diff --git a/docs/src/js/classes/BlobFile.md b/docs/src/js/classes/BlobFile.md index 84a596d1a..ee9f9ad28 100644 --- a/docs/src/js/classes/BlobFile.md +++ b/docs/src/js/classes/BlobFile.md @@ -10,16 +10,50 @@ A lazy handle to blob bytes. Create one with [Table.fetchBlobFiles](Table.md#fet ## Methods +### close() + +```ts +close(): Promise +``` + +Releases the handle. Reads after `close()` fail. Calling it again does +nothing. + +#### Returns + +`Promise`<`void`> + +*** + +### isClosed() + +```ts +isClosed(): boolean +``` + +Returns true after [BlobFile.close](BlobFile.md#close). + +#### Returns + +`boolean` + +*** + ### read() ```ts -read(): Promise +read(maxBytes?): Promise ``` -Reads from the cursor to the end and advances the cursor. +Reads from the cursor and advances the cursor. -A second call returns an empty buffer. [BlobFile.readRange](BlobFile.md#readrange) does -not move the cursor. +Reads to the end when `maxBytes` is omitted, or at most `maxBytes` bytes +otherwise. Returns an empty buffer at the end of the blob. +[BlobFile.readRange](BlobFile.md#readrange) does not move the cursor. + +#### Parameters + +* **maxBytes?**: `bigint` #### Returns @@ -49,6 +83,45 @@ Fails when `end` is past the blob size. Does not move the cursor. *** +### readRanges() + +```ts +readRanges(ranges): Promise +``` + +Reads several half-open byte ranges. Returns one buffer per range, in +the order given. + +Fails when any `end` is past the blob size. Does not move the cursor. + +#### Parameters + +* **ranges**: [`BlobRange`](../type-aliases/BlobRange.md)[] + +#### Returns + +`Promise`<`Buffer`[]> + +*** + +### seek() + +```ts +seek(position): Promise +``` + +Moves the cursor to `position`, in bytes from the start of the blob. + +#### Parameters + +* **position**: `bigint` + +#### Returns + +`Promise`<`void`> + +*** + ### size() ```ts @@ -60,3 +133,17 @@ Returns the blob size in bytes. #### Returns `bigint` + +*** + +### tell() + +```ts +tell(): Promise +``` + +Returns the cursor position in bytes. + +#### Returns + +`Promise`<`bigint`> diff --git a/docs/src/js/globals.md b/docs/src/js/globals.md index 2f49578b1..9b9f76334 100644 --- a/docs/src/js/globals.md +++ b/docs/src/js/globals.md @@ -158,6 +158,7 @@ - [AnalyzePlanDistributedMetrics](type-aliases/AnalyzePlanDistributedMetrics.md) - [BaseTokenizer](type-aliases/BaseTokenizer.md) - [BlobOptions](type-aliases/BlobOptions.md) +- [BlobRange](type-aliases/BlobRange.md) - [Data](type-aliases/Data.md) - [DataLike](type-aliases/DataLike.md) - [FieldLike](type-aliases/FieldLike.md) diff --git a/docs/src/js/type-aliases/BlobRange.md b/docs/src/js/type-aliases/BlobRange.md new file mode 100644 index 000000000..85cd48242 --- /dev/null +++ b/docs/src/js/type-aliases/BlobRange.md @@ -0,0 +1,27 @@ +[**@lancedb/lancedb**](../README.md) • **Docs** + +*** + +[@lancedb/lancedb](../globals.md) / BlobRange + +# Type Alias: BlobRange + +```ts +type BlobRange: object; +``` + +A half-open byte range `[start, end)` for [BlobFile.readRanges](../classes/BlobFile.md#readranges). + +## Type declaration + +### end + +```ts +end: bigint; +``` + +### start + +```ts +start: bigint; +``` diff --git a/nodejs/__test__/table.test.ts b/nodejs/__test__/table.test.ts index ae257455d..64f343cdc 100644 --- a/nodejs/__test__/table.test.ts +++ b/nodejs/__test__/table.test.ts @@ -2625,6 +2625,74 @@ describe("when dealing with blob columns", () => { ).rejects.toThrow(/exceeds blob size/); }); + it("reads at most maxBytes and advances the cursor", async () => { + const { table, rowIds } = await openBlobTable(); + const [handle] = await table.fetchBlobFiles("image", rowIds); + expect((await handle!.read(2n)).toString()).toBe("al"); + expect(await handle!.tell()).toBe(2n); + expect((await handle!.read(2n)).toString()).toBe("ph"); + expect((await handle!.read(10n)).toString()).toBe("a"); + expect(await handle!.tell()).toBe(5n); + expect(await handle!.read(1n)).toEqual(Buffer.alloc(0)); + }); + + it("seeks the cursor", async () => { + const { table, rowIds, alpha } = await openBlobTable(); + const [handle] = await table.fetchBlobFiles("image", rowIds); + await handle!.seek(3n); + expect(await handle!.tell()).toBe(3n); + expect((await handle!.read()).toString()).toBe("ha"); + await handle!.seek(0n); + expect(await handle!.read()).toEqual(alpha); + }); + + it("rejects a negative seek position", async () => { + const { table, rowIds } = await openBlobTable(); + const [handle] = await table.fetchBlobFiles("image", rowIds); + await expect(handle!.seek(-1n)).rejects.toThrow(/cannot be negative/); + }); + + it("readRanges returns one buffer per range in order", async () => { + const { table, rowIds } = await openBlobTable(); + const [handle] = await table.fetchBlobFiles("image", rowIds); + const buffers = await handle!.readRanges([ + { start: 3n, end: 5n }, + { start: 0n, end: 2n }, + { start: 3n, end: 5n }, + ]); + expect(buffers.map((b) => b.toString())).toEqual(["ha", "al", "ha"]); + expect(await handle!.tell()).toBe(0n); + }); + + it("fails when a readRanges end is past the blob size", async () => { + const { table, rowIds, alpha } = await openBlobTable(); + const [handle] = await table.fetchBlobFiles("image", rowIds); + await expect( + handle!.readRanges([ + { start: 0n, end: 1n }, + { start: 0n, end: BigInt(alpha.length + 1) }, + ]), + ).rejects.toThrow(/exceeds blob size/); + }); + + it("fails reads after close and closes once", async () => { + const { table, rowIds } = await openBlobTable(); + const [handle] = await table.fetchBlobFiles("image", rowIds); + expect(handle!.isClosed()).toBe(false); + await handle!.close(); + expect(handle!.isClosed()).toBe(true); + await expect(handle!.close()).resolves.toBeUndefined(); + await expect(handle!.read()).rejects.toThrow(/already closed/); + await expect(handle!.read(1n)).rejects.toThrow(/already closed/); + await expect(handle!.readRange(0n, 1n)).rejects.toThrow(/already closed/); + await expect(handle!.readRanges([{ start: 0n, end: 1n }])).rejects.toThrow( + /already closed/, + ); + await expect(handle!.seek(0n)).rejects.toThrow(/already closed/); + await expect(handle!.tell()).rejects.toThrow(/already closed/); + expect(handle!.size()).toBe(5n); + }); + it("rejects fetchBlobs on a non-blob column", async () => { const { table, rowIds } = await openBlobTable(); await expect(table.fetchBlobs("id", rowIds)).rejects.toThrow(/blob/i); diff --git a/nodejs/lancedb/blob.ts b/nodejs/lancedb/blob.ts index 244faac09..fc8c43196 100644 --- a/nodejs/lancedb/blob.ts +++ b/nodejs/lancedb/blob.ts @@ -141,13 +141,14 @@ export class BlobFile { } /** - * Reads from the cursor to the end and advances the cursor. + * Reads from the cursor and advances the cursor. * - * A second call returns an empty buffer. {@link BlobFile.readRange} does - * not move the cursor. + * Reads to the end when `maxBytes` is omitted, or at most `maxBytes` bytes + * otherwise. Returns an empty buffer at the end of the blob. + * {@link BlobFile.readRange} does not move the cursor. */ - read(): Promise { - return this.inner.read(); + read(maxBytes?: bigint): Promise { + return this.inner.read(maxBytes); } /** @@ -158,8 +159,47 @@ export class BlobFile { readRange(start: bigint, end: bigint): Promise { return this.inner.readRange(start, end); } + + /** + * Reads several half-open byte ranges. Returns one buffer per range, in + * the order given. + * + * Fails when any `end` is past the blob size. Does not move the cursor. + */ + readRanges(ranges: BlobRange[]): Promise { + return this.inner.readRanges(ranges); + } + + /** Moves the cursor to `position`, in bytes from the start of the blob. */ + seek(position: bigint): Promise { + return this.inner.seek(position); + } + + /** Returns the cursor position in bytes. */ + tell(): Promise { + return this.inner.tell(); + } + + /** + * Releases the handle. Reads after `close()` fail. Calling it again does + * nothing. + */ + close(): Promise { + return this.inner.close(); + } + + /** Returns true after {@link BlobFile.close}. */ + isClosed(): boolean { + return this.inner.isClosed(); + } } +/** A half-open byte range `[start, end)` for {@link BlobFile.readRanges}. */ +export type BlobRange = { + start: bigint; + end: bigint; +}; + export function coerceBlobValue(value: unknown): BlobInput | null { if (value == null) { return null; diff --git a/nodejs/lancedb/index.ts b/nodejs/lancedb/index.ts index ed6889232..2e444784b 100644 --- a/nodejs/lancedb/index.ts +++ b/nodejs/lancedb/index.ts @@ -84,7 +84,7 @@ export { } from "./arrow"; export { blob, isBlobField, BlobFile } from "./blob"; -export type { BlobOptions } from "./blob"; +export type { BlobOptions, BlobRange } from "./blob"; export { Connection, diff --git a/nodejs/src/blob.rs b/nodejs/src/blob.rs index 230a11bae..413bf6d97 100644 --- a/nodejs/src/blob.rs +++ b/nodejs/src/blob.rs @@ -3,6 +3,7 @@ use std::ops::Range; use std::sync::Arc; +use std::sync::atomic::{AtomicBool, Ordering}; use arrow_array::{Array, LargeBinaryArray}; use lancedb::blob::BlobFile as LanceBlobFile; @@ -11,15 +12,31 @@ use napi_derive::napi; use crate::error::convert_error; +#[napi(object)] +pub struct BlobRange { + pub start: BigInt, + pub end: BigInt, +} + #[napi] pub struct BlobFile { inner: Arc, + closed: AtomicBool, } impl BlobFile { pub(crate) fn new(inner: LanceBlobFile) -> Self { Self { inner: Arc::new(inner), + closed: AtomicBool::new(false), + } + } + + fn ensure_open(&self) -> napi::Result<()> { + if self.closed.load(Ordering::Acquire) { + Err(napi::Error::from_reason("blob file is already closed")) + } else { + Ok(()) } } } @@ -32,13 +49,23 @@ impl BlobFile { } #[napi] - pub async fn read(&self) -> napi::Result { - let bytes = self.inner.read().await.map_err(|err| convert_error(&err))?; + pub async fn read(&self, max_bytes: Option) -> napi::Result { + self.ensure_open()?; + let bytes = match max_bytes { + None => self.inner.read().await, + Some(max_bytes) => { + let max_bytes = usize::try_from(parse_u64(max_bytes, "maxBytes")?) + .map_err(|_| napi::Error::from_reason("maxBytes is too large"))?; + self.inner.read_up_to(max_bytes).await + } + } + .map_err(|err| convert_error(&err))?; Ok(Buffer::from(bytes.as_ref())) } #[napi] pub async fn read_range(&self, start: BigInt, end: BigInt) -> napi::Result { + self.ensure_open()?; let range = bigint_range(start, end)?; let bytes = self .inner @@ -47,6 +74,54 @@ impl BlobFile { .map_err(|err| convert_error(&err))?; Ok(Buffer::from(bytes.as_ref())) } + + #[napi] + pub async fn read_ranges(&self, ranges: Vec) -> napi::Result> { + self.ensure_open()?; + let ranges = ranges + .into_iter() + .map(|range| bigint_range(range.start, range.end)) + .collect::>>()?; + let buffers = self + .inner + .read_ranges(&ranges) + .await + .map_err(|err| convert_error(&err))?; + Ok(buffers + .iter() + .map(|bytes| Buffer::from(bytes.as_ref())) + .collect()) + } + + #[napi] + pub async fn seek(&self, position: BigInt) -> napi::Result<()> { + self.ensure_open()?; + let position = parse_u64(position, "position")?; + self.inner + .seek(position) + .await + .map_err(|err| convert_error(&err)) + } + + #[napi] + pub async fn tell(&self) -> napi::Result { + self.ensure_open()?; + let position = self.inner.tell().await.map_err(|err| convert_error(&err))?; + Ok(BigInt::from(position)) + } + + #[napi] + pub async fn close(&self) -> napi::Result<()> { + if self.closed.swap(true, Ordering::AcqRel) { + return Ok(()); + } + self.inner.close().await.map_err(|err| convert_error(&err)) + } + + #[napi] + pub fn is_closed(&self) -> bool { + self.closed.load(Ordering::Acquire) + } } fn bigint_range(start: BigInt, end: BigInt) -> napi::Result> {