X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FMbox.pm;h=8837400a435788d1fa1ef17b6dc85674bc59672d;hb=9bd675d33ad1e49bd2ebe12a1d216216e61380de;hp=05de6be1a678f75ac258b24233c9f52d8c7a585f;hpb=87dca6d8d5988c5eb54019cca342450b0b7dd6b7;p=public-inbox.git diff --git a/lib/PublicInbox/Mbox.pm b/lib/PublicInbox/Mbox.pm index 05de6be1..8837400a 100644 --- a/lib/PublicInbox/Mbox.pm +++ b/lib/PublicInbox/Mbox.pm @@ -1,8 +1,12 @@ -# Copyright (C) 2015-2018 all contributors +# Copyright (C) 2015-2019 all contributors # License: AGPL-3.0+ -# Streaming interface for formatting messages as an mboxrd. -# Used by the web interface +# 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) package PublicInbox::Mbox; use strict; use warnings; @@ -12,8 +16,8 @@ use Email::Simple; use Email::MIME::Encode; sub subject_fn ($) { - my ($simple) = @_; - my $fn = $simple->header('Subject'); + my ($hdr) = @_; + my $fn = $hdr->header('Subject'); return 'no-subject' unless defined($fn); # no need for full Email::MIME, here @@ -32,21 +36,26 @@ sub mb_stream { } # 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, $head, $tail, $db, $cur) = @$more; - if ($cur) { - pop @$more; - return msg_str($ctx, $cur); + my ($ctx, $id, $prev, $next, $mref, $hdr) = @$more; + if ($hdr) { # first message hits this, only + pop @$more; # $hdr + return msg_hdr($ctx, $hdr); } - for (; !defined($cur) && $head != $tail; $head++) { - my $smsg = PublicInbox::SearchMsg->get($head, $db, $ctx->{mid}); - my $mref = $ctx->{-inbox}->msg_by_smsg($smsg) or next; - $cur = Email::Simple->new($mref); - $cur = msg_str($ctx, $cur); + if ($mref) { # all messages hit this + pop @$more; # $mref + return msg_body($$mref); } - $more->[1] = $head; - $cur; + 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 = 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 } sub close {} # noop @@ -55,29 +64,17 @@ sub emit_raw { my ($ctx) = @_; my $mid = $ctx->{mid}; my $ibx = $ctx->{-inbox}; - my $first; - my $more; - my ($head, $tail, $db); - my %seen; - if (my $srch = $ibx->search) { - $srch->retry_reopen(sub { - ($head, $tail, $db) = $srch->each_smsg_by_mid($mid); - for (; !defined($first) && $head != $tail; $head++) { - my @args = ($head, $db, $mid); - my $smsg = PublicInbox::SearchMsg->get(@args); - my $mref = $ibx->msg_by_smsg($smsg) or next; - $first = Email::Simple->new($mref); - } - if ($head != $tail) { - $more = [ $ctx, $head, $tail, $db, $first ]; - } - }); + 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 { - my $mref = $ibx->msg_by_mid($mid) or return; - $first = Email::Simple->new($mref); + $mref = $ibx->msg_by_mid($mid) or return; } - return unless defined $first; - my $fn = subject_fn($first); + my $hdr = Email::Simple->new($mref)->header_obj; + $more = [ $ctx, $id, $prev, $next, $mref, $hdr ]; # for ->getline + my $fn = subject_fn($hdr); my @hdr = ('Content-Type'); if ($ibx->{obfuscate}) { # obfuscation is stupid, but maybe scrapers are, too... @@ -88,12 +85,11 @@ sub emit_raw { $fn .= '.txt'; } push @hdr, 'Content-Disposition', "inline; filename=$fn"; - [ 200, \@hdr, $more ? mb_stream($more) : [ msg_str($ctx, $first) ] ]; + [ 200, \@hdr, mb_stream($more) ]; } -sub msg_str { - my ($ctx, $simple, $mid) = @_; # Email::Simple object - my $header_obj = $simple->header_obj; +sub msg_hdr ($$;$) { + my ($ctx, $header_obj, $mid) = @_; # drop potentially confusing headers, ssoma already should've dropped # Lines and Content-Length @@ -109,7 +105,7 @@ sub msg_str { 'List-Archive', "<$base>", 'List-Post', "{-primary_address}>", ); - my $crlf = $simple->crlf; + my $crlf = $header_obj->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) { @@ -125,22 +121,37 @@ sub msg_str { $buf .= "$k: $v$crlf" if defined $v; } $buf .= $crlf; +} +sub msg_body ($) { # 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"; + $_[0] =~ s/^(>*From )/>$1/gm; + $_[0] .= "\n"; } sub thread_mbox { - my ($ctx, $srch, $sfx) = @_; + my ($ctx, $over, $sfx) = @_; eval { require IO::Compress::Gzip }; return sub { need_gzip(@_) } if $@; - - my $cb = sub { $srch->get_thread($ctx->{mid}, @_) }; - PublicInbox::MboxGz->response($ctx, $cb); + my $mid = $ctx->{mid}; + my $msgs = $over->get_thread($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, $msgs->[0]->subject); } sub emit_range { @@ -155,12 +166,59 @@ sub emit_range { mbox_all($ctx, $query); } +sub mbox_all_ids { + my ($ctx) = @_; + my $prev = 0; + my $ibx = $ctx->{-inbox}; + my $ids = $ibx->mm->ids_after(\$prev) or return + [404, [qw(Content-Type text/plain)], ["No results found\n"]]; + my $i = 0; + my $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, $cb, 'all'); +} + sub mbox_all { my ($ctx, $query) = @_; eval { require IO::Compress::Gzip }; return sub { need_gzip(@_) } if $@; - my $cb = sub { $ctx->{srch}->query($query, @_) }; + 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); } @@ -191,8 +249,6 @@ sub new { gz => IO::Compress::Gzip->new(\$buf, Time => 0), cb => $cb, ctx => $ctx, - msgs => [], - opts => { offset => 0 }, }, $class; } @@ -200,57 +256,37 @@ sub response { my ($class, $ctx, $cb, $fn) = @_; my $body = $class->new($ctx, $cb); # http://www.iana.org/assignments/media-types/application/gzip - $body->{hdr} = [ 'Content-Type', 'application/gzip' ]; - $body->{fn} = $fn; - my $hdr = $body->getline; # fill in Content-Disposition filename - [ 200, $hdr, $body ]; -} - -sub set_filename ($$) { - my ($fn, $msg) = @_; - return to_filename($fn) if defined($fn); - - PublicInbox::Mbox::subject_fn($msg); + my @h = qw(Content-Type application/gzip); + if ($fn) { + $fn = to_filename($fn); + push @h, 'Content-Disposition', "inline; filename=$fn.mbox.gz"; + } + [ 200, \@h, $body ]; } # called by Plack::Util::foreach or similar sub getline { my ($self) = @_; my $ctx = $self->{ctx} or return; - my $ibx = $ctx->{-inbox}; my $gz = $self->{gz}; - my $msgs = $self->{msgs}; - do { - # work on existing result set - while (defined(my $smsg = shift @$msgs)) { - my $msg = eval { $ibx->msg_by_smsg($smsg) } or next; - $msg = Email::Simple->new($msg); - $gz->write(PublicInbox::Mbox::msg_str($ctx, $msg, - $smsg->mid)); - - # use subject of first message as subject - if (my $hdr = delete $self->{hdr}) { - my $fn = set_filename($self->{fn}, $msg); - push @$hdr, 'Content-Disposition', - "inline; filename=$fn.mbox.gz"; - return $hdr; - } - my $bref = $self->{buf}; - if (length($$bref) >= 8192) { - my $ret = $$bref; # copy :< - ${$self->{buf}} = ''; - return $ret; - } + while (my $smsg = $self->{cb}->()) { + my $mref = $ctx->{-inbox}->msg_by_smsg($smsg) or next; + my $h = Email::Simple->new($mref)->header_obj; + $gz->write(PublicInbox::Mbox::msg_hdr($ctx, $h, $smsg->{mid})); + $gz->write(PublicInbox::Mbox::msg_body($$mref)); - # be fair to other clients on public-inbox-httpd: - return ''; + my $bref = $self->{buf}; + if (length($$bref) >= 8192) { + my $ret = $$bref; # copy :< + ${$self->{buf}} = ''; + return $ret; } - # refill result set - $msgs = $self->{msgs} = $self->{cb}->($self->{opts}); - $self->{opts}->{offset} += scalar @$msgs; - } while (@$msgs); - $gz->close; + # be fair to other clients on public-inbox-httpd: + return ''; + } + delete($self->{gz})->close; + # signal that we're done and can return undef next call: delete $self->{ctx}; ${delete $self->{buf}}; }