#!/usr/bin/env python

import anydbm
import string
import re
import sys

locations = anydbm.open('./locations', 'c')

addresses = locations.keys()
#print addresses
#print len(addresses)

places = open('/var/www/aviationtoolbox/raw_data/Census/TIGER_2000/places2k.txt', 'r')

# Columns 1-2: United States Postal Service State Abbreviation
# Columns 3-4: State Federal Information Processing Standard (FIPS) code
# Columns 5-9: Place FIPS Code
# Columns 10-73: Name
# Columns 74-82: Total Population (2000)
# Columns 83-91: Total Housing Units (2000)
# Columns 92-105: Land Area (square meters) - Created for statistical purposes only.
# Columns 106-119: Water Area(square meters) - Created for statistical purposes only.
# Columns 120-131: Land Area (square miles) - Created for statistical purposes only.
# Columns 132-143: Water Area (square miles) - Created for statistical purposes only.
# Columns 144-153: Latitude (decimal degrees) First character is blank or "-" denoting North or South latitude respectively
# Columns 154-164: Longitude (decimal degrees) First character is blank or "-" denoting East or West longitude respectively

#city_re = re.compile('^([A-Z][a-z]+\.?([ -][A-Z][a-z]+\.?)*)(.*)$')
#city_re = re.compile('^(.*)((city)|(town)|(borough)) *$')

#city_re = re.compile('^(.*)( (city|town|borough|CDP|village|comunidad|urbana|\(balance\)|municipality)) *$')
city_with_suffix_re = re.compile('^(.*[^ ])( (city|town|borough|CDP|village|comunidad|urbana|\(balance\)|municipality))+ *$')

for line in places.readlines():
	state = line[:2]
	city = line[9:73]
	latitude = line[143:153]
	longitude = line[153:163]

	if 0 and not 'Indianapolis' in city:
		continue

	while 1:
		match = city_with_suffix_re.match(city)
		if not match:
			break
		#print city
		city = match.group(1)

	location_string = string.join(['', string.lower(city), string.lower(state)], '|')

	if 0 and not locations.has_key(location_string):
		print line[9:73], state, city
		None

	locations[location_string] = '%s|%s' % (longitude, latitude)