ktx/packages/cli/test/ingest-report-file.test.ts

79 lines
2.3 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';
import { afterEach, beforeEach, describe, expect, it } 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 { readIngestReportSnapshotFile } from '../src/ingest-report-file.js';
2026-05-10 23:12:26 +02:00
function reportSnapshot() {
return {
id: 'report-1',
runId: 'run-1',
jobId: 'job-1',
connectionId: 'warehouse',
sourceKey: 'metabase',
createdAt: '2026-04-30T12:00:00.000Z',
body: {
syncId: 'sync-1',
diffSummary: { added: 1, modified: 0, deleted: 0, unchanged: 0 },
commitSha: null,
workUnits: [],
failedWorkUnits: [],
reconciliationSkipped: true,
conflictsResolved: [],
evictionsApplied: [],
unmappedFallbacks: [],
evictionInputs: [],
unresolvedCards: [],
supersededBy: null,
overrideOf: null,
provenanceRows: [],
toolTranscripts: [],
},
};
}
describe('readIngestReportSnapshotFile', () => {
let tempDir: string;
beforeEach(async () => {
2026-05-10 23:51:24 +02:00
tempDir = await mkdtemp(join(tmpdir(), 'ktx-report-file-'));
2026-05-10 23:12:26 +02:00
});
afterEach(async () => {
await rm(tempDir, { recursive: true, force: true });
});
it('reads and parses an ingest report JSON file', async () => {
const reportPath = join(tempDir, 'report.json');
await writeFile(reportPath, `${JSON.stringify(reportSnapshot(), null, 2)}\n`, 'utf-8');
const report = await readIngestReportSnapshotFile(reportPath);
expect(report).toMatchObject({
id: 'report-1',
runId: 'run-1',
jobId: 'job-1',
connectionId: 'warehouse',
sourceKey: 'metabase',
});
});
it('reports invalid JSON with the file path', async () => {
const reportPath = join(tempDir, 'invalid.json');
await writeFile(reportPath, '{not json', 'utf-8');
await expect(readIngestReportSnapshotFile(reportPath)).rejects.toThrow(
`Invalid JSON in ingest report file ${reportPath}`,
);
});
it('reports schema failures with the file path', async () => {
const reportPath = join(tempDir, 'wrong-shape.json');
await writeFile(reportPath, JSON.stringify({ id: 'report-1' }), 'utf-8');
await expect(readIngestReportSnapshotFile(reportPath)).rejects.toThrow(
`Invalid ingest report file ${reportPath}`,
);
});
});