dc0ff6b7cda41fce2d04b9cce778901be0c760bf
hiram
  Tue Sep 1 10:57:30 2020 -0700
add duplicate verification refs #26145

diff --git src/hg/makeDb/doc/assemblyEquivalence/update.2020-08-31.txt src/hg/makeDb/doc/assemblyEquivalence/update.2020-08-31.txt
index bd298f1..23eba08 100644
--- src/hg/makeDb/doc/assemblyEquivalence/update.2020-08-31.txt
+++ src/hg/makeDb/doc/assemblyEquivalence/update.2020-08-31.txt
@@ -149,25 +149,34 @@
 join hgFixed.asmEquivalent.tsv existing.2020-08-31.tsv | wc
       5100   66300  702561
 
 ### probably should *not* be losing any from before:
 join -v 2 hgFixed.asmEquivalent.tsv existing.2020-08-31.tsv | wc -l
       0
 
 # if not 0, investigate.  Sometimes a new assembly is now an
 # exact match to something where it was a near match before to
 # a previous assembly of that organism.
 
 ### there should be some new ones
 join -v 1 hgFixed.asmEquivalent.tsv existing.2020-08-31.tsv | wc
          20     140    1784
 
+### There should be no duplicate equivalents:
+cut -f1,2 hgFixed.asmEquivalent.tsv | sort | uniq -c | sort -rn | head
+      1 zonAlb1 Zonotrichia_albicollis.Zonotrichia_albicollis-1.0.1
+      1 zonAlb1 GCF_000385455.1_Zonotrichia_albicollis-1.0.1
+      1 zonAlb1 GCA_000385455.1_Zonotrichia_albicollis-1.0.1
+      1 xipMac1 GCA_000241075.1_Xiphophorus_maculatus-4.4.2
+      1 xenTro9 Xenopus_tropicalis.Xenopus_tropicalis_v9.1
+... etc ...
+
 #### To load up new table contents:
 hgLoadSqlTab hgFixed asmEquivalent ~/kent/src/hg/lib/asmEquivalent.sql \
    hgFixed.asmEquivalent.tsv
 
 hgsql -N -e 'select * from asmEquivalent;' hgFixed \
    | sort > updated.2020-08-31.tsv
 
 wc -l updated.2020-08-31.tsv existing.2020-08-31.tsv
   2344 updated.2020-08-31.tsv
   2320 existing.2020-08-31.tsv