Matthieu Moy <Matthieu.Moy@xxxxxxx> writes:
> This is meant to replace commit 6a9e55b0fc5df40 in branch
> mm/mediawiki-file-attachments in pu.
Bad timing for our mails to cross; it is already on 'next'.
Would the following be a good "incremental update" on top of the
named commit?
-- >8 --
From: Matthieu Moy <Matthieu.Moy@xxxxxxx>
Date: Wed, 4 Jul 2012 14:53:36 +0200
Subject: [PATCH] git-remote-mediawiki: improve support for non-English Wikis
Mediafiles can live in namespaces with names different from Image
and File. While at it, rework the code to make it simpler and easier
to read.
Signed-off-by: Matthieu Moy <Matthieu.Moy@xxxxxxx>
Signed-off-by: Junio C Hamano <gitster@xxxxxxxxx>
---
contrib/mw-to-git/git-remote-mediawiki | 140 ++++++++++++++-------------------
1 file changed, 61 insertions(+), 79 deletions(-)
diff --git a/contrib/mw-to-git/git-remote-mediawiki b/contrib/mw-to-git/git-remote-mediawiki
index 76b78bc..063a978 100755
--- a/contrib/mw-to-git/git-remote-mediawiki
+++ b/contrib/mw-to-git/git-remote-mediawiki
@@ -33,7 +33,6 @@
use strict;
use MediaWiki::API;
use DateTime::Format::ISO8601;
-use FileHandle;
# By default, use UTF-8 to communicate with Git and the user
binmode STDERR, ":utf8";
@@ -90,9 +89,6 @@ my $shallow_import = run_git("config --get --bool remote.". $remotename .".shall
chomp($shallow_import);
$shallow_import = ($shallow_import eq "true");
-# Cache for MediaWiki namespace ids.
-my %namespace_id;
-
# Dumb push: don't update notes and mediawiki ref to reflect the last push.
#
# Configurable with mediawiki.dumbPush, or per-remote with
@@ -267,7 +263,13 @@ sub mw_connect_maybe {
## Functions for listing pages on the remote wiki
sub get_mw_tracked_pages {
my $pages = shift;
- my @some_pages = @tracked_pages;
+ get_mw_page_list(\@tracked_pages, $pages);
+}
+
+sub get_mw_page_list {
+ my $page_list = shift;
+ my $pages = shift;
+ my @some_pages = @$page_list;
while (@some_pages) {
my $last = 50;
if ($#some_pages < $last) {
@@ -443,17 +445,17 @@ sub get_linked_mediafiles {
my $result = $mediawiki->api($query);
while (my ($id, $page) = each(%{$result->{query}->{pages}})) {
- my @titles;
+ my @media_titles;
if (defined($page->{links})) {
my @link_titles = map $_->{title}, @{$page->{links}};
- push(@titles, @link_titles);
+ push(@media_titles, @link_titles);
}
if (defined($page->{images})) {
my @image_titles = map $_->{title}, @{$page->{images}};
- push(@titles, @image_titles);
+ push(@media_titles, @image_titles);
}
- if (@titles) {
- get_mw_first_pages(\@titles, \%{$pages});
+ if (@media_titles) {
+ get_mw_page_list(\@media_titles, $pages);
}
}
@@ -463,16 +465,16 @@ sub get_linked_mediafiles {
sub get_mw_mediafile_for_page_revision {
# Name of the file on Wiki, with the prefix.
- my $mw_filename = shift;
+ my $filename = shift;
my $timestamp = shift;
my %mediafile;
- # Search if on MediaWiki exists a media file with given
- # timestamp. In that case download the file.
+ # Search if on a media file with given timestamp exists on
+ # MediaWiki. In that case download the file.
my $query = {
action => 'query',
prop => 'imageinfo',
- titles => $mw_filename,
+ titles => "File:" . $filename,
iistart => $timestamp,
iiend => $timestamp,
iiprop => 'timestamp|archivename|url',
@@ -480,62 +482,33 @@ sub get_mw_mediafile_for_page_revision {
};
my $result = $mediawiki->api($query);
- my ($fileid, $file) = each ( %{$result->{query}->{pages}} );
+ my ($fileid, $file) = each( %{$result->{query}->{pages}} );
# If not defined it means there is no revision of the file for
# given timestamp.
if (defined($file->{imageinfo})) {
- # Get real name of media file.
- my $filename;
- if (index($mw_filename, 'File:') == 0) {
- $filename = substr $mw_filename, 5;
- } else {
- $filename = substr $mw_filename, 6;
- }
$mediafile{title} = $filename;
my $fileinfo = pop(@{$file->{imageinfo}});
$mediafile{timestamp} = $fileinfo->{timestamp};
- # If this is an old version of the file, the file has to be
- # obtained from the archive. Otherwise it can be downloaded
- # by MediaWiki API download() function.
- if (defined($fileinfo->{archivename})) {
- $mediafile{content} = download_mw_mediafile_from_archive($fileinfo->{url});
- } else {
- $mediafile{content} = download_mw_mediafile($mw_filename);
- }
+ # Mediawiki::API's download function doesn't support https URLs
+ # and can't download old versions of files.
+ print STDERR "\tDownloading file $mediafile{title}, version $mediafile{timestamp}\n";
+ $mediafile{content} = download_mw_mediafile($fileinfo->{url});
}
return %mediafile;
}
-sub download_mw_mediafile_from_archive {
+sub download_mw_mediafile {
my $url = shift;
- my $file;
- my $ua = LWP::UserAgent->new;
- my $response = $ua->get($url);
- if ($response->code) {
- $file = $response->decoded_content;
+ my $response = $mediawiki->{ua}->get($url);
+ if ($response->code == 200) {
+ return $response->decoded_content;
} else {
- print STDERR "Error downloading a file from archive.\n";
- }
-
- return $file;
-}
-
-sub download_mw_mediafile {
- my $filename = shift;
-
- $mediawiki->{config}->{files_url} = $url;
-
- my $file_content = $mediawiki->download( { title => $filename } );
- if (!defined($file_content)) {
- print STDERR "\tFile \'$filename\' could not be downloaded.\n";
- exit 1;
- } elsif ($file_content eq "") {
- print STDERR "\tFile \'$filename\' does not exist on the wiki.\n";
+ print STDERR "Error downloading mediafile from :\n";
+ print STDERR "URL: $url\n";
+ print STDERR "Server response: " . $response->code . " " . $response->message . "\n";
exit 1;
- } else {
- return $file_content;
}
}
@@ -878,24 +851,16 @@ sub mw_import_ref {
$commit{date} = DateTime::Format::ISO8601->parse_datetime($last_timestamp);
# Differentiates classic pages and media files.
- my @prefix = split(":", $page_title);
-
+ my ($namespace, $filename) = $page_title =~ /^([^:]*):(.*)$/;
my %mediafile;
- if ($prefix[0] eq "File" || $prefix[0] eq "Image") {
- # The name of the file is the same as the media page.
- my $filename = $page_title;
+ if ($namespace && get_mw_namespace_id($namespace) == get_mw_namespace_id("File")) {
%mediafile = get_mw_mediafile_for_page_revision($filename, $rev->{timestamp});
}
# If this is a revision of the media page for new version
# of a file do one common commit for both file and media page.
# Else do commit only for that page.
print STDERR "$n/", scalar(@revisions), ": Revision #$pagerevid->{revid} of $commit{title}\n";
- if (%mediafile) {
- print STDERR "\tDownloading file $mediafile{title}, version $mediafile{timestamp}\n";
- import_file_revision(\%commit, ($fetch_from == 1), $n, \%mediafile);
- } else {
- import_file_revision(\%commit, ($fetch_from == 1), $n);
- }
+ import_file_revision(\%commit, ($fetch_from == 1), $n, \%mediafile);
}
if ($fetch_from == 1 && $n == 0) {
@@ -1201,28 +1166,35 @@ sub get_allowed_file_extensions {
return %hashFile;
}
+# In memory cache for MediaWiki namespace ids.
+my %namespace_id;
+
+# Namespaces whose id is cached in the configuration file
+# (to avoid duplicates)
+my %cached_mw_namespace_id;
+
# Return MediaWiki id for a canonical namespace name.
# Ex.: "File", "Project".
-# Looks for the namespace id in the local configuration
-# variables, if it is not found asks MW API.
sub get_mw_namespace_id {
mw_connect_maybe();
my $name = shift;
if (!exists $namespace_id{$name}) {
# Look at configuration file, if the record for that namespace is
- # already stored. Namespaces are stored in form:
+ # already cached. Namespaces are stored in form:
# "Name_of_namespace:Id_namespace", ex.: "File:6".
my @temp = split(/[ \n]/, run_git("config --get-all remote."
- . $remotename .".namespaces"));
+ . $remotename .".namespaceCache"));
chomp(@temp);
foreach my $ns (@temp) {
- my ($n, $s) = split(/:/, $ns);
- $namespace_id{$n} = $s;
+ my ($n, $id) = split(/:/, $ns);
+ $namespace_id{$n} = $id;
+ $cached_mw_namespace_id{$n} = 1;
}
}
if (!exists $namespace_id{$name}) {
+ print STDERR "Namespace $name not found in cache, querying the wiki ...\n";
# NS not found => get namespace id from MW and store it in
# configuration file.
my $query = {
@@ -1233,16 +1205,26 @@ sub get_mw_namespace_id {
my $result = $mediawiki->api($query);
while (my ($id, $ns) = each(%{$result->{query}->{namespaces}})) {
- if (defined($ns->{canonical}) && ($ns->{canonical} eq $name)) {
- run_git("config --add remote.". $remotename
- .".namespaces ". $name .":". $ns->{id});
- $namespace_id{$name} = $ns->{id};
- }
+ if (defined($ns->{id}) && defined($ns->{canonical})) {
+ $namespace_id{$ns->{canonical}} = $ns->{id};
+ if ($ns->{'*'}) {
+ # alias (e.g. french Fichier: as alias for canonical File:)
+ $namespace_id{$ns->{'*'}} = $ns->{id};
+ }
+ }
}
}
- if (exists $namespace_id{$name}) {
- return $namespace_id{$name};
+ my $id = $namespace_id{$name};
+
+ if (defined $id) {
+ # Store explicitely requested namespaces on disk
+ if (!exists $cached_mw_namespace_id{$name}) {
+ run_git("config --add remote.". $remotename
+ .".namespaceCache \"". $name .":". $id ."\"");
+ $cached_mw_namespace_id{$name} = 1;
+ }
+ return $id;
} else {
die "No such namespace $name on MediaWiki.";
}
--
1.7.11.1.243.g7462176
--
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