-# Copyright (C) 2015-2020 all contributors <meta@public-inbox.org>
+# Copyright (C) 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
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));
+ my $ibx = $ctx->{ibx};
+ my $eml = delete($ctx->{eml}) // $ibx->smsg_eml($smsg) // return;
+ if (($ctx->{smsg} = $ibx->over->next_by_mid(@{$ctx->{next_arg}}))) {
+ $ctx->translate(msg_hdr($ctx, $eml), msg_body($eml));
} else { # last message
- $ctx->zmore(msg_body($eml));
- $ctx->zflush;
+ $ctx->zflush(msg_hdr($ctx, $eml), msg_body($eml));
}
}
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)));
+ $ctx->{smsg} = $ctx->{ibx}->over->next_by_mid(@{$ctx->{next_arg}});
+ local $ctx->{eml} = $eml; # for mbox_hdr
+ $ctx->write(msg_hdr($ctx, $eml), msg_body($eml));
}
-sub res_hdr ($$) {
- my ($ctx, $subject) = @_;
- my $fn = $subject // '';
+sub mbox_hdr ($) {
+ my ($ctx) = @_;
+ my $eml = $ctx->{eml} //= $ctx->{ibx}->smsg_eml($ctx->{smsg});
+ my $fn = $eml->header_str('Subject') // '';
$fn =~ s/^re:\s+//i;
$fn = to_filename($fn) // 'no-subject';
my @hdr = ('Content-Type');
- if ($ctx->{-inbox}->{obfuscate}) {
+ if ($ctx->{ibx}->{obfuscate}) {
# obfuscation is stupid, but maybe scrapers are, too...
push @hdr, 'application/mbox';
$fn .= '.mbox';
push @hdr, 'text/plain';
$fn .= '.txt';
}
+ my $cs = $ctx->{eml}->ct->{attributes}->{charset} // 'UTF-8';
+ $cs = 'UTF-8' if $cs =~ /[^a-zA-Z0-9\-\_]/; # avoid header injection
+ $hdr[-1] .= "; charset=$cs";
push @hdr, 'Content-Disposition', "inline; filename=$fn";
- \@hdr;
+ [ 200, \@hdr ];
}
# for rare cases where v1 inboxes aren't indexed w/ ->over at all
sub no_over_raw ($) {
my ($ctx) = @_;
- my $mref = $ctx->{-inbox}->msg_by_mid($ctx->{mid}) or return;
- my $eml = PublicInbox::Eml->new($mref);
- [ 200, res_hdr($ctx, $eml->header_str('Subject')),
- [ msg_hdr($ctx, $eml, $ctx->{mid}) . msg_body($eml) ] ]
+ my $mref = $ctx->{ibx}->msg_by_mid($ctx->{mid}) or return;
+ my $eml = $ctx->{eml} = PublicInbox::Eml->new($mref);
+ [ @{mbox_hdr($ctx)}, [ msg_hdr($ctx, $eml) . msg_body($eml) ] ]
}
# /$INBOX/$MESSAGE_ID/raw
sub emit_raw {
my ($ctx) = @_;
- $ctx->{base_url} = $ctx->{-inbox}->base_url($ctx->{env});
- my $over = $ctx->{-inbox}->over or return no_over_raw($ctx);
+ my $over = $ctx->{ibx}->over or return no_over_raw($ctx);
my ($id, $prev);
my $mip = $ctx->{next_arg} = [ $ctx->{mid}, \$id, \$prev ];
my $smsg = $ctx->{smsg} = $over->next_by_mid(@$mip) or return;
- my $res_hdr = res_hdr($ctx, $smsg->{subject});
bless $ctx, __PACKAGE__;
- $ctx->psgi_response(200, $res_hdr);
+ $ctx->psgi_response(\&mbox_hdr);
}
-sub msg_hdr ($$;$) {
- my ($ctx, $eml, $mid) = @_;
+sub msg_hdr ($$) {
+ my ($ctx, $eml) = @_;
my $header_obj = $eml->header_obj;
# drop potentially confusing headers, ssoma already should've dropped
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;
# 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 = $header_obj->header_raw($k);
- foreach (@v) {
- if ($v eq $_) {
- $v = undef;
- last;
- }
- }
- $buf .= "$k: $v$crlf" if defined $v;
- }
- $buf .= $crlf;
+ "From mboxrd\@z Thu Jan 1 00:00:00 1970" . $crlf . $buf . $crlf;
}
sub msg_body ($) {
return $smsg;
}
# refill result set
- $ctx->{msgs} = $msgs = $ctx->{over}->get_thread($ctx->{mid},
- $ctx->{prev});
+ 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];
}
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, $msgs->[0]->{subject});
}
sub all_ids_cb {
my ($ctx) = @_;
+ my $over = $ctx->{ibx}->over or return $ctx->gone('over');
my $ids = $ctx->{ids};
do {
while ((my $num = shift @$ids)) {
- my $smsg = $ctx->{over}->get_art($num) or next;
+ my $smsg = $over->get_art($num) or next;
return $smsg;
}
- $ctx->{ids} = $ids = $ctx->{mm}->ids_after(\($ctx->{prev}));
+ $ctx->{ids} = $ids = $over->ids_after(\($ctx->{prev}));
} while (@$ids);
}
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
+ 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"]];
$ctx->{ids} = $ids;
$ctx->{prev} = $prev;
+ $ctx->{-low_prio} = 1;
require PublicInbox::MboxGz;
PublicInbox::MboxGz::mbox_gz($ctx, \&all_ids_cb, 'all');
}
-sub gone ($$) {
- my ($ctx, $what) = @_;
- warn "W: `$ctx->{-inbox}->{inboxdir}' $what went away unexpectedly\n";
- undef;
-}
-
sub results_cb {
my ($ctx) = @_;
- my $over = $ctx->{-inbox}->over or return gone($ctx, 'over');
+ 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;
}
- # refill result set
- my $srch = $ctx->{-inbox}->isrch or return gone($ctx, 'search');
+ # 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->{ids} = $srch->mset_to_artnums($mset, $ctx->{qopts});
+ $ctx->{-low_prio} = 1;
}
}
sub results_thread_cb {
my ($ctx) = @_;
- my $over = $ctx->{-inbox}->over or return gone($ctx, 'over');
+ 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;
# refills ctx->{xids}
next if $over->expand_thread($ctx);
- # refill result set
- my $srch = $ctx->{-inbox}->isrch or return gone($ctx, 'search');
+ # 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->{ids} = $srch->mset_to_artnums($mset, $ctx->{qopts});
+ $ctx->{-low_prio} = 1;
}
}
my ($ctx, $q) = @_;
my $q_string = $q->{'q'};
return mbox_all_ids($ctx) if $q_string !~ /\S/;
- my $srch = $ctx->{-inbox}->isrch or
+ my $srch = $ctx->{ibx}->isrch or
return PublicInbox::WWW::need($ctx, 'Search');
- my $over = $ctx->{-inbox}->over or
+ my $over = $ctx->{ibx}->over or
return PublicInbox::WWW::need($ctx, 'Overview');
- my $qopts = $ctx->{qopts} = { mset => 2 }; # order by docid
- $qopts->{thread} = 1 if $q->{t};
+ 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);
+ $ctx->{ids} = $srch->mset_to_artnums($mset, $qopts);
require PublicInbox::MboxGz;
my $fn;
if ($q->{t} && $srch->has_threadid) {