#!/usr/bin/env python

import sys

from the_semantic_db_code import *
from the_semantic_db_functions import *
from the_semantic_db_processor import *

C = context_list("geonames AU id version")

#file = "data/ascii-just-adelaide.txt"
file = "data/ascii-cities15000.txt"
#file = "data/ascii-AU.txt"


with open(file,'r') as f:
  for line in f:
#    print("line:",line)
#    fields = len(line.split("\t"))
#    print("fields:",fields)
    
    id,name,asciiname,altname,lat,long,feat_class,feat_code,country,cc2,admin1,admin2,admin3,admin4,population,elevation,dem,tz,mod_date = line.split("\t")
#    print("id:        ",id)
#    print("name:      ",asciiname)
#    print("lat:       ",lat)
#    print("long:      ",long)
#    print("country:   ",country)
#    print("population:",population)
#    print("dem:       ",dem)
#    print("tz:        ",tz)

#    print()

    if int(population) >= 0:
      x = ket("id: " + id)    
#      x = ket("location: " + asciiname)
      C.learn("id",x,"geonameid: " + id)
      C.learn("name",x,asciiname)                  # how handle if more than one location shares name, but not id?
      C.learn("lat",x,ket("latitude",lat))         # currently the last one over-writes the previous.
      C.learn("long",x,ket("longitude",long))      # heh. id is unique, name is not!
      C.learn("country",x,"country: " + country)   # ie, you are doing it wrong using location as x.
      C.learn("population",x,ket("population",population))
      C.learn("tz",x,"time-zone: " + tz)

print(C.dump_universe())