From: Eric Wong <e@yhbt.net>
Date: Wed, 10 Jun 2020 07:04:19 +0000 (+0000)
Subject: imap: speed up HEADER.FIELDS[.NOT] range fetches
X-Git-Tag: v1.6.0~445
X-Git-Url: http://www.git.stargrave.org/?p=public-inbox.git;a=commitdiff_plain;h=05978869826c50252d49a7977470ee3107eb2d16

imap: speed up HEADER.FIELDS[.NOT] range fetches

While we can't memoize the regexp forever like we do with other
Eml users, we can still benefit from caching regexp compilation
on a per-request basis.

A FETCH request from mutt on a 4K message inbox is around 8%
faster after this.  Since regexp compilation via qr// isn't
unbearably slow, a shared cache probably isn't worth the
trouble of implementing.  A per-request cache seems enough.
---

diff --git a/lib/PublicInbox/IMAP.pm b/lib/PublicInbox/IMAP.pm
index 0852ffab..39667199 100644
--- a/lib/PublicInbox/IMAP.pm
+++ b/lib/PublicInbox/IMAP.pm
@@ -544,25 +544,23 @@ sub hdrs_regexp ($) {
 
 # BODY[($SECTION_IDX.)?HEADER.FIELDS.NOT ($HDRS)]<$offset.$bytes>
 sub partial_hdr_not {
-	my ($eml, $section_idx, $hdrs) = @_;
+	my ($eml, $section_idx, $hdrs_re) = @_;
 	if (defined $section_idx) {
 		$eml = eml_body_idx($eml, $section_idx) or return;
 	}
 	my $str = $eml->header_obj->as_string;
-	my $re = hdrs_regexp($hdrs);
-	$str =~ s/$re//g;
+	$str =~ s/$hdrs_re//g;
 	$str .= "\r\n";
 }
 
 # BODY[($SECTION_IDX.)?HEADER.FIELDS ($HDRS)]<$offset.$bytes>
 sub partial_hdr_get {
-	my ($eml, $section_idx, $hdrs) = @_;
+	my ($eml, $section_idx, $hdrs_re) = @_;
 	if (defined $section_idx) {
 		$eml = eml_body_idx($eml, $section_idx) or return;
 	}
 	my $str = $eml->header_obj->as_string;
-	my $re = hdrs_regexp($hdrs);
-	join('', ($str =~ m/($re)/g), "\r\n");
+	join('', ($str =~ m/($hdrs_re)/g), "\r\n");
 }
 
 sub partial_prepare ($$$) {
@@ -583,9 +581,10 @@ sub partial_prepare ($$$) {
 				(?:HEADER\.FIELDS(\.NOT)?)\x20 # 2
 				\(([A-Z0-9\-\x20]+)\) # 3 - hdrs
 			\](?:<([0-9]+)(?:\.([0-9]+))?>)?\z/sx) { # 4 5
-		$partial->{$att} = [ $2 ? \&partial_hdr_not
-					: \&partial_hdr_get,
-					$1, $3, $4, $5 ];
+		my $tmp = $partial->{$att} = [ $2 ? \&partial_hdr_not
+						: \&partial_hdr_get,
+						$1, undef, $4, $5 ];
+		$tmp->[2] = hdrs_regexp($3);
 	} else {
 		undef;
 	}
diff --git a/t/imap.t b/t/imap.t
index fe6352b6..451b6596 100644
--- a/t/imap.t
+++ b/t/imap.t
@@ -46,17 +46,21 @@ use PublicInbox::IMAPD;
 	my $partial_body = \&PublicInbox::IMAP::partial_body;
 	my $partial_hdr_get = \&PublicInbox::IMAP::partial_hdr_get;
 	my $partial_hdr_not = \&PublicInbox::IMAP::partial_hdr_not;
+	my $hdrs_regexp = \&PublicInbox::IMAP::hdrs_regexp;
 	is_deeply($x, {
 		'BODY[9]' => [ $partial_body, 9, undef, undef, undef ],
 		'BODY[9]<5>' => [ $partial_body, 9, undef, 5, undef ],
 		'BODY[9]<5.1>' => [ $partial_body, 9, undef, 5, 1 ],
 		'BODY[1.1]' => [ $partial_body, '1.1', undef, undef, undef ],
 		'BODY[HEADER.FIELDS (DATE FROM)]' => [ $partial_hdr_get,
-					undef, 'DATE FROM', undef, undef ],
+					undef, $hdrs_regexp->('DATE FROM'),
+					undef, undef ],
 		'BODY[HEADER.FIELDS.NOT (TO)]' => [ $partial_hdr_not,
-						undef, 'TO', undef, undef ],
+						undef, $hdrs_regexp->('TO'),
+						undef, undef ],
 		'BODY[1.1.HEADER.FIELDS (TO)]' => [ $partial_hdr_get,
-						'1.1', 'TO', undef, undef ],
+						'1.1', $hdrs_regexp->('TO'),
+						undef, undef ],
 	}, 'structure matches expected');
 }