X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FMbox.pm;h=d5beceaf65e18b650e147dfef5ed213e8f1a5270;hb=1e5d704f1234ded472b800e42bedb5579780296e;hp=9e808c09502064e57642cf2f1c7e7e401d387a4e;hpb=e84f0a4fe260060b2055ed4c856308b4bb73b641;p=public-inbox.git diff --git a/lib/PublicInbox/Mbox.pm b/lib/PublicInbox/Mbox.pm index 9e808c09..d5beceaf 100644 --- a/lib/PublicInbox/Mbox.pm +++ b/lib/PublicInbox/Mbox.pm @@ -1,4 +1,4 @@ -# Copyright (C) 2015-2019 all contributors +# Copyright (C) 2015-2020 all contributors # License: AGPL-3.0+ # Streaming (via getline) interface for formatting messages as an mboxrd. @@ -12,22 +12,23 @@ use strict; use warnings; use PublicInbox::MID qw/mid_escape/; use PublicInbox::Hval qw/to_filename/; +use PublicInbox::Smsg; +use PublicInbox::WwwStream qw(html_oneshot); use Email::Simple; use Email::MIME::Encode; sub subject_fn ($) { my ($hdr) = @_; my $fn = $hdr->header('Subject'); - return 'no-subject' unless defined($fn); + return 'no-subject' if (!defined($fn) || $fn eq ''); # no need for full Email::MIME, here if ($fn =~ /=\?/) { eval { $fn = Encode::decode('MIME-Header', $fn) }; - $fn = 'no-subject' if $@; + return 'no-subject' if $@; } $fn =~ s/^re:\s+//i; - $fn = to_filename($fn); - $fn eq '' ? 'no-subject' : $fn; + $fn eq '' ? 'no-subject' : to_filename($fn); } sub mb_stream { @@ -43,19 +44,16 @@ sub getline { 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($$mref); + return msg_hdr($ctx, $hdr) . msg_body($$mref); } 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, $hdr); # all but first message hits this + @$more = ($ctx, $id, $prev, $next); # $next may be undef, here + msg_hdr($ctx, $hdr) . msg_body($$mref); } sub close {} # noop @@ -134,28 +132,30 @@ sub msg_body ($) { $_[0] .= "\n"; } +sub thread_cb { + my ($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, {}); + eval { require PublicInbox::MboxGz }; + return need_gzip($ctx) if $@; + 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} = $over; # bump refcnt + PublicInbox::MboxGz->response($ctx, \&thread_cb, $msgs->[0]->subject); } sub emit_range { @@ -170,132 +170,78 @@ sub emit_range { mbox_all($ctx, $query); } +sub all_ids_cb { + my ($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} = $prev; + return PublicInbox::MboxGz->response($ctx, \&all_ids_cb, 'all'); +} + +sub results_cb { + my ($ctx) = @_; + my $mset = $ctx->{mset}; + my $srch = $ctx->{srch}; + while (1) { + while (my $mi = (($mset->items)[$ctx->{iter}++])) { + my $smsg = PublicInbox::Smsg::from_mitem($mi, + $srch) 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; + $ctx->{iter} = 0; + } } sub mbox_all { my ($ctx, $query) = @_; - eval { require IO::Compress::Gzip }; - return sub { need_gzip(@_) } if $@; + eval { require PublicInbox::MboxGz }; + return need_gzip($ctx) if $@; return mbox_all_ids($ctx) if $query eq ''; - my $opts = { mset => 2 }; - my $srch = $ctx->{-inbox}->search or + my $qopts = $ctx->{qopts} = { mset => 2 }; + my $srch = $ctx->{srch} = $ctx->{-inbox}->search or return PublicInbox::WWW::need($ctx, 'Search');; - my $mset = $srch->query($query, $opts); - $opts->{offset} = $mset->size or + my $mset = $ctx->{mset} = $srch->query($query, $qopts); + $qopts->{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); + $ctx->{iter} = 0; + $ctx->{query} = $query; + PublicInbox::MboxGz->response($ctx, \&results_cb, 'results-'.$query); } 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 - $fh->close; -} - -1; - -package PublicInbox::MboxGz; -use strict; -use warnings; -use PublicInbox::Hval qw/to_filename/; - -sub new { - my ($class, $ctx, $cb) = @_; - my $buf = ''; - $ctx->{base_url} = $ctx->{-inbox}->base_url($ctx->{env}); - bless { - buf => \$buf, - gz => IO::Compress::Gzip->new(\$buf, Time => 0), - cb => $cb, - ctx => $ctx, - }, $class; -} + html_oneshot($_[0], 501, \<gzipped mbox not available -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"; - } - [ 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 $ret; - } +The administrator needs to install the Compress::Raw::Zlib Perl module +to support gzipped mboxes. - # be fair to other clients on public-inbox-httpd: - return ''; - } - delete($self->{gz})->close; - # signal that we're done and can return undef next call: - delete $self->{ctx}; - ${delete $self->{buf}}; +Return to index +EOF } -sub close {} # noop - 1;