7f0ad33bd004bc5616a9214534d74371f9f51940
angie
  Thu Sep 2 17:48:56 2021 -0700
Greatly increase tolerance for missing BioSample records.  I reported this to NCBI; sounds like that's just the way it is with importing delays.

diff --git src/hg/utils/otto/sarscov2phylo/gbMetadataAddBioSample.pl src/hg/utils/otto/sarscov2phylo/gbMetadataAddBioSample.pl
index 8e089c7..e2c7b35 100755
--- src/hg/utils/otto/sarscov2phylo/gbMetadataAddBioSample.pl
+++ src/hg/utils/otto/sarscov2phylo/gbMetadataAddBioSample.pl
@@ -69,27 +69,27 @@
       if (! $gbName) {
         $gbName = $bName;
       } elsif (($gbName eq '1' || $gbName eq 'NA') && length($bName) > length($gbName)) {
         $gbName = $bName;
       } elsif ($gbName eq 'nasopharyngeal' && $bName =~ m/\d/) {
         $gbName = $bName;
       }
       if (! $gbGeo) {
         $gbGeo = $bCountry;
       }
       print join("\t", $gbAcc, $bAcc, $gbDate, $gbGeo, $host, $gbName, $completeness, $len);
     } else {
       # BioSample file doesn't have info for this BioSample accession
       print STDERR "Missing BioSample info for $bAcc\n";
       $missingCount++;
-      if ($missingCount >= 1000) {
+      if ($missingCount >= 100000) {
         die "Too many missing BioSamples, quitting.\n";
       }
       # Pass through as-is
       print;
     }
   } else {
     # No associated BioSample, just pass through as-is
     print;
   }
 }