ktx/packages/cli/src/connectors/mysql/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

190 lines
5.3 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 MysqlTableNameRef = Pick<KtxTableRef, 'name'> & Partial<Pick<KtxTableRef, 'catalog' | 'db'>>;
/** @internal */
export class KtxMysqlDialect implements KtxDialect {
readonly type = 'mysql' as const;
private readonly typeMappings: Record<string, KtxSchemaDimensionType> = {
datetime: 'time',
timestamp: 'time',
date: 'time',
time: 'time',
year: 'time',
tinyint: 'number',
smallint: 'number',
mediumint: 'number',
int: 'number',
integer: 'number',
bigint: 'number',
decimal: 'number',
numeric: 'number',
float: 'number',
double: 'number',
real: 'number',
varchar: 'string',
char: 'string',
text: 'string',
tinytext: 'string',
mediumtext: 'string',
longtext: 'string',
enum: 'string',
set: 'string',
json: 'string',
bit: 'boolean',
bool: 'boolean',
boolean: 'boolean',
};
quoteIdentifier(identifier: string): string {
return `\`${identifier.replace(/`/g, '``')}\``;
}
formatTableName(table: MysqlTableNameRef): string {
return formatDialectTableName(table, this.quoteIdentifier.bind(this), 'ansi');
}
formatDisplayRef(table: MysqlTableNameRef): string {
return formatDialectDisplayRef(table, 'ansi');
}
parseDisplayRef(display: string): KtxTableRef | null {
return parseDialectDisplayRef(display, 'ansi');
}
columnDisplayTablePartCount(): 1 | 2 | 3 {
return columnDisplayPartCount('ansi');
}
mapDataType(nativeType: string): string {
return nativeType;
}
mapToDimensionType(nativeType: string): KtxSchemaDimensionType {
if (!nativeType) {
return 'string';
}
const lower = nativeType.toLowerCase().trim();
if (lower.includes('tinyint(1)')) {
return 'boolean';
}
const normalized = lower.includes('(') ? lower.split('(')[0] : lower;
if (this.typeMappings[normalized]) {
return this.typeMappings[normalized];
}
if (normalized.includes('time') || normalized.includes('date')) {
return 'time';
}
if (
normalized.includes('int') ||
normalized.includes('num') ||
normalized.includes('dec') ||
normalized.includes('float') ||
normalized.includes('double')
) {
return 'number';
}
if (normalized.includes('bit') || normalized === 'bool' || normalized === 'boolean') {
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} 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 CHAR)) != '' LIMIT ${limit}`;
}
getRandomSampleFilter(samplePct: number): string {
if (samplePct <= 0 || samplePct >= 1) {
return '';
}
return `RAND() < ${samplePct}`;
}
getTableSampleClause(_samplePct: number): string {
return '';
}
getLimitOffsetClause(limit: number, offset?: number): string {
return limitOffsetClause(limit, offset);
}
getTopClause(_limit: number): string {
return '';
}
getNullCountExpression(column: string): string {
return `SUM(CASE WHEN ${column} IS NULL THEN 1 ELSE 0 END)`;
}
getDistinctCountExpression(column: string): string {
return `COUNT(DISTINCT ${column})`;
}
textLengthExpression(columnSql: string): string {
return `CHAR_LENGTH(CAST(${columnSql} AS CHAR))`;
}
castToText(columnSql: string): string {
return `CAST(${columnSql} AS CHAR)`;
}
getSampleValueAggregation(innerSql: string): string {
return `(SELECT GROUP_CONCAT(CAST(value AS CHAR) SEPARATOR CHAR(31)) FROM (${innerSql}) AS relationship_profile_values)`;
}
generateCardinalitySampleQuery(tableName: string, columnName: string, sampleSize: number): string {
return `
SELECT COUNT(DISTINCT val) AS cardinality
FROM (
SELECT ${columnName} AS val
FROM ${tableName}
WHERE ${columnName} IS NOT NULL
LIMIT ${sampleSize}
) AS sampled
`;
}
generateDistinctValuesQuery(tableName: string, columnName: string, limit: number): string {
return `
SELECT DISTINCT CAST(${columnName} AS CHAR) 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 `
SELECT COUNT(DISTINCT val) AS cardinality
FROM (
SELECT ${columnName} AS val
FROM ${tableName}
WHERE ${columnName} IS NOT NULL
ORDER BY RAND()
LIMIT ${sampleSize}
) AS sampled
`;
}
}