Merge main into gatekeeper/fix-4284-1

nodejs/__test__/materialized_view.test.ts

@@ -52,9 +52,19 @@ describe("materialized views", () => {
       "SELECT * FROM people",
     );
 
+    for (const [format, fn] of [
+      [3, "vector_duplicate_pairs"],
+      [4, "vector_dedup"],
+    ]) {
+      const native = `SELECT * FROM ${fn}('images', 3, 'phash', 4)`;
+      expect(read(JSON.stringify({ format, query: native })).query).toBe(
+        native,
+      );
+    }
+
     // A newer writer's layout is reported, never guessed at.
     for (const newer of [
-      `{"format":3,"query":${JSON.stringify(query)}}`,
+      `{"format":5,"query":${JSON.stringify(query)}}`,
       '{"kind":"select_v3","source_table":"people"}',
     ]) {
       expect(() => read(newer)).toThrow(/cannot refresh/);

nodejs/__test__/remote.test.ts

@@ -85,6 +85,69 @@ async function withMockDatabase(
 }
 
 describe("remote connection", () => {
+  it("rejects the external blob opt-in without blocking regular adds", async () => {
+    let insertRequests = 0;
+    const describeRequests: string[] = [];
+
+    await withMockDatabase(
+      (req, res) => {
+        const requestPath = req.url ?? "";
+        if (requestPath.endsWith("/describe/")) {
+          describeRequests.push(requestPath);
+          res.writeHead(200, { "Content-Type": "application/json" }).end(
+            JSON.stringify({
+              name: "items",
+              version: 1,
+              schema: {
+                fields: [
+                  {
+                    name: "id",
+                    type: { type: "int64" },
+                    nullable: true,
+                  },
+                ],
+              },
+            }),
+          );
+          return;
+        }
+        if (requestPath.endsWith("/insert/")) {
+          insertRequests++;
+          req.resume();
+          req.on("end", () => {
+            res
+              .writeHead(200, { "Content-Type": "application/json" })
+              .end(JSON.stringify({ version: insertRequests + 1 }));
+          });
+          return;
+        }
+        res.writeHead(404).end();
+      },
+      async (db) => {
+        const table = await db.openTable("items");
+
+        await expect(
+          table.add([{ id: 1n }], {
+            allowExternalBlobOutsideBases: true,
+          }),
+        ).rejects.toThrow("only supported on local tables");
+        expect(insertRequests).toBe(0);
+
+        await expect(table.add([{ id: 2n }])).resolves.toMatchObject({
+          version: 2,
+        });
+        await expect(
+          table.add([{ id: 3n }], {
+            allowExternalBlobOutsideBases: false,
+          }),
+        ).resolves.toMatchObject({ version: 3 });
+      },
+    );
+
+    expect(describeRequests.length).toBeGreaterThan(0);
+    expect(insertRequests).toBe(2);
+  });
+
   it("lists materialized views through the namespace route", async () => {
     await withMockDatabase(
       (req, res) => {

nodejs/__test__/table.test.ts

@@ -2,6 +2,7 @@
 // SPDX-FileCopyrightText: Copyright The LanceDB Authors
 
 import * as fs from "fs";
+import { pathToFileURL } from "node:url";
 import * as path from "path";
 import * as tmp from "tmp";
 
@@ -416,6 +417,26 @@ describe.each([arrow15, arrow16, arrow17, arrow18])(
       expect(await table.countRows("id == 10")).toBe(1);
     });
 
+    it("should let me update float values to NaN and Infinity", async () => {
+      const db = await connect(tmpDir.name);
+      const floats = await db.createTable("floats", [
+        { id: 1, price: 1.5 },
+        { id: 2, price: 2.5 },
+        { id: 3, price: 3.5 },
+        { id: 4, price: 4.5 },
+      ]);
+      await floats.update({ values: { price: NaN }, where: "id = 1" });
+      await floats.update({ values: { price: Infinity }, where: "id = 2" });
+      await floats.update({ values: { price: -Infinity }, where: "id = 3" });
+
+      const rows = await floats.query().toArray();
+      const price = (id: number) => rows.find((row) => row.id === id).price;
+      expect(price(1)).toBeNaN();
+      expect(price(2)).toBe(Infinity);
+      expect(price(3)).toBe(-Infinity);
+      expect(price(4)).toBe(4.5);
+    });
+
     // https://github.com/lancedb/lancedb/issues/1293
     test.each([new arrow.Float16(), new arrow.Float32(), new arrow.Float64()])(
       "can create empty table with non default float type: %s",
@@ -2429,6 +2450,118 @@ describe("when dealing with blob columns", () => {
     await expect(table.countRows()).resolves.toBe(0);
   });
 
+  it("requires an explicit opt-in for blob URIs outside registered bases", async () => {
+    const { table, uri } = await openExternalBlobTable();
+
+    await expect(table.add([{ id: 1n, payload: uri }])).rejects.toThrow(
+      "allow_external_blob_outside_bases",
+    );
+    await expect(table.countRows()).resolves.toBe(0);
+
+    await expect(
+      table.add([{ id: 2n, payload: uri }], {
+        allowExternalBlobOutsideBases: false,
+      }),
+    ).rejects.toThrow("allow_external_blob_outside_bases");
+    await expect(table.countRows()).resolves.toBe(0);
+  });
+
+  it.each([
+    ["URI string", (uri: string) => uri],
+    ["URI struct", (uri: string) => ({ uri })],
+  ])(
+    "round-trips an external blob from a %s after reopening",
+    async (_label, blobValue) => {
+      const { db, table, uri, payload } = await openExternalBlobTable();
+
+      const result = await table.add([{ id: 1n, payload: blobValue(uri) }], {
+        allowExternalBlobOutsideBases: true,
+      });
+      expect(result.version).toBeGreaterThan(0);
+      await expect(table.countRows()).resolves.toBe(1);
+
+      table.close();
+      const reopened = await db.openTable("external_blobs");
+      const rows = await reopened.query().withRowId().toArray();
+      expect(rows).toHaveLength(1);
+      expect(rows[0].payload.blob_uri).toBe(uri);
+      const bytes = await reopened.fetchBlobs("payload", [
+        rows[0]._rowid as bigint,
+      ]);
+      expect(bytes[0]).toEqual(payload);
+    },
+  );
+
+  it("applies the external blob opt-in to Arrow table input", async () => {
+    const { table, schema, uri, payload } = await openExternalBlobTable();
+    const input = makeArrowTable([{ id: 1n, payload: uri }], { schema });
+
+    const result = await table.add(input, {
+      allowExternalBlobOutsideBases: true,
+    });
+
+    expect(result.version).toBeGreaterThan(0);
+    const rows = await table.query().withRowId().toArray();
+    expect(rows[0].payload.blob_uri).toBe(uri);
+    const bytes = await table.fetchBlobs("payload", [rows[0]._rowid as bigint]);
+    expect(bytes[0]).toEqual(payload);
+  });
+
+  it("applies the external blob opt-in only to the current add", async () => {
+    const { table, uri } = await openExternalBlobTable();
+
+    await table.add([{ id: 1n, payload: uri }], {
+      allowExternalBlobOutsideBases: true,
+    });
+    await expect(table.countRows()).resolves.toBe(1);
+
+    await expect(table.add([{ id: 2n, payload: uri }])).rejects.toThrow(
+      "allow_external_blob_outside_bases",
+    );
+    await expect(table.countRows()).resolves.toBe(1);
+  });
+
+  it("supports progress and overwrite with the external blob opt-in", async () => {
+    const { table, uri, payload } = await openExternalBlobTable();
+    await table.add([{ id: 1n, payload: Buffer.from("old") }]);
+
+    let resolveFinal!: (progress: import("../lancedb").WriteProgress) => void;
+    let rejectFinal!: (error: Error) => void;
+    const finalProgress = new Promise<import("../lancedb").WriteProgress>(
+      (resolve, reject) => {
+        resolveFinal = resolve;
+        rejectFinal = reject;
+      },
+    );
+    const timeout = setTimeout(
+      () => rejectFinal(new Error("timed out waiting for final progress")),
+      5_000,
+    );
+    try {
+      const result = await table.add([{ id: 2n, payload: uri }], {
+        mode: "overwrite",
+        allowExternalBlobOutsideBases: true,
+        progress: (progress) => {
+          if (progress.done) {
+            resolveFinal(progress);
+          }
+        },
+      });
+      expect(result.version).toBeGreaterThan(0);
+      const progress = await finalProgress;
+      expect(progress.outputRows).toBe(1);
+      expect(progress.totalRows).toBe(1);
+    } finally {
+      clearTimeout(timeout);
+    }
+
+    const rows = await table.query().withRowId().toArray();
+    expect(rows).toHaveLength(1);
+    expect(rows[0].id).toBe(2n);
+    const bytes = await table.fetchBlobs("payload", [rows[0]._rowid as bigint]);
+    expect(bytes[0]).toEqual(payload);
+  });
+
   it("discovers blob columns", async () => {
     const { table } = await openBlobTable();
     expect(await table.blobColumns()).toEqual(["image"]);
@@ -2700,6 +2833,20 @@ describe("when dealing with blob columns", () => {
     const rowIds = [1, 2, 3].map((id) => rowIdById.get(id)!);
     return { table, rowIds, alpha, beta };
   }
+
+  async function openExternalBlobTable() {
+    const db = await connect(path.join(tmpDir.name, "db"));
+    const payload = Buffer.from("external-payload");
+    const payloadPath = path.join(tmpDir.name, "payload.bin");
+    fs.writeFileSync(payloadPath, payload);
+    const uri = pathToFileURL(payloadPath).href;
+    const schema = new Schema([
+      new Field("id", new Int64(), true),
+      blob("payload"),
+    ]);
+    const table = await db.createEmptyTable("external_blobs", schema);
+    return { db, table, schema, uri, payload };
+  }
 });
 
 describe("when dealing with tags", () => {

nodejs/__test__/util.test.ts

@@ -14,6 +14,9 @@ test.each([
   [new ArrayBuffer(8), "X'0000000000000000'"],
   [Buffer.from("hello"), "X'68656c6c6f'"],
   ["Hello 'world'", "'Hello ''world'''"],
+  [NaN, "CAST('NaN' AS DOUBLE)"],
+  [Infinity, "CAST('Infinity' AS DOUBLE)"],
+  [-Infinity, "CAST('-Infinity' AS DOUBLE)"],
 ])("toSQL(%p) === %p", (value, expected) => {
   expect(toSQL(value)).toBe(expected);
 });

nodejs/lancedb/materialized_view.ts

@@ -9,9 +9,10 @@ export const DEFINITION_META_KEY = "mv.definition";
 
 /**
  * The newest stored layout this version reads: `{"format": N, "query": "<SQL>"}`,
- * format 2 being a query with `GROUP BY`.
+ * format 2 being a query with `GROUP BY`, format 3 native pairs and format 4
+ * native dedup results.
  */
-export const DEFINITION_FORMAT = 2;
+export const DEFINITION_FORMAT = 4;
 
 /**
  * The query that defines a materialized view, as stored:

nodejs/lancedb/table.ts

@@ -124,6 +124,17 @@ export interface AddDataOptions {
    * ```
    */
   progress: (progress: WriteProgress) => void;
+
+  /**
+   * Whether blob URIs outside registered external bases may be written.
+   *
+   * Defaults to `false`. This option is supported only for local/native
+   * tables; remote tables return an error when it is enabled. An enabled write
+   * stores the absolute URI reference without registering a base or copying
+   * the external object into the database. The object must remain accessible
+   * when the blob is read later.
+   */
+  allowExternalBlobOutsideBases?: boolean;
 }
 
 export interface UpdateOptions {
@@ -528,6 +539,10 @@ export abstract class Table {
    * duplicates. Null blobs are `null`. Empty blobs are empty buffers.
    * One missing or deleted row ID rejects the entire batch, including on remote
    * tables; no partial results are returned.
+   * Remote servers limit each request to 1024 row IDs and 64 MiB of blob bytes.
+   * The client splits requests automatically and reads an individual larger
+   * blob through the Range route. This method still materializes all bytes in
+   * memory; use {@link Table.fetchBlobFiles} for large values.
    */
   abstract fetchBlobs(
     column: string,
@@ -1095,7 +1110,12 @@ export class LocalTable extends Table {
           }
         }
       : undefined;
-    return await this.inner.add(buffer, mode, progress);
+    return await this.inner.add(
+      buffer,
+      mode,
+      progress,
+      options?.allowExternalBlobOutsideBases,
+    );
   }
 
   async update(

nodejs/lancedb/util.ts

@@ -15,6 +15,14 @@ export function toSQL(value: IntoSql): string {
   if (typeof value === "string") {
     return `'${value.replace(/'/g, "''")}'`;
   } else if (typeof value === "number") {
+    // toString() gives "NaN" / "Infinity", which SQL reads as column names.
+    if (Number.isNaN(value)) {
+      return "CAST('NaN' AS DOUBLE)";
+    } else if (!Number.isFinite(value)) {
+      return value > 0
+        ? "CAST('Infinity' AS DOUBLE)"
+        : "CAST('-Infinity' AS DOUBLE)";
+    }
     return value.toString();
   } else if (typeof value === "boolean") {
     return value ? "TRUE" : "FALSE";

nodejs/src/table.rs

@@ -74,13 +74,14 @@ impl Table {
 
     #[napi(
         catch_unwind,
-        ts_args_type = "buf: Buffer, mode: string, progressCallback?: (progress: WriteProgressInfo) => void"
+        ts_args_type = "buf: Buffer, mode: string, progressCallback?: (progress: WriteProgressInfo) => void, allowExternalBlobOutsideBases?: boolean"
     )]
     pub async fn add(
         &self,
         buf: Buffer,
         mode: String,
         progress_callback: Option<ProgressFn>,
+        allow_external_blob_outside_bases: Option<bool>,
     ) -> napi::Result<AddResult> {
         let batches = ipc_file_to_batches(buf.to_vec())
             .map_err(|e| napi::Error::from_reason(format!("Failed to read IPC file: {}", e)))?;
@@ -105,6 +106,9 @@ impl Table {
             return Err(napi::Error::from_reason(format!("Invalid mode: {}", mode)));
         };
 
+        op = op
+            .allow_external_blob_outside_bases(allow_external_blob_outside_bases.unwrap_or(false));
+
         if let Some(tsfn) = progress_callback {
             op = op.progress(move |p| {
                 // NonBlocking: dispatch onto the JS event loop without