From 16fc08e2d86dad152194829d21bc55b2ef0c8fb1 Mon Sep 17 00:00:00 2001 From: Eric Wong Date: Wed, 29 Oct 2008 23:49:26 -0700 Subject: git-svn: respect i18n.commitencoding config SVN itself always stores log messages in the repository as UTF-8. git always stores/retrieves everything as raw binary data with no transformations whatsoever. To interact with SVN, we need to encode log messages as UTF-8 before sending them to SVN, as SVN cannot do it for us. When retrieving log messages from SVN, we also need to (attempt to) reencode the UTF-8 log message back to the user-specified commit encoding. Note, handling i18n.logoutputencoding for "git svn log" also needs to be done in a future change. Also, this change only deals with the encoding of commit messages and nothing else (path names, blob content, ...). In-Reply-To: <8b168cfb0810282014r789ac01dnec51824de1078f0@mail.gmail.com> James North wrote: > Hi, > > I'm using git-svn on a system with ISO-8859-1 encoding. The problem is > when I try to use "git svn dcommit" to send changes to a remote svn > (also ISO-8859-1). > > Seems like git-svn is sending commit messages with utf-8 (just a > guessing...) and they look bad on the remote svn log. E.g. "Ca?\241a > de cami?\243n" > > I have tried using i18n.commitencoding=ISO-8859-1 as suggested by the > warning when doing "git svn dcommit" but messages still are sent with > wrong encoding. Signed-off-by: Eric Wong --- git-svn.perl | 24 +++++++++++++++++++++--- 1 file changed, 21 insertions(+), 3 deletions(-) (limited to 'git-svn.perl') diff --git a/git-svn.perl b/git-svn.perl index 70a664ca0b..2abb7b5937 100755 --- a/git-svn.perl +++ b/git-svn.perl @@ -1136,9 +1136,19 @@ sub get_commit_entry { system($editor, $commit_editmsg); } rename $commit_editmsg, $commit_msg or croak $!; - open $log_fh, '<', $commit_msg or croak $!; - { local $/; chomp($log_entry{log} = <$log_fh>); } - close $log_fh or croak $!; + { + # SVN requires messages to be UTF-8 when entering the repo + local $/; + open $log_fh, '<', $commit_msg or croak $!; + binmode $log_fh; + chomp($log_entry{log} = <$log_fh>); + + if (my $enc = Git::config('i18n.commitencoding')) { + require Encode; + Encode::from_to($log_entry{log}, $enc, 'UTF-8'); + } + close $log_fh or croak $!; + } unlink $commit_msg; \%log_entry; } @@ -2273,6 +2283,14 @@ sub do_git_commit { } defined(my $pid = open3(my $msg_fh, my $out_fh, '>&STDERR', @exec)) or croak $!; + binmode $msg_fh; + + # we always get UTF-8 from SVN, but we may want our commits in + # a different encoding. + if (my $enc = Git::config('i18n.commitencoding')) { + require Encode; + Encode::from_to($log_entry->{log}, 'UTF-8', $enc); + } print $msg_fh $log_entry->{log} or croak $!; restore_commit_header_env($old_env); unless ($self->no_metadata) { -- cgit v1.2.1