X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FMsgIter.pm;h=ce08ff846ee95dd281bdb3f3aee6312e665cde8e;hb=3c39f9c942a6975245fda878e9b957d8d3367662;hp=d0dd82fb3e1dc1cd676bf91380041b20e1a0de5a;hpb=4f7977b42aab1595b3a45b41e19499b38c46c8cc;p=public-inbox.git

diff --git a/lib/PublicInbox/MsgIter.pm b/lib/PublicInbox/MsgIter.pm
index d0dd82fb..ce08ff84 100644
--- a/lib/PublicInbox/MsgIter.pm
+++ b/lib/PublicInbox/MsgIter.pm
@@ -1,11 +1,13 @@
-# Copyright (C) 2016 all contributors <meta@public-inbox.org>
+# Copyright (C) 2016-2019 all contributors <meta@public-inbox.org>
 # License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
-#
+
+# read-only utilities for Email::MIME
 package PublicInbox::MsgIter;
 use strict;
 use warnings;
 use base qw(Exporter);
-our @EXPORT = qw(msg_iter);
+our @EXPORT = qw(msg_iter msg_part_text);
+use PublicInbox::MIME;
 
 # Like Email::MIME::walk_parts, but this is:
 # * non-recursive
@@ -33,4 +35,27 @@ sub msg_iter ($$) {
 	}
 }
 
+sub msg_part_text ($$) {
+	my ($part, $ct) = @_;
+
+	my $s = eval { $part->body_str };
+	my $err = $@;
+
+	# text/plain is the default, multipart/mixed happened a few
+	# times when it should not have been:
+	#   <87llgalspt.fsf@free.fr>
+	#   <200308111450.h7BEoOu20077@mail.osdl.org>
+	if ($ct =~ m!\btext/plain\b!i || $ct =~ m!\bmultipart/mixed\b!i) {
+		# Try to assume UTF-8 because Alpine seems to
+		# do wacky things and set charset=X-UNKNOWN
+		$part->charset_set('UTF-8');
+		$s = eval { $part->body_str };
+
+		# If forcing charset=UTF-8 failed,
+		# caller will warn further down...
+		$s = $part->body if $@;
+	}
+	($s, $err);
+}
+
 1;