Files
planet/backend/app/services/bgp_enrichment.py

426 lines
14 KiB
Python

"""Enrichment helpers for BGP observation and anomaly pipelines."""
from __future__ import annotations
import ipaddress
from collections import defaultdict
from datetime import UTC, datetime
from typing import Any
from sqlalchemy import Integer, cast, select, text
from sqlalchemy.ext.asyncio import AsyncSession
from app.core.countries import get_country_centroid, normalize_country
from app.models.bgp_observation import BGPObservation
from app.models.collected_data import CollectedData
def _safe_int(value: Any) -> int | None:
try:
if value in (None, ""):
return None
return int(value)
except (TypeError, ValueError):
return None
def _parse_timestamp(value: Any) -> datetime:
if isinstance(value, datetime):
return value.astimezone(UTC) if value.tzinfo else value.replace(tzinfo=UTC)
if isinstance(value, (int, float)):
return datetime.fromtimestamp(value, tz=UTC)
if isinstance(value, str) and value:
normalized = value.replace("Z", "+00:00")
parsed = datetime.fromisoformat(normalized)
return parsed.astimezone(UTC) if parsed.tzinfo else parsed.replace(tzinfo=UTC)
return datetime.now(UTC)
def _dedupe_as_path(as_path: list[int]) -> list[int]:
deduped: list[int] = []
for asn in as_path:
if not deduped or deduped[-1] != asn:
deduped.append(asn)
return deduped
def _compact_locations(items: list[dict[str, Any]]) -> list[dict[str, Any]]:
results: list[dict[str, Any]] = []
seen: set[tuple[Any, ...]] = set()
for item in items:
key = (
item.get("country"),
item.get("city"),
item.get("latitude"),
item.get("longitude"),
)
if key in seen:
continue
seen.add(key)
results.append(item)
return results
def extract_bgp_network_fields(prefix: str) -> dict[str, Any]:
if not prefix:
return {
"prefix_family": None,
"prefix_length": None,
"prefix_supernet": None,
"is_more_specific": False,
}
try:
network = ipaddress.ip_network(prefix, strict=False)
except ValueError:
return {
"prefix_family": None,
"prefix_length": None,
"prefix_supernet": None,
"is_more_specific": False,
}
supernet_prefix = 16 if network.version == 4 else 32
if network.prefixlen > supernet_prefix:
prefix_supernet = str(network.supernet(new_prefix=supernet_prefix))
else:
prefix_supernet = str(network)
return {
"prefix_family": f"ipv{network.version}",
"prefix_length": int(network.prefixlen),
"prefix_supernet": prefix_supernet,
"is_more_specific": network.prefixlen > (24 if network.version == 4 else 48),
}
async def _lookup_prefix_geography(
db: AsyncSession,
prefix_values: list[str],
) -> dict[str, dict[str, Any]]:
async def _query_prefix_metadata(
*,
source: str,
family: str,
range_start: str,
range_end: str,
) -> dict[str, Any] | None:
result = await db.execute(
text(
"""
SELECT metadata
FROM collected_data
WHERE source = :source
AND COALESCE(is_current, TRUE) = TRUE
AND metadata->>'family' = :family
AND CAST(metadata->>'range_start' AS inet) <= CAST(:range_start AS inet)
AND CAST(metadata->>'range_end' AS inet) >= CAST(:range_end AS inet)
ORDER BY
masklen(CAST(metadata->>'prefix' AS cidr)) DESC NULLS LAST,
id DESC
LIMIT 1
"""
),
{
"source": source,
"family": family,
"range_start": range_start,
"range_end": range_end,
},
)
row = result.fetchone()
if not row:
return None
if isinstance(row, dict):
payload = row.get("metadata") or row.get("extra_data")
elif hasattr(row, "_mapping"):
payload = row._mapping.get("metadata") or row._mapping.get("extra_data")
else:
payload = row[0]
return payload if isinstance(payload, dict) else None
results: dict[str, dict[str, Any]] = {}
for prefix in prefix_values:
try:
network = ipaddress.ip_network(prefix, strict=False)
except ValueError:
continue
family = f"ipv{network.version}"
range_start = str(network.network_address)
range_end = str(network.broadcast_address)
payload = await _query_prefix_metadata(
source="opengeofeed_prefix_geo",
family=family,
range_start=range_start,
range_end=range_end,
)
selected_source = "opengeofeed"
if not payload:
payload = await _query_prefix_metadata(
source="iptoasn_prefix_geo",
family=family,
range_start=range_start,
range_end=range_end,
)
selected_source = "iptoasn"
if not payload:
payload = await _query_prefix_metadata(
source="nro_delegated_prefix_geo",
family=family,
range_start=range_start,
range_end=range_end,
)
selected_source = "nro_delegated"
if not payload:
continue
country = normalize_country(payload.get("country") or payload.get("country_code"))
prefix_hint = payload.get("prefix") or prefix
asn = _safe_int(payload.get("asn"))
as_name = payload.get("as_name")
city = payload.get("city")
centroid = get_country_centroid(country)
regions = []
if country:
regions.append(
{
"country": country,
"city": city,
"latitude": centroid.get("latitude") if centroid else None,
"longitude": centroid.get("longitude") if centroid else None,
}
)
results[prefix] = {
"prefix": prefix_hint,
"country": country,
"city": city,
"asn": asn,
"as_name": as_name,
"source": payload.get("source_dataset")
or (
"opengeofeed_public"
if selected_source == "opengeofeed"
else (
"iptoasn_combined"
if selected_source == "iptoasn"
else "nro_delegated_stats"
)
),
"confidence": payload.get("confidence")
or (
"geofeed"
if selected_source == "opengeofeed"
else (
"country_range"
if selected_source == "iptoasn"
else "registry_allocated"
)
),
"geography_mode": "prefix_geography",
"regions": regions,
}
return results
async def enrich_bgp_events_for_batch(
db: AsyncSession,
*,
source: str,
events: list[dict[str, Any]],
) -> list[dict[str, Any]]:
if not events:
return []
prefixes = {
str((event.get("metadata") or {}).get("prefix") or "").strip()
for event in events
if (event.get("metadata") or {}).get("prefix")
}
prefix_values = sorted(prefix for prefix in prefixes if prefix)
origin_asns = sorted(
{
asn
for event in events
for asn in [
_safe_int((event.get("metadata") or {}).get("origin_asn")),
_safe_int((event.get("metadata") or {}).get("new_origin_asn")),
]
if asn is not None
}
)
historical_prefix_baseline: dict[str, dict[str, Any]] = {}
if prefix_values:
previous_result = await db.execute(
select(
BGPObservation.prefix,
BGPObservation.origin_asn,
BGPObservation.collector,
BGPObservation.collector_geo,
).where(
BGPObservation.source == source,
BGPObservation.prefix.in_(prefix_values),
)
)
by_prefix: defaultdict[str, list[dict[str, Any]]] = defaultdict(list)
for prefix, origin_asn, collector, collector_geo in previous_result.all():
if prefix:
by_prefix[str(prefix)].append(
{
"origin_asn": origin_asn,
"collector": collector,
"collector_geo": collector_geo or {},
}
)
for prefix, observations in by_prefix.items():
unique_origins = sorted(
{
observation["origin_asn"]
for observation in observations
if observation["origin_asn"] is not None
}
)
unique_collectors = sorted(
{
observation["collector"]
for observation in observations
if observation["collector"]
}
)
historical_prefix_baseline[prefix] = {
"historical_origin_asns": unique_origins,
"historical_collectors": unique_collectors,
"historical_observation_count": len(observations),
"historical_regions": _compact_locations(
[
observation["collector_geo"] or {}
for observation in observations
if observation["collector_geo"]
]
),
}
asn_profiles: dict[int, dict[str, Any]] = {}
prefix_geographies = await _lookup_prefix_geography(db, prefix_values) if prefix_values else {}
if origin_asns:
peeringdb_result = await db.execute(
select(CollectedData)
.where(CollectedData.source == "peeringdb_network")
.where(CollectedData.is_current.is_(True))
.where(
cast(CollectedData.extra_data["asn"].as_string(), Integer).in_(origin_asns),
)
.order_by(CollectedData.id.desc())
)
for record in peeringdb_result.scalars().all():
metadata = record.extra_data or {}
asn = _safe_int(metadata.get("asn"))
if asn is None or asn not in origin_asns:
continue
current = asn_profiles.get(asn)
if current and (current.get("id") or 0) > (record.id or 0):
continue
asn_profiles[asn] = {
"id": record.id,
"asn": asn,
"name": record.name,
"country": metadata.get("country"),
"city": metadata.get("city"),
"source": "peeringdb_network",
"info_type": metadata.get("info_type"),
"info_traffic": metadata.get("info_traffic"),
"info_ratio": metadata.get("info_ratio"),
"ix_count": metadata.get("ix_count"),
"url": metadata.get("url"),
}
collector_counts: defaultdict[str, int] = defaultdict(int)
for event in events:
collector = (event.get("metadata") or {}).get("collector")
if collector:
collector_counts[str(collector)] += 1
enriched: list[dict[str, Any]] = []
for event in events:
metadata = dict(event.get("metadata") or {})
prefix = str(metadata.get("prefix") or "").strip()
as_path = metadata.get("as_path") or []
normalized_as_path = [asn for asn in (_safe_int(item) for item in as_path) if asn is not None]
deduped_as_path = _dedupe_as_path(normalized_as_path)
collector = str(metadata.get("collector") or "").strip()
collector_location = metadata.get("collector_location") or {}
baseline = historical_prefix_baseline.get(prefix, {})
prefix_geography = prefix_geographies.get(prefix)
observed_at = _parse_timestamp(metadata.get("timestamp") or event.get("reference_date"))
origin_asn = _safe_int(metadata.get("origin_asn"))
new_origin_asn = _safe_int(metadata.get("new_origin_asn"))
baseline_regions = baseline.get("historical_regions", [])
prefix_scope_regions = _compact_locations([*baseline_regions])
enrichment = {
**extract_bgp_network_fields(prefix),
"observed_at": observed_at.isoformat(),
"normalized_as_path": normalized_as_path,
"deduped_as_path": deduped_as_path,
"deduped_as_path_length": len(deduped_as_path),
"path_prepending": len(normalized_as_path) > len(deduped_as_path),
"collector_region": {
"city": collector_location.get("city"),
"country": collector_location.get("country"),
},
"collector_observation_count_in_batch": collector_counts.get(collector, 0),
"batch_visibility_collectors": sorted(collector_counts.keys()),
"prefix_baseline": baseline,
"is_new_origin_for_prefix": (
origin_asn is not None
and origin_asn
not in set(baseline.get("historical_origin_asns", []))
),
"rpki_validation": {
"status": "unknown",
"reason": "no_rpki_roa_dataset_configured",
},
"origin_asn_profile": asn_profiles.get(origin_asn),
"new_origin_asn_profile": asn_profiles.get(new_origin_asn),
"prefix_geography": prefix_geography,
"prefix_scope": {
"countries": sorted(
{
item.get("country")
for item in prefix_scope_regions
if item.get("country")
}
),
"cities": sorted(
{
item.get("city")
for item in prefix_scope_regions
if item.get("city")
}
),
"regions": prefix_scope_regions,
},
}
enriched.append(
{
**event,
"metadata": {
**metadata,
"enrichment": enrichment,
},
}
)
return enriched