ktx/packages/cli/test/setup-sources-notion.test.ts

135 lines
4.1 KiB
TypeScript
Raw Permalink Normal View History

import { mkdtemp, readFile, rm, writeFile } from 'node:fs/promises';
import { tmpdir } from 'node:os';
import { join } from 'node:path';
test: split cli tests from source tree (#216) * feat(cli): define full warehouse dialect contract * test(cli): keep dialect edge tests focused * fix(cli): stabilize dialect contract foundation * refactor(connectors): own read-only query preparation * refactor(connectors): resolve dialects through registry * refactor(connectors): keep concrete dialect classes internal * chore(workspace): enforce dialect import boundary * refactor(cli): resolve relationship dialect at scan boundary * refactor(cli): use dialect display parsing for entity details * refactor(cli): use dialect display parsing for warehouse catalog * refactor(cli): use dialect SQL in relationship workflows * test(cli): verify solid dialect scan workflow closure * test: split cli tests from source tree * refactor(cli): standardize BigQuery scope listing * feat(sqlite): implement connector scope listing * test(connectors): cover required table listing * feat(cli): add warehouse driver registry * refactor(setup): route scope discovery through driver registry * refactor(cli): route local query execution through driver registry * refactor(historic-sql): route dialect support through driver registry * refactor(cli): test warehouse connections through driver registry * fix(cli): close driver registry type export gaps * Improve setup daemon diagnostics * refactor(setup): centralize rail-prefixed diagnostics + query-history fallback Extract errorMessage, writePrefixedLines, and flushPrefixedBufferedCommandOutput into clack.ts so the setup wizard, managed daemons, and embedding/agent steps share one rail-formatted writer. setup-databases.ts also adds a "disable query history and retry" option when the schema-context build fails and query history is the likely culprit, surfaced via a new failed-query-history-unavailable status. * fix(cli): carry catalog through the picker so BigQuery/Snowflake/SQL Server scope filters match The setup picker's KtxTableListEntry was a 2-level { schema, name }, so qualifiedTableId always wrote db.name into enabled_tables. When BigQuery, Snowflake, or SQL Server later ran fast ingest, their introspect step filtered the scope set with scopedTableNames(scope, { catalog: projectId|database, db }) — catalog was non-null on the introspect side but null in the scope refs, so every entry was rejected, the live-database adapter staged zero table files, and detect() failed with 'Adapter "live-database" did not recognize fetched source output'. Align the picker boundary with the canonical 3-level KtxTableRef: - Add catalog: string | null to KtxTableListEntry. - BigQuery/Snowflake/SQL Server listTables populate catalog from the resolved projectId / database; Postgres/MySQL/ClickHouse/SQLite set null. - qualifiedTableId emits catalog.schema.name when catalog is non-null (resolveEnabledTables already accepts the 3-part shape) and schemasFromEnabledTables now goes through parseDottedTableEntry so it recovers the schema correctly from both 2-part and 3-part entries. - Export parseDottedTableEntry from enabled-tables.ts (@internal) for picker reuse. Update listTables expectations in all seven connector tests and the setup / picker test fixtures. Add a picker regression test that covers the catalog-bearing round-trip (save + refine). * fix(cli): allow debug telemetry under opt-out env
2026-05-26 08:49:05 +02:00
import { initKtxProject } from '../src/context/project/project.js';
import { type KtxProjectConnectionConfig, parseKtxProjectConfig, serializeKtxProjectConfig } from '../src/context/project/config.js';
import { afterEach, beforeEach, describe, expect, it, vi } from 'vitest';
import {
runKtxSetupSourcesStep,
type KtxSetupSourcesPromptAdapter,
test: split cli tests from source tree (#216) * feat(cli): define full warehouse dialect contract * test(cli): keep dialect edge tests focused * fix(cli): stabilize dialect contract foundation * refactor(connectors): own read-only query preparation * refactor(connectors): resolve dialects through registry * refactor(connectors): keep concrete dialect classes internal * chore(workspace): enforce dialect import boundary * refactor(cli): resolve relationship dialect at scan boundary * refactor(cli): use dialect display parsing for entity details * refactor(cli): use dialect display parsing for warehouse catalog * refactor(cli): use dialect SQL in relationship workflows * test(cli): verify solid dialect scan workflow closure * test: split cli tests from source tree * refactor(cli): standardize BigQuery scope listing * feat(sqlite): implement connector scope listing * test(connectors): cover required table listing * feat(cli): add warehouse driver registry * refactor(setup): route scope discovery through driver registry * refactor(cli): route local query execution through driver registry * refactor(historic-sql): route dialect support through driver registry * refactor(cli): test warehouse connections through driver registry * fix(cli): close driver registry type export gaps * Improve setup daemon diagnostics * refactor(setup): centralize rail-prefixed diagnostics + query-history fallback Extract errorMessage, writePrefixedLines, and flushPrefixedBufferedCommandOutput into clack.ts so the setup wizard, managed daemons, and embedding/agent steps share one rail-formatted writer. setup-databases.ts also adds a "disable query history and retry" option when the schema-context build fails and query history is the likely culprit, surfaced via a new failed-query-history-unavailable status. * fix(cli): carry catalog through the picker so BigQuery/Snowflake/SQL Server scope filters match The setup picker's KtxTableListEntry was a 2-level { schema, name }, so qualifiedTableId always wrote db.name into enabled_tables. When BigQuery, Snowflake, or SQL Server later ran fast ingest, their introspect step filtered the scope set with scopedTableNames(scope, { catalog: projectId|database, db }) — catalog was non-null on the introspect side but null in the scope refs, so every entry was rejected, the live-database adapter staged zero table files, and detect() failed with 'Adapter "live-database" did not recognize fetched source output'. Align the picker boundary with the canonical 3-level KtxTableRef: - Add catalog: string | null to KtxTableListEntry. - BigQuery/Snowflake/SQL Server listTables populate catalog from the resolved projectId / database; Postgres/MySQL/ClickHouse/SQLite set null. - qualifiedTableId emits catalog.schema.name when catalog is non-null (resolveEnabledTables already accepts the 3-part shape) and schemasFromEnabledTables now goes through parseDottedTableEntry so it recovers the schema correctly from both 2-part and 3-part entries. - Export parseDottedTableEntry from enabled-tables.ts (@internal) for picker reuse. Update listTables expectations in all seven connector tests and the setup / picker test fixtures. Add a picker regression test that covers the catalog-bearing round-trip (save + refine). * fix(cli): allow debug telemetry under opt-out env
2026-05-26 08:49:05 +02:00
} from '../src/setup-sources.js';
const notionMocks = vi.hoisted(() => ({
tokens: [] as string[],
retrieveBotUser: vi.fn(async () => ({ name: 'Docs Bot' })),
retrievePage: vi.fn(async () => ({ id: 'page-1' })),
}));
test: split cli tests from source tree (#216) * feat(cli): define full warehouse dialect contract * test(cli): keep dialect edge tests focused * fix(cli): stabilize dialect contract foundation * refactor(connectors): own read-only query preparation * refactor(connectors): resolve dialects through registry * refactor(connectors): keep concrete dialect classes internal * chore(workspace): enforce dialect import boundary * refactor(cli): resolve relationship dialect at scan boundary * refactor(cli): use dialect display parsing for entity details * refactor(cli): use dialect display parsing for warehouse catalog * refactor(cli): use dialect SQL in relationship workflows * test(cli): verify solid dialect scan workflow closure * test: split cli tests from source tree * refactor(cli): standardize BigQuery scope listing * feat(sqlite): implement connector scope listing * test(connectors): cover required table listing * feat(cli): add warehouse driver registry * refactor(setup): route scope discovery through driver registry * refactor(cli): route local query execution through driver registry * refactor(historic-sql): route dialect support through driver registry * refactor(cli): test warehouse connections through driver registry * fix(cli): close driver registry type export gaps * Improve setup daemon diagnostics * refactor(setup): centralize rail-prefixed diagnostics + query-history fallback Extract errorMessage, writePrefixedLines, and flushPrefixedBufferedCommandOutput into clack.ts so the setup wizard, managed daemons, and embedding/agent steps share one rail-formatted writer. setup-databases.ts also adds a "disable query history and retry" option when the schema-context build fails and query history is the likely culprit, surfaced via a new failed-query-history-unavailable status. * fix(cli): carry catalog through the picker so BigQuery/Snowflake/SQL Server scope filters match The setup picker's KtxTableListEntry was a 2-level { schema, name }, so qualifiedTableId always wrote db.name into enabled_tables. When BigQuery, Snowflake, or SQL Server later ran fast ingest, their introspect step filtered the scope set with scopedTableNames(scope, { catalog: projectId|database, db }) — catalog was non-null on the introspect side but null in the scope refs, so every entry was rejected, the live-database adapter staged zero table files, and detect() failed with 'Adapter "live-database" did not recognize fetched source output'. Align the picker boundary with the canonical 3-level KtxTableRef: - Add catalog: string | null to KtxTableListEntry. - BigQuery/Snowflake/SQL Server listTables populate catalog from the resolved projectId / database; Postgres/MySQL/ClickHouse/SQLite set null. - qualifiedTableId emits catalog.schema.name when catalog is non-null (resolveEnabledTables already accepts the 3-part shape) and schemasFromEnabledTables now goes through parseDottedTableEntry so it recovers the schema correctly from both 2-part and 3-part entries. - Export parseDottedTableEntry from enabled-tables.ts (@internal) for picker reuse. Update listTables expectations in all seven connector tests and the setup / picker test fixtures. Add a picker regression test that covers the catalog-bearing round-trip (save + refine). * fix(cli): allow debug telemetry under opt-out env
2026-05-26 08:49:05 +02:00
vi.mock('../src/context/ingest/adapters/notion/notion-client.js', async (importOriginal) => {
const actual = await importOriginal<typeof import('../src/context/ingest/adapters/notion/notion-client.js')>();
return {
...actual,
NotionClient: vi.fn().mockImplementation(function NotionClient(token: string) {
notionMocks.tokens.push(token);
return {
retrieveBotUser: notionMocks.retrieveBotUser,
retrievePage: notionMocks.retrievePage,
};
}),
};
});
function makeIo() {
let stdout = '';
let stderr = '';
return {
io: {
stdout: {
isTTY: true,
write: (chunk: string) => {
stdout += chunk;
},
},
stderr: {
write: (chunk: string) => {
stderr += chunk;
},
},
},
stdout: () => stdout,
stderr: () => stderr,
};
}
function prompts(values: { multiselect?: string[][]; select?: string[] }): KtxSetupSourcesPromptAdapter {
const multiselectValues = [...(values.multiselect ?? [])];
const selectValues = [...(values.select ?? [])];
return {
multiselect: vi.fn(async () => multiselectValues.shift() ?? []),
select: vi.fn(async () => selectValues.shift() ?? 'back'),
autocomplete: vi.fn(async () => selectValues.shift() ?? 'back'),
text: vi.fn(async () => ''),
password: vi.fn(async () => undefined),
cancel: vi.fn(),
log: vi.fn(),
};
}
describe('setup sources Notion validation', () => {
let tempDir: string;
let projectDir: string;
beforeEach(async () => {
notionMocks.tokens.length = 0;
notionMocks.retrieveBotUser.mockClear();
notionMocks.retrievePage.mockClear();
tempDir = await mkdtemp(join(tmpdir(), 'ktx-setup-sources-notion-'));
projectDir = join(tempDir, 'project');
await initKtxProject({ projectDir });
});
afterEach(async () => {
await rm(tempDir, { recursive: true, force: true });
});
async function readConfig() {
return parseKtxProjectConfig(await readFile(join(projectDir, 'ktx.yaml'), 'utf-8'));
}
async function writeConfigConnection(connectionId: string, connection: KtxProjectConnectionConfig) {
const config = await readConfig();
await writeFile(
join(projectDir, 'ktx.yaml'),
serializeKtxProjectConfig({
...config,
connections: {
...config.connections,
warehouse: { driver: 'postgres', url: 'env:DATABASE_URL' },
[connectionId]: connection,
},
setup: {
...config.setup,
database_connection_ids: ['warehouse'],
},
}),
'utf-8',
);
}
it('validates an existing Notion source that uses an inline auth token', async () => {
await writeConfigConnection('notion', {
driver: 'notion',
auth_token: 'ntn_inline_token',
crawl_mode: 'all_accessible',
});
const io = makeIo();
await expect(
runKtxSetupSourcesStep(
{ projectDir, inputMode: 'auto', runInitialSourceIngest: false, skipSources: false },
io.io,
{
prompts: prompts({
multiselect: [['notion']],
select: ['existing:notion'],
}),
},
),
).resolves.toEqual({ status: 'ready', projectDir, connectionIds: ['notion'] });
expect(notionMocks.tokens).toEqual(['ntn_inline_token']);
expect(notionMocks.retrieveBotUser).toHaveBeenCalledOnce();
expect(io.stderr()).toBe('');
});
});