"""HTTP helpers for the HubSpot PLG pipeline."""

import logging
import urllib.parse
from typing import Any, Dict, Iterator, List, Optional

from dlt.sources.helpers import requests

logger = logging.getLogger(__name__)

BASE_URL = "https://api.hubapi.com/"


def get_url(endpoint: str) -> str:
    return urllib.parse.urljoin(BASE_URL, endpoint)


def _get_headers(api_key: str) -> Dict[str, str]:
    return {"authorization": f"Bearer {api_key}"}


def fetch_crm_objects(
    endpoint: str,
    api_key: str,
    params: Optional[Dict[str, Any]] = None,
) -> Iterator[List[Dict[str, Any]]]:
    """Paginated GET for CRM v3 endpoints. Flattens each result's
    ``properties`` dict into the top-level row and preserves ``id``."""
    url = get_url(endpoint)
    headers = _get_headers(api_key)
    params = dict(params or {})

    while True:
        r = requests.get(url, headers=headers, params=params)
        data = r.json()

        results = data.get("results", [])
        if results:
            page: List[Dict[str, Any]] = []
            for item in results:
                obj = item.get("properties", item)
                if "id" not in obj and "id" in item:
                    obj["id"] = item["id"]
                page.append(obj)
            yield page

        after = (data.get("paging") or {}).get("next", {}).get("after")
        if not after:
            break
        params["after"] = after


def fetch_get_pages(
    endpoint: str,
    api_key: str,
    params: Optional[Dict[str, Any]] = None,
    results_key: str = "results",
) -> Iterator[List[Dict[str, Any]]]:
    """Generic paginated GET that yields raw result dicts (no property
    flattening). Works for /marketing/v3/emails, /automation/v4/flows,
    /marketing/v3/forms, etc."""
    url = get_url(endpoint)
    headers = _get_headers(api_key)
    params = dict(params or {})

    while True:
        r = requests.get(url, headers=headers, params=params)
        data = r.json()

        results = data.get(results_key, [])
        if results:
            yield results

        after = (data.get("paging") or {}).get("next", {}).get("after")
        if not after:
            break
        params["after"] = after


def fetch_post_pages(
    endpoint: str,
    api_key: str,
    body: Optional[Dict[str, Any]] = None,
    results_key: str = "lists",
    offset_key: str = "offset",
    count_key: str = "count",
    page_size: int = 250,
) -> Iterator[List[Dict[str, Any]]]:
    """Paginated POST (used by /crm/v3/lists/search which uses offset-based
    pagination)."""
    url = get_url(endpoint)
    headers = {**_get_headers(api_key), "Content-Type": "application/json"}
    body = dict(body or {})
    body.setdefault(offset_key, 0)
    body.setdefault(count_key, page_size)

    while True:
        r = requests.post(url, headers=headers, json=body)
        data = r.json()

        results = data.get(results_key, [])
        if results:
            yield results

        total = data.get("total")
        body[offset_key] += len(results)
        if not results or (total is not None and body[offset_key] >= total):
            break


def fetch_json(
    endpoint: str,
    api_key: str,
    params: Optional[Dict[str, Any]] = None,
) -> Dict[str, Any]:
    """Single GET request returning raw JSON (no pagination)."""
    url = get_url(endpoint)
    headers = _get_headers(api_key)
    r = requests.get(url, headers=headers, params=params)
    return r.json()


def fetch_form_submissions(
    form_guid: str,
    api_key: str,
    limit: int = 50,
) -> Iterator[List[Dict[str, Any]]]:
    """Paginated GET for form submission endpoint which uses cursor-based
    ``after`` in the response body."""
    endpoint = f"/form-integrations/v1/submissions/forms/{form_guid}"
    url = get_url(endpoint)
    headers = _get_headers(api_key)
    params: Dict[str, Any] = {"limit": limit}

    while True:
        r = requests.get(url, headers=headers, params=params)
        data = r.json()

        results = data.get("results", [])
        if results:
            yield results

        after = data.get("paging", {}).get("next", {}).get("after")
        if not after:
            break
        params["after"] = after