git/list[1] front-page[2] threads[3] people[4] search[5] about
 

[PATCH 4/8] Replace hand rolled URL escapes with canonicalization

From
Michael G. Schwern <schwern@pobox.com>
Date
Jul 28, 2012, 09:47 UTC
Message-ID
<1343468872-72133-5-git-send-email-schwern@pobox.com>
In-Reply-To
<1343468872-72133-1-git-send-email-schwern@pobox.com>
From: "Michael G. Schwern" <schwern@pobox.com>
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.
---
 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 6e3e240..6e97545 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 cb6d83a..4219e5b 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 ef7b3dd..ed9dbe9 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);
@@ -314,7 +296,7 @@ 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;
@@ -327,7 +309,7 @@ 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);
@@ -582,7 +564,8 @@ 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 {
-- 
1.7.11.3
Previous: Michael G. SchwernNext: Michael G. Schwern
Message 16 of 50 in “Fix git-svn for SVN 1.7”
  1. Michael G. SchwernJul 28, 2012
  2. 1/8 SVN 1.7 will truncate "not-a%40{0}" to just "not-a".Michael G. Schwern, Jul 28, 2012
  3. Jonathan NiederJul 28, 2012
  4. Michael G SchwernJul 28, 2012
  5. svn test: escape peg revision separator using empty peg revJonathan Nieder, Oct 9, 2012
  6. Michael J GruberOct 9, 2012
  7. Jonathan NiederOct 9, 2012
  8. Eric WongOct 10, 2012
  9. Jonathan NiederOct 10, 2012
  10. Eric WongOct 10, 2012
  11. Jonathan NiederOct 10, 2012
  12. Eric WongOct 10, 2012
  13. Junio C HamanoOct 10, 2012
  14. 2/8 Fix typo in testMichael G. Schwern, Jul 28, 2012
  15. 3/8 Improve our URL canonicalization to be more like SVN 1.7's.Michael G. Schwern, Jul 28, 2012
  16. 4/8 Replace hand rolled URL escapes with canonicalizationMichael G. Schwern, Jul 28, 2012
  17. 5/8 Canonicalize earlier in a couple spots.Michael G. Schwern, Jul 28, 2012
  18. 6/8 Add function to append a path to a URL.Michael G. Schwern, Jul 28, 2012
  19. 7/8 Turn on canonicalization on newly minted URLs.Michael G. Schwern, Jul 28, 2012
  20. test: work around SVN 1.7 mishandling of svn:special changesJonathan Nieder, Oct 6, 2012
  21. git svn: work around SVN 1.7 mishandling of svn:special changesJonathan Nieder, Oct 9, 2012
  22. Eric WongOct 10, 2012
  23. git svn: work around SVN 1.7 mishandling of svn:special changesJonathan Nieder, Oct 10, 2012
  24. 8/8 Remove some ad hoc canonicalizations.Michael G. Schwern, Jul 28, 2012
  25. Eric WongJul 30, 2012
  26. Michael G SchwernJul 30, 2012
  27. Eric WongJul 30, 2012
  28. Michael G SchwernJul 31, 2012
  29. Eric WongJul 31, 2012
  30. Michael G SchwernJul 31, 2012
  31. Junio C HamanoJul 31, 2012
  32. Michael G SchwernJul 31, 2012
  33. Eric WongJul 31, 2012
  34. Junio C HamanoJul 31, 2012
  35. Michael G SchwernJul 31, 2012
  36. Michael G SchwernJul 31, 2012
  37. Eric WongAug 1, 2012
  38. Eric WongAug 2, 2012
  39. Jonathan NiederAug 2, 2012
  40. Junio C HamanoAug 2, 2012
  41. Robin H. JohnsonAug 2, 2012
  42. Eric WongAug 2, 2012
  43. Junio C HamanoAug 21, 2012
  44. Eric WongAug 21, 2012
  45. Junio C HamanoAug 21, 2012
  46. Eric WongAug 2, 2012
  47. Junio C HamanoAug 2, 2012
  48. Eric WongAug 2, 2012
  49. Eric WongAug 2, 2012
  50. Junio C HamanoAug 2, 2012

Read the whole thread, see it on lore, or plain text.

$ cat FOOTERMessages come from the public archive at lore.kernel.org/git, fetched every hour. The front page is chosen and written each morning by an AI editor and can be wrong; the threads themselves are the record. About and API. For agents: an MCP server at https://gitlist.dev/mcp, and any thread, story or person page as Markdown by adding .md to its URL (or sending Accept: text/markdown). Details in /llms.txt.