summaryrefslogtreecommitdiff
path: root/contrib/mw-to-git/git-remote-mediawiki.perl
diff options
context:
space:
mode:
Diffstat (limited to 'contrib/mw-to-git/git-remote-mediawiki.perl')
-rwxr-xr-xcontrib/mw-to-git/git-remote-mediawiki.perl103
1 files changed, 27 insertions, 76 deletions
diff --git a/contrib/mw-to-git/git-remote-mediawiki.perl b/contrib/mw-to-git/git-remote-mediawiki.perl
index 71baf8ace8..85d0c42296 100755
--- a/contrib/mw-to-git/git-remote-mediawiki.perl
+++ b/contrib/mw-to-git/git-remote-mediawiki.perl
@@ -14,6 +14,8 @@
use strict;
use MediaWiki::API;
use Git;
+use Git::Mediawiki qw(clean_filename smudge_filename connect_maybe
+ EMPTY HTTP_CODE_OK);
use DateTime::Format::ISO8601;
use warnings;
@@ -23,9 +25,6 @@ binmode STDOUT, ':encoding(UTF-8)';
use URI::Escape;
-# 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
# privileges). Deleted pages are replaced with this content.
use constant DELETED_CONTENT => "[[Category:Deleted]]\n";
@@ -40,8 +39,6 @@ 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*';
-use constant EMPTY => q{};
-
# Number of pages taken into account at once in submodule get_mw_page_list
use constant SLICE_SIZE => 50;
@@ -50,8 +47,6 @@ use constant SLICE_SIZE => 50;
# the number of links to be returned (500 links max).
use constant BATCH_SIZE => 10;
-use constant HTTP_CODE_OK => 200;
-
if (@ARGV != 2) {
exit_error_usage();
}
@@ -199,37 +194,6 @@ sub parse_command {
# MediaWiki API instance, created lazily.
my $mediawiki;
-sub mw_connect_maybe {
- if ($mediawiki) {
- return;
- }
- $mediawiki = MediaWiki::API->new;
- $mediawiki->{config}->{api_url} = "${url}/api.php";
- if ($wiki_login) {
- my %credential = (
- 'url' => $url,
- 'username' => $wiki_login,
- 'password' => $wiki_passwd
- );
- Git::credential(\%credential);
- my $request = {lgname => $credential{username},
- lgpassword => $credential{password},
- lgdomain => $wiki_domain};
- if ($mediawiki->login($request)) {
- Git::credential(\%credential, 'approve');
- print {*STDERR} qq(Logged in mediawiki user "$credential{username}".\n);
- } else {
- print {*STDERR} qq(Failed to log in mediawiki user "$credential{username}" on ${url}\n);
- print {*STDERR} ' (error ' .
- $mediawiki->{error}->{code} . ': ' .
- $mediawiki->{error}->{details} . ")\n";
- Git::credential(\%credential, 'reject');
- exit 1;
- }
- }
- return;
-}
-
sub fatal_mw_error {
my $action = shift;
print STDERR "fatal: could not $action.\n";
@@ -339,7 +303,7 @@ sub get_mw_first_pages {
# Get the list of pages to be fetched according to configuration.
sub get_mw_pages {
- mw_connect_maybe();
+ $mediawiki = connect_maybe($mediawiki, $remotename, $url);
print {*STDERR} "Listing pages on remote wiki...\n";
@@ -529,7 +493,7 @@ sub get_last_local_revision {
# 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();
+ $mediawiki = connect_maybe($mediawiki, $remotename, $url);
my $query = {
action => 'query',
@@ -545,7 +509,7 @@ sub get_last_global_remote_rev {
# Get the last remote revision concerning the tracked pages and the tracked
# categories.
sub get_last_remote_revision {
- mw_connect_maybe();
+ $mediawiki = connect_maybe($mediawiki, $remotename, $url);
my %pages_hash = get_mw_pages();
my @pages = values(%pages_hash);
@@ -601,29 +565,6 @@ sub mediawiki_smudge {
return "${string}\n";
}
-sub mediawiki_clean_filename {
- my $filename = shift;
- $filename =~ s{@{[SLASH_REPLACEMENT]}}{/}g;
- # [, ], |, {, and } are forbidden by MediaWiki, even URL-encoded.
- # Do a variant of URL-encoding, i.e. looks like URL-encoding,
- # but with _ added to prevent MediaWiki from thinking this is
- # an actual special character.
- $filename =~ s/[\[\]\{\}\|]/sprintf("_%%_%x", ord($&))/ge;
- # If we use the uri escape before
- # we should unescape here, before anything
-
- return $filename;
-}
-
-sub mediawiki_smudge_filename {
- my $filename = shift;
- $filename =~ s{/}{@{[SLASH_REPLACEMENT]}}g;
- $filename =~ s/ /_/g;
- # Decode forbidden characters encoded in mediawiki_clean_filename
- $filename =~ s/_%_([0-9a-fA-F][0-9a-fA-F])/sprintf('%c', hex($1))/ge;
- return $filename;
-}
-
sub literal_data {
my ($content) = @_;
print {*STDOUT} 'data ', bytes::length($content), "\n", $content;
@@ -635,9 +576,9 @@ sub literal_data_raw {
my ($content) = @_;
# Avoid confusion between size in bytes and in characters
utf8::downgrade($content);
- binmode {*STDOUT}, ':raw';
+ binmode STDOUT, ':raw';
print {*STDOUT} 'data ', bytes::length($content), "\n", $content;
- binmode {*STDOUT}, ':encoding(UTF-8)';
+ binmode STDOUT, ':encoding(UTF-8)';
return;
}
@@ -681,6 +622,9 @@ sub fetch_mw_revisions_for_page {
rvstartid => $fetch_from,
rvlimit => 500,
pageids => $id,
+
+ # Let MediaWiki know that we support the latest API.
+ continue => '',
};
my $revnum = 0;
@@ -696,8 +640,15 @@ sub fetch_mw_revisions_for_page {
push(@page_revs, $page_rev_ids);
$revnum++;
}
- last if (!$result->{'query-continue'});
- $query->{rvstartid} = $result->{'query-continue'}->{revisions}->{rvstartid};
+
+ if ($result->{'query-continue'}) { # For legacy APIs
+ $query->{rvstartid} = $result->{'query-continue'}->{revisions}->{rvstartid};
+ } elsif ($result->{continue}) { # For newer APIs
+ $query->{rvstartid} = $result->{continue}->{rvcontinue};
+ $query->{continue} = $result->{continue}->{continue};
+ } else {
+ last;
+ }
}
if ($shallow_import && @page_revs) {
print {*STDERR} " Found 1 revision (shallow import).\n";
@@ -831,7 +782,7 @@ sub mw_import_ref {
return;
}
- mw_connect_maybe();
+ $mediawiki = connect_maybe($mediawiki, $remotename, $url);
print {*STDERR} "Searching revisions...\n";
my $last_local = get_last_local_revision();
@@ -945,7 +896,7 @@ sub mw_import_revids {
my %commit;
$commit{author} = $rev->{user} || 'Anonymous';
$commit{comment} = $rev->{comment} || EMPTY_MESSAGE;
- $commit{title} = mediawiki_smudge_filename($page_title);
+ $commit{title} = smudge_filename($page_title);
$commit{mw_revision} = $rev->{revid};
$commit{content} = mediawiki_smudge($rev->{'*'});
@@ -1006,7 +957,7 @@ sub mw_upload_file {
}
# Deleting and uploading a file requires a priviledged user
if ($file_deleted) {
- mw_connect_maybe();
+ $mediawiki = connect_maybe($mediawiki, $remotename, $url);
my $query = {
action => 'delete',
title => $path,
@@ -1022,7 +973,7 @@ sub mw_upload_file {
# Don't let perl try to interpret file content as UTF-8 => use "raw"
my $content = run_git("cat-file blob ${new_sha1}", 'raw');
if ($content ne EMPTY) {
- mw_connect_maybe();
+ $mediawiki = connect_maybe($mediawiki, $remotename, $url);
$mediawiki->{config}->{upload_url} =
"${url}/index.php/Special:Upload";
$mediawiki->edit({
@@ -1070,7 +1021,7 @@ sub mw_push_file {
my $old_sha1 = $diff_info_split[2];
my $page_created = ($old_sha1 eq NULL_SHA1);
my $page_deleted = ($new_sha1 eq NULL_SHA1);
- $complete_file_name = mediawiki_clean_filename($complete_file_name);
+ $complete_file_name = clean_filename($complete_file_name);
my ($title, $extension) = $complete_file_name =~ /^(.*)\.([^\.]*)$/;
if (!defined($extension)) {
@@ -1093,7 +1044,7 @@ sub mw_push_file {
$file_content = run_git("cat-file blob ${new_sha1}");
}
- mw_connect_maybe();
+ $mediawiki = connect_maybe($mediawiki, $remotename, $url);
my $result = $mediawiki->edit( {
action => 'edit',
@@ -1279,7 +1230,7 @@ sub mw_push_revision {
}
sub get_allowed_file_extensions {
- mw_connect_maybe();
+ $mediawiki = connect_maybe($mediawiki, $remotename, $url);
my $query = {
action => 'query',
@@ -1303,7 +1254,7 @@ my %cached_mw_namespace_id;
# Return MediaWiki id for a canonical namespace name.
# Ex.: "File", "Project".
sub get_mw_namespace_id {
- mw_connect_maybe();
+ $mediawiki = connect_maybe($mediawiki, $remotename, $url);
my $name = shift;
if (!exists $namespace_id{$name}) {