diff find_in_reference.py @ 1:856033fb26e8

Add case insensitive option
author Jim Johnson <jj@umn.edu>
date Fri, 17 Jan 2014 14:50:53 -0600
parents fe0327a3ba81
children 30975b3ff0dc
line wrap: on
line diff
--- a/find_in_reference.py	Sat Jan 04 09:03:57 2014 -0500
+++ b/find_in_reference.py	Fri Jan 17 14:50:53 2014 -0600
@@ -40,6 +40,7 @@
   parser.add_option( '-f', '--filtered', dest='filtered', help='The output file for input lines not in the output')
   parser.add_option('-c','--input_column', dest='input_column', default=None, help='The column for the value in the input file. (first column = 1, default to last column)')
   parser.add_option('-C','--reference_column', dest='reference_column', default=None, help='The column for the value in the reference file. (first column = 1, default to last column)')
+  parser.add_option( '-I', '--case_insensitive', dest='ignore_case', action="store_true", default=False, help='case insensitive' )
   parser.add_option( '-k', '--keep', dest='keep', action="store_true", default=False, help='' )
   parser.add_option( '-d', '--debug', dest='debug', action='store_true', default=False, help='Turn on wrapper debugging to stdout'  )
   (options, args) = parser.parse_args()
@@ -89,11 +90,15 @@
     try:
       found = False
       search_string = line.split('\t')[incol].rstrip('\r\n')
+      if options.ignore_case:
+        search_string = search_string.upper()
       if options.debug: 
         print >> sys.stderr, "search: %s" % (search_string)
       refFile = open(options.reference,'r')
       for tn,fline in enumerate(refFile):
         target_string = fline.split('\t')[refcol]
+        if options.ignore_case:
+          target_string = target_string.upper()
         if options.debug: 
           print >> sys.stderr, "in: %s %s %s" % (search_string,search_string in target_string,target_string)
         if search_string in target_string: