[RFC 0/3] search: more mairix compatibility changes

[RFC 0/3] search: more mairix compatibility changes

[Eric Wong]

1/3 and 2/3 should not be problematic, but 3/3 seems to be...

Eric Wong (3):
      search: allow searching user fields (To/Cc/From)
      search: drop longer subject: prefix for search
      search: more granular message body searching

[PATCH 1/3] search: allow searching user fields (To/Cc/From)

[Eric Wong]

Sometimes it can be useful to search based on who the
message was sent to, sent by, or Cc:-ed.  Of course,
headers can be faked, but they usually are not...

Anyways this mostly matches the behavior of mairix(1).
---
 lib/PublicInbox/Search.pm    | 10 +++++++-
 lib/PublicInbox/SearchIdx.pm | 59 +++++++++++++++++++++++++++++++-------------
 t/search.t                   | 37 +++++++++++++++++++++++++++
 3 files changed, 88 insertions(+), 18 deletions(-)

diff --git a/lib/PublicInbox/Search.pm b/lib/PublicInbox/Search.pm
index 445c2d8..aec459b 100644
--- a/lib/PublicInbox/Search.pm
+++ b/lib/PublicInbox/Search.pm
@@ -51,8 +51,8 @@ my %bool_pfx_internal = (
 	thread => 'G', # newsGroup (or similar entity - e.g. a web forum name)
 );
 
-# do we still need these? probably not..
 my %bool_pfx_external = (
+	# do we still need these? probably not..
 	path => 'XPATH',
 	mid => 'Q', # uniQue id (Message-ID)
 );
@@ -61,6 +61,14 @@ my %prob_prefix = (
 	subject => 'S',
 	s => 'S', # for mairix compatibility
 	m => 'Q', # 'mid' is exact, 'm' can do partial
+	f => 'A', # for mairix compatibility
+	t => 'XTO', # for mairix compatibility
+	tc => 'XTC', # for mairix compatibility
+	c => 'XCC', # for mairix compatibility
+	tcf => 'XTCF', # for mairix compatibility
+	# n.b.: leaving out "a:" alias for "tcf:" even though
+	# mairix supports it.  It is only mentioned in passing in mairix(1)
+	# and the extra two letters are not significantly longer.
 );
 
 # not documenting m: and mid: for now, the using the URLs works w/o Xapian
diff --git a/lib/PublicInbox/SearchIdx.pm b/lib/PublicInbox/SearchIdx.pm
index f54f5f2..37fefbe 100644
--- a/lib/PublicInbox/SearchIdx.pm
+++ b/lib/PublicInbox/SearchIdx.pm
@@ -96,12 +96,51 @@ sub _lock_release {
 	close $lockfh or die "close failed: $!\n";
 }
 
-sub add_val {
+sub add_val ($$$) {
 	my ($doc, $col, $num) = @_;
 	$num = Search::Xapian::sortable_serialise($num);
 	$doc->add_value($col, $num);
 }
 
+sub add_values ($$$) {
+	my ($smsg, $bytes, $num) = @_;
+
+	my $ts = $smsg->ts;
+	my $doc = $smsg->{doc};
+	add_val($doc, &PublicInbox::Search::TS, $ts);
+
+	defined($num) and add_val($doc, &PublicInbox::Search::NUM, $num);
+
+	defined($bytes) and add_val($doc, &PublicInbox::Search::BYTES, $bytes);
+
+	add_val($doc, &PublicInbox::Search::LINES,
+			$smsg->{mime}->body_raw =~ tr!\n!\n!);
+
+	my $yyyymmdd = strftime('%Y%m%d', gmtime($ts));
+	$doc->add_value(&PublicInbox::Search::YYYYMMDD, $yyyymmdd);
+}
+
+sub index_users ($$) {
+	my ($tg, $smsg) = @_;
+
+	my $from = $smsg->from;
+	my $to = $smsg->to;
+	my $cc = $smsg->cc;
+
+	$tg->index_text($from, 1, 'A'); # A - author
+	$tg->increase_termpos;
+
+	$tg->index_text($to, 1, 'XTO') if $to ne '';
+	$tg->index_text($cc, 1, 'XCC') if $cc ne '';
+	my $tc = join("\t", $to, $cc);
+	$tg->index_text($tc, 1, 'XTC') if $tc ne '';
+	my $tcf = join("\t", $tc, $from);
+	$tg->index_text($tcf, 1, 'XTCF') if $tcf ne '';
+
+	$tg->index_text($from);
+	$tg->increase_termpos;
+}
+
 sub add_message {
 	my ($self, $mime, $bytes, $num, $blob) = @_; # mime = Email::MIME object
 	my $db = $self->{xdb};
@@ -129,20 +168,7 @@ sub add_message {
 			$doc->add_term(xpfx('path') . id_compress($path));
 		}
 
-		my $ts = $smsg->ts;
-		add_val($doc, &PublicInbox::Search::TS, $ts);
-
-		defined($num) and
-			add_val($doc, &PublicInbox::Search::NUM, $num);
-
-		defined($bytes) and
-			add_val($doc, &PublicInbox::Search::BYTES, $bytes);
-
-		add_val($doc, &PublicInbox::Search::LINES,
-				$mime->body_raw =~ tr!\n!\n!);
-
-		my $yyyymmdd = strftime('%Y%m%d', gmtime($ts));
-		$doc->add_value(&PublicInbox::Search::YYYYMMDD, $yyyymmdd);
+		add_values($smsg, $bytes, $num);
 
 		my $tg = $self->term_generator;
 
@@ -152,8 +178,7 @@ sub add_message {
 		$tg->index_text($subj) if $subj;
 		$tg->increase_termpos;
 
-		$tg->index_text($smsg->from);
-		$tg->increase_termpos;
+		index_users($tg, $smsg);
 
 		msg_iter($mime, sub {
 			my ($part, $depth, @idx) = @{$_[0]};
diff --git a/t/search.t b/t/search.t
index db94c0a..bb0861a 100644
--- a/t/search.t
+++ b/t/search.t
@@ -86,6 +86,7 @@ my $rw_commit = sub {
 			'Message-ID' => '<last@s>',
 			From => 'John Smith <js@example.com>',
 			To => 'list@example.com',
+			Cc => 'foo@example.com',
 		],
 		body => "goodbye forever :<\n");
 
@@ -324,6 +325,42 @@ sub filter_mids {
 	is(scalar @{$res->{msgs}}, 0, 'nothing before 19931001');
 }
 
+# names and addresses
+{
+	my $res = $ro->query('t:list@example.com');
+	is(scalar @{$res->{msgs}}, 6, 'searched To: successfully');
+	foreach my $smsg (@{$res->{msgs}}) {
+		like($smsg->to, qr/\blist\@example\.com\b/, 'to appears');
+	}
+
+	$res = $ro->query('tc:list@example.com');
+	is(scalar @{$res->{msgs}}, 6, 'searched To+Cc: successfully');
+	foreach my $smsg (@{$res->{msgs}}) {
+		my $tocc = join("\n", $smsg->to, $smsg->cc);
+		like($tocc, qr/\blist\@example\.com\b/, 'tocc appears');
+	}
+
+	foreach my $pfx ('tcf:', 'c:') {
+		$res = $ro->query($pfx . 'foo@example.com');
+		is(scalar @{$res->{msgs}}, 1,
+			"searched $pfx successfully for Cc:");
+		foreach my $smsg (@{$res->{msgs}}) {
+			like($smsg->cc, qr/\bfoo\@example\.com\b/,
+				'cc appears');
+		}
+	}
+
+	foreach my $pfx ('', 'tcf:', 'f:') {
+		$res = $ro->query($pfx . 'Laggy');
+		is(scalar @{$res->{msgs}}, 1,
+			"searched $pfx successfully for From:");
+		foreach my $smsg (@{$res->{msgs}}) {
+			like($smsg->from, qr/Laggy Sender/,
+				"From appears with $pfx");
+		}
+	}
+}
+
 done_testing();
 
 1;
-- 
EW

[PATCH 2/3] search: drop longer subject: prefix for search

[Eric Wong]

We only document the "s:" anyways.  While the long name is more
descriptive, the ambiguity makes agnostic caching (by Varnish or
similar) slightly harder and longer URLs are more likely to be
accidentally truncated when shared.
---
 lib/PublicInbox/Search.pm |  1 -
 t/search.t                | 14 +++++++-------
 2 files changed, 7 insertions(+), 8 deletions(-)

diff --git a/lib/PublicInbox/Search.pm b/lib/PublicInbox/Search.pm
index aec459b..3b25b66 100644
--- a/lib/PublicInbox/Search.pm
+++ b/lib/PublicInbox/Search.pm
@@ -58,7 +58,6 @@ my %bool_pfx_external = (
 );
 
 my %prob_prefix = (
-	subject => 'S',
 	s => 'S', # for mairix compatibility
 	m => 'Q', # 'mid' is exact, 'm' can do partial
 	f => 'A', # for mairix compatibility
diff --git a/t/search.t b/t/search.t
index bb0861a..7abaf83 100644
--- a/t/search.t
+++ b/t/search.t
@@ -123,19 +123,19 @@ sub filter_mids {
 		is($res->{total}, 0, "path variant `$p' does not match");
 	}
 
-	$res = $ro->query('subject:(Hello world)');
+	$res = $ro->query('s:(Hello world)');
 	@res = filter_mids($res);
-	is_deeply(\@res, \@exp, 'got expected results for subject:() match');
+	is_deeply(\@res, \@exp, 'got expected results for s:() match');
 
-	$res = $ro->query('subject:"Hello world"');
+	$res = $ro->query('s:"Hello world"');
 	@res = filter_mids($res);
-	is_deeply(\@res, \@exp, 'got expected results for subject:"" match');
+	is_deeply(\@res, \@exp, 'got expected results for s:"" match');
 
-	$res = $ro->query('subject:"Hello world"', {limit => 1});
+	$res = $ro->query('s:"Hello world"', {limit => 1});
 	is(scalar @{$res->{msgs}}, 1, "limit works");
 	my $first = $res->{msgs}->[0];
 
-	$res = $ro->query('subject:"Hello world"', {offset => 1});
+	$res = $ro->query('s:"Hello world"', {offset => 1});
 	is(scalar @{$res->{msgs}}, 1, "offset works");
 	my $second = $res->{msgs}->[0];
 
@@ -181,7 +181,7 @@ sub filter_mids {
 	$rw_commit->();
 	$ro->reopen;
 
-	# Subject:
+	# subject
 	my $res = $ro->query('ghost');
 	my @exp = sort qw(ghost-message@s ghost-reply@s);
 	my @res = filter_mids($res);
-- 
EW

[PATCH 3/3] search: more granular message body searching

[Eric Wong]

"bs:" and "b:" are adapted from mairix(1)

We will also support searching explicitly for quoted vs
non-quoted text via "q:" and "nq:" prefixes since sometimes
readers will not care for quoted text.

In the future, we will support parsing diffs (perhaps when
repobrowse integration is complete).

Note: this roughly doubles the size of the Xapian database due
to the additional information; so this change may not be worth
it.
---
 lib/PublicInbox/Search.pm    | 18 ++++++++++++------
 lib/PublicInbox/SearchIdx.pm | 17 ++++++++++++++---
 t/search.t                   | 25 +++++++++++++++++++++++++
 3 files changed, 51 insertions(+), 9 deletions(-)

diff --git a/lib/PublicInbox/Search.pm b/lib/PublicInbox/Search.pm
index 3b25b66..f74129d 100644
--- a/lib/PublicInbox/Search.pm
+++ b/lib/PublicInbox/Search.pm
@@ -58,16 +58,22 @@ my %bool_pfx_external = (
 );
 
 my %prob_prefix = (
-	s => 'S', # for mairix compatibility
+	# for mairix compatibility
+	s => 'S',
 	m => 'Q', # 'mid' is exact, 'm' can do partial
-	f => 'A', # for mairix compatibility
-	t => 'XTO', # for mairix compatibility
-	tc => 'XTC', # for mairix compatibility
-	c => 'XCC', # for mairix compatibility
-	tcf => 'XTCF', # for mairix compatibility
+	f => 'A',
+	t => 'XTO',
+	tc => 'XTC',
+	c => 'XCC',
+	tcf => 'XTCF',
+	b => 'XBODY',
+	bs => 'XBS',
+
 	# n.b.: leaving out "a:" alias for "tcf:" even though
 	# mairix supports it.  It is only mentioned in passing in mairix(1)
 	# and the extra two letters are not significantly longer.
+	q => 'XQUOT',
+	nq => 'XNQ',
 );
 
 # not documenting m: and mid: for now, the using the URLs works w/o Xapian
diff --git a/lib/PublicInbox/SearchIdx.pm b/lib/PublicInbox/SearchIdx.pm
index 37fefbe..cd27a29 100644
--- a/lib/PublicInbox/SearchIdx.pm
+++ b/lib/PublicInbox/SearchIdx.pm
@@ -173,7 +173,10 @@ sub add_message {
 		my $tg = $self->term_generator;
 
 		$tg->set_document($doc);
-		$tg->index_text($subj, 1, 'S') if $subj;
+		if ($subj) {
+			$tg->index_text($subj, 1, 'S');
+			$tg->index_text($subj, 1, 'XBS');
+		}
 		$tg->increase_termpos;
 		$tg->index_text($subj) if $subj;
 		$tg->increase_termpos;
@@ -199,13 +202,21 @@ sub add_message {
 				}
 			}
 			if (@quot) {
-				$tg->index_text(join("\n", @quot), 0);
+				my $s = join("\n", @quot);
 				@quot = ();
+				$tg->index_text($s, 1, 'XQUOT');
+				$tg->index_text($s, 0, 'XBS');
+				$tg->index_text($s, 0, 'XBODY');
+				$tg->index_text($s, 0);
 				$tg->increase_termpos;
 			}
 			if (@orig) {
-				$tg->index_text(join("\n", @orig));
+				my $s = join("\n", @orig);
 				@orig = ();
+				$tg->index_text($s, 1, 'XNQ');
+				$tg->index_text($s, 1, 'XBS');
+				$tg->index_text($s, 1, 'XBODY');
+				$tg->index_text($s);
 				$tg->increase_termpos;
 			}
 		});
diff --git a/t/search.t b/t/search.t
index 7abaf83..bddb545 100644
--- a/t/search.t
+++ b/t/search.t
@@ -361,6 +361,31 @@ sub filter_mids {
 	}
 }
 
+{
+	$rw_commit->();
+	$ro->reopen;
+	my $res = $ro->query('b:hello');
+	is(scalar @{$res->{msgs}}, 0, 'no match on body search only');
+	$res = $ro->query('bs:smith');
+	is(scalar @{$res->{msgs}}, 0,
+		'no match on body+subject search for From');
+
+	$res = $ro->query('q:theatre');
+	is(scalar @{$res->{msgs}}, 1, 'only one quoted body');
+	like($res->{msgs}->[0]->from, qr/\AQuoter/, 'got quoted body');
+
+	$res = $ro->query('nq:theatre');
+	is(scalar @{$res->{msgs}}, 1, 'only one non-quoted body');
+	like($res->{msgs}->[0]->from, qr/\ANon-Quoter/, 'got non-quoted body');
+
+	foreach my $pfx (qw(b: bs:)) {
+		$res = $ro->query($pfx . 'theatre');
+		is(scalar @{$res->{msgs}}, 2, "searched both bodies for $pfx");
+		like($res->{msgs}->[0]->from, qr/\ANon-Quoter/,
+			"non-quoter first for $pfx");
+	}
+}
+
 done_testing();
 
 1;
-- 
EW