2a7d8d36d651b483f7624b95c494086d5595ebf5
hiram
  Mon Apr 25 10:20:41 2016 -0700
hashVal is not unique for different strings, try using md5sum refs #17168

diff --git src/utils/twoBitDup/twoBitDup.c src/utils/twoBitDup/twoBitDup.c
index 200b0cf..973201c 100644
--- src/utils/twoBitDup/twoBitDup.c
+++ src/utils/twoBitDup/twoBitDup.c
@@ -1,27 +1,28 @@
 /* twoBitDup - check to see if a twobit file has any identical sequences in it. */
 
 /* Copyright (C) 2013 The Regents of the University of California 
  * See README in this or parent directory for licensing information. */
 #include "common.h"
 #include "linefile.h"
 #include "hash.h"
 #include "options.h"
 #include "twoBit.h"
 #include "dnaseq.h"
 #include "math.h"
 #include "udc.h"
+#include "md5.h"
 
 static char const rcsid[] = "$Id: newProg.c,v 1.30 2010/03/24 21:18:33 hiram Exp $";
 
 void usage()
 /* Explain usage and exit. */
 {
 errAbort(
   "twoBitDup - check to see if a twobit file has any identical sequences in it\n"
   "usage:\n"
   "   twoBitDup file.2bit\n"
   "options:\n"
   "   -keyList=file - file to write a key list, two columns: key and sequenceName\n"
   "   -udcDir=/dir/to/cache - place to put cache for remote bigBed/bigWigs\n"
   );
 }
@@ -52,32 +53,35 @@
     verbose(2, "writing key list to %s\n", keyList);
     keyListFile = mustOpen(keyList, "w");
     }
 
 for (index = tbf->indexList; index != NULL; index = index->next)
     {
     verbose(2,"grabbing seq %s\n", index->name);
     int size;
     struct dnaSeq *seq = twoBitReadSeqFragExt(tbf, index->name,
 	0, 0, FALSE, &size);
     struct hashEl *hel;
     if ((hel = hashLookup(seqHash, seq->dna)) != NULL)
 	printf("%s and %s are identical\n", index->name, (char *)hel->val);
     else
 	hel = hashAdd(seqHash, seq->dna, index->name);
-    if (keyListFile)
-       fprintf(keyListFile, "%x\t%s\n", hel->hashVal, index->name);
+    if (keyListFile) {
+       char *md5Sum = md5HexForString(seq->dna);
+       fprintf(keyListFile, "%s\t%s\n", md5Sum, index->name);
+       freeMem(md5Sum);
+    }
     freeDnaSeq(&seq);
     }
 }
 
 int main(int argc, char *argv[])
 /* Process command line. */
 {
 optionInit(&argc, argv, options);
 if (argc != 2)
     usage();
 keyList = optionVal("keyList", NULL);
 udcSetDefaultDir(optionVal("udcDir", udcDefaultDir()));
 twoBitDup(argv[1]);
 return 0;
 }