feat: add_bases registers extra table storage prefixes

TableBase plus add_bases on native, memory, namespace, and Cloud
clients.

nodejs/__test__/remote.test.ts

@@ -1001,4 +1001,49 @@ describe("remote connection jobs surface", () => {
       },
     );
   });
+
+  it("addBases posts the bases array", async () => {
+    const postedBodies: unknown[] = [];
+    await withMockDatabase(
+      (req, res) => {
+        const path = req.url ?? "";
+        if (path.endsWith("/describe/")) {
+          res.writeHead(200, { "Content-Type": "application/json" }).end(
+            JSON.stringify({
+              name: "photos",
+              version: 1,
+              schema: { fields: [] },
+            }),
+          );
+          return;
+        }
+        if (path.endsWith("/bases/")) {
+          const chunks: Buffer[] = [];
+          req.on("data", (chunk) => chunks.push(chunk));
+          req.on("end", () => {
+            postedBodies.push(JSON.parse(Buffer.concat(chunks).toString()));
+            res
+              .writeHead(200, { "Content-Type": "application/json" })
+              .end(JSON.stringify({ version: 2 }));
+          });
+          return;
+        }
+        res.writeHead(404).end();
+      },
+      async (db) => {
+        const table = await db.openTable("photos");
+        await table.addBases({ path: "s3://bucket/media/" });
+      },
+    );
+    expect(postedBodies).toEqual([
+      {
+        bases: [
+          {
+            path: "s3://bucket/media/",
+            isDatasetRoot: false,
+          },
+        ],
+      },
+    ]);
+  });
 });

nodejs/__test__/table.test.ts

@@ -4,6 +4,7 @@
 import * as fs from "fs";
 import * as path from "path";
 import * as tmp from "tmp";
+import { pathToFileURL } from "url";
 
 import * as arrow15 from "apache-arrow-15";
 import * as arrow16 from "apache-arrow-16";
@@ -3404,3 +3405,22 @@ describe("computed columns", () => {
     expect(rows.map((r) => r.doubled).sort()).toEqual([10, 2]);
   });
 });
+
+describe("table bases", () => {
+  let tmpDir: tmp.DirResult;
+  beforeEach(() => {
+    tmpDir = tmp.dirSync({ unsafeCleanup: true });
+  });
+  afterEach(() => tmpDir.removeCallback());
+
+  it("addBases accepts a file uri", async () => {
+    const conn = await connect(tmpDir.name);
+    const table = await conn.createEmptyTable(
+      "photos",
+      new arrow.Schema([new arrow.Field("id", new arrow.Int64(), false)]),
+    );
+    const media = path.join(tmpDir.name, "media");
+    fs.mkdirSync(media);
+    await table.addBases(pathToFileURL(media).toString());
+  });
+});

nodejs/lancedb/index.ts

@@ -130,6 +130,7 @@ export {
 
 export {
   Table,
+  TableBase,
   Branches,
   BranchColumnSummary,
   BranchColumnChange,

nodejs/lancedb/table.ts

@@ -78,6 +78,25 @@ export interface WriteProgress {
   done: boolean;
 }
 
+/**
+ * An extra storage prefix registered on a table.
+ *
+ * `path` is an object-store URI. `name` is an optional alias. `isDatasetRoot`
+ * is true when `path` points to a Lance dataset root. When false, `path`
+ * points directly to the directory containing the referenced files.
+ */
+export interface TableBase {
+  /** Object store URI such as `s3://bucket/media/`. */
+  path: string;
+  /** Optional alias. */
+  name?: string;
+  /**
+   * True when `path` is a Lance dataset root. When false, `path` is the
+   * directory containing the referenced files.
+   */
+  isDatasetRoot?: boolean;
+}
+
 /**
  * Options for adding data to a table.
  */
@@ -563,6 +582,15 @@ export abstract class Table {
       | { computed: AddColumnsSql[] },
   ): Promise<AddColumnsResult>;
 
+  /**
+   * Register additional storage bases for this table.
+   *
+   * A URI string is a non-root base with no alias.
+   */
+  abstract addBases(
+    bases: string | TableBase | Array<string | TableBase>,
+  ): Promise<void>;
+
   /**
    * Fill the rows of a computed column that hold no value yet.
    *
@@ -1196,6 +1224,12 @@ export class LocalTable extends Table {
     throw new Error("Invalid input type for addColumns");
   }
 
+  async addBases(
+    bases: string | TableBase | Array<string | TableBase>,
+  ): Promise<void> {
+    await this.inner.addBases(normalizeBases(bases));
+  }
+
   async refreshColumn(column: string): Promise<RefreshColumnResult> {
     return await this.inner.refreshColumn(column);
   }
@@ -1396,6 +1430,21 @@ export class LocalTable extends Table {
   }
 }
 
+function normalizeBases(
+  bases: string | TableBase | Array<string | TableBase>,
+): TableBase[] {
+  const baseInputs = Array.isArray(bases) ? bases : [bases];
+  return baseInputs.map((base) =>
+    typeof base === "string"
+      ? { path: base, isDatasetRoot: false }
+      : {
+          path: base.path,
+          name: base.name,
+          isDatasetRoot: base.isDatasetRoot ?? false,
+        },
+  );
+}
+
 /**
  *  A definition of a column alteration. The alteration changes the column at
  * `path` to have the new name `name`, to be nullable if `nullable` is true,

nodejs/src/table.rs

@@ -10,6 +10,7 @@ use lancedb::table::{
     AddDataMode, ColumnAlteration as LanceColumnAlteration, Duration,
     FieldMetadataUpdate as LanceFieldMetadataUpdate, FtsToken as LanceDbFtsToken,
     NewColumnTransform, OptimizeAction, OptimizeOptions, Ref, Table as LanceDbTable,
+    TableBase as LanceTableBase,
 };
 use napi::bindgen_prelude::*;
 use napi::threadsafe_function::{ThreadsafeFunction, ThreadsafeFunctionCallMode};
@@ -446,6 +447,18 @@ impl Table {
         Ok(res.into())
     }
 
+    #[napi(catch_unwind)]
+    pub async fn add_bases(&self, bases: Vec<TableBase>) -> napi::Result<()> {
+        self.inner_ref()?
+            .add_bases(bases.into_iter().map(|base| LanceTableBase {
+                path: base.path,
+                name: base.name,
+                is_dataset_root: base.is_dataset_root,
+            }))
+            .await
+            .default_error()
+    }
+
     #[napi(catch_unwind)]
     pub async fn drop_columns(&self, columns: Vec<String>) -> napi::Result<DropColumnsResult> {
         let col_refs = columns.iter().map(String::as_str).collect::<Vec<_>>();
@@ -700,6 +713,18 @@ impl Table {
     }
 }
 
+#[napi(object)]
+/// An extra storage prefix registered on a table.
+pub struct TableBase {
+    /// Object store URI such as `s3://bucket/media/`.
+    pub path: String,
+    /// Optional alias.
+    pub name: Option<String>,
+    /// True when `path` is a Lance dataset root. When false, `path` is the
+    /// directory containing the referenced files.
+    pub is_dataset_root: bool,
+}
+
 #[napi(object)]
 /// A description of an index currently configured on a column
 pub struct IndexConfig {