-# Copyright (C) 2015-2018 all contributors <meta@public-inbox.org>
+# Copyright (C) 2015-2020 all contributors <meta@public-inbox.org>
# License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
-# Streaming interface for formatting messages as an mboxrd.
-# Used by the web interface
+# 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)
package PublicInbox::Mbox;
use strict;
use warnings;
-use PublicInbox::MID qw/mid_clean mid_escape/;
+use PublicInbox::MID qw/mid_escape/;
use PublicInbox::Hval qw/to_filename/;
-use Email::Simple;
-use Email::MIME::Encode;
-
-sub subject_fn ($) {
- my ($simple) = @_;
- my $fn = $simple->header('Subject');
- return 'no-subject' unless defined($fn);
-
- # no need for full Email::MIME, here
- if ($fn =~ /=\?/) {
- eval { $fn = Encode::decode('MIME-Header', $fn) };
- $fn = 'no-subject' if $@;
- }
- $fn =~ s/^re:\s+//i;
- $fn = to_filename($fn);
- $fn eq '' ? 'no-subject' : $fn;
-}
-
-sub mb_stream {
- my ($more) = @_;
- bless $more, 'PublicInbox::Mbox';
-}
+use PublicInbox::Smsg;
+use PublicInbox::Eml;
+use PublicInbox::GitAsyncCat;
+use PublicInbox::GzipFilter qw(gzf_maybe);
# called by PSGI server as body response
+# this gets called twice for every message, once to return the header,
+# once to retrieve the body
sub getline {
- my ($more) = @_; # self
- my ($ctx, $id, $prev, $next, $cur) = @$more;
- if ($cur) { # first
- pop @$more;
- return msg_str($ctx, $cur);
- }
- $cur = $next or return;
+ my ($ctx) = @_; # ctx
+ my $smsg = $ctx->{smsg} or return;
my $ibx = $ctx->{-inbox};
- $next = $ibx->search->next_by_mid($ctx->{mid}, \$id, \$prev);
- @$more = ($ctx, $id, $prev, $next); # $next may be undef, here
- my $mref = $ibx->msg_by_smsg($cur) or return;
- msg_str($ctx, Email::Simple->new($mref));
+ my $eml = $ibx->smsg_eml($smsg) or return;
+ $ctx->{smsg} = $ibx->over->next_by_mid($ctx->{mid}, @{$ctx->{id_prev}});
+ msg_hdr($ctx, $eml, $smsg->{mid}) . msg_body($eml);
}
-sub close {} # noop
+sub close { !!delete($_[0]->{http_out}) }
-sub emit_raw {
+sub mbox_async_step ($) { # public-inbox-httpd-only
my ($ctx) = @_;
- my $mid = $ctx->{mid};
- my $ibx = $ctx->{-inbox};
- my $first;
- my $more;
- if (my $srch = $ibx->search) {
- my ($id, $prev);
- my $smsg = $srch->next_by_mid($mid, \$id, \$prev) or return;
- my $mref = $ibx->msg_by_smsg($smsg) or return;
- $first = Email::Simple->new($mref);
- my $next = $srch->next_by_mid($mid, \$id, \$prev);
- # $more is for ->getline
- $more = [ $ctx, $id, $prev, $next, $first ] if $next;
+ if (my $smsg = $ctx->{smsg}) {
+ git_async_cat($ctx->{-inbox}->git, $smsg->{blob},
+ \&mbox_blob_cb, $ctx);
+ } elsif (my $out = delete $ctx->{http_out}) {
+ $out->close;
+ }
+}
+
+# called by PublicInbox::DS::write
+sub mbox_async_next {
+ my ($http) = @_; # PublicInbox::HTTP
+ my $ctx = $http->{forward} or return; # client aborted
+ eval {
+ $ctx->{smsg} = $ctx->{-inbox}->over->next_by_mid(
+ $ctx->{mid}, @{$ctx->{id_prev}});
+ mbox_async_step($ctx);
+ };
+}
+
+# this is public-inbox-httpd-specific
+sub mbox_blob_cb { # git->cat_async callback
+ my ($bref, $oid, $type, $size, $ctx) = @_;
+ my $http = $ctx->{env}->{'psgix.io'} or return; # client abort
+ my $smsg = delete $ctx->{smsg} or die 'BUG: no smsg';
+ if (!defined($oid)) {
+ # it's possible to have TOCTOU if an admin runs
+ # public-inbox-(edit|purge), just move onto the next message
+ return $http->next_step(\&mbox_async_next);
} else {
- my $mref = $ibx->msg_by_mid($mid) or return;
- $first = Email::Simple->new($mref);
+ $smsg->{blob} eq $oid or die "BUG: $smsg->{blob} != $oid";
}
- return unless defined $first;
- my $fn = subject_fn($first);
+ my $eml = PublicInbox::Eml->new($bref);
+ $ctx->{http_out}->write(msg_hdr($ctx, $eml, $smsg->{mid}));
+ $ctx->{http_out}->write(msg_body($eml));
+ $http->next_step(\&mbox_async_next);
+}
+
+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, $more ? mb_stream($more) : [ msg_str($ctx, $first) ] ];
+ \@hdr;
}
-sub msg_str {
- my ($ctx, $simple, $mid) = @_; # Email::Simple object
- my $header_obj = $simple->header_obj;
+# 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) ] ]
+}
+
+sub stream_raw { # MboxGz response callback
+ my ($ctx) = @_;
+ delete($ctx->{smsg}) //
+ $ctx->{-inbox}->over->next_by_mid($ctx->{mid},
+ @{$ctx->{id_prev}});
+}
+
+# /$INBOX/$MESSAGE_ID/raw
+sub emit_raw {
+ my ($ctx) = @_;
+ my $env = $ctx->{env};
+ $ctx->{base_url} = $ctx->{-inbox}->base_url($env);
+ my $over = $ctx->{-inbox}->over or return no_over_raw($ctx);
+ my ($id, $prev);
+ my $smsg = $over->next_by_mid($ctx->{mid}, \$id, \$prev) or return;
+ $ctx->{smsg} = $smsg;
+ my $res_hdr = res_hdr($ctx, $smsg->{subject});
+ $ctx->{id_prev} = [ \$id, \$prev ];
+
+ if (my $gzf = gzf_maybe($res_hdr, $env)) {
+ $ctx->{gz} = delete $gzf->{gz};
+ require PublicInbox::MboxGz;
+ PublicInbox::MboxGz::response($ctx, \&stream_raw, $res_hdr);
+ } elsif ($env->{'pi-httpd.async'}) {
+ sub {
+ my ($wcb) = @_; # -httpd provided write callback
+ $ctx->{http_out} = $wcb->([200, $res_hdr]);
+ $ctx->{env}->{'psgix.io'}->{forward} = $ctx;
+ bless $ctx, __PACKAGE__;
+ mbox_async_step($ctx); # start stepping
+ };
+ } else { # generic PSGI code path
+ bless $ctx, __PACKAGE__; # respond to ->getline
+ [ 200, $res_hdr, $ctx ];
+ }
+}
+
+sub msg_hdr ($$;$) {
+ my ($ctx, $eml, $mid) = @_;
+ my $header_obj = $eml->header_obj;
# drop potentially confusing headers, ssoma already should've dropped
# Lines and Content-Length
$header_obj->header_set($d);
}
my $ibx = $ctx->{-inbox};
- my $base = $ibx->base_url($ctx->{env});
+ my $base = $ctx->{base_url};
$mid = $ctx->{mid} unless defined $mid;
$mid = mid_escape($mid);
my @append = (
'List-Archive', "<$base>",
'List-Post', "<mailto:$ibx->{-primary_address}>",
);
- my $crlf = $simple->crlf;
- my $buf = "From mboxrd\@z Thu Jan 1 00:00:00 1970\n" .
- $header_obj->as_string;
+ my $crlf = $header_obj->crlf;
+ 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;
$buf .= "$k: $v$crlf" if defined $v;
}
$buf .= $crlf;
+}
+sub msg_body ($) {
+ my $bdy = $_[0]->{bdy} // return "\n";
# mboxrd quoting style
- # ref: http://www.qmail.org/man/man5/mbox.html
- my $body = $simple->body;
- $body =~ s/^(>*From )/>$1/gm;
- $buf .= $body;
- $buf .= "\n";
+ # 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
+ $$bdy =~ s/^(>*From )/>$1/gm;
+ $$bdy .= "\n";
+}
+
+sub thread_cb {
+ my ($ctx) = @_;
+ my $msgs = $ctx->{msgs};
+ while (1) {
+ if (my $smsg = shift @$msgs) {
+ return $smsg;
+ }
+ # refill result set
+ $ctx->{msgs} = $msgs = $ctx->{over}->get_thread($ctx->{mid},
+ $ctx->{prev});
+ return unless @$msgs;
+ $ctx->{prev} = $msgs->[-1];
+ }
}
sub thread_mbox {
- my ($ctx, $srch, $sfx) = @_;
- eval { require IO::Compress::Gzip };
- return sub { need_gzip(@_) } if $@;
- my $mid = $ctx->{mid};
- my $msgs = $srch->get_thread($mid, {});
+ my ($ctx, $over, $sfx) = @_;
+ my $msgs = $ctx->{msgs} = $over->get_thread($ctx->{mid}, {});
return [404, [qw(Content-Type text/plain)], []] if !@$msgs;
- my $prev = $msgs->[-1];
- my $i = 0;
- my $cb = sub {
- while (1) {
- if (my $smsg = $msgs->[$i++]) {
- return $smsg;
- }
- # refill result set
- $msgs = $srch->get_thread($mid, $prev);
- return unless @$msgs;
- $prev = $msgs->[-1];
- $i = 0;
- }
- };
- PublicInbox::MboxGz->response($ctx, $cb, $msgs->[0]->subject);
+ $ctx->{prev} = $msgs->[-1];
+ $ctx->{over} = $over; # bump refcnt
+ require PublicInbox::MboxGz;
+ PublicInbox::MboxGz::mbox_gz($ctx, \&thread_cb, $msgs->[0]->{subject});
}
sub emit_range {
mbox_all($ctx, $query);
}
+sub all_ids_cb {
+ my ($ctx) = @_;
+ my $ids = $ctx->{ids};
+ do {
+ while ((my $num = shift @$ids)) {
+ my $smsg = $ctx->{over}->get_art($num) or next;
+ return $smsg;
+ }
+ $ctx->{ids} = $ids = $ctx->{mm}->ids_after(\($ctx->{prev}));
+ } while (@$ids);
+}
+
sub mbox_all_ids {
my ($ctx) = @_;
+ my $ibx = $ctx->{-inbox};
my $prev = 0;
- my $ids = $ctx->{-inbox}->mm->ids_after(\$prev) or return
+ my $mm = $ctx->{mm} = $ibx->mm;
+ my $ids = $mm->ids_after(\$prev) or return
[404, [qw(Content-Type text/plain)], ["No results found\n"]];
- my $i = 0;
- my $over = $ctx->{srch}->{over_ro};
- my $cb = sub {
- do {
- while ((my $num = $ids->[$i++])) {
- my $smsg = $over->get_art($num) or next;
- return $smsg;
- }
- $ids = $ctx->{-inbox}->mm->ids_after(\$prev);
- $i = 0;
- } while (@$ids);
- undef;
- };
- return PublicInbox::MboxGz->response($ctx, $cb, 'all');
+ $ctx->{over} = $ibx->over or
+ return PublicInbox::WWW::need($ctx, 'Overview');
+ $ctx->{ids} = $ids;
+ $ctx->{prev} = $prev;
+ require PublicInbox::MboxGz;
+ PublicInbox::MboxGz::mbox_gz($ctx, \&all_ids_cb, 'all');
}
-sub mbox_all {
- my ($ctx, $query) = @_;
-
- eval { require IO::Compress::Gzip };
- return sub { need_gzip(@_) } if $@;
- return mbox_all_ids($ctx) if $query eq '';
- my $opts = { mset => 2 };
+sub results_cb {
+ my ($ctx) = @_;
+ my $mset = $ctx->{mset};
my $srch = $ctx->{srch};
- my $mset = $srch->query($query, $opts);
- $opts->{offset} = $mset->size or
- return [404, [qw(Content-Type text/plain)],
- ["No results found\n"]];
- my $i = 0;
- my $cb = sub { # called by MboxGz->getline
- while (1) {
- while (my $mi = (($mset->items)[$i++])) {
- my $doc = $mi->get_document;
- my $smsg = $srch->retry_reopen(sub {
- PublicInbox::SearchMsg->load_doc($doc);
- }) or next;
- return $smsg;
- }
- # refill result set
- $mset = $srch->query($query, $opts);
- my $size = $mset->size or return;
- $opts->{offset} += $size;
- $i = 0;
+ while (1) {
+ while (my $mi = (($mset->items)[$ctx->{iter}++])) {
+ my $smsg = PublicInbox::Smsg::from_mitem($mi,
+ $srch) or next;
+ return $smsg;
}
- };
- PublicInbox::MboxGz->response($ctx, $cb, 'results-'.$query);
-}
-
-sub need_gzip {
- my $fh = $_[0]->([501, ['Content-Type' => 'text/html']]);
- my $title = 'gzipped mbox not available';
- $fh->write(<<EOF);
-<html><head><title>$title</title><body><pre>$title
-The administrator needs to install the IO::Compress::Gzip Perl module
-to support gzipped mboxes.
-<a href="../">Return to index</a></pre></body></html>
-EOF
- $fh->close;
-}
-
-1;
-
-package PublicInbox::MboxGz;
-use strict;
-use warnings;
-use PublicInbox::Hval qw/to_filename/;
-
-sub new {
- my ($class, $ctx, $cb) = @_;
- my $buf = '';
- bless {
- buf => \$buf,
- gz => IO::Compress::Gzip->new(\$buf, Time => 0),
- cb => $cb,
- ctx => $ctx,
- }, $class;
-}
-
-sub response {
- my ($class, $ctx, $cb, $fn) = @_;
- my $body = $class->new($ctx, $cb);
- # http://www.iana.org/assignments/media-types/application/gzip
- my @h = qw(Content-Type application/gzip);
- if ($fn) {
- $fn = to_filename($fn);
- push @h, 'Content-Disposition', "inline; filename=$fn.mbox.gz";
+ # refill result set
+ $mset = $ctx->{mset} = $srch->query($ctx->{query},
+ $ctx->{qopts});
+ my $size = $mset->size or return;
+ $ctx->{qopts}->{offset} += $size;
+ $ctx->{iter} = 0;
}
- [ 200, \@h, $body ];
}
-# called by Plack::Util::foreach or similar
-sub getline {
- my ($self) = @_;
- my $ctx = $self->{ctx} or return;
- while (my $smsg = $self->{cb}->()) {
- my $msg = $ctx->{-inbox}->msg_by_smsg($smsg) or next;
- $msg = Email::Simple->new($msg);
- $self->{gz}->write(PublicInbox::Mbox::msg_str($ctx, $msg,
- $smsg->{mid}));
- my $bref = $self->{buf};
- if (length($$bref) >= 8192) {
- my $ret = $$bref; # copy :<
- ${$self->{buf}} = '';
- return $ret;
- }
+sub mbox_all {
+ my ($ctx, $query) = @_;
- # be fair to other clients on public-inbox-httpd:
- return '';
- }
- delete($self->{gz})->close;
- # signal that we're done and can return undef next call:
- delete $self->{ctx};
- ${delete $self->{buf}};
+ return mbox_all_ids($ctx) if $query eq '';
+ my $qopts = $ctx->{qopts} = { mset => 2 };
+ my $srch = $ctx->{srch} = $ctx->{-inbox}->search or
+ return PublicInbox::WWW::need($ctx, 'Search');;
+ my $mset = $ctx->{mset} = $srch->query($query, $qopts);
+ $qopts->{offset} = $mset->size or
+ return [404, [qw(Content-Type text/plain)],
+ ["No results found\n"]];
+ $ctx->{iter} = 0;
+ $ctx->{query} = $query;
+ require PublicInbox::MboxGz;
+ PublicInbox::MboxGz::mbox_gz($ctx, \&results_cb, 'results-'.$query);
}
-sub close {} # noop
-
1;