9217651e6774e9963587e76f203bac2df8b7a81e
hiram
  Thu Apr 28 15:21:10 2016 -0700
ready to use with doIdKeys.pl automation script refs #17168

diff --git src/utils/twoBitDup/twoBitDup.c src/utils/twoBitDup/twoBitDup.c
index 973201c..858cfa2 100644
--- src/utils/twoBitDup/twoBitDup.c
+++ src/utils/twoBitDup/twoBitDup.c
@@ -10,32 +10,37 @@
 #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"
+  "  -keyList=file - file to write a key list, two columns: md5sum and sequenceName\n"
+  "                   NOTE: use of keyList is very time expensive for 2bit files\n"
+  "                   with a large number of sequences (> 5,000).  Better to\n"
+  "                   use a cluster run with the doIdKeys.pl automation script.\n"
   "  -udcDir=/dir/to/cache - place to put cache for remote bigBed/bigWigs\n"
+  "\nexample: twoBitDup -keyList=stdout db.2bit \\\n"
+  "          | grep -v 'are identical' | sort > db.idKeys.txt"
   );
 }
 
 static char *keyList = NULL;
 
 static struct optionSpec options[] = {
    {"keyList", OPTION_STRING},
    {"udcDir", OPTION_STRING},
    {NULL, 0},
 };
 
 void twoBitDup(char *filename)
 /* twoBitDup - check to see if a twobit file has any identical sequences in it. */
 {
 struct twoBitFile *tbf;