 +                                       jhi\100cc.hut.fi
285 +                                       jarkko.hietaniemi\100nokia.com
286 merijn                                  h.m.brand\100xs4all.nl
287 +                                       h.m.brand\100hccnet.nl
288 +                                       merijn\100l1.procura.nl
289 mhx                                     mhx-perl\100gmx.net
290 nicholas                                nick\100unfortu.net
291 +                                       nick\100ccl4.org
292 +                                       nick\100talking.bollo.cx
293 +                                       nick\100plum.flirble.org
294 +                                       nick\100babyhippo.co.uk
295 +                                       nick\100bagpuss.unfortu.net
296 nick                                    nick\100ing-simmons.net
297 +                                       nik\100tiuk.ti.com
298 +                                       nick.ing-simmons\100elixent.com
299 pudge                                   pudge\100pobox.com
300 rgs                                     rgarciasuarez\100free.fr
301 +                                       rgarciasuarez\100mandrakesoft.com
302 +                                       rgarciasuarez\100mandriva.com
303 +                                       rgarciasuarez\100gmail.com
304 +                                       raphel.garcia-suarez\100hexaflux.com
305 sky                                     sky\100nanisky.com
306 +                                       artur\100contiller.se
307 +                                       arthur\100contiller.se
308 steveh                                  steve.hay\100uk.radan.com
309 stevep                                  steve\100fisharerojo.org
310 +                                       steve.peters\100gmail.com
311
312 #
313 # Mere mortals.
314 #
315 7k8lrvf02\100sneakemail.com             kjx9zthh3001\100sneakemail.com
316 +                                       dtr8sin02\100sneakemail.com
317 +                                       rt8363b02\100sneakemail.com
318 +                                       o6hhmk002\100sneakemail.com
319
320 abe\100ztreet.demon.nl                  abeltje\100cpan.org
321 abigail\100abigail.be                   abigail\100foad.org
322 +                                       abigail\100abigail.nl
323 ajohnson\100nvidia.com                  ajohnson\100wischip.com
324 alexm\100netli.com                      alexm\100w-m.ru
325 alian\100cpan.org                       alian\100alianwebserver.com
326 allens\100cpan.org                      easmith\100beatrice.rutgers.edu
327 andreas.koenig\100anima.de        andreas.koenig.gmwojprw\100franz.ak.mind.de
328 +                                 andreas.koenig.7os6vvqr\100franz.ak.mind.de
329 +                                       a.koenig\100mind.de
330 anno4000\100lublin.zrz.tu-berlin.de     anno4000\100mailbox.tu-berlin.de
331 +                                       siegel\100zrz.tu-berlin.de
332 ash\100cpan.org                         ash_cpan\100firemirror.com
333 avarab\100gmail.com                     avar\100cpan.org
334
335 bah\100ecnvantage.com                   bholzman\100longitude.com
336 ben_tilly\100operamail.com              btilly\100gmail.com
337
338 chromatic\100wgz.org                    chromatic\100rmci.net
339 clkao\100clkao.org                      clkao\100bestpractical.com
340 cp\100onsitetech.com                    publiustemp-p5p\100yahoo.com
341 +                                       publiustemp-p5p3\100yahoo.com
342 cpan\100audreyt.org                     autrijus\100egb.elixus.org
343 +                                       autrijus\100geb.elixus.org
344 +                                       autrijus\100gmail.com
345 +                                       autrijus\100ossf.iis.sinica.edu.tw
346 +                                       autrijus\100autrijus.org
347 +                                       audreyt\100audreyt.org
348
349 damian\100cs.monash.edu.au              damian\100conway.org
350 david.dyck\100fluke.com                 dcd\100tc.fluke.com
351 demerphq\100gmail.com                   demerphq\100hotmail.com
352 domo\100computer.org                    shouldbedomo\100mac.com
353
354 epeschko\100den-mdev1                   esp5\100pge.com
355
356 fugazi\100zyx.net                       larrysh\100cpan.org
357
358 gellyfish\100gellyfish.com              jns\100gellyfish.com
359 gp\100familiehaase.de                   gerrit\100familiehaase.de
360 grazz\100pobox.com                      grazz\100nyc.rr.com
361
362 hio\100ymir.co.jp                       hio\100hio.jp
363
364 japhy\100pobox.com                      japhy\100pobox.org
365 +                                       japhy\100perlmonk.org
366 +                                       japhy\100cpan.org
367 jari.aalto\100poboxes.com               jari.aalto\100cante.net
368 jcromie\100divsol.com                   jcromie\100cpan.org
369 +                                       jim.cromie\100gmail.com
370 jdhedden\100cpan.org                    jerry\100hedden.us
371 +                                       jdhedden\1001979.usna.com
372 +                                       jdhedden\100gmail.com
373 +                                       jdhedden\100yahoo.com
374 jfriedl\100yahoo.com                    jfriedl\100yahoo-inc.com
375 jjore\100cpan.org                       twists\100gmail.com
376 juerd\100cpan.org                       juerd\100convolution.nl
377
378 kane\100dwim.org                        kane\100xs4all.net
379 +                                       kane\100cpan.org
380 +                                       kane\100xs4all.nl
381 +                                       jos\100dwim.org
382 +                                       jib\100ripe.net
383 kroepke\100dolphin-services.de          kay\100dolphin-services.de
384 kstar\100wolfetech.com                  kstar\100cpan.org
385
386 mats\100sm6sxl.net                      mats\100sm5sxl.net
387 mbarbon\100dsi.unive.it                 mattia.barbon\100libero.it
388 mcmahon\100ibiblio.org                  mcmahon\100metalab.unc.edu
389 merijnb\100iloquent.nl                  merijnb\100iloquent.com
390 mgjv\100comdyn.com.au                   mgjv\100tradingpost.com.au
391 michael.schroeder\100informatik.uni-erlangen.de mls\100suse.de
392 mike\100stok.co.uk                      mike\100exegenix.com
393 mjtg\100cam.ac.uk                       mjtg\100cus.cam.ac.uk
394
395 nospam-abuse\100bloodgate.com           tels\100bloodgate.com
396 +                                       perl_dummy\100bloodgate.com
397 nospam-abuse\100ilyaz.org               ilya\100math.ohio-state.edu
398 +                                       ilya\100math.berkeley.edu
399 +                                       ilya\100math.berkeley.edu
400
401 p5-authors\100crystalflame.net          perl\100crystalflame.net
402 +                                       rs\100crystalflame.net
403 paul.green\100stratus.com               paul_greenvos\100vos.stratus.com
404 paul.marquess\100btinternet.com         paul_marquess\100yahoo.co.uk
405 +                                       paul.marquess\100ntlworld.com
406 +                                       paul.marquess\100openwave.com
407 pcg\100goof.com                         schmorp\100schmorp.de
408 # Maybe we should special case this to get real names out?
409 perlbug\100perl.org                     perlbug-followup\100perl.org
410 +                                       bugs-perl5\100bugs6.perl.org
411 phil\100perkpartners.com                phil\100finchcomputer.com
412 pimlott\100idiomtech.com                andrew\100pimlott.net
413 pne\100cpan.org                         philip.newton\100gmx.net
414 +                                       philip.newton\100datenrevision.de
415 +                                       pnewton\100gmx.de
416
417 radu\100netsoft.ro                      rgreab\100fx.ro
418 richard.foley\100ubsw.com               richard.foley\100t-online.de
419 +                                       richard.foley\100ubs.com
420 +                                       richard.foley\100rfi.net
421 rick\100consumercontact.com             rick\100bort.ca
422 +                                       rick.delaney\100rogers.com
423 rjk\100linguist.dartmouth.edu           rjk\100linguist.thayer.dartmouth.edu
424 +                                       rjk-perl-p5p\100tamias.net
425 rmgiroux\100acm.org                     rmgiroux\100hotmail.com
426 robin.barker\100npl.co.uk               rmb1\100cise.npl.co.uk
427 +                                       rmbarker\100cpan.org
428 rootbeer\100teleport.com                rootbeer\100redcat.com
429
430 schubiger\100cpan.org                   steven\100accognoscere.org
431 +                                       sts\100accognoscere.org
432 schwern\100pobox.com                    schwern\100gmail.com
433 sebastien\100aperghis.net               maddingue\100free.fr
434 +                                       saper\100cpan.org
435 simon\100simon-cozens.org               simon\100pembro4.pmb.ox.ac.uk
436 +                                       simon\100brecon.co.uk
437 +                                       simon\100othersideofthe.earth.li
438 +                                       simon\100cozens.net
439 +                                       simon\100netthink.co.uk
440 slaven\100rezic.de                      slaven.rezic\100berlin.de
441 +                                       (srezic\100iconmobile.com)
442 smcc\100mit.edu                         smcc\100ocf.berkeley.edu
443 +                                       smcc\100csua.berkeley.edu
444 spider\100orb.nashua.nh.us              spider\100web.zk3.dec.com
445 +                                       spider\100leggy.zk3.dec.com
446 +                                       spider-perl\100orb.nashua.nh.us
447 +                                       spider\100peano.zk3.dec.com
448 stef\100mongueurs.net                   stef\100payrard.net
449 +                                       s.payrard\100wanadoo.fr
450
451 tassilo.parseval\100post.rwth-aachen.de tassilo.von.parseval\100rwth-aachen.de
452 thomas.dorner\100start.de               tdorner\100amadeus.net
453 tjenness\100cpan.org                    t.jenness\100jach.hawaii.edu
454 +                                       timj\100jach.hawaii.edu
455 tom.horsley\100mail.ccur.com            tom.horsley\100ccur.com
456
457 vkonovalov\100lucent.com                vkonovalov\100peterstar.ru
458 +                                       konovalo\100mail.wplus.net
459 +                                       vadim\100vkonovalov.ru
460 +                                       vkonovalov\100spb.lucent.com
461 +                                       vkonovalov\100alcatel-lucent.com
462
463 whatever\100davidnicol.com              davidnicol\100gmail.com
464 wolfgang.laun\100alcatel.at             wolfgang.laun\100chello.at
465 +                                       wolfgang.laun\100thalesgroup.com
466 +                                       wolfgang.laun\100gmail.com