fix matching for AOR and MIAMI address

Signed-off-by: John Seekins <[email protected]>

Author: johnseekins

enrichers/openstreetmap.py

@@ -65,8 +65,6 @@ def search(self) -> dict:
                     logger.debug(" OSM search error for '%s': %s", facility_name, e)
                     self.resp_info["search_query_steps"].append(f"(Failed -> {e})")  # type: ignore [attr-defined]
                     continue
-                if data:
-                    return self.resp_info
         # when the URL result is a "way" this is usually correct.
         # checks top five results.
         match_terms = ["prison", "detention", "correctional", "jail"]
@@ -86,6 +84,8 @@ def search(self) -> dict:
                     self.resp_info["details"]["longitude"] = lon  # type: ignore [index]
                     self.resp_info["title"] = title
                     return self.resp_info
+        if not data:
+            return self.resp_info
         # fallback to first result
         first_result = data[0]
         logger.debug("Address searches didn't directly find anything, just using the first result: %s", first_result)

field_offices.py

@@ -171,7 +171,7 @@ def _extract_single_office(self, element: BeautifulSoup, page_url: str) -> dict:
             office["email"] = email[0]["href"].split(":", 1)[1]
         detail_txt = details.text  # type: ignore [union-attr]
         logger.debug("Detail text: %s", detail_txt)
-        aor_match = re.match(r"Area of Responsibility:(.+)\n?Email", detail_txt)
+        aor_match = re.search(r"Area of Responsibility:(.+)Email", detail_txt)
         if aor_match:
             office["aor"] = aor_match.group(1).strip().replace("\xa0", " ")
 

scraper.py

@@ -118,7 +118,6 @@ def _clean_street(self, street: str, locality: str = "") -> Tuple[str, bool]:
             {"match": "351 Elliott Street", "replace": "351 ELLIOTT ST", "locality": "Honolulu"},
             {"match": "1 Success Loop Rd", "replace": "1 SUCCESS LOOP DR", "locality": "Berlin"},
             {"match": "700 Arch Street", "replace": "700 ARCH ST", "locality": "Philadelphia"},
-            {"match": "33 NE 4th Street", "replace": "33 NE 4 STREET", "locality": "Miami"},
             {"match": "1300 Metropolitan", "replace": "1300 METROPOLITAN AVE", "locality": "Leavenworth"},
             {"match": "601 McDonough Blvd SE", "replace": "601 MCDONOUGH BOULEVARD SE", "locality": "Atlanta"},
             {"match": "1705 E Hanna Rd", "replace": "1705 EAST HANNA RD", "locality": "Eloy"},
@@ -155,7 +154,8 @@ def _clean_street(self, street: str, locality: str = "") -> Tuple[str, bool]:
             {"match": "9998 S. Highway 98", "replace": "9998 SOUTH HIGHWAY 83", "locality": "Laredo"},
             # a unique one, 'cause the PHONE NUMBER IS IN THE ADDRESS?!
             {"match": "911 PARR BLVD 775 328 3308", "replace": "911 E Parr Blvd", "locality": "RENO"},
-            # fix a few shockingly bad addresses in spreadsheet
+            # fix a few bad addresses in spreadsheet
+            {"match": "33 NE 4 STREET", "replace": "33 NE 4th Street", "locality": "MIAMI"},
             {"match": "DEPARTMENT OF CORRECTIONS 1618 ASH STREET", "replace": "1618 Ash Street", "locality": "ERIE"},
             {"match": "203 ASPINAL AVE. PO BOX 3236", "replace": "203 Aspinall Avenue", "locality": "HAGATNA"},
             {