From: Eric Wong <e@yhbt.net>
To: meta@public-inbox.org
Subject: [PATCH 10/13] eml: remove dependency on Email::MIME::Encodings
Date: Thu, 7 May 2020 21:05:53 +0000 [thread overview]
Message-ID: <20200507210556.22995-11-e@yhbt.net> (raw)
In-Reply-To: <20200507210556.22995-1-e@yhbt.net>
Since Email::MIME usage is going away, Email::MIME::Encodings
might as well go away, too. We can also use fewer branches
and just rely on hash lookups, unlike E::M::E.
---
lib/PublicInbox/Eml.pm | 47 ++++++++++++++++++++++++++++++------------
1 file changed, 34 insertions(+), 13 deletions(-)
diff --git a/lib/PublicInbox/Eml.pm b/lib/PublicInbox/Eml.pm
index 1988bdb3..1adaff04 100644
--- a/lib/PublicInbox/Eml.pm
+++ b/lib/PublicInbox/Eml.pm
@@ -30,18 +30,24 @@ use v5.10.1;
use Carp qw(croak);
use Encode qw(find_encoding decode encode); # stdlib
use Text::Wrap qw(wrap); # stdlib, we need Perl 5.6+ for $huge
+use MIME::Base64 3.05; # Perl 5.10.0 / 5.9.2
+use MIME::QuotedPrint 3.05; # ditto
my $MIME_Header = find_encoding('MIME-Header');
use PublicInbox::EmlContentFoo qw(parse_content_type parse_content_disposition);
-use Email::MIME::Encodings;
$PublicInbox::EmlContentFoo::STRICT_PARAMS = 0;
our $MAXPARTS = 1000; # same as SpamAssassin
our $MAXDEPTH = 20; # seems enough, Perl sucks, here
our $MAXBOUNDLEN = 2048; # same as postfix
-my $NO_ENCODE_RE = qr/\A(?:7bit|8bit|binary)[ \t]*(?:;|$)?/i;
+my %MIME_ENC = (qp => \&enc_qp, base64 => \&encode_base64);
+my %MIME_DEC = (qp => \&dec_qp, base64 => \&decode_base64);
+$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 { $_ => 1 } qw(From To Cc Sender Reply-To);
my %DECODE_FULL = (
Subject => 1,
@@ -111,13 +117,6 @@ sub ct ($) {
$_[0]->{ct} //= parse_content_type(header($_[0], 'Content-Type'));
}
-sub body_decode ($$) {
- my $cte = header_raw($_[0], 'Content-Transfer-Encoding');
- ($cte) = ($cte =~ /([a-zA-Z0-9\-]+)/) if $cte; # For S/MIME, etc
- (!$cte || $cte =~ $NO_ENCODE_RE) ?
- $_[1] : Email::MIME::Encodings::decode($cte, $_[1], '7bit');
-}
-
# returns a queue of sub-parts iff it's worth descending into
# TODO: descend into message/rfc822 parts (Email::MIME didn't)
sub mp_descend ($$) {
@@ -197,6 +196,22 @@ sub each_part {
}
}
+sub enc_qp {
+ # prevent MIME::QuotedPrint from encoding CR as =0D since it's
+ # against RFCs and breaks MUAs
+ $_[0] =~ s/\r\n/\n/sg;
+ encode_qp($_[0], "\r\n");
+}
+
+sub dec_qp {
+ # RFC 2822 requires all lines to end in CRLF, though... :<
+ $_[0] = decode_qp($_[0]);
+ $_[0] =~ s/\n/\r\n/sg;
+ $_[0]
+}
+
+sub identity_codec { $_[0] }
+
########### compatibility section for existing Email::MIME uses #########
sub header_obj {
@@ -240,9 +255,9 @@ EOF
sub body_set {
my ($self, $body) = @_;
my $bdy = $self->{bdy} = ref($body) ? $body : \$body;
- my $cte = header_raw($self, 'Content-Transfer-Encoding');
- if ($cte && $cte !~ $NO_ENCODE_RE) {
- $$bdy = Email::MIME::Encodings::encode($cte, $$bdy)
+ if (my $cte = header_raw($self, 'Content-Transfer-Encoding')) {
+ my $enc = $MIME_ENC{lc($cte)} or croak("can't encode `$cte'");
+ $$bdy = $enc->($$bdy); # in-place
}
undef;
}
@@ -351,7 +366,13 @@ sub header_str {
sub body_raw { ${$_[0]->{bdy} // \''}; }
-sub body { body_decode($_[0], body_raw($_[0])) }
+sub body {
+ my $raw = body_raw($_[0]);
+ my $cte = header_raw($_[0], 'Content-Transfer-Encoding') or return $raw;
+ ($cte) = ($cte =~ /([a-zA-Z0-9\-]+)/) or return $raw; # For S/MIME, etc
+ my $dec = $MIME_DEC{lc($cte)} or return $raw;
+ $dec->($raw);
+}
sub body_str {
my ($self) = @_;
next prev parent reply other threads:[~2020-05-07 21:05 UTC|newest]
Thread overview: 15+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-05-07 21:05 [PATCH 00/13] eml: pure-Perl replacement for Email::MIME Eric Wong
2020-05-07 21:05 ` [PATCH 01/13] msg_iter: make ->each_part method for PublicInbox::MIME Eric Wong
2020-05-07 21:05 ` [PATCH 02/13] msg_iter: pass $idx as a scalar, not array Eric Wong
2020-05-07 21:05 ` [PATCH 03/13] filter/rubylang: avoid recursing subparts to strip trailers Eric Wong
2020-05-07 21:05 ` [PATCH 04/13] smsg: use capitalization for header retrieval Eric Wong
2020-05-07 21:05 ` [PATCH 05/13] eml: pure-Perl replacement for Email::MIME Eric Wong
2020-05-07 21:05 ` [PATCH 06/13] switch read-only Email::Simple users to Eml Eric Wong
2020-05-07 21:05 ` [PATCH 07/13] replace most uses of PublicInbox::MIME with Eml Eric Wong
2020-05-07 21:05 ` [PATCH 08/13] EmlContentFoo: Email::MIME::ContentType replacement Eric Wong
2020-05-07 21:05 ` [PATCH 09/13] EmlContentFoo: relax Encode version requirement Eric Wong
2020-05-07 21:05 ` Eric Wong [this message]
2020-05-07 21:05 ` [PATCH 11/13] xt: eml comparison tests Eric Wong
2020-05-08 4:47 ` Eric Wong
2020-05-07 21:05 ` [PATCH 12/13] remove most internal Email::MIME usage Eric Wong
2020-05-07 21:05 ` [PATCH 13/13] eml: drop trailing blank line on missing epilogue Eric Wong
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
List information: https://public-inbox.org/README
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20200507210556.22995-11-e@yhbt.net \
--to=e@yhbt.net \
--cc=meta@public-inbox.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).