-# Copyright (C) 2015-2018 all contributors <meta@public-inbox.org>
+# Copyright (C) 2015-2021 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 interface for mboxrd HTTP responses
+# See PublicInbox::GzipFilter for details.
package PublicInbox::Mbox;
use strict;
-use warnings;
-use PublicInbox::MID qw/mid_clean mid_escape/;
+use parent 'PublicInbox::GzipFilter';
+use PublicInbox::MID qw/mid_escape/;
use PublicInbox::Hval qw/to_filename/;
-use Email::Simple;
-use Email::MIME::Encode;
+use PublicInbox::Smsg;
+use PublicInbox::Eml;
-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 $@;
+# called by PSGI server as body response
+# this gets called twice for every message, once to return the header,
+# once to retrieve the body
+sub getline {
+ my ($ctx) = @_; # ctx
+ my $smsg = $ctx->{smsg} or return;
+ my $ibx = $ctx->{ibx};
+ my $eml = delete($ctx->{eml}) // $ibx->smsg_eml($smsg) // return;
+ my $n = $ctx->{smsg} = $ibx->over->next_by_mid(@{$ctx->{next_arg}});
+ $ctx->zmore(msg_hdr($ctx, $eml));
+ if ($n) {
+ $ctx->translate(msg_body($eml));
+ } else { # last message
+ $ctx->zmore(msg_body($eml));
+ $ctx->zflush;
}
- $fn =~ s/^re:\s+//i;
- $fn = to_filename($fn);
- $fn eq '' ? 'no-subject' : $fn;
}
-sub mb_stream {
- my ($more) = @_;
- bless $more, 'PublicInbox::Mbox';
+# called by PublicInbox::DS::write after http->next_step
+sub async_next {
+ my ($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 $@;
}
-# called by PSGI server as body response
-sub getline {
- my ($more) = @_; # self
- my ($ctx, $id, $prev, $next, $cur) = @$more;
- if ($cur) { # first
- pop @$more;
- return msg_str($ctx, $cur);
- }
- $cur = $next or return;
- my $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));
+sub async_eml { # for async_blob_cb
+ my ($ctx, $eml) = @_;
+ my $smsg = delete $ctx->{smsg};
+ # next message
+ $ctx->{smsg} = $ctx->{ibx}->over->next_by_mid(@{$ctx->{next_arg}});
+ local $ctx->{eml} = $eml; # for mbox_hdr
+ $ctx->zmore(msg_hdr($ctx, $eml));
+ $ctx->write(msg_body($eml));
}
-sub close {} # noop
-
-sub emit_raw {
+sub mbox_hdr ($) {
my ($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;
- } else {
- my $mref = $ibx->msg_by_mid($mid) or return;
- $first = Email::Simple->new($mref);
- }
- return unless defined $first;
- my $fn = subject_fn($first);
+ my $eml = $ctx->{eml} //= $ctx->{ibx}->smsg_eml($ctx->{smsg});
+ my $fn = $eml->header_str('Subject') // '';
+ $fn =~ s/^re:\s+//i;
+ $fn = to_filename($fn) // 'no-subject';
my @hdr = ('Content-Type');
- if ($ibx->{obfuscate}) {
+ if ($ctx->{ibx}->{obfuscate}) {
# obfuscation is stupid, but maybe scrapers are, too...
push @hdr, 'application/mbox';
$fn .= '.mbox';
push @hdr, 'text/plain';
$fn .= '.txt';
}
+ my $cs = $ctx->{eml}->ct->{attributes}->{charset} // 'UTF-8';
+ $cs = 'UTF-8' if $cs =~ /[^a-zA-Z0-9\-\_]/; # avoid header injection
+ $hdr[-1] .= "; charset=$cs";
push @hdr, 'Content-Disposition', "inline; filename=$fn";
- [ 200, \@hdr, $more ? mb_stream($more) : [ msg_str($ctx, $first) ] ];
+ [ 200, \@hdr ];
}
-sub msg_str {
- my ($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 = $ctx->{ibx}->msg_by_mid($ctx->{mid}) or return;
+ my $eml = $ctx->{eml} = PublicInbox::Eml->new($mref);
+ [ @{mbox_hdr($ctx)}, [ msg_hdr($ctx, $eml) . msg_body($eml) ] ]
+}
+
+# /$INBOX/$MESSAGE_ID/raw
+sub emit_raw {
+ my ($ctx) = @_;
+ $ctx->{base_url} = $ctx->{ibx}->base_url($ctx->{env});
+ my $over = $ctx->{ibx}->over or return no_over_raw($ctx);
+ my ($id, $prev);
+ my $mip = $ctx->{next_arg} = [ $ctx->{mid}, \$id, \$prev ];
+ my $smsg = $ctx->{smsg} = $over->next_by_mid(@$mip) or return;
+ bless $ctx, __PACKAGE__;
+ $ctx->psgi_response(\&mbox_hdr);
+}
+
+sub msg_hdr ($$) {
+ my ($ctx, $eml) = @_;
+ my $header_obj = $eml->header_obj;
# drop potentially confusing headers, ssoma already should've dropped
# Lines and Content-Length
foreach my $d (qw(Lines Bytes Content-Length Status)) {
$header_obj->header_set($d);
}
- my $ibx = $ctx->{-inbox};
- my $base = $ibx->base_url($ctx->{env});
- $mid = $ctx->{mid} unless defined $mid;
- $mid = mid_escape($mid);
- my @append = (
- 'Archived-At', "<$base$mid/>",
- 'List-Archive', "<$base>",
- 'List-Post', "<mailto:$ibx->{-primary_address}>",
- );
- my $crlf = $simple->crlf;
- my $buf = "From mboxrd\@z Thu Jan 1 00:00:00 1970\n" .
- $header_obj->as_string;
- for (my $i = 0; $i < @append; $i += 2) {
- my $k = $append[$i];
- my $v = $append[$i + 1];
- my @v = $header_obj->header($k);
- foreach (@v) {
- if ($v eq $_) {
- $v = undef;
- last;
- }
- }
- $buf .= "$k: $v$crlf" if defined $v;
- }
- $buf .= $crlf;
+ my $crlf = $header_obj->crlf;
+ my $buf = $header_obj->as_string;
+ # fixup old bug from import (pre-a0c07cba0e5d8b6a)
+ $buf =~ s/\A[\r\n]*From [^\r\n]*\r?\n//s;
+ "From mboxrd\@z Thu Jan 1 00:00:00 1970" . $crlf . $buf . $crlf;
+}
+sub msg_body ($) {
+ my $bdy = $_[0]->{bdy} // return "\n";
# mboxrd quoting style
- # ref: http://www.qmail.org/man/man5/mbox.html
- my $body = $simple->body;
- $body =~ s/^(>*From )/>$1/gm;
- $buf .= $body;
- $buf .= "\n";
+ # https://en.wikipedia.org/wiki/Mbox#Modified_mbox
+ # https://www.loc.gov/preservation/digital/formats/fdd/fdd000385.shtml
+ # https://web.archive.org/http://www.qmail.org/man/man5/mbox.html
+ $$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
+ my $over = $ctx->{ibx}->over or return $ctx->gone('over');
+ $ctx->{msgs} = $msgs = $over->get_thread($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} = $msgs->[-1];
+ require PublicInbox::MboxGz;
+ PublicInbox::MboxGz::mbox_gz($ctx, \&thread_cb, $msgs->[0]->{subject});
}
sub emit_range {
my ($ctx, $range) = @_;
- my $query;
+ my $q;
if ($range eq 'all') { # TODO: YYYY[-MM]
- $query = '';
+ $q = '';
} else {
return [404, [qw(Content-Type text/plain)], []];
}
- mbox_all($ctx, $query);
+ mbox_all($ctx, { q => $q });
+}
+
+sub all_ids_cb {
+ my ($ctx) = @_;
+ my $over = $ctx->{ibx}->over or return $ctx->gone('over');
+ my $ids = $ctx->{ids};
+ do {
+ while ((my $num = shift @$ids)) {
+ my $smsg = $over->get_art($num) or next;
+ return $smsg;
+ }
+ $ctx->{ids} = $ids = $over->ids_after(\($ctx->{prev}));
+ } while (@$ids);
}
sub mbox_all_ids {
my ($ctx) = @_;
my $prev = 0;
- my $ids = $ctx->{-inbox}->mm->ids_after(\$prev) or return
+ my $over = $ctx->{ibx}->over or
+ return PublicInbox::WWW::need($ctx, 'Overview');
+ my $ids = $over->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->{ids} = $ids;
+ $ctx->{prev} = $prev;
+ $ctx->{-low_prio} = 1;
+ require PublicInbox::MboxGz;
+ PublicInbox::MboxGz::mbox_gz($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 };
- 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;
- $i = 0;
+sub results_cb {
+ my ($ctx) = @_;
+ my $over = $ctx->{ibx}->over or return $ctx->gone('over');
+ while (1) {
+ while (defined(my $num = shift(@{$ctx->{ids}}))) {
+ my $smsg = $over->get_art($num) 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;
+ # refill result set, deprioritize since there's many results
+ my $srch = $ctx->{ibx}->isrch or return $ctx->gone('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, $ctx->{qopts});
+ $ctx->{-low_prio} = 1;
+ }
}
-1;
+sub results_thread_cb {
+ my ($ctx) = @_;
-package PublicInbox::MboxGz;
-use strict;
-use warnings;
-use PublicInbox::Hval qw/to_filename/;
+ my $over = $ctx->{ibx}->over or return $ctx->gone('over');
+ while (1) {
+ while (defined(my $num = shift(@{$ctx->{xids}}))) {
+ my $smsg = $over->get_art($num) or next;
+ return $smsg;
+ }
-sub new {
- my ($class, $ctx, $cb) = @_;
- my $buf = '';
- bless {
- buf => \$buf,
- gz => IO::Compress::Gzip->new(\$buf, Time => 0),
- cb => $cb,
- ctx => $ctx,
- }, $class;
-}
+ # refills ctx->{xids}
+ next if $over->expand_thread($ctx);
-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, deprioritize since there's many results
+ my $srch = $ctx->{ibx}->isrch or return $ctx->gone('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, $ctx->{qopts});
+ $ctx->{-low_prio} = 1;
}
- [ 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, $q) = @_;
+ my $q_string = $q->{'q'};
+ return mbox_all_ids($ctx) if $q_string !~ /\S/;
+ my $srch = $ctx->{ibx}->isrch or
+ return PublicInbox::WWW::need($ctx, 'Search');
+ my $over = $ctx->{ibx}->over or
+ return PublicInbox::WWW::need($ctx, 'Overview');
- # be fair to other clients on public-inbox-httpd:
- return '';
+ my $qopts = $ctx->{qopts} = { relevance => -2 }; # ORDER BY docid DESC
+ $qopts->{threads} = 1 if $q->{t};
+ $srch->query_approxidate($ctx->{ibx}->git, $q_string);
+ 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, $qopts);
+ 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, $fn);
}
- delete($self->{gz})->close;
- # signal that we're done and can return undef next call:
- delete $self->{ctx};
- ${delete $self->{buf}};
}
-sub close {} # noop
-
1;