def unify_geo_data(input_string):
"""
Return unified geographic data
>>> data = unify_geo_data("Av. rivadavia 9858, buenos aires, argentina")
>>> data == {'latitud': -34.637979199999997, 'city': u'Buenos Aires',\
'country': u'Argentina', 'number': u'9858',\
'state': u'Capital Federal',\
'street': u'Av Rivadavia', 'street2': '',\
'longitud': -58.503058099999997, 'zip': 'C1407DZU'}
True
>>> data = unify_geo_data("gral paz 9858, general san martin,
buenos aires, argentina")
>>> data == {'latitud': -34.581238599999999, 'city': '', 'zip': '',\
'country': u'Argentina', 'number': u'9858',\
'state': u'Buenos Aires', 'street': u'Gral. Paz',\
'street2': '', 'longitud': -58.513873400000001}
True
>>> data = unify_geo_data("VICTORIA OCAMPO 360 PISO PB,
CAPITAL FEDERAL,CAPITAL FEDERAL,Argentina")
>>> data == {'latitud': -34.601967000000002, 'city': u'Buenos Aires',\
'zip': '', 'country': u'Argentina', 'street2': 'piso pb',\
'number': u'360', 'state': u'Capital Federal',\
'street': u'Victoria Ocampo', 'longitud': -58.364093699999998}
True
>>> data = unify_geo_data("AV. DEL LIBERTADOR 767 PISO 1,
VICENTE LOPEZ,BUENOS AIRES,Argentina")
>>> data == {'latitud': -34.527026800000002, 'city': u'Vicente L\xf3pez',\
'zip': u'1638', 'country': u'Argentina', 'street2': 'piso 1',\
'number': u'767', 'state': u'Buenos Aires Province',\
'street': u'Av Del Libertador Gral. San Martin',\
'longitud': -58.471314999999997}
True
>>> data = unify_geo_data("PELLEGRINI 255,,,SANTA ROSA,LA PAMPA,Argentina")
>>> data == {'latitud': -36.619441799999997, 'city': u'Santa Rosa',\
'zip': u'L6300DRE', 'country': u'Argentina', 'street2': '',\
'number': u'255', 'state': u'La Pampa', \
'street': u'Pellegrini',\
'longitud': -64.292496499999999}
True
"""
input_string = input_string.lower()
# Remove sporius data for search and store it in street2
street2 = []
for country in street2_searcher.keys():
if country in input_string:
for rexp in street2_searcher[country]:
match = rexp.search(input_string)
if match:
street2.append(','.join(match.groups()))
input_string = rexp.sub('', input_string)
street2 = ','.join(street2)
input_string = input_string.encode('ascii', 'ignore')
# Search data in geographics database
try:
_gc = geocode(_st(input_string, " ", " "))
if _gc is None:
return {'error': 'No geocoding service available'}
if not _gc:
return {'error': 'No answer'}
except GeocoderTimedOut:
return {'error': 'Connection timeout'}
if len(_gc) > 1:
i = mostequivalent(map(lambda (a, b): a, _gc), input_string)
_gc = _gc[i]
else:
_gc = _gc[0]
place, lat, lng = [_gc[k] for k in ['display_name', 'lat', 'lon']]
_logger.debug("PLACE: %s" % place)
for _re in address_re:
result = _re.search(place)
if result:
result = result.groupdict()
break
_logger.debug("IGNORE: %s" % _re)
if not result:
return False
_logger.debug("RESULT: %s" % result)
data = {
'country': result['country'],
'zip': result['zip'],
'state': result['state'],
'city': result['city'],
'nbhd': result['nbhd'],
'number': result['number'],
'street': result['street'],
'street2': result['building'],
'latitud': float(lat),
'longitud': float(lng),
}
return data
def unify_geo_data(input_string):
"""
Return unified geographic data
>>> data = unify_geo_data("Av. rivadavia 9858, buenos aires, argentina")
>>> data == {'latitud': -34.637979199999997, 'city': u'Buenos Aires',\
'country': u'Argentina', 'number': u'9858',\
'state': u'Capital Federal',\
'street': u'Av Rivadavia', 'street2': '',\
'longitud': -58.503058099999997, 'zip': 'C1407DZU'}
True
>>> data = unify_geo_data("gral paz 9858, general san martin, buenos aires, argentina")
>>> data == {'latitud': -34.581238599999999, 'city': '', 'zip': '',\
'country': u'Argentina', 'number': u'9858',\
'state': u'Buenos Aires', 'street': u'Gral. Paz',\
'street2': '', 'longitud': -58.513873400000001}
True
>>> data = unify_geo_data("VICTORIA OCAMPO 360 PISO PB,CAPITAL FEDERAL,CAPITAL FEDERAL,Argentina")
>>> data == {'latitud': -34.601967000000002, 'city': u'Buenos Aires',\
'zip': '', 'country': u'Argentina', 'street2': 'piso pb',\
'number': u'360', 'state': u'Capital Federal',\
'street': u'Victoria Ocampo', 'longitud': -58.364093699999998}
True
>>> data = unify_geo_data("AV. DEL LIBERTADOR 767 PISO 1,VICENTE LOPEZ,BUENOS AIRES,Argentina")
>>> data == {'latitud': -34.527026800000002, 'city': u'Vicente L\xf3pez',\
'zip': u'1638', 'country': u'Argentina', 'street2': 'piso 1',\
'number': u'767', 'state': u'Buenos Aires Province',\
'street': u'Av Del Libertador Gral. San Martin',\
'longitud': -58.471314999999997}
True
>>> data = unify_geo_data("PELLEGRINI 255,,,SANTA ROSA,LA PAMPA,Argentina")
>>> data == {'latitud': -36.619441799999997, 'city': u'Santa Rosa',\
'zip': u'L6300DRE', 'country': u'Argentina', 'street2': '',\
'number': u'255', 'state': u'La Pampa', 'street': u'Pellegrini',\
'longitud': -64.292496499999999}
True
"""
#print >> sys.stderr, "Unifying:", input_string
input_string = input_string.lower()
# Remove sporius data for search and store it in street2
street2 = []
for country in street2_searcher.keys():
if country in input_string:
for rexp in street2_searcher[country]:
match = rexp.search(input_string)
if match:
street2.append(','.join(match.groups()))
input_string = rexp.sub('', input_string)
street2 = ','.join(street2)
input_string = input_string.encode('ascii', 'ignore')
# Search data in geographics database
try:
place, (lat, lng) = geocode(_st(input_string, " ", " "))
except ValueError:
places = list(geocode(input_string, exactly_one=False))
i = mostequivalent(map(lambda (a,b): a, places), input_string)
place, (lat, lng) = places[i]
data = {}
result = map(lambda s: s.strip(), place.split(','))
result = [u'']*(4-len(result)) + result
# Ordering data
if len(result) == 4:
address, data['city'], data['state'], data['country'] = result
else:
raise RuntimeError('Exists more than 4 tokens in the place.')
data['latitud'] = lat
data['longitud'] = lng
# Split address data
if data['country'] in ['Argentina',]:
s = re.search(r'^\s*(.*)\s+(\d+)\s*$', address)
if s != None:
street, number = s.groups()
else:
street = input_string.split(',')[0]
s = re.search(r'(.*)\s+(\d+)', street)
if s != None:
street, number = s.groups()
else:
number = ''
data['city'] = address
else:
number, street = re.search(r'(\d*)\s+(.*)', address).groups()
data['street'] = street.strip()
data['street2'] = street2.strip()
data['number'] = number.strip()
# Load zip data
#try:
#data['zip'] = search_zip(data['street'], data['number'], data['city'],
#data['state'], data['country'])
#except:
data['zip'] = ''
return data
def unify_geo_data(input_string):
"""
Return unified geographic data
>>> data = unify_geo_data("Av. rivadavia 9858, buenos aires, argentina")
>>> data == {'latitud': -34.637979199999997, 'city': u'Buenos Aires',\
'country': u'Argentina', 'number': u'9858',\
'state': u'Capital Federal',\
'street': u'Av Rivadavia', 'street2': '',\
'longitud': -58.503058099999997, 'zip': 'C1407DZU'}
True
>>> data = unify_geo_data("gral paz 9858, general san martin, buenos aires, argentina")
>>> data == {'latitud': -34.581238599999999, 'city': '', 'zip': '',\
'country': u'Argentina', 'number': u'9858',\
'state': u'Buenos Aires', 'street': u'Gral. Paz',\
'street2': '', 'longitud': -58.513873400000001}
True
>>> data = unify_geo_data("VICTORIA OCAMPO 360 PISO PB,CAPITAL FEDERAL,CAPITAL FEDERAL,Argentina")
>>> data == {'latitud': -34.601967000000002, 'city': u'Buenos Aires',\
'zip': '', 'country': u'Argentina', 'street2': 'piso pb',\
'number': u'360', 'state': u'Capital Federal',\
'street': u'Victoria Ocampo', 'longitud': -58.364093699999998}
True
>>> data = unify_geo_data("AV. DEL LIBERTADOR 767 PISO 1,VICENTE LOPEZ,BUENOS AIRES,Argentina")
>>> data == {'latitud': -34.527026800000002, 'city': u'Vicente L\xf3pez',\
'zip': u'1638', 'country': u'Argentina', 'street2': 'piso 1',\
'number': u'767', 'state': u'Buenos Aires Province',\
'street': u'Av Del Libertador Gral. San Martin',\
'longitud': -58.471314999999997}
True
>>> data = unify_geo_data("PELLEGRINI 255,,,SANTA ROSA,LA PAMPA,Argentina")
>>> data == {'latitud': -36.619441799999997, 'city': u'Santa Rosa',\
'zip': u'L6300DRE', 'country': u'Argentina', 'street2': '',\
'number': u'255', 'state': u'La Pampa', 'street': u'Pellegrini',\
'longitud': -64.292496499999999}
True
"""
#print >> sys.stderr, "Unifying:", input_string
input_string = input_string.lower()
# Remove sporius data for search and store it in street2
street2 = []
for country in street2_searcher.keys():
if country in input_string:
for rexp in street2_searcher[country]:
match = rexp.search(input_string)
if match:
street2.append(','.join(match.groups()))
input_string = rexp.sub('', input_string)
street2 = ','.join(street2)
input_string = input_string.encode('ascii', 'ignore')
# Search data in geographics database
try:
place, (lat, lng) = geocode(_st(input_string, " ", " "))
except ValueError:
places = list(geocode(input_string, exactly_one=False))
i = mostequivalent(map(lambda (a, b): a, places), input_string)
place, (lat, lng) = places[i]
data = {}
result = map(lambda s: s.strip(), place.split(','))
result = [u''] * (4 - len(result)) + result
# Ordering data
if len(result) == 4:
address, data['city'], data['state'], data['country'] = result
else:
raise RuntimeError('Exists more than 4 tokens in the place.')
data['latitud'] = lat
data['longitud'] = lng
# Split address data
if data['country'] in [
'Argentina',
]:
s = re.search(r'^\s*(.*)\s+(\d+)\s*$', address)
if s != None:
street, number = s.groups()
else:
street = input_string.split(',')[0]
s = re.search(r'(.*)\s+(\d+)', street)
if s != None:
street, number = s.groups()
else:
number = ''
data['city'] = address
else:
number, street = re.search(r'(\d*)\s+(.*)', address).groups()
data['street'] = street.strip()
data['street2'] = street2.strip()
data['number'] = number.strip()
# Load zip data
#try:
#data['zip'] = search_zip(data['street'], data['number'], data['city'],
#data['state'], data['country'])
#except:
data['zip'] = ''
return data
def unify_geo_data(input_string):
"""
Return unified geographic data
>>> data = unify_geo_data("Av. rivadavia 9858, buenos aires, argentina")
>>> data == {'latitud': -34.637979199999997, 'city': u'Buenos Aires',\
'country': u'Argentina', 'number': u'9858',\
'state': u'Capital Federal',\
'street': u'Av Rivadavia', 'street2': '',\
'longitud': -58.503058099999997, 'zip': 'C1407DZU'}
True
>>> data = unify_geo_data("gral paz 9858, general san martin,
buenos aires, argentina")
>>> data == {'latitud': -34.581238599999999, 'city': '', 'zip': '',\
'country': u'Argentina', 'number': u'9858',\
'state': u'Buenos Aires', 'street': u'Gral. Paz',\
'street2': '', 'longitud': -58.513873400000001}
True
>>> data = unify_geo_data("VICTORIA OCAMPO 360 PISO PB,
CAPITAL FEDERAL,CAPITAL FEDERAL,Argentina")
>>> data == {'latitud': -34.601967000000002, 'city': u'Buenos Aires',\
'zip': '', 'country': u'Argentina', 'street2': 'piso pb',\
'number': u'360', 'state': u'Capital Federal',\
'street': u'Victoria Ocampo', 'longitud': -58.364093699999998}
True
>>> data = unify_geo_data("AV. DEL LIBERTADOR 767 PISO 1,
VICENTE LOPEZ,BUENOS AIRES,Argentina")
>>> data == {'latitud': -34.527026800000002, 'city': u'Vicente L\xf3pez',\
'zip': u'1638', 'country': u'Argentina', 'street2': 'piso 1',\
'number': u'767', 'state': u'Buenos Aires Province',\
'street': u'Av Del Libertador Gral. San Martin',\
'longitud': -58.471314999999997}
True
>>> data = unify_geo_data("PELLEGRINI 255,,,SANTA ROSA,LA PAMPA,Argentina")
>>> data == {'latitud': -36.619441799999997, 'city': u'Santa Rosa',\
'zip': u'L6300DRE', 'country': u'Argentina', 'street2': '',\
'number': u'255', 'state': u'La Pampa', \
'street': u'Pellegrini',\
'longitud': -64.292496499999999}
True
"""
input_string = input_string.lower()
# Remove sporius data for search and store it in street2
street2 = []
for country in street2_searcher.keys():
if country in input_string:
for rexp in street2_searcher[country]:
match = rexp.search(input_string)
if match:
street2.append(','.join(match.groups()))
input_string = rexp.sub('', input_string)
street2 = ','.join(street2)
input_string = input_string.encode('ascii', 'ignore')
# Search data in geographics database
try:
_gc = geocode(_st(input_string, " ", " "))
if _gc is None:
return {'error': 'No geocoding service available'}
if not _gc:
return {'error': 'No answer'}
except GeocoderTimedOut:
return {'error': 'Connection timeout'}
if len(_gc) > 1:
i = mostequivalent(map(lambda (a, b): a, _gc), input_string)
_gc = _gc[i]
else:
_gc = _gc[0]
place, lat, lng = [_gc[k] for k in ['display_name', 'lat', 'lon']]
_logger.debug("PLACE: %s" % place)
for _re in address_re:
result = _re.search(place)
if result:
result = result.groupdict()
break
_logger.debug("IGNORE: %s" % _re)
assert result is not None, "Geolocalization return wrong address."
_logger.debug("RESULT: %s" % result)
data = {
'country': result['country'],
'zip': result['zip'],
'state': result['state'],
'city': result['city'],
'nbhd': result['nbhd'],
'number': result['number'],
'street': result['street'],
'street2': result['building'],
'latitud': float(lat),
'longitud': float(lng),
}
return data