Compare commits

..

1 Commits

Author SHA1 Message Date
Lance Release
4c97b6d3ee Bump version: 0.31.0-beta.1 → 0.31.0-beta.2 2026-06-23 16:22:35 +00:00
13 changed files with 204 additions and 461 deletions

96
Cargo.lock generated
View File

@@ -3432,8 +3432,8 @@ checksum = "42703706b716c37f96a77aea830392ad231f44c9e9a67872fa5548707e11b11c"
[[package]]
name = "fsst"
version = "9.0.0-beta.8"
source = "git+https://github.com/lance-format/lance.git?rev=4acefffd5d38f88003fce681ae1d0871077ce5e7#4acefffd5d38f88003fce681ae1d0871077ce5e7"
version = "9.0.0-beta.2"
source = "git+https://github.com/lance-format/lance.git?tag=v9.0.0-beta.2#23211989de648fefc4454f5eee09ec176f0a465b"
dependencies = [
"arrow-array",
"rand 0.9.4",
@@ -4735,8 +4735,8 @@ checksum = "e037a2e1d8d5fdbd49b16a4ea09d5d6401c1f29eca5ff29d03d3824dba16256a"
[[package]]
name = "lance"
version = "9.0.0-beta.8"
source = "git+https://github.com/lance-format/lance.git?rev=4acefffd5d38f88003fce681ae1d0871077ce5e7#4acefffd5d38f88003fce681ae1d0871077ce5e7"
version = "9.0.0-beta.2"
source = "git+https://github.com/lance-format/lance.git?tag=v9.0.0-beta.2#23211989de648fefc4454f5eee09ec176f0a465b"
dependencies = [
"arc-swap",
"arrow",
@@ -4771,7 +4771,7 @@ dependencies = [
"futures",
"half",
"humantime",
"itertools 0.14.0",
"itertools 0.13.0",
"lance-arrow",
"lance-core",
"lance-datafusion",
@@ -4810,8 +4810,8 @@ dependencies = [
[[package]]
name = "lance-arrow"
version = "9.0.0-beta.8"
source = "git+https://github.com/lance-format/lance.git?rev=4acefffd5d38f88003fce681ae1d0871077ce5e7#4acefffd5d38f88003fce681ae1d0871077ce5e7"
version = "9.0.0-beta.2"
source = "git+https://github.com/lance-format/lance.git?tag=v9.0.0-beta.2#23211989de648fefc4454f5eee09ec176f0a465b"
dependencies = [
"arrow-array",
"arrow-buffer",
@@ -4832,7 +4832,7 @@ dependencies = [
[[package]]
name = "lance-arrow-scalar"
version = "58.0.0"
source = "git+https://github.com/lance-format/lance.git?rev=4acefffd5d38f88003fce681ae1d0871077ce5e7#4acefffd5d38f88003fce681ae1d0871077ce5e7"
source = "git+https://github.com/lance-format/lance.git?tag=v9.0.0-beta.2#23211989de648fefc4454f5eee09ec176f0a465b"
dependencies = [
"arrow-array",
"arrow-buffer",
@@ -4846,7 +4846,7 @@ dependencies = [
[[package]]
name = "lance-arrow-stats"
version = "58.0.0"
source = "git+https://github.com/lance-format/lance.git?rev=4acefffd5d38f88003fce681ae1d0871077ce5e7#4acefffd5d38f88003fce681ae1d0871077ce5e7"
source = "git+https://github.com/lance-format/lance.git?tag=v9.0.0-beta.2#23211989de648fefc4454f5eee09ec176f0a465b"
dependencies = [
"arrow-array",
"arrow-schema",
@@ -4855,8 +4855,8 @@ dependencies = [
[[package]]
name = "lance-bitpacking"
version = "9.0.0-beta.8"
source = "git+https://github.com/lance-format/lance.git?rev=4acefffd5d38f88003fce681ae1d0871077ce5e7#4acefffd5d38f88003fce681ae1d0871077ce5e7"
version = "9.0.0-beta.2"
source = "git+https://github.com/lance-format/lance.git?tag=v9.0.0-beta.2#23211989de648fefc4454f5eee09ec176f0a465b"
dependencies = [
"arrayref",
"paste",
@@ -4865,8 +4865,8 @@ dependencies = [
[[package]]
name = "lance-core"
version = "9.0.0-beta.8"
source = "git+https://github.com/lance-format/lance.git?rev=4acefffd5d38f88003fce681ae1d0871077ce5e7#4acefffd5d38f88003fce681ae1d0871077ce5e7"
version = "9.0.0-beta.2"
source = "git+https://github.com/lance-format/lance.git?tag=v9.0.0-beta.2#23211989de648fefc4454f5eee09ec176f0a465b"
dependencies = [
"arrow-array",
"arrow-buffer",
@@ -4878,7 +4878,7 @@ dependencies = [
"datafusion-common",
"datafusion-sql",
"futures",
"itertools 0.14.0",
"itertools 0.13.0",
"lance-arrow",
"lance-derive",
"libc",
@@ -4904,8 +4904,8 @@ dependencies = [
[[package]]
name = "lance-datafusion"
version = "9.0.0-beta.8"
source = "git+https://github.com/lance-format/lance.git?rev=4acefffd5d38f88003fce681ae1d0871077ce5e7#4acefffd5d38f88003fce681ae1d0871077ce5e7"
version = "9.0.0-beta.2"
source = "git+https://github.com/lance-format/lance.git?tag=v9.0.0-beta.2#23211989de648fefc4454f5eee09ec176f0a465b"
dependencies = [
"arrow",
"arrow-array",
@@ -4935,8 +4935,8 @@ dependencies = [
[[package]]
name = "lance-datagen"
version = "9.0.0-beta.8"
source = "git+https://github.com/lance-format/lance.git?rev=4acefffd5d38f88003fce681ae1d0871077ce5e7#4acefffd5d38f88003fce681ae1d0871077ce5e7"
version = "9.0.0-beta.2"
source = "git+https://github.com/lance-format/lance.git?tag=v9.0.0-beta.2#23211989de648fefc4454f5eee09ec176f0a465b"
dependencies = [
"arrow",
"arrow-array",
@@ -4953,8 +4953,8 @@ dependencies = [
[[package]]
name = "lance-derive"
version = "9.0.0-beta.8"
source = "git+https://github.com/lance-format/lance.git?rev=4acefffd5d38f88003fce681ae1d0871077ce5e7#4acefffd5d38f88003fce681ae1d0871077ce5e7"
version = "9.0.0-beta.2"
source = "git+https://github.com/lance-format/lance.git?tag=v9.0.0-beta.2#23211989de648fefc4454f5eee09ec176f0a465b"
dependencies = [
"proc-macro2",
"quote",
@@ -4963,8 +4963,8 @@ dependencies = [
[[package]]
name = "lance-encoding"
version = "9.0.0-beta.8"
source = "git+https://github.com/lance-format/lance.git?rev=4acefffd5d38f88003fce681ae1d0871077ce5e7#4acefffd5d38f88003fce681ae1d0871077ce5e7"
version = "9.0.0-beta.2"
source = "git+https://github.com/lance-format/lance.git?tag=v9.0.0-beta.2#23211989de648fefc4454f5eee09ec176f0a465b"
dependencies = [
"arrow-arith",
"arrow-array",
@@ -4980,7 +4980,7 @@ dependencies = [
"futures",
"hex",
"hyperloglogplus",
"itertools 0.14.0",
"itertools 0.13.0",
"lance-arrow",
"lance-bitpacking",
"lance-core",
@@ -4999,8 +4999,8 @@ dependencies = [
[[package]]
name = "lance-file"
version = "9.0.0-beta.8"
source = "git+https://github.com/lance-format/lance.git?rev=4acefffd5d38f88003fce681ae1d0871077ce5e7#4acefffd5d38f88003fce681ae1d0871077ce5e7"
version = "9.0.0-beta.2"
source = "git+https://github.com/lance-format/lance.git?tag=v9.0.0-beta.2#23211989de648fefc4454f5eee09ec176f0a465b"
dependencies = [
"arrow-arith",
"arrow-array",
@@ -5030,8 +5030,8 @@ dependencies = [
[[package]]
name = "lance-index"
version = "9.0.0-beta.8"
source = "git+https://github.com/lance-format/lance.git?rev=4acefffd5d38f88003fce681ae1d0871077ce5e7#4acefffd5d38f88003fce681ae1d0871077ce5e7"
version = "9.0.0-beta.2"
source = "git+https://github.com/lance-format/lance.git?tag=v9.0.0-beta.2#23211989de648fefc4454f5eee09ec176f0a465b"
dependencies = [
"arc-swap",
"arrow",
@@ -5056,7 +5056,7 @@ dependencies = [
"fst",
"futures",
"half",
"itertools 0.14.0",
"itertools 0.13.0",
"jieba-rs",
"jsonb",
"lance-arrow",
@@ -5096,8 +5096,8 @@ dependencies = [
[[package]]
name = "lance-io"
version = "9.0.0-beta.8"
source = "git+https://github.com/lance-format/lance.git?rev=4acefffd5d38f88003fce681ae1d0871077ce5e7#4acefffd5d38f88003fce681ae1d0871077ce5e7"
version = "9.0.0-beta.2"
source = "git+https://github.com/lance-format/lance.git?tag=v9.0.0-beta.2#23211989de648fefc4454f5eee09ec176f0a465b"
dependencies = [
"arrow",
"arrow-arith",
@@ -5138,8 +5138,8 @@ dependencies = [
[[package]]
name = "lance-linalg"
version = "9.0.0-beta.8"
source = "git+https://github.com/lance-format/lance.git?rev=4acefffd5d38f88003fce681ae1d0871077ce5e7#4acefffd5d38f88003fce681ae1d0871077ce5e7"
version = "9.0.0-beta.2"
source = "git+https://github.com/lance-format/lance.git?tag=v9.0.0-beta.2#23211989de648fefc4454f5eee09ec176f0a465b"
dependencies = [
"arrow-array",
"arrow-buffer",
@@ -5155,8 +5155,8 @@ dependencies = [
[[package]]
name = "lance-namespace"
version = "9.0.0-beta.8"
source = "git+https://github.com/lance-format/lance.git?rev=4acefffd5d38f88003fce681ae1d0871077ce5e7#4acefffd5d38f88003fce681ae1d0871077ce5e7"
version = "9.0.0-beta.2"
source = "git+https://github.com/lance-format/lance.git?tag=v9.0.0-beta.2#23211989de648fefc4454f5eee09ec176f0a465b"
dependencies = [
"arrow",
"async-trait",
@@ -5168,8 +5168,8 @@ dependencies = [
[[package]]
name = "lance-namespace-impls"
version = "9.0.0-beta.8"
source = "git+https://github.com/lance-format/lance.git?rev=4acefffd5d38f88003fce681ae1d0871077ce5e7#4acefffd5d38f88003fce681ae1d0871077ce5e7"
version = "9.0.0-beta.2"
source = "git+https://github.com/lance-format/lance.git?tag=v9.0.0-beta.2#23211989de648fefc4454f5eee09ec176f0a465b"
dependencies = [
"arrow",
"arrow-ipc",
@@ -5223,15 +5223,15 @@ dependencies = [
[[package]]
name = "lance-select"
version = "9.0.0-beta.8"
source = "git+https://github.com/lance-format/lance.git?rev=4acefffd5d38f88003fce681ae1d0871077ce5e7#4acefffd5d38f88003fce681ae1d0871077ce5e7"
version = "9.0.0-beta.2"
source = "git+https://github.com/lance-format/lance.git?tag=v9.0.0-beta.2#23211989de648fefc4454f5eee09ec176f0a465b"
dependencies = [
"arrow-array",
"arrow-buffer",
"arrow-schema",
"byteorder",
"bytes",
"itertools 0.14.0",
"itertools 0.13.0",
"lance-core",
"roaring",
"tracing",
@@ -5239,8 +5239,8 @@ dependencies = [
[[package]]
name = "lance-table"
version = "9.0.0-beta.8"
source = "git+https://github.com/lance-format/lance.git?rev=4acefffd5d38f88003fce681ae1d0871077ce5e7#4acefffd5d38f88003fce681ae1d0871077ce5e7"
version = "9.0.0-beta.2"
source = "git+https://github.com/lance-format/lance.git?tag=v9.0.0-beta.2#23211989de648fefc4454f5eee09ec176f0a465b"
dependencies = [
"arrow",
"arrow-array",
@@ -5279,8 +5279,8 @@ dependencies = [
[[package]]
name = "lance-testing"
version = "9.0.0-beta.8"
source = "git+https://github.com/lance-format/lance.git?rev=4acefffd5d38f88003fce681ae1d0871077ce5e7#4acefffd5d38f88003fce681ae1d0871077ce5e7"
version = "9.0.0-beta.2"
source = "git+https://github.com/lance-format/lance.git?tag=v9.0.0-beta.2#23211989de648fefc4454f5eee09ec176f0a465b"
dependencies = [
"arrow-array",
"arrow-schema",
@@ -5293,8 +5293,8 @@ dependencies = [
[[package]]
name = "lance-tokenizer"
version = "9.0.0-beta.8"
source = "git+https://github.com/lance-format/lance.git?rev=4acefffd5d38f88003fce681ae1d0871077ce5e7#4acefffd5d38f88003fce681ae1d0871077ce5e7"
version = "9.0.0-beta.2"
source = "git+https://github.com/lance-format/lance.git?tag=v9.0.0-beta.2#23211989de648fefc4454f5eee09ec176f0a465b"
dependencies = [
"icu_segmenter",
"jieba-rs",
@@ -5307,7 +5307,7 @@ dependencies = [
[[package]]
name = "lancedb"
version = "0.31.0-beta.2"
version = "0.31.0-beta.1"
dependencies = [
"ahash",
"anyhow",
@@ -5390,7 +5390,7 @@ dependencies = [
[[package]]
name = "lancedb-nodejs"
version = "0.31.0-beta.2"
version = "0.31.0-beta.1"
dependencies = [
"arrow-array",
"arrow-buffer",
@@ -5415,7 +5415,7 @@ dependencies = [
[[package]]
name = "lancedb-python"
version = "0.34.0-beta.2"
version = "0.34.0-beta.1"
dependencies = [
"arrow",
"async-trait",

View File

@@ -13,20 +13,20 @@ categories = ["database-implementations"]
rust-version = "1.91.0"
[workspace.dependencies]
lance = { "version" = "=9.0.0-beta.8", default-features = false, "rev" = "4acefffd5d38f88003fce681ae1d0871077ce5e7", "git" = "https://github.com/lance-format/lance.git" }
lance-core = { "version" = "=9.0.0-beta.8", "rev" = "4acefffd5d38f88003fce681ae1d0871077ce5e7", "git" = "https://github.com/lance-format/lance.git" }
lance-datagen = { "version" = "=9.0.0-beta.8", "rev" = "4acefffd5d38f88003fce681ae1d0871077ce5e7", "git" = "https://github.com/lance-format/lance.git" }
lance-file = { "version" = "=9.0.0-beta.8", "rev" = "4acefffd5d38f88003fce681ae1d0871077ce5e7", "git" = "https://github.com/lance-format/lance.git" }
lance-io = { "version" = "=9.0.0-beta.8", default-features = false, "rev" = "4acefffd5d38f88003fce681ae1d0871077ce5e7", "git" = "https://github.com/lance-format/lance.git" }
lance-index = { "version" = "=9.0.0-beta.8", "rev" = "4acefffd5d38f88003fce681ae1d0871077ce5e7", "git" = "https://github.com/lance-format/lance.git" }
lance-linalg = { "version" = "=9.0.0-beta.8", "rev" = "4acefffd5d38f88003fce681ae1d0871077ce5e7", "git" = "https://github.com/lance-format/lance.git" }
lance-namespace = { "version" = "=9.0.0-beta.8", "rev" = "4acefffd5d38f88003fce681ae1d0871077ce5e7", "git" = "https://github.com/lance-format/lance.git" }
lance-namespace-impls = { "version" = "=9.0.0-beta.8", default-features = false, "rev" = "4acefffd5d38f88003fce681ae1d0871077ce5e7", "git" = "https://github.com/lance-format/lance.git" }
lance-table = { "version" = "=9.0.0-beta.8", "rev" = "4acefffd5d38f88003fce681ae1d0871077ce5e7", "git" = "https://github.com/lance-format/lance.git" }
lance-testing = { "version" = "=9.0.0-beta.8", "rev" = "4acefffd5d38f88003fce681ae1d0871077ce5e7", "git" = "https://github.com/lance-format/lance.git" }
lance-datafusion = { "version" = "=9.0.0-beta.8", "rev" = "4acefffd5d38f88003fce681ae1d0871077ce5e7", "git" = "https://github.com/lance-format/lance.git" }
lance-encoding = { "version" = "=9.0.0-beta.8", "rev" = "4acefffd5d38f88003fce681ae1d0871077ce5e7", "git" = "https://github.com/lance-format/lance.git" }
lance-arrow = { "version" = "=9.0.0-beta.8", "rev" = "4acefffd5d38f88003fce681ae1d0871077ce5e7", "git" = "https://github.com/lance-format/lance.git" }
lance = { "version" = "=9.0.0-beta.2", default-features = false, "tag" = "v9.0.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
lance-core = { "version" = "=9.0.0-beta.2", "tag" = "v9.0.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
lance-datagen = { "version" = "=9.0.0-beta.2", "tag" = "v9.0.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
lance-file = { "version" = "=9.0.0-beta.2", "tag" = "v9.0.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
lance-io = { "version" = "=9.0.0-beta.2", default-features = false, "tag" = "v9.0.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
lance-index = { "version" = "=9.0.0-beta.2", "tag" = "v9.0.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
lance-linalg = { "version" = "=9.0.0-beta.2", "tag" = "v9.0.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
lance-namespace = { "version" = "=9.0.0-beta.2", "tag" = "v9.0.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
lance-namespace-impls = { "version" = "=9.0.0-beta.2", default-features = false, "tag" = "v9.0.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
lance-table = { "version" = "=9.0.0-beta.2", "tag" = "v9.0.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
lance-testing = { "version" = "=9.0.0-beta.2", "tag" = "v9.0.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
lance-datafusion = { "version" = "=9.0.0-beta.2", "tag" = "v9.0.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
lance-encoding = { "version" = "=9.0.0-beta.2", "tag" = "v9.0.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
lance-arrow = { "version" = "=9.0.0-beta.2", "tag" = "v9.0.0-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 }

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.8</lance-core.version>
<lance-core.version>9.0.0-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>

View File

@@ -1,12 +1,12 @@
{
"name": "@lancedb/lancedb",
"version": "0.31.0-beta.2",
"version": "0.31.0-beta.1",
"lockfileVersion": 3,
"requires": true,
"packages": {
"": {
"name": "@lancedb/lancedb",
"version": "0.31.0-beta.2",
"version": "0.31.0-beta.1",
"cpu": [
"x64",
"arm64"

View File

@@ -81,7 +81,6 @@ class ColPaliEmbeddings(EmbeddingFunction):
warnings.warn(
"use_token_pooling is deprecated, use pooling_strategy=None instead",
DeprecationWarning,
stacklevel=2,
)
self.pooling_strategy = None

View File

@@ -124,7 +124,6 @@ class RemoteDBConnection(DBConnection):
"request_thread_pool is no longer used and will be removed in "
"a future release.",
DeprecationWarning,
stacklevel=2,
)
if connection_timeout is not None:
@@ -133,7 +132,6 @@ class RemoteDBConnection(DBConnection):
"release. Please use client_config.timeout_config.connect_timeout "
"instead.",
DeprecationWarning,
stacklevel=2,
)
client_config.timeout_config.connect_timeout = timedelta(
seconds=connection_timeout
@@ -144,7 +142,6 @@ class RemoteDBConnection(DBConnection):
"read_timeout is deprecated and will be removed in a future release. "
"Please use client_config.timeout_config.read_timeout instead.",
DeprecationWarning,
stacklevel=2,
)
client_config.timeout_config.read_timeout = timedelta(seconds=read_timeout)

View File

@@ -845,8 +845,7 @@ class RemoteTable(Table):
"""
warnings.warn(
"cleanup_old_versions() is a no-op on LanceDB Cloud. "
"Tables are automatically cleaned up and optimized.",
stacklevel=2,
"Tables are automatically cleaned up and optimized."
)
pass
@@ -858,8 +857,7 @@ class RemoteTable(Table):
"""
warnings.warn(
"compact_files() is a no-op on LanceDB Cloud. "
"Tables are automatically compacted and optimized.",
stacklevel=2,
"Tables are automatically compacted and optimized."
)
pass
@@ -876,8 +874,7 @@ class RemoteTable(Table):
"""
warnings.warn(
"optimize() is a no-op on LanceDB Cloud. "
"Indices are optimized automatically.",
stacklevel=2,
"Indices are optimized automatically."
)
pass

View File

@@ -3409,20 +3409,18 @@ class LanceTable(Table):
if data_storage_version is not None:
warnings.warn(
"setting data_storage_version directly on create_table is deprecated. "
"setting data_storage_version directly on create_table is deprecated. ",
"Use database_options instead.",
DeprecationWarning,
stacklevel=2,
)
if storage_options is None:
storage_options = {}
storage_options["new_table_data_storage_version"] = data_storage_version
if enable_v2_manifest_paths is not None:
warnings.warn(
"setting enable_v2_manifest_paths directly on create_table is "
"setting enable_v2_manifest_paths directly on create_table is ",
"deprecated. Use database_options instead.",
DeprecationWarning,
stacklevel=2,
)
if storage_options is None:
storage_options = {}
@@ -5664,7 +5662,6 @@ class AsyncTable:
"The 'retrain' parameter is deprecated and will be removed in a "
"future version.",
DeprecationWarning,
stacklevel=2,
)
return await self._inner.optimize(

View File

@@ -576,9 +576,6 @@ impl Connection {
/// For LanceNamespaceDatabase, it is the underlying LanceNamespace.
/// For ListingDatabase, it is the equivalent DirectoryNamespace.
/// For RemoteDatabase, it is the equivalent RestNamespace.
///
/// Remote connections using dynamic headers forward them through the
/// namespace client's per-request context provider.
pub async fn namespace_client(&self) -> Result<Arc<dyn lance_namespace::LanceNamespace>> {
self.internal.namespace_client().await
}
@@ -587,9 +584,6 @@ impl Connection {
/// Returns (impl_type, properties) where:
/// - impl_type: "dir" for DirectoryNamespace, "rest" for RestNamespace
/// - properties: configuration properties for the namespace
///
/// Remote connections using dynamic headers cannot be exported because the
/// namespace client config only carries static headers.
pub async fn namespace_client_config(
&self,
) -> Result<(String, std::collections::HashMap<String, String>)> {

View File

@@ -14,6 +14,7 @@ use lance::io::{ObjectStore, ObjectStoreParams, WrappingObjectStore};
use lance_datafusion::utils::StreamingWriteSource;
use lance_encoding::version::LanceFileVersion;
use lance_io::object_store::{StorageOptionsAccessor, StorageOptionsProvider};
use lance_table::io::commit::commit_handler_from_url;
use object_store::local::LocalFileSystem;
use snafu::ResultExt;
@@ -234,9 +235,11 @@ impl ListingDatabaseOptionsBuilder {
/// We will have two tables named `table1` and `table2`.
#[derive(Debug)]
pub struct ListingDatabase {
object_store: Arc<ObjectStore>,
query_string: Option<String>,
pub(crate) uri: String,
pub(crate) base_path: object_store::path::Path,
// the object store wrapper to use on write path
pub(crate) store_wrapper: Option<Arc<dyn WrappingObjectStore>>,
@@ -255,13 +258,8 @@ pub struct ListingDatabase {
// Session for object stores and caching
session: Arc<lance::session::Session>,
// Namespace-backed database for child namespace operations (manifest mode).
// Namespace-backed database for child namespace operations
namespace_database: Arc<LanceNamespaceDatabase>,
// V1 (manifest-disabled) directory namespace for root table lifecycle, so root
// drops are soft-deletes and purge/table_status are available. Shares the same root
// as `namespace_database` but in directory mode.
root_namespace_database: Arc<LanceNamespaceDatabase>,
}
impl std::fmt::Display for ListingDatabase {
@@ -282,6 +280,7 @@ impl std::fmt::Display for ListingDatabase {
}
}
const LANCE_EXTENSION: &str = "lance";
const ENGINE: &str = "engine";
const MIRRORED_STORE: &str = "mirroredStore";
@@ -343,39 +342,6 @@ impl ListingDatabase {
))
}
/// Build the V1 (manifest-disabled) directory namespace used for *root* table
/// lifecycle ops.
///
/// Root tables in a listing database are flat `<name>.lance` directories; soft-delete
/// (drop/purge/TTL) is a V1-only mechanism, so root ops go through this namespace.
/// Child namespaces are manifest-backed and handled by the separate
/// (manifest-enabled) `namespace_database`.
async fn connect_root_namespace_database(
uri: &str,
storage_options: HashMap<String, String>,
namespace_client_properties: HashMap<String, String>,
read_consistency_interval: Option<std::time::Duration>,
session: Arc<lance::session::Session>,
) -> Result<Arc<LanceNamespaceDatabase>> {
let mut ns_properties = Self::build_namespace_client_properties(
uri,
&storage_options,
namespace_client_properties,
);
ns_properties.insert("manifest_enabled".to_string(), "false".to_string());
Ok(Arc::new(
LanceNamespaceDatabase::connect(
"dir",
ns_properties,
storage_options,
read_consistency_interval,
Some(session),
HashSet::new(),
)
.await?,
))
}
async fn prepare_namespace_root(
uri: &str,
storage_options: &HashMap<String, String>,
@@ -582,7 +548,7 @@ impl ListingDatabase {
},
..Default::default()
};
let (object_store, _base_path) = ObjectStore::from_uri_and_params(
let (object_store, base_path) = ObjectStore::from_uri_and_params(
session.store_registry(),
&plain_uri,
&os_params,
@@ -611,18 +577,12 @@ impl ListingDatabase {
session.clone(),
)
.await?;
let root_namespace_database = Self::connect_root_namespace_database(
&table_base_uri,
options.storage_options.clone(),
request.namespace_client_properties.clone(),
request.read_consistency_interval,
session.clone(),
)
.await?;
Ok(Self {
uri: table_base_uri,
query_string,
base_path,
object_store,
store_wrapper: write_store_wrapper,
read_consistency_interval: request.read_consistency_interval,
storage_options: options.storage_options,
@@ -630,7 +590,6 @@ impl ListingDatabase {
new_table_config: options.new_table_config,
session,
namespace_database,
root_namespace_database,
})
}
Err(_) => {
@@ -654,7 +613,7 @@ impl ListingDatabase {
session: Option<Arc<lance::session::Session>>,
) -> Result<Self> {
let session = session.unwrap_or_else(|| Arc::new(lance::session::Session::default()));
let (object_store, _base_path) = ObjectStore::from_uri_and_params(
let (object_store, base_path) = ObjectStore::from_uri_and_params(
session.store_registry(),
path,
&ObjectStoreParams::default(),
@@ -665,14 +624,6 @@ impl ListingDatabase {
}
let namespace_database = Self::connect_namespace_database(
path,
HashMap::new(),
namespace_client_properties.clone(),
read_consistency_interval,
session.clone(),
)
.await?;
let root_namespace_database = Self::connect_root_namespace_database(
path,
HashMap::new(),
namespace_client_properties,
@@ -684,6 +635,8 @@ impl ListingDatabase {
Ok(Self {
uri: path.to_string(),
query_string: None,
base_path,
object_store,
store_wrapper: None,
read_consistency_interval,
storage_options: HashMap::new(),
@@ -691,7 +644,6 @@ impl ListingDatabase {
new_table_config,
session,
namespace_database,
root_namespace_database,
})
}
@@ -753,10 +705,42 @@ impl ListingDatabase {
self.namespace_database.clone()
}
/// The V1 directory namespace used for root table lifecycle (soft-delete drop, purge,
/// table_status, O(1) listing).
fn root_namespace_database(&self) -> Arc<LanceNamespaceDatabase> {
self.root_namespace_database.clone()
async fn drop_tables(&self, names: Vec<String>) -> Result<()> {
let object_store_params = ObjectStoreParams {
storage_options_accessor: if self.storage_options.is_empty() {
None
} else {
Some(Arc::new(StorageOptionsAccessor::with_static_options(
self.storage_options.clone(),
)))
},
..Default::default()
};
let mut uri = self.uri.clone();
if let Some(query_string) = &self.query_string {
uri.push_str(&format!("?{}", query_string));
}
let commit_handler = commit_handler_from_url(&uri, &Some(object_store_params)).await?;
for name in names {
let dir_name = format!("{}.{}", name, LANCE_EXTENSION);
let full_path = self.base_path.clone().join(dir_name.clone());
commit_handler.delete(&full_path).await?;
self.object_store
.remove_dir_all(full_path.clone())
.await
.map_err(|err| match err {
// this error is not lance::Error::DatasetNotFound, as the method
// `remove_dir_all` may be used to remove something not be a dataset
lance::Error::NotFound { .. } => Error::TableNotFound {
name: name.clone(),
source: Box::new(err),
},
_ => Error::from(err),
})?;
}
Ok(())
}
/// Inherit storage options from the connection into the target map
@@ -962,43 +946,88 @@ impl Database for ListingDatabase {
if !request.namespace_path.is_empty() {
return self.namespace_database().table_names(request).await;
}
// Root tables: the V1 namespace lists them in a single read_dir (O(1) requests)
// and excludes soft-deleted tables, instead of a per-table probe here.
self.root_namespace_database().table_names(request).await
let mut f = self
.object_store
.read_dir(self.base_path.clone())
.await?
.iter()
.map(Path::new)
.filter(|path| {
let is_lance = path
.extension()
.and_then(|e| e.to_str())
.map(|e| e == LANCE_EXTENSION);
is_lance.unwrap_or(false)
})
.filter_map(|p| p.file_stem().and_then(|s| s.to_str().map(String::from)))
.collect::<Vec<String>>();
f.sort();
if let Some(start_after) = request.start_after {
let index = f
.iter()
.position(|name| name.as_str() > start_after.as_str())
.unwrap_or(f.len());
f.drain(0..index);
}
if let Some(limit) = request.limit {
f.truncate(limit as usize);
}
Ok(f)
}
async fn list_tables(&self, request: ListTablesRequest) -> Result<ListTablesResponse> {
if request.id.as_ref().map(|v| !v.is_empty()).unwrap_or(false) {
return self.namespace_database().list_tables(request).await;
}
self.root_namespace_database().list_tables(request).await
let mut f = self
.object_store
.read_dir(self.base_path.clone())
.await?
.iter()
.map(Path::new)
.filter(|path| {
let is_lance = path
.extension()
.and_then(|e| e.to_str())
.map(|e| e == LANCE_EXTENSION);
is_lance.unwrap_or(false)
})
.filter_map(|p| p.file_stem().and_then(|s| s.to_str().map(String::from)))
.collect::<Vec<String>>();
f.sort();
// Handle pagination with page_token
if let Some(ref page_token) = request.page_token {
let index = f
.iter()
.position(|name| name.as_str() > page_token.as_str())
.unwrap_or(f.len());
f.drain(0..index);
}
// Determine if there's a next page
let next_page_token = if let Some(limit) = request.limit {
if f.len() > limit as usize {
let token = f[limit as usize].clone();
f.truncate(limit as usize);
Some(token)
} else {
None
}
} else {
None
};
Ok(ListTablesResponse {
tables: f,
page_token: next_page_token,
})
}
async fn create_table(&self, request: CreateTableRequest) -> Result<Arc<dyn BaseTable>> {
if !request.namespace_path.is_empty() {
return self.namespace_database().create_table(request).await;
}
let mut request = request;
// Re-creating a soft-deleted table is a revive: clear the delete marker (via the
// V1 root namespace, under its lifecycle lock so a concurrent purge can't race),
// making the table live again, then overwrite its data through the native create
// path below (preserving lineage as a new version). A plain native create would
// leave the marker in place, keeping the table hidden.
if matches!(
self.root_namespace_database()
.namespace_client()
.await?
.table_status(Some(vec![request.name.clone()]))
.await?,
lance_namespace::TableLifecycle::SoftDeleted { .. }
) {
self.root_namespace_database()
.namespace_client()
.await?
.undelete_table(Some(vec![request.name.clone()]))
.await?;
request.mode = CreateTableMode::Overwrite;
}
// Use provided location if available, otherwise derive from table name
let table_uri = request
.location
@@ -1117,19 +1146,6 @@ impl Database for ListingDatabase {
if !request.namespace_path.is_empty() {
return self.namespace_database().open_table(request).await;
}
// A soft-deleted (dropped-but-not-purged) table must read as absent even though
// its data still exists on disk. Consult the V1 root namespace (which owns the
// marker); if soft-deleted, route to it so the open surfaces TableNotFound.
if matches!(
self.root_namespace_database()
.namespace_client()
.await?
.table_status(Some(vec![request.name.clone()]))
.await?,
lance_namespace::TableLifecycle::SoftDeleted { .. }
) {
return self.root_namespace_database().open_table(request).await;
}
// Use provided location if available, otherwise derive from table name
let table_uri = request
.location
@@ -1229,23 +1245,20 @@ impl Database for ListingDatabase {
.drop_table(name, namespace_path)
.await;
}
// Root table: route through the V1 namespace so the drop is a soft-delete (writes
// a marker, leaves data for later purge) rather than an immediate remove_dir_all.
self.root_namespace_database()
.drop_table(name, namespace_path)
.await
self.drop_tables(vec![name.to_string()]).await
}
#[allow(deprecated)]
async fn drop_all_tables(&self, namespace_path: &[String]) -> Result<()> {
// Check if namespace parameter is provided
if !namespace_path.is_empty() {
return self
.namespace_database()
.drop_all_tables(namespace_path)
.await;
}
self.root_namespace_database()
.drop_all_tables(namespace_path)
.await
let tables = self.table_names(TableNamesRequest::default()).await?;
self.drop_tables(tables).await
}
fn as_any(&self) -> &dyn std::any::Any {
@@ -1253,9 +1266,6 @@ impl Database for ListingDatabase {
}
async fn namespace_client(&self) -> Result<Arc<dyn lance_namespace::LanceNamespace>> {
// Returns the manifest-backed namespace so callers can operate on child
// namespaces (multi-level table ids) through the client. Root-table soft-delete
// lifecycle (table_status/purge) is reached via the V1 root namespace internally.
self.namespace_database.namespace_client().await
}
@@ -2605,67 +2615,4 @@ mod tests {
.unwrap();
assert!(post_drop.tables.is_empty());
}
/// Root-table drop is a soft-delete routed through the V1 namespace: the table is
/// hidden from listing/open but its data survives until purged, and re-creating it
/// revives it. Verifies the consolidation end-to-end at the ListingDatabase level.
#[tokio::test]
async fn test_root_table_soft_delete_lifecycle() {
let (_tempdir, db) = setup_database().await;
let schema = Arc::new(Schema::new(vec![Field::new("id", DataType::Int32, false)]));
let create = |name: &str| CreateTableRequest {
name: name.to_string(),
namespace_path: vec![],
data: Box::new(RecordBatch::new_empty(schema.clone())) as Box<dyn Scannable>,
mode: CreateTableMode::Create,
write_options: Default::default(),
location: None,
namespace_client: None,
};
let open = |name: &str| OpenTableRequest {
name: name.to_string(),
namespace_path: vec![],
index_cache_size: None,
lance_read_params: None,
location: None,
namespace_client: None,
managed_versioning: None,
};
db.create_table(create("t")).await.unwrap();
db.drop_table("t", &[]).await.unwrap();
// Hidden from listing and not openable...
#[allow(deprecated)]
let names = db.table_names(TableNamesRequest::default()).await.unwrap();
assert!(!names.contains(&"t".to_string()));
assert!(matches!(
db.open_table(open("t")).await,
Err(Error::TableNotFound { .. })
));
// ...but data survives: it shows up as purgable via the V1 root namespace.
let root_ns = db
.root_namespace_database()
.namespace_client()
.await
.unwrap();
let purgable = root_ns.list_purgable_tables(None).await.unwrap();
assert_eq!(purgable.len(), 1);
assert_eq!(purgable[0].id, vec!["t".to_string()]);
// Re-creating revives it.
db.create_table(create("t")).await.unwrap();
db.open_table(open("t")).await.unwrap();
#[allow(deprecated)]
let names = db.table_names(TableNamesRequest::default()).await.unwrap();
assert!(names.contains(&"t".to_string()));
assert!(root_ns.list_purgable_tables(None).await.unwrap().is_empty());
// Drop then purge reclaims it for good.
db.drop_table("t", &[]).await.unwrap();
let purged = root_ns.purge_tables(None).await.unwrap();
assert_eq!(purged, vec![vec!["t".to_string()]]);
assert!(root_ns.list_purgable_tables(None).await.unwrap().is_empty());
}
}

View File

@@ -583,9 +583,9 @@ impl Database for LanceNamespaceDatabase {
self.namespace
.drop_table(drop_request)
.await
// Preserve TableNotFound (e.g. dropping a non-existent table) rather than
// flattening every failure to a generic Runtime error.
.map_err(|e| map_namespace_lance_error(e, name))?;
.map_err(|e| Error::Runtime {
message: format!("Failed to drop table: {}", e),
})?;
Ok(())
}

View File

@@ -459,14 +459,12 @@ impl<S: HttpSend> RestfulLanceDbClient<S> {
config: &ClientConfig,
) -> Result<HeaderMap> {
let mut headers = HeaderMap::new();
if !api_key.is_empty() {
headers.insert(
HeaderName::from_static("x-api-key"),
HeaderValue::from_str(api_key).map_err(|_| Error::InvalidInput {
message: "non-ascii api key provided".to_string(),
})?,
);
}
headers.insert(
HeaderName::from_static("x-api-key"),
HeaderValue::from_str(api_key).map_err(|_| Error::InvalidInput {
message: "non-ascii api key provided".to_string(),
})?,
);
if region == "local" {
let host = format!("{}.local.api.lancedb.com", db_name);
headers.insert(
@@ -1007,33 +1005,6 @@ mod tests {
assert!(!config_tls.assert_hostname);
}
#[test]
fn test_default_headers_skip_empty_api_key() {
let headers = RestfulLanceDbClient::<Sender>::default_headers(
"",
"us-east-1",
"db-name",
false,
&RemoteOptions::default(),
None,
&ClientConfig::default(),
)
.unwrap();
assert!(!headers.contains_key("x-api-key"));
let headers = RestfulLanceDbClient::<Sender>::default_headers(
"api-key",
"us-east-1",
"db-name",
false,
&RemoteOptions::default(),
None,
&ClientConfig::default(),
)
.unwrap();
assert_eq!(headers.get("x-api-key").unwrap(), "api-key");
}
// Test implementation of HeaderProvider
#[derive(Debug, Clone)]
struct TestHeaderProvider {

View File

@@ -7,7 +7,6 @@ use std::sync::Arc;
use async_trait::async_trait;
use http::StatusCode;
use lance_io::object_store::StorageOptions;
use lance_namespace_impls::{DynamicContextProvider, OperationInfo};
use moka::future::Cache;
use reqwest::header::CONTENT_TYPE;
@@ -27,9 +26,7 @@ use crate::remote::util::stream_as_body;
use crate::table::BaseTable;
use super::ARROW_STREAM_CONTENT_TYPE;
use super::client::{
ClientConfig, HeaderProvider, HttpSend, RequestResultExt, RestfulLanceDbClient, Sender,
};
use super::client::{ClientConfig, HttpSend, RequestResultExt, RestfulLanceDbClient, Sender};
use super::table::RemoteTable;
use super::util::parse_server_version;
@@ -197,66 +194,10 @@ pub struct RemoteDatabase<S: HttpSend = Sender> {
uri: String,
/// Headers to pass to the namespace client for authentication
namespace_headers: HashMap<String, String>,
namespace_context_provider: Option<Arc<dyn DynamicContextProvider>>,
/// TLS configuration for mTLS support
tls_config: Option<super::client::TlsConfig>,
}
#[derive(Clone)]
struct NamespaceHeaderProviderContext {
header_provider: Arc<dyn HeaderProvider>,
}
impl std::fmt::Debug for NamespaceHeaderProviderContext {
fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
f.debug_struct("NamespaceHeaderProviderContext")
.field("header_provider", &"Some(...)")
.finish()
}
}
impl DynamicContextProvider for NamespaceHeaderProviderContext {
fn provide_context(&self, _info: &OperationInfo) -> HashMap<String, String> {
let header_provider = Arc::clone(&self.header_provider);
let handle = match std::thread::Builder::new()
.name("lancedb-namespace-headers".to_string())
.spawn(move || {
tokio::runtime::Builder::new_current_thread()
.enable_all()
.build()
.map_err(|e| Error::Runtime {
message: format!(
"Failed to create runtime for namespace header provider: {e}"
),
})?
.block_on(header_provider.get_headers())
}) {
Ok(handle) => handle,
Err(err) => {
log::warn!("Failed to spawn dynamic namespace header provider thread: {err}");
return HashMap::new();
}
};
let headers = handle.join();
match headers {
Ok(Ok(headers)) => headers
.into_iter()
.map(|(key, value)| (format!("headers.{key}"), value))
.collect(),
Ok(Err(err)) => {
log::warn!("Failed to get dynamic namespace headers: {err}");
HashMap::new()
}
Err(_) => {
log::warn!("Dynamic namespace header provider panicked");
HashMap::new()
}
}
}
}
impl RemoteDatabase {
pub fn try_new(
uri: &str,
@@ -287,16 +228,6 @@ impl RemoteDatabase {
})
.collect();
let namespace_context_provider =
client_config
.header_provider
.as_ref()
.map(|header_provider| {
Arc::new(NamespaceHeaderProviderContext {
header_provider: Arc::clone(header_provider),
}) as Arc<dyn DynamicContextProvider>
});
let client = RestfulLanceDbClient::try_new(
&parsed,
region,
@@ -316,7 +247,6 @@ impl RemoteDatabase {
table_cache,
uri: uri.to_owned(),
namespace_headers,
namespace_context_provider,
tls_config: client_config.tls_config,
})
}
@@ -341,7 +271,6 @@ mod test_utils {
table_cache: Cache::new(0),
uri: "http://localhost".to_string(),
namespace_headers: HashMap::new(),
namespace_context_provider: None,
tls_config: None,
}
}
@@ -352,18 +281,11 @@ mod test_utils {
T: Into<reqwest::Body>,
{
let client = client_with_handler_and_config(handler, config.clone());
let namespace_context_provider =
config.header_provider.as_ref().map(|header_provider| {
Arc::new(NamespaceHeaderProviderContext {
header_provider: Arc::clone(header_provider),
}) as Arc<dyn DynamicContextProvider>
});
Self {
client,
table_cache: Cache::new(0),
uri: "http://localhost".to_string(),
namespace_headers: config.extra_headers.clone(),
namespace_context_provider,
tls_config: config.tls_config.clone(),
}
}
@@ -837,12 +759,9 @@ impl<S: HttpSend> Database for RemoteDatabase<S> {
// Create a RestNamespace pointing to the same remote host with the same authentication headers
let mut builder = lance_namespace_impls::RestNamespaceBuilder::new(self.client.host())
.delimiter(&self.client.id_delimiter)
// TODO: support header provider
.headers(self.namespace_headers.clone());
if let Some(context_provider) = &self.namespace_context_provider {
builder = builder.context_provider(Arc::clone(context_provider));
}
// Apply mTLS configuration if present
if let Some(tls_config) = &self.tls_config {
if let Some(cert_file) = &tls_config.cert_file {
@@ -862,14 +781,6 @@ impl<S: HttpSend> Database for RemoteDatabase<S> {
}
async fn namespace_client_config(&self) -> Result<(String, HashMap<String, String>)> {
if self.namespace_context_provider.is_some() {
return Err(Error::NotSupported {
message:
"Cannot export a namespace client config when dynamic headers are configured; use LanceDB connection namespace methods instead"
.to_string(),
});
}
let mut properties = HashMap::new();
properties.insert("uri".to_string(), self.client.host().to_string());
properties.insert("delimiter".to_string(), self.client.id_delimiter.clone());
@@ -921,13 +832,12 @@ impl From<StorageOptions> for RemoteOptions {
#[cfg(test)]
mod tests {
use super::{NamespaceHeaderProviderContext, build_cache_key};
use super::build_cache_key;
use std::collections::HashMap;
use std::sync::{Arc, OnceLock};
use arrow_array::{Int32Array, RecordBatch};
use arrow_schema::{DataType, Field, Schema};
use lance_namespace_impls::{DynamicContextProvider, OperationInfo};
use crate::connection::ConnectBuilder;
use crate::{
@@ -1792,75 +1702,6 @@ mod tests {
assert!(namespace_client.is_ok());
}
#[test]
fn test_namespace_header_provider_context_maps_headers() {
#[derive(Debug)]
struct TestHeaderProvider;
#[async_trait::async_trait]
impl HeaderProvider for TestHeaderProvider {
async fn get_headers(&self) -> crate::Result<HashMap<String, String>> {
Ok(HashMap::from([(
"authorization".to_string(),
"Bearer token".to_string(),
)]))
}
}
let context_provider = NamespaceHeaderProviderContext {
header_provider: Arc::new(TestHeaderProvider) as Arc<dyn HeaderProvider>,
};
let context =
context_provider.provide_context(&OperationInfo::new("list_tables", "namespace"));
assert_eq!(
context.get("headers.authorization"),
Some(&"Bearer token".to_string())
);
}
#[tokio::test]
async fn test_namespace_client_supports_dynamic_headers() {
#[derive(Debug)]
struct TestHeaderProvider;
#[async_trait::async_trait]
impl HeaderProvider for TestHeaderProvider {
async fn get_headers(&self) -> crate::Result<HashMap<String, String>> {
Ok(HashMap::from([(
"authorization".to_string(),
"Bearer token".to_string(),
)]))
}
}
let client_config = ClientConfig {
header_provider: Some(Arc::new(TestHeaderProvider) as Arc<dyn HeaderProvider>),
..Default::default()
};
let conn = Connection::new_with_handler_and_config(
|_| {
http::Response::builder()
.status(200)
.body(r#"{"tables": []}"#)
.unwrap()
},
client_config,
);
let namespace_client = conn.namespace_client().await;
assert!(namespace_client.is_ok());
match conn.namespace_client_config().await {
Err(Error::NotSupported { message })
if message.contains("dynamic headers are configured") => {}
Err(err) => panic!("expected NotSupported, got {err:?}"),
Ok(_) => panic!("expected namespace_client_config to reject dynamic headers"),
}
}
/// Integration tests using RestAdapter to run RemoteDatabase against a real namespace server
mod rest_adapter_integration {
use super::*;