diff options
Diffstat (limited to 'lib/PublicInbox/Mbox.pm')
| -rw-r--r-- | lib/PublicInbox/Mbox.pm | 310 |
1 files changed, 176 insertions, 134 deletions
diff --git a/lib/PublicInbox/Mbox.pm b/lib/PublicInbox/Mbox.pm index b46dacfd..17893a09 100644 --- a/lib/PublicInbox/Mbox.pm +++ b/lib/PublicInbox/Mbox.pm @@ -1,76 +1,59 @@ -# 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 (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 v5.12; +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 PublicInbox::Eml; -sub subject_fn ($) { - my ($hdr) = @_; - my $fn = $hdr->header_str('Subject'); - return 'no-subject' if (!defined($fn) || $fn eq ''); - - $fn =~ s/^re:\s+//i; - $fn eq '' ? 'no-subject' : to_filename($fn); -} - -sub mb_stream { - my ($more) = @_; - bless $more, 'PublicInbox::Mbox'; -} - # called by PSGI server as body response # this gets called twice for every message, once to return the header, # once to retrieve the body sub getline { - my ($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($$mref); + my ($ctx) = @_; # ctx + my $smsg = $ctx->{smsg} or return; + my $ibx = $ctx->{ibx}; + my $eml = delete($ctx->{eml}) // $ibx->smsg_eml($smsg) // return; + if (($ctx->{smsg} = $ibx->over->next_by_mid(@{$ctx->{next_arg}}))) { + $ctx->translate(msg_hdr($ctx, $eml), msg_body($eml)); + } else { # last message + $ctx->zflush(msg_hdr($ctx, $eml), msg_body($eml)); } - my $cur = $next or return; - my $ibx = $ctx->{-inbox}; - $next = $ibx->over->next_by_mid($ctx->{mid}, \$id, \$prev); - $mref = $ibx->msg_by_smsg($cur) or return; - $hdr = PublicInbox::Eml->new($mref)->header_obj; - @$more = ($ctx, $id, $prev, $next); # $next may be undef, here - msg_hdr($ctx, $hdr) . msg_body($$mref); } -sub close {} # noop +# 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} // return $ctx->close; + $ctx->smsg_blob($smsg) if $smsg; + }; + warn "E: $@" if $@; +} -# /$INBOX/$MESSAGE_ID/raw -sub emit_raw { +sub async_eml { # for async_blob_cb + my ($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 + $ctx->write(msg_hdr($ctx, $eml), msg_body($eml)); +} + +sub mbox_hdr ($) { my ($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 $hdr = PublicInbox::Eml->new($mref)->header_obj; - $more = [ $ctx, $id, $prev, $next, $mref, $hdr ]; # for ->getline - my $fn = subject_fn($hdr); + 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'; @@ -78,55 +61,54 @@ sub emit_raw { 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=$fn"; - [ 200, \@hdr, mb_stream($more) ]; + [ 200, \@hdr ]; } -sub msg_hdr ($$;$) { - my ($ctx, $header_obj, $mid) = @_; +# for rare cases where v1 inboxes aren't indexed w/ ->over at all +sub no_over_raw ($) { + my ($ctx) = @_; + my $mref = $ctx->{ibx}->msg_by_mid($ctx->{mid}) or return; + my $eml = $ctx->{eml} = PublicInbox::Eml->new($mref); + [ @{mbox_hdr($ctx)}, [ msg_hdr($ctx, $eml) . msg_body($eml) ] ] +} - # drop potentially confusing headers, ssoma already should've dropped - # Lines and Content-Length - foreach my $d (qw(Lines Bytes Content-Length Status)) { - $header_obj->header_set($d); - } - my $ibx = $ctx->{-inbox}; - my $base = $ctx->{base_url}; - $mid = $ctx->{mid} unless defined $mid; - $mid = mid_escape($mid); - my @append = ( - 'Archived-At', "<$base$mid/>", - 'List-Archive', "<$base>", - 'List-Post', "<mailto:$ibx->{-primary_address}>", - ); - my $crlf = $header_obj->crlf; - my $buf = $header_obj->as_string; - # fixup old bug from import (pre-a0c07cba0e5d8b6a) - $buf =~ s/\A[\r\n]*From [^\r\n]*\r?\n//s; - $buf = "From mboxrd\@z Thu Jan 1 00:00:00 1970" . $crlf . $buf; - - for (my $i = 0; $i < @append; $i += 2) { - my $k = $append[$i]; - my $v = $append[$i + 1]; - my @v = $header_obj->header_raw($k); - foreach (@v) { - if ($v eq $_) { - $v = undef; - last; - } - } - $buf .= "$k: $v$crlf" if defined $v; +# /$INBOX/$MESSAGE_ID/raw +sub emit_raw { + my ($ctx) = @_; + my $over = $ctx->{ibx}->over or return no_over_raw($ctx); + my ($id, $prev); + my $mip = $ctx->{next_arg} = [ $ctx->{mid}, \$id, \$prev ]; + my $smsg = $ctx->{smsg} = $over->next_by_mid(@$mip) or return; + bless $ctx, __PACKAGE__; + $ctx->psgi_response(\&mbox_hdr); +} + +sub msg_hdr ($$) { + my ($ctx, $eml) = @_; + + # drop potentially confusing headers, various importers should've + # already dropped these, but we can't trust stuff we've cloned + for my $d (qw(Lines Bytes Content-Length Status)) { + $eml->header_set($d); } - $buf .= $crlf; + my $crlf = $eml->crlf; + my $buf = $eml->header_obj->as_string; + PublicInbox::Eml::strip_from($buf); + "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 # 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 { @@ -137,8 +119,9 @@ sub thread_cb { 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} = $msgs->[-1]; } @@ -146,86 +129,145 @@ sub thread_cb { sub thread_mbox { my ($ctx, $over, $sfx) = @_; - require PublicInbox::MboxGz; 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, $msgs->[0]->{subject}); } sub emit_range { my ($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 = $ctx->{over}->get_art($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); + undef; } 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} = $prev; - return PublicInbox::MboxGz->response($ctx, \&all_ids_cb, 'all'); + $ctx->{-low_prio} = 1; + require PublicInbox::MboxGz; + PublicInbox::MboxGz::mbox_gz($ctx, \&all_ids_cb, 'all'); } -sub results_cb { - my ($ctx) = @_; - my $mset = $ctx->{mset}; - my $srch = $ctx->{srch}; +my $refill_ids_cb = sub { # async_mset cb + my ($ctx, $http, $mset, $err) = @_; + $http = undef unless $ctx->{-really_async}; + if ($err) { + warn "E: $err"; + $ctx->close if $http; # our async httpd + return; + } + # refill result set, deprioritize since there's many results + my $size = $mset->size or do { + $ctx->close if $http; + $ctx->{-mbox_done} = 1; + return; + }; + $ctx->{qopts}->{offset} += $size; + $ctx->{ids} = $ctx->{srch}->mset_to_artnums($mset, $ctx->{qopts}); + $ctx->{-low_prio} = 1; # true + return if !$http; + eval { + my $smsg = results_cb($ctx) // return $ctx->close; + return if !$smsg; # '' wait for async_mset + $ctx->smsg_blob($ctx->{smsg} = $smsg); + }; + warn "E: $@" if $@; +}; + +sub results_cb { # async_next or MboxGz->getline cb + my ($ctx, $http) = @_; + my $over = $ctx->{ibx}->over or return $ctx->gone('over'); while (1) { - while (my $mi = (($mset->items)[$ctx->{iter}++])) { - my $smsg = PublicInbox::Smsg::from_mitem($mi, - $srch) or next; + my $ids = $ctx->{xids} // $ctx->{ids}; + while (defined(my $num = shift(@$ids))) { + my $smsg = $over->get_art($num) or next; return $smsg; } - # 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; + next if $ctx->{xids} && $over->expand_thread($ctx); + return '' if $ctx->{srch}->async_mset(@$ctx{qw(query qopts)}, + $refill_ids_cb, $ctx, $http); + return if $ctx->{-mbox_done}; + } +} + +sub mbox_qry_cb { # async_mset cb + my ($ctx, $q, $mset, $err) = @_; + my $wcb = delete $ctx->{wcb}; + if ($err) { + warn "E: $err"; + return $wcb->([500, [qw(Content-Type text/plain)], + [ "Internal server error\n" ]]) } + $ctx->{qopts}->{offset} = $mset->size or + return $wcb->([404, [qw(Content-Type text/plain)], + ["No results found\n"]]); + $ctx->{ids} = $ctx->{srch}->mset_to_artnums($mset, $ctx->{qopts}); + my $fn; + if ($q->{t} && $ctx->{srch}->has_threadid) { + $ctx->{xids} = []; # triggers over->expand_thread + $fn = "results-thread-$ctx->{query}"; + } else { + $fn = "results-$ctx->{query}"; + } + require PublicInbox::MboxGz; + my $res = PublicInbox::MboxGz::mbox_gz($ctx, \&results_cb, $fn); + ref($res) eq 'CODE' ? $res->($wcb) : $wcb->($res); } sub mbox_all { - my ($ctx, $query) = @_; + my ($ctx, $q) = @_; + my $qstr = $q->{'q'}; + return mbox_all_ids($ctx) if $qstr !~ /\S/; + my $srch = $ctx->{srch} = $ctx->{ibx}->isrch or + return PublicInbox::WWW::need($ctx, 'Search'); + my $opt = $ctx->{qopts} = { relevance => -2 }; # ORDER BY docid DESC - require PublicInbox::MboxGz; - return mbox_all_ids($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} = $query; - PublicInbox::MboxGz->response($ctx, \&results_cb, 'results-'.$query); + # {threadid} limits results to a given thread + # {threads} collapses results from messages in the same thread, + # allowing us to use ->expand_thread w/o duplicates in our own code + if (defined($ctx->{mid})) { + my $over = ($ctx->{ibx}->{isrch} ? + $ctx->{ibx}->{isrch}->{es}->over : + $ctx->{ibx}->over) or + return PublicInbox::WWW::need($ctx, 'Overview'); + $opt->{threadid} = $over->mid2tid($ctx->{mid}); + } + $opt->{threads} = 1 if $q->{t}; + $srch->query_approxidate($ctx->{ibx}->git, $qstr); + $ctx->{query} = $qstr; + sub { # called by PSGI server + $ctx->{wcb} = $_[0]; # PSGI server supplied write cb + $srch->async_mset($qstr, $opt, \&mbox_qry_cb, $ctx, $q) and + $ctx->{-really_async} = 1; + }; } 1; |