rust/lancedb
1
0
Fork 0
mirror of https://github.com/lancedb/lancedb.git synced 2026-11-14 14:46:53 +00:00
Code Issues Packages Projects Releases Wiki Activity

chore: update lance dependency to v9.1.0-beta.2

Browse Source
This commit is contained in:
lancedb automation
2026-07-15 23:21:30 +00:00
parent 00c4a7b843
commit 4b6288765e
13 changed files with 822 additions and 1022 deletions
Download Patch File Download Diff File Expand all files Collapse all files
Cargo.lock
Generated
+776 -958
View File
File diff suppressed because it is too large Load Diff
Cargo.toml
+23 -23
View File
@@ -13,20 +13,20 @@ categories = ["database-implementations"]
rust-version = "1.91.0"
[workspace.dependencies]
lance = { "version" = "=9.0.0-beta.24", default-features = false, "tag" = "v9.0.0-beta.24", "git" = "https://github.com/lance-format/lance.git" }
lance-core = { "version" = "=9.0.0-beta.24", "tag" = "v9.0.0-beta.24", "git" = "https://github.com/lance-format/lance.git" }
lance-datagen = { "version" = "=9.0.0-beta.24", "tag" = "v9.0.0-beta.24", "git" = "https://github.com/lance-format/lance.git" }
lance-file = { "version" = "=9.0.0-beta.24", "tag" = "v9.0.0-beta.24", "git" = "https://github.com/lance-format/lance.git" }
lance-io = { "version" = "=9.0.0-beta.24", default-features = false, "tag" = "v9.0.0-beta.24", "git" = "https://github.com/lance-format/lance.git" }
lance-index = { "version" = "=9.0.0-beta.24", "tag" = "v9.0.0-beta.24", "git" = "https://github.com/lance-format/lance.git" }
lance-linalg = { "version" = "=9.0.0-beta.24", "tag" = "v9.0.0-beta.24", "git" = "https://github.com/lance-format/lance.git" }
lance-namespace = { "version" = "=9.0.0-beta.24", "tag" = "v9.0.0-beta.24", "git" = "https://github.com/lance-format/lance.git" }
lance-namespace-impls = { "version" = "=9.0.0-beta.24", default-features = false, "tag" = "v9.0.0-beta.24", "git" = "https://github.com/lance-format/lance.git" }
lance-table = { "version" = "=9.0.0-beta.24", "tag" = "v9.0.0-beta.24", "git" = "https://github.com/lance-format/lance.git" }
lance-testing = { "version" = "=9.0.0-beta.24", "tag" = "v9.0.0-beta.24", "git" = "https://github.com/lance-format/lance.git" }
lance-datafusion = { "version" = "=9.0.0-beta.24", "tag" = "v9.0.0-beta.24", "git" = "https://github.com/lance-format/lance.git" }
lance-encoding = { "version" = "=9.0.0-beta.24", "tag" = "v9.0.0-beta.24", "git" = "https://github.com/lance-format/lance.git" }
lance-arrow = { "version" = "=9.0.0-beta.24", "tag" = "v9.0.0-beta.24", "git" = "https://github.com/lance-format/lance.git" }
lance = { "version" = "=9.1.0-beta.2", default-features = false, "tag" = "v9.1.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
lance-core = { "version" = "=9.1.0-beta.2", "tag" = "v9.1.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
lance-datagen = { "version" = "=9.1.0-beta.2", "tag" = "v9.1.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
lance-file = { "version" = "=9.1.0-beta.2", "tag" = "v9.1.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
lance-io = { "version" = "=9.1.0-beta.2", default-features = false, "tag" = "v9.1.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
lance-index = { "version" = "=9.1.0-beta.2", "tag" = "v9.1.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
lance-linalg = { "version" = "=9.1.0-beta.2", "tag" = "v9.1.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
lance-namespace = { "version" = "=9.1.0-beta.2", "tag" = "v9.1.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
lance-namespace-impls = { "version" = "=9.1.0-beta.2", default-features = false, "tag" = "v9.1.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
lance-table = { "version" = "=9.1.0-beta.2", "tag" = "v9.1.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
lance-testing = { "version" = "=9.1.0-beta.2", "tag" = "v9.1.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
lance-datafusion = { "version" = "=9.1.0-beta.2", "tag" = "v9.1.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
lance-encoding = { "version" = "=9.1.0-beta.2", "tag" = "v9.1.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
lance-arrow = { "version" = "=9.1.0-beta.2", "tag" = "v9.1.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
ahash = "0.8"
# Note that this one does not include pyarrow
arrow = { version = "58.0.0", optional = false }
@@ -39,15 +39,15 @@ arrow-schema = "58.0.0"
arrow-select = "58.0.0"
arrow-cast = "58.0.0"
async-trait = "0"
datafusion = { version = "53.0.0", default-features = false }
datafusion-catalog = "53.0.0"
datafusion-common = { version = "53.0.0", default-features = false }
datafusion-execution = "53.0.0"
datafusion-expr = "53.0.0"
datafusion-functions = "53.0.0"
datafusion-physical-plan = "53.0.0"
datafusion-physical-expr = "53.0.0"
datafusion-sql = "53.0.0"
datafusion = { version = "54.0.0", default-features = false }
datafusion-catalog = "54.0.0"
datafusion-common = { version = "54.0.0", default-features = false }
datafusion-execution = "54.0.0"
datafusion-expr = "54.0.0"
datafusion-functions = "54.0.0"
datafusion-physical-plan = "54.0.0"
datafusion-physical-expr = "54.0.0"
datafusion-sql = "54.0.0"
env_logger = "0.11"
half = { "version" = "2.7.1", default-features = false, features = [
"num-traits",
java/pom.xml
+1 -1
View File
@@ -28,7 +28,7 @@
<properties>
<project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
<arrow.version>15.0.0</arrow.version>
<lance-core.version>9.0.0-beta.24</lance-core.version>
<lance-core.version>9.1.0-beta.2</lance-core.version>
<spotless.skip>false</spotless.skip>
<spotless.version>2.30.0</spotless.version>
<spotless.java.googlejavaformat.version>1.7</spotless.java.googlejavaformat.version>
rust/lancedb/src/dataloader/permutation/shuffle.rs
+14 -3
View File
@@ -8,13 +8,13 @@ use arrow_array::{RecordBatch, UInt64Array};
use futures::{StreamExt, TryStreamExt};
use lance::io::ObjectStore;
use lance_core::{cache::LanceCache, utils::futures::FinallyStreamExt};
use lance_encoding::decoder::DecoderPlugins;
use lance_encoding::decoder::{DecoderPlugins, FilterExpression};
use lance_file::{
reader::{FileReader, FileReaderOptions},
writer::{FileWriter, FileWriterOptions},
};
use lance_index::scalar::IndexReader;
use lance_io::{
ReadBatchParams,
scheduler::{ScanScheduler, SchedulerConfig},
utils::CachedFileSize,
};
@@ -239,7 +239,18 @@ impl Shuffler {
)
.await?;
// Need to read the entire file in a single batch for in-memory shuffling
let batch = reader.read_record_batch(0, reader.num_rows()).await?;
let batch = reader
.read_stream(
ReadBatchParams::RangeFull,
reader.num_rows() as u32,
1,
FilterExpression::no_filter(),
)
.await?
.try_collect::<Vec<_>>()
.await?;
let schema = Arc::new(arrow_schema::Schema::from(reader.schema().as_ref()));
let batch = concat_batches(&schema, &batch)?;
let mut rng = rng.lock().unwrap_or_else(|e| e.into_inner());
Self::shuffle_batch(&batch, &mut rng, clump_size)
}
rust/lancedb/src/dataloader/permutation/split.rs
+2 -2
View File
@@ -8,7 +8,7 @@ use std::sync::{
use arrow_array::{Array, BooleanArray, RecordBatch, UInt64Array};
use arrow_schema::{DataType, Field, Schema};
use datafusion_common::hash_utils::create_hashes;
use datafusion_common::hash_utils::{RandomState, create_hashes};
use futures::{StreamExt, TryStreamExt};
use lance_arrow::SchemaExt;
@@ -234,7 +234,7 @@ impl Splitter {
.cloned()
.collect::<Vec<_>>();
let mut hashes = vec![0; batch.num_rows()];
let random_state = ahash::RandomState::with_seeds(0, 0, 0, 0);
let random_state = RandomState::with_seed(0);
create_hashes(&arrays, &random_state, &mut hashes).unwrap();
// As an example, let's assume the weights are 1, 2. Our total weight is 3.
//
rust/lancedb/src/remote/table.rs
-1
View File
@@ -1251,7 +1251,6 @@ impl<S: HttpSend + 'static> RemoteTable<S> {
match result {
Ok(_) => {
let add_result = insert
.as_any()
.downcast_ref::<RemoteInsertExec<S>>()
.and_then(|i| i.add_result())
.unwrap_or(AddResult { version: 0 });
rust/lancedb/src/remote/table/insert.rs
-5
View File
@@ -3,7 +3,6 @@
//! DataFusion ExecutionPlan for inserting data into remote LanceDB tables.
use std::any::Any;
use std::sync::{Arc, Mutex};
use arrow_array::{ArrayRef, RecordBatch, UInt64Array};
@@ -237,10 +236,6 @@ impl<S: HttpSend + 'static> ExecutionPlan for RemoteInsertExec<S> {
Self::static_name()
}
fn as_any(&self) -> &dyn Any {
self
}
fn properties(&self) -> &Arc<PlanProperties> {
&self.properties
}
rust/lancedb/src/table/datafusion.rs
+1 -9
View File
@@ -89,10 +89,6 @@ impl ExecutionPlan for MetadataEraserExec {
"MetadataEraserExec"
}
fn as_any(&self) -> &dyn std::any::Any {
self
}
fn properties(&self) -> &Arc<PlanProperties> {
&self.properties
}
@@ -138,7 +134,7 @@ impl ExecutionPlan for MetadataEraserExec {
)
}
fn partition_statistics(&self, partition: Option<usize>) -> DataFusionResult<Statistics> {
fn partition_statistics(&self, partition: Option<usize>) -> DataFusionResult<Arc<Statistics>> {
self.input.partition_statistics(partition)
}
@@ -188,10 +184,6 @@ impl BaseTableAdapter {
#[async_trait]
impl TableProvider for BaseTableAdapter {
fn as_any(&self) -> &dyn std::any::Any {
self
}
fn schema(&self) -> Arc<ArrowSchema> {
self.schema.clone()
}
rust/lancedb/src/table/datafusion/insert.rs
-5
View File
@@ -3,7 +3,6 @@
//! DataFusion ExecutionPlan for inserting data into LanceDB tables.
use std::any::Any;
use std::sync::atomic::{AtomicU64, Ordering};
use std::sync::{Arc, LazyLock, Mutex};
@@ -146,10 +145,6 @@ impl ExecutionPlan for InsertExec {
Self::static_name()
}
fn as_any(&self) -> &dyn Any {
self
}
fn properties(&self) -> &Arc<PlanProperties> {
&self.properties
}
rust/lancedb/src/table/datafusion/reject_nan.rs
-5
View File
@@ -3,7 +3,6 @@
//! A DataFusion projection that rejects vectors containing NaN values.
use std::any::Any;
use std::sync::{Arc, LazyLock};
use arrow_array::{Array, FixedSizeListArray};
@@ -86,10 +85,6 @@ impl RejectNanUdf {
}
impl ScalarUDFImpl for RejectNanUdf {
fn as_any(&self) -> &dyn Any {
self
}
fn name(&self) -> &str {
"reject_nan"
}
rust/lancedb/src/table/datafusion/scannable_exec.rs
+3 -7
View File
@@ -66,10 +66,6 @@ impl ExecutionPlan for ScannableExec {
"ScannableExec"
}
fn as_any(&self) -> &dyn std::any::Any {
self
}
fn properties(&self) -> &Arc<PlanProperties> {
&self.properties
}
@@ -121,14 +117,14 @@ impl ExecutionPlan for ScannableExec {
)))
}
fn partition_statistics(&self, _partition: Option<usize>) -> DFResult<Statistics> {
Ok(Statistics {
fn partition_statistics(&self, _partition: Option<usize>) -> DFResult<Arc<Statistics>> {
Ok(Arc::new(Statistics {
num_rows: self
.num_rows
.map(Precision::Exact)
.unwrap_or(Precision::Absent),
total_byte_size: Precision::Absent,
column_statistics: vec![],
})
}))
}
}
rust/lancedb/src/table/datafusion/udtf/fts.rs
-1
View File
@@ -138,7 +138,6 @@ mod tests {
// Downcast to BaseTableAdapter and apply FTS query
let base_adapter = table_provider
.as_any()
.downcast_ref::<BaseTableAdapter>()
.ok_or_else(|| {
DataFusionError::Internal(
rust/lancedb/src/table/query.rs
+2 -2
View File
@@ -982,10 +982,10 @@ mod tests {
use crate::table::query::create_plan;
fn find_ann_approx_mode(plan: &dyn ExecutionPlan) -> Option<ApproxMode> {
if let Some(ann) = plan.as_any().downcast_ref::<ANNIvfSubIndexExec>() {
if let Some(ann) = plan.downcast_ref::<ANNIvfSubIndexExec>() {
return Some(ann.query().approx_mode);
}
if let Some(ann) = plan.as_any().downcast_ref::<ANNIvfPartitionExec>() {
if let Some(ann) = plan.downcast_ref::<ANNIvfPartitionExec>() {
return Some(ann.query.approx_mode);
}
plan.children()