git-svn: canonicalize newly-minted URLs

Go through all the spots that use the new add_path_to_url() to
make a new URL and canonicalize them.

* copyfrom_path has to be canonicalized else find_parent_branch
  will get confused

* due to the `canonicalize_url($full_url) ne $full_url)` line of
  logic in gs_do_switch(), $full_url is left alone until after.

At this point SVN 1.7 passes except for 3 tests in
t9100-git-svn-basic.sh that look like an SVN bug to do with
symlinks.

[ew: commit title]

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

2 files changed, 22 insertions, 6 deletions

diff --git a/perl/Git/SVN.pm b/perl/Git/SVN.pm
index ec5e826468..d0087b2897 100644
--- a/perl/Git/SVN.pm
+++ b/perl/Git/SVN.pm
@@ -362,6 +362,8 @@ sub init_remote_config {
 sub find_by_url { # repos_root and, path are optional
 	my ($class, $full_url, $repos_root, $path) = @_;
 
+	$full_url = canonicalize_url($full_url);
+
 	return undef unless defined $full_url;
 	remove_username($full_url);
 	remove_username($repos_root) if defined $repos_root;
@@ -400,6 +402,11 @@ sub find_by_url { # repos_root and, path are optional
 			}
 			$p =~ s#^\Q$z\E(?:/|$)#$prefix# or next;
 		}
+
+		# remote fetch paths are not URI escaped.  Decode ours
+		# so they match
+		$p = uri_decode($p);
+
 		foreach my $f (keys %$fetch) {
 			next if $f ne $p;
 			return Git::SVN->new($fetch->{$f}, $repo_id, $f);
@@ -934,18 +941,18 @@ sub rewrite_uuid {
 sub metadata_url {
 	my ($self) = @_;
 	my $url = $self->rewrite_root || $self->url;
-	return add_path_to_url( $url, $self->path );
+	return canonicalize_url( add_path_to_url( $url, $self->path ) );
 }
 
 sub full_url {
 	my ($self) = @_;
-	return add_path_to_url( $self->url, $self->path );
+	return canonicalize_url( add_path_to_url( $self->url, $self->path ) );
 }
 
 sub full_pushurl {
 	my ($self) = @_;
 	if ($self->{pushurl}) {
-		return add_path_to_url( $self->{pushurl}, $self->path );
+		return canonicalize_url( add_path_to_url( $self->{pushurl}, $self->path ) );
 	} else {
 		return $self->full_url;
 	}
@@ -1113,7 +1120,7 @@ sub find_parent_branch {
 	my $r = $i->{copyfrom_rev};
 	my $repos_root = $self->ra->{repos_root};
 	my $url = $self->ra->url;
-	my $new_url = add_path_to_url( $url, $branch_from );
+	my $new_url = canonicalize_url( add_path_to_url( $url, $branch_from ) );
 	print STDERR  "Found possible branch point: ",
 	              "$new_url => ", $self->full_url, ", $r\n"
 	              unless $::_q > 1;
@@ -1869,7 +1876,9 @@ sub make_log_entry {
 		$email ||= "$author\@$uuid";
 		$commit_email ||= "$author\@$uuid";
 	} elsif ($self->use_svnsync_props) {
-		my $full_url = add_path_to_url( $self->svnsync->{url}, $self->path );
+		my $full_url = canonicalize_url(
+			add_path_to_url( $self->svnsync->{url}, $self->path )
+		);
 		remove_username($full_url);
 		my $uuid = $self->svnsync->{uuid};
 		$log_entry{metadata} = "$full_url\@$rev $uuid";
diff --git a/perl/Git/SVN/Ra.pm b/perl/Git/SVN/Ra.pm
index ec3c570b21..90ec30bfff 100644
--- a/perl/Git/SVN/Ra.pm
+++ b/perl/Git/SVN/Ra.pm
@@ -5,6 +5,7 @@ use warnings;
 use SVN::Client;
 use Git::SVN::Utils qw(
 	canonicalize_url
+	canonicalize_path
 	add_path_to_url
 );
 
@@ -102,6 +103,7 @@ sub new {
 			$Git::SVN::Prompt::_no_auth_cache = 1;
 		}
 	} # no warnings 'once'
+
 	my $self = SVN::Ra->new(url => $url, auth => $baton,
 	                      config => $config,
 			      pool => SVN::Pool->new,
@@ -198,6 +200,7 @@ sub get_log {
 				qw/copyfrom_path copyfrom_rev action/;
 			if ($s{'copyfrom_path'}) {
 				$s{'copyfrom_path'} =~ s/$prefix_regex//;
+				$s{'copyfrom_path'} = canonicalize_path($s{'copyfrom_path'});
 			}
 			$_[0]{$p} = \%s;
 		}
@@ -301,7 +304,11 @@ sub gs_do_switch {
 		$ra = Git::SVN::Ra->new($full_url);
 		$ra_invalid = 1;
 	} elsif ($old_url ne $full_url) {
-		SVN::_Ra::svn_ra_reparent($self->{session}, $full_url, $pool);
+		SVN::_Ra::svn_ra_reparent(
+			$self->{session},
+			canonicalize_url($full_url),
+			$pool
+		);
 		$self->url($full_url);
 		$reparented = 1;
 	}