bug fix on json load

load_corpus.py

@@ -11,7 +11,7 @@
     parser = argparse.ArgumentParser()
     parser.add_argument('-s', nargs='+', help="paths to files", required=True)
     parser.add_argument('-o', action='store', help="optional base name of output files", type=str, default=False)
-    parser.add_argument('-f', action="store", help="optional list of features in json", default=False)
+    parser.add_argument('-f', action="store", help="optional list of features, either in json (generated by Superstyl) or simple txt (one word per line)", default=False)
     parser.add_argument('-t', action='store', help="types of features (words, chars, affixes - "
                                                    "as per Sapkota et al. 2015 - or pos). pos are currently"
                                                    "only implemented for Modern English", type=str,
@@ -57,9 +57,18 @@
     args = parser.parse_args()
 
     if args.f:
-        print(".......loading preexisting feature list.......")
         with open(args.f, 'r') as f:
-            my_feats = json.loads(f.read())
+            if args.f.split(".")[-1] == "json":
+                print(".......loading preexisting feature list from json.......")
+                my_feats = json.loads(f.read())
+
+            elif args.f.split(".")[-1] == "txt":
+                print(".......loading preexisting feature list from txt.......")
+                my_feats = [[feat.rstrip(), 0] for feat in f.readlines()]
+
+            else:
+                print(".......unknown feature list format. Ignoring.......")
+                my_feats = None
 
     else:
         my_feats = None