"""Tests for the WeChat chat-group scraper (M2).

Drives the real page-number pagination + normalization logic through
``respx`` by wiring a real ``YunkeClient`` (primed with a fake session so the
login flow is skipped) against a mocked transport.

The fixture ships 3 records across 2 pages of size 2, plus a terminating
empty page (the documented primary stop signal for page-number endpoints):

* page 1 -> 2 records, ``total=3``
* page 2 -> 1 record, ``total=3``
* page 3 -> empty ``data`` array (no more rows)

The scraper must yield exactly the 3 records (normalized to ``ChatGroup``
snake_case columns + ``raw_json``), parse ``memberIds`` into
``member_ids_list`` (dropping empty segments), make exactly 3 calls, and stop
without a 4th.
"""

from __future__ import annotations

import json as _json

import httpx
import respx

from app.scraper.wechat import scrape_wechat_groups
from app.session.yunke_client import YunkeClient
from tests.cassettes.chatroom_fixture import (
    CHATROOM_RECORDS,
    DEFAULT_PAGE_SIZE,
    TOTAL,
    make_chatroom_list_response,
)

BASE = "https://crm2.yunkecn.com"
CHATROOM_LIST_URL = f"{BASE}/wechatweb/chatroom/getChatroomList"

USERID = "a" * 32
COMPANY = "8m0atd"


def _primed_client() -> YunkeClient:
    """A YunkeClient already in a logged-in state (login flow skipped)."""
    return YunkeClient(base_url=BASE, userid=USERID, company=COMPANY)


# ---------------------------------------------------------------------------
# End-to-end: pagination + field mapping + member_ids_list parsing
# ---------------------------------------------------------------------------


@respx.mock
async def test_scrape_wechat_groups_yields_records_and_paginates():
    """Two full pages + a terminating empty page -> 3 records, 3 calls."""
    page1 = make_chatroom_list_response(
        CHATROOM_RECORDS[:2], total=TOTAL, page_num=1, page_size=DEFAULT_PAGE_SIZE
    )
    page2 = make_chatroom_list_response(
        CHATROOM_RECORDS[2:], total=TOTAL, page_num=2, page_size=DEFAULT_PAGE_SIZE
    )
    page3 = make_chatroom_list_response(
        [], total=TOTAL, page_num=3, page_size=DEFAULT_PAGE_SIZE
    )

    route = respx.post(CHATROOM_LIST_URL).mock(
        side_effect=[
            httpx.Response(200, json=page1),
            httpx.Response(200, json=page2),
            httpx.Response(200, json=page3),
        ]
    )

    client = _primed_client()
    try:
        results = [
            r async for r in scrape_wechat_groups(client, page_size=DEFAULT_PAGE_SIZE)
        ]
    finally:
        await client.aclose()

    # Pagination: exactly 3 calls (page1, page2, empty-page stop).
    assert route.call_count == 3

    # Exactly the 3 fixture records (not duplicated, not dropped).
    assert len(results) == 3
    assert {r["room_id"] for r in results} == {
        rec["chatRoomId"] for rec in CHATROOM_RECORDS
    }

    # Field mapping for each record (compare against the source record).
    for result, record in zip(results, CHATROOM_RECORDS, strict=True):
        # Identity + channel.
        assert result["room_id"] == record["chatRoomId"]
        assert result["channel"] == "wechat"

        # Naming + ownership.
        assert result["room_name"] == record["chatRoomName"]
        assert result["owner_account_id"] == record["wechatId"]
        assert result["owner_account_nickname"] == record["wechatNickName"]
        assert result["owner_user_id"] == record["userId"]
        assert result["owner_user_phone"] == record["userPhone"]

        # Counts.
        assert result["member_count"] == record["memberCount"]
        assert result["message_count"] == record["messageCount"]
        assert result["own_message_count"] == record["ownMessageCount"]
        assert result["loss_members"] == record["lossMembers"]
        assert result["add_members"] == record["addMembers"]

        # Avatar + timestamps.
        assert result["head_image_url"] == record["headImageUrl"]
        assert result["last_chat_time"] == record["lastChatTime"]
        assert result["update_time"] == record["updateTime"]

        # member_ids carried raw; member_ids_list parsed (empties dropped).
        assert result["member_ids"] == record["memberIds"]
        assert result["member_ids_list"] == [
            seg for seg in record["memberIds"].split(";") if seg
        ]

        # Version carried verbatim; raw_json preserves the original record.
        assert result["version"] == record["version"]
        assert result["raw_json"] == record


# ---------------------------------------------------------------------------
# member_ids_list parsing edge cases
# ---------------------------------------------------------------------------


@respx.mock
async def test_scrape_wechat_groups_drops_empty_member_id_segments():
    """Trailing/empty ``memberIds`` segments are dropped from member_ids_list."""
    # Record 2 has a trailing ";" -> one empty segment that must be dropped.
    page1 = make_chatroom_list_response(
        [CHATROOM_RECORDS[1]], total=1, page_num=1, page_size=DEFAULT_PAGE_SIZE
    )
    page2 = make_chatroom_list_response([], total=1, page_num=2)
    respx.post(CHATROOM_LIST_URL).mock(
        side_effect=[httpx.Response(200, json=page1), httpx.Response(200, json=page2)]
    )

    client = _primed_client()
    try:
        results = [r async for r in scrape_wechat_groups(client, page_size=DEFAULT_PAGE_SIZE)]
    finally:
        await client.aclose()

    assert len(results) == 1
    # "wxid_member_b1;wxid_member_b2;" -> 2 ids (trailing empty dropped).
    assert results[0]["member_ids_list"] == ["wxid_member_b1", "wxid_member_b2"]


@respx.mock
async def test_scrape_wechat_groups_handles_missing_member_ids():
    """A group with no ``memberIds`` field yields an empty member_ids_list."""
    record = {"chatRoomId": "x@chatroom", "chatRoomName": "Empty"}
    page1 = make_chatroom_list_response([record], total=1, page_num=1)
    page2 = make_chatroom_list_response([], total=1, page_num=2)
    respx.post(CHATROOM_LIST_URL).mock(
        side_effect=[httpx.Response(200, json=page1), httpx.Response(200, json=page2)]
    )

    client = _primed_client()
    try:
        results = [r async for r in scrape_wechat_groups(client, page_size=DEFAULT_PAGE_SIZE)]
    finally:
        await client.aclose()

    assert len(results) == 1
    assert results[0]["member_ids"] is None
    assert results[0]["member_ids_list"] == []


# ---------------------------------------------------------------------------
# Pagination body: pageNum/pageSize advanced correctly
# ---------------------------------------------------------------------------


@respx.mock
async def test_scrape_wechat_groups_sends_pagination_body():
    """Outgoing request body carries pageNum/pageSize; advances per page."""
    page1 = make_chatroom_list_response(
        [CHATROOM_RECORDS[0]], total=TOTAL, page_num=1, page_size=1
    )
    page2 = make_chatroom_list_response([], total=TOTAL, page_num=2, page_size=1)
    route = respx.post(CHATROOM_LIST_URL).mock(
        side_effect=[httpx.Response(200, json=page1), httpx.Response(200, json=page2)]
    )

    client = _primed_client()
    try:
        results = [r async for r in scrape_wechat_groups(client, page_size=1)]
    finally:
        await client.aclose()

    # One record on page 1, empty page 2 stops the loop.
    assert len(results) == 1
    assert route.call_count == 2

    body1 = _json.loads(route.calls[0].request.content.decode())
    assert body1["pageNum"] == 1
    assert body1["pageSize"] == 1

    body2 = _json.loads(route.calls[1].request.content.decode())
    assert body2["pageNum"] == 2
    assert body2["pageSize"] == 1


# ---------------------------------------------------------------------------
# Empty first page -> no yields, single call
# ---------------------------------------------------------------------------


@respx.mock
async def test_scrape_wechat_groups_stops_on_empty_first_page():
    """If the very first page is empty, scraper stops without over-fetching."""
    empty = make_chatroom_list_response([], total=0, page_num=1)
    route = respx.post(CHATROOM_LIST_URL).mock(
        return_value=httpx.Response(200, json=empty)
    )

    client = _primed_client()
    try:
        results = [r async for r in scrape_wechat_groups(client)]
    finally:
        await client.aclose()

    assert results == []
    assert route.call_count == 1