searchmsg: favor direct hash access over accessor methods

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

diff --git a/lib/PublicInbox/SearchIdx.pm b/lib/PublicInbox/SearchIdx.pm
index fb68f4b12a66878dbe53108194fbea4396e6ce2c..87ee0d46406ef688aa215356143923a82ddd9b14 100644 (file)
--- a/lib/PublicInbox/SearchIdx.pm
+++ b/lib/PublicInbox/SearchIdx.pm
@@ -4,8 +4,8 @@
 #
 # Indexes mail with Xapian and our (SQLite-based) ::Msgmap for use
 # with the web and NNTP interfaces.  This index maintains thread
-# relationships for use by Mail::Thread.  This writes to the search
-# index.
+# relationships for use by PublicInbox::SearchThread.
+# This writes to the search index.
 package PublicInbox::SearchIdx;
 use strict;
 use warnings;
@@ -155,7 +155,7 @@ sub add_message {
                if ($smsg) {
                        # convert a ghost to a regular message
                        # it will also clobber any existing regular message
-                       $doc_id = $smsg->doc_id;
+                       $doc_id = $smsg->{doc_id};
                        $old_tid = $smsg->thread_id;
                }
                $smsg = PublicInbox::SearchMsg->new($mime);
@@ -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;
 
@@ -285,14 +289,14 @@ sub link_message {
        my ($self, $smsg, $old_tid) = @_;
        my $doc = $smsg->{doc};
        my $mid = $smsg->mid;
-       my $mime = $smsg->mime;
+       my $mime = $smsg->{mime};
        my $hdr = $mime->header_obj;
        my $refs = $hdr->header_raw('References');
        my @refs = $refs ? ($refs =~ /<([^>]+)>/g) : ();
-       if (my $irt = $hdr->header_raw('In-Reply-To')) {
-               # last References should be $irt
-               # we will de-dupe later
-               push @refs, mid_clean($irt);
+       my $irt = $hdr->header_raw('In-Reply-To');
+       if (defined $irt) {
+               $irt = mid_clean($irt);
+               $irt = undef if $mid eq $irt;
        }
 
        my $tid;
@@ -301,6 +305,15 @@ sub link_message {
                my @orig_refs = @refs;
                @refs = ();
 
+               if (defined $irt) {
+                       # to check MAX_MID_SIZE
+                       push @orig_refs, $irt;
+
+                       # below, we will ensure IRT (if specified)
+                       # is the last References
+                       $uniq{$irt} = 1;
+               }
+
                # prevent circular references via References: here:
                foreach my $ref (@orig_refs) {
                        if (length($ref) > MAX_MID_SIZE) {
@@ -311,6 +324,11 @@ sub link_message {
                        push @refs, $ref;
                }
        }
+
+       # last References should be IRT, but some mail clients do things
+       # out of order, so trust IRT over References iff IRT exists
+       push @refs, $irt if defined $irt;
+
        if (@refs) {
                $smsg->{references} = '<'.join('> <', @refs).'>';