user/dev discussion of public-inbox itself
 help / color / mirror / code / Atom feed
From: Eric Wong <e@yhbt.net>
To: meta@public-inbox.org
Subject: [PATCH 72/82] imap: FETCH: more granular CRLF conversion
Date: Wed, 10 Jun 2020 07:05:09 +0000	[thread overview]
Message-ID: <20200610070519.18252-73-e@yhbt.net> (raw)
In-Reply-To: <20200610070519.18252-1-e@yhbt.net>

This speeds up requests from mutt for HEADER.FIELDS by around 10%
since we don't waste time doing CRLF conversion on large message
bodies that get discarded, anyways.
---
 lib/PublicInbox/IMAP.pm | 80 ++++++++++++++++++++++++++---------------
 t/imap.t                | 29 +++++++++------
 2 files changed, 70 insertions(+), 39 deletions(-)

diff --git a/lib/PublicInbox/IMAP.pm b/lib/PublicInbox/IMAP.pm
index e9fa338b5fe..3cc68e66872 100644
--- a/lib/PublicInbox/IMAP.pm
+++ b/lib/PublicInbox/IMAP.pm
@@ -40,20 +40,27 @@ sub UID_BLOCK () { 50_000 }
 # these values area also used for sorting
 sub NEED_SMSG () { 1 }
 sub NEED_BLOB () { NEED_SMSG|2 }
-sub NEED_EML () { NEED_BLOB|4 }
-my $OP_EML_NEW = [ NEED_EML - 1, \&op_eml_new ];
+sub CRLF_BREF () { 4 }
+sub EML_HDR () { 8 }
+sub CRLF_HDR () { 16 }
+sub EML_BDY () { 32 }
+sub CRLF_BDY () { 64 }
+my $OP_EML_NEW = [ EML_HDR - 1, \&op_eml_new ];
+my $OP_CRLF_BREF = [ CRLF_BREF, \&op_crlf_bref ];
+my $OP_CRLF_HDR = [ CRLF_HDR, \&op_crlf_hdr ];
+my $OP_CRLF_BDY = [ CRLF_BDY, \&op_crlf_bdy ];
 
 my %FETCH_NEED = (
-	'BODY[HEADER]' => [ NEED_EML, \&emit_rfc822_header ],
-	'BODY[TEXT]' => [ NEED_EML, \&emit_rfc822_text ],
-	'BODY[]' => [ NEED_BLOB, \&emit_rfc822 ],
-	'RFC822.HEADER' => [ NEED_EML, \&emit_rfc822_header ],
-	'RFC822.TEXT' => [ NEED_EML, \&emit_rfc822_text ],
+	'BODY[HEADER]' => [ NEED_BLOB|EML_HDR|CRLF_HDR, \&emit_rfc822_header ],
+	'BODY[TEXT]' => [ NEED_BLOB|EML_BDY|CRLF_BDY, \&emit_rfc822_text ],
+	'BODY[]' => [ NEED_BLOB|CRLF_BREF, \&emit_rfc822 ],
+	'RFC822.HEADER' => [ NEED_BLOB|EML_HDR|CRLF_HDR, \&emit_rfc822_header ],
+	'RFC822.TEXT' => [ NEED_BLOB|EML_BDY|CRLF_BDY, \&emit_rfc822_text ],
 	'RFC822.SIZE' => [ NEED_SMSG, \&emit_rfc822_size ],
-	RFC822 => [ NEED_BLOB, \&emit_rfc822 ],
-	BODY => [ NEED_EML, \&emit_body ],
-	BODYSTRUCTURE => [ NEED_EML, \&emit_bodystructure ],
-	ENVELOPE => [ NEED_EML, \&emit_envelope ],
+	RFC822 => [ NEED_BLOB|CRLF_BREF, \&emit_rfc822 ],
+	BODY => [ NEED_BLOB|EML_HDR|EML_BDY, \&emit_body ],
+	BODYSTRUCTURE => [ NEED_BLOB|EML_HDR|EML_BDY, \&emit_bodystructure ],
+	ENVELOPE => [ NEED_BLOB|EML_HDR, \&emit_envelope ],
 	FLAGS => [ 0, \&emit_flags ],
 	INTERNALDATE => [ NEED_SMSG, \&emit_internaldate ],
 );
@@ -494,10 +501,6 @@ sub fetch_blob_cb { # called by git->cat_async via git_async_cat
 	} else {
 		$smsg->{blob} eq $oid or die "BUG: $smsg->{blob} != $oid";
 	}
-	$$bref =~ s/(?<!\r)\n/\r\n/sg; # make strict clients happy
-
-	# fixup old bug from import (pre-a0c07cba0e5d8b6a)
-	$$bref =~ s/\A[\r\n]*From [^\r\n]*\r\n//s;
 	fetch_run_ops($self, $self->{uid_base}, $smsg, $bref, $ops, $partial);
 	requeue_once($self);
 }
@@ -554,6 +557,18 @@ sub emit_body {
 # set $eml once ($_[4] == $eml, $_[3] == $bref)
 sub op_eml_new { $_[4] = PublicInbox::Eml->new($_[3]) }
 
+# s/From / fixes old bug from import (pre-a0c07cba0e5d8b6a)
+sub to_crlf_full {
+	${$_[0]} =~ s/(?<!\r)\n/\r\n/sg;
+	${$_[0]} =~ s/\A[\r\n]*From [^\r\n]*\r\n//s;
+}
+
+sub op_crlf_bref { to_crlf_full($_[3]) }
+
+sub op_crlf_hdr { to_crlf_full($_[4]->{hdr}) }
+
+sub op_crlf_bdy { ${$_[4]->{bdy}} =~ s/(?<!\r)\n/\r\n/sg if $_[4]->{bdy} }
+
 sub uid_clamp ($$$) {
 	my ($self, $beg, $end) = @_;
 	my $uid_min = $self->{uid_base} + 1;
@@ -790,8 +805,8 @@ sub partial_hdr_get {
 	join('', ($str =~ m/($hdrs_re)/g), "\r\n");
 }
 
-sub partial_prepare ($$$) {
-	my ($partial, $want, $att) = @_;
+sub partial_prepare ($$$$) {
+	my ($need, $partial, $want, $att) = @_;
 
 	# recombine [ "BODY[1.HEADER.FIELDS", "(foo", "bar)]" ]
 	# back to: "BODY[1.HEADER.FIELDS (foo bar)]"
@@ -804,6 +819,7 @@ sub partial_prepare ($$$) {
 			(?:\.(HEADER|MIME|TEXT))? # 2 - section_name
 			\](?:<([0-9]+)(?:\.([0-9]+))?>)?\z/sx) { # 3, 4
 		$partial->{$att} = [ \&partial_body, $1, $2, $3, $4 ];
+		$$need |= CRLF_BREF|EML_HDR|EML_BDY;
 	} elsif ($att =~ /\ABODY\[(?:([0-9]+(?:\.[0-9]+)*)\.)? # 1 - section_idx
 				(?:HEADER\.FIELDS(\.NOT)?)\x20 # 2
 				\(([A-Z0-9\-\x20]+)\) # 3 - hdrs
@@ -812,6 +828,7 @@ sub partial_prepare ($$$) {
 						: \&partial_hdr_get,
 						$1, undef, $4, $5 ];
 		$tmp->[2] = hdrs_regexp($3);
+		$$need |= CRLF_HDR|EML_HDR;
 	} else {
 		undef;
 	}
@@ -857,16 +874,9 @@ sub fetch_compile ($) {
 			while (my ($k, $fl_cb) = each %$x) {
 				next if $seen{$k}++;
 				$need |= $fl_cb->[0];
-
-				# insert a special op to convert $bref to $eml
-				# the first time we need it
-				if ($need == NEED_EML && !$seen{$need}++) {
-					push @op, $OP_EML_NEW;
-				}
-				# $fl_cb = [ flags, \&emit_foo ]
-				push @op, [ @$fl_cb , $k ];
+				push @op, [ @$fl_cb, $k ];
 			}
-		} elsif (!partial_prepare(\%partial, $want, $att)) {
+		} elsif (!partial_prepare(\$need, \%partial, $want, $att)) {
 			return "BAD param: $att";
 		}
 	}
@@ -874,11 +884,25 @@ sub fetch_compile ($) {
 
 	# stabilize partial order for consistency and ease-of-debugging:
 	if (scalar keys %partial) {
-		$need = NEED_EML;
-		push @op, $OP_EML_NEW if !$seen{$need}++;
+		$need |= NEED_BLOB;
 		$r[2] = [ map { [ $_, @{$partial{$_}} ] } sort keys %partial ];
 	}
 
+	push @op, $OP_EML_NEW if ($need & (EML_HDR|EML_BDY));
+
+	# do we need CRLF conversion?
+	if ($need & CRLF_BREF) {
+		push @op, $OP_CRLF_BREF;
+	} elsif (my $crlf = ($need & (CRLF_HDR|CRLF_BDY))) {
+		if ($crlf == (CRLF_HDR|CRLF_BDY)) {
+			push @op, $OP_CRLF_BREF;
+		} elsif ($need & CRLF_HDR) {
+			push @op, $OP_CRLF_HDR;
+		} else {
+			push @op, $OP_CRLF_BDY;
+		}
+	}
+
 	$r[0] = $need & NEED_BLOB ? \&fetch_blob :
 		($need & NEED_SMSG ? \&fetch_smsg : \&fetch_uid);
 
diff --git a/t/imap.t b/t/imap.t
index 2401237c8a0..81b3d844e76 100644
--- a/t/imap.t
+++ b/t/imap.t
@@ -70,21 +70,26 @@ EOF
 {
 	my $partial_prepare = \&PublicInbox::IMAP::partial_prepare;
 	my $x = {};
-	my $r = $partial_prepare->($x, [], my $p = 'BODY[9]');
+	my $n = 0;
+	my $r = $partial_prepare->(\$n, $x, [], my $p = 'BODY[9]');
 	ok($r, $p);
-	$r = $partial_prepare->($x, [], $p = 'BODY[9]<5>');
+	$r = $partial_prepare->(\$n, $x, [], $p = 'BODY[9]<5>');
 	ok($r, $p);
-	$r = $partial_prepare->($x, [], $p = 'BODY[9]<5.1>');
+	$r = $partial_prepare->(\$n, $x, [], $p = 'BODY[9]<5.1>');
 	ok($r, $p);
-	$r = $partial_prepare->($x, [], $p = 'BODY[1.1]');
+	$r = $partial_prepare->(\$n, $x, [], $p = 'BODY[1.1]');
 	ok($r, $p);
-	$r = $partial_prepare->($x, [], $p = 'BODY[HEADER.FIELDS (DATE FROM)]');
+	$r = $partial_prepare->(\$n, $x, [],
+				$p = 'BODY[HEADER.FIELDS (DATE FROM)]');
 	ok($r, $p);
-	$r = $partial_prepare->($x, [], $p = 'BODY[HEADER.FIELDS.NOT (TO)]');
+	$r = $partial_prepare->(\$n, $x, [],
+				$p = 'BODY[HEADER.FIELDS.NOT (TO)]');
 	ok($r, $p);
-	$r = $partial_prepare->($x, [], $p = 'BODY[HEDDER.FIELDS.NOT (TO)]');
+	$r = $partial_prepare->(\$n, $x, [],
+				$p = 'BODY[HEDDER.FIELDS.NOT (TO)]');
 	ok(!$r, "rejected misspelling $p");
-	$r = $partial_prepare->($x, [], $p = 'BODY[1.1.HEADER.FIELDS (TO)]');
+	$r = $partial_prepare->(\$n, $x, [],
+				$p = 'BODY[1.1.HEADER.FIELDS (TO)]');
 	ok($r, $p);
 	my $partial_body = \&PublicInbox::IMAP::partial_body;
 	my $partial_hdr_get = \&PublicInbox::IMAP::partial_hdr_get;
@@ -111,12 +116,14 @@ EOF
 	my $fetch_compile = \&PublicInbox::IMAP::fetch_compile;
 	my ($cb, $ops, $partial) = $fetch_compile->(['BODY[]']);
 	is($partial, undef, 'no partial fetch data');
-	is_deeply($ops,
-		[ 'BODY[]', \&PublicInbox::IMAP::emit_rfc822 ],
-		'proper key and op compiled for BODY[]');
+	is_deeply($ops, [
+		undef, \&PublicInbox::IMAP::op_crlf_bref,
+		'BODY[]', \&PublicInbox::IMAP::emit_rfc822
+	], 'proper key and op compiled for BODY[]');
 
 	($cb, $ops, $partial) = $fetch_compile->(['BODY', 'BODY[]']);
 	is_deeply($ops, [
+		undef, \&PublicInbox::IMAP::op_crlf_bref,
 		'BODY[]', \&PublicInbox::IMAP::emit_rfc822,
 		undef, \&PublicInbox::IMAP::op_eml_new,
 		'BODY', \&PublicInbox::IMAP::emit_body,

  parent reply	other threads:[~2020-06-10  7:07 UTC|newest]

Thread overview: 84+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-06-10  7:03 [PATCH 00/82] public-inbox-imapd: read-only IMAP server Eric Wong
2020-06-10  7:03 ` [PATCH 01/82] doc: add some IMAP standards Eric Wong
2020-06-10  7:03 ` [PATCH 02/82] nntpd: restrict allowed newsgroup names Eric Wong
2020-06-10  7:04 ` [PATCH 03/82] preliminary imap server implementation Eric Wong
2020-06-10  7:04 ` [PATCH 04/82] inboxidle: new class to detect inbox changes Eric Wong
2020-06-10  7:04 ` [PATCH 05/82] imap: support IDLE Eric Wong
2020-06-10  7:04 ` [PATCH 06/82] msgmap: split ->max into its own method Eric Wong
2020-06-10  7:04 ` [PATCH 07/82] imap: delay InboxIdle start, support refresh Eric Wong
2020-06-10  7:04 ` [PATCH 08/82] imap: implement STATUS command Eric Wong
2020-06-10  7:04 ` [PATCH 09/82] imap: use Text::ParseWords::parse_line to handle quoted words Eric Wong
2020-06-10  7:04 ` [PATCH 10/82] imap: support LIST command Eric Wong
2020-06-10  7:04 ` [PATCH 11/82] t/imapd: support FakeInotify and KQNotify Eric Wong
2020-06-10  7:04 ` [PATCH 12/82] imap: support fetch for BODYSTRUCTURE and BODY Eric Wong
2020-06-10  7:04 ` [PATCH 13/82] eml: each_part: single part $idx is 1 Eric Wong
2020-06-10  7:04 ` [PATCH 14/82] imap: allow fetch of partial of BODY[...] and headers Eric Wong
2020-06-10  7:04 ` [PATCH 15/82] imap: always include `resp-text' in responses Eric Wong
2020-06-10  7:04 ` [PATCH 16/82] imap: split out unit tests and benchmarks Eric Wong
2020-06-10  7:04 ` [PATCH 17/82] imap: fix multi-message partial header fetches Eric Wong
2020-06-10  7:04 ` [PATCH 18/82] imap: simplify partial fetch structure Eric Wong
2020-06-10  7:04 ` [PATCH 19/82] imap: support sequence number FETCH Eric Wong
2020-06-10  7:04 ` [PATCH 20/82] imap: do not include ".PEEK" in responses Eric Wong
2020-06-10  7:04 ` [PATCH 21/82] imap: support the CLOSE command Eric Wong
2020-06-10  7:04 ` [PATCH 22/82] imap: speed up HEADER.FIELDS[.NOT] range fetches Eric Wong
2020-06-10  7:04 ` [PATCH 23/82] git: async: flatten the inflight array Eric Wong
2020-06-10  7:04 ` [PATCH 24/82] git: do our own read buffering for cat-file Eric Wong
2020-06-10  7:04 ` [PATCH 25/82] imap: use git-cat-file asynchronously Eric Wong
2020-06-10  7:04 ` [PATCH 26/82] git: idle rbuf for async Eric Wong
2020-06-10  7:04 ` [PATCH 27/82] imap: support LSUB command Eric Wong
2020-06-10  7:04 ` [PATCH 28/82] imap: FETCH: support comma-delimited ranges Eric Wong
2020-06-10  7:04 ` [PATCH 29/82] add imapd compression test Eric Wong
2020-06-10  7:04 ` [PATCH 30/82] testcommon: tcp_(server|connect): BAIL_OUT on failure Eric Wong
2020-06-10  7:04 ` [PATCH 31/82] *deflate: drop invalid comment about rbuf Eric Wong
2020-06-10  7:04 ` [PATCH 32/82] imap: fix pipelining with async git Eric Wong
2020-06-10  7:04 ` [PATCH 33/82] git: cat_async: provide requested OID + "missing" on missing blobs Eric Wong
2020-06-10  7:04 ` [PATCH 34/82] git: move async_cat reference to PublicInbox::Git Eric Wong
2020-06-10  7:04 ` [PATCH 35/82] git: async: automatic retry on alternates change Eric Wong
2020-06-10  7:04 ` [PATCH 36/82] imapclient: wrapper for Mail::IMAPClient Eric Wong
2020-06-10  7:04 ` [PATCH 37/82] xt: add imapd-validate and imapd-mbsync-oimap Eric Wong
2020-06-10  7:04 ` [PATCH 38/82] imap: support out-of-bounds ranges Eric Wong
2020-06-10  7:04 ` [PATCH 39/82] xt/perf-imap-list: time refresh_inboxlist Eric Wong
2020-06-10  7:04 ` [PATCH 40/82] imap: case-insensitive mailbox name comparisons Eric Wong
2020-06-10  7:04 ` [PATCH 41/82] imap: break giant inboxes into sub-inboxes of 50K messages Eric Wong
2020-06-10  7:04 ` [PATCH 42/82] imap: start doing iterative config reloading Eric Wong
2020-06-10  7:04 ` [PATCH 43/82] imap: require ".$UID_MIN-$UID_END" suffix Eric Wong
2020-06-10  7:04 ` [PATCH 44/82] imapd: ensure LIST is sorted alphabetically, for now Eric Wong
2020-06-10  7:04 ` [PATCH 45/82] imap: omit $UID_END from mailbox name, use index Eric Wong
2020-06-10  7:04 ` [PATCH 46/82] t/config.t: always compare against git bool behavior Eric Wong
2020-06-10  7:04 ` [PATCH 47/82] xt/*: show some tunable parameters Eric Wong
2020-06-10  7:04 ` [PATCH 48/82] imap: STATUS and LIST are case-insensitive, too Eric Wong
2020-06-10  7:04 ` [PATCH 49/82] imap: EXAMINE/STATUS: return correct counts Eric Wong
2020-06-10  7:04 ` [PATCH 50/82] imap: avoid uninitialized warnings on incomplete commands Eric Wong
2020-06-10  7:04 ` [PATCH 51/82] imap: start parsing out queries for SQLite and Xapian Eric Wong
2020-06-10  7:04 ` [PATCH 52/82] imap: SEARCH: clamp results to the 50K UID range Eric Wong
2020-06-10  7:04 ` [PATCH 53/82] imap: allow UID range search on timestamps Eric Wong
2020-06-10  7:04 ` [PATCH 54/82] over: get_art: use dbh->prepare_cached Eric Wong
2020-06-10  7:04 ` [PATCH 55/82] search: index byte size of a message for IMAP search Eric Wong
2020-06-10  7:04 ` [PATCH 56/82] search: index UID for IMAP search, too Eric Wong
2020-06-10  7:04 ` [PATCH 57/82] imap: remove dummies from sequence number FETCH Eric Wong
2020-06-10  7:04 ` [PATCH 58/82] imap: compile UID FETCH to opcodes Eric Wong
2020-06-10  7:04 ` [PATCH 59/82] imap: UID FETCH: optimize for smsg-only case Eric Wong
2020-06-10  7:04 ` [PATCH 60/82] imap: UID FETCH: optimize (UID FLAGS) harder Eric Wong
2020-06-10  7:04 ` [PATCH 61/82] imap: IDLE: avoid extraneous wakeups, keep-alive Eric Wong
2020-06-10  7:04 ` [PATCH 62/82] imap: 30 minute auto-logout timer Eric Wong
2020-06-10  7:05 ` [PATCH 63/82] imap: split ->logged_in attribute into a separate class Eric Wong
2020-06-10  7:05 ` [PATCH 64/82] searchidx: v1 (re)-index uses git asynchronously Eric Wong
2020-06-10  7:05 ` [PATCH 65/82] index: account for CRLF conversion when storing bytes Eric Wong
2020-06-10  7:05 ` [PATCH 66/82] imap: rely on smsg->{bytes} for RFC822.SIZE Eric Wong
2020-06-10  7:05 ` [PATCH 67/82] imap: UID FETCH requires at least one data item Eric Wong
2020-06-10  7:05 ` [PATCH 68/82] imap: LIST shows "INBOX" in all caps Eric Wong
2020-06-10  7:05 ` [PATCH 69/82] imap: support 8000 octet lines Eric Wong
2020-06-10  7:05 ` [PATCH 70/82] imap: reinstate some message sequence number support Eric Wong
2020-06-10  7:05 ` [PATCH 71/82] imap: cleanup ->{uid_base} usage Eric Wong
2020-06-10  7:05 ` Eric Wong [this message]
2020-06-10  7:05 ` [PATCH 73/82] imap: further speed up HEADER.FIELDS FETCH requests Eric Wong
2020-06-10  7:05 ` [PATCH 74/82] imap: FETCH: try to make fake MSNs sequentially Eric Wong
2020-06-10  7:05 ` [PATCH 75/82] imap: STATUS/EXAMINE: rely on SQLite overview Eric Wong
2020-06-10  7:05 ` [PATCH 76/82] imap: UID SEARCH: support multiple ranges Eric Wong
2020-06-10  7:05 ` [PATCH 77/82] imap: wire up Xapian, MSN SEARCH and multi sequence-sets Eric Wong
2020-06-10  7:05 ` [PATCH 78/82] imap: misc cleanups and notes Eric Wong
2020-06-10  7:05 ` [PATCH 79/82] imapd: don't bother sorting LIST output Eric Wong
2020-06-10  7:05 ` [PATCH 80/82] imap: remove non-UID SEARCH for now Eric Wong
2020-06-10  7:05 ` [PATCH 81/82] over: uid_range: remove LIMIT Eric Wong
2020-06-10  7:05 ` [PATCH 82/82] imap: FETCH: proper MSN => UID mapping for requests Eric Wong
2020-06-12 23:49 ` [PATCH 83/82] imap: introduce memory-efficient uo2m mapping Eric Wong

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

  List information: https://public-inbox.org/README

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20200610070519.18252-73-e@yhbt.net \
    --to=e@yhbt.net \
    --cc=meta@public-inbox.org \
    --subject='Re: [PATCH 72/82] imap: FETCH: more granular CRLF conversion' \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

Code repositories for project(s) associated with this inbox:

	https://80x24.org/public-inbox.git

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).