From 302b21aa94317dc74cbe6601212242f54e592d8a Mon Sep 17 00:00:00 2001
From: "lancedb-gatefixer[bot]"
 <313497061+lancedb-gatefixer[bot]@users.noreply.github.com>
Date: Wed, 26 Aug 2026 06:42:29 +0800
Subject: [PATCH] test(node): cover nested PDF metadata queries (#3827)

## Summary

- add an end-to-end Node regression matching LangChain PDFLoader
metadata
- verify create/query round trips rich nested `loc` and `pdf.info`
fields against the currently configured Apache Arrow peer

## Root cause

LanceDB v0.14 delegated nested object inference to Apache Arrow. Nested
strings were dictionary-encoded with colliding dictionary IDs, so
serializing query results as an IPC file failed with a
dictionary-replacement error. Current `main` recursively infers nested
fields and avoids those invalid dictionaries, but the reported LangChain
path had no end-to-end regression coverage.

## Validation

- `pnpm build`
- `pnpm lint`
- `pnpm run docs`
- `pnpm test --runInBand` (678 passed, 5 skipped)

Fixes #1963

<!-- lance-gatekeeper-fix:v1 agent=bf8d489db7db2e17678b143f9f0a36d2
generation=1 -->

---------

Co-authored-by: Gatefixer <313497061+lancedb-gatefixer[bot]@users.noreply.github.com>
Co-authored-by: Xuanwo <github@xuanwo.io>
---
 nodejs/__test__/table.test.ts | 50 +++++++++++++++++++++++++++++++++++
 1 file changed, 50 insertions(+)

diff --git a/nodejs/__test__/table.test.ts b/nodejs/__test__/table.test.ts
index 0aee5caf0..aaa144f16 100644
--- a/nodejs/__test__/table.test.ts
+++ b/nodejs/__test__/table.test.ts
@@ -685,6 +685,56 @@ describe.each([arrow15, arrow16, arrow17, arrow18])(
   },
 );
 
+// https://github.com/lancedb/lancedb/issues/1963
+it("should query documents with LangChain PDF metadata", async () => {
+  const tmpDir = tmp.dirSync({ unsafeCleanup: true });
+  try {
+    const db = await connect(tmpDir.name);
+    const documents = [
+      {
+        text: "first page",
+        vector: [1, 0],
+        source: "first.pdf",
+        loc: { pageNumber: 1, lines: { from: 1, to: 12 } },
+        pdf: {
+          version: "1.10.100",
+          info: {
+            format: "PDF 1.7",
+            producer: "pdf.js",
+            creator: "Writer",
+          },
+          totalPages: 2,
+        },
+      },
+      {
+        text: "second page",
+        vector: [0, 1],
+        source: "second.pdf",
+        loc: { pageNumber: 2, lines: { from: 13, to: 24 } },
+        pdf: {
+          version: "1.10.100",
+          info: {
+            format: "PDF 1.7",
+            producer: "pdf.js",
+            creator: "Writer",
+          },
+          totalPages: 2,
+        },
+      },
+    ];
+    const documentsTable = await db.createTable("documents", documents);
+
+    const results = await documentsTable.query().toArray();
+
+    expect(results).toHaveLength(2);
+    expect(results[0].source).toBe("first.pdf");
+    expect(results[0].pdf.info.producer).toBe("pdf.js");
+    expect(results[1].loc.pageNumber).toBe(2);
+  } finally {
+    tmpDir.removeCallback();
+  }
+});
+
 describe("merge insert", () => {
   let tmpDir: tmp.DirResult;
   let table: Table;