From mboxrd@z Thu Jan  1 00:00:00 1970
Return-Path: <normalperson@yhbt.net>
X-Spam-Checker-Version: SpamAssassin 3.3.2 (2011-06-06) on dcvr.yhbt.net
X-Spam-Level: 
X-Spam-ASN: 
X-Spam-Status: No, score=-3.5 required=3.0 tests=ALL_TRUSTED,BAYES_00,
 RP_MATCHES_RCVD shortcircuit=no autolearn=unavailable version=3.3.2
X-Original-To: meta@public-inbox.org
Received: from localhost (dcvr.yhbt.net [127.0.0.1]) by dcvr.yhbt.net
 (Postfix) with ESMTP id 8987F1F81A for <meta@public-inbox.org>; Tue, 18 Aug
 2015 01:21:10 +0000 (UTC)
From: Eric Wong <e@80x24.org>
To: meta@public-inbox.org
Subject: [PATCH 1/5] view: cleaner Message-ID filtering for References
Date: Tue, 18 Aug 2015 01:21:06 +0000
Message-Id: <1439860870-8086-1-git-send-email-e@80x24.org>
List-Id: <meta@public-inbox.org>

Avoid compiling a weird and potentially fragile regexp every
time and use the same logic as our search module to dedupe
References.
---
 lib/PublicInbox/View.pm | 27 +++++++++++++++++----------
 1 file changed, 17 insertions(+), 10 deletions(-)

diff --git a/lib/PublicInbox/View.pm b/lib/PublicInbox/View.pm
index 6fbc366..b0b8e14 100644
--- a/lib/PublicInbox/View.pm
+++ b/lib/PublicInbox/View.pm
@@ -395,10 +395,19 @@ sub headers_to_html_header {
 
 	my $refs = $header_obj->header_raw('References');
 	if ($refs) {
-		$refs =~ s/\s*\Q$irt\E\s*// if (defined $irt);
-		my @refs = ($refs =~ /<([^>]+)>/g);
+		# avoid redundant URLs wasting bandwidth
+		my %seen;
+		$seen{mid_clean($irt)} = 1 if defined $irt;
+		my @refs;
+		my @raw_refs = ($refs =~ /<([^>]+)>/g);
+		foreach my $ref (@raw_refs) {
+			next if $seen{$ref};
+			$seen{$ref} = 1;
+			push @refs, linkify_ref($ref);
+		}
+
 		if (@refs) {
-			$rv .= 'References: '. linkify_refs(@refs) . "\n";
+			$rv .= 'References: '. join(' ', @refs) . "\n";
 		}
 	}
 
@@ -466,13 +475,11 @@ sub html_footer {
 	"$irt<a\nhref=\"" . ascii_html($href) . '">reply</a>' . $idx;
 }
 
-sub linkify_refs {
-	join(' ', map {
-		my $v = PublicInbox::Hval->new_msgid($_);
-		my $html = $v->as_html;
-		my $href = $v->as_href;
-		"&lt;<a\nhref=\"$href.html\">$html</a>&gt;";
-	} @_);
+sub linkify_ref {
+	my $v = PublicInbox::Hval->new_msgid($_[0]);
+	my $html = $v->as_html;
+	my $href = $v->as_href;
+	"&lt;<a\nhref=\"$href.html\">$html</a>&gt;";
 }
 
 sub anchor_for {
-- 
EW