guarddog-nexus/guarddog_nexus/routes/webhooks.py

"""Nexus webhook receiver — handles component/asset webhooks."""

import hashlib
import hmac
import json
import re

from fastapi import APIRouter, BackgroundTasks, Header, HTTPException, Request, status

from ..config import config
from ..constants import (
    DEFAULT_ECOSYSTEM,
    METADATA_PATTERNS,
    PACKAGE_EXTENSIONS,
    RELEVANT_WEBHOOK_ACTIONS,
    WEBHOOK_IGNORE_NO_ASSET_OR_COMPONENT,
    WEBHOOK_IGNORE_NO_NAME_OR_VERSION,
    WEBHOOK_IGNORE_NON_PACKAGE,
    WEBHOOK_STATUS_ACCEPTED,
    WEBHOOK_STATUS_IGNORED,
)
from ..core.harvester import harvest
from ..db.engine import get_session
from ..logging_setup import log

router = APIRouter(prefix="/webhooks", tags=["webhooks"])

_METADATA_RE = [re.compile(p) for p in METADATA_PATTERNS]


def _is_package_asset(name: str) -> bool:
    for pat in _METADATA_RE:
        if pat.search(name):
            return False
    return name.endswith(PACKAGE_EXTENSIONS)


def _build_download_url(repo: str, asset_path: str) -> str:
    base = config.nexus_url.rstrip("/")
    asset_path = asset_path.strip("/")
    return f"{base}/repository/{repo}/{asset_path}"


def _extract_asset_path(asset: dict) -> str | None:
    for key in ("path", "name"):
        val = asset.get(key)
        if val:
            return val
    return None


def _detect_ecosystem(source: dict) -> str:
    """Detect ecosystem from asset or component format field."""
    fmt = source.get("format", "").lower()
    if fmt in ("pypi", "pip", "python"):
        return "pypi"
    if fmt in ("go", "golang"):
        return "go"
    if fmt in ("npm", "node"):
        return "npm"
    return fmt or DEFAULT_ECOSYSTEM


@router.post("/nexus")
async def nexus_webhook(
    request: Request,
    background_tasks: BackgroundTasks,
    x_nexus_webhook_signature: str | None = Header(None, alias="X-Nexus-Webhook-Signature"),
):
    payload = await request.body()

    if config.webhook_secret:
        if not x_nexus_webhook_signature:
            log.warning("Webhook rejected: missing signature header")
            raise HTTPException(
                status_code=status.HTTP_401_UNAUTHORIZED, detail="Missing signature"
            )
        expected = hmac.new(
            config.webhook_secret.encode(), payload, hashlib.sha256
        ).hexdigest()
        if not hmac.compare_digest(x_nexus_webhook_signature, expected):
            log.warning("Webhook rejected: invalid signature")
            raise HTTPException(
                status_code=status.HTTP_403_FORBIDDEN, detail="Invalid signature"
            )

    try:
        data = json.loads(payload.decode("utf-8"))
    except json.JSONDecodeError:
        log.warning("Webhook received invalid JSON")
        raise HTTPException(
            status_code=status.HTTP_400_BAD_REQUEST, detail="Invalid JSON"
        )

    action = data.get("action", "").upper()
    if action not in RELEVANT_WEBHOOK_ACTIONS:
        return {"status": WEBHOOK_STATUS_IGNORED, "action": action}

    # Nexus sends initiator as "username/IP" — parse both fields
    raw_initiator = data.get("initiator", "")
    initiator = None
    source_ip = None
    if raw_initiator and "/" in raw_initiator:
        parts = raw_initiator.rsplit("/", 1)
        initiator = parts[0]
        source_ip = parts[1]
    elif raw_initiator:
        initiator = raw_initiator
        source_ip = request.client.host if request.client else None

    log.info("Webhook: action=%s initiator=%s source_ip=%s",
             action, initiator, source_ip)

    repository = data.get("repositoryName", "")
    asset = data.get("asset")
    component = data.get("component")

    if asset:
        asset_path = _extract_asset_path(asset)
        if not asset_path or not _is_package_asset(asset_path):
            return {"status": WEBHOOK_STATUS_IGNORED, "reason": WEBHOOK_IGNORE_NON_PACKAGE}

        download_url = asset.get("downloadUrl") or _build_download_url(
            repository, asset_path
        )
        ecosystem = _detect_ecosystem(asset)

        log.info("Webhook: %s asset %s (%s) in %s", action, asset_path, ecosystem, repository)

        background_tasks.add_task(
            _scan_in_background, download_url, repository, ecosystem, asset_path,
            initiator=initiator, source_ip=source_ip,
        )
        return {"status": WEBHOOK_STATUS_ACCEPTED, "asset": asset_path, "action": action}

    if component:
        name = component.get("name", "")
        version = component.get("version", "")
        if not name or not version:
            return {
                "status": WEBHOOK_STATUS_IGNORED,
                "reason": WEBHOOK_IGNORE_NO_NAME_OR_VERSION,
            }

        ecosystem = _detect_ecosystem(component)
        background_tasks.add_task(_scan_component, repository, name, version, ecosystem)
        return {
            "status": WEBHOOK_STATUS_ACCEPTED,
            "component": f"{name}=={version}",
            "action": action,
        }

    return {
        "status": WEBHOOK_STATUS_IGNORED,
        "reason": WEBHOOK_IGNORE_NO_ASSET_OR_COMPONENT,
    }


async def _scan_component(repository: str, name: str, version: str, ecosystem: str):
    from ..core.nexus import nexus_get

    api_path = (
        f"/service/rest/v1/search"
        f"?repository={repository}&name={name}&version={version}&format={ecosystem}"
    )
    try:
        resp = await nexus_get(api_path)
        resp.raise_for_status()
        data = resp.json()
    except Exception as e:
        log.warning("Component lookup error for %s==%s: %s", name, version, e)
        return

    items = data.get("items", [])
    if not items:
        log.warning("No items found in search for %s==%s", name, version)
        return

    for item in items:
        for asset in item.get("assets", []):
            asset_path = _extract_asset_path(asset)
            if not asset_path or not _is_package_asset(asset_path):
                continue
            download_url = asset.get("downloadUrl") or _build_download_url(
                repository, asset_path
            )
            log.info("Scanning component asset: %s", asset_path)
            async for session in get_session():
                await harvest(
                    download_url, repository, ecosystem, asset_path, session
                )
                break


async def _scan_in_background(
    download_url: str,
    repository: str,
    format_: str,
    asset_path: str,
    initiator: str | None = None,
    source_ip: str | None = None,
):
    try:
        async for session in get_session():
            await harvest(
                download_url, repository, format_, asset_path, session,
                initiator=initiator, source_ip=source_ip,
            )
            break
    except Exception as e:
        log.error("Background scan failed: %s", e)