Merge branch 'mm/mediawiki-tests'

* mm/mediawiki-tests:
  git-remote-mediawiki: be more defensive when requests fail
  git-remote-mediawiki: more efficient 'pull' in the best case
  git-remote-mediawiki: extract revision-importing loop to a function
  git-remote-mediawiki: refactor loop over revision ids
  git-remote-mediawiki: change return type of get_mw_pages
  git-remote-mediawiki (t9363): test 'File:' import and export
  git-remote-mediawiki: support for uploading file in test environment
  git-remote-mediawiki (t9362): test git-remote-mediawiki with UTF8 characters
  git-remote-mediawiki (t9361): test git-remote-mediawiki pull and push
  git-remote-mediawiki (t9360): test git-remote-mediawiki clone
  git-remote-mediawiki: test environment of git-remote-mediawiki
  git-remote-mediawiki: scripts to install, delete and clear a MediaWiki
This commit is contained in:
Junio C Hamano
2012-07-13 15:37:46 -07:00
18 changed files with 2260 additions and 26 deletions

View File

@ -13,12 +13,9 @@
#
# Known limitations:
#
# - 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.
# - 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)
@ -84,6 +81,21 @@ 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
@ -374,7 +386,7 @@ sub get_mw_pages {
get_all_mediafiles(\%pages);
}
}
return values(%pages);
return %pages;
}
# usage: $out = run_git("command args");
@ -528,10 +540,31 @@ 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;
@ -797,8 +830,6 @@ 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;
@ -807,35 +838,106 @@ 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) {
# 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 $pagerevid";
}
if (!defined($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];
# Count page even if we skip it, since we display
# $n/$total and $total includes skipped pages.
$n++;
my $page_title = $result->{query}->{pages}->{$pagerevid->{pageid}}->{title};
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*';
$commit{title} = mediawiki_smudge_filename($page_title);
$commit{mw_revision} = $pagerevid->{revid};
$commit{mw_revision} = $rev->{revid};
$commit{content} = mediawiki_smudge($rev->{'*'});
if (!defined($rev->{timestamp})) {
@ -854,16 +956,11 @@ sub mw_import_ref {
# If this is a revision of the media page for new version
# of a file do one common commit for both file and media page.
# Else do commit only for that page.
print STDERR "$n/", scalar(@revisions), ": Revision #$pagerevid->{revid} of $commit{title}\n";
import_file_revision(\%commit, ($fetch_from == 1), $n, \%mediafile);
print STDERR "$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 {