X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FMbox.pm;h=5693d30b1c5ab80ce08fe56f694ffd84b94d7522;hb=95bdac7f09c69036efed537a4d03d5bdd2ae4eb6;hp=6aa05170392cc42d841db0d026b2cc2ec189cf1d;hpb=db154d6852643c74eaa296e5967b05ab19f5ac99;p=public-inbox.git

diff --git a/lib/PublicInbox/Mbox.pm b/lib/PublicInbox/Mbox.pm
index 6aa05170..5693d30b 100644
--- a/lib/PublicInbox/Mbox.pm
+++ b/lib/PublicInbox/Mbox.pm
@@ -1,144 +1,251 @@
-# Copyright (C) 2015 all contributors <meta@public-inbox.org>
-# License: AGPLv3 or later (https://www.gnu.org/licenses/agpl-3.0.txt)
-# Streaming interface for formatting messages as an mboxrd
+# Copyright (C) 2015-2020 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)
 package PublicInbox::Mbox;
 use strict;
 use warnings;
-use PublicInbox::MID qw/mid2path/;
-require Email::Simple;
+use PublicInbox::MID qw/mid_escape/;
+use PublicInbox::Hval qw/to_filename/;
+use PublicInbox::SearchMsg;
+use Email::Simple;
+use Email::MIME::Encode;
+
+sub subject_fn ($) {
+	my ($hdr) = @_;
+	my $fn = $hdr->header('Subject');
+	return 'no-subject' if (!defined($fn) || $fn eq '');
+
+	# no need for full Email::MIME, here
+	if ($fn =~ /=\?/) {
+		eval { $fn = Encode::decode('MIME-Header', $fn) };
+		return 'no-subject' if $@;
+	}
+	$fn =~ s/^re:\s+//i;
+	$fn eq '' ? 'no-subject' : to_filename($fn);
+}
 
-sub thread_mbox {
-	my ($ctx, $srch, $sfx) = @_;
-	sub {
-		my ($response) = @_; # Plack callback
-		emit_mbox($response, $ctx, $srch, $sfx);
+sub mb_stream {
+	my ($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; # $hdr
+		return msg_hdr($ctx, $hdr);
+	}
+	if ($mref) { # all messages hit this
+		pop @$more; # $mref
+		return 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
 }
 
-sub emit1 {
-	my $simple = Email::Simple->new(pop);
-	sub {
-		my ($response) = @_;
-		# single message should be easily renderable in browsers
-		my $fh = $response->([200, ['Content-Type'=>'text/plain']]);
-		emit_msg($fh, $simple);
-		$fh->close;
+sub close {} # noop
+
+# /$INBOX/$MESSAGE_ID/raw
+sub emit_raw {
+	my ($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 $hdr = Email::Simple->new($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...
+		push @hdr, 'application/mbox';
+		$fn .= '.mbox';
+	} else {
+		push @hdr, 'text/plain';
+		$fn .= '.txt';
 	}
+	push @hdr, 'Content-Disposition', "inline; filename=$fn";
+	[ 200, \@hdr, mb_stream($more) ];
 }
 
-sub emit_msg {
-	my ($fh, $simple) = @_; # 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
 	foreach my $d (qw(Lines Bytes Content-Length Status)) {
 		$header_obj->header_set($d);
 	}
-
-	my $buf = $header_obj->as_string;
-	unless ($buf =~ /\AFrom /) {
-		$fh->write("From mboxrd\@z Thu Jan  1 00:00:00 1970\n");
+	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 = "From mboxrd\@z Thu Jan  1 00:00:00 1970\n" .
+			$header_obj->as_string;
+	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;
+			}
+		}
+		$buf .= "$k: $v$crlf" if defined $v;
 	}
-	$fh->write($buf .= $simple->crlf);
-
-	$buf = $simple->body;
-	$simple->body_set('');
+	$buf .= $crlf;
+}
 
+sub msg_body ($) {
 	# mboxrd quoting style
-	# ref: http://www.qmail.org/man/man5/mbox.html
-	$buf =~ s/^(>*From )/>$1/gm;
+	# 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";
+}
 
-	$buf .= "\n" unless $buf =~ /\n\z/s;
+sub thread_cb {
+	my ($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];
+	}
+}
 
-	$fh->write($buf);
+sub thread_mbox {
+	my ($ctx, $over, $sfx) = @_;
+	eval { require PublicInbox::MboxGz };
+	return need_gzip() if $@;
+	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);
 }
 
-sub emit_mbox {
-	my ($response, $ctx, $srch, $sfx) = @_;
-	my $type = 'mbox';
-	if ($sfx) {
-		eval { require IO::Compress::Gzip };
-		return need_gzip($response) if $@;
-		$type = 'gzip';
-	}
+sub emit_range {
+	my ($ctx, $range) = @_;
 
-	# http://www.iana.org/assignments/media-types/application/gzip
-	# http://www.iana.org/assignments/media-types/application/mbox
-	my $fh = $response->([200, ['Content-Type' => "application/$type"]]);
-	$fh = PublicInbox::MboxGz->new($fh) if $sfx;
+	my $query;
+	if ($range eq 'all') { # TODO: YYYY[-MM]
+		$query = '';
+	} else {
+		return [404, [qw(Content-Type text/plain)], []];
+	}
+	mbox_all($ctx, $query);
+}
 
-	require PublicInbox::GitCatFile;
-	my $mid = $ctx->{mid};
-	my $git = PublicInbox::GitCatFile->new($ctx->{git_dir});
-	my %opts = (offset => 0);
-	my $nr;
+sub all_ids_cb {
+	my ($ctx) = @_;
+	my $ids = $ctx->{ids};
 	do {
-		my $res = $srch->get_thread($mid, \%opts);
-		my $msgs = $res->{msgs};
-		$nr = scalar @$msgs;
-		while (defined(my $smsg = shift @$msgs)) {
-			my $msg = eval {
-				my $p = 'HEAD:'.mid2path($smsg->mid);
-				Email::Simple->new($git->cat_file($p));
-			};
-			emit_msg($fh, $msg) if $msg;
+		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);
+}
 
-		$opts{offset} += $nr;
-	} while ($nr > 0);
+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} = $ibx->over or
+		return PublicInbox::WWW::need($ctx, 'Overview');
+	$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 $smsg = PublicInbox::SearchMsg::from_mitem($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;
+	}
+}
 
-	$fh->close;
+sub mbox_all {
+	my ($ctx, $query) = @_;
+
+	eval { require PublicInbox::MboxGz };
+	return need_gzip() if $@;
+	return mbox_all_ids($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);
 }
 
 sub need_gzip {
-	my $fh = $_[0]->([501, ['Content-Type' => 'text/html']]);
 	my $title = 'gzipped mbox not available';
-	$fh->write(<<EOF);
+	my $body = <<EOF;
 <html><head><title>$title</title><body><pre>$title
-The administrator needs to install the IO::Compress::Gzip Perl module
+The administrator needs to install the Compress::Raw::Zlib Perl module
 to support gzipped mboxes.
 <a href="../">Return to index</a></pre></body></html>
 EOF
-	$fh->close;
-}
-
-1;
-
-# fh may not be a proper IO, so we wrap the write and close methods
-# to prevent IO::Compress::Gzip from complaining
-package PublicInbox::MboxGz;
-use strict;
-use warnings;
-
-sub new {
-	my ($class, $fh) = @_;
-	my $buf;
-	bless {
-		buf => \$buf,
-		gz => IO::Compress::Gzip->new(\$buf),
-		fh => $fh,
-	}, $class;
-}
-
-sub _flush_buf {
-	my ($self) = @_;
-	if (defined ${$self->{buf}}) {
-		$self->{fh}->write(${$self->{buf}});
-		${$self->{buf}} = undef;
-	}
-}
-
-sub write {
-	$_[0]->{gz}->write($_[1]);
-	_flush_buf($_[0]);
-}
 
-sub close {
-	my ($self) = @_;
-	$self->{gz}->close;
-	_flush_buf($self);
-	$self->{fh}->close;
+	[501,[qw(Content-Type text/html Content-Length), bytes::length($body)],
+	[ $body ] ];
 }
 
 1;