fix tests, format

.gitignore

@@ -1,2 +1,3 @@
 .DS_Store
 __pycache__
+.vscode

.style.yapf

@@ -0,0 +1,2 @@
+[style]
+based_on_style = google

README.md

@@ -6,15 +6,13 @@ This tool is based on the fares-v2 [draft specification](https://docs.google.com
 
 The tool validates ONLY fares-v2 specific files and dependent files, and does NOT validate GTFS schedule data.
 
-The tool does NOT read areas from stop_times.txt for performance reasons, but can using the -s option defined below.
-
 ## Requirements
 
 python 3
 
 ## Validate a fares dataset
 
-`python3 validate.py PATH-TO-FOLDER-CONTAINING-FARES-V2-DATASET [-s, --read-stop-times] [-o, --output-file FILE-TO-EXPORT-VALIDATION-REPORT-TO]`
+`python3 validate.py PATH-TO-FOLDER-CONTAINING-FARES-V2-DATASET [-o, --output-file FILE-TO-EXPORT-VALIDATION-REPORT-TO]`
 
 For example:
 

fares_validator/__main__.py

@@ -6,9 +6,18 @@
 
 def main():
     parser = argparse.ArgumentParser(description='Validate GTFS fares-v2 data.')
-    parser.add_argument("-s", "--read-stop-times", help="Scan stop_times for area_ids", action='store_true')
-    parser.add_argument("-o", "--output-file", type=str, help="Export the errors and warnings to a file")
-    parser.add_argument("input_gtfs_folder", type=str, help="Path to unzipped folder containing the Fares-v2 GTFS")
+    parser.add_argument("-s",
+                        "--read-stop-times",
+                        help="Scan stop_times for area_ids",
+                        action='store_true')
+    parser.add_argument("-o",
+                        "--output-file",
+                        type=str,
+                        help="Export the errors and warnings to a file")
+    parser.add_argument(
+        "input_gtfs_folder",
+        type=str,
+        help="Path to unzipped folder containing the Fares-v2 GTFS")
 
     args = parser.parse_args()
 
@@ -25,7 +34,9 @@ def main():
             f = open(args.output_file, 'w')
             f.write(output)
         except Exception:
-            raise Exception('Writing to output file failed. Please ensure the output file path is valid.')
+            raise Exception(
+                'Writing to output file failed. Please ensure the output file path is valid.'
+            )
     else:
         print(output)
 

fares_validator/diagnostics.py

@@ -13,6 +13,7 @@ def format(code, line_context='', path='', extra_info=''):
 
 
 class Diagnostics:
+
     def __init__(self):
         self.errors = []
         self.warnings = []

fares_validator/errors.py

@@ -1,9 +1,6 @@
 # generic errors (see utils.py)
 AMOUNT_WITH_MIN_OR_MAX_AMOUNT = 'An amount is defined alongside at least one of min_ or max_amount.'
 AMOUNT_WITHOUT_CURRENCY = 'An amount field is defined without a currency to accompany it.'
-CONFLICTING_FARE_CONTAINER_ON_FARE_PRODUCT = 'A fare_container referenced conflicts with the fare_container on the fare_product.'
-CONFLICTING_RIDER_CATEGORY_ON_FARE_CONTAINER = 'A rider_category referenced conflicts with the rider_category on the fare_container.'
-CONFLICTING_RIDER_CATEGORY_ON_FARE_PRODUCT = 'A rider_category referenced conflicts with the rider_category on the fare_product.'
 CURRENCY_WITHOUT_AMOUNT = 'A currency is defined without an amount field to accompany it.'
 FOREIGN_ID_INVALID = 'An id defined in a dependent table is referenced, but does not exist in that table.'
 INVALID_AMOUNT_FORMAT = 'An amount field is defined, but is not an integer or float.'
@@ -16,16 +13,13 @@
 UNRECOGNIZED_CURRENCY_CODE = 'A currency code is unrecognized.'
 
 # areas.txt
-DUPLICATE_AREAS_TXT_ENTRY = 'There are two entries in areas.txt with the same area_id and greater_area_id.'
+DUPLICATE_AREAS_TXT_ENTRY = 'There are two entries in areas.txt with the same area_id.'
 EMPTY_AREA_ID_AREAS = 'An entry in areas.txt has empty area_id.'
-GREATER_AREA_ID_LOOP = 'Some area_ids have themselves as greater_area_ids.'
-UNDEFINED_GREATER_AREA_ID = 'A greater_area_id is not defined as an area_id in areas.txt.'
 
 # stop_areas.txt
+DUPLICATE_STOP_AREAS_TXT_ENTRY = 'There are two entries in stop_areas.txt with the same area_id and stop_id.'
 EMPTY_AREA_ID_STOP_AREAS = 'An entry in stop_areas.txt has empty area_id.'
 EMPTY_STOP_ID_STOP_AREAS = 'An entry in stop_areas.txt has empty stop_id.'
-INVALID_AREA_ID = 'An entry in stop_areas.txt references a non-existent area_id.'
-INVALID_STOP_ID = 'An entry in stop_areas.txt references a non-existent stop_id.'
 
 # calendar.txt, calendar_dates.txt
 DUPLICATE_SERVICE_ID = 'A service_id is defined twice in calendar.txt.'
@@ -73,36 +67,23 @@
 TIMEFRAME_TYPE_WITHOUT_TIMEFRAME = 'A timeframe_type in fare_products.txt is defined without a timeframe_id.'
 
 # fare_leg_rules.txt
-AMOUNT_WITH_FARE_PRODUCT = 'An entry in fare_leg_rules.txt has both a fare_product and an amount field defined.'
-AREA_WITHOUT_IS_SYMMETRICAL = 'A from_ and/or to_area in fare_leg_rules.txt is defined without is_symmetrical.'
-CONTAINS_AREA_WITHOUT_FROM_TO_AREA = 'A contains_area in fare_leg_rules.txt is defined without a from and to area.'
 DISTANCE_TYPE_WITHOUT_DISTANCE = 'A distance_type in fare_leg_rules.txt is defined without a min_ or max_distance.'
 DISTANCE_WITHOUT_DISTANCE_TYPE = 'A min_ or max_distance in fare_leg_rules.txt is defined without a distance_type.'
 FARE_LEG_NAME_WITH_FARE_PRODUCT = 'An entry in fare_leg_rules.txt has both a fare_product and a fare_leg_name field defined.'
 INVALID_DISTANCE_TYPE = 'A distance_type in fare_leg_rules.txt has an invalid value.'
-INVALID_IS_SYMMETRICAL_LEG_RULES = 'An is_symmetrical in fare_leg_rules.txt is not one of the accepted values.'
 INVALID_MAX_DISTANCE = 'A max_distance in fare_leg_rules.txt is not a float.'
 INVALID_MIN_DISTANCE = 'A min_distance in fare_leg_rules.txt is not a float.'
-IS_SYMMETRICAL_WITHOUT_FROM_TO_AREA = 'An is_symmetrical in fare_leg_rules.txt is defined without a from_ and/or to_area.'
 NEGATIVE_MAX_DISTANCE = 'A max_distance in fare_leg_rules.txt is negative.'
 NEGATIVE_MIN_DISTANCE = 'A min_distance in fare_leg_rules.txt is negative.'
 
 # fare_transfer_rules.txt
-AMOUNT_WITHOUT_FARE_TRANSFER_TYPE = 'An entry in fare_transfer_rules.txt has an amount field defined without fare_transfer_type.'
 DURATION_LIMIT_WITHOUT_LIMIT_TYPE = 'An entry in fare_transfer_rules.txt has duration_limit without duration_limit_type.'
 DURATION_LIMIT_TYPE_WITHOUT_DURATION = 'An entry in fare_transfer_rules.txt has duration_limit_type without duration_limit.'
-FARE_TRANSFER_TYPE_WITHOUT_AMOUNT = 'An entry in fare_transfer_rules.txt has fare_transfer_type defined without an amount field.'
 INVALID_DURATION_LIMIT = 'An entry in fare_transfer_rules.txt has duration_limit with invalid value.'
 INVALID_DURATION_LIMIT_TYPE = 'An entry in fare_transfer_rules.txt has duration_limit_type with invalid value.'
 INVALID_FARE_TRANSFER_TYPE = 'An entry in fare_transfer_rules.txt has fare_transfer_type with invalid value.'
 INVALID_FROM_LEG_GROUP = 'A from_leg_group_id in fare_transfer_rules.txt is not defined in fare_leg_rules.txt.'
-INVALID_IS_SYMMETRICAL_TRANSFER_RULES = 'An is_symmetrical in fare_transfer_rules.txt is not one of the accepted values.'
-INVALID_SPANNING_LIMIT = 'An entry in fare_transfer_rules.txt has spanning_limit with incorrect type or invalid integer value.'
+INVALID_TRANSFER_COUNT = 'An entry in fare_transfer_rules.txt has transfer_count with incorrect type or invalid integer value.'
 INVALID_TO_LEG_GROUP = 'A to_leg_group_id in fare_transfer_rules.txt is not defined in fare_leg_rules.txt.'
-INVALID_TRANSFER_SEQUENCE = 'A transfer_sequence in fare_transfer_rules.txt has incorrect type or invalid integer value.'
-IS_SYMMETRICAL_WITHOUT_FROM_TO_LEG_GROUP = 'An is_symmetrical in fare_transfer_rules.txt is defined without a from_ and/or to_leg_group_id.'
-LEG_GROUP_WITHOUT_IS_SYMMETRICAL = 'A from_ and/or to_leg_group_id in fare_transfer_rules.txt is defined without is_symmetrical.'
-SPANNING_LIMIT_WITH_BAD_LEGS = 'An entry in fare_transfer_rules.txt has spanning_limit with different from and to leg group ids.'
-SPANNING_LIMIT_WITH_TRANSFER_ID = 'An entry in fare_transfer_rules.txt has spanning_limit with transfer_id defined.'
-TRANSFER_ID_WITHOUT_TRANSFER_SEQUENCE = 'A transfer_id in fare_transfer_rules.txt is defined without a transfer_sequence.'
-TRANSFER_SEQUENCE_WITHOUT_TRANSFER_ID = 'A transfer_sequence in fare_transfer_rules.txt is defined without a transfer_id.'
+NONEXISTENT_FILTER_FARE_PRODUCT_ID = 'A filter_fare_product referenced is not defined in fare_products.txt.'
+TRANSFER_COUNT_WITH_BAD_LEGS = 'An entry in fare_transfer_rules.txt has transfer_count with different from and to leg group ids.'

fares_validator/fare_leg_rule_checkers.py

@@ -3,26 +3,13 @@
 
 
 def check_areas(line, areas, unused_areas):
-    if line.is_symmetrical and line.is_symmetrical not in {'0', '1'}:
-        line.add_error(INVALID_IS_SYMMETRICAL_LEG_RULES)
-
-    if line.contains_area_id and (not line.from_area_id and not line.to_area_id):
-        line.add_error(CONTAINS_AREA_WITHOUT_FROM_TO_AREA)
-
-    if (line.from_area_id or line.to_area_id) and not line.is_symmetrical:
-        line.add_error(AREA_WITHOUT_IS_SYMMETRICAL)
-
-    if (not line.from_area_id and not line.to_area_id) and line.is_symmetrical:
-        line.add_error(IS_SYMMETRICAL_WITHOUT_FROM_TO_AREA)
-
     if line.from_area_id and line.from_area_id in unused_areas:
         unused_areas.remove(line.from_area_id)
     if line.to_area_id and line.to_area_id in unused_areas:
         unused_areas.remove(line.to_area_id)
 
     utils.check_linked_id(line, 'from_area_id', areas)
     utils.check_linked_id(line, 'to_area_id', areas)
-    utils.check_linked_id(line, 'contains_area_id', areas)
 
 
 def check_distances(line):

fares_validator/fare_product_checkers.py

@@ -3,13 +3,17 @@
 
 
 class LinkedEntities:
+
     def __init__(self):
         self.rider_category_ids = set()
         self.fare_container_ids = set()
 
 
-def check_linked_fp_entities(line, rider_categories, rider_category_by_fare_container, linked_entities_by_fare_product):
-    linked_entities = linked_entities_by_fare_product.setdefault(line.fare_product_id, LinkedEntities())
+def check_linked_fp_entities(line, rider_categories,
+                             rider_category_by_fare_container,
+                             linked_entities_by_fare_product):
+    linked_entities = linked_entities_by_fare_product.setdefault(
+        line.fare_product_id, LinkedEntities())
 
     if line.rider_category_id:
         linked_entities.rider_category_ids.add(line.rider_category_id)
@@ -23,8 +27,10 @@ def check_linked_fp_entities(line, rider_categories, rider_category_by_fare_cont
         if line.fare_container_id not in rider_category_by_fare_container:
             line.add_error(NONEXISTENT_FARE_CONTAINER_ID)
 
-        fare_container_rider_cat = rider_category_by_fare_container.get(line.fare_container_id)
-        if line.rider_category_id and fare_container_rider_cat and (line.rider_category_id != fare_container_rider_cat):
+        fare_container_rider_cat = rider_category_by_fare_container.get(
+            line.fare_container_id)
+        if line.rider_category_id and fare_container_rider_cat and (
+                line.rider_category_id != fare_container_rider_cat):
             line.add_error(CONFLICTING_RIDER_CATEGORY_ON_FARE_CONTAINER)
     else:
         linked_entities.fare_container_ids.add('')
@@ -46,7 +52,9 @@ def check_durations_and_offsets(line):
     if line.duration_start and line.duration_start not in {'0', '1'}:
         line.add_error(INVALID_DURATION_START)
 
-    if line.duration_unit and line.duration_unit not in {'0', '1', '2', '3', '4', '5', '6'}:
+    if line.duration_unit and line.duration_unit not in {
+            '0', '1', '2', '3', '4', '5', '6'
+    }:
         line.add_error(INVALID_DURATION_UNIT)
 
     if line.duration_type and line.duration_type not in {'1', '2'}:
@@ -74,7 +82,9 @@ def check_durations_and_offsets(line):
         if line.duration_unit:
             line.add_error(DURATION_UNIT_WITHOUT_AMOUNT)
 
-    if line.offset_unit and line.offset_unit not in {'0', '1', '2', '3', '4', '5', '6'}:
+    if line.offset_unit and line.offset_unit not in {
+            '0', '1', '2', '3', '4', '5', '6'
+    }:
         line.add_error(INVALID_OFFSET_UNIT)
 
     if line.offset_amount:

fares_validator/fare_transfer_rule_checkers.py

@@ -2,12 +2,6 @@
 
 
 def check_leg_groups(line, leg_group_ids, unused_leg_groups):
-    if line.is_symmetrical and line.is_symmetrical not in {'0', '1'}:
-        line.add_error(INVALID_IS_SYMMETRICAL_TRANSFER_RULES)
-    if (line.from_leg_group_id or line.to_leg_group_id) and not line.is_symmetrical:
-        line.add_error(LEG_GROUP_WITHOUT_IS_SYMMETRICAL)
-    if (not line.from_leg_group_id and not line.to_leg_group_id) and line.is_symmetrical:
-        line.add_error(IS_SYMMETRICAL_WITHOUT_FROM_TO_LEG_GROUP)
     if line.from_leg_group_id and not line.from_leg_group_id in leg_group_ids:
         line.add_error(INVALID_FROM_LEG_GROUP)
     if line.to_leg_group_id and not line.to_leg_group_id in leg_group_ids:
@@ -19,36 +13,22 @@ def check_leg_groups(line, leg_group_ids, unused_leg_groups):
         unused_leg_groups.remove(line.to_leg_group_id)
 
 
-def check_spans_and_transfer_ids(line):
-    if line.spanning_limit:
+def check_transfer_count(line):
+    if line.transfer_count:
         if line.from_leg_group_id != line.to_leg_group_id:
-            line.add_error(SPANNING_LIMIT_WITH_BAD_LEGS)
-        if line.transfer_id:
-            line.add_error(SPANNING_LIMIT_WITH_TRANSFER_ID)
+            line.add_error(TRANSFER_COUNT_WITH_BAD_LEGS)
         try:
-            limit = int(line.spanning_limit)
-            if limit <= 1:
-                line.add_error(INVALID_SPANNING_LIMIT)
+            limit = int(line.transfer_count)
+            if limit < 1 and limit != -1:
+                line.add_error(INVALID_TRANSFER_COUNT)
         except ValueError:
-            line.add_error(INVALID_SPANNING_LIMIT)
-
-    if line.transfer_id:
-        if not line.transfer_sequence:
-            line.add_error(TRANSFER_ID_WITHOUT_TRANSFER_SEQUENCE)
-
-    if line.transfer_sequence:
-        if not line.transfer_id:
-            line.add_error(TRANSFER_SEQUENCE_WITHOUT_TRANSFER_ID)
-        try:
-            seq = int(line.transfer_sequence)
-            if seq < 1:
-                line.add_error(INVALID_TRANSFER_SEQUENCE)
-        except ValueError:
-            line.add_error(INVALID_TRANSFER_SEQUENCE)
+            line.add_error(INVALID_TRANSFER_COUNT)
 
 
 def check_durations(line):
-    if line.duration_limit_type and line.duration_limit_type not in {'0', '1', '2', '3'}:
+    if line.duration_limit_type and line.duration_limit_type not in {
+            '0', '1', '2', '3'
+    }:
         line.add_error(INVALID_DURATION_LIMIT_TYPE)
 
     if line.duration_limit:

fares_validator/loader.py

@@ -23,31 +23,28 @@ def run_validator(gtfs_root_dir, should_read_stop_times):
 
     gtfs.networks = read_gtfs_entities.networks(gtfs_root_dir, results)
 
-    read_gtfs_entities.read_areas_in_stop_files(gtfs_root_dir, gtfs.areas, results, should_read_stop_times)
-
     gtfs.service_ids = read_gtfs_entities.service_ids(gtfs_root_dir, results)
 
     gtfs.timeframe_ids = read_fares_entities.timeframes(gtfs_root_dir, results)
     unused_timeframes = gtfs.timeframe_ids.copy()
 
-    gtfs.rider_category_ids = read_fares_entities.rider_categories(gtfs_root_dir, results)
+    gtfs.rider_category_ids = read_fares_entities.rider_categories(
+        gtfs_root_dir, results)
 
-    gtfs.rider_category_by_fare_container = read_fares_entities.fare_containers(gtfs_root_dir,
-                                                                                gtfs.rider_category_ids,
-                                                                                results)
+    gtfs.rider_category_by_fare_container = read_fares_entities.fare_containers(
+        gtfs_root_dir, gtfs.rider_category_ids, results)
 
-    gtfs.linked_entities_by_fare_product = read_fares_entities.fare_products(gtfs_root_dir,
-                                                                             gtfs,
-                                                                             unused_timeframes,
-                                                                             results)
+    gtfs.linked_entities_by_fare_product = read_fares_entities.fare_products(
+        gtfs_root_dir, gtfs, unused_timeframes, results)
 
-    gtfs.leg_group_ids = read_fares_entities.fare_leg_rules(gtfs_root_dir, gtfs,
-                                                            unused_timeframes, results)
+    gtfs.leg_group_ids = read_fares_entities.fare_leg_rules(
+        gtfs_root_dir, gtfs, unused_timeframes, results)
 
     read_fares_entities.fare_transfer_rules(gtfs_root_dir, gtfs, results)
 
     if len(unused_timeframes):
         warning_info = 'Unused timeframes: ' + str(unused_timeframes)
-        results.add_warning(diagnostics.format(warn.UNUSED_TIMEFRAME_IDS, '', '', warning_info))
+        results.add_warning(
+            diagnostics.format(warn.UNUSED_TIMEFRAME_IDS, '', '', warning_info))
 
     return results