AegisSight/AegisSight-Monitor
3
0
Fork 0
Code Issues Pull-Requests Actions Pakete Projekte Releases Wiki Aktivität

Geoparsing: Laender vor Staedten pruefen, Alias-Tabelle

Quellcode durchsuchen 
Behebt falsche Geocodierung bei Laendernamen die auch als Staedte
existieren (Lebanon->US statt Libanon, Jordan->HK statt Jordanien).

- Laender-Aliase (50+ deutsch/englisch) werden zuerst geprueft
- geonamescache Laendersuche vor Staedtesuche
- Stadtsuche in eigene _geocode_city() Funktion extrahiert
- Bestehende falsche Marker in DB korrigiert

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Dieser Commit ist enthalten in:
claude-dev
2026-03-08 23:39:45 +01:00
Ursprung e761c86a28
Commit 606c60a815
1 geänderte Dateien mit 409 neuen und 318 gelöschten Zeilen
Patch-Datei herunterladen Vergleichs-Datei herunterladen Alle Dateien ausklappen Alle Dateien einklappen

153
src/agents/geoparsing.py
Datei anzeigen

@@ -31,12 +31,71 @@ def _get_geonamescache():
return _gc
# Bekannte Laendernamen (deutsch/englisch/alternativ -> ISO-2 Code + Hauptstadt-Koordinaten)
_COUNTRY_ALIASES = {
"libanon": {"code": "LB", "name": "Lebanon", "lat": 33.8938, "lon": 35.5018},
"lebanon": {"code": "LB", "name": "Lebanon", "lat": 33.8938, "lon": 35.5018},
"jordan": {"code": "JO", "name": "Jordan", "lat": 31.9454, "lon": 35.9284},
"jordanien": {"code": "JO", "name": "Jordan", "lat": 31.9454, "lon": 35.9284},
"iran": {"code": "IR", "name": "Iran", "lat": 35.6892, "lon": 51.3890},
"irak": {"code": "IQ", "name": "Iraq", "lat": 33.3152, "lon": 44.3661},
"iraq": {"code": "IQ", "name": "Iraq", "lat": 33.3152, "lon": 44.3661},
"israel": {"code": "IL", "name": "Israel", "lat": 31.7683, "lon": 35.2137},
"syrien": {"code": "SY", "name": "Syria", "lat": 33.5138, "lon": 36.2765},
"syria": {"code": "SY", "name": "Syria", "lat": 33.5138, "lon": 36.2765},
"tuerkei": {"code": "TR", "name": "Turkey", "lat": 39.9334, "lon": 32.8597},
"turkey": {"code": "TR", "name": "Turkey", "lat": 39.9334, "lon": 32.8597},
"kuwait": {"code": "KW", "name": "Kuwait", "lat": 29.3759, "lon": 47.9774},
"bahrain": {"code": "BH", "name": "Bahrain", "lat": 26.0667, "lon": 50.5577},
"katar": {"code": "QA", "name": "Qatar", "lat": 25.2854, "lon": 51.5310},
"qatar": {"code": "QA", "name": "Qatar", "lat": 25.2854, "lon": 51.5310},
"jemen": {"code": "YE", "name": "Yemen", "lat": 15.3694, "lon": 44.1910},
"yemen": {"code": "YE", "name": "Yemen", "lat": 15.3694, "lon": 44.1910},
"oman": {"code": "OM", "name": "Oman", "lat": 23.5880, "lon": 58.3829},
"pakistan": {"code": "PK", "name": "Pakistan", "lat": 33.6844, "lon": 73.0479},
"afghanistan": {"code": "AF", "name": "Afghanistan", "lat": 34.5553, "lon": 69.2075},
"aegypten": {"code": "EG", "name": "Egypt", "lat": 30.0444, "lon": 31.2357},
"egypt": {"code": "EG", "name": "Egypt", "lat": 30.0444, "lon": 31.2357},
"saudi-arabien": {"code": "SA", "name": "Saudi Arabia", "lat": 24.7136, "lon": 46.6753},
"saudi arabia": {"code": "SA", "name": "Saudi Arabia", "lat": 24.7136, "lon": 46.6753},
"deutschland": {"code": "DE", "name": "Germany", "lat": 52.5200, "lon": 13.4050},
"germany": {"code": "DE", "name": "Germany", "lat": 52.5200, "lon": 13.4050},
"frankreich": {"code": "FR", "name": "France", "lat": 48.8566, "lon": 2.3522},
"france": {"code": "FR", "name": "France", "lat": 48.8566, "lon": 2.3522},
"russland": {"code": "RU", "name": "Russia", "lat": 55.7558, "lon": 37.6173},
"russia": {"code": "RU", "name": "Russia", "lat": 55.7558, "lon": 37.6173},
"china": {"code": "CN", "name": "China", "lat": 39.9042, "lon": 116.4074},
"indien": {"code": "IN", "name": "India", "lat": 28.6139, "lon": 77.2090},
"india": {"code": "IN", "name": "India", "lat": 28.6139, "lon": 77.2090},
"usa": {"code": "US", "name": "United States", "lat": 38.9072, "lon": -77.0369},
"vereinigte staaten": {"code": "US", "name": "United States", "lat": 38.9072, "lon": -77.0369},
"united states": {"code": "US", "name": "United States", "lat": 38.9072, "lon": -77.0369},
"grossbritannien": {"code": "GB", "name": "United Kingdom", "lat": 51.5074, "lon": -0.1278},
"united kingdom": {"code": "GB", "name": "United Kingdom", "lat": 51.5074, "lon": -0.1278},
"schweiz": {"code": "CH", "name": "Switzerland", "lat": 46.9480, "lon": 7.4474},
"switzerland": {"code": "CH", "name": "Switzerland", "lat": 46.9480, "lon": 7.4474},
"spanien": {"code": "ES", "name": "Spain", "lat": 40.4168, "lon": -3.7038},
"spain": {"code": "ES", "name": "Spain", "lat": 40.4168, "lon": -3.7038},
"italien": {"code": "IT", "name": "Italy", "lat": 41.9028, "lon": 12.4964},
"italy": {"code": "IT", "name": "Italy", "lat": 41.9028, "lon": 12.4964},
"zypern": {"code": "CY", "name": "Cyprus", "lat": 35.1856, "lon": 33.3823},
"cyprus": {"code": "CY", "name": "Cyprus", "lat": 35.1856, "lon": 33.3823},
"aserbaidschan": {"code": "AZ", "name": "Azerbaijan", "lat": 40.4093, "lon": 49.8671},
"azerbaijan": {"code": "AZ", "name": "Azerbaijan", "lat": 40.4093, "lon": 49.8671},
"griechenland": {"code": "GR", "name": "Greece", "lat": 37.9838, "lon": 23.7275},
"greece": {"code": "GR", "name": "Greece", "lat": 37.9838, "lon": 23.7275},
"niederlande": {"code": "NL", "name": "Netherlands", "lat": 52.3676, "lon": 4.9041},
"netherlands": {"code": "NL", "name": "Netherlands", "lat": 52.3676, "lon": 4.9041},
"ukraine": {"code": "UA", "name": "Ukraine", "lat": 50.4501, "lon": 30.5234},
}
def _geocode_offline(name: str, country_code: str = "") -> Optional[dict]:
"""Geocoding ueber geonamescache (offline).
Args:
name: Ortsname (normalisiert von Haiku)
country_code: ISO-2 Laendercode (von Haiku) fuer bessere Disambiguierung
Reihenfolge: 1. Bekannte Laender-Aliase, 2. geonamescache-Laender, 3. Staedte.
Laender werden IMMER vor Staedten geprueft um Verwechslungen zu vermeiden
(z.B. Lebanon/US vs Libanon, Jordan/HK vs Jordanien).
"""
gc = _get_geonamescache()
if gc is None:
@@ -44,7 +103,51 @@ def _geocode_offline(name: str, country_code: str = "") -> Optional[dict]:
name_lower = name.lower().strip()
# 1. Stadtsuche
# 1. Bekannte Laender-Aliase (schnellster + sicherster Pfad)
alias = _COUNTRY_ALIASES.get(name_lower)
if alias:
return {
"lat": alias["lat"],
"lon": alias["lon"],
"country_code": alias["code"],
"normalized_name": alias["name"],
"confidence": 0.95,
}
# 2. geonamescache Laendersuche (vor Staedten!)
countries = gc.get_countries()
for code, country in countries.items():
if country.get("name", "").lower() == name_lower:
capital = country.get("capital", "")
if capital:
# Hauptstadt geocoden, aber als Land benennen
cap_alias = _COUNTRY_ALIASES.get(capital.lower())
if cap_alias:
return {
"lat": cap_alias["lat"],
"lon": cap_alias["lon"],
"country_code": code,
"normalized_name": country["name"],
"confidence": 0.9,
}
# Rekursiv die Hauptstadt suchen (nur Staedte-Pfad)
cap_result = _geocode_city(capital, code)
if cap_result:
cap_result["normalized_name"] = country["name"]
cap_result["confidence"] = 0.9
return cap_result
# 3. Stadtsuche (nur wenn kein Land gefunden)
return _geocode_city(name, country_code)
def _geocode_city(name: str, country_code: str = "") -> Optional[dict]:
"""Sucht einen Stadtnamen in geonamescache."""
gc = _get_geonamescache()
if gc is None:
return None
name_lower = name.lower().strip()
cities = gc.get_cities()
matches = []
for gid, city in cities.items():
@@ -57,34 +160,22 @@ def _geocode_offline(name: str, country_code: str = "") -> Optional[dict]:
if city_name.lower() == name_lower or name_lower in alt_list:
matches.append(city)
if matches:
# Disambiguierung: country_code bevorzugen, dann Population
if country_code:
cc_matches = [c for c in matches if c.get("countrycode", "").upper() == (country_code or "").upper()]
if cc_matches:
matches = cc_matches
best = max(matches, key=lambda c: c.get("population", 0))
return {
"lat": float(best["latitude"]),
"lon": float(best["longitude"]),
"country_code": best.get("countrycode", ""),
"normalized_name": best["name"],
"confidence": min(1.0, 0.6 + (best.get("population", 0) / 10_000_000)),
}
if not matches:
return None
# 2. Laendersuche
countries = gc.get_countries()
for code, country in countries.items():
if country.get("name", "").lower() == name_lower:
capital = country.get("capital", "")
if capital:
cap_result = _geocode_offline(capital)
if cap_result:
cap_result["normalized_name"] = country["name"]
cap_result["confidence"] = 0.5
return cap_result
return None
# Disambiguierung: country_code bevorzugen, dann Population
if country_code:
cc_matches = [c for c in matches if c.get("countrycode", "").upper() == (country_code or "").upper()]
if cc_matches:
matches = cc_matches
best = max(matches, key=lambda c: c.get("population", 0))
return {
"lat": float(best["latitude"]),
"lon": float(best["longitude"]),
"country_code": best.get("countrycode", ""),
"normalized_name": best["name"],
"confidence": min(1.0, 0.6 + (best.get("population", 0) / 10_000_000)),
}
def _geocode_location(name: str, country_code: str = "", haiku_coords: Optional[dict] = None) -> Optional[dict]: