searchmsg: favor direct hash access over accessor methods

[public-inbox.git] / lib / PublicInbox / Search.pm

diff --git a/lib/PublicInbox/Search.pm b/lib/PublicInbox/Search.pm
index 0c05677216f3e3e3887ffadfa18ff4d963e5e234..86354b571f88541fe2d271c92c220204a151bf97 100644 (file)
--- a/lib/PublicInbox/Search.pm
+++ b/lib/PublicInbox/Search.pm
@@ -67,13 +67,11 @@ my %prob_prefix = (
        tc => 'XTO XCC',
        c => 'XCC',
        tcf => 'XTO XCC A',
+       a => '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)
-       # and the extra two letters are not significantly longer.
        q => 'XQUOT',
        nq => 'XNQ',
 
@@ -83,24 +81,26 @@ my %prob_prefix = (
 
 # not documenting m: and mid: for now, the using the URLs works w/o Xapian
 our @HELP = (
-       's:' => <<EOF,
-match within Subject only  e.g. s:"a quick brown fox"
-This is a probabilistic search with support for stemming
-and wildcards '*'
-EOF
+       's:' => 'match within Subject  e.g. s:"a quick brown fox"',
        'd:' => <<EOF,
 date range as YYYYMMDD  e.g. d:19931002..20101002
 Open-ended ranges such as d:19931002.. and d:..20101002
-are also supported.
+are also supported
 EOF
+       'b:' => 'match within message body, including text attachments',
+       'nq:' => 'match non-quoted text within message body',
+       'quot:' => 'match quoted text within message body',
+       'n:' => 'match filename of attachment(s)',
+       't:' => 'match within the To header',
+       'c:' => 'match within the Cc header',
+       'f:' => 'match within the From header',
+       'a:' => 'match within the To, Cc, and From headers',
+       'tc:' => 'match within the To and Cc headers',
+       'bs:' => 'match within the Subject and body',
 );
-# TODO: (from mairix, some of these are maybe)
-# b (body), f (From:), c (Cc:), n (attachment), t (To:)
-# tc (To:+Cc:), bs (body + Subject), tcf (To: +Cc: +From:)
-#
-# Non-mairix:
+chomp @HELP;
+# TODO:
 # df (filenames from diff)
-# nq (non-quoted body)
 # da (diff a/ removed lines)
 # db (diff b/ added lines)
 
@@ -108,12 +108,6 @@ my %all_pfx = (%bool_pfx_internal, %bool_pfx_external, %prob_prefix);
 
 sub xpfx { $all_pfx{$_[0]} }
 
-our %PFX2TERM_RMAP;
-my %meta_pfx = (mid => 1, thread => 1, path => 1);
-while (my ($k, $v) = each %all_pfx) {
-       $PFX2TERM_RMAP{$v} = $k if $meta_pfx{$k};
-}
-
 my $mail_query = Search::Xapian::Query->new(xpfx('type') . 'mail');
 
 sub xdir {
@@ -158,25 +152,35 @@ sub get_thread {
        }
        $opts ||= {};
        $opts->{limit} ||= 1000;
+
+       # always sort threads by timestamp, this makes life easier
+       # for the threading algorithm (in SearchThread.pm)
+       $opts->{asc} = 1;
+
        _do_enquire($self, $qtid, $opts);
 }
 
-sub _do_enquire {
-       my ($self, $query, $opts) = @_;
+sub retry_reopen {
+       my ($self, $cb) = @_;
        my $ret;
        for (1..10) {
-               eval { $ret = _enquire_once($self, $query, $opts) };
+               eval { $ret = $cb->() };
                return $ret unless $@;
                # Exception: The revision being read has been discarded -
                # you should call Xapian::Database::reopen()
-               if (index($@, 'Xapian::Database::reopen') >= 0) {
+               if (ref($@) eq 'Search::Xapian::DatabaseModifiedError') {
                        reopen($self);
                } else {
-                       die $@;
+                       die;
                }
        }
 }
 
+sub _do_enquire {
+       my ($self, $query, $opts) = @_;
+       retry_reopen($self, sub { _enquire_once($self, $query, $opts) });
+}
+
 sub _enquire_once {
        my ($self, $query, $opts) = @_;
        my $enquire = $self->enquire;
@@ -238,11 +242,12 @@ sub qp {
                        /\Aserial:(\w+):/ or next;
                        my $pfx = $1;
                        push @$user_pfx, "$pfx:", <<EOF;
-alternate serial number  e.g. $pfx:12345
+alternate serial number  e.g. $pfx:12345 (boolean)
 EOF
                        # gmane => XGMANE
                        $qp->add_boolean_prefix($pfx, 'X'.uc($pfx));
                }
+               chomp @$user_pfx;
        }
 
        while (my ($name, $prefix) = each %prob_prefix) {
@@ -277,15 +282,17 @@ sub lookup_message {
                # raises on error:
                my $doc = $self->{xdb}->get_document($doc_id);
                $smsg = PublicInbox::SearchMsg->wrap($doc, $mid);
-               $smsg->doc_id($doc_id);
+               $smsg->{doc_id} = $doc_id;
        }
        $smsg;
 }
 
 sub lookup_mail { # no ghosts!
        my ($self, $mid) = @_;
-       my $smsg = lookup_message($self, $mid) or return;
-       PublicInbox::SearchMsg->load_doc($smsg->{doc});
+       retry_reopen($self, sub {
+               my $smsg = lookup_message($self, $mid) or return;
+               PublicInbox::SearchMsg->load_doc($smsg->{doc});
+       });
 }
 
 sub find_unique_doc_id {