summaryrefslogtreecommitdiff
path: root/contrib/mw-to-git/git-remote-mediawiki
diff options
context:
space:
mode:
Diffstat (limited to 'contrib/mw-to-git/git-remote-mediawiki')
-rwxr-xr-xcontrib/mw-to-git/git-remote-mediawiki777
1 files changed, 650 insertions, 127 deletions
diff --git a/contrib/mw-to-git/git-remote-mediawiki b/contrib/mw-to-git/git-remote-mediawiki
index c18bfa1f15..68555d4265 100755
--- a/contrib/mw-to-git/git-remote-mediawiki
+++ b/contrib/mw-to-git/git-remote-mediawiki
@@ -9,40 +9,19 @@
# License: GPL v2 or later
# Gateway between Git and MediaWiki.
-# https://github.com/Bibzball/Git-Mediawiki/wiki
-#
-# 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
-# page-based synchronization. We could switch to a wiki-wide
-# synchronization when the synchronization involves few revisions
-# but the wiki is large.
-#
-# - Git renames could be turned into MediaWiki renames (see TODO
-# below)
-#
-# - login/password support requires the user to write the password
-# cleartext in a file (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;
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;
+
use warnings;
# Mediawiki filenames can contain forward slashes. This variable decides by which pattern they should be replaced
@@ -59,6 +38,9 @@ use constant EMPTY_CONTENT => "<!-- empty page -->\n";
# 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];
@@ -71,10 +53,18 @@ chomp(@tracked_pages);
my @tracked_categories = split(/[ \n]/, run_git("config --get-all remote.". $remotename .".categories"));
chomp(@tracked_categories);
+# 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");
-# TODO: ideally, this should be able to read from keyboard, but we're
-# inside a remote helper, so our stdin is connect to git, not to a
-# terminal.
+# Note: mwPassword is discourraged. Use the credential system instead.
my $wiki_passwd = run_git("config --get remote.". $remotename .".mwPassword");
my $wiki_domain = run_git("config --get remote.". $remotename .".mwDomain");
chomp($wiki_login);
@@ -86,6 +76,21 @@ my $shallow_import = run_git("config --get --bool remote.". $remotename .".shall
chomp($shallow_import);
$shallow_import = ($shallow_import eq "true");
+# Fetch (clone and pull) by revisions instead of by pages. This behavior
+# is more efficient when we have a wiki with lots of pages and we fetch
+# the revisions quite often so that they concern only few pages.
+# Possible values:
+# - by_rev: perform one query per new revision on the remote wiki
+# - by_page: query each tracked page for new revision
+my $fetch_strategy = run_git("config --get remote.$remotename.fetchStrategy");
+unless ($fetch_strategy) {
+ $fetch_strategy = run_git("config --get mediawiki.fetchStrategy");
+}
+chomp($fetch_strategy);
+unless ($fetch_strategy) {
+ $fetch_strategy = "by_page";
+}
+
# Dumb push: don't update notes and mediawiki ref to reflect the last push.
#
# Configurable with mediawiki.dumbPush, or per-remote with
@@ -151,32 +156,152 @@ while (<STDIN>) {
########################## Functions ##############################
+## credential API management (generic functions)
+
+sub credential_read {
+ my %credential;
+ my $reader = shift;
+ my $op = shift;
+ while (<$reader>) {
+ my ($key, $value) = /([^=]*)=(.*)/;
+ if (not defined $key) {
+ die "ERROR receiving response from git credential $op:\n$_\n";
+ }
+ $credential{$key} = $value;
+ }
+ return %credential;
+}
+
+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 (length $value && $key ne 'url') {
+ print $writer "$key=$value\n";
+ }
+ }
+}
+
+sub credential_run {
+ my $op = shift;
+ my $credential = shift;
+ my $pid = open2(my $reader, my $writer, "git credential $op");
+ credential_write($credential, $writer);
+ print $writer "\n";
+ close($writer);
+
+ if ($op eq "fill") {
+ %$credential = credential_read($reader, $op);
+ } else {
+ if (<$reader>) {
+ die "ERROR while running git credential $op:\n$_";
+ }
+ }
+ close($reader);
+ waitpid($pid, 0);
+ my $child_exit_status = $? >> 8;
+ if ($child_exit_status != 0) {
+ die "'git credential $op' failed with code $child_exit_status.";
+ }
+}
+
# MediaWiki API instance, created lazily.
my $mediawiki;
sub mw_connect_maybe {
if ($mediawiki) {
- return;
+ return;
}
$mediawiki = MediaWiki::API->new;
$mediawiki->{config}->{api_url} = "$url/api.php";
if ($wiki_login) {
- if (!$mediawiki->login({
- lgname => $wiki_login,
- lgpassword => $wiki_passwd,
- lgdomain => $wiki_domain,
- })) {
- print STDERR "Failed to log in mediawiki user \"$wiki_login\" on $url\n";
- print STDERR "(error " .
- $mediawiki->{error}->{code} . ': ' .
- $mediawiki->{error}->{details} . ")\n";
- exit 1;
+ my %credential = (url => $url);
+ $credential{username} = $wiki_login;
+ $credential{password} = $wiki_passwd;
+ credential_run("fill", \%credential);
+ my $request = {lgname => $credential{username},
+ lgpassword => $credential{password},
+ lgdomain => $wiki_domain};
+ if ($mediawiki->login($request)) {
+ credential_run("approve", \%credential);
+ print STDERR "Logged in mediawiki user \"$credential{username}\".\n";
} else {
- print STDERR "Logged in with user \"$wiki_login\".\n";
+ print STDERR "Failed to log in mediawiki user \"$credential{username}\" on $url\n";
+ print STDERR " (error " .
+ $mediawiki->{error}->{code} . ': ' .
+ $mediawiki->{error}->{details} . ")\n";
+ credential_run("reject", \%credential);
+ exit 1;
+ }
+ }
+}
+
+## 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};
@@ -205,70 +330,45 @@ sub get_mw_first_pages {
}
}
+# Get the list of pages to be fetched according to configuration.
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) {
$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);
+ print STDERR (scalar keys %pages) . " pages found.\n";
+ return %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);
@@ -276,6 +376,123 @@ 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");
@@ -297,13 +514,36 @@ sub get_last_local_revision {
# Remember the timestamp corresponding to a revision id.
my %basetimestamps;
+# Get the last remote revision without taking in account which pages are
+# tracked or not. This function makes a single request to the wiki thus
+# avoid a loop onto all tracked pages. This is useful for the fetch-by-rev
+# option.
+sub get_last_global_remote_rev {
+ mw_connect_maybe();
+
+ my $query = {
+ action => 'query',
+ list => 'recentchanges',
+ prop => 'revisions',
+ rclimit => '1',
+ rcdir => 'older',
+ };
+ my $result = $mediawiki->api($query);
+ return $result->{query}->{recentchanges}[0]->{revid};
+}
+
+# Get the last remote revision concerning the tracked pages and the tracked
+# categories.
sub get_last_remote_revision {
mw_connect_maybe();
- my @pages = get_mw_pages();
+ my %pages_hash = get_mw_pages();
+ my @pages = values(%pages_hash);
my $max_rev_num = 0;
+ print STDERR "Getting last revision id on tracked pages...\n";
+
foreach my $page (@pages) {
my $id = $page->{pageid};
@@ -379,6 +619,16 @@ sub literal_data {
print STDOUT "data ", bytes::length($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
@@ -466,6 +716,11 @@ 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 = $commit{comment};
@@ -485,6 +740,10 @@ sub import_file_revision {
if ($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";
@@ -547,8 +806,6 @@ sub mw_import_ref {
mw_connect_maybe();
- my @pages = get_mw_pages();
-
print STDERR "Searching revisions...\n";
my $last_local = get_last_local_revision();
my $fetch_from = $last_local + 1;
@@ -557,36 +814,111 @@ sub mw_import_ref {
} else {
print STDERR ", fetching from here.\n";
}
+
+ my $n = 0;
+ if ($fetch_strategy eq "by_rev") {
+ print STDERR "Fetching & writing export data by revs...\n";
+ $n = mw_import_ref_by_revs($fetch_from);
+ } elsif ($fetch_strategy eq "by_page") {
+ print STDERR "Fetching & writing export data by pages...\n";
+ $n = mw_import_ref_by_pages($fetch_from);
+ } else {
+ print STDERR "fatal: invalid fetch strategy \"$fetch_strategy\".\n";
+ print STDERR "Check your configuration variables remote.$remotename.fetchStrategy and mediawiki.fetchStrategy\n";
+ exit 1;
+ }
+
+ if ($fetch_from == 1 && $n == 0) {
+ print STDERR "You appear to have cloned an empty MediaWiki.\n";
+ # Something has to be done remote-helper side. If nothing is done, an error is
+ # thrown saying that HEAD is refering to unknown object 0000000000000000000
+ # and the clone fails.
+ }
+}
+
+sub mw_import_ref_by_pages {
+
+ my $fetch_from = shift;
+ my %pages_hash = get_mw_pages();
+ my @pages = values(%pages_hash);
+
my ($n, @revisions) = fetch_mw_revisions(\@pages, $fetch_from);
- # Creation of the fast-import stream
- print STDERR "Fetching & writing export data...\n";
+ @revisions = sort {$a->{revid} <=> $b->{revid}} @revisions;
+ my @revision_ids = map $_->{revid}, @revisions;
- $n = 0;
+ return mw_import_revids($fetch_from, \@revision_ids, \%pages_hash);
+}
+
+sub mw_import_ref_by_revs {
+
+ my $fetch_from = shift;
+ my %pages_hash = get_mw_pages();
+
+ my $last_remote = get_last_global_remote_rev();
+ my @revision_ids = $fetch_from..$last_remote;
+ return mw_import_revids($fetch_from, \@revision_ids, \%pages_hash);
+}
+
+# Import revisions given in second argument (array of integers).
+# Only pages appearing in the third argument (hash indexed by page titles)
+# will be imported.
+sub mw_import_revids {
+ my $fetch_from = shift;
+ my $revision_ids = shift;
+ my $pages = shift;
+
+ my $n = 0;
+ my $n_actual = 0;
my $last_timestamp = 0; # Placeholer in case $rev->timestamp is undefined
- foreach my $pagerevid (sort {$a->{revid} <=> $b->{revid}} @revisions) {
+ 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',
prop => 'revisions',
rvprop => 'content|timestamp|comment|user|ids',
- revids => $pagerevid->{revid},
+ revids => $pagerevid,
};
my $result = $mediawiki->api($query);
- my $rev = pop(@{$result->{query}->{pages}->{$pagerevid->{pageid}}->{revisions}});
+ if (!$result) {
+ die "Failed to retrieve modified page for revision $pagerevid";
+ }
- $n++;
+ if (defined($result->{query}->{badrevids}->{$pagerevid})) {
+ # The revision id does not exist on the remote wiki.
+ next;
+ }
+
+ if (!defined($result->{query}->{pages})) {
+ die "Invalid revision $pagerevid.";
+ }
+
+ my @result_pages = values(%{$result->{query}->{pages}});
+ my $result_page = $result_pages[0];
+ my $rev = $result_pages[0]->{revisions}->[0];
+
+ my $page_title = $result_page->{title};
+
+ if (!exists($pages->{$page_title})) {
+ print STDERR "$n/", scalar(@$revision_ids),
+ ": Skipping revision #$rev->{revid} of $page_title\n";
+ next;
+ }
+
+ $n_actual++;
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{mw_revision} = $pagerevid->{revid};
+ $commit{comment} = $rev->{comment} || EMPTY_MESSAGE;
+ $commit{title} = mediawiki_smudge_filename($page_title);
+ $commit{mw_revision} = $rev->{revid};
$commit{content} = mediawiki_smudge($rev->{'*'});
if (!defined($rev->{timestamp})) {
@@ -596,17 +928,23 @@ sub mw_import_ref {
}
$commit{date} = DateTime::Format::ISO8601->parse_datetime($last_timestamp);
- print STDERR "$n/", scalar(@revisions), ": Revision #$pagerevid->{revid} of $commit{title}\n";
-
- import_file_revision(\%commit, ($fetch_from == 1), $n);
+ # Differentiates classic pages and media files.
+ my ($namespace, $filename) = $page_title =~ /^([^:]*):(.*)$/;
+ my %mediafile;
+ 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, $rev->{timestamp});
+ }
+ }
+ # If this is a revision of the media page for new version
+ # of a file do one common commit for both file and media page.
+ # Else do commit only for that page.
+ print STDERR "$n/", scalar(@$revision_ids), ": Revision #$rev->{revid} of $commit{title}\n";
+ import_file_revision(\%commit, ($fetch_from == 1), $n_actual, \%mediafile);
}
- if ($fetch_from == 1 && $n == 0) {
- print STDERR "You appear to have cloned an empty MediaWiki.\n";
- # Something has to be done remote-helper side. If nothing is done, an error is
- # thrown saying that HEAD is refering to unknown object 0000000000000000000
- # and the clone fails.
- }
+ return $n_actual;
}
sub error_non_fast_forward {
@@ -624,6 +962,63 @@ 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:
@@ -636,7 +1031,12 @@ 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 $newrevid;
+
+ if ($summary eq EMPTY_MESSAGE) {
+ $summary = '';
+ }
my $new_sha1 = $diff_info_split[3];
my $old_sha1 = $diff_info_split[2];
@@ -644,9 +1044,16 @@ 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 $ns = get_mw_namespace_id_for_page($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
@@ -664,7 +1071,7 @@ 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
@@ -676,7 +1083,7 @@ 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 ' .
@@ -686,9 +1093,14 @@ sub mw_push_file {
}
$newrevid = $result->{edit}->{newrevid};
print STDERR "Pushed file: $new_sha1 - $title\n";
+ } elsif ($export_media) {
+ $newrevid = mw_upload_file($complete_file_name, $new_sha1,
+ $extension, $page_deleted,
+ $summary);
} else {
- print STDERR "$complete_file_name not a mediawiki file (Not pushable on this version of git-remote-mediawiki).\n"
+ print STDERR "Ignoring media file $title\n";
}
+ $newrevid = ($newrevid or $oldrevid);
return ($newrevid, "ok");
}
@@ -760,16 +1172,26 @@ sub mw_push_revision {
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
@@ -791,8 +1213,8 @@ 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) {
@@ -817,7 +1239,7 @@ sub mw_push_revision {
}
}
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");
}
}
@@ -825,3 +1247,104 @@ 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(/:/, $ns);
+ if ($id eq 'notANameSpace') {
+ $namespace_id{$n} = {is_namespace => 0};
+ } else {
+ $namespace_id{$n} = {is_namespace => 1, id => $id};
+ }
+ $cached_mw_namespace_id{$n} = 1;
+ }
+ }
+
+ 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}} = {is_namespace => 1, id => $ns->{id}};
+ if ($ns->{'*'}) {
+ # alias (e.g. french Fichier: as alias for canonical File:)
+ $namespace_id{$ns->{'*'}} = {is_namespace => 1, id => $ns->{id}};
+ }
+ }
+ }
+ }
+
+ my $ns = $namespace_id{$name};
+ my $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 {
+ return;
+ }
+}