Fix mojibake in DX cluster and RBN spot comments

Both providers always decoded telnet bytes as Latin-1, which silently
mangles nodes that send UTF-8 (Latin-1 decode never raises, so mixed
encodings across cluster nodes went unnoticed). Added a shared
decode_telnet_bytes() helper that tries UTF-8 first and falls back to
Latin-1, since a byte stream that happens to be valid multi-byte UTF-8
is essentially never accidental Latin-1 text.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>

providers/spot/dxcluster.py

@@ -9,7 +9,7 @@ import telnetlib3
 
 from core.config import SERVER_OWNER_CALLSIGN
 from data.spot import Spot
-from providers.spot.spot_provider import SpotProvider
+from providers.spot.spot_provider import SpotProvider, decode_telnet_bytes
 
 logger = logging.getLogger(__name__)
 
@@ -96,7 +96,7 @@ class DXCluster(SpotProvider):
                 try:
                     # Check new telnet info against regular expression
                     telnet_output = self._telnet.read_until("\n".encode("latin-1"))
-                    match = self._spot_line_pattern.match(telnet_output.decode("latin-1"))
+                    match = self._spot_line_pattern.match(decode_telnet_bytes(telnet_output))
                     if match:
                         spot_time = datetime.strptime(match.group(5), "%H%MZ").replace(tzinfo=pytz.UTC)
                         spot_datetime = datetime.combine(

providers/spot/rbn.py

@@ -9,7 +9,7 @@ import telnetlib3
 
 from core.config import SERVER_OWNER_CALLSIGN
 from data.spot import Spot
-from providers.spot.spot_provider import SpotProvider
+from providers.spot.spot_provider import SpotProvider, decode_telnet_bytes
 
 logger = logging.getLogger(__name__)
 
@@ -81,7 +81,7 @@ class RBN(SpotProvider):
                 try:
                     # Check new telnet info against regular expression
                     telnet_output = self._telnet.read_until("\n".encode("latin-1"))
-                    match = self._LINE_PATTERN.match(telnet_output.decode("latin-1"))
+                    match = self._LINE_PATTERN.match(decode_telnet_bytes(telnet_output))
                     if match:
                         spot_time = datetime.strptime(match.group(5), "%H%MZ").replace(tzinfo=pytz.UTC)
                         spot_datetime = datetime.combine(

providers/spot/spot_provider.py

@@ -5,6 +5,18 @@ import pytz
 from core.data_store import DATA_STORE
 
 
+def decode_telnet_bytes(data: bytes) -> str:
+    """Decode a line of text received from a telnet connection. DX cluster and RBN nodes are inconsistent about the
+    character encoding they use for spot comments: most send UTF-8, but some older ones send Latin-1/CP1252. Try
+    UTF-8 first, since valid multi-byte UTF-8 sequences are very unlikely to occur by chance in Latin-1 text, then
+    fall back to Latin-1, which can decode any byte sequence without raising."""
+
+    try:
+        return data.decode("utf-8")
+    except UnicodeDecodeError:
+        return data.decode("latin-1")
+
+
 class SpotProvider:
     """Generic spot provider class. Subclasses of this query the individual APIs for data."""