From: Kevin <[email protected]> this introduces a new remote.origin.namespaces argument that is a space-separated list of namespaces. the list of pages extract is then taken from all the specified namespaces.
Reviewed-by: Antoine Beaupré <[email protected]> Signed-off-by: Antoine Beaupré <[email protected]> --- contrib/mw-to-git/git-remote-mediawiki.perl | 34 +++++++++++++++++++++++++++-- 1 file changed, 32 insertions(+), 2 deletions(-) diff --git a/contrib/mw-to-git/git-remote-mediawiki.perl b/contrib/mw-to-git/git-remote-mediawiki.perl index e7f857c1a..1c5e39831 100755 --- a/contrib/mw-to-git/git-remote-mediawiki.perl +++ b/contrib/mw-to-git/git-remote-mediawiki.perl @@ -17,6 +17,7 @@ use Git; use Git::Mediawiki qw(clean_filename smudge_filename connect_maybe EMPTY HTTP_CODE_OK); use DateTime::Format::ISO8601; +use Scalar::Util; use warnings; # By default, use UTF-8 to communicate with Git and the user @@ -63,6 +64,10 @@ chomp(@tracked_pages); my @tracked_categories = split(/[ \n]/, run_git("config --get-all remote.${remotename}.categories")); chomp(@tracked_categories); +# Just like @tracked_categories, but for MediaWiki namespaces. +my @tracked_namespaces = split(/[ \n]/, run_git("config --get-all remote.${remotename}.namespaces")); +chomp(@tracked_namespaces); + # Import media files on pull my $import_media = run_git("config --get --bool remote.${remotename}.mediaimport"); chomp($import_media); @@ -256,6 +261,23 @@ sub get_mw_tracked_categories { return; } +sub get_mw_tracked_namespaces { + my $pages = shift; + foreach my $local_namespace (@tracked_namespaces) { + my $mw_pages = $mediawiki->list( { + action => 'query', + list => 'allpages', + apnamespace => get_mw_namespace_id($local_namespace), + aplimit => 'max' } ) + || die $mediawiki->{error}->{code} . ': ' + . $mediawiki->{error}->{details} . "\n"; + foreach my $page (@{$mw_pages}) { + $pages->{$page->{title}} = $page; + } + } + return; +} + sub get_mw_all_pages { my $pages = shift; # No user-provided list, get the list of pages from the API. @@ -319,6 +341,10 @@ sub get_mw_pages { $user_defined = 1; get_mw_tracked_categories(\%pages); } + if (@tracked_namespaces) { + $user_defined = 1; + get_mw_tracked_namespaces(\%pages); + } if (!$user_defined) { get_mw_all_pages(\%pages); } @@ -1263,7 +1289,6 @@ my %cached_mw_namespace_id; sub get_mw_namespace_id { $mediawiki = connect_maybe($mediawiki, $remotename, $url); my $name = shift; - if (!exists $namespace_id{$name}) { # Look at configuration file, if the record for that namespace is # already cached. Namespaces are stored in form: @@ -1331,7 +1356,12 @@ sub get_mw_namespace_id { sub get_mw_namespace_id_for_page { my $namespace = shift; if ($namespace =~ /^([^:]*):/) { - return get_mw_namespace_id($namespace); + my ($ns, $id) = split(/:/, $namespace); + if (Scalar::Util::looks_like_number($id)) { + return get_mw_namespace_id($ns); + } else{ + return + } } else { return; } -- 2.11.0
