ktx/packages/cli/test/context/ingest/adapters/metricflow/chunk.test.ts

125 lines
5.5 KiB
TypeScript
Raw Permalink Normal View History

2026-05-10 23:12:26 +02:00
import { join, resolve } from 'node:path';
import { 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 { chunkMetricFlowProject } from '../../../../../src/context/ingest/adapters/metricflow/chunk.js';
import { parseMetricFlowStagedDir } from '../../../../../src/context/ingest/adapters/metricflow/parse.js';
2026-05-10 23:12:26 +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
2026-05-26 08:49:05 +02:00
const FIXTURES = resolve(__dirname, '../../../../fixtures/metricflow');
2026-05-10 23:12:26 +02:00
const SINGLE = join(FIXTURES, 'single-model');
const EXTENDS_CHAIN = join(FIXTURES, 'extends-chain');
const MULTI = join(FIXTURES, 'multi-component');
const DBT_MIXED = join(FIXTURES, 'dbt-mixed');
describe('chunkMetricFlowProject — first run', () => {
it('single-model fixture emits one WU with the orders model + its metric file (collapsed via metric refs)', async () => {
const project = await parseMetricFlowStagedDir(SINGLE);
const result = chunkMetricFlowProject(project);
expect(result.workUnits).toHaveLength(1);
const wu = result.workUnits[0];
expect(wu.unitKey).toBe('metricflow-orders');
expect(wu.rawFiles).toEqual(['models/orders.yml']);
expect(wu.dependencyPaths).toEqual([]);
expect(wu.peerFileIndex).toEqual([]);
});
it('extends-chain fixture collapses orders + orders_ext + metrics/orders_final into ONE WU', async () => {
const project = await parseMetricFlowStagedDir(EXTENDS_CHAIN);
const result = chunkMetricFlowProject(project);
expect(result.workUnits).toHaveLength(1);
const wu = result.workUnits[0];
expect(wu.unitKey).toBe('metricflow-orders');
expect(wu.rawFiles.sort()).toEqual(['metrics/orders_final.yml', 'models/orders.yml', 'models/orders_ext.yml']);
expect(wu.notes).toContain('orders');
expect(wu.notes).toContain('orders_ext');
expect(wu.notes).toContain('revenue');
});
it('multi-component fixture emits two disjoint WUs ordered by leadName', async () => {
const project = await parseMetricFlowStagedDir(MULTI);
const result = chunkMetricFlowProject(project);
expect(result.workUnits).toHaveLength(2);
expect(result.workUnits.map((wu) => wu.unitKey)).toEqual(['metricflow-campaigns', 'metricflow-orders']);
expect(result.workUnits[0].rawFiles).toEqual(['models/marketing/campaigns.yml']);
expect(result.workUnits[0].peerFileIndex).toEqual(['models/sales/orders.yml']);
expect(result.workUnits[1].rawFiles).toEqual(['models/sales/orders.yml']);
expect(result.workUnits[1].peerFileIndex).toEqual(['models/marketing/campaigns.yml']);
});
it('dbt-mixed fixture: non-MetricFlow YAML (dbt_project.yml) lands in peerFileIndex, not in any WU', async () => {
const project = await parseMetricFlowStagedDir(DBT_MIXED);
const result = chunkMetricFlowProject(project);
expect(result.workUnits).toHaveLength(1);
expect(result.workUnits[0].rawFiles).toEqual(['models/orders.yml']);
expect(result.workUnits[0].peerFileIndex).toEqual(['dbt_project.yml']);
});
it('chunk is deterministic: two identical invocations return structurally-equal WUs', async () => {
const p1 = await parseMetricFlowStagedDir(EXTENDS_CHAIN);
const p2 = await parseMetricFlowStagedDir(EXTENDS_CHAIN);
const r1 = chunkMetricFlowProject(p1);
const r2 = chunkMetricFlowProject(p2);
expect(JSON.stringify(r1)).toBe(JSON.stringify(r2));
});
it('DiffSet re-sync: only WUs with a touched rawFile are kept', async () => {
const project = await parseMetricFlowStagedDir(MULTI);
const result = chunkMetricFlowProject(project, {
diffSet: {
added: [],
modified: ['models/sales/orders.yml'],
deleted: [],
unchanged: ['models/marketing/campaigns.yml'],
},
});
expect(result.workUnits).toHaveLength(1);
expect(result.workUnits[0].unitKey).toBe('metricflow-orders');
expect(result.workUnits[0].rawFiles).toEqual(['models/sales/orders.yml']);
expect(result.workUnits[0].dependencyPaths).toEqual([]); // no unchanged sibling in this component
});
it('DiffSet re-sync: unchanged component siblings move from rawFiles into dependencyPaths', async () => {
const project = await parseMetricFlowStagedDir(EXTENDS_CHAIN);
const result = chunkMetricFlowProject(project, {
diffSet: {
added: [],
modified: ['models/orders_ext.yml'], // only the extension file changed
deleted: [],
unchanged: ['models/orders.yml', 'metrics/orders_final.yml'],
},
});
expect(result.workUnits).toHaveLength(1);
const wu = result.workUnits[0];
expect(wu.rawFiles).toEqual(['models/orders_ext.yml']);
expect(wu.dependencyPaths.sort()).toEqual(['metrics/orders_final.yml', 'models/orders.yml']);
});
it('DiffSet re-sync: all-unchanged yields zero WUs', async () => {
const project = await parseMetricFlowStagedDir(EXTENDS_CHAIN);
const result = chunkMetricFlowProject(project, {
diffSet: {
added: [],
modified: [],
deleted: [],
unchanged: ['models/orders.yml', 'models/orders_ext.yml', 'metrics/orders_final.yml'],
},
});
expect(result.workUnits).toEqual([]);
expect(result.eviction).toBeUndefined();
});
it('DiffSet re-sync: deleted files produce an EvictionUnit', async () => {
const project = await parseMetricFlowStagedDir(MULTI);
const result = chunkMetricFlowProject(project, {
diffSet: {
added: [],
modified: [],
deleted: ['models/marketing/campaigns.yml'],
unchanged: ['models/sales/orders.yml'],
},
});
expect(result.workUnits).toEqual([]);
expect(result.eviction).toEqual({
deletedRawPaths: ['models/marketing/campaigns.yml'],
});
});
});