# Copyright (C) 2015-2020 all contributors <meta@public-inbox.org>
# License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
-# Streaming (via getline) interface for formatting messages as an mboxrd.
-# Used by the PSGI web interface.
-#
-# public-inbox-httpd favors "getline" response bodies to take a
-# "pull"-based approach to feeding slow clients (as opposed to a
-# more common "push" model)
+# Streaming interface for mboxrd HTTP responses
+# See PublicInbox::GzipFilter for details.
package PublicInbox::Mbox;
use strict;
-use warnings;
+use parent 'PublicInbox::GzipFilter';
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;
-
-sub subject_fn ($) {
- my ($hdr) = @_;
- my $fn = $hdr->header('Subject');
- return 'no-subject' if (!defined($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);
-}
-
-sub mb_stream {
- my ($more) = @_;
- bless $more, 'PublicInbox::Mbox';
-}
+use PublicInbox::Eml;
# called by PSGI server as body response
# this gets called twice for every message, once to return the header,
# once to retrieve the body
sub getline {
- my ($more) = @_; # self
- my ($ctx, $id, $prev, $next, $mref, $hdr) = @$more;
- if ($hdr) { # first message hits this, only
- pop @$more; # $hdr
- pop @$more; # $mref
- return msg_hdr($ctx, $hdr) . msg_body($$mref);
- }
- my $cur = $next or return;
+ my ($ctx) = @_; # ctx
+ my $smsg = $ctx->{smsg} or return;
my $ibx = $ctx->{-inbox};
- $next = $ibx->over->next_by_mid($ctx->{mid}, \$id, \$prev);
- $mref = $ibx->msg_by_smsg($cur) or return;
- $hdr = Email::Simple->new($mref)->header_obj;
- @$more = ($ctx, $id, $prev, $next); # $next may be undef, here
- msg_hdr($ctx, $hdr) . msg_body($$mref);
+ my $eml = $ibx->smsg_eml($smsg) or return;
+ my $n = $ctx->{smsg} = $ibx->over->next_by_mid(@{$ctx->{next_arg}});
+ $ctx->zmore(msg_hdr($ctx, $eml, $smsg->{mid}));
+ if ($n) {
+ $ctx->translate(msg_body($eml));
+ } else { # last message
+ $ctx->zmore(msg_body($eml));
+ $ctx->zflush;
+ }
+}
+
+# called by PublicInbox::DS::write
+sub async_next {
+ my ($http) = @_; # PublicInbox::HTTP
+ my $ctx = $http->{forward} or return; # client aborted
+ eval {
+ my $smsg = $ctx->{smsg} or return $ctx->close;
+ $ctx->smsg_blob($smsg);
+ };
+ warn "E: $@" if $@;
}
-sub close {} # noop
+sub async_eml { # ->{async_eml} for async_blob_cb
+ my ($ctx, $eml) = @_;
+ my $smsg = delete $ctx->{smsg};
+ # next message
+ $ctx->{smsg} = $ctx->{-inbox}->over->next_by_mid(@{$ctx->{next_arg}});
-# /$INBOX/$MESSAGE_ID/raw
-sub emit_raw {
- my ($ctx) = @_;
- my $mid = $ctx->{mid};
- my $ibx = $ctx->{-inbox};
- $ctx->{base_url} = $ibx->base_url($ctx->{env});
- my ($mref, $more, $id, $prev, $next);
- if (my $over = $ibx->over) {
- my $smsg = $over->next_by_mid($mid, \$id, \$prev) or return;
- $mref = $ibx->msg_by_smsg($smsg) or return;
- $next = $over->next_by_mid($mid, \$id, \$prev);
- } else {
- $mref = $ibx->msg_by_mid($mid) or return;
- }
- my $hdr = Email::Simple->new($mref)->header_obj;
- $more = [ $ctx, $id, $prev, $next, $mref, $hdr ]; # for ->getline
- my $fn = subject_fn($hdr);
+ $ctx->zmore(msg_hdr($ctx, $eml, $smsg->{mid}));
+ $ctx->{http_out}->write($ctx->translate(msg_body($eml)));
+}
+
+sub res_hdr ($$) {
+ my ($ctx, $subject) = @_;
+ my $fn = $subject // 'no-subject';
+ $fn =~ s/^re:\s+//i;
+ $fn = $fn eq '' ? 'no-subject' : to_filename($fn);
my @hdr = ('Content-Type');
- if ($ibx->{obfuscate}) {
+ if ($ctx->{-inbox}->{obfuscate}) {
# obfuscation is stupid, but maybe scrapers are, too...
push @hdr, 'application/mbox';
$fn .= '.mbox';
$fn .= '.txt';
}
push @hdr, 'Content-Disposition', "inline; filename=$fn";
- [ 200, \@hdr, mb_stream($more) ];
+ \@hdr;
+}
+
+# for rare cases where v1 inboxes aren't indexed w/ ->over at all
+sub no_over_raw ($) {
+ my ($ctx) = @_;
+ my $mref = $ctx->{-inbox}->msg_by_mid($ctx->{mid}) or return;
+ my $eml = PublicInbox::Eml->new($mref);
+ [ 200, res_hdr($ctx, $eml->header_str('Subject')),
+ [ msg_hdr($ctx, $eml, $ctx->{mid}) . msg_body($eml) ] ]
+}
+
+# /$INBOX/$MESSAGE_ID/raw
+sub emit_raw {
+ my ($ctx) = @_;
+ $ctx->{base_url} = $ctx->{-inbox}->base_url($ctx->{env});
+ my $over = $ctx->{-inbox}->over or return no_over_raw($ctx);
+ my ($id, $prev);
+ my $mip = $ctx->{next_arg} = [ $ctx->{mid}, \$id, \$prev ];
+ my $smsg = $ctx->{smsg} = $over->next_by_mid(@$mip) or return;
+ my $res_hdr = res_hdr($ctx, $smsg->{subject});
+ bless $ctx, __PACKAGE__;
+ $ctx->psgi_response(200, $res_hdr, \&async_next, \&async_eml);
}
sub msg_hdr ($$;$) {
- my ($ctx, $header_obj, $mid) = @_;
+ my ($ctx, $eml, $mid) = @_;
+ my $header_obj = $eml->header_obj;
# drop potentially confusing headers, ssoma already should've dropped
# Lines and Content-Length
'List-Post', "<mailto:$ibx->{-primary_address}>",
);
my $crlf = $header_obj->crlf;
- my $buf = 'From mboxrd@z Thu Jan 1 00:00:00 1970' . $crlf .
- $header_obj->as_string;
+ my $buf = $header_obj->as_string;
+ # fixup old bug from import (pre-a0c07cba0e5d8b6a)
+ $buf =~ s/\A[\r\n]*From [^\r\n]*\r?\n//s;
+ $buf = "From mboxrd\@z Thu Jan 1 00:00:00 1970" . $crlf . $buf;
+
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 $_) {
$v = undef;
}
sub msg_body ($) {
+ my $bdy = $_[0]->{bdy} // return "\n";
# mboxrd quoting style
# https://en.wikipedia.org/wiki/Mbox#Modified_mbox
# https://www.loc.gov/preservation/digital/formats/fdd/fdd000385.shtml
# https://web.archive.org/http://www.qmail.org/man/man5/mbox.html
- $_[0] =~ s/^(>*From )/>$1/gm;
- $_[0] .= "\n";
+ $$bdy =~ s/^(>*From )/>$1/gm;
+ $$bdy .= "\n";
}
sub thread_cb {
sub thread_mbox {
my ($ctx, $over, $sfx) = @_;
- eval { require PublicInbox::MboxGz };
- return need_gzip($ctx) if $@;
my $msgs = $ctx->{msgs} = $over->get_thread($ctx->{mid}, {});
return [404, [qw(Content-Type text/plain)], []] if !@$msgs;
$ctx->{prev} = $msgs->[-1];
$ctx->{over} = $over; # bump refcnt
- PublicInbox::MboxGz->response($ctx, \&thread_cb, $msgs->[0]->subject);
+ require PublicInbox::MboxGz;
+ PublicInbox::MboxGz::mbox_gz($ctx, \&thread_cb, $msgs->[0]->{subject});
}
sub emit_range {
return PublicInbox::WWW::need($ctx, 'Overview');
$ctx->{ids} = $ids;
$ctx->{prev} = $prev;
- return PublicInbox::MboxGz->response($ctx, \&all_ids_cb, 'all');
+ require PublicInbox::MboxGz;
+ PublicInbox::MboxGz::mbox_gz($ctx, \&all_ids_cb, 'all');
}
sub results_cb {
sub mbox_all {
my ($ctx, $query) = @_;
- eval { require PublicInbox::MboxGz };
- return need_gzip($ctx) if $@;
return mbox_all_ids($ctx) if $query eq '';
my $qopts = $ctx->{qopts} = { mset => 2 };
my $srch = $ctx->{srch} = $ctx->{-inbox}->search or
["No results found\n"]];
$ctx->{iter} = 0;
$ctx->{query} = $query;
- PublicInbox::MboxGz->response($ctx, \&results_cb, 'results-'.$query);
-}
-
-sub need_gzip {
- html_oneshot($_[0], 501, \<<EOF);
-<pre>gzipped mbox not available
-
-The administrator needs to install the Compress::Raw::Zlib Perl module
-to support gzipped mboxes.
-
-<a href="../">Return to index</a></pre>
-EOF
+ require PublicInbox::MboxGz;
+ PublicInbox::MboxGz::mbox_gz($ctx, \&results_cb, 'results-'.$query);
}
1;