analytics/app/clients/google.py

"""Shared Google API client used by Analytics, Search Console and Google Ads.

A single Google OAuth mechanism backs all three services - the only difference
is the OAuth *scope* (carried on ``GoogleCredentials.scope``) and, for Google
Ads, a couple of extra headers. Request/response bodies are forwarded as-is so
callers keep the full upstream API surface; this module only handles
authentication (Bearer token), the optional quota-project header and error
mapping.

Auth (token wins over service account):
  * If an access token was supplied in the header, it is used directly.
  * Otherwise a short-lived access token is minted from the service-account JSON
    via google-auth for the requested scope and cached in-memory (keyed by
    key id + email + scope) until shortly before it expires. Key material is
    never written to disk or log.
"""
from __future__ import annotations

import hashlib
import threading
import time
from typing import Any

import httpx
from fastapi.concurrency import run_in_threadpool

from .. import config
from ..credentials import GoogleCredentials
from ..errors import MissingCredentialsError, UpstreamError
from ..logging_config import get_logger

logger = get_logger(__name__)

# In-memory access-token cache: { cache_key: (token, expiry_epoch_seconds) }.
# Memory only - mirrors the stateless design (no secret ever persisted).
_token_cache: dict[str, tuple[str, float]] = {}
_token_lock = threading.Lock()

# Refresh a minted token this many seconds before its real expiry.
_EXPIRY_SKEW = 60.0


def _mint_token_sync(info: dict, scope: str) -> tuple[str, float]:
    """Mint an OAuth2 access token from a service-account key (blocking)."""
    # Imported lazily so the module imports even if google-auth is missing,
    # and so the dependency is only needed when service-account auth is used.
    from google.auth.transport.requests import Request
    from google.oauth2 import service_account

    try:
        creds = service_account.Credentials.from_service_account_info(
            info, scopes=[scope]
        )
    except (ValueError, KeyError) as exc:
        raise MissingCredentialsError(
            f"Service-account credentials are not usable: {exc}"
        ) from exc

    try:
        creds.refresh(Request())
    except Exception as exc:  # google.auth.exceptions.RefreshError and friends
        # Surface as upstream auth failure - do NOT log the key material.
        raise UpstreamError(
            f"Failed to obtain Google access token from service account: {exc}",
            status=401,
        ) from exc

    expiry = creds.expiry.timestamp() if creds.expiry else (time.time() + 3600)
    return creds.token, expiry


def _cache_key(info: dict, scope: str) -> str:
    # Identify a key by its private_key_id + client_email + scope. Hashed so the
    # raw identifiers never sit in a dict key we might later log.
    raw = f"{info.get('private_key_id', '')}|{info.get('client_email', '')}|{scope}"
    return hashlib.sha256(raw.encode("utf-8")).hexdigest()


async def bearer_token(creds: GoogleCredentials) -> str:
    if creds.access_token:
        return creds.access_token

    if creds.service_account_info is None:
        # Credential dependencies guarantee one of the two, but be defensive.
        raise MissingCredentialsError(
            "No Google access token and no service-account credentials available."
        )

    scope = creds.scope
    key = _cache_key(creds.service_account_info, scope)
    now = time.time()

    with _token_lock:
        cached = _token_cache.get(key)
        if cached and cached[1] - _EXPIRY_SKEW > now:
            return cached[0]

    # Mint outside the lock (network call); google-auth is blocking, so offload
    # it to a thread to avoid stalling the event loop.
    token, expiry = await run_in_threadpool(
        _mint_token_sync, creds.service_account_info, scope
    )
    with _token_lock:
        _token_cache[key] = (token, expiry)
    return token


class GoogleApiClient:
    """Authenticated HTTP client for any Google REST API.

    ``extra_headers`` lets callers add upstream-specific headers (e.g. the
    Google Ads ``developer-token`` / ``login-customer-id``).
    """

    def __init__(
        self,
        creds: GoogleCredentials,
        extra_headers: dict[str, str] | None = None,
        *,
        service_name: str = "Google",
    ) -> None:
        self._creds = creds
        self._extra_headers = extra_headers or {}
        self._service_name = service_name

    async def request(
        self,
        method: str,
        url: str,
        *,
        params: dict | None = None,
        json_body: Any | None = None,
    ) -> Any:
        token = await bearer_token(self._creds)
        headers = {"Authorization": f"Bearer {token}"}
        if self._creds.quota_project:
            headers["x-goog-user-project"] = self._creds.quota_project
        headers.update(self._extra_headers)

        try:
            async with httpx.AsyncClient(
                timeout=config.HTTP_TIMEOUT_SECONDS
            ) as client:
                resp = await client.request(
                    method, url, params=params, json=json_body, headers=headers
                )
        except httpx.TimeoutException as exc:
            raise UpstreamError(
                f"{self._service_name} request timed out.", status=504
            ) from exc
        except httpx.HTTPError as exc:
            raise UpstreamError(
                f"{self._service_name} is unreachable: {exc}", status=502
            ) from exc

        return _parse_google_response(resp, self._service_name)

    async def get(self, url: str, params: dict | None = None) -> Any:
        return await self.request("GET", url, params=params)

    async def post(self, url: str, json_body: Any) -> Any:
        return await self.request("POST", url, json_body=json_body)


def _parse_google_response(resp: httpx.Response, service_name: str) -> Any:
    try:
        payload = resp.json()
    except ValueError:
        payload = {"raw": resp.text}

    if resp.is_success:
        return payload

    # Google returns {"error": {"code", "message", "status", ...}}; Google Ads
    # streaming returns a list whose first element may carry the error.
    message = f"{service_name} API error"
    err_obj: Any = None
    if isinstance(payload, dict):
        err_obj = payload.get("error")
    elif isinstance(payload, list) and payload and isinstance(payload[0], dict):
        err_obj = payload[0].get("error")
    if isinstance(err_obj, dict) and err_obj.get("message"):
        message = err_obj["message"]

    raise UpstreamError(
        message,
        status=502 if resp.status_code >= 500 else resp.status_code,
        upstream_status=resp.status_code,
        body=payload,
    )