-# Copyright (C) 2015 all contributors <meta@public-inbox.org>
-# License: AGPLv3 or later (https://www.gnu.org/licenses/agpl-3.0.txt)
-# Streaming interface for formatting messages as an mboxrd
+# 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 mboxrd HTTP responses
+# See PublicInbox::GzipFilter for details.
package PublicInbox::Mbox;
use strict;
-use warnings;
-use PublicInbox::MID qw/mid2path/;
-require Email::Simple;
+use parent 'PublicInbox::GzipFilter';
+use PublicInbox::MID qw/mid_escape/;
+use PublicInbox::Hval qw/to_filename/;
+use PublicInbox::Smsg;
+use PublicInbox::Eml;
-sub thread_mbox {
- my ($ctx, $srch, $sfx) = @_;
- sub {
- my ($response) = @_; # Plack callback
- emit_mbox($response, $ctx, $srch, $sfx);
+# called by PSGI server as body response
+# this gets called twice for every message, once to return the header,
+# once to retrieve the body
+sub getline {
+ my ($ctx) = @_; # ctx
+ my $smsg = $ctx->{smsg} or return;
+ my $ibx = $ctx->{-inbox};
+ 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;
}
}
-sub emit1 {
- my $simple = Email::Simple->new(pop);
- sub {
- my ($response) = @_;
- # single message should be easily renderable in browsers
- my $fh = $response->([200, ['Content-Type'=>'text/plain']]);
- emit_msg($fh, $simple);
- $fh->close;
+# called by PublicInbox::DS::write after http->next_step
+sub async_next {
+ my ($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 $@;
+}
+
+sub async_eml { # for async_blob_cb
+ my ($ctx, $eml) = @_;
+ my $smsg = delete $ctx->{smsg};
+ # next message
+ $ctx->{smsg} = $ctx->{-inbox}->over->next_by_mid(@{$ctx->{next_arg}});
+
+ $ctx->zmore(msg_hdr($ctx, $eml, $smsg->{mid}));
+ $ctx->{http_out}->write($ctx->translate(msg_body($eml)));
+}
+
+sub res_hdr ($$) {
+ my ($ctx, $subject) = @_;
+ my $fn = $subject // '';
+ $fn =~ s/^re:\s+//i;
+ $fn = to_filename($fn) // 'no-subject';
+ my @hdr = ('Content-Type');
+ if ($ctx->{-inbox}->{obfuscate}) {
+ # obfuscation is stupid, but maybe scrapers are, too...
+ push @hdr, 'application/mbox';
+ $fn .= '.mbox';
+ } else {
+ push @hdr, 'text/plain';
+ $fn .= '.txt';
}
+ push @hdr, 'Content-Disposition', "inline; filename=$fn";
+ \@hdr;
+}
+
+# for rare cases where v1 inboxes aren't indexed w/ ->over at all
+sub no_over_raw ($) {
+ my ($ctx) = @_;
+ my $mref = $ctx->{-inbox}->msg_by_mid($ctx->{mid}) or return;
+ my $eml = PublicInbox::Eml->new($mref);
+ [ 200, res_hdr($ctx, $eml->header_str('Subject')),
+ [ msg_hdr($ctx, $eml, $ctx->{mid}) . msg_body($eml) ] ]
}
-sub emit_msg {
- my ($fh, $simple) = @_; # Email::Simple object
- my $header_obj = $simple->header_obj;
+# /$INBOX/$MESSAGE_ID/raw
+sub emit_raw {
+ my ($ctx) = @_;
+ $ctx->{base_url} = $ctx->{-inbox}->base_url($ctx->{env});
+ my $over = $ctx->{-inbox}->over or return no_over_raw($ctx);
+ my ($id, $prev);
+ my $mip = $ctx->{next_arg} = [ $ctx->{mid}, \$id, \$prev ];
+ my $smsg = $ctx->{smsg} = $over->next_by_mid(@$mip) or return;
+ my $res_hdr = res_hdr($ctx, $smsg->{subject});
+ bless $ctx, __PACKAGE__;
+ $ctx->psgi_response(200, $res_hdr);
+}
+
+sub msg_hdr ($$;$) {
+ my ($ctx, $eml, $mid) = @_;
+ my $header_obj = $eml->header_obj;
# drop potentially confusing headers, ssoma already should've dropped
# Lines and Content-Length
foreach my $d (qw(Lines Bytes Content-Length Status)) {
$header_obj->header_set($d);
}
-
+ my $ibx = $ctx->{-inbox};
+ my $base = $ctx->{base_url};
+ $mid = $ctx->{mid} unless defined $mid;
+ $mid = mid_escape($mid);
+ my @append = (
+ 'Archived-At', "<$base$mid/>",
+ 'List-Archive', "<$base>",
+ 'List-Post', "<mailto:$ibx->{-primary_address}>",
+ );
+ my $crlf = $header_obj->crlf;
my $buf = $header_obj->as_string;
- unless ($buf =~ /\AFrom /) {
- $fh->write("From mboxrd\@z Thu Jan 1 00:00:00 1970\n");
- }
- $fh->write($buf .= $simple->crlf);
+ # 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;
- $buf = $simple->body;
- $simple->body_set('');
+ for (my $i = 0; $i < @append; $i += 2) {
+ my $k = $append[$i];
+ my $v = $append[$i + 1];
+ my @v = $header_obj->header_raw($k);
+ foreach (@v) {
+ if ($v eq $_) {
+ $v = undef;
+ last;
+ }
+ }
+ $buf .= "$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
- $buf =~ s/^(>*From )/>$1/gm;
+ # 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";
+}
- $buf .= "\n" unless $buf =~ /\n\z/s;
+sub thread_cb {
+ my ($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];
+ }
+}
- $fh->write($buf);
+sub thread_mbox {
+ my ($ctx, $over, $sfx) = @_;
+ my $msgs = $ctx->{msgs} = $over->get_thread($ctx->{mid}, {});
+ return [404, [qw(Content-Type text/plain)], []] if !@$msgs;
+ $ctx->{prev} = $msgs->[-1];
+ $ctx->{over} = $over; # bump refcnt
+ require PublicInbox::MboxGz;
+ PublicInbox::MboxGz::mbox_gz($ctx, \&thread_cb, $msgs->[0]->{subject});
}
-sub emit_mbox {
- my ($response, $ctx, $srch, $sfx) = @_;
- my $type = 'mbox';
- if ($sfx) {
- eval { require IO::Compress::Gzip };
- return need_gzip($response) if $@;
- $type = 'gzip';
- }
+sub emit_range {
+ my ($ctx, $range) = @_;
- # http://www.iana.org/assignments/media-types/application/gzip
- # http://www.iana.org/assignments/media-types/application/mbox
- my $fh = $response->([200, ['Content-Type' => "application/$type"]]);
- $fh = PublicInbox::MboxGz->new($fh) if $sfx;
+ my $q;
+ if ($range eq 'all') { # TODO: YYYY[-MM]
+ $q = '';
+ } else {
+ return [404, [qw(Content-Type text/plain)], []];
+ }
+ mbox_all($ctx, { q => $q });
+}
- require PublicInbox::GitCatFile;
- my $mid = $ctx->{mid};
- my $git = PublicInbox::GitCatFile->new($ctx->{git_dir});
- my %opts = (offset => 0);
- my $nr;
+sub all_ids_cb {
+ my ($ctx) = @_;
+ my $ids = $ctx->{ids};
do {
- my $res = $srch->get_thread($mid, \%opts);
- my $msgs = $res->{msgs};
- $nr = scalar @$msgs;
- while (defined(my $smsg = shift @$msgs)) {
- my $msg = eval {
- my $p = 'HEAD:'.mid2path($smsg->mid);
- Email::Simple->new($git->cat_file($p));
- };
- emit_msg($fh, $msg) if $msg;
+ 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);
+}
- $opts{offset} += $nr;
- } while ($nr > 0);
+sub mbox_all_ids {
+ my ($ctx) = @_;
+ my $ibx = $ctx->{-inbox};
+ my $prev = 0;
+ my $mm = $ctx->{mm} = $ibx->mm;
+ my $ids = $mm->ids_after(\$prev) or return
+ [404, [qw(Content-Type text/plain)], ["No results found\n"]];
+ $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');
+}
- $fh->close;
+sub gone ($$) {
+ my ($ctx, $what) = @_;
+ warn "W: `$ctx->{-inbox}->{inboxdir}' $what went away unexpectedly\n";
+ undef;
}
-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
- $fh->close;
+sub results_cb {
+ my ($ctx) = @_;
+ my $over = $ctx->{-inbox}->over or return gone($ctx, 'over');
+ while (1) {
+ while (defined(my $num = shift(@{$ctx->{ids}}))) {
+ my $smsg = $over->get_art($num) or next;
+ return $smsg;
+ }
+ # refill result set
+ my $srch = $ctx->{-inbox}->isrch or return gone($ctx, 'search');
+ my $mset = $srch->mset($ctx->{query}, $ctx->{qopts});
+ my $size = $mset->size or return;
+ $ctx->{qopts}->{offset} += $size;
+ $ctx->{ids} = $srch->mset_to_artnums($mset);
+ }
}
-1;
+sub results_thread_cb {
+ my ($ctx) = @_;
-# fh may not be a proper IO, so we wrap the write and close methods
-# to prevent IO::Compress::Gzip from complaining
-package PublicInbox::MboxGz;
-use strict;
-use warnings;
-
-sub new {
- my ($class, $fh) = @_;
- my $buf;
- bless {
- buf => \$buf,
- gz => IO::Compress::Gzip->new(\$buf),
- fh => $fh,
- }, $class;
-}
-
-sub _flush_buf {
- my ($self) = @_;
- if (defined ${$self->{buf}}) {
- $self->{fh}->write(${$self->{buf}});
- ${$self->{buf}} = undef;
+ my $over = $ctx->{-inbox}->over or return gone($ctx, 'over');
+ while (1) {
+ while (defined(my $num = shift(@{$ctx->{xids}}))) {
+ my $smsg = $over->get_art($num) or next;
+ return $smsg;
+ }
+
+ # refills ctx->{xids}
+ next if $over->expand_thread($ctx);
+
+ # refill result set
+ my $srch = $ctx->{-inbox}->isrch or return gone($ctx, 'search');
+ my $mset = $srch->mset($ctx->{query}, $ctx->{qopts});
+ my $size = $mset->size or return;
+ $ctx->{qopts}->{offset} += $size;
+ $ctx->{ids} = $srch->mset_to_artnums($mset);
}
-}
-sub write {
- $_[0]->{gz}->write($_[1]);
- _flush_buf($_[0]);
}
-sub close {
- my ($self) = @_;
- $self->{gz}->close;
- _flush_buf($self);
- $self->{fh}->close;
+sub mbox_all {
+ my ($ctx, $q) = @_;
+ my $q_string = $q->{'q'};
+ return mbox_all_ids($ctx) if $q_string !~ /\S/;
+ my $srch = $ctx->{-inbox}->isrch or
+ return PublicInbox::WWW::need($ctx, 'Search');
+ my $over = $ctx->{-inbox}->over or
+ return PublicInbox::WWW::need($ctx, 'Overview');
+
+ my $qopts = $ctx->{qopts} = { mset => 2 }; # order by docid
+ $qopts->{thread} = 1 if $q->{t};
+ my $mset = $srch->mset($q_string, $qopts);
+ $qopts->{offset} = $mset->size or
+ return [404, [qw(Content-Type text/plain)],
+ ["No results found\n"]];
+ $ctx->{query} = $q_string;
+ $ctx->{ids} = $srch->mset_to_artnums($mset);
+ require PublicInbox::MboxGz;
+ my $fn;
+ if ($q->{t} && $srch->has_threadid) {
+ $fn = 'results-thread-'.$q_string;
+ PublicInbox::MboxGz::mbox_gz($ctx, \&results_thread_cb, $fn);
+ } else {
+ $fn = 'results-'.$q_string;
+ PublicInbox::MboxGz::mbox_gz($ctx, \&results_cb, $fn);
+ }
}
1;