X-Git-Url: http://git.freeside.biz/gitweb/?p=freeside.git;a=blobdiff_plain;f=rt%2Fsbin%2Frt-fulltext-indexer.in;h=b84ca94994819977beab735aa220aff49c4d654b;hp=7e31cac84d3b5290c28996bd75de47a4abf4ead0;hb=e9e0cf0989259b94d9758eceff448666a2e5a5cc;hpb=85e677b86fc37c54e6de2b06340351a28f5a5916

diff --git a/rt/sbin/rt-fulltext-indexer.in b/rt/sbin/rt-fulltext-indexer.in
index 7e31cac84..b84ca9499 100644
--- a/rt/sbin/rt-fulltext-indexer.in
+++ b/rt/sbin/rt-fulltext-indexer.in
@@ -3,7 +3,7 @@
 #
 # COPYRIGHT:
 #
-# This software is Copyright (c) 1996-2012 Best Practical Solutions, LLC
+# This software is Copyright (c) 1996-2014 Best Practical Solutions, LLC
 #                                          <sales@bestpractical.com>
 #
 # (Except where explicitly superseded by other copyright notices)
@@ -217,6 +217,11 @@ sub attachments {
         VALUE => 'deleted'
     );
 
+    # On newer DBIx::SearchBuilder's, indicate that making the query DISTINCT
+    # is unnecessary because the joins won't produce duplicates.  This
+    # drastically improves performance when fetching attachments.
+    $res->{joins_are_distinct} = 1;
+
     return goto_specific(
         suffix => $type,
         error => "Don't know how to find $type attachments",
@@ -369,11 +374,18 @@ sub process_pg {
 
     my $status = eval { $dbh->do( $query, undef, $$text, $attachment->id ) };
     unless ( $status ) {
-        if ($dbh->errstr =~ /string is too long for tsvector/) {
-            warn "Attachment @{[$attachment->id]} not indexed, as it contains too many unique words to be indexed";
+        if ( $dbh->err == 7  && $dbh->state eq '54000' ) {
+            warn "Attachment @{[$attachment->id]} cannot be indexed. Most probably it contains too many unique words. Error: ". $dbh->errstr;
+        } elsif ( $dbh->err == 7 && $dbh->state eq '22021' ) {
+            warn "Attachment @{[$attachment->id]} cannot be indexed. Most probably it contains invalid UTF8 bytes. Error: ". $dbh->errstr;
         } else {
             die "error: ". $dbh->errstr;
         }
+
+        # Insert an empty tsvector, so we count this row as "indexed"
+        # for purposes of knowing where to pick up
+        eval { $dbh->do( $query, undef, "", $attachment->id ) }
+            or die "Failed to insert empty tsvector: " . $dbh->errstr;
     }
 }