feat: add table branch support (#3490)

### Description

Adds first-class support for table branches across the Rust core and the
Python and TypeScript SDKs.

Rust

```rust
use lance::dataset::refs::Ref;

// Create a branch from main and write to it — main is untouched.
let exp = table.create_branch("exp", Ref::Version(None, None)).await?;
exp.add(batches).await?;

// Reopen the branch later: check out from a table, or open it directly.
let exp = table.checkout_branch("exp").await?;
let exp = db.open_table("items").branch("exp").execute().await?;

let branches = table.list_branches().await?;
table.delete_branch("exp").await?;
```

Python

```python
# Create a branch from main and write to it
branch = await table.branches.create("exp", from_ref="main")
await branch.add(data)

# Reopen the branch later: check out from a table, or open it directly.
branch = await table.branches.checkout("exp")
branch = await db.open_table("items", branch="exp")

await table.branches.list()
await table.branches.delete("exp")
```

TypeScript

```typescript
const branches = await table.branches();

// Create a branch from main and write to it
const branch = await branches.create("exp");
await branch.add(data);

// Reopen the branch later: check out from a table, or open it directly.
const checkedOut = await branches.checkout("exp");
const opened = await db.openTable("items", undefined, { branch: "exp" });

await branches.list();
await branches.delete("exp");
```

### Testing
- Added unit tests
- ran smoke tests against python and typescript sdks on local machine


### Next steps
- Add RemoteTable support
- Add Branch Comparison support
- Merge Branching support
This commit is contained in:
Brendan Clement
2026-06-08 16:26:46 -07:00
committed by GitHub
parent 3e25f584eb
commit 53517b3aaa
24 changed files with 1275 additions and 35 deletions

View File

@@ -85,6 +85,64 @@ describe.each([arrow15, arrow16, arrow17, arrow18])(
await expect(table.countRows()).resolves.toBe(3);
});
it("should support branches", async () => {
await table.add([{ id: 1 }]);
expect(await table.countRows()).toBe(1);
// fork an isolated, writable branch from main
const branch = await (await table.branches()).create("exp");
expect(await branch.countRows()).toBe(1);
await branch.add([{ id: 2 }]);
expect(await branch.countRows()).toBe(2);
// main is untouched by branch writes
expect(await table.countRows()).toBe(1);
// listed, with main (null) as the parent
const list = await (await table.branches()).list();
expect(Object.keys(list)).toContain("exp");
expect(list["exp"].parentBranch).toBeNull();
// fromRef="main" is equivalent to the default
await (await table.branches()).create("exp2", "main");
const list2 = await (await table.branches()).list();
expect(list2["exp2"].parentBranch).toBeNull();
// checkout returns a handle scoped to the branch's latest
const checkedOut = await (await table.branches()).checkout("exp");
expect(await checkedOut.countRows()).toBe(2);
// delete removes it
await (await table.branches()).delete("exp");
await (await table.branches()).delete("exp2");
const after = await (await table.branches()).list();
expect(Object.keys(after)).not.toContain("exp");
});
it("should open a branch via open_table", async () => {
const db = await connect(tmpDir.name);
await table.add([{ id: 1 }]);
const branch = await (await table.branches()).create("exp");
await branch.add([{ id: 2 }]);
// open_table(..., { branch }) returns a handle scoped to the branch
const opened = await db.openTable("some_table", undefined, {
branch: "exp",
});
expect(await opened.countRows()).toBe(2);
// opening without branch still tracks main
expect(await (await db.openTable("some_table")).countRows()).toBe(1);
});
it("rejects invalid branch inputs", async () => {
const branches = await table.branches();
await expect(branches.create("")).rejects.toThrow("non-empty");
await expect(branches.checkout("")).rejects.toThrow("non-empty");
await expect(branches.delete("")).rejects.toThrow("non-empty");
await expect(branches.create("bad", "main", -1)).rejects.toThrow(
"non-negative",
);
});
it("should show table stats", async () => {
await table.add([{ id: 1 }, { id: 2 }]);
await table.add([{ id: 1 }]);