Wellfound-AI / core /address_processor.py
Zoey7Web's picture
Upload 26 files
67c9c05 verified
Raw
History Blame Contribute Delete
12.3 kB
"""
Address Processor - Smart address handling for location.apply and state.apply.
Handles:
- HQ address extraction with priority rules
- US address selection when multiple locations exist
- State abbreviation mapping
- Hiring concentration analysis
"""
import re
from typing import Optional, Tuple, Dict
# US State abbreviations and full names mapping
US_STATES = {
"alabama": "Alabama", "alaska": "Alaska", "arizona": "Arizona",
"arkansas": "Arkansas", "california": "California", "colorado": "Colorado",
"connecticut": "Connecticut", "delaware": "Delaware", "florida": "Florida",
"georgia": "Georgia", "hawaii": "Hawaii", "idaho": "Idaho",
"illinois": "Illinois", "indiana": "Indiana", "iowa": "Iowa",
"kansas": "Kansas", "kentucky": "Kentucky", "louisiana": "Louisiana",
"maine": "Maine", "maryland": "Maryland", "massachusetts": "Massachusetts",
"michigan": "Michigan", "minnesota": "Minnesota", "mississippi": "Mississippi",
"missouri": "Missouri", "montana": "Montana", "nebraska": "Nebraska",
"nevada": "Nevada", "new hampshire": "New Hampshire", "new jersey": "New Jersey",
"new mexico": "New Mexico", "new york": "New York",
"north carolina": "North Carolina", "north dakota": "North Dakota",
"ohio": "Ohio", "oklahoma": "Oklahoma", "oregon": "Oregon",
"pennsylvania": "Pennsylvania", "rhode island": "Rhode Island",
"south carolina": "South Carolina", "south dakota": "South Dakota",
"tennessee": "Tennessee", "texas": "Texas", "utah": "Utah",
"vermont": "Vermont", "virginia": "Virginia", "washington": "Washington",
"west virginia": "West Virginia", "wisconsin": "Wisconsin", "wyoming": "Wyoming",
"district of columbia": "District of Columbia", "washington dc": "District of Columbia",
"dc": "District of Columbia",
}
STATE_ABBREV = {
"AL": "Alabama", "AK": "Alaska", "AZ": "Arizona", "AR": "Arkansas",
"CA": "California", "CO": "Colorado", "CT": "Connecticut", "DE": "Delaware",
"FL": "Florida", "GA": "Georgia", "HI": "Hawaii", "ID": "Idaho",
"IL": "Illinois", "IN": "Indiana", "IA": "Iowa", "KS": "Kansas",
"KY": "Kentucky", "LA": "Louisiana", "ME": "Maine", "MD": "Maryland",
"MA": "Massachusetts", "MI": "Michigan", "MN": "Minnesota", "MS": "Mississippi",
"MO": "Missouri", "MT": "Montana", "NE": "Nebraska", "NV": "Nevada",
"NH": "New Hampshire", "NJ": "New Jersey", "NM": "New Mexico", "NY": "New York",
"NC": "North Carolina", "ND": "North Dakota", "OH": "Ohio", "OK": "Oklahoma",
"OR": "Oregon", "PA": "Pennsylvania", "RI": "Rhode Island",
"SC": "South Carolina", "SD": "South Dakota", "TN": "Tennessee",
"TX": "Texas", "UT": "Utah", "VT": "Vermont", "VA": "Virginia",
"WA": "Washington", "WV": "West Virginia", "WI": "Wisconsin", "WY": "Wyoming",
"DC": "District of Columbia",
}
# Reverse mapping
STATE_TO_ABBREV = {v: k for k, v in STATE_ABBREV.items()}
# Add lowercase versions
STATE_TO_ABBREV.update({v.lower(): k for k, v in STATE_ABBREV.items()})
class AddressProcessor:
"""Smart address processing for location.apply and state.apply columns."""
# Known non-US locations (country/city names)
NON_US_LOCATIONS = {
"india", "china", "japan", "korea", "singapore", "hong kong",
"canada", "uk", "united kingdom", "england", "germany", "france",
"australia", "brazil", "mexico", "spain", "italy", "netherlands",
"sweden", "switzerland", "ireland", "dubai", "uae", "bangalore",
"bengaluru", "mumbai", "delhi", "toronto", "vancouver", "london",
"berlin", "paris", "sydney", "tokyo", "seoul", "dublin", "amsterdam",
"stockholm", "zurich", "hyderabad", "pune", "chennai", "gurgaon",
"noida", "manila", "jakarta", "bangkok", "ho chi minh", "saigon",
"kuala lumpur", "taipei", "shanghai", "beijing", "shenzhen",
"warsaw", "lisbon", "madrid", "barcelona", "milan", "rome",
"vienna", "brussels", "oslo", "helsinki", "copenhagen",
"auckland", "wellington", "tel aviv", "istanbul", "moscow",
"cape town", "johannesburg", "nairobi", "lagos", "cairo",
"buenos aires", "sao paulo", "santiago", "bogota", "lima",
}
def determine_location_apply(
self,
wellfound_location: str,
ai_contact_data: Dict,
scraped_addresses: list,
) -> Tuple[Optional[str], Optional[str]]:
"""
Determine location.apply (city) and state.apply (state).
Priority:
1. US HQ address from AI contact extraction
2. US office from AI contact extraction
3. Hiring focus location from AI extraction
4. Wellfound location (if US)
5. First US address found on website
"""
location_apply = None
state_apply = None
# Priority 1: HQ address if it's in the US
hq_city = ai_contact_data.get("headquarters_city")
hq_state = ai_contact_data.get("headquarters_state")
hq_country = ai_contact_data.get("headquarters_country", "").lower()
if hq_city and self._is_us_location(hq_state, hq_country):
location_apply = self._normalize_city(hq_city)
state_apply = self._normalize_state(hq_state)
# Priority 2: US office
if not location_apply:
us_city = ai_contact_data.get("us_office_city")
us_state = ai_contact_data.get("us_office_state")
if us_city and us_state:
location_apply = self._normalize_city(us_city)
state_apply = self._normalize_state(us_state)
# Priority 3: Hiring focus location (if US)
if not location_apply:
hiring_loc = ai_contact_data.get("hiring_focus_location", "")
city, state = self._parse_location_string(hiring_loc)
if city and state and self._is_us_state(state):
location_apply = self._normalize_city(city)
state_apply = self._normalize_state(state)
# Priority 4: Parse wellfound location for US parts
if not location_apply and wellfound_location:
city, state = self._extract_us_from_wellfound_location(wellfound_location)
if city:
location_apply = self._normalize_city(city)
if state:
state_apply = self._normalize_state(state)
# Priority 5: First US address from scraping
if not location_apply and scraped_addresses:
for addr in scraped_addresses:
city, state = self._parse_address_string(addr)
if city and state and self._is_us_state(state):
location_apply = self._normalize_city(city)
state_apply = self._normalize_state(state)
break
return location_apply, state_apply
def _is_us_location(self, state: Optional[str], country: Optional[str]) -> bool:
"""Check if a location is in the US."""
if country and country.lower() in ("us", "usa", "united states", "united states of america"):
return True
if state and self._is_us_state(state):
return True
return False
def _is_us_state(self, state: str) -> bool:
"""Check if a string is a valid US state."""
s = state.strip().lower()
if s in US_STATES:
return True
if s.upper() in STATE_ABBREV:
return True
return False
def _normalize_state(self, state: str) -> Optional[str]:
"""Convert state to full name."""
s = state.strip()
if s.upper() in STATE_ABBREV:
return STATE_ABBREV[s.upper()]
s_lower = s.lower()
if s_lower in US_STATES:
return US_STATES[s_lower]
return s
def _normalize_city(self, city: str) -> str:
"""Normalize city name."""
city = city.strip().strip(",.;")
# Handle "City, State" format
if "," in city:
city = city.split(",")[0].strip()
return city
def _parse_location_string(self, location: str) -> Tuple[Optional[str], Optional[str]]:
"""Parse 'City, State' or 'City, State, Country' format."""
if not location:
return None, None
parts = [p.strip() for p in location.split(",")]
if len(parts) >= 2:
city = parts[0]
for part in parts[1:]:
if self._is_us_state(part):
return city, part
return city, None
return None, None
def _extract_us_from_wellfound_location(self, location: str) -> Tuple[Optional[str], Optional[str]]:
"""Extract US city/state from wellfound location string like 'San Francisco , New York'."""
if not location:
return None, None
parts = [p.strip() for p in location.split(",")]
for part in parts:
if self._is_us_state(part):
# This is a state - look for preceding city
idx = parts.index(part.strip())
if idx > 0:
city = parts[idx - 1]
# Verify city is not a non-US location
if city.lower() not in self.NON_US_LOCATIONS:
return city, part
# State name as city? (e.g., "New York")
if part.lower() in ("new york", "washington"):
return part, part
# Check if any part is a known US city
us_cities = {
"san francisco": "California", "new york": "New York",
"new york city": "New York", "los angeles": "California",
"chicago": "Illinois", "boston": "Massachusetts",
"seattle": "Washington", "austin": "Texas",
"denver": "Colorado", "portland": "Oregon",
"san diego": "California", "san jose": "California",
"palo alto": "California", "mountain view": "California",
"menlo park": "California", "redwood city": "California",
"sunnyvale": "California", "santa clara": "California",
"oakland": "California", "berkeley": "California",
"miami": "Florida", "atlanta": "Georgia",
"dallas": "Texas", "houston": "Texas",
"philadelphia": "Pennsylvania", "phoenix": "Arizona",
"minneapolis": "Minnesota", "detroit": "Michigan",
"salt lake city": "Utah", "raleigh": "North Carolina",
"charlotte": "North Carolina", "nashville": "Tennessee",
"boulder": "Colorado", "cambridge": "Massachusetts",
"pittsburgh": "Pennsylvania", "ann arbor": "Michigan",
"madison": "Wisconsin", "irvine": "California",
"santa monica": "California", "cupertino": "California",
"bellevue": "Washington", "arlington": "Virginia",
"reston": "Virginia", "mclean": "Virginia",
"bethesda": "Maryland", "columbia": "Maryland",
"st louis": "Missouri", "kansas city": "Missouri",
"indianapolis": "Indiana", "columbus": "Ohio",
"cleveland": "Ohio", "cincinnati": "Ohio",
"tampa": "Florida", "orlando": "Florida",
"durham": "North Carolina", "chapel hill": "North Carolina",
"remote": None,
}
for part in parts:
part_lower = part.strip().lower()
if part_lower in us_cities and us_cities[part_lower]:
return part.strip(), us_cities[part_lower]
return None, None
def _parse_address_string(self, addr: str) -> Tuple[Optional[str], Optional[str]]:
"""Parse a US address string into city and state."""
if not addr:
return None, None
# Match "City, State ZIP" pattern
match = re.search(
r'([A-Z][a-z]+(?:\s[A-Z][a-z]+)*),\s*([A-Z]{2})\s*\d{5}',
addr
)
if match:
return match.group(1), match.group(2)
# Match "City, State" pattern
match = re.search(
r'([A-Z][a-z]+(?:\s[A-Z][a-z]+)*),\s*([A-Z][a-z]+(?:\s[A-Z][a-z]+)*)',
addr
)
if match:
city = match.group(1)
state = match.group(2)
if self._is_us_state(state):
return city, state
return None, None