X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FMbox.pm;h=1945915059905946d94ce20cca2f192f7845aef7;hb=525555d14118f92f86be54c683f797089c52a78d;hp=0c3e52fe42367382d922b01c0e2f77f6b0ee84d1;hpb=ecea327e3d4386a22652fc08f71ac7d65b8f9b70;p=public-inbox.git diff --git a/lib/PublicInbox/Mbox.pm b/lib/PublicInbox/Mbox.pm index 0c3e52fe..19459150 100644 --- a/lib/PublicInbox/Mbox.pm +++ b/lib/PublicInbox/Mbox.pm @@ -1,82 +1,62 @@ -# Copyright (C) 2015-2018 all contributors +# Copyright (C) 2015-2020 all contributors # License: AGPL-3.0+ -# 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 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; - -sub subject_fn ($) { - my ($hdr) = @_; - my $fn = $hdr->header('Subject'); - return 'no-subject' unless defined($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 $more, 'PublicInbox::Mbox'; -} +use PublicInbox::Smsg; +use PublicInbox::Eml; # called by PSGI server as body response # this gets called twice for every message, once to return the header, # once to retrieve the body sub getline { - my ($more) = @_; # self - my ($ctx, $id, $prev, $next, $mref, $hdr) = @$more; - if ($hdr) { # first message hits this, only - pop @$more; # $hdr - return msg_hdr($ctx, $hdr); - } - if ($mref) { # all messages hit this - pop @$more; # $mref - return msg_body($$mref); - } - my $cur = $next or return; + my ($ctx) = @_; # ctx + my $smsg = $ctx->{smsg} or return; my $ibx = $ctx->{-inbox}; - $next = $ibx->over->next_by_mid($ctx->{mid}, \$id, \$prev); - $mref = $ibx->msg_by_smsg($cur) or return; - $hdr = Email::Simple->new($mref)->header_obj; - @$more = ($ctx, $id, $prev, $next, $mref); # $next may be undef, here - msg_hdr($ctx, $hdr); # all but first message hits this + my $eml = $ibx->smsg_eml($smsg) or return; + my $n = $ctx->{smsg} = $ibx->over->next_by_mid(@{$ctx->{next_arg}}); + $ctx->zmore(msg_hdr($ctx, $eml, $smsg->{mid})); + if ($n) { + $ctx->translate(msg_body($eml)); + } else { # last message + $ctx->zmore(msg_body($eml)); + $ctx->zflush; + } } -sub close {} # noop +# called by PublicInbox::DS::write after http->next_step +sub async_next { + my ($http) = @_; # PublicInbox::HTTP + my $ctx = $http->{forward} or return; # client aborted + eval { + my $smsg = $ctx->{smsg} or return $ctx->close; + $ctx->smsg_blob($smsg); + }; + warn "E: $@" if $@; +} -sub emit_raw { - my ($ctx) = @_; - my $mid = $ctx->{mid}; - my $ibx = $ctx->{-inbox}; - my ($mref, $more, $id, $prev, $next); - if (my $over = $ibx->over) { - my $smsg = $over->next_by_mid($mid, \$id, \$prev) or return; - $mref = $ibx->msg_by_smsg($smsg) or return; - $next = $over->next_by_mid($mid, \$id, \$prev); - } else { - $mref = $ibx->msg_by_mid($mid) or return; - } - my $hdr = Email::Simple->new($mref)->header_obj; - $more = [ $ctx, $id, $prev, $next, $mref, $hdr ]; # for ->getline - my $fn = subject_fn($hdr); +sub async_eml { # for async_blob_cb + my ($ctx, $eml) = @_; + my $smsg = delete $ctx->{smsg}; + # next message + $ctx->{smsg} = $ctx->{-inbox}->over->next_by_mid(@{$ctx->{next_arg}}); + + $ctx->zmore(msg_hdr($ctx, $eml, $smsg->{mid})); + $ctx->{http_out}->write($ctx->translate(msg_body($eml))); +} + +sub res_hdr ($$) { + my ($ctx, $subject) = @_; + my $fn = $subject // ''; + $fn =~ s/^re:\s+//i; + $fn = to_filename($fn) // 'no-subject'; my @hdr = ('Content-Type'); - if ($ibx->{obfuscate}) { + if ($ctx->{-inbox}->{obfuscate}) { # obfuscation is stupid, but maybe scrapers are, too... push @hdr, 'application/mbox'; $fn .= '.mbox'; @@ -85,11 +65,34 @@ sub emit_raw { $fn .= '.txt'; } push @hdr, 'Content-Disposition', "inline; filename=$fn"; - [ 200, \@hdr, mb_stream($more) ]; + \@hdr; +} + +# for rare cases where v1 inboxes aren't indexed w/ ->over at all +sub no_over_raw ($) { + 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) ] ] +} + +# /$INBOX/$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 ($$;$) { - my ($ctx, $header_obj, $mid) = @_; + my ($ctx, $eml, $mid) = @_; + my $header_obj = $eml->header_obj; # drop potentially confusing headers, ssoma already should've dropped # Lines and Content-Length @@ -97,7 +100,7 @@ sub msg_hdr ($$;$) { $header_obj->header_set($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 = ( @@ -106,12 +109,15 @@ sub msg_hdr ($$;$) { 'List-Post', "{-primary_address}>", ); my $crlf = $header_obj->crlf; - my $buf = "From mboxrd\@z Thu Jan 1 00:00:00 1970\n" . - $header_obj->as_string; + my $buf = $header_obj->as_string; + # fixup old bug from import (pre-a0c07cba0e5d8b6a) + $buf =~ s/\A[\r\n]*From [^\r\n]*\r?\n//s; + $buf = "From mboxrd\@z Thu Jan 1 00:00:00 1970" . $crlf . $buf; + for (my $i = 0; $i < @append; $i += 2) { my $k = $append[$i]; my $v = $append[$i + 1]; - my @v = $header_obj->header($k); + my @v = $header_obj->header_raw($k); foreach (@v) { if ($v eq $_) { $v = undef; @@ -124,173 +130,151 @@ sub msg_hdr ($$;$) { } sub msg_body ($) { + my $bdy = $_[0]->{bdy} // return "\n"; # mboxrd quoting style - # ref: http://www.qmail.org/man/man5/mbox.html - $_[0] =~ s/^(>*From )/>$1/gm; - $_[0] .= "\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, $over, $sfx) = @_; - eval { require IO::Compress::Gzip }; - return sub { need_gzip(@_) } if $@; - my $mid = $ctx->{mid}; - my $msgs = $over->get_thread($mid, {}); + 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 = $over->get_thread($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, $msgs->[0]->{subject}); } sub emit_range { my ($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 $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 $prev = 0; my $ibx = $ctx->{-inbox}; - my $ids = $ibx->mm->ids_after(\$prev) or return + 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"]]; - my $i = 0; - my $over = $ibx->over or + $ctx->{over} = $ibx->over or return PublicInbox::WWW::need($ctx, 'Overview'); - my $cb = sub { - do { - while ((my $num = $ids->[$i++])) { - my $smsg = $over->get_art($num) or next; - return $smsg; - } - $ids = $ibx->mm->ids_after(\$prev); - $i = 0; - } while (@$ids); - undef; - }; - return PublicInbox::MboxGz->response($ctx, $cb, 'all'); + $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 }; - my $srch = $ctx->{-inbox}->search or - return PublicInbox::WWW::need($ctx, 'Search');; - 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; - $i = 0; - } - }; - PublicInbox::MboxGz->response($ctx, $cb, 'results-'.$query); +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(<$title
$title
-The administrator needs to install the IO::Compress::Gzip Perl module
-to support gzipped mboxes.
-Return to index
-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) = @_; -package PublicInbox::MboxGz; -use strict; -use warnings; -use PublicInbox::Hval qw/to_filename/; + 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; + } -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 + 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); } - [ 200, \@h, $body ]; -} -# called by Plack::Util::foreach or similar -sub getline { - my ($self) = @_; - my $ctx = $self->{ctx} or return; - my $gz = $self->{gz}; - while (my $smsg = $self->{cb}->()) { - my $mref = $ctx->{-inbox}->msg_by_smsg($smsg) or next; - my $h = Email::Simple->new($mref)->header_obj; - $gz->write(PublicInbox::Mbox::msg_hdr($ctx, $h, $smsg->{mid})); - $gz->write(PublicInbox::Mbox::msg_body($$mref)); +} - 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 = $ctx->{-inbox}->isrch or + return PublicInbox::WWW::need($ctx, 'Search'); + my $over = $ctx->{-inbox}->over or + return PublicInbox::WWW::need($ctx, 'Overview'); - # be fair to other clients on public-inbox-httpd: - return ''; + 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, $fn); } - delete($self->{gz})->close; - # signal that we're done and can return undef next call: - delete $self->{ctx}; - ${delete $self->{buf}}; } -sub close {} # noop - 1;