X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FMbox.pm;h=d5beceaf65e18b650e147dfef5ed213e8f1a5270;hb=1e5d704f1234ded472b800e42bedb5579780296e;hp=11b23022ff5ed8270af2f5f70ad0bbf3524c08af;hpb=6f4fcc32237e46fb219df9ad4e92aeb3a170d03f;p=public-inbox.git

diff --git a/lib/PublicInbox/Mbox.pm b/lib/PublicInbox/Mbox.pm
index 11b23022..d5beceaf 100644
--- a/lib/PublicInbox/Mbox.pm
+++ b/lib/PublicInbox/Mbox.pm
@@ -1,29 +1,34 @@
-# Copyright (C) 2015-2018 all contributors <meta@public-inbox.org>
+# Copyright (C) 2015-2020 all contributors <meta@public-inbox.org>
 # License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
 
-# 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;
-use PublicInbox::MID qw/mid_clean mid_escape/;
+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 ($) {
-	my ($simple) = @_;
-	my $fn = $simple->header('Subject');
-	return 'no-subject' unless defined($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) };
-		$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 {
@@ -32,43 +37,44 @@ 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, $id, $prev, $next, $cur) = @$more;
-	if ($cur) { # first
-		pop @$more;
-		return msg_str($ctx, $cur);
+	my ($ctx, $id, $prev, $next, $mref, $hdr) = @$more;
+	if ($hdr) { # first message hits this, only
+		pop @$more; # $hdr
+		pop @$more; # $mref
+		return msg_hdr($ctx, $hdr) . msg_body($$mref);
 	}
-	$cur = $next or return;
+	my $cur = $next or return;
 	my $ibx = $ctx->{-inbox};
-	$next = $ibx->search->next_by_mid($ctx->{mid}, \$id, \$prev);
+	$next = $ibx->over->next_by_mid($ctx->{mid}, \$id, \$prev);
+	$mref = $ibx->msg_by_smsg($cur) or return;
+	$hdr = Email::Simple->new($mref)->header_obj;
 	@$more = ($ctx, $id, $prev, $next); # $next may be undef, here
-	my $mref = $ibx->msg_by_smsg($cur) or return;
-	msg_str($ctx, Email::Simple->new($mref));
+	msg_hdr($ctx, $hdr) . msg_body($$mref);
 }
 
 sub close {} # noop
 
+# /$INBOX/$MESSAGE_ID/raw
 sub emit_raw {
 	my ($ctx) = @_;
 	my $mid = $ctx->{mid};
 	my $ibx = $ctx->{-inbox};
-	my $first;
-	my $more;
-	if (my $srch = $ibx->search) {
-		my ($id, $prev);
-		my $smsg = $srch->next_by_mid($mid, \$id, \$prev) or return;
-		my $mref = $ibx->msg_by_smsg($smsg) or return;
-		$first = Email::Simple->new($mref);
-		my $next = $srch->next_by_mid($mid, \$id, \$prev);
-		# $more is for ->getline
-		$more = [ $ctx, $id, $prev, $next, $first ] if $next;
+	$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 {
-		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...
@@ -79,12 +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
@@ -92,7 +97,7 @@ sub msg_str {
 		$header_obj->header_set($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 = (
@@ -100,7 +105,7 @@ sub msg_str {
 		'List-Archive', "<$base>",
 		'List-Post', "<mailto:$ibx->{-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) {
@@ -116,37 +121,41 @@ 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";
+	# 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;
+	$_[0] .= "\n";
+}
+
+sub thread_cb {
+	my ($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, $srch, $sfx) = @_;
-	eval { require IO::Compress::Gzip };
-	return sub { need_gzip(@_) } if $@;
-	my $mid = $ctx->{mid};
-	my $msgs = $srch->get_thread($mid, {});
+	my ($ctx, $over, $sfx) = @_;
+	eval { require PublicInbox::MboxGz };
+	return need_gzip($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 = $srch->get_thread($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 {
@@ -161,126 +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 $ibx = $ctx->{-inbox};
 	my $prev = 0;
-	my $ids = $ctx->{-inbox}->mm->ids_after(\$prev) or return
+	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 = $ctx->{srch}->{over_ro};
-	my $cb = sub {
-		do {
-			while ((my $num = $ids->[$i++])) {
-				my $smsg = $over->get_art($num) or next;
-				return $smsg;
-			}
-			$ids = $ctx->{-inbox}->mm->ids_after(\$prev);
-			$i = 0;
-		} while (@$ids);
-		undef;
-	};
-	return PublicInbox::MboxGz->response($ctx, $cb, 'all');
+	$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 $smsg = PublicInbox::Smsg::from_mitem($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->{srch};
-	my $mset = $srch->query($query, $opts);
-	$opts->{offset} = $mset->size or
+	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"]];
-	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';
-	$fh->write(<<EOF);
-<html><head><title>$title</title><body><pre>$title
-The administrator needs to install the IO::Compress::Gzip Perl module
-to support gzipped mboxes.
-<a href="../">Return to index</a></pre></body></html>
-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 = '';
-	bless {
-		buf => \$buf,
-		gz => IO::Compress::Gzip->new(\$buf, Time => 0),
-		cb => $cb,
-		ctx => $ctx,
-	}, $class;
-}
-
-sub response {
-	my ($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, $body ];
-}
+	html_oneshot($_[0], 501, \<<EOF);
+<pre>gzipped mbox not available
 
-# called by Plack::Util::foreach or similar
-sub getline {
-	my ($self) = @_;
-	my $ctx = $self->{ctx} or return;
-	while (my $smsg = $self->{cb}->()) {
-		my $msg = $ctx->{-inbox}->msg_by_smsg($smsg) or next;
-		$msg = Email::Simple->new($msg);
-		$self->{gz}->write(PublicInbox::Mbox::msg_str($ctx, $msg,
-				$smsg->{mid}));
-		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}};
+<a href="../">Return to index</a></pre>
+EOF
 }
 
-sub close {} # noop
-
 1;