diff find_in_reference.py @ 1:e83e0ce8fb68

Add option to reverse the search, find reference field in input field

--- a/find_in_reference.py	Wed Feb 05 08:12:47 2014 -0500
+++ b/find_in_reference.py	Wed Aug 13 15:01:33 2014 -0500
@@ -41,6 +41,7 @@
   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( '-R', '--reverse_find', dest='reverse_find', action="store_true", default=False, help='find the reference string in the input string' )
   parser.add_option( '-k', '--keep', dest='keep', action="store_true", default=False, help='' )
   parser.add_option( '-a', '--annotation_columns', dest='annotation_columns', default=None, help='If string is found, add these columns from reference' )
   parser.add_option( '-s', '--annotation_separator', dest='annotation_separator', default=';', help='separator character between annotations from different lines' )
@@ -108,12 +109,14 @@
       refFile = open(options.reference,'r')
       for tn,fline in enumerate(refFile):
         fields = fline.split('\t')
-        target_string =fields[refcol]
+        target_string = fields[refcol].rstrip('\r\n')
         if options.ignore_case:
           target_string = target_string.upper()
+        search = search_string if not options.reverse_find else target_string
+        target = target_string if not options.reverse_find else search_string
         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:
+          print >> sys.stderr, "in: %s %s %s" % (search,search in target,target)
+        if search in target:
           found = True
           if annotate:
             annotation = options.annotation_col_sep.join([fields[i] for i in annotation_columns])