[PATCH 4/5] git-remote-mediawiki: split get_mw_pages into smaller functions
Signed-off-by: Matthieu Moy <Matthieu.Moy@imag.fr>
---
contrib/mw-to-git/git-remote-mediawiki | 106 +++++++++++++++++++--------------
1 file changed, 62 insertions(+), 44 deletions(-)
diff --git a/contrib/mw-to-git/git-remote-mediawiki b/contrib/mw-to-git/git-remote-mediawiki
index 3405772..76d8824 100755
--- a/contrib/mw-to-git/git-remote-mediawiki
+++ b/contrib/mw-to-git/git-remote-mediawiki
@@ -258,6 +258,64 @@ 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;
+ while (@some_pages) {
+ my $last = 50;
+ if ($#some_pages < $last) {
+ $last = $#some_pages;
+ }
+ my @slice = @some_pages[0..$last];
+ get_mw_first_pages(\@slice, $pages);
+ @some_pages = @some_pages[51..$#some_pages];
+ }
+}
+
+sub get_mw_tracked_categories {
+ my $pages = shift;
+ foreach my $category (@tracked_categories) {
+ if (index($category, ':') < 0) {
+ # Mediawiki requires the Category
+ # prefix, but let's not force the user
+ # to specify it.
+ $category = "Category:" . $category;
+ }
+ my $mw_pages = $mediawiki->list( {
+ action => 'query',
+ list => 'categorymembers',
+ cmtitle => $category,
+ cmlimit => 'max' } )
+ || die $mediawiki->{error}->{code} . ': '
+ . $mediawiki->{error}->{details};
+ foreach my $page (@{$mw_pages}) {
+ $pages->{$page->{title}} = $page;
+ }
+ }
+}
+
+sub get_mw_all_pages {
+ my $pages = shift;
+ # No user-provided list, get the list of pages from the API.
+ my $mw_pages = $mediawiki->list({
+ action => 'query',
+ list => 'allpages',
+ aplimit => 'max'
+ });
+ if (!defined($mw_pages)) {
+ print STDERR "fatal: could not get the list of wiki pages.\n";
+ 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 1;
+ }
+ foreach my $page (@{$mw_pages}) {
+ $pages->{$page->{title}} = $page;
+ }
+}
+
+# queries the wiki for a set of pages. Meant to be used within a loop
+# querying the wiki for slices of page list.
sub get_mw_first_pages {
my $some_pages = shift;
my @some_pages = @{$some_pages};
@@ -286,6 +344,7 @@ sub get_mw_first_pages {
}
}
+# Get the list of pages to be fetched according to configuration.
sub get_mw_pages {
mw_connect_maybe();
@@ -295,55 +354,14 @@ sub get_mw_pages {
$user_defined = 1;
# The user provided a list of pages titles, but we
# still need to query the API to get the page IDs.
-
- my @some_pages = @tracked_pages;
- while (@some_pages) {
- my $last = 50;
- if ($#some_pages < $last) {
- $last = $#some_pages;
- }
- my @slice = @some_pages[0..$last];
- get_mw_first_pages(\@slice, \%pages);
- @some_pages = @some_pages[51..$#some_pages];
- }
+ get_mw_tracked_pages(\%pages);
}
if (@tracked_categories) {
$user_defined = 1;
- foreach my $category (@tracked_categories) {
- if (index($category, ':') < 0) {
- # Mediawiki requires the Category
- # prefix, but let's not force the user
- # to specify it.
- $category = "Category:" . $category;
- }
- my $mw_pages = $mediawiki->list( {
- action => 'query',
- list => 'categorymembers',
- cmtitle => $category,
- cmlimit => 'max' } )
- || die $mediawiki->{error}->{code} . ': ' . $mediawiki->{error}->{details};
- foreach my $page (@{$mw_pages}) {
- $pages{$page->{title}} = $page;
- }
- }
+ get_mw_tracked_categories(\%pages);
}
if (!$user_defined) {
- # No user-provided list, get the list of pages from
- # the API.
- my $mw_pages = $mediawiki->list({
- action => 'query',
- list => 'allpages',
- aplimit => 500,
- });
- if (!defined($mw_pages)) {
- print STDERR "fatal: could not get the list of wiki pages.\n";
- 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 1;
- }
- foreach my $page (@{$mw_pages}) {
- $pages{$page->{title}} = $page;
- }
+ get_mw_all_pages(\%pages);
}
return values(%pages);
}
--
1.7.11.5.g0c7e058.dirty
Matthieu Moy <matthieu.moy@imag.fr>