mirror of
https://github.com/lancedb/lancedb.git
synced 2026-01-12 23:02:59 +00:00
chore: update lance dependency to v2.0.0-beta.7
This commit is contained in:
2000
Cargo.lock
generated
2000
Cargo.lock
generated
File diff suppressed because it is too large
Load Diff
60
Cargo.toml
60
Cargo.toml
@@ -15,39 +15,39 @@ categories = ["database-implementations"]
|
||||
rust-version = "1.78.0"
|
||||
|
||||
[workspace.dependencies]
|
||||
lance = { "version" = "=1.0.1", default-features = false }
|
||||
lance-core = "=1.0.1"
|
||||
lance-datagen = "=1.0.1"
|
||||
lance-file = "=1.0.1"
|
||||
lance-io = { "version" = "=1.0.1", default-features = false }
|
||||
lance-index = "=1.0.1"
|
||||
lance-linalg = "=1.0.1"
|
||||
lance-namespace = "=1.0.1"
|
||||
lance-namespace-impls = { "version" = "=1.0.1", default-features = false }
|
||||
lance-table = "=1.0.1"
|
||||
lance-testing = "=1.0.1"
|
||||
lance-datafusion = "=1.0.1"
|
||||
lance-encoding = "=1.0.1"
|
||||
lance-arrow = "=1.0.1"
|
||||
lance = { "version" = "=2.0.0-beta.7", default-features = false, "tag" = "v2.0.0-beta.7", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-core = { "version" = "=2.0.0-beta.7", "tag" = "v2.0.0-beta.7", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-datagen = { "version" = "=2.0.0-beta.7", "tag" = "v2.0.0-beta.7", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-file = { "version" = "=2.0.0-beta.7", "tag" = "v2.0.0-beta.7", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-io = { "version" = "=2.0.0-beta.7", default-features = false, "tag" = "v2.0.0-beta.7", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-index = { "version" = "=2.0.0-beta.7", "tag" = "v2.0.0-beta.7", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-linalg = { "version" = "=2.0.0-beta.7", "tag" = "v2.0.0-beta.7", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-namespace = { "version" = "=2.0.0-beta.7", "tag" = "v2.0.0-beta.7", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-namespace-impls = { "version" = "=2.0.0-beta.7", default-features = false, "tag" = "v2.0.0-beta.7", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-table = { "version" = "=2.0.0-beta.7", "tag" = "v2.0.0-beta.7", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-testing = { "version" = "=2.0.0-beta.7", "tag" = "v2.0.0-beta.7", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-datafusion = { "version" = "=2.0.0-beta.7", "tag" = "v2.0.0-beta.7", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-encoding = { "version" = "=2.0.0-beta.7", "tag" = "v2.0.0-beta.7", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-arrow = { "version" = "=2.0.0-beta.7", "tag" = "v2.0.0-beta.7", "git" = "https://github.com/lance-format/lance.git" }
|
||||
ahash = "0.8"
|
||||
# Note that this one does not include pyarrow
|
||||
arrow = { version = "56.2", optional = false }
|
||||
arrow-array = "56.2"
|
||||
arrow-data = "56.2"
|
||||
arrow-ipc = "56.2"
|
||||
arrow-ord = "56.2"
|
||||
arrow-schema = "56.2"
|
||||
arrow-select = "56.2"
|
||||
arrow-cast = "56.2"
|
||||
arrow = { version = "57.2.0", optional = false }
|
||||
arrow-array = "57.2.0"
|
||||
arrow-data = "57.2.0"
|
||||
arrow-ipc = "57.2.0"
|
||||
arrow-ord = "57.2.0"
|
||||
arrow-schema = "57.2.0"
|
||||
arrow-select = "57.2.0"
|
||||
arrow-cast = "57.2.0"
|
||||
async-trait = "0"
|
||||
datafusion = { version = "50.1", default-features = false }
|
||||
datafusion-catalog = "50.1"
|
||||
datafusion-common = { version = "50.1", default-features = false }
|
||||
datafusion-execution = "50.1"
|
||||
datafusion-expr = "50.1"
|
||||
datafusion-physical-plan = "50.1"
|
||||
datafusion = { version = "51.0.0", default-features = false }
|
||||
datafusion-catalog = "51.0.0"
|
||||
datafusion-common = { version = "51.0.0", default-features = false }
|
||||
datafusion-execution = "51.0.0"
|
||||
datafusion-expr = "51.0.0"
|
||||
datafusion-physical-plan = "51.0.0"
|
||||
env_logger = "0.11"
|
||||
half = { "version" = "2.6.0", default-features = false, features = [
|
||||
half = { "version" = "2.7.1", default-features = false, features = [
|
||||
"num-traits",
|
||||
] }
|
||||
futures = "0"
|
||||
@@ -59,7 +59,7 @@ rand = "0.9"
|
||||
snafu = "0.8"
|
||||
url = "2"
|
||||
num-traits = "0.2"
|
||||
regex = "1.10"
|
||||
regex = "1.12"
|
||||
lazy_static = "1"
|
||||
semver = "1.0.25"
|
||||
chrono = "0.4"
|
||||
|
||||
@@ -14,15 +14,15 @@ name = "_lancedb"
|
||||
crate-type = ["cdylib"]
|
||||
|
||||
[dependencies]
|
||||
arrow = { version = "56.2", features = ["pyarrow"] }
|
||||
arrow = { version = "57.2.0", features = ["pyarrow"] }
|
||||
async-trait = "0.1"
|
||||
lancedb = { path = "../rust/lancedb", default-features = false }
|
||||
lance-core.workspace = true
|
||||
lance-namespace.workspace = true
|
||||
lance-io.workspace = true
|
||||
env_logger.workspace = true
|
||||
pyo3 = { version = "0.25", features = ["extension-module", "abi3-py39"] }
|
||||
pyo3-async-runtimes = { version = "0.25", features = [
|
||||
pyo3 = { version = "0.26", features = ["extension-module", "abi3-py39"] }
|
||||
pyo3-async-runtimes = { version = "0.26", features = [
|
||||
"attributes",
|
||||
"tokio-runtime",
|
||||
] }
|
||||
@@ -32,7 +32,7 @@ snafu.workspace = true
|
||||
tokio = { version = "1.40", features = ["sync"] }
|
||||
|
||||
[build-dependencies]
|
||||
pyo3-build-config = { version = "0.25", features = [
|
||||
pyo3-build-config = { version = "0.26", features = [
|
||||
"extension-module",
|
||||
"abi3-py39",
|
||||
] }
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
#![allow(deprecated)]
|
||||
// SPDX-License-Identifier: Apache-2.0
|
||||
// SPDX-FileCopyrightText: Copyright The LanceDB Authors
|
||||
|
||||
@@ -10,8 +11,7 @@ use arrow::{
|
||||
use futures::stream::StreamExt;
|
||||
use lancedb::arrow::SendableRecordBatchStream;
|
||||
use pyo3::{
|
||||
exceptions::PyStopAsyncIteration, pyclass, pymethods, Bound, PyAny, PyObject, PyRef, PyResult,
|
||||
Python,
|
||||
exceptions::PyStopAsyncIteration, pyclass, pymethods, Bound, Py, PyAny, PyRef, PyResult, Python,
|
||||
};
|
||||
use pyo3_async_runtimes::tokio::future_into_py;
|
||||
|
||||
@@ -36,8 +36,11 @@ impl RecordBatchStream {
|
||||
#[pymethods]
|
||||
impl RecordBatchStream {
|
||||
#[getter]
|
||||
pub fn schema(&self, py: Python) -> PyResult<PyObject> {
|
||||
(*self.schema).clone().into_pyarrow(py)
|
||||
pub fn schema(&self, py: Python) -> PyResult<Py<PyAny>> {
|
||||
(*self.schema)
|
||||
.clone()
|
||||
.into_pyarrow(py)
|
||||
.map(|bound| bound.unbind())
|
||||
}
|
||||
|
||||
pub fn __aiter__(self_: PyRef<'_, Self>) -> PyRef<'_, Self> {
|
||||
@@ -53,7 +56,12 @@ impl RecordBatchStream {
|
||||
.next()
|
||||
.await
|
||||
.ok_or_else(|| PyStopAsyncIteration::new_err(""))?;
|
||||
Python::with_gil(|py| inner_next.infer_error()?.to_pyarrow(py))
|
||||
Python::with_gil(|py| {
|
||||
inner_next
|
||||
.infer_error()?
|
||||
.to_pyarrow(py)
|
||||
.map(|bound| bound.unbind())
|
||||
})
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
#![allow(deprecated)]
|
||||
// SPDX-License-Identifier: Apache-2.0
|
||||
// SPDX-FileCopyrightText: Copyright The LanceDB Authors
|
||||
|
||||
@@ -304,6 +305,7 @@ impl Connection {
|
||||
},
|
||||
page_token,
|
||||
limit: limit.map(|l| l as i32),
|
||||
..Default::default()
|
||||
};
|
||||
let response = inner.list_namespaces(request).await.infer_error()?;
|
||||
Python::with_gil(|py| -> PyResult<Py<PyDict>> {
|
||||
@@ -325,21 +327,16 @@ impl Connection {
|
||||
let inner = self_.get_inner()?.clone();
|
||||
let py = self_.py();
|
||||
future_into_py(py, async move {
|
||||
use lance_namespace::models::{create_namespace_request, CreateNamespaceRequest};
|
||||
let mode_enum = mode.and_then(|m| match m.to_lowercase().as_str() {
|
||||
"create" => Some(create_namespace_request::Mode::Create),
|
||||
"exist_ok" => Some(create_namespace_request::Mode::ExistOk),
|
||||
"overwrite" => Some(create_namespace_request::Mode::Overwrite),
|
||||
_ => None,
|
||||
});
|
||||
use lance_namespace::models::CreateNamespaceRequest;
|
||||
let request = CreateNamespaceRequest {
|
||||
id: if namespace.is_empty() {
|
||||
None
|
||||
} else {
|
||||
Some(namespace)
|
||||
},
|
||||
mode: mode_enum,
|
||||
mode,
|
||||
properties,
|
||||
..Default::default()
|
||||
};
|
||||
let response = inner.create_namespace(request).await.infer_error()?;
|
||||
Python::with_gil(|py| -> PyResult<Py<PyDict>> {
|
||||
@@ -360,25 +357,16 @@ impl Connection {
|
||||
let inner = self_.get_inner()?.clone();
|
||||
let py = self_.py();
|
||||
future_into_py(py, async move {
|
||||
use lance_namespace::models::{drop_namespace_request, DropNamespaceRequest};
|
||||
let mode_enum = mode.and_then(|m| match m.to_uppercase().as_str() {
|
||||
"SKIP" => Some(drop_namespace_request::Mode::Skip),
|
||||
"FAIL" => Some(drop_namespace_request::Mode::Fail),
|
||||
_ => None,
|
||||
});
|
||||
let behavior_enum = behavior.and_then(|b| match b.to_uppercase().as_str() {
|
||||
"RESTRICT" => Some(drop_namespace_request::Behavior::Restrict),
|
||||
"CASCADE" => Some(drop_namespace_request::Behavior::Cascade),
|
||||
_ => None,
|
||||
});
|
||||
use lance_namespace::models::DropNamespaceRequest;
|
||||
let request = DropNamespaceRequest {
|
||||
id: if namespace.is_empty() {
|
||||
None
|
||||
} else {
|
||||
Some(namespace)
|
||||
},
|
||||
mode: mode_enum,
|
||||
behavior: behavior_enum,
|
||||
mode,
|
||||
behavior,
|
||||
..Default::default()
|
||||
};
|
||||
let response = inner.drop_namespace(request).await.infer_error()?;
|
||||
Python::with_gil(|py| -> PyResult<Py<PyDict>> {
|
||||
@@ -405,6 +393,7 @@ impl Connection {
|
||||
} else {
|
||||
Some(namespace)
|
||||
},
|
||||
..Default::default()
|
||||
};
|
||||
let response = inner.describe_namespace(request).await.infer_error()?;
|
||||
Python::with_gil(|py| -> PyResult<Py<PyDict>> {
|
||||
@@ -434,6 +423,7 @@ impl Connection {
|
||||
},
|
||||
page_token,
|
||||
limit: limit.map(|l| l as i32),
|
||||
..Default::default()
|
||||
};
|
||||
let response = inner.list_tables(request).await.infer_error()?;
|
||||
Python::with_gil(|py| -> PyResult<Py<PyDict>> {
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
#![allow(deprecated)]
|
||||
// SPDX-License-Identifier: Apache-2.0
|
||||
// SPDX-FileCopyrightText: Copyright The LanceDB Authors
|
||||
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
#![allow(deprecated)]
|
||||
// SPDX-License-Identifier: Apache-2.0
|
||||
// SPDX-FileCopyrightText: Copyright The LanceDB Authors
|
||||
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
#![allow(deprecated)]
|
||||
// SPDX-License-Identifier: Apache-2.0
|
||||
// SPDX-FileCopyrightText: Copyright The LanceDB Authors
|
||||
|
||||
@@ -281,7 +282,7 @@ impl PyPermutationReader {
|
||||
let reader = slf.reader.clone();
|
||||
future_into_py(slf.py(), async move {
|
||||
let schema = reader.output_schema(selection).await.infer_error()?;
|
||||
Python::with_gil(|py| schema.to_pyarrow(py))
|
||||
Python::with_gil(|py| schema.to_pyarrow(py).map(|b| b.unbind()))
|
||||
})
|
||||
}
|
||||
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
#![allow(deprecated)]
|
||||
// SPDX-License-Identifier: Apache-2.0
|
||||
// SPDX-FileCopyrightText: Copyright The LanceDB Authors
|
||||
|
||||
@@ -216,7 +217,7 @@ impl<'py> IntoPyObject<'py> for PyQueryVectors {
|
||||
let py_objs = self
|
||||
.0
|
||||
.into_iter()
|
||||
.map(|v| v.to_data().into_pyarrow(py))
|
||||
.map(|v| v.to_data().into_pyarrow(py).map(|b| b.unbind()))
|
||||
.collect::<Result<Vec<_>, _>>()?;
|
||||
PyList::new(py, py_objs)
|
||||
}
|
||||
@@ -453,7 +454,7 @@ impl Query {
|
||||
let inner = self_.inner.clone();
|
||||
future_into_py(self_.py(), async move {
|
||||
let schema = inner.output_schema().await.infer_error()?;
|
||||
Python::with_gil(|py| schema.to_pyarrow(py))
|
||||
Python::with_gil(|py| schema.to_pyarrow(py).map(|b| b.unbind()))
|
||||
})
|
||||
}
|
||||
|
||||
@@ -532,7 +533,7 @@ impl TakeQuery {
|
||||
let inner = self_.inner.clone();
|
||||
future_into_py(self_.py(), async move {
|
||||
let schema = inner.output_schema().await.infer_error()?;
|
||||
Python::with_gil(|py| schema.to_pyarrow(py))
|
||||
Python::with_gil(|py| schema.to_pyarrow(py).map(|b| b.unbind()))
|
||||
})
|
||||
}
|
||||
|
||||
@@ -627,7 +628,7 @@ impl FTSQuery {
|
||||
let inner = self_.inner.clone();
|
||||
future_into_py(self_.py(), async move {
|
||||
let schema = inner.output_schema().await.infer_error()?;
|
||||
Python::with_gil(|py| schema.to_pyarrow(py))
|
||||
Python::with_gil(|py| schema.to_pyarrow(py).map(|b| b.unbind()))
|
||||
})
|
||||
}
|
||||
|
||||
@@ -806,7 +807,7 @@ impl VectorQuery {
|
||||
let inner = self_.inner.clone();
|
||||
future_into_py(self_.py(), async move {
|
||||
let schema = inner.output_schema().await.infer_error()?;
|
||||
Python::with_gil(|py| schema.to_pyarrow(py))
|
||||
Python::with_gil(|py| schema.to_pyarrow(py).map(|b| b.unbind()))
|
||||
})
|
||||
}
|
||||
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
#![allow(deprecated)]
|
||||
// SPDX-License-Identifier: Apache-2.0
|
||||
// SPDX-FileCopyrightText: Copyright The LanceDB Authors
|
||||
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
#![allow(deprecated)]
|
||||
// SPDX-License-Identifier: Apache-2.0
|
||||
// SPDX-FileCopyrightText: Copyright The LanceDB Authors
|
||||
use std::{collections::HashMap, sync::Arc};
|
||||
@@ -287,7 +288,7 @@ impl Table {
|
||||
let inner = self_.inner_ref()?.clone();
|
||||
future_into_py(self_.py(), async move {
|
||||
let schema = inner.schema().await.infer_error()?;
|
||||
Python::with_gil(|py| schema.to_pyarrow(py))
|
||||
Python::with_gil(|py| schema.to_pyarrow(py).map(|b| b.unbind()))
|
||||
})
|
||||
}
|
||||
|
||||
|
||||
@@ -9,7 +9,7 @@ use std::sync::Arc;
|
||||
use async_trait::async_trait;
|
||||
use lance_namespace::{
|
||||
models::{
|
||||
CreateEmptyTableRequest, CreateNamespaceRequest, CreateNamespaceResponse,
|
||||
CreateNamespaceRequest, CreateNamespaceResponse, DeclareTableRequest,
|
||||
DescribeNamespaceRequest, DescribeNamespaceResponse, DescribeTableRequest,
|
||||
DropNamespaceRequest, DropNamespaceResponse, DropTableRequest, ListNamespacesRequest,
|
||||
ListNamespacesResponse, ListTablesRequest, ListTablesResponse,
|
||||
@@ -137,6 +137,7 @@ impl Database for LanceNamespaceDatabase {
|
||||
id: Some(request.namespace),
|
||||
page_token: request.start_after,
|
||||
limit: request.limit.map(|l| l as i32),
|
||||
..Default::default()
|
||||
};
|
||||
|
||||
let response = self.namespace.list_tables(ns_request).await?;
|
||||
@@ -154,6 +155,7 @@ impl Database for LanceNamespaceDatabase {
|
||||
let describe_request = DescribeTableRequest {
|
||||
id: Some(table_id.clone()),
|
||||
version: None,
|
||||
..Default::default()
|
||||
};
|
||||
|
||||
let describe_result = self.namespace.describe_table(describe_request).await;
|
||||
@@ -171,6 +173,7 @@ impl Database for LanceNamespaceDatabase {
|
||||
// Drop the existing table - must succeed
|
||||
let drop_request = DropTableRequest {
|
||||
id: Some(table_id.clone()),
|
||||
..Default::default()
|
||||
};
|
||||
self.namespace
|
||||
.drop_table(drop_request)
|
||||
@@ -202,29 +205,24 @@ impl Database for LanceNamespaceDatabase {
|
||||
let mut table_id = request.namespace.clone();
|
||||
table_id.push(request.name.clone());
|
||||
|
||||
let create_empty_request = CreateEmptyTableRequest {
|
||||
let declare_request = DeclareTableRequest {
|
||||
id: Some(table_id.clone()),
|
||||
location: None,
|
||||
properties: if self.storage_options.is_empty() {
|
||||
None
|
||||
} else {
|
||||
Some(self.storage_options.clone())
|
||||
},
|
||||
vend_credentials: None,
|
||||
..Default::default()
|
||||
};
|
||||
|
||||
let create_empty_response = self
|
||||
let declare_response = self
|
||||
.namespace
|
||||
.create_empty_table(create_empty_request)
|
||||
.declare_table(declare_request)
|
||||
.await
|
||||
.map_err(|e| Error::Runtime {
|
||||
message: format!("Failed to create empty table: {}", e),
|
||||
message: format!("Failed to declare table: {}", e),
|
||||
})?;
|
||||
|
||||
let location = create_empty_response
|
||||
.location
|
||||
.ok_or_else(|| Error::Runtime {
|
||||
message: "Table location is missing from create_empty_table response".to_string(),
|
||||
})?;
|
||||
let location = declare_response.location.ok_or_else(|| Error::Runtime {
|
||||
message: "Table location is missing from declare_table response".to_string(),
|
||||
})?;
|
||||
|
||||
let native_table = NativeTable::create_from_namespace(
|
||||
self.namespace.clone(),
|
||||
@@ -281,7 +279,10 @@ impl Database for LanceNamespaceDatabase {
|
||||
let mut table_id = namespace.to_vec();
|
||||
table_id.push(name.to_string());
|
||||
|
||||
let drop_request = DropTableRequest { id: Some(table_id) };
|
||||
let drop_request = DropTableRequest {
|
||||
id: Some(table_id),
|
||||
..Default::default()
|
||||
};
|
||||
self.namespace
|
||||
.drop_table(drop_request)
|
||||
.await
|
||||
@@ -438,6 +439,7 @@ mod tests {
|
||||
id: Some(vec!["test_ns".into()]),
|
||||
mode: None,
|
||||
properties: None,
|
||||
..Default::default()
|
||||
})
|
||||
.await
|
||||
.expect("Failed to create namespace");
|
||||
@@ -499,6 +501,7 @@ mod tests {
|
||||
id: Some(vec!["test_ns".into()]),
|
||||
mode: None,
|
||||
properties: None,
|
||||
..Default::default()
|
||||
})
|
||||
.await
|
||||
.expect("Failed to create namespace");
|
||||
@@ -563,6 +566,7 @@ mod tests {
|
||||
id: Some(vec!["test_ns".into()]),
|
||||
mode: None,
|
||||
properties: None,
|
||||
..Default::default()
|
||||
})
|
||||
.await
|
||||
.expect("Failed to create namespace");
|
||||
@@ -647,6 +651,7 @@ mod tests {
|
||||
id: Some(vec!["test_ns".into()]),
|
||||
mode: None,
|
||||
properties: None,
|
||||
..Default::default()
|
||||
})
|
||||
.await
|
||||
.expect("Failed to create namespace");
|
||||
@@ -703,6 +708,7 @@ mod tests {
|
||||
id: Some(vec!["test_ns".into()]),
|
||||
mode: None,
|
||||
properties: None,
|
||||
..Default::default()
|
||||
})
|
||||
.await
|
||||
.expect("Failed to create namespace");
|
||||
@@ -784,6 +790,7 @@ mod tests {
|
||||
id: Some(vec!["test_ns".into()]),
|
||||
mode: None,
|
||||
properties: None,
|
||||
..Default::default()
|
||||
})
|
||||
.await
|
||||
.expect("Failed to create namespace");
|
||||
@@ -818,6 +825,7 @@ mod tests {
|
||||
id: Some(vec!["test_ns".into()]),
|
||||
mode: None,
|
||||
properties: None,
|
||||
..Default::default()
|
||||
})
|
||||
.await
|
||||
.expect("Failed to create namespace");
|
||||
|
||||
@@ -8,10 +8,9 @@ use datafusion_execution::{disk_manager::DiskManagerBuilder, runtime_env::Runtim
|
||||
use datafusion_expr::col;
|
||||
use futures::TryStreamExt;
|
||||
use lance_core::ROW_ID;
|
||||
use lance_datafusion::exec::SessionContextExt;
|
||||
|
||||
use crate::{
|
||||
arrow::{SendableRecordBatchStream, SendableRecordBatchStreamExt, SimpleRecordBatchStream},
|
||||
arrow::{SendableRecordBatchStream, SimpleRecordBatchStream},
|
||||
connect,
|
||||
database::{CreateTableData, CreateTableRequest, Database},
|
||||
dataloader::permutation::{
|
||||
@@ -178,12 +177,17 @@ impl PermutationBuilder {
|
||||
.build_arc()
|
||||
.unwrap(),
|
||||
);
|
||||
let df = ctx
|
||||
.read_one_shot(data.into_df_stream())
|
||||
let batches = data
|
||||
.map_err(|e| Error::Other {
|
||||
message: format!("Failed to setup sort by split id: {}", e),
|
||||
source: Some(e.into()),
|
||||
})?;
|
||||
})
|
||||
.try_collect::<Vec<_>>()
|
||||
.await?;
|
||||
let df = ctx.read_batches(batches).map_err(|e| Error::Other {
|
||||
message: format!("Failed to setup sort by split id: {}", e),
|
||||
source: Some(e.into()),
|
||||
})?;
|
||||
let df_stream = df
|
||||
.sort_by(vec![col(SPLIT_ID_COLUMN)])
|
||||
.map_err(|e| Error::Other {
|
||||
|
||||
@@ -1720,6 +1720,7 @@ mod tests {
|
||||
id: Some(namespace.clone()),
|
||||
mode: None,
|
||||
properties: None,
|
||||
..Default::default()
|
||||
})
|
||||
.await
|
||||
.expect("Failed to create namespace");
|
||||
@@ -1746,6 +1747,7 @@ mod tests {
|
||||
id: Some(namespace.clone()),
|
||||
page_token: None,
|
||||
limit: None,
|
||||
..Default::default()
|
||||
})
|
||||
.await
|
||||
.expect("Failed to list tables");
|
||||
@@ -1758,6 +1760,7 @@ mod tests {
|
||||
id: Some(namespace.clone()),
|
||||
page_token: None,
|
||||
limit: None,
|
||||
..Default::default()
|
||||
})
|
||||
.await
|
||||
.unwrap();
|
||||
@@ -1799,6 +1802,7 @@ mod tests {
|
||||
id: Some(namespace.clone()),
|
||||
mode: None,
|
||||
properties: None,
|
||||
..Default::default()
|
||||
})
|
||||
.await
|
||||
.expect("Failed to create namespace");
|
||||
@@ -1825,6 +1829,7 @@ mod tests {
|
||||
id: Some(namespace.clone()),
|
||||
page_token: None,
|
||||
limit: None,
|
||||
..Default::default()
|
||||
})
|
||||
.await
|
||||
.unwrap();
|
||||
|
||||
@@ -42,8 +42,8 @@ use lance_index::DatasetIndexExt;
|
||||
use lance_index::IndexType;
|
||||
use lance_io::object_store::LanceNamespaceStorageOptionsProvider;
|
||||
use lance_namespace::models::{
|
||||
QueryTableRequest as NsQueryTableRequest, QueryTableRequestFullTextQuery,
|
||||
QueryTableRequestVector, StringFtsQuery,
|
||||
QueryTableRequest as NsQueryTableRequest, QueryTableRequestColumns,
|
||||
QueryTableRequestFullTextQuery, QueryTableRequestVector, StringFtsQuery,
|
||||
};
|
||||
use lance_namespace::LanceNamespace;
|
||||
use lance_table::format::Manifest;
|
||||
@@ -1411,26 +1411,35 @@ impl Table {
|
||||
let projected_plans = plans
|
||||
.into_iter()
|
||||
.enumerate()
|
||||
.map(|(plan_i, plan)| {
|
||||
let query_index = datafusion_common::ScalarValue::Int32(Some(plan_i as i32));
|
||||
let query_index_expr =
|
||||
datafusion_physical_plan::expressions::Literal::new(query_index);
|
||||
let query_index_expr =
|
||||
Arc::new(query_index_expr) as Arc<dyn datafusion_physical_plan::PhysicalExpr>;
|
||||
let mut projections = vec![(query_index_expr, "query_index".to_string())];
|
||||
projections.extend_from_slice(&project_all_columns);
|
||||
let projection = ProjectionExec::try_new(projections, plan).unwrap();
|
||||
Arc::new(projection) as Arc<dyn datafusion_physical_plan::ExecutionPlan>
|
||||
})
|
||||
.collect::<Vec<_>>();
|
||||
.map(
|
||||
|(plan_i, plan)| -> Result<Arc<dyn datafusion_physical_plan::ExecutionPlan>> {
|
||||
let query_index = datafusion_common::ScalarValue::Int32(Some(plan_i as i32));
|
||||
let query_index_expr =
|
||||
datafusion_physical_plan::expressions::Literal::new(query_index);
|
||||
let query_index_expr = Arc::new(query_index_expr)
|
||||
as Arc<dyn datafusion_physical_plan::PhysicalExpr>;
|
||||
let mut projections = vec![(query_index_expr, "query_index".to_string())];
|
||||
projections.extend_from_slice(&project_all_columns);
|
||||
let projection =
|
||||
ProjectionExec::try_new(projections, plan).map_err(|e| Error::Runtime {
|
||||
message: format!("Failed to build projection plan: {e}"),
|
||||
})?;
|
||||
Ok(Arc::new(projection) as Arc<dyn datafusion_physical_plan::ExecutionPlan>)
|
||||
},
|
||||
)
|
||||
.collect::<Result<Vec<_>>>()?;
|
||||
|
||||
let unioned = Arc::new(UnionExec::new(projected_plans));
|
||||
let unioned = UnionExec::try_new(projected_plans).map_err(|e| Error::Runtime {
|
||||
message: format!("Failed to union query plans: {e}"),
|
||||
})?;
|
||||
// We require 1 partition in the final output
|
||||
let repartitioned = RepartitionExec::try_new(
|
||||
unioned,
|
||||
datafusion_physical_plan::Partitioning::RoundRobinBatch(1),
|
||||
)
|
||||
.unwrap();
|
||||
.map_err(|e| Error::Runtime {
|
||||
message: format!("Failed to repartition query plans: {e}"),
|
||||
})?;
|
||||
Ok(Arc::new(repartitioned))
|
||||
}
|
||||
|
||||
@@ -2334,6 +2343,23 @@ impl NativeTable {
|
||||
|
||||
/// Convert an AnyQuery to the namespace QueryTableRequest format.
|
||||
fn convert_to_namespace_query(&self, query: &AnyQuery) -> Result<NsQueryTableRequest> {
|
||||
let to_namespace_columns =
|
||||
|select: &Select| -> Result<Option<Box<QueryTableRequestColumns>>> {
|
||||
match select {
|
||||
Select::All => Ok(None),
|
||||
Select::Columns(cols) => {
|
||||
let mut columns = QueryTableRequestColumns::new();
|
||||
columns.column_names = Some(cols.clone());
|
||||
Ok(Some(Box::new(columns)))
|
||||
}
|
||||
Select::Dynamic(_) => Err(Error::NotSupported {
|
||||
message:
|
||||
"Dynamic column selection is not supported for server-side queries"
|
||||
.to_string(),
|
||||
}),
|
||||
}
|
||||
};
|
||||
|
||||
match query {
|
||||
AnyQuery::VectorQuery(vq) => {
|
||||
// Extract the query vector(s)
|
||||
@@ -2345,19 +2371,6 @@ impl NativeTable {
|
||||
None => None,
|
||||
};
|
||||
|
||||
// Convert select to columns list
|
||||
let columns = match &vq.base.select {
|
||||
Select::All => None,
|
||||
Select::Columns(cols) => Some(cols.clone()),
|
||||
Select::Dynamic(_) => {
|
||||
return Err(Error::NotSupported {
|
||||
message:
|
||||
"Dynamic column selection is not supported for server-side queries"
|
||||
.to_string(),
|
||||
});
|
||||
}
|
||||
};
|
||||
|
||||
// Check for unsupported features
|
||||
if vq.base.reranker.is_some() {
|
||||
return Err(Error::NotSupported {
|
||||
@@ -2365,6 +2378,8 @@ impl NativeTable {
|
||||
});
|
||||
}
|
||||
|
||||
let columns = to_namespace_columns(&vq.base.select)?;
|
||||
|
||||
// Convert FTS query if present
|
||||
let full_text_query = vq.base.full_text_search.as_ref().map(|fts| {
|
||||
let columns = fts.columns();
|
||||
@@ -2402,6 +2417,7 @@ impl NativeTable {
|
||||
bypass_vector_index: Some(!vq.use_index),
|
||||
full_text_query,
|
||||
version: None,
|
||||
..Default::default()
|
||||
})
|
||||
}
|
||||
AnyQuery::Query(q) => {
|
||||
@@ -2419,16 +2435,7 @@ impl NativeTable {
|
||||
.map(|f| self.filter_to_sql(f))
|
||||
.transpose()?;
|
||||
|
||||
let columns = match &q.select {
|
||||
Select::All => None,
|
||||
Select::Columns(cols) => Some(cols.clone()),
|
||||
Select::Dynamic(_) => {
|
||||
return Err(Error::NotSupported {
|
||||
message: "Dynamic columns are not supported for server-side query"
|
||||
.to_string(),
|
||||
});
|
||||
}
|
||||
};
|
||||
let columns = to_namespace_columns(&q.select)?;
|
||||
|
||||
// Handle full text search if present
|
||||
let full_text_query = q.full_text_search.as_ref().map(|fts| {
|
||||
@@ -2472,6 +2479,7 @@ impl NativeTable {
|
||||
fast_search: None,
|
||||
lower_bound: None,
|
||||
upper_bound: None,
|
||||
..Default::default()
|
||||
})
|
||||
}
|
||||
}
|
||||
@@ -5146,7 +5154,13 @@ mod tests {
|
||||
assert_eq!(ns_request.k, 10);
|
||||
assert_eq!(ns_request.offset, Some(5));
|
||||
assert_eq!(ns_request.filter, Some("id > 0".to_string()));
|
||||
assert_eq!(ns_request.columns, Some(vec!["id".to_string()]));
|
||||
assert_eq!(
|
||||
ns_request
|
||||
.columns
|
||||
.as_ref()
|
||||
.and_then(|cols| cols.column_names.clone()),
|
||||
Some(vec!["id".to_string()])
|
||||
);
|
||||
assert_eq!(ns_request.vector_column, Some("vector".to_string()));
|
||||
assert_eq!(ns_request.distance_type, Some("l2".to_string()));
|
||||
assert!(ns_request.vector.single_vector.is_some());
|
||||
@@ -5187,7 +5201,13 @@ mod tests {
|
||||
assert_eq!(ns_request.k, 20);
|
||||
assert_eq!(ns_request.offset, Some(5));
|
||||
assert_eq!(ns_request.filter, Some("id > 5".to_string()));
|
||||
assert_eq!(ns_request.columns, Some(vec!["id".to_string()]));
|
||||
assert_eq!(
|
||||
ns_request
|
||||
.columns
|
||||
.as_ref()
|
||||
.and_then(|cols| cols.column_names.clone()),
|
||||
Some(vec!["id".to_string()])
|
||||
);
|
||||
assert_eq!(ns_request.with_row_id, Some(true));
|
||||
assert_eq!(ns_request.bypass_vector_index, Some(true));
|
||||
assert!(ns_request.vector_column.is_none()); // No vector column for plain queries
|
||||
|
||||
@@ -101,6 +101,7 @@ impl DatasetRef {
|
||||
refs::Ref::Version(_, Some(target_ver)) => version != target_ver,
|
||||
refs::Ref::Version(_, None) => true, // No specific version, always checkout
|
||||
refs::Ref::Tag(_) => true, // Always checkout for tags
|
||||
refs::Ref::VersionNumber(target_ver) => version != target_ver,
|
||||
};
|
||||
|
||||
if should_checkout {
|
||||
|
||||
Reference in New Issue
Block a user