git svn: add an option to recode pathnames

Introduce a new option 'svn.pathnameencoding' that instructs git svn to
recode pathnames to a given encoding.  It can be used by windows users
and by those who work in non-utf8 locales to avoid corrupted file names
with non-ascii characters.

[rp: renamed the option and added manpage documentation]

Signed-off-by: Dmitry Statyvka <dstatyvka@tmsoft-ltd.kiev.ua>
Signed-off-by: Robert Pollak <robert.pollak@gmail.com>
Acked-by: Eric Wong <normalperson@yhbt.net>

2 files changed, 15 insertions, 0 deletions

diff --git a/Documentation/git-svn.txt b/Documentation/git-svn.txt
index b09bd9761f..4b84d08fc8 100644
--- a/Documentation/git-svn.txt
+++ b/Documentation/git-svn.txt
@@ -646,6 +646,12 @@ svn.brokenSymlinkWorkaround::
 	revision fetched.  If unset, 'git svn' assumes this option to
 	be "true".
 
+svn.pathnameencoding::
+	This instructs git svn to recode pathnames to a given encoding.
+	It can be used by windows users and by those who work in non-utf8
+	locales to avoid corrupted file names with non-ASCII characters.
+	Valid encodings are the ones supported by Perl's Encode module.
+
 Since the noMetadata, rewriteRoot, rewriteUUID, useSvnsyncProps and useSvmProps
 options all affect the metadata generated and used by 'git svn'; they
 *must* be set in the configuration file before any history is imported
diff --git a/git-svn.perl b/git-svn.perl
index c4163584a9..c92238ece2 100755
--- a/git-svn.perl
+++ b/git-svn.perl
@@ -4050,6 +4050,7 @@ sub new {
 	$self->{absent_dir} = {};
 	$self->{absent_file} = {};
 	$self->{gii} = $git_svn->tmp_index_do(sub { Git::IndexInfo->new });
+	$self->{pathnameencoding} = Git::config('svn.pathnameencoding');
 	$self;
 }
 
@@ -4133,6 +4134,10 @@ sub open_directory {
 
 sub git_path {
 	my ($self, $path) = @_;
+	if (my $enc = $self->{pathnameencoding}) {
+		require Encode;
+		Encode::from_to($path, 'UTF-8', $enc);
+	}
 	if ($self->{path_strip}) {
 		$path =~ s!$self->{path_strip}!! or
 		  die "Failed to strip path '$path' ($self->{path_strip})\n";
@@ -4521,6 +4526,10 @@ sub split_path {
 
 sub repo_path {
 	my ($self, $path) = @_;
+	if (my $enc = $self->{pathnameencoding}) {
+		require Encode;
+		Encode::from_to($path, $enc, 'UTF-8');
+	}
 	$self->{path_prefix}.(defined $path ? $path : '');
 }