ktx/packages/cli/src/connectors/bigquery/dialect.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

193 lines
5.6 KiB
TypeScript

import type { KtxDialect } from '../../context/connections/dialects.js';
import {
columnDisplayPartCount,
formatDialectDisplayRef,
formatDialectTableName,
limitOffsetClause,
parseDialectDisplayRef,
} from '../../context/connections/dialect-helpers.js';
import type { KtxSchemaDimensionType, KtxTableRef } from '../../context/scan/types.js';
type BigQueryTableNameRef = Pick<KtxTableRef, 'name'> & Partial<Pick<KtxTableRef, 'catalog' | 'db'>>;
/** @internal */
export class KtxBigQueryDialect implements KtxDialect {
readonly type = 'bigquery' as const;
private readonly typeMappings: Record<string, KtxSchemaDimensionType> = {
TIMESTAMP: 'time',
DATETIME: 'time',
DATE: 'time',
TIME: 'time',
INT64: 'number',
INTEGER: 'number',
FLOAT64: 'number',
FLOAT: 'number',
NUMERIC: 'number',
BIGNUMERIC: 'number',
STRING: 'string',
BYTES: 'string',
BOOL: 'boolean',
BOOLEAN: 'boolean',
};
quoteIdentifier(identifier: string): string {
return `\`${identifier.replace(/`/g, '\\`')}\``;
}
formatTableName(table: BigQueryTableNameRef): string {
return formatDialectTableName(table, this.quoteIdentifier.bind(this), 'three-part');
}
formatDisplayRef(table: BigQueryTableNameRef): string {
return formatDialectDisplayRef(table, 'three-part');
}
parseDisplayRef(display: string): KtxTableRef | null {
return parseDialectDisplayRef(display, 'three-part');
}
columnDisplayTablePartCount(): 1 | 2 | 3 {
return columnDisplayPartCount('three-part');
}
mapDataType(nativeType: string): string {
const fieldType = nativeType.toUpperCase().trim();
if (fieldType === 'RECORD' || fieldType === 'STRUCT') {
return 'JSON';
}
const typeMapping: Record<string, string> = {
STRING: 'VARCHAR',
BYTES: 'VARBINARY',
INTEGER: 'BIGINT',
INT64: 'BIGINT',
FLOAT: 'DOUBLE',
FLOAT64: 'DOUBLE',
NUMERIC: 'DECIMAL',
BIGNUMERIC: 'DECIMAL',
BOOLEAN: 'BOOLEAN',
BOOL: 'BOOLEAN',
TIMESTAMP: 'TIMESTAMP',
DATE: 'DATE',
TIME: 'TIME',
DATETIME: 'DATETIME',
GEOGRAPHY: 'GEOGRAPHY',
JSON: 'JSON',
};
return typeMapping[fieldType] || fieldType;
}
mapToDimensionType(nativeType: string): KtxSchemaDimensionType {
if (!nativeType) {
return 'string';
}
const normalizedType = nativeType.toUpperCase().trim();
if (this.typeMappings[normalizedType]) {
return this.typeMappings[normalizedType];
}
if (normalizedType.includes('TIME') || normalizedType.includes('DATE')) {
return 'time';
}
if (normalizedType.includes('INT') || normalizedType.includes('NUM') || normalizedType.includes('FLOAT')) {
return 'number';
}
if (normalizedType.includes('BOOL')) {
return 'boolean';
}
return 'string';
}
generateSampleQuery(tableName: string, limit: number, columns?: string[]): string {
const columnList =
columns && columns.length > 0 ? columns.map((column) => this.quoteIdentifier(column)).join(', ') : '*';
return `SELECT ${columnList} FROM ${tableName} ORDER BY RAND() LIMIT ${limit}`;
}
generateColumnSampleQuery(tableName: string, columnName: string, limit: number): string {
const quotedColumn = this.quoteIdentifier(columnName);
return `SELECT ${quotedColumn} FROM ${tableName} WHERE ${quotedColumn} IS NOT NULL AND TRIM(CAST(${quotedColumn} AS STRING)) != '' ORDER BY RAND() LIMIT ${limit}`;
}
getRandomSampleFilter(samplePct: number): string {
if (samplePct <= 0 || samplePct >= 1) {
return '';
}
return `RAND() < ${samplePct}`;
}
getTableSampleClause(samplePct: number): string {
if (samplePct <= 0 || samplePct >= 1) {
return '';
}
return `TABLESAMPLE SYSTEM (${samplePct * 100} PERCENT)`;
}
getLimitOffsetClause(limit: number, offset?: number): string {
return limitOffsetClause(limit, offset);
}
getTopClause(_limit: number): string {
return '';
}
getNullCountExpression(column: string): string {
return `COUNTIF(${column} IS NULL)`;
}
getDistinctCountExpression(column: string): string {
return `APPROX_COUNT_DISTINCT(${column})`;
}
textLengthExpression(columnSql: string): string {
return `LENGTH(CAST(${columnSql} AS STRING))`;
}
castToText(columnSql: string): string {
return `CAST(${columnSql} AS STRING)`;
}
getSampleValueAggregation(innerSql: string): string {
return `(SELECT STRING_AGG(CAST(value AS STRING), '\\u001F') FROM (${innerSql}) AS relationship_profile_values)`;
}
generateCardinalitySampleQuery(tableName: string, columnName: string, sampleSize: number): string {
return `
WITH sampled AS (
SELECT ${columnName} AS val
FROM ${tableName}
WHERE ${columnName} IS NOT NULL
LIMIT ${sampleSize}
)
SELECT APPROX_COUNT_DISTINCT(val) AS cardinality
FROM sampled
`;
}
generateDistinctValuesQuery(tableName: string, columnName: string, limit: number): string {
return `
SELECT DISTINCT CAST(${columnName} AS STRING) AS val
FROM ${tableName}
WHERE ${columnName} IS NOT NULL
ORDER BY val
LIMIT ${limit}
`;
}
generateColumnStatisticsQuery(_schemaName: string, _tableName: string): string | null {
return null;
}
generateRandomizedCardinalitySampleQuery(tableName: string, columnName: string, sampleSize: number): string {
return `
WITH sampled AS (
SELECT ${columnName} AS val
FROM ${tableName}
WHERE ${columnName} IS NOT NULL
ORDER BY RAND()
LIMIT ${sampleSize}
)
SELECT APPROX_COUNT_DISTINCT(val) AS cardinality
FROM sampled
`;
}
}