mirror of
https://github.com/Kaelio/ktx.git
synced 2026-06-16 08:25:14 +02:00
refactor(workspace): fold internal packages into cli
This commit is contained in:
Andrey Avtomonov
parent
8c2333cc15
commit
ac3885b652
945 changed files with 517 additions and 2686 deletions
347
packages/cli/src/connectors/sqlserver/connector.test.ts
Normal file
347
packages/cli/src/connectors/sqlserver/connector.test.ts
Normal file
|
|
@ -0,0 +1,347 @@
|
|||
import { describe, expect, it, vi } from 'vitest';
|
||||
import {
|
||||
createSqlServerLiveDatabaseIntrospection,
|
||||
isKtxSqlServerConnectionConfig,
|
||||
KtxSqlServerScanConnector,
|
||||
sqlServerConnectionPoolConfigFromConfig,
|
||||
type KtxSqlServerPoolFactory,
|
||||
type KtxSqlServerQueryResult,
|
||||
} from './index.js';
|
||||
|
||||
function recordset<T extends Record<string, unknown>>(
|
||||
rows: T[],
|
||||
columnNames: string[],
|
||||
): T[] & { columns: Record<string, { type: { declaration: string } }> } {
|
||||
const withColumns = rows as T[] & { columns: Record<string, { type: { declaration: string } }> };
|
||||
withColumns.columns = Object.fromEntries(columnNames.map((name) => [name, { type: { declaration: 'nvarchar' } }]));
|
||||
return withColumns;
|
||||
}
|
||||
|
||||
function result<T extends Record<string, unknown>>(rows: T[], columnNames: string[]): KtxSqlServerQueryResult {
|
||||
return { recordset: recordset(rows, columnNames) };
|
||||
}
|
||||
|
||||
function fakePoolFactory(): KtxSqlServerPoolFactory {
|
||||
const query = vi.fn(async (sql: string): Promise<KtxSqlServerQueryResult> => {
|
||||
if (sql.includes('INFORMATION_SCHEMA.TABLES')) {
|
||||
return result(
|
||||
[
|
||||
{ table_name: 'customers', table_type: 'BASE TABLE' },
|
||||
{ table_name: 'orders', table_type: 'BASE TABLE' },
|
||||
{ table_name: 'order_summary', table_type: 'VIEW' },
|
||||
],
|
||||
['table_name', 'table_type'],
|
||||
);
|
||||
}
|
||||
if (sql.includes("ep.name = 'MS_Description'") && sql.includes('ep.minor_id = 0')) {
|
||||
return result([{ table_name: 'customers', table_comment: 'Customer table' }], [
|
||||
'table_name',
|
||||
'table_comment',
|
||||
]);
|
||||
}
|
||||
if (sql.includes("ep.name = 'MS_Description'") && sql.includes('ep.minor_id = c.column_id')) {
|
||||
return result([{ table_name: 'customers', column_name: 'id', column_comment: 'PK' }], [
|
||||
'table_name',
|
||||
'column_name',
|
||||
'column_comment',
|
||||
]);
|
||||
}
|
||||
if (sql.includes('INFORMATION_SCHEMA.COLUMNS')) {
|
||||
return result(
|
||||
[
|
||||
{ table_name: 'customers', column_name: 'id', data_type: 'int', is_nullable: 'NO' },
|
||||
{ table_name: 'customers', column_name: 'name', data_type: 'nvarchar', is_nullable: 'NO' },
|
||||
{ table_name: 'orders', column_name: 'id', data_type: 'int', is_nullable: 'NO' },
|
||||
{ table_name: 'orders', column_name: 'customer_id', data_type: 'int', is_nullable: 'NO' },
|
||||
{ table_name: 'orders', column_name: 'status', data_type: 'nvarchar', is_nullable: 'YES' },
|
||||
{ table_name: 'order_summary', column_name: 'status', data_type: 'nvarchar', is_nullable: 'YES' },
|
||||
],
|
||||
['table_name', 'column_name', 'data_type', 'is_nullable'],
|
||||
);
|
||||
}
|
||||
if (sql.includes("CONSTRAINT_TYPE = 'PRIMARY KEY'")) {
|
||||
return result(
|
||||
[
|
||||
{ table_name: 'customers', column_name: 'id' },
|
||||
{ table_name: 'orders', column_name: 'id' },
|
||||
],
|
||||
['table_name', 'column_name'],
|
||||
);
|
||||
}
|
||||
if (sql.includes('REFERENTIAL_CONSTRAINTS')) {
|
||||
return result(
|
||||
[
|
||||
{
|
||||
table_name: 'orders',
|
||||
column_name: 'customer_id',
|
||||
referenced_table_schema: 'dbo',
|
||||
referenced_table_name: 'customers',
|
||||
referenced_column_name: 'id',
|
||||
constraint_name: 'orders_customer_id_fk',
|
||||
},
|
||||
],
|
||||
[
|
||||
'table_name',
|
||||
'column_name',
|
||||
'referenced_table_schema',
|
||||
'referenced_table_name',
|
||||
'referenced_column_name',
|
||||
'constraint_name',
|
||||
],
|
||||
);
|
||||
}
|
||||
if (sql.includes('sys.partitions') && sql.includes('GROUP BY t.name')) {
|
||||
return result(
|
||||
[
|
||||
{ table_name: 'customers', row_count: 2 },
|
||||
{ table_name: 'orders', row_count: 2 },
|
||||
],
|
||||
['table_name', 'row_count'],
|
||||
);
|
||||
}
|
||||
if (sql.includes('SELECT TOP 1 [id], [status] FROM [dbo].[orders]')) {
|
||||
return result([{ id: 10, status: 'paid' }], ['id', 'status']);
|
||||
}
|
||||
if (sql.includes('SELECT TOP 1 * FROM (select id, status from dbo.orders) AS ktx_query_result')) {
|
||||
return result([{ id: 10, status: 'paid' }], ['id', 'status']);
|
||||
}
|
||||
if (sql.includes('SELECT TOP 5 [status] FROM [dbo].[orders]')) {
|
||||
return result([{ status: 'paid' }, { status: 'open' }], ['status']);
|
||||
}
|
||||
if (sql.includes('COUNT(DISTINCT val)')) {
|
||||
return result([{ cardinality: 2 }], ['cardinality']);
|
||||
}
|
||||
if (sql.includes('SELECT TOP 10 val')) {
|
||||
return result([{ val: 'open' }, { val: 'paid' }], ['val']);
|
||||
}
|
||||
if (sql.includes('SUM(p.rows) AS row_count') && sql.includes('t.name = @tableName')) {
|
||||
return result([{ row_count: 2 }], ['row_count']);
|
||||
}
|
||||
if (sql.includes('SELECT s.name AS schema_name')) {
|
||||
return result([{ schema_name: 'dbo' }, { schema_name: 'sales' }], ['schema_name']);
|
||||
}
|
||||
if (sql.trim() === 'SELECT 1') {
|
||||
return result([{ ok: 1 }], ['ok']);
|
||||
}
|
||||
throw new Error(`Unexpected SQL: ${sql}`);
|
||||
});
|
||||
const request: { input(name: string, value: unknown): typeof request; query: typeof query } = {
|
||||
input: vi.fn((_key: string, _value: unknown) => request),
|
||||
query,
|
||||
};
|
||||
const close = vi.fn(async () => undefined);
|
||||
return {
|
||||
createPool: vi.fn(async () => ({
|
||||
request: () => request,
|
||||
close,
|
||||
})),
|
||||
};
|
||||
}
|
||||
|
||||
describe('KtxSqlServerScanConnector', () => {
|
||||
it('resolves SQL Server connection configuration safely', () => {
|
||||
expect(
|
||||
isKtxSqlServerConnectionConfig({
|
||||
driver: 'sqlserver',
|
||||
host: 'localhost',
|
||||
database: 'analytics',
|
||||
}),
|
||||
).toBe(true);
|
||||
expect(isKtxSqlServerConnectionConfig({ driver: 'mysql', host: 'localhost', database: 'analytics' })).toBe(false);
|
||||
expect(
|
||||
sqlServerConnectionPoolConfigFromConfig({
|
||||
connectionId: 'warehouse',
|
||||
connection: {
|
||||
driver: 'sqlserver',
|
||||
host: 'db.example.test',
|
||||
port: 14330,
|
||||
database: 'analytics',
|
||||
username: 'reader',
|
||||
trustServerCertificate: false,
|
||||
},
|
||||
}),
|
||||
).toMatchObject({
|
||||
server: 'db.example.test',
|
||||
port: 14330,
|
||||
database: 'analytics',
|
||||
user: 'reader',
|
||||
options: { encrypt: true, trustServerCertificate: false },
|
||||
});
|
||||
});
|
||||
|
||||
it('introspects schema, primary keys, comments, row counts, views, and foreign keys', async () => {
|
||||
const connector = new KtxSqlServerScanConnector({
|
||||
connectionId: 'warehouse',
|
||||
connection: {
|
||||
driver: 'sqlserver',
|
||||
host: 'db.example.test',
|
||||
database: 'analytics',
|
||||
username: 'reader',
|
||||
schema: 'dbo',
|
||||
},
|
||||
poolFactory: fakePoolFactory(),
|
||||
now: () => new Date('2026-04-29T16:00:00.000Z'),
|
||||
});
|
||||
|
||||
const snapshot = await connector.introspect(
|
||||
{ connectionId: 'warehouse', driver: 'sqlserver' },
|
||||
{ runId: 'scan-run-1' },
|
||||
);
|
||||
|
||||
expect(snapshot).toMatchObject({
|
||||
connectionId: 'warehouse',
|
||||
driver: 'sqlserver',
|
||||
extractedAt: '2026-04-29T16:00:00.000Z',
|
||||
scope: { catalogs: ['analytics'], schemas: ['dbo'] },
|
||||
metadata: {
|
||||
database: 'analytics',
|
||||
host: 'db.example.test',
|
||||
schemas: ['dbo'],
|
||||
table_count: 3,
|
||||
total_columns: 6,
|
||||
},
|
||||
});
|
||||
expect(snapshot.tables.map((table) => [table.name, table.kind, table.estimatedRows, table.comment])).toEqual([
|
||||
['customers', 'table', 2, 'Customer table'],
|
||||
['orders', 'table', 2, null],
|
||||
['order_summary', 'view', null, null],
|
||||
]);
|
||||
expect(snapshot.tables.find((table) => table.name === 'customers')?.columns[0]).toMatchObject({
|
||||
name: 'id',
|
||||
nativeType: 'int',
|
||||
normalizedType: 'int',
|
||||
dimensionType: 'number',
|
||||
nullable: false,
|
||||
primaryKey: true,
|
||||
comment: 'PK',
|
||||
});
|
||||
expect(snapshot.tables.find((table) => table.name === 'orders')?.foreignKeys).toEqual([
|
||||
{
|
||||
fromColumn: 'customer_id',
|
||||
toCatalog: 'analytics',
|
||||
toDb: 'dbo',
|
||||
toTable: 'customers',
|
||||
toColumn: 'id',
|
||||
constraintName: 'orders_customer_id_fk',
|
||||
},
|
||||
]);
|
||||
});
|
||||
|
||||
it('runs samples, distinct values, read-only SQL, row count, schema list, and cleanup', async () => {
|
||||
const poolFactory = fakePoolFactory();
|
||||
const connector = new KtxSqlServerScanConnector({
|
||||
connectionId: 'warehouse',
|
||||
connection: {
|
||||
driver: 'sqlserver',
|
||||
host: 'db.example.test',
|
||||
database: 'analytics',
|
||||
username: 'reader',
|
||||
schema: 'dbo',
|
||||
},
|
||||
poolFactory,
|
||||
});
|
||||
|
||||
await expect(
|
||||
connector.sampleTable(
|
||||
{
|
||||
connectionId: 'warehouse',
|
||||
table: { catalog: 'analytics', db: 'dbo', name: 'orders' },
|
||||
columns: ['id', 'status'],
|
||||
limit: 1,
|
||||
},
|
||||
{ runId: 'scan-run-1' },
|
||||
),
|
||||
).resolves.toEqual({
|
||||
headers: ['id', 'status'],
|
||||
headerTypes: ['nvarchar', 'nvarchar'],
|
||||
rows: [[10, 'paid']],
|
||||
totalRows: 1,
|
||||
});
|
||||
|
||||
await expect(
|
||||
connector.sampleColumn(
|
||||
{ connectionId: 'warehouse', table: { catalog: 'analytics', db: 'dbo', name: 'orders' }, column: 'status', limit: 5 },
|
||||
{ runId: 'scan-run-1' },
|
||||
),
|
||||
).resolves.toMatchObject({ values: ['paid', 'open'], nullCount: null, distinctCount: null });
|
||||
|
||||
await expect(
|
||||
connector.getColumnDistinctValues(
|
||||
{ catalog: 'analytics', db: 'dbo', name: 'orders' },
|
||||
'status',
|
||||
{ maxCardinality: 5, limit: 10, sampleSize: 100 },
|
||||
),
|
||||
).resolves.toEqual({ values: ['open', 'paid'], cardinality: 2 });
|
||||
|
||||
await expect(
|
||||
connector.executeReadOnly(
|
||||
{ connectionId: 'warehouse', sql: 'select id, status from dbo.orders', maxRows: 1 },
|
||||
{ runId: 'scan-run-1' },
|
||||
),
|
||||
).resolves.toMatchObject({ headers: ['id', 'status'], rows: [[10, 'paid']], totalRows: 1, rowCount: 1 });
|
||||
|
||||
await expect(
|
||||
connector.executeReadOnly({ connectionId: 'warehouse', sql: 'delete from orders' }, { runId: 'scan-run-1' }),
|
||||
).rejects.toThrow('Only read-only SELECT/WITH queries can be executed locally');
|
||||
|
||||
await expect(connector.getTableRowCount('orders')).resolves.toBe(2);
|
||||
await expect(connector.listSchemas()).resolves.toEqual(['dbo', 'sales']);
|
||||
await expect(
|
||||
connector.columnStats(
|
||||
{ connectionId: 'warehouse', table: { catalog: 'analytics', db: 'dbo', name: 'orders' }, column: 'status' },
|
||||
{ runId: 'scan-run-1' },
|
||||
),
|
||||
).resolves.toBeNull();
|
||||
|
||||
await connector.cleanup();
|
||||
});
|
||||
|
||||
it('adapts native SQL Server snapshots to live-database introspection for local ingest', async () => {
|
||||
const introspection = createSqlServerLiveDatabaseIntrospection({
|
||||
connections: {
|
||||
warehouse: {
|
||||
driver: 'sqlserver',
|
||||
host: 'db.example.test',
|
||||
database: 'analytics',
|
||||
username: 'reader',
|
||||
schema: 'dbo',
|
||||
},
|
||||
},
|
||||
poolFactory: fakePoolFactory(),
|
||||
now: () => new Date('2026-04-29T16:00:00.000Z'),
|
||||
});
|
||||
|
||||
const snapshot = await introspection.extractSchema('warehouse');
|
||||
|
||||
expect(snapshot).toMatchObject({
|
||||
connectionId: 'warehouse',
|
||||
extractedAt: '2026-04-29T16:00:00.000Z',
|
||||
});
|
||||
expect(snapshot.tables.find((table) => table.name === 'customers')).toMatchObject({
|
||||
name: 'customers',
|
||||
catalog: 'analytics',
|
||||
db: 'dbo',
|
||||
columns: [
|
||||
{
|
||||
name: 'id',
|
||||
nativeType: 'int',
|
||||
normalizedType: 'int',
|
||||
dimensionType: 'number',
|
||||
nullable: false,
|
||||
primaryKey: true,
|
||||
comment: 'PK',
|
||||
},
|
||||
{
|
||||
name: 'name',
|
||||
nativeType: 'nvarchar',
|
||||
normalizedType: 'nvarchar',
|
||||
dimensionType: 'string',
|
||||
nullable: false,
|
||||
primaryKey: false,
|
||||
comment: null,
|
||||
},
|
||||
],
|
||||
foreignKeys: [],
|
||||
});
|
||||
});
|
||||
});
|
||||
727
packages/cli/src/connectors/sqlserver/connector.ts
Normal file
727
packages/cli/src/connectors/sqlserver/connector.ts
Normal file
|
|
@ -0,0 +1,727 @@
|
|||
import { assertReadOnlySql } from '../../context/connections/index.js';
|
||||
import {
|
||||
createKtxConnectorCapabilities,
|
||||
type KtxColumnSampleInput,
|
||||
type KtxColumnSampleResult,
|
||||
type KtxColumnStatsInput,
|
||||
type KtxColumnStatsResult,
|
||||
type KtxQueryResult,
|
||||
type KtxReadOnlyQueryInput,
|
||||
type KtxScanConnector,
|
||||
type KtxScanContext,
|
||||
type KtxScanInput,
|
||||
type KtxSchemaColumn,
|
||||
type KtxSchemaForeignKey,
|
||||
type KtxSchemaSnapshot,
|
||||
type KtxSchemaTable,
|
||||
type KtxTableListEntry,
|
||||
type KtxTableRef,
|
||||
type KtxTableSampleInput,
|
||||
type KtxTableSampleResult,
|
||||
} from '../../context/scan/index.js';
|
||||
import { readFileSync } from 'node:fs';
|
||||
import { homedir } from 'node:os';
|
||||
import { resolve } from 'node:path';
|
||||
import sql from 'mssql';
|
||||
import { KtxSqlServerDialect } from './dialect.js';
|
||||
|
||||
export interface KtxSqlServerConnectionConfig {
|
||||
driver?: string;
|
||||
host?: string;
|
||||
port?: number;
|
||||
database?: string;
|
||||
username?: string;
|
||||
user?: string;
|
||||
password?: string;
|
||||
url?: string;
|
||||
schema?: string;
|
||||
schemas?: string[];
|
||||
trustServerCertificate?: boolean;
|
||||
[key: string]: unknown;
|
||||
}
|
||||
|
||||
export interface KtxSqlServerPoolConfig {
|
||||
server: string;
|
||||
port: number;
|
||||
database: string;
|
||||
user: string;
|
||||
password?: string;
|
||||
options: { encrypt: true; trustServerCertificate: boolean };
|
||||
pool: { max: number; min: number; idleTimeoutMillis: number };
|
||||
}
|
||||
|
||||
export interface KtxSqlServerQueryResult {
|
||||
recordset?: Array<Record<string, unknown>> & { columns?: Record<string, { type?: { declaration?: string } }> };
|
||||
}
|
||||
|
||||
interface KtxSqlServerRequest {
|
||||
input(name: string, value: unknown): KtxSqlServerRequest;
|
||||
query(query: string): Promise<KtxSqlServerQueryResult>;
|
||||
}
|
||||
|
||||
export interface KtxSqlServerPool {
|
||||
request(): KtxSqlServerRequest;
|
||||
close(): Promise<void>;
|
||||
}
|
||||
|
||||
export interface KtxSqlServerPoolFactory {
|
||||
createPool(config: KtxSqlServerPoolConfig): Promise<KtxSqlServerPool>;
|
||||
}
|
||||
|
||||
interface KtxSqlServerResolvedEndpoint {
|
||||
host: string;
|
||||
port: number;
|
||||
close?: () => Promise<void>;
|
||||
}
|
||||
|
||||
export interface KtxSqlServerEndpointResolver {
|
||||
resolve(input: {
|
||||
host: string;
|
||||
port: number;
|
||||
connection: KtxSqlServerConnectionConfig;
|
||||
}): Promise<KtxSqlServerResolvedEndpoint>;
|
||||
}
|
||||
|
||||
export interface KtxSqlServerScanConnectorOptions {
|
||||
connectionId: string;
|
||||
connection: KtxSqlServerConnectionConfig | undefined;
|
||||
poolFactory?: KtxSqlServerPoolFactory;
|
||||
endpointResolver?: KtxSqlServerEndpointResolver;
|
||||
env?: NodeJS.ProcessEnv;
|
||||
now?: () => Date;
|
||||
}
|
||||
|
||||
export interface KtxSqlServerReadOnlyQueryInput extends KtxReadOnlyQueryInput {
|
||||
params?: Record<string, unknown>;
|
||||
}
|
||||
|
||||
export interface KtxSqlServerColumnDistinctValuesOptions {
|
||||
maxCardinality: number;
|
||||
limit: number;
|
||||
sampleSize?: number;
|
||||
}
|
||||
|
||||
export interface KtxSqlServerColumnDistinctValuesResult {
|
||||
values: string[] | null;
|
||||
cardinality: number;
|
||||
}
|
||||
|
||||
interface KtxSqlServerTableSampleResult extends KtxTableSampleResult {
|
||||
headerTypes?: string[];
|
||||
}
|
||||
|
||||
function sqlTypeDeclaration(type: unknown): string {
|
||||
if (typeof type === 'function') {
|
||||
try {
|
||||
return sqlTypeDeclaration(type());
|
||||
} catch {
|
||||
return 'unknown';
|
||||
}
|
||||
}
|
||||
if (typeof type === 'object' && type !== null && 'declaration' in type) {
|
||||
const declaration = (type as { declaration?: unknown }).declaration;
|
||||
return typeof declaration === 'string' ? declaration : 'unknown';
|
||||
}
|
||||
return 'unknown';
|
||||
}
|
||||
|
||||
function sqlRecordset(
|
||||
rows: Array<Record<string, unknown>> | undefined,
|
||||
columns: Record<string, { type?: unknown }> | undefined,
|
||||
): NonNullable<KtxSqlServerQueryResult['recordset']> {
|
||||
const recordset = [...(rows ?? [])] as NonNullable<KtxSqlServerQueryResult['recordset']>;
|
||||
recordset.columns = Object.fromEntries(
|
||||
Object.entries(columns ?? {}).map(([name, metadata]) => [
|
||||
name,
|
||||
{ type: { declaration: sqlTypeDeclaration(metadata.type) } },
|
||||
]),
|
||||
);
|
||||
return recordset;
|
||||
}
|
||||
|
||||
class DefaultSqlServerPoolFactory implements KtxSqlServerPoolFactory {
|
||||
async createPool(config: KtxSqlServerPoolConfig): Promise<KtxSqlServerPool> {
|
||||
const pool = await new sql.ConnectionPool(config as sql.config).connect();
|
||||
return {
|
||||
request() {
|
||||
const request = pool.request();
|
||||
return {
|
||||
input(name: string, value: unknown) {
|
||||
request.input(name, value);
|
||||
return this;
|
||||
},
|
||||
async query(query: string) {
|
||||
const result = await request.query(query);
|
||||
return {
|
||||
recordset: sqlRecordset(result.recordset as Array<Record<string, unknown>> | undefined, result.recordset?.columns),
|
||||
};
|
||||
},
|
||||
};
|
||||
},
|
||||
close: () => pool.close(),
|
||||
};
|
||||
}
|
||||
}
|
||||
|
||||
function stringConfigValue(
|
||||
connection: KtxSqlServerConnectionConfig | undefined,
|
||||
key: keyof KtxSqlServerConnectionConfig,
|
||||
env: NodeJS.ProcessEnv,
|
||||
): string | undefined {
|
||||
const value = connection?.[key];
|
||||
return typeof value === 'string' && value.trim().length > 0 ? resolveStringReference(value.trim(), env) : undefined;
|
||||
}
|
||||
|
||||
function resolveStringReference(value: string, env: NodeJS.ProcessEnv): string {
|
||||
if (value.startsWith('env:')) {
|
||||
return env[value.slice('env:'.length)] ?? '';
|
||||
}
|
||||
if (value.startsWith('file:')) {
|
||||
const rawPath = value.slice('file:'.length);
|
||||
const path = rawPath.startsWith('~') ? resolve(homedir(), rawPath.slice(1)) : rawPath;
|
||||
return readFileSync(path, 'utf-8').trim();
|
||||
}
|
||||
return value;
|
||||
}
|
||||
|
||||
function parseSqlServerUrl(url: string): Partial<KtxSqlServerConnectionConfig> {
|
||||
const parsed = new URL(url);
|
||||
return {
|
||||
host: parsed.hostname,
|
||||
port: parsed.port ? Number(parsed.port) : undefined,
|
||||
database: parsed.pathname.replace(/^\/+/, '') || undefined,
|
||||
username: parsed.username ? decodeURIComponent(parsed.username) : undefined,
|
||||
password: parsed.password ? decodeURIComponent(parsed.password) : undefined,
|
||||
trustServerCertificate: parsed.searchParams.get('trustServerCertificate') === 'true',
|
||||
};
|
||||
}
|
||||
|
||||
function maybeNumber(value: unknown): number | undefined {
|
||||
return typeof value === 'number' && Number.isFinite(value) ? value : undefined;
|
||||
}
|
||||
|
||||
function schemaNames(connection: KtxSqlServerConnectionConfig, env: NodeJS.ProcessEnv): string[] {
|
||||
if (Array.isArray(connection.schemas) && connection.schemas.length > 0) {
|
||||
return connection.schemas.filter((schema) => schema.trim().length > 0).map((schema) => resolveStringReference(schema, env));
|
||||
}
|
||||
return [stringConfigValue(connection, 'schema', env) ?? 'dbo'];
|
||||
}
|
||||
|
||||
function groupByTable<T extends { table_name: string }>(rows: T[]): Map<string, T[]> {
|
||||
const grouped = new Map<string, T[]>();
|
||||
for (const row of rows) {
|
||||
const values = grouped.get(row.table_name) ?? [];
|
||||
values.push(row);
|
||||
grouped.set(row.table_name, values);
|
||||
}
|
||||
return grouped;
|
||||
}
|
||||
|
||||
function firstNumber(value: unknown): number | null {
|
||||
const numberValue = Number(value);
|
||||
return Number.isFinite(numberValue) ? numberValue : null;
|
||||
}
|
||||
|
||||
function limitSqlForSqlServerExecution(sqlText: string, maxRows: number | undefined): string {
|
||||
const trimmed = assertReadOnlySql(sqlText).replace(/;+\s*$/, '');
|
||||
if (!maxRows) {
|
||||
return trimmed;
|
||||
}
|
||||
if (!Number.isInteger(maxRows) || maxRows <= 0) {
|
||||
throw new Error('maxRows must be a positive integer.');
|
||||
}
|
||||
return `SELECT TOP ${maxRows} * FROM (${trimmed}) AS ktx_query_result`;
|
||||
}
|
||||
|
||||
export function isKtxSqlServerConnectionConfig(
|
||||
connection: KtxSqlServerConnectionConfig | undefined,
|
||||
): connection is KtxSqlServerConnectionConfig {
|
||||
return String(connection?.driver ?? '').toLowerCase() === 'sqlserver';
|
||||
}
|
||||
|
||||
export function sqlServerConnectionPoolConfigFromConfig(input: {
|
||||
connectionId: string;
|
||||
connection: KtxSqlServerConnectionConfig | undefined;
|
||||
env?: NodeJS.ProcessEnv;
|
||||
}): KtxSqlServerPoolConfig {
|
||||
const inputDriver = input.connection?.driver ?? 'unknown';
|
||||
if (!isKtxSqlServerConnectionConfig(input.connection)) {
|
||||
throw new Error(`Native SQL Server connector cannot run driver "${inputDriver}"`);
|
||||
}
|
||||
|
||||
const env = input.env ?? process.env;
|
||||
const referencedUrl = stringConfigValue(input.connection, 'url', env);
|
||||
const urlConfig = referencedUrl ? parseSqlServerUrl(referencedUrl) : {};
|
||||
const merged: KtxSqlServerConnectionConfig = { ...urlConfig, ...input.connection };
|
||||
const server = stringConfigValue(merged, 'host', env);
|
||||
const database = stringConfigValue(merged, 'database', env);
|
||||
const user = stringConfigValue(merged, 'username', env) ?? stringConfigValue(merged, 'user', env);
|
||||
|
||||
if (!server) {
|
||||
throw new Error(`Native SQL Server connector requires connections.${input.connectionId}.host or url`);
|
||||
}
|
||||
if (!database) {
|
||||
throw new Error(`Native SQL Server connector requires connections.${input.connectionId}.database or url`);
|
||||
}
|
||||
if (!user) {
|
||||
throw new Error(`Native SQL Server connector requires connections.${input.connectionId}.username, user, or url`);
|
||||
}
|
||||
|
||||
return {
|
||||
server,
|
||||
port: maybeNumber(merged.port) ?? 1433,
|
||||
database,
|
||||
user,
|
||||
password: stringConfigValue(merged, 'password', env),
|
||||
options: { encrypt: true, trustServerCertificate: merged.trustServerCertificate ?? true },
|
||||
pool: { max: 10, min: 0, idleTimeoutMillis: 30000 },
|
||||
};
|
||||
}
|
||||
|
||||
export class KtxSqlServerScanConnector implements KtxScanConnector {
|
||||
readonly id: string;
|
||||
readonly driver = 'sqlserver' as const;
|
||||
readonly capabilities = createKtxConnectorCapabilities({
|
||||
tableSampling: true,
|
||||
columnSampling: true,
|
||||
columnStats: false,
|
||||
readOnlySql: true,
|
||||
nestedAnalysis: false,
|
||||
formalForeignKeys: true,
|
||||
estimatedRowCounts: true,
|
||||
});
|
||||
|
||||
private readonly connectionId: string;
|
||||
private readonly connection: KtxSqlServerConnectionConfig;
|
||||
private readonly poolConfig: KtxSqlServerPoolConfig;
|
||||
private readonly schemas: string[];
|
||||
private readonly poolFactory: KtxSqlServerPoolFactory;
|
||||
private readonly endpointResolver?: KtxSqlServerEndpointResolver;
|
||||
private readonly now: () => Date;
|
||||
private readonly dialect = new KtxSqlServerDialect();
|
||||
private pool: KtxSqlServerPool | null = null;
|
||||
private resolvedEndpoint: KtxSqlServerResolvedEndpoint | null = null;
|
||||
|
||||
constructor(options: KtxSqlServerScanConnectorOptions) {
|
||||
this.connectionId = options.connectionId;
|
||||
this.connection = options.connection ?? {};
|
||||
const env = options.env ?? process.env;
|
||||
this.poolConfig = sqlServerConnectionPoolConfigFromConfig({
|
||||
connectionId: options.connectionId,
|
||||
connection: options.connection,
|
||||
env,
|
||||
});
|
||||
this.schemas = schemaNames(this.connection, env);
|
||||
this.poolFactory = options.poolFactory ?? new DefaultSqlServerPoolFactory();
|
||||
this.endpointResolver = options.endpointResolver;
|
||||
this.now = options.now ?? (() => new Date());
|
||||
this.id = `sqlserver:${options.connectionId}`;
|
||||
}
|
||||
|
||||
async testConnection(): Promise<{ success: boolean; error?: string }> {
|
||||
try {
|
||||
await this.query('SELECT 1');
|
||||
return { success: true };
|
||||
} catch (error) {
|
||||
return { success: false, error: error instanceof Error ? error.message : String(error) };
|
||||
}
|
||||
}
|
||||
|
||||
async introspect(input: KtxScanInput, _ctx: KtxScanContext): Promise<KtxSchemaSnapshot> {
|
||||
this.assertConnection(input.connectionId);
|
||||
const tables: KtxSchemaTable[] = [];
|
||||
for (const schemaName of this.schemas) {
|
||||
tables.push(...(await this.introspectSchema(schemaName)));
|
||||
}
|
||||
return {
|
||||
connectionId: this.connectionId,
|
||||
driver: 'sqlserver',
|
||||
extractedAt: this.now().toISOString(),
|
||||
scope: { catalogs: [this.poolConfig.database], schemas: this.schemas },
|
||||
metadata: {
|
||||
database: this.poolConfig.database,
|
||||
schemas: this.schemas,
|
||||
host: this.poolConfig.server,
|
||||
table_count: tables.length,
|
||||
total_columns: tables.reduce((sum, table) => sum + table.columns.length, 0),
|
||||
},
|
||||
tables,
|
||||
};
|
||||
}
|
||||
|
||||
async sampleTable(input: KtxTableSampleInput, _ctx: KtxScanContext): Promise<KtxSqlServerTableSampleResult> {
|
||||
this.assertConnection(input.connectionId);
|
||||
const result = await this.query(this.dialect.generateSampleQuery(this.qTableName(input.table), input.limit, input.columns));
|
||||
return { headers: result.headers, headerTypes: result.headerTypes, rows: result.rows, totalRows: result.totalRows };
|
||||
}
|
||||
|
||||
async sampleColumn(input: KtxColumnSampleInput, _ctx: KtxScanContext): Promise<KtxColumnSampleResult> {
|
||||
this.assertConnection(input.connectionId);
|
||||
const result = await this.query(
|
||||
this.dialect.generateColumnSampleQuery(this.qTableName(input.table), input.column, input.limit),
|
||||
);
|
||||
const values = result.rows.filter((row) => row.length > 0 && row[0] !== null).map((row) => row[0]);
|
||||
return { values, nullCount: null, distinctCount: null };
|
||||
}
|
||||
|
||||
async columnStats(_input: KtxColumnStatsInput, _ctx: KtxScanContext): Promise<KtxColumnStatsResult | null> {
|
||||
return null;
|
||||
}
|
||||
|
||||
async executeReadOnly(input: KtxSqlServerReadOnlyQueryInput, _ctx: KtxScanContext): Promise<KtxQueryResult> {
|
||||
this.assertConnection(input.connectionId);
|
||||
const limitedSql = limitSqlForSqlServerExecution(input.sql, input.maxRows);
|
||||
const prepared = this.dialect.prepareQuery(limitedSql, input.params);
|
||||
const result = await this.query(prepared.sql, prepared.params);
|
||||
return { ...result, rowCount: result.rows.length };
|
||||
}
|
||||
|
||||
async getColumnDistinctValues(
|
||||
table: KtxTableRef,
|
||||
columnName: string,
|
||||
options: KtxSqlServerColumnDistinctValuesOptions,
|
||||
): Promise<KtxSqlServerColumnDistinctValuesResult | null> {
|
||||
const tableName = this.qTableName(table);
|
||||
const quotedColumn = this.dialect.quoteIdentifier(columnName);
|
||||
const cardinalityRows = await this.queryRaw<{ cardinality: unknown }>(
|
||||
this.dialect.generateCardinalitySampleQuery(tableName, quotedColumn, options.sampleSize ?? 10000),
|
||||
);
|
||||
const cardinality = Number(cardinalityRows[0]?.cardinality);
|
||||
if (Number.isNaN(cardinality)) {
|
||||
return null;
|
||||
}
|
||||
if (cardinality === 0) {
|
||||
return { values: [], cardinality: 0 };
|
||||
}
|
||||
if (cardinality > options.maxCardinality) {
|
||||
return { values: null, cardinality };
|
||||
}
|
||||
const valuesRows = await this.queryRaw<{ val: unknown }>(
|
||||
this.dialect.generateDistinctValuesQuery(tableName, quotedColumn, options.limit),
|
||||
);
|
||||
return { values: valuesRows.filter((row) => row.val !== null).map((row) => String(row.val)), cardinality };
|
||||
}
|
||||
|
||||
async getTableRowCount(tableName: string, schemaName = this.schemas[0] ?? 'dbo'): Promise<number> {
|
||||
const rows = await this.queryRaw<{ row_count: unknown }>(
|
||||
`
|
||||
SELECT SUM(p.rows) AS row_count
|
||||
FROM sys.tables t
|
||||
INNER JOIN sys.partitions p ON t.object_id = p.object_id
|
||||
INNER JOIN sys.schemas s ON t.schema_id = s.schema_id
|
||||
WHERE s.name = @schemaName
|
||||
AND t.name = @tableName
|
||||
AND p.index_id IN (0, 1)
|
||||
`,
|
||||
{ schemaName, tableName },
|
||||
);
|
||||
return firstNumber(rows[0]?.row_count) ?? 0;
|
||||
}
|
||||
|
||||
qTableName(table: Pick<KtxTableRef, 'name'> & Partial<Pick<KtxTableRef, 'catalog' | 'db'>>): string {
|
||||
return this.dialect.formatTableName(table);
|
||||
}
|
||||
|
||||
quoteIdentifier(identifier: string): string {
|
||||
return this.dialect.quoteIdentifier(identifier);
|
||||
}
|
||||
|
||||
async listSchemas(): Promise<string[]> {
|
||||
const rows = await this.queryRaw<{ schema_name: string }>(`
|
||||
SELECT s.name AS schema_name
|
||||
FROM sys.schemas s
|
||||
WHERE s.name NOT IN (
|
||||
'INFORMATION_SCHEMA', 'sys', 'guest',
|
||||
'db_owner', 'db_accessadmin', 'db_securityadmin', 'db_ddladmin',
|
||||
'db_backupoperator', 'db_datareader', 'db_datawriter',
|
||||
'db_denydatareader', 'db_denydatawriter'
|
||||
)
|
||||
ORDER BY s.name
|
||||
`);
|
||||
return rows.map((row) => row.schema_name);
|
||||
}
|
||||
|
||||
async listTables(schemas?: string[]): Promise<KtxTableListEntry[]> {
|
||||
const filterSchemas = schemas ?? (await this.listSchemas());
|
||||
if (filterSchemas.length === 0) return [];
|
||||
const params: Record<string, unknown> = {};
|
||||
const placeholders = filterSchemas.map((s, i) => {
|
||||
params[`schema${i}`] = s;
|
||||
return `@schema${i}`;
|
||||
});
|
||||
const rows = await this.queryRaw<{ schema_name: string; table_name: string; table_type: string }>(
|
||||
`
|
||||
SELECT s.name AS schema_name, o.name AS table_name, o.type_desc AS table_type
|
||||
FROM sys.objects o
|
||||
JOIN sys.schemas s ON o.schema_id = s.schema_id
|
||||
WHERE o.type IN ('U', 'V')
|
||||
AND s.name IN (${placeholders.join(', ')})
|
||||
ORDER BY s.name, o.name
|
||||
`,
|
||||
params,
|
||||
);
|
||||
return rows.map((row) => ({
|
||||
schema: row.schema_name,
|
||||
name: row.table_name,
|
||||
kind: row.table_type === 'VIEW' ? ('view' as const) : ('table' as const),
|
||||
}));
|
||||
}
|
||||
|
||||
async cleanup(): Promise<void> {
|
||||
if (this.pool) {
|
||||
await this.pool.close();
|
||||
this.pool = null;
|
||||
}
|
||||
if (this.resolvedEndpoint?.close) {
|
||||
await this.resolvedEndpoint.close();
|
||||
this.resolvedEndpoint = null;
|
||||
}
|
||||
}
|
||||
|
||||
private async introspectSchema(schemaName: string): Promise<KtxSchemaTable[]> {
|
||||
const tables = await this.queryRaw<{ table_name: string; table_type: string }>(
|
||||
`
|
||||
SELECT TABLE_NAME AS table_name, TABLE_TYPE AS table_type
|
||||
FROM INFORMATION_SCHEMA.TABLES
|
||||
WHERE TABLE_SCHEMA = @schemaName
|
||||
AND TABLE_TYPE IN ('BASE TABLE', 'VIEW')
|
||||
ORDER BY TABLE_NAME
|
||||
`,
|
||||
{ schemaName },
|
||||
);
|
||||
const columns = await this.queryRaw<{
|
||||
table_name: string;
|
||||
column_name: string;
|
||||
data_type: string;
|
||||
is_nullable: string;
|
||||
}>(
|
||||
`
|
||||
SELECT TABLE_NAME AS table_name, COLUMN_NAME AS column_name, DATA_TYPE AS data_type, IS_NULLABLE AS is_nullable
|
||||
FROM INFORMATION_SCHEMA.COLUMNS
|
||||
WHERE TABLE_SCHEMA = @schemaName
|
||||
ORDER BY TABLE_NAME, ORDINAL_POSITION
|
||||
`,
|
||||
{ schemaName },
|
||||
);
|
||||
const tableComments = await this.tableComments(schemaName);
|
||||
const columnComments = await this.columnComments(schemaName);
|
||||
const primaryKeys = await this.primaryKeys(schemaName);
|
||||
const foreignKeys = await this.foreignKeys(schemaName);
|
||||
const rowCounts = await this.rowCounts(schemaName);
|
||||
const columnsByTable = groupByTable(columns);
|
||||
const foreignKeysByTable = groupByTable(foreignKeys);
|
||||
|
||||
return tables.map((table) => ({
|
||||
catalog: this.poolConfig.database,
|
||||
db: schemaName,
|
||||
name: table.table_name,
|
||||
kind: table.table_type === 'VIEW' ? 'view' : 'table',
|
||||
comment: tableComments.get(table.table_name) ?? null,
|
||||
estimatedRows: table.table_type === 'VIEW' ? null : rowCounts.get(table.table_name) ?? 0,
|
||||
columns: (columnsByTable.get(table.table_name) ?? []).map((column) =>
|
||||
this.toSchemaColumn(column, primaryKeys.get(table.table_name) ?? new Set(), columnComments),
|
||||
),
|
||||
foreignKeys: (foreignKeysByTable.get(table.table_name) ?? []).map((row) => this.toSchemaForeignKey(row)),
|
||||
}));
|
||||
}
|
||||
|
||||
private async tableComments(schemaName: string): Promise<Map<string, string>> {
|
||||
const rows = await this.queryRaw<{ table_name: string; table_comment: string }>(
|
||||
`
|
||||
SELECT o.name AS table_name, CAST(ep.value AS NVARCHAR(MAX)) AS table_comment
|
||||
FROM sys.objects o
|
||||
INNER JOIN sys.schemas s ON o.schema_id = s.schema_id
|
||||
INNER JOIN sys.extended_properties ep ON ep.major_id = o.object_id
|
||||
AND ep.minor_id = 0
|
||||
AND ep.name = 'MS_Description'
|
||||
WHERE s.name = @schemaName
|
||||
AND o.type IN ('U', 'V')
|
||||
`,
|
||||
{ schemaName },
|
||||
);
|
||||
return new Map(rows.map((row) => [row.table_name, row.table_comment]));
|
||||
}
|
||||
|
||||
private async columnComments(schemaName: string): Promise<Map<string, string>> {
|
||||
const rows = await this.queryRaw<{ table_name: string; column_name: string; column_comment: string }>(
|
||||
`
|
||||
SELECT o.name AS table_name, c.name AS column_name, CAST(ep.value AS NVARCHAR(MAX)) AS column_comment
|
||||
FROM sys.columns c
|
||||
INNER JOIN sys.objects o ON c.object_id = o.object_id
|
||||
INNER JOIN sys.schemas s ON o.schema_id = s.schema_id
|
||||
INNER JOIN sys.extended_properties ep ON ep.major_id = c.object_id
|
||||
AND ep.minor_id = c.column_id
|
||||
AND ep.name = 'MS_Description'
|
||||
WHERE s.name = @schemaName
|
||||
AND o.type IN ('U', 'V')
|
||||
`,
|
||||
{ schemaName },
|
||||
);
|
||||
return new Map(rows.map((row) => [`${row.table_name}.${row.column_name}`, row.column_comment]));
|
||||
}
|
||||
|
||||
private async primaryKeys(schemaName: string): Promise<Map<string, Set<string>>> {
|
||||
const rows = await this.queryRaw<{ table_name: string; column_name: string }>(
|
||||
`
|
||||
SELECT tc.TABLE_NAME AS table_name, kcu.COLUMN_NAME AS column_name
|
||||
FROM INFORMATION_SCHEMA.TABLE_CONSTRAINTS tc
|
||||
JOIN INFORMATION_SCHEMA.KEY_COLUMN_USAGE kcu
|
||||
ON tc.CONSTRAINT_NAME = kcu.CONSTRAINT_NAME
|
||||
AND tc.TABLE_SCHEMA = kcu.TABLE_SCHEMA
|
||||
WHERE tc.CONSTRAINT_TYPE = 'PRIMARY KEY'
|
||||
AND tc.TABLE_SCHEMA = @schemaName
|
||||
ORDER BY tc.TABLE_NAME, kcu.ORDINAL_POSITION
|
||||
`,
|
||||
{ schemaName },
|
||||
);
|
||||
const grouped = new Map<string, Set<string>>();
|
||||
for (const row of rows) {
|
||||
const columns = grouped.get(row.table_name) ?? new Set<string>();
|
||||
columns.add(row.column_name);
|
||||
grouped.set(row.table_name, columns);
|
||||
}
|
||||
return grouped;
|
||||
}
|
||||
|
||||
private async foreignKeys(schemaName: string): Promise<
|
||||
Array<{
|
||||
table_name: string;
|
||||
column_name: string;
|
||||
referenced_table_schema: string;
|
||||
referenced_table_name: string;
|
||||
referenced_column_name: string;
|
||||
constraint_name: string;
|
||||
}>
|
||||
> {
|
||||
return this.queryRaw(
|
||||
`
|
||||
SELECT
|
||||
fk.TABLE_NAME AS table_name,
|
||||
fk.COLUMN_NAME AS column_name,
|
||||
pk.TABLE_SCHEMA AS referenced_table_schema,
|
||||
pk.TABLE_NAME AS referenced_table_name,
|
||||
pk.COLUMN_NAME AS referenced_column_name,
|
||||
fk.CONSTRAINT_NAME AS constraint_name
|
||||
FROM INFORMATION_SCHEMA.REFERENTIAL_CONSTRAINTS rc
|
||||
JOIN INFORMATION_SCHEMA.KEY_COLUMN_USAGE fk
|
||||
ON fk.CONSTRAINT_CATALOG = rc.CONSTRAINT_CATALOG
|
||||
AND fk.CONSTRAINT_SCHEMA = rc.CONSTRAINT_SCHEMA
|
||||
AND fk.CONSTRAINT_NAME = rc.CONSTRAINT_NAME
|
||||
JOIN INFORMATION_SCHEMA.KEY_COLUMN_USAGE pk
|
||||
ON pk.CONSTRAINT_CATALOG = rc.UNIQUE_CONSTRAINT_CATALOG
|
||||
AND pk.CONSTRAINT_SCHEMA = rc.UNIQUE_CONSTRAINT_SCHEMA
|
||||
AND pk.CONSTRAINT_NAME = rc.UNIQUE_CONSTRAINT_NAME
|
||||
AND pk.ORDINAL_POSITION = fk.ORDINAL_POSITION
|
||||
WHERE fk.TABLE_SCHEMA = @schemaName
|
||||
ORDER BY fk.TABLE_NAME, fk.COLUMN_NAME
|
||||
`,
|
||||
{ schemaName },
|
||||
);
|
||||
}
|
||||
|
||||
private async rowCounts(schemaName: string): Promise<Map<string, number>> {
|
||||
const rows = await this.queryRaw<{ table_name: string; row_count: unknown }>(
|
||||
`
|
||||
SELECT t.name AS table_name, SUM(p.rows) AS row_count
|
||||
FROM sys.tables t
|
||||
INNER JOIN sys.partitions p ON t.object_id = p.object_id
|
||||
INNER JOIN sys.schemas s ON t.schema_id = s.schema_id
|
||||
WHERE s.name = @schemaName
|
||||
AND p.index_id IN (0, 1)
|
||||
GROUP BY t.name
|
||||
`,
|
||||
{ schemaName },
|
||||
);
|
||||
return new Map(rows.map((row) => [row.table_name, firstNumber(row.row_count) ?? 0]));
|
||||
}
|
||||
|
||||
private toSchemaColumn(
|
||||
column: { table_name: string; column_name: string; data_type: string; is_nullable: string },
|
||||
primaryKeys: Set<string>,
|
||||
comments: Map<string, string>,
|
||||
): KtxSchemaColumn {
|
||||
return {
|
||||
name: column.column_name,
|
||||
nativeType: column.data_type,
|
||||
normalizedType: this.dialect.mapDataType(column.data_type),
|
||||
dimensionType: this.dialect.mapToDimensionType(column.data_type),
|
||||
nullable: column.is_nullable === 'YES',
|
||||
primaryKey: primaryKeys.has(column.column_name),
|
||||
comment: comments.get(`${column.table_name}.${column.column_name}`) ?? null,
|
||||
};
|
||||
}
|
||||
|
||||
private toSchemaForeignKey(row: {
|
||||
column_name: string;
|
||||
referenced_table_schema: string;
|
||||
referenced_table_name: string;
|
||||
referenced_column_name: string;
|
||||
constraint_name: string;
|
||||
}): KtxSchemaForeignKey {
|
||||
return {
|
||||
fromColumn: row.column_name,
|
||||
toCatalog: this.poolConfig.database,
|
||||
toDb: row.referenced_table_schema,
|
||||
toTable: row.referenced_table_name,
|
||||
toColumn: row.referenced_column_name,
|
||||
constraintName: row.constraint_name || null,
|
||||
};
|
||||
}
|
||||
|
||||
private async poolForQuery(): Promise<KtxSqlServerPool> {
|
||||
if (!this.pool) {
|
||||
const config = { ...this.poolConfig };
|
||||
if (this.endpointResolver) {
|
||||
this.resolvedEndpoint = await this.endpointResolver.resolve({
|
||||
host: config.server,
|
||||
port: config.port,
|
||||
connection: this.connection,
|
||||
});
|
||||
config.server = this.resolvedEndpoint.host;
|
||||
config.port = this.resolvedEndpoint.port;
|
||||
}
|
||||
this.pool = await this.poolFactory.createPool(config);
|
||||
}
|
||||
return this.pool;
|
||||
}
|
||||
|
||||
private async queryRaw<T extends Record<string, unknown>>(query: string, params?: Record<string, unknown>): Promise<T[]> {
|
||||
const pool = await this.poolForQuery();
|
||||
const request = pool.request();
|
||||
if (params) {
|
||||
for (const [key, value] of Object.entries(params)) {
|
||||
request.input(key, value);
|
||||
}
|
||||
}
|
||||
const result = await request.query(query);
|
||||
return (result.recordset ?? []) as T[];
|
||||
}
|
||||
|
||||
private async query(query: string, params?: Record<string, unknown>): Promise<Omit<KtxQueryResult, 'rowCount'>> {
|
||||
const pool = await this.poolForQuery();
|
||||
const request = pool.request();
|
||||
if (params) {
|
||||
for (const [key, value] of Object.entries(params)) {
|
||||
request.input(key, value);
|
||||
}
|
||||
}
|
||||
const result = await request.query(assertReadOnlySql(query));
|
||||
const recordset = result.recordset ?? [];
|
||||
const columnMetadata = recordset.columns ?? {};
|
||||
const metadataHeaders = Object.keys(columnMetadata);
|
||||
const headers = metadataHeaders.length > 0 ? metadataHeaders : Object.keys(recordset[0] ?? {});
|
||||
const headerTypes = headers.map((header) => columnMetadata[header]?.type?.declaration ?? 'unknown');
|
||||
return {
|
||||
headers,
|
||||
headerTypes,
|
||||
rows: recordset.map((row) => headers.map((header) => row[header])),
|
||||
totalRows: recordset.length,
|
||||
};
|
||||
}
|
||||
|
||||
private assertConnection(connectionId: string): void {
|
||||
if (connectionId !== this.connectionId) {
|
||||
throw new Error(`KTX SQL Server connector ${this.id} cannot serve connection ${connectionId}`);
|
||||
}
|
||||
}
|
||||
}
|
||||
49
packages/cli/src/connectors/sqlserver/dialect.test.ts
Normal file
49
packages/cli/src/connectors/sqlserver/dialect.test.ts
Normal file
|
|
@ -0,0 +1,49 @@
|
|||
import { describe, expect, it } from 'vitest';
|
||||
import { KtxSqlServerDialect } from './dialect.js';
|
||||
|
||||
describe('KtxSqlServerDialect', () => {
|
||||
const dialect = new KtxSqlServerDialect();
|
||||
|
||||
it('quotes identifiers and formats schema-qualified table names', () => {
|
||||
expect(dialect.quoteIdentifier('events')).toBe('[events]');
|
||||
expect(dialect.quoteIdentifier('odd]name')).toBe('[odd]]name]');
|
||||
expect(dialect.formatTableName({ catalog: 'warehouse', db: 'dbo', name: 'events' })).toBe('[dbo].[events]');
|
||||
expect(dialect.formatTableName({ catalog: null, db: null, name: 'events' })).toBe('[events]');
|
||||
});
|
||||
|
||||
it('maps SQL Server types to KTX dimension types', () => {
|
||||
expect(dialect.mapToDimensionType('datetime2')).toBe('time');
|
||||
expect(dialect.mapToDimensionType('decimal(18, 2)')).toBe('number');
|
||||
expect(dialect.mapToDimensionType('bigint')).toBe('number');
|
||||
expect(dialect.mapToDimensionType('bit')).toBe('boolean');
|
||||
expect(dialect.mapToDimensionType('uniqueidentifier')).toBe('string');
|
||||
expect(dialect.mapToDimensionType('')).toBe('string');
|
||||
});
|
||||
|
||||
it('builds sampling, distinct-value, pagination, and time SQL', () => {
|
||||
expect(dialect.generateSampleQuery('[dbo].[events]', 25, ['id', 'event_name'])).toBe(
|
||||
'SELECT TOP 25 [id], [event_name] FROM [dbo].[events]',
|
||||
);
|
||||
expect(dialect.generateColumnSampleQuery('[dbo].[events]', 'event_name', 10)).toBe(
|
||||
"SELECT TOP 10 [event_name] FROM [dbo].[events] WHERE [event_name] IS NOT NULL AND LTRIM(RTRIM(CAST([event_name] AS NVARCHAR(MAX)))) != ''",
|
||||
);
|
||||
expect(dialect.generateDistinctValuesQuery('[dbo].[events]', '[event_name]', 5)).toContain('SELECT TOP 5 val');
|
||||
expect(dialect.getTopClause(10)).toBe('TOP 10');
|
||||
expect(dialect.getLimitOffsetClause(10, 20)).toBe('OFFSET 20 ROWS FETCH NEXT 10 ROWS ONLY');
|
||||
expect(dialect.getTimeTruncExpression('created_at', 'month')).toBe(
|
||||
'DATEFROMPARTS(YEAR(created_at), MONTH(created_at), 1)',
|
||||
);
|
||||
});
|
||||
|
||||
it('prepares named parameters using SQL Server @ parameters', () => {
|
||||
expect(
|
||||
dialect.prepareQuery('select * from events where id = :id and name = :name', {
|
||||
id: 10,
|
||||
name: 'signup',
|
||||
}),
|
||||
).toEqual({
|
||||
sql: 'select * from events where id = @id and name = @name',
|
||||
params: { id: 10, name: 'signup' },
|
||||
});
|
||||
});
|
||||
});
|
||||
201
packages/cli/src/connectors/sqlserver/dialect.ts
Normal file
201
packages/cli/src/connectors/sqlserver/dialect.ts
Normal file
|
|
@ -0,0 +1,201 @@
|
|||
import type { KtxSchemaDimensionType, KtxTableRef } from '../../context/scan/index.js';
|
||||
|
||||
type SqlServerTableNameRef = Pick<KtxTableRef, 'name'> & Partial<Pick<KtxTableRef, 'catalog' | 'db'>>;
|
||||
|
||||
export class KtxSqlServerDialect {
|
||||
readonly type = 'sqlserver';
|
||||
|
||||
private readonly typeMappings: Record<string, KtxSchemaDimensionType> = {
|
||||
datetime: 'time',
|
||||
datetime2: 'time',
|
||||
date: 'time',
|
||||
time: 'time',
|
||||
datetimeoffset: 'time',
|
||||
smalldatetime: 'time',
|
||||
timestamp: 'time',
|
||||
int: 'number',
|
||||
bigint: 'number',
|
||||
smallint: 'number',
|
||||
tinyint: 'number',
|
||||
decimal: 'number',
|
||||
numeric: 'number',
|
||||
float: 'number',
|
||||
real: 'number',
|
||||
money: 'number',
|
||||
smallmoney: 'number',
|
||||
varchar: 'string',
|
||||
nvarchar: 'string',
|
||||
char: 'string',
|
||||
nchar: 'string',
|
||||
text: 'string',
|
||||
ntext: 'string',
|
||||
uniqueidentifier: 'string',
|
||||
xml: 'string',
|
||||
bit: 'boolean',
|
||||
};
|
||||
|
||||
quoteIdentifier(identifier: string): string {
|
||||
return `[${identifier.replace(/\]/g, ']]')}]`;
|
||||
}
|
||||
|
||||
formatTableName(table: SqlServerTableNameRef): string {
|
||||
return table.db
|
||||
? `${this.quoteIdentifier(table.db)}.${this.quoteIdentifier(table.name)}`
|
||||
: this.quoteIdentifier(table.name);
|
||||
}
|
||||
|
||||
mapDataType(nativeType: string): string {
|
||||
return nativeType;
|
||||
}
|
||||
|
||||
mapToDimensionType(nativeType: string): KtxSchemaDimensionType {
|
||||
if (!nativeType) {
|
||||
return 'string';
|
||||
}
|
||||
const lower = nativeType.toLowerCase().trim();
|
||||
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('money')
|
||||
) {
|
||||
return 'number';
|
||||
}
|
||||
if (normalized.includes('bit')) {
|
||||
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 TOP ${limit} ${columnList} FROM ${tableName}`;
|
||||
}
|
||||
|
||||
generateColumnSampleQuery(tableName: string, columnName: string, limit: number): string {
|
||||
const quotedColumn = this.quoteIdentifier(columnName);
|
||||
return `SELECT TOP ${limit} ${quotedColumn} FROM ${tableName} WHERE ${quotedColumn} IS NOT NULL AND LTRIM(RTRIM(CAST(${quotedColumn} AS NVARCHAR(MAX)))) != ''`;
|
||||
}
|
||||
|
||||
prepareQuery(sql: string, params?: Record<string, unknown>): { sql: string; params?: Record<string, unknown> } {
|
||||
if (!params) {
|
||||
return { sql, params: undefined };
|
||||
}
|
||||
let parameterizedQuery = sql;
|
||||
for (const key of Object.keys(params)) {
|
||||
parameterizedQuery = parameterizedQuery.replace(new RegExp(`:${key}\\b`, 'g'), `@${key}`);
|
||||
}
|
||||
return { sql: parameterizedQuery, params };
|
||||
}
|
||||
|
||||
getRandomSampleFilter(samplePct: number): string {
|
||||
if (samplePct <= 0 || samplePct >= 1) {
|
||||
return '';
|
||||
}
|
||||
return `ABS(CHECKSUM(NEWID())) % 100 < ${Math.round(samplePct * 100)}`;
|
||||
}
|
||||
|
||||
getTableSampleClause(samplePct: number): string {
|
||||
if (samplePct <= 0 || samplePct >= 1) {
|
||||
return '';
|
||||
}
|
||||
return `TABLESAMPLE (${samplePct * 100} PERCENT)`;
|
||||
}
|
||||
|
||||
getLimitOffsetClause(limit: number, offset?: number): string {
|
||||
return offset !== undefined && offset > 0 ? `OFFSET ${offset} ROWS FETCH NEXT ${limit} ROWS ONLY` : '';
|
||||
}
|
||||
|
||||
getTopClause(limit: number): string {
|
||||
return `TOP ${limit}`;
|
||||
}
|
||||
|
||||
getNullCountExpression(column: string): string {
|
||||
return `SUM(CASE WHEN ${column} IS NULL THEN 1 ELSE 0 END)`;
|
||||
}
|
||||
|
||||
getDistinctCountExpression(column: string): string {
|
||||
return `COUNT(DISTINCT ${column})`;
|
||||
}
|
||||
|
||||
generateCardinalitySampleQuery(tableName: string, columnName: string, sampleSize: number): string {
|
||||
return `
|
||||
WITH sampled AS (
|
||||
SELECT TOP ${sampleSize} ${columnName} AS val
|
||||
FROM ${tableName}
|
||||
WHERE ${columnName} IS NOT NULL
|
||||
)
|
||||
SELECT COUNT(DISTINCT val) AS cardinality
|
||||
FROM sampled
|
||||
`;
|
||||
}
|
||||
|
||||
generateDistinctValuesQuery(tableName: string, columnName: string, limit: number): string {
|
||||
return `
|
||||
SELECT TOP ${limit} val
|
||||
FROM (
|
||||
SELECT DISTINCT CAST(${columnName} AS NVARCHAR(MAX)) AS val
|
||||
FROM ${tableName}
|
||||
WHERE ${columnName} IS NOT NULL
|
||||
) AS distinct_vals
|
||||
ORDER BY val
|
||||
`;
|
||||
}
|
||||
|
||||
generateColumnStatisticsQuery(_schemaName: string, _tableName: string): string | null {
|
||||
return null;
|
||||
}
|
||||
|
||||
generateRandomizedCardinalitySampleQuery(tableName: string, columnName: string, sampleSize: number): string {
|
||||
return `
|
||||
WITH sampled AS (
|
||||
SELECT TOP ${sampleSize} ${columnName} AS val
|
||||
FROM ${tableName}
|
||||
WHERE ${columnName} IS NOT NULL
|
||||
ORDER BY NEWID()
|
||||
)
|
||||
SELECT COUNT(DISTINCT val) AS cardinality
|
||||
FROM sampled
|
||||
`;
|
||||
}
|
||||
|
||||
getTimeTruncExpression(
|
||||
column: string,
|
||||
granularity: 'day' | 'week' | 'month' | 'quarter' | 'year',
|
||||
timezone?: string,
|
||||
): string {
|
||||
const col = timezone ? `${column} AT TIME ZONE 'UTC' AT TIME ZONE '${timezone}'` : column;
|
||||
switch (granularity) {
|
||||
case 'day':
|
||||
return `CAST(${col} AS DATE)`;
|
||||
case 'week':
|
||||
return `DATEADD(WEEK, DATEDIFF(WEEK, 0, ${col}), 0)`;
|
||||
case 'month':
|
||||
return `DATEFROMPARTS(YEAR(${col}), MONTH(${col}), 1)`;
|
||||
case 'quarter':
|
||||
return `DATEFROMPARTS(YEAR(${col}), (DATEPART(QUARTER, ${col}) - 1) * 3 + 1, 1)`;
|
||||
case 'year':
|
||||
return `DATEFROMPARTS(YEAR(${col}), 1, 1)`;
|
||||
}
|
||||
}
|
||||
|
||||
getCustomTimeTruncExpression(column: string, interval: string, origin?: string, timezone?: string): string {
|
||||
const col = timezone ? `${column} AT TIME ZONE 'UTC' AT TIME ZONE '${timezone}'` : column;
|
||||
const [amount, unit] = interval.split(' ');
|
||||
const originExpr = origin ? `'${origin}'` : `'1970-01-01'`;
|
||||
return `DATEADD(${unit}, (DATEDIFF(${unit}, ${originExpr}, ${col}) / ${amount}) * ${amount}, ${originExpr})`;
|
||||
}
|
||||
|
||||
parseIntervalToSql(interval: string): string {
|
||||
return `'${interval}'`;
|
||||
}
|
||||
}
|
||||
17
packages/cli/src/connectors/sqlserver/index.ts
Normal file
17
packages/cli/src/connectors/sqlserver/index.ts
Normal file
|
|
@ -0,0 +1,17 @@
|
|||
export { KtxSqlServerDialect } from './dialect.js';
|
||||
export {
|
||||
isKtxSqlServerConnectionConfig,
|
||||
KtxSqlServerScanConnector,
|
||||
sqlServerConnectionPoolConfigFromConfig,
|
||||
type KtxSqlServerColumnDistinctValuesOptions,
|
||||
type KtxSqlServerColumnDistinctValuesResult,
|
||||
type KtxSqlServerConnectionConfig,
|
||||
type KtxSqlServerEndpointResolver,
|
||||
type KtxSqlServerPool,
|
||||
type KtxSqlServerPoolConfig,
|
||||
type KtxSqlServerPoolFactory,
|
||||
type KtxSqlServerQueryResult,
|
||||
type KtxSqlServerReadOnlyQueryInput,
|
||||
type KtxSqlServerScanConnectorOptions,
|
||||
} from './connector.js';
|
||||
export { createSqlServerLiveDatabaseIntrospection } from './live-database-introspection.js';
|
||||
|
|
@ -0,0 +1,40 @@
|
|||
import type { LiveDatabaseIntrospectionPort } from '../../context/ingest/index.js';
|
||||
import type { KtxProjectConnectionConfig } from '../../context/project/index.js';
|
||||
import {
|
||||
KtxSqlServerScanConnector,
|
||||
type KtxSqlServerConnectionConfig,
|
||||
type KtxSqlServerEndpointResolver,
|
||||
type KtxSqlServerPoolFactory,
|
||||
} from './connector.js';
|
||||
|
||||
interface CreateSqlServerLiveDatabaseIntrospectionOptions {
|
||||
connections: Record<string, KtxProjectConnectionConfig>;
|
||||
poolFactory?: KtxSqlServerPoolFactory;
|
||||
endpointResolver?: KtxSqlServerEndpointResolver;
|
||||
now?: () => Date;
|
||||
}
|
||||
|
||||
export function createSqlServerLiveDatabaseIntrospection(
|
||||
options: CreateSqlServerLiveDatabaseIntrospectionOptions,
|
||||
): LiveDatabaseIntrospectionPort {
|
||||
return {
|
||||
async extractSchema(connectionId: string) {
|
||||
const connection = options.connections[connectionId] as KtxSqlServerConnectionConfig | undefined;
|
||||
const connector = new KtxSqlServerScanConnector({
|
||||
connectionId,
|
||||
connection,
|
||||
poolFactory: options.poolFactory,
|
||||
endpointResolver: options.endpointResolver,
|
||||
now: options.now,
|
||||
});
|
||||
try {
|
||||
return await connector.introspect(
|
||||
{ connectionId, driver: 'sqlserver' },
|
||||
{ runId: `sqlserver-${connectionId}` },
|
||||
);
|
||||
} finally {
|
||||
await connector.cleanup();
|
||||
}
|
||||
},
|
||||
};
|
||||
}
|
||||
Loading…
Add table
Add a link
Reference in a new issue