There are some commercial address standardization software such as:
http://www.semaphorecorp.com/zp4/
(i do not work for this company :) but have used their software)
jim
On Nov 29, 7:31 am, Corey Oordt <[EMAIL PROTECTED]> wrote:
> I ported part of the Geo Street Address from the perl module:
>
> >>>>>>>>address_regex.py
> from geocode.address_dicts import *
>
> STREET_TYPE_REGEX = "|".join(STREET_TYPES.keys()) + "|" +
> "|".join(STREET_TYPES.values())
> STATE_REGEX = "|".join(STATE_CODES.values())
> DIRECTIONS_REGEX = "|".join(DIRECTIONS.keys()) + "|" +
> "|".join(DIRECTIONS.values())
> ZIP_REGEX = "\\d{5}(?:-*\\d{4})?"
> ZIP_LOOSE_REGEX = "[\\d-]+" #To catch malformed zipcodes
> CORNER_REGEX = "(?:\\bAND\\b|\\bAT\\b|&|\\@)"
> UNIT_REGEX = "(?:(?:su?i?te|p\\W*[om]\\W*b(?:ox)?|dept|apt|ro*m|fl|apt|
> unit|box)\\W+|\#\\W*)[\\w-]+"
> NUMBER_REGEX = "\\d+-?\\d*"
> FRACTION_REGEX = "\\d+\/\\d+"
>
> # Possible street combinations:
> STREET_REGEX = """
> (?:
> # special cases like 100 South Street
> (?:
> (?P<street1>""" + DIRECTIONS_REGEX + """)\\W+
> (?P<street_type1>""" + STREET_TYPE_REGEX + """)\\b
> )
> |
> (?:(?P<pre_dir>""" + DIRECTIONS_REGEX + """)\\W+)?
> (?:
> (?P<street2>[^,]+)
> (?:[^\\w,]+(?P<street_type2>""" + STREET_TYPE_REGEX + """)\\b)
> (?:[^\\w,]+(?P<post_dir1>""" + DIRECTIONS_REGEX + """)\\b)?
> |
> (?P<street3>[^,]*\\d)
> (?P<post_dir2>""" + DIRECTIONS_REGEX + """)
> |
> (?P<street4>[^,]+?)
> (?:[^\\w,]+(?P<street_type3>""" + STREET_TYPE_REGEX + """)\\b)?
> (?:[^\\w,]+(?P<post_dir3>""" + DIRECTIONS_REGEX + """)\\b)?
> )
> )"""
>
> CITYSTATE_REGEX = """
> (?:
> (?P<city>[^,]+?),\\W+
> (?P<state>""" + STATE_REGEX +""")\\W*
> )?"""
>
> PLACE_REGEX = CITYSTATE_REGEX + """(?:(?P<zip>""" + ZIP_REGEX +"""))?"""
>
> ADDRESS_REGEX = """^\\W*
> (?P<number>""" + NUMBER_REGEX + """)?\\W*
> (?:""" + FRACTION_REGEX + """\\W*)? # We don't need to keep the
> fractional part
> """ + STREET_REGEX + """\\W+
> (?:""" + UNIT_REGEX + """\\W+)? # We don't need to keep a unit part
> """# + PLACE_REGEX + """\\W*$"""
>
> INTERSECTION_REGEX = "\\W*" + STREET_REGEX + \
> "\\W*?\\s+" + CORNER_REGEX + "\\s+" \
> + STREET_REGEX + "\\W+" \
> + PLACE_REGEX
>
> <<<<<<<<<<<<<<<<<<<<<<<
>
> >>>>>>>>>>>>address_dicts.py
> DIRECTIONS = {
> "NORTH": "N",
> "NORTHEAST": "NE",
> "EAST": "E",
> "SOUTHEAST": "SE",
> "SOUTH": "S",
> "SOUTHWEST": "SW",
> "WEST": "W",
> "NORTHWEST": "NW",
>
> }
>
> STATE_CODES = {
> "ALABAMA": "AL",
> "ALASKA": "AK",
> "AMERICAN SAMOA": "AS",
> "ARIZONA": "AZ",
> "ARKANSAS": "AR",
> "CALIFORNIA": "CA",
> "COLORADO": "CO",
> "CONNECTICUT": "CT",
> "DELAWARE": "DE",
> "DISTRICT OF COLUMBIA": "DC",
> "FEDERATED STATES OF MICRONESIA": "FM",
> "FLORIDA": "FL",
> "GEORGIA": "GA",
> "GUAM": "GU",
> "HAWAII": "HI",
> "IDAHO": "ID",
> "ILLINOIS": "IL",
> "INDIANA": "IN",
> "IOWA": "IA",
> "KANSAS": "KS",
> "KENTUCKY": "KY",
> "LOUISIANA": "LA",
> "MAINE": "ME",
> "MARSHALL ISLANDS": "MH",
> "MARYLAND": "MD",
> "MASSACHUSETTS": "MA",
> "MICHIGAN": "MI",
> "MINNESOTA": "MN",
> "MISSISSIPPI": "MS",
> "MISSOURI": "MO",
> "MONTANA": "MT",
> "NEBRASKA": "NE",
> "NEVADA": "NV",
> "NEW HAMPSHIRE": "NH",
> "NEW JERSEY": "NJ",
> "NEW MEXICO": "NM",
> "NEW YORK": "NY",
> "NORTH CAROLINA": "NC",
> "NORTH DAKOTA": "ND",
> "NORTHERN MARIANA ISLANDS": "MP",
> "OHIO": "OH",
> "OKLAHOMA": "OK",
> "OREGON": "OR",
> "PALAU": "PW",
> "PENNSYLVANIA": "PA",
> "PUERTO RICO": "PR",
> "RHODE ISLAND": "RI",
> "SOUTH CAROLINA": "SC",
> "SOUTH DAKOTA": "SD",
> "TENNESSEE": "TN",
> "TEXAS": "TX",
> "UTAH": "UT",
> "VERMONT": "VT",
> "VIRGIN ISLANDS": "VI",
> "VIRGINIA": "VA",
> "WASHINGTON": "WA",
> "WEST VIRGINIA": "WV",
> "WISCONSIN": "WI",
> "WYOMING": "WY",
>
> }
>
> STREET_TYPES = {
> "ALLEE": "ALY",
> "ALLEY": "ALY",
> "ALLY": "ALY",
> "ANEX": "ANX",
> "ANNEX": "ANX",
> "ANNX": "ANX",
> "ARCADE": "ARC",
> "AV": "AVE",
> "AVEN": "AVE",
> "AVENU": "AVE",
> "AVENUE": "AVE",
> "AVN": "AVE",
> "AVNUE": "AVE",
> "BAYOO": "BYU",
> "BAYOU": "BYU",
> "BEACH": "BCH",
> "BEND": "BND",
> "BLUF": "BLF",
> "BLUFF": "BLF",
> "BLUFFS": "BLFS",
> "BOT": "BTM",
> "BOTTM": "BTM",
> "BOTTOM": "BTM",
> "BOUL": "BLVD",
> "BOULEVARD": "BLVD",
> "BOULV": "BLVD",
> "BRANCH": "BR",
> "BRDGE": "BRG",
> "BRIDGE": "BRG",
> "BRNCH": "BR",
> "BROOK": "BRK",
> "BROOKS": "BRKS",
> "BURG": "BG",
> "BURGS": "BGS",
> "BYPA": "BYP",
> "BYPAS": "BYP",
> "BYPASS": "BYP",
> "BYPS": "BYP",
> "CAMP": "CP",
> "CANYN": "CYN",
> "CANYON": "CYN",
> "CAPE": "CPE",
> "CAUSEWAY": "CSWY",
> "CAUSWAY": "CSWY",
> "CEN": "CTR",
> "CENT": "CTR",
> "CENTER": "CTR",
> "CENTERS": "CTRS",
> "CENTR": "CTR",
> "CENTRE": "CTR",
> "CIRC": "CIR",
> "CIRCL": "CIR",
> "CIRCLE": "CIR",
> "CIRCLES": "CIRS",
> "CK": "CRK",
> "CLIFF": "CLF",
> "CLIFFS": "CLFS",
> "CLUB": "CLB",
> "CMP": "CP",
> "CNTER": "CTR",
> "CNTR": "CTR",
> "CNYN": "CYN",
> "COMMON": "CMN",
> "CORNER": "COR",
> "CORNERS": "CORS",
> "COURSE": "CRSE",
> "COURT": "CT",
> "COURTS": "CTS",
> "COVE": "CV",
> "COVES": "CVS",
> "CR": "CRK",
> "CRCL": "CIR",
> "CRCLE": "CIR",
> "CRECENT": "CRES",
> "CREEK": "CRK",
> "CRESCENT": "CRES",
> "CRESENT": "CRES",
> "CREST": "CRST",
> "CROSSING": "XING",
> "CROSSROAD": "XRD",
> "CRSCNT": "CRES",
> "CRSENT": "CRES",
> "CRSNT": "CRES",
> "CRSSING": "XING",
> "CRSSNG": "XING",
> "CRT": "CT",
> "CURVE": "CURV",
> "DALE": "DL",
> "DAM": "DM",
> "DIV": "DV",
> "DIVIDE": "DV",
> "DRIV": "DR",
> "DRIVE": "DR",
> "DRIVES": "DRS",
> "DRV": "DR",
> "DVD": "DV",
> "ESTATE": "EST",
> "ESTATES": "ESTS",
> "EXP": "EXPY",
> "EXPR": "EXPY",
> "EXPRESS": "EXPY",
> "EXPRESSWAY": "EXPY",
> "EXPW": "EXPY",
> "EXTENSION": "EXT",
> "EXTENSIONS": "EXTS",
> "EXTN": "EXT",
> "EXTNSN": "EXT",
> "FALLS": "FLS",
> "FERRY": "FRY",
> "FIELD": "FLD",
> "FIELDS": "FLDS",
> "FLAT": "FLT",
> "FLATS": "FLTS",
> "FORD": "FRD",
> "FORDS": "FRDS",
> "FOREST": "FRST",
> "FORESTS": "FRST",
> "FORG": "FRG",
> "FORGE": "FRG",
> "FORGES": "FRGS",
> "FORK": "FRK",
> "FORKS": "FRKS",
> "FORT": "FT",
> "FREEWAY": "FWY",
> "FREEWY": "FWY",
> "FRRY": "FRY",
> "FRT": "FT",
> "FRWAY": "FWY",
> "FRWY": "FWY",
> "GARDEN": "GDN",
> "GARDENS": "GDNS",
> "GARDN": "GDN",
> "GATEWAY": "GTWY",
> "GATEWY": "GTWY",
> "GATWAY": "GTWY",
> "GLEN": "GLN",
> "GLENS": "GLNS",
> "GRDEN": "GDN",
> "GRDN": "GDN",
> "GRDNS": "GDNS",
> "GREEN": "GRN",
> "GREENS": "GRNS",
> "GROV": "GRV",
> "GROVE": "GRV",
> "GROVES": "GRVS",
> "GTWAY": "GTWY",
> "HARB": "HBR",
> "HARBOR": "HBR",
> "HARBORS": "HBRS",
> "HARBR": "HBR",
> "HAVEN": "HVN",
> "HAVN": "HVN",
> "HEIGHT": "HTS",
> "HEIGHTS": "HTS",
> "HGTS": "HTS",
> "HIGHWAY": "HWY",
> "HIGHWY": "HWY",
> "HILL": "HL",
> "HILLS": "HLS",
> "HIWAY": "HWY",
> "HIWY": "HWY",
> "HLLW": "HOLW",
> "HOLLOW": "HOLW",
> "HOLLOWS": "HOLW",
> "HOLWS": "HOLW",
> "HRBOR": "HBR",
> "HT": "HTS",
> "HWAY": "HWY",
> "INLET": "INLT",
> "ISLAND": "IS",
> "ISLANDS": "ISS",
> "ISLES": "ISLE",
> "ISLND": "IS",
> "ISLNDS": "ISS",
> "JCTION": "JCT",
> "JCTN": "JCT",
> "JCTNS": "JCTS",
> "JUNCTION": "JCT",
> "JUNCTIONS": "JCTS",
> "JUNCTN": "JCT",
> "JUNCTON": "JCT",
> "KEY": "KY",
> "KEYS": "KYS",
> "KNOL": "KNL",
> "KNOLL": "KNL",
> "KNOLLS": "KNLS",
> "LA": "LN",
> "LAKE": "LK",
> "LAKES": "LKS",
> "LANDING": "LNDG",
> "LANE": "LN",
> "LANES": "LN",
> "LDGE": "LDG",
> "LIGHT": "LGT",
> "LIGHTS": "LGTS",
> "LNDNG": "LNDG",
> "LOAF": "LF",
> "LOCK": "LCK",
> "LOCKS": "LCKS",
> "LODG": "LDG",
> "LODGE": "LDG",
> "LOOPS": "LOOP",
> "MANOR": "MNR",
> "MANORS": "MNRS",
> "MEADOW": "MDW",
> "MEADOWS": "MDWS",
> "MEDOWS": "MDWS",
> "MILL": "ML",
> "MILLS": "MLS",
> "MISSION": "MSN",
> "MISSN": "MSN",
> "MNT": "MT",
> "MNTAIN": "MTN",
> "MNTN": "MTN",
> "MNTNS": "MTNS",
> "MOTORWAY": "MTWY",
> "MOUNT": "MT",
> "MOUNTAIN": "MTN",
> "MOUNTAINS": "MTNS",
> "MOUNTIN": "MTN",
> "MSSN": "MSN",
> "MTIN": "MTN",
> "NECK": "NCK",
> "ORCHARD": "ORCH",
> "ORCHRD": "ORCH",
> "OVERPASS": "OPAS",
> "OVL": "OVAL",
> "PARKS": "PARK",
> "PARKWAY": "PKWY",
> "PARKWAYS": "PKWY",
> "PARKWY": "PKWY",
> "PASSAGE": "PSGE",
> "PATHS": "PATH",
> "PIKES": "PIKE",
> "PINE": "PNE",
> "PINES": "PNES",
> "PK": "PARK",
> "PKWAY": "PKWY",
> "PKWYS": "PKWY",
> "PKY": "PKWY",
> "PLACE": "PL",
> "PLAIN": "PLN",
> "PLAINES": "PLNS",
> "PLAINS": "PLNS",
> "PLAZA": "PLZ",
> "PLZA": "PLZ",
> "POINT": "PT",
> "POINTS": "PTS",
> "PORT": "PRT",
> "PORTS": "PRTS",
> "PRAIRIE": "PR",
> "PRARIE": "PR",
> "PRK": "PARK",
> "PRR": "PR",
> "RAD": "RADL",
> "RADIAL": "RADL",
> "RADIEL": "RADL",
> "RANCH": "RNCH",
> "RANCHES": "RNCH",
> "RAPID": "RPD",
> "RAPIDS": "RPDS",
> "RDGE": "RDG",
> "REST": "RST",
> "RIDGE": "RDG",
> "RIDGES": "RDGS",
> "RIVER": "RIV",
> "RIVR": "RIV",
> "RNCHS": "RNCH",
> "ROAD": "RD",
> "ROADS": "RDS",
> "ROUTE": "RTE",
> "RVR": "RIV",
> "SHOAL": "SHL",
> "SHOALS": "SHLS",
> "SHOAR": "SHR",
> "SHOARS": "SHRS",
> "SHORE": "SHR",
> "SHORES": "SHRS",
> "SKYWAY": "SKWY",
> "SPNG": "SPG",
> "SPNGS": "SPGS",
> "SPRING": "SPG",
> "SPRINGS": "SPGS",
> "SPRNG": "SPG",
> "SPRNGS": "SPGS",
> "SPURS": "SPUR",
> "SQR": "SQ",
> "SQRE": "SQ",
> "SQRS": "SQS",
> "SQU": "SQ",
> "SQUARE": "SQ",
> "SQUARES": "SQS",
> "STATION": "STA",
> "STATN": "STA",
> "STN": "STA",
> "STR": "ST",
> "STRAV": "STRA",
> "STRAVE": "STRA",
> "STRAVEN": "STRA",
> "STRAVENUE": "STRA",
> "STRAVN": "STRA",
> "STREAM": "STRM",
> "STREET": "ST",
> "STREETS": "STS",
> "STREME": "STRM",
> "STRT": "ST",
> "STRVN": "STRA",
> "STRVNUE": "STRA",
> "SUMIT": "SMT",
> "SUMITT": "SMT",
> "SUMMIT": "SMT",
> "TERR": "TER",
> "TERRACE": "TER",
> "THROUGHWAY": "TRWY",
> "TPK": "TPKE",
> "TR": "TRL",
> "TRACE": "TRCE",
> "TRACES": "TRCE",
> "TRACK": "TRAK",
> "TRACKS": "TRAK",
> "TRAFFICWAY": "TRFY",
> "TRAIL": "TRL",
> "TRAILS": "TRL",
> "TRK": "TRAK",
> "TRKS": "TRAK",
> "TRLS": "TRL",
> "TRNPK": "TPKE",
> "TRPK": "TPKE",
> "TUNEL": "TUNL",
> "TUNLS": "TUNL",
> "TUNNEL": "TUNL",
> "TUNNELS": "TUNL",
> "TUNNL": "TUNL",
> "TURNPIKE": "TPKE",
> "TURNPK": "TPKE",
> "UNDERPASS": "UPAS",
> "UNION": "UN",
> "UNIONS": "UNS",
> "VALLEY": "VLY",
> "VALLEYS": "VLYS",
> "VALLY": "VLY",
> "VDCT": "VIA",
> "VIADCT": "VIA",
> "VIADUCT": "VIA",
> "VIEW": "VW",
> "VIEWS": "VWS",
> "VILL": "VLG",
> "VILLAG": "VLG",
> "VILLAGE": "VLG",
> "VILLAGES": "VLGS",
> "VILLE": "VL",
> "VILLG": "VLG",
> "VILLIAGE": "VLG",
> "VIST": "VIS",
> "VISTA": "VIS",
> "VLLY": "VLY",
> "VST": "VIS",
> "VSTA": "VIS",
> "WALKS": "WALK",
> "WELL": "WL",
> "WELLS": "WLS",
> "WY": "WAY",}
>
> <<<<<<<<<<<<<<<<<<<<<<<
>
> >>>>>>>>>>>>>>>>>> address.py
> import re
>
> from geocode.address_dicts import *
> from geocode.address_regex import *
> from geocode.models import GeocodeCache, GeocodeError
> from geocode import app_settings
> from geopy import geocoders
>
> # These are the possible order of pieces of an address. We are going
> to parse
> # in reverse order.
>
> class Address(object):
> """A class to handle the pieces of a parsed address"""
> def __init__(self, zipcode = '', state = '', city = '', unit = '',
> post_dir = '', street_type = '', street = '', pre_dir = '',
> fraction = '', number = ''):
> self.zipcode = ''
> self.state = ''
> self.city = ''
> self.unit = ''
> self.post_dir = ''
> self.street_type = ''
> self.street = ''
> self.pre_dir = ''
> self.fraction = ''
> self.number = ''
>
> def __str__(self):
> out = " ".join((self.number, self.fraction, self.pre_dir,
> self.street,
> self.street_type, self.post_dir, self.unit))
>
> out = re.sub(" +", " ", out.strip()) # convert multiple
> spaces into 1
> out2 = self.city + ", " + self.state
> if len(self.zipcode) > 5:
> out2 += " " + self.zipcode[:5]
> else:
> out2 += " " + self.zipcode
> out2 = re.sub(" +", " ", out2) # convert multiple spaces
> into 1
> out2 = re.sub(",$", "", out2.strip()) # remove trailing space
> and/or comma
> out2 = re.sub("^, ", "", out2) # remove leading comma space
>
> if out != '' and out2 != '':
> return out + ", " + out2
> else:
> return out + out2
>
> def is_zipcode(piece, addr_parts):
> """Is the passed string a zipcode
> Expects addr_parts to be an Address Object"""
> m = re.match("(?P<zipcode>%s)" % ZIP_LOOSE_REGEX, piece,
> re.IGNORECASE|re.VERBOSE)
> if m:
> addr_parts.zipcode = m.groupdict()['zipcode']
> return True
> else:
> return False
>
> def is_state(piece, addr_parts):
> """Is the passed string a state"""
> m = re.match("(?P<state>%s)" % STATE_REGEX, piece, re.IGNORECASE|
> re.VERBOSE)
> if m:
> addr_parts["state"] = m.groupdict()['state']
> return True
> else:
> return False
>
> def is_city(piece, addr_parts):
> """Is the passed string a city"""
> # If the previous piece was a state, then we can safely assume
> that this
> # piece is a city. Otherwise, skip it.
> if addr_parts.has_key('state') and addr_parts['state'] != '':
> addr_parts['city'] = piece
> return True
> else:
> return False
>
> def is_unit(piece, addr_parts):
> """Is the passed string a unit description"""
> m = re.match("(?P<unit>%s)" % UNIT_REGEX, piece, re.IGNORECASE|
> re.VERBOSE)
> if m:
> addr_parts["unit"] = m.groupdict()['unit']
> return True
> else:
> return False
>
> def is_post_dir(piece, addr_parts):
> """Is the passed string a direction"""
> m = re.match("(?P<post_dir>%s)" % DIRECTIONS_REGEX, piece,
> re.IGNORECASE|re.VERBOSE)
> if m:
> addr_parts["post_dir"] = m.groupdict()['post_dir']
> if addr_parts['post_dir'] in DIRECTIONS.keys():
> addr_parts['post_dir'] = DIRECTIONS[addr_parts['post_dir']]
> return True
> else:
> return False
>
> def is_pre_dir(piece, addr_parts):
> """Is the passed string a direction"""
> m = re.match("(?P<pre_dir>%s)" % DIRECTIONS_REGEX, piece,
> re.IGNORECASE|re.VERBOSE)
> if m:
> addr_parts["pre_dir"] = m.groupdict()['pre_dir']
> if addr_parts['pre_dir'] in DIRECTIONS.keys():
> addr_parts['pre_dir'] = DIRECTIONS[addr_parts['pre_dir']]
> return True
> else:
> return False
>
> def is_street_type(piece, addr_parts):
> """Is the passed string a street descriptor"""
> m = re.match("(?P<street_type>%s)" % STREET_TYPE_REGEX, piece,
> re.IGNORECASE|re.VERBOSE)
> if m:
> addr_parts["street_type"] = m.groupdict()['street_type']
> if addr_parts['street_type'] in STREET_TYPES.keys():
> addr_parts['street_type'] =
> STREET_TYPES[addr_parts['street_type']]
> return True
> else:
> return False
>
> def is_street(piece, addr_parts):
> """Is the passed string a street. If it gets this far, we must
> assume it is."""
> addr_parts['street'] = piece
> return True
>
> def is_fraction(piece, addr_parts):
> """Is the passed string a fraction"""
> m = re.match("(?P<fraction>%s)" % FRACTION_REGEX, piece,
> re.IGNORECASE|re.VERBOSE)
> if m:
> addr_parts["fraction"] = m.groupdict()['fraction']
> return True
> else:
> return False
>
> def is_number(piece, addr_parts):
> """Is the passed string a house number"""
> # If we are this far, we assume it is. Because there are strange
> numbers
> # such as W333 S405, we are going to added it to the end of the
> number in addr_parts
> if addr_parts['number'] != '':
> addr_parts['number'] += " "
> addr_parts['number'] += piece
> return True
>
> def is_address(piece, addr_parts):
> """Is the passed string an address line"""
> m =re.match(ADDRESS_REGEX, piece, re.IGNORECASE|re.VERBOSE)
> if m:
> match_dict = m.groupdict()
> for key, value in match_dict.items():
> addr_parts[key] = value or ''
> if addr_parts['pre_dir'] in DIRECTIONS.keys():
> addr_parts['pre_dir'] = DIRECTIONS[addr_parts['pre_dir']]
> if addr_parts['street_type'] in DIRECTIONS.keys():
> addr_parts['street_type'] =
> DIRECTIONS[addr_parts['street_type']]
> if addr_parts['post_dir'] in DIRECTIONS.keys():
> addr_parts['post_dir'] = DIRECTIONS[addr_parts['post_dir']]
>
> return True
> else:
> return False
>
> def is_citystatezip(piece, addr_parts):
> """
> Is the passed string a city, state zip.
> Expects addr_parts to be an Address object
> """
> m = re.match(PLACE_REGEX, piece, re.IGNORECASE|re.VERBOSE)
> if m and m.end() != 0:
> match_dict = m.groupdict()
> if 'city' in match_dict.keys():
> addr_parts.city = match_dict['city'] or ''
> else:
> addr_parts.city = ''
> if 'state' in match_dict.keys():
> addr_parts.state = match_dict['state'] or ''
> else:
> addr_parts.state = ''
> if 'state' in match_dict.keys():
> addr_parts.zipcode = match_dict['zip'] or ''
> else:
> addr_parts.zipcode = ''
>
> return True
> else:
> return False
>
> def addr_piece_test_generator():
> """A generator that will return the next test."""
>
> addr_piece_tests = [
> is_zipcode,
> is_state,
> is_city,
> is_unit,
> is_post_dir,
> is_street_type,
> is_street,
> is_pre_dir,
> is_fraction,
> is_number,
> ]
>
> for test in addr_piece_tests:
> yield test
>
> while True:
> yield addr_piece_tests[len(addr_piece_tests)] # Always yield
> the number function when all done
>
> def parse_location(address):
> """
> Given a location, convert it to uppercase and make sure it is in a
> standard format
> """
> # Convert commas to spaces, and remove periods
> address = address.upper().replace(".", "")
> addr = Address()
>
> addr_result = re.search(ADDRESS_REGEX + PLACE_REGEX + "\\W*$",
> address, re.IGNORECASE|re.VERBOSE)
>
> if addr_result:
> result_dict = addr_result.groupdict()
> # Normalize predir
> if result_dict["pre_dir"] in DIRECTIONS.keys():
> addr.pre_dir = DIRECTIONS[result_dict["pre_dir"]]
> else:
> addr.pre_dir = result_dict["pre_dir"] or ""
>
> # Normalize postdir
> addr.post_dir = result_dict["post_dir1"] or \
> result_dict["post_dir2"] or \
> result_dict["post_dir3"] or ""
> if addr.post_dir in DIRECTIONS.keys():
> addr.post_dir = DIRECTIONS[addr.post_dir]
>
> # Normalize street type
> addr.street_type = result_dict["street_type1"] or \
> result_dict["street_type2"] or \
> result_dict["street_type3"] or ""
> if addr.street_type in STREET_TYPES.keys():
> addr.street_type = STREET_TYPES[addr.street_type]
>
> # Get the street
> addr.street = result_dict["street1"] or \
> result_dict["street2"] or \
> result_dict["street3"] or \
> result_dict["street4"] or ""
> addr.number = result_dict["number"] or ""
>
> addr.city = result_dict["city"]
> addr.state = result_dict["state"]
> addr.zipcode = result_dict["zip"] or " "
> if len(addr.zipcode) > 5:
> addr.zipcode = result_dict["zip"][:5] # get rid of the
> plus 4, if there
>
> return addr
> else:
> if is_citystatezip(address, addr):
> return addr
> else:
> if is_zipcode(address, addr):
> return addr
>
> def normalize_location(location):
> """Determine if the location is a corner or an address"""
>
> if re.search(".+" + CORNER_REGEX + ".+", location, re.IGNORECASE|
> re.VERBOSE):
> return location.upper()
> else:
> addr = parse_location(location)
>
> return str(addr)
--~--~---------~--~----~------------~-------~--~----~
You received this message because you are subscribed to the Google Groups
"Django users" group.
To post to this group, send email to django-users@googlegroups.com
To unsubscribe from this group, send email to [EMAIL PROTECTED]
For more options, visit this group at
http://groups.google.com/group/django-users?hl=en
-~----------~----~----~----~------~----~------~--~---
