diff --git a/nodejs/__test__/arrow.test.ts b/nodejs/__test__/arrow.test.ts index cb56cb5ae..83b4fae46 100644 --- a/nodejs/__test__/arrow.test.ts +++ b/nodejs/__test__/arrow.test.ts @@ -1,5 +1,7 @@ // SPDX-License-Identifier: Apache-2.0 // SPDX-FileCopyrightText: Copyright The LanceDB Authors +import * as fs from "node:fs"; +import * as vm from "node:vm"; import * as arrow15 from "apache-arrow-15"; import * as arrow16 from "apache-arrow-16"; import * as arrow17 from "apache-arrow-17"; @@ -40,6 +42,41 @@ function sampleRecords(): Array> { ]; } +it("serializes an Arrow Table created in another JavaScript realm", async () => { + const context = vm.createContext({ + TextDecoder, + TextEncoder, + console, + setTimeout, + clearTimeout, + }); + vm.runInContext( + fs.readFileSync( + require.resolve("apache-arrow-15/Arrow.es2015.min"), + "utf8", + ), + context, + ); + const foreignTable: unknown = vm.runInContext( + "Arrow.tableFromArrays({ id: new Int32Array([1, 2, 3]), text: ['foo', 'bar', 'baz'] })", + context, + ); + + const foreignMetadata = ( + foreignTable as { schema: { metadata: Map } } + ).schema.metadata; + expect(foreignMetadata).not.toBeInstanceOf(Map); + + const buf = await fromDataToBuffer( + foreignTable as Parameters[0], + ); + const actual = currentTableFromIPC(buf); + + expect(actual.numRows).toBe(3); + expect(actual.getChild("id")?.toJSON()).toEqual([1, 2, 3]); + expect(actual.getChild("text")?.toJSON()).toEqual(["foo", "bar", "baz"]); +}); + it("preserves field metadata from a provided schema", async function () { const jsonMetadata = new Map([["ARROW:extension:name", "lance.json"]]); const schema = new CurrentSchema([ diff --git a/nodejs/lancedb/arrow.ts b/nodejs/lancedb/arrow.ts index b52ab50ef..1b6b98cc9 100644 --- a/nodejs/lancedb/arrow.ts +++ b/nodejs/lancedb/arrow.ts @@ -72,8 +72,7 @@ export type FieldLike = }; export type DataLike = - // biome-ignore lint/suspicious/noExplicitAny: - | import("apache-arrow").Data> + | import("apache-arrow").Data | { // biome-ignore lint/suspicious/noExplicitAny: type: any; @@ -82,6 +81,7 @@ export type DataLike = stride: number; nullable: boolean; children: DataLike[]; + dictionary?: { data: readonly DataLike[] }; get nullCount(): number; // biome-ignore lint/suspicious/noExplicitAny: values: Buffers[BufferType.DATA]; diff --git a/nodejs/lancedb/sanitize.ts b/nodejs/lancedb/sanitize.ts index 8fb2f1a0a..454c82247 100644 --- a/nodejs/lancedb/sanitize.ts +++ b/nodejs/lancedb/sanitize.ts @@ -94,17 +94,24 @@ export function sanitizeMetadata( if (metadataLike === undefined || metadataLike === null) { return undefined; } - if (!(metadataLike instanceof Map)) { + + let entries: IterableIterator<[unknown, unknown]>; + try { + entries = Map.prototype.entries.call(metadataLike); + } catch { throw Error("Expected metadata, if present, to be a Map"); } - for (const item of metadataLike) { - if (typeof item[0] !== "string" || typeof item[1] !== "string") { + + const metadata = new Map(); + for (const [key, value] of entries) { + if (typeof key !== "string" || typeof value !== "string") { throw Error( "Expected metadata, if present, to be a Map but it had non-string keys or values", ); } + metadata.set(key, value); } - return metadataLike as Map; + return metadata; } export function sanitizeInt(typeLike: object) {