ktx/packages/cli/test/context/ingest/adapters/metricflow/parse.test.ts
Andrey Avtomonov 56985b7e09
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

206 lines
7.6 KiB
TypeScript

import { mkdir, 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';
import { parseMetricFlowStagedDir } from '../../../../../src/context/ingest/adapters/metricflow/parse.js';
async function writeFixture(stagedDir: string, relPath: string, body: string): Promise<void> {
const abs = join(stagedDir, relPath);
await mkdir(join(abs, '..'), { recursive: true });
await writeFile(abs, body, 'utf-8');
}
describe('parseMetricFlowStagedDir', () => {
let stagedDir: string;
beforeEach(async () => {
stagedDir = await mkdtemp(join(tmpdir(), 'mf-parse-'));
});
afterEach(async () => {
await rm(stagedDir, { recursive: true, force: true });
});
it('extracts one semantic_model with its measures + dimensions + entities', async () => {
await writeFixture(
stagedDir,
'models/orders.yml',
[
'semantic_models:',
' - name: orders',
' description: Order fact table.',
" model: ref('orders')",
' entities:',
' - name: order_id',
' type: primary',
' - name: customer_id',
' type: foreign',
' dimensions:',
' - name: ordered_at',
' type: time',
' type_params:',
' time_granularity: day',
' measures:',
' - name: order_count',
' agg: count',
' expr: order_id',
' - name: gross_amount',
' agg: sum',
' expr: amount',
'',
].join('\n'),
);
const project = await parseMetricFlowStagedDir(stagedDir);
expect(project.semanticModels).toHaveLength(1);
const sm = project.semanticModels[0];
expect(sm.path).toBe('models/orders.yml');
expect(sm.name).toBe('orders');
expect(sm.modelRef).toBe('orders');
expect(sm.measureNames).toEqual(['gross_amount', 'order_count']);
expect(sm.dimensionNames).toEqual(['ordered_at']);
expect(sm.entityNames).toEqual(['customer_id', 'order_id']);
expect(sm.primaryEntities).toEqual(['order_id']);
expect(sm.foreignEntities).toEqual(['customer_id']);
expect(sm.extendsFrom).toEqual([]);
expect(project.files).toEqual([
{
path: 'models/orders.yml',
content: expect.stringContaining('semantic_models:'),
},
]);
});
it('captures `extends:` as a string OR a list', async () => {
await writeFixture(
stagedDir,
'models/orders.yml',
[
'semantic_models:',
' - name: orders',
" model: ref('orders')",
' measures:',
' - {name: order_count, agg: count, expr: order_id}',
'',
].join('\n'),
);
await writeFixture(
stagedDir,
'models/orders_ext_list.yml',
[
'semantic_models:',
' - name: orders_ext_list',
" model: ref('orders_ext')",
' extends: [orders]',
' measures:',
' - {name: refund_amount, agg: sum, expr: refund_amt}',
'',
].join('\n'),
);
await writeFixture(
stagedDir,
'models/orders_ext_str.yml',
[
'semantic_models:',
' - name: orders_ext_str',
" model: ref('orders_ext')",
' extends: orders',
' measures:',
' - {name: refund_amount2, agg: sum, expr: refund_amt2}',
'',
].join('\n'),
);
const project = await parseMetricFlowStagedDir(stagedDir);
const list = project.semanticModels.find((sm) => sm.name === 'orders_ext_list');
const str = project.semanticModels.find((sm) => sm.name === 'orders_ext_str');
expect(list?.extendsFrom).toEqual(['orders']);
expect(str?.extendsFrom).toEqual(['orders']);
});
it('extracts metrics with referenced measures for simple + derived + ratio + cumulative', async () => {
await writeFixture(
stagedDir,
'metrics/core.yml',
[
'metrics:',
' - name: total_orders',
' type: simple',
' type_params:',
' measure: order_count',
' - name: revenue',
' type: derived',
' type_params:',
' expr: gross_amount - refund_amount',
' metrics:',
' - name: gross_amount',
' - name: refund_amount',
' - name: refund_rate',
' type: ratio',
' type_params:',
' numerator: refund_amount',
' denominator: gross_amount',
' - name: cum_revenue',
' type: cumulative',
' type_params:',
' measure: gross_amount',
' window: 7 days',
'',
].join('\n'),
);
const project = await parseMetricFlowStagedDir(stagedDir);
expect(project.metrics).toHaveLength(4);
const byName = new Map(project.metrics.map((m) => [m.name, m]));
expect(byName.get('total_orders')?.type).toBe('simple');
expect(byName.get('total_orders')?.measureRef).toBe('order_count');
expect(byName.get('revenue')?.type).toBe('derived');
expect(byName.get('revenue')?.dependsOn.sort()).toEqual(['gross_amount', 'refund_amount']);
expect(byName.get('refund_rate')?.type).toBe('ratio');
expect(byName.get('refund_rate')?.dependsOn.sort()).toEqual(['gross_amount', 'refund_amount']);
expect(byName.get('cum_revenue')?.type).toBe('cumulative');
expect(byName.get('cum_revenue')?.measureRef).toBe('gross_amount');
});
it('returns empty arrays for a non-MetricFlow YAML (e.g. dbt_project.yml)', async () => {
await writeFixture(stagedDir, 'dbt_project.yml', 'name: my_proj\nversion: "1.0.0"\n');
const project = await parseMetricFlowStagedDir(stagedDir);
expect(project.semanticModels).toEqual([]);
expect(project.metrics).toEqual([]);
expect(project.allPaths).toEqual(['dbt_project.yml']);
});
it('skips files that are not YAML (or fail to parse) without throwing', async () => {
await writeFixture(stagedDir, 'broken.yml', '{ this is: not valid YAML :::');
await writeFixture(stagedDir, 'other.txt', 'ignore me');
const project = await parseMetricFlowStagedDir(stagedDir);
expect(project.semanticModels).toEqual([]);
expect(project.metrics).toEqual([]);
// allPaths includes `.yml` / `.yaml` only, even when unparseable:
expect(project.allPaths).toEqual(['broken.yml']);
});
it('allPaths is sorted deterministically', async () => {
await writeFixture(stagedDir, 'models/z.yml', 'semantic_models: []\n');
await writeFixture(stagedDir, 'models/a.yml', 'semantic_models: []\n');
await writeFixture(stagedDir, 'metrics/b.yaml', 'metrics: []\n');
const project = await parseMetricFlowStagedDir(stagedDir);
expect(project.allPaths).toEqual(['metrics/b.yaml', 'models/a.yml', 'models/z.yml']);
});
it("extracts modelRef from ref('name') and source('src','table') and literal strings", async () => {
await writeFixture(
stagedDir,
'models/a.yml',
[
'semantic_models:',
' - {name: a, model: "ref(\'orders\')", measures: [{name: c, agg: count, expr: id}]}',
" - {name: b, model: \"source('raw','orders_raw')\", measures: [{name: c, agg: count, expr: id}]}",
' - {name: c, model: plain_table, measures: [{name: c, agg: count, expr: id}]}',
'',
].join('\n'),
);
const project = await parseMetricFlowStagedDir(stagedDir);
const byName = new Map(project.semanticModels.map((s) => [s.name, s]));
expect(byName.get('a')?.modelRef).toBe('orders');
expect(byName.get('b')?.modelRef).toBe('orders_raw');
expect(byName.get('c')?.modelRef).toBe('plain_table');
});
});