This is a live mirror of the Perl 5 development currently hosted at https://github.com/perl/perl5
Assimilate HTML-Parser and HTML-Tagset. HTML-Parser is now a prereq
[perl5.git] / Porting / checkAUTHORS.pl
CommitLineData
5649b9c9
NC
1#!/usr/bin/perl -w
2use strict;
3use Text::Wrap;
4$Text::Wrap::columns = 80;
5my ($committer, $patch, $log);
6use Getopt::Long;
7
2b0ba25f
NC
8my ($rank, $percentage, $cumulative, $reverse, $ta, @authors, %authors,
9 %untraced, %patchers, %committers);
ff4d71b5
NC
10my $result = GetOptions ("rank" => \$rank, # rank authors
11 "thanks-applied" => \$ta, # ranks committers
15b8f96d
NC
12 "acknowledged=s" => \@authors , # authors files
13 "percentage" => \$percentage, # show as %age
2b0ba25f
NC
14 "cumulative" => \$cumulative,
15 "reverse" => \$reverse,
15b8f96d 16 );
5649b9c9 17
ff4d71b5 18if (!$result or (($rank||0) + ($ta||0) + (@authors ? 1 : 0) != 1) or !@ARGV) {
5649b9c9
NC
19 die <<"EOS";
20$0 --rank Changelogs # rank authors by patches
21$0 --acknowledged <authors file> Changelogs # Display unacknowledged authors
ff4d71b5 22$0 --thanks-applied Changelogs # ranks committers
15b8f96d 23$0 --percentage ... # show rankings as percentages
2b0ba25f
NC
24$0 --cumulative ... # show rankings cumulatively
25$0 --reverse ... # show rankings in reverse
5649b9c9
NC
26Specify stdin as - if needs be. Remember that option names can be abbreviated.
27EOS
28}
29
8513229b
A
30
31my $prev = "";
32my %map;
33
34while (<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 {$_} = "?" for
4bc69901 48 "agrow\100thegotonerd.com",
8513229b
A
49 "alexander_bluhm\100genua.de",
50 "alexander_gernler\100genua.de",
51 "ammon\100rhythm.com",
52 "bah\100longitude.com",
53 "bbucklan\100jpl-devvax.jpl.nasa.gov",
a94e4597 54 "ben\100linuxgazette.net",
8513229b
A
55 "bilbo\100ua.fm",
56 "bob\100starlabs.net",
57 "bonefish\100cs.tu-berlin.de",
58 "bstrand\100switchmanagement.com",
59 "cygwin\100cygwin.com",
60 "david\100dhaller.de",
61 "dformosa\100dformosa.zeta.org.au",
62 "dgay\100acm.org",
63 "erik\100cs.uni-jena.de",
64 "glasser\100tang-eleven-seventy-nine.mit.edu",
65 "gml4410\100ggr.co.uk",
66 "grommel\100sears.com",
67 "ilya\100juil.nonet",
68 "info\100lingo.kiev.ua",
69 "jms\100mathras.comcast.net",
a94e4597 70 "johnh\100isi.edu",
8513229b
A
71 "kan\100dcit.cz",
72 "kaminsky\100math.huji.ac.il",
73 "knew-p5p\100pimb.org",
74 "kvr\100centrum.cz",
a94e4597 75 "lemkemch\100t-online.de",
8513229b
A
76 "mauzo\100csv.warwick.ac.uk",
77 "merijnb\100ms.com",
78 "mlelstv\100serpens.de",
79 "p.boven\100sara.nl",
80 "padre\100elte.hu",
81 "perlbug\100veggiechinese.net",
82 "pm\100capmon.dk",
83 "premchai21\100yahoo.com",
84 "pxm\100nubz.org",
85 "raf\100tradingpost.com.au",
86 "scott\100perlcode.org",
87 "smoketst\100hp46t243.cup.hp.com",
88 "yath-perlbug\100yath.de",
89;
90
91#
92# Email addresses for people that don't have an email address in AUTHORS
93# Presumably deliberately?
94#
95
96$map {$_} = '!' for
cf3e690a
A
97 # Nick Ing-Simmons has passed away (2006-09-25).
98 "nick\100ing-simmons.net",
99 "nik\100tiuk.ti.com",
100 "nick.ing-simmons\100elixent.com",
101
102 # Iain Truskett has passed away (2003-12-29).
8513229b
A
103 "perl\100dellah.anu.edu.au",
104 "spoon\100dellah.org",
105 "spoon\100cpan.org",
106
107 # Ton Hospel
108 "me-02\100ton.iguana.be",
109 "perl-5.8.0\100ton.iguana.be",
110 "perl5-porters\100ton.iguana.be",
111
112 # Beau Cox
113 "beau\100beaucox.com",
114
115 # Randy W. Sims
116 "ml-perl\100thepierianspring.org",
117
118 # Yuval Kogman
119 "nothingmuch\100woobling.org",
120
121;
122
a7ad7795 123
5649b9c9
NC
124if (@authors) {
125 my %raw;
126 foreach my $filename (@authors) {
127 open FH, "<$filename" or die "Can't open $filename: $!";
128 while (<FH>) {
129 next if /^\#/;
130 next if /^-- /;
131 if (/<([^>]+)>/) {
132 # Easy line.
133 $raw{$1}++;
134 } elsif (/^([-A-Za-z0-9 .\'À-ÖØöø-ÿ]+)[\t\n]/) {
135 # Name only
136 $untraced{$1}++;
137 } else {
138 chomp;
139 warn "Can't parse line '$_'";
140 }
141 }
142 }
143 foreach (keys %raw) {
144 print "E-mail $_ occurs $raw{$_} times\n" if $raw{$_} > 1;
145 $_ = lc $_;
146 $authors{$map{$_} || $_}++;
147 }
2b90724c
NC
148 ++$authors{'!'};
149 ++$authors{'?'};
5649b9c9
NC
150}
151
152while (<>) {
153 next if /^-+/;
154 if (m!^\[\s+(\d+)\]\s+By:\s+(\S+)\s+on!) {
155 # new patch
156 my @new = ($1, $2);
157 &process ($committer, $patch, $log);
158 ($patch, $committer) = @new;
159 undef $log;
160 } elsif (s/^(\s+Log: )//) {
161 die "Duplicate Log:" if $log;
162 $log = $_;
163 my $prefix = " " x length $1;
164 LOG: while (<>) {
84fd1186 165 next if /^$/;
bdb5e10e 166 s/^\t/ /;
5649b9c9
NC
167 if (s/^$prefix//) {
168 $log .= $_;
169 } elsif (/^\s+Branch:/) {
170 last LOG;
171 } else {
84fd1186
NC
172 chomp;
173 die "Malformed log end with '$_'";
5649b9c9
NC
174 }
175 }
176 }
177}
178
179&process ($committer, $patch, $log);
180
181if ($rank) {
ff4d71b5
NC
182 &display_ordered(\%patchers);
183} elsif ($ta) {
184 &display_ordered(\%committers);
5649b9c9
NC
185} elsif (%authors) {
186 my %missing;
187 foreach (sort keys %patchers) {
188 next if $authors{$_};
189 # Sort by number of patches, then name.
190 $missing{$patchers{$_}}->{$_}++;
191 }
192 foreach my $patches (sort {$b <=> $a} keys %missing) {
193 print "$patches patch(es)\n";
194 foreach my $author (sort keys %{$missing{$patches}}) {
195 print " $author\n";
196 }
197 }
198}
199
200sub display_ordered {
ff4d71b5 201 my $what = shift;
5649b9c9 202 my @sorted;
15b8f96d 203 my $total;
ff4d71b5 204 while (my ($name, $count) = each %$what) {
5649b9c9 205 push @{$sorted[$count]}, $name;
15b8f96d 206 $total += $count;
5649b9c9
NC
207 }
208
209 my $i = @sorted;
2b0ba25f
NC
210 return unless @sorted;
211 my $sum = 0;
212 foreach my $i ($reverse ? 0 .. $#sorted : reverse 0 .. $#sorted) {
5649b9c9 213 next unless $sorted[$i];
15b8f96d 214 my $prefix;
2b0ba25f
NC
215 $sum += $i * @{$sorted[$i]};
216 # Value to display is either this one, or the cumulative sum.
217 my $value = $cumulative ? $sum : $i;
15b8f96d 218 if ($percentage) {
2b0ba25f 219 $prefix = sprintf "%6.2f:\t", 100 * $value / $total;
15b8f96d 220 } else {
2b0ba25f 221 $prefix = "$value:\t";
15b8f96d
NC
222 }
223 print wrap ($prefix, "\t", join (" ", sort @{$sorted[$i]}), "\n");
5649b9c9
NC
224 }
225}
226
227sub process {
228 my ($committer, $patch, $log) = @_;
229 return unless $committer;
2b90724c 230 my @authors = $log =~ /From:\s+.*?([^"\@ \t\n<>]+\@[^"\@ \t\n<>]+)/gm;
5649b9c9
NC
231
232 if (@authors) {
233 foreach (@authors) {
234 s/^<//;
235 s/>$//;
236 $_ = lc $_;
237 $patchers{$map{$_} || $_}++;
238 }
239 # print "$patch: @authors\n";
ff4d71b5 240 ++$committers{$committer};
5649b9c9
NC
241 } else {
242 # print "$patch: $committer\n";
243 # Not entirely fair as this means that the maint pumpking scores for
244 # everything intergrated that wasn't a third party patch in blead
245 $patchers{$committer}++;
246 }
247}
248
249
8513229b
A
250__DATA__
251
252#
253# List of mappings. First entry the "correct" email address, as appears
254# in the AUTHORS file. Second is any "alias" mapped to it.
255#
256# If the "correct" email address is a '+', the entry above is reused;
257# this for addresses with more than one alias.
258#
259# Note that all entries are in lowercase. Further, no '@' signs should
260# appear; use \100 instead.
261#
262#
263# Committers.
264#
265adi enache\100rdslink.ro
266alanbur alan.burlison\100sun.com
267+ alan.burlison\100uk.sun.com
268ams ams\100wiw.org
269chip chip\100pobox.com
270craigb craig.berry\100psinetcs.com
271+ craig.berry\100metamorgs.com
272+ craig.berry\100signaltreesolutions.com
273+ craigberry\100mac.com
a94e4597 274+ craig.a.berry\100gmail.com
8513229b
A
275davem davem\100fdgroup.com
276+ davem\100iabyn.nospamdeletethisbit.com
a94e4597 277+ davem\100iabyn.com
8513229b
A
278+ davem\100fdgroup.co.uk
279+ davem\100fdisolutions.com
280+ davem\100iabyn.com
281demerphq demerphq\100gmail.com
282+ yves.orton\100de.mci.com
283+ yves.orton\100mciworldcom.de
284doughera doughera\100lafayette.edu
285gbarr gbarr\100pobox.com
286gisle gisle\100activestate.com
287+ gisle\100aas.no
288gsar gsar\100activestate.com
289+ gsar\100cpan.org
290hv hv\100crypt.compulink.co.uk
291+ hv\100crypt.org
292jhi jhi\100iki.fi
293+ jhietaniemi\100gmail.com
294+ jhi\100kosh.hut.fi
295+ jhi\100cc.hut.fi
296+ jarkko.hietaniemi\100nokia.com
297merijn h.m.brand\100xs4all.nl
298+ h.m.brand\100hccnet.nl
299+ merijn\100l1.procura.nl
300mhx mhx-perl\100gmx.net
301nicholas nick\100unfortu.net
302+ nick\100ccl4.org
303+ nick\100talking.bollo.cx
304+ nick\100plum.flirble.org
305+ nick\100babyhippo.co.uk
306+ nick\100bagpuss.unfortu.net
8513229b
A
307pudge pudge\100pobox.com
308rgs rgarciasuarez\100free.fr
309+ rgarciasuarez\100mandrakesoft.com
310+ rgarciasuarez\100mandriva.com
311+ rgarciasuarez\100gmail.com
312+ raphel.garcia-suarez\100hexaflux.com
313sky sky\100nanisky.com
314+ artur\100contiller.se
315+ arthur\100contiller.se
b692cd7a
SH
316steveh stevehay\100planit.com
317+ steve.hay\100uk.radan.com
8513229b
A
318stevep steve\100fisharerojo.org
319+ steve.peters\100gmail.com
320
321#
322# Mere mortals.
323#
3247k8lrvf02\100sneakemail.com kjx9zthh3001\100sneakemail.com
325+ dtr8sin02\100sneakemail.com
326+ rt8363b02\100sneakemail.com
327+ o6hhmk002\100sneakemail.com
a94e4597
S
328+ smueller\100cpan.org
329+ l2ot9pa02\100sneakemail.com
330+ wyp3rlx02\100sneakemail.com
8513229b
A
331
332abe\100ztreet.demon.nl abeltje\100cpan.org
333abigail\100abigail.be abigail\100foad.org
334+ abigail\100abigail.nl
335ajohnson\100nvidia.com ajohnson\100wischip.com
336alexm\100netli.com alexm\100w-m.ru
a94e4597 337alex-p5p\100earth.li alex\100rcon.rog
8513229b
A
338alian\100cpan.org alian\100alianwebserver.com
339allens\100cpan.org easmith\100beatrice.rutgers.edu
340andreas.koenig\100anima.de andreas.koenig.gmwojprw\100franz.ak.mind.de
341+ andreas.koenig.7os6vvqr\100franz.ak.mind.de
342+ a.koenig\100mind.de
343anno4000\100lublin.zrz.tu-berlin.de anno4000\100mailbox.tu-berlin.de
344+ siegel\100zrz.tu-berlin.de
345ash\100cpan.org ash_cpan\100firemirror.com
346avarab\100gmail.com avar\100cpan.org
347
348bah\100ecnvantage.com bholzman\100longitude.com
851d3318 349bcarter@gumdrop.flyinganvil.org q.eibcartereio.=~m-b.{6}-cgimosx@gumdrop.flyinganvil.org
8513229b
A
350ben_tilly\100operamail.com btilly\100gmail.com
351
352chromatic\100wgz.org chromatic\100rmci.net
353clkao\100clkao.org clkao\100bestpractical.com
354cp\100onsitetech.com publiustemp-p5p\100yahoo.com
355+ publiustemp-p5p3\100yahoo.com
356cpan\100audreyt.org autrijus\100egb.elixus.org
357+ autrijus\100geb.elixus.org
358+ autrijus\100gmail.com
359+ autrijus\100ossf.iis.sinica.edu.tw
360+ autrijus\100autrijus.org
361+ audreyt\100audreyt.org
362
363damian\100cs.monash.edu.au damian\100conway.org
364david.dyck\100fluke.com dcd\100tc.fluke.com
365demerphq\100gmail.com demerphq\100hotmail.com
366domo\100computer.org shouldbedomo\100mac.com
367
368epeschko\100den-mdev1 esp5\100pge.com
369
370fugazi\100zyx.net larrysh\100cpan.org
371
372gellyfish\100gellyfish.com jns\100gellyfish.com
373gp\100familiehaase.de gerrit\100familiehaase.de
374grazz\100pobox.com grazz\100nyc.rr.com
375
376hio\100ymir.co.jp hio\100hio.jp
377
378japhy\100pobox.com japhy\100pobox.org
379+ japhy\100perlmonk.org
380+ japhy\100cpan.org
381jari.aalto\100poboxes.com jari.aalto\100cante.net
382jcromie\100divsol.com jcromie\100cpan.org
383+ jim.cromie\100gmail.com
384jdhedden\100cpan.org jerry\100hedden.us
385+ jdhedden\1001979.usna.com
386+ jdhedden\100gmail.com
387+ jdhedden\100yahoo.com
388jfriedl\100yahoo.com jfriedl\100yahoo-inc.com
389jjore\100cpan.org twists\100gmail.com
390juerd\100cpan.org juerd\100convolution.nl
391
392kane\100dwim.org kane\100xs4all.net
393+ kane\100cpan.org
394+ kane\100xs4all.nl
395+ jos\100dwim.org
396+ jib\100ripe.net
397kroepke\100dolphin-services.de kay\100dolphin-services.de
398kstar\100wolfetech.com kstar\100cpan.org
399
400mats\100sm6sxl.net mats\100sm5sxl.net
401mbarbon\100dsi.unive.it mattia.barbon\100libero.it
402mcmahon\100ibiblio.org mcmahon\100metalab.unc.edu
403merijnb\100iloquent.nl merijnb\100iloquent.com
404mgjv\100comdyn.com.au mgjv\100tradingpost.com.au
405michael.schroeder\100informatik.uni-erlangen.de mls\100suse.de
406mike\100stok.co.uk mike\100exegenix.com
407mjtg\100cam.ac.uk mjtg\100cus.cam.ac.uk
408
409nospam-abuse\100bloodgate.com tels\100bloodgate.com
410+ perl_dummy\100bloodgate.com
a94e4597
S
411ilya\100math.berkeley.edu ilya\100math.ohio-state.edu
412+ nospam-abuse\100ilyaz.org
8513229b
A
413
414p5-authors\100crystalflame.net perl\100crystalflame.net
415+ rs\100crystalflame.net
416paul.green\100stratus.com paul_greenvos\100vos.stratus.com
417paul.marquess\100btinternet.com paul_marquess\100yahoo.co.uk
418+ paul.marquess\100ntlworld.com
419+ paul.marquess\100openwave.com
420pcg\100goof.com schmorp\100schmorp.de
421# Maybe we should special case this to get real names out?
422perlbug\100perl.org perlbug-followup\100perl.org
423+ bugs-perl5\100bugs6.perl.org
424phil\100perkpartners.com phil\100finchcomputer.com
425pimlott\100idiomtech.com andrew\100pimlott.net
426pne\100cpan.org philip.newton\100gmx.net
427+ philip.newton\100datenrevision.de
428+ pnewton\100gmx.de
429
430radu\100netsoft.ro rgreab\100fx.ro
431richard.foley\100ubsw.com richard.foley\100t-online.de
432+ richard.foley\100ubs.com
433+ richard.foley\100rfi.net
434rick\100consumercontact.com rick\100bort.ca
435+ rick.delaney\100rogers.com
a94e4597 436+ rick\100bort.ca
4bc69901 437rjbs\100cpan.org rjbs-perl-p5p\100lists.manxome.org
8513229b
A
438rjk\100linguist.dartmouth.edu rjk\100linguist.thayer.dartmouth.edu
439+ rjk-perl-p5p\100tamias.net
440rmgiroux\100acm.org rmgiroux\100hotmail.com
a94e4597
S
441rmbarker\100cpan.org rmb1\100cise.npl.co.uk
442+ robin.barker\100npl.co.uk
8513229b
A
443rootbeer\100teleport.com rootbeer\100redcat.com
444
445schubiger\100cpan.org steven\100accognoscere.org
446+ sts\100accognoscere.org
447schwern\100pobox.com schwern\100gmail.com
8ed05479
MS
448+ schwern\100athens.arena-i.com
449+ schwern\100blackrider.aocn.com
450+ schwern\100ool-18b93024.dyn.optonline.net
8513229b
A
451sebastien\100aperghis.net maddingue\100free.fr
452+ saper\100cpan.org
453simon\100simon-cozens.org simon\100pembro4.pmb.ox.ac.uk
454+ simon\100brecon.co.uk
455+ simon\100othersideofthe.earth.li
456+ simon\100cozens.net
457+ simon\100netthink.co.uk
458slaven\100rezic.de slaven.rezic\100berlin.de
a94e4597 459+ srezic\100iconmobile.com
8513229b
A
460smcc\100mit.edu smcc\100ocf.berkeley.edu
461+ smcc\100csua.berkeley.edu
462spider\100orb.nashua.nh.us spider\100web.zk3.dec.com
463+ spider\100leggy.zk3.dec.com
464+ spider-perl\100orb.nashua.nh.us
465+ spider\100peano.zk3.dec.com
466stef\100mongueurs.net stef\100payrard.net
467+ s.payrard\100wanadoo.fr
468
469tassilo.parseval\100post.rwth-aachen.de tassilo.von.parseval\100rwth-aachen.de
470thomas.dorner\100start.de tdorner\100amadeus.net
471tjenness\100cpan.org t.jenness\100jach.hawaii.edu
472+ timj\100jach.hawaii.edu
473tom.horsley\100mail.ccur.com tom.horsley\100ccur.com
474
475vkonovalov\100lucent.com vkonovalov\100peterstar.ru
476+ konovalo\100mail.wplus.net
477+ vadim\100vkonovalov.ru
478+ vkonovalov\100spb.lucent.com
479+ vkonovalov\100alcatel-lucent.com
480
481whatever\100davidnicol.com davidnicol\100gmail.com
482wolfgang.laun\100alcatel.at wolfgang.laun\100chello.at
483+ wolfgang.laun\100thalesgroup.com
484+ wolfgang.laun\100gmail.com