208 lines
7.9 KiB
Python
208 lines
7.9 KiB
Python
"""IPtoASN prefix geography collector.
|
|
|
|
Downloads the public combined IPv4+IPv6 TSV database and stores coarse
|
|
prefix-to-country/ASN geography hints for BGP enrichment.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import asyncio
|
|
import gzip
|
|
import time
|
|
from datetime import UTC, datetime
|
|
from ipaddress import summarize_address_range, ip_address
|
|
from pathlib import Path
|
|
from typing import Any
|
|
|
|
import httpx
|
|
|
|
from app.services.collectors.base import BaseCollector
|
|
from app.services.collectors.downloads import ResumableFileDownloader
|
|
|
|
|
|
class IPtoASNPrefixGeoCollector(BaseCollector):
|
|
name = "iptoasn_prefix_geo"
|
|
priority = "P1"
|
|
module = "L3"
|
|
frequency_hours = 24
|
|
data_type = "prefix_geography"
|
|
fail_on_empty = True
|
|
_downloader = ResumableFileDownloader(
|
|
cache_namespace="iptoasn",
|
|
default_accept="application/gzip,application/octet-stream,*/*",
|
|
)
|
|
|
|
@staticmethod
|
|
def _build_dataset_urls(resolved_url: str) -> list[str]:
|
|
if "ip2asn-combined.tsv.gz" in resolved_url:
|
|
return [
|
|
resolved_url.replace("ip2asn-combined.tsv.gz", "ip2asn-v4.tsv.gz"),
|
|
resolved_url.replace("ip2asn-combined.tsv.gz", "ip2asn-v6.tsv.gz"),
|
|
]
|
|
return [resolved_url]
|
|
|
|
def _parse_rows_from_gzip_file(self, file_path: Path) -> list[dict[str, Any]]:
|
|
rows: list[dict[str, Any]] = []
|
|
with gzip.open(file_path, "rt", encoding="utf-8", errors="replace") as f:
|
|
for raw_line in f:
|
|
line = raw_line.strip()
|
|
if not line or line.startswith("#"):
|
|
continue
|
|
parts = line.split("\t")
|
|
if len(parts) < 5:
|
|
continue
|
|
range_start, range_end, asn, country_code, as_name = parts[:5]
|
|
rows.append(
|
|
{
|
|
"range_start": range_start,
|
|
"range_end": range_end,
|
|
"asn": asn,
|
|
"country_code": country_code,
|
|
"as_name": as_name,
|
|
}
|
|
)
|
|
if not rows:
|
|
raise RuntimeError(f"IPtoASN dataset parsed empty rows: {file_path.name}")
|
|
return rows
|
|
|
|
async def _fetch_dataset_rows(
|
|
self,
|
|
client: httpx.AsyncClient,
|
|
url: str,
|
|
*,
|
|
progress_callback=None,
|
|
) -> list[dict[str, Any]]:
|
|
file_path = await self._downloader.download_file(
|
|
client,
|
|
url,
|
|
extension=".tsv.gz",
|
|
progress_callback=progress_callback,
|
|
validate_existing=lambda p: self._validate_gzip_dataset(p),
|
|
)
|
|
return self._parse_rows_from_gzip_file(file_path)
|
|
|
|
def _validate_gzip_dataset(self, file_path: Path) -> bool:
|
|
try:
|
|
self._parse_rows_from_gzip_file(file_path)
|
|
return True
|
|
except Exception:
|
|
return False
|
|
|
|
async def fetch(self) -> list[dict[str, Any]]:
|
|
if not self._resolved_url:
|
|
raise RuntimeError("IPtoASN combined URL is not configured")
|
|
|
|
dataset_urls = self._build_dataset_urls(self._resolved_url)
|
|
|
|
async with httpx.AsyncClient(timeout=180.0, follow_redirects=True) as client:
|
|
remote_infos = await asyncio.gather(
|
|
*(self._downloader.fetch_remote_info(client, url) for url in dataset_urls)
|
|
)
|
|
expected_sizes = [
|
|
info.get("content_length")
|
|
for info in remote_infos
|
|
if isinstance(info.get("content_length"), int)
|
|
]
|
|
total_expected = sum(expected_sizes) if expected_sizes else 0
|
|
if total_expected > 0 and self._current_task and self._db_session:
|
|
self._current_task.total_records = total_expected
|
|
self._current_task.records_processed = 0
|
|
self._current_task.progress = 0.0
|
|
await self._db_session.commit()
|
|
await self._publish_task_update(force=True)
|
|
|
|
url_progress: dict[str, int] = {url: 0 for url in dataset_urls}
|
|
progress_lock = asyncio.Lock()
|
|
last_emit = {"t": 0.0, "value": 0}
|
|
min_emit_bytes = max(total_expected // 200, 2 * 1024 * 1024) if total_expected > 0 else 4 * 1024 * 1024
|
|
|
|
async def on_url_progress(url: str, downloaded_bytes: int, total_bytes: int | None) -> None:
|
|
if total_expected <= 0:
|
|
return
|
|
async with progress_lock:
|
|
current = max(0, downloaded_bytes)
|
|
if current < url_progress[url]:
|
|
return
|
|
url_progress[url] = current
|
|
aggregated = sum(url_progress.values())
|
|
now = time.monotonic()
|
|
should_emit = (
|
|
aggregated >= total_expected
|
|
or aggregated - last_emit["value"] >= min_emit_bytes
|
|
or now - last_emit["t"] >= 2.0
|
|
)
|
|
if not should_emit:
|
|
return
|
|
last_emit["value"] = aggregated
|
|
last_emit["t"] = now
|
|
await self.update_progress(min(aggregated, total_expected), commit=True)
|
|
|
|
batches = await asyncio.gather(
|
|
*(
|
|
self._fetch_dataset_rows(
|
|
client,
|
|
url,
|
|
progress_callback=lambda downloaded, total, u=url: on_url_progress(u, downloaded, total),
|
|
)
|
|
for url in dataset_urls
|
|
)
|
|
)
|
|
if total_expected > 0:
|
|
await self.update_progress(total_expected, commit=True, force=True)
|
|
|
|
rows: list[dict[str, Any]] = []
|
|
for batch in batches:
|
|
rows.extend(batch)
|
|
return rows
|
|
|
|
def transform(self, raw_data: list[dict[str, Any]]) -> list[dict[str, Any]]:
|
|
reference_date = datetime.now(UTC).isoformat()
|
|
transformed: list[dict[str, Any]] = []
|
|
|
|
for item in raw_data:
|
|
try:
|
|
start_ip = ip_address(str(item["range_start"]))
|
|
end_ip = ip_address(str(item["range_end"]))
|
|
except ValueError:
|
|
continue
|
|
|
|
if start_ip.version != end_ip.version:
|
|
continue
|
|
|
|
summarized = list(summarize_address_range(start_ip, end_ip))
|
|
primary_prefix = str(summarized[0]) if summarized else f"{start_ip}/{32 if start_ip.version == 4 else 128}"
|
|
family = f"ipv{start_ip.version}"
|
|
|
|
asn_value = item.get("asn")
|
|
try:
|
|
normalized_asn = int(str(asn_value))
|
|
except (TypeError, ValueError):
|
|
normalized_asn = None
|
|
|
|
transformed.append(
|
|
{
|
|
"source_id": f"{family}:{item['range_start']}-{item['range_end']}",
|
|
"name": primary_prefix,
|
|
"title": f"{primary_prefix} {item.get('country_code', '').strip()}".strip(),
|
|
"country": item.get("country_code"),
|
|
"city": "",
|
|
"latitude": None,
|
|
"longitude": None,
|
|
"metadata": {
|
|
"family": family,
|
|
"range_start": item["range_start"],
|
|
"range_end": item["range_end"],
|
|
"prefix": primary_prefix,
|
|
"prefixes": [str(prefix) for prefix in summarized[:8]],
|
|
"range_prefix_count": len(summarized),
|
|
"country_code": item.get("country_code"),
|
|
"asn": normalized_asn,
|
|
"as_name": item.get("as_name"),
|
|
"source_dataset": "iptoasn_combined",
|
|
},
|
|
"reference_date": reference_date,
|
|
}
|
|
)
|
|
|
|
return transformed
|