gitweb: Better git-unquoting and gitweb-quoting of pathnames

Extend unquote subroutine, which unquotes quoted and escaped filenames
which git may return, to deal not only with octal char sequence
quoting, but also quoting ordinary characters including '\"' and '\\'
which are respectively quoted '"' and '\', and to deal also with
C escape sequences including '\t' for TAB and '\n' for LF.

Add esc_path subroutine for gitweb quoting and HTML escaping filenames
(currently it does equivalent of ls' --hide-control-chars, which means
showing undisplayable characters (including '\n' and '\t') as '?'
(question mark) character, and use 'span' element with cntrl CSS class
to help rendering them differently.

Convert gitweb to use esc_path correctly to print pathnames.

Signed-off-by: Jakub Narebski <jnareb@gmail.com>
Signed-off-by: Junio C Hamano <junkio@cox.net>

2 files changed, 60 insertions, 19 deletions

diff --git a/gitweb/gitweb.css b/gitweb/gitweb.css
index 0eda98237..e19e6bc2e 100644
--- a/gitweb/gitweb.css
+++ b/gitweb/gitweb.css
@@ -16,6 +16,13 @@ a:hover, a:visited, a:active {
 	color: #880000;
 }
 
+span.cntrl {
+	border: dashed #aaaaaa;
+	border-width: 1px;
+	padding: 0px 2px 0px 2px;
+	margin:  0px 2px 0px 2px;
+}
+
 img.logo {
 	float: right;
 	border-width: 0px;
diff --git a/gitweb/gitweb.perl b/gitweb/gitweb.perl
index c46629f82..fcf255def 100755
--- a/gitweb/gitweb.perl
+++ b/gitweb/gitweb.perl
@@ -584,12 +584,46 @@ sub esc_html ($;%) {
 	return $str;
 }
 
+# quote control characters and escape filename to HTML
+sub esc_path {
+	my $str = shift;
+	$str = esc_html($str);
+	$str =~ s|([[:cntrl:]])|<span class="cntrl">?</span>|g;
+	return $str;
+}
+
 # git may return quoted and escaped filenames
 sub unquote {
 	my $str = shift;
+
+	sub unq {
+		my $seq = shift;
+		my %es = ( # character escape codes, aka escape sequences
+			't' => "\t",   # tab            (HT, TAB)
+			'n' => "\n",   # newline        (NL)
+			'r' => "\r",   # return         (CR)
+			'f' => "\f",   # form feed      (FF)
+			'b' => "\b",   # backspace      (BS)
+			'a' => "\a",   # alarm (bell)   (BEL)
+			'e' => "\e",   # escape         (ESC)
+			'v' => "\013", # vertical tab   (VT)
+		);
+
+		if ($seq =~ m/^[0-7]{1,3}$/) {
+			# octal char sequence
+			return chr(oct($seq));
+		} elsif (exists $es{$seq}) {
+			# C escape sequence, aka character escape code
+			return $es{$seq}
+		}
+		# quoted ordinary character
+		return $seq;
+	}
+
 	if ($str =~ m/^"(.*)"$/) {
+		# needs unquoting
 		$str = $1;
-		$str =~ s/\\([0-7]{1,3})/chr(oct($1))/eg;
+		$str =~ s/\\([^0-7]|[0-7]{1,3})/unq($1)/eg;
 	}
 	return $str;
 }
@@ -1520,7 +1554,7 @@ sub git_header_html {
 		if (defined $action) {
 			$title .= "/$action";
 			if (defined $file_name) {
-				$title .= " - " . esc_html($file_name);
+				$title .= " - " . esc_path($file_name);
 				if ($action eq "tree" && $file_name !~ m|/$|) {
 					$title .= "/";
 				}
@@ -1791,20 +1825,20 @@ sub git_print_page_path {
 			$fullname .= ($fullname ? '/' : '') . $dir;
 			print $cgi->a({-href => href(action=>"tree", file_name=>$fullname,
 			                             hash_base=>$hb),
-			              -title => $fullname}, esc_html($dir));
+			              -title => $fullname}, esc_path($dir));
 			print " / ";
 		}
 		if (defined $type && $type eq 'blob') {
 			print $cgi->a({-href => href(action=>"blob_plain", file_name=>$file_name,
 			                             hash_base=>$hb),
-			              -title => $name}, esc_html($basename));
+			              -title => $name}, esc_path($basename));
 		} elsif (defined $type && $type eq 'tree') {
 			print $cgi->a({-href => href(action=>"tree", file_name=>$file_name,
 			                             hash_base=>$hb),
-			              -title => $name}, esc_html($basename));
+			              -title => $name}, esc_path($basename));
 			print " / ";
 		} else {
-			print esc_html($basename);
+			print esc_path($basename);
 		}
 	}
 	print "<br/></div>\n";
@@ -1876,7 +1910,7 @@ sub git_print_tree_entry {
 		print "<td class=\"list\">" .
 			$cgi->a({-href => href(action=>"blob", hash=>$t->{'hash'},
 			                       file_name=>"$basedir$t->{'name'}", %base_key),
-			        -class => "list"}, esc_html($t->{'name'})) . "</td>\n";
+			        -class => "list"}, esc_path($t->{'name'})) . "</td>\n";
 		print "<td class=\"link\">";
 		print $cgi->a({-href => href(action=>"blob", hash=>$t->{'hash'},
 					     file_name=>"$basedir$t->{'name'}", %base_key)},
@@ -1903,7 +1937,7 @@ sub git_print_tree_entry {
 		print "<td class=\"list\">";
 		print $cgi->a({-href => href(action=>"tree", hash=>$t->{'hash'},
 		                             file_name=>"$basedir$t->{'name'}", %base_key)},
-		              esc_html($t->{'name'}));
+		              esc_path($t->{'name'}));
 		print "</td>\n";
 		print "<td class=\"link\">";
 		print $cgi->a({-href => href(action=>"tree", hash=>$t->{'hash'},
@@ -1968,7 +2002,7 @@ sub git_difftree_body {
 			print "<td>";
 			print $cgi->a({-href => href(action=>"blob", hash=>$diff{'to_id'},
 			                             hash_base=>$hash, file_name=>$diff{'file'}),
-			              -class => "list"}, esc_html($diff{'file'}));
+			              -class => "list"}, esc_path($diff{'file'}));
 			print "</td>\n";
 			print "<td>$mode_chng</td>\n";
 			print "<td class=\"link\">";
@@ -1984,7 +2018,7 @@ sub git_difftree_body {
 			print "<td>";
 			print $cgi->a({-href => href(action=>"blob", hash=>$diff{'from_id'},
 			                             hash_base=>$parent, file_name=>$diff{'file'}),
-			               -class => "list"}, esc_html($diff{'file'}));
+			               -class => "list"}, esc_path($diff{'file'}));
 			print "</td>\n";
 			print "<td>$mode_chng</td>\n";
 			print "<td class=\"link\">";
@@ -2024,7 +2058,7 @@ sub git_difftree_body {
 			print "<td>";
 			print $cgi->a({-href => href(action=>"blob", hash=>$diff{'to_id'},
 			                             hash_base=>$hash, file_name=>$diff{'file'}),
-			              -class => "list"}, esc_html($diff{'file'}));
+			              -class => "list"}, esc_path($diff{'file'}));
 			print "</td>\n";
 			print "<td>$mode_chnge</td>\n";
 			print "<td class=\"link\">";
@@ -2064,11 +2098,11 @@ sub git_difftree_body {
 			print "<td>" .
 			      $cgi->a({-href => href(action=>"blob", hash_base=>$hash,
 			                             hash=>$diff{'to_id'}, file_name=>$diff{'to_file'}),
-			              -class => "list"}, esc_html($diff{'to_file'})) . "</td>\n" .
+			              -class => "list"}, esc_path($diff{'to_file'})) . "</td>\n" .
 			      "<td><span class=\"file_status $nstatus\">[$nstatus from " .
 			      $cgi->a({-href => href(action=>"blob", hash_base=>$parent,
 			                             hash=>$diff{'from_id'}, file_name=>$diff{'from_file'}),
-			              -class => "list"}, esc_html($diff{'from_file'})) .
+			              -class => "list"}, esc_path($diff{'from_file'})) .
 			      " with " . (int $diff{'similarity'}) . "% similarity$mode_chng]</span></td>\n" .
 			      "<td class=\"link\">";
 			if ($action eq 'commitdiff') {
@@ -2191,7 +2225,7 @@ sub git_patchset_body {
 			$file  ||= $diffinfo->{'file'};
 			$file = $cgi->a({-href => href(action=>"blob", hash_base=>$hash_parent,
 			                               hash=>$diffinfo->{'from_id'}, file_name=>$file),
-			                -class => "list"}, esc_html($file));
+			                -class => "list"}, esc_path($file));
 			$patch_line =~ s|a/.*$|a/$file|g;
 			print "<div class=\"diff from_file\">$patch_line</div>\n";
 
@@ -2203,7 +2237,7 @@ sub git_patchset_body {
 			$file  ||= $diffinfo->{'file'};
 			$file = $cgi->a({-href => href(action=>"blob", hash_base=>$hash,
 			                               hash=>$diffinfo->{'to_id'}, file_name=>$file),
-			                -class => "list"}, esc_html($file));
+			                -class => "list"}, esc_path($file));
 			$patch_line =~ s|b/.*|b/$file|g;
 			print "<div class=\"diff to_file\">$patch_line</div>\n";
 
@@ -3521,8 +3555,8 @@ sub git_blobdiff {
 
 	} else {
 		while (my $line = <$fd>) {
-			$line =~ s!a/($hash|$hash_parent)!'a/'.esc_html($diffinfo{'from_file'})!eg;
-			$line =~ s!b/($hash|$hash_parent)!'b/'.esc_html($diffinfo{'to_file'})!eg;
+			$line =~ s!a/($hash|$hash_parent)!'a/'.esc_path($diffinfo{'from_file'})!eg;
+			$line =~ s!b/($hash|$hash_parent)!'b/'.esc_path($diffinfo{'to_file'})!eg;
 
 			print $line;
 
@@ -3879,7 +3913,7 @@ sub git_search {
 						print $cgi->a({-href => href(action=>"blob", hash_base=>$co{'id'},
 						                             hash=>$set{'id'}, file_name=>$set{'file'}),
 						              -class => "list"},
-						              "<span class=\"match\">" . esc_html($set{'file'}) . "</span>") .
+						              "<span class=\"match\">" . esc_path($set{'file'}) . "</span>") .
 						      "<br/>\n";
 					}
 					print "</td>\n" .
@@ -4014,7 +4048,7 @@ XML
 			if (!($line =~ m/^:([0-7]{6}) ([0-7]{6}) ([0-9a-fA-F]{40}) ([0-9a-fA-F]{40}) (.)([0-9]{0,3})\t(.*)$/)) {
 				next;
 			}
-			my $file = esc_html(unquote($7));
+			my $file = esc_path(unquote($7));
 			$file = to_utf8($file);
 			print "$file<br/>\n";
 		}