switch read-only Email::Simple users to Eml

Since PublicInbox::Eml doesn't parse MIME subparts
up front, it can replace most uses of Email::Simple
without performance penalty.

This will eventually allow us to lower overall internal
API footprint by not having to keep the MIME vs Simple
distinction.

diff --git a/lib/PublicInbox/Mbox.pm b/lib/PublicInbox/Mbox.pm
index 97bec5e79a3b468b88faa0b2e8ac72bbf198552f..94e61d4d2ffdd99b3a5c5a9b2d14f2ca5bbfc1d5 100644 (file)
--- a/lib/PublicInbox/Mbox.pm
+++ b/lib/PublicInbox/Mbox.pm
@@ -14,19 +14,13 @@ use PublicInbox::MID qw/mid_escape/;
 use PublicInbox::Hval qw/to_filename/;
 use PublicInbox::Smsg;
 use PublicInbox::WwwStream qw(html_oneshot);
-use Email::Simple;
-use Email::MIME::Encode;
+use PublicInbox::Eml;
 
 sub subject_fn ($) {
        my ($hdr) = @_;
-       my $fn = $hdr->header('Subject');
+       my $fn = $hdr->header_str('Subject');
        return 'no-subject' if (!defined($fn) || $fn eq '');
 
-       # no need for full Email::MIME, here
-       if ($fn =~ /=\?/) {
-               eval { $fn = Encode::decode('MIME-Header', $fn) };
-               return 'no-subject' if $@;
-       }
        $fn =~ s/^re:\s+//i;
        $fn eq '' ? 'no-subject' : to_filename($fn);
 }
@@ -51,7 +45,7 @@ sub getline {
        my $ibx = $ctx->{-inbox};
        $next = $ibx->over->next_by_mid($ctx->{mid}, \$id, \$prev);
        $mref = $ibx->msg_by_smsg($cur) or return;
-       $hdr = Email::Simple->new($mref)->header_obj;
+       $hdr = PublicInbox::Eml->new($mref)->header_obj;
        @$more = ($ctx, $id, $prev, $next); # $next may be undef, here
        msg_hdr($ctx, $hdr) . msg_body($$mref);
 }
@@ -72,7 +66,7 @@ sub emit_raw {
        } else {
                $mref = $ibx->msg_by_mid($mid) or return;
        }
-       my $hdr = Email::Simple->new($mref)->header_obj;
+       my $hdr = PublicInbox::Eml->new($mref)->header_obj;
        $more = [ $ctx, $id, $prev, $next, $mref, $hdr ]; # for ->getline
        my $fn = subject_fn($hdr);
        my @hdr = ('Content-Type');
@@ -114,7 +108,7 @@ sub msg_hdr ($$;$) {
        for (my $i = 0; $i < @append; $i += 2) {
                my $k = $append[$i];
                my $v = $append[$i + 1];
-               my @v = $header_obj->header($k);
+               my @v = $header_obj->header_raw($k);
                foreach (@v) {
                        if ($v eq $_) {
                                $v = undef;

diff --git a/lib/PublicInbox/MboxGz.pm b/lib/PublicInbox/MboxGz.pm
index e506de3da0ea52566e958ab8ac09462d8c1217db..f7fc4afc147fab95da0df4f4ce483f78f942fa68 100644 (file)
--- a/lib/PublicInbox/MboxGz.pm
+++ b/lib/PublicInbox/MboxGz.pm
@@ -3,7 +3,7 @@
 package PublicInbox::MboxGz;
 use strict;
 use warnings;
-use Email::Simple;
+use PublicInbox::Eml;
 use PublicInbox::Hval qw/to_filename/;
 use PublicInbox::Mbox;
 use Compress::Raw::Zlib qw(Z_FINISH Z_OK);
@@ -41,7 +41,7 @@ sub getline {
        my $buf = delete($self->{buf});
        while (my $smsg = $self->{cb}->($ctx)) {
                my $mref = $ctx->{-inbox}->msg_by_smsg($smsg) or next;
-               my $h = Email::Simple->new($mref)->header_obj;
+               my $h = PublicInbox::Eml->new($mref)->header_obj;
 
                my $err = $gz->deflate(
                        PublicInbox::Mbox::msg_hdr($ctx, $h, $smsg->{mid}),

diff --git a/lib/PublicInbox/NNTP.pm b/lib/PublicInbox/NNTP.pm
index e9c66cd1c7038251ff8081925ad452441333b8a6..54207500dd8db5576658ae993169efd10318fdc5 100644 (file)
--- a/lib/PublicInbox/NNTP.pm
+++ b/lib/PublicInbox/NNTP.pm
@@ -8,7 +8,7 @@ use warnings;
 use base qw(PublicInbox::DS);
 use fields qw(nntpd article ng long_cb);
 use PublicInbox::MID qw(mid_escape $MID_EXTRACT);
-use Email::Simple;
+use PublicInbox::Eml;
 use POSIX qw(strftime);
 use PublicInbox::DS qw(now);
 use Digest::SHA qw(sha1_hex);
@@ -383,7 +383,7 @@ sub cmd_quit ($) {
 
 sub header_append ($$$) {
        my ($hdr, $k, $v) = @_;
-       my @v = $hdr->header($k);
+       my @v = $hdr->header_raw($k);
        foreach (@v) {
                return if $v eq $_;
        }
@@ -416,11 +416,11 @@ sub set_nntp_headers ($$$$$) {
        # leafnode (and maybe other NNTP clients) have trouble dealing
        # with v2 messages which have multiple Message-IDs (either due
        # to our own content-based dedupe or buggy git-send-email versions).
-       my @mids = $hdr->header('Message-ID');
+       my @mids = $hdr->header_raw('Message-ID');
        if (scalar(@mids) > 1) {
                my $mid0 = "<$mid>";
                $hdr->header_set('Message-ID', $mid0);
-               my @alt = $hdr->header('X-Alt-Message-ID');
+               my @alt = $hdr->header_raw('X-Alt-Message-ID');
                my %seen = map { $_ => 1 } (@alt, $mid0);
                push(@alt, grep { !$seen{$_}++ } @mids);
                $hdr->header_set('X-Alt-Message-ID', @alt);
@@ -478,10 +478,9 @@ found:
        my $smsg = $ng->over->get_art($n) or return $err;
        my $msg = $ng->msg_by_smsg($smsg) or return $err;
 
-       # Email::Simple->new will modify $msg in-place as documented
-       # in its manpage, so what's left is the body and we won't need
-       # to call Email::Simple::body(), later
-       my $hdr = Email::Simple->new($msg)->header_obj;
+       # PublicInbox::Eml->new will modify $msg in-place, so what's
+       # left is the body and we won't need to call ->body(), later
+       my $hdr = PublicInbox::Eml->new($msg)->header_obj;
        set_nntp_headers($self, $hdr, $ng, $n, $mid) if $set_headers;
        [ $n, $mid, $msg, $hdr ];
 }
@@ -511,9 +510,7 @@ sub msg_hdr_write ($$$) {
        $hdr =~ s/(?<!\r)\n/\r\n/sg; # Alpine barfs without this
 
        # for leafnode compatibility, we need to ensure Message-ID headers
-       # are only a single line.  We can't subclass Email::Simple::Header
-       # and override _default_fold_at in here, either; since that won't
-       # affect messages already in the archive.
+       # are only a single line.
        $hdr =~ s/^(Message-ID:)[ \t]*\r\n[ \t]+([^\r]+)\r\n/$1 $2\r\n/igsm;
        $hdr .= "\r\n" if $body_follows;
        $self->msg_more($hdr);

diff --git a/lib/PublicInbox/WWW.pm b/lib/PublicInbox/WWW.pm
index 3a428218f783c85849085a1fec549fcaf260adfc..1ff857dec0585b81c04dcbf31bb46d2e0f3a4d4f 100644 (file)
--- a/lib/PublicInbox/WWW.pm
+++ b/lib/PublicInbox/WWW.pm
@@ -22,6 +22,7 @@ use PublicInbox::MID qw(mid_escape);
 use PublicInbox::GitHTTPBackend;
 use PublicInbox::UserContent;
 use PublicInbox::WwwStatic qw(r path_info_raw);
+use PublicInbox::Eml;
 
 # TODO: consider a routing tree now that we have more endpoints:
 our $INBOX_RE = qr!\A/([\w\-][\w\.\-]*)!;
@@ -231,9 +232,8 @@ sub invalid_inbox_mid {
                my ($x2, $x38) = ($1, $2);
                # this is horrifically wasteful for legacy URLs:
                my $str = $ctx->{-inbox}->msg_by_path("$x2/$x38") or return;
-               require Email::Simple;
-               my $s = Email::Simple->new($str);
-               $mid = PublicInbox::MID::mid_clean($s->header('Message-ID'));
+               my $s = PublicInbox::Eml->new($str);
+               $mid = PublicInbox::MID::mid_clean($s->header_raw('Message-ID'));
                return r301($ctx, $inbox, mid_escape($mid));
        }
        undef;