get rid of unnecessary bytes::length usage

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

diff --git a/lib/PublicInbox/Eml.pm b/lib/PublicInbox/Eml.pm
index 4d3fffc0387ae7653653dbae561ab03551789c29..955d6a96a51c12b549478145afd45491dd5c9e25 100644 (file)
--- a/lib/PublicInbox/Eml.pm
+++ b/lib/PublicInbox/Eml.pm
@@ -1,4 +1,4 @@
-# Copyright (C) 2020 all contributors <meta@public-inbox.org>
+# Copyright (C) 2020-2021 all contributors <meta@public-inbox.org>
 # License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
 #
 # Lazy MIME parser, it still slurps the full message but keeps short
@@ -51,7 +51,9 @@ $MIME_ENC{quotedprint} = $MIME_ENC{'quoted-printable'} = $MIME_ENC{qp};
 $MIME_DEC{quotedprint} = $MIME_DEC{'quoted-printable'} = $MIME_DEC{qp};
 $MIME_ENC{$_} = \&identity_codec for qw(7bit 8bit binary);
 
-my %DECODE_ADDRESS = map { $_ => 1 } qw(From To Cc Sender Reply-To);
+my %DECODE_ADDRESS = map {
+       ($_ => 1, "Resent-$_" => 1)
+} qw(From To Cc Sender Reply-To Bcc);
 my %DECODE_FULL = (
        Subject => 1,
        'Content-Description' => 1,
@@ -217,7 +219,7 @@ sub mp_descend ($$) {
                # There's also a case where quoted text showed up in the
                # preamble
                # <20060515162817.65F0F1BBAE@citi.umich.edu>
-               unshift(@parts, new_sub(undef, \$pre)) if $pre =~ /:/s;
+               unshift(@parts, new_sub(undef, \$pre)) if index($pre, ':') >= 0;
                return \@parts;
        }
        # "multipart", but no boundary found, treat as single part
@@ -234,6 +236,7 @@ sub mp_descend ($$) {
 # $cb - user-supplied callback sub
 # $arg - user-supplied arg (think pthread_create)
 # $once - unref body scalar during iteration
+# $all - used by IMAP server, only
 sub each_part {
        my ($self, $cb, $arg, $once, $all) = @_;
        my $p = mp_descend($self, $once // 0) or
@@ -332,7 +335,7 @@ sub body_set {
 sub body_str_set {
        my ($self, $body_str) = @_;
        my $charset = ct($self)->{attributes}->{charset} or
-               Carp::confess('body_str was given, but no charset is defined');
+               croak('body_str was given, but no charset is defined');
        body_set($self, \(encode($charset, $body_str, Encode::FB_CROAK)));
 }
 
@@ -454,7 +457,7 @@ sub body_str {
                if ($STR_TYPE{$ct->{type}} && $STR_SUBTYPE{$ct->{subtype}}) {
                        return body($self);
                }
-               Carp::confess("can't get body as a string for ",
+               croak("can't get body as a string for ",
                        join("\n\t", header_raw($self, 'Content-Type')));
        }
        decode($charset, body($self), Encode::FB_CROAK);
@@ -477,6 +480,25 @@ sub charset_set {
 
 sub crlf { $_[0]->{crlf} // "\n" }
 
+# warnings to ignore when handling spam mailboxes and maybe other places
+sub warn_ignore {
+       my $s = "@_";
+       # Email::Address::XS warnings
+       $s =~ /^Argument contains empty /
+       || $s =~ /^Element at index [0-9]+.*? contains /
+       # PublicInbox::MsgTime
+       || $s =~ /^bogus TZ offset: .+?, ignoring and assuming \+0000/
+       || $s =~ /^bad Date: .+? in /
+       # Encode::Unicode::UTF7
+       || $s =~ /^Bad UTF7 data escape at /
+}
+
+# this expects to be RHS in this assignment: "local $SIG{__WARN__} = ..."
+sub warn_ignore_cb {
+       my $cb = $SIG{__WARN__} // \&CORE::warn;
+       sub { $cb->(@_) unless warn_ignore(@_) }
+}
+
 sub willneed { re_memo($_) for @_ }
 
 willneed(qw(From To Cc Date Subject Content-Type In-Reply-To References