# License: GPL v2 or later
# Gateway between Git and MediaWiki.
-# https://github.com/Bibzball/Git-Mediawiki/wiki
-#
-# Known limitations:
-#
-# - Several strategies are provided to fetch modifications from the
-# wiki, but no automatic heuristics is provided, the user has
-# to understand and chose which strategy is appropriate for him.
-#
-# - Git renames could be turned into MediaWiki renames (see TODO
-# below)
-#
-# - No way to import "one page, and all pages included in it"
-#
-# - Multiple remote MediaWikis have not been very well tested.
+# Documentation & bugtracker: https://github.com/moy/Git-Mediawiki/
use strict;
use MediaWiki::API;
# used to reflect file creation or deletion in diff.
use constant NULL_SHA1 => "0000000000000000000000000000000000000000";
+# Used on Git's side to reflect empty edit messages on the wiki
+use constant EMPTY_MESSAGE => '*Empty MediaWiki Message*';
+
my $remotename = $ARGV[0];
my $url = $ARGV[1];
my @tracked_categories = split(/[ \n]/, run_git("config --get-all remote.". $remotename .".categories"));
chomp(@tracked_categories);
-# Import media files too.
+# Import media files on pull
my $import_media = run_git("config --get --bool remote.". $remotename .".mediaimport");
chomp($import_media);
$import_media = ($import_media eq "true");
+# Export media files on push
+my $export_media = run_git("config --get --bool remote.". $remotename .".mediaexport");
+chomp($export_media);
+$export_media = !($export_media eq "false");
+
my $wiki_login = run_git("config --get remote.". $remotename .".mwLogin");
# Note: mwPassword is discourraged. Use the credential system instead.
my $wiki_passwd = run_git("config --get remote.". $remotename .".mwPassword");
## credential API management (generic functions)
-sub credential_from_url {
- my $url = shift;
- my $parsed = URI->new($url);
- my %credential;
-
- if ($parsed->scheme) {
- $credential{protocol} = $parsed->scheme;
- }
- if ($parsed->host) {
- $credential{host} = $parsed->host;
- }
- if ($parsed->path) {
- $credential{path} = $parsed->path;
- }
- if ($parsed->userinfo) {
- if ($parsed->userinfo =~ /([^:]*):(.*)/) {
- $credential{username} = $1;
- $credential{password} = $2;
- } else {
- $credential{username} = $parsed->userinfo;
- }
- }
-
- return %credential;
-}
-
sub credential_read {
my %credential;
my $reader = shift;
sub credential_write {
my $credential = shift;
my $writer = shift;
+ # url overwrites other fields, so it must come first
+ print $writer "url=$credential->{url}\n" if exists $credential->{url};
while (my ($key, $value) = each(%$credential) ) {
- if ($value) {
+ if (length $value && $key ne 'url') {
print $writer "$key=$value\n";
}
}
$mediawiki = MediaWiki::API->new;
$mediawiki->{config}->{api_url} = "$url/api.php";
if ($wiki_login) {
- my %credential = credential_from_url($url);
+ my %credential = (url => $url);
$credential{username} = $wiki_login;
$credential{password} = $wiki_passwd;
credential_run("fill", \%credential);
sub get_mw_pages {
mw_connect_maybe();
+ print STDERR "Listing pages on remote wiki...\n";
+
my %pages; # hash on page titles to avoid duplicates
my $user_defined;
if (@tracked_pages) {
get_all_mediafiles(\%pages);
}
}
+ print STDERR (scalar keys %pages) . " pages found.\n";
return %pages;
}
my $max_rev_num = 0;
+ print STDERR "Getting last revision id on tracked pages...\n";
+
foreach my $page (@pages) {
my $id = $page->{pageid};
return ($n, @revisions);
}
+sub fe_escape_path {
+ my $path = shift;
+ $path =~ s/\\/\\\\/g;
+ $path =~ s/"/\\"/g;
+ $path =~ s/\n/\\n/g;
+ return '"' . $path . '"';
+}
+
sub import_file_revision {
my $commit = shift;
my %commit = %{$commit};
print STDOUT "from refs/mediawiki/$remotename/master^0\n";
}
if ($content ne DELETED_CONTENT) {
- print STDOUT "M 644 inline $title.mw\n";
+ print STDOUT "M 644 inline " .
+ fe_escape_path($title . ".mw") . "\n";
literal_data($content);
if (%mediafile) {
- print STDOUT "M 644 inline $mediafile{title}\n";
+ print STDOUT "M 644 inline "
+ . fe_escape_path($mediafile{title}) . "\n";
literal_data_raw($mediafile{content});
}
print STDOUT "\n\n";
} else {
- print STDOUT "D $title.mw\n";
+ print STDOUT "D " . fe_escape_path($title . ".mw") . "\n";
}
# mediawiki revision number in the git note
my $last_timestamp = 0; # Placeholer in case $rev->timestamp is undefined
foreach my $pagerevid (@$revision_ids) {
+ # Count page even if we skip it, since we display
+ # $n/$total and $total includes skipped pages.
+ $n++;
+
# fetch the content of the pages
my $query = {
action => 'query',
die "Failed to retrieve modified page for revision $pagerevid";
}
+ if (defined($result->{query}->{badrevids}->{$pagerevid})) {
+ # The revision id does not exist on the remote wiki.
+ next;
+ }
+
if (!defined($result->{query}->{pages})) {
die "Invalid revision $pagerevid.";
}
my $result_page = $result_pages[0];
my $rev = $result_pages[0]->{revisions}->[0];
- # Count page even if we skip it, since we display
- # $n/$total and $total includes skipped pages.
- $n++;
-
my $page_title = $result_page->{title};
if (!exists($pages->{$page_title})) {
my %commit;
$commit{author} = $rev->{user} || 'Anonymous';
- $commit{comment} = $rev->{comment} || '*Empty MediaWiki Message*';
+ $commit{comment} = $rev->{comment} || EMPTY_MESSAGE;
$commit{title} = mediawiki_smudge_filename($page_title);
$commit{mw_revision} = $rev->{revid};
$commit{content} = mediawiki_smudge($rev->{'*'});
# Differentiates classic pages and media files.
my ($namespace, $filename) = $page_title =~ /^([^:]*):(.*)$/;
my %mediafile;
- if ($namespace && get_mw_namespace_id($namespace) == get_mw_namespace_id("File")) {
- %mediafile = get_mw_mediafile_for_page_revision($filename, $rev->{timestamp});
+ if ($namespace) {
+ my $id = get_mw_namespace_id($namespace);
+ if ($id && $id == get_mw_namespace_id("File")) {
+ %mediafile = get_mw_mediafile_for_page_revision($filename, $rev->{timestamp});
+ }
}
# If this is a revision of the media page for new version
# of a file do one common commit for both file and media page.
my $oldrevid = shift;
my $newrevid;
+ if ($summary eq EMPTY_MESSAGE) {
+ $summary = '';
+ }
+
my $new_sha1 = $diff_info_split[3];
my $old_sha1 = $diff_info_split[2];
my $page_created = ($old_sha1 eq NULL_SHA1);
$extension = "";
}
if ($extension eq "mw") {
+ my $ns = get_mw_namespace_id_for_page($complete_file_name);
+ if ($ns && $ns == get_mw_namespace_id("File") && (!$export_media)) {
+ print STDERR "Ignoring media file related page: $complete_file_name\n";
+ return ($oldrevid, "ok");
+ }
my $file_content;
if ($page_deleted) {
# Deleting a page usually requires
}
$newrevid = $result->{edit}->{newrevid};
print STDERR "Pushed file: $new_sha1 - $title\n";
- } else {
+ } elsif ($export_media) {
$newrevid = mw_upload_file($complete_file_name, $new_sha1,
$extension, $page_deleted,
$summary);
+ } else {
+ print STDERR "Ignoring media file $title\n";
}
$newrevid = ($newrevid or $oldrevid);
return ($newrevid, "ok");
if ($last_local_revid > 0) {
my $parsed_sha1 = $remoteorigin_sha1;
# Find a path from last MediaWiki commit to pushed commit
+ print STDERR "Computing path from local to remote ...\n";
+ my @local_ancestry = split(/\n/, run_git("rev-list --boundary --parents $local ^$parsed_sha1"));
+ my %local_ancestry;
+ foreach my $line (@local_ancestry) {
+ if (my ($child, $parents) = $line =~ m/^-?([a-f0-9]+) ([a-f0-9 ]+)/) {
+ foreach my $parent (split(' ', $parents)) {
+ $local_ancestry{$parent} = $child;
+ }
+ } elsif (!$line =~ m/^([a-f0-9]+)/) {
+ die "Unexpected output from git rev-list: $line";
+ }
+ }
while ($parsed_sha1 ne $HEAD_sha1) {
- my @commit_info = grep(/^$parsed_sha1/, split(/\n/, run_git("rev-list --children $local")));
- if (!@commit_info) {
+ my $child = $local_ancestry{$parsed_sha1};
+ if (!$child) {
+ printf STDERR "Cannot find a path in history from remote commit to last commit\n";
return error_non_fast_forward($remote);
}
- my @commit_info_split = split(/ |\n/, $commit_info[0]);
- # $commit_info_split[1] is the sha1 of the commit to export
- # $commit_info_split[0] is the sha1 of its direct child
- push(@commit_pairs, \@commit_info_split);
- $parsed_sha1 = $commit_info_split[1];
+ push(@commit_pairs, [$parsed_sha1, $child]);
+ $parsed_sha1 = $child;
}
} else {
# No remote mediawiki revision. Export the whole
}
}
unless ($dumb_push) {
- run_git("notes --ref=$remotename/mediawiki add -m \"mediawiki_revision: $mw_revision\" $sha1_commit");
+ run_git("notes --ref=$remotename/mediawiki add -f -m \"mediawiki_revision: $mw_revision\" $sha1_commit");
run_git("update-ref -m \"Git-MediaWiki push\" refs/mediawiki/$remotename/master $sha1_commit $sha1_child");
}
}
# Look at configuration file, if the record for that namespace is
# already cached. Namespaces are stored in form:
# "Name_of_namespace:Id_namespace", ex.: "File:6".
- my @temp = split(/[ \n]/, run_git("config --get-all remote."
+ my @temp = split(/[\n]/, run_git("config --get-all remote."
. $remotename .".namespaceCache"));
chomp(@temp);
foreach my $ns (@temp) {
my ($n, $id) = split(/:/, $ns);
- $namespace_id{$n} = $id;
+ if ($id eq 'notANameSpace') {
+ $namespace_id{$n} = {is_namespace => 0};
+ } else {
+ $namespace_id{$n} = {is_namespace => 1, id => $id};
+ }
$cached_mw_namespace_id{$n} = 1;
}
}
while (my ($id, $ns) = each(%{$result->{query}->{namespaces}})) {
if (defined($ns->{id}) && defined($ns->{canonical})) {
- $namespace_id{$ns->{canonical}} = $ns->{id};
+ $namespace_id{$ns->{canonical}} = {is_namespace => 1, id => $ns->{id}};
if ($ns->{'*'}) {
# alias (e.g. french Fichier: as alias for canonical File:)
- $namespace_id{$ns->{'*'}} = $ns->{id};
+ $namespace_id{$ns->{'*'}} = {is_namespace => 1, id => $ns->{id}};
}
}
}
}
- my $id = $namespace_id{$name};
+ my $ns = $namespace_id{$name};
+ my $id;
- if (defined $id) {
- # Store explicitely requested namespaces on disk
- if (!exists $cached_mw_namespace_id{$name}) {
- run_git("config --add remote.". $remotename
- .".namespaceCache \"". $name .":". $id ."\"");
- $cached_mw_namespace_id{$name} = 1;
- }
- return $id;
+ unless (defined $ns) {
+ print STDERR "No such namespace $name on MediaWiki.\n";
+ $ns = {is_namespace => 0};
+ $namespace_id{$name} = $ns;
+ }
+
+ if ($ns->{is_namespace}) {
+ $id = $ns->{id};
+ }
+
+ # Store "notANameSpace" as special value for inexisting namespaces
+ my $store_id = ($id || 'notANameSpace');
+
+ # Store explicitely requested namespaces on disk
+ if (!exists $cached_mw_namespace_id{$name}) {
+ run_git("config --add remote.". $remotename
+ .".namespaceCache \"". $name .":". $store_id ."\"");
+ $cached_mw_namespace_id{$name} = 1;
+ }
+ return $id;
+}
+
+sub get_mw_namespace_id_for_page {
+ if (my ($namespace) = $_[0] =~ /^([^:]*):/) {
+ return get_mw_namespace_id($namespace);
} else {
- die "No such namespace $name on MediaWiki.";
+ return;
}
}