diff options
| -rwxr-xr-x | contrib/mw-to-git/git-remote-mediawiki | 450 |
1 files changed, 386 insertions, 64 deletions
diff --git a/contrib/mw-to-git/git-remote-mediawiki b/contrib/mw-to-git/git-remote-mediawiki index c07b4f0ee6..6b128e88e8 100755 --- a/contrib/mw-to-git/git-remote-mediawiki +++ b/contrib/mw-to-git/git-remote-mediawiki @@ -13,9 +13,6 @@ # # Known limitations: # -# - Only wiki pages are managed, no support for [[File:...]] -# attachments. -# # - Poor performance in the best case: it takes forever to check # whether we're up-to-date (on fetch or push) or to fetch a few # revisions from a large wiki, because we use exclusively a @@ -33,11 +30,10 @@ use strict; use MediaWiki::API; use DateTime::Format::ISO8601; -use encoding 'utf8'; -# use encoding 'utf8' doesn't change STDERROR -# but we're going to output UTF-8 filenames to STDERR +# By default, use UTF-8 to communicate with Git and the user binmode STDERR, ":utf8"; +binmode STDOUT, ":utf8"; use URI::Escape; use IPC::Open2; @@ -70,6 +66,11 @@ chomp(@tracked_pages); my @tracked_categories = split(/[ \n]/, run_git("config --get-all remote.". $remotename .".categories")); chomp(@tracked_categories); +# Import media files too. +my $import_media = run_git("config --get --bool remote.". $remotename .".mediaimport"); +chomp($import_media); +$import_media = ($import_media eq "true"); + 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"); @@ -254,6 +255,70 @@ sub mw_connect_maybe { } } +## Functions for listing pages on the remote wiki +sub get_mw_tracked_pages { + my $pages = shift; + get_mw_page_list(\@tracked_pages, $pages); +} + +sub get_mw_page_list { + my $page_list = shift; + my $pages = shift; + my @some_pages = @$page_list; + while (@some_pages) { + my $last = 50; + if ($#some_pages < $last) { + $last = $#some_pages; + } + my @slice = @some_pages[0..$last]; + get_mw_first_pages(\@slice, $pages); + @some_pages = @some_pages[51..$#some_pages]; + } +} + +sub get_mw_tracked_categories { + my $pages = shift; + foreach my $category (@tracked_categories) { + if (index($category, ':') < 0) { + # Mediawiki requires the Category + # prefix, but let's not force the user + # to specify it. + $category = "Category:" . $category; + } + my $mw_pages = $mediawiki->list( { + action => 'query', + list => 'categorymembers', + cmtitle => $category, + cmlimit => 'max' } ) + || die $mediawiki->{error}->{code} . ': ' + . $mediawiki->{error}->{details}; + foreach my $page (@{$mw_pages}) { + $pages->{$page->{title}} = $page; + } + } +} + +sub get_mw_all_pages { + my $pages = shift; + # No user-provided list, get the list of pages from the API. + my $mw_pages = $mediawiki->list({ + action => 'query', + list => 'allpages', + aplimit => 'max' + }); + if (!defined($mw_pages)) { + print STDERR "fatal: could not get the list of wiki pages.\n"; + print STDERR "fatal: '$url' does not appear to be a mediawiki\n"; + print STDERR "fatal: make sure '$url/api.php' is a valid page.\n"; + exit 1; + } + foreach my $page (@{$mw_pages}) { + $pages->{$page->{title}} = $page; + } +} + +# queries the wiki for a set of pages. Meant to be used within a loop +# querying the wiki for slices of page list. sub get_mw_first_pages { my $some_pages = shift; my @some_pages = @{$some_pages}; @@ -282,6 +347,7 @@ sub get_mw_first_pages { } } +# Get the list of pages to be fetched according to configuration. sub get_mw_pages { mw_connect_maybe(); @@ -291,61 +357,32 @@ sub get_mw_pages { $user_defined = 1; # The user provided a list of pages titles, but we # still need to query the API to get the page IDs. - - my @some_pages = @tracked_pages; - while (@some_pages) { - my $last = 50; - if ($#some_pages < $last) { - $last = $#some_pages; - } - my @slice = @some_pages[0..$last]; - get_mw_first_pages(\@slice, \%pages); - @some_pages = @some_pages[51..$#some_pages]; - } + get_mw_tracked_pages(\%pages); } if (@tracked_categories) { $user_defined = 1; - foreach my $category (@tracked_categories) { - if (index($category, ':') < 0) { - # Mediawiki requires the Category - # prefix, but let's not force the user - # to specify it. - $category = "Category:" . $category; - } - my $mw_pages = $mediawiki->list( { - action => 'query', - list => 'categorymembers', - cmtitle => $category, - cmlimit => 'max' } ) - || die $mediawiki->{error}->{code} . ': ' . $mediawiki->{error}->{details}; - foreach my $page (@{$mw_pages}) { - $pages{$page->{title}} = $page; - } - } + get_mw_tracked_categories(\%pages); } if (!$user_defined) { - # No user-provided list, get the list of pages from - # the API. - my $mw_pages = $mediawiki->list({ - action => 'query', - list => 'allpages', - aplimit => 500, - }); - if (!defined($mw_pages)) { - print STDERR "fatal: could not get the list of wiki pages.\n"; - print STDERR "fatal: '$url' does not appear to be a mediawiki\n"; - print STDERR "fatal: make sure '$url/api.php' is a valid page.\n"; - exit 1; - } - foreach my $page (@{$mw_pages}) { - $pages{$page->{title}} = $page; + get_mw_all_pages(\%pages); + } + if ($import_media) { + print STDERR "Getting media files for selected pages...\n"; + if ($user_defined) { + get_linked_mediafiles(\%pages); + } else { + get_all_mediafiles(\%pages); } } return values(%pages); } +# usage: $out = run_git("command args"); +# $out = run_git("command args", "raw"); # don't interpret output as UTF-8. sub run_git { - open(my $git, "-|:encoding(UTF-8)", "git " . $_[0]); + my $args = shift; + my $encoding = (shift || "encoding(UTF-8)"); + open(my $git, "-|:$encoding", "git " . $args); my $res = do { local $/; <$git> }; close($git); @@ -353,6 +390,123 @@ sub run_git { } +sub get_all_mediafiles { + my $pages = shift; + # Attach list of all pages for media files from the API, + # they are in a different namespace, only one namespace + # can be queried at the same moment + my $mw_pages = $mediawiki->list({ + action => 'query', + list => 'allpages', + apnamespace => get_mw_namespace_id("File"), + aplimit => 'max' + }); + if (!defined($mw_pages)) { + print STDERR "fatal: could not get the list of pages for media files.\n"; + print STDERR "fatal: '$url' does not appear to be a mediawiki\n"; + print STDERR "fatal: make sure '$url/api.php' is a valid page.\n"; + exit 1; + } + foreach my $page (@{$mw_pages}) { + $pages->{$page->{title}} = $page; + } +} + +sub get_linked_mediafiles { + my $pages = shift; + my @titles = map $_->{title}, values(%{$pages}); + + # The query is split in small batches because of the MW API limit of + # the number of links to be returned (500 links max). + my $batch = 10; + while (@titles) { + if ($#titles < $batch) { + $batch = $#titles; + } + my @slice = @titles[0..$batch]; + + # pattern 'page1|page2|...' required by the API + my $mw_titles = join('|', @slice); + + # Media files could be included or linked from + # a page, get all related + my $query = { + action => 'query', + prop => 'links|images', + titles => $mw_titles, + plnamespace => get_mw_namespace_id("File"), + pllimit => 'max' + }; + my $result = $mediawiki->api($query); + + while (my ($id, $page) = each(%{$result->{query}->{pages}})) { + my @media_titles; + if (defined($page->{links})) { + my @link_titles = map $_->{title}, @{$page->{links}}; + push(@media_titles, @link_titles); + } + if (defined($page->{images})) { + my @image_titles = map $_->{title}, @{$page->{images}}; + push(@media_titles, @image_titles); + } + if (@media_titles) { + get_mw_page_list(\@media_titles, $pages); + } + } + + @titles = @titles[($batch+1)..$#titles]; + } +} + +sub get_mw_mediafile_for_page_revision { + # Name of the file on Wiki, with the prefix. + my $filename = shift; + my $timestamp = shift; + my %mediafile; + + # Search if on a media file with given timestamp exists on + # MediaWiki. In that case download the file. + my $query = { + action => 'query', + prop => 'imageinfo', + titles => "File:" . $filename, + iistart => $timestamp, + iiend => $timestamp, + iiprop => 'timestamp|archivename|url', + iilimit => 1 + }; + my $result = $mediawiki->api($query); + + my ($fileid, $file) = each( %{$result->{query}->{pages}} ); + # If not defined it means there is no revision of the file for + # given timestamp. + if (defined($file->{imageinfo})) { + $mediafile{title} = $filename; + + my $fileinfo = pop(@{$file->{imageinfo}}); + $mediafile{timestamp} = $fileinfo->{timestamp}; + # Mediawiki::API's download function doesn't support https URLs + # and can't download old versions of files. + print STDERR "\tDownloading file $mediafile{title}, version $mediafile{timestamp}\n"; + $mediafile{content} = download_mw_mediafile($fileinfo->{url}); + } + return %mediafile; +} + +sub download_mw_mediafile { + my $url = shift; + + my $response = $mediawiki->{ua}->get($url); + if ($response->code == 200) { + return $response->decoded_content; + } else { + print STDERR "Error downloading mediafile from :\n"; + print STDERR "URL: $url\n"; + print STDERR "Server response: " . $response->code . " " . $response->message . "\n"; + exit 1; + } +} + sub get_last_local_revision { # Get note regarding last mediawiki revision my $note = run_git("notes --ref=$remotename/mediawiki show refs/mediawiki/$remotename/master 2>/dev/null"); @@ -456,6 +610,16 @@ sub literal_data { print STDOUT "data ", bytes::length($content), "\n", $content; } +sub literal_data_raw { + # Output possibly binary content. + my ($content) = @_; + # Avoid confusion between size in bytes and in characters + utf8::downgrade($content); + binmode STDOUT, ":raw"; + print STDOUT "data ", bytes::length($content), "\n", $content; + binmode STDOUT, ":utf8"; +} + sub mw_capabilities { # Revisions are imported to the private namespace # refs/mediawiki/$remotename/ by the helper and fetched into @@ -543,6 +707,11 @@ sub import_file_revision { my %commit = %{$commit}; my $full_import = shift; my $n = shift; + my $mediafile = shift; + my %mediafile; + if ($mediafile) { + %mediafile = %{$mediafile}; + } my $title = $commit{title}; my $comment = $commit{comment}; @@ -562,6 +731,10 @@ sub import_file_revision { if ($content ne DELETED_CONTENT) { print STDOUT "M 644 inline $title.mw\n"; literal_data($content); + if (%mediafile) { + print STDOUT "M 644 inline $mediafile{title}\n"; + literal_data_raw($mediafile{content}); + } print STDOUT "\n\n"; } else { print STDOUT "D $title.mw\n"; @@ -657,12 +830,11 @@ sub mw_import_ref { $n++; + my $page_title = $result->{query}->{pages}->{$pagerevid->{pageid}}->{title}; my %commit; $commit{author} = $rev->{user} || 'Anonymous'; $commit{comment} = $rev->{comment} || '*Empty MediaWiki Message*'; - $commit{title} = mediawiki_smudge_filename( - $result->{query}->{pages}->{$pagerevid->{pageid}}->{title} - ); + $commit{title} = mediawiki_smudge_filename($page_title); $commit{mw_revision} = $pagerevid->{revid}; $commit{content} = mediawiki_smudge($rev->{'*'}); @@ -673,9 +845,17 @@ sub mw_import_ref { } $commit{date} = DateTime::Format::ISO8601->parse_datetime($last_timestamp); + # 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, $rev->{timestamp}); + } + # If this is a revision of the media page for new version + # of a file do one common commit for both file and media page. + # Else do commit only for that page. print STDERR "$n/", scalar(@revisions), ": Revision #$pagerevid->{revid} of $commit{title}\n"; - - import_file_revision(\%commit, ($fetch_from == 1), $n); + import_file_revision(\%commit, ($fetch_from == 1), $n, \%mediafile); } if ($fetch_from == 1 && $n == 0) { @@ -701,6 +881,63 @@ sub error_non_fast_forward { return 0; } +sub mw_upload_file { + my $complete_file_name = shift; + my $new_sha1 = shift; + my $extension = shift; + my $file_deleted = shift; + my $summary = shift; + my $newrevid; + my $path = "File:" . $complete_file_name; + my %hashFiles = get_allowed_file_extensions(); + if (!exists($hashFiles{$extension})) { + print STDERR "$complete_file_name is not a permitted file on this wiki.\n"; + print STDERR "Check the configuration of file uploads in your mediawiki.\n"; + return $newrevid; + } + # Deleting and uploading a file requires a priviledged user + if ($file_deleted) { + mw_connect_maybe(); + my $query = { + action => 'delete', + title => $path, + reason => $summary + }; + if (!$mediawiki->edit($query)) { + print STDERR "Failed to delete file on remote wiki\n"; + print STDERR "Check your permissions on the remote site. Error code:\n"; + print STDERR $mediawiki->{error}->{code} . ':' . $mediawiki->{error}->{details}; + exit 1; + } + } else { + # Don't let perl try to interpret file content as UTF-8 => use "raw" + my $content = run_git("cat-file blob $new_sha1", "raw"); + if ($content ne "") { + mw_connect_maybe(); + $mediawiki->{config}->{upload_url} = + "$url/index.php/Special:Upload"; + $mediawiki->edit({ + action => 'upload', + filename => $complete_file_name, + comment => $summary, + file => [undef, + $complete_file_name, + Content => $content], + ignorewarnings => 1, + }, { + skip_encoding => 1 + } ) || die $mediawiki->{error}->{code} . ':' + . $mediawiki->{error}->{details}; + my $last_file_page = $mediawiki->get_page({title => $path}); + $newrevid = $last_file_page->{revid}; + print STDERR "Pushed file: $new_sha1 - $complete_file_name.\n"; + } else { + print STDERR "Empty file $complete_file_name not pushed.\n"; + } + } + return $newrevid; +} + sub mw_push_file { my $diff_info = shift; # $diff_info contains a string in this format: @@ -713,7 +950,8 @@ sub mw_push_file { my $summary = shift; # MediaWiki revision number. Keep the previous one by default, # in case there's no edit to perform. - my $newrevid = shift; + my $oldrevid = shift; + my $newrevid; my $new_sha1 = $diff_info_split[3]; my $old_sha1 = $diff_info_split[2]; @@ -721,9 +959,11 @@ sub mw_push_file { my $page_deleted = ($new_sha1 eq NULL_SHA1); $complete_file_name = mediawiki_clean_filename($complete_file_name); - if (substr($complete_file_name,-3) eq ".mw") { - my $title = substr($complete_file_name,0,-3); - + my ($title, $extension) = $complete_file_name =~ /^(.*)\.([^\.]*)$/; + if (!defined($extension)) { + $extension = ""; + } + if ($extension eq "mw") { my $file_content; if ($page_deleted) { # Deleting a page usually requires @@ -741,7 +981,7 @@ sub mw_push_file { action => 'edit', summary => $summary, title => $title, - basetimestamp => $basetimestamps{$newrevid}, + basetimestamp => $basetimestamps{$oldrevid}, text => mediawiki_clean($file_content, $page_created), }, { skip_encoding => 1 # Helps with names with accentuated characters @@ -753,7 +993,7 @@ sub mw_push_file { $mediawiki->{error}->{code} . ' from mediwiki: ' . $mediawiki->{error}->{details} . ".\n"; - return ($newrevid, "non-fast-forward"); + return ($oldrevid, "non-fast-forward"); } else { # Other errors. Shouldn't happen => just die() die 'Fatal: Error ' . @@ -764,8 +1004,11 @@ sub mw_push_file { $newrevid = $result->{edit}->{newrevid}; print STDERR "Pushed file: $new_sha1 - $title\n"; } else { - print STDERR "$complete_file_name not a mediawiki file (Not pushable on this version of git-remote-mediawiki).\n" + $newrevid = mw_upload_file($complete_file_name, $new_sha1, + $extension, $page_deleted, + $summary); } + $newrevid = ($newrevid or $oldrevid); return ($newrevid, "ok"); } @@ -868,8 +1111,8 @@ sub mw_push_revision { # TODO: we could detect rename, and encode them with a #redirect on the wiki. # TODO: for now, it's just a delete+add my @diff_info_list = split(/\0/, $diff_infos); - # Keep the first line of the commit message as mediawiki comment for the revision - my $commit_msg = (split(/\n/, run_git("show --pretty=format:\"%s\" $sha1_commit")))[0]; + # Keep the subject line of the commit message as mediawiki comment for the revision + my $commit_msg = run_git("log --no-walk --format=\"%s\" $sha1_commit"); chomp($commit_msg); # Push every blob while (@diff_info_list) { @@ -902,3 +1145,82 @@ sub mw_push_revision { print STDOUT "ok $remote\n"; return 1; } + +sub get_allowed_file_extensions { + mw_connect_maybe(); + + my $query = { + action => 'query', + meta => 'siteinfo', + siprop => 'fileextensions' + }; + my $result = $mediawiki->api($query); + my @file_extensions= map $_->{ext},@{$result->{query}->{fileextensions}}; + my %hashFile = map {$_ => 1}@file_extensions; + + return %hashFile; +} + +# In memory cache for MediaWiki namespace ids. +my %namespace_id; + +# Namespaces whose id is cached in the configuration file +# (to avoid duplicates) +my %cached_mw_namespace_id; + +# Return MediaWiki id for a canonical namespace name. +# Ex.: "File", "Project". +sub get_mw_namespace_id { + mw_connect_maybe(); + 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: + # "Name_of_namespace:Id_namespace", ex.: "File:6". + 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; + $cached_mw_namespace_id{$n} = 1; + } + } + + if (!exists $namespace_id{$name}) { + print STDERR "Namespace $name not found in cache, querying the wiki ...\n"; + # NS not found => get namespace id from MW and store it in + # configuration file. + my $query = { + action => 'query', + meta => 'siteinfo', + siprop => 'namespaces' + }; + my $result = $mediawiki->api($query); + + while (my ($id, $ns) = each(%{$result->{query}->{namespaces}})) { + if (defined($ns->{id}) && defined($ns->{canonical})) { + $namespace_id{$ns->{canonical}} = $ns->{id}; + if ($ns->{'*'}) { + # alias (e.g. french Fichier: as alias for canonical File:) + $namespace_id{$ns->{'*'}} = $ns->{id}; + } + } + } + } + + my $id = $namespace_id{$name}; + + 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; + } else { + die "No such namespace $name on MediaWiki."; + } +} |