eml: header_raw converts octets to Perl UTF-8

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

diff --git a/lib/PublicInbox/Smsg.pm b/lib/PublicInbox/Smsg.pm
index a2f54507425f546785754770ba49fa87cb26417d..b132381b4ab2c3a93fd78b1fe042d1710a2c3fe8 100644 (file)
--- a/lib/PublicInbox/Smsg.pm
+++ b/lib/PublicInbox/Smsg.pm
@@ -9,13 +9,15 @@
 # large threads in our WWW UI and the NNTP range responses.
 package PublicInbox::Smsg;
 use strict;
-use warnings;
-use base qw(Exporter);
+use v5.10.1;
+use parent qw(Exporter);
 our @EXPORT_OK = qw(subject_normalized);
 use PublicInbox::MID qw(mids references);
 use PublicInbox::Address;
 use PublicInbox::MsgTime qw(msg_timestamp msg_datestamp);
 
+sub oidbin { pack('H*', $_[0]->{blob}) }
+
 sub to_doc_data {
        my ($self) = @_;
        join("\n",
@@ -97,9 +99,6 @@ sub populate {
                # to protect git and NNTP clients
                $val =~ tr/\0\t\n/   /;
 
-               # rare: in case headers have wide chars (not RFC2047-encoded)
-               utf8::decode($val);
-
                # lower-case fields for read-only stuff
                $self->{lc($f)} = $val;
 
@@ -113,8 +112,10 @@ sub populate {
                $self->{$f} = $val if $val ne '';
        }
        $sync //= {};
-       $self->{-ds} = [ my @ds = msg_datestamp($hdr, $sync->{autime}) ];
-       $self->{-ts} = [ my @ts = msg_timestamp($hdr, $sync->{cotime}) ];
+       my @ds = msg_datestamp($hdr, $sync->{autime} // $self->{ds});
+       my @ts = msg_timestamp($hdr, $sync->{cotime} // $self->{ts});
+       $self->{-ds} = \@ds;
+       $self->{-ts} = \@ts;
        $self->{ds} //= $ds[0]; # no zone
        $self->{ts} //= $ts[0];
        $self->{mid} //= mids($hdr)->[0];