X-Git-Url: http://www.git.stargrave.org/?p=public-inbox.git;a=blobdiff_plain;f=lib%2FPublicInbox%2FWwwAttach.pm;h=09c66d0239cb40a5a3942f957154b4ec54fc1097;hp=2de568041f31a17b28f76faf28e68a892b755a5e;hb=c39ed01a3a4c6c4634642eb875a16538aceacfc3;hpb=9bd675d33ad1e49bd2ebe12a1d216216e61380de

diff --git a/lib/PublicInbox/WwwAttach.pm b/lib/PublicInbox/WwwAttach.pm
index 2de56804..09c66d02 100644
--- a/lib/PublicInbox/WwwAttach.pm
+++ b/lib/PublicInbox/WwwAttach.pm
@@ -1,43 +1,107 @@
-# Copyright (C) 2016-2019 all contributors <meta@public-inbox.org>
+# Copyright (C) 2016-2020 all contributors <meta@public-inbox.org>
 # License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
 
 # For retrieving attachments from messages in the WWW interface
 package PublicInbox::WwwAttach; # internal package
 use strict;
-use warnings;
+use parent qw(PublicInbox::GzipFilter);
 use bytes (); # only for bytes::length
-use Email::MIME::ContentType qw(parse_content_type);
-use PublicInbox::MIME;
-use PublicInbox::MsgIter;
+use PublicInbox::EmlContentFoo qw(parse_content_type);
+use PublicInbox::Eml;
+
+sub referer_match ($) {
+	my ($ctx) = @_;
+	my $env = $ctx->{env};
+	my $referer = $env->{HTTP_REFERER} // '';
+	return 1 if $referer eq ''; # no referer is always OK for wget/curl
+
+	# prevent deep-linking from other domains on some browsers (Firefox)
+	# n.b.: $ctx->{-inbox}->base_url($env) with INBOX_URL won't work
+	# with dillo, we can only match "$url_scheme://$HTTP_HOST/" without
+	# path components
+	my $base_url = $env->{'psgi.url_scheme'} . '://' .
+			($env->{HTTP_HOST} //
+			 "$env->{SERVER_NAME}:$env->{SERVER_PORT}") . '/';
+	index($referer, $base_url) == 0;
+}
+
+sub get_attach_i { # ->each_part callback
+	my ($part, $depth, $idx) = @{$_[0]};
+	my $ctx = $_[1];
+	return if $idx ne $ctx->{idx}; # [0-9]+(?:\.[0-9]+)+
+	my $res = $ctx->{res};
+	$res->[0] = 200;
+	my $ct = $part->content_type;
+	$ct = parse_content_type($ct) if $ct;
+
+	if ($ct && (($ct->{type} || '') eq 'text')) {
+		# display all text as text/plain:
+		my $cset = $ct->{attributes}->{charset};
+		if ($cset && ($cset =~ /\A[a-zA-Z0-9_\-]+\z/)) {
+			$res->[1]->[1] .= qq(; charset=$cset);
+		}
+		$ctx->{gz} = PublicInbox::GzipFilter::gz_or_noop($res->[1],
+								$ctx->{env});
+		$part = $ctx->zflush($part->body);
+	} else { # TODO: allow user to configure safe types
+		if (referer_match($ctx)) {
+			$res->[1]->[1] = 'application/octet-stream';
+			$part = $part->body;
+		} else {
+			$res->[0] = 403;
+			$res->[1]->[1] = 'text/plain';
+			$part = "Deep-linking prevented\n";
+		}
+	}
+	push @{$res->[1]}, 'Content-Length', bytes::length($part);
+	$res->[2]->[0] = $part;
+}
+
+sub async_eml { # for async_blob_cb
+	my ($ctx, $eml) = @_;
+	eval { $eml->each_part(\&get_attach_i, $ctx, 1) };
+	if ($@) {
+		$ctx->{res}->[0] = 500;
+		warn "E: $@";
+	}
+}
+
+sub async_next {
+	my ($http) = @_;
+	my $ctx = $http->{forward} or return; # client aborted
+	# finally, we call the user-supplied callback
+	eval { $ctx->{wcb}->($ctx->{res}) };
+	warn "E: $@" if $@;
+}
+
+sub scan_attach ($) { # public-inbox-httpd only
+	my ($ctx) = @_;
+	$ctx->{env}->{'psgix.io'}->{forward} = $ctx;
+	$ctx->smsg_blob($ctx->{smsg});
+}
 
 # /$LISTNAME/$MESSAGE_ID/$IDX-$FILENAME
 sub get_attach ($$$) {
 	my ($ctx, $idx, $fn) = @_;
-	my $res = [ 404, [ 'Content-Type', 'text/plain' ], [ "Not found\n" ] ];
-	my $mime = $ctx->{-inbox}->msg_by_mid($ctx->{mid}) or return $res;
-	$mime = PublicInbox::MIME->new($mime);
-	msg_iter($mime, sub {
-		my ($part, $depth, @idx) = @{$_[0]};
-		return if join('.', @idx) ne $idx;
-		$res->[0] = 200;
-		my $ct = $part->content_type;
-		$ct = parse_content_type($ct) if $ct;
-
-		# discrete == type, we remain Debian wheezy-compatible
-		if ($ct && (($ct->{discrete} || '') eq 'text')) {
-			# display all text as text/plain:
-			my $cset = $ct->{attributes}->{charset};
-			if ($cset && ($cset =~ /\A[a-zA-Z0-9_\-]+\z/)) {
-				$res->[1]->[1] .= qq(; charset=$cset);
-			}
-		} else { # TODO: allow user to configure safe types
-			$res->[1]->[1] = 'application/octet-stream';
+	$ctx->{res} = [ 404, [ 'Content-Type' => 'text/plain' ],
+				[ "Not found\n" ] ];
+	$ctx->{idx} = $idx;
+	bless $ctx, __PACKAGE__;
+	my $eml;
+	if ($ctx->{smsg} = $ctx->{-inbox}->smsg_by_mid($ctx->{mid})) {
+		return sub { # public-inbox-httpd-only
+			$ctx->{wcb} = $_[0];
+			scan_attach($ctx);
+		} if $ctx->{env}->{'pi-httpd.async'};
+		# generic PSGI:
+		$eml = $ctx->{-inbox}->smsg_eml($ctx->{smsg});
+	} elsif (!$ctx->{-inbox}->over) {
+		if (my $bref = $ctx->{-inbox}->msg_by_mid($ctx->{mid})) {
+			$eml = PublicInbox::Eml->new($bref);
 		}
-		$part = $part->body;
-		push @{$res->[1]}, 'Content-Length', bytes::length($part);
-		$res->[2]->[0] = $part;
-	});
-	$res;
+	}
+	$eml->each_part(\&get_attach_i, $ctx, 1) if $eml;
+	$ctx->{res}
 }
 
 1;