85d3810535
Closes the 'admin pre-stages a curated table/view for analysts' use case end-to-end across both supported source connectors. Backend (BigQuery + Keboola, schema v20): - schema v20 adds source_query TEXT to table_registry (renumbered from v19 after main's #150 RBAC migration also bumped to v19) - connectors/bigquery/extractor.py adds materialize_query(table_id, sql, *, bq, output_dir, max_bytes=...) — BqAccess session, dry-run cost guardrail (default 10 GiB, configurable via data_source.bigquery.max_bytes_per_materialize), idempotent ATTACH, rows/bytes/md5 metadata for sync_state - connectors/keboola/access.py — new KeboolaAccess facade (parallel of BqAccess) wrapping ATTACH 'keboola://...' AS kbc - connectors/keboola/extractor.py adds materialize_query — same shape, no dry-run analog (Keboola Storage API has different cost model); legacy bucket-download path skips query_mode='materialized' rows - app/api/sync.py:_run_materialized_pass dispatches by source_type to the right materialize_query - app/api/admin.py: RegisterTableRequest accepts source_query; model_validator coheres mode↔source_query↔bucket; PUT preserves omitted fields; deprecation marks (Field(deprecated=True)) on sync_strategy + profile_after_sync (no extractor reads them; profile_after_sync becomes inert — bug from earlier work where /api/sync/trigger never honored the flag); _BQ_OPTIONAL_FIELD_DEFAULTS injects defaults into GET /server-config payload Operator + CLI surface: - da admin register-table --query / --query-mode materialized - scripts/smoke-test-materialized-bq.sh — end-to-end smoke for operators Tests (incl. spike + integration + regression): - test_db_migration_v20, test_table_registry_source_query - test_bq_materialize, test_bq_cost_guardrail, test_bq_init_extract_skips - test_keboola_access, test_keboola_extension_query_passthrough (lock-in for the DuckDB extension capability), test_keboola_materialize, test_keboola_init_extract_skips, test_keboola_materialized_e2e (skipped without KBC_TEST_* creds) - test_sync_trigger_materialized, test_sync_trigger_keboola_materialized - test_api_admin_materialized, test_cli_admin_materialized - test_admin_bq_register, test_admin_discover_bigquery, test_admin_keboola_materialized, test_admin_phase_c_deprecation, test_admin_put_preservation, test_materialized_e2e Cost: BQ uses bigquery_query() (jobs API, view-aware) — works on tables, views, materialized views uniformly. Keboola uses ATTACH+COPY parquet through the DuckDB extension.
95 lines
2.9 KiB
Python
95 lines
2.9 KiB
Python
"""Tests for Keboola materialized registration."""
|
|
import pytest
|
|
|
|
|
|
def test_register_keboola_materialized_accepts_source_query(seeded_app):
|
|
c = seeded_app["client"]
|
|
token = seeded_app["admin_token"]
|
|
auth = {"Authorization": f"Bearer {token}"}
|
|
r = c.post(
|
|
"/api/admin/register-table",
|
|
headers=auth,
|
|
json={
|
|
"name": "orders_recent",
|
|
"source_type": "keboola",
|
|
"query_mode": "materialized",
|
|
"source_query": "SELECT * FROM kbc.\"in.c-sales\".\"orders\" WHERE date > '2026-01-01'",
|
|
"sync_schedule": "daily 03:00",
|
|
},
|
|
)
|
|
assert r.status_code == 201, r.text
|
|
|
|
|
|
def test_register_keboola_materialized_rejects_missing_source_query(seeded_app):
|
|
c = seeded_app["client"]
|
|
token = seeded_app["admin_token"]
|
|
auth = {"Authorization": f"Bearer {token}"}
|
|
r = c.post(
|
|
"/api/admin/register-table",
|
|
headers=auth,
|
|
json={
|
|
"name": "orders_recent",
|
|
"source_type": "keboola",
|
|
"query_mode": "materialized",
|
|
# source_query missing
|
|
},
|
|
)
|
|
assert r.status_code == 422
|
|
assert "source_query" in r.text
|
|
|
|
|
|
def test_register_keboola_materialized_skips_bucket_check(seeded_app):
|
|
"""Materialized rows don't need bucket/source_table — the SELECT inlines
|
|
the references. Mirror of BQ materialized validator behavior."""
|
|
c = seeded_app["client"]
|
|
token = seeded_app["admin_token"]
|
|
auth = {"Authorization": f"Bearer {token}"}
|
|
r = c.post(
|
|
"/api/admin/register-table",
|
|
headers=auth,
|
|
json={
|
|
"name": "x",
|
|
"source_type": "keboola",
|
|
"query_mode": "materialized",
|
|
"source_query": "SELECT 1",
|
|
# No bucket / source_table — must still succeed.
|
|
},
|
|
)
|
|
assert r.status_code == 201, r.text
|
|
|
|
|
|
def test_update_keboola_materialized_clears_stale_source_query_on_mode_switch(seeded_app):
|
|
c = seeded_app["client"]
|
|
token = seeded_app["admin_token"]
|
|
auth = {"Authorization": f"Bearer {token}"}
|
|
|
|
# Register materialized.
|
|
r = c.post(
|
|
"/api/admin/register-table",
|
|
headers=auth,
|
|
json={
|
|
"name": "x",
|
|
"source_type": "keboola",
|
|
"query_mode": "materialized",
|
|
"source_query": "SELECT 1",
|
|
},
|
|
)
|
|
assert r.status_code == 201
|
|
|
|
# PUT to switch back to local — source_query must clear.
|
|
r = c.put(
|
|
"/api/admin/registry/x",
|
|
headers=auth,
|
|
json={
|
|
"source_type": "keboola",
|
|
"query_mode": "local",
|
|
"bucket": "in.c-foo",
|
|
"source_table": "y",
|
|
},
|
|
)
|
|
assert r.status_code == 200
|
|
|
|
r = c.get("/api/admin/registry", headers=auth)
|
|
rows = r.json()["tables"]
|
|
row = next(t for t in rows if t["id"] == "x")
|
|
assert row.get("source_query") in (None, "")
|