Compare commits

..

2 Commits

Author SHA1 Message Date
westonpace 1d624f21de fix: remove .lance-reserved marker after writing table in namespace mode
lance v6.0.0-beta.2 introduced a `.lance-reserved` marker file in
declare_table to prevent directory scans from seeing incomplete tables.
lancedb calls declare_table to get the canonical URI, then writes data
separately via NativeTable::create_from_namespace, but never cleaned up
the marker. This caused list_directory_tables() to skip tables with the
marker, making newly created tables invisible in table_names().

After writing the table, delete the marker using the dataset's configured
object store so it works for both local and cloud storage.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-23 13:08:20 -07:00
lancedb automation 1decf28f2a chore: update lance dependency to v6.0.0-beta.2 2026-04-23 05:24:01 +00:00
47 changed files with 409 additions and 1122 deletions
+1 -1
View File
@@ -1,5 +1,5 @@
[tool.bumpversion]
current_version = "0.28.0-beta.10"
current_version = "0.28.0-beta.9"
parse = """(?x)
(?P<major>0|[1-9]\\d*)\\.
(?P<minor>0|[1-9]\\d*)\\.
-18
View File
@@ -1,18 +0,0 @@
version: 2
# Scope: the root Cargo workspace, which produces the Rust binaries we
# ship to users (the Node.js and Python native extensions). The
# `rust/lancedb` library crate shares the same lockfile; its consumers
# pick their own dependency versions, but bumping transitive deps here
# keeps the binaries we ship current.
updates:
- package-ecosystem: cargo
directory: /
schedule:
interval: weekly
open-pull-requests-limit: 10
groups:
rust-minor-patch:
update-types:
- minor
- patch
+3 -9
View File
@@ -21,9 +21,6 @@ jobs:
linux:
name: Python ${{ matrix.config.platform }} manylinux${{ matrix.config.manylinux }}
timeout-minutes: 60
permissions:
id-token: write
contents: read
strategy:
matrix:
config:
@@ -63,12 +60,10 @@ jobs:
- uses: ./.github/workflows/upload_wheel
if: startsWith(github.ref, 'refs/tags/python-v')
with:
pypi_token: ${{ secrets.LANCEDB_PYPI_API_TOKEN }}
fury_token: ${{ secrets.FURY_TOKEN }}
mac:
timeout-minutes: 90
permissions:
id-token: write
contents: read
runs-on: ${{ matrix.config.runner }}
strategy:
matrix:
@@ -93,12 +88,10 @@ jobs:
- uses: ./.github/workflows/upload_wheel
if: startsWith(github.ref, 'refs/tags/python-v')
with:
pypi_token: ${{ secrets.LANCEDB_PYPI_API_TOKEN }}
fury_token: ${{ secrets.FURY_TOKEN }}
windows:
timeout-minutes: 60
permissions:
id-token: write
contents: read
runs-on: windows-latest
steps:
- uses: actions/checkout@v4
@@ -117,6 +110,7 @@ jobs:
- uses: ./.github/workflows/upload_wheel
if: startsWith(github.ref, 'refs/tags/python-v')
with:
pypi_token: ${{ secrets.LANCEDB_PYPI_API_TOKEN }}
fury_token: ${{ secrets.FURY_TOKEN }}
gh-release:
if: startsWith(github.ref, 'refs/tags/python-v')
-14
View File
@@ -9,10 +9,7 @@ on:
- Cargo.toml
- Cargo.lock
- rust-toolchain.toml
- deny.toml
- rust/**
- nodejs/Cargo.toml
- python/Cargo.toml
- .github/workflows/rust.yml
permissions:
@@ -59,17 +56,6 @@ jobs:
- name: Run clippy (without remote feature)
run: cargo clippy --profile ci --workspace --tests -- -D warnings
deny:
# Supply-chain checks: advisories, licenses, banned crates, and source
# restrictions. Configuration lives in `deny.toml` at the workspace root.
timeout-minutes: 10
runs-on: ubuntu-24.04
steps:
- uses: actions/checkout@v4
- uses: EmbarkStudios/cargo-deny-action@v2
with:
command: check advisories bans licenses sources
build-no-lock:
runs-on: ubuntu-24.04
timeout-minutes: 30
+21 -10
View File
@@ -2,6 +2,9 @@ name: upload-wheel
description: "Upload wheels to Pypi"
inputs:
pypi_token:
required: true
description: "release token for the repo"
fury_token:
required: true
description: "release token for the fury repo"
@@ -9,6 +12,12 @@ inputs:
runs:
using: "composite"
steps:
- name: Install dependencies
shell: bash
run: |
python -m pip install --upgrade pip
pip install twine
python3 -m pip install --upgrade pkginfo
- name: Choose repo
shell: bash
id: choose_repo
@@ -18,17 +27,19 @@ runs:
else
echo "repo=pypi" >> $GITHUB_OUTPUT
fi
- name: Publish to Fury
if: steps.choose_repo.outputs.repo == 'fury'
- name: Publish to PyPI
shell: bash
env:
FURY_TOKEN: ${{ inputs.fury_token }}
PYPI_TOKEN: ${{ inputs.pypi_token }}
run: |
WHEEL=$(ls target/wheels/lancedb-*.whl 2> /dev/null | head -n 1)
echo "Uploading $WHEEL to Fury"
curl -f -F package=@$WHEEL https://$FURY_TOKEN@push.fury.io/lancedb/
- name: Publish to PyPI
if: steps.choose_repo.outputs.repo == 'pypi'
uses: pypa/gh-action-pypi-publish@release/v1
with:
packages-dir: target/wheels/
if [[ ${{ steps.choose_repo.outputs.repo }} == fury ]]; then
WHEEL=$(ls target/wheels/lancedb-*.whl 2> /dev/null | head -n 1)
echo "Uploading $WHEEL to Fury"
curl -f -F package=@$WHEEL https://$FURY_TOKEN@push.fury.io/lancedb/
else
twine upload --repository ${{ steps.choose_repo.outputs.repo }} \
--username __token__ \
--password $PYPI_TOKEN \
target/wheels/lancedb-*.whl
fi
Generated
+248 -264
View File
File diff suppressed because it is too large Load Diff
+33 -31
View File
@@ -1,5 +1,7 @@
[workspace]
members = ["rust/lancedb", "nodejs", "python"]
# Python package needs to be built by maturin.
exclude = ["python"]
resolver = "2"
[workspace.package]
@@ -13,40 +15,40 @@ categories = ["database-implementations"]
rust-version = "1.91.0"
[workspace.dependencies]
lance = { "version" = "=6.0.0-beta.7", default-features = false, "tag" = "v6.0.0-beta.7", "git" = "https://github.com/lance-format/lance.git" }
lance-core = { "version" = "=6.0.0-beta.7", "tag" = "v6.0.0-beta.7", "git" = "https://github.com/lance-format/lance.git" }
lance-datagen = { "version" = "=6.0.0-beta.7", "tag" = "v6.0.0-beta.7", "git" = "https://github.com/lance-format/lance.git" }
lance-file = { "version" = "=6.0.0-beta.7", "tag" = "v6.0.0-beta.7", "git" = "https://github.com/lance-format/lance.git" }
lance-io = { "version" = "=6.0.0-beta.7", default-features = false, "tag" = "v6.0.0-beta.7", "git" = "https://github.com/lance-format/lance.git" }
lance-index = { "version" = "=6.0.0-beta.7", "tag" = "v6.0.0-beta.7", "git" = "https://github.com/lance-format/lance.git" }
lance-linalg = { "version" = "=6.0.0-beta.7", "tag" = "v6.0.0-beta.7", "git" = "https://github.com/lance-format/lance.git" }
lance-namespace = { "version" = "=6.0.0-beta.7", "tag" = "v6.0.0-beta.7", "git" = "https://github.com/lance-format/lance.git" }
lance-namespace-impls = { "version" = "=6.0.0-beta.7", default-features = false, "tag" = "v6.0.0-beta.7", "git" = "https://github.com/lance-format/lance.git" }
lance-table = { "version" = "=6.0.0-beta.7", "tag" = "v6.0.0-beta.7", "git" = "https://github.com/lance-format/lance.git" }
lance-testing = { "version" = "=6.0.0-beta.7", "tag" = "v6.0.0-beta.7", "git" = "https://github.com/lance-format/lance.git" }
lance-datafusion = { "version" = "=6.0.0-beta.7", "tag" = "v6.0.0-beta.7", "git" = "https://github.com/lance-format/lance.git" }
lance-encoding = { "version" = "=6.0.0-beta.7", "tag" = "v6.0.0-beta.7", "git" = "https://github.com/lance-format/lance.git" }
lance-arrow = { "version" = "=6.0.0-beta.7", "tag" = "v6.0.0-beta.7", "git" = "https://github.com/lance-format/lance.git" }
lance = { "version" = "=6.0.0-beta.2", default-features = false, "tag" = "v6.0.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
lance-core = { "version" = "=6.0.0-beta.2", "tag" = "v6.0.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
lance-datagen = { "version" = "=6.0.0-beta.2", "tag" = "v6.0.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
lance-file = { "version" = "=6.0.0-beta.2", "tag" = "v6.0.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
lance-io = { "version" = "=6.0.0-beta.2", default-features = false, "tag" = "v6.0.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
lance-index = { "version" = "=6.0.0-beta.2", "tag" = "v6.0.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
lance-linalg = { "version" = "=6.0.0-beta.2", "tag" = "v6.0.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
lance-namespace = { "version" = "=6.0.0-beta.2", "tag" = "v6.0.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
lance-namespace-impls = { "version" = "=6.0.0-beta.2", default-features = false, "tag" = "v6.0.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
lance-table = { "version" = "=6.0.0-beta.2", "tag" = "v6.0.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
lance-testing = { "version" = "=6.0.0-beta.2", "tag" = "v6.0.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
lance-datafusion = { "version" = "=6.0.0-beta.2", "tag" = "v6.0.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
lance-encoding = { "version" = "=6.0.0-beta.2", "tag" = "v6.0.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
lance-arrow = { "version" = "=6.0.0-beta.2", "tag" = "v6.0.0-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 }
arrow-array = "58.0.0"
arrow-data = "58.0.0"
arrow-ipc = "58.0.0"
arrow-ord = "58.0.0"
arrow-schema = "58.0.0"
arrow-select = "58.0.0"
arrow-cast = "58.0.0"
arrow = { version = "57.2", optional = false }
arrow-array = "57.2"
arrow-data = "57.2"
arrow-ipc = "57.2"
arrow-ord = "57.2"
arrow-schema = "57.2"
arrow-select = "57.2"
arrow-cast = "57.2"
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 = "52.1", default-features = false }
datafusion-catalog = "52.1"
datafusion-common = { version = "52.1", default-features = false }
datafusion-execution = "52.1"
datafusion-expr = "52.1"
datafusion-functions = "52.1"
datafusion-physical-plan = "52.1"
datafusion-physical-expr = "52.1"
datafusion-sql = "52.1"
env_logger = "0.11"
half = { "version" = "2.7.1", default-features = false, features = [
"num-traits",
-172
View File
@@ -1,172 +0,0 @@
# cargo-deny configuration for LanceDB.
#
# Run locally with `cargo deny check`. See
# https://embarkstudios.github.io/cargo-deny/ for the full reference.
# The set of target triples we care about. cargo-deny will only consider
# dependencies that are used on at least one of these targets. Keeping this
# explicit avoids noise from platform-specific crates (e.g. wasm, android,
# ios) that we never actually ship.
[graph]
targets = [
"x86_64-unknown-linux-gnu",
"aarch64-unknown-linux-gnu",
"x86_64-apple-darwin",
"aarch64-apple-darwin",
"x86_64-pc-windows-msvc",
"aarch64-pc-windows-msvc",
]
all-features = true
[output]
feature-depth = 1
# ---------------------------------------------------------------------------
# Advisories: security vulnerabilities and yanked crates.
# ---------------------------------------------------------------------------
[advisories]
version = 2
# Fail the check if any crate in the lockfile has been yanked from crates.io.
# Yanked crates are a signal the author retracted the release (often due to
# bugs or security issues) and should not be depended on.
yanked = "deny"
# Advisory IDs we have explicitly reviewed and chosen to accept. Every
# entry must include a rationale and, where possible, an upstream issue
# pointing to a fix. Revisit this list whenever dependencies are updated.
ignore = [
# rsa: Marvin Attack timing side-channel in PKCS#1 v1.5 decryption.
# Reached only through opendal → reqsign → rsa. We do not use RSA
# decryption in LanceDB ourselves; this is dormant in the signing path.
# No fixed release exists upstream as of this writing.
# https://rustsec.org/advisories/RUSTSEC-2023-0071
{ id = "RUSTSEC-2023-0071", reason = "rsa crate via opendal/reqsign; no fixed upstream release" },
# instant: unmaintained. Pulled in via backoff → instant. Upstream
# recommends switching to `web-time`; fix has to come from backoff.
# https://rustsec.org/advisories/RUSTSEC-2024-0384
{ id = "RUSTSEC-2024-0384", reason = "transitive via backoff; waiting on backoff replacement" },
# paste: unmaintained (author archived the repo). Used transitively by
# datafusion and the arrow ecosystem; widespread, no drop-in replacement.
# https://rustsec.org/advisories/RUSTSEC-2024-0436
{ id = "RUSTSEC-2024-0436", reason = "transitive via datafusion; awaiting ecosystem migration" },
# tantivy: segfault on malformed input due to missing bounds check.
# Pulled in via lance for full-text search. We only feed tantivy
# documents we construct ourselves, not attacker-controlled bytes.
# Tracked for a lance dependency bump.
# https://rustsec.org/advisories/RUSTSEC-2025-0003
{ id = "RUSTSEC-2025-0003", reason = "tantivy via lance; inputs are internally produced, not user-supplied bytes" },
# backoff: unmaintained. Reached only via async-openai. Replacement
# requires async-openai to migrate (or us to drop async-openai).
# https://rustsec.org/advisories/RUSTSEC-2025-0012
{ id = "RUSTSEC-2025-0012", reason = "transitive via async-openai; waiting on upstream migration" },
# number_prefix: unmaintained. Transitive via indicatif → hf-hub.
# No security impact, just maintenance status.
# https://rustsec.org/advisories/RUSTSEC-2025-0119
{ id = "RUSTSEC-2025-0119", reason = "transitive via hf-hub/indicatif; cosmetic formatting crate" },
# rustls-pemfile: unmaintained. Reached from two separate chains:
# rustls-native-certs 0.6 (via hyper-rustls 0.24) and object_store 0.12.
# Both upstream dependencies need to move before we can drop it.
# https://rustsec.org/advisories/RUSTSEC-2025-0134
{ id = "RUSTSEC-2025-0134", reason = "transitive via rustls-native-certs/object_store; waiting on upstream migration" },
# rustls-webpki 0.101.7 (old major line): name-constraint checks for
# URI / wildcard names. Pulled in only via the legacy rustls 0.21 chain
# from aws-smithy-http-client. The 0.103 line we actively use is patched.
# Clearing the 0.101 copy requires the aws-sdk chain to migrate off
# rustls 0.21.
# https://rustsec.org/advisories/RUSTSEC-2026-0098
# https://rustsec.org/advisories/RUSTSEC-2026-0099
{ id = "RUSTSEC-2026-0098", reason = "only affects rustls-webpki 0.101 from legacy aws-smithy/rustls 0.21 chain" },
{ id = "RUSTSEC-2026-0099", reason = "only affects rustls-webpki 0.101 from legacy aws-smithy/rustls 0.21 chain" },
# rustls-webpki 0.101.7: reachable panic in CRL parsing. Same legacy
# rustls 0.21 chain from aws-smithy-http-client as above. The 0.103 line
# we actively use is upgraded to 0.103.13 which contains the fix.
# https://rustsec.org/advisories/RUSTSEC-2026-0104
{ id = "RUSTSEC-2026-0104", reason = "only affects rustls-webpki 0.101 from legacy aws-smithy/rustls 0.21 chain" },
]
# ---------------------------------------------------------------------------
# Licenses: only allow licenses we've reviewed as compatible with Apache-2.0.
# ---------------------------------------------------------------------------
[licenses]
version = 2
# SPDX identifiers for licenses that are compatible with our Apache-2.0
# distribution. Additions require legal review.
allow = [
"Apache-2.0",
"Apache-2.0 WITH LLVM-exception",
"MIT",
"BSD-2-Clause",
"BSD-3-Clause",
"ISC",
"Unicode-3.0",
"Unicode-DFS-2016",
"Zlib",
"CC0-1.0",
"MPL-2.0",
"BSL-1.0",
"OpenSSL",
# 0BSD ("BSD Zero Clause") is effectively public domain — no attribution
# required. Pulled in by `mock_instant`.
"0BSD",
# bzip2-1.0.6 is the permissive upstream bzip2 license (BSD-like). Pulled
# in by `libbz2-rs-sys`, the pure-Rust bzip2 implementation.
"bzip2-1.0.6",
# CDLA-Permissive-2.0 is a permissive data license used by `webpki-roots`
# for the Mozilla CA root bundle. Data-only, distribution-compatible.
"CDLA-Permissive-2.0",
]
confidence-threshold = 0.8
# Crates whose license cannot be determined from Cargo metadata but whose
# license we've manually confirmed from upstream. Keep this list minimal.
[[licenses.clarify]]
# polars-arrow-format omits the `license` field in its Cargo.toml, but the
# upstream repo (pola-rs/polars-arrow-format) is dual-licensed Apache-2.0 OR
# MIT. See https://github.com/pola-rs/polars-arrow-format/blob/main/LICENSE
crate = "polars-arrow-format"
expression = "Apache-2.0 OR MIT"
license-files = []
# ---------------------------------------------------------------------------
# Bans: disallow specific crates and flag dependency hygiene issues.
# ---------------------------------------------------------------------------
[bans]
# Warn (not deny) on duplicate versions of the same crate. In a large
# workspace like this one, duplicates are common and often unavoidable
# transitively. We surface them to discourage growth, but don't fail CI.
multiple-versions = "warn"
# Wildcard version requirements (`foo = "*"`) are a footgun — they let any
# future release in without review. Ban them outright.
wildcards = "deny"
# Internal workspace crates reference each other via `path = "..."`, which
# cargo-deny sees as a wildcard version. That's fine for private workspace
# members (not published to crates.io), so allow it specifically for paths.
allow-wildcard-paths = true
# Features that, if enabled, should cause the check to fail.
deny = []
# Crates to skip when checking for duplicate versions.
skip = []
# Similar to `skip`, but also skips the entire transitive subtree.
skip-tree = []
# ---------------------------------------------------------------------------
# Sources: restrict where crates can come from.
# ---------------------------------------------------------------------------
[sources]
# Deny any registry other than the ones explicitly listed below.
unknown-registry = "deny"
# Deny any git dependency whose host isn't in the allow-list below. This
# prevents accidental pulls from arbitrary forks.
unknown-git = "deny"
allow-registry = ["https://github.com/rust-lang/crates.io-index"]
# Lance is developed in a sibling repo and pulled as a git dependency until
# releases are cut to crates.io. Allow that specific host.
allow-git = [
"https://github.com/lance-format/lance",
]
+1 -1
View File
@@ -14,7 +14,7 @@ Add the following dependency to your `pom.xml`:
<dependency>
<groupId>com.lancedb</groupId>
<artifactId>lancedb-core</artifactId>
<version>0.28.0-beta.10</version>
<version>0.28.0-beta.9</version>
</dependency>
```
@@ -41,29 +41,6 @@ for testing purposes.
***
### manifestEnabled?
```ts
optional manifestEnabled: boolean;
```
(For LanceDB OSS only): use directory namespace manifests as the source
of truth for table metadata. Existing directory-listed root tables are
migrated into the manifest on access.
***
### namespaceClientProperties?
```ts
optional namespaceClientProperties: Record<string, string>;
```
(For LanceDB OSS only): extra properties for the backing namespace
client used by manifest-enabled native connections.
***
### readConsistencyInterval?
```ts
+1 -1
View File
@@ -8,7 +8,7 @@
<parent>
<groupId>com.lancedb</groupId>
<artifactId>lancedb-parent</artifactId>
<version>0.28.0-beta.10</version>
<version>0.28.0-beta.9</version>
<relativePath>../pom.xml</relativePath>
</parent>
+2 -2
View File
@@ -6,7 +6,7 @@
<groupId>com.lancedb</groupId>
<artifactId>lancedb-parent</artifactId>
<version>0.28.0-beta.10</version>
<version>0.28.0-beta.9</version>
<packaging>pom</packaging>
<name>${project.artifactId}</name>
<description>LanceDB Java SDK Parent POM</description>
@@ -28,7 +28,7 @@
<properties>
<project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
<arrow.version>15.0.0</arrow.version>
<lance-core.version>6.0.0-beta.7</lance-core.version>
<lance-core.version>6.0.0-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>
+4 -5
View File
@@ -1,8 +1,7 @@
[package]
name = "lancedb-nodejs"
edition.workspace = true
version = "0.28.0-beta.10"
publish = false
version = "0.28.0-beta.9"
license.workspace = true
description.workspace = true
repository.workspace = true
@@ -16,7 +15,7 @@ crate-type = ["cdylib"]
async-trait.workspace = true
arrow-ipc.workspace = true
arrow-array.workspace = true
arrow-buffer = "58.0.0"
arrow-buffer = "57.2"
half.workspace = true
arrow-schema.workspace = true
env_logger.workspace = true
@@ -32,8 +31,8 @@ lzma-sys = { version = "0.1", features = ["static"] }
log.workspace = true
# Pin to resolve build failures; update periodically for security patches.
aws-lc-sys = "=0.40.0"
aws-lc-rs = "=1.16.3"
aws-lc-sys = "=0.38.0"
aws-lc-rs = "=1.16.1"
[build-dependencies]
napi-build = "2.3.1"
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "@lancedb/lancedb-darwin-arm64",
"version": "0.28.0-beta.10",
"version": "0.28.0-beta.9",
"os": ["darwin"],
"cpu": ["arm64"],
"main": "lancedb.darwin-arm64.node",
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "@lancedb/lancedb-linux-arm64-gnu",
"version": "0.28.0-beta.10",
"version": "0.28.0-beta.9",
"os": ["linux"],
"cpu": ["arm64"],
"main": "lancedb.linux-arm64-gnu.node",
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "@lancedb/lancedb-linux-arm64-musl",
"version": "0.28.0-beta.10",
"version": "0.28.0-beta.9",
"os": ["linux"],
"cpu": ["arm64"],
"main": "lancedb.linux-arm64-musl.node",
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "@lancedb/lancedb-linux-x64-gnu",
"version": "0.28.0-beta.10",
"version": "0.28.0-beta.9",
"os": ["linux"],
"cpu": ["x64"],
"main": "lancedb.linux-x64-gnu.node",
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "@lancedb/lancedb-linux-x64-musl",
"version": "0.28.0-beta.10",
"version": "0.28.0-beta.9",
"os": ["linux"],
"cpu": ["x64"],
"main": "lancedb.linux-x64-musl.node",
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "@lancedb/lancedb-win32-arm64-msvc",
"version": "0.28.0-beta.10",
"version": "0.28.0-beta.9",
"os": [
"win32"
],
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "@lancedb/lancedb-win32-x64-msvc",
"version": "0.28.0-beta.10",
"version": "0.28.0-beta.9",
"os": ["win32"],
"cpu": ["x64"],
"main": "lancedb.win32-x64-msvc.node",
+2 -2
View File
@@ -1,12 +1,12 @@
{
"name": "@lancedb/lancedb",
"version": "0.28.0-beta.10",
"version": "0.28.0-beta.9",
"lockfileVersion": 3,
"requires": true,
"packages": {
"": {
"name": "@lancedb/lancedb",
"version": "0.28.0-beta.10",
"version": "0.28.0-beta.9",
"cpu": [
"x64",
"arm64"
+1 -1
View File
@@ -11,7 +11,7 @@
"ann"
],
"private": false,
"version": "0.28.0-beta.10",
"version": "0.28.0-beta.9",
"main": "dist/index.js",
"exports": {
".": "./dist/index.js",
-6
View File
@@ -67,12 +67,6 @@ impl Connection {
builder = builder.storage_option(key, value);
}
}
if let Some(manifest_enabled) = options.manifest_enabled {
builder = builder.manifest_enabled(manifest_enabled);
}
if let Some(namespace_client_properties) = options.namespace_client_properties {
builder = builder.namespace_client_properties(namespace_client_properties);
}
// Create client config, optionally with header provider
let client_config = options.client_config.unwrap_or_default();
-7
View File
@@ -37,13 +37,6 @@ pub struct ConnectionOptions {
///
/// The available options are described at https://docs.lancedb.com/storage/
pub storage_options: Option<HashMap<String, String>>,
/// (For LanceDB OSS only): use directory namespace manifests as the source
/// of truth for table metadata. Existing directory-listed root tables are
/// migrated into the manifest on access.
pub manifest_enabled: Option<bool>,
/// (For LanceDB OSS only): extra properties for the backing namespace
/// client used by manifest-enabled native connections.
pub namespace_client_properties: Option<HashMap<String, String>>,
/// (For LanceDB OSS only): the session to use for this connection. Holds
/// shared caches and other session-specific state.
pub session: Option<session::Session>,
+1 -1
View File
@@ -1,5 +1,5 @@
[tool.bumpversion]
current_version = "0.31.0-beta.11"
current_version = "0.31.0-beta.9"
parse = """(?x)
(?P<major>0|[1-9]\\d*)\\.
(?P<minor>0|[1-9]\\d*)\\.
+5 -6
View File
@@ -1,7 +1,6 @@
[package]
name = "lancedb-python"
version = "0.31.0-beta.11"
publish = false
version = "0.31.0-beta.9"
edition.workspace = true
description = "Python bindings for LanceDB"
license.workspace = true
@@ -15,7 +14,7 @@ name = "_lancedb"
crate-type = ["cdylib"]
[dependencies]
arrow = { version = "58.0.0", features = ["pyarrow"] }
arrow = { version = "57.2", features = ["pyarrow"] }
async-trait = "0.1"
bytes = "1"
lancedb = { path = "../rust/lancedb", default-features = false }
@@ -25,8 +24,8 @@ lance-namespace-impls.workspace = true
lance-io.workspace = true
env_logger.workspace = true
log.workspace = true
pyo3 = { version = "0.28", features = ["extension-module", "abi3-py39"] }
pyo3-async-runtimes = { version = "0.28", features = [
pyo3 = { version = "0.26", features = ["extension-module", "abi3-py39"] }
pyo3-async-runtimes = { version = "0.26", features = [
"attributes",
"tokio-runtime",
] }
@@ -38,7 +37,7 @@ snafu.workspace = true
tokio = { version = "1.40", features = ["sync"] }
[build-dependencies]
pyo3-build-config = { version = "0.28", features = [
pyo3-build-config = { version = "0.26", features = [
"extension-module",
"abi3-py39",
] }
+4 -30
View File
@@ -73,7 +73,6 @@ def connect(
client_config: Union[ClientConfig, Dict[str, Any], None] = None,
storage_options: Optional[Dict[str, str]] = None,
session: Optional[Session] = None,
manifest_enabled: bool = False,
namespace_client_impl: Optional[str] = None,
namespace_client_properties: Optional[Dict[str, str]] = None,
namespace_client_pushdown_operations: Optional[List[str]] = None,
@@ -112,10 +111,6 @@ def connect(
storage_options: dict, optional
Additional options for the storage backend. See available options at
<https://docs.lancedb.com/storage/>
manifest_enabled : bool, default False
When true for local/native connections, use directory namespace
manifests as the source of truth for table metadata. Existing
directory-listed root tables are migrated into the manifest on access.
session: Session, optional
(For LanceDB OSS only)
A session to use for this connection. Sessions allow you to configure
@@ -163,11 +158,11 @@ def connect(
conn : DBConnection
A connection to a LanceDB database.
"""
if namespace_client_impl is not None:
if namespace_client_properties is None:
if namespace_client_impl is not None or namespace_client_properties is not None:
if namespace_client_impl is None or namespace_client_properties is None:
raise ValueError(
"namespace_client_properties must be provided when "
"namespace_client_impl is set"
"Both namespace_client_impl and "
"namespace_client_properties must be provided"
)
if kwargs:
raise ValueError(f"Unknown keyword arguments: {kwargs}")
@@ -180,12 +175,6 @@ def connect(
namespace_client_pushdown_operations=namespace_client_pushdown_operations,
)
if namespace_client_properties is not None and not manifest_enabled:
raise ValueError(
"namespace_client_impl must be provided when using "
"namespace_client_properties unless manifest_enabled=True"
)
if namespace_client_pushdown_operations is not None:
raise ValueError(
"namespace_client_pushdown_operations is only valid when "
@@ -223,8 +212,6 @@ def connect(
read_consistency_interval=read_consistency_interval,
storage_options=storage_options,
session=session,
manifest_enabled=manifest_enabled,
namespace_client_properties=namespace_client_properties,
)
@@ -302,8 +289,6 @@ def deserialize_conn(
parsed["uri"],
read_consistency_interval=rci,
storage_options=storage_options,
manifest_enabled=parsed.get("manifest_enabled", False),
namespace_client_properties=parsed.get("namespace_client_properties"),
)
else:
raise ValueError(f"Unknown connection_type: {connection_type}")
@@ -319,8 +304,6 @@ async def connect_async(
client_config: Optional[Union[ClientConfig, Dict[str, Any]]] = None,
storage_options: Optional[Dict[str, str]] = None,
session: Optional[Session] = None,
manifest_enabled: bool = False,
namespace_client_properties: Optional[Dict[str, str]] = None,
) -> AsyncConnection:
"""Connect to a LanceDB database.
@@ -360,13 +343,6 @@ async def connect_async(
cache sizes for index and metadata caches, which can significantly
impact memory use and performance. They can also be re-used across
multiple connections to share the same cache state.
manifest_enabled : bool, default False
When true for local/native connections, use directory namespace
manifests as the source of truth for table metadata. Existing
directory-listed root tables are migrated into the manifest on access.
namespace_client_properties : dict, optional
Additional directory namespace client properties to use with
``manifest_enabled=True``.
Examples
--------
@@ -409,8 +385,6 @@ async def connect_async(
client_config,
storage_options,
session,
manifest_enabled,
namespace_client_properties,
)
)
-2
View File
@@ -242,8 +242,6 @@ async def connect(
client_config: Optional[Union[ClientConfig, Dict[str, Any]]],
storage_options: Optional[Dict[str, str]],
session: Optional[Session],
manifest_enabled: bool = False,
namespace_client_properties: Optional[Dict[str, str]] = None,
) -> Connection: ...
class RecordBatchStream:
+1 -9
View File
@@ -590,13 +590,8 @@ class LanceDBConnection(DBConnection):
read_consistency_interval: Optional[timedelta] = None,
storage_options: Optional[Dict[str, str]] = None,
session: Optional[Session] = None,
manifest_enabled: bool = False,
namespace_client_properties: Optional[Dict[str, str]] = None,
_inner: Optional[LanceDbConnection] = None,
):
self.storage_options = storage_options
self._manifest_enabled = manifest_enabled
self._namespace_client_properties = namespace_client_properties
if _inner is not None:
self._conn = _inner
self._cached_namespace_client = None
@@ -638,8 +633,6 @@ class LanceDBConnection(DBConnection):
None,
storage_options,
session,
manifest_enabled,
namespace_client_properties,
)
# TODO: It would be nice if we didn't store self.storage_options but it is
@@ -647,6 +640,7 @@ class LanceDBConnection(DBConnection):
# work because some paths like LanceDBConnection.from_inner will lose the
# storage_options. Also, this class really shouldn't be holding any state
# beyond _conn.
self.storage_options = storage_options
self._conn = AsyncConnection(LOOP.run(do_connect()))
self._cached_namespace_client: Optional[LanceNamespace] = None
@@ -683,8 +677,6 @@ class LanceDBConnection(DBConnection):
"connection_type": "local",
"uri": self.uri,
"storage_options": self.storage_options,
"manifest_enabled": self._manifest_enabled,
"namespace_client_properties": self._namespace_client_properties,
"read_consistency_interval_seconds": (
rci.total_seconds() if rci else None
),
+1 -9
View File
@@ -525,7 +525,7 @@ impl Connection {
}
#[pyfunction]
#[pyo3(signature = (uri, api_key=None, region=None, host_override=None, read_consistency_interval=None, client_config=None, storage_options=None, session=None, manifest_enabled=false, namespace_client_properties=None))]
#[pyo3(signature = (uri, api_key=None, region=None, host_override=None, read_consistency_interval=None, client_config=None, storage_options=None, session=None))]
#[allow(clippy::too_many_arguments)]
pub fn connect(
py: Python<'_>,
@@ -537,8 +537,6 @@ pub fn connect(
client_config: Option<PyClientConfig>,
storage_options: Option<HashMap<String, String>>,
session: Option<crate::session::Session>,
manifest_enabled: bool,
namespace_client_properties: Option<HashMap<String, String>>,
) -> PyResult<Bound<'_, PyAny>> {
future_into_py(py, async move {
let mut builder = lancedb::connect(&uri);
@@ -558,12 +556,6 @@ pub fn connect(
if let Some(storage_options) = storage_options {
builder = builder.storage_options(storage_options);
}
if manifest_enabled {
builder = builder.manifest_enabled(true);
}
if let Some(namespace_client_properties) = namespace_client_properties {
builder = builder.namespace_client_properties(namespace_client_properties);
}
#[cfg(feature = "remote")]
if let Some(client_config) = client_config {
builder = builder.client_config(client_config.into());
+1 -1
View File
@@ -17,7 +17,7 @@ use pyo3::{Bound, PyAny, PyResult, exceptions::PyValueError, prelude::*, pyfunct
/// [`expr_lit`] and combined with the methods on this struct. On the Python
/// side a thin wrapper class (`lancedb.expr.Expr`) delegates to these methods
/// and adds Python operator overloads.
#[pyclass(name = "PyExpr", from_py_object)]
#[pyclass(name = "PyExpr")]
#[derive(Clone)]
pub struct PyExpr(pub DfExpr);
+1 -1
View File
@@ -33,7 +33,7 @@ impl PyHeaderProvider {
Ok(headers_py) => {
// Convert Python dict to Rust HashMap
let bound_headers = headers_py.bind(py);
let dict: &Bound<PyDict> = bound_headers.cast().map_err(|e| {
let dict: &Bound<PyDict> = bound_headers.downcast().map_err(|e| {
format!("HeaderProvider.get_headers must return a dict: {}", e)
})?;
+2 -2
View File
@@ -13,7 +13,7 @@ use pyo3::{
Bound, FromPyObject, PyAny, PyResult, Python,
exceptions::{PyKeyError, PyValueError},
intern, pyclass, pymethods,
types::{PyAnyMethods, PyString},
types::PyAnyMethods,
};
use crate::util::parse_distance_type;
@@ -22,7 +22,7 @@ pub fn class_name(ob: &'_ Bound<'_, PyAny>) -> PyResult<String> {
let full_name = ob
.getattr(intern!(ob.py(), "__class__"))?
.getattr(intern!(ob.py(), "__name__"))?;
let full_name = full_name.cast::<PyString>()?.to_string_lossy();
let full_name = full_name.downcast()?.to_string_lossy();
match full_name.rsplit_once('.') {
Some((_, name)) => Ok(name.to_string()),
+2 -2
View File
@@ -183,7 +183,7 @@ async fn call_py_method_primitive<Req, Resp>(
) -> lance_core::Result<Resp>
where
Req: serde::Serialize + Send + 'static,
Resp: for<'a, 'py> pyo3::FromPyObject<'a, 'py> + Send + 'static,
Resp: for<'py> pyo3::FromPyObject<'py> + Send + 'static,
{
let request_json = serde_json::to_string(&request).map_err(|e| {
lance_core::Error::io(format!(
@@ -203,7 +203,7 @@ where
// Call the Python method
let result = py_namespace.call_method1(py, method_name, (request_arg,))?;
let value: Resp = result.extract(py).map_err(Into::into)?;
let value: Resp = result.extract(py)?;
Ok::<_, PyErr>(value)
})
})
+5 -5
View File
@@ -25,12 +25,12 @@ use pyo3_async_runtimes::tokio::future_into_py;
fn table_from_py<'a>(table: Bound<'a, PyAny>) -> PyResult<Bound<'a, Table>> {
if table.hasattr("_inner")? {
Ok(table.getattr("_inner")?.cast_into::<Table>()?)
Ok(table.getattr("_inner")?.downcast_into::<Table>()?)
} else if table.hasattr("_table")? {
Ok(table
.getattr("_table")?
.getattr("_inner")?
.cast_into::<Table>()?)
.downcast_into::<Table>()?)
} else {
Err(PyRuntimeError::new_err(
"Provided table does not appear to be a Table or RemoteTable instance",
@@ -90,9 +90,9 @@ impl PyAsyncPermutationBuilder {
database
.getattr("_conn")?
.getattr("_inner")?
.cast_into::<Connection>()?
.downcast_into::<Connection>()?
} else {
database.getattr("_inner")?.cast_into::<Connection>()?
database.getattr("_inner")?.downcast_into::<Connection>()?
};
let database = conn.borrow().database()?;
slf.modify(|builder| builder.persist(database, table_name))
@@ -243,7 +243,7 @@ impl PyPermutationReader {
let Some(selection) = selection else {
return Ok(Select::All);
};
let selection = selection.cast_into::<PyDict>()?;
let selection = selection.downcast_into::<PyDict>()?;
let selection = selection
.iter()
.map(|(key, value)| {
+7 -10
View File
@@ -33,7 +33,7 @@ use pyo3::pyfunction;
use pyo3::pymethods;
use pyo3::types::PyList;
use pyo3::types::{PyDict, PyString};
use pyo3::{Borrowed, FromPyObject, exceptions::PyRuntimeError};
use pyo3::{FromPyObject, exceptions::PyRuntimeError};
use pyo3::{PyErr, pyclass};
use pyo3::{exceptions::PyValueError, intern};
use pyo3_async_runtimes::tokio::future_into_py;
@@ -43,12 +43,9 @@ use crate::util::parse_distance_type;
use crate::{arrow::RecordBatchStream, util::PyLanceDB};
use crate::{error::PythonErrorExt, index::class_name};
impl<'a, 'py> FromPyObject<'a, 'py> for PyLanceDB<FtsQuery> {
type Error = PyErr;
fn extract(ob: Borrowed<'a, 'py, PyAny>) -> PyResult<Self> {
let ob = ob.to_owned();
match class_name(&ob)?.as_str() {
impl FromPyObject<'_> for PyLanceDB<FtsQuery> {
fn extract_bound(ob: &Bound<'_, PyAny>) -> PyResult<Self> {
match class_name(ob)?.as_str() {
"MatchQuery" => {
let query = ob.getattr("query")?.extract()?;
let column = ob.getattr("column")?.extract()?;
@@ -427,7 +424,7 @@ impl Query {
"Query text is required for nearest_to_text",
))?;
let query = if let Ok(query_text) = fts_query.cast::<PyString>() {
let query = if let Ok(query_text) = fts_query.downcast::<PyString>() {
let mut query_text = query_text.to_string();
let columns = query
.get_item("columns")?
@@ -609,7 +606,7 @@ impl TakeQuery {
}
}
#[pyclass(from_py_object)]
#[pyclass]
#[derive(Clone)]
pub struct FTSQuery {
inner: LanceDbQuery,
@@ -738,7 +735,7 @@ impl FTSQuery {
}
}
#[pyclass(from_py_object)]
#[pyclass]
#[derive(Clone)]
pub struct VectorQuery {
inner: LanceDbVectorQuery,
+1 -1
View File
@@ -11,7 +11,7 @@ use pyo3::{PyResult, pyclass, pymethods};
/// Sessions allow you to configure cache sizes for index and metadata caches,
/// which can significantly impact memory use and performance. They can
/// also be re-used across multiple connections to share the same cache state.
#[pyclass(from_py_object)]
#[pyclass]
#[derive(Clone)]
pub struct Session {
pub(crate) inner: Arc<LanceSession>,
+10 -10
View File
@@ -29,7 +29,7 @@ use pyo3_async_runtimes::tokio::future_into_py;
mod scannable;
/// Statistics about a compaction operation.
#[pyclass(get_all, from_py_object)]
#[pyclass(get_all)]
#[derive(Clone, Debug)]
pub struct CompactionStats {
/// The number of fragments removed
@@ -43,7 +43,7 @@ pub struct CompactionStats {
}
/// Statistics about a cleanup operation
#[pyclass(get_all, from_py_object)]
#[pyclass(get_all)]
#[derive(Clone, Debug)]
pub struct RemovalStats {
/// The number of bytes removed
@@ -53,7 +53,7 @@ pub struct RemovalStats {
}
/// Statistics about an optimize operation
#[pyclass(get_all, from_py_object)]
#[pyclass(get_all)]
#[derive(Clone, Debug)]
pub struct OptimizeStats {
/// Statistics about the compaction operation
@@ -62,7 +62,7 @@ pub struct OptimizeStats {
pub prune: RemovalStats,
}
#[pyclass(get_all, from_py_object)]
#[pyclass(get_all)]
#[derive(Clone, Debug)]
pub struct UpdateResult {
pub rows_updated: u64,
@@ -88,7 +88,7 @@ impl From<lancedb::table::UpdateResult> for UpdateResult {
}
}
#[pyclass(get_all, from_py_object)]
#[pyclass(get_all)]
#[derive(Clone, Debug)]
pub struct AddResult {
pub version: u64,
@@ -109,7 +109,7 @@ impl From<lancedb::table::AddResult> for AddResult {
}
}
#[pyclass(get_all, from_py_object)]
#[pyclass(get_all)]
#[derive(Clone, Debug)]
pub struct DeleteResult {
pub num_deleted_rows: u64,
@@ -135,7 +135,7 @@ impl From<lancedb::table::DeleteResult> for DeleteResult {
}
}
#[pyclass(get_all, from_py_object)]
#[pyclass(get_all)]
#[derive(Clone, Debug)]
pub struct MergeResult {
pub version: u64,
@@ -171,7 +171,7 @@ impl From<lancedb::table::MergeResult> for MergeResult {
}
}
#[pyclass(get_all, from_py_object)]
#[pyclass(get_all)]
#[derive(Clone, Debug)]
pub struct AddColumnsResult {
pub version: u64,
@@ -192,7 +192,7 @@ impl From<lancedb::table::AddColumnsResult> for AddColumnsResult {
}
}
#[pyclass(get_all, from_py_object)]
#[pyclass(get_all)]
#[derive(Clone, Debug)]
pub struct AlterColumnsResult {
pub version: u64,
@@ -213,7 +213,7 @@ impl From<lancedb::table::AlterColumnsResult> for AlterColumnsResult {
}
}
#[pyclass(get_all, from_py_object)]
#[pyclass(get_all)]
#[derive(Clone, Debug)]
pub struct DropColumnsResult {
pub version: u64,
+2 -5
View File
@@ -126,11 +126,8 @@ impl Scannable for PyScannable {
}
}
impl<'a, 'py> FromPyObject<'a, 'py> for PyScannable {
type Error = pyo3::PyErr;
fn extract(ob: pyo3::Borrowed<'a, 'py, PyAny>) -> pyo3::PyResult<Self> {
let ob = ob.to_owned();
impl<'py> FromPyObject<'py> for PyScannable {
fn extract_bound(ob: &pyo3::Bound<'py, PyAny>) -> pyo3::PyResult<Self> {
// Convert from Scannable dataclass.
let schema: PyArrowType<Schema> = ob.getattr("schema")?.extract()?;
let schema = Arc::new(schema.0);
+2 -7
View File
@@ -1,6 +1,6 @@
[package]
name = "lancedb"
version = "0.28.0-beta.10"
version = "0.28.0-beta.9"
edition.workspace = true
description = "LanceDB: A serverless, low-latency vector database for AI applications"
license.workspace = true
@@ -111,12 +111,7 @@ default = []
aws = ["lance/aws", "lance-io/aws", "lance-namespace-impls/dir-aws"]
oss = ["lance/oss", "lance-io/oss", "lance-namespace-impls/dir-oss"]
gcs = ["lance/gcp", "lance-io/gcp", "lance-namespace-impls/dir-gcp"]
azure = [
"lance/azure",
"lance-io/azure",
"lance-namespace-impls/dir-azure",
"lance-namespace-impls/credential-vendor-azure",
]
azure = ["lance/azure", "lance-io/azure", "lance-namespace-impls/dir-azure"]
huggingface = [
"lance/huggingface",
"lance-io/huggingface",
-175
View File
@@ -590,15 +590,6 @@ pub struct ConnectRequest {
/// storage options.
pub namespace_client_properties: HashMap<String, String>,
/// Use directory namespace manifests as the source of truth for native
/// LanceDB table metadata.
///
/// When enabled for a local/native connection, LanceDB returns a
/// namespace-backed database directly. Directory listing fallback remains
/// enabled for migration, and directory-listing-to-manifest migration is
/// forced on.
pub manifest_enabled: bool,
/// The interval at which to check for updates from other processes.
///
/// If None, then consistency is not checked. For performance
@@ -639,7 +630,6 @@ impl ConnectBuilder {
read_consistency_interval: None,
options: HashMap::new(),
namespace_client_properties: HashMap::new(),
manifest_enabled: false,
session: None,
},
embedding_registry: None,
@@ -801,17 +791,6 @@ impl ConnectBuilder {
self
}
/// Enable or disable manifest-backed directory namespace mode for local
/// native connections.
///
/// When enabled, the connection uses the directory namespace database
/// directly for all table operations and forces
/// `dir_listing_to_manifest_migration_enabled=true`.
pub fn manifest_enabled(mut self, enabled: bool) -> Self {
self.request.manifest_enabled = enabled;
self
}
/// The interval at which to check for updates from other processes. This
/// only affects LanceDB OSS.
///
@@ -907,16 +886,6 @@ impl ConnectBuilder {
pub async fn execute(self) -> Result<Connection> {
if self.request.uri.starts_with("db") {
self.execute_remote()
} else if self.request.manifest_enabled {
let internal = Arc::new(
ListingDatabase::connect_manifest_enabled_namespace_database(&self.request).await?,
);
Ok(Connection {
internal,
embedding_registry: self
.embedding_registry
.unwrap_or_else(|| Arc::new(MemoryRegistry::new())),
})
} else {
let internal = Arc::new(ListingDatabase::connect_with_options(&self.request).await?);
Ok(Connection {
@@ -1163,9 +1132,6 @@ mod tests {
use lance_testing::datagen::{BatchGenerator, IncrementingInt32};
use tempfile::tempdir;
use crate::database::listing::{ListingDatabaseOptions, OPT_NEW_TABLE_V2_MANIFEST_PATHS};
use crate::database::namespace::LanceNamespaceDatabase;
use crate::table::NativeTable;
use crate::test_utils::connection::new_test_connection;
use super::*;
@@ -1238,147 +1204,6 @@ mod tests {
);
}
#[tokio::test]
async fn test_connect_with_manifest_enabled_uses_directory_namespace() {
let tmp_dir = tempdir().unwrap();
let uri = tmp_dir.path().to_str().unwrap();
let db = connect(uri)
.manifest_enabled(true)
.storage_option("timeout", "30s")
.namespace_client_property("manifest_enabled", "false")
.namespace_client_property("dir_listing_to_manifest_migration_enabled", "false")
.execute()
.await
.unwrap();
assert!(
db.database()
.as_any()
.downcast_ref::<LanceNamespaceDatabase>()
.is_some()
);
assert_eq!(db.uri(), uri);
let (ns_impl, properties) = db.namespace_client_config().await.unwrap();
assert_eq!(ns_impl, "dir");
assert_eq!(properties.get("root"), Some(&uri.to_string()));
assert_eq!(
properties.get("manifest_enabled"),
Some(&"true".to_string())
);
assert_eq!(
properties.get("dir_listing_to_manifest_migration_enabled"),
Some(&"true".to_string())
);
assert_eq!(properties.get("storage.timeout"), Some(&"30s".to_string()));
}
#[tokio::test]
async fn test_manifest_enabled_rejects_commit_engine_uri() {
let Err(err) = connect("s3+ddb://bucket/db?ddbTableName=manifest")
.manifest_enabled(true)
.execute()
.await
else {
panic!("expected manifest-enabled s3+ddb connection to fail");
};
assert!(
matches!(err, Error::NotSupported { message } if message.contains("commit engine URI schemes"))
);
let Err(err) = connect("s3://bucket/db?engine=ddb&ddbTableName=manifest")
.manifest_enabled(true)
.execute()
.await
else {
panic!("expected manifest-enabled engine query connection to fail");
};
assert!(
matches!(err, Error::NotSupported { message } if message.contains("commit engine"))
);
}
#[tokio::test]
async fn test_manifest_enabled_connection_migrates_root_listing_table() {
let tmp_dir = tempdir().unwrap();
let uri = tmp_dir.path().to_str().unwrap();
let schema = Arc::new(Schema::new(vec![Field::new("x", DataType::Int32, false)]));
connect(uri)
.execute()
.await
.unwrap()
.create_empty_table("legacy", schema)
.execute()
.await
.unwrap();
let db = connect(uri).manifest_enabled(true).execute().await.unwrap();
let tables = db.table_names().execute().await.unwrap();
assert_eq!(tables, vec!["legacy".to_string()]);
db.open_table("legacy").execute().await.unwrap();
}
#[tokio::test]
async fn test_manifest_enabled_preserves_new_table_options() {
let tmp_dir = tempdir().unwrap();
let uri = tmp_dir.path().to_str().unwrap();
let options = ListingDatabaseOptions::builder()
.enable_v2_manifest_paths(true)
.build();
let schema = Arc::new(Schema::new(vec![Field::new("x", DataType::Int32, false)]));
let table = connect(uri)
.manifest_enabled(true)
.database_options(&options)
.execute()
.await
.unwrap()
.create_empty_table("v1_manifest", schema)
.storage_option(OPT_NEW_TABLE_V2_MANIFEST_PATHS, "false")
.execute()
.await
.unwrap();
let native_table = table
.base_table()
.as_any()
.downcast_ref::<NativeTable>()
.unwrap();
assert!(!native_table.uses_v2_manifest_paths().await.unwrap());
}
#[tokio::test]
async fn test_manifest_enabled_vend_input_storage_options() {
let tmp_dir = tempdir().unwrap();
let uri = tmp_dir.path().to_str().unwrap();
let schema = Arc::new(Schema::new(vec![Field::new("x", DataType::Int32, false)]));
let table = connect(uri)
.manifest_enabled(true)
.storage_option("test_storage_option", "test_value")
.namespace_client_property("vend_input_storage_options", "true")
.namespace_client_property(
"vend_input_storage_options_refresh_interval_millis",
"60000",
)
.execute()
.await
.unwrap()
.create_empty_table("vended", schema)
.execute()
.await
.unwrap();
let storage_options = table.latest_storage_options().await.unwrap().unwrap();
assert_eq!(
storage_options.get("test_storage_option"),
Some(&"test_value".to_string())
);
assert!(storage_options.contains_key("expires_at_millis"));
}
#[tokio::test]
async fn test_table_names() {
let tc = new_test_connection().await.unwrap();
+9 -143
View File
@@ -285,7 +285,7 @@ const MIRRORED_STORE: &str = "mirroredStore";
/// A connection to LanceDB
impl ListingDatabase {
pub(crate) fn build_namespace_client_properties(
fn build_namespace_client_properties(
uri: &str,
storage_options: &HashMap<String, String>,
namespace_client_properties: HashMap<String, String>,
@@ -298,24 +298,6 @@ impl ListingDatabase {
properties
}
pub(crate) fn build_manifest_enabled_namespace_client_properties(
uri: &str,
storage_options: &HashMap<String, String>,
namespace_client_properties: HashMap<String, String>,
) -> HashMap<String, String> {
let mut properties = Self::build_namespace_client_properties(
uri,
storage_options,
namespace_client_properties,
);
properties.insert("manifest_enabled".to_string(), "true".to_string());
properties.insert(
"dir_listing_to_manifest_migration_enabled".to_string(),
"true".to_string(),
);
properties
}
async fn connect_namespace_database(
uri: &str,
storage_options: HashMap<String, String>,
@@ -341,119 +323,6 @@ impl ListingDatabase {
))
}
async fn prepare_namespace_root(
uri: &str,
storage_options: &HashMap<String, String>,
session: Arc<lance::session::Session>,
) -> Result<String> {
match url::Url::parse(uri) {
Ok(url) if url.scheme().len() == 1 && cfg!(windows) => {
let (object_store, _) = ObjectStore::from_uri_and_params(
session.store_registry(),
uri,
&ObjectStoreParams::default(),
)
.await?;
if object_store.is_local() {
Self::try_create_dir(uri).context(CreateDirSnafu { path: uri })?;
}
Ok(uri.to_string())
}
Ok(mut url) => {
if url.scheme().contains('+') {
return Err(Error::NotSupported {
message: "commit engine URI schemes are not supported for manifest-enabled namespace connections".to_string(),
});
}
for (key, value) in url.query_pairs() {
if key == ENGINE {
return Err(Error::NotSupported {
message: format!(
"commit engine '{}' is not supported for manifest-enabled namespace connections",
value
),
});
} else if key == MIRRORED_STORE {
return Err(Error::NotSupported {
message: "mirrored store is not supported for manifest-enabled namespace connections"
.to_string(),
});
}
}
url.set_query(None);
let plain_uri = url.to_string();
let os_params = ObjectStoreParams {
storage_options_accessor: if storage_options.is_empty() {
None
} else {
Some(Arc::new(StorageOptionsAccessor::with_static_options(
storage_options.clone(),
)))
},
..Default::default()
};
let (object_store, _) = ObjectStore::from_uri_and_params(
session.store_registry(),
&plain_uri,
&os_params,
)
.await?;
if object_store.is_local() {
Self::try_create_dir(&plain_uri).context(CreateDirSnafu {
path: plain_uri.clone(),
})?;
}
Ok(plain_uri)
}
Err(_) => {
let (object_store, _) = ObjectStore::from_uri_and_params(
session.store_registry(),
uri,
&ObjectStoreParams::default(),
)
.await?;
if object_store.is_local() {
Self::try_create_dir(uri).context(CreateDirSnafu { path: uri })?;
}
Ok(uri.to_string())
}
}
}
pub(crate) async fn connect_manifest_enabled_namespace_database(
request: &ConnectRequest,
) -> Result<LanceNamespaceDatabase> {
let options = ListingDatabaseOptions::parse_from_map(&request.options)?;
let session = request
.session
.clone()
.unwrap_or_else(|| Arc::new(lance::session::Session::default()));
let namespace_root =
Self::prepare_namespace_root(&request.uri, &options.storage_options, session.clone())
.await?;
let ns_properties = Self::build_manifest_enabled_namespace_client_properties(
&namespace_root,
&options.storage_options,
request.namespace_client_properties.clone(),
);
LanceNamespaceDatabase::connect_with_new_table_config(
"dir",
ns_properties,
options.storage_options,
request.read_consistency_interval,
Some(session),
HashSet::new(),
options.new_table_config,
)
.await
.map(|db| db.with_uri(request.uri.clone()))
}
/// Connect to a listing database
///
/// The URI should be a path to a directory where the tables are stored.
@@ -821,12 +690,15 @@ impl ListingDatabase {
store_params.storage_options_accessor = Some(Arc::new(accessor));
}
write_params.data_storage_version = storage_version_override
.or(write_params.data_storage_version)
.or(self.new_table_config.data_storage_version);
write_params.data_storage_version = self
.new_table_config
.data_storage_version
.or(storage_version_override);
if let Some(enable_v2_manifest_paths) =
v2_manifest_override.or(self.new_table_config.enable_v2_manifest_paths)
if let Some(enable_v2_manifest_paths) = self
.new_table_config
.enable_v2_manifest_paths
.or(v2_manifest_override)
{
write_params.enable_v2_manifest_paths = enable_v2_manifest_paths;
}
@@ -1286,7 +1158,6 @@ mod tests {
client_config: Default::default(),
options: Default::default(),
namespace_client_properties: Default::default(),
manifest_enabled: false,
read_consistency_interval: None,
session: None,
};
@@ -1421,7 +1292,6 @@ mod tests {
client_config: Default::default(),
options: options.clone(),
namespace_client_properties: Default::default(),
manifest_enabled: false,
read_consistency_interval: None,
session: None,
};
@@ -1957,7 +1827,6 @@ mod tests {
client_config: Default::default(),
options,
namespace_client_properties: Default::default(),
manifest_enabled: false,
read_consistency_interval: None,
session: None,
};
@@ -2064,7 +1933,6 @@ mod tests {
client_config: Default::default(),
options,
namespace_client_properties: Default::default(),
manifest_enabled: false,
read_consistency_interval: None,
session: None,
};
@@ -2137,7 +2005,6 @@ mod tests {
client_config: Default::default(),
options,
namespace_client_properties: Default::default(),
manifest_enabled: false,
read_consistency_interval: None,
session: None,
};
@@ -2335,7 +2202,6 @@ mod tests {
client_config: Default::default(),
options: Default::default(),
namespace_client_properties,
manifest_enabled: false,
read_consistency_interval: None,
session: None,
};
+18 -111
View File
@@ -8,7 +8,9 @@ use std::sync::Arc;
use async_trait::async_trait;
use lance::io::commit::namespace_manifest::LanceNamespaceExternalManifestStore;
use lance_io::object_store::{ObjectStoreParams, StorageOptionsAccessor};
use lance_io::object_store::{
ObjectStore as LanceObjectStore, ObjectStoreParams, ObjectStoreRegistry, StorageOptionsAccessor,
};
use lance_namespace::{
LanceNamespace,
models::{
@@ -24,10 +26,6 @@ use lance_table::io::commit::external_manifest::ExternalManifestCommitHandler;
use crate::connection::NamespaceClientPushdownOperation;
use crate::database::ReadConsistency;
use crate::database::listing::{
NewTableConfig, OPT_NEW_TABLE_ENABLE_STABLE_ROW_IDS, OPT_NEW_TABLE_STORAGE_VERSION,
OPT_NEW_TABLE_V2_MANIFEST_PATHS,
};
use crate::error::{Error, Result};
use crate::table::NativeTable;
use lance::dataset::WriteMode;
@@ -54,8 +52,6 @@ pub struct LanceNamespaceDatabase {
ns_impl: String,
// Namespace properties used to construct the namespace client
ns_properties: HashMap<String, String>,
// Options for tables created by this connection
new_table_config: NewTableConfig,
}
impl LanceNamespaceDatabase {
@@ -77,15 +73,9 @@ impl LanceNamespaceDatabase {
pushdown_operations: namespace_client_pushdown_operations,
ns_impl: namespace_client_impl,
ns_properties: namespace_client_properties,
new_table_config: NewTableConfig::default(),
}
}
pub(crate) fn with_uri(mut self, uri: impl Into<String>) -> Self {
self.uri = uri.into();
self
}
pub async fn connect(
ns_impl: &str,
ns_properties: HashMap<String, String>,
@@ -93,27 +83,6 @@ impl LanceNamespaceDatabase {
read_consistency_interval: Option<std::time::Duration>,
session: Option<Arc<lance::session::Session>>,
pushdown_operations: HashSet<NamespaceClientPushdownOperation>,
) -> Result<Self> {
Self::connect_with_new_table_config(
ns_impl,
ns_properties,
storage_options,
read_consistency_interval,
session,
pushdown_operations,
NewTableConfig::default(),
)
.await
}
pub(crate) async fn connect_with_new_table_config(
ns_impl: &str,
ns_properties: HashMap<String, String>,
storage_options: HashMap<String, String>,
read_consistency_interval: Option<std::time::Duration>,
session: Option<Arc<lance::session::Session>>,
pushdown_operations: HashSet<NamespaceClientPushdownOperation>,
new_table_config: NewTableConfig,
) -> Result<Self> {
let mut builder = ConnectBuilder::new(ns_impl);
for (key, value) in ns_properties.clone() {
@@ -135,79 +104,8 @@ impl LanceNamespaceDatabase {
pushdown_operations,
ns_impl: ns_impl.to_string(),
ns_properties,
new_table_config,
})
}
fn extract_storage_overrides(
&self,
request: &DbCreateTableRequest,
) -> Result<(
Option<lance_encoding::version::LanceFileVersion>,
Option<bool>,
Option<bool>,
)> {
let storage_options = request
.write_options
.lance_write_params
.as_ref()
.and_then(|p| p.store_params.as_ref())
.and_then(|sp| sp.storage_options());
let storage_version_override = storage_options
.and_then(|opts| opts.get(OPT_NEW_TABLE_STORAGE_VERSION))
.map(|s| s.parse::<lance_encoding::version::LanceFileVersion>())
.transpose()?;
let v2_manifest_override = storage_options
.and_then(|opts| opts.get(OPT_NEW_TABLE_V2_MANIFEST_PATHS))
.map(|s| s.parse::<bool>())
.transpose()
.map_err(|_| Error::InvalidInput {
message: "enable_v2_manifest_paths must be a boolean".to_string(),
})?;
let stable_row_ids_override = storage_options
.and_then(|opts| opts.get(OPT_NEW_TABLE_ENABLE_STABLE_ROW_IDS))
.map(|s| s.parse::<bool>())
.transpose()
.map_err(|_| Error::InvalidInput {
message: "enable_stable_row_ids must be a boolean".to_string(),
})?;
Ok((
storage_version_override,
v2_manifest_override,
stable_row_ids_override,
))
}
fn apply_new_table_config(
&self,
params: &mut lance::dataset::WriteParams,
request: &DbCreateTableRequest,
) -> Result<()> {
let (storage_version_override, v2_manifest_override, stable_row_ids_override) =
self.extract_storage_overrides(request)?;
params.data_storage_version = storage_version_override
.or(params.data_storage_version)
.or(self.new_table_config.data_storage_version);
if let Some(enable_v2_manifest_paths) =
v2_manifest_override.or(self.new_table_config.enable_v2_manifest_paths)
{
params.enable_v2_manifest_paths = enable_v2_manifest_paths;
}
if let Some(enable_stable_row_ids) =
stable_row_ids_override.or(self.new_table_config.enable_stable_row_ids)
{
params.enable_stable_row_ids = enable_stable_row_ids;
}
Ok(())
}
}
impl std::fmt::Debug for LanceNamespaceDatabase {
@@ -403,12 +301,7 @@ impl Database for LanceNamespaceDatabase {
};
// Build write params with storage options and commit handler
let mut params = request
.write_options
.lance_write_params
.clone()
.unwrap_or_default();
self.apply_new_table_config(&mut params, &request)?;
let mut params = request.write_options.lance_write_params.unwrap_or_default();
if matches!(request.mode, CreateTableMode::Overwrite) {
params.mode = WriteMode::Overwrite;
@@ -450,6 +343,20 @@ impl Database for LanceNamespaceDatabase {
)
.await?;
// lance >= v6.0.0-beta.2: declare_table creates a `.lance-reserved` marker file to
// prevent directory scanning from seeing an incomplete table. After writing data we
// must remove it so the table appears in directory listings.
if let Ok(dataset) = native_table.dataset.get().await {
let registry = Arc::new(ObjectStoreRegistry::default());
if let Ok(table_path) = LanceObjectStore::extract_path_from_uri(registry, dataset.uri())
{
let _ = dataset
.object_store
.delete(&table_path.child(".lance-reserved"))
.await;
}
}
Ok(Arc::new(native_table))
}
+3 -3
View File
@@ -43,7 +43,7 @@ pub struct RemoteInsertExec<S: HttpSend = Sender> {
client: RestfulLanceDbClient<S>,
input: Arc<dyn ExecutionPlan>,
overwrite: bool,
properties: Arc<PlanProperties>,
properties: PlanProperties,
add_result: Arc<Mutex<Option<AddResult>>>,
metrics: ExecutionPlanMetricsSet,
upload_id: Option<String>,
@@ -118,7 +118,7 @@ impl<S: HttpSend + 'static> RemoteInsertExec<S> {
client,
input,
overwrite,
properties: Arc::new(properties),
properties,
add_result: Arc::new(Mutex::new(None)),
metrics: ExecutionPlanMetricsSet::new(),
upload_id,
@@ -232,7 +232,7 @@ impl<S: HttpSend + 'static> ExecutionPlan for RemoteInsertExec<S> {
self
}
fn properties(&self) -> &Arc<PlanProperties> {
fn properties(&self) -> &PlanProperties {
&self.properties
}
+4 -9
View File
@@ -39,26 +39,21 @@ use lance_index::scalar::FullTextSearchQuery;
struct MetadataEraserExec {
input: Arc<dyn ExecutionPlan>,
schema: Arc<ArrowSchema>,
properties: Arc<PlanProperties>,
properties: PlanProperties,
}
impl MetadataEraserExec {
fn compute_properties_from_input(
input: &Arc<dyn ExecutionPlan>,
schema: &Arc<ArrowSchema>,
) -> Arc<PlanProperties> {
) -> PlanProperties {
let input_properties = input.properties();
let eq_properties = input_properties
.eq_properties
.clone()
.with_new_schema(schema.clone())
.unwrap();
Arc::new(
input_properties
.as_ref()
.clone()
.with_eq_properties(eq_properties),
)
input_properties.clone().with_eq_properties(eq_properties)
}
fn new(input: Arc<dyn ExecutionPlan>) -> Self {
@@ -92,7 +87,7 @@ impl ExecutionPlan for MetadataEraserExec {
self
}
fn properties(&self) -> &Arc<PlanProperties> {
fn properties(&self) -> &PlanProperties {
&self.properties
}
+3 -3
View File
@@ -81,7 +81,7 @@ pub struct InsertExec {
dataset: Arc<Dataset>,
input: Arc<dyn ExecutionPlan>,
write_params: WriteParams,
properties: Arc<PlanProperties>,
properties: PlanProperties,
partial_transactions: Arc<Mutex<Vec<Transaction>>>,
metrics: ExecutionPlanMetricsSet,
}
@@ -107,7 +107,7 @@ impl InsertExec {
dataset,
input,
write_params,
properties: Arc::new(properties),
properties,
partial_transactions: Arc::new(Mutex::new(Vec::with_capacity(num_partitions))),
metrics: ExecutionPlanMetricsSet::new(),
}
@@ -136,7 +136,7 @@ impl ExecutionPlan for InsertExec {
self
}
fn properties(&self) -> &Arc<PlanProperties> {
fn properties(&self) -> &PlanProperties {
&self.properties
}
@@ -20,7 +20,7 @@ pub(crate) struct ScannableExec {
// We don't require Scannable to be Sync, so we wrap it in a Mutex to allow safe concurrent access.
source: Mutex<Box<dyn Scannable>>,
num_rows: Option<usize>,
properties: Arc<PlanProperties>,
properties: PlanProperties,
tracker: Option<Arc<WriteProgressTracker>>,
}
@@ -49,7 +49,7 @@ impl ScannableExec {
Self {
source,
num_rows,
properties: Arc::new(properties),
properties,
tracker,
}
}
@@ -70,7 +70,7 @@ impl ExecutionPlan for ScannableExec {
self
}
fn properties(&self) -> &Arc<PlanProperties> {
fn properties(&self) -> &PlanProperties {
&self.properties
}