浅念
8a22fd9ff8
Mirrors the WeChat scraper patterns (M3) using the shared paginator +
parser + repo building blocks. Three new async generators yield
snake_case dicts + verbatim raw_json, ready for the channel-generic
upsert_customer / upsert_messages repos.
- app/scraper/whatsapp.py (new): scrape_whatsapp_accounts /
scrape_whatsapp_friends (page-number pagination over the
data.overviews / data.totalCount envelope) and scrape_whatsapp_messages
(backward-cursor pagination, JSON body {uid,friendUid,start,end} —
NOT form-encoded like WeChat msg/chats). Drops type==-2 dividers;
maps mediaName -> file_url as a deferred-download key.
- app/scraper/parsers.py: add normalize_whatsapp_type (0->text,
1->image, -2->divider, else unknown; never raises) and a shared
coerce_int_or_none scraper helper (mirrors repos._coerce_int so the
scraper emits type_raw ints without a DB dependency).
- app/storage/repos.py: add upsert_whatsapp_account (PK uid) which
also upserts the embedded Staff(user_id, name) via the existing
upsert_staff_from_account helper; WhatsappAccount imported.
Tests (respx mocks, no network): 3 cassette fixtures + 3 scraper test
modules (accounts/friends/messages), parsers + repos extended with WA
cases. Divider drop, backward-cursor advance (end == E1-1), JSON body
asserts, embedded-staff upsert, and channel-generic Customer/Message
upserts all covered.
Suite: 182 -> 211 passing. ruff clean.
Co-Authored-By: Claude <noreply@anthropic.com>
118 lines
4.4 KiB
Python
118 lines
4.4 KiB
Python
"""Tests for the message-type normalization parser (Task 1.6).
|
|
|
|
The parser must be total — it never raises on weird input — because every
|
|
incoming WeChat record runs through it during a scrape, and one malformed
|
|
type code must not abort the whole pull. Unknown codes pass through as
|
|
``"unknown"`` so the message is still ingested (and recoverable via
|
|
``raw_json``); only the ``-2`` date-divider code maps to ``"divider"``,
|
|
which the scraper uses as its drop signal.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import pytest
|
|
|
|
from app.scraper.parsers import (
|
|
coerce_int_or_none,
|
|
normalize_wechat_type,
|
|
normalize_whatsapp_type,
|
|
)
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
"raw,expected",
|
|
[
|
|
# Phase-0 confirmed codes (see docs/superpowers/specs/phase0-findings.md §2).
|
|
(1, "text"),
|
|
(-2, "divider"), # date separator — NOT a real message (scraper drops it)
|
|
(2, "image"), # image / sticker (webp) — file/fileTh are direct URLs
|
|
(3, "image_legacy"), # old image format — file is an opaque ID (needs another endpoint)
|
|
(4, "video"), # mp4 — file is a direct URL
|
|
(10, "system"), # system / link / card / invite — non-media, skip download
|
|
# Still-unconfirmed codes — pass through as "unknown", never dropped.
|
|
# (6, 9, 13, 15, 21, 22 — voice/file/transfer/redpacket/quote/etc; raw_json retains the code.)
|
|
(6, "unknown"),
|
|
(9, "unknown"),
|
|
(34, "unknown"), # voice (legacy WeChat code, not yet seen in yunke)
|
|
(49, "unknown"), # file / link / transfer
|
|
(10000, "unknown"),
|
|
# Stringified ints (the upstream API may send either form).
|
|
("1", "text"),
|
|
("-2", "divider"),
|
|
("2", "image"),
|
|
("3", "image_legacy"),
|
|
("4", "video"),
|
|
("10", "system"),
|
|
("34", "unknown"),
|
|
],
|
|
)
|
|
def test_normalize_wechat_type_maps_known_and_unknown(raw, expected):
|
|
assert normalize_wechat_type(raw) == expected
|
|
|
|
|
|
def test_normalize_wechat_type_never_raises():
|
|
"""Whatever we throw at it, it returns a string — never raises."""
|
|
for raw in (None, "", "junk", "1.5", [], {}, object(), float("nan")):
|
|
out = normalize_wechat_type(raw)
|
|
assert isinstance(out, str)
|
|
assert out == "unknown"
|
|
|
|
|
|
# ===========================================================================
|
|
# WhatsApp message-type normalization (M3)
|
|
# ===========================================================================
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
"raw,expected",
|
|
[
|
|
# Phase-0 confirmed WhatsApp codes (see data dictionary §3):
|
|
(0, "text"),
|
|
(1, "image"), # image / media
|
|
(-2, "divider"), # date separator — NOT a real message (scraper drops it)
|
|
# Unconfirmed / other media codes — pass through as "unknown", never dropped.
|
|
(2, "unknown"),
|
|
(3, "unknown"),
|
|
(13, "unknown"),
|
|
(100, "unknown"),
|
|
# Stringified ints (the upstream API may send either form).
|
|
("0", "text"),
|
|
("1", "image"),
|
|
("-2", "divider"),
|
|
("2", "unknown"),
|
|
],
|
|
)
|
|
def test_normalize_whatsapp_type_maps_known_and_unknown(raw, expected):
|
|
assert normalize_whatsapp_type(raw) == expected
|
|
|
|
|
|
def test_normalize_whatsapp_type_never_raises():
|
|
"""Whatever we throw at it, it returns a string — never raises."""
|
|
for raw in (None, "", "junk", "1.5", [], {}, object(), float("nan")):
|
|
out = normalize_whatsapp_type(raw)
|
|
assert isinstance(out, str)
|
|
assert out == "unknown"
|
|
|
|
|
|
# ===========================================================================
|
|
# coerce_int_or_none — shared scraper helper (M3)
|
|
# ===========================================================================
|
|
|
|
|
|
def test_coerce_int_or_none_handles_documented_cases():
|
|
"""``type_raw``-style fields: str -> int; None preserved; 0 preserved."""
|
|
assert coerce_int_or_none(None) is None
|
|
assert coerce_int_or_none(0) == 0
|
|
assert coerce_int_or_none(2) == 2
|
|
assert coerce_int_or_none(-2) == -2
|
|
assert coerce_int_or_none("0") == 0
|
|
assert coerce_int_or_none("2") == 2
|
|
assert coerce_int_or_none("-2") == -2
|
|
|
|
|
|
def test_coerce_int_or_none_returns_none_for_non_numeric_string():
|
|
"""A non-numeric value (e.g. a label) -> None."""
|
|
assert coerce_int_or_none("text") is None
|
|
assert coerce_int_or_none("") is None
|
|
assert coerce_int_or_none("unknown") is None
|