feat: refine metadata catalog workflows

This commit is contained in:
Codex
2026-09-02 11:38:47 +02:00
parent 076c9742c5
commit 4531746038
48 changed files with 1345 additions and 493 deletions
@@ -1,6 +1,9 @@
import { expect, test, vi } from "vitest";
import { mkdtempSync, rmSync, writeFileSync } from "node:fs";
import { tmpdir } from "node:os";
import { join } from "node:path";
import {
PostgresDescriptionSourceSampler,
ConcreteDescriptionSourceSampler,
type DescriptionSourceSamplingTarget,
} from "../src/catalog/description-source-sampler.js";
import type {
@@ -8,6 +11,8 @@ import type {
CatalogPostgresAccess,
} from "../src/catalog/postgres-access.js";
import type { WorkspaceDatabase } from "../src/catalog/types.js";
import type { WorkspaceSecretStore } from "../src/workspaces/secret-store.js";
import { CATALOG_SECRET_IDS } from "../src/catalog/secrets.js";
const database: WorkspaceDatabase = {
id: "11111111-1111-4111-8111-111111111111",
@@ -51,7 +56,7 @@ test("samples at most five source rows and five distinct non-null examples in a
const access: CatalogPostgresAccess = {
connect: vi.fn(async () => ({ query, end }) as CatalogDatabaseClient),
};
const sampler = new PostgresDescriptionSourceSampler(access);
const sampler = new ConcreteDescriptionSourceSampler(access);
const controller = new AbortController();
const samples = await sampler.sample(database, [target], controller.signal);
@@ -92,13 +97,71 @@ test("samples at most five source rows and five distinct non-null examples in a
expect(end).toHaveBeenCalledOnce();
});
test("samples source rows through the configured REST run_query binding", async () => {
const root = mkdtempSync(join(tmpdir(), "tht-source-rest-"));
const credentialFile = join(root, "api-key");
writeFileSync(credentialFile, "test-api-key\n", { mode: 0o600 });
const release = vi.fn();
const secretStore = {
materialize: vi.fn(() => ({
files: new Map([[CATALOG_SECRET_IDS.apiKey, credentialFile]]),
release,
})),
} as unknown as WorkspaceSecretStore;
const fetchMock = vi.fn(async () => new Response(JSON.stringify([
{ 'status"code': "active", ward: null },
{ 'status"code': "pending", ward: "A" },
]), { status: 200, headers: { "content-type": "application/json" } }));
vi.stubGlobal("fetch", fetchMock);
const access: CatalogPostgresAccess = {
connect: vi.fn(async () => { throw new Error("PostgreSQL access must not be used"); }),
};
const sampler = new ConcreteDescriptionSourceSampler(access, secretStore);
const restDatabase: WorkspaceDatabase = {
...database,
binding: {
transport: "rest_api",
baseUrl: "https://dwh.example.test/root/",
restPath: "/health",
restAuth: "x-api-key",
},
};
try {
await expect(sampler.sample(restDatabase, [target], new AbortController().signal)).resolves.toEqual([{
targetId: target.targetId,
tableName: target.tableName,
rows: [
{ fields: [{ name: 'status"code', value: "active" }, { name: "ward", value: null }] },
{ fields: [{ name: 'status"code', value: "pending" }, { name: "ward", value: "A" }] },
],
representativeValues: [
{ column: 'status"code', values: ["active", "pending"] },
{ column: "ward", values: ["A"] },
],
}]);
expect(access.connect).not.toHaveBeenCalled();
expect(fetchMock).toHaveBeenCalledWith("https://dwh.example.test/root/rpc/run_query", expect.objectContaining({
method: "POST",
headers: { "content-type": "application/json", "x-api-key": "test-api-key" },
body: JSON.stringify({
query_text: 'SELECT LEFT(("status""code")::text, 256) AS "status""code", LEFT(("ward")::text, 256) AS "ward" FROM "clinical""data"."patient""facts" LIMIT 5',
}),
}));
expect(release).toHaveBeenCalledOnce();
} finally {
vi.unstubAllGlobals();
rmSync(root, { recursive: true, force: true });
}
});
test("does not issue a SELECT when a protected target has no source columns", async () => {
const query = vi.fn(async () => ({ rows: [] }));
const end = vi.fn(async () => undefined);
const access: CatalogPostgresAccess = {
connect: vi.fn(async () => ({ query, end }) as CatalogDatabaseClient),
};
const sampler = new PostgresDescriptionSourceSampler(access);
const sampler = new ConcreteDescriptionSourceSampler(access);
const samples = await sampler.sample(database, [{
targetId: target.targetId,
@@ -129,7 +192,7 @@ test("rolls back and closes the source connection when sampling fails", async ()
const access: CatalogPostgresAccess = {
connect: vi.fn(async () => ({ query, end }) as CatalogDatabaseClient),
};
const sampler = new PostgresDescriptionSourceSampler(access);
const sampler = new ConcreteDescriptionSourceSampler(access);
const controller = new AbortController();
await expect(sampler.sample(database, [target], controller.signal)).rejects.toThrow();