ktx/packages/cli/test/local-scan-connectors.test.ts

133 lines
4 KiB
TypeScript
Raw Permalink Normal View History

2026-05-10 23:12:26 +02:00
import { mkdtemp, rm, writeFile } from 'node:fs/promises';
import { tmpdir } from 'node:os';
import { join } from 'node:path';
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 { initKtxProject, loadKtxProject } from '../src/context/project/project.js';
2026-05-10 23:12:26 +02:00
import { afterEach, beforeEach, 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 { createKtxCliScanConnector } from '../src/local-scan-connectors.js';
2026-05-10 23:12:26 +02:00
const bigQueryMock = vi.hoisted(() => ({
constructorInputs: [] as Array<{
connectionId: string;
connection: unknown;
}>,
}));
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
vi.mock('../src/connectors/bigquery/connector.js', () => ({
2026-05-10 23:51:24 +02:00
isKtxBigQueryConnectionConfig: (connection: { driver?: unknown } | undefined) =>
2026-05-10 23:12:26 +02:00
String(connection?.driver ?? '').toLowerCase() === 'bigquery',
2026-05-10 23:51:24 +02:00
KtxBigQueryScanConnector: class {
2026-05-10 23:12:26 +02:00
readonly id: string;
readonly driver = 'bigquery';
constructor(options: { connectionId: string; connection: unknown }) {
2026-05-10 23:12:26 +02:00
bigQueryMock.constructorInputs.push(options);
this.id = `bigquery:${options.connectionId}`;
}
},
}));
2026-05-10 23:51:24 +02:00
describe('createKtxCliScanConnector', () => {
2026-05-10 23:12:26 +02:00
let tempDir: string;
beforeEach(async () => {
bigQueryMock.constructorInputs.length = 0;
2026-05-10 23:51:24 +02:00
tempDir = await mkdtemp(join(tmpdir(), 'ktx-cli-scan-connector-'));
2026-05-10 23:12:26 +02:00
});
afterEach(async () => {
await rm(tempDir, { recursive: true, force: true });
});
it('creates a native sqlite connector from standalone config', async () => {
await initKtxProject({ projectDir: tempDir });
2026-05-10 23:12:26 +02:00
await writeFile(
2026-05-10 23:51:24 +02:00
join(tempDir, 'ktx.yaml'),
2026-05-10 23:12:26 +02:00
[
'connections:',
' warehouse:',
' driver: sqlite',
' path: warehouse.db',
'',
].join('\n'),
'utf-8',
);
2026-05-10 23:51:24 +02:00
const project = await loadKtxProject({ projectDir: tempDir });
2026-05-10 23:12:26 +02:00
2026-05-10 23:51:24 +02:00
const connector = await createKtxCliScanConnector(project, 'warehouse');
2026-05-10 23:12:26 +02:00
expect(connector.id).toBe('sqlite:warehouse');
expect(connector.driver).toBe('sqlite');
});
it('passes canonical BigQuery YAML scan limits through to the connector', async () => {
await initKtxProject({ projectDir: tempDir });
2026-05-10 23:12:26 +02:00
await writeFile(
2026-05-10 23:51:24 +02:00
join(tempDir, 'ktx.yaml'),
2026-05-10 23:12:26 +02:00
[
'connections:',
' warehouse:',
' driver: bigquery',
' dataset_id: analytics',
' max_bytes_billed: "987654321"',
' job_timeout_ms: 30000',
2026-05-10 23:12:26 +02:00
'',
].join('\n'),
'utf-8',
);
2026-05-10 23:51:24 +02:00
const project = await loadKtxProject({ projectDir: tempDir });
2026-05-10 23:12:26 +02:00
2026-05-10 23:51:24 +02:00
const connector = await createKtxCliScanConnector(project, 'warehouse');
2026-05-10 23:12:26 +02:00
expect(connector.id).toBe('bigquery:warehouse');
expect(connector.driver).toBe('bigquery');
expect(bigQueryMock.constructorInputs).toEqual([
expect.objectContaining({
connectionId: 'warehouse',
connection: expect.objectContaining({
max_bytes_billed: '987654321',
job_timeout_ms: 30000,
}),
2026-05-10 23:12:26 +02:00
}),
]);
expect(bigQueryMock.constructorInputs[0]).not.toHaveProperty('maxBytesBilled');
2026-05-10 23:12:26 +02:00
});
it('rejects daemon-only fallback driver configs at config parse time', async () => {
await initKtxProject({ projectDir: tempDir });
2026-05-10 23:12:26 +02:00
await writeFile(
2026-05-10 23:51:24 +02:00
join(tempDir, 'ktx.yaml'),
2026-05-10 23:12:26 +02:00
[
'connections:',
' warehouse:',
' driver: duckdb',
' path: warehouse.duckdb',
'',
].join('\n'),
'utf-8',
);
await expect(loadKtxProject({ projectDir: tempDir })).rejects.toThrow(
/connections\.warehouse\.driver:.*Invalid discriminator value/,
2026-05-10 23:12:26 +02:00
);
});
it('rejects connection blocks with no driver field at config parse time', async () => {
await initKtxProject({ projectDir: tempDir });
2026-05-10 23:12:26 +02:00
await writeFile(
2026-05-10 23:51:24 +02:00
join(tempDir, 'ktx.yaml'),
2026-05-10 23:12:26 +02:00
[
'connections:',
' warehouse:',
' type: postgres',
' url: postgresql://example/db',
'',
].join('\n'),
'utf-8',
);
await expect(loadKtxProject({ projectDir: tempDir })).rejects.toThrow(
/connections\.warehouse\.driver:.*Invalid discriminator value/,
2026-05-10 23:12:26 +02:00
);
});
});