ktx/packages/cli/test/context/ingest/historic-sql-probes/bigquery-runner.test.ts

111 lines
3.8 KiB
TypeScript
Raw Permalink Normal View History

import { describe, expect, it, vi } from 'vitest';
test: split cli tests from source tree (#216) * feat(cli): define full warehouse dialect contract * test(cli): keep dialect edge tests focused * fix(cli): stabilize dialect contract foundation * refactor(connectors): own read-only query preparation * refactor(connectors): resolve dialects through registry * refactor(connectors): keep concrete dialect classes internal * chore(workspace): enforce dialect import boundary * refactor(cli): resolve relationship dialect at scan boundary * refactor(cli): use dialect display parsing for entity details * refactor(cli): use dialect display parsing for warehouse catalog * refactor(cli): use dialect SQL in relationship workflows * test(cli): verify solid dialect scan workflow closure * test: split cli tests from source tree * refactor(cli): standardize BigQuery scope listing * feat(sqlite): implement connector scope listing * test(connectors): cover required table listing * feat(cli): add warehouse driver registry * refactor(setup): route scope discovery through driver registry * refactor(cli): route local query execution through driver registry * refactor(historic-sql): route dialect support through driver registry * refactor(cli): test warehouse connections through driver registry * fix(cli): close driver registry type export gaps * Improve setup daemon diagnostics * refactor(setup): centralize rail-prefixed diagnostics + query-history fallback Extract errorMessage, writePrefixedLines, and flushPrefixedBufferedCommandOutput into clack.ts so the setup wizard, managed daemons, and embedding/agent steps share one rail-formatted writer. setup-databases.ts also adds a "disable query history and retry" option when the schema-context build fails and query history is the likely culprit, surfaced via a new failed-query-history-unavailable status. * fix(cli): carry catalog through the picker so BigQuery/Snowflake/SQL Server scope filters match The setup picker's KtxTableListEntry was a 2-level { schema, name }, so qualifiedTableId always wrote db.name into enabled_tables. When BigQuery, Snowflake, or SQL Server later ran fast ingest, their introspect step filtered the scope set with scopedTableNames(scope, { catalog: projectId|database, db }) — catalog was non-null on the introspect side but null in the scope refs, so every entry was rejected, the live-database adapter staged zero table files, and detect() failed with 'Adapter "live-database" did not recognize fetched source output'. Align the picker boundary with the canonical 3-level KtxTableRef: - Add catalog: string | null to KtxTableListEntry. - BigQuery/Snowflake/SQL Server listTables populate catalog from the resolved projectId / database; Postgres/MySQL/ClickHouse/SQLite set null. - qualifiedTableId emits catalog.schema.name when catalog is non-null (resolveEnabledTables already accepts the 3-part shape) and schemasFromEnabledTables now goes through parseDottedTableEntry so it recovers the schema correctly from both 2-part and 3-part entries. - Export parseDottedTableEntry from enabled-tables.ts (@internal) for picker reuse. Update listTables expectations in all seven connector tests and the setup / picker test fixtures. Add a picker regression test that covers the catalog-bearing round-trip (save + refine). * fix(cli): allow debug telemetry under opt-out env
2026-05-26 08:49:05 +02:00
import { HistoricSqlGrantsMissingError } from '../../../../src/context/ingest/adapters/historic-sql/errors.js';
import { BigQueryJobsByProjectProbeRunner } from '../../../../src/context/ingest/historic-sql-probes/bigquery-runner.js';
describe('BigQueryJobsByProjectProbeRunner', () => {
it('creates a region-scoped reader, runs it, and cleans up the connector', async () => {
const cleanup = vi.fn(async () => undefined);
const reader = {
probe: vi.fn(async () => ({ warnings: [], info: ['region: eu'] })),
};
const createReader = vi.fn(() => reader);
const runner = new BigQueryJobsByProjectProbeRunner({
createReader,
createClient: () => ({ client: { executeQuery: vi.fn() }, cleanup }),
resolveReference: () => '{"project_id":"project-1"}',
});
await expect(
runner.run({
projectDir: '/work/project',
connectionId: 'bq',
connection: {
driver: 'bigquery',
credentials_json: 'env:BQ_CREDENTIALS_JSON',
location: 'EU',
},
env: {},
}),
).resolves.toEqual({ warnings: [], info: ['region: eu'] });
expect(createReader).toHaveBeenCalledWith({ projectId: 'project-1', region: 'EU' });
expect(reader.probe).toHaveBeenCalledOnce();
expect(cleanup).toHaveBeenCalledOnce();
});
it('uses us as the default BigQuery region', async () => {
const createReader = vi.fn(() => ({
probe: vi.fn(async () => ({ warnings: [], info: [] })),
}));
const runner = new BigQueryJobsByProjectProbeRunner({
createReader,
createClient: () => ({ client: {}, cleanup: vi.fn(async () => undefined) }),
resolveReference: () => '{"project_id":"project-1"}',
});
await runner.run({
projectDir: '/work/project',
connectionId: 'bq',
connection: {
driver: 'bigquery',
credentials_json: '{"project_id":"project-1"}',
},
env: {},
});
expect(createReader).toHaveBeenCalledWith({ projectId: 'project-1', region: 'us' });
});
it('rejects missing BigQuery credentials_json.project_id', async () => {
const runner = new BigQueryJobsByProjectProbeRunner({
createReader: vi.fn(),
createClient: () => ({ client: {}, cleanup: vi.fn() }),
resolveReference: () => '{"client_email":"svc@example.test"}',
});
await expect(
runner.run({
projectDir: '/work/project',
connectionId: 'bq',
connection: {
driver: 'bigquery',
credentials_json: 'env:BQ_CREDENTIALS_JSON',
},
env: {},
}),
).rejects.toThrow('Query history BigQuery connection bq requires credentials_json.project_id');
});
it('formats successful BigQuery details', () => {
const runner = new BigQueryJobsByProjectProbeRunner();
expect(
runner.formatSuccessDetail({
warnings: ['JOBS_BY_PROJECT is delayed'],
info: ['region: us'],
}),
).toEqual({
detail: 'INFORMATION_SCHEMA.JOBS_BY_PROJECT ready; region: us',
warnings: ['JOBS_BY_PROJECT is delayed'],
});
});
it('maps BigQuery grant errors to runner advice', () => {
const runner = new BigQueryJobsByProjectProbeRunner();
expect(
runner.fixAdvice(
new HistoricSqlGrantsMissingError({
dialect: 'bigquery',
message: 'principal cannot query JOBS_BY_PROJECT',
remediation:
'Grant roles/bigquery.resourceViewer on the BigQuery project, or grant a custom role containing bigquery.jobs.listAll.',
}),
),
).toEqual({
failHeadline: 'BigQuery principal cannot read INFORMATION_SCHEMA.JOBS_BY_PROJECT',
remediation:
'Grant roles/bigquery.resourceViewer on the BigQuery project, or grant a custom role containing bigquery.jobs.listAll.',
});
});
});