wwwstream: improve documentation and variable naming

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

diff --git a/lib/PublicInbox/Search.pm b/lib/PublicInbox/Search.pm
index 445c2d8a403f4b3a314954852d7afd3819de565f..8da30c19c9d87661e4f4a0b7f8435f1d69d59c81 100644 (file)
--- 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
@@ -51,38 +52,55 @@ 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)
 );
 
 my %prob_prefix = (
-       subject => 'S',
-       s => 'S', # for mairix compatibility
-       m => 'Q', # 'mid' is exact, 'm' can do partial
+       # for mairix compatibility
+       s => 'S',
+       m => 'XMID', # 'mid:' (bool) is exact, 'm:' (prob) can do partial
+       f => 'A',
+       t => 'XTO',
+       tc => 'XTO XCC',
+       c => 'XCC',
+       tcf => 'XTO XCC A',
+       a => 'XTO XCC A',
+       b => 'XNQ XQUOT',
+       bs => 'XNQ XQUOT S',
+       n => 'XFN',
+
+       q => 'XQUOT',
+       nq => 'XNQ',
+
+       # default:
+       '' => 'XMID S A XNQ XQUOT XFN',
 );
 
 # 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)
 
@@ -205,7 +223,7 @@ 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);
@@ -220,15 +238,16 @@ 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) {
-               $qp->add_prefix($name, $prefix);
+               $qp->add_prefix($name, $_) foreach split(/ /, $prefix);
        }
 
        $self->{query_parser} = $qp;