Merge branch 'ms/git-svn-1.7'

A series by Michael Schwern via Eric to update git-svn to revamp the
way URLs are internally passed around, to make it work with SVN 1.7.

* ms/git-svn-1.7:
  git-svn: remove ad-hoc canonicalizations
  git-svn: canonicalize newly-minted URLs
  git-svn: introduce add_path_to_url function
  git-svn: canonicalize earlier
  git-svn: replace URL escapes with canonicalization
  git-svn: attempt to mimic SVN 1.7 URL canonicalization
  t9107: fix typo
  t9118: workaround inconsistency between SVN versions
  Git::SVN{,::Ra}: canonicalize earlier
  git-svn: path canonicalization uses SVN API
  Git::SVN::Utils: remove irrelevant comment
  git-svn: add join_paths() to safely concatenate paths
  git-svn: factor out _collapse_dotdot function
  git-svn: use SVN 1.7 to canonicalize when possible
  git-svn: move canonicalization to Git::SVN::Utils
  use Git::SVN{,::RA}->url accessor globally
  use Git::SVN->path accessor globally
  Git::SVN::Ra: use accessor for URLs
  Git::SVN: use accessor for URLs internally
  Git::SVN: use accessors internally for path

1 files changed, 51 insertions, 41 deletions

diff --git a/perl/Git/SVN/Ra.pm b/perl/Git/SVN/Ra.pm
index 23ff43e86b..90ec30bfff 100644
--- a/perl/Git/SVN/Ra.pm
+++ b/perl/Git/SVN/Ra.pm
@@ -3,6 +3,12 @@ use vars qw/@ISA $config_dir $_ignore_refs_regex $_log_window_size/;
 use strict;
 use warnings;
 use SVN::Client;
+use Git::SVN::Utils qw(
+	canonicalize_url
+	canonicalize_path
+	add_path_to_url
+);
+
 use SVN::Ra;
 BEGIN {
 	@ISA = qw(SVN::Ra);
@@ -62,29 +68,11 @@ sub _auth_providers () {
 	\@rv;
 }
 
-sub escape_uri_only {
-	my ($uri) = @_;
-	my @tmp;
-	foreach (split m{/}, $uri) {
-		s/([^~\w.%+-]|%(?![a-fA-F0-9]{2}))/sprintf("%%%02X",ord($1))/eg;
-		push @tmp, $_;
-	}
-	join('/', @tmp);
-}
-
-sub escape_url {
-	my ($url) = @_;
-	if ($url =~ m#^(https?)://([^/]+)(.*)$#) {
-		my ($scheme, $domain, $uri) = ($1, $2, escape_uri_only($3));
-		$url = "$scheme://$domain$uri";
-	}
-	$url;
-}
 
 sub new {
 	my ($class, $url) = @_;
-	$url =~ s!/+$!!;
-	return $RA if ($RA && $RA->{url} eq $url);
+	$url = canonicalize_url($url);
+	return $RA if ($RA && $RA->url eq $url);
 
 	::_req_svn();
 
@@ -115,17 +103,34 @@ sub new {
 			$Git::SVN::Prompt::_no_auth_cache = 1;
 		}
 	} # no warnings 'once'
-	my $self = SVN::Ra->new(url => escape_url($url), auth => $baton,
+
+	my $self = SVN::Ra->new(url => $url, auth => $baton,
 	                      config => $config,
 			      pool => SVN::Pool->new,
 	                      auth_provider_callbacks => $callbacks);
-	$self->{url} = $url;
+	$RA = bless $self, $class;
+
+	# Make sure its canonicalized
+	$self->url($url);
 	$self->{svn_path} = $url;
 	$self->{repos_root} = $self->get_repos_root;
 	$self->{svn_path} =~ s#^\Q$self->{repos_root}\E(/|$)##;
 	$self->{cache} = { check_path => { r => 0, data => {} },
 	                   get_dir => { r => 0, data => {} } };
-	$RA = bless $self, $class;
+
+	return $RA;
+}
+
+sub url {
+	my $self = shift;
+
+	if (@_) {
+		my $url = shift;
+		$self->{url} = canonicalize_url($url);
+		return;
+	}
+
+	return $self->{url};
 }
 
 sub check_path {
@@ -195,6 +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;
 		}
@@ -246,7 +252,7 @@ sub get_commit_editor {
 sub gs_do_update {
 	my ($self, $rev_a, $rev_b, $gs, $editor) = @_;
 	my $new = ($rev_a == $rev_b);
-	my $path = $gs->{path};
+	my $path = $gs->path;
 
 	if ($new && -e $gs->{index}) {
 		unlink $gs->{index} or die
@@ -282,30 +288,33 @@ sub gs_do_update {
 # svn_ra_reparent didn't work before 1.4)
 sub gs_do_switch {
 	my ($self, $rev_a, $rev_b, $gs, $url_b, $editor) = @_;
-	my $path = $gs->{path};
+	my $path = $gs->path;
 	my $pool = SVN::Pool->new;
 
-	my $full_url = $self->{url};
-	my $old_url = $full_url;
-	$full_url .= '/' . $path if length $path;
+	my $old_url = $self->url;
+	my $full_url = add_path_to_url( $self->url, $path );
 	my ($ra, $reparented);
 
 	if ($old_url =~ m#^svn(\+ssh)?://# ||
 	    ($full_url =~ m#^https?://# &&
-	     escape_url($full_url) ne $full_url)) {
+	     canonicalize_url($full_url) ne $full_url)) {
 		$_[0] = undef;
 		$self = undef;
 		$RA = undef;
 		$ra = Git::SVN::Ra->new($full_url);
 		$ra_invalid = 1;
 	} elsif ($old_url ne $full_url) {
-		SVN::_Ra::svn_ra_reparent($self->{session}, $full_url, $pool);
-		$self->{url} = $full_url;
+		SVN::_Ra::svn_ra_reparent(
+			$self->{session},
+			canonicalize_url($full_url),
+			$pool
+		);
+		$self->url($full_url);
 		$reparented = 1;
 	}
 
 	$ra ||= $self;
-	$url_b = escape_url($url_b);
+	$url_b = canonicalize_url($url_b);
 	my $reporter = $ra->do_switch($rev_b, '', 1, $url_b, $editor, $pool);
 	my @lock = (::compare_svn_version('1.2.0') >= 0) ? (undef) : ();
 	$reporter->set_path('', $rev_a, 0, @lock, $pool);
@@ -313,7 +322,7 @@ sub gs_do_switch {
 
 	if ($reparented) {
 		SVN::_Ra::svn_ra_reparent($self->{session}, $old_url, $pool);
-		$self->{url} = $old_url;
+		$self->url($old_url);
 	}
 
 	$pool->clear;
@@ -326,7 +335,7 @@ sub longest_common_path {
 	my $common_max = scalar @$gsv;
 
 	foreach my $gs (@$gsv) {
-		my @tmp = split m#/#, $gs->{path};
+		my @tmp = split m#/#, $gs->path;
 		my $p = '';
 		foreach (@tmp) {
 			$p .= length($p) ? "/$_" : $_;
@@ -362,7 +371,7 @@ sub gs_fetch_loop_common {
 	my $inc = $_log_window_size;
 	my ($min, $max) = ($base, $head < $base + $inc ? $head : $base + $inc);
 	my $longest_path = longest_common_path($gsv, $globs);
-	my $ra_url = $self->{url};
+	my $ra_url = $self->url;
 	my $find_trailing_edge;
 	while (1) {
 		my %revs;
@@ -508,7 +517,7 @@ sub match_globs {
 				 ($self->check_path($p, $r) !=
 				  $SVN::Node::dir));
 			next unless $p =~ /$g->{path}->{regex}/;
-			$exists->{$p} = Git::SVN->init($self->{url}, $p, undef,
+			$exists->{$p} = Git::SVN->init($self->url, $p, undef,
 					 $g->{ref}->full_path($de), 1);
 		}
 	}
@@ -532,7 +541,7 @@ sub match_globs {
 			next if ($self->check_path($pathname, $r) !=
 			         $SVN::Node::dir);
 			$exists->{$pathname} = Git::SVN->init(
-			                      $self->{url}, $pathname, undef,
+			                      $self->url, $pathname, undef,
 			                      $g->{ref}->full_path($p), 1);
 		}
 		my $c = '';
@@ -548,19 +557,20 @@ sub match_globs {
 
 sub minimize_url {
 	my ($self) = @_;
-	return $self->{url} if ($self->{url} eq $self->{repos_root});
+	return $self->url if ($self->url eq $self->{repos_root});
 	my $url = $self->{repos_root};
 	my @components = split(m!/!, $self->{svn_path});
 	my $c = '';
 	do {
-		$url .= "/$c" if length $c;
+		$url = add_path_to_url($url, $c);
 		eval {
 			my $ra = (ref $self)->new($url);
 			my $latest = $ra->get_latest_revnum;
 			$ra->get_log("", $latest, 0, 1, 0, 1, sub {});
 		};
 	} while ($@ && ($c = shift @components));
-	$url;
+
+	return canonicalize_url($url);
 }
 
 sub can_do_switch {
@@ -568,7 +578,7 @@ sub can_do_switch {
 	unless (defined $can_do_switch) {
 		my $pool = SVN::Pool->new;
 		my $rep = eval {
-			$self->do_switch(1, '', 0, $self->{url},
+			$self->do_switch(1, '', 0, $self->url,
 			                 SVN::Delta::Editor->new, $pool);
 		};
 		if ($@) {