Skip to content

stricter numbered highway parsing #92

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
DeviousStoat merged 1 commit into from
Jul 3, 2026
Merged

stricter numbered highway parsing #92

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
132 changes: 69 additions & 63 deletions pyap/source_US/data.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -110,76 +110,82 @@ def str_list_to_upper_lower_regex(str_list: List[str]) -> str:
from_to="{1,5}",
)

STATE_ABBRS = (
"AL",
"AK",
"AZ",
"AR",
"CA",
"CO",
"CT",
"DE",
"FL",
"GA",
"HI",
"ID",
"IL",
"IN",
"IA",
"KS",
"KY",
"LA",
"ME",
"MD",
"MA",
r"MI(?:CH)?\.?",
"MN",
"MS",
"MO",
"MT",
"NE",
"NV",
"NH",
"NJ",
"NM",
r"NY|N\.Y\.",
"NC",
"ND",
"OH",
"OK",
"OR",
"PA",
"RI",
"SC",
"SD",
"TN",
"TX",
"UT",
"VT",
"VA",
"WA",
"WV",
"WI",
"WY",
)

# Some abbreviations are non-standard.
NON_STATE_ABBRS = (
"AS",
"GU",
"MP",
"PR",
"VI",
r"D\.?C\.?",
)


def states_abbrvs_regex() -> str:
# Some abbreviations are non-standard
_STATE_ABBRS = {
"AL",
"AK",
"AZ",
"AR",
"CA",
"CO",
"CT",
"DE",
"FL",
"GA",
"HI",
"ID",
"IL",
"IN",
"IA",
"KS",
"KY",
"LA",
"ME",
"MD",
"MA",
"MI(?:CH)?\.?",
"MN",
"MS",
"MO",
"MT",
"NE",
"NV",
"NH",
"NJ",
"NM",
"NY|N\.Y\.",
"NC",
"ND",
"OH",
"OK",
"OR",
"PA",
"RI",
"SC",
"SD",
"TN",
"TX",
"UT",
"VT",
"VA",
"WA",
"WV",
"WI",
"WY",
}
_NON_STATE_ABBRS = {
"AS",
"GU",
"MP",
"PR",
"VI",
"D\.?C\.?",
}
return (
r"(?:"
+ str_list_to_upper_lower_regex(list(_STATE_ABBRS | _NON_STATE_ABBRS))
+ str_list_to_upper_lower_regex(list(STATE_ABBRS + NON_STATE_ABBRS))
+ r")(?![A-Za-z])"
)


def state_highway_abbrvs_regex() -> str:
return r"(?:" + "|".join(STATE_ABBRS + NON_STATE_ABBRS) + r")(?![A-Za-z])"


"""
Regexp for matching street name.
In example below:
Expand Down Expand Up @@ -265,7 +271,7 @@ def states_abbrvs_regex() -> str:
# Some states name their state-maintained highways by the state abbreviation
# and the number.
numbered_state_highway = r"""(?:{states}\ \d{{1,4}}(?!\d))""".format(
states=states_abbrvs_regex()
states=state_highway_abbrvs_regex()
)


Expand Down
11 changes: 11 additions & 0 deletions tests/test_parser.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -34,6 +34,17 @@ def test_api_parse_single_street():
assert str(addresses[0].full_address) == "255 SOUTH STREET"


def test_api_parse_single_street_skips_mixed_case_state_highway_false_positive():
test_address = (
"Hilmar Cheese Company, Inc.\n"
"Plies: aR 8901 North Lander Avenue\n"
"ANY\n"
"2-CHEESE COMPANY No Hilmar, California 95324"
)
addresses = parse_single_street(test_address, country="US")
assert str(addresses[0].full_street) == "8901 North Lander Avenue"


def test_address_class_init():
addr = address.Address(
country_id="US",
Expand Down
2 changes: 2 additions & 0 deletions tests/test_parser_us.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -178,7 +178,9 @@ def test_street_name(input, expected):
("W. STATE ROAD 123", True),
("Alt 123", True),
("Alternate 123", True),
("NC 54", True),
# negative assertions
("nC 54", False),
],
)
def test_numbered_or_typeless_street_name(input, expected):
Expand Down
Loading