git-svn: allow disabling expensive broken symlink checks

Since dbc6c74d0858d77e61e092a48d467e725211f8e9, git-svn has had
an expensive check for broken symlinks that exist in some
repositories.  This leads to a heavy performance hit on
repositories with many empty blobs that are not supposed to be
symlinks.

The workaround is enabled by default; and may be disabled via:

  git config svn.brokenSymlinkWorkaround false

Reported by Markus Heidelberg.

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

3 files changed, 38 insertions, 0 deletions

diff --git a/Documentation/git-svn.txt b/Documentation/git-svn.txt
index 7b654f7928..3d456545d7 100644
--- a/Documentation/git-svn.txt
+++ b/Documentation/git-svn.txt
@@ -499,6 +499,14 @@ svn-remote.<name>.rewriteRoot::
 	the repository with a public http:// or svn:// URL in the
 	metadata so users of it will see the public URL.
 
+svn.brokenSymlinkWorkaround::
+This disables potentially expensive checks to workaround broken symlinks
+checked into SVN by broken clients.  Set this option to "false" if you
+track a SVN repository with many empty blobs that are not symlinks.
+This option may be changed while "git-svn" is running and take effect on
+the next revision fetched.  If unset, git-svn assumes this option to be
+"true".
+
 --
 
 Since the noMetadata, rewriteRoot, useSvnsyncProps and useSvmProps
diff --git a/git-svn.perl b/git-svn.perl
index 79888a05c4..bebcbdea20 100755
--- a/git-svn.perl
+++ b/git-svn.perl
@@ -3271,10 +3271,18 @@ sub new {
 # do_{switch,update}
 sub _mark_empty_symlinks {
 	my ($git_svn) = @_;
+	my $bool = Git::config_bool('svn.brokenSymlinkWorkaround');
+	return {} if (defined($bool) && ! $bool);
+
 	my %ret;
 	my ($rev, $cmt) = $git_svn->last_rev_commit;
 	return {} unless ($rev && $cmt);
 
+	# allow the warning to be printed for each revision we fetch to
+	# ensure the user sees it.  The user can also disable the workaround
+	# on the repository even while git svn is running and the next
+	# revision fetched will skip this expensive function.
+	my $printed_warning;
 	chomp(my $empty_blob = `git hash-object -t blob --stdin < /dev/null`);
 	my ($ls, $ctx) = command_output_pipe(qw/ls-tree -r -z/, $cmt);
 	local $/ = "\0";
@@ -3283,6 +3291,18 @@ sub _mark_empty_symlinks {
 	while (<$ls>) {
 		chomp;
 		s/\A100644 blob $empty_blob\t//o or next;
+		unless ($printed_warning) {
+			print STDERR "Scanning for empty symlinks, ",
+			             "this may take a while if you have ",
+				     "many empty files\n",
+				     "You may disable this with `",
+				     "git config svn.brokenSymlinkWorkaround ",
+				     "false'.\n",
+				     "This may be done in a different ",
+				     "terminal without restarting ",
+				     "git svn\n";
+			$printed_warning = 1;
+		}
 		my $path = $_;
 		my (undef, $props) =
 		               $git_svn->ra->get_file($pfx.$path, $rev, undef);
diff --git a/t/t9131-git-svn-empty-symlink.sh b/t/t9131-git-svn-empty-symlink.sh
index 704a4f8574..20529a878c 100755
--- a/t/t9131-git-svn-empty-symlink.sh
+++ b/t/t9131-git-svn-empty-symlink.sh
@@ -87,4 +87,14 @@ test_expect_success '"bar" is an empty file' 'test -f x/bar && ! test -s x/bar'
 test_expect_success 'get "bar" => symlink fix from svn' \
 		'(cd x && git svn rebase)'
 test_expect_success '"bar" becomes a symlink' 'test -L x/bar'
+
+
+test_expect_success 'clone using git svn' 'git svn clone -r1 "$svnrepo" y'
+test_expect_success 'disable broken symlink workaround' \
+  '(cd y && git config svn.brokenSymlinkWorkaround false)'
+test_expect_success '"bar" is an empty file' 'test -f y/bar && ! test -s y/bar'
+test_expect_success 'get "bar" => symlink fix from svn' \
+		'(cd y && git svn rebase)'
+test_expect_success '"bar" does not become a symlink' '! test -L y/bar'
+
 test_done