ktx/packages/cli/test/context/ingest/dbt-shared/project-vars.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

118 lines
4 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 {
loadProjectInfo,
parseProjectName,
parseProjectVars,
resolveJinjaVariables,
} from '../../../../src/context/ingest/dbt-shared/project-vars.js';
function entries(map: Map<string, string>): Record<string, string> {
return Object.fromEntries([...map.entries()].sort(([a], [b]) => a.localeCompare(b)));
}
describe('dbt-shared project vars', () => {
let tmpRoot: string;
beforeEach(async () => {
tmpRoot = await mkdtemp(join(tmpdir(), 'dbt-project-vars-'));
});
afterEach(async () => {
await rm(tmpRoot, { recursive: true, force: true });
});
it('extracts top-level vars, nested dotted vars, and scalar values only', () => {
const vars = parseProjectVars(`
name: revenue_project
vars:
database: analytics
enabled: true
threads: 4
ignored_list:
- a
ignored_null:
pkg:
region: us
fiscal_year: 2026
`);
expect(entries(vars)).toEqual({
database: 'analytics',
enabled: 'true',
'pkg.fiscal_year': '2026',
'pkg.region': 'us',
threads: '4',
});
});
it('returns an empty variable map for missing vars, malformed YAML, arrays, and scalar documents', () => {
expect(entries(parseProjectVars('name: no_vars\n'))).toEqual({});
expect(entries(parseProjectVars('{{{{ invalid yaml'))).toEqual({});
expect(entries(parseProjectVars('- just\n- a\n- list\n'))).toEqual({});
});
it('extracts a string project name and returns null for invalid or missing names', () => {
expect(parseProjectName('name: revenue_project\n')).toBe('revenue_project');
expect(parseProjectName('version: 1\n')).toBeNull();
expect(parseProjectName('{{{{ invalid yaml')).toBeNull();
expect(parseProjectName('name: 42\n')).toBeNull();
});
it('resolves exact var names, honors defaults, and reports unresolved names without throwing', () => {
const variables = new Map<string, string>([
['database', 'analytics'],
['pkg.region', 'us'],
]);
const result = resolveJinjaVariables(
[
'database: "{{ var(\'database\') }}"',
'region: "{{ var("pkg.region") }}"',
'schema: "{{ var(\'schema\', \'public\') }}"',
'missing: "{{ var(\'missing\') }}"',
].join('\n'),
variables,
);
expect(result.content).toContain('database: "analytics"');
expect(result.content).toContain('region: "us"');
expect(result.content).toContain('schema: "public"');
expect(result.content).toContain('missing: "{{ var(\'missing\') }}"');
expect(result.unresolvedVars).toEqual(['missing']);
});
it('keeps package-scoped variables exact and does not resolve by suffix', () => {
const variables = parseProjectVars(`
vars:
pkg:
database: package_db
`);
const result = resolveJinjaVariables(
'database: "{{ var(\'database\', \'fallback_db\') }}"\npackage_database: "{{ var(\'pkg.database\') }}"\n',
variables,
);
expect(result.content).toContain('database: "fallback_db"');
expect(result.content).toContain('package_database: "package_db"');
expect(result.unresolvedVars).toEqual([]);
});
it('loads dbt_project.yml before dbt_project.yaml and falls back to an empty project info object', async () => {
const projectDir = join(tmpRoot, 'project');
await mkdir(projectDir, { recursive: true });
await writeFile(join(projectDir, 'dbt_project.yaml'), 'name: yaml_project\nvars:\n database: yaml_db\n');
await writeFile(join(projectDir, 'dbt_project.yml'), 'name: yml_project\nvars:\n database: yml_db\n');
const loaded = await loadProjectInfo(projectDir);
expect(loaded.projectName).toBe('yml_project');
expect(entries(loaded.variables)).toEqual({ database: 'yml_db' });
const missing = await loadProjectInfo(join(tmpRoot, 'missing'));
expect(missing.projectName).toBeNull();
expect(entries(missing.variables)).toEqual({});
});
});