* [PATCH 01/10] search: allow searching user fields (To/Cc/From)
2016-09-09 0:01 [PATCH 0/10] search: more mairix prefix compatibility Eric Wong
@ 2016-09-09 0:01 ` Eric Wong
2016-09-09 0:01 ` [PATCH 02/10] search: drop longer subject: prefix for search Eric Wong
` (8 subsequent siblings)
9 siblings, 0 replies; 11+ messages in thread
From: Eric Wong @ 2016-09-09 0:01 UTC (permalink / raw)
To: meta
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
^ permalink raw reply related [flat|nested] 11+ messages in thread* [PATCH 02/10] search: drop longer subject: prefix for search
2016-09-09 0:01 [PATCH 0/10] search: more mairix prefix compatibility Eric Wong
2016-09-09 0:01 ` [PATCH 01/10] search: allow searching user fields (To/Cc/From) Eric Wong
@ 2016-09-09 0:01 ` Eric Wong
2016-09-09 0:01 ` [PATCH 03/10] search: more granular message body searching Eric Wong
` (7 subsequent siblings)
9 siblings, 0 replies; 11+ messages in thread
From: Eric Wong @ 2016-09-09 0:01 UTC (permalink / raw)
To: meta
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
^ permalink raw reply related [flat|nested] 11+ messages in thread* [PATCH 03/10] search: more granular message body searching
2016-09-09 0:01 [PATCH 0/10] search: more mairix prefix compatibility Eric Wong
2016-09-09 0:01 ` [PATCH 01/10] search: allow searching user fields (To/Cc/From) Eric Wong
2016-09-09 0:01 ` [PATCH 02/10] search: drop longer subject: prefix for search Eric Wong
@ 2016-09-09 0:01 ` Eric Wong
2016-09-09 0:01 ` [PATCH 04/10] search: fix space regressions from recent changes Eric Wong
` (6 subsequent siblings)
9 siblings, 0 replies; 11+ messages in thread
From: Eric Wong @ 2016-09-09 0:01 UTC (permalink / raw)
To: meta
"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
^ permalink raw reply related [flat|nested] 11+ messages in thread* [PATCH 04/10] search: fix space regressions from recent changes
2016-09-09 0:01 [PATCH 0/10] search: more mairix prefix compatibility Eric Wong
` (2 preceding siblings ...)
2016-09-09 0:01 ` [PATCH 03/10] search: more granular message body searching Eric Wong
@ 2016-09-09 0:01 ` Eric Wong
2016-09-09 0:01 ` [PATCH 05/10] search: match quote detection behavior of view Eric Wong
` (5 subsequent siblings)
9 siblings, 0 replies; 11+ messages in thread
From: Eric Wong @ 2016-09-09 0:01 UTC (permalink / raw)
To: meta
As of Xapian 1.0.4 (from 2007) is possible to use
Search::Xapian::QueryParser::add_prefix multiple times with the
same user field name but different term prefixes.
This brings my current git@vger mirror from 6.5GB to 2.1GB
(both sizes are after xapian-compact).
---
lib/PublicInbox/Search.pm | 15 +++++++++------
lib/PublicInbox/SearchIdx.pm | 25 ++++---------------------
2 files changed, 13 insertions(+), 27 deletions(-)
diff --git a/lib/PublicInbox/Search.pm b/lib/PublicInbox/Search.pm
index f74129d..c8e297f 100644
--- a/lib/PublicInbox/Search.pm
+++ b/lib/PublicInbox/Search.pm
@@ -60,20 +60,23 @@ my %bool_pfx_external = (
my %prob_prefix = (
# for mairix compatibility
s => 'S',
- m => 'Q', # 'mid' is exact, 'm' can do partial
+ m => 'XMID', # 'mid:' (bool) is exact, 'm:' (prob) can do partial
f => 'A',
t => 'XTO',
- tc => 'XTC',
+ tc => 'XTO XCC',
c => 'XCC',
- tcf => 'XTCF',
- b => 'XBODY',
- bs => 'XBS',
+ tcf => 'XTO XCC A',
+ b => 'XNQ XQUOT',
+ bs => 'XNQ XQUOT S',
# 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',
+
+ # default:
+ '' => 'XMID S A XNQ XQUOT',
);
# not documenting m: and mid: for now, the using the URLs works w/o Xapian
@@ -241,7 +244,7 @@ EOF
}
while (my ($name, $prefix) = each %prob_prefix) {
- $qp->add_prefix($name, $prefix);
+ $qp->add_prefix($name, $_) foreach split(/ /, $prefix);
}
$self->{query_parser} = $qp;
diff --git a/lib/PublicInbox/SearchIdx.pm b/lib/PublicInbox/SearchIdx.pm
index cd27a29..ae89060 100644
--- a/lib/PublicInbox/SearchIdx.pm
+++ b/lib/PublicInbox/SearchIdx.pm
@@ -129,15 +129,9 @@ sub index_users ($$) {
$tg->index_text($from, 1, 'A'); # A - author
$tg->increase_termpos;
-
$tg->index_text($to, 1, 'XTO') if $to ne '';
+ $tg->increase_termpos;
$tg->index_text($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;
}
@@ -173,12 +167,7 @@ sub add_message {
my $tg = $self->term_generator;
$tg->set_document($doc);
- if ($subj) {
- $tg->index_text($subj, 1, 'S');
- $tg->index_text($subj, 1, 'XBS');
- }
- $tg->increase_termpos;
- $tg->index_text($subj) if $subj;
+ $tg->index_text($subj, 1, 'S') if $subj;
$tg->increase_termpos;
index_users($tg, $smsg);
@@ -204,25 +193,19 @@ sub add_message {
if (@quot) {
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);
+ $tg->index_text($s, 0, 'XQUOT');
$tg->increase_termpos;
}
if (@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);
$tg->increase_termpos;
}
});
link_message($self, $smsg, $old_tid);
- $tg->index_text($mid, 1);
+ $tg->index_text($mid, 1, 'XMID');
$doc->set_data($smsg->to_doc_data($blob));
if (my $altid = $self->{-altid}) {
--
EW
^ permalink raw reply related [flat|nested] 11+ messages in thread* [PATCH 05/10] search: match quote detection behavior of view
2016-09-09 0:01 [PATCH 0/10] search: more mairix prefix compatibility Eric Wong
` (3 preceding siblings ...)
2016-09-09 0:01 ` [PATCH 04/10] search: fix space regressions from recent changes Eric Wong
@ 2016-09-09 0:01 ` Eric Wong
2016-09-09 0:01 ` [PATCH 06/10] search: increase term positions for each quoted hunk Eric Wong
` (4 subsequent siblings)
9 siblings, 0 replies; 11+ messages in thread
From: Eric Wong @ 2016-09-09 0:01 UTC (permalink / raw)
To: meta
This is stricter than the mutt quote_regexp default
("^([ \t]*[|>:}#])+" on Debian jessie),
but matches what we have in View.pm.
I prefer the stricter quote detection since it is less ambiguous
and less likely to hide/obscure important details.
---
lib/PublicInbox/SearchIdx.pm | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/lib/PublicInbox/SearchIdx.pm b/lib/PublicInbox/SearchIdx.pm
index ae89060..25452da 100644
--- a/lib/PublicInbox/SearchIdx.pm
+++ b/lib/PublicInbox/SearchIdx.pm
@@ -184,7 +184,7 @@ sub add_message {
$part->body_set('');
my @lines = split(/\n/, $body);
while (defined(my $l = shift @lines)) {
- if ($l =~ /^\s*>/) {
+ if ($l =~ /^>/) {
push @quot, $l;
} else {
push @orig, $l;
--
EW
^ permalink raw reply related [flat|nested] 11+ messages in thread* [PATCH 06/10] search: increase term positions for each quoted hunk
2016-09-09 0:01 [PATCH 0/10] search: more mairix prefix compatibility Eric Wong
` (4 preceding siblings ...)
2016-09-09 0:01 ` [PATCH 05/10] search: match quote detection behavior of view Eric Wong
@ 2016-09-09 0:01 ` Eric Wong
2016-09-09 0:01 ` [PATCH 07/10] search: fix compatibility with Debian wheezy Eric Wong
` (3 subsequent siblings)
9 siblings, 0 replies; 11+ messages in thread
From: Eric Wong @ 2016-09-09 0:01 UTC (permalink / raw)
To: meta
We pay a storage cost for storing positional information
in Xapian, make good use of it by attempting to preserve
it for (hopefully) better search results.
---
lib/PublicInbox/SearchIdx.pm | 23 +++++++++++------------
1 file changed, 11 insertions(+), 12 deletions(-)
diff --git a/lib/PublicInbox/SearchIdx.pm b/lib/PublicInbox/SearchIdx.pm
index 25452da..0e499ad 100644
--- a/lib/PublicInbox/SearchIdx.pm
+++ b/lib/PublicInbox/SearchIdx.pm
@@ -135,6 +135,13 @@ sub index_users ($$) {
$tg->increase_termpos;
}
+sub index_body ($$$) {
+ my ($tg, $lines, $inc) = @_;
+ $tg->index_text(join("\n", @$lines), $inc, $inc ? 'XNQ' : 'XQUOT');
+ @$lines = ();
+ $tg->increase_termpos;
+}
+
sub add_message {
my ($self, $mime, $bytes, $num, $blob) = @_; # mime = Email::MIME object
my $db = $self->{xdb};
@@ -185,23 +192,15 @@ sub add_message {
my @lines = split(/\n/, $body);
while (defined(my $l = shift @lines)) {
if ($l =~ /^>/) {
+ index_body($tg, \@orig, 1) if @orig;
push @quot, $l;
} else {
+ index_body($tg, \@quot, 0) if @quot;
push @orig, $l;
}
}
- if (@quot) {
- my $s = join("\n", @quot);
- @quot = ();
- $tg->index_text($s, 0, 'XQUOT');
- $tg->increase_termpos;
- }
- if (@orig) {
- my $s = join("\n", @orig);
- @orig = ();
- $tg->index_text($s, 1, 'XNQ');
- $tg->increase_termpos;
- }
+ index_body($tg, \@quot, 0) if @quot;
+ index_body($tg, \@orig, 1) if @orig;
});
link_message($self, $smsg, $old_tid);
--
EW
^ permalink raw reply related [flat|nested] 11+ messages in thread* [PATCH 07/10] search: fix compatibility with Debian wheezy
2016-09-09 0:01 [PATCH 0/10] search: more mairix prefix compatibility Eric Wong
` (5 preceding siblings ...)
2016-09-09 0:01 ` [PATCH 06/10] search: increase term positions for each quoted hunk Eric Wong
@ 2016-09-09 0:01 ` Eric Wong
2016-09-09 0:01 ` [PATCH 08/10] search: avoid mindlessly calling body_set Eric Wong
` (2 subsequent siblings)
9 siblings, 0 replies; 11+ messages in thread
From: Eric Wong @ 2016-09-09 0:01 UTC (permalink / raw)
To: meta
Specifying the "d:" field only worked for
NumberValueRangeProcessor in older versions of Xapian, such
as the one in Debian wheezy (libsearch-xapian-perl=1.2.10.0-1)
This slipped through since I rarely use wheezy, anymore, and
perhaps nobody else does, either. Perhaps wheezy support may be
dropped, soon.
Unfortunately, this requires a schema version bump.
---
lib/PublicInbox/Search.pm | 5 +++--
lib/PublicInbox/SearchIdx.pm | 2 +-
2 files changed, 4 insertions(+), 3 deletions(-)
diff --git a/lib/PublicInbox/Search.pm b/lib/PublicInbox/Search.pm
index c8e297f..ceee39a 100644
--- a/lib/PublicInbox/Search.pm
+++ b/lib/PublicInbox/Search.pm
@@ -38,7 +38,8 @@ use constant {
# 9 - disable Message-ID compression (SHA-1)
# 10 - optimize doc for NNTP overviews
# 11 - merge threads when vivifying ghosts
- SCHEMA_VERSION => 11,
+ # 12 - change YYYYMMDD value column to numeric
+ SCHEMA_VERSION => 12,
# n.b. FLAG_PURE_NOT is expensive not suitable for a public website
# as it could become a denial-of-service vector
@@ -221,7 +222,7 @@ sub qp {
$qp->set_stemmer($self->stemmer);
$qp->set_stemming_strategy(STEM_SOME);
$qp->add_valuerangeprocessor(
- Search::Xapian::StringValueRangeProcessor->new(YYYYMMDD, 'd:'));
+ Search::Xapian::NumberValueRangeProcessor->new(YYYYMMDD, 'd:'));
while (my ($name, $prefix) = each %bool_pfx_external) {
$qp->add_boolean_prefix($name, $prefix);
diff --git a/lib/PublicInbox/SearchIdx.pm b/lib/PublicInbox/SearchIdx.pm
index 0e499ad..86be9ed 100644
--- a/lib/PublicInbox/SearchIdx.pm
+++ b/lib/PublicInbox/SearchIdx.pm
@@ -117,7 +117,7 @@ sub add_values ($$$) {
$smsg->{mime}->body_raw =~ tr!\n!\n!);
my $yyyymmdd = strftime('%Y%m%d', gmtime($ts));
- $doc->add_value(&PublicInbox::Search::YYYYMMDD, $yyyymmdd);
+ add_val($doc, PublicInbox::Search::YYYYMMDD, $yyyymmdd);
}
sub index_users ($$) {
--
EW
^ permalink raw reply related [flat|nested] 11+ messages in thread* [PATCH 08/10] search: avoid mindlessly calling body_set
2016-09-09 0:01 [PATCH 0/10] search: more mairix prefix compatibility Eric Wong
` (6 preceding siblings ...)
2016-09-09 0:01 ` [PATCH 07/10] search: fix compatibility with Debian wheezy Eric Wong
@ 2016-09-09 0:01 ` Eric Wong
2016-09-09 0:01 ` [PATCH 09/10] search: match the behavior of WWW for indexing text Eric Wong
2016-09-09 0:01 ` [PATCH 10/10] search: index attachment filenames Eric Wong
9 siblings, 0 replies; 11+ messages in thread
From: Eric Wong @ 2016-09-09 0:01 UTC (permalink / raw)
To: meta
It's not worth entering a complex codepath in Email::MIME to
save some (probably immeasurable amount of) memory, here. We've
already stopped doing this in our WWW code a while back, too.
If we really cared enough about it, we'd prioritize work on a
streaming replacement for Email::MIME.
---
lib/PublicInbox/SearchIdx.pm | 1 -
1 file changed, 1 deletion(-)
diff --git a/lib/PublicInbox/SearchIdx.pm b/lib/PublicInbox/SearchIdx.pm
index 86be9ed..0e2d225 100644
--- a/lib/PublicInbox/SearchIdx.pm
+++ b/lib/PublicInbox/SearchIdx.pm
@@ -188,7 +188,6 @@ sub add_message {
my (@orig, @quot);
my $body = $part->body;
- $part->body_set('');
my @lines = split(/\n/, $body);
while (defined(my $l = shift @lines)) {
if ($l =~ /^>/) {
--
EW
^ permalink raw reply related [flat|nested] 11+ messages in thread* [PATCH 09/10] search: match the behavior of WWW for indexing text
2016-09-09 0:01 [PATCH 0/10] search: more mairix prefix compatibility Eric Wong
` (7 preceding siblings ...)
2016-09-09 0:01 ` [PATCH 08/10] search: avoid mindlessly calling body_set Eric Wong
@ 2016-09-09 0:01 ` Eric Wong
2016-09-09 0:01 ` [PATCH 10/10] search: index attachment filenames Eric Wong
9 siblings, 0 replies; 11+ messages in thread
From: Eric Wong @ 2016-09-09 0:01 UTC (permalink / raw)
To: meta
The basic rule is that if it is displayable via our WWW
interface, it should be indexable text for Xapian search.
---
lib/PublicInbox/SearchIdx.pm | 21 ++++++++++++++++-----
1 file changed, 16 insertions(+), 5 deletions(-)
diff --git a/lib/PublicInbox/SearchIdx.pm b/lib/PublicInbox/SearchIdx.pm
index 0e2d225..fb68f4b 100644
--- a/lib/PublicInbox/SearchIdx.pm
+++ b/lib/PublicInbox/SearchIdx.pm
@@ -148,7 +148,6 @@ sub add_message {
my ($doc_id, $old_tid);
my $mid = mid_clean(mid_mime($mime));
- my $ct_msg = $mime->header('Content-Type') || 'text/plain';
eval {
die 'Message-ID too long' if length($mid) > MAX_MID_SIZE;
@@ -181,10 +180,22 @@ sub add_message {
msg_iter($mime, sub {
my ($part, $depth, @idx) = @{$_[0]};
- my $ct = $part->content_type || $ct_msg;
-
- # account for filter bugs...
- $ct =~ m!\btext/plain\b!i or return;
+ my $ct = $part->content_type || 'text/plain';
+
+ return if $ct =~ m!\btext/x?html\b!i;
+
+ my $s = eval { $part->body_str };
+ if ($@) {
+ if ($ct =~ m!\btext/plain\b!i) {
+ # Try to assume UTF-8 because Alpine
+ # seems to do wacky things and set
+ # charset=X-UNKNOWN
+ $part->charset_set('UTF-8');
+ $s = eval { $part->body_str };
+ $s = $part->body if $@;
+ }
+ }
+ defined $s or return;
my (@orig, @quot);
my $body = $part->body;
--
EW
^ permalink raw reply related [flat|nested] 11+ messages in thread* [PATCH 10/10] search: index attachment filenames
2016-09-09 0:01 [PATCH 0/10] search: more mairix prefix compatibility Eric Wong
` (8 preceding siblings ...)
2016-09-09 0:01 ` [PATCH 09/10] search: match the behavior of WWW for indexing text Eric Wong
@ 2016-09-09 0:01 ` Eric Wong
9 siblings, 0 replies; 11+ messages in thread
From: Eric Wong @ 2016-09-09 0:01 UTC (permalink / raw)
To: meta
And while we're at it, ensure searching inside displayable
attachment bodies works.
---
lib/PublicInbox/Search.pm | 3 ++-
lib/PublicInbox/SearchIdx.pm | 4 ++++
t/search.t | 44 ++++++++++++++++++++++++++++++++++++++++++++
3 files changed, 50 insertions(+), 1 deletion(-)
diff --git a/lib/PublicInbox/Search.pm b/lib/PublicInbox/Search.pm
index ceee39a..0c05677 100644
--- a/lib/PublicInbox/Search.pm
+++ b/lib/PublicInbox/Search.pm
@@ -69,6 +69,7 @@ my %prob_prefix = (
tcf => 'XTO XCC A',
b => 'XNQ XQUOT',
bs => 'XNQ XQUOT S',
+ n => 'XFN',
# n.b.: leaving out "a:" alias for "tcf:" even though
# mairix supports it. It is only mentioned in passing in mairix(1)
@@ -77,7 +78,7 @@ my %prob_prefix = (
nq => 'XNQ',
# default:
- '' => 'XMID S A XNQ XQUOT',
+ '' => 'XMID S A XNQ XQUOT XFN',
);
# not documenting m: and mid: for now, the using the URLs works w/o Xapian
diff --git a/lib/PublicInbox/SearchIdx.pm b/lib/PublicInbox/SearchIdx.pm
index fb68f4b..23aef9f 100644
--- a/lib/PublicInbox/SearchIdx.pm
+++ b/lib/PublicInbox/SearchIdx.pm
@@ -181,6 +181,10 @@ sub add_message {
msg_iter($mime, sub {
my ($part, $depth, @idx) = @{$_[0]};
my $ct = $part->content_type || 'text/plain';
+ my $fn = $part->filename;
+ if (defined $fn && $fn ne '') {
+ $tg->index_text($fn, 1, 'XFN');
+ }
return if $ct =~ m!\btext/x?html\b!i;
diff --git a/t/search.t b/t/search.t
index bddb545..cce3b9e 100644
--- a/t/search.t
+++ b/t/search.t
@@ -386,6 +386,50 @@ sub filter_mids {
}
}
+{
+ my $part1 = Email::MIME->create(
+ attributes => {
+ content_type => 'text/plain',
+ disposition => 'attachment',
+ charset => 'US-ASCII',
+ encoding => 'quoted-printable',
+ filename => 'attached_fart.txt',
+ },
+ body_str => 'inside the attachment',
+ );
+ my $part2 = Email::MIME->create(
+ attributes => {
+ content_type => 'text/plain',
+ disposition => 'attachment',
+ charset => 'US-ASCII',
+ encoding => 'quoted-printable',
+ filename => 'part_deux.txt',
+ },
+ body_str => 'inside another',
+ );
+ my $amsg = Email::MIME->create(
+ header_str => [
+ Subject => 'see attachment',
+ 'Message-ID' => '<file@attached>',
+ From => 'John Smith <js@example.com>',
+ To => 'list@example.com',
+ ],
+ parts => [ $part1, $part2 ],
+ );
+ ok($rw->add_message($amsg), 'added attachment');
+ $rw_commit->();
+ $ro->reopen;
+ my $n = $ro->query('n:attached_fart.txt');
+ is(scalar @{$n->{msgs}}, 1, 'got result for n:');
+ my $res = $ro->query('part_deux.txt');
+ is(scalar @{$res->{msgs}}, 1, 'got result without n:');
+ is($n->{msgs}->[0]->mid, $res->{msgs}->[0]->mid,
+ 'same result with and without');
+ my $txt = $ro->query('"inside another"');
+ is($txt->{msgs}->[0]->mid, $res->{msgs}->[0]->mid,
+ 'search inside text attachments works');
+}
+
done_testing();
1;
--
EW
^ permalink raw reply related [flat|nested] 11+ messages in thread