From a9c903a57ff9a18c56a53bcba4316eade423fef6 Mon Sep 17 00:00:00 2001 From: Eric Wong Date: Fri, 9 Sep 2016 00:01:24 +0000 Subject: search: more granular message body searching "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/SearchIdx.pm | 17 ++++++++++++++--- 1 file changed, 14 insertions(+), 3 deletions(-) (limited to 'lib/PublicInbox/SearchIdx.pm') diff --git a/lib/PublicInbox/SearchIdx.pm b/lib/PublicInbox/SearchIdx.pm index 37fefbea..cd27a294 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; } }); -- cgit v1.2.3-24-ge0c7