X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FMbox.pm;h=4f84eea6745d5cbc08f835e64200ebe3ce44dd00;hb=ead71b8c387f0748338a4add37eeb437a14b02d8;hp=1c792c893a3ea6ee4099f9ff9fea2193a1a44f81;hpb=1e2f280d973dd0a744d134368fa9fbfbb6aab161;p=public-inbox.git diff --git a/lib/PublicInbox/Mbox.pm b/lib/PublicInbox/Mbox.pm index 1c792c89..4f84eea6 100644 --- a/lib/PublicInbox/Mbox.pm +++ b/lib/PublicInbox/Mbox.pm @@ -1,175 +1,254 @@ -# Copyright (C) 2015 all contributors -# License: AGPLv3 or later (https://www.gnu.org/licenses/agpl-3.0.txt) +# Copyright (C) 2015-2021 all contributors +# License: AGPL-3.0+ -# 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/; -use URI::Escape qw/uri_escape_utf8/; -use Plack::Util; -require Email::Simple; - -sub emit1 { - my $simple = Email::Simple->new(pop); - my $ctx = pop; - sub { - my ($response) = @_; - # single message should be easily renderable in browsers - my $fh = $response->([200, ['Content-Type'=>'text/plain']]); - emit_msg($ctx, $fh, $simple); - $fh->close; +use parent 'PublicInbox::GzipFilter'; +use PublicInbox::MID qw/mid_escape/; +use PublicInbox::Hval qw/to_filename/; +use PublicInbox::Smsg; +use PublicInbox::Eml; + +# called by PSGI server as body response +# this gets called twice for every message, once to return the header, +# once to retrieve the body +sub getline { + my ($ctx) = @_; # ctx + my $smsg = $ctx->{smsg} or return; + my $ibx = $ctx->{ibx}; + 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, $eml)); + if ($n) { + $ctx->translate(msg_body($eml)); + } else { # last message + $ctx->zmore(msg_body($eml)); + $ctx->zflush; } } -sub emit_msg { - my ($ctx, $fh, $simple) = @_; # Email::Simple object - my $header_obj = $simple->header_obj; +# called by PublicInbox::DS::write after http->next_step +sub async_next { + my ($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} = $ctx->{ibx}->over->next_by_mid(@{$ctx->{next_arg}}); + + $ctx->zmore(msg_hdr($ctx, $eml)); + $ctx->write(msg_body($eml)); +} + +sub res_hdr ($$) { + my ($ctx, $subject) = @_; + my $fn = $subject // ''; + $fn =~ s/^re:\s+//i; + $fn = to_filename($fn) // 'no-subject'; + my @hdr = ('Content-Type'); + if ($ctx->{ibx}->{obfuscate}) { + # obfuscation is stupid, but maybe scrapers are, too... + push @hdr, 'application/mbox'; + $fn .= '.mbox'; + } else { + push @hdr, 'text/plain'; + $fn .= '.txt'; + } + push @hdr, 'Content-Disposition', "inline; filename=$fn"; + \@hdr; +} + +# for rare cases where v1 inboxes aren't indexed w/ ->over at all +sub no_over_raw ($) { + my ($ctx) = @_; + my $mref = $ctx->{ibx}->msg_by_mid($ctx->{mid}) or return; + my $eml = PublicInbox::Eml->new($mref); + [ 200, res_hdr($ctx, $eml->header_str('Subject')), + [ msg_hdr($ctx, $eml) . msg_body($eml) ] ] +} + +# /$INBOX/$MESSAGE_ID/raw +sub emit_raw { + my ($ctx) = @_; + $ctx->{base_url} = $ctx->{ibx}->base_url($ctx->{env}); + my $over = $ctx->{ibx}->over or return no_over_raw($ctx); + my ($id, $prev); + my $mip = $ctx->{next_arg} = [ $ctx->{mid}, \$id, \$prev ]; + my $smsg = $ctx->{smsg} = $over->next_by_mid(@$mip) or return; + my $res_hdr = res_hdr($ctx, $smsg->{subject}); + bless $ctx, __PACKAGE__; + $ctx->psgi_response(200, $res_hdr); +} + +sub msg_hdr ($$) { + 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->{cgi}); - my $mid = mid_clean($header_obj->header('Message-ID')); - $mid = uri_escape_utf8($mid); - my @append = ( - 'Archived-At', "<$base$mid/>", - 'List-Archive', "<$base>", - 'List-Post', "{-primary_address}>", - ); - my $append = ''; - my $crlf = $simple->crlf; - 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; - } - } - $append .= "$k: $v$crlf" if defined $v; - } + 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"); - } - $append .= $crlf; - $fh->write($buf .= $append); - - $buf = $simple->body; - $simple->body_set(''); + # 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 - $buf =~ s/^(>*From )/>$1/gm; - - $fh->write($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 noop {} +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 $cb = sub { $srch->get_thread($ctx->{mid}, @_) }; - # http://www.iana.org/assignments/media-types/application/gzip - [200, ['Content-Type' => 'application/gzip'], - PublicInbox::MboxGz->new($ctx, $cb) ]; + my ($ctx, $over, $sfx) = @_; + my $msgs = $ctx->{msgs} = $over->get_thread($ctx->{mid}, {}); + return [404, [qw(Content-Type text/plain)], []] if !@$msgs; + $ctx->{prev} = $msgs->[-1]; + require PublicInbox::MboxGz; + PublicInbox::MboxGz::mbox_gz($ctx, \&thread_cb, $msgs->[0]->{subject}); } sub emit_range { my ($ctx, $range) = @_; - eval { require IO::Compress::Gzip }; - return sub { need_gzip(@_) } if $@; - my $query; + my $q; if ($range eq 'all') { # TODO: YYYY[-MM] - $query = ''; + $q = ''; } else { return [404, [qw(Content-Type text/plain)], []]; } - my $cb = sub { $ctx->{srch}->query($query, @_) }; + mbox_all($ctx, { q => $q }); +} - # http://www.iana.org/assignments/media-types/application/gzip - [200, [qw(Content-Type application/gzip)], - PublicInbox::MboxGz->new($ctx, $cb) ]; +sub all_ids_cb { + my ($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 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 - $fh->close; +sub mbox_all_ids { + my ($ctx) = @_; + my $prev = 0; + 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'); } -1; +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; + } + # 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}); + $ctx->{-low_prio} = 1; + } +} -package PublicInbox::MboxGz; -use strict; -use warnings; -use PublicInbox::MID qw(mid2path); - -sub new { - my ($class, $ctx, $cb) = @_; - my $buf; - bless { - buf => \$buf, - gz => IO::Compress::Gzip->new(\$buf, Time => 0), - cb => $cb, - ctx => $ctx, - msgs => [], - opts => { asc => 1, offset => 0 }, - }, $class; -} - -sub _flush_buf { - my ($self) = @_; - my $ret = $self->{buf}; - $ret = $$ret; - ${$self->{buf}} = undef; - $ret; -} - -# called by Plack::Util::foreach or similar -sub getline { - my ($self) = @_; - my $res; - my $ctx = $self->{ctx}; - my $git = $ctx->{git}; - do { - while (defined(my $smsg = shift @{$self->{msgs}})) { - my $msg = eval { - my $p = 'HEAD:'.mid2path($smsg->mid); - Email::Simple->new($git->cat_file($p)); - }; - $msg or next; - - PublicInbox::Mbox::emit_msg($ctx, $self->{gz}, $msg); - my $ret = _flush_buf($self); - return $ret if $ret; +sub results_thread_cb { + my ($ctx) = @_; + + 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; } - $res = $self->{cb}->($self->{opts}); - $self->{msgs} = $res->{msgs}; - $res = scalar @{$self->{msgs}}; - $self->{opts}->{offset} += $res; - } while ($res); - $self->{gz}->close; - _flush_buf($self); + + # refills ctx->{xids} + next if $over->expand_thread($ctx); + + # 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}); + $ctx->{-low_prio} = 1; + } + } -sub close {} # noop +sub mbox_all { + my ($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'); + + 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); + } +} 1;