4e32052e618df259f0c0d77434641db7793e41d1
hiram
  Sun Nov 29 23:24:26 2020 -0800
correctly remove duplicate sequences from NCBI rm.out refs #24396

diff --git src/hg/utils/automation/doAssemblyHub.pl src/hg/utils/automation/doAssemblyHub.pl
index 6a1ed3d..14a9717 100755
--- src/hg/utils/automation/doAssemblyHub.pl
+++ src/hg/utils/automation/doAssemblyHub.pl
@@ -1126,30 +1126,34 @@
 	"\nERROR: step repeatmasker may be running\n");
        exit 255;
      }
   }
   &HgAutomate::mustMkdir($runDir);
 
   my $whatItDoes = "construct repeatMasker track data";
   my $bossScript = newBash HgRemoteScript("$runDir/doRepeatMasker.bash",
                     $workhorse, $runDir, $whatItDoes);
 
   my $rmskOpts = "";
   if ($ncbiRmsk) {
      if ( -s "$buildDir/download/${asmId}_rm.out.gz" ) {
        $rmskOpts = " \\
   -ncbiRmsk=\"$buildDir/download/${asmId}_rm.out.gz\" ";
+       if ( -s "${buildDir}/download/${asmId}.remove.dups.list" ) {
+         $rmskOpts .= " \\
+  -dupList=\"${buildDir}/download/${asmId}.remove.dups.list\" ";
+       }
        if ($ucscNames) {
          $rmskOpts .= " \\
   -liftSpec=\"$buildDir/sequence/$asmId.ncbiToUcsc.lift\"";
        }
      }
   }
 
   $bossScript->add(<<_EOF_
 export asmId=$asmId
 
 if [ $buildDir/\$asmId.2bit -nt faSize.rmsk.txt ]; then
 export species=`echo $rmskSpecies | sed -e 's/_/ /g;'`
 
 rm -f versionInfo.txt