#! /usr/bin/perl
# Copyright (C) 2011
# Jérémie Nikaes <jeremie.nikaes@ensimag.imag.fr>
# Arnaud Lacurie <arnaud.lacurie@ensimag.imag.fr>
# Claire Fousse <claire.fousse@ensimag.imag.fr>
# David Amouyal <david.amouyal@ensimag.imag.fr>
# Matthieu Moy <matthieu.moy@grenoble-inp.fr>
# License: GPL v2 or later
# Gateway between Git and MediaWiki.
# https://github.com/Bibzball/Git-Mediawiki/wiki
#
# Known limitations:
#
# - Several strategies are provided to fetch modifications from the
# wiki, but no automatic heuristics is provided, the user has
# to understand and chose which strategy is appropriate for him.
#
# - Git renames could be turned into MediaWiki renames (see TODO
# below)
#
# - No way to import "one page, and all pages included in it"
#
# - Multiple remote MediaWikis have not been very well tested.
use strict;
use MediaWiki::API;
use DateTime::Format::ISO8601;
# 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
use constant SLASH_REPLACEMENT => "%2F";
# It's not always possible to delete pages (may require some
# priviledges). Deleted pages are replaced with this content.
use constant DELETED_CONTENT => "[[Category:Deleted]]\n";
# It's not possible to create empty pages. New empty files in Git are
# sent with this content instead.
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];
# Accept both space-separated and multiple keys in config file.
# Spaces should be written as _ anyway because we'll use chomp.
my @tracked_pages = split(/[ \n]/, run_git("config --get-all remote.". $remotename .".pages"));
chomp(@tracked_pages);
# Just like @tracked_pages, but for MediaWiki categories.
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");
# 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);
chomp($wiki_passwd);
chomp($wiki_domain);
# Import only last revisions (both for clone and fetch)
my $shallow_import = run_git("config --get --bool remote.". $remotename .".shallow");
chomp($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
# remote.<remotename>.dumbPush.
#
# This means the user will have to re-import the just-pushed
# revisions. On the other hand, this means that the Git revisions
# corresponding to MediaWiki revisions are all imported from the wiki,
# regardless of whether they were initially created in Git or from the
# web interface, hence all users will get the same history (i.e. if
# the push from Git to MediaWiki loses some information, everybody
# will get the history with information lost). If the import is
# deterministic, this means everybody gets the same sha1 for each
# MediaWiki revision.
my $dumb_push = run_git("config --get --bool remote.$remotename.dumbPush");
unless ($dumb_push) {
$dumb_push = run_git("config --get --bool mediawiki.dumbPush");
|