python-openpublictransport 0.1.7__tar.gz → 0.1.9__tar.gz

{python_openpublictransport-0.1.7 → python_openpublictransport-0.1.9}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: python-openpublictransport
-Version: 0.1.7
+Version: 0.1.9
 Summary: Python library for public transport APIs (EFA, OTP2, TRIAS, FPTF, HAFAS, GTFS-RT)
 License: MIT
 Requires-Python: >=3.11

{python_openpublictransport-0.1.7 → python_openpublictransport-0.1.9}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "python-openpublictransport"
-version = "0.1.7"
+version = "0.1.9"
 description = "Python library for public transport APIs (EFA, OTP2, TRIAS, FPTF, HAFAS, GTFS-RT)"
 readme = "README.md"
 license = { text = "MIT" }

{python_openpublictransport-0.1.7 → python_openpublictransport-0.1.9}/src/openpublictransport/providers/national_rail.py

@@ -46,10 +46,17 @@ _SOAP_TEMPLATE = """<?xml version="1.0" encoding="UTF-8"?>
 
 
 def _strip_namespaces(xml_string: str) -> str:
-    """Remove XML namespace prefixes and declarations for simpler parsing."""
+    """Remove XML namespace prefixes and declarations for simpler parsing.
+
+    Real OpenLDBWS responses use namespace prefixes that contain digits
+    (``lt4:``, ``lt5:``, ``lt7:``, ``lt8:`` …). The prefix pattern must
+    therefore allow digits — matching only ``[a-zA-Z]+`` leaves those tags
+    prefixed after their xmlns declarations have been stripped, producing an
+    "unbound prefix" XML parse error and an empty departure board.
+    """
     xml_string = re.sub(r' xmlns[^=]*="[^"]*"', "", xml_string)
-    xml_string = re.sub(r"<([a-zA-Z]+):", "<", xml_string)
-    xml_string = re.sub(r"</([a-zA-Z]+):", "</", xml_string)
+    xml_string = re.sub(r"<([A-Za-z][\w.\-]*):", "<", xml_string)
+    xml_string = re.sub(r"</([A-Za-z][\w.\-]*):", "</", xml_string)
     return xml_string
 
 
@@ -274,10 +281,22 @@ class NationalRailProvider(BaseProvider):
         )
 
     async def search_stops(self, search_term: str) -> List[Dict[str, Any]]:
-        """Find UK railway stations with CRS codes via Overpass API (OSM)."""
-        escaped = re.sub(r"[.*+?^${}()|[\]\\]", r"\\\g<0>", search_term)
-
-        query = f"""[out:json][timeout:15];
+        """Find UK railway stations with CRS codes via Overpass API (OSM).
+
+        A search term that looks like a 3-letter CRS code (e.g. "WIN", "RDG")
+        is matched directly against the ``ref:crs`` tag; anything else is
+        matched against the station name(s).
+        """
+        term = search_term.strip()
+
+        if re.fullmatch(r"[A-Za-z]{3}", term):
+            # Direct CRS code lookup (ref:crs is stored uppercase in OSM)
+            query = f"""[out:json][timeout:15];
+node["railway"="station"]["ref:crs"="{term.upper()}"]({_UK_BBOX});
+out 10;"""
+        else:
+            escaped = re.sub(r"[.*+?^${}()|[\]\\]", r"\\\g<0>", term)
+            query = f"""[out:json][timeout:15];
 (
   node["railway"="station"]["ref:crs"]["name"~"{escaped}",i]({_UK_BBOX});
   node["railway"="station"]["ref:crs"]["official_name"~"{escaped}",i]({_UK_BBOX});

{python_openpublictransport-0.1.7 → python_openpublictransport-0.1.9}/src/python_openpublictransport.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: python-openpublictransport
-Version: 0.1.7
+Version: 0.1.9
 Summary: Python library for public transport APIs (EFA, OTP2, TRIAS, FPTF, HAFAS, GTFS-RT)
 License: MIT
 Requires-Python: >=3.11

{python_openpublictransport-0.1.7 → python_openpublictransport-0.1.9}/src/python_openpublictransport.egg-info/SOURCES.txt

@@ -45,4 +45,6 @@ src/python_openpublictransport.egg-info/PKG-INFO
 src/python_openpublictransport.egg-info/SOURCES.txt
 src/python_openpublictransport.egg-info/dependency_links.txt
 src/python_openpublictransport.egg-info/requires.txt
-src/python_openpublictransport.egg-info/top_level.txt
+src/python_openpublictransport.egg-info/top_level.txt
+tests/test_national_rail.py
+tests/test_national_rail_parse.py

python_openpublictransport-0.1.9/tests/test_national_rail.py

@@ -0,0 +1,91 @@
+"""Tests for the National Rail (UK) provider stop search.
+
+Focus: a 3-letter CRS code (e.g. "WIN") must be looked up directly against the
+OSM ``ref:crs`` tag, while a longer term is matched against station names.
+Regression test for https://github.com/NerdySoftPaw/openpublictransport/issues/39
+"""
+
+import pytest
+
+from openpublictransport.providers.national_rail import NationalRailProvider
+
+
+class _FakeResponse:
+    def __init__(self, payload):
+        self._payload = payload
+        self.status = 200
+
+    async def __aenter__(self):
+        return self
+
+    async def __aexit__(self, *exc):
+        return False
+
+    async def json(self, content_type=None):
+        return self._payload
+
+
+class _FakeSession:
+    """Records the Overpass query and returns a canned payload."""
+
+    def __init__(self, payload):
+        self._payload = payload
+        self.last_query = None
+
+    def post(self, url, data=None, headers=None, timeout=None):
+        # The Overpass query is sent as form data under the "data" key.
+        self.last_query = (data or {}).get("data", "")
+        return _FakeResponse(self._payload)
+
+
+_PAYLOAD = {
+    "elements": [
+        {
+            "type": "node",
+            "tags": {
+                "railway": "station",
+                "ref:crs": "WIN",
+                "name": "Winchester",
+                "operator": "South Western Railway",
+            },
+        }
+    ]
+}
+
+
+async def _search(term):
+    session = _FakeSession(_PAYLOAD)
+    provider = NationalRailProvider(session)
+    results = await provider.search_stops(term)
+    return results, session.last_query
+
+
+async def test_crs_code_search_queries_ref_crs():
+    """A 3-letter code searches ref:crs directly, not the name."""
+    results, query = await _search("WIN")
+
+    assert '["ref:crs"="WIN"]' in query
+    assert '"name"~' not in query
+
+    assert results == [
+        {
+            "id": "WIN",
+            "name": "Winchester",
+            "place": "South Western Railway",
+            "area_type": "stop",
+        }
+    ]
+
+
+async def test_lowercase_code_is_uppercased():
+    """CRS codes are case-insensitive and normalised to uppercase."""
+    _, query = await _search("win")
+    assert '["ref:crs"="WIN"]' in query
+
+
+async def test_name_search_queries_name_tags():
+    """A longer term matches the name tags, not an exact CRS code."""
+    _, query = await _search("Winchester")
+
+    assert '"name"~"Winchester"' in query
+    assert '["ref:crs"="' not in query

python_openpublictransport-0.1.9/tests/test_national_rail_parse.py

@@ -0,0 +1,92 @@
+"""Tests for National Rail (UK) OpenLDBWS response parsing.
+
+Regression test for the departure board coming back empty ("Invalid or empty
+API response") for every user: real OpenLDBWS responses use namespace prefixes
+containing digits (`lt4:`, `lt5:`, `lt7:` …), which the namespace-stripping
+regex did not handle, causing an "unbound prefix" XML parse error.
+See https://github.com/NerdySoftPaw/openpublictransport/issues/39
+"""
+
+from datetime import datetime
+from xml.etree import ElementTree as ET
+from zoneinfo import ZoneInfo
+
+import openpublictransport.providers.national_rail as nr
+
+# A realistic OpenLDBWS GetDepartureBoardResponse: digit-bearing prefixes
+# (lt4/lt5/lt7) and their xmlns declarations, exactly as the live service emits.
+SAMPLE = """<?xml version="1.0" encoding="utf-8"?>
+<soap:Envelope xmlns:soap="http://schemas.xmlsoap.org/soap/envelope/">
+ <soap:Body>
+  <GetDepartureBoardResponse xmlns="http://thalesgroup.com/RTTI/2017-10-01/ldb/">
+   <GetStationBoardResult xmlns:lt="http://thalesgroup.com/RTTI/2012-01-13/ldb/types" xmlns:lt4="http://thalesgroup.com/RTTI/2015-11-27/ldb/types" xmlns:lt5="http://thalesgroup.com/RTTI/2016-02-16/ldb/types" xmlns:lt7="http://thalesgroup.com/RTTI/2017-02-02/ldb/types">
+    <lt4:locationName>Winchester</lt4:locationName>
+    <lt4:crs>WIN</lt4:crs>
+    <lt7:trainServices>
+     <lt7:service>
+      <lt4:std>18:05</lt4:std>
+      <lt4:etd>On time</lt4:etd>
+      <lt4:platform>2</lt4:platform>
+      <lt4:operator>South Western Railway</lt4:operator>
+      <lt4:operatorCode>SW</lt4:operatorCode>
+      <lt5:destination>
+       <lt4:location>
+        <lt4:locationName>London Waterloo</lt4:locationName>
+        <lt4:crs>WAT</lt4:crs>
+       </lt4:location>
+      </lt5:destination>
+     </lt7:service>
+     <lt7:service>
+      <lt4:std>18:20</lt4:std>
+      <lt4:etd>18:27</lt4:etd>
+      <lt4:operator>Great Western Railway</lt4:operator>
+      <lt4:operatorCode>GW</lt4:operatorCode>
+      <lt5:destination>
+       <lt4:location>
+        <lt4:locationName>Southampton Central</lt4:locationName>
+        <lt4:crs>SOU</lt4:crs>
+       </lt4:location>
+      </lt5:destination>
+     </lt7:service>
+    </lt7:trainServices>
+   </GetStationBoardResult>
+  </GetDepartureBoardResponse>
+ </soap:Body>
+</soap:Envelope>"""
+
+
+def test_strip_namespaces_handles_digit_prefixes():
+    """Digit-bearing prefixes must be stripped so the XML parses."""
+    stripped = nr._strip_namespaces(SAMPLE)
+    # No prefixed tags and no dangling xmlns declarations should remain.
+    assert "lt4:" not in stripped
+    assert "lt7:" not in stripped
+    assert "xmlns" not in stripped
+    # Must now be parseable (previously raised "unbound prefix").
+    root = ET.fromstring(stripped)
+    assert len(root.findall(".//service")) == 2
+
+
+def test_parses_services_into_departures():
+    """The full parse path yields the expected departures."""
+    root = ET.fromstring(nr._strip_namespaces(SAMPLE))
+    provider = nr.NationalRailProvider(session=None)
+    tz = ZoneInfo("Europe/London")
+    now = datetime(2026, 7, 2, 18, 0, tzinfo=tz)
+
+    deps = []
+    for svc in root.findall(".//service"):
+        d = provider._service_to_dict(svc, now.date(), tz, now)
+        assert d is not None
+        deps.append(provider.parse_departure(d, tz, now))
+
+    assert deps[0].destination == "London Waterloo"
+    assert deps[0].planned_time == "18:05"
+    assert deps[0].platform == "2"
+    assert deps[0].line == "SW"
+    assert deps[0].delay == 0
+
+    # Second service is estimated 7 minutes late (18:05 std -> 18:27 etd on 18:20).
+    assert deps[1].destination == "Southampton Central"
+    assert deps[1].delay == 7
+    assert deps[1].is_realtime is True