handle "multipart/mixed" messages which are not multipart

[public-inbox.git] / lib / PublicInbox / MsgIter.pm

diff --git a/lib/PublicInbox/MsgIter.pm b/lib/PublicInbox/MsgIter.pm
index a795f6175b93003118e64b229e10197f94b5c847..9e2d797fecc240d4f191ba8f3fe7fd84b410148e 100644 (file)
--- a/lib/PublicInbox/MsgIter.pm
+++ b/lib/PublicInbox/MsgIter.pm
@@ -5,7 +5,7 @@ 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:
@@ -34,4 +34,27 @@ 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;