mirror of
https://github.com/Kaelio/ktx.git
synced 2026-06-07 07:55:13 +02:00
56985b7e09
* 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
68 lines
2.4 KiB
TypeScript
68 lines
2.4 KiB
TypeScript
import { execFileSync } from 'node:child_process';
|
|
import { Ajv2020 } from 'ajv/dist/2020.js';
|
|
import { describe, expect, it } from 'vitest';
|
|
|
|
import { resolvedSourceSchema } from '../../../src/context/sl/schemas.js';
|
|
import { toResolvedWire } from '../../../src/context/sl/semantic-layer.service.js';
|
|
import type { SemanticLayerSource } from '../../../src/context/sl/types.js';
|
|
|
|
function loadPythonSourceDefinitionSchema(): Record<string, unknown> | null {
|
|
try {
|
|
const stdout = execFileSync('uv', ['run', 'python', '-m', 'semantic_layer', 'dump-schema'], {
|
|
cwd: new URL('../../../..', import.meta.url),
|
|
encoding: 'utf8',
|
|
stdio: ['ignore', 'pipe', 'ignore'],
|
|
});
|
|
return JSON.parse(stdout) as Record<string, unknown>;
|
|
} catch {
|
|
return null;
|
|
}
|
|
}
|
|
|
|
const sourceDefinitionJsonSchema = loadPythonSourceDefinitionSchema();
|
|
|
|
const fixtures: SemanticLayerSource[] = [
|
|
{
|
|
name: 'orders',
|
|
table: 'public.orders',
|
|
grain: ['id'],
|
|
columns: [
|
|
{ name: 'id', type: 'number' },
|
|
{
|
|
name: 'status',
|
|
type: 'string',
|
|
descriptions: { dbt: 'Order lifecycle status.' },
|
|
constraints: { dbt: { not_null: true } },
|
|
enum_values: { dbt: ['placed', 'shipped'] },
|
|
tests: { dbt: [{ name: 'accepted_values', package: 'dbt' }] },
|
|
},
|
|
],
|
|
joins: [{ to: 'customers', on: 'orders.customer_id = customers.id', relationship: 'many_to_one' }],
|
|
measures: [{ name: 'order_count', expr: 'count(id)' }],
|
|
segments: [{ name: 'paid', expr: "status = 'paid'" }],
|
|
default_time_dimension: { dbt: 'created_at' },
|
|
tags: { dbt: ['mart'] },
|
|
freshness: { dbt: { loaded_at_field: 'updated_at' } },
|
|
},
|
|
{
|
|
name: 'aav_orders',
|
|
sql: 'select id, status from public.orders where status = paid',
|
|
grain: ['id'],
|
|
columns: [{ name: 'id', type: 'number' }],
|
|
joins: [],
|
|
measures: [],
|
|
},
|
|
];
|
|
|
|
describe.skipIf(sourceDefinitionJsonSchema === null)('resolved source JSON Schema contract', () => {
|
|
it('keeps TS resolved-source fixtures accepted by the Python SourceDefinition schema', () => {
|
|
const ajv = new Ajv2020({ allErrors: true, strict: false });
|
|
const validate = ajv.compile(sourceDefinitionJsonSchema as Record<string, unknown>);
|
|
|
|
for (const fixture of fixtures) {
|
|
const wire = toResolvedWire(fixture);
|
|
expect(resolvedSourceSchema.safeParse(wire).success).toBe(true);
|
|
expect(validate(wire), JSON.stringify(validate.errors, null, 2)).toBe(true);
|
|
}
|
|
});
|
|
});
|