Class: GtfsDf::Graph

Inherits:
Object
  • Object
show all
Defined in:
lib/gtfs_df/graph.rb

Constant Summary collapse

FILES =
%w[
  agency routes trips stop_times calendar calendar_dates shapes transfers frequencies fare_attributes fare_rules
  fare_leg_join_rules fare_transfer_rules areas networks route_networks location_groups location_group_stops booking_rules
  stop_areas fare_leg_rules
]
STANDARD_FILE_NODES =
FILES.map do |file|
  [file, {id: file, file: file, filter: nil}]
end.to_h.freeze
STOP_NODES =

Separate node definitions for stops and parent stations to handle the self-referential relationship in stops.txt where stops reference parent stations via parent_station column. This allows filtering to preserve parent stations when their child stops are referenced.

{
  "stops" => {
    id: "stops",
    file: "stops",
    filter_attrs: {
      filter_col: "location_type",
      filter: Polars.col("location_type").is_in(
        Schema::EnumValues::STOP_LOCATION_TYPES.map(&:first)
      ) | Polars.col("location_type").is_null
    }
  },
  "parent_stations" => {
    id: "parent_stations",
    file: "stops",
    filter_attrs: {
      filter_col: "location_type",
      filter: Polars.col("location_type").is_in(
        Schema::EnumValues::STATION_LOCATION_TYPES.map(&:first)
      ) & Polars.col("location_type").is_not_null
    }
  }
}.freeze
NODES =
STANDARD_FILE_NODES.merge(STOP_NODES).freeze

Class Method Summary collapse

Class Method Details

.build(bidirectional: false) ⇒ Object

Returns a directed graph of GTFS file dependencies



44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
# File 'lib/gtfs_df/graph.rb', line 44

def self.build(bidirectional: false)
  g = NetworkX::DiGraph.new
  NODES.keys.each { |node| g.add_node(node) }

  # Edges should be parent, child
  # TODO: Add fare_rules -> stops + test
  edges = [
    ["agency", "routes", {dependencies: [
      {"agency" => "agency_id", "routes" => "agency_id"}
    ]}],
    ["agency", "fare_attributes", {dependencies: [
      {"fare_attributes" => "agency_id",
       "agency" => "agency_id", :allow_null => true}
    ], optional: true}],
    ["fare_attributes", "fare_rules", {dependencies: [
      {"fare_attributes" => "fare_id",
       "fare_rules" => "fare_id"}
    ]}],
    ["routes", "fare_rules", {dependencies: [
      {"fare_rules" => "route_id", "routes" => "route_id", :allow_null => true}
    ], optional: true}],
    ["routes", "trips", {dependencies: [
      {"routes" => "route_id", "trips" => "route_id"}
    ]}],
    ["trips", "stop_times", {dependencies: [
      {"trips" => "trip_id", "stop_times" => "trip_id"}
    ]}],
    ["stops", "stop_times", {dependencies: [
      {"stop_times" => "stop_id", "stops" => "stop_id"}
    ]}],
    # Self-referential edge: stops can reference parent stations (location_type=1)
    ["parent_stations", "stops", {dependencies: [
      {"stops" => "parent_station", "parent_stations" => "stop_id", :allow_null => true}
    ]}],
    ["stops", "transfers", {dependencies: [
      {"stops" => "stop_id", "transfers" => "from_stop_id"},
      {"stops" => "stop_id", "transfers" => "to_stop_id"}
    ], optional: true}],
    ["calendar", "trips", {dependencies: [
      {"trips" => "service_id", "calendar" => "service_id"}
    ]}],
    ["calendar_dates", "trips", {dependencies: [
      {"trips" => "service_id", "calendar_dates" => "service_id"}
    ]}],
    ["shapes", "trips", {dependencies: [
      {"trips" => "shape_id", "shapes" => "shape_id", :allow_null => true}
    ]}],
    ["trips", "frequencies", {dependencies: [
      {"trips" => "trip_id", "frequencies" => "trip_id"}
    ], optional: true}],

    # --- GTFS Extensions ---
    ["stops", "fare_leg_join_rules",
      {dependencies: [
        {"stops" => "stop_id", "fare_leg_join_rules" => "from_stop_id"},
        {"stops" => "stop_id", "fare_leg_join_rules" => "to_stop_id"}
      ]}],
    ["networks", "fare_leg_join_rules", {dependencies: [
      {"fare_leg_join_rules" => "from_network_id", "networks" => "network_id"},
      {"fare_leg_join_rules" => "to_network_id", "networks" => "network_id"}
    ]}],
    ["fare_leg_rules", "fare_leg_join_rules",
      {dependencies: [
        {"fare_leg_join_rules" => "fare_leg_rule_id", "fare_leg_rules" => "fare_leg_rule_id"}
      ]}],
    ["fare_transfer_rules", "fare_leg_rules",
      {dependencies: [
        {"fare_transfer_rules" => "from_leg_group_id", "fare_leg_rules" => "leg_group_id"},
        {"fare_transfer_rules" => "to_leg_group_id", "fare_leg_rules" => "leg_group_id"}
      ]}],
    ["fare_products", "fare_transfer_rules",
      {dependencies: [
        {"fare_transfer_rules" => "fare_product_id", "fare_products" => "fare_product_id"}
      ]}],
    ["areas", "stop_areas", {dependencies: [
      {"areas" => "area_id", "stop_areas" => "area_id"}
    ]}],
    ["areas", "stops", {dependencies: [
      {"stops" => "area_id", "areas" => "area_id"}
    ]}],
    ["areas", "fare_leg_rules", {dependencies: [
      {"areas" => "area_id", "fare_leg_rules" => "from_area_id"},
      {"areas" => "area_id", "fare_leg_rules" => "to_area_id"}
    ]}],
    ["networks", "route_networks", {dependencies: [
      {"networks" => "network_id", "route_networks" => "network_id"}
    ]}],
    ["networks", "routes", {dependencies: [
      {"networks" => "network_id", "routes" => "network_id"}
    ]}],
    ["networks", "fare_leg_rules", {dependencies: [
      {"networks" => "network_id", "fare_leg_rules" => "network_id"}
    ]}],
    ["routes", "route_networks", {dependencies: [
      {"route_networks" => "route_id", "routes" => "route_id"}
    ]}],
    ["networks", "route_networks", {dependencies: [
      {"route_networks" => "network_id", "networks" => "network_id"}
    ]}],
    ["location_groups", "location_group_stops", {dependencies: [
      {"location_groups" => "location_group_id", "location_group_stops" => "location_group_id"}
    ]}],
    ["location_groups", "stops", {dependencies: [
      {"location_groups" => "location_group_id", "stops" => "location_group_id"}
    ]}],
    ["stops", "location_group_stops", {dependencies: [
      {"location_group_stops" => "stop_id", "stops" => "stop_id"}
    ]}],
    ["stops", "location_group_stops", {dependencies: [
      {"stops" => "stop_id", "location_group_stops" => "stop_id"}
    ]}],
    ["location_groups", "location_group_stops", {dependencies: [
      {"location_group_stops" => "location_group_id", "location_groups" => "location_group_id"}
    ]}],
    ["booking_rules", "stop_times", {dependencies: [
      {"booking_rules" => "booking_rule_id", "stop_times" => "pickup_booking_rule_id"},
      {"booking_rules" => "booking_rule_id", "stop_times" => "drop_off_booking_rule_id"}
    ]}]
  ]

  edges.each do |from, to, attrs|
    g.add_edge(from, to, **attrs)
    if bidirectional
      # When adding the reverse edge, if the relationship is optional (child is not required),
      # mark the reverse edge as weak. This prevents empty child tables (e.g. fare_rules)
      # from filtering parent tables (e.g. routes) into emptiness.
      reverse_attrs = attrs.dup
      if attrs[:optional]
        reverse_attrs[:type] = :weak
      end
      g.add_edge(to, from, **reverse_attrs)
    end
  end
  g
end