From 83f2848d479befe4090aa980bef3e5fc50feb55a Mon Sep 17 00:00:00 2001
From: Thuc Pham <51660321+thucpn@users.noreply.github.com>
Date: Wed, 9 Oct 2024 12:34:46 +0700
Subject: [PATCH] feat: add test split nodes with UUID (#1315)
---
.../tests/node-parser/text-splitter.test.ts | 23 +++++++++++++++++++
1 file changed, 23 insertions(+)
diff --git a/packages/core/tests/node-parser/text-splitter.test.ts b/packages/core/tests/node-parser/text-splitter.test.ts
index 1ccf9a93a..531896492 100644
--- a/packages/core/tests/node-parser/text-splitter.test.ts
+++ b/packages/core/tests/node-parser/text-splitter.test.ts
@@ -2,6 +2,7 @@ import {
SentenceSplitter,
splitBySentenceTokenizer,
} from "@llamaindex/core/node-parser";
+import { Document } from "@llamaindex/core/schema";
import { describe, expect, test } from "vitest";
describe("sentence splitter", () => {
@@ -115,4 +116,26 @@ describe("sentence splitter", () => {
const split = splitBySentenceTokenizer();
expect(split(text)).toEqual([text]);
});
+
+ test("split nodes with UUID IDs and correct relationships", () => {
+ const UUID_REGEX =
+ /^[0-9a-f]{8}-[0-9a-f]{4}-4[0-9a-f]{3}-[89ab][0-9a-f]{3}-[0-9a-f]{12}$/i;
+ const sentenceSplitter = new SentenceSplitter();
+ const docId = "test-doc-id";
+ const doc = new Document({
+ id_: docId,
+ text: "This is a test sentence. This is another test sentence.",
+ });
+ const nodes = sentenceSplitter.getNodesFromDocuments([doc]);
+ nodes.forEach((node) => {
+ // test node id should match uuid regex
+ expect(node.id_).toMatch(UUID_REGEX);
+
+ // test source reference to the doc ID
+ const source = node.relationships?.SOURCE;
+ expect(source).toBeDefined();
+ expect(source).toHaveProperty("nodeId");
+ expect((source as { nodeId: string }).nodeId).toEqual(docId);
+ });
+ });
});
--
GitLab