mirror of
https://github.com/Kaelio/ktx.git
synced 2026-07-04 10:52:13 +02:00
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
This commit is contained in:
parent
924868841d
commit
56985b7e09
548 changed files with 5048 additions and 2228 deletions
|
|
@ -1,291 +0,0 @@
|
|||
import { mkdtemp, rm } from 'node:fs/promises';
|
||||
import { tmpdir } from 'node:os';
|
||||
import { join } from 'node:path';
|
||||
import { afterEach, beforeEach, describe, expect, it } from 'vitest';
|
||||
import { initKtxProject, type KtxLocalProject } from '../../context/project/project.js';
|
||||
import { createKtxEntityDetailsService } from './entity-details.js';
|
||||
import type { KtxConnectionDriver, KtxScanReport, KtxSchemaTable } from './types.js';
|
||||
|
||||
describe('createKtxEntityDetailsService', () => {
|
||||
let tempDir: string;
|
||||
let project: KtxLocalProject;
|
||||
|
||||
beforeEach(async () => {
|
||||
tempDir = await mkdtemp(join(tmpdir(), 'ktx-entity-details-service-'));
|
||||
project = await initKtxProject({ projectDir: join(tempDir, 'project') });
|
||||
});
|
||||
|
||||
afterEach(async () => {
|
||||
await rm(tempDir, { recursive: true, force: true });
|
||||
});
|
||||
|
||||
function scanReport(input: {
|
||||
connectionId: string;
|
||||
syncId: string;
|
||||
runId: string;
|
||||
driver?: KtxConnectionDriver;
|
||||
createdAt?: string;
|
||||
}): KtxScanReport {
|
||||
const rawSourcesDir = `raw-sources/${input.connectionId}/live-database/${input.syncId}`;
|
||||
return {
|
||||
connectionId: input.connectionId,
|
||||
driver: input.driver ?? 'postgres',
|
||||
syncId: input.syncId,
|
||||
runId: input.runId,
|
||||
trigger: 'mcp',
|
||||
mode: 'structural',
|
||||
dryRun: false,
|
||||
artifactPaths: {
|
||||
rawSourcesDir,
|
||||
reportPath: `${rawSourcesDir}/scan-report.json`,
|
||||
manifestShards: [],
|
||||
enrichmentArtifacts: [],
|
||||
},
|
||||
diffSummary: {
|
||||
tablesAdded: 0,
|
||||
tablesModified: 0,
|
||||
tablesDeleted: 0,
|
||||
tablesUnchanged: 1,
|
||||
columnsAdded: 0,
|
||||
columnsModified: 0,
|
||||
columnsDeleted: 0,
|
||||
},
|
||||
manifestShardsWritten: 0,
|
||||
structuralSyncStats: {
|
||||
tablesCreated: 1,
|
||||
tablesUpdated: 0,
|
||||
tablesDeleted: 0,
|
||||
columnsCreated: 0,
|
||||
columnsUpdated: 0,
|
||||
columnsDeleted: 0,
|
||||
},
|
||||
enrichment: {
|
||||
dataDictionary: 'skipped',
|
||||
tableDescriptions: 'skipped',
|
||||
columnDescriptions: 'skipped',
|
||||
embeddings: 'skipped',
|
||||
deterministicRelationships: 'skipped',
|
||||
llmRelationshipValidation: 'skipped',
|
||||
statisticalValidation: 'skipped',
|
||||
},
|
||||
capabilityGaps: [],
|
||||
warnings: [],
|
||||
relationships: { accepted: 0, review: 0, rejected: 0, skipped: 0 },
|
||||
enrichmentState: { resumedStages: [], completedStages: [], failedStages: [] },
|
||||
createdAt: input.createdAt ?? '2026-05-14T09:00:00.000Z',
|
||||
};
|
||||
}
|
||||
|
||||
function ordersTable(input: { db?: string | null; estimatedRows?: number | null } = {}): KtxSchemaTable {
|
||||
return {
|
||||
catalog: null,
|
||||
db: input.db ?? 'public',
|
||||
name: 'orders',
|
||||
kind: 'table',
|
||||
comment: 'Customer orders',
|
||||
estimatedRows: input.estimatedRows ?? 12,
|
||||
columns: [
|
||||
{
|
||||
name: 'id',
|
||||
nativeType: 'integer',
|
||||
normalizedType: 'integer',
|
||||
dimensionType: 'number',
|
||||
nullable: false,
|
||||
primaryKey: true,
|
||||
comment: 'Order id',
|
||||
},
|
||||
{
|
||||
name: 'status',
|
||||
nativeType: 'text',
|
||||
normalizedType: 'text',
|
||||
dimensionType: 'string',
|
||||
nullable: false,
|
||||
primaryKey: false,
|
||||
comment: 'Order status',
|
||||
},
|
||||
],
|
||||
foreignKeys: [
|
||||
{
|
||||
fromColumn: 'customer_id',
|
||||
toCatalog: null,
|
||||
toDb: 'public',
|
||||
toTable: 'customers',
|
||||
toColumn: 'id',
|
||||
constraintName: 'orders_customer_id_fkey',
|
||||
},
|
||||
],
|
||||
};
|
||||
}
|
||||
|
||||
async function seedScan(input: {
|
||||
connectionId?: string;
|
||||
syncId: string;
|
||||
runId: string;
|
||||
driver?: KtxConnectionDriver;
|
||||
extractedAt?: string;
|
||||
tables?: KtxSchemaTable[];
|
||||
}): Promise<void> {
|
||||
const connectionId = input.connectionId ?? 'warehouse';
|
||||
const report = scanReport({
|
||||
connectionId,
|
||||
syncId: input.syncId,
|
||||
runId: input.runId,
|
||||
driver: input.driver,
|
||||
createdAt: input.extractedAt,
|
||||
});
|
||||
const root = report.artifactPaths.rawSourcesDir;
|
||||
await project.fileStore.writeFile(
|
||||
`${root}/connection.json`,
|
||||
JSON.stringify(
|
||||
{
|
||||
connectionId,
|
||||
driver: report.driver,
|
||||
extractedAt: input.extractedAt ?? report.createdAt,
|
||||
scope: { schemas: ['public'] },
|
||||
},
|
||||
null,
|
||||
2,
|
||||
),
|
||||
'ktx',
|
||||
'ktx@example.com',
|
||||
'seed connection',
|
||||
);
|
||||
for (const table of input.tables ?? [ordersTable()]) {
|
||||
await project.fileStore.writeFile(
|
||||
`${root}/tables/${table.db ?? 'default'}-${table.name}.json`,
|
||||
JSON.stringify(table, null, 2),
|
||||
'ktx',
|
||||
'ktx@example.com',
|
||||
`seed ${table.name}`,
|
||||
);
|
||||
}
|
||||
await project.fileStore.writeFile(
|
||||
`${root}/scan-report.json`,
|
||||
JSON.stringify(report, null, 2),
|
||||
'ktx',
|
||||
'ktx@example.com',
|
||||
'seed scan report',
|
||||
);
|
||||
}
|
||||
|
||||
it('returns the latest scan snapshot table details for a display string', async () => {
|
||||
await seedScan({ syncId: 'sync-1', runId: 'scan-old', extractedAt: '2026-05-14T08:00:00.000Z' });
|
||||
await seedScan({
|
||||
syncId: 'sync-2',
|
||||
runId: 'scan-new',
|
||||
extractedAt: '2026-05-14T09:00:00.000Z',
|
||||
tables: [ordersTable({ estimatedRows: 99 })],
|
||||
});
|
||||
const service = createKtxEntityDetailsService(project);
|
||||
|
||||
const result = await service.read({
|
||||
connectionId: 'warehouse',
|
||||
entities: [{ table: 'public.orders' }],
|
||||
});
|
||||
|
||||
expect(result.results).toHaveLength(1);
|
||||
expect(result.results[0]).toMatchObject({
|
||||
ok: true,
|
||||
connectionId: 'warehouse',
|
||||
display: 'public.orders',
|
||||
estimatedRows: 99,
|
||||
snapshot: {
|
||||
syncId: 'sync-2',
|
||||
scanRunId: 'scan-new',
|
||||
extractedAt: '2026-05-14T09:00:00.000Z',
|
||||
},
|
||||
columns: [
|
||||
{ name: 'id', nativeType: 'integer', primaryKey: true },
|
||||
{ name: 'status', nativeType: 'text', nullable: false },
|
||||
],
|
||||
});
|
||||
});
|
||||
|
||||
it('filters requested columns while keeping full-table foreign keys', async () => {
|
||||
await seedScan({ syncId: 'sync-1', runId: 'scan-1' });
|
||||
const service = createKtxEntityDetailsService(project);
|
||||
|
||||
const result = await service.read({
|
||||
connectionId: 'warehouse',
|
||||
entities: [{ table: { catalog: null, db: 'public', name: 'orders' }, columns: ['status'] }],
|
||||
});
|
||||
|
||||
expect(result.results[0]).toMatchObject({
|
||||
ok: true,
|
||||
columns: [{ name: 'status' }],
|
||||
foreignKeys: [
|
||||
{
|
||||
fromColumn: 'customer_id',
|
||||
toDb: 'public',
|
||||
toTable: 'customers',
|
||||
toColumn: 'id',
|
||||
},
|
||||
],
|
||||
});
|
||||
});
|
||||
|
||||
it('returns a structured missing-scan error', async () => {
|
||||
const service = createKtxEntityDetailsService(project);
|
||||
|
||||
const result = await service.read({
|
||||
connectionId: 'warehouse',
|
||||
entities: [{ table: 'public.orders' }],
|
||||
});
|
||||
|
||||
expect(result.results).toEqual([
|
||||
{
|
||||
ok: false,
|
||||
connectionId: 'warehouse',
|
||||
table: 'public.orders',
|
||||
error: {
|
||||
code: 'scan_missing',
|
||||
message: 'No live-database scan found for connection "warehouse"; run `ktx ingest warehouse` or `ktx scan warehouse`.',
|
||||
},
|
||||
},
|
||||
]);
|
||||
});
|
||||
|
||||
it('reports ambiguous bare table names across schemas', async () => {
|
||||
await seedScan({
|
||||
syncId: 'sync-1',
|
||||
runId: 'scan-1',
|
||||
tables: [ordersTable({ db: 'public' }), ordersTable({ db: 'archive' })],
|
||||
});
|
||||
const service = createKtxEntityDetailsService(project);
|
||||
|
||||
const result = await service.read({
|
||||
connectionId: 'warehouse',
|
||||
entities: [{ table: 'orders' }],
|
||||
});
|
||||
|
||||
expect(result.results[0]).toMatchObject({
|
||||
ok: false,
|
||||
error: {
|
||||
code: 'ambiguous_table',
|
||||
candidates: [
|
||||
{ tableRef: { catalog: null, db: 'archive', name: 'orders' }, display: 'archive.orders' },
|
||||
{ tableRef: { catalog: null, db: 'public', name: 'orders' }, display: 'public.orders' },
|
||||
],
|
||||
},
|
||||
});
|
||||
});
|
||||
|
||||
it('reports missing requested columns with available column candidates', async () => {
|
||||
await seedScan({ syncId: 'sync-1', runId: 'scan-1' });
|
||||
const service = createKtxEntityDetailsService(project);
|
||||
|
||||
const result = await service.read({
|
||||
connectionId: 'warehouse',
|
||||
entities: [{ table: 'public.orders', columns: ['status', 'plan_tier'] }],
|
||||
});
|
||||
|
||||
expect(result.results[0]).toMatchObject({
|
||||
ok: false,
|
||||
error: {
|
||||
code: 'column_not_found',
|
||||
message: 'Column(s) not found on public.orders: plan_tier',
|
||||
candidates: ['id', 'status'],
|
||||
},
|
||||
});
|
||||
});
|
||||
});
|
||||
Loading…
Add table
Add a link
Reference in a new issue