Giant refactor to rebrand "SIG" as "Activity" anywhere that doesn't touch API or config file (which is to be addressed in a future breaking change). #147

providers/activityrefdata/activity_ref_data_provider.py

@@ -0,0 +1,53 @@
+import logging
+from datetime import datetime
+from threading import Event
+
+import pytz
+
+from core.data_store import DATA_STORE
+
+logger = logging.getLogger(__name__)
+
+
+class ActivityRefDataProvider:
+    """Generic activity reference data provider class. Subclasses of this query the individual URLs or files for
+    data."""
+
+    def __init__(self, sig_name, provider_config):
+        """Constructor. Note the parameter and attribute are still named "sig_name" for consistency with the API's
+        "sig" field name."""
+
+        self.sig_name = sig_name
+        self.enabled = provider_config["enabled"]
+        self.last_update_time = datetime.min.replace(tzinfo=pytz.UTC)
+        self.status = "Not Started" if self.enabled else "Disabled"
+        self.reference_count = 0
+        self._stop_event = Event()
+
+    def start(self):
+        """Start the provider. This should return immediately after spawning threads to access the remote resources"""
+
+        raise NotImplementedError("Subclasses must implement this method")
+
+    def stop(self):
+        """Stop any threads and prepare for application shutdown. Subclasses should implement this method and call
+        super()."""
+
+        self._stop_event.set()
+
+    def _add_data(self, new_data):
+        """Add all the provided reference data objects to the data store."""
+
+        # with transact() batches all writes together to save making thousands of individual sqlite writes
+        with DATA_STORE.activity_refs.transact():
+            for d in new_data:
+                DATA_STORE.activity_refs.set(f"{self.sig_name}:{d.id}", d)
+
+                # For the big data sources, loading will take a few minutes. If we want to shut down the software neatly
+                # within the first few minutes of startup, we need a way to abort this expensive process of filling up the
+                # disk cache.
+                if self._stop_event.is_set():
+                    break
+
+        self.reference_count = len(new_data)
+        logger.info(f"Loaded {self.reference_count} references for {self.sig_name} into the data store.")

providers/activityrefdata/arlhs.py

@@ -0,0 +1,48 @@
+import csv
+from time import sleep
+
+from core.enums import ActivityRefType
+from data.activity_ref import ActivityRef
+from providers.activityrefdata.file_download_activity_ref_data_provider import (
+    FileDownloadActivityRefDataProvider,
+)
+
+
+class ARLHS(FileDownloadActivityRefDataProvider):
+    """Activity ref data provider for Amateur Radio Light House Society"""
+
+    POLL_INTERVAL_DAYS = 30
+    ACTIVITY = "ARLHS"
+    DATA_URL = "https://www.gma.rocks/download/lighthouse.csv"
+
+    def __init__(self, provider_config):
+        super().__init__(self.ACTIVITY, provider_config, self.DATA_URL, self.POLL_INTERVAL_DAYS)
+
+    def _http_response_to_data(self, http_response):
+        new_data = []
+        for row in csv.DictReader(http_response.content.decode("utf-8-sig").splitlines()[1:]):
+            if "ARLHS" in row and row["ARLHS"] != "":
+                ref_id = row["ARLHS"]
+                new_data.append(
+                    ActivityRef(
+                        sig=self.ACTIVITY,
+                        id=ref_id,
+                        name=row.get("Name", None),
+                        ref_type=ActivityRefType.LIGHTHOUSE,
+                        url=f"https://www.cqgma.org/zinfo.php?ref={ref_id}",
+                        latitude=float(row["Latitude"]) if "Latitude" in row and row["Latitude"] != "" else None,
+                        longitude=float(row["Longitude"]) if "Longitude" in row and row["Longitude"] != "" else None,
+                        grid=row["Maidenhead Locator"],
+                    )
+                )
+
+            # Bail out if a stop has been requested, i.e. the program is shutting down - no need to parse the rest of
+            # the data in this case
+            if self._stop_event.is_set():
+                break
+
+            # Very short pause. This will extend the time to handle activity refs by a few seconds but will ensure some time
+            # is available for other threads e.g. the web server.
+            sleep(0.001)
+
+        return new_data

providers/activityrefdata/cota.py

@@ -0,0 +1,52 @@
+from time import sleep
+
+from pyhamtools.locator import latlong_to_locator
+
+from core.enums import ActivityRefType
+from data.activity_ref import ActivityRef
+from providers.activityrefdata.file_download_activity_ref_data_provider import FileDownloadActivityRefDataProvider
+
+
+class COTA(FileDownloadActivityRefDataProvider):
+    """Activity ref data provider for Castles on the Air"""
+
+    POLL_INTERVAL_DAYS = 30
+    ACTIVITY = "COTA"
+    DATA_URL = "https://www.cotagroup.org/cotagroup/map/data/castles-all-7d90ee2a5e1175e5dece1bbf9dc87504.json"
+
+    def __init__(self, provider_config):
+        super().__init__(self.ACTIVITY, provider_config, self.DATA_URL, self.POLL_INTERVAL_DAYS)
+
+    def _http_response_to_data(self, http_response):
+        new_data = []
+        data = http_response.json()
+        if isinstance(data, list):
+            for ref in data[2]:
+                ref_id = ref[3]
+                name = ref[4]
+                lat = float(ref[0])
+                lon = float(ref[1])
+                grid = latlong_to_locator(lat, lon)
+
+                new_data.append(
+                    ActivityRef(
+                        sig=self.ACTIVITY,
+                        id=ref_id,
+                        name=name,
+                        ref_type=ActivityRefType.CASTLE,
+                        grid=grid,
+                        latitude=lat,
+                        longitude=lon,
+                    )
+                )
+
+                # Bail out if a stop has been requested, i.e. the program is shutting down - no need to parse the rest
+                # of the data in this case
+                if self._stop_event.is_set():
+                    break
+
+                # Very short pause. This will extend the time to handle activity refs by a few seconds but will ensure some time
+                # is available for other threads e.g. the web server.
+                sleep(0.001)
+
+        return new_data

providers/activityrefdata/dce.py

@@ -0,0 +1,42 @@
+import io
+from time import sleep
+
+import pandas as pd
+
+from core.enums import ActivityRefType
+from data.activity_ref import ActivityRef
+from providers.activityrefdata.file_download_activity_ref_data_provider import FileDownloadActivityRefDataProvider
+
+
+class DCE(FileDownloadActivityRefDataProvider):
+    """Activity ref data provider for Diploma Castillos de España"""
+
+    POLL_INTERVAL_DAYS = 365
+    ACTIVITY = "DCE"
+    DATA_URL = "https://www.acracb.org/dce/descargas/General/directorio_referencias_dce.xls"
+
+    def __init__(self, provider_config):
+        super().__init__(self.ACTIVITY, provider_config, self.DATA_URL, self.POLL_INTERVAL_DAYS)
+
+    def _http_response_to_data(self, http_response):
+        new_data = []
+
+        file_stream = io.BytesIO(http_response.content)
+        df = pd.read_excel(file_stream, engine="xlrd", header=None)
+
+        for index, row in df.iterrows():
+            if row.iloc[0] and row.iloc[2]:
+                new_data.append(
+                    ActivityRef(sig=self.ACTIVITY, id=row.iloc[0].strip(), name=row.iloc[2].strip(), ref_type=ActivityRefType.CASTLE)
+                )
+
+            # Bail out if a stop has been requested, i.e. the program is shutting down - no need to parse the rest of
+            # the data in this case
+            if self._stop_event.is_set():
+                break
+
+            # Very short pause. This will extend the time to handle activity refs by a few seconds but will ensure some time
+            # is available for other threads e.g. the web server.
+            sleep(0.001)
+
+        return new_data

providers/activityrefdata/defe.py

@@ -0,0 +1,46 @@
+import io
+from time import sleep
+
+import pandas as pd
+
+from core.enums import ActivityRefType
+from data.activity_ref import ActivityRef
+from providers.activityrefdata.file_download_activity_ref_data_provider import FileDownloadActivityRefDataProvider
+
+
+class DEFE(FileDownloadActivityRefDataProvider):
+    """Activity ref data provider for Diploma Estationes de Ferrocarril de España"""
+
+    POLL_INTERVAL_DAYS = 365
+    ACTIVITY = "DEFE"
+    DATA_URL = "https://www.acracb.org/defe/descargas/General/directorio_referencias_defe.xls"
+
+    def __init__(self, provider_config):
+        super().__init__(self.ACTIVITY, provider_config, self.DATA_URL, self.POLL_INTERVAL_DAYS)
+
+    def _http_response_to_data(self, http_response):
+        new_data = []
+
+        file_stream = io.BytesIO(http_response.content)
+        df = pd.read_excel(file_stream, engine="xlrd", header=None)
+
+        for index, row in df.iterrows():
+            # Skip the header row
+            if str(row.iloc[0]) == "NºDEFE":
+                continue
+
+            if row.iloc[0] and row.iloc[1]:
+                new_data.append(
+                    ActivityRef(sig=self.ACTIVITY, id=row.iloc[0].strip(), name=row.iloc[1].strip(), ref_type=ActivityRefType.BUILDING)
+                )
+
+            # Bail out if a stop has been requested, i.e. the program is shutting down - no need to parse the rest of
+            # the data in this case
+            if self._stop_event.is_set():
+                break
+
+            # Very short pause. This will extend the time to handle activity refs by a few seconds but will ensure some time
+            # is available for other threads e.g. the web server.
+            sleep(0.001)
+
+        return new_data

providers/activityrefdata/dme.py

@@ -0,0 +1,63 @@
+import csv
+from time import sleep
+
+from pyhamtools.locator import latlong_to_locator
+
+from core.enums import ActivityRefType
+from data.activity_ref import ActivityRef
+from providers.activityrefdata.local_file_activity_ref_data_provider import (
+    LocalFileActivityRefDataProvider,
+)
+
+
+class DME(LocalFileActivityRefDataProvider):
+    """Activity ref data provider for Diploma Municipios de Espana"""
+
+    ACTIVITY = "DME"
+    PATH = "datafiles/MUNICIPIOS.csv"
+
+    def __init__(self, provider_config):
+        super().__init__(self.ACTIVITY, provider_config, self.PATH)
+
+    def _file_to_data(self, path):
+        new_data = []
+        with open(path, encoding="latin-1") as _f:
+            for row in csv.DictReader(_f, delimiter=";"):
+                # Store reference IDs with the "DME-" prefix rather than just the number. This will prevent Spothole
+                # from agressively thinking every number in a spot comment is DME after it's seen "DME" once. The only
+                # numbers that count are straight after "DME " or "DME-". The dash versus space is normalised in
+                # activity_lookup_helper.py.
+                ref_id = "DME-" + row["COD_INE"][:5]
+                latitude = (
+                    float(row["LATITUD_ETRS89_REGCAN95"].replace(",", "."))
+                    if row.get("LATITUD_ETRS89_REGCAN95")
+                    else None
+                )
+                longitude = (
+                    float(row["LONGITUD_ETRS89_REGCAN95"].replace(",", "."))
+                    if row.get("LONGITUD_ETRS89_REGCAN95")
+                    else None
+                )
+
+                ref = ActivityRef(
+                    sig=self.ACTIVITY,
+                    id=ref_id,
+                    ref_type=ActivityRefType.TOWN,
+                    name=f"{row['NOMBRE_ACTUAL']}, {row['PROVINCIA']}",
+                    latitude=latitude,
+                    longitude=longitude,
+                )
+                if latitude and longitude:
+                    ref.grid = latlong_to_locator(latitude, longitude, 6)
+                new_data.append(ref)
+
+                # Bail out if a stop has been requested, i.e. the program is shutting down - no need to parse the rest
+                # of the data in this case
+                if self._stop_event.is_set():
+                    break
+
+                # Very short pause. This will extend the time to handle activity refs by a few seconds but will ensure some time
+                # is available for other threads e.g. the web server.
+                sleep(0.001)
+
+        return new_data

providers/activityrefdata/dmue.py

@@ -0,0 +1,37 @@
+import csv
+from time import sleep
+
+from core.enums import ActivityRefType
+from data.activity_ref import ActivityRef
+from providers.activityrefdata.file_download_activity_ref_data_provider import FileDownloadActivityRefDataProvider
+
+
+class DMUE(FileDownloadActivityRefDataProvider):
+    """Activity ref data provider for Diploma Museos de España"""
+
+    POLL_INTERVAL_DAYS = 365
+    ACTIVITY = "DMUE"
+    DATA_URL = "https://dmue.radiogalena.es/nom_dmue.csv"
+
+    def __init__(self, provider_config):
+        super().__init__(self.ACTIVITY, provider_config, self.DATA_URL, self.POLL_INTERVAL_DAYS)
+
+    def _http_response_to_data(self, http_response):
+        new_data = []
+
+        for row in csv.reader(http_response.content.decode("utf-8-sig").splitlines(), delimiter=";"):
+            if len(row) > 1 and row[0] and row[1]:
+                new_data.append(
+                    ActivityRef(sig=self.ACTIVITY, id=row[0].strip(), name=row[1].strip(), ref_type=ActivityRefType.BUILDING)
+                )
+
+            # Bail out if a stop has been requested, i.e. the program is shutting down - no need to parse the rest of
+            # the data in this case
+            if self._stop_event.is_set():
+                break
+
+            # Very short pause. This will extend the time to handle activity refs by a few seconds but will ensure some time
+            # is available for other threads e.g. the web server.
+            sleep(0.001)
+
+        return new_data

providers/activityrefdata/dmve.py

@@ -0,0 +1,50 @@
+import io
+from time import sleep
+
+import pandas as pd
+
+from core.enums import ActivityRefType
+from data.activity_ref import ActivityRef
+from providers.activityrefdata.file_download_activity_ref_data_provider import FileDownloadActivityRefDataProvider
+
+
+class DMVE(FileDownloadActivityRefDataProvider):
+    """Activity ref data provider for Diploma Monumentos y Vestigios de España"""
+
+    POLL_INTERVAL_DAYS = 365
+    ACTIVITY = "DMVE"
+    DATA_URL = "https://www.acracb.org/dmve/descargas/General/directorio_referencias_dmve.xls"
+
+    def __init__(self, provider_config):
+        super().__init__(self.ACTIVITY, provider_config, self.DATA_URL, self.POLL_INTERVAL_DAYS)
+
+    def _http_response_to_data(self, http_response):
+        new_data = []
+
+        file_stream = io.BytesIO(http_response.content)
+        # Despide the .xls extension this is actually an xlsx file, so we need openpyxl not xlrd
+        df = pd.read_excel(file_stream, engine="openpyxl", header=None)
+
+        for index, row in df.iterrows():
+            ref = row.iloc[0]
+            name = row.iloc[1]
+
+            # Skip the header row and blank rows
+            if str(ref) == "REF.":
+                continue
+            if pd.isna(ref) or pd.isna(name):
+                continue
+
+            if ref and name:
+                new_data.append(ActivityRef(sig=self.ACTIVITY, id=ref.strip(), name=name.strip(), ref_type=ActivityRefType.BUILDING))
+
+            # Bail out if a stop has been requested, i.e. the program is shutting down - no need to parse the rest of
+            # the data in this case
+            if self._stop_event.is_set():
+                break
+
+            # Very short pause. This will extend the time to handle activity refs by a few seconds but will ensure some time
+            # is available for other threads e.g. the web server.
+            sleep(0.001)
+
+        return new_data

providers/activityrefdata/dtmba.py

@@ -0,0 +1,35 @@
+from time import sleep
+
+from core.enums import ActivityRefType
+from data.activity_ref import ActivityRef
+from providers.activityrefdata.file_download_activity_ref_data_provider import FileDownloadActivityRefDataProvider
+
+
+class DTMBA(FileDownloadActivityRefDataProvider):
+    """Activity ref data provider for Diploma Teatri Musei Belle Arti"""
+
+    POLL_INTERVAL_DAYS = 30
+    ACTIVITY = "DTMBA"
+    DATA_URL = "https://www.iu1fig.com/share/iz0eik/dtmba/export.php"
+
+    def __init__(self, provider_config):
+        super().__init__(self.ACTIVITY, provider_config, self.DATA_URL, self.POLL_INTERVAL_DAYS)
+
+    def _http_response_to_data(self, http_response):
+        new_data = []
+        for row in http_response.content.decode("utf-8-sig").splitlines():
+            split = row.split(";")
+            ref_id = split[0]
+            ref_name = split[1]
+            new_data.append(ActivityRef(sig=self.ACTIVITY, id=ref_id, name=ref_name, ref_type=ActivityRefType.BUILDING))
+
+            # Bail out if a stop has been requested, i.e. the program is shutting down - no need to parse the rest of
+            # the data in this case
+            if self._stop_event.is_set():
+                break
+
+            # Very short pause. This will extend the time to handle activity refs by a few seconds but will ensure some time
+            # is available for other threads e.g. the web server.
+            sleep(0.001)
+
+        return new_data

providers/activityrefdata/fea.py

@@ -0,0 +1,56 @@
+from io import BytesIO
+from time import sleep
+
+import pdfplumber
+
+from core.enums import ActivityRefType
+from data.activity_ref import ActivityRef
+from providers.activityrefdata.file_download_activity_ref_data_provider import FileDownloadActivityRefDataProvider
+
+
+class FEA(FileDownloadActivityRefDataProvider):
+    """Activity ref data provider for Diploma Faros de España"""
+
+    POLL_INTERVAL_DAYS = 30
+    ACTIVITY = "FEA"
+    DATA_URL = "http://ea5ol.net/Lista%20Faros.pdf"
+
+    def __init__(self, provider_config):
+        super().__init__(self.ACTIVITY, provider_config, self.DATA_URL, self.POLL_INTERVAL_DAYS)
+
+    def _http_response_to_data(self, http_response):
+        new_data = []
+
+        # Use PDFPlumber to extract the tables in the PDF
+        with pdfplumber.open(BytesIO(http_response.content)) as pdf:
+            all_rows = []
+
+            for page_number, page in enumerate(pdf.pages, start=1):
+                tables = page.extract_tables()
+
+                for table_number, table in enumerate(tables, start=1):
+                    if not table:
+                        continue
+
+                    rows = [row for row in table if any(cell and cell.strip() for cell in row)]
+                    all_rows.extend(rows)
+
+        for row in all_rows:
+            if not "REF" in row[0] and not "\n" in row[0]:
+                # FEA references are technically [DE]\-\d{4}(\.\d)? but spotters always seem to miss out the D- or E-
+                # prefix and just use FEA-1234 or FEA 1234, so we add both copies to the database.
+                ref_id_1 = row[0].strip()
+                ref_id_2 = ref_id_1.replace("D-", "FEA-").replace("E-", "FEA-")
+                new_data.append(ActivityRef(sig=self.ACTIVITY, id=ref_id_1, name=row[1].strip(), ref_type=ActivityRefType.LIGHTHOUSE))
+                new_data.append(ActivityRef(sig=self.ACTIVITY, id=ref_id_2, name=row[1].strip(), ref_type=ActivityRefType.LIGHTHOUSE))
+
+            # Bail out if a stop has been requested, i.e. the program is shutting down - no need to parse the rest of
+            # the data in this case
+            if self._stop_event.is_set():
+                break
+
+            # Very short pause. This will extend the time to handle activity refs by a few seconds but will ensure some time
+            # is available for other threads e.g. the web server.
+            sleep(0.001)
+
+        return new_data

providers/activityrefdata/file_download_activity_ref_data_provider.py

@@ -0,0 +1,84 @@
+import logging
+from datetime import datetime
+from threading import Thread
+
+import pytz
+from requests.exceptions import ConnectionError, ConnectTimeout, ReadTimeout
+
+from core.constants import HTTP_HEADERS
+from core.url_data_cache import URLDataCache
+from providers.activityrefdata.activity_ref_data_provider import ActivityRefDataProvider
+
+logger = logging.getLogger(__name__)
+
+
+class FileDownloadActivityRefDataProvider(ActivityRefDataProvider):
+    """Generic activity ref data provider class for providers that fetch their data from the web by downloading a
+    file."""
+
+    def __init__(self, sig_name, provider_config, url, poll_interval):
+        """Set up the provider, note poll_interval is in *days*."""
+        super().__init__(sig_name, provider_config)
+        self._url = url
+        self._poll_interval = poll_interval
+        self._thread = None
+        self._url_data_cache = URLDataCache(f"sigrefdata_{sig_name}")  # cache dir name kept for continuity
+
+    def start(self):
+        # Fire off the polling thread. It will poll immediately on startup, then sleep for poll_interval between
+        # subsequent polls, so start() returns immediately and the application can continue starting.
+        logger.info(f"Set up query of {self.sig_name} activity ref data every {self._poll_interval!s} days.")
+        self._thread = Thread(target=self._run, name=f"FileDownloadActivityRefDataProvider-{self.sig_name}", daemon=True)
+        self._thread.start()
+
+    def stop(self):
+        super().stop()
+        if self._thread:
+            self._thread.join(timeout=35)
+            if self._thread.is_alive():
+                logger.warning(f"{self.sig_name} activity ref data worker thread did not exit on time and will be killed.")
+
+    def _run(self):
+        while True:
+            self._poll()
+            if self._stop_event.wait(timeout=self._poll_interval * 60 * 60 * 24):
+                break
+
+    def _poll(self):
+        try:
+            # Request data from API. Use the data cache (with a TTL of 1 day) here, not as the main mechanism for
+            # caching, but just so continual restarts of the software during testing don't hammer the servers.
+            logger.debug(f"Downloading {self.sig_name} activity ref data...")
+            http_response = self._url_data_cache.get(self._url, headers=HTTP_HEADERS)
+            # Check response code was good
+            if http_response.ok:
+                # Pass off to the subclass for processing
+                new_data = self._http_response_to_data(http_response)
+                # Add the new data to the activity ref data store
+                if new_data:
+                    self._add_data(new_data)
+
+                self.status = "OK"
+                self.last_update_time = datetime.now(pytz.UTC)
+                logger.debug(f"Received activity ref data for {self.sig_name}")
+            else:
+                self.status = "Error"
+                logger.warning(f"HTTP {http_response.status_code} when downloading activity ref data for {self.sig_name}.")
+
+        except ConnectionError:
+            self.status = "Error"
+            logger.warning(f"Connection error when downloading activity ref data for {self.sig_name}.")
+        except (ConnectTimeout, ReadTimeout):
+            self.status = "Error"
+            logger.warning(f"Timeout when downloading activity ref data for {self.sig_name}.")
+        except Exception:
+            self.status = "Error"
+            logger.exception(f"Exception in HTTP Activity Ref Data Provider ({self.sig_name})")
+            self._stop_event.wait(timeout=1)
+
+    def _http_response_to_data(self, http_response):
+        """Convert an HTTP response returned by the server into activity ref data. The whole response is provided here
+        so the subclass implementations can check for HTTP status codes if necessary, and handle the response as
+        JSON, CSV, whatever the remote file actually is."""
+
+        raise NotImplementedError("Subclasses must implement this method")

providers/activityrefdata/gma.py

@@ -0,0 +1,50 @@
+import csv
+from time import sleep
+
+from core.enums import ActivityRefType
+from data.activity_ref import ActivityRef
+from providers.activityrefdata.file_download_activity_ref_data_provider import (
+    FileDownloadActivityRefDataProvider,
+)
+
+
+class GMA(FileDownloadActivityRefDataProvider):
+    """Activity ref data provider for Global Mountain Activity"""
+
+    POLL_INTERVAL_DAYS = 30
+    ACTIVITY = "GMA"
+    DATA_URL = "https://www.gma.rocks/download/summits.csv"
+
+    def __init__(self, provider_config):
+        super().__init__(self.ACTIVITY, provider_config, self.DATA_URL, self.POLL_INTERVAL_DAYS)
+
+    def _http_response_to_data(self, http_response):
+        new_data = []
+        for row in csv.DictReader(http_response.content.decode("utf-8-sig").splitlines()[1:]):
+            ref_id = row["Reference"]
+            new_data.append(
+                ActivityRef(
+                    sig=self.ACTIVITY,
+                    id=ref_id,
+                    name=row.get("Name", None),
+                    ref_type=ActivityRefType.SUMMIT,
+                    url=f"https://www.cqgma.org/zinfo.php?ref={ref_id}",
+                    latitude=float(row["Latitude"]) if "Latitude" in row and row["Latitude"] != "" else None,
+                    longitude=float(row["Longitude"]) if "Longitude" in row and row["Longitude"] != "" else None,
+                    altitude=float(row["Height (m)"].replace("m", ""))
+                    if "Height (m)" in row and row["Height (m)"] != ""
+                    else None,
+                    grid=row["Maidenhead Locator"],
+                )
+            )
+
+            # Bail out if a stop has been requested, i.e. the program is shutting down - no need to parse the rest of
+            # the data in this case
+            if self._stop_event.is_set():
+                break
+
+            # Very short pause. This will extend the time to handle activity refs by a few seconds but will ensure some time
+            # is available for other threads e.g. the web server.
+            sleep(0.001)
+
+        return new_data

providers/activityrefdata/illw.py

@@ -0,0 +1,48 @@
+import csv
+from time import sleep
+
+from core.enums import ActivityRefType
+from data.activity_ref import ActivityRef
+from providers.activityrefdata.file_download_activity_ref_data_provider import (
+    FileDownloadActivityRefDataProvider,
+)
+
+
+class ILLW(FileDownloadActivityRefDataProvider):
+    """Activity ref data provider for International Lighthouse & Lightship Weekend"""
+
+    POLL_INTERVAL_DAYS = 30
+    ACTIVITY = "ILLW"
+    DATA_URL = "https://www.gma.rocks/download/lighthouse.csv"
+
+    def __init__(self, provider_config):
+        super().__init__(self.ACTIVITY, provider_config, self.DATA_URL, self.POLL_INTERVAL_DAYS)
+
+    def _http_response_to_data(self, http_response):
+        new_data = []
+        for row in csv.DictReader(http_response.content.decode("utf-8-sig").splitlines()[1:]):
+            if "ILLW" in row and row["ILLW"] != "":
+                ref_id = row["ILLW"]
+                new_data.append(
+                    ActivityRef(
+                        sig=self.ACTIVITY,
+                        id=ref_id,
+                        name=row.get("Name", None),
+                        ref_type=ActivityRefType.LIGHTHOUSE,
+                        url=f"https://www.cqgma.org/zinfo.php?ref={ref_id}",
+                        latitude=float(row["Latitude"]) if "Latitude" in row and row["Latitude"] != "" else None,
+                        longitude=float(row["Longitude"]) if "Longitude" in row and row["Longitude"] != "" else None,
+                        grid=row["Maidenhead Locator"],
+                    )
+                )
+
+            # Bail out if a stop has been requested, i.e. the program is shutting down - no need to parse the rest of
+            # the data in this case
+            if self._stop_event.is_set():
+                break
+
+            # Very short pause. This will extend the time to handle activity refs by a few seconds but will ensure some time
+            # is available for other threads e.g. the web server.
+            sleep(0.001)
+
+        return new_data

providers/activityrefdata/iota.py

@@ -0,0 +1,64 @@
+import logging
+from time import sleep
+
+from pyhamtools.locator import latlong_to_locator
+
+from core.enums import ActivityRefType
+from data.activity_ref import ActivityRef
+from providers.activityrefdata.file_download_activity_ref_data_provider import (
+    FileDownloadActivityRefDataProvider,
+)
+
+logger = logging.getLogger(__name__)
+
+
+class IOTA(FileDownloadActivityRefDataProvider):
+    """Activity ref data provider for Islands on the Air"""
+
+    POLL_INTERVAL_DAYS = 365
+    ACTIVITY = "IOTA"
+    DATA_URL = "https://www.iota-world.org/islands-on-the-air/downloads/download-file.html?path=groups.json"
+
+    def __init__(self, provider_config):
+        super().__init__(self.ACTIVITY, provider_config, self.DATA_URL, self.POLL_INTERVAL_DAYS)
+
+    def _http_response_to_data(self, http_response):
+        new_data = []
+        data = http_response.json()
+        if isinstance(data, list):
+            for ref in data:
+                ref_id = ref["refno"]
+                latitude = (float(ref["latitude_min"]) + float(ref["latitude_max"])) / 2.0
+                longitude = (float(ref["longitude_min"]) + float(ref["longitude_max"])) / 2.0
+                grid = None
+                try:
+                    grid = latlong_to_locator(latitude, longitude, 6)
+                except ValueError:
+                    logger.debug(
+                        "Error converting lat/lon to locator for an IOTA reference %f %f",
+                        latitude,
+                        longitude,
+                    )
+
+                new_data.append(
+                    ActivityRef(
+                        sig=self.ACTIVITY,
+                        id=ref_id,
+                        name=ref["name"],
+                        ref_type=ActivityRefType.ISLAND,
+                        grid=grid,
+                        latitude=latitude,
+                        longitude=longitude,
+                    )
+                )
+
+                # Bail out if a stop has been requested, i.e. the program is shutting down - no need to parse the rest
+                # of the data in this case
+                if self._stop_event.is_set():
+                    break
+
+                # Very short pause. This will extend the time to handle activity refs by a few seconds but will ensure some time
+                # is available for other threads e.g. the web server.
+                sleep(0.001)
+
+        return new_data

providers/activityrefdata/krmnpa.py

@@ -0,0 +1,14 @@
+from providers.activityrefdata.pnp_kml_activity_ref_data_provider import (
+    ParksNPeaksKMLActivityRefDataProvider,
+)
+
+
+class KRMNPA(ParksNPeaksKMLActivityRefDataProvider):
+    """Activity ref data provider for the Keith Roget Memorrial National Parks Award (KRMNPA)."""
+
+    POLL_INTERVAL_DAYS = 365
+    ACTIVITY = "KRMNPA"
+    DATA_URL = "https://parksnpeaks.org/getPOI.php?poiClass=KRMNPA&poiFormat=4"
+
+    def __init__(self, provider_config):
+        super().__init__(self.ACTIVITY, provider_config, self.DATA_URL, self.POLL_INTERVAL_DAYS)

providers/activityrefdata/llota.py

@@ -0,0 +1,53 @@
+from time import sleep
+
+from pyhamtools.locator import locator_to_latlong
+
+from core.enums import ActivityRefType
+from data.activity_ref import ActivityRef
+from providers.activityrefdata.file_download_activity_ref_data_provider import (
+    FileDownloadActivityRefDataProvider,
+)
+
+
+class LLOTA(FileDownloadActivityRefDataProvider):
+    """Activity ref data provider for Lagos y Lagunas on the Air"""
+
+    POLL_INTERVAL_DAYS = 7
+    ACTIVITY = "LLOTA"
+    DATA_URL = "https://llota.app/api/public/references"
+
+    def __init__(self, provider_config):
+        super().__init__(self.ACTIVITY, provider_config, self.DATA_URL, self.POLL_INTERVAL_DAYS)
+
+    def _http_response_to_data(self, http_response):
+        new_data = []
+        data = http_response.json()
+        if isinstance(data, list):
+            for ref in data:
+                ref_id = ref["reference_code"]
+                grid = str(ref["grid_locator"])
+                ll = locator_to_latlong(grid)
+
+                new_data.append(
+                    ActivityRef(
+                        sig=self.ACTIVITY,
+                        id=ref_id,
+                        name=str(ref["name"]),
+                        ref_type=ActivityRefType.LAKE,
+                        url=f"https://llota.app/list/ref/{ref_id}",
+                        grid=grid,
+                        latitude=ll[0],
+                        longitude=ll[1],
+                    )
+                )
+
+                # Bail out if a stop has been requested, i.e. the program is shutting down - no need to parse the rest
+                # of the data in this case
+                if self._stop_event.is_set():
+                    break
+
+                # Very short pause. This will extend the time to handle activity refs by a few seconds but will ensure some time
+                # is available for other threads e.g. the web server.
+                sleep(0.001)
+
+        return new_data

providers/activityrefdata/local_file_activity_ref_data_provider.py

@@ -0,0 +1,36 @@
+import logging
+from datetime import datetime
+
+import pytz
+
+from providers.activityrefdata.activity_ref_data_provider import ActivityRefDataProvider
+
+logger = logging.getLogger(__name__)
+
+
+class LocalFileActivityRefDataProvider(ActivityRefDataProvider):
+    """Generic activity ref data provider class for providers that fetch their data from a local file on startup."""
+
+    def __init__(self, sig_name, provider_config, path):
+        super().__init__(sig_name, provider_config)
+        self._path = path
+
+    def start(self):
+        logger.debug(f"Loading {self.sig_name} activity ref data from file.")
+        try:
+            new_data = self._file_to_data(self._path)
+            if new_data:
+                self._add_data(new_data)
+                self.status = "OK"
+                self.last_update_time = datetime.now(pytz.UTC)
+            else:
+                self.status = "Error"
+                logger.info(f"Failed to load activity ref data for {self.sig_name}")
+        except Exception:
+            self.status = "Error"
+            logger.exception(f"Exception in local file Activity Ref Data Provider ({self.sig_name})")
+
+    def _file_to_data(self, path):
+        """Load a file on the given path and turn it into activity ref data."""
+
+        raise NotImplementedError("Subclasses must implement this method")

providers/activityrefdata/mota.py

@@ -0,0 +1,47 @@
+import csv
+from time import sleep
+
+from core.enums import ActivityRefType
+from data.activity_ref import ActivityRef
+from providers.activityrefdata.file_download_activity_ref_data_provider import (
+    FileDownloadActivityRefDataProvider,
+)
+
+
+class MOTA(FileDownloadActivityRefDataProvider):
+    """Activity ref data provider for Mills on the Air"""
+
+    POLL_INTERVAL_DAYS = 30
+    ACTIVITY = "MOTA"
+    DATA_URL = "https://www.gma.rocks/download/mills.csv"
+
+    def __init__(self, provider_config):
+        super().__init__(self.ACTIVITY, provider_config, self.DATA_URL, self.POLL_INTERVAL_DAYS)
+
+    def _http_response_to_data(self, http_response):
+        new_data = []
+        for row in csv.DictReader(http_response.content.decode("utf-8-sig").splitlines()[1:]):
+            ref_id = row["Reference"]
+            new_data.append(
+                ActivityRef(
+                    sig=self.ACTIVITY,
+                    id=ref_id,
+                    name=row.get("Name", None),
+                    ref_type=ActivityRefType.MILL,
+                    url=f"https://www.cqgma.org/zinfo.php?ref={ref_id}",
+                    latitude=float(row["Latitude"]) if "Latitude" in row and row["Latitude"] != "" else None,
+                    longitude=float(row["Longitude"]) if "Longitude" in row and row["Longitude"] != "" else None,
+                    grid=row["Maidenhead Locator"],
+                )
+            )
+
+            # Bail out if a stop has been requested, i.e. the program is shutting down - no need to parse the rest of
+            # the data in this case
+            if self._stop_event.is_set():
+                break
+
+            # Very short pause. This will extend the time to handle activity refs by a few seconds but will ensure some time
+            # is available for other threads e.g. the web server.
+            sleep(0.001)
+
+        return new_data

providers/activityrefdata/pga.py

@@ -0,0 +1,58 @@
+from time import sleep
+
+from bs4 import BeautifulSoup
+
+from core.enums import ActivityRefType
+from data.activity_ref import ActivityRef
+from providers.activityrefdata.file_download_activity_ref_data_provider import FileDownloadActivityRefDataProvider
+
+
+class PGA(FileDownloadActivityRefDataProvider):
+    """Activity ref data provider for Polish Gmina Award"""
+
+    POLL_INTERVAL_DAYS = 30
+    ACTIVITY = "PGA"
+    DATA_URL = "http://www.spga.pl/lista_pga2.php"
+
+    def __init__(self, provider_config):
+        super().__init__(self.ACTIVITY, provider_config, self.DATA_URL, self.POLL_INTERVAL_DAYS)
+
+    def _http_response_to_data(self, http_response):
+        new_data = []
+        soup = BeautifulSoup(http_response.text, "html.parser")
+
+        # Iterate through tables in the page
+        for table in soup.find_all("table"):
+            header_cells = table.find_all(["th", "td"], limit=10)
+            header_texts = [c.get_text(strip=True) for c in header_cells]
+
+            # If it has "PGA" and "Nazwa" in the header, it's the main data table
+            if any("PGA" in t for t in header_texts) and any("Nazwa" in t for t in header_texts):
+                # Iterate through all rows except the first
+                rows = table.find_all("tr")
+                for row in rows[1:]:
+                    cells = row.find_all("td")
+                    ref_id = cells[0].get_text(strip=True)
+                    name = cells[1].get_text(strip=True)
+                    if not ref_id:
+                        continue
+
+                    new_data.append(
+                        ActivityRef(
+                            sig=self.ACTIVITY,
+                            id=ref_id,
+                            name=name,
+                            ref_type=ActivityRefType.REGION,
+                        )
+                    )
+
+                    # Bail out if a stop has been requested, i.e. the program is shutting down - no need to parse the rest
+                    # of the data in this case
+                    if self._stop_event.is_set():
+                        break
+
+                    # Very short pause. This will extend the time to handle activity refs by a few seconds but will ensure some time
+                    # is available for other threads e.g. the web server.
+                    sleep(0.001)
+
+        return new_data

providers/activityrefdata/pnp_kml_activity_ref_data_provider.py

@@ -0,0 +1,65 @@
+import re
+from time import sleep
+
+from fastkml import kml
+from pyhamtools.locator import latlong_to_locator
+
+from core.enums import ActivityRefType
+from data.activity_ref import ActivityRef
+from providers.activityrefdata.file_download_activity_ref_data_provider import (
+    FileDownloadActivityRefDataProvider,
+)
+
+
+class ParksNPeaksKMLActivityRefDataProvider(FileDownloadActivityRefDataProvider):
+    """Base class for activity ref data providers that use parksnpeaks.org KML POI feeds and have references that
+    use the VKFF refs rather than their own system (i.e. KRMNPA and SANPCPA)."""
+
+    REF_PATTERN = re.compile(r"VKFF-\d+")
+
+    def __init__(self, sig_name, provider_config, url, poll_interval):
+        """Set up the provider, note poll_interval is in *days*."""
+        super().__init__(sig_name, provider_config, url, poll_interval)
+
+    def _http_response_to_data(self, http_response):
+        new_data = []
+
+        k = kml.KML.from_string(http_response.content)
+
+        for document in k.features:
+            # noinspection unresolved-references
+            for folder in document.features:
+                # noinspection unresolved-references
+                for placemark in folder.features:
+                    description = placemark.description or ""
+                    match = self.REF_PATTERN.search(description)
+                    if not match:
+                        # No VKFF reference found in this placemark - skip it (e.g. non-park waypoints)
+                        continue
+                    ref_id = match.group(0)
+
+                    longitude, latitude = placemark.geometry.x, placemark.geometry.y
+
+                    ref = ActivityRef(
+                        sig=self.sig_name,
+                        id=ref_id,
+                        name=placemark.name,
+                        ref_type=ActivityRefType.PARK,
+                        url=f"https://parksnpeaks.org/getPark.php?actPark={ref_id}",
+                        latitude=latitude,
+                        longitude=longitude,
+                    )
+                    if latitude and longitude:
+                        ref.grid = latlong_to_locator(latitude, longitude, 6)
+                    new_data.append(ref)
+
+                    # Bail out if a stop has been requested, i.e. the program is shutting down - no need to
+                    # parse the rest of the data in this case
+                    if self._stop_event.is_set():
+                        return new_data
+
+                    # Very short pause. This will extend the time to handle activity refs by a few seconds but will ensure some time
+                    # is available for other threads e.g. the web server.
+                    sleep(0.001)
+
+        return new_data

providers/activityrefdata/pota.py

@@ -0,0 +1,47 @@
+import csv
+from time import sleep
+
+from core.enums import ActivityRefType
+from data.activity_ref import ActivityRef
+from providers.activityrefdata.file_download_activity_ref_data_provider import (
+    FileDownloadActivityRefDataProvider,
+)
+
+
+class POTA(FileDownloadActivityRefDataProvider):
+    """Activity ref data provider for Parks on the Air"""
+
+    POLL_INTERVAL_DAYS = 7
+    ACTIVITY = "POTA"
+    DATA_URL = "https://pota.app/all_parks_ext.csv"
+
+    def __init__(self, provider_config):
+        super().__init__(self.ACTIVITY, provider_config, self.DATA_URL, self.POLL_INTERVAL_DAYS)
+
+    def _http_response_to_data(self, http_response):
+        new_data = []
+        for row in csv.DictReader(http_response.content.decode("utf-8-sig").splitlines()):
+            ref_id = row["reference"]
+            new_data.append(
+                ActivityRef(
+                    sig=self.ACTIVITY,
+                    id=ref_id,
+                    name=row.get("name", None),
+                    ref_type=ActivityRefType.PARK,
+                    url=f"https://pota.app/#/park/{ref_id}",
+                    grid=row.get("grid", None),
+                    latitude=float(row["latitude"]) if "latitude" in row and row["latitude"] != "" else None,
+                    longitude=float(row["longitude"]) if "longitude" in row and row["longitude"] != "" else None,
+                )
+            )
+
+            # Bail out if a stop has been requested, i.e. the program is shutting down - no need to parse the rest of
+            # the data in this case
+            if self._stop_event.is_set():
+                break
+
+            # Very short pause. This will extend the time to handle activity refs by a few seconds but will ensure some time
+            # is available for other threads e.g. the web server.
+            sleep(0.001)
+
+        return new_data

providers/activityrefdata/sanpcpa.py

@@ -0,0 +1,14 @@
+from providers.activityrefdata.pnp_kml_activity_ref_data_provider import (
+    ParksNPeaksKMLActivityRefDataProvider,
+)
+
+
+class SANPCPA(ParksNPeaksKMLActivityRefDataProvider):
+    """Activity ref data provider for the South Australia National Parks and Conservation Parks Award (SANPCPA)."""
+
+    POLL_INTERVAL_DAYS = 365
+    ACTIVITY = "SANPCPA"
+    DATA_URL = "https://parksnpeaks.org/getPOI.php?poiClass=SANPCPA&poiFormat=4"
+
+    def __init__(self, provider_config):
+        super().__init__(self.ACTIVITY, provider_config, self.DATA_URL, self.POLL_INTERVAL_DAYS)

providers/activityrefdata/siota.py

@@ -0,0 +1,46 @@
+import csv
+from time import sleep
+
+from core.enums import ActivityRefType
+from data.activity_ref import ActivityRef
+from providers.activityrefdata.file_download_activity_ref_data_provider import (
+    FileDownloadActivityRefDataProvider,
+)
+
+
+class SIOTA(FileDownloadActivityRefDataProvider):
+    """Activity ref data provider for Silos on the Air"""
+
+    POLL_INTERVAL_DAYS = 30
+    ACTIVITY = "SIOTA"
+    DATA_URL = "https://www.silosontheair.com/data/silos.csv"
+
+    def __init__(self, provider_config):
+        super().__init__(self.ACTIVITY, provider_config, self.DATA_URL, self.POLL_INTERVAL_DAYS)
+
+    def _http_response_to_data(self, http_response):
+        new_data = []
+        for row in csv.DictReader(http_response.content.decode("utf-8-sig").splitlines()):
+            ref_id = row["SILO_CODE"]
+            new_data.append(
+                ActivityRef(
+                    sig=self.ACTIVITY,
+                    id=ref_id,
+                    name=row.get("NAME", None),
+                    ref_type=ActivityRefType.SILO,
+                    grid=row.get("LOCATOR", None),
+                    latitude=float(row["LAT"]) if "LAT" in row else None,
+                    longitude=float(row["LNG"]) if "LNG" in row else None,
+                )
+            )
+
+            # Bail out if a stop has been requested, i.e. the program is shutting down - no need to parse the rest of
+            # the data in this case
+            if self._stop_event.is_set():
+                break
+
+            # Very short pause. This will extend the time to handle activity refs by a few seconds but will ensure some time
+            # is available for other threads e.g. the web server.
+            sleep(0.001)
+
+        return new_data

providers/activityrefdata/sota.py

@@ -0,0 +1,54 @@
+import csv
+from time import sleep
+
+from pyhamtools.locator import latlong_to_locator
+
+from core.enums import ActivityRefType
+from data.activity_ref import ActivityRef
+from providers.activityrefdata.file_download_activity_ref_data_provider import (
+    FileDownloadActivityRefDataProvider,
+)
+
+
+class SOTA(FileDownloadActivityRefDataProvider):
+    """Activity ref data provider for Summits on the Air"""
+
+    POLL_INTERVAL_DAYS = 30
+    ACTIVITY = "SOTA"
+    DATA_URL = "https://storage.sota.org.uk/summitslist.csv"
+
+    def __init__(self, provider_config):
+        super().__init__(self.ACTIVITY, provider_config, self.DATA_URL, self.POLL_INTERVAL_DAYS)
+
+    def _http_response_to_data(self, http_response):
+        new_data = []
+        for row in csv.DictReader(http_response.content.decode("utf-8-sig").splitlines()[1:]):
+            ref_id = row["SummitCode"]
+            latitude = float(row["Latitude"]) if "Latitude" in row and row["Latitude"] != "" else None
+            longitude = float(row["Longitude"]) if "Longitude" in row and row["Longitude"] != "" else None
+            altitude = float(row["AltM"]) if "AltM" in row and row["AltM"] != "" else None
+            ref = ActivityRef(
+                sig=self.ACTIVITY,
+                id=ref_id,
+                name=row.get("SummitName", None),
+                ref_type=ActivityRefType.SUMMIT,
+                url=f"https://www.sotadata.org.uk/en/summit/{ref_id}",
+                latitude=latitude,
+                longitude=longitude,
+                altitude=altitude,
+                activation_score=int(row["Points"]) if "Points" in row else None,
+            )
+            if latitude and longitude:
+                ref.grid = latlong_to_locator(latitude, longitude, 6)
+            new_data.append(ref)
+
+            # Bail out if a stop has been requested, i.e. the program is shutting down - no need to parse the rest of
+            # the data in this case
+            if self._stop_event.is_set():
+                break
+
+            # Very short pause. This will extend the time to handle activity refs by a few seconds but will ensure some time
+            # is available for other threads e.g. the web server.
+            sleep(0.001)
+
+        return new_data

providers/activityrefdata/toilets.py

@@ -0,0 +1,41 @@
+import csv
+
+from core.enums import ActivityRefType
+from data.activity_ref import ActivityRef
+from providers.activityrefdata.local_file_activity_ref_data_provider import (
+    LocalFileActivityRefDataProvider,
+)
+
+
+class Toilets(LocalFileActivityRefDataProvider):
+    """Activity ref data provider for Toilets on the Air"""
+
+    ACTIVITY = "Toilets"
+    PATH = "datafiles/toilets.csv"
+
+    def __init__(self, provider_config):
+        super().__init__(self.ACTIVITY, provider_config, self.PATH)
+
+    def _file_to_data(self, path):
+        new_data = []
+        with open(path) as _f:
+            csv_data = _f.read()
+            dr = csv.DictReader(csv_data.splitlines())
+            for row in dr:
+                new_data.append(
+                    ActivityRef(
+                        sig=self.ACTIVITY,
+                        id=row["ref"],
+                        name=row["ref"],
+                        ref_type=ActivityRefType.TOILET,
+                        latitude=float(row["lat"]),
+                        longitude=float(row["lon"]),
+                    )
+                )
+
+                # Bail out if a stop has been requested, i.e. the program is shutting down - no need to parse the rest
+                # of the data in this case
+                if self._stop_event.is_set():
+                    break
+
+        return new_data

providers/activityrefdata/towers.py

@@ -0,0 +1,47 @@
+import csv
+from time import sleep
+
+from core.enums import ActivityRefType
+from data.activity_ref import ActivityRef
+from providers.activityrefdata.file_download_activity_ref_data_provider import (
+    FileDownloadActivityRefDataProvider,
+)
+
+
+class Towers(FileDownloadActivityRefDataProvider):
+    """Activity ref data provider for Towers on the Air"""
+
+    POLL_INTERVAL_DAYS = 30
+    ACTIVITY = "Towers"
+    DATA_URL = "https://wwtota.com/servis/generate_csv.php?ref=&filter=all"
+
+    def __init__(self, provider_config):
+        super().__init__(self.ACTIVITY, provider_config, self.DATA_URL, self.POLL_INTERVAL_DAYS)
+
+    def _http_response_to_data(self, http_response):
+        new_data = []
+        for row in csv.DictReader(http_response.content.decode("utf-8-sig").splitlines(), delimiter=";"):
+            ref_id = row["Ref"]
+            new_data.append(
+                ActivityRef(
+                    sig=self.ACTIVITY,
+                    id=ref_id,
+                    name=row.get("Nazev", None),
+                    ref_type=ActivityRefType.TOWER,
+                    url=f"https://wwtota.com/seznam/karta_rozhledny.php?ref={ref_id}",
+                    grid=row["Lokator"] if "Lokator" in row and row["Lokator"] != "" else None,
+                    latitude=float(row["Lat"]) if "Lat" in row and row["Lat"] != "" else None,
+                    longitude=float(row["Lon"]) if "Lon" in row and row["Lon"] != "" else None,
+                )
+            )
+
+            # Bail out if a stop has been requested, i.e. the program is shutting down - no need to parse the rest of
+            # the data in this case
+            if self._stop_event.is_set():
+                break
+
+            # Very short pause. This will extend the time to handle activity refs by a few seconds but will ensure some time
+            # is available for other threads e.g. the web server.
+            sleep(0.001)
+
+        return new_data

providers/activityrefdata/wca.py

@@ -0,0 +1,66 @@
+import csv
+import logging
+from time import sleep
+
+from pyhamtools.locator import latlong_to_locator
+
+from core.enums import ActivityRefType
+from data.activity_ref import ActivityRef
+from providers.activityrefdata.file_download_activity_ref_data_provider import (
+    FileDownloadActivityRefDataProvider,
+)
+
+logger = logging.getLogger(__name__)
+
+
+class WCA(FileDownloadActivityRefDataProvider):
+    """Activity ref data provider for World Castles Award"""
+
+    POLL_INTERVAL_DAYS = 30
+    ACTIVITY = "WCA"
+    DATA_URL = "https://polo.ham2k.com/data/activities/wca/all-castles.csv"
+
+    def __init__(self, provider_config):
+        super().__init__(self.ACTIVITY, provider_config, self.DATA_URL, self.POLL_INTERVAL_DAYS)
+
+    def _http_response_to_data(self, http_response):
+        new_data = []
+        for row in csv.DictReader(http_response.content.decode("utf-8-sig").splitlines()):
+            ref_id = row["REF"]
+
+            coords_str = row["COORDINATES"]
+            latitude = None
+            longitude = None
+            grid = None
+            try:
+                if coords_str:
+                    split = coords_str.split(", ")
+                    latitude = float(split[0])
+                    longitude = float(split[1])
+                    grid = latlong_to_locator(latitude, longitude)
+            except ValueError:
+                logger.debug(f"Encountered dodgy formatting in WCA CSV, skipping location data for {ref_id}")
+
+            new_data.append(
+                ActivityRef(
+                    sig=self.ACTIVITY,
+                    id=ref_id,
+                    name=row.get("CLEAN NAME", None),
+                    ref_type=ActivityRefType.CASTLE,
+                    url=f"https://www.cqgma.org/zinfo.php?ref={ref_id}",
+                    latitude=latitude,
+                    longitude=longitude,
+                    grid=grid,
+                )
+            )
+
+            # Bail out if a stop has been requested, i.e. the program is shutting down - no need to parse the rest of
+            # the data in this case
+            if self._stop_event.is_set():
+                break
+
+            # Very short pause. This will extend the time to handle activity refs by a few seconds but will ensure some time
+            # is available for other threads e.g. the web server.
+            sleep(0.001)
+
+        return new_data

providers/activityrefdata/wota.py

@@ -0,0 +1,54 @@
+from time import sleep
+
+from core.enums import ActivityRefType
+from data.activity_ref import ActivityRef
+from providers.activityrefdata.file_download_activity_ref_data_provider import (
+    FileDownloadActivityRefDataProvider,
+)
+
+
+class WOTA(FileDownloadActivityRefDataProvider):
+    """Activity ref data provider for Wainwrights on the Air"""
+
+    POLL_INTERVAL_DAYS = 365
+    ACTIVITY = "WOTA"
+    DATA_URL = "https://www.wota.org.uk/mapping/data/summits.json"
+
+    def __init__(self, provider_config):
+        super().__init__(self.ACTIVITY, provider_config, self.DATA_URL, self.POLL_INTERVAL_DAYS)
+
+    def _http_response_to_data(self, http_response):
+        new_data = []
+        for feature in http_response.json().get("features", []):
+            ref_id = feature["properties"]["wotaId"]
+            # Fudge WOTA URLs. Outlying fell (LDO) URLs don't match their ID numbers but require 214 to be
+            # added to them
+            url = f"https://www.wota.org.uk/MM_{ref_id}"
+            if ref_id.upper().startswith("LDO-"):
+                number = int(ref_id.upper().replace("LDO-", ""))
+                url = f"https://www.wota.org.uk/MM_LDO-{number + 214!s}"
+
+            new_data.append(
+                ActivityRef(
+                    sig=self.ACTIVITY,
+                    id=ref_id,
+                    name=feature["properties"]["title"],
+                    url=url,
+                    ref_type=ActivityRefType.SUMMIT,
+                    grid=feature["properties"]["qthLocator"],
+                    latitude=feature["geometry"]["coordinates"][1],
+                    longitude=feature["geometry"]["coordinates"][0],
+                    altitude=feature["properties"]["height"],
+                )
+            )
+
+            # Bail out if a stop has been requested, i.e. the program is shutting down - no need to parse the rest of
+            # the data in this case
+            if self._stop_event.is_set():
+                break
+
+            # Very short pause. This will extend the time to handle activity refs by a few seconds but will ensure some time
+            # is available for other threads e.g. the web server.
+            sleep(0.001)
+
+        return new_data

providers/activityrefdata/wwbota.py

@@ -0,0 +1,47 @@
+import csv
+from time import sleep
+
+from core.enums import ActivityRefType
+from data.activity_ref import ActivityRef
+from providers.activityrefdata.file_download_activity_ref_data_provider import (
+    FileDownloadActivityRefDataProvider,
+)
+
+
+class WWBOTA(FileDownloadActivityRefDataProvider):
+    """Activity ref data provider for Worldwide Bunkers on the Air"""
+
+    POLL_INTERVAL_DAYS = 30
+    ACTIVITY = "WWBOTA"
+    DATA_URL = "https://api.wwbota.org/bunkers/?format=CSV"
+
+    def __init__(self, provider_config):
+        super().__init__(self.ACTIVITY, provider_config, self.DATA_URL, self.POLL_INTERVAL_DAYS)
+
+    def _http_response_to_data(self, http_response):
+        new_data = []
+        for row in csv.DictReader(http_response.content.decode("utf-8-sig").splitlines()):
+            ref_id = row["Reference"]
+            new_data.append(
+                ActivityRef(
+                    sig=self.ACTIVITY,
+                    id=ref_id,
+                    name=row.get("Name", None),
+                    ref_type=ActivityRefType.BUNKER,
+                    url=f"https://bunkerwiki.org/?s={ref_id}" if ref_id.startswith("B/G") else None,
+                    grid=row["Locator"] if "Locator" in row and row["Locator"] != "" else None,
+                    latitude=float(row["Lat"]) if "Lat" in row and row["Lat"] != "" else None,
+                    longitude=float(row["Long"]) if "Long" in row and row["Long"] != "" else None,
+                )
+            )
+
+            # Bail out if a stop has been requested, i.e. the program is shutting down - no need to parse the rest of
+            # the data in this case
+            if self._stop_event.is_set():
+                break
+
+            # Very short pause. This will extend the time to handle activity refs by a few seconds but will ensure some time
+            # is available for other threads e.g. the web server.
+            sleep(0.001)
+
+        return new_data

providers/activityrefdata/wwff.py

@@ -0,0 +1,51 @@
+import csv
+from time import sleep
+
+from core.enums import ActivityRefType
+from data.activity_ref import ActivityRef
+from providers.activityrefdata.file_download_activity_ref_data_provider import (
+    FileDownloadActivityRefDataProvider,
+)
+
+
+class WWFF(FileDownloadActivityRefDataProvider):
+    """Activity ref data provider for Worldwide Flora & Fauna"""
+
+    POLL_INTERVAL_DAYS = 30
+    ACTIVITY = "WWFF"
+    DATA_URL = "https://wwff.co/wwff-data/wwff_directory.csv"
+
+    def __init__(self, provider_config):
+        super().__init__(self.ACTIVITY, provider_config, self.DATA_URL, self.POLL_INTERVAL_DAYS)
+
+    def _http_response_to_data(self, http_response):
+        new_data = []
+        for row in csv.DictReader(http_response.content.decode("utf-8-sig").splitlines()):
+            ref_id = row["reference"]
+            new_data.append(
+                ActivityRef(
+                    sig=self.ACTIVITY,
+                    id=ref_id,
+                    name=row.get("name", None),
+                    ref_type=ActivityRefType.PARK,
+                    url=f"https://wwff.co/directory/?showRef={ref_id}",
+                    grid=row["iaruLocator"] if "iaruLocator" in row and row["iaruLocator"] != "-" else None,
+                    latitude=float(row["latitude"])
+                    if "latitude" in row and row["latitude"] != "" and row["latitude"] != "-"
+                    else None,
+                    longitude=float(row["longitude"])
+                    if "longitude" in row and row["longitude"] != "" and row["longitude"] != "-"
+                    else None,
+                )
+            )
+
+            # Bail out if a stop has been requested, i.e. the program is shutting down - no need to parse the rest of
+            # the data in this case
+            if self._stop_event.is_set():
+                break
+
+            # Very short pause. This will extend the time to handle activity refs by a few seconds but will ensure some time
+            # is available for other threads e.g. the web server.
+            sleep(0.001)
+
+        return new_data

providers/activityrefdata/zlota.py

@@ -0,0 +1,65 @@
+from time import sleep
+
+from pyhamtools.locator import latlong_to_locator
+
+from core.enums import ActivityRefType
+from data.activity_ref import ActivityRef
+from providers.activityrefdata.file_download_activity_ref_data_provider import (
+    FileDownloadActivityRefDataProvider,
+)
+
+
+class ZLOTA(FileDownloadActivityRefDataProvider):
+    """Activity ref data provider for New Zealand on the Air"""
+
+    POLL_INTERVAL_DAYS = 30
+    ACTIVITY = "ZLOTA"
+    DATA_URL = "https://ontheair.nz/assets/assets.json"
+
+    def __init__(self, provider_config):
+        super().__init__(self.ACTIVITY, provider_config, self.DATA_URL, self.POLL_INTERVAL_DAYS)
+
+    def _http_response_to_data(self, http_response):
+        new_data = []
+        data = http_response.json()
+        if isinstance(data, list):
+            for ref in data:
+                ref_id = ref["code"]
+                latitude = ref["latitude"]
+                longitude = ref["longitude"]
+                try:
+                    ref_type = ActivityRefType(ref["asset_type"].title().upper())
+                except ValueError:
+                    ref_type = None
+
+                new_ref = ActivityRef(
+                    sig=self.ACTIVITY,
+                    id=ref_id,
+                    name=ref["name"],
+                    ref_type=ref_type,
+                    url=f"https://ontheair.nz/assets/{ref_id.replace('/', '_')}",
+                    latitude=latitude,
+                    longitude=longitude,
+                )
+
+                # Check lat/lon validity and update grid accordingly
+                if latitude and longitude:
+                    try:
+                        new_ref.grid = latlong_to_locator(latitude, longitude, 6)
+                    except ValueError:
+                        # Junk lat/lon, remove from the spot
+                        new_ref.latitude = None
+                        new_ref.longitude = None
+
+                new_data.append(new_ref)
+
+                # Bail out if a stop has been requested, i.e. the program is shutting down - no need to parse the rest
+                # of the data in this case
+                if self._stop_event.is_set():
+                    break
+
+                # Very short pause. This will extend the time to handle activity refs by a few seconds but will ensure some time
+                # is available for other threads e.g. the web server.
+                sleep(0.001)
+
+        return new_data