Fix unicode encoding error with CSV parsing

Author: jonthornton

scripts/make_stations_csv.py

@@ -15,7 +15,7 @@ def main():
     transfers = {}
 
     # load stops into a dict
-    with open(args.stops_file, 'rb') as f:
+    with open(args.stops_file, 'r') as f:
         reader = csv.DictReader(f)
         for row in reader:
             if row['parent_station']:
@@ -28,7 +28,7 @@ def main():
                 }
 
     # load transfer groups into a dict. duplicates will be filtered out later
-    with open(args.transfers_file, 'rb') as f:
+    with open(args.transfers_file, 'r') as f:
         reader = csv.DictReader(f)
         for row in reader:
             if row['from_stop_id'] == row['to_stop_id']:

scripts/make_stations_json.py

@@ -11,7 +11,7 @@ def main():
     args = parser.parse_args()
 
     stations = {}
-    with open(args.stations_file, 'rb') as f:
+    with open(args.stations_file, 'r') as f:
         reader = csv.DictReader(f)
         for row in reader:
 
@@ -33,11 +33,11 @@ def main():
             sum(v[0] for v in station['stops'].values()) / float(len(station['stops'])),
             sum(v[1] for v in station['stops'].values()) / float(len(station['stops']))
         ]
-        station['id'] = md5(''.join(station['stops'].keys())).hexdigest()[:ID_LENGTH]
+        station['id'] = md5(''.join(station['stops'].keys()).encode('utf-8')).hexdigest()[:ID_LENGTH]
 
         while station['id'] in keyed_stations:
             # keep hashing til we get a unique ID
-            station['id'] = md5(station['id']).hexdigest()[:ID_LENGTH]
+            station['id'] = md5(station['id'].encode('utf-8')).hexdigest()[:ID_LENGTH]
 
         keyed_stations[station['id']] = station