yunke/yunke-server/tests/test_scrape_wechat_voice_calls.py

"""Tests for the WeChat voice-call scraper (Task 2.4).

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 ``PhoneCall``
column shape (``channel="voice_call"``), make exactly 3 calls, and stop
without a 4th. Field mapping asserted end-to-end incl.:

* ``id``         -> ``call_id`` (PK)
* ``duration``   -> ``call_duration`` (string seconds coerced to int)
* ``startTime``  -> ``start_call_time`` (``YYYY-MM-DD HH:MM:SS`` -> ms epoch)
* ``ossFileName``-> ``record_file`` (may be null)
* ``isSend``     -> ``incoming_call`` with INVERTED polarity
  (voice-call ``isSend`` is 0=incoming/1=outgoing; ``PhoneCall.incoming_call``
  is 1=incoming/0=outgoing — so ``incoming_call = 1 - isSend``).
* ``talker``     -> ``call_number`` (the customer / room id)
* ``talkerNickName`` -> ``plan_customer_name``
"""

from __future__ import annotations

import datetime as dt
import json as _json

import httpx
import respx

from app.scraper.wechat import scrape_wechat_voice_calls
from app.session.yunke_client import YunkeClient
from tests.cassettes.voiceCall_fixture import (
    DEFAULT_PAGE_SIZE,
    TOTAL,
    VOICE_RECORDS,
    make_voice_list_response,
)

BASE = "https://crm2.yunkecn.com"
VOICE_LIST_URL = f"{BASE}/wechatweb/callRecord/queryWeChatVoiceList"

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)


def _ms(date_str: str) -> int:
    """Expected ms-epoch for a ``YYYY-MM-DD HH:MM:SS`` string parsed as UTC.

    Mirrors the scraper's documented parsing rule so the assertion is an
    independent recomputation (not a self-reference).
    """
    return int(
        dt.datetime.strptime(date_str, "%Y-%m-%d %H:%M:%S")
        .replace(tzinfo=dt.UTC)
        .timestamp()
        * 1000
    )


# ---------------------------------------------------------------------------
# End-to-end: pagination + field mapping + raw_json
# ---------------------------------------------------------------------------


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

    route = respx.post(VOICE_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_voice_calls(
                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 4 fixture records (not duplicated, not dropped).
    assert len(results) == 4
    assert {r["call_id"] for r in results} == {rec["id"] for rec in VOICE_RECORDS}

    # Field mapping for each record (compare against the source record).
    for result, record in zip(results, VOICE_RECORDS, strict=True):
        # Identity + channel.
        assert result["call_id"] == record["id"]
        assert result["channel"] == "voice_call"

        # Staff side.
        assert result["user_id"] == record["userId"]
        assert result["user_id_name"] == record["userName"]

        # Customer side: talker -> call_number, talkerNickName -> plan_customer_name.
        assert result["call_number"] == record["talker"]
        assert result["plan_customer_name"] == record["talkerNickName"]

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

        # Status + duration + start time coercions.
        assert result["call_status"] == record["callStatus"]
        assert result["call_duration"] == int(record["duration"])
        assert result["start_call_time"] == _ms(record["startTime"])

        # incoming_call polarity: isSend 0=incoming -> 1; 1=outgoing -> 0.
        if record["isSend"] == 0:
            assert result["incoming_call"] == 1
        else:
            assert result["incoming_call"] == 0

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


# ---------------------------------------------------------------------------
# Null ossFileName -> record_file None
# ---------------------------------------------------------------------------


@respx.mock
async def test_scrape_wechat_voice_calls_null_oss_file_name_yields_none_record_file():
    """A record with ``ossFileName=null`` -> ``record_file`` None."""
    rec = {
        "id": "vc_null",
        "userId": "staff_user_001",
        "userName": "Alice Wang",
        "talker": "wxid_friend_x",
        "talkerNickName": "Customer X",
        "isSend": 1,
        "callStatus": 2,
        "ossFileName": None,
        "duration": "0",
        "startTime": "2026-01-15 10:00:00",
        "weChatId": "wxid_staff_alice01",
    }
    page1 = make_voice_list_response(
        [rec], total=1, page_num=1, page_size=DEFAULT_PAGE_SIZE
    )
    page2 = make_voice_list_response(
        [], total=1, page_num=2, page_size=DEFAULT_PAGE_SIZE
    )
    respx.post(VOICE_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_voice_calls(
                client, page_size=DEFAULT_PAGE_SIZE
            )
        ]
    finally:
        await client.aclose()

    assert len(results) == 1
    assert results[0]["record_file"] is None
    assert results[0]["call_status"] == 2
    # Outgoing (isSend=1) -> incoming_call=0.
    assert results[0]["incoming_call"] == 0


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


@respx.mock
async def test_scrape_wechat_voice_calls_sends_pagination_body():
    """Outgoing request body carries pageNum/pageSize; advances per page."""
    page1 = make_voice_list_response(
        VOICE_RECORDS[:1], total=TOTAL, page_num=1, page_size=1
    )
    page2 = make_voice_list_response(
        [], total=TOTAL, page_num=2, page_size=1
    )
    route = respx.post(VOICE_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_voice_calls(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_voice_calls_stops_on_empty_first_page():
    """If the very first page is empty, scraper stops without over-fetching."""
    empty = make_voice_list_response([], total=0, page_num=1)
    route = respx.post(VOICE_LIST_URL).mock(
        return_value=httpx.Response(200, json=empty)
    )

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

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