From mboxrd@z Thu Jan  1 00:00:00 1970
Return-Path: <e@80x24.org>
X-Spam-Checker-Version: SpamAssassin 3.4.2 (2018-09-13) on dcvr.yhbt.net
X-Spam-Level: 
X-Spam-ASN:  
X-Spam-Status: No, score=-4.0 required=3.0 tests=ALL_TRUSTED,BAYES_00
	shortcircuit=no autolearn=ham autolearn_force=no version=3.4.2
Received: from localhost (dcvr.yhbt.net [127.0.0.1])
	by dcvr.yhbt.net (Postfix) with ESMTP id 894961F5AE
	for <meta@public-inbox.org>; Sat, 19 Jun 2021 03:22:28 +0000 (UTC)
From: Eric Wong <e@80x24.org>
To: meta@public-inbox.org
Subject: [PATCH] view: extra check to for redundant messages in HTML view
Date: Sat, 19 Jun 2021 03:22:28 +0000
Message-Id: <20210619032228.27196-1-e@80x24.org>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
List-Id: <meta.public-inbox.org>

There appears to be some cases of duplicates appearing due to
-extindex.  I haven't nailed down the cause of it, yet, but
this should make things easier for readers using the PSGI
HTML interface in the meantime.

The raw mboxrd remains undeduplicated for now, and the
correct fix/workaround would be some fsck-like mode for
public-inbox-extindex.
---
 lib/PublicInbox/View.pm | 24 ++++++++++++++++--------
 1 file changed, 16 insertions(+), 8 deletions(-)

diff --git a/lib/PublicInbox/View.pm b/lib/PublicInbox/View.pm
index 530c878f..fc0cd77e 100644
--- a/lib/PublicInbox/View.pm
+++ b/lib/PublicInbox/View.pm
@@ -22,6 +22,7 @@ use PublicInbox::ViewDiff qw(flush_diff);
 use PublicInbox::Eml;
 use Time::Local qw(timegm);
 use PublicInbox::Smsg qw(subject_normalized);
+use PublicInbox::ContentHash qw(content_hash);
 use constant COLS => 72;
 use constant INDENT => '  ';
 use constant TCHILD => '` ';
@@ -35,9 +36,11 @@ sub msg_page_i {
 		$ctx->{mhref} = ($ctx->{nr} || $ctx->{smsg}) ?
 				"../${\mid_href($smsg->{mid})}/" : '';
 		my $obuf = $ctx->{obuf} = _msg_page_prepare_obuf($eml, $ctx);
-		multipart_text_as_html($eml, $ctx);
+		if (length($$obuf)) {
+			multipart_text_as_html($eml, $ctx);
+			$$obuf .= '</pre><hr>';
+		}
 		delete $ctx->{obuf};
-		$$obuf .= '</pre><hr>';
 		$$obuf .= html_footer($ctx, $ctx->{first_hdr}) if !$ctx->{smsg};
 		$$obuf;
 	} else { # called by WwwStream::async_next or getline
@@ -53,9 +56,11 @@ sub no_over_html ($) {
 	$ctx->{mhref} = '';
 	PublicInbox::WwwStream::init($ctx);
 	my $obuf = $ctx->{obuf} = _msg_page_prepare_obuf($eml, $ctx);
-	multipart_text_as_html($eml, $ctx);
+	if (length($$obuf)) {
+		multipart_text_as_html($eml, $ctx);
+		$$obuf .= '</pre><hr>';
+	}
 	delete $ctx->{obuf};
-	$$obuf .= '</pre><hr>';
 	eval { $$obuf .= html_footer($ctx, $eml) };
 	html_oneshot($ctx, 200, $obuf);
 }
@@ -646,13 +651,16 @@ sub _msg_page_prepare_obuf {
 	my $mids = mids_for_index($eml);
 	my $nr = $ctx->{nr}++;
 	if ($nr) { # unlikely
+		if ($ctx->{chash} eq content_hash($eml)) {
+			warn "W: BUG? @$mids not deduplicated properly\n";
+			return \$rv;
+		}
+		$rv .=
+"<pre>WARNING: multiple messages have this Message-ID\n</pre>";
 		$rv .= '<pre>';
 	} else {
 		$ctx->{first_hdr} = $eml->header_obj;
-		if ($ctx->{smsg}) {
-			$rv .=
-"<pre>WARNING: multiple messages have this Message-ID\n</pre>";
-		}
+		$ctx->{chash} = content_hash($eml) if $ctx->{smsg}; # reused MID
 		$rv .= "<pre\nid=b>"; # anchor for body start
 	}
 	$ctx->{-upfx} = '../' if $over;