www: implement generic help text

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

diff --git a/lib/PublicInbox/Search.pm b/lib/PublicInbox/Search.pm
index 856c8c144c8ea1afcb4d0cae2a736ffad4e955ef..445c2d8a403f4b3a314954852d7afd3819de565f 100644 (file)
--- a/lib/PublicInbox/Search.pm
+++ b/lib/PublicInbox/Search.pm
@@ -12,6 +12,7 @@ use constant TS => 0; # timestamp
 use constant NUM => 1; # NNTP article number
 use constant BYTES => 2; # :bytes as defined in RFC 3977
 use constant LINES => 3; # :lines as defined in RFC 3977
+use constant YYYYMMDD => 4; # for searching in the WWW UI
 
 use Search::Xapian qw/:standard/;
 use PublicInbox::SearchMsg;
@@ -36,7 +37,8 @@ use constant {
        # 8 - remove redundant/unneeded document data
        # 9 - disable Message-ID compression (SHA-1)
        # 10 - optimize doc for NNTP overviews
-       SCHEMA_VERSION => 10,
+       # 11 - merge threads when vivifying ghosts
+       SCHEMA_VERSION => 11,
 
        # n.b. FLAG_PURE_NOT is expensive not suitable for a public website
        # as it could become a denial-of-service vector
@@ -49,6 +51,7 @@ 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 = (
        path => 'XPATH',
        mid => 'Q', # uniQue id (Message-ID)
@@ -60,6 +63,29 @@ my %prob_prefix = (
        m => 'Q', # 'mid' is exact, 'm' can do partial
 );
 
+# 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
+       'd:' => <<EOF,
+date range as YYYYMMDD  e.g. d:19931002..20101002
+Open-ended ranges such as d:19931002.. and d:..20101002
+are also supported.
+EOF
+);
+# 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:
+# df (filenames from diff)
+# nq (non-quoted body)
+# da (diff a/ removed lines)
+# db (diff b/ added lines)
+
 my %all_pfx = (%bool_pfx_internal, %bool_pfx_external, %prob_prefix);
 
 sub xpfx { $all_pfx{$_[0]} }
@@ -78,10 +104,10 @@ sub xdir {
 }
 
 sub new {
-       my ($class, $git_dir) = @_;
+       my ($class, $git_dir, $altid) = @_;
        my $dir = $class->xdir($git_dir);
        my $db = Search::Xapian::Database->new($dir);
-       bless { xdb => $db, git_dir => $git_dir }, $class;
+       bless { xdb => $db, git_dir => $git_dir, altid => $altid }, $class;
 }
 
 sub reopen { $_[0]->{xdb}->reopen }
@@ -106,12 +132,15 @@ sub get_thread {
 
        return { total => 0, msgs => [] } unless $smsg;
        my $qtid = Search::Xapian::Query->new(xpfx('thread').$smsg->thread_id);
-       my $path = id_compress($smsg->path);
-       my $qsub = Search::Xapian::Query->new(xpfx('path').$path);
-       my $query = Search::Xapian::Query->new(OP_OR, $qtid, $qsub);
+       my $path = $smsg->path;
+       if (defined $path && $path ne '') {
+               my $path = id_compress($smsg->path);
+               my $qsub = Search::Xapian::Query->new(xpfx('path').$path);
+               $qtid = Search::Xapian::Query->new(OP_OR, $qtid, $qsub);
+       }
        $opts ||= {};
        $opts->{limit} ||= 1000;
-       _do_enquire($self, $query, $opts);
+       _do_enquire($self, $qtid, $opts);
 }
 
 sub _do_enquire {
@@ -175,13 +204,29 @@ sub qp {
        $qp->set_database($self->{xdb});
        $qp->set_stemmer($self->stemmer);
        $qp->set_stemming_strategy(STEM_SOME);
-       $qp->add_valuerangeprocessor($self->ts_range_processor);
-       $qp->add_valuerangeprocessor($self->date_range_processor);
+       $qp->add_valuerangeprocessor(
+               Search::Xapian::StringValueRangeProcessor->new(YYYYMMDD, 'd:'));
 
        while (my ($name, $prefix) = each %bool_pfx_external) {
                $qp->add_boolean_prefix($name, $prefix);
        }
 
+       # we do not actually create AltId objects,
+       # just parse the spec to avoid the extra DB handles for now.
+       if (my $altid = $self->{altid}) {
+               my $user_pfx = $self->{-user_pfx} ||= [];
+               for (@$altid) {
+                       # $_ = 'serial:gmane:/path/to/gmane.msgmap.sqlite3'
+                       /\Aserial:(\w+):/ or next;
+                       my $pfx = $1;
+                       push @$user_pfx, "$pfx:", <<EOF;
+alternate serial number  e.g. $pfx:12345
+EOF
+                       # gmane => XGMANE
+                       $qp->add_boolean_prefix($pfx, 'X'.uc($pfx));
+               }
+       }
+
        while (my ($name, $prefix) = each %prob_prefix) {
                $qp->add_prefix($name, $prefix);
        }
@@ -189,14 +234,6 @@ sub qp {
        $self->{query_parser} = $qp;
 }
 
-sub ts_range_processor {
-       $_[0]->{tsrp} ||= Search::Xapian::NumberValueRangeProcessor->new(TS);
-}
-
-sub date_range_processor {
-       $_[0]->{drp} ||= Search::Xapian::DateValueRangeProcessor->new(TS);
-}
-
 sub num_range_processor {
        $_[0]->{nrp} ||= Search::Xapian::NumberValueRangeProcessor->new(NUM);
 }
@@ -227,6 +264,12 @@ sub lookup_message {
        $smsg;
 }
 
+sub lookup_mail { # no ghosts!
+       my ($self, $mid) = @_;
+       my $smsg = lookup_message($self, $mid) or return;
+       PublicInbox::SearchMsg->load_doc($smsg->{doc});
+}
+
 sub find_unique_doc_id {
        my ($self, $term, $value) = @_;
 
@@ -306,4 +349,14 @@ sub enquire {
        $self->{enquire} ||= Search::Xapian::Enquire->new($self->{xdb});
 }
 
+sub help {
+       my ($self) = @_;
+       $self->qp; # parse altids
+       my @ret = @HELP;
+       if (my $user_pfx = $self->{-user_pfx}) {
+               push @ret, @$user_pfx;
+       }
+       \@ret;
+}
+
 1;