X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FSearchIdx.pm;h=87ee0d46406ef688aa215356143923a82ddd9b14;hb=492910d43c179a7e1919b2d0f417aea9473f9730;hp=25452daec4280eae41a3d8f311c49bd2d5c0cbde;hpb=6ca633a1360a0974a8ebb117554a856022d797c6;p=public-inbox.git

diff --git a/lib/PublicInbox/SearchIdx.pm b/lib/PublicInbox/SearchIdx.pm
index 25452dae..87ee0d46 100644
--- 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;
@@ -117,7 +117,7 @@ sub add_values ($$$) {
 			$smsg->{mime}->body_raw =~ tr!\n!\n!);
 
 	my $yyyymmdd = strftime('%Y%m%d', gmtime($ts));
-	$doc->add_value(&PublicInbox::Search::YYYYMMDD, $yyyymmdd);
+	add_val($doc, PublicInbox::Search::YYYYMMDD, $yyyymmdd);
 }
 
 sub index_users ($$) {
@@ -135,13 +135,19 @@ sub index_users ($$) {
 	$tg->increase_termpos;
 }
 
+sub index_body ($$$) {
+	my ($tg, $lines, $inc) = @_;
+	$tg->index_text(join("\n", @$lines), $inc, $inc ? 'XNQ' : 'XQUOT');
+	@$lines = ();
+	$tg->increase_termpos;
+}
+
 sub add_message {
 	my ($self, $mime, $bytes, $num, $blob) = @_; # mime = Email::MIME object
 	my $db = $self->{xdb};
 
 	my ($doc_id, $old_tid);
 	my $mid = mid_clean(mid_mime($mime));
-	my $ct_msg = $mime->header('Content-Type') || 'text/plain';
 
 	eval {
 		die 'Message-ID too long' if length($mid) > MAX_MID_SIZE;
@@ -149,7 +155,7 @@ sub add_message {
 		if ($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);
@@ -174,34 +180,41 @@ sub add_message {
 
 		msg_iter($mime, sub {
 			my ($part, $depth, @idx) = @{$_[0]};
-			my $ct = $part->content_type || $ct_msg;
+			my $ct = $part->content_type || 'text/plain';
+			my $fn = $part->filename;
+			if (defined $fn && $fn ne '') {
+				$tg->index_text($fn, 1, 'XFN');
+			}
 
-			# account for filter bugs...
-			$ct =~ m!\btext/plain\b!i or return;
+			return if $ct =~ m!\btext/x?html\b!i;
+
+			my $s = eval { $part->body_str };
+			if ($@) {
+				if ($ct =~ m!\btext/plain\b!i) {
+					# Try to assume UTF-8 because Alpine
+					# seems to do wacky things and set
+					# charset=X-UNKNOWN
+					$part->charset_set('UTF-8');
+					$s = eval { $part->body_str };
+					$s = $part->body if $@;
+				}
+			}
+			defined $s or return;
 
 			my (@orig, @quot);
 			my $body = $part->body;
-			$part->body_set('');
 			my @lines = split(/\n/, $body);
 			while (defined(my $l = shift @lines)) {
 				if ($l =~ /^>/) {
+					index_body($tg, \@orig, 1) if @orig;
 					push @quot, $l;
 				} else {
+					index_body($tg, \@quot, 0) if @quot;
 					push @orig, $l;
 				}
 			}
-			if (@quot) {
-				my $s = join("\n", @quot);
-				@quot = ();
-				$tg->index_text($s, 0, 'XQUOT');
-				$tg->increase_termpos;
-			}
-			if (@orig) {
-				my $s = join("\n", @orig);
-				@orig = ();
-				$tg->index_text($s, 1, 'XNQ');
-				$tg->increase_termpos;
-			}
+			index_body($tg, \@quot, 0) if @quot;
+			index_body($tg, \@orig, 1) if @orig;
 		});
 
 		link_message($self, $smsg, $old_tid);
@@ -276,14 +289,14 @@ sub link_message {
 	my ($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;
@@ -292,6 +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) {
@@ -302,6 +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).'>';