From 9c27a57b2da502b7dd3736013b7a185fb6e5064e Mon Sep 17 00:00:00 2001
From: "Michael G. Schwern" <schwern@pobox.com>
Date: Sat, 28 Jul 2012 02:47:48 -0700
Subject: [PATCH] git-svn: replace URL escapes with canonicalization

The old hand-rolled URL escape functions were inferior to
canonicalization functions.

Continuing to move towards getting everything canonicalizing the same way.

* Git::SVN->init_remote_config and Git::SVN::Ra->minimize_url both
  have to canonicalize the same way else init_remote_config
  will incorrectly think they're different URLs causing
  t9107-git-svn-migrate.sh to fail.

[ew: commit title]

Signed-off-by: Eric Wong <normalperson@yhbt.net>
---
 git-svn.perl       | 24 +++---------------------
 perl/Git/SVN.pm    |  2 +-
 perl/Git/SVN/Ra.pm | 27 +++++----------------------
 3 files changed, 9 insertions(+), 44 deletions(-)

diff --git a/git-svn.perl b/git-svn.perl
index 6e3e240473..6e975457f9 100755
--- a/git-svn.perl
+++ b/git-svn.perl
@@ -1412,24 +1412,6 @@ sub cmd_commit_diff {
 	}
 }
 
-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 ($url =~ m#^([^:]+)://([^/]*)(.*)$#) {
-		my ($scheme, $domain, $uri) = ($1, $2, escape_uri_only($3));
-		$url = "$scheme://$domain$uri";
-	}
-	$url;
-}
 
 sub cmd_info {
 	my $path = canonicalize_path(defined($_[0]) ? $_[0] : ".");
@@ -1457,18 +1439,18 @@ sub cmd_info {
 	my $full_url = $url . ($fullpath eq "" ? "" : "/$fullpath");
 
 	if ($_url) {
-		print escape_url($full_url), "\n";
+		print canonicalize_url($full_url), "\n";
 		return;
 	}
 
 	my $result = "Path: $path\n";
 	$result .= "Name: " . basename($path) . "\n" if $file_type ne "dir";
-	$result .= "URL: " . escape_url($full_url) . "\n";
+	$result .= "URL: " . canonicalize_url($full_url) . "\n";
 
 	eval {
 		my $repos_root = $gs->repos_root;
 		Git::SVN::remove_username($repos_root);
-		$result .= "Repository Root: " . escape_url($repos_root) . "\n";
+		$result .= "Repository Root: " . canonicalize_url($repos_root) . "\n";
 	};
 	if ($@) {
 		$result .= "Repository Root: (offline)\n";
diff --git a/perl/Git/SVN.pm b/perl/Git/SVN.pm
index a2e7144b4c..6a2a52e808 100644
--- a/perl/Git/SVN.pm
+++ b/perl/Git/SVN.pm
@@ -296,7 +296,7 @@ sub find_existing_remote {
 
 sub init_remote_config {
 	my ($self, $url, $no_write) = @_;
-	$url =~ s!/+$!!; # strip trailing slash
+	$url = canonicalize_url($url);
 	my $r = read_all_remotes();
 	my $existing = find_existing_remote($url, $r);
 	if ($existing) {
diff --git a/perl/Git/SVN/Ra.pm b/perl/Git/SVN/Ra.pm
index 77bceb913a..268b368de3 100644
--- a/perl/Git/SVN/Ra.pm
+++ b/perl/Git/SVN/Ra.pm
@@ -66,24 +66,6 @@ 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) = @_;
@@ -119,7 +101,7 @@ sub new {
 			$Git::SVN::Prompt::_no_auth_cache = 1;
 		}
 	} # no warnings 'once'
-	my $self = SVN::Ra->new(url => escape_url($url), auth => $baton,
+	my $self = SVN::Ra->new(url => canonicalize_url($url), auth => $baton,
 	                      config => $config,
 			      pool => SVN::Pool->new,
 	                      auth_provider_callbacks => $callbacks);
@@ -312,7 +294,7 @@ sub gs_do_switch {
 
 	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;
@@ -325,7 +307,7 @@ sub gs_do_switch {
 	}
 
 	$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);
@@ -580,7 +562,8 @@ sub minimize_url {
 			$ra->get_log("", $latest, 0, 1, 0, 1, sub {});
 		};
 	} while ($@ && ($c = shift @components));
-	$url;
+
+	return canonicalize_url($url);
 }
 
 sub can_do_switch {