[PATCH 6/8] gitweb: Highlight interesting parts of diff

["Michał Kiedrowicz" <michal.kiedrowicz@gmail.com>]

Reading diff output is sometimes very hard, even if it's colored,
especially if lines differ only in few characters.  This is often true
when a commit fixes a typo or renames some variables or functions.

This commit teaches gitweb to highlight characters that are different
between old and new line.  This should work in the similar manner as in
Trac or GitHub.

The code that comares lines is based on
contrib/diff-highlight/diff-highlight, except that it works with
multiline changes too.  It also won't highlight lines that are
completely different because that would only make the output unreadable.
Combined diffs are not supported but a following commit will change it.

Signed-off-by: Michał Kiedrowicz <michal.kiedrowicz@gmail.com>
---
 gitweb/gitweb.perl |   82 ++++++++++++++++++++++++++++++++++++++++++++++++---
 1 files changed, 77 insertions(+), 5 deletions(-)

diff --git a/gitweb/gitweb.perl b/gitweb/gitweb.perl
index db61553..1a5b454 100755
--- a/gitweb/gitweb.perl
+++ b/gitweb/gitweb.perl
@@ -2322,7 +2322,7 @@ sub format_cc_diff_chunk_header {
 # wrap patch (diff) line into a <div> (not to be used for diff headers),
 # the line must be esc_html()'ed
 sub format_diff_line {
-	my ($line, $diff_class, $from, $to) = @_;
+	my ($line, $diff_class) = @_;
 
 	my $diff_classes = "diff";
 	$diff_classes .= " $diff_class" if ($diff_class);
@@ -4923,14 +4923,85 @@ sub print_inline_diff_lines {
 	print foreach (@$add);
 }
 
+# Highlight characters from $prefix to $suffix and escape HTML.
+# $str is a reference to the array of characters.
+sub esc_html_mark_range {
+	my ($str, $prefix, $suffix) = @_;
+
+	# Don't generate empty <span> element.
+	if ($prefix == $suffix + 1) {
+		return esc_html(join('', @$str), -nbsp=>1);
+	}
+
+	my $before = join('', @{$str}[0..($prefix - 1)]);
+	my $marked = join('', @{$str}[$prefix..$suffix]);
+	my $after = join('', @{$str}[($suffix + 1)..$#{$str}]);
+
+	return esc_html($before, -nbsp=>1) .
+		$cgi->span({-class=>'marked'}, esc_html($marked, -nbsp=>1)) .
+		esc_html($after,-nbsp=>1);
+}
+
+# Format removed and added line, mark changed part and HTML-format them.
+sub format_rem_add_line {
+	my ($rem, $add) = @_;
+	my @r = split(//, $rem);
+	my @a = split(//, $add);
+	my ($esc_rem, $esc_add);
+	my ($prefix, $suffix_rem, $suffix_add) = (1, $#r, $#a);
+	my ($prefix_is_space, $suffix_is_space) = (1, 1);
+
+	while ($prefix < @r && $prefix < @a) {
+		last if ($r[$prefix] ne $a[$prefix]);
+
+		$prefix_is_space = 0 if ($r[$prefix] !~ /\s/);
+		$prefix++;
+	}
+
+	while ($suffix_rem >= $prefix && $suffix_add >= $prefix) {
+		last if ($r[$suffix_rem] ne $a[$suffix_add]);
+
+		$suffix_is_space = 0 if ($r[$suffix_rem] !~ /\s/);
+		$suffix_rem--;
+		$suffix_add--;
+	}
+
+	# Mark lines that are different from each other, but have some common
+	# part that isn't whitespace.  If lines are completely different, don't
+	# mark them because that would make output unreadable, especially if
+	# diff consists of multiple lines.
+	if (($prefix == 1 && $suffix_rem == $#r && $suffix_add == $#a)
+		|| ($prefix_is_space && $suffix_is_space)) {
+		$esc_rem = esc_html($rem);
+		$esc_add = esc_html($add);
+	} else {
+		$esc_rem = esc_html_mark_range(\@r, $prefix, $suffix_rem);
+		$esc_add = esc_html_mark_range(\@a, $prefix, $suffix_add);
+	}
+
+	return format_diff_line($esc_rem, 'rem'),
+		format_diff_line($esc_add, 'add');
+}
+
 # HTML-format diff context, removed and added lines.
 sub format_ctx_rem_add_lines {
-	my ($ctx, $rem, $add) = @_;
+	my ($ctx, $rem, $add, $is_combined) = @_;
 	my (@new_ctx, @new_rem, @new_add);
+	my $num_add_lines = @$add;
+
+	if (!$is_combined && $num_add_lines > 0 && $num_add_lines == @$rem) {
+		for (my $i = 0; $i < $num_add_lines; $i++) {
+			my ($line_rem, $line_add) = format_rem_add_line(
+				$rem->[$i], $add->[$i]);
+			push @new_rem, $line_rem;
+			push @new_add, $line_add;
+		}
+	} else {
+		@new_rem = map { format_diff_line(esc_html($_, -nbsp=>1), 'rem') } @$rem;
+		@new_add = map { format_diff_line(esc_html($_, -nbsp=>1), 'add') } @$add;
+	}
 
 	@new_ctx = map { format_diff_line(esc_html($_, -nbsp=>1), 'ctx') } @$ctx;
-	@new_rem = map { format_diff_line(esc_html($_, -nbsp=>1), 'rem') } @$rem;
-	@new_add = map { format_diff_line(esc_html($_, -nbsp=>1), 'add') } @$add;
 
 	return (\@new_ctx, \@new_rem, \@new_add);
 }
@@ -4939,7 +5010,8 @@ sub format_ctx_rem_add_lines {
 sub print_diff_lines {
 	my ($ctx, $rem, $add, $diff_style, $is_combined) = @_;
 
-	($ctx, $rem, $add) = format_ctx_rem_add_lines($ctx, $rem, $add);
+	($ctx, $rem, $add) = format_ctx_rem_add_lines($ctx, $rem, $add,
+		$is_combined);
 
 	if ($diff_style eq 'sidebyside' && !$is_combined) {
 		print_sidebyside_diff_lines($ctx, $rem, $add);
-- 
1.7.3.4