src/hg/encode/encodeValidate/doEncodeValidate.pl 1.145

1.145 2009/02/13 11:57:04 mikep
allowing gene name to comprise any char but <tab>
Index: src/hg/encode/encodeValidate/doEncodeValidate.pl
===================================================================
RCS file: /projects/compbio/cvsroot/kent/src/hg/encode/encodeValidate/doEncodeValidate.pl,v
retrieving revision 1.144
retrieving revision 1.145
diff -b -B -U 4 -r1.144 -r1.145
--- src/hg/encode/encodeValidate/doEncodeValidate.pl	13 Feb 2009 11:13:23 -0000	1.144
+++ src/hg/encode/encodeValidate/doEncodeValidate.pl	13 Feb 2009 11:57:04 -0000	1.145
@@ -886,9 +886,10 @@
     return ();
 }
 
 sub validateRpkm
-# Wold lab format, has name and 2 floats 
+# Wold lab format, has gene name and 2 floats 
+#   Allowing Gene name to be composed of any characters but <tab>
 # Example lines:-
 #HBG2    0.583   1973.85
 #RPS20   0.523   1910.01
 #RPLP0   1.312   1800.51
@@ -900,9 +901,9 @@
     while(<$fh>) {
         chomp;
         $lineNumber++;
         die "Failed $type validation, file '$file'; line $lineNumber: line=[$_]\n"
-            unless m/^(\w+)\t(\d+\.\d+)\t(\d+\.\d+)$/;
+            unless m/^([^\t]+)\t(\d+\.\d+)\t(\d+\.\d+)$/;
         last if($opt_quick && $lineNumber >= $quickCount);
     }
     $fh->close();
     HgAutomate::verbose(2, "File \'$file\' passed $type validation\n");