[RFC/PATCH] gitweb: Option to chop at beginning and in the middle in chop_str

From

Jakub Narebski <jnareb@gmail.com>

Date

Feb 23, 2008, 21:44 UTC

Message-ID

<20080223214226.16470.29333.stgit@localhost.localdomain>

In-Reply-To

<200802222014.13205.jnareb@gmail.com>

Add support for '-cut' option to chop_str subroutine, to cut at the
beginning (from the left side of the string), in the middle (center of
the string), or at the end (from the right side of the string) which
is the default:
  chop_str(somestring, len, slop, -pos=>'left')    ->  ... string
  chop_str(somestring, len, slop, -pos=>'center')  ->  som ... ing
  chop_str(somestring, len, slop, -pos=>'right')   ->  somestr ...

    ...st this with <<very long ... and how>> the actual out...

instead of:

    Could som... <<very long search stri...>> the actual out...

(where <<something>> denotes emphasized / colored fragment).

Signed-off-by: Jakub Narebski <jnareb@gmail.com>
---
And here it is as a patch to gitweb to play with. I agree with Junio
that the output is better, but I'm not sure if it is worth the
complication in code; perhaps is.

 gitweb/gitweb.perl |   74 +++++++++++++++++++++++++++++++++++++++++-----------
 1 files changed, 58 insertions(+), 16 deletions(-)

diff --git a/gitweb/gitweb.perl b/gitweb/gitweb.perl
index e8226b1..59d44b3 100755
--- a/gitweb/gitweb.perl
+++ b/gitweb/gitweb.perl
@@ -848,32 +848,74 @@ sub project_in_list {
 ## ----------------------------------------------------------------------
 ## HTML aware string manipulation
 
+# cut (chop) string to given length, with additional slop,
+# optionally from left and in the middle.
 sub chop_str {
 	my $str = shift;
 	my $len = shift;
 	my $add_len = shift || 10;
+	# supported opts:
+	# * -cut => 'left' | 'center' | 'right', defaults to 'right'
+	#   denotes where (which part) to chop
+	my %opts = @_;
 
 	# allow only $len chars, but don't cut a word if it would fit in $add_len
 	# if it doesn't fit, cut it if it's still longer than the dots we would add
-	$str =~ m/^(.{0,$len}[^ \/\-_:\.@]{0,$add_len})(.*)/;
-	my $body = $1;
-	my $tail = $2;
-	if (length($tail) > 4) {
-		$tail = " ...";
-		$body =~ s/&[^;]*$//; # remove chopped character entities
+	# remove chopped character entities entirely
+
+	# when chopping in the middle, distribute $len into left and right part
+	if (defined $opts{'-cut'} && $opts{'-cut'} eq 'center') {
+		$len = int($len/2);
+	}
+
+	# regexps: ending and beginning with word part up to $add_len
+	my $endre = qr/.{0,$len}[^ \/\-_:\.@]{0,$add_len}/;
+	my $begre = qr/[^ \/\-_:\.@]{0,$add_len}.{0,$len}/;
+
+	if (defined $opts{'-cut'} && $opts{'-cut'} eq 'left') {
+		$str =~ m/^(.*?)($begre)$/;
+		my ($lead, $body) = ($1, $2);
+		if (length($lead) > 4) {
+			if ($lead =~ m/&[^;]*$/) {
+				$body =~ s/^[^;]*;//;
+			}
+			$lead = "... ";
+		}
+		return "$lead$body";
+
+	} elsif (defined $opts{'-cut'} && $opts{'-cut'} eq 'center') {
+		$str =~ m/^($endre)(.*)$/;
+		my ($left, $str)  = ($1, $2);
+		$str =~ m/^(.*?)($begre)$/;
+		my ($mid, $right) = ($1, $2);
+		if (length($mid) > 5) {
+			$left =~ s/&[^;]*$//;
+			if ($mid =~ m/&[^;]*$/) {
+				$right =~ s/^[^;]*;//;
+			}
+			$mid = " ... ";
+		}
+		return "$left$mid$right";
+
+	} else {
+		$str =~ m/^($endre)(.*)$/;
+		my $body = $1;
+		my $tail = $2;
+		if (length($tail) > 4) {
+			$body =~ s/&[^;]*$//;
+			$tail = " ...";
+		}
+		return "$body$tail";
 	}
-	return "$body$tail";
 }
 
 # takes the same arguments as chop_str, but also wraps a <span> around the
 # result with a title attribute if it does get chopped. Additionally, the
 # string is HTML-escaped.
 sub chop_and_escape_str {
-	my $str = shift;
-	my $len = shift;
-	my $add_len = shift || 10;
+	my ($str) = @_;
 
-	my $chopped = chop_str($str, $len, $add_len);
+	my $chopped = chop_str(@_);
 	if ($chopped eq $str) {
 		return esc_html($chopped);
 	} else {
@@ -3791,11 +3833,11 @@ sub git_search_grep_body {
 		foreach my $line (@$comment) {
 			if ($line =~ m/^(.*)($search_regexp)(.*)$/i) {
 				my ($lead, $match, $trail) = ($1, $2, $3);
-				$match = chop_str($match, 70, 5);       # in case match is very long
-				my $contextlen = int((80 - length($match))/2); # for the remainder
-				$contextlen = 30 if ($contextlen > 30); # but not too much
-				$lead  = chop_str($lead,  $contextlen, 10);
-				$trail = chop_str($trail, $contextlen, 10);
+				$match = chop_str($match, 70, 5, -cut=>'center');
+				my $contextlen = int((80 - length($match))/2);
+				$contextlen = 30 if ($contextlen > 30);
+				$lead  = chop_str($lead,  $contextlen, 10, -cut=>'left');
+				$trail = chop_str($trail, $contextlen, 10, -cut=>'right');
 
 				$lead  = esc_html($lead);
 				$match = esc_html($match);