[PATCH] Add a remote helper to interact with mediawiki, pull & clone handled

[Jeremie Nikaes <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 pull

You need the following packages installed (available on common
repositories):
      libmediawiki-api-perl
      libdatetime-format-iso8601-perl

Use 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 in case.

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>
---
 contrib/mw-to-git/git-remote-mediawiki     |  306 ++++++++++++++++++++++++++++
 contrib/mw-to-git/git-remote-mediawiki.txt |    7 +
 2 files changed, 313 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..9db64c2
--- /dev/null
+++ b/contrib/mw-to-git/git-remote-mediawiki
@@ -0,0 +1,306 @@
+#! /usr/bin/perl
+
+use strict;
+use Switch;
+use MediaWiki::API;
+use Storable qw(freeze thaw);
+use DateTime::Format::ISO8601;
+use Encode qw(encode_utf8);
+
+# Mediawiki filenames can contain forward slashes. This variable decides by which pattern they should be replaced
+my $slash_replacement = "<slash>";
+
+my $remotename = $ARGV[0];
+my $url = $ARGV[1];
+
+print STDERR "$url\n";
+
+# commands parser
+my $loop = 1;
+my $entry;
+my @cmd;
+while ($loop) {
+	$| = 1; #flush STDOUT
+	$entry = <STDIN>;
+	print STDERR $entry;
+	chomp($entry);
+	@cmd = undef;
+	@cmd = split(/ /,$entry);
+	switch ($cmd[0]) {
+		case "capabilities" {
+			if ($cmd[1] eq "") {
+				mw_capabilities();
+			} else {
+			       $loop = 0;
+			}
+		}
+		case "list" {
+			if ($cmd[2] eq "") {
+				mw_list($cmd[1]);
+			} else {
+			       $loop = 0;
+			}
+		}
+		case "import" {
+			if ($cmd[1] ne "" && $cmd[2] eq "") {
+				mw_import($cmd[1]);
+			} 
+		}
+		case "option" {
+			if ($cmd[1] ne "" && $cmd[2] ne "" && $cmd[3] eq "") {
+				mw_option($cmd[1],$cmd[2]);
+			} 
+		}
+		case "push" {
+			#check the pattern <src>:<dst>
+			my @pushargs = split(/:/,$cmd[1]);
+			if ($pushargs[1] ne "" && $pushargs[2] eq "") {
+				mw_push($pushargs[0],$pushargs[1]);
+			} else {
+			       $loop = 0;
+			}
+		} else {
+			$loop = 0;
+		}
+	}
+	close(FILE);
+}
+
+########################## Functions ##############################
+
+sub get_last_local_revision {
+	# Get last commit sha1
+	my $commit_sha1 = `git rev-parse refs/mediawiki/$remotename/master 2>/dev/null`;
+
+	# Get note regarding that commit
+	chomp($commit_sha1);
+	my $note = `git log --notes=mediawiki 2>/dev/null | grep "mediawiki_revision: " | sed -n 1p`;
+	$note =~ s/^\s+//; #left trim of note 
+	my @note_info = split(/ /, $note);
+
+	my $lastrevision_number;
+	if (!($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 = $mediawiki->list({
+		action => 'query',
+		list => 'allpages',
+		aplimit => 500,
+	});
+
+	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 "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 STDERR "not yet implemented \n";
+	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 = $mediawiki->list({
+		action => 'query',
+		list => 'allpages',
+		aplimit => 500,
+	});
+	if ($pages == undef) {
+		print STDERR "fatal: '$url' does not appear to be a mediawiki\n";
+		exit;
+	}
+
+	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;
+	my $last_timestamp = 0;
+	foreach my $page (@$pages) {
+		my $id = $page->{pageid};
+
+		print STDERR "$n/", scalar(@$pages), ": ". encode_utf8($page->{title})."\n";
+		$n++;
+
+		my $query = {
+			action => 'query',
+			prop => 'revisions',
+			rvprop => 'ids',
+			rvdir => 'newer',
+			rvstartid => $fetch_from,
+			rvlimit => 500,
+			pageids => $page->{pageid},
+		};
+
+		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";
+	binmode STDOUT, ':binary';
+	$n = 0;
+
+	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';
+		my $dt;
+
+		# This has to be verified, haven't been able to reproduce the scenario
+		if ($rev->{timestamp} != undef) {
+			$dt = DateTime::Format::ISO8601->parse_datetime($rev->{timestamp});
+		} else {
+			$dt = $last_timestamp + 1;
+		}
+		$last_timestamp = $dt;
+
+
+		my $comment = defined $rev->{comment} ? $rev->{comment} : '*Empty MediaWiki Message*';
+		my $title = encode_utf8($result->{query}->{pages}->{$pagerevids->{pageid}}->{title});
+		my $content = $rev->{'*'};
+		
+		$title =~ y/ /_/;
+		$title =~ s/\//$slash_replacement/g;
+
+		print STDERR "$n/", scalar(@revisions), ": Revision n°$pagerevids->{revid} of $title\n";
+
+		print "commit refs/mediawiki/$remotename/master\n";
+		print "mark :$n\n";
+		print "committer $user <$user\@$wiki_name> ", $dt->epoch, " +0000\n";
+		literal_data(encode_utf8($comment));
+		# If it's not a clone, needs to know where to start from
+		if ($fetch_from != 1 && $n == 1) {
+			print "from refs/mediawiki/$remotename/master^0\n";
+		}
+		print "M 644 inline $title.mw\n";
+		literal_data(encode_utf8($content));
+		print "\n\n";
+
+
+		# mediawiki revision number in the git note
+		if ($fetch_from == 1 && $n == 1) {
+			print "reset refs/notes/mediawiki\n";
+		}
+		print "commit refs/notes/mediawiki\n";
+		print "committer $user <$user\@$wiki_name> ", $dt->epoch, " +0000\n";
+		literal_data(encode_utf8("note added by git-mediawiki"));
+		if ($fetch_from != 1 && $n == 1) {
+			print "from refs/notes/mediawiki^0\n";
+		}
+		print "N inline :$n\n";
+		literal_data(encode_utf8("mediawiki_revision: " . $pagerevids->{revid}));
+		print "\n\n";
+	}
+
+	if ($fetch_from == 1) {
+		if ($n != 0) {
+			print "reset $_[0]\n"; #$_[0] contains refs/heads/master
+			print "from :$n\n";
+		} else {
+			print STDERR "You appear to have cloned an empty mediawiki\n";
+			#What do we have to do here ? If nothing is done, an error is thrown saying that
+			#HEAD is refering to unknown object 0000000000000000000
+		}
+	}
+
+}
+
+sub mw_push {
+
+	print STDERR "Not yet implemented";
+	print "\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