浅念
d9060b6920
- VoiceClip model (BigInteger PK voice_clip_id, structured cols + raw_json)
- Alembic migration a1b2c3d4e5f6 (chains from 8c4f1d2a9e6b)
- scrape_voice_clips(client, user_id, *, channel, page_size) per-employee scraper
over POST /wechatweb/call/list {pageNum, pageSize, userId}; channel stamped
locally (wechat/whatsapp), startTime/endTime ms-epoch string -> int
- upsert_voice_clip repo + start_time/end_time/mp3_duration int coercion
- sync_voice_clips orchestrator: iterates distinct user_id across
WechatAccount + WhatsappAccount, stamps channel per account table
- scheduler ENTITY_FUNCS['voice_clips'] + added to daily 'all' job
- GET /api/voice-clips (user_id exact beats user_real_name fuzzy; channel;
company_code; start/end window on end_time; ordered end_time desc)
- VoiceClipOut schema + router registered in main.py
- tests: scraper (5) + API (11) = 16 new; full suite 370 green
Co-Authored-By: Claude <noreply@anthropic.com>
240 lines
7.9 KiB
Python
240 lines
7.9 KiB
Python
"""Tests for GET /api/voice-clips — 长语音 (voice_clip) list.
|
|
|
|
Seeds 3 clips (2 wechat for user u1 at end_time 1000/3000, 1 whatsapp for u2
|
|
at end_time 2000) and asserts filters + ordering (``end_time desc``) +
|
|
pagination + the ``user_id``-beats-``user_real_name`` precedence rule.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
from sqlalchemy.ext.asyncio import AsyncSession
|
|
|
|
from app.db.models import VoiceClip
|
|
|
|
|
|
async def _seed(session: AsyncSession) -> None:
|
|
session.add_all(
|
|
[
|
|
VoiceClip(
|
|
voice_clip_id=1,
|
|
user_id="u1",
|
|
channel="wechat",
|
|
user_real_name="Alice",
|
|
company_code="8m0atd",
|
|
start_time=900,
|
|
end_time=1000,
|
|
oss_file_name="https://oss/clip1.mp3",
|
|
mp3_duration=100,
|
|
duration_format="00:01:40",
|
|
),
|
|
VoiceClip(
|
|
voice_clip_id=2,
|
|
user_id="u2",
|
|
channel="whatsapp",
|
|
user_real_name="Bob",
|
|
company_code="8m0atd",
|
|
start_time=1900,
|
|
end_time=2000,
|
|
oss_file_name="https://oss/clip2.mp3",
|
|
mp3_duration=60,
|
|
duration_format="00:01:00",
|
|
),
|
|
VoiceClip(
|
|
voice_clip_id=3,
|
|
user_id="u1",
|
|
channel="wechat",
|
|
user_real_name="Alice",
|
|
company_code="other",
|
|
start_time=2900,
|
|
end_time=3000,
|
|
oss_file_name=None,
|
|
mp3_duration=0,
|
|
duration_format="00:00:00",
|
|
),
|
|
]
|
|
)
|
|
await session.commit()
|
|
|
|
|
|
async def test_default_list_returns_all_ordered_desc(make_client):
|
|
"""No filters -> 3 rows, ordered by ``end_time desc``."""
|
|
client = await make_client(_seed)
|
|
r = await client.get("/api/voice-clips")
|
|
assert r.status_code == 200
|
|
body = r.json()
|
|
assert body["total"] == 3
|
|
assert [it["voice_clip_id"] for it in body["items"]] == [3, 2, 1]
|
|
for key in (
|
|
"voice_clip_id",
|
|
"user_id",
|
|
"channel",
|
|
"user_real_name",
|
|
"wx_id",
|
|
"talker",
|
|
"status",
|
|
"is_send",
|
|
"company_code",
|
|
"start_time",
|
|
"end_time",
|
|
"oss_file_name",
|
|
"mp3_duration",
|
|
"duration_format",
|
|
"raw_json",
|
|
):
|
|
assert key in body["items"][0]
|
|
|
|
|
|
async def test_filter_by_user_id(make_client):
|
|
"""``?user_id=u1`` -> 2 clips for Alice."""
|
|
client = await make_client(_seed)
|
|
r = await client.get("/api/voice-clips", params={"user_id": "u1"})
|
|
assert r.status_code == 200
|
|
body = r.json()
|
|
assert body["total"] == 2
|
|
assert {it["voice_clip_id"] for it in body["items"]} == {1, 3}
|
|
|
|
|
|
async def test_user_id_takes_precedence_over_user_real_name(make_client):
|
|
"""When both ``user_id`` and ``user_real_name`` are given, user_id wins.
|
|
|
|
The 云客 modal switches between the two based on whether the user edited
|
|
the staff-name box; the id is the more precise filter and wins on conflict.
|
|
Here ``user_id=u1`` (Alice) + ``user_real_name=Bob`` should still return
|
|
Alice's clips (user_id path), NOT Bob's.
|
|
"""
|
|
client = await make_client(_seed)
|
|
r = await client.get(
|
|
"/api/voice-clips", params={"user_id": "u1", "user_real_name": "Bob"}
|
|
)
|
|
assert r.status_code == 200
|
|
body = r.json()
|
|
assert body["total"] == 2
|
|
assert {it["voice_clip_id"] for it in body["items"]} == {1, 3}
|
|
|
|
|
|
async def test_filter_by_user_real_name_fuzzy(make_client):
|
|
"""``?user_real_name=ob`` -> Bob's clip only (ILIKE contains)."""
|
|
client = await make_client(_seed)
|
|
r = await client.get("/api/voice-clips", params={"user_real_name": "ob"})
|
|
assert r.status_code == 200
|
|
body = r.json()
|
|
assert body["total"] == 1
|
|
assert body["items"][0]["voice_clip_id"] == 2
|
|
|
|
|
|
async def test_filter_by_channel(make_client):
|
|
"""``?channel=whatsapp`` -> the single WA clip."""
|
|
client = await make_client(_seed)
|
|
r = await client.get("/api/voice-clips", params={"channel": "whatsapp"})
|
|
assert r.status_code == 200
|
|
body = r.json()
|
|
assert body["total"] == 1
|
|
assert body["items"][0]["voice_clip_id"] == 2
|
|
|
|
|
|
async def test_filter_by_company_code(make_client):
|
|
"""``?company_code=8m0atd`` -> 2 clips (clip 3 has 'other')."""
|
|
client = await make_client(_seed)
|
|
r = await client.get("/api/voice-clips", params={"company_code": "8m0atd"})
|
|
assert r.status_code == 200
|
|
body = r.json()
|
|
assert body["total"] == 2
|
|
assert {it["voice_clip_id"] for it in body["items"]} == {1, 2}
|
|
|
|
|
|
async def test_time_window_filter(make_client):
|
|
"""``?start=1500&end=2500`` -> only clip 2 (end_time 2000)."""
|
|
client = await make_client(_seed)
|
|
r = await client.get("/api/voice-clips", params={"start": 1500, "end": 2500})
|
|
assert r.status_code == 200
|
|
body = r.json()
|
|
assert body["total"] == 1
|
|
assert body["items"][0]["voice_clip_id"] == 2
|
|
|
|
|
|
async def test_filters_compose(make_client):
|
|
"""``user_id=u1 & start=1500`` -> only clip 3 (u1's later clip)."""
|
|
client = await make_client(_seed)
|
|
r = await client.get(
|
|
"/api/voice-clips", params={"user_id": "u1", "start": 1500}
|
|
)
|
|
assert r.status_code == 200
|
|
body = r.json()
|
|
assert body["total"] == 1
|
|
assert body["items"][0]["voice_clip_id"] == 3
|
|
|
|
|
|
async def test_pagination(make_client):
|
|
"""``page_size=1`` -> 1 item, total 3."""
|
|
client = await make_client(_seed)
|
|
r = await client.get("/api/voice-clips", params={"page": 1, "page_size": 1})
|
|
assert r.status_code == 200
|
|
body = r.json()
|
|
assert body["total"] == 3
|
|
assert len(body["items"]) == 1
|
|
assert body["items"][0]["voice_clip_id"] == 3
|
|
|
|
|
|
async def test_oss_file_name_serializes(make_client):
|
|
"""``oss_file_name`` (OSS recording URL) round-trips so the modal can
|
|
render an inline ``<audio>`` player — present when set, None when unset.
|
|
"""
|
|
client = await make_client(_seed)
|
|
r = await client.get("/api/voice-clips")
|
|
assert r.status_code == 200
|
|
by_id = {it["voice_clip_id"]: it for it in r.json()["items"]}
|
|
assert by_id[1]["oss_file_name"] == "https://oss/clip1.mp3"
|
|
assert by_id[3]["oss_file_name"] is None
|
|
|
|
|
|
async def test_raw_json_serializes_verbatim(make_client):
|
|
"""``raw_json`` round-trips the verbatim upstream record when set."""
|
|
|
|
async def seed(session: AsyncSession) -> None:
|
|
await _seed(session)
|
|
session.add(
|
|
VoiceClip(
|
|
voice_clip_id=99,
|
|
user_id="u1",
|
|
channel="wechat",
|
|
user_real_name="Alice",
|
|
start_time=5000,
|
|
end_time=5100,
|
|
raw_json={
|
|
"id": 99,
|
|
"userId": "u1",
|
|
"userRealName": "Alice",
|
|
"startTime": "5000",
|
|
"endTime": "5100",
|
|
"ossFileName": "https://oss/clip99.mp3",
|
|
"mp3Duration": 100,
|
|
"durationFormat": "00:01:40",
|
|
"companyCode": "8m0atd",
|
|
},
|
|
)
|
|
)
|
|
await session.commit()
|
|
|
|
client = await make_client(seed)
|
|
r = await client.get("/api/voice-clips", params={"user_id": "u1", "start": 5000})
|
|
assert r.status_code == 200
|
|
body = r.json()
|
|
assert body["total"] == 1
|
|
assert body["items"][0]["voice_clip_id"] == 99
|
|
assert body["items"][0]["raw_json"] == {
|
|
"id": 99,
|
|
"userId": "u1",
|
|
"userRealName": "Alice",
|
|
"startTime": "5000",
|
|
"endTime": "5100",
|
|
"ossFileName": "https://oss/clip99.mp3",
|
|
"mp3Duration": 100,
|
|
"durationFormat": "00:01:40",
|
|
"companyCode": "8m0atd",
|
|
}
|
|
|
|
# Seeded without an explicit raw_json -> JSON null.
|
|
r_all = await client.get("/api/voice-clips")
|
|
by_id = {it["voice_clip_id"]: it for it in r_all.json()["items"]}
|
|
assert by_id[1]["raw_json"] is None
|