mirror of
https://github.com/Kaelio/ktx.git
synced 2026-07-04 10:52:13 +02:00
fix(snowflake): unblock multi-schema ingest and relationship discovery (#204)
* feat(setup): drop redundant Snowflake schema prompt; fall back to free-text on listSchemas failure Snowflake setup previously asked for a single schema as free text, then ran a multiselect against the discovered schemas — two schema questions back-to-back, with the first being only a session bootstrap. The SDK's `schema` is optional, so the bootstrap step is unnecessary. - Remove the free-text Snowflake schema prompt; only pass `schema` to snowflake-sdk when one is configured. - When `listSchemas()` fails (e.g. role lacks SHOW SCHEMAS), prompt the user for a comma-separated list, persist it as `schema_names`, and use it as both the table-list filter and the multiselect default. Applies to every driver with a scope-discovery spec, not just Snowflake. - Update docs to lead with `schema_names`; keep `schema_name` as a documented single-schema shorthand. * fix(snowflake): keep introspecting when primary-key discovery is denied The PK query joins INFORMATION_SCHEMA.TABLE_CONSTRAINTS and INFORMATION_SCHEMA.KEY_COLUMN_USAGE, which require grants the connection role may not have. Previously a 'SQL compilation error: Object ANALYTICS.INFORMATION_SCHEMA.KEY_COLUMN_USAGE does not exist or not authorized' aborted the entire introspect — schemas, columns, and row counts were all discarded over a missing nice-to-have. Wrap the constraint query in try/catch, log a one-line warning per schema, and return an empty PK map. Columns end up with primaryKey=false; relationship inference still has FK and profiling to fall back on. * fix(scan): unblock relationship discovery on Snowflake Two adjacent bugs prevented the scan's relationship pipeline from producing any joins on a Snowflake warehouse: - relationship-profiling.ts fell through to a default `GROUP_CONCAT` branch for unknown drivers. Snowflake has no GROUP_CONCAT, so every per-table profile query failed with "Unknown function GROUP_CONCAT". Add an explicit Snowflake branch that uses LISTAGG with a literal '\x1f' delimiter (Snowflake requires the delimiter to be a constant, so CHR(31) is rejected). - description-generation.ts destructured `connector.sampleTable` and `connector.sampleColumn` into bare locals, losing the `this` binding when the class-method connectors (Snowflake, Postgres, MySQL) were invoked. Every sample call threw "Cannot read properties of undefined (reading 'assertConnection')" and degraded LLM descriptions to metadata-only prompts. Call the methods through the connector instead. Without these, even after the primary-key probe is allowed to fail softly, the scan ends up with 0 validated relationships and an empty `joins:` block in every shard YAML. * test(scan): cover table-ref helpers * feat(scan): plumb tableScope through live-database introspection port * feat(scan): apply tableScope during metadata fetch * feat(scan): enforce table scope at fetch boundary * feat(scan): pool Snowflake sessions and batch enrichment for faster ingest (#206) * feat(cli): add RSA key-pair auth option to Snowflake setup wizard Extends the interactive Snowflake setup flow with an authentication-method prompt (password vs RSA/JWT key-pair). The RSA branch collects a private-key path (env/file/absolute) and an optional passphrase; the resulting connection config records `authMethod: 'rsa'` with `privateKey` and `passphrase` instead of `password`. * feat(scan): pool Snowflake sessions * fix(scan): reuse structural snapshots and cleanup connectors * feat(scan): parallelize relationship profiling * feat(scan): batch table description generation * docs: document Snowflake ingest concurrency knobs * fix(scan): close Snowflake ingest perf verification gaps * fix(scan): keep batched description failure bounded * feat(scan): dispatch query-history probes by connection driver Extract historic-sql dialect resolution into a shared helper so the status-project readiness check and the local ingest factory agree on which connections enable query history and which probe to run. The status command now picks the postgres/snowflake/bigquery probe based on the connection's driver instead of always reporting against postgres, which previously caused snowflake connections with queryHistory.enabled to surface a misleading "driver is snowflake" failure. Also drops a noisy console.warn from Snowflake primary-key discovery — INFORMATION_SCHEMA.KEY_COLUMN_USAGE is commonly ungranted for read-only roles and the FK + profiling paths handle the empty PK map already. * fix(llm): allow StructuredOutput tool and raise maxTurns for generateObject The Claude Code agent SDK announces an internal pseudo-tool named StructuredOutput in the system/init message whenever outputFormat is set to { type: 'json_schema' }. The runtime's isolation check built its allowedToolIds set only from MCP tool ids and treated StructuredOutput as an unexpected host-injected tool, so every generateObject call threw "Claude Code runtime isolation failed: tools=StructuredOutput ..." and the table-descriptions and relationship-LLM-proposal enrichment stages recorded null output across the board. Whitelist StructuredOutput specifically in generateObject's allowedToolIds — the check also enforces missing_tools symmetry, so generateText and runAgentLoop, which do not see StructuredOutput, must not require it. generateObject also ran with maxTurns: 1, which the model intermittently breached when it emitted thinking text before the structured response. Raised to 5 to give the schema-bound call enough headroom without allowing unbounded loops. The existing tests now exercise the path with an init message that announces StructuredOutput so the regression cannot slip back in. * chore(scripts): add ktx-reset.sh project-cleanup helper Convenience script for repeatable ingest testing: takes a project directory and prunes everything except ktx.yaml and .ktx/secrets/, so the next ktx setup or ktx ingest run starts from a known-clean state.
This commit is contained in:
Andrey Avtomonov
GitHub
parent
b0dd13ce7c
commit
394a985d2a
72 changed files with 3508 additions and 655 deletions
|
|
@ -1,6 +1,15 @@
|
|||
import { describe, expect, it, vi } from 'vitest';
|
||||
|
||||
const createPool = vi.hoisted(() => vi.fn());
|
||||
|
||||
vi.mock('snowflake-sdk', () => ({
|
||||
default: { createPool },
|
||||
createPool,
|
||||
}));
|
||||
|
||||
import { createSnowflakeLiveDatabaseIntrospection } from '../../connectors/snowflake/live-database-introspection.js';
|
||||
import { isKtxSnowflakeConnectionConfig, KtxSnowflakeScanConnector, snowflakeConnectionConfigFromConfig, type KtxSnowflakeDriver, type KtxSnowflakeDriverFactory } from '../../connectors/snowflake/connector.js';
|
||||
import { tableRefSet } from '../../context/scan/table-ref.js';
|
||||
|
||||
function fakeDriverFactory(): KtxSnowflakeDriverFactory {
|
||||
const driver: KtxSnowflakeDriver = {
|
||||
|
|
@ -63,6 +72,38 @@ function fakeDriverFactory(): KtxSnowflakeDriverFactory {
|
|||
return { createDriver: vi.fn(() => driver) };
|
||||
}
|
||||
|
||||
function fakeSnowflakeStatement(headers: string[] = ['ONE']) {
|
||||
return {
|
||||
getColumns: () => headers.map((header) => ({ getName: () => header, getType: () => 'TEXT' })),
|
||||
};
|
||||
}
|
||||
|
||||
function installSnowflakePoolMock() {
|
||||
const executedSql: string[] = [];
|
||||
const connection = {
|
||||
execute: vi.fn(
|
||||
(input: {
|
||||
sqlText: string;
|
||||
complete: (
|
||||
error: Error | null,
|
||||
statement: ReturnType<typeof fakeSnowflakeStatement>,
|
||||
rows: Array<Record<string, unknown>>,
|
||||
) => void;
|
||||
}) => {
|
||||
executedSql.push(input.sqlText);
|
||||
input.complete(null, fakeSnowflakeStatement(), [{ ONE: 1 }]);
|
||||
},
|
||||
),
|
||||
};
|
||||
const pool = {
|
||||
use: vi.fn(async (fn: (conn: typeof connection) => Promise<unknown>) => fn(connection)),
|
||||
drain: vi.fn(async () => undefined),
|
||||
clear: vi.fn(async () => undefined),
|
||||
};
|
||||
createPool.mockReturnValue(pool);
|
||||
return { connection, pool, executedSql };
|
||||
}
|
||||
|
||||
describe('KtxSnowflakeScanConnector', () => {
|
||||
it('resolves Snowflake connection configuration safely', () => {
|
||||
expect(
|
||||
|
|
@ -99,6 +140,99 @@ describe('KtxSnowflakeScanConnector', () => {
|
|||
});
|
||||
});
|
||||
|
||||
it('defaults and validates Snowflake maxSessions', () => {
|
||||
const baseConnection = {
|
||||
driver: 'snowflake',
|
||||
authMethod: 'password',
|
||||
account: 'acct',
|
||||
warehouse: 'WH',
|
||||
database: 'ANALYTICS',
|
||||
schema_name: 'PUBLIC',
|
||||
username: 'reader',
|
||||
password: 'fixture-pass', // pragma: allowlist secret
|
||||
} as const;
|
||||
|
||||
expect(
|
||||
snowflakeConnectionConfigFromConfig({
|
||||
connectionId: 'warehouse',
|
||||
connection: baseConnection,
|
||||
}),
|
||||
).toMatchObject({ maxSessions: 4 });
|
||||
|
||||
expect(
|
||||
snowflakeConnectionConfigFromConfig({
|
||||
connectionId: 'warehouse',
|
||||
connection: { ...baseConnection, maxSessions: 8 },
|
||||
}),
|
||||
).toMatchObject({ maxSessions: 8 });
|
||||
|
||||
for (const maxSessions of [0, -1, 1.5, Number.NaN]) {
|
||||
expect(() =>
|
||||
snowflakeConnectionConfigFromConfig({
|
||||
connectionId: 'warehouse',
|
||||
connection: { ...baseConnection, maxSessions },
|
||||
}),
|
||||
).toThrow('connections.warehouse.maxSessions must be a positive integer');
|
||||
}
|
||||
});
|
||||
|
||||
it('uses one lazy Snowflake pool and drains it during cleanup', async () => {
|
||||
const { pool, executedSql } = installSnowflakePoolMock();
|
||||
const close = vi.fn(async () => undefined);
|
||||
const connector = new KtxSnowflakeScanConnector({
|
||||
connectionId: 'warehouse',
|
||||
connection: {
|
||||
driver: 'snowflake',
|
||||
authMethod: 'password',
|
||||
account: 'acct',
|
||||
warehouse: 'WH',
|
||||
database: 'ANALYTICS',
|
||||
schema_name: 'PUBLIC',
|
||||
username: 'reader',
|
||||
password: 'fixture-pass', // pragma: allowlist secret
|
||||
role: 'ANALYST',
|
||||
maxSessions: 3,
|
||||
},
|
||||
sdkOptionsProvider: {
|
||||
resolve: vi.fn(async () => ({ sdkOptions: { application: 'ktx-test' }, close })),
|
||||
},
|
||||
});
|
||||
|
||||
expect(createPool).not.toHaveBeenCalled();
|
||||
|
||||
await connector.executeReadOnly({ connectionId: 'warehouse', sql: 'select 1', maxRows: 1 }, { runId: 'run-1' });
|
||||
await connector.executeReadOnly({ connectionId: 'warehouse', sql: 'select 1', maxRows: 1 }, { runId: 'run-1' });
|
||||
|
||||
expect(createPool).toHaveBeenCalledTimes(1);
|
||||
expect(createPool).toHaveBeenCalledWith(
|
||||
expect.objectContaining({
|
||||
account: 'acct',
|
||||
username: 'reader',
|
||||
warehouse: 'WH',
|
||||
database: 'ANALYTICS',
|
||||
schema: 'PUBLIC',
|
||||
role: 'ANALYST',
|
||||
password: 'fixture-pass', // pragma: allowlist secret
|
||||
clientSessionKeepAlive: true,
|
||||
clientSessionKeepAliveHeartbeatFrequency: 900,
|
||||
application: 'ktx-test',
|
||||
}),
|
||||
expect.objectContaining({
|
||||
min: 0,
|
||||
max: 3,
|
||||
evictionRunIntervalMillis: 30_000,
|
||||
acquireTimeoutMillis: 60_000,
|
||||
}),
|
||||
);
|
||||
expect(pool.use).toHaveBeenCalledTimes(2);
|
||||
expect(executedSql.some((sql) => /^USE\s+/i.test(sql.trim()))).toBe(false);
|
||||
|
||||
await connector.cleanup();
|
||||
expect(pool.drain).toHaveBeenCalledBefore(pool.clear);
|
||||
expect(pool.clear).toHaveBeenCalledTimes(1);
|
||||
expect(close).toHaveBeenCalledTimes(1);
|
||||
});
|
||||
|
||||
it('introspects schema, primary keys, comments, row counts, and dimensions', async () => {
|
||||
const connector = new KtxSnowflakeScanConnector({
|
||||
connectionId: 'warehouse',
|
||||
|
|
@ -157,6 +291,108 @@ describe('KtxSnowflakeScanConnector', () => {
|
|||
]);
|
||||
});
|
||||
|
||||
it('continues introspection when primary-key discovery is not authorized', async () => {
|
||||
const driverFactory = fakeDriverFactory();
|
||||
const driver = (driverFactory.createDriver as ReturnType<typeof vi.fn>).getMockImplementation() as
|
||||
| (() => KtxSnowflakeDriver)
|
||||
| undefined;
|
||||
if (!driver) throw new Error('driver mock missing');
|
||||
const built = driver();
|
||||
(built.query as ReturnType<typeof vi.fn>).mockImplementation(async (sql: string) => {
|
||||
if (sql.includes('TABLE_CONSTRAINTS')) {
|
||||
throw new Error(
|
||||
"SQL compilation error: Object 'ANALYTICS.INFORMATION_SCHEMA.KEY_COLUMN_USAGE' does not exist or not authorized.",
|
||||
);
|
||||
}
|
||||
throw new Error(`Unexpected SQL: ${sql}`);
|
||||
});
|
||||
(driverFactory.createDriver as ReturnType<typeof vi.fn>).mockReturnValue(built);
|
||||
|
||||
const warn = vi.spyOn(console, 'warn').mockImplementation(() => undefined);
|
||||
try {
|
||||
const connector = new KtxSnowflakeScanConnector({
|
||||
connectionId: 'warehouse',
|
||||
connection: {
|
||||
driver: 'snowflake',
|
||||
authMethod: 'password',
|
||||
account: 'acct',
|
||||
warehouse: 'WH',
|
||||
database: 'ANALYTICS',
|
||||
schema_name: 'PUBLIC',
|
||||
username: 'reader',
|
||||
password: 'fixture-pass', // pragma: allowlist secret
|
||||
},
|
||||
driverFactory,
|
||||
});
|
||||
|
||||
const snapshot = await connector.introspect(
|
||||
{ connectionId: 'warehouse', driver: 'snowflake' },
|
||||
{ runId: 'scan-run-pk-skip' },
|
||||
);
|
||||
|
||||
expect(snapshot.tables.map((table) => table.name).sort()).toEqual(['ORDERS', 'ORDER_SUMMARY']);
|
||||
expect(snapshot.tables.every((table) => table.columns.every((column) => column.primaryKey === false))).toBe(true);
|
||||
expect(warn).not.toHaveBeenCalled();
|
||||
} finally {
|
||||
warn.mockRestore();
|
||||
}
|
||||
});
|
||||
|
||||
it('limits introspection to tables in tableScope', async () => {
|
||||
const queries: Array<{ sql: string; params?: unknown }> = [];
|
||||
const getSchemaMetadata = vi.fn(async (_schemaName?: string, scopedNames?: readonly string[] | null) =>
|
||||
scopedNames?.includes('ORDERS')
|
||||
? [
|
||||
{
|
||||
name: 'ORDERS',
|
||||
catalog: 'ANALYTICS',
|
||||
db: 'MARTS',
|
||||
rowCount: 10,
|
||||
comment: null,
|
||||
columns: [{ name: 'ID', type: 'NUMBER', nullable: false, comment: null }],
|
||||
},
|
||||
]
|
||||
: [],
|
||||
);
|
||||
const driverFactory: KtxSnowflakeDriverFactory = {
|
||||
createDriver: vi.fn(() => ({
|
||||
test: vi.fn(async () => ({ success: true })),
|
||||
query: vi.fn(async (sql: string, params?: unknown) => {
|
||||
queries.push({ sql, params });
|
||||
return { headers: [], rows: [], totalRows: 0, rowCount: 0 };
|
||||
}),
|
||||
getSchemaMetadata,
|
||||
listSchemas: vi.fn(async () => []),
|
||||
listTables: vi.fn(async () => []),
|
||||
cleanup: vi.fn(async () => undefined),
|
||||
})),
|
||||
};
|
||||
const connector = new KtxSnowflakeScanConnector({
|
||||
connectionId: 'warehouse',
|
||||
connection: {
|
||||
driver: 'snowflake',
|
||||
authMethod: 'password',
|
||||
account: 'acct',
|
||||
warehouse: 'WH',
|
||||
database: 'ANALYTICS',
|
||||
schema_name: 'MARTS',
|
||||
username: 'reader',
|
||||
password: 'fixture-pass', // pragma: allowlist secret
|
||||
},
|
||||
driverFactory,
|
||||
});
|
||||
const scope = tableRefSet([{ catalog: 'ANALYTICS', db: 'MARTS', name: 'ORDERS' }]);
|
||||
const snapshot = await connector.introspect(
|
||||
{ connectionId: 'warehouse', driver: 'snowflake', tableScope: scope },
|
||||
{ runId: 'scope-test' },
|
||||
);
|
||||
expect(snapshot.tables.map((table) => table.name)).toEqual(['ORDERS']);
|
||||
expect(getSchemaMetadata).toHaveBeenCalledWith('MARTS', ['ORDERS']);
|
||||
const primaryKeysQuery = queries.find((query) => query.sql.includes('TABLE_CONSTRAINTS'));
|
||||
expect(primaryKeysQuery?.sql).toMatch(/AND tc\.TABLE_NAME IN \(\?\)/);
|
||||
expect(primaryKeysQuery?.params).toEqual(['MARTS', 'ANALYTICS', 'ORDERS']);
|
||||
});
|
||||
|
||||
it('supports read-only query, sampling, distinct values, row counts, schema listing, and cleanup', async () => {
|
||||
const driverFactory = fakeDriverFactory();
|
||||
const connector = new KtxSnowflakeScanConnector({
|
||||
|
|
|
|||
|
|
@ -4,9 +4,12 @@ import { homedir } from 'node:os';
|
|||
import { resolve } from 'node:path';
|
||||
import { assertReadOnlySql, limitSqlForExecution } from '../../context/connections/read-only-sql.js';
|
||||
import { createKtxConnectorCapabilities, type KtxColumnSampleInput, type KtxColumnSampleResult, type KtxColumnStatsInput, type KtxColumnStatsResult, type KtxQueryResult, type KtxReadOnlyQueryInput, type KtxScanConnector, type KtxScanContext, type KtxScanInput, type KtxSchemaColumn, type KtxSchemaSnapshot, type KtxSchemaTable, type KtxTableRef, type KtxTableSampleInput, type KtxTableListEntry, type KtxTableSampleResult } from '../../context/scan/types.js';
|
||||
import * as snowflake from 'snowflake-sdk';
|
||||
import { scopedTableNames } from '../../context/scan/table-ref.js';
|
||||
import snowflake from 'snowflake-sdk';
|
||||
import type { Bind, Binds, Connection, ConnectionOptions } from 'snowflake-sdk';
|
||||
import { KtxSnowflakeDialect } from './dialect.js';
|
||||
import { assertSafeSnowflakeIdentifier, quoteSnowflakeIdentifier } from './identifiers.js';
|
||||
import { configureSnowflakeSdkLogger } from './sdk-logger.js';
|
||||
|
||||
export interface KtxSnowflakeConnectionConfig {
|
||||
driver?: string;
|
||||
|
|
@ -21,6 +24,7 @@ export interface KtxSnowflakeConnectionConfig {
|
|||
privateKey?: string;
|
||||
passphrase?: string;
|
||||
role?: string;
|
||||
maxSessions?: number;
|
||||
[key: string]: unknown;
|
||||
}
|
||||
|
||||
|
|
@ -35,6 +39,7 @@ export interface KtxSnowflakeResolvedConnectionConfig {
|
|||
privateKey?: string;
|
||||
passphrase?: string;
|
||||
role?: string;
|
||||
maxSessions: number;
|
||||
}
|
||||
|
||||
export interface KtxSnowflakeRawColumnMetadata {
|
||||
|
|
@ -56,7 +61,7 @@ export interface KtxSnowflakeRawTableMetadata {
|
|||
export interface KtxSnowflakeDriver {
|
||||
test(): Promise<{ success: boolean; error?: string }>;
|
||||
query(sql: string, params?: unknown): Promise<KtxQueryResult>;
|
||||
getSchemaMetadata(schemaName?: string): Promise<KtxSnowflakeRawTableMetadata[]>;
|
||||
getSchemaMetadata(schemaName?: string, scopedTableNames?: readonly string[] | null): Promise<KtxSnowflakeRawTableMetadata[]>;
|
||||
listSchemas(): Promise<string[]>;
|
||||
listTables(schemas?: string[]): Promise<KtxTableListEntry[]>;
|
||||
cleanup(): Promise<void>;
|
||||
|
|
@ -79,6 +84,12 @@ export interface KtxSnowflakeSdkOptionsProvider {
|
|||
export interface KtxSnowflakeScanConnectorOptions {
|
||||
connectionId: string;
|
||||
connection: KtxSnowflakeConnectionConfig | undefined;
|
||||
/**
|
||||
* KTX project directory. When provided, snowflake-sdk's logger is redirected to
|
||||
* `<projectDir>/.ktx/logs/snowflake.log` so its JSON output does not bleed into
|
||||
* the CLI's TTY. Tests that use a fake driverFactory can leave this undefined.
|
||||
*/
|
||||
projectDir?: string;
|
||||
driverFactory?: KtxSnowflakeDriverFactory;
|
||||
sdkOptionsProvider?: KtxSnowflakeSdkOptionsProvider;
|
||||
env?: NodeJS.ProcessEnv;
|
||||
|
|
@ -123,13 +134,31 @@ function stringConfigValue(
|
|||
return typeof value === 'string' && value.trim().length > 0 ? resolveStringReference(value.trim(), env) : undefined;
|
||||
}
|
||||
|
||||
function positiveIntegerConfigValue(input: {
|
||||
connection: KtxSnowflakeConnectionConfig;
|
||||
key: keyof KtxSnowflakeConnectionConfig;
|
||||
connectionId: string;
|
||||
defaultValue: number;
|
||||
}): number {
|
||||
const value = input.connection[input.key];
|
||||
if (value === undefined) {
|
||||
return input.defaultValue;
|
||||
}
|
||||
const numberValue = Number(value);
|
||||
if (!Number.isInteger(numberValue) || numberValue < 1) {
|
||||
throw new Error(`connections.${input.connectionId}.${String(input.key)} must be a positive integer`);
|
||||
}
|
||||
return numberValue;
|
||||
}
|
||||
|
||||
function schemaNames(connection: KtxSnowflakeConnectionConfig, env: NodeJS.ProcessEnv): string[] {
|
||||
if (Array.isArray(connection.schema_names) && connection.schema_names.length > 0) {
|
||||
return connection.schema_names
|
||||
.filter((schema) => schema.trim().length > 0)
|
||||
.map((schema) => resolveStringReference(schema, env));
|
||||
}
|
||||
return [stringConfigValue(connection, 'schema_name', env) ?? 'PUBLIC'];
|
||||
const single = stringConfigValue(connection, 'schema_name', env);
|
||||
return single ? [single] : [];
|
||||
}
|
||||
|
||||
function firstNumber(value: unknown): number | null {
|
||||
|
|
@ -159,7 +188,7 @@ function normalizeSnowflakeValue(value: unknown, columnType?: string): unknown {
|
|||
return value;
|
||||
}
|
||||
|
||||
function toSnowflakeBind(value: unknown): snowflake.Bind {
|
||||
function toSnowflakeBind(value: unknown): Bind {
|
||||
if (value === null || typeof value === 'string' || typeof value === 'number' || typeof value === 'boolean') {
|
||||
return value;
|
||||
}
|
||||
|
|
@ -169,7 +198,7 @@ function toSnowflakeBind(value: unknown): snowflake.Bind {
|
|||
return String(value);
|
||||
}
|
||||
|
||||
function toSnowflakeBinds(params: unknown[] | undefined): snowflake.Binds | undefined {
|
||||
function toSnowflakeBinds(params: unknown[] | undefined): Binds | undefined {
|
||||
return params?.map((value) => toSnowflakeBind(value));
|
||||
}
|
||||
|
||||
|
|
@ -220,6 +249,12 @@ export function snowflakeConnectionConfigFromConfig(input: {
|
|||
database,
|
||||
schemas: resolvedSchemas,
|
||||
username,
|
||||
maxSessions: positiveIntegerConfigValue({
|
||||
connection: input.connection,
|
||||
key: 'maxSessions',
|
||||
connectionId: input.connectionId,
|
||||
defaultValue: 4,
|
||||
}),
|
||||
};
|
||||
const role = stringConfigValue(input.connection, 'role', env);
|
||||
if (role) {
|
||||
|
|
@ -255,6 +290,7 @@ class DefaultSnowflakeDriverFactory implements KtxSnowflakeDriverFactory {
|
|||
|
||||
class SnowflakeSdkDriver implements KtxSnowflakeDriver {
|
||||
private closeSdkOptions: Array<() => Promise<void>> = [];
|
||||
private pool: ReturnType<typeof snowflake.createPool> | null = null;
|
||||
|
||||
constructor(
|
||||
private readonly resolved: KtxSnowflakeResolvedConnectionConfig,
|
||||
|
|
@ -275,37 +311,50 @@ class SnowflakeSdkDriver implements KtxSnowflakeDriver {
|
|||
}
|
||||
|
||||
async query(sql: string, params?: unknown): Promise<KtxQueryResult> {
|
||||
let connection: snowflake.Connection | null = null;
|
||||
const binds = Array.isArray(params) ? toSnowflakeBinds(params) : undefined;
|
||||
try {
|
||||
connection = await this.createConnection();
|
||||
const binds = Array.isArray(params) ? toSnowflakeBinds(params) : undefined;
|
||||
const result = await this.executeSnowflakeQuery(connection, sql, binds);
|
||||
const pool = await this.getPool();
|
||||
const result = await pool.use(async (connection: snowflake.Connection) =>
|
||||
this.executeSnowflakeQuery(connection, sql, binds),
|
||||
);
|
||||
return { ...result, totalRows: result.rows.length, rowCount: result.rows.length };
|
||||
} finally {
|
||||
if (connection) {
|
||||
await this.destroyConnection(connection);
|
||||
} catch (error) {
|
||||
const message = error instanceof Error ? error.message : String(error);
|
||||
if (/timeout/i.test(message) && /pool|acquire/i.test(message)) {
|
||||
throw new Error(
|
||||
"Snowflake session pool exhausted after 60s - consider lowering maxSessions or increasing your account's concurrent-statement limit.",
|
||||
);
|
||||
}
|
||||
throw error;
|
||||
}
|
||||
}
|
||||
|
||||
async getSchemaMetadata(schemaName = this.resolved.schemas[0] ?? 'PUBLIC'): Promise<KtxSnowflakeRawTableMetadata[]> {
|
||||
async getSchemaMetadata(
|
||||
schemaName = this.resolved.schemas[0] ?? 'PUBLIC',
|
||||
scopedTableNames: readonly string[] | null = null,
|
||||
): Promise<KtxSnowflakeRawTableMetadata[]> {
|
||||
const scopeClause =
|
||||
scopedTableNames && scopedTableNames.length > 0
|
||||
? `AND TABLE_NAME IN (${scopedTableNames.map(() => '?').join(', ')})`
|
||||
: '';
|
||||
const scopeParams = scopedTableNames ?? [];
|
||||
const tablesResult = await this.query(
|
||||
`
|
||||
SELECT TABLE_NAME, TABLE_TYPE, COMMENT, ROW_COUNT
|
||||
FROM INFORMATION_SCHEMA.TABLES
|
||||
WHERE TABLE_SCHEMA = ? AND TABLE_CATALOG = ?
|
||||
WHERE TABLE_SCHEMA = ? AND TABLE_CATALOG = ? ${scopeClause}
|
||||
ORDER BY TABLE_NAME
|
||||
`,
|
||||
[schemaName, this.resolved.database],
|
||||
[schemaName, this.resolved.database, ...scopeParams],
|
||||
);
|
||||
const columnsResult = await this.query(
|
||||
`
|
||||
SELECT TABLE_NAME, COLUMN_NAME, DATA_TYPE, IS_NULLABLE, COMMENT, ORDINAL_POSITION
|
||||
FROM INFORMATION_SCHEMA.COLUMNS
|
||||
WHERE TABLE_SCHEMA = ? AND TABLE_CATALOG = ?
|
||||
WHERE TABLE_SCHEMA = ? AND TABLE_CATALOG = ? ${scopeClause}
|
||||
ORDER BY TABLE_NAME, ORDINAL_POSITION
|
||||
`,
|
||||
[schemaName, this.resolved.database],
|
||||
[schemaName, this.resolved.database, ...scopeParams],
|
||||
);
|
||||
const columnsByTable = new Map<string, KtxSnowflakeRawColumnMetadata[]>();
|
||||
for (const row of columnsResult.rows) {
|
||||
|
|
@ -357,27 +406,41 @@ class SnowflakeSdkDriver implements KtxSnowflakeDriver {
|
|||
}
|
||||
|
||||
async cleanup(): Promise<void> {
|
||||
const pool = this.pool;
|
||||
this.pool = null;
|
||||
if (pool) {
|
||||
// Drain before clear so in-flight Snowflake statements finish before idle
|
||||
// sessions are closed.
|
||||
await pool.drain();
|
||||
await pool.clear();
|
||||
}
|
||||
const closers = this.closeSdkOptions;
|
||||
this.closeSdkOptions = [];
|
||||
await Promise.all(closers.map((close) => close()));
|
||||
await Promise.all(closers.map((close) => Promise.resolve(close())));
|
||||
}
|
||||
|
||||
private async runTest(): Promise<{ success: boolean; error?: string }> {
|
||||
let connection: snowflake.Connection | null = null;
|
||||
try {
|
||||
connection = await this.createConnection();
|
||||
await this.executeSnowflakeQuery(connection, 'SELECT 1');
|
||||
await this.query('SELECT 1');
|
||||
return { success: true };
|
||||
} catch (error) {
|
||||
return { success: false, error: error instanceof Error ? error.message : String(error) };
|
||||
} finally {
|
||||
if (connection) {
|
||||
await this.destroyConnection(connection);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
private async createConnection(): Promise<snowflake.Connection> {
|
||||
private async getPool(): Promise<ReturnType<typeof snowflake.createPool>> {
|
||||
if (!this.pool) {
|
||||
this.pool = snowflake.createPool(await this.resolveConnectionOptions(), {
|
||||
min: 0,
|
||||
max: this.resolved.maxSessions,
|
||||
evictionRunIntervalMillis: 30_000,
|
||||
acquireTimeoutMillis: 60_000,
|
||||
});
|
||||
}
|
||||
return this.pool;
|
||||
}
|
||||
|
||||
private async resolveConnectionOptions(): Promise<snowflake.ConnectionOptions> {
|
||||
const patch = await this.sdkOptionsProvider?.resolve({
|
||||
account: this.resolved.account,
|
||||
connection: { ...this.resolved, driver: 'snowflake' },
|
||||
|
|
@ -385,60 +448,27 @@ class SnowflakeSdkDriver implements KtxSnowflakeDriver {
|
|||
if (patch?.close) {
|
||||
this.closeSdkOptions.push(patch.close);
|
||||
}
|
||||
const baseConfig: snowflake.ConnectionOptions = {
|
||||
const sessionSchema = this.resolved.schemas[0];
|
||||
const baseConfig: ConnectionOptions = {
|
||||
account: this.resolved.account,
|
||||
username: this.resolved.username,
|
||||
warehouse: this.resolved.warehouse,
|
||||
database: this.resolved.database,
|
||||
schema: this.resolved.schemas[0] ?? 'PUBLIC',
|
||||
...(sessionSchema ? { schema: sessionSchema } : {}),
|
||||
role: this.resolved.role,
|
||||
clientSessionKeepAlive: true,
|
||||
clientSessionKeepAliveHeartbeatFrequency: 900,
|
||||
...patch?.sdkOptions,
|
||||
};
|
||||
const connectionConfig: snowflake.ConnectionOptions =
|
||||
this.resolved.authMethod === 'rsa'
|
||||
? { ...baseConfig, authenticator: 'SNOWFLAKE_JWT', privateKey: this.decryptPrivateKey() }
|
||||
: { ...baseConfig, password: this.resolved.password };
|
||||
const connection = snowflake.createConnection(connectionConfig);
|
||||
return new Promise((resolveConnection, rejectConnection) => {
|
||||
connection.connect((error, connected) => {
|
||||
if (error) {
|
||||
rejectConnection(error);
|
||||
return;
|
||||
}
|
||||
const resolvedConnection = connected ?? connection;
|
||||
this.setConnectionContext(resolvedConnection).then(
|
||||
() => resolveConnection(resolvedConnection),
|
||||
(contextError) => {
|
||||
resolvedConnection.destroy(() => undefined);
|
||||
rejectConnection(contextError);
|
||||
},
|
||||
);
|
||||
});
|
||||
});
|
||||
}
|
||||
|
||||
private async setConnectionContext(connection: snowflake.Connection): Promise<void> {
|
||||
if (this.resolved.role) {
|
||||
await this.executeSnowflakeQuery(connection, `USE ROLE ${quoteSnowflakeIdentifier(this.resolved.role, 'role')}`);
|
||||
}
|
||||
await this.executeSnowflakeQuery(
|
||||
connection,
|
||||
`USE WAREHOUSE ${quoteSnowflakeIdentifier(this.resolved.warehouse, 'warehouse')}`,
|
||||
);
|
||||
await this.executeSnowflakeQuery(
|
||||
connection,
|
||||
`USE DATABASE ${quoteSnowflakeIdentifier(this.resolved.database, 'database')}`,
|
||||
);
|
||||
await this.executeSnowflakeQuery(
|
||||
connection,
|
||||
`USE SCHEMA ${quoteSnowflakeIdentifier(this.resolved.schemas[0] ?? 'PUBLIC', 'schema')}`,
|
||||
);
|
||||
return this.resolved.authMethod === 'rsa'
|
||||
? { ...baseConfig, authenticator: 'SNOWFLAKE_JWT', privateKey: this.decryptPrivateKey() }
|
||||
: { ...baseConfig, password: this.resolved.password };
|
||||
}
|
||||
|
||||
private async executeSnowflakeQuery(
|
||||
connection: snowflake.Connection,
|
||||
connection: Connection,
|
||||
sqlText: string,
|
||||
binds?: snowflake.Binds,
|
||||
binds?: Binds,
|
||||
): Promise<{ headers: string[]; headerTypes?: string[]; rows: unknown[][] }> {
|
||||
return new Promise((resolveQuery, rejectQuery) => {
|
||||
connection.execute({
|
||||
|
|
@ -461,18 +491,6 @@ class SnowflakeSdkDriver implements KtxSnowflakeDriver {
|
|||
});
|
||||
}
|
||||
|
||||
private destroyConnection(connection: snowflake.Connection): Promise<void> {
|
||||
return new Promise((resolveDestroy, rejectDestroy) => {
|
||||
connection.destroy((error) => {
|
||||
if (error) {
|
||||
rejectDestroy(error);
|
||||
return;
|
||||
}
|
||||
resolveDestroy();
|
||||
});
|
||||
});
|
||||
}
|
||||
|
||||
private decryptPrivateKey(): string {
|
||||
if (!this.resolved.privateKey) {
|
||||
throw new Error('Private key is required for RSA authentication');
|
||||
|
|
@ -510,6 +528,9 @@ export class KtxSnowflakeScanConnector implements KtxScanConnector {
|
|||
this.driverFactory = options.driverFactory ?? new DefaultSnowflakeDriverFactory();
|
||||
this.now = options.now ?? (() => new Date());
|
||||
this.id = `snowflake:${options.connectionId}`;
|
||||
if (options.projectDir) {
|
||||
configureSnowflakeSdkLogger(options.projectDir);
|
||||
}
|
||||
}
|
||||
|
||||
async testConnection(): Promise<{ success: boolean; error?: string }> {
|
||||
|
|
@ -520,7 +541,11 @@ export class KtxSnowflakeScanConnector implements KtxScanConnector {
|
|||
this.assertConnection(input.connectionId);
|
||||
const tables: KtxSchemaTable[] = [];
|
||||
for (const schemaName of this.resolved.schemas) {
|
||||
const rawTables = await this.getDriver().getSchemaMetadata(schemaName);
|
||||
const scopedNames = input.tableScope
|
||||
? scopedTableNames(input.tableScope, { catalog: this.resolved.database, db: schemaName })
|
||||
: null;
|
||||
if (scopedNames && scopedNames.length === 0) continue;
|
||||
const rawTables = await this.getDriver().getSchemaMetadata(schemaName, scopedNames);
|
||||
const primaryKeys = await this.primaryKeys(rawTables.map((table) => table.name), schemaName);
|
||||
tables.push(...rawTables.map((table) => this.toSchemaTable(table, primaryKeys)));
|
||||
}
|
||||
|
|
@ -653,32 +678,39 @@ export class KtxSnowflakeScanConnector implements KtxScanConnector {
|
|||
}
|
||||
|
||||
private async primaryKeys(tableNames: string[], schemaName: string): Promise<Map<string, Set<string>>> {
|
||||
if (tableNames.length === 0) {
|
||||
return new Map();
|
||||
}
|
||||
const result = await this.getDriver().query(
|
||||
`
|
||||
SELECT tc.TABLE_NAME, kcu.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
|
||||
AND tc.TABLE_CATALOG = kcu.TABLE_CATALOG
|
||||
WHERE tc.CONSTRAINT_TYPE = 'PRIMARY KEY'
|
||||
AND tc.TABLE_SCHEMA = ?
|
||||
AND tc.TABLE_CATALOG = ?
|
||||
ORDER BY tc.TABLE_NAME, kcu.ORDINAL_POSITION
|
||||
`,
|
||||
[schemaName, this.resolved.database],
|
||||
);
|
||||
const grouped = new Map<string, Set<string>>();
|
||||
for (const tableName of tableNames) {
|
||||
grouped.set(tableName, new Set());
|
||||
}
|
||||
for (const row of result.rows) {
|
||||
const tableName = String(row[0]);
|
||||
const columnName = String(row[1]);
|
||||
grouped.get(tableName)?.add(columnName);
|
||||
if (tableNames.length === 0) {
|
||||
return grouped;
|
||||
}
|
||||
const tableNamePlaceholders = tableNames.map(() => '?').join(', ');
|
||||
try {
|
||||
const result = await this.getDriver().query(
|
||||
`
|
||||
SELECT tc.TABLE_NAME, kcu.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
|
||||
AND tc.TABLE_CATALOG = kcu.TABLE_CATALOG
|
||||
WHERE tc.CONSTRAINT_TYPE = 'PRIMARY KEY'
|
||||
AND tc.TABLE_SCHEMA = ?
|
||||
AND tc.TABLE_CATALOG = ?
|
||||
AND tc.TABLE_NAME IN (${tableNamePlaceholders})
|
||||
ORDER BY tc.TABLE_NAME, kcu.ORDINAL_POSITION
|
||||
`,
|
||||
[schemaName, this.resolved.database, ...tableNames],
|
||||
);
|
||||
for (const row of result.rows) {
|
||||
const tableName = String(row[0]);
|
||||
const columnName = String(row[1]);
|
||||
grouped.get(tableName)?.add(columnName);
|
||||
}
|
||||
} catch {
|
||||
// INFORMATION_SCHEMA.KEY_COLUMN_USAGE often isn't granted to read-only roles;
|
||||
// continue with empty PK map and let FK inference + profiling carry the slack.
|
||||
}
|
||||
return grouped;
|
||||
}
|
||||
|
|
|
|||
|
|
@ -0,0 +1,31 @@
|
|||
import { KtxSnowflakeScanConnector, type KtxSnowflakeScanConnectorOptions } from './connector.js';
|
||||
|
||||
export type KtxSnowflakeHistoricSqlQueryClientOptions = KtxSnowflakeScanConnectorOptions;
|
||||
|
||||
export class KtxSnowflakeHistoricSqlQueryClient {
|
||||
private readonly connectionId: string;
|
||||
private readonly connector: KtxSnowflakeScanConnector;
|
||||
|
||||
constructor(options: KtxSnowflakeHistoricSqlQueryClientOptions) {
|
||||
this.connectionId = options.connectionId;
|
||||
this.connector = new KtxSnowflakeScanConnector(options);
|
||||
}
|
||||
|
||||
async executeQuery(
|
||||
sql: string,
|
||||
): Promise<{ headers: string[]; rows: unknown[][]; totalRows: number }> {
|
||||
const result = await this.connector.executeReadOnly(
|
||||
{ connectionId: this.connectionId, sql },
|
||||
{} as never,
|
||||
);
|
||||
return {
|
||||
headers: result.headers,
|
||||
rows: result.rows,
|
||||
totalRows: result.totalRows,
|
||||
};
|
||||
}
|
||||
|
||||
async cleanup(): Promise<void> {
|
||||
await this.connector.cleanup();
|
||||
}
|
||||
}
|
||||
|
|
@ -1,4 +1,7 @@
|
|||
import type { LiveDatabaseIntrospectionPort } from '../../context/ingest/adapters/live-database/types.js';
|
||||
import type {
|
||||
LiveDatabaseIntrospectionOptions,
|
||||
LiveDatabaseIntrospectionPort,
|
||||
} from '../../context/ingest/adapters/live-database/types.js';
|
||||
import type { KtxProjectConnectionConfig } from '../../context/project/config.js';
|
||||
import {
|
||||
KtxSnowflakeScanConnector,
|
||||
|
|
@ -9,6 +12,7 @@ import {
|
|||
|
||||
interface CreateSnowflakeLiveDatabaseIntrospectionOptions {
|
||||
connections: Record<string, KtxProjectConnectionConfig>;
|
||||
projectDir?: string;
|
||||
driverFactory?: KtxSnowflakeDriverFactory;
|
||||
sdkOptionsProvider?: KtxSnowflakeSdkOptionsProvider;
|
||||
now?: () => Date;
|
||||
|
|
@ -18,18 +22,23 @@ export function createSnowflakeLiveDatabaseIntrospection(
|
|||
options: CreateSnowflakeLiveDatabaseIntrospectionOptions,
|
||||
): LiveDatabaseIntrospectionPort {
|
||||
return {
|
||||
async extractSchema(connectionId: string) {
|
||||
async extractSchema(connectionId: string, introspectionOptions?: LiveDatabaseIntrospectionOptions) {
|
||||
const connection = options.connections[connectionId] as KtxSnowflakeConnectionConfig | undefined;
|
||||
const connector = new KtxSnowflakeScanConnector({
|
||||
connectionId,
|
||||
connection,
|
||||
...(options.projectDir ? { projectDir: options.projectDir } : {}),
|
||||
driverFactory: options.driverFactory,
|
||||
sdkOptionsProvider: options.sdkOptionsProvider,
|
||||
now: options.now,
|
||||
});
|
||||
try {
|
||||
return await connector.introspect(
|
||||
{ connectionId, driver: 'snowflake' },
|
||||
{
|
||||
connectionId,
|
||||
driver: 'snowflake',
|
||||
...(introspectionOptions?.tableScope ? { tableScope: introspectionOptions.tableScope } : {}),
|
||||
},
|
||||
{ runId: `snowflake-${connectionId}` },
|
||||
);
|
||||
} finally {
|
||||
|
|
|
|||
57
packages/cli/src/connectors/snowflake/sdk-logger.test.ts
Normal file
57
packages/cli/src/connectors/snowflake/sdk-logger.test.ts
Normal file
|
|
@ -0,0 +1,57 @@
|
|||
import { mkdtempSync, rmSync, statSync } from 'node:fs';
|
||||
import { tmpdir } from 'node:os';
|
||||
import { join, resolve } from 'node:path';
|
||||
import { afterEach, beforeEach, describe, expect, it, vi } from 'vitest';
|
||||
|
||||
const { configure } = vi.hoisted(() => ({ configure: vi.fn() }));
|
||||
vi.mock('snowflake-sdk', () => ({
|
||||
default: { configure },
|
||||
}));
|
||||
|
||||
import {
|
||||
configureSnowflakeSdkLogger,
|
||||
resetSnowflakeSdkLoggerConfigurationForTests,
|
||||
} from './sdk-logger.js';
|
||||
|
||||
describe('configureSnowflakeSdkLogger', () => {
|
||||
let projectDir: string;
|
||||
|
||||
beforeEach(() => {
|
||||
configure.mockReset();
|
||||
resetSnowflakeSdkLoggerConfigurationForTests();
|
||||
projectDir = mkdtempSync(join(tmpdir(), 'ktx-snowflake-logger-'));
|
||||
});
|
||||
|
||||
afterEach(() => {
|
||||
rmSync(projectDir, { recursive: true, force: true });
|
||||
});
|
||||
|
||||
it('routes logs to <projectDir>/.ktx/logs/snowflake.log with console output disabled', () => {
|
||||
const expected = resolve(projectDir, '.ktx', 'logs', 'snowflake.log');
|
||||
const returned = configureSnowflakeSdkLogger(projectDir);
|
||||
expect(returned).toBe(expected);
|
||||
expect(configure).toHaveBeenCalledTimes(1);
|
||||
expect(configure).toHaveBeenCalledWith({
|
||||
logFilePath: expected,
|
||||
additionalLogToConsole: false,
|
||||
});
|
||||
expect(statSync(resolve(projectDir, '.ktx', 'logs')).isDirectory()).toBe(true);
|
||||
});
|
||||
|
||||
it('is idempotent for the same projectDir', () => {
|
||||
configureSnowflakeSdkLogger(projectDir);
|
||||
configureSnowflakeSdkLogger(projectDir);
|
||||
expect(configure).toHaveBeenCalledTimes(1);
|
||||
});
|
||||
|
||||
it('reconfigures when projectDir changes', () => {
|
||||
const other = mkdtempSync(join(tmpdir(), 'ktx-snowflake-logger-other-'));
|
||||
try {
|
||||
configureSnowflakeSdkLogger(projectDir);
|
||||
configureSnowflakeSdkLogger(other);
|
||||
expect(configure).toHaveBeenCalledTimes(2);
|
||||
} finally {
|
||||
rmSync(other, { recursive: true, force: true });
|
||||
}
|
||||
});
|
||||
});
|
||||
32
packages/cli/src/connectors/snowflake/sdk-logger.ts
Normal file
32
packages/cli/src/connectors/snowflake/sdk-logger.ts
Normal file
|
|
@ -0,0 +1,32 @@
|
|||
import { mkdirSync } from 'node:fs';
|
||||
import { resolve } from 'node:path';
|
||||
import snowflake from 'snowflake-sdk';
|
||||
|
||||
let configuredLogFilePath: string | null = null;
|
||||
|
||||
/**
|
||||
* Redirects the snowflake-sdk logger to a project-scoped file so its JSON output
|
||||
* does not bleed into the CLI's TTY (which would pollute the setup wizard and
|
||||
* break the in-place progress repainter in `context-build-view.ts`).
|
||||
*
|
||||
* Idempotent per process: re-calling with the same projectDir is a no-op.
|
||||
*/
|
||||
export function configureSnowflakeSdkLogger(projectDir: string): string {
|
||||
const logDir = resolve(projectDir, '.ktx', 'logs');
|
||||
const logFilePath = resolve(logDir, 'snowflake.log');
|
||||
if (configuredLogFilePath === logFilePath) {
|
||||
return logFilePath;
|
||||
}
|
||||
mkdirSync(logDir, { recursive: true });
|
||||
snowflake.configure({
|
||||
logFilePath,
|
||||
additionalLogToConsole: false,
|
||||
});
|
||||
configuredLogFilePath = logFilePath;
|
||||
return logFilePath;
|
||||
}
|
||||
|
||||
/** @internal */
|
||||
export function resetSnowflakeSdkLoggerConfigurationForTests(): void {
|
||||
configuredLogFilePath = null;
|
||||
}
|
||||
Loading…
Add table
Add a link
Reference in a new issue