ktx/packages/cli/test/connectors/bigquery/dialect.test.ts

45 lines
2.1 KiB
TypeScript
Raw Permalink Normal View History

2026-05-10 23:12:26 +02:00
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 { KtxBigQueryDialect } from '../../../src/connectors/bigquery/dialect.js';
2026-05-10 23:12:26 +02:00
2026-05-10 23:51:24 +02:00
describe('KtxBigQueryDialect', () => {
const dialect = new KtxBigQueryDialect();
2026-05-10 23:12:26 +02:00
it('quotes identifiers and formats project.dataset.table names', () => {
expect(dialect.quoteIdentifier('order`items')).toBe('`order\\`items`');
expect(dialect.formatTableName({ catalog: 'project-1', db: 'analytics', name: 'orders' })).toBe(
'`project-1`.`analytics`.`orders`',
);
expect(dialect.formatTableName({ db: 'analytics', name: 'orders' })).toBe('`analytics`.`orders`');
expect(dialect.formatTableName({ name: 'orders' })).toBe('`orders`');
});
it('maps native BigQuery types to normalized types and scan dimensions', () => {
expect(dialect.mapDataType('INT64')).toBe('BIGINT');
expect(dialect.mapDataType('STRUCT')).toBe('JSON');
expect(dialect.mapDataType('GEOGRAPHY')).toBe('GEOGRAPHY');
expect(dialect.mapToDimensionType('TIMESTAMP')).toBe('time');
expect(dialect.mapToDimensionType('NUMERIC')).toBe('number');
expect(dialect.mapToDimensionType('BOOL')).toBe('boolean');
expect(dialect.mapToDimensionType('JSON')).toBe('string');
});
it('generates sampling, cardinality, and distinct-value SQL', () => {
expect(dialect.generateSampleQuery('`p`.`d`.`orders`', 5, ['id', 'status'])).toBe(
'SELECT `id`, `status` FROM `p`.`d`.`orders` ORDER BY RAND() LIMIT 5',
);
expect(dialect.generateColumnSampleQuery('`p`.`d`.`orders`', 'status', 10)).toBe(
"SELECT `status` FROM `p`.`d`.`orders` WHERE `status` IS NOT NULL AND TRIM(CAST(`status` AS STRING)) != '' ORDER BY RAND() LIMIT 10",
);
expect(dialect.generateCardinalitySampleQuery('`p`.`d`.`orders`', '`status`', 100)).toContain(
'SELECT APPROX_COUNT_DISTINCT(val) AS cardinality',
);
expect(dialect.generateDistinctValuesQuery('`p`.`d`.`orders`', '`status`', 20)).toContain(
'SELECT DISTINCT CAST(`status` AS STRING) AS val',
);
});
it('keeps unsupported statistics explicit', () => {
expect(dialect.generateColumnStatisticsQuery('analytics', 'orders')).toBeNull();
});
});