feat: add table stats API (#2363)

* Add a new "table stats" API to expose basic table and fragment
statistics with local and remote table implementations

### Questions
* This is using `calculate_data_stats` to determine total bytes in the
table. This seems like a potentially expensive operation - are there any
concerns about performance for large datasets?

### Notes
* bytes_on_disk seems to be stored at the column level but there does
not seem to be a way to easily calculate total bytes per fragment. This
may need to be added in lance before we can support fragment size
(bytes) statistics.

<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->

## Summary by CodeRabbit

- **New Features**
- Added a method to retrieve comprehensive table statistics, including
total rows, index counts, storage size, and detailed fragment size
metrics such as minimum, maximum, mean, and percentiles.
- Enabled fetching of table statistics from remote sources through
asynchronous requests.
- Extended table interfaces across Python, Rust, and Node.js to support
synchronous and asynchronous retrieval of table statistics.
- **Tests**
- Introduced tests to verify the accuracy of the new table statistics
feature for both populated and empty tables.
<!-- end of auto-generated comment: release notes by coderabbit.ai -->

nodejs/__test__/table.test.ts

@@ -71,6 +71,29 @@ describe.each([arrow15, arrow16, arrow17, arrow18])(
       await expect(table.countRows()).resolves.toBe(3);
     });
 
+    it("should show table stats", async () => {
+      await table.add([{ id: 1 }, { id: 2 }]);
+      await table.add([{ id: 1 }]);
+      await expect(table.stats()).resolves.toEqual({
+        fragmentStats: {
+          lengths: {
+            max: 2,
+            mean: 1,
+            min: 1,
+            p25: 1,
+            p50: 2,
+            p75: 2,
+            p99: 2,
+          },
+          numFragments: 2,
+          numSmallFragments: 2,
+        },
+        numIndices: 0,
+        numRows: 3,
+        totalBytes: 24,
+      });
+    });
+
     it("should overwrite data if asked", async () => {
       await table.add([{ id: 1 }, { id: 2 }]);
       await table.add([{ id: 1 }], { mode: "overwrite" });

nodejs/lancedb/index.ts

@@ -23,6 +23,9 @@ export {
   OptimizeStats,
   CompactionStats,
   RemovalStats,
+  TableStatistics,
+  FragmentStatistics,
+  FragmentSummaryStats,
   Tags,
   TagContents,
 } from "./native.js";

nodejs/lancedb/table.ts

@@ -20,6 +20,7 @@ import {
   IndexConfig,
   IndexStatistics,
   OptimizeStats,
+  TableStatistics,
   Tags,
   Table as _NativeTable,
 } from "./native";
@@ -482,6 +483,13 @@ export abstract class Table {
    * Use {@link Table.listIndices} to find the names of the indices.
    */
   abstract indexStats(name: string): Promise<IndexStatistics | undefined>;
+
+  /** Returns table and fragment statistics
+   *
+   * @returns {TableStatistics} The table and fragment statistics
+   *
+   */
+  abstract stats(): Promise<TableStatistics>;
 }
 
 export class LocalTable extends Table {
@@ -775,6 +783,11 @@ export class LocalTable extends Table {
     }
     return stats;
   }
+
+  async stats(): Promise<TableStatistics> {
+    return await this.inner.stats();
+  }
+
   mergeInsert(on: string | string[]): MergeInsertBuilder {
     on = Array.isArray(on) ? on : [on];
     return new MergeInsertBuilder(this.inner.mergeInsert(on), this.schema());

nodejs/src/table.rs

@@ -157,6 +157,12 @@ impl Table {
             .default_error()
     }
 
+    #[napi(catch_unwind)]
+    pub async fn stats(&self) -> Result<TableStatistics> {
+        let stats = self.inner_ref()?.stats().await.default_error()?;
+        Ok(stats.into())
+    }
+
     #[napi(catch_unwind)]
     pub async fn update(
         &self,
@@ -555,6 +561,80 @@ impl From<lancedb::index::IndexStatistics> for IndexStatistics {
     }
 }
 
+#[napi(object)]
+pub struct TableStatistics {
+    /// The total number of bytes in the table
+    pub total_bytes: i64,
+
+    /// The number of rows in the table
+    pub num_rows: i64,
+
+    /// The number of indices in the table
+    pub num_indices: i64,
+
+    /// Statistics on table fragments
+    pub fragment_stats: FragmentStatistics,
+}
+
+#[napi(object)]
+pub struct FragmentStatistics {
+    /// The number of fragments in the table
+    pub num_fragments: i64,
+
+    /// The number of uncompacted fragments in the table
+    pub num_small_fragments: i64,
+
+    /// Statistics on the number of rows in the table fragments
+    pub lengths: FragmentSummaryStats,
+}
+
+#[napi(object)]
+pub struct FragmentSummaryStats {
+    /// The number of rows in the fragment with the fewest rows
+    pub min: i64,
+
+    /// The number of rows in the fragment with the most rows
+    pub max: i64,
+
+    /// The mean number of rows in the fragments
+    pub mean: i64,
+
+    /// The 25th percentile of number of rows in the fragments
+    pub p25: i64,
+
+    /// The 50th percentile of number of rows in the fragments
+    pub p50: i64,
+
+    /// The 75th percentile of number of rows in the fragments
+    pub p75: i64,
+
+    /// The 99th percentile of number of rows in the fragments
+    pub p99: i64,
+}
+
+impl From<lancedb::table::TableStatistics> for TableStatistics {
+    fn from(v: lancedb::table::TableStatistics) -> Self {
+        Self {
+            total_bytes: v.total_bytes as i64,
+            num_rows: v.num_rows as i64,
+            num_indices: v.num_indices as i64,
+            fragment_stats: FragmentStatistics {
+                num_fragments: v.fragment_stats.num_fragments as i64,
+                num_small_fragments: v.fragment_stats.num_small_fragments as i64,
+                lengths: FragmentSummaryStats {
+                    min: v.fragment_stats.lengths.min as i64,
+                    max: v.fragment_stats.lengths.max as i64,
+                    mean: v.fragment_stats.lengths.mean as i64,
+                    p25: v.fragment_stats.lengths.p25 as i64,
+                    p50: v.fragment_stats.lengths.p50 as i64,
+                    p75: v.fragment_stats.lengths.p75 as i64,
+                    p99: v.fragment_stats.lengths.p99 as i64,
+                },
+            },
+        }
+    }
+}
+
 #[napi(object)]
 pub struct Version {
     pub version: i64,