contrib/mw-to-git/git-remote-mediawiki

   1 #! /usr/bin/perl
   2
   3 # Copyright (C) 2011
   4 #     Jérémie Nikaes <jeremie.nikaes@ensimag.imag.fr>
   5 #     Arnaud Lacurie <arnaud.lacurie@ensimag.imag.fr>
   6 #     Claire Fousse <claire.fousse@ensimag.imag.fr>
   7 #     David Amouyal <david.amouyal@ensimag.imag.fr>
   8 #     Matthieu Moy <matthieu.moy@grenoble-inp.fr>
   9 # License: GPL v2 or later
  10
  11 # Gateway between Git and MediaWiki.
  12 #   https://github.com/Bibzball/Git-Mediawiki/wiki
  13 #
  14 # Known limitations:
  15 #
  16 # - Only wiki pages are managed, no support for [[File:...]]
  17 #   attachments.
  18 #
  19 # - Poor performance in the best case: it takes forever to check
  20 #   whether we're up-to-date (on fetch or push) or to fetch a few
  21 #   revisions from a large wiki, because we use exclusively a
  22 #   page-based synchronization. We could switch to a wiki-wide
  23 #   synchronization when the synchronization involves few revisions
  24 #   but the wiki is large.
  25 #
  26 # - Git renames could be turned into MediaWiki renames (see TODO
  27 #   below)
  28 #
  29 # - login/password support requires the user to write the password
  30 #   cleartext in a file (see TODO below).
  31 #
  32 # - No way to import "one page, and all pages included in it"
  33 #
  34 # - Multiple remote MediaWikis have not been very well tested.
  35
  36 use strict;
  37 use MediaWiki::API;
  38 use DateTime::Format::ISO8601;
  39 use encoding 'utf8';
  40
  41 # use encoding 'utf8' doesn't change STDERROR
  42 # but we're going to output UTF-8 filenames to STDERR
  43 binmode STDERR, ":utf8";
  44
  45 use URI::Escape;
  46 use warnings;
  47
  48 # Mediawiki filenames can contain forward slashes. This variable decides by which pattern they should be replaced
  49 use constant SLASH_REPLACEMENT => "%2F";
  50
  51 # It's not always possible to delete pages (may require some
  52 # priviledges). Deleted pages are replaced with this content.
  53 use constant DELETED_CONTENT => "[[Category:Deleted]]\n";
  54
  55 # It's not possible to create empty pages. New empty files in Git are
  56 # sent with this content instead.
  57 use constant EMPTY_CONTENT => "<!-- empty page -->\n";
  58
  59 # used to reflect file creation or deletion in diff.
  60 use constant NULL_SHA1 => "0000000000000000000000000000000000000000";
  61
  62 my $remotename = $ARGV[0];
  63 my $url = $ARGV[1];
  64
  65 # Accept both space-separated and multiple keys in config file.
  66 # Spaces should be written as _ anyway because we'll use chomp.
  67 my @tracked_pages = split(/[ \n]/, run_git("config --get-all remote.". $remotename .".pages"));
  68 chomp(@tracked_pages);
  69
  70 # Just like @tracked_pages, but for MediaWiki categories.
  71 my @tracked_categories = split(/[ \n]/, run_git("config --get-all remote.". $remotename .".categories"));
  72 chomp(@tracked_categories);
  73
  74 my $wiki_login = run_git("config --get remote.". $remotename .".mwLogin");
  75 # TODO: ideally, this should be able to read from keyboard, but we're
  76 # inside a remote helper, so our stdin is connect to git, not to a
  77 # terminal.
  78 my $wiki_passwd = run_git("config --get remote.". $remotename .".mwPassword");
  79 my $wiki_domain = run_git("config --get remote.". $remotename .".mwDomain");
  80 chomp($wiki_login);
  81 chomp($wiki_passwd);
  82 chomp($wiki_domain);
  83
  84 # Import only last revisions (both for clone and fetch)
  85 my $shallow_import = run_git("config --get --bool remote.". $remotename .".shallow");
  86 chomp($shallow_import);
  87 $shallow_import = ($shallow_import eq "true");
  88
  89 # Dumb push: don't update notes and mediawiki ref to reflect the last push.
  90 #
  91 # Configurable with mediawiki.dumbPush, or per-remote with
  92 # remote.<remotename>.dumbPush.
  93 #
  94 # This means the user will have to re-import the just-pushed
  95 # revisions. On the other hand, this means that the Git revisions
  96 # corresponding to MediaWiki revisions are all imported from the wiki,
  97 # regardless of whether they were initially created in Git or from the
  98 # web interface, hence all users will get the same history (i.e. if
  99 # the push from Git to MediaWiki loses some information, everybody
 100 # will get the history with information lost). If the import is
 101 # deterministic, this means everybody gets the same sha1 for each
 102 # MediaWiki revision.
 103 my $dumb_push = run_git("config --get --bool remote.$remotename.dumbPush");
 104 unless ($dumb_push) {
 105         $dumb_push = run_git("config --get --bool mediawiki.dumbPush");
 106 }
 107 chomp($dumb_push);
 108 $dumb_push = ($dumb_push eq "true");
 109
 110 my $wiki_name = $url;
 111 $wiki_name =~ s/[^\/]*:\/\///;
 112
 113 # Commands parser
 114 my $entry;
 115 my @cmd;
 116 while (<STDIN>) {
 117         chomp;
 118         @cmd = split(/ /);
 119         if (defined($cmd[0])) {
 120                 # Line not blank
 121                 if ($cmd[0] eq "capabilities") {
 122                         die("Too many arguments for capabilities") unless (!defined($cmd[1]));
 123                         mw_capabilities();
 124                 } elsif ($cmd[0] eq "list") {
 125                         die("Too many arguments for list") unless (!defined($cmd[2]));
 126                         mw_list($cmd[1]);
 127                 } elsif ($cmd[0] eq "import") {
 128                         die("Invalid arguments for import") unless ($cmd[1] ne "" && !defined($cmd[2]));
 129                         mw_import($cmd[1]);
 130                 } elsif ($cmd[0] eq "option") {
 131                         die("Too many arguments for option") unless ($cmd[1] ne "" && $cmd[2] ne "" && !defined($cmd[3]));
 132                         mw_option($cmd[1],$cmd[2]);
 133                 } elsif ($cmd[0] eq "push") {
 134                         mw_push($cmd[1]);
 135                 } else {
 136                         print STDERR "Unknown command. Aborting...\n";
 137                         last;
 138                 }
 139         } else {
 140                 # blank line: we should terminate
 141                 last;
 142         }
 143
 144         BEGIN { $| = 1 } # flush STDOUT, to make sure the previous
 145                          # command is fully processed.
 146 }
 147
 148 ########################## Functions ##############################
 149
 150 # MediaWiki API instance, created lazily.
 151 my $mediawiki;
 152
 153 sub mw_connect_maybe {
 154         if ($mediawiki) {
 155             return;
 156         }
 157         $mediawiki = MediaWiki::API->new;
 158         $mediawiki->{config}->{api_url} = "$url/api.php";
 159         if ($wiki_login) {
 160                 if (!$mediawiki->login({
 161                         lgname => $wiki_login,
 162                         lgpassword => $wiki_passwd,
 163                         lgdomain => $wiki_domain,
 164                 })) {
 165                         print STDERR "Failed to log in mediawiki user \"$wiki_login\" on $url\n";
 166                         print STDERR "(error " .
 167                             $mediawiki->{error}->{code} . ': ' .
 168                             $mediawiki->{error}->{details} . ")\n";
 169                         exit 1;
 170                 } else {
 171                         print STDERR "Logged in with user \"$wiki_login\".\n";
 172                 }
 173         }
 174 }
 175
 176 sub get_mw_first_pages {
 177         my $some_pages = shift;
 178         my @some_pages = @{$some_pages};
 179
 180         my $pages = shift;
 181
 182         # pattern 'page1|page2|...' required by the API
 183         my $titles = join('|', @some_pages);
 184
 185         my $mw_pages = $mediawiki->api({
 186                 action => 'query',
 187                 titles => $titles,
 188         });
 189         if (!defined($mw_pages)) {
 190                 print STDERR "fatal: could not query the list of wiki pages.\n";
 191                 print STDERR "fatal: '$url' does not appear to be a mediawiki\n";
 192                 print STDERR "fatal: make sure '$url/api.php' is a valid page.\n";
 193                 exit 1;
 194         }
 195         while (my ($id, $page) = each(%{$mw_pages->{query}->{pages}})) {
 196                 if ($id < 0) {
 197                         print STDERR "Warning: page $page->{title} not found on wiki\n";
 198                 } else {
 199                         $pages->{$page->{title}} = $page;
 200                 }
 201         }
 202 }
 203
 204 sub get_mw_pages {
 205         mw_connect_maybe();
 206
 207         my %pages; # hash on page titles to avoid duplicates
 208         my $user_defined;
 209         if (@tracked_pages) {
 210                 $user_defined = 1;
 211                 # The user provided a list of pages titles, but we
 212                 # still need to query the API to get the page IDs.
 213
 214                 my @some_pages = @tracked_pages;
 215                 while (@some_pages) {
 216                         my $last = 50;
 217                         if ($#some_pages < $last) {
 218                                 $last = $#some_pages;
 219                         }
 220                         my @slice = @some_pages[0..$last];
 221                         get_mw_first_pages(\@slice, \%pages);
 222                         @some_pages = @some_pages[51..$#some_pages];
 223                 }
 224         }
 225         if (@tracked_categories) {
 226                 $user_defined = 1;
 227                 foreach my $category (@tracked_categories) {
 228                         if (index($category, ':') < 0) {
 229                                 # Mediawiki requires the Category
 230                                 # prefix, but let's not force the user
 231                                 # to specify it.
 232                                 $category = "Category:" . $category;
 233                         }
 234                         my $mw_pages = $mediawiki->list( {
 235                                 action => 'query',
 236                                 list => 'categorymembers',
 237                                 cmtitle => $category,
 238                                 cmlimit => 'max' } )
 239                             || die $mediawiki->{error}->{code} . ': ' . $mediawiki->{error}->{details};
 240                         foreach my $page (@{$mw_pages}) {
 241                                 $pages{$page->{title}} = $page;
 242                         }
 243                 }
 244         }
 245         if (!$user_defined) {
 246                 # No user-provided list, get the list of pages from
 247                 # the API.
 248                 my $mw_pages = $mediawiki->list({
 249                         action => 'query',
 250                         list => 'allpages',
 251                         aplimit => 500,
 252                 });
 253                 if (!defined($mw_pages)) {
 254                         print STDERR "fatal: could not get the list of wiki pages.\n";
 255                         print STDERR "fatal: '$url' does not appear to be a mediawiki\n";
 256                         print STDERR "fatal: make sure '$url/api.php' is a valid page.\n";
 257                         exit 1;
 258                 }
 259                 foreach my $page (@{$mw_pages}) {
 260                         $pages{$page->{title}} = $page;
 261                 }
 262         }
 263         return values(%pages);
 264 }
 265
 266 sub run_git {
 267         open(my $git, "-|:encoding(UTF-8)", "git " . $_[0]);
 268         my $res = do { local $/; <$git> };
 269         close($git);
 270
 271         return $res;
 272 }
 273
 274
 275 sub get_last_local_revision {
 276         # Get note regarding last mediawiki revision
 277         my $note = run_git("notes --ref=$remotename/mediawiki show refs/mediawiki/$remotename/master 2>/dev/null");
 278         my @note_info = split(/ /, $note);
 279
 280         my $lastrevision_number;
 281         if (!(defined($note_info[0]) && $note_info[0] eq "mediawiki_revision:")) {
 282                 print STDERR "No previous mediawiki revision found";
 283                 $lastrevision_number = 0;
 284         } else {
 285                 # Notes are formatted : mediawiki_revision: #number
 286                 $lastrevision_number = $note_info[1];
 287                 chomp($lastrevision_number);
 288                 print STDERR "Last local mediawiki revision found is $lastrevision_number";
 289         }
 290         return $lastrevision_number;
 291 }
 292
 293 # Remember the timestamp corresponding to a revision id.
 294 my %basetimestamps;
 295
 296 sub get_last_remote_revision {
 297         mw_connect_maybe();
 298
 299         my @pages = get_mw_pages();
 300
 301         my $max_rev_num = 0;
 302
 303         foreach my $page (@pages) {
 304                 my $id = $page->{pageid};
 305
 306                 my $query = {
 307                         action => 'query',
 308                         prop => 'revisions',
 309                         rvprop => 'ids|timestamp',
 310                         pageids => $id,
 311                 };
 312
 313                 my $result = $mediawiki->api($query);
 314
 315                 my $lastrev = pop(@{$result->{query}->{pages}->{$id}->{revisions}});
 316
 317                 $basetimestamps{$lastrev->{revid}} = $lastrev->{timestamp};
 318
 319                 $max_rev_num = ($lastrev->{revid} > $max_rev_num ? $lastrev->{revid} : $max_rev_num);
 320         }
 321
 322         print STDERR "Last remote revision found is $max_rev_num.\n";
 323         return $max_rev_num;
 324 }
 325
 326 # Clean content before sending it to MediaWiki
 327 sub mediawiki_clean {
 328         my $string = shift;
 329         my $page_created = shift;
 330         # Mediawiki does not allow blank space at the end of a page and ends with a single \n.
 331         # This function right trims a string and adds a \n at the end to follow this rule
 332         $string =~ s/\s+$//;
 333         if ($string eq "" && $page_created) {
 334                 # Creating empty pages is forbidden.
 335                 $string = EMPTY_CONTENT;
 336         }
 337         return $string."\n";
 338 }
 339
 340 # Filter applied on MediaWiki data before adding them to Git
 341 sub mediawiki_smudge {
 342         my $string = shift;
 343         if ($string eq EMPTY_CONTENT) {
 344                 $string = "";
 345         }
 346         # This \n is important. This is due to mediawiki's way to handle end of files.
 347         return $string."\n";
 348 }
 349
 350 sub mediawiki_clean_filename {
 351         my $filename = shift;
 352         $filename =~ s/@{[SLASH_REPLACEMENT]}/\//g;
 353         # [, ], |, {, and } are forbidden by MediaWiki, even URL-encoded.
 354         # Do a variant of URL-encoding, i.e. looks like URL-encoding,
 355         # but with _ added to prevent MediaWiki from thinking this is
 356         # an actual special character.
 357         $filename =~ s/[\[\]\{\}\|]/sprintf("_%%_%x", ord($&))/ge;
 358         # If we use the uri escape before
 359         # we should unescape here, before anything
 360
 361         return $filename;
 362 }
 363
 364 sub mediawiki_smudge_filename {
 365         my $filename = shift;
 366         $filename =~ s/\//@{[SLASH_REPLACEMENT]}/g;
 367         $filename =~ s/ /_/g;
 368         # Decode forbidden characters encoded in mediawiki_clean_filename
 369         $filename =~ s/_%_([0-9a-fA-F][0-9a-fA-F])/sprintf("%c", hex($1))/ge;
 370         return $filename;
 371 }
 372
 373 sub literal_data {
 374         my ($content) = @_;
 375         print STDOUT "data ", bytes::length($content), "\n", $content;
 376 }
 377
 378 sub mw_capabilities {
 379         # Revisions are imported to the private namespace
 380         # refs/mediawiki/$remotename/ by the helper and fetched into
 381         # refs/remotes/$remotename later by fetch.
 382         print STDOUT "refspec refs/heads/*:refs/mediawiki/$remotename/*\n";
 383         print STDOUT "import\n";
 384         print STDOUT "list\n";
 385         print STDOUT "push\n";
 386         print STDOUT "\n";
 387 }
 388
 389 sub mw_list {
 390         # MediaWiki do not have branches, we consider one branch arbitrarily
 391         # called master, and HEAD pointing to it.
 392         print STDOUT "? refs/heads/master\n";
 393         print STDOUT "\@refs/heads/master HEAD\n";
 394         print STDOUT "\n";
 395 }
 396
 397 sub mw_option {
 398         print STDERR "remote-helper command 'option $_[0]' not yet implemented\n";
 399         print STDOUT "unsupported\n";
 400 }
 401
 402 sub fetch_mw_revisions_for_page {
 403         my $page = shift;
 404         my $id = shift;
 405         my $fetch_from = shift;
 406         my @page_revs = ();
 407         my $query = {
 408                 action => 'query',
 409                 prop => 'revisions',
 410                 rvprop => 'ids',
 411                 rvdir => 'newer',
 412                 rvstartid => $fetch_from,
 413                 rvlimit => 500,
 414                 pageids => $id,
 415         };
 416
 417         my $revnum = 0;
 418         # Get 500 revisions at a time due to the mediawiki api limit
 419         while (1) {
 420                 my $result = $mediawiki->api($query);
 421
 422                 # Parse each of those 500 revisions
 423                 foreach my $revision (@{$result->{query}->{pages}->{$id}->{revisions}}) {
 424                         my $page_rev_ids;
 425                         $page_rev_ids->{pageid} = $page->{pageid};
 426                         $page_rev_ids->{revid} = $revision->{revid};
 427                         push(@page_revs, $page_rev_ids);
 428                         $revnum++;
 429                 }
 430                 last unless $result->{'query-continue'};
 431                 $query->{rvstartid} = $result->{'query-continue'}->{revisions}->{rvstartid};
 432         }
 433         if ($shallow_import && @page_revs) {
 434                 print STDERR "  Found 1 revision (shallow import).\n";
 435                 @page_revs = sort {$b->{revid} <=> $a->{revid}} (@page_revs);
 436                 return $page_revs[0];
 437         }
 438         print STDERR "  Found ", $revnum, " revision(s).\n";
 439         return @page_revs;
 440 }
 441
 442 sub fetch_mw_revisions {
 443         my $pages = shift; my @pages = @{$pages};
 444         my $fetch_from = shift;
 445
 446         my @revisions = ();
 447         my $n = 1;
 448         foreach my $page (@pages) {
 449                 my $id = $page->{pageid};
 450
 451                 print STDERR "page $n/", scalar(@pages), ": ". $page->{title} ."\n";
 452                 $n++;
 453                 my @page_revs = fetch_mw_revisions_for_page($page, $id, $fetch_from);
 454                 @revisions = (@page_revs, @revisions);
 455         }
 456
 457         return ($n, @revisions);
 458 }
 459
 460 sub import_file_revision {
 461         my $commit = shift;
 462         my %commit = %{$commit};
 463         my $full_import = shift;
 464         my $n = shift;
 465
 466         my $title = $commit{title};
 467         my $comment = $commit{comment};
 468         my $content = $commit{content};
 469         my $author = $commit{author};
 470         my $date = $commit{date};
 471
 472         print STDOUT "commit refs/mediawiki/$remotename/master\n";
 473         print STDOUT "mark :$n\n";
 474         print STDOUT "committer $author <$author\@$wiki_name> ", $date->epoch, " +0000\n";
 475         literal_data($comment);
 476
 477         # If it's not a clone, we need to know where to start from
 478         if (!$full_import && $n == 1) {
 479                 print STDOUT "from refs/mediawiki/$remotename/master^0\n";
 480         }
 481         if ($content ne DELETED_CONTENT) {
 482                 print STDOUT "M 644 inline $title.mw\n";
 483                 literal_data($content);
 484                 print STDOUT "\n\n";
 485         } else {
 486                 print STDOUT "D $title.mw\n";
 487         }
 488
 489         # mediawiki revision number in the git note
 490         if ($full_import && $n == 1) {
 491                 print STDOUT "reset refs/notes/$remotename/mediawiki\n";
 492         }
 493         print STDOUT "commit refs/notes/$remotename/mediawiki\n";
 494         print STDOUT "committer $author <$author\@$wiki_name> ", $date->epoch, " +0000\n";
 495         literal_data("Note added by git-mediawiki during import");
 496         if (!$full_import && $n == 1) {
 497                 print STDOUT "from refs/notes/$remotename/mediawiki^0\n";
 498         }
 499         print STDOUT "N inline :$n\n";
 500         literal_data("mediawiki_revision: " . $commit{mw_revision});
 501         print STDOUT "\n\n";
 502 }
 503
 504 # parse a sequence of
 505 # <cmd> <arg1>
 506 # <cmd> <arg2>
 507 # \n
 508 # (like batch sequence of import and sequence of push statements)
 509 sub get_more_refs {
 510         my $cmd = shift;
 511         my @refs;
 512         while (1) {
 513                 my $line = <STDIN>;
 514                 if ($line =~ m/^$cmd (.*)$/) {
 515                         push(@refs, $1);
 516                 } elsif ($line eq "\n") {
 517                         return @refs;
 518                 } else {
 519                         die("Invalid command in a '$cmd' batch: ". $_);
 520                 }
 521         }
 522 }
 523
 524 sub mw_import {
 525         # multiple import commands can follow each other.
 526         my @refs = (shift, get_more_refs("import"));
 527         foreach my $ref (@refs) {
 528                 mw_import_ref($ref);
 529         }
 530         print STDOUT "done\n";
 531 }
 532
 533 sub mw_import_ref {
 534         my $ref = shift;
 535         # The remote helper will call "import HEAD" and
 536         # "import refs/heads/master".
 537         # Since HEAD is a symbolic ref to master (by convention,
 538         # followed by the output of the command "list" that we gave),
 539         # we don't need to do anything in this case.
 540         if ($ref eq "HEAD") {
 541                 return;
 542         }
 543
 544         mw_connect_maybe();
 545
 546         my @pages = get_mw_pages();
 547
 548         print STDERR "Searching revisions...\n";
 549         my $last_local = get_last_local_revision();
 550         my $fetch_from = $last_local + 1;
 551         if ($fetch_from == 1) {
 552                 print STDERR ", fetching from beginning.\n";
 553         } else {
 554                 print STDERR ", fetching from here.\n";
 555         }
 556         my ($n, @revisions) = fetch_mw_revisions(\@pages, $fetch_from);
 557
 558         # Creation of the fast-import stream
 559         print STDERR "Fetching & writing export data...\n";
 560
 561         $n = 0;
 562         my $last_timestamp = 0; # Placeholer in case $rev->timestamp is undefined
 563
 564         foreach my $pagerevid (sort {$a->{revid} <=> $b->{revid}} @revisions) {
 565                 # fetch the content of the pages
 566                 my $query = {
 567                         action => 'query',
 568                         prop => 'revisions',
 569                         rvprop => 'content|timestamp|comment|user|ids',
 570                         revids => $pagerevid->{revid},
 571                 };
 572
 573                 my $result = $mediawiki->api($query);
 574
 575                 my $rev = pop(@{$result->{query}->{pages}->{$pagerevid->{pageid}}->{revisions}});
 576
 577                 $n++;
 578
 579                 my %commit;
 580                 $commit{author} = $rev->{user} || 'Anonymous';
 581                 $commit{comment} = $rev->{comment} || '*Empty MediaWiki Message*';
 582                 $commit{title} = mediawiki_smudge_filename(
 583                         $result->{query}->{pages}->{$pagerevid->{pageid}}->{title}
 584                     );
 585                 $commit{mw_revision} = $pagerevid->{revid};
 586                 $commit{content} = mediawiki_smudge($rev->{'*'});
 587
 588                 if (!defined($rev->{timestamp})) {
 589                         $last_timestamp++;
 590                 } else {
 591                         $last_timestamp = $rev->{timestamp};
 592                 }
 593                 $commit{date} = DateTime::Format::ISO8601->parse_datetime($last_timestamp);
 594
 595                 print STDERR "$n/", scalar(@revisions), ": Revision #$pagerevid->{revid} of $commit{title}\n";
 596
 597                 import_file_revision(\%commit, ($fetch_from == 1), $n);
 598         }
 599
 600         if ($fetch_from == 1 && $n == 0) {
 601                 print STDERR "You appear to have cloned an empty MediaWiki.\n";
 602                 # Something has to be done remote-helper side. If nothing is done, an error is
 603                 # thrown saying that HEAD is refering to unknown object 0000000000000000000
 604                 # and the clone fails.
 605         }
 606 }
 607
 608 sub error_non_fast_forward {
 609         my $advice = run_git("config --bool advice.pushNonFastForward");
 610         chomp($advice);
 611         if ($advice ne "false") {
 612                 # Native git-push would show this after the summary.
 613                 # We can't ask it to display it cleanly, so print it
 614                 # ourselves before.
 615                 print STDERR "To prevent you from losing history, non-fast-forward updates were rejected\n";
 616                 print STDERR "Merge the remote changes (e.g. 'git pull') before pushing again. See the\n";
 617                 print STDERR "'Note about fast-forwards' section of 'git push --help' for details.\n";
 618         }
 619         print STDOUT "error $_[0] \"non-fast-forward\"\n";
 620         return 0;
 621 }
 622
 623 sub mw_push_file {
 624         my $diff_info = shift;
 625         # $diff_info contains a string in this format:
 626         # 100644 100644 <sha1_of_blob_before_commit> <sha1_of_blob_now> <status>
 627         my @diff_info_split = split(/[ \t]/, $diff_info);
 628
 629         # Filename, including .mw extension
 630         my $complete_file_name = shift;
 631         # Commit message
 632         my $summary = shift;
 633         # MediaWiki revision number. Keep the previous one by default,
 634         # in case there's no edit to perform.
 635         my $newrevid = shift;
 636
 637         my $new_sha1 = $diff_info_split[3];
 638         my $old_sha1 = $diff_info_split[2];
 639         my $page_created = ($old_sha1 eq NULL_SHA1);
 640         my $page_deleted = ($new_sha1 eq NULL_SHA1);
 641         $complete_file_name = mediawiki_clean_filename($complete_file_name);
 642
 643         if (substr($complete_file_name,-3) eq ".mw") {
 644                 my $title = substr($complete_file_name,0,-3);
 645
 646                 my $file_content;
 647                 if ($page_deleted) {
 648                         # Deleting a page usually requires
 649                         # special priviledges. A common
 650                         # convention is to replace the page
 651                         # with this content instead:
 652                         $file_content = DELETED_CONTENT;
 653                 } else {
 654                         $file_content = run_git("cat-file blob $new_sha1");
 655                 }
 656
 657                 mw_connect_maybe();
 658
 659                 my $result = $mediawiki->edit( {
 660                         action => 'edit',
 661                         summary => $summary,
 662                         title => $title,
 663                         basetimestamp => $basetimestamps{$newrevid},
 664                         text => mediawiki_clean($file_content, $page_created),
 665                                   }, {
 666                                           skip_encoding => 1 # Helps with names with accentuated characters
 667                                   });
 668                 if (!$result) {
 669                         if ($mediawiki->{error}->{code} == 3) {
 670                                 # edit conflicts, considered as non-fast-forward
 671                                 print STDERR 'Warning: Error ' .
 672                                     $mediawiki->{error}->{code} .
 673                                     ' from mediwiki: ' . $mediawiki->{error}->{details} .
 674                                     ".\n";
 675                                 return ($newrevid, "non-fast-forward");
 676                         } else {
 677                                 # Other errors. Shouldn't happen => just die()
 678                                 die 'Fatal: Error ' .
 679                                     $mediawiki->{error}->{code} .
 680                                     ' from mediwiki: ' . $mediawiki->{error}->{details};
 681                         }
 682                 }
 683                 $newrevid = $result->{edit}->{newrevid};
 684                 print STDERR "Pushed file: $new_sha1 - $title\n";
 685         } else {
 686                 print STDERR "$complete_file_name not a mediawiki file (Not pushable on this version of git-remote-mediawiki).\n"
 687         }
 688         return ($newrevid, "ok");
 689 }
 690
 691 sub mw_push {
 692         # multiple push statements can follow each other
 693         my @refsspecs = (shift, get_more_refs("push"));
 694         my $pushed;
 695         for my $refspec (@refsspecs) {
 696                 my ($force, $local, $remote) = $refspec =~ /^(\+)?([^:]*):([^:]*)$/
 697                     or die("Invalid refspec for push. Expected <src>:<dst> or +<src>:<dst>");
 698                 if ($force) {
 699                         print STDERR "Warning: forced push not allowed on a MediaWiki.\n";
 700                 }
 701                 if ($local eq "") {
 702                         print STDERR "Cannot delete remote branch on a MediaWiki\n";
 703                         print STDOUT "error $remote cannot delete\n";
 704                         next;
 705                 }
 706                 if ($remote ne "refs/heads/master") {
 707                         print STDERR "Only push to the branch 'master' is supported on a MediaWiki\n";
 708                         print STDOUT "error $remote only master allowed\n";
 709                         next;
 710                 }
 711                 if (mw_push_revision($local, $remote)) {
 712                         $pushed = 1;
 713                 }
 714         }
 715
 716         # Notify Git that the push is done
 717         print STDOUT "\n";
 718
 719         if ($pushed && $dumb_push) {
 720                 print STDERR "Just pushed some revisions to MediaWiki.\n";
 721                 print STDERR "The pushed revisions now have to be re-imported, and your current branch\n";
 722                 print STDERR "needs to be updated with these re-imported commits. You can do this with\n";
 723                 print STDERR "\n";
 724                 print STDERR "  git pull --rebase\n";
 725                 print STDERR "\n";
 726         }
 727 }
 728
 729 sub mw_push_revision {
 730         my $local = shift;
 731         my $remote = shift; # actually, this has to be "refs/heads/master" at this point.
 732         my $last_local_revid = get_last_local_revision();
 733         print STDERR ".\n"; # Finish sentence started by get_last_local_revision()
 734         my $last_remote_revid = get_last_remote_revision();
 735         my $mw_revision = $last_remote_revid;
 736
 737         # Get sha1 of commit pointed by local HEAD
 738         my $HEAD_sha1 = run_git("rev-parse $local 2>/dev/null"); chomp($HEAD_sha1);
 739         # Get sha1 of commit pointed by remotes/$remotename/master
 740         my $remoteorigin_sha1 = run_git("rev-parse refs/remotes/$remotename/master 2>/dev/null");
 741         chomp($remoteorigin_sha1);
 742
 743         if ($last_local_revid > 0 &&
 744             $last_local_revid < $last_remote_revid) {
 745                 return error_non_fast_forward($remote);
 746         }
 747
 748         if ($HEAD_sha1 eq $remoteorigin_sha1) {
 749                 # nothing to push
 750                 return 0;
 751         }
 752
 753         # Get every commit in between HEAD and refs/remotes/origin/master,
 754         # including HEAD and refs/remotes/origin/master
 755         my @commit_pairs = ();
 756         if ($last_local_revid > 0) {
 757                 my $parsed_sha1 = $remoteorigin_sha1;
 758                 # Find a path from last MediaWiki commit to pushed commit
 759                 while ($parsed_sha1 ne $HEAD_sha1) {
 760                         my @commit_info =  grep(/^$parsed_sha1/, split(/\n/, run_git("rev-list --children $local")));
 761                         if (!@commit_info) {
 762                                 return error_non_fast_forward($remote);
 763                         }
 764                         my @commit_info_split = split(/ |\n/, $commit_info[0]);
 765                         # $commit_info_split[1] is the sha1 of the commit to export
 766                         # $commit_info_split[0] is the sha1 of its direct child
 767                         push(@commit_pairs, \@commit_info_split);
 768                         $parsed_sha1 = $commit_info_split[1];
 769                 }
 770         } else {
 771                 # No remote mediawiki revision. Export the whole
 772                 # history (linearized with --first-parent)
 773                 print STDERR "Warning: no common ancestor, pushing complete history\n";
 774                 my $history = run_git("rev-list --first-parent --children $local");
 775                 my @history = split('\n', $history);
 776                 @history = @history[1..$#history];
 777                 foreach my $line (reverse @history) {
 778                         my @commit_info_split = split(/ |\n/, $line);
 779                         push(@commit_pairs, \@commit_info_split);
 780                 }
 781         }
 782
 783         foreach my $commit_info_split (@commit_pairs) {
 784                 my $sha1_child = @{$commit_info_split}[0];
 785                 my $sha1_commit = @{$commit_info_split}[1];
 786                 my $diff_infos = run_git("diff-tree -r --raw -z $sha1_child $sha1_commit");
 787                 # TODO: we could detect rename, and encode them with a #redirect on the wiki.
 788                 # TODO: for now, it's just a delete+add
 789                 my @diff_info_list = split(/\0/, $diff_infos);
 790                 # Keep the first line of the commit message as mediawiki comment for the revision
 791                 my $commit_msg = (split(/\n/, run_git("show --pretty=format:\"%s\" $sha1_commit")))[0];
 792                 chomp($commit_msg);
 793                 # Push every blob
 794                 while (@diff_info_list) {
 795                         my $status;
 796                         # git diff-tree -z gives an output like
 797                         # <metadata>\0<filename1>\0
 798                         # <metadata>\0<filename2>\0
 799                         # and we've split on \0.
 800                         my $info = shift(@diff_info_list);
 801                         my $file = shift(@diff_info_list);
 802                         ($mw_revision, $status) = mw_push_file($info, $file, $commit_msg, $mw_revision);
 803                         if ($status eq "non-fast-forward") {
 804                                 # we may already have sent part of the
 805                                 # commit to MediaWiki, but it's too
 806                                 # late to cancel it. Stop the push in
 807                                 # the middle, but still give an
 808                                 # accurate error message.
 809                                 return error_non_fast_forward($remote);
 810                         }
 811                         if ($status ne "ok") {
 812                                 die("Unknown error from mw_push_file()");
 813                         }
 814                 }
 815                 unless ($dumb_push) {
 816                         run_git("notes --ref=$remotename/mediawiki add -m \"mediawiki_revision: $mw_revision\" $sha1_commit");
 817                         run_git("update-ref -m \"Git-MediaWiki push\" refs/mediawiki/$remotename/master $sha1_commit $sha1_child");
 818                 }
 819         }
 820
 821         print STDOUT "ok $remote\n";
 822         return 1;
 823 }