X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FMbox.pm;h=94e61d4d2ffdd99b3a5c5a9b2d14f2ca5bbfc1d5;hb=3b1b7abf814dbc7f2a737b2ca0e12b0fa518ff44;hp=42cedd15f5dead4a73170094327501f12111d983;hpb=4f0eed9d221a3e16da35145a17501798422f359e;p=public-inbox.git

diff --git a/lib/PublicInbox/Mbox.pm b/lib/PublicInbox/Mbox.pm
index 42cedd15..94e61d4d 100644
--- a/lib/PublicInbox/Mbox.pm
+++ b/lib/PublicInbox/Mbox.pm
@@ -1,4 +1,4 @@
-# Copyright (C) 2015-2019 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 (via getline) interface for formatting messages as an mboxrd.
@@ -12,22 +12,17 @@ use strict;
 use warnings;
 use PublicInbox::MID qw/mid_escape/;
 use PublicInbox::Hval qw/to_filename/;
-use Email::Simple;
-use Email::MIME::Encode;
+use PublicInbox::Smsg;
+use PublicInbox::WwwStream qw(html_oneshot);
+use PublicInbox::Eml;
 
 sub subject_fn ($) {
 	my ($hdr) = @_;
-	my $fn = $hdr->header('Subject');
-	return 'no-subject' unless defined($fn);
+	my $fn = $hdr->header_str('Subject');
+	return 'no-subject' if (!defined($fn) || $fn eq '');
 
-	# no need for full Email::MIME, here
-	if ($fn =~ /=\?/) {
-		eval { $fn = Encode::decode('MIME-Header', $fn) };
-		$fn = 'no-subject' if $@;
-	}
 	$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 +38,16 @@ 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
+	$hdr = PublicInbox::Eml->new($mref)->header_obj;
+	@$more = ($ctx, $id, $prev, $next); # $next may be undef, here
+	msg_hdr($ctx, $hdr) . msg_body($$mref);
 }
 
 sub close {} # noop
@@ -74,7 +66,7 @@ sub emit_raw {
 	} else {
 		$mref = $ibx->msg_by_mid($mid) or return;
 	}
-	my $hdr = Email::Simple->new($mref)->header_obj;
+	my $hdr = PublicInbox::Eml->new($mref)->header_obj;
 	$more = [ $ctx, $id, $prev, $next, $mref, $hdr ]; # for ->getline
 	my $fn = subject_fn($hdr);
 	my @hdr = ('Content-Type');
@@ -108,12 +100,15 @@ sub msg_hdr ($$;$) {
 		'List-Post', "<mailto:$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;
+	my $buf = $header_obj->as_string;
+	# fixup old bug from import (pre-a0c07cba0e5d8b6a)
+	$buf =~ s/\A[\r\n]*From [^\r\n]*\r?\n//s;
+	$buf = "From mboxrd\@z Thu Jan  1 00:00:00 1970" . $crlf . $buf;
+
 	for (my $i = 0; $i < @append; $i += 2) {
 		my $k = $append[$i];
 		my $v = $append[$i + 1];
-		my @v = $header_obj->header($k);
+		my @v = $header_obj->header_raw($k);
 		foreach (@v) {
 			if ($v eq $_) {
 				$v = undef;
@@ -134,28 +129,29 @@ sub msg_body ($) {
 	$_[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 PublicInbox::MboxGz };
-	return sub { need_gzip(@_) } if $@;
-	my $mid = $ctx->{mid};
-	my $msgs = $over->get_thread($mid, {});
+	require PublicInbox::MboxGz;
+	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 {
@@ -170,72 +166,66 @@ 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 PublicInbox::MboxGz };
-	return sub { need_gzip(@_) } if $@;
+	require PublicInbox::MboxGz;
 	return mbox_all_ids($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);
-}
-
-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 Compress::Raw::Zlib Perl module
-to support gzipped mboxes.
-<a href="../">Return to index</a></pre></body></html>
-EOF
-	$fh->close;
+	$ctx->{iter} = 0;
+	$ctx->{query} = $query;
+	PublicInbox::MboxGz->response($ctx, \&results_cb, 'results-'.$query);
 }
 
 1;