[PATCHv3 1/2] Add a remote helper to interact with mediawiki, pull & clone handled
- From
- Jeremie Nikaes <jeremie.nikaes@ensimag.imag.fr>
- Date
- Jun 9, 2011, 13:15 UTC
- Message-ID
- <1307625360-10973-1-git-send-email-jeremie.nikaes@ensimag.imag.fr>
Implement a gate between git and mediawiki, allowing git users to push and pull objects from mediawiki just as one would do with a classic git repository thanks to remote-helpers.
Currently supported commands are :
git clone mediawiki::http://onewiki.com
git pullYou need the following packages installed (available on common
repositories):
libmediawiki-api-perl
libdatetime-format-iso8601-perlUse remote helpers in order to be as transparent as possible to the git user.
Download Mediawiki revisions through the Mediawiki API and then fast-import into git.
Mediawiki revisions and git commits are linked thanks to notes bound to commits.
The import part is done on a refs/mediawiki/<remote> branch before coming to refs/remote/origin/master (Huge thanks to Jonathan Nieder for his help)
For now, the whole wiki is cloned, but it will be possible to clone only some pages: the clone is based on a list of pages which is now all pages.
Code clarified & improved with the help of Jeff King and Junio C Hamano.
We were not able to reproduce the empty timestamp bug noticed by Jeff King, thus needing some further testing. A placeholder is still implemented just in case. Its value is the value of the last valid timestamp received + 1
With "use encoding 'utf-8'" non-iso characters are now fully supported in both file content and filename. A small helper run_git is also added to execute any git command, helping to also utf-8 encode results from git commands. However, utf-8 encoding for filenames could raise problems if different file systems handle utf-8 filenames differently. A uri_escape of mediawiki filenames could be imaginable, and is still to be discussed further.
Partial cloning is supported using the following syntax : "git clone mediawiki::http://wikiurl##A_Page##Another_Page" As always, this url is kept in .git/config, helping to always keep track of these specific pages
Signed-off-by: Jérémie Nikaes <jeremie.nikaes@ensimag.imag.fr> Signed-off-by: Arnaud Lacurie <arnaud.lacurie@ensimag.imag.fr> Signed-off-by: Claire Fousse <claire.fousse@ensimag.imag.fr> Signed-off-by: David Amouyal <david.amouyal@ensimag.imag.fr> Signed-off-by: Matthieu Moy <matthieu.moy@grenoble-inp.fr> Signed-off-by: Sylvain Boulmé <sylvain.boulme@imag.fr> --- -- diff with v2 Added the timestamp placeholder Utf8 encoding now properly supported Partial cloning functionality added
contrib/mw-to-git/git-remote-mediawiki | 322 ++++++++++++++++++++++++++++ contrib/mw-to-git/git-remote-mediawiki.txt | 7 + 2 files changed, 329 insertions(+), 0 deletions(-) create mode 100755 contrib/mw-to-git/git-remote-mediawiki create mode 100644 contrib/mw-to-git/git-remote-mediawiki.txt
diff --git a/contrib/mw-to-git/git-remote-mediawiki b/contrib/mw-to-git/git-remote-mediawiki new file mode 100755 index 0000000..176ff09 --- /dev/null +++ b/contrib/mw-to-git/git-remote-mediawiki @@ -0,0 +1,322 @@ +#! /usr/bin/perl + +use strict; +use MediaWiki::API; +use DateTime::Format::ISO8601; +use encoding 'utf8'; +use URI::Escape; +use warnings; + +# Mediawiki filenames can contain forward slashes. This variable decides by which pattern they should be replaced +my $slash_replacement = "%2F"; + +my $remotename = $ARGV[0]; +# Current syntax to fetch only a set of pages mediawiki::http://mediawikiurl##A_Page##Another_Page +my @pages_titles = split(/##/,$ARGV[1]); +my $url = shift (@pages_titles); + + +# commands parser +my $entry; +my @cmd; +while (1) { + $| = 1; #flush STDOUT + $entry = <STDIN>; + chomp($entry); + @cmd = split(/ /,$entry); + if (defined($cmd[0])) { + if ($cmd[0] eq "capabilities") { + last unless (!defined($cmd[1])); + mw_capabilities(); + } elsif ($cmd[0] eq "list") { + last unless (!defined($cmd[2])); + mw_list($cmd[1]); + } elsif ($cmd[0] eq "import") { + last unless ($cmd[1] ne "" && !defined($cmd[2])); + mw_import($cmd[1]); + } elsif ($cmd[0] eq "option") { + last unless ($cmd[1] ne "" && $cmd[2] ne "" && !defined($cmd[3])); + mw_option($cmd[1],$cmd[2]); + } elsif ($cmd[0] eq "push") { + # Check the pattern <src>:<dst> + my @pushargs = split(/:/,$cmd[1]); + last unless ($pushargs[1] ne "" && !defined($pushargs[2])); + mw_push($pushargs[0],$pushargs[1]); + } else { + print STDERR "Unknown capability. Aborting...\n"; + last; + } + } else { + # End of input + last; + } + +} + +########################## Functions ############################## +sub get_pages{ + my $mediawiki = MediaWiki::API->new; + $mediawiki->{config}->{api_url} = "$url/api.php"; + + my $pages; + if (!@pages_titles){ + $pages = $mediawiki->list({ + action => 'query', + list => 'allpages', + aplimit => 500, + }); + if (!defined($pages)) { + 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; + } + return @$pages; + } else { + #the list of titles should follow the pattern 'page1|page2|...' + my $titles = ""; + foreach my $title (@pages_titles){ + $titles.="$title|"; + } + #supress the last | that is add in the foreach + chop($titles); + + $pages = $mediawiki->api({ + action => 'query', + titles => $titles, + }); + if (!defined($pages)) { + print STDERR "fatal: None of the pages exist \n"; + exit 1; + } + return values (%{$pages->{query}->{pages}}); + } +} + +sub run_git { + open(my $git, "-|:encoding(UTF-8)", "git " . $_[0]); + my $res = do { local $/; <$git> }; + close($git); + + return $res; +} + + +sub get_last_local_revision { + # Get note regarding last mediawiki revision + my $note = run_git("notes --ref=mediawiki show refs/mediawiki/$remotename/master 2>/dev/null"); + my @note_info = split(/ /, $note); + + my $lastrevision_number; + if (!(defined($note_info[0]) && $note_info[0] eq "mediawiki_revision:")) { + print STDERR "No previous mediawiki revision found"; + $lastrevision_number = 0; + } else { + # Notes are formatted : mediawiki_revision: #number + $lastrevision_number = $note_info[1]; + chomp($lastrevision_number); + print STDERR "Last local mediawiki revision found is $lastrevision_number "; + } + return $lastrevision_number; +} + +sub get_last_remote_revision { + my $mediawiki = MediaWiki::API->new; + $mediawiki->{config}->{api_url} = "$url/api.php"; + + my @pages = get_pages(); + + my $max_rev_num = 0; + + foreach my $page (@pages) { + my $id = $page->{pageid}; + + my $query = { + action => 'query', + prop => 'revisions', + rvprop => 'ids', + pageids => $id, + }; + + my $result = $mediawiki->api($query); + + my $lastrev = pop(@{$result->{query}->{pages}->{$id}->{revisions}}); + + $max_rev_num = ($lastrev->{revid} > $max_rev_num ? $lastrev->{revid} : $max_rev_num); + } + + print STDERR "Last remote revision found is $max_rev_num\n"; + return $max_rev_num; +} + +sub literal_data { + my ($content) = @_; + print STDOUT "data ", bytes::length($content), "\n", $content; +} + +sub mw_capabilities { + # Revisions are imported to the private namespace + # refs/mediawiki/$remotename/ by the helper and fetched into + # refs/remotes/$remotename later by fetch. + print STDOUT "refspec refs/heads/*:refs/mediawiki/$remotename/*\n"; + print STDOUT "import\n"; + print STDOUT "list\n"; + print STDOUT "option\n"; + print STDOUT "push\n"; + print STDOUT "\n"; +} + +sub mw_list { + # MediaWiki do not have branches, we consider one branch arbitrarily + # called master + print STDOUT "? refs/heads/master\n"; + print STDOUT '@'."refs/heads/master HEAD\n"; + print STDOUT "\n"; + +} + +sub mw_option { + print STDOUT "unsupported\n"; +} + +sub mw_import { + my @wiki_name = split(/:\/\//,$url); + my $wiki_name = $wiki_name[1]; + + my $mediawiki = MediaWiki::API->new; + $mediawiki->{config}->{api_url} = "$url/api.php"; + + my @pages = get_pages(); + + my @revisions; + print STDERR "Searching revisions...\n"; + my $fetch_from = get_last_local_revision() + 1; + if ($fetch_from == 1) { + print STDERR ", fetching from beginning\n"; + } else { + print STDERR ", fetching from here\n"; + } + my $n = 1; + foreach my $page (@pages) { + my $id = $page->{pageid}; + + print STDERR "$n/", scalar(@pages), ": ". $page->{title}."\n"; + $n++; + + my $query = { + action => 'query', + prop => 'revisions', + rvprop => 'ids', + rvdir => 'newer', + rvstartid => $fetch_from, + rvlimit => 500, + pageids => $id, + }; + + my $revnum = 0; + # Get 500 revisions at a time due to the mediawiki api limit + while (1) { + my $result = $mediawiki->api($query); + + # Parse each of those 500 revisions + foreach my $revision (@{$result->{query}->{pages}->{$id}->{revisions}}) { + my $page_rev_ids; + $page_rev_ids->{pageid} = $page->{pageid}; + $page_rev_ids->{revid} = $revision->{revid}; + push (@revisions, $page_rev_ids); + $revnum++; + } + last unless $result->{'query-continue'}; + $query->{rvstartid} = $result->{'query-continue'}->{revisions}->{rvstartid}; + } + print STDERR " Found ", $revnum, " revision(s).\n"; + } + + # Creation of the fast-import stream + print STDERR "Fetching & writing export data...\n"; + + $n = 0; + my $last_timestamp = 0; #Placeholer in case $rev->timestamp is undefined + + foreach my $pagerevids (sort {$a->{revid} <=> $b->{revid}} @revisions) { + #fetch the content of the pages + my $query = { + action => 'query', + prop => 'revisions', + rvprop => 'content|timestamp|comment|user|ids', + revids => $pagerevids->{revid}, + }; + + my $result = $mediawiki->api($query); + + my $rev = pop(@{$result->{query}->{pages}->{$pagerevids->{pageid}}->{revisions}}); + + $n++; + my $user = $rev->{user} || 'Anonymous'; + + if (!defined($rev->{timestamp})) { + $last_timestamp++; + } else { + $last_timestamp = $rev->{timestamp}; + } + my $dt = DateTime::Format::ISO8601->parse_datetime($last_timestamp); + + my $comment = defined $rev->{comment} ? $rev->{comment} : '*Empty MediaWiki Message*'; + + my $title = $result->{query}->{pages}->{$pagerevids->{pageid}}->{title}; + $title =~ y/ /_/; + #$title = uri_escape($title); #It would be nice to use uri_escape to be cross compatible + #on different file systems handling accentuated characters differently + $title =~ s/\//$slash_replacement/g; + + my $content = $rev->{'*'}; + # This \n is important. This is due to mediawiki's way to handle end of files. + $content .= "\n"; + + print STDERR "$n/", scalar(@revisions), ": Revision #$pagerevids->{revid} of $title\n"; + + print STDOUT "commit refs/mediawiki/$remotename/master\n"; + print STDOUT "mark :$n\n"; + print STDOUT "committer $user <$user\@$wiki_name> ", $dt->epoch, " +0000\n"; + literal_data($comment); + # If it's not a clone, needs to know where to start from + if ($fetch_from != 1 && $n == 1) { + print STDOUT "from refs/mediawiki/$remotename/master^0\n"; + } + print STDOUT "M 644 inline $title.mw\n"; + literal_data($content); + print STDOUT "\n\n"; + + + + + # mediawiki revision number in the git note + if ($fetch_from == 1 && $n == 1) { + print STDOUT "reset refs/notes/mediawiki\n"; + } + print STDOUT "commit refs/notes/mediawiki\n"; + print STDOUT "committer $user <$user\@$wiki_name> ", $dt->epoch, " +0000\n"; + literal_data("note added by git-mediawiki"); + if ($fetch_from != 1 && $n == 1) { + print STDOUT "from refs/notes/mediawiki^0\n"; + } + print STDOUT "N inline :$n\n"; + literal_data("mediawiki_revision: " . $pagerevids->{revid}); + print STDOUT "\n\n"; + } + + if ($fetch_from == 1) { + if ($n != 0) { + print STDOUT "reset $_[0]\n"; #$_[0] contains refs/heads/master + print STDOUT "from :$n\n"; + } else { + 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 + } + } + +} + +sub mw_push { + print STDERR "Push not yet implemented\n"; +} diff --git a/contrib/mw-to-git/git-remote-mediawiki.txt b/contrib/mw-to-git/git-remote-mediawiki.txt new file mode 100644 index 0000000..4d211f5 --- /dev/null +++ b/contrib/mw-to-git/git-remote-mediawiki.txt @@ -0,0 +1,7 @@ +Git-Mediawiki is a project which aims the creation of a gate +between git and mediawiki, allowing git users to push and pull +objects from mediawiki just as one would do with a classic git +repository thanks to remote-helpers. + +For more information, visit the wiki at +https://github.com/Bibzball/Git-Mediawiki/wiki
-- 1.7.4.1