git-remote-mediawiki: fix encoding issue for UTF-8 media files

When a media file contains valid UTF-8, git-remote-mediawiki tried to be
too clever about the encoding, and the call to utf8::downgrade() on the
downloaded content was failing with

  Wide character in subroutine entry at git-remote-mediawiki line 583.

Instead, use $response->decode() to apply decoding linked to the
Content-Encoding: header, and return the content without attempting any
charset decoding.

Signed-off-by: Matthieu Moy <Matthieu.Moy@imag.fr>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

diff --git a/contrib/mw-to-git/git-remote-mediawiki.perl b/contrib/mw-to-git/git-remote-mediawiki.perl
index 3f8d993afaca53024aa75b4118da9ee80e6a6313..8dd74a9a406e9cfd685ea1af3947e4bea4c82f90 100755 (executable)
--- a/contrib/mw-to-git/git-remote-mediawiki.perl
+++ b/contrib/mw-to-git/git-remote-mediawiki.perl
@@ -461,7 +461,12 @@ sub download_mw_mediafile {
 
        my $response = $mediawiki->{ua}->get($download_url);
        if ($response->code == HTTP_CODE_OK) {
-               return $response->decoded_content;
+               # It is tempting to return
+               # $response->decoded_content({charset => "none"}), but
+               # when doing so, utf8::downgrade($content) fails with
+               # "Wide character in subroutine entry".
+               $response->decode();
+               return $response->content();
        } else {
                print {*STDERR} "Error downloading mediafile from :\n";
                print {*STDERR} "URL: ${download_url}\n";

diff --git a/contrib/mw-to-git/t/t9363-mw-to-git-export-import.sh b/contrib/mw-to-git/t/t9363-mw-to-git-export-import.sh
index 5a0373935f1f4b66c4521158e4b3c41508c908ea..3ff3a095670ecdf578dc9f4d51841c102c5a10fd 100755 (executable)
--- a/contrib/mw-to-git/t/t9363-mw-to-git-export-import.sh
+++ b/contrib/mw-to-git/t/t9363-mw-to-git-export-import.sh
@@ -58,6 +58,25 @@ test_expect_success 'git clone works on previously created wiki with media files
        test_cmp mw_dir_clone/Foo.txt mw_dir/Foo.txt
 '
 
+test_expect_success 'git push can upload media (File:) files containing valid UTF-8' '
+       wiki_reset &&
+       git clone mediawiki::'"$WIKI_URL"' mw_dir &&
+       (
+               cd mw_dir &&
+               "$PERL_PATH" -e "print STDOUT \"UTF-8 content: éèàéê€.\";" >Bar.txt &&
+               git add Bar.txt &&
+               git commit -m "add a text file with UTF-8 content" &&
+               git push
+       )
+'
+
+test_expect_success 'git clone works on previously created wiki with media files containing valid UTF-8' '
+       test_when_finished "rm -rf mw_dir mw_dir_clone" &&
+       git clone -c remote.origin.mediaimport=true \
+               mediawiki::'"$WIKI_URL"' mw_dir_clone &&
+       test_cmp mw_dir_clone/Bar.txt mw_dir/Bar.txt
+'
+
 test_expect_success 'git push & pull work with locally renamed media files' '
        wiki_reset &&
        git clone mediawiki::'"$WIKI_URL"' mw_dir &&