"""Tests for the voice-clip (长语音) scraper.

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 4 records across 2 pages of size 2, plus a terminating
empty page (the page-number paginator's primary stop signal):

* page 1 -> 2 records, ``total=4``
* page 2 -> 2 records, ``total=4``
* page 3 -> empty ``data`` array (no more rows)

The scraper must yield exactly the 4 records normalized to the ``VoiceClip``
column shape, make exactly 3 calls, and stop without a 4th. Field mapping
asserted end-to-end incl.:

* ``id``           -> ``voice_clip_id`` (PK, int)
* ``userId``       -> ``user_id``
* ``userRealName`` -> ``user_real_name``
* ``startTime``/``endTime`` -> ``start_time``/``end_time`` (ms-epoch STRING
  coerced to int)
* ``ossFileName``  -> ``oss_file_name`` (may be null)
* ``mp3Duration``  -> ``mp3_duration`` (int seconds)
* ``channel``      -> stamped locally from the ``channel`` arg (``wechat`` /
  ``whatsapp``), NOT from the API response
"""

from __future__ import annotations

import json as _json

import httpx
import respx

from app.scraper.voice_clip import scrape_voice_clips
from app.session.yunke_client import YunkeClient
from tests.cassettes.voiceClip_fixture import (
    DEFAULT_PAGE_SIZE,
    TOTAL,
    VOICE_CLIP_RECORDS,
    make_voice_clip_list_response,
)

BASE = "https://crm2.yunkecn.com"
VOICE_CLIP_LIST_URL = f"{BASE}/wechatweb/call/list"

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 + raw_json
# ---------------------------------------------------------------------------


@respx.mock
async def test_scrape_voice_clips_yields_records_and_paginates():
    """Two full pages + a terminating empty page -> 4 records, 3 calls."""
    page1 = make_voice_clip_list_response(
        VOICE_CLIP_RECORDS[:2], total=TOTAL, page_num=1, page_size=DEFAULT_PAGE_SIZE
    )
    page2 = make_voice_clip_list_response(
        VOICE_CLIP_RECORDS[2:], total=TOTAL, page_num=2, page_size=DEFAULT_PAGE_SIZE
    )
    page3 = make_voice_clip_list_response(
        [], total=TOTAL, page_num=3, page_size=DEFAULT_PAGE_SIZE
    )

    route = respx.post(VOICE_CLIP_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_voice_clips(
                client,
                "832EC001_wechat_staff",
                channel="wechat",
                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 4 fixture records (not duplicated, not dropped).
    assert len(results) == 4
    assert {r["voice_clip_id"] for r in results} == {
        rec["id"] for rec in VOICE_CLIP_RECORDS
    }

    # Field mapping for each record (compare against the source record).
    for result, record in zip(results, VOICE_CLIP_RECORDS, strict=True):
        # Identity + locally-stamped channel.
        assert result["voice_clip_id"] == record["id"]
        assert result["channel"] == "wechat"

        # Staff side.
        assert result["user_id"] == record["userId"]
        assert result["user_real_name"] == record["userRealName"]
        assert result["company_code"] == record["companyCode"]

        # ms-epoch strings coerced to int.
        assert result["start_time"] == int(record["startTime"])
        assert result["end_time"] == int(record["endTime"])

        # Recording URL (may be None).
        assert result["oss_file_name"] == record["ossFileName"]

        # Duration fields.
        assert result["mp3_duration"] == record["mp3Duration"]
        assert result["duration_format"] == record["durationFormat"]

        # raw_json preserves the original record verbatim.
        assert result["raw_json"] == record


# ---------------------------------------------------------------------------
# Channel is stamped locally (NOT from the API response)
# ---------------------------------------------------------------------------


@respx.mock
async def test_scrape_voice_clips_stamps_whatsapp_channel():
    """``channel="whatsapp"`` is stamped on every record regardless of payload."""
    page1 = make_voice_clip_list_response(
        VOICE_CLIP_RECORDS[:1], total=1, page_num=1, page_size=DEFAULT_PAGE_SIZE
    )
    page2 = make_voice_clip_list_response(
        [], total=1, page_num=2, page_size=DEFAULT_PAGE_SIZE
    )
    respx.post(VOICE_CLIP_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_voice_clips(
                client, "F33DA003_wa_staff", channel="whatsapp"
            )
        ]
    finally:
        await client.aclose()

    assert len(results) == 1
    assert results[0]["channel"] == "whatsapp"


# ---------------------------------------------------------------------------
# Null ossFileName -> oss_file_name None
# ---------------------------------------------------------------------------


@respx.mock
async def test_scrape_voice_clips_null_oss_file_name_yields_none():
    """A record with ``ossFileName=null`` -> ``oss_file_name`` None."""
    rec = {
        "id": 66010,
        "userId": "staff_x",
        "userRealName": "X",
        "wxId": None,
        "talker": None,
        "status": None,
        "isSend": None,
        "companyCode": "8m0atd",
        "startTime": "1786072733000",
        "endTime": "1786072733000",
        "ossFileName": None,
        "mp3Duration": 0,
        "durationFormat": "00:00:00",
    }
    page1 = make_voice_clip_list_response(
        [rec], total=1, page_num=1, page_size=DEFAULT_PAGE_SIZE
    )
    page2 = make_voice_clip_list_response(
        [], total=1, page_num=2, page_size=DEFAULT_PAGE_SIZE
    )
    respx.post(VOICE_CLIP_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_voice_clips(
                client, "staff_x", channel="wechat", page_size=DEFAULT_PAGE_SIZE
            )
        ]
    finally:
        await client.aclose()

    assert len(results) == 1
    assert results[0]["oss_file_name"] is None
    assert results[0]["voice_clip_id"] == 66010


# ---------------------------------------------------------------------------
# Pagination body: pageNum/pageSize/userId
# ---------------------------------------------------------------------------


@respx.mock
async def test_scrape_voice_clips_sends_pagination_body():
    """Body carries ``userId`` + advancing ``pageNum``/``pageSize`` only.

    The ``call/list`` endpoint takes ``{pageNum, pageSize, userId}``. The
    optional ``startTime``/``endTime`` filters are omitted for full-history
    sync (the scraper pulls the employee's whole voice-clip set in one pass).
    """
    page1 = make_voice_clip_list_response(
        VOICE_CLIP_RECORDS[:1], total=TOTAL, page_num=1, page_size=1
    )
    page2 = make_voice_clip_list_response(
        [], total=TOTAL, page_num=2, page_size=1
    )
    route = respx.post(VOICE_CLIP_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_voice_clips(
                client, "EMP_USER_001", channel="wechat", 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

    # Page 1 body: userId + standard pagination pair, no time window.
    body1 = _json.loads(route.calls[0].request.content.decode())
    assert body1["userId"] == "EMP_USER_001"
    assert body1["pageNum"] == 1
    assert body1["pageSize"] == 1
    # No startTime/endTime (full-history scrape).
    assert "startTime" not in body1
    assert "endTime" not in body1

    # Page 2 advances pageNum and keeps userId verbatim.
    body2 = _json.loads(route.calls[1].request.content.decode())
    assert body2["pageNum"] == 2
    assert body2["pageSize"] == 1
    assert body2["userId"] == "EMP_USER_001"


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


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

    client = _primed_client()
    try:
        results = [r async for r in scrape_voice_clips(client, "any_user")]
    finally:
        await client.aclose()

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