Files
lancedb/nodejs/src/merge.rs
Weston Pace f6c9d31f98 feat: add polars dataframe integration (#3584)
This PR is part cleanup, part feature, part example.

It removes `IntoArrow` and `IntoArrowStream`. There was only one
redundant call site between the two. Once we moved everything to
`Scannable` these traits no longer serve any purpose.

It adds a `Scannable` impl for a polars DataFrame. We used to have this
at one point for `IntoArrow` so this is more like a regression fix than
anything.

It adds an example (and unit test) which ensures we can ingest from a
Polars DataFrame and export to one. LazyFrame support would be a
follow-up (though a pretty straightforward one) but we've never had
proper LazyFrame support before.
2026-06-30 08:28:41 -07:00

90 lines
2.5 KiB
Rust

// SPDX-License-Identifier: Apache-2.0
// SPDX-FileCopyrightText: Copyright The LanceDB Authors
use std::time::Duration;
use lancedb::{ipc::ipc_file_to_batches, table::merge::MergeInsertBuilder};
use napi::bindgen_prelude::*;
use napi_derive::napi;
use crate::{error::convert_error, table::MergeResult};
#[napi]
#[derive(Clone)]
/// A builder used to create and run a merge insert operation
pub struct NativeMergeInsertBuilder {
pub(crate) inner: MergeInsertBuilder,
}
#[napi]
impl NativeMergeInsertBuilder {
#[napi]
pub fn when_matched_update_all(&self, condition: Option<String>) -> Self {
let mut this = self.clone();
this.inner.when_matched_update_all(condition);
this
}
#[napi]
pub fn when_not_matched_insert_all(&self) -> Self {
let mut this = self.clone();
this.inner.when_not_matched_insert_all();
this
}
#[napi]
pub fn when_not_matched_by_source_delete(&self, filter: Option<String>) -> Self {
let mut this = self.clone();
this.inner.when_not_matched_by_source_delete(filter);
this
}
#[napi]
pub fn set_timeout(&mut self, timeout: u32) {
self.inner.timeout(Duration::from_millis(timeout as u64));
}
#[napi]
pub fn use_index(&self, use_index: bool) -> Self {
let mut this = self.clone();
this.inner.use_index(use_index);
this
}
#[napi]
pub fn use_lsm_write(&self, use_lsm_write: bool) -> Self {
let mut this = self.clone();
this.inner.use_lsm_write(use_lsm_write);
this
}
#[napi]
pub fn validate_single_shard(&self, validate_single_shard: bool) -> Self {
let mut this = self.clone();
this.inner.validate_single_shard(validate_single_shard);
this
}
#[napi(catch_unwind)]
pub async fn execute(&self, buf: Buffer) -> napi::Result<MergeResult> {
let data = ipc_file_to_batches(buf.to_vec()).map_err(|e| {
napi::Error::from_reason(format!("Failed to read IPC file: {}", convert_error(&e)))
})?;
let this = self.clone();
let res = this.inner.execute(data).await.map_err(|e| {
napi::Error::from_reason(format!(
"Failed to execute merge insert: {}",
convert_error(&e)
))
})?;
Ok(res.into())
}
}
impl From<MergeInsertBuilder> for NativeMergeInsertBuilder {
fn from(inner: MergeInsertBuilder) -> Self {
Self { inner }
}
}