a35abb0541
Completes TODO #5. Forwarding a post now asks whether to save it whole or extract its media; sending media directly is unchanged. Built on forwarding rather than copying file_ids. The bot already has the post in its private chat with the owner, so it stores message ids and forwards them back. forwardMessages takes a list and keeps an album intact, which is what made the caption-plus-album case tractable; ids must be strictly ascending, so they are sorted on the way out. - Vault rows live in their own table and every query is scoped to an owner_id, so a guessed id cannot reach someone else's saved post. Nothing in the vault is searchable inline, moderated or federated, and the separate table makes that structural rather than a flag. - Albums arrive as separate messages with no completion signal, so they are buffered by media_group_id behind a 1s debounce and prompt once. - The add path now takes a list of items, so extracting an album stores every piece under one set of keywords instead of asking repeatedly. - /vault searches keywords and the original caption, since the point of a vault is finding something you never got round to tagging. - Retrieval failures are reported: a message id is a pointer into the chat, not a self-contained file_id, so clearing history breaks it. Three near-identical keyword collectors are now one helper. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
185 lines
6.8 KiB
Python
185 lines
6.8 KiB
Python
"""Migration tests. Run with: python test_db.py
|
|
|
|
The v1->v2 migration rebuilds the media table, so it drops the original.
|
|
These cases cover the paths that rebuild touches before it ever runs against
|
|
a real bot_db/media.db.
|
|
"""
|
|
import asyncio
|
|
import importlib
|
|
import os
|
|
import sqlite3
|
|
import sys
|
|
import tempfile
|
|
|
|
V1_SCHEMA = """
|
|
CREATE TABLE media (
|
|
id INTEGER PRIMARY KEY AUTOINCREMENT,
|
|
owner_id INTEGER NOT NULL,
|
|
file_id TEXT NOT NULL,
|
|
file_unique_id TEXT NOT NULL UNIQUE,
|
|
media_type TEXT NOT NULL,
|
|
keywords TEXT NOT NULL,
|
|
added_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP
|
|
);
|
|
"""
|
|
|
|
|
|
def user_version(path: str) -> int:
|
|
with sqlite3.connect(path) as c:
|
|
return c.execute("PRAGMA user_version").fetchone()[0]
|
|
|
|
|
|
def load_db(path: str):
|
|
os.environ["DB_PATH"] = path
|
|
import db
|
|
return importlib.reload(db)
|
|
|
|
|
|
async def test_legacy_upgrade(tmp: str):
|
|
path = os.path.join(tmp, "legacy.db")
|
|
with sqlite3.connect(path) as c:
|
|
c.executescript(V1_SCHEMA)
|
|
c.execute("INSERT INTO media (id,owner_id,file_id,file_unique_id,media_type,keywords)"
|
|
" VALUES (7,111,'FID_A','UNI_A','photo','cat,funny')")
|
|
c.execute("INSERT INTO media (id,owner_id,file_id,file_unique_id,media_type,keywords)"
|
|
" VALUES (9,111,'FID_B','UNI_B','gif','dog')")
|
|
|
|
db = load_db(path)
|
|
await db.init_db()
|
|
|
|
# Pinned to the module so adding a migration does not require editing this.
|
|
assert user_version(path) == db.SCHEMA_VERSION
|
|
rows = sorted((r["id"], r["keywords"]) for r in await db.search_media(""))
|
|
assert rows == [(7, "cat,funny"), (9, "dog")], f"rows not preserved: {rows}"
|
|
with sqlite3.connect(path) as c:
|
|
statuses = {r[0] for r in c.execute("SELECT status FROM media")}
|
|
tables = {r[0] for r in c.execute("SELECT name FROM sqlite_master WHERE type='table'")}
|
|
assert statuses == {"approved"}, f"upgraded rows must stay live: {statuses}"
|
|
assert "vault_items" in tables, "upgrading should create the vault table too"
|
|
print(" legacy v1 database upgrades with ids, keywords and visibility intact")
|
|
|
|
|
|
async def test_per_owner_uniqueness(tmp: str):
|
|
path = os.path.join(tmp, "owners.db")
|
|
db = load_db(path)
|
|
await db.init_db()
|
|
|
|
await db.add_media(111, "FID_A", "UNI_A", "photo", ["cat"])
|
|
await db.add_media(222, "FID_A2", "UNI_A", "photo", ["cat"])
|
|
assert len(await db.search_media("cat")) == 2, "two owners must each keep their own row"
|
|
assert len(await db.search_media("", owner_id=222)) == 1, "owner scoping failed"
|
|
print(" two owners can save the same file; owner scoping filters correctly")
|
|
|
|
|
|
async def test_readd_keeps_id(tmp: str):
|
|
path = os.path.join(tmp, "readd.db")
|
|
db = load_db(path)
|
|
await db.init_db()
|
|
|
|
await db.add_media(111, "FID_A", "UNI_A", "photo", ["cat"])
|
|
original = (await db.search_media("cat"))[0]["id"]
|
|
await db.add_media(111, "FID_NEW", "UNI_A", "photo", ["kitten"])
|
|
row = await db.get_media_by_id(original)
|
|
|
|
assert row is not None, "re-adding the same file orphaned its id"
|
|
assert row["keywords"] == "kitten" and row["file_id"] == "FID_NEW"
|
|
print(" re-adding a file updates in place and keeps its id")
|
|
|
|
|
|
async def test_fresh_and_idempotent(tmp: str):
|
|
path = os.path.join(tmp, "fresh.db")
|
|
db = load_db(path)
|
|
await db.init_db()
|
|
|
|
with sqlite3.connect(path) as c:
|
|
sql = c.execute("SELECT sql FROM sqlite_master WHERE name='media'").fetchone()[0]
|
|
assert "UNIQUE(owner_id, file_unique_id)" in sql
|
|
assert user_version(path) == db.SCHEMA_VERSION
|
|
|
|
await db.init_db()
|
|
await db.init_db()
|
|
print(" fresh install lands on the current version; init_db is idempotent")
|
|
|
|
|
|
async def test_pending_is_hidden(tmp: str):
|
|
path = os.path.join(tmp, "pending.db")
|
|
db = load_db(path)
|
|
await db.init_db()
|
|
|
|
await db.add_media(111, "F1", "U1", "photo", ["live"])
|
|
await db.add_media(222, "F2", "U2", "photo", ["waiting"], status="pending")
|
|
|
|
assert len(await db.search_media("")) == 1, "pending items must not be searchable"
|
|
assert await db.count_media() == 1
|
|
assert len(await db.list_media(0, 30)) == 1, "pending items must not appear in /list"
|
|
assert len(await db.search_media("", status=None)) == 2, "status=None should see everything"
|
|
assert await db.count_pending() == 1
|
|
print(" pending items stay out of search, /list and counts until approved")
|
|
|
|
|
|
async def test_queue_is_oldest_first(tmp: str):
|
|
path = os.path.join(tmp, "queue.db")
|
|
db = load_db(path)
|
|
await db.init_db()
|
|
|
|
for i in range(3):
|
|
await db.add_media(100 + i, f"F{i}", f"U{i}", "photo", [f"kw{i}"], status="pending")
|
|
|
|
first = await db.next_pending()
|
|
assert first["keywords"] == "kw0", f"queue must be oldest-first, got {first['keywords']}"
|
|
|
|
# Approving removes it from the queue and the next one steps up.
|
|
assert await db.set_status(first["id"], "approved", 999) is True
|
|
second = await db.next_pending()
|
|
assert second["keywords"] == "kw1"
|
|
assert await db.count_pending() == 2
|
|
print(" queue serves oldest first and advances as items are handled")
|
|
|
|
|
|
async def test_two_moderators_cannot_double_review(tmp: str):
|
|
path = os.path.join(tmp, "race.db")
|
|
db = load_db(path)
|
|
await db.init_db()
|
|
|
|
await db.add_media(111, "F1", "U1", "photo", ["kw"], status="pending")
|
|
item = await db.next_pending()
|
|
|
|
assert await db.set_status(item["id"], "approved", 111) is True
|
|
assert await db.set_status(item["id"], "rejected", 222) is False, \
|
|
"a second moderator must not overwrite a completed review"
|
|
|
|
row = await db.get_media_by_id(item["id"])
|
|
assert row["status"] == "approved", "first review must win"
|
|
print(" a second moderator cannot overturn an already-reviewed item")
|
|
|
|
|
|
async def test_rejected_stays_hidden(tmp: str):
|
|
path = os.path.join(tmp, "rejected.db")
|
|
db = load_db(path)
|
|
await db.init_db()
|
|
|
|
await db.add_media(111, "F1", "U1", "photo", ["nope"], status="pending")
|
|
item = await db.next_pending()
|
|
await db.set_status(item["id"], "rejected", 999)
|
|
|
|
assert await db.search_media("nope") == [], "rejected items must never surface"
|
|
assert await db.count_pending() == 0
|
|
assert await db.next_pending() is None
|
|
print(" rejected items leave the queue and never surface in search")
|
|
|
|
|
|
async def main():
|
|
sys.path.insert(0, os.path.dirname(os.path.abspath(__file__)))
|
|
with tempfile.TemporaryDirectory() as tmp:
|
|
for test in (test_legacy_upgrade, test_per_owner_uniqueness,
|
|
test_readd_keeps_id, test_fresh_and_idempotent,
|
|
test_pending_is_hidden, test_queue_is_oldest_first,
|
|
test_two_moderators_cannot_double_review,
|
|
test_rejected_stays_hidden):
|
|
await test(tmp)
|
|
print("\nAll database tests passed.")
|
|
|
|
|
|
if __name__ == "__main__":
|
|
asyncio.run(main())
|