Implements 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
Remote helpers have been used in order to be as transparent as possible
to the git user.
Mediawiki revisions are downloaded through the Mediawiki API and then
fast-imported 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.
Signed-off-by: JÃrÃmie Nikaes <jeremie.nikaes@xxxxxxxxxxxxxxx>
Signed-off-by: Arnaud Lacurie <arnaud.lacurie@xxxxxxxxxxxxxxx>
Signed-off-by: Claire Fousse <claire.fousse@xxxxxxxxxxxxxxx>
Signed-off-by: David Amouyal <david.amouyal@xxxxxxxxxxxxxxx>
Signed-off-by: Matthieu Moy <matthieu.moy@xxxxxxxxxxxxxxx>
Signed-off-by: Sylvain Boulmà <sylvain.boulme@xxxxxxx>
---
contrib/mw-to-git/git-remote-mediawiki | 252 ++++++++++++++++++++++++++++
contrib/mw-to-git/git-remote-mediawiki.txt | 7 +
2 files changed, 259 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..f20edc4
--- /dev/null
+++ b/contrib/mw-to-git/git-remote-mediawiki
@@ -0,0 +1,252 @@
+#! /usr/bin/perl
+
+use strict;
+use Switch;
+use MediaWiki::API;
+use Storable qw(freeze thaw);
+use DateTime::Format::ISO8601;
+use Encode qw(encode_utf8);
+
+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 "" && $cmd[2] eq "") {
+ mw_import($url);
+ } else {
+ $loop = 0;
+ }
+ }
+ case "option" {
+ mw_option($cmd[1],$cmd[2]);
+ }
+ case "push" {
+ #check the pattern +<src>:<dist>
+ my @pushargs = split(/:/,$cmd[1]);
+ if ($pushargs[1] ne "" && $pushargs[2] eq ""
+ && (substr($pushargs[0],0,1) eq "+")) {
+ mw_push(substr($pushargs[0],1),$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 notes show $commit_sha1 2>/dev/null`;
+ my @note_info = split(/ /, $note);
+
+ my $lastrevision_number;
+ if (!($note_info[0] eq "mediawiki_revision:")) {
+ print STDERR "No previous mediawiki revision found, fetching from beginning\n";
+ $lastrevision_number = 0;
+ } else {
+ # Notes are formatted : mediawiki_revision: #number
+ $lastrevision_number = $note_info[1];
+ chomp($lastrevision_number);
+ print STDERR "Last mediawiki revision found is $lastrevision_number, fetching from here\n";
+ }
+ return $lastrevision_number;
+}
+
+sub mw_capabilities {
+ # Revisions are imported to the private namespace
+ # refs/mediawiki/$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: '$url' does not appear to be a mediawiki\n";
+ print STDERR "fatal: make sure '$url/api.php' is a valid page\n";
+ exit;
+ }
+
+ my @revisions;
+ print STDERR "Searching revisions...\n";
+ my $fetch_from = get_last_local_revision() + 1;
+ 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 => $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 "\n";
+ }
+ 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 $dt = DateTime::Format::ISO8601->parse_datetime($rev->{timestamp});
+
+ my $comment = defined $rev->{comment} ? $rev->{comment} : '*Empty MediaWiki Message*';
+ my $title = $result->{query}->{pages}->{$pagerevids->{pageid}}->{title};
+ my $content = $rev->{'*'};
+ $title =~ y/ /_/;
+
+ print STDERR "$n/", scalar(@revisions), ": Revision nÂ$pagerevids->{revid} of $title\n";
+
+ print "commit refs/mediawiki/$remotename/master\n";
+ print "mark :$n\n";
+ print "committer $user <$user\@$wiki_name> ", $dt->epoch, " +0000\n";
+ print "data ", bytes::length(encode_utf8($comment)), "\n", 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 $title.wiki\n";
+ print "data ", bytes::length(encode_utf8($content)), "\n", encode_utf8($content);
+ print "\n\n";
+
+
+ # mediawiki revision number in the git note
+ my $note_comment = encode_utf8("note added by git-mediawiki");
+ my $note_comment_length = bytes::length($note_comment);
+ my $note_content = encode_utf8("mediawiki_revision: " . $pagerevids->{revid} . "\n");
+ my $note_content_length = bytes::length($note_content);
+
+ if ($fetch_from == 1 && $n == 1) {
+ print "reset refs/notes/commits\n";
+ }
+ print "commit refs/notes/commits\n";
+ print "committer $user <user\@example.com> ", $dt->epoch, " +0000\n";
+ print "data ", $note_comment_length, "\n", $note_comment;
+ if ($fetch_from != 1 && $n == 1) {
+ print "from refs/notes/commits^0\n";
+ }
+ print "N inline :$n\n";
+ print "data ", $note_content_length, "\n", $note_content;
+ print "\n\n";
+ }
+
+ if ($fetch_from == 1) {
+ if ($n != 0) {
+ print "reset refs/heads/master\n";
+ print "from :$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 \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
--
1.7.5.3.486.gdc5865
--
To unsubscribe from this list: send the line "unsubscribe git" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html