def main():
usage = """usage: python gdb_import_gtfs.py [options] <graphdb_filename> <gtfsdb_filename> [<agency_id>]"""
parser = OptionParser(usage=usage)
parser.add_option("-n", "--namespace", dest="namespace", default="0",
help="agency namespace")
parser.add_option("-m", "--maxtrips", dest="maxtrips", default=None, help="maximum number of trips to load")
parser.add_option("-d", "--date", dest="sample_date", default=None, help="only load transit running on a given day. YYYYMMDD" )
(options, args) = parser.parse_args()
if len(args) != 2:
parser.print_help()
exit(-1)
graphdb_filename = args[0]
gtfsdb_filename = args[1]
agency_id = args[2] if len(args)==3 else None
print "importing from gtfsdb '%s' into graphdb '%s'"%(gtfsdb_filename, graphdb_filename)
gtfsdb = GTFSDatabase( gtfsdb_filename )
gdb = GraphDatabase( graphdb_filename, overwrite=False )
maxtrips = int(options.maxtrips) if options.maxtrips else None
gdb_load_gtfsdb( gdb, options.namespace, gtfsdb, gdb.get_cursor(), agency_id, maxtrips=maxtrips, sample_date=options.sample_date)
gdb.commit()
print "done"
def main():
usage = """usage: python gdb_link_osm_gtfs.py <graphdb_filename> <osmdb_filename> <gtfsdb_filename>"""
parser = OptionParser(usage=usage)
(options, args) = parser.parse_args()
if len(args) != 3:
parser.print_help()
exit(-1)
graphdb_filename = args[0]
osmdb_filename = args[1]
gtfsdb_filename = args[2]
gtfsdb = GTFSDatabase( gtfsdb_filename )
osmdb = OSMDB( osmdb_filename )
gdb = GraphDatabase( graphdb_filename )
n_stops = gtfsdb.count_stops()
for i, (stop_id, stop_name, stop_lat, stop_lon) in enumerate( gtfsdb.stops() ):
print "%d/%d"%(i,n_stops)
nd_id, nd_lat, nd_lon, nd_dist = osmdb.nearest_node( stop_lat, stop_lon )
station_vertex_id = "sta-%s"%stop_id
osm_vertex_id = "osm-%s"%nd_id
print station_vertex_id, osm_vertex_id
gdb.add_edge( station_vertex_id, osm_vertex_id, Link() )
gdb.add_edge( osm_vertex_id, station_vertex_id, Link() )
def main():
usage = """usage: python dedupe.py <graphdb_filename>"""
parser = OptionParser(usage=usage)
(options, args) = parser.parse_args()
if len(args) != 1:
parser.print_help()
exit(-1)
graphdb_filename = args[0]
gtfsdb = GTFSDatabase( graphdb_filename )
query = """
SELECT count(*), monday, tuesday, wednesday, thursday, friday, saturday, sunday, start_date, end_date
FROM calendar
GROUP BY monday, tuesday, wednesday, thursday, friday, saturday, sunday, start_date, end_date"""
duped_periods = gtfsdb.execute( query )
equivilants = []
for count, m,t,w,th,f,s,su,start_date,end_date in duped_periods:
# no need to check for dupes if there's only one
if count==1:
continue
#print count, m, t, w, th, f, s, su, start_date, end_date
# get service_ids for this dow/start_date/end_date combination
service_ids = [x[0] for x in list( gtfsdb.execute( "SELECT service_id FROM calendar where monday=? and tuesday=? and wednesday=? and thursday=? and friday=? and saturday=? and sunday=? and start_date=? and end_date=?", (m,t,w,th,f,s,su,start_date,end_date) ) ) ]
# group by service periods with the same set of exceptions
exception_set_grouper = {}
for service_id in service_ids:
exception_set = list(gtfsdb.execute( "SELECT date, exception_type FROM calendar_dates WHERE service_id=?", (service_id,) ) )
exception_set.sort()
exception_set = tuple(exception_set)
exception_set_grouper[exception_set] = exception_set_grouper.get(exception_set,[])
exception_set_grouper[exception_set].append( service_id )
# extend list of equivilants
for i, exception_set_group in enumerate( exception_set_grouper.values() ):
equivilants.append( ("%d%d%d%d%d%d%d-%s-%s-%d"%(m,t,w,th,f,s,su,start_date,end_date,i), exception_set_group) )
for new_name, old_names in equivilants:
for old_name in old_names:
print old_name, new_name
c = gtfsdb.conn.cursor()
c.execute( "UPDATE calendar SET service_id=? WHERE service_id=?", (new_name, old_name) )
c.execute( "UPDATE calendar_dates SET service_id=? WHERE service_id=?", (new_name, old_name) )
c.execute( "UPDATE trips SET service_id=? WHERE service_id=?", (new_name, old_name) )
gtfsdb.conn.commit()
c.close()
def ccp_save_cache(self):
time_0 = time.time()
log.debug('ccp_save_cache: loading the transit database')
db_transit = GTFSDatabase(conf.transitdb_filename)
# NOTE: Cannot cache edges, since they are C-objects. See usages of
# compiler.gtfsdb_to_edges(maxtrips). We can, however, at least
# count the edges....
self.cache_edges(db_transit)
log.debug('ccp_save_cache: making the transit graph link cache')
self.cache_links(db_transit)
log.debug('ccp_save_cache: done: %s' %
(misc.time_format_elapsed(time_0), ))
def load_make_graph_add_transit(self, qb):
# Not calling base class fcn.
# FIXME: What happens here on update? We reload all, don't we?
# FIXME: For p2, only do this on load, not on update.
# BUG nnnn: For p2, start new instance of route finder and then
# just change routed_ports to use that one, then kill
# the existing one.
time_0 = time.time()
usage_0 = None
if conf.debug_mem_usage:
usage_0 = mem_usage.get_usage_mb()
log.debug('load: adding transit...')
loaded = False
# Load the transit network, maybe (if we have data for it).
if conf.transitdb_filename:
self.cache_reg = self.links_get_cache_reg(qb)
log.debug('load: loading the transit database')
db_transit = GTFSDatabase(conf.transitdb_filename)
log.debug('load: making the transit graph')
self.load_transit(qb, db_transit)
# Link the two graphs
log.debug('load: linking the two graphs')
self.link_graphs(qb, db_transit)
loaded = True
# else, using Graphserver, but no public transit data to load.
if loaded:
log.info('load: added transit: in %s' %
(misc.time_format_elapsed(time_0), ))
else:
# MAYBE: Let devs test without loading transit.
raise GWIS_Error(
'Unable to load route finder: no transit info found.')
conf.debug_log_mem_usage(log, usage_0, 'tgraph.load / transit')
return loaded
def main():
usage = """usage: python gdb_link_gtfs_gtfs.py <graphdb_filename> <gtfsdb_filename> <range>"""
parser = OptionParser(usage=usage)
(options, args) = parser.parse_args()
if len(args) != 3:
parser.print_help()
exit(-1)
graphdb_filename = args[0]
gtfsdb_filename = args[1]
range = float(args[2])
gtfsdb = GTFSDatabase(gtfsdb_filename)
gdb = GraphDatabase(graphdb_filename)
n_stops = gtfsdb.count_stops()
for i, (stop_id, stop_name, stop_lat,
stop_lon) in enumerate(gtfsdb.stops()):
print "%d/%d %s" % (i, n_stops, stop_id),
station_vertex_id = "sta-%s" % stop_id
for link_stop_id, link_stop_name, link_stop_lat, link_stop_lon in gtfsdb.nearby_stops(
stop_lat, stop_lon, range):
if link_stop_id == stop_id:
continue
print ".",
link_length = vincenty(stop_lat, stop_lon, link_stop_lat,
link_stop_lon)
link_station_vertex_id = "sta-%s" % link_stop_id
gdb.add_edge(station_vertex_id, link_station_vertex_id,
Street("link", link_length))
print ""
#!/usr/bin/python
import sys, struct
# requires graphserver to be installed
from graphserver.ext.gtfs.gtfsdb import GTFSDatabase
if len(sys.argv) != 2:
print 'usage: datecheck.py inputfile.gtfsdb'
exit(1)
else:
gtfsdb_file = sys.argv[1]
try:
with open(gtfsdb_file) as f:
db = GTFSDatabase(gtfsdb_file)
except IOError as e:
print 'gtfsdb file %s cannot be opened' % gtfsdb_file
exit(1)
# check that all routes gs reports running are actually running on each day
for line in sys.stdin.readlines():
trip_id, fromid, fromtime, toid, totime = line.split()
if trip_id == 'walk':
continue
service_id = list(
db.execute('select service_id from trips where trip_id = ?',
(trip_id, )))[0][0]
print trip_id, '___', service_id
# and date > 20130415 and date < 20130420
for line in db.execute(
def __init__(self, gtfsdb_filename, timezone_name="America/Los_Angeles"):
self.gtfsdb = GTFSDatabase(gtfsdb_filename)
self.timezone_name = timezone_name
