[PATCH/RFCv2 5/5] gitweb: Highlight matched part of shortened project description

[Jakub Narebski <jnareb@gmail.com>]

Previous commit make gitweb use esc_html_match_hl() to mark match in
the _whole_ description of a project when searching projects.

This commit makes gitweb highlight match in _shortened_ description,
based on match in whole description, using esc_html_match_hl_chopped()
subroutine.

If match is in removed (chopped) part, even partially, then trailing
"... " is highlighted.

Signed-off-by: Jakub Narebski <jnareb@gmail.com>
---
This version removes code duplication from v1.

It is still marked as RFC, because I am not sure if it is right way
to highlight match in shortened string, or if we better use full string,
or full string if match is in chopped part.

 gitweb/gitweb.perl |   40 ++++++++++++++++++++++++++++++++++++++--
 1 files changed, 38 insertions(+), 2 deletions(-)

diff --git a/gitweb/gitweb.perl b/gitweb/gitweb.perl
index c650268..f71afe0 100755
--- a/gitweb/gitweb.perl
+++ b/gitweb/gitweb.perl
@@ -1720,11 +1720,46 @@ sub esc_html_match_hl {
 	my ($str, $regexp) = @_;
 	return esc_html($str) unless defined $regexp;
 
+	return esc_html_match_hl_chopped($str, undef, $regexp);
+}
+
+
+# highlight match (if any) of shortened string, and escape HTML
+sub esc_html_match_hl_chopped {
+	my ($str, $chopped, $regexp) = @_;
+	return esc_html($chopped) unless defined $regexp;
+
 	my @matches;
 	while ($str =~ /$regexp/g) {
 		push @matches, [$-[0], $+[0]];
 	}
-	return esc_html($str) unless @matches;
+	return esc_html(defined $chopped ? $chopped : $str) unless @matches;
+
+	# filter matches so that we mark chopped string, if it is present
+	if (defined $chopped) {
+		my $tail = "... "; # see chop_str
+		unless ($chopped =~ s/\Q$tail\E$//) {
+			$tail = '';
+		}
+		my $chop_len = length($chopped);
+		my $tail_len = length($tail);
+		my @filtered;
+
+		for my $m (@matches) {
+			if ($m->[0] > $chop_len) {
+				push @filtered, [ $chop_len, $chop_len + $tail_len ] if ($tail_len > 0);
+				last;
+			} elsif ($m->[1] > $chop_len) {
+				push @filtered, [ $m->[0], $chop_len + $tail_len ];
+				last;
+			}
+			push @filtered, $m;
+		}
+
+		# further operations are on chopped string
+		$str = $chopped . $tail;
+		@matches = @filtered;
+	}
 
 	my $out = '';
 	my $pos = 0;
@@ -5372,7 +5407,8 @@ sub git_project_list_rows {
 		      "<td>" . $cgi->a({-href => href(project=>$pr->{'path'}, action=>"summary"),
 		                        -class => "list", -title => $pr->{'descr_long'}},
 		                        $search_regexp
-		                        ? esc_html_match_hl($pr->{'descr_long'}, $search_regexp)
+		                        ? esc_html_match_hl_chopped($pr->{'descr_long'},
+		                                                    $pr->{'descr'}, $search_regexp)
 		                        : esc_html($pr->{'descr'})) .
 		      "</td>\n" .
 		      "<td><i>" . chop_and_escape_str($pr->{'owner'}, 15) . "</i></td>\n";
-- 
1.7.9