From mboxrd@z Thu Jan  1 00:00:00 1970
Return-Path: <e@80x24.org>
X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) 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=3.4.0
Received: from localhost (dcvr.yhbt.net [127.0.0.1])
	by dcvr.yhbt.net (Postfix) with ESMTP id 842952022A;
	Thu, 18 Aug 2016 01:39:41 +0000 (UTC)
From: Eric Wong <e@80x24.org>
To: meta@public-inbox.org
Cc: Thomas Ferris Nicolaisen <tfnico@gmail.com>,
	Johannes Schindelin <Johannes.Schindelin@gmx.de>
Subject: [PATCH 2/3] view: try to display bogus charsets for text/plain
Date: Thu, 18 Aug 2016 01:39:40 +0000
Message-Id: <20160818013941.8673-3-e@80x24.org>
In-Reply-To: <20160818013941.8673-1-e@80x24.org>
References: <20160818013941.8673-1-e@80x24.org>
List-Id: <meta@public-inbox.org>

Alpine seems to set charset=X-UNKNOWN for valid UTF-8 text,
which causes Email::MIME::body_str to fail as X-UNKNOWN
is not a valid encoding.  So, blindly display the body
as plain-text but warn users about possibly mangled text.

Reported-by: Thomas Ferris Nicolaisen <tfnico@gmail.com>
---
 lib/PublicInbox/View.pm | 30 +++++++++++++++++++++++-------
 1 file changed, 23 insertions(+), 7 deletions(-)

diff --git a/lib/PublicInbox/View.pm b/lib/PublicInbox/View.pm
index 3057221..3f0e122 100644
--- a/lib/PublicInbox/View.pm
+++ b/lib/PublicInbox/View.pm
@@ -407,14 +407,17 @@ sub flush_quote {
 	$$s .= qq(<span\nclass="q">) . $rv . '</span>'
 }
 
-sub attach_link ($$$$) {
-	my ($upfx, $ct, $p, $fn) = @_;
+sub attach_link ($$$$;$) {
+	my ($upfx, $ct, $p, $fn, $err) = @_;
 	my ($part, $depth, @idx) = @$p;
 	my $nl = $idx[-1] > 1 ? "\n" : '';
 	my $idx = join('.', @idx);
 	my $size = bytes::length($part->body);
 	$ct ||= 'text/plain';
-	$ct =~ s/;.*//; # no attributes
+
+	# hide attributes normally, unless we want to aid users in
+	# spotting MUA problems:
+	$ct =~ s/;.*// unless $err;
 	$ct = ascii_html($ct);
 	my $desc = $part->header('Content-Description');
 	$desc = $fn unless defined $desc;
@@ -427,7 +430,12 @@ sub attach_link ($$$$) {
 	} else {
 		$sfn = 'a.bin';
 	}
-	my $ret = qq($nl<a\nhref="$upfx$idx-$sfn">[-- Attachment #$idx: );
+	my $ret = qq($nl<a\nhref="$upfx$idx-$sfn">);
+	if ($err) {
+		$ret .=
+"[-- Warning: decoded text below may be mangled --]\n";
+	}
+	$ret .= "[-- Attachment #$idx: ";
 	my $ts = "Type: $ct, Size: $size bytes";
 	$ret .= ($desc eq '') ? "$ts --]" : "$desc --]\n[-- $ts --]";
 	$ret .= "</a>\n";
@@ -446,12 +454,20 @@ sub add_text_body {
 	my $s = eval { $part->body_str };
 
 	# badly-encoded message? tell the world about it!
-	return attach_link($upfx, $ct, $p, $fn) if $@;
+	my $err = $@;
+	if ($err) {
+		if ($ct =~ m!\btext/plain\b!i) {
+			# attach_link will warn further down...
+			$s = $part->body;
+		} else {
+			return attach_link($upfx, $ct, $p, $fn);
+		}
+	}
 
 	my @lines = split(/^/m, $s);
 	$s = '';
-	if (defined($fn) || $depth > 0) {
-		$s .= attach_link($upfx, $ct, $p, $fn);
+	if (defined($fn) || $depth > 0 || $err) {
+		$s .= attach_link($upfx, $ct, $p, $fn, $err);
 		$s .= "\n";
 	}
 	my @quot;
-- 
EW