git-svn: refuse to dcommit non-UTF-8 messages

...without i18n.commitencoding set in the config.

SVN tries to store all commit messages in UTF-8, however it is
up to the job of the clients to enforce this rule.  SVN servers
themselves do not always enforce this; allowing clients to
commit malformed UTF-8 messages and break repositories.

So git-svn will enforce this and tell the user to set
i18n.commitencoding when a git commit is is not in UTF-8.

Signed-off-by: Eric Wong <normalperson@yhbt.net>

2 files changed, 61 insertions, 3 deletions

diff --git a/git-svn.perl b/git-svn.perl
index a70c7d7b2c..33017974d0 100755
--- a/git-svn.perl
+++ b/git-svn.perl
@@ -1178,16 +1178,27 @@ sub get_commit_entry {
 	}
 	rename $commit_editmsg, $commit_msg or croak $!;
 	{
+		require Encode;
 		# 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');
+		my $enc = Git::config('i18n.commitencoding') || 'UTF-8';
+		my $msg = $log_entry{log};
+
+		eval { $msg = Encode::decode($enc, $msg, 1) };
+		if ($@) {
+			die "Could not decode as $enc:\n", $msg,
+			    "\nPerhaps you need to set i18n.commitencoding\n";
 		}
+
+		eval { $msg = Encode::encode('UTF-8', $msg, 1) };
+		die "Could not encode as UTF-8:\n$msg\n" if $@;
+
+		$log_entry{log} = $msg;
+
 		close $log_fh or croak $!;
 	}
 	unlink $commit_msg;
diff --git a/t/t9139-git-svn-non-utf8-commitencoding.sh b/t/t9139-git-svn-non-utf8-commitencoding.sh
new file mode 100755
index 0000000000..2b1db97337
--- /dev/null
+++ b/t/t9139-git-svn-non-utf8-commitencoding.sh
@@ -0,0 +1,47 @@
+#!/bin/sh
+#
+# Copyright (c) 2009 Eric Wong
+
+test_description='git svn refuses to dcommit non-UTF8 messages'
+
+. ./lib-git-svn.sh
+
+# ISO-2022-JP can pass for valid UTF-8, so skipping that in this test
+
+for H in ISO-8859-1 EUCJP
+do
+	test_expect_success "$H setup" '
+		mkdir $H &&
+		svn_cmd import -m "$H test" $H "$svnrepo"/$H &&
+		git svn clone "$svnrepo"/$H $H
+	'
+done
+
+for H in ISO-8859-1 EUCJP
+do
+	test_expect_success "$H commit on git side" '
+	(
+		cd $H &&
+		git config i18n.commitencoding $H &&
+		git checkout -b t refs/remotes/git-svn &&
+		echo $H >F &&
+		git add F &&
+		git commit -a -F "$TEST_DIRECTORY"/t3900/$H.txt &&
+		E=$(git cat-file commit HEAD | sed -ne "s/^encoding //p") &&
+		test "z$E" = "z$H"
+	)
+	'
+done
+
+for H in ISO-8859-1 EUCJP
+do
+	test_expect_success "$H dcommit to svn" '
+	(
+		cd $H &&
+		git config --unset i18n.commitencoding &&
+		! git svn dcommit
+	)
+	'
+done
+
+test_done