mirror of
https://github.com/lancedb/lancedb.git
synced 2026-03-26 02:20:40 +00:00
Compare commits
31 Commits
jack/memta
...
v0.27.1
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
0e3d36e8a5 | ||
|
|
9b229f1e7c | ||
|
|
f5b21c0aa4 | ||
|
|
e927924d26 | ||
|
|
11a4966bfc | ||
|
|
dd5aaa72dc | ||
|
|
3a200d77ef | ||
|
|
bd09c53938 | ||
|
|
0b18e33180 | ||
|
|
c89240b16c | ||
|
|
099ff355a4 | ||
|
|
c5995fda67 | ||
|
|
25eb1fbfa4 | ||
|
|
4ac41c5c3f | ||
|
|
9a5b0398ec | ||
|
|
d1d720d08a | ||
|
|
c2e543f1b7 | ||
|
|
216c1b5f77 | ||
|
|
fc1867da83 | ||
|
|
f951da2b00 | ||
|
|
6530d82690 | ||
|
|
b3fc9c444f | ||
|
|
6de8f42dcd | ||
|
|
5c3bd68e58 | ||
|
|
4be85444f0 | ||
|
|
68c07f333f | ||
|
|
814a379e08 | ||
|
|
f31561c5bb | ||
|
|
e0c5ceac03 | ||
|
|
e93bb3355a | ||
|
|
b75991eb07 |
@@ -1,5 +1,5 @@
|
||||
[tool.bumpversion]
|
||||
current_version = "0.27.0-beta.3"
|
||||
current_version = "0.27.1"
|
||||
parse = """(?x)
|
||||
(?P<major>0|[1-9]\\d*)\\.
|
||||
(?P<minor>0|[1-9]\\d*)\\.
|
||||
|
||||
6
.github/workflows/dev.yml
vendored
6
.github/workflows/dev.yml
vendored
@@ -15,7 +15,7 @@ jobs:
|
||||
name: Label PR
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
- uses: srvaroa/labeler@master
|
||||
- uses: srvaroa/labeler@v1
|
||||
env:
|
||||
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
|
||||
commitlint:
|
||||
@@ -24,7 +24,7 @@ jobs:
|
||||
name: Verify PR title / description conforms to semantic-release
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
- uses: actions/setup-node@v3
|
||||
- uses: actions/setup-node@v4
|
||||
with:
|
||||
node-version: "18"
|
||||
# These rules are disabled because Github will always ensure there
|
||||
@@ -47,7 +47,7 @@ jobs:
|
||||
|
||||
${{ github.event.pull_request.body }}
|
||||
- if: failure()
|
||||
uses: actions/github-script@v6
|
||||
uses: actions/github-script@v7
|
||||
with:
|
||||
script: |
|
||||
const message = `**ACTION NEEDED**
|
||||
|
||||
4
.github/workflows/docs.yml
vendored
4
.github/workflows/docs.yml
vendored
@@ -53,7 +53,7 @@ jobs:
|
||||
python -m pip install --extra-index-url https://pypi.fury.io/lance-format/ --extra-index-url https://pypi.fury.io/lancedb/ -e .
|
||||
python -m pip install --extra-index-url https://pypi.fury.io/lance-format/ --extra-index-url https://pypi.fury.io/lancedb/ -r ../docs/requirements.txt
|
||||
- name: Set up node
|
||||
uses: actions/setup-node@v3
|
||||
uses: actions/setup-node@v4
|
||||
with:
|
||||
node-version: 20
|
||||
cache: 'npm'
|
||||
@@ -68,7 +68,7 @@ jobs:
|
||||
run: |
|
||||
PYTHONPATH=. mkdocs build
|
||||
- name: Setup Pages
|
||||
uses: actions/configure-pages@v2
|
||||
uses: actions/configure-pages@v5
|
||||
- name: Upload artifact
|
||||
uses: actions/upload-pages-artifact@v3
|
||||
with:
|
||||
|
||||
9
.github/workflows/nodejs.yml
vendored
9
.github/workflows/nodejs.yml
vendored
@@ -7,6 +7,7 @@ on:
|
||||
pull_request:
|
||||
paths:
|
||||
- Cargo.toml
|
||||
- Cargo.lock
|
||||
- nodejs/**
|
||||
- rust/**
|
||||
- docs/src/js/**
|
||||
@@ -37,7 +38,7 @@ jobs:
|
||||
with:
|
||||
fetch-depth: 0
|
||||
lfs: true
|
||||
- uses: actions/setup-node@v3
|
||||
- uses: actions/setup-node@v4
|
||||
with:
|
||||
node-version: 20
|
||||
cache: 'npm'
|
||||
@@ -77,7 +78,7 @@ jobs:
|
||||
with:
|
||||
fetch-depth: 0
|
||||
lfs: true
|
||||
- uses: actions/setup-node@v3
|
||||
- uses: actions/setup-node@v4
|
||||
name: Setup Node.js 20 for build
|
||||
with:
|
||||
# @napi-rs/cli v3 requires Node >= 20.12 (via @inquirer/prompts@8).
|
||||
@@ -94,7 +95,7 @@ jobs:
|
||||
run: |
|
||||
npm ci --include=optional
|
||||
npm run build:debug -- --profile ci
|
||||
- uses: actions/setup-node@v3
|
||||
- uses: actions/setup-node@v4
|
||||
name: Setup Node.js ${{ matrix.node-version }} for test
|
||||
with:
|
||||
node-version: ${{ matrix.node-version }}
|
||||
@@ -143,7 +144,7 @@ jobs:
|
||||
with:
|
||||
fetch-depth: 0
|
||||
lfs: true
|
||||
- uses: actions/setup-node@v3
|
||||
- uses: actions/setup-node@v4
|
||||
with:
|
||||
node-version: 20
|
||||
cache: 'npm'
|
||||
|
||||
17
.github/workflows/npm-publish.yml
vendored
17
.github/workflows/npm-publish.yml
vendored
@@ -19,6 +19,7 @@ on:
|
||||
paths:
|
||||
- .github/workflows/npm-publish.yml
|
||||
- Cargo.toml # Change in dependency frequently breaks builds
|
||||
- Cargo.lock
|
||||
|
||||
concurrency:
|
||||
group: ${{ github.workflow }}-${{ github.ref }}
|
||||
@@ -124,7 +125,12 @@ jobs:
|
||||
pre_build: |-
|
||||
set -e &&
|
||||
apt-get update &&
|
||||
apt-get install -y protobuf-compiler pkg-config
|
||||
apt-get install -y protobuf-compiler pkg-config &&
|
||||
# The base image (manylinux2014-cross) sets TARGET_CC to the old
|
||||
# GCC 4.8 cross-compiler. aws-lc-sys checks TARGET_CC before CC,
|
||||
# so it picks up GCC even though the napi-rs image sets CC=clang.
|
||||
# Override to use the image's clang-18 which supports -fuse-ld=lld.
|
||||
export TARGET_CC=clang TARGET_CXX=clang++
|
||||
- target: x86_64-unknown-linux-musl
|
||||
# This one seems to need some extra memory
|
||||
host: ubuntu-2404-8x-x64
|
||||
@@ -144,9 +150,10 @@ jobs:
|
||||
set -e &&
|
||||
apt-get update &&
|
||||
apt-get install -y protobuf-compiler pkg-config &&
|
||||
# https://github.com/aws/aws-lc-rs/issues/737#issuecomment-2725918627
|
||||
ln -s /usr/aarch64-unknown-linux-gnu/lib/gcc/aarch64-unknown-linux-gnu/4.8.5/crtbeginS.o /usr/aarch64-unknown-linux-gnu/aarch64-unknown-linux-gnu/sysroot/usr/lib/crtbeginS.o &&
|
||||
ln -s /usr/aarch64-unknown-linux-gnu/lib/gcc /usr/aarch64-unknown-linux-gnu/aarch64-unknown-linux-gnu/sysroot/usr/lib/gcc &&
|
||||
export TARGET_CC=clang TARGET_CXX=clang++ &&
|
||||
# The manylinux2014 sysroot has glibc 2.17 headers which lack
|
||||
# AT_HWCAP2 (added in Linux 3.17). Define it for aws-lc-sys.
|
||||
export CFLAGS="$CFLAGS -DAT_HWCAP2=26" &&
|
||||
rustup target add aarch64-unknown-linux-gnu
|
||||
- target: aarch64-unknown-linux-musl
|
||||
host: ubuntu-2404-8x-x64
|
||||
@@ -266,7 +273,7 @@ jobs:
|
||||
- target: x86_64-unknown-linux-gnu
|
||||
host: ubuntu-latest
|
||||
- target: aarch64-unknown-linux-gnu
|
||||
host: buildjet-16vcpu-ubuntu-2204-arm
|
||||
host: ubuntu-2404-8x-arm64
|
||||
node:
|
||||
- '20'
|
||||
runs-on: ${{ matrix.settings.host }}
|
||||
|
||||
1
.github/workflows/pypi-publish.yml
vendored
1
.github/workflows/pypi-publish.yml
vendored
@@ -9,6 +9,7 @@ on:
|
||||
paths:
|
||||
- .github/workflows/pypi-publish.yml
|
||||
- Cargo.toml # Change in dependency frequently breaks builds
|
||||
- Cargo.lock
|
||||
|
||||
env:
|
||||
PIP_EXTRA_INDEX_URL: "https://pypi.fury.io/lance-format/ https://pypi.fury.io/lancedb/"
|
||||
|
||||
1
.github/workflows/python.yml
vendored
1
.github/workflows/python.yml
vendored
@@ -7,6 +7,7 @@ on:
|
||||
pull_request:
|
||||
paths:
|
||||
- Cargo.toml
|
||||
- Cargo.lock
|
||||
- python/**
|
||||
- rust/**
|
||||
- .github/workflows/python.yml
|
||||
|
||||
1
.github/workflows/rust.yml
vendored
1
.github/workflows/rust.yml
vendored
@@ -7,6 +7,7 @@ on:
|
||||
pull_request:
|
||||
paths:
|
||||
- Cargo.toml
|
||||
- Cargo.lock
|
||||
- rust/**
|
||||
- .github/workflows/rust.yml
|
||||
|
||||
|
||||
425
Cargo.lock
generated
425
Cargo.lock
generated
File diff suppressed because it is too large
Load Diff
28
Cargo.toml
28
Cargo.toml
@@ -15,20 +15,20 @@ categories = ["database-implementations"]
|
||||
rust-version = "1.91.0"
|
||||
|
||||
[workspace.dependencies]
|
||||
lance = { "version" = "=3.0.0-rc.2", default-features = false, "tag" = "v3.0.0-rc.2", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-core = { "version" = "=3.0.0-rc.2", "tag" = "v3.0.0-rc.2", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-datagen = { "version" = "=3.0.0-rc.2", "tag" = "v3.0.0-rc.2", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-file = { "version" = "=3.0.0-rc.2", "tag" = "v3.0.0-rc.2", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-io = { "version" = "=3.0.0-rc.2", default-features = false, "tag" = "v3.0.0-rc.2", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-index = { "version" = "=3.0.0-rc.2", "tag" = "v3.0.0-rc.2", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-linalg = { "version" = "=3.0.0-rc.2", "tag" = "v3.0.0-rc.2", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-namespace = { "version" = "=3.0.0-rc.2", "tag" = "v3.0.0-rc.2", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-namespace-impls = { "version" = "=3.0.0-rc.2", default-features = false, "tag" = "v3.0.0-rc.2", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-table = { "version" = "=3.0.0-rc.2", "tag" = "v3.0.0-rc.2", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-testing = { "version" = "=3.0.0-rc.2", "tag" = "v3.0.0-rc.2", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-datafusion = { "version" = "=3.0.0-rc.2", "tag" = "v3.0.0-rc.2", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-encoding = { "version" = "=3.0.0-rc.2", "tag" = "v3.0.0-rc.2", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-arrow = { "version" = "=3.0.0-rc.2", "tag" = "v3.0.0-rc.2", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance = { version = "=3.0.1", default-features = false }
|
||||
lance-core = { version = "=3.0.1" }
|
||||
lance-datagen = { version = "=3.0.1" }
|
||||
lance-file = { version = "=3.0.1" }
|
||||
lance-io = { version = "=3.0.1", default-features = false }
|
||||
lance-index = { version = "=3.0.1" }
|
||||
lance-linalg = { version = "=3.0.1" }
|
||||
lance-namespace = { version = "=3.0.1" }
|
||||
lance-namespace-impls = { version = "=3.0.1", default-features = false }
|
||||
lance-table = { version = "=3.0.1" }
|
||||
lance-testing = { version = "=3.0.1" }
|
||||
lance-datafusion = { version = "=3.0.1" }
|
||||
lance-encoding = { version = "=3.0.1" }
|
||||
lance-arrow = { version = "=3.0.1" }
|
||||
ahash = "0.8"
|
||||
# Note that this one does not include pyarrow
|
||||
arrow = { version = "57.2", optional = false }
|
||||
|
||||
@@ -3,6 +3,7 @@
|
||||
from __future__ import annotations
|
||||
|
||||
import argparse
|
||||
import functools
|
||||
import json
|
||||
import os
|
||||
import re
|
||||
@@ -26,6 +27,7 @@ SEMVER_RE = re.compile(
|
||||
)
|
||||
|
||||
|
||||
@functools.total_ordering
|
||||
@dataclass(frozen=True)
|
||||
class SemVer:
|
||||
major: int
|
||||
@@ -156,7 +158,9 @@ def read_current_version(repo_root: Path) -> str:
|
||||
|
||||
|
||||
def determine_latest_tag(tags: Iterable[TagInfo]) -> TagInfo:
|
||||
return max(tags, key=lambda tag: tag.semver)
|
||||
# Stable releases (no prerelease) are always preferred over pre-releases.
|
||||
# Within each group, standard semver ordering applies.
|
||||
return max(tags, key=lambda tag: (not tag.semver.prerelease, tag.semver))
|
||||
|
||||
|
||||
def write_outputs(args: argparse.Namespace, payload: dict) -> None:
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
version: "3.9"
|
||||
services:
|
||||
localstack:
|
||||
image: localstack/localstack:3.3
|
||||
image: localstack/localstack:4.0
|
||||
ports:
|
||||
- 4566:4566
|
||||
environment:
|
||||
|
||||
@@ -1,27 +1,27 @@
|
||||
#Simple base dockerfile that supports basic dependencies required to run lance with FTS and Hybrid Search
|
||||
#Usage docker build -t lancedb:latest -f Dockerfile .
|
||||
FROM python:3.10-slim-buster
|
||||
# Simple base dockerfile that supports basic dependencies required to run lance with FTS and Hybrid Search
|
||||
# Usage: docker build -t lancedb:latest -f Dockerfile .
|
||||
FROM python:3.12-slim-bookworm
|
||||
|
||||
# Install Rust
|
||||
RUN apt-get update && apt-get install -y curl build-essential && \
|
||||
curl https://sh.rustup.rs -sSf | sh -s -- -y
|
||||
|
||||
# Set the environment variable for Rust
|
||||
ENV PATH="/root/.cargo/bin:${PATH}"
|
||||
|
||||
# Install protobuf compiler
|
||||
RUN apt-get install -y protobuf-compiler && \
|
||||
# Install build dependencies in a single layer
|
||||
RUN apt-get update && \
|
||||
apt-get install -y --no-install-recommends \
|
||||
curl \
|
||||
build-essential \
|
||||
protobuf-compiler \
|
||||
git \
|
||||
ca-certificates && \
|
||||
apt-get clean && \
|
||||
rm -rf /var/lib/apt/lists/*
|
||||
|
||||
RUN apt-get -y update &&\
|
||||
apt-get -y upgrade && \
|
||||
apt-get -y install git
|
||||
# Install Rust (pinned installer, non-interactive)
|
||||
RUN curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y --default-toolchain stable --profile minimal
|
||||
|
||||
# Set the environment variable for Rust
|
||||
ENV PATH="/root/.cargo/bin:${PATH}"
|
||||
|
||||
# Verify installations
|
||||
RUN python --version && \
|
||||
rustc --version && \
|
||||
protoc --version
|
||||
|
||||
RUN pip install tantivy lancedb
|
||||
RUN pip install --no-cache-dir tantivy lancedb
|
||||
|
||||
@@ -52,14 +52,21 @@ plugins:
|
||||
options:
|
||||
docstring_style: numpy
|
||||
heading_level: 3
|
||||
show_source: true
|
||||
show_symbol_type_in_heading: true
|
||||
show_signature_annotations: true
|
||||
show_root_heading: true
|
||||
show_docstring_examples: true
|
||||
show_docstring_attributes: false
|
||||
show_docstring_other_parameters: true
|
||||
show_symbol_type_heading: true
|
||||
show_labels: false
|
||||
show_if_no_docstring: true
|
||||
show_source: false
|
||||
members_order: source
|
||||
docstring_section_style: list
|
||||
signature_crossrefs: true
|
||||
separate_signature: true
|
||||
filters:
|
||||
- "!^_"
|
||||
import:
|
||||
# for cross references
|
||||
- https://arrow.apache.org/docs/objects.inv
|
||||
@@ -113,7 +120,7 @@ markdown_extensions:
|
||||
emoji_index: !!python/name:material.extensions.emoji.twemoji
|
||||
emoji_generator: !!python/name:material.extensions.emoji.to_svg
|
||||
- markdown.extensions.toc:
|
||||
toc_depth: 3
|
||||
toc_depth: 4
|
||||
permalink: true
|
||||
permalink_title: Anchor link to this section
|
||||
|
||||
|
||||
@@ -1,9 +1,9 @@
|
||||
mkdocs==1.5.3
|
||||
mkdocs-jupyter==0.24.1
|
||||
mkdocs-material==9.5.3
|
||||
mkdocs-autorefs<=1.0
|
||||
mkdocs-autorefs>=0.5,<=1.0
|
||||
mkdocstrings[python]==0.25.2
|
||||
griffe
|
||||
mkdocs-render-swagger-plugin
|
||||
pydantic
|
||||
mkdocs-redirects
|
||||
griffe>=0.40,<1.0
|
||||
mkdocs-render-swagger-plugin>=0.1.0
|
||||
pydantic>=2.0,<3.0
|
||||
mkdocs-redirects>=1.2.0
|
||||
@@ -14,7 +14,7 @@ Add the following dependency to your `pom.xml`:
|
||||
<dependency>
|
||||
<groupId>com.lancedb</groupId>
|
||||
<artifactId>lancedb-core</artifactId>
|
||||
<version>0.27.0-beta.3</version>
|
||||
<version>0.27.1</version>
|
||||
</dependency>
|
||||
```
|
||||
|
||||
|
||||
@@ -71,11 +71,12 @@ Add new columns with defined values.
|
||||
|
||||
#### Parameters
|
||||
|
||||
* **newColumnTransforms**: [`AddColumnsSql`](../interfaces/AddColumnsSql.md)[]
|
||||
pairs of column names and
|
||||
the SQL expression to use to calculate the value of the new column. These
|
||||
expressions will be evaluated for each row in the table, and can
|
||||
reference existing columns in the table.
|
||||
* **newColumnTransforms**: `Field`<`any`> \| `Field`<`any`>[] \| `Schema`<`any`> \| [`AddColumnsSql`](../interfaces/AddColumnsSql.md)[]
|
||||
Either:
|
||||
- An array of objects with column names and SQL expressions to calculate values
|
||||
- A single Arrow Field defining one column with its data type (column will be initialized with null values)
|
||||
- An array of Arrow Fields defining columns with their data types (columns will be initialized with null values)
|
||||
- An Arrow Schema defining columns with their data types (columns will be initialized with null values)
|
||||
|
||||
#### Returns
|
||||
|
||||
@@ -484,19 +485,7 @@ Modeled after ``VACUUM`` in PostgreSQL.
|
||||
- Prune: Removes old versions of the dataset
|
||||
- Index: Optimizes the indices, adding new data to existing indices
|
||||
|
||||
Experimental API
|
||||
----------------
|
||||
|
||||
The optimization process is undergoing active development and may change.
|
||||
Our goal with these changes is to improve the performance of optimization and
|
||||
reduce the complexity.
|
||||
|
||||
That being said, it is essential today to run optimize if you want the best
|
||||
performance. It should be stable and safe to use in production, but it our
|
||||
hope that the API may be simplified (or not even need to be called) in the
|
||||
future.
|
||||
|
||||
The frequency an application shoudl call optimize is based on the frequency of
|
||||
The frequency an application should call optimize is based on the frequency of
|
||||
data modifications. If data is frequently added, deleted, or updated then
|
||||
optimize should be run frequently. A good rule of thumb is to run optimize if
|
||||
you have added or modified 100,000 or more records or run more than 20 data
|
||||
|
||||
@@ -37,3 +37,12 @@ tbl.optimize({cleanupOlderThan: new Date()});
|
||||
```ts
|
||||
deleteUnverified: boolean;
|
||||
```
|
||||
|
||||
Because they may be part of an in-progress transaction, files newer than
|
||||
7 days old are not deleted by default. If you are sure that there are no
|
||||
in-progress transactions, then you can set this to true to delete all
|
||||
files older than `cleanupOlderThan`.
|
||||
|
||||
**WARNING**: This should only be set to true if you can guarantee that
|
||||
no other process is currently working on this dataset. Otherwise the
|
||||
dataset could be put into a corrupted state.
|
||||
|
||||
@@ -1,4 +1,4 @@
|
||||
# LanceDB Java SDK
|
||||
# LanceDB Java Enterprise Client
|
||||
|
||||
## Configuration and Initialization
|
||||
|
||||
|
||||
@@ -8,7 +8,7 @@
|
||||
<parent>
|
||||
<groupId>com.lancedb</groupId>
|
||||
<artifactId>lancedb-parent</artifactId>
|
||||
<version>0.27.0-beta.3</version>
|
||||
<version>0.27.1-final.0</version>
|
||||
<relativePath>../pom.xml</relativePath>
|
||||
</parent>
|
||||
|
||||
@@ -56,21 +56,21 @@
|
||||
<dependency>
|
||||
<groupId>org.apache.logging.log4j</groupId>
|
||||
<artifactId>log4j-slf4j2-impl</artifactId>
|
||||
<version>2.24.3</version>
|
||||
<version>2.25.3</version>
|
||||
<scope>test</scope>
|
||||
</dependency>
|
||||
|
||||
<dependency>
|
||||
<groupId>org.apache.logging.log4j</groupId>
|
||||
<artifactId>log4j-core</artifactId>
|
||||
<version>2.24.3</version>
|
||||
<version>2.25.3</version>
|
||||
<scope>test</scope>
|
||||
</dependency>
|
||||
|
||||
<dependency>
|
||||
<groupId>org.apache.logging.log4j</groupId>
|
||||
<artifactId>log4j-api</artifactId>
|
||||
<version>2.24.3</version>
|
||||
<version>2.25.3</version>
|
||||
<scope>test</scope>
|
||||
</dependency>
|
||||
</dependencies>
|
||||
|
||||
18
java/pom.xml
18
java/pom.xml
@@ -6,7 +6,7 @@
|
||||
|
||||
<groupId>com.lancedb</groupId>
|
||||
<artifactId>lancedb-parent</artifactId>
|
||||
<version>0.27.0-beta.3</version>
|
||||
<version>0.27.1-final.0</version>
|
||||
<packaging>pom</packaging>
|
||||
<name>${project.artifactId}</name>
|
||||
<description>LanceDB Java SDK Parent POM</description>
|
||||
@@ -111,7 +111,7 @@
|
||||
<plugin>
|
||||
<groupId>org.apache.maven.plugins</groupId>
|
||||
<artifactId>maven-source-plugin</artifactId>
|
||||
<version>2.2.1</version>
|
||||
<version>3.3.1</version>
|
||||
<executions>
|
||||
<execution>
|
||||
<id>attach-sources</id>
|
||||
@@ -124,7 +124,7 @@
|
||||
<plugin>
|
||||
<groupId>org.apache.maven.plugins</groupId>
|
||||
<artifactId>maven-javadoc-plugin</artifactId>
|
||||
<version>2.9.1</version>
|
||||
<version>3.11.2</version>
|
||||
<executions>
|
||||
<execution>
|
||||
<id>attach-javadocs</id>
|
||||
@@ -178,15 +178,15 @@
|
||||
<plugins>
|
||||
<plugin>
|
||||
<artifactId>maven-clean-plugin</artifactId>
|
||||
<version>3.1.0</version>
|
||||
<version>3.4.1</version>
|
||||
</plugin>
|
||||
<plugin>
|
||||
<artifactId>maven-resources-plugin</artifactId>
|
||||
<version>3.0.2</version>
|
||||
<version>3.3.1</version>
|
||||
</plugin>
|
||||
<plugin>
|
||||
<artifactId>maven-compiler-plugin</artifactId>
|
||||
<version>3.8.1</version>
|
||||
<version>3.14.0</version>
|
||||
<configuration>
|
||||
<compilerArgs>
|
||||
<arg>-h</arg>
|
||||
@@ -205,11 +205,11 @@
|
||||
</plugin>
|
||||
<plugin>
|
||||
<artifactId>maven-jar-plugin</artifactId>
|
||||
<version>3.0.2</version>
|
||||
<version>3.4.2</version>
|
||||
</plugin>
|
||||
<plugin>
|
||||
<artifactId>maven-install-plugin</artifactId>
|
||||
<version>2.5.2</version>
|
||||
<version>3.1.3</version>
|
||||
</plugin>
|
||||
<plugin>
|
||||
<groupId>com.diffplug.spotless</groupId>
|
||||
@@ -327,7 +327,7 @@
|
||||
<plugin>
|
||||
<groupId>org.apache.maven.plugins</groupId>
|
||||
<artifactId>maven-gpg-plugin</artifactId>
|
||||
<version>1.5</version>
|
||||
<version>3.2.7</version>
|
||||
<executions>
|
||||
<execution>
|
||||
<id>sign-artifacts</id>
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
[package]
|
||||
name = "lancedb-nodejs"
|
||||
edition.workspace = true
|
||||
version = "0.27.0-beta.3"
|
||||
version = "0.27.1"
|
||||
license.workspace = true
|
||||
description.workspace = true
|
||||
repository.workspace = true
|
||||
@@ -25,12 +25,12 @@ napi = { version = "3.8.3", default-features = false, features = [
|
||||
] }
|
||||
napi-derive = "3.5.2"
|
||||
# Prevent dynamic linking of lzma, which comes from datafusion
|
||||
lzma-sys = { version = "*", features = ["static"] }
|
||||
lzma-sys = { version = "0.1", features = ["static"] }
|
||||
log.workspace = true
|
||||
|
||||
# Workaround for build failure until we can fix it.
|
||||
aws-lc-sys = "=0.28.0"
|
||||
aws-lc-rs = "=1.13.0"
|
||||
# Pin to resolve build failures; update periodically for security patches.
|
||||
aws-lc-sys = "=0.38.0"
|
||||
aws-lc-rs = "=1.16.1"
|
||||
|
||||
[build-dependencies]
|
||||
napi-build = "2.3.1"
|
||||
|
||||
@@ -63,6 +63,7 @@ describe.each([arrow15, arrow16, arrow17, arrow18])(
|
||||
tableFromIPC,
|
||||
DataType,
|
||||
Dictionary,
|
||||
Uint8: ArrowUint8,
|
||||
// biome-ignore lint/suspicious/noExplicitAny: <explanation>
|
||||
} = <any>arrow;
|
||||
type Schema = ApacheArrow["Schema"];
|
||||
@@ -362,6 +363,38 @@ describe.each([arrow15, arrow16, arrow17, arrow18])(
|
||||
).toEqual(new Float64().toString());
|
||||
});
|
||||
|
||||
it("will infer FixedSizeList<Float32> from Float32Array values", async function () {
|
||||
const table = makeArrowTable([
|
||||
{ id: "a", vector: new Float32Array([0.1, 0.2, 0.3]) },
|
||||
{ id: "b", vector: new Float32Array([0.4, 0.5, 0.6]) },
|
||||
]);
|
||||
|
||||
expect(DataType.isFixedSizeList(table.getChild("vector")?.type)).toBe(
|
||||
true,
|
||||
);
|
||||
const vectorType = table.getChild("vector")?.type;
|
||||
expect(vectorType.listSize).toBe(3);
|
||||
expect(vectorType.children[0].type.toString()).toEqual(
|
||||
new Float32().toString(),
|
||||
);
|
||||
});
|
||||
|
||||
it("will infer FixedSizeList<Uint8> from Uint8Array values", async function () {
|
||||
const table = makeArrowTable([
|
||||
{ id: "a", vector: new Uint8Array([1, 2, 3]) },
|
||||
{ id: "b", vector: new Uint8Array([4, 5, 6]) },
|
||||
]);
|
||||
|
||||
expect(DataType.isFixedSizeList(table.getChild("vector")?.type)).toBe(
|
||||
true,
|
||||
);
|
||||
const vectorType = table.getChild("vector")?.type;
|
||||
expect(vectorType.listSize).toBe(3);
|
||||
expect(vectorType.children[0].type.toString()).toEqual(
|
||||
new ArrowUint8().toString(),
|
||||
);
|
||||
});
|
||||
|
||||
it("will use dictionary encoded strings if asked", async function () {
|
||||
const table = makeArrowTable([{ str: "hello" }]);
|
||||
expect(DataType.isUtf8(table.getChild("str")?.type)).toBe(true);
|
||||
|
||||
@@ -1259,6 +1259,98 @@ describe("schema evolution", function () {
|
||||
expect(await table.schema()).toEqual(expectedSchema);
|
||||
});
|
||||
|
||||
it("can add columns with schema for explicit data types", async function () {
|
||||
const con = await connect(tmpDir.name);
|
||||
const table = await con.createTable("vectors", [
|
||||
{ id: 1n, vector: [0.1, 0.2] },
|
||||
]);
|
||||
|
||||
// Define schema for new columns with explicit data types
|
||||
// Note: All columns must be nullable when using addColumns with Schema
|
||||
// because they are initially populated with null values
|
||||
const newColumnsSchema = new Schema([
|
||||
new Field("price", new Float64(), true),
|
||||
new Field("category", new Utf8(), true),
|
||||
new Field("rating", new Int32(), true),
|
||||
]);
|
||||
|
||||
const result = await table.addColumns(newColumnsSchema);
|
||||
expect(result).toHaveProperty("version");
|
||||
expect(result.version).toBe(2);
|
||||
|
||||
const expectedSchema = new Schema([
|
||||
new Field("id", new Int64(), true),
|
||||
new Field(
|
||||
"vector",
|
||||
new FixedSizeList(2, new Field("item", new Float32(), true)),
|
||||
true,
|
||||
),
|
||||
new Field("price", new Float64(), true),
|
||||
new Field("category", new Utf8(), true),
|
||||
new Field("rating", new Int32(), true),
|
||||
]);
|
||||
expect(await table.schema()).toEqual(expectedSchema);
|
||||
|
||||
// Verify that new columns are populated with null values
|
||||
const results = await table.query().toArray();
|
||||
expect(results).toHaveLength(1);
|
||||
expect(results[0].price).toBeNull();
|
||||
expect(results[0].category).toBeNull();
|
||||
expect(results[0].rating).toBeNull();
|
||||
});
|
||||
|
||||
it("can add a single column using Field", async function () {
|
||||
const con = await connect(tmpDir.name);
|
||||
const table = await con.createTable("vectors", [
|
||||
{ id: 1n, vector: [0.1, 0.2] },
|
||||
]);
|
||||
|
||||
// Add a single field
|
||||
const priceField = new Field("price", new Float64(), true);
|
||||
const result = await table.addColumns(priceField);
|
||||
expect(result).toHaveProperty("version");
|
||||
expect(result.version).toBe(2);
|
||||
|
||||
const expectedSchema = new Schema([
|
||||
new Field("id", new Int64(), true),
|
||||
new Field(
|
||||
"vector",
|
||||
new FixedSizeList(2, new Field("item", new Float32(), true)),
|
||||
true,
|
||||
),
|
||||
new Field("price", new Float64(), true),
|
||||
]);
|
||||
expect(await table.schema()).toEqual(expectedSchema);
|
||||
});
|
||||
|
||||
it("can add multiple columns using array of Fields", async function () {
|
||||
const con = await connect(tmpDir.name);
|
||||
const table = await con.createTable("vectors", [
|
||||
{ id: 1n, vector: [0.1, 0.2] },
|
||||
]);
|
||||
|
||||
// Add multiple fields as array
|
||||
const fields = [
|
||||
new Field("price", new Float64(), true),
|
||||
new Field("category", new Utf8(), true),
|
||||
];
|
||||
const result = await table.addColumns(fields);
|
||||
expect(result).toHaveProperty("version");
|
||||
expect(result.version).toBe(2);
|
||||
|
||||
const expectedSchema = new Schema([
|
||||
new Field("id", new Int64(), true),
|
||||
new Field(
|
||||
"vector",
|
||||
new FixedSizeList(2, new Field("item", new Float32(), true)),
|
||||
true,
|
||||
),
|
||||
new Field("price", new Float64(), true),
|
||||
new Field("category", new Utf8(), true),
|
||||
]);
|
||||
expect(await table.schema()).toEqual(expectedSchema);
|
||||
});
|
||||
|
||||
it("can alter the columns in the schema", async function () {
|
||||
const con = await connect(tmpDir.name);
|
||||
const schema = new Schema([
|
||||
@@ -2204,3 +2296,36 @@ describe("when creating an empty table", () => {
|
||||
expect((actualSchema.fields[1].type as Float64).precision).toBe(2);
|
||||
});
|
||||
});
|
||||
|
||||
// Ensure we can create float32 arrays without using Arrow
|
||||
// by utilizing native JS TypedArray support
|
||||
//
|
||||
// https://github.com/lancedb/lancedb/issues/3115
|
||||
describe("when creating a table with Float32Array vectors", () => {
|
||||
let tmpDir: tmp.DirResult;
|
||||
beforeEach(() => {
|
||||
tmpDir = tmp.dirSync({ unsafeCleanup: true });
|
||||
});
|
||||
afterEach(() => {
|
||||
tmpDir.removeCallback();
|
||||
});
|
||||
|
||||
it("should persist Float32Array as FixedSizeList<Float32> in the LanceDB schema", async () => {
|
||||
const db = await connect(tmpDir.name);
|
||||
const table = await db.createTable("test", [
|
||||
{ id: "a", vector: new Float32Array([0.1, 0.2, 0.3]) },
|
||||
{ id: "b", vector: new Float32Array([0.4, 0.5, 0.6]) },
|
||||
]);
|
||||
|
||||
const schema = await table.schema();
|
||||
const vectorField = schema.fields.find((f) => f.name === "vector");
|
||||
expect(vectorField).toBeDefined();
|
||||
expect(vectorField!.type).toBeInstanceOf(FixedSizeList);
|
||||
|
||||
const fsl = vectorField!.type as FixedSizeList;
|
||||
expect(fsl.listSize).toBe(3);
|
||||
expect(fsl.children[0].type.typeId).toBe(Type.Float);
|
||||
// precision: HALF=0, SINGLE=1, DOUBLE=2
|
||||
expect((fsl.children[0].type as Float32).precision).toBe(1);
|
||||
});
|
||||
});
|
||||
|
||||
599
nodejs/examples/package-lock.json
generated
599
nodejs/examples/package-lock.json
generated
@@ -30,12 +30,15 @@
|
||||
"x64",
|
||||
"arm64"
|
||||
],
|
||||
"dev": true,
|
||||
"license": "Apache-2.0",
|
||||
"optional": true,
|
||||
"os": [
|
||||
"darwin",
|
||||
"linux",
|
||||
"win32"
|
||||
],
|
||||
"peer": true,
|
||||
"dependencies": {
|
||||
"reflect-metadata": "^0.2.2"
|
||||
},
|
||||
@@ -91,14 +94,15 @@
|
||||
}
|
||||
},
|
||||
"node_modules/@babel/code-frame": {
|
||||
"version": "7.26.2",
|
||||
"resolved": "https://registry.npmjs.org/@babel/code-frame/-/code-frame-7.26.2.tgz",
|
||||
"integrity": "sha512-RJlIHRueQgwWitWgF8OdFYGZX328Ax5BCemNGlqHfplnRT9ESi8JkFlvaVYbS+UubVY6dpv87Fs2u5M29iNFVQ==",
|
||||
"version": "7.29.0",
|
||||
"resolved": "https://registry.npmjs.org/@babel/code-frame/-/code-frame-7.29.0.tgz",
|
||||
"integrity": "sha512-9NhCeYjq9+3uxgdtp20LSiJXJvN0FeCtNGpJxuMFZ1Kv3cWUNb6DOhJwUvcVCzKGR66cw4njwM6hrJLqgOwbcw==",
|
||||
"dev": true,
|
||||
"license": "MIT",
|
||||
"dependencies": {
|
||||
"@babel/helper-validator-identifier": "^7.25.9",
|
||||
"@babel/helper-validator-identifier": "^7.28.5",
|
||||
"js-tokens": "^4.0.0",
|
||||
"picocolors": "^1.0.0"
|
||||
"picocolors": "^1.1.1"
|
||||
},
|
||||
"engines": {
|
||||
"node": ">=6.9.0"
|
||||
@@ -233,19 +237,21 @@
|
||||
}
|
||||
},
|
||||
"node_modules/@babel/helper-string-parser": {
|
||||
"version": "7.25.9",
|
||||
"resolved": "https://registry.npmjs.org/@babel/helper-string-parser/-/helper-string-parser-7.25.9.tgz",
|
||||
"integrity": "sha512-4A/SCr/2KLd5jrtOMFzaKjVtAei3+2r/NChoBNoZ3EyP/+GlhoaEGoWOZUmFmoITP7zOJyHIMm+DYRd8o3PvHA==",
|
||||
"version": "7.27.1",
|
||||
"resolved": "https://registry.npmjs.org/@babel/helper-string-parser/-/helper-string-parser-7.27.1.tgz",
|
||||
"integrity": "sha512-qMlSxKbpRlAridDExk92nSobyDdpPijUq2DW6oDnUqd0iOGxmQjyqhMIihI9+zv4LPyZdRje2cavWPbCbWm3eA==",
|
||||
"dev": true,
|
||||
"license": "MIT",
|
||||
"engines": {
|
||||
"node": ">=6.9.0"
|
||||
}
|
||||
},
|
||||
"node_modules/@babel/helper-validator-identifier": {
|
||||
"version": "7.25.9",
|
||||
"resolved": "https://registry.npmjs.org/@babel/helper-validator-identifier/-/helper-validator-identifier-7.25.9.tgz",
|
||||
"integrity": "sha512-Ed61U6XJc3CVRfkERJWDz4dJwKe7iLmmJsbOGu9wSloNSFttHV0I8g6UAgb7qnK5ly5bGLPd4oXZlxCdANBOWQ==",
|
||||
"version": "7.28.5",
|
||||
"resolved": "https://registry.npmjs.org/@babel/helper-validator-identifier/-/helper-validator-identifier-7.28.5.tgz",
|
||||
"integrity": "sha512-qSs4ifwzKJSV39ucNjsvc6WVHs6b7S03sOh2OcHF9UHfVPqWWALUsNUVzhSBiItjRZoLHx7nIarVjqKVusUZ1Q==",
|
||||
"dev": true,
|
||||
"license": "MIT",
|
||||
"engines": {
|
||||
"node": ">=6.9.0"
|
||||
}
|
||||
@@ -260,25 +266,27 @@
|
||||
}
|
||||
},
|
||||
"node_modules/@babel/helpers": {
|
||||
"version": "7.26.0",
|
||||
"resolved": "https://registry.npmjs.org/@babel/helpers/-/helpers-7.26.0.tgz",
|
||||
"integrity": "sha512-tbhNuIxNcVb21pInl3ZSjksLCvgdZy9KwJ8brv993QtIVKJBBkYXz4q4ZbAv31GdnC+R90np23L5FbEBlthAEw==",
|
||||
"version": "7.28.6",
|
||||
"resolved": "https://registry.npmjs.org/@babel/helpers/-/helpers-7.28.6.tgz",
|
||||
"integrity": "sha512-xOBvwq86HHdB7WUDTfKfT/Vuxh7gElQ+Sfti2Cy6yIWNW05P8iUslOVcZ4/sKbE+/jQaukQAdz/gf3724kYdqw==",
|
||||
"dev": true,
|
||||
"license": "MIT",
|
||||
"dependencies": {
|
||||
"@babel/template": "^7.25.9",
|
||||
"@babel/types": "^7.26.0"
|
||||
"@babel/template": "^7.28.6",
|
||||
"@babel/types": "^7.28.6"
|
||||
},
|
||||
"engines": {
|
||||
"node": ">=6.9.0"
|
||||
}
|
||||
},
|
||||
"node_modules/@babel/parser": {
|
||||
"version": "7.26.2",
|
||||
"resolved": "https://registry.npmjs.org/@babel/parser/-/parser-7.26.2.tgz",
|
||||
"integrity": "sha512-DWMCZH9WA4Maitz2q21SRKHo9QXZxkDsbNZoVD62gusNtNBBqDg9i7uOhASfTfIGNzW+O+r7+jAlM8dwphcJKQ==",
|
||||
"version": "7.29.0",
|
||||
"resolved": "https://registry.npmjs.org/@babel/parser/-/parser-7.29.0.tgz",
|
||||
"integrity": "sha512-IyDgFV5GeDUVX4YdF/3CPULtVGSXXMLh1xVIgdCgxApktqnQV0r7/8Nqthg+8YLGaAtdyIlo2qIdZrbCv4+7ww==",
|
||||
"dev": true,
|
||||
"license": "MIT",
|
||||
"dependencies": {
|
||||
"@babel/types": "^7.26.0"
|
||||
"@babel/types": "^7.29.0"
|
||||
},
|
||||
"bin": {
|
||||
"parser": "bin/babel-parser.js"
|
||||
@@ -510,14 +518,15 @@
|
||||
}
|
||||
},
|
||||
"node_modules/@babel/template": {
|
||||
"version": "7.25.9",
|
||||
"resolved": "https://registry.npmjs.org/@babel/template/-/template-7.25.9.tgz",
|
||||
"integrity": "sha512-9DGttpmPvIxBb/2uwpVo3dqJ+O6RooAFOS+lB+xDqoE2PVCE8nfoHMdZLpfCQRLwvohzXISPZcgxt80xLfsuwg==",
|
||||
"version": "7.28.6",
|
||||
"resolved": "https://registry.npmjs.org/@babel/template/-/template-7.28.6.tgz",
|
||||
"integrity": "sha512-YA6Ma2KsCdGb+WC6UpBVFJGXL58MDA6oyONbjyF/+5sBgxY/dwkhLogbMT2GXXyU84/IhRw/2D1Os1B/giz+BQ==",
|
||||
"dev": true,
|
||||
"license": "MIT",
|
||||
"dependencies": {
|
||||
"@babel/code-frame": "^7.25.9",
|
||||
"@babel/parser": "^7.25.9",
|
||||
"@babel/types": "^7.25.9"
|
||||
"@babel/code-frame": "^7.28.6",
|
||||
"@babel/parser": "^7.28.6",
|
||||
"@babel/types": "^7.28.6"
|
||||
},
|
||||
"engines": {
|
||||
"node": ">=6.9.0"
|
||||
@@ -542,13 +551,14 @@
|
||||
}
|
||||
},
|
||||
"node_modules/@babel/types": {
|
||||
"version": "7.26.0",
|
||||
"resolved": "https://registry.npmjs.org/@babel/types/-/types-7.26.0.tgz",
|
||||
"integrity": "sha512-Z/yiTPj+lDVnF7lWeKCIJzaIkI0vYO87dMpZ4bg4TDrFe4XXLFWL1TbXU27gBP3QccxV9mZICCrnjnYlJjXHOA==",
|
||||
"version": "7.29.0",
|
||||
"resolved": "https://registry.npmjs.org/@babel/types/-/types-7.29.0.tgz",
|
||||
"integrity": "sha512-LwdZHpScM4Qz8Xw2iKSzS+cfglZzJGvofQICy7W7v4caru4EaAmyUuO6BGrbyQ2mYV11W0U8j5mBhd14dd3B0A==",
|
||||
"dev": true,
|
||||
"license": "MIT",
|
||||
"dependencies": {
|
||||
"@babel/helper-string-parser": "^7.25.9",
|
||||
"@babel/helper-validator-identifier": "^7.25.9"
|
||||
"@babel/helper-string-parser": "^7.27.1",
|
||||
"@babel/helper-validator-identifier": "^7.28.5"
|
||||
},
|
||||
"engines": {
|
||||
"node": ">=6.9.0"
|
||||
@@ -1151,95 +1161,6 @@
|
||||
"url": "https://opencollective.com/libvips"
|
||||
}
|
||||
},
|
||||
"node_modules/@isaacs/cliui": {
|
||||
"version": "8.0.2",
|
||||
"resolved": "https://registry.npmjs.org/@isaacs/cliui/-/cliui-8.0.2.tgz",
|
||||
"integrity": "sha512-O8jcjabXaleOG9DQ0+ARXWZBTfnP4WNAqzuiJK7ll44AmxGKv/J2M4TPjxjY3znBCfvBXFzucm1twdyFybFqEA==",
|
||||
"dependencies": {
|
||||
"string-width": "^5.1.2",
|
||||
"string-width-cjs": "npm:string-width@^4.2.0",
|
||||
"strip-ansi": "^7.0.1",
|
||||
"strip-ansi-cjs": "npm:strip-ansi@^6.0.1",
|
||||
"wrap-ansi": "^8.1.0",
|
||||
"wrap-ansi-cjs": "npm:wrap-ansi@^7.0.0"
|
||||
},
|
||||
"engines": {
|
||||
"node": ">=12"
|
||||
}
|
||||
},
|
||||
"node_modules/@isaacs/cliui/node_modules/ansi-regex": {
|
||||
"version": "6.1.0",
|
||||
"resolved": "https://registry.npmjs.org/ansi-regex/-/ansi-regex-6.1.0.tgz",
|
||||
"integrity": "sha512-7HSX4QQb4CspciLpVFwyRe79O3xsIZDDLER21kERQ71oaPodF8jL725AgJMFAYbooIqolJoRLuM81SpeUkpkvA==",
|
||||
"engines": {
|
||||
"node": ">=12"
|
||||
},
|
||||
"funding": {
|
||||
"url": "https://github.com/chalk/ansi-regex?sponsor=1"
|
||||
}
|
||||
},
|
||||
"node_modules/@isaacs/cliui/node_modules/ansi-styles": {
|
||||
"version": "6.2.1",
|
||||
"resolved": "https://registry.npmjs.org/ansi-styles/-/ansi-styles-6.2.1.tgz",
|
||||
"integrity": "sha512-bN798gFfQX+viw3R7yrGWRqnrN2oRkEkUjjl4JNn4E8GxxbjtG3FbrEIIY3l8/hrwUwIeCZvi4QuOTP4MErVug==",
|
||||
"engines": {
|
||||
"node": ">=12"
|
||||
},
|
||||
"funding": {
|
||||
"url": "https://github.com/chalk/ansi-styles?sponsor=1"
|
||||
}
|
||||
},
|
||||
"node_modules/@isaacs/cliui/node_modules/emoji-regex": {
|
||||
"version": "9.2.2",
|
||||
"resolved": "https://registry.npmjs.org/emoji-regex/-/emoji-regex-9.2.2.tgz",
|
||||
"integrity": "sha512-L18DaJsXSUk2+42pv8mLs5jJT2hqFkFE4j21wOmgbUqsZ2hL72NsUU785g9RXgo3s0ZNgVl42TiHp3ZtOv/Vyg=="
|
||||
},
|
||||
"node_modules/@isaacs/cliui/node_modules/string-width": {
|
||||
"version": "5.1.2",
|
||||
"resolved": "https://registry.npmjs.org/string-width/-/string-width-5.1.2.tgz",
|
||||
"integrity": "sha512-HnLOCR3vjcY8beoNLtcjZ5/nxn2afmME6lhrDrebokqMap+XbeW8n9TXpPDOqdGK5qcI3oT0GKTW6wC7EMiVqA==",
|
||||
"dependencies": {
|
||||
"eastasianwidth": "^0.2.0",
|
||||
"emoji-regex": "^9.2.2",
|
||||
"strip-ansi": "^7.0.1"
|
||||
},
|
||||
"engines": {
|
||||
"node": ">=12"
|
||||
},
|
||||
"funding": {
|
||||
"url": "https://github.com/sponsors/sindresorhus"
|
||||
}
|
||||
},
|
||||
"node_modules/@isaacs/cliui/node_modules/strip-ansi": {
|
||||
"version": "7.1.0",
|
||||
"resolved": "https://registry.npmjs.org/strip-ansi/-/strip-ansi-7.1.0.tgz",
|
||||
"integrity": "sha512-iq6eVVI64nQQTRYq2KtEg2d2uU7LElhTJwsH4YzIHZshxlgZms/wIc4VoDQTlG/IvVIrBKG06CrZnp0qv7hkcQ==",
|
||||
"dependencies": {
|
||||
"ansi-regex": "^6.0.1"
|
||||
},
|
||||
"engines": {
|
||||
"node": ">=12"
|
||||
},
|
||||
"funding": {
|
||||
"url": "https://github.com/chalk/strip-ansi?sponsor=1"
|
||||
}
|
||||
},
|
||||
"node_modules/@isaacs/cliui/node_modules/wrap-ansi": {
|
||||
"version": "8.1.0",
|
||||
"resolved": "https://registry.npmjs.org/wrap-ansi/-/wrap-ansi-8.1.0.tgz",
|
||||
"integrity": "sha512-si7QWI6zUMq56bESFvagtmzMdGOtoxfR+Sez11Mobfc7tm+VkUckk9bW2UeffTGVUbOksxmSw0AA2gs8g71NCQ==",
|
||||
"dependencies": {
|
||||
"ansi-styles": "^6.1.0",
|
||||
"string-width": "^5.0.1",
|
||||
"strip-ansi": "^7.0.1"
|
||||
},
|
||||
"engines": {
|
||||
"node": ">=12"
|
||||
},
|
||||
"funding": {
|
||||
"url": "https://github.com/chalk/wrap-ansi?sponsor=1"
|
||||
}
|
||||
},
|
||||
"node_modules/@isaacs/fs-minipass": {
|
||||
"version": "4.0.1",
|
||||
"resolved": "https://registry.npmjs.org/@isaacs/fs-minipass/-/fs-minipass-4.0.1.tgz",
|
||||
@@ -1606,15 +1527,6 @@
|
||||
"resolved": "../dist",
|
||||
"link": true
|
||||
},
|
||||
"node_modules/@pkgjs/parseargs": {
|
||||
"version": "0.11.0",
|
||||
"resolved": "https://registry.npmjs.org/@pkgjs/parseargs/-/parseargs-0.11.0.tgz",
|
||||
"integrity": "sha512-+1VkjdD0QBLPodGrJUeqarH8VAIvQODIbwh9XpP5Syisf7YoQgsJKPNFoqqLQlu+VQ/tVSshMR6loPMn8U+dPg==",
|
||||
"optional": true,
|
||||
"engines": {
|
||||
"node": ">=14"
|
||||
}
|
||||
},
|
||||
"node_modules/@protobufjs/aspromise": {
|
||||
"version": "1.1.2",
|
||||
"resolved": "https://registry.npmjs.org/@protobufjs/aspromise/-/aspromise-1.1.2.tgz",
|
||||
@@ -1846,6 +1758,7 @@
|
||||
"version": "5.0.1",
|
||||
"resolved": "https://registry.npmjs.org/ansi-regex/-/ansi-regex-5.0.1.tgz",
|
||||
"integrity": "sha512-quJQXlTSUGL2LH9SUXo8VwsY4soanhgo6LNSm84E1LBcE8s3O0wpdiRzyR9z/ZZJMlMWv37qOOb9pdJlMUEKFQ==",
|
||||
"dev": true,
|
||||
"engines": {
|
||||
"node": ">=8"
|
||||
}
|
||||
@@ -1854,6 +1767,7 @@
|
||||
"version": "4.3.0",
|
||||
"resolved": "https://registry.npmjs.org/ansi-styles/-/ansi-styles-4.3.0.tgz",
|
||||
"integrity": "sha512-zbB9rCJAT1rbjiVDb2hqKFHNYLxgtk8NURxZ3IZwD3F6NtxbXZQCnnSi1Lkx+IDohdPlFp222wVALIheZJQSEg==",
|
||||
"dev": true,
|
||||
"dependencies": {
|
||||
"color-convert": "^2.0.1"
|
||||
},
|
||||
@@ -2019,13 +1933,15 @@
|
||||
"node_modules/balanced-match": {
|
||||
"version": "1.0.2",
|
||||
"resolved": "https://registry.npmjs.org/balanced-match/-/balanced-match-1.0.2.tgz",
|
||||
"integrity": "sha512-3oSeUO0TMV67hN1AmbXsK4yaqU7tjiHlbxRDZOpH0KW9+CeX4bRAaX0Anxt0tx2MrpRpWwQaPwIlISEJhYU5Pw=="
|
||||
"integrity": "sha512-3oSeUO0TMV67hN1AmbXsK4yaqU7tjiHlbxRDZOpH0KW9+CeX4bRAaX0Anxt0tx2MrpRpWwQaPwIlISEJhYU5Pw==",
|
||||
"dev": true
|
||||
},
|
||||
"node_modules/brace-expansion": {
|
||||
"version": "1.1.11",
|
||||
"resolved": "https://registry.npmjs.org/brace-expansion/-/brace-expansion-1.1.11.tgz",
|
||||
"integrity": "sha512-iCuPHDFgrHX7H2vEI/5xpz07zSHB00TpugqhmYtVmMO6518mCuRMoOYFldEBl0g187ufozdaHgWKcYFb61qGiA==",
|
||||
"version": "1.1.12",
|
||||
"resolved": "https://registry.npmjs.org/brace-expansion/-/brace-expansion-1.1.12.tgz",
|
||||
"integrity": "sha512-9T9UjW3r0UW5c1Q7GTwllptXwhvYmEzFhzMfZ9H7FQWt+uZePjZPjBP/W1ZEyZ1twGWom5/56TF4lPcqjnDHcg==",
|
||||
"dev": true,
|
||||
"license": "MIT",
|
||||
"dependencies": {
|
||||
"balanced-match": "^1.0.0",
|
||||
"concat-map": "0.0.1"
|
||||
@@ -2102,6 +2018,19 @@
|
||||
"integrity": "sha512-E+XQCRwSbaaiChtv6k6Dwgc+bx+Bs6vuKJHHl5kox/BaKbhiXzqQOwK4cO22yElGp2OCmjwVhT3HmxgyPGnJfQ==",
|
||||
"dev": true
|
||||
},
|
||||
"node_modules/call-bind-apply-helpers": {
|
||||
"version": "1.0.2",
|
||||
"resolved": "https://registry.npmjs.org/call-bind-apply-helpers/-/call-bind-apply-helpers-1.0.2.tgz",
|
||||
"integrity": "sha512-Sp1ablJ0ivDkSzjcaJdxEunN5/XvksFJ2sMBFfq6x0ryhQV/2b/KwFe21cMpmHtPOSij8K99/wSfoEuTObmuMQ==",
|
||||
"license": "MIT",
|
||||
"dependencies": {
|
||||
"es-errors": "^1.3.0",
|
||||
"function-bind": "^1.1.2"
|
||||
},
|
||||
"engines": {
|
||||
"node": ">= 0.4"
|
||||
}
|
||||
},
|
||||
"node_modules/callsites": {
|
||||
"version": "3.1.0",
|
||||
"resolved": "https://registry.npmjs.org/callsites/-/callsites-3.1.0.tgz",
|
||||
@@ -2298,9 +2227,11 @@
|
||||
}
|
||||
},
|
||||
"node_modules/cross-spawn": {
|
||||
"version": "7.0.3",
|
||||
"resolved": "https://registry.npmjs.org/cross-spawn/-/cross-spawn-7.0.3.tgz",
|
||||
"integrity": "sha512-iRDPJKUPVEND7dHPO8rkbOnPpyDygcDFtWjpeWNCgy8WP2rXcxXL8TskReQl6OrB2G7+UJrags1q15Fudc7G6w==",
|
||||
"version": "7.0.6",
|
||||
"resolved": "https://registry.npmjs.org/cross-spawn/-/cross-spawn-7.0.6.tgz",
|
||||
"integrity": "sha512-uV2QOWP2nWzsy2aMp8aRibhi9dlzF5Hgh5SHaB9OiTGEyDTiJJyx0uy51QXdyWbtAHNua4XJzUKca3OzKUd3vA==",
|
||||
"dev": true,
|
||||
"license": "MIT",
|
||||
"dependencies": {
|
||||
"path-key": "^3.1.0",
|
||||
"shebang-command": "^2.0.0",
|
||||
@@ -2384,10 +2315,19 @@
|
||||
"node": "^14.15.0 || ^16.10.0 || >=18.0.0"
|
||||
}
|
||||
},
|
||||
"node_modules/eastasianwidth": {
|
||||
"version": "0.2.0",
|
||||
"resolved": "https://registry.npmjs.org/eastasianwidth/-/eastasianwidth-0.2.0.tgz",
|
||||
"integrity": "sha512-I88TYZWc9XiYHRQ4/3c5rjjfgkjhLyW2luGIheGERbNQ6OY7yTybanSpDXZa8y7VUP9YmDcYa+eyq4ca7iLqWA=="
|
||||
"node_modules/dunder-proto": {
|
||||
"version": "1.0.1",
|
||||
"resolved": "https://registry.npmjs.org/dunder-proto/-/dunder-proto-1.0.1.tgz",
|
||||
"integrity": "sha512-KIN/nDJBQRcXw0MLVhZE9iQHmG68qAVIBg9CqmUYjmQIhgij9U5MFvrqkUL5FbtyyzZuOeOt0zdeRe4UY7ct+A==",
|
||||
"license": "MIT",
|
||||
"dependencies": {
|
||||
"call-bind-apply-helpers": "^1.0.1",
|
||||
"es-errors": "^1.3.0",
|
||||
"gopd": "^1.2.0"
|
||||
},
|
||||
"engines": {
|
||||
"node": ">= 0.4"
|
||||
}
|
||||
},
|
||||
"node_modules/ejs": {
|
||||
"version": "3.1.10",
|
||||
@@ -2425,7 +2365,8 @@
|
||||
"node_modules/emoji-regex": {
|
||||
"version": "8.0.0",
|
||||
"resolved": "https://registry.npmjs.org/emoji-regex/-/emoji-regex-8.0.0.tgz",
|
||||
"integrity": "sha512-MSjYzcWNOA0ewAHpz0MxpYFvwg6yjy1NG3xteoqz644VCo/RPgnr1/GGt+ic3iJTzQ8Eu3TdM14SawnVUmGE6A=="
|
||||
"integrity": "sha512-MSjYzcWNOA0ewAHpz0MxpYFvwg6yjy1NG3xteoqz644VCo/RPgnr1/GGt+ic3iJTzQ8Eu3TdM14SawnVUmGE6A==",
|
||||
"dev": true
|
||||
},
|
||||
"node_modules/error-ex": {
|
||||
"version": "1.3.2",
|
||||
@@ -2442,6 +2383,51 @@
|
||||
"integrity": "sha512-zz06S8t0ozoDXMG+ube26zeCTNXcKIPJZJi8hBrF4idCLms4CG9QtK7qBl1boi5ODzFpjswb5JPmHCbMpjaYzg==",
|
||||
"dev": true
|
||||
},
|
||||
"node_modules/es-define-property": {
|
||||
"version": "1.0.1",
|
||||
"resolved": "https://registry.npmjs.org/es-define-property/-/es-define-property-1.0.1.tgz",
|
||||
"integrity": "sha512-e3nRfgfUZ4rNGL232gUgX06QNyyez04KdjFrF+LTRoOXmrOgFKDg4BCdsjW8EnT69eqdYGmRpJwiPVYNrCaW3g==",
|
||||
"license": "MIT",
|
||||
"engines": {
|
||||
"node": ">= 0.4"
|
||||
}
|
||||
},
|
||||
"node_modules/es-errors": {
|
||||
"version": "1.3.0",
|
||||
"resolved": "https://registry.npmjs.org/es-errors/-/es-errors-1.3.0.tgz",
|
||||
"integrity": "sha512-Zf5H2Kxt2xjTvbJvP2ZWLEICxA6j+hAmMzIlypy4xcBg1vKVnx89Wy0GbS+kf5cwCVFFzdCFh2XSCFNULS6csw==",
|
||||
"license": "MIT",
|
||||
"engines": {
|
||||
"node": ">= 0.4"
|
||||
}
|
||||
},
|
||||
"node_modules/es-object-atoms": {
|
||||
"version": "1.1.1",
|
||||
"resolved": "https://registry.npmjs.org/es-object-atoms/-/es-object-atoms-1.1.1.tgz",
|
||||
"integrity": "sha512-FGgH2h8zKNim9ljj7dankFPcICIK9Cp5bm+c2gQSYePhpaG5+esrLODihIorn+Pe6FGJzWhXQotPv73jTaldXA==",
|
||||
"license": "MIT",
|
||||
"dependencies": {
|
||||
"es-errors": "^1.3.0"
|
||||
},
|
||||
"engines": {
|
||||
"node": ">= 0.4"
|
||||
}
|
||||
},
|
||||
"node_modules/es-set-tostringtag": {
|
||||
"version": "2.1.0",
|
||||
"resolved": "https://registry.npmjs.org/es-set-tostringtag/-/es-set-tostringtag-2.1.0.tgz",
|
||||
"integrity": "sha512-j6vWzfrGVfyXxge+O0x5sh6cvxAog0a/4Rdd2K36zCMV5eJ+/+tOAngRO8cODMNWbVRdVlmGZQL2YS3yR8bIUA==",
|
||||
"license": "MIT",
|
||||
"dependencies": {
|
||||
"es-errors": "^1.3.0",
|
||||
"get-intrinsic": "^1.2.6",
|
||||
"has-tostringtag": "^1.0.2",
|
||||
"hasown": "^2.0.2"
|
||||
},
|
||||
"engines": {
|
||||
"node": ">= 0.4"
|
||||
}
|
||||
},
|
||||
"node_modules/escalade": {
|
||||
"version": "3.2.0",
|
||||
"resolved": "https://registry.npmjs.org/escalade/-/escalade-3.2.0.tgz",
|
||||
@@ -2554,19 +2540,21 @@
|
||||
}
|
||||
},
|
||||
"node_modules/filelist/node_modules/brace-expansion": {
|
||||
"version": "2.0.1",
|
||||
"resolved": "https://registry.npmjs.org/brace-expansion/-/brace-expansion-2.0.1.tgz",
|
||||
"integrity": "sha512-XnAIvQ8eM+kC6aULx6wuQiwVsnzsi9d3WxzV3FpWTGA19F621kwdbsAcFKXgKUHZWsy+mY6iL1sHTxWEFCytDA==",
|
||||
"version": "2.0.2",
|
||||
"resolved": "https://registry.npmjs.org/brace-expansion/-/brace-expansion-2.0.2.tgz",
|
||||
"integrity": "sha512-Jt0vHyM+jmUBqojB7E1NIYadt0vI0Qxjxd2TErW94wDz+E2LAm5vKMXXwg6ZZBTHPuUlDgQHKXvjGBdfcF1ZDQ==",
|
||||
"dev": true,
|
||||
"license": "MIT",
|
||||
"dependencies": {
|
||||
"balanced-match": "^1.0.0"
|
||||
}
|
||||
},
|
||||
"node_modules/filelist/node_modules/minimatch": {
|
||||
"version": "5.1.6",
|
||||
"resolved": "https://registry.npmjs.org/minimatch/-/minimatch-5.1.6.tgz",
|
||||
"integrity": "sha512-lKwV/1brpG6mBUFHtb7NUmtABCb2WZZmm2wNiOA5hAb8VdCS4B3dtMWyvcoViccwAW/COERjXLt0zP1zXUN26g==",
|
||||
"version": "5.1.9",
|
||||
"resolved": "https://registry.npmjs.org/minimatch/-/minimatch-5.1.9.tgz",
|
||||
"integrity": "sha512-7o1wEA2RyMP7Iu7GNba9vc0RWWGACJOCZBJX2GJWip0ikV+wcOsgVuY9uE8CPiyQhkGFSlhuSkZPavN7u1c2Fw==",
|
||||
"dev": true,
|
||||
"license": "ISC",
|
||||
"dependencies": {
|
||||
"brace-expansion": "^2.0.1"
|
||||
},
|
||||
@@ -2604,39 +2592,16 @@
|
||||
"resolved": "https://registry.npmjs.org/flatbuffers/-/flatbuffers-1.12.0.tgz",
|
||||
"integrity": "sha512-c7CZADjRcl6j0PlvFy0ZqXQ67qSEZfrVPynmnL+2zPc+NtMvrF8Y0QceMo7QqnSPc7+uWjUIAbvCQ5WIKlMVdQ=="
|
||||
},
|
||||
"node_modules/foreground-child": {
|
||||
"version": "3.3.0",
|
||||
"resolved": "https://registry.npmjs.org/foreground-child/-/foreground-child-3.3.0.tgz",
|
||||
"integrity": "sha512-Ld2g8rrAyMYFXBhEqMz8ZAHBi4J4uS1i/CxGMDnjyFWddMXLVcDp051DZfu+t7+ab7Wv6SMqpWmyFIj5UbfFvg==",
|
||||
"dependencies": {
|
||||
"cross-spawn": "^7.0.0",
|
||||
"signal-exit": "^4.0.1"
|
||||
},
|
||||
"engines": {
|
||||
"node": ">=14"
|
||||
},
|
||||
"funding": {
|
||||
"url": "https://github.com/sponsors/isaacs"
|
||||
}
|
||||
},
|
||||
"node_modules/foreground-child/node_modules/signal-exit": {
|
||||
"version": "4.1.0",
|
||||
"resolved": "https://registry.npmjs.org/signal-exit/-/signal-exit-4.1.0.tgz",
|
||||
"integrity": "sha512-bzyZ1e88w9O1iNJbKnOlvYTrWPDl46O1bG0D3XInv+9tkPrxrN8jUUTiFlDkkmKWgn1M6CfIA13SuGqOa9Korw==",
|
||||
"engines": {
|
||||
"node": ">=14"
|
||||
},
|
||||
"funding": {
|
||||
"url": "https://github.com/sponsors/isaacs"
|
||||
}
|
||||
},
|
||||
"node_modules/form-data": {
|
||||
"version": "4.0.1",
|
||||
"resolved": "https://registry.npmjs.org/form-data/-/form-data-4.0.1.tgz",
|
||||
"integrity": "sha512-tzN8e4TX8+kkxGPK8D5u0FNmjPUjw3lwC9lSLxxoB/+GtsJG91CO8bSWy73APlgAZzZbXEYZJuxjkHH2w+Ezhw==",
|
||||
"version": "4.0.5",
|
||||
"resolved": "https://registry.npmjs.org/form-data/-/form-data-4.0.5.tgz",
|
||||
"integrity": "sha512-8RipRLol37bNs2bhoV67fiTEvdTrbMUYcFTiy3+wuuOnUog2QBHCZWXDRijWQfAkhBj2Uf5UnVaiWwA5vdd82w==",
|
||||
"license": "MIT",
|
||||
"dependencies": {
|
||||
"asynckit": "^0.4.0",
|
||||
"combined-stream": "^1.0.8",
|
||||
"es-set-tostringtag": "^2.1.0",
|
||||
"hasown": "^2.0.2",
|
||||
"mime-types": "^2.1.12"
|
||||
},
|
||||
"engines": {
|
||||
@@ -2684,7 +2649,6 @@
|
||||
"version": "1.1.2",
|
||||
"resolved": "https://registry.npmjs.org/function-bind/-/function-bind-1.1.2.tgz",
|
||||
"integrity": "sha512-7XHNxH7qX9xG5mIwxkhumTox/MIRNcOgDrxWsMt2pAr23WHp6MrRlN7FBSFpCpr+oVO0F744iUgR82nJMfG2SA==",
|
||||
"dev": true,
|
||||
"funding": {
|
||||
"url": "https://github.com/sponsors/ljharb"
|
||||
}
|
||||
@@ -2707,6 +2671,30 @@
|
||||
"node": "6.* || 8.* || >= 10.*"
|
||||
}
|
||||
},
|
||||
"node_modules/get-intrinsic": {
|
||||
"version": "1.3.0",
|
||||
"resolved": "https://registry.npmjs.org/get-intrinsic/-/get-intrinsic-1.3.0.tgz",
|
||||
"integrity": "sha512-9fSjSaos/fRIVIp+xSJlE6lfwhES7LNtKaCBIamHsjr2na1BiABJPo0mOjjz8GJDURarmCPGqaiVg5mfjb98CQ==",
|
||||
"license": "MIT",
|
||||
"dependencies": {
|
||||
"call-bind-apply-helpers": "^1.0.2",
|
||||
"es-define-property": "^1.0.1",
|
||||
"es-errors": "^1.3.0",
|
||||
"es-object-atoms": "^1.1.1",
|
||||
"function-bind": "^1.1.2",
|
||||
"get-proto": "^1.0.1",
|
||||
"gopd": "^1.2.0",
|
||||
"has-symbols": "^1.1.0",
|
||||
"hasown": "^2.0.2",
|
||||
"math-intrinsics": "^1.1.0"
|
||||
},
|
||||
"engines": {
|
||||
"node": ">= 0.4"
|
||||
},
|
||||
"funding": {
|
||||
"url": "https://github.com/sponsors/ljharb"
|
||||
}
|
||||
},
|
||||
"node_modules/get-package-type": {
|
||||
"version": "0.1.0",
|
||||
"resolved": "https://registry.npmjs.org/get-package-type/-/get-package-type-0.1.0.tgz",
|
||||
@@ -2716,6 +2704,19 @@
|
||||
"node": ">=8.0.0"
|
||||
}
|
||||
},
|
||||
"node_modules/get-proto": {
|
||||
"version": "1.0.1",
|
||||
"resolved": "https://registry.npmjs.org/get-proto/-/get-proto-1.0.1.tgz",
|
||||
"integrity": "sha512-sTSfBjoXBp89JvIKIefqw7U2CCebsc74kiY6awiGogKtoSGbgjYE/G/+l9sF3MWFPNc9IcoOC4ODfKHfxFmp0g==",
|
||||
"license": "MIT",
|
||||
"dependencies": {
|
||||
"dunder-proto": "^1.0.1",
|
||||
"es-object-atoms": "^1.0.0"
|
||||
},
|
||||
"engines": {
|
||||
"node": ">= 0.4"
|
||||
}
|
||||
},
|
||||
"node_modules/get-stream": {
|
||||
"version": "6.0.1",
|
||||
"resolved": "https://registry.npmjs.org/get-stream/-/get-stream-6.0.1.tgz",
|
||||
@@ -2758,6 +2759,18 @@
|
||||
"node": ">=4"
|
||||
}
|
||||
},
|
||||
"node_modules/gopd": {
|
||||
"version": "1.2.0",
|
||||
"resolved": "https://registry.npmjs.org/gopd/-/gopd-1.2.0.tgz",
|
||||
"integrity": "sha512-ZUKRh6/kUFoAiTAtTYPZJ3hw9wNxx+BIBOijnlG9PnrJsCcSjs1wyyD6vJpaYtgnzDrKYRSqf3OO6Rfa93xsRg==",
|
||||
"license": "MIT",
|
||||
"engines": {
|
||||
"node": ">= 0.4"
|
||||
},
|
||||
"funding": {
|
||||
"url": "https://github.com/sponsors/ljharb"
|
||||
}
|
||||
},
|
||||
"node_modules/graceful-fs": {
|
||||
"version": "4.2.11",
|
||||
"resolved": "https://registry.npmjs.org/graceful-fs/-/graceful-fs-4.2.11.tgz",
|
||||
@@ -2778,11 +2791,37 @@
|
||||
"node": ">=8"
|
||||
}
|
||||
},
|
||||
"node_modules/has-symbols": {
|
||||
"version": "1.1.0",
|
||||
"resolved": "https://registry.npmjs.org/has-symbols/-/has-symbols-1.1.0.tgz",
|
||||
"integrity": "sha512-1cDNdwJ2Jaohmb3sg4OmKaMBwuC48sYni5HUw2DvsC8LjGTLK9h+eb1X6RyuOHe4hT0ULCW68iomhjUoKUqlPQ==",
|
||||
"license": "MIT",
|
||||
"engines": {
|
||||
"node": ">= 0.4"
|
||||
},
|
||||
"funding": {
|
||||
"url": "https://github.com/sponsors/ljharb"
|
||||
}
|
||||
},
|
||||
"node_modules/has-tostringtag": {
|
||||
"version": "1.0.2",
|
||||
"resolved": "https://registry.npmjs.org/has-tostringtag/-/has-tostringtag-1.0.2.tgz",
|
||||
"integrity": "sha512-NqADB8VjPFLM2V0VvHUewwwsw0ZWBaIdgo+ieHtK3hasLz4qeCRjYcqfB6AQrBggRKppKF8L52/VqdVsO47Dlw==",
|
||||
"license": "MIT",
|
||||
"dependencies": {
|
||||
"has-symbols": "^1.0.3"
|
||||
},
|
||||
"engines": {
|
||||
"node": ">= 0.4"
|
||||
},
|
||||
"funding": {
|
||||
"url": "https://github.com/sponsors/ljharb"
|
||||
}
|
||||
},
|
||||
"node_modules/hasown": {
|
||||
"version": "2.0.2",
|
||||
"resolved": "https://registry.npmjs.org/hasown/-/hasown-2.0.2.tgz",
|
||||
"integrity": "sha512-0hJU9SCPvmMzIBdZFqNPXWa6dqh7WdH0cII9y+CyS8rG3nL48Bclra9HmKhVVUHyPWNH5Y7xDwAB7bfgSjkUMQ==",
|
||||
"dev": true,
|
||||
"dependencies": {
|
||||
"function-bind": "^1.1.2"
|
||||
},
|
||||
@@ -2882,6 +2921,7 @@
|
||||
"version": "3.0.0",
|
||||
"resolved": "https://registry.npmjs.org/is-fullwidth-code-point/-/is-fullwidth-code-point-3.0.0.tgz",
|
||||
"integrity": "sha512-zymm5+u+sCsSWyD9qNaejV3DFvhCKclKdizYaJUuHA83RLjb7nSuGnddCHGv0hk+KY7BMAlsWeK4Ueg6EV6XQg==",
|
||||
"dev": true,
|
||||
"engines": {
|
||||
"node": ">=8"
|
||||
}
|
||||
@@ -2919,7 +2959,8 @@
|
||||
"node_modules/isexe": {
|
||||
"version": "2.0.0",
|
||||
"resolved": "https://registry.npmjs.org/isexe/-/isexe-2.0.0.tgz",
|
||||
"integrity": "sha512-RHxMLp9lnKHGHRng9QFhRCMbYAcVpn69smSGcq3f36xjgVVWThj4qqLbTLlq7Ssj8B+fIQ1EuCEGI2lKsyQeIw=="
|
||||
"integrity": "sha512-RHxMLp9lnKHGHRng9QFhRCMbYAcVpn69smSGcq3f36xjgVVWThj4qqLbTLlq7Ssj8B+fIQ1EuCEGI2lKsyQeIw==",
|
||||
"dev": true
|
||||
},
|
||||
"node_modules/istanbul-lib-coverage": {
|
||||
"version": "3.2.2",
|
||||
@@ -2987,20 +3028,6 @@
|
||||
"node": ">=8"
|
||||
}
|
||||
},
|
||||
"node_modules/jackspeak": {
|
||||
"version": "3.4.3",
|
||||
"resolved": "https://registry.npmjs.org/jackspeak/-/jackspeak-3.4.3.tgz",
|
||||
"integrity": "sha512-OGlZQpz2yfahA/Rd1Y8Cd9SIEsqvXkLVoSw/cgwhnhFMDbsQFeZYoJJ7bIZBS9BcamUW96asq/npPWugM+RQBw==",
|
||||
"dependencies": {
|
||||
"@isaacs/cliui": "^8.0.2"
|
||||
},
|
||||
"funding": {
|
||||
"url": "https://github.com/sponsors/isaacs"
|
||||
},
|
||||
"optionalDependencies": {
|
||||
"@pkgjs/parseargs": "^0.11.0"
|
||||
}
|
||||
},
|
||||
"node_modules/jake": {
|
||||
"version": "10.9.2",
|
||||
"resolved": "https://registry.npmjs.org/jake/-/jake-10.9.2.tgz",
|
||||
@@ -3605,10 +3632,11 @@
|
||||
"dev": true
|
||||
},
|
||||
"node_modules/js-yaml": {
|
||||
"version": "3.14.1",
|
||||
"resolved": "https://registry.npmjs.org/js-yaml/-/js-yaml-3.14.1.tgz",
|
||||
"integrity": "sha512-okMH7OXXJ7YrN9Ok3/SXrnu4iX9yOk+25nqX4imS2npuvTYDmo/QEZoqwZkYaIDk3jVvBOTOIEgEhaLOynBS9g==",
|
||||
"version": "3.14.2",
|
||||
"resolved": "https://registry.npmjs.org/js-yaml/-/js-yaml-3.14.2.tgz",
|
||||
"integrity": "sha512-PMSmkqxr106Xa156c2M265Z+FTrPl+oxd/rgOQy2tijQeK5TxQ43psO1ZCwhVOSdnn+RzkzlRz/eY4BgJBYVpg==",
|
||||
"dev": true,
|
||||
"license": "MIT",
|
||||
"dependencies": {
|
||||
"argparse": "^1.0.7",
|
||||
"esprima": "^4.0.0"
|
||||
@@ -3728,6 +3756,15 @@
|
||||
"tmpl": "1.0.5"
|
||||
}
|
||||
},
|
||||
"node_modules/math-intrinsics": {
|
||||
"version": "1.1.0",
|
||||
"resolved": "https://registry.npmjs.org/math-intrinsics/-/math-intrinsics-1.1.0.tgz",
|
||||
"integrity": "sha512-/IXtbwEk5HTPyEwyKX6hGkYXxM9nbj64B+ilVJnC/R6B0pH5G4V3b0pVbL7DBj4tkhBAppbQUlf6F6Xl9LHu1g==",
|
||||
"license": "MIT",
|
||||
"engines": {
|
||||
"node": ">= 0.4"
|
||||
}
|
||||
},
|
||||
"node_modules/merge-stream": {
|
||||
"version": "2.0.0",
|
||||
"resolved": "https://registry.npmjs.org/merge-stream/-/merge-stream-2.0.0.tgz",
|
||||
@@ -3776,10 +3813,11 @@
|
||||
}
|
||||
},
|
||||
"node_modules/minimatch": {
|
||||
"version": "3.1.2",
|
||||
"resolved": "https://registry.npmjs.org/minimatch/-/minimatch-3.1.2.tgz",
|
||||
"integrity": "sha512-J7p63hRiAjw1NDEww1W7i37+ByIrOWO5XQQAzZ3VOcL0PNybwpfmV/N05zFAzwQ9USyEcX6t3UO+K5aqBQOIHw==",
|
||||
"version": "3.1.5",
|
||||
"resolved": "https://registry.npmjs.org/minimatch/-/minimatch-3.1.5.tgz",
|
||||
"integrity": "sha512-VgjWUsnnT6n+NUk6eZq77zeFdpW2LWDzP6zFGrCbHXiYNul5Dzqk2HHQ5uFH2DNW5Xbp8+jVzaeNt94ssEEl4w==",
|
||||
"dev": true,
|
||||
"license": "ISC",
|
||||
"dependencies": {
|
||||
"brace-expansion": "^1.1.7"
|
||||
},
|
||||
@@ -3796,31 +3834,17 @@
|
||||
}
|
||||
},
|
||||
"node_modules/minizlib": {
|
||||
"version": "3.0.1",
|
||||
"resolved": "https://registry.npmjs.org/minizlib/-/minizlib-3.0.1.tgz",
|
||||
"integrity": "sha512-umcy022ILvb5/3Djuu8LWeqUa8D68JaBzlttKeMWen48SjabqS3iY5w/vzeMzMUNhLDifyhbOwKDSznB1vvrwg==",
|
||||
"version": "3.1.0",
|
||||
"resolved": "https://registry.npmjs.org/minizlib/-/minizlib-3.1.0.tgz",
|
||||
"integrity": "sha512-KZxYo1BUkWD2TVFLr0MQoM8vUUigWD3LlD83a/75BqC+4qE0Hb1Vo5v1FgcfaNXvfXzr+5EhQ6ing/CaBijTlw==",
|
||||
"license": "MIT",
|
||||
"dependencies": {
|
||||
"minipass": "^7.0.4",
|
||||
"rimraf": "^5.0.5"
|
||||
"minipass": "^7.1.2"
|
||||
},
|
||||
"engines": {
|
||||
"node": ">= 18"
|
||||
}
|
||||
},
|
||||
"node_modules/mkdirp": {
|
||||
"version": "3.0.1",
|
||||
"resolved": "https://registry.npmjs.org/mkdirp/-/mkdirp-3.0.1.tgz",
|
||||
"integrity": "sha512-+NsyUUAZDmo6YVHzL/stxSu3t9YS1iljliy3BSDrXJ/dkn1KYdmtZODGGjLcc9XLgVVpH4KshHB8XmZgMhaBXg==",
|
||||
"bin": {
|
||||
"mkdirp": "dist/cjs/src/bin.js"
|
||||
},
|
||||
"engines": {
|
||||
"node": ">=10"
|
||||
},
|
||||
"funding": {
|
||||
"url": "https://github.com/sponsors/isaacs"
|
||||
}
|
||||
},
|
||||
"node_modules/ms": {
|
||||
"version": "2.1.3",
|
||||
"resolved": "https://registry.npmjs.org/ms/-/ms-2.1.3.tgz",
|
||||
@@ -4010,11 +4034,6 @@
|
||||
"node": ">=6"
|
||||
}
|
||||
},
|
||||
"node_modules/package-json-from-dist": {
|
||||
"version": "1.0.1",
|
||||
"resolved": "https://registry.npmjs.org/package-json-from-dist/-/package-json-from-dist-1.0.1.tgz",
|
||||
"integrity": "sha512-UEZIS3/by4OC8vL3P2dTXRETpebLI2NiI5vIrjaD/5UtrkFX/tNbwjTSRAGC/+7CAo2pIcBaRgWmcBBHcsaCIw=="
|
||||
},
|
||||
"node_modules/parse-json": {
|
||||
"version": "5.2.0",
|
||||
"resolved": "https://registry.npmjs.org/parse-json/-/parse-json-5.2.0.tgz",
|
||||
@@ -4055,6 +4074,7 @@
|
||||
"version": "3.1.1",
|
||||
"resolved": "https://registry.npmjs.org/path-key/-/path-key-3.1.1.tgz",
|
||||
"integrity": "sha512-ojmeN0qd+y0jszEtoY48r0Peq5dwMEkIlCOu6Q5f41lfkswXuKtYrhgoTpLnyIcHm24Uhqx+5Tqm2InSwLhE6Q==",
|
||||
"dev": true,
|
||||
"engines": {
|
||||
"node": ">=8"
|
||||
}
|
||||
@@ -4065,26 +4085,6 @@
|
||||
"integrity": "sha512-LDJzPVEEEPR+y48z93A0Ed0yXb8pAByGWo/k5YYdYgpY2/2EsOsksJrq7lOHxryrVOn1ejG6oAp8ahvOIQD8sw==",
|
||||
"dev": true
|
||||
},
|
||||
"node_modules/path-scurry": {
|
||||
"version": "1.11.1",
|
||||
"resolved": "https://registry.npmjs.org/path-scurry/-/path-scurry-1.11.1.tgz",
|
||||
"integrity": "sha512-Xa4Nw17FS9ApQFJ9umLiJS4orGjm7ZzwUrwamcGQuHSzDyth9boKDaycYdDcZDuqYATXw4HFXgaqWTctW/v1HA==",
|
||||
"dependencies": {
|
||||
"lru-cache": "^10.2.0",
|
||||
"minipass": "^5.0.0 || ^6.0.2 || ^7.0.0"
|
||||
},
|
||||
"engines": {
|
||||
"node": ">=16 || 14 >=14.18"
|
||||
},
|
||||
"funding": {
|
||||
"url": "https://github.com/sponsors/isaacs"
|
||||
}
|
||||
},
|
||||
"node_modules/path-scurry/node_modules/lru-cache": {
|
||||
"version": "10.4.3",
|
||||
"resolved": "https://registry.npmjs.org/lru-cache/-/lru-cache-10.4.3.tgz",
|
||||
"integrity": "sha512-JNAzZcXrCt42VGLuYz0zfAzDfAvJWW6AfYlDBQyDV5DClI2m5sAmK+OIO7s59XfsRsWHp02jAJrRadPRGTt6SQ=="
|
||||
},
|
||||
"node_modules/picocolors": {
|
||||
"version": "1.1.1",
|
||||
"resolved": "https://registry.npmjs.org/picocolors/-/picocolors-1.1.1.tgz",
|
||||
@@ -4246,61 +4246,6 @@
|
||||
"node": ">=10"
|
||||
}
|
||||
},
|
||||
"node_modules/rimraf": {
|
||||
"version": "5.0.10",
|
||||
"resolved": "https://registry.npmjs.org/rimraf/-/rimraf-5.0.10.tgz",
|
||||
"integrity": "sha512-l0OE8wL34P4nJH/H2ffoaniAokM2qSmrtXHmlpvYr5AVVX8msAyW0l8NVJFDxlSK4u3Uh/f41cQheDVdnYijwQ==",
|
||||
"dependencies": {
|
||||
"glob": "^10.3.7"
|
||||
},
|
||||
"bin": {
|
||||
"rimraf": "dist/esm/bin.mjs"
|
||||
},
|
||||
"funding": {
|
||||
"url": "https://github.com/sponsors/isaacs"
|
||||
}
|
||||
},
|
||||
"node_modules/rimraf/node_modules/brace-expansion": {
|
||||
"version": "2.0.1",
|
||||
"resolved": "https://registry.npmjs.org/brace-expansion/-/brace-expansion-2.0.1.tgz",
|
||||
"integrity": "sha512-XnAIvQ8eM+kC6aULx6wuQiwVsnzsi9d3WxzV3FpWTGA19F621kwdbsAcFKXgKUHZWsy+mY6iL1sHTxWEFCytDA==",
|
||||
"dependencies": {
|
||||
"balanced-match": "^1.0.0"
|
||||
}
|
||||
},
|
||||
"node_modules/rimraf/node_modules/glob": {
|
||||
"version": "10.4.5",
|
||||
"resolved": "https://registry.npmjs.org/glob/-/glob-10.4.5.tgz",
|
||||
"integrity": "sha512-7Bv8RF0k6xjo7d4A/PxYLbUCfb6c+Vpd2/mB2yRDlew7Jb5hEXiCD9ibfO7wpk8i4sevK6DFny9h7EYbM3/sHg==",
|
||||
"dependencies": {
|
||||
"foreground-child": "^3.1.0",
|
||||
"jackspeak": "^3.1.2",
|
||||
"minimatch": "^9.0.4",
|
||||
"minipass": "^7.1.2",
|
||||
"package-json-from-dist": "^1.0.0",
|
||||
"path-scurry": "^1.11.1"
|
||||
},
|
||||
"bin": {
|
||||
"glob": "dist/esm/bin.mjs"
|
||||
},
|
||||
"funding": {
|
||||
"url": "https://github.com/sponsors/isaacs"
|
||||
}
|
||||
},
|
||||
"node_modules/rimraf/node_modules/minimatch": {
|
||||
"version": "9.0.5",
|
||||
"resolved": "https://registry.npmjs.org/minimatch/-/minimatch-9.0.5.tgz",
|
||||
"integrity": "sha512-G6T0ZX48xgozx7587koeX9Ys2NYy6Gmv//P89sEte9V9whIapMNF4idKxnW2QtCcLiTWlb/wfCabAtAFWhhBow==",
|
||||
"dependencies": {
|
||||
"brace-expansion": "^2.0.1"
|
||||
},
|
||||
"engines": {
|
||||
"node": ">=16 || 14 >=14.17"
|
||||
},
|
||||
"funding": {
|
||||
"url": "https://github.com/sponsors/isaacs"
|
||||
}
|
||||
},
|
||||
"node_modules/semver": {
|
||||
"version": "7.6.3",
|
||||
"resolved": "https://registry.npmjs.org/semver/-/semver-7.6.3.tgz",
|
||||
@@ -4354,6 +4299,7 @@
|
||||
"version": "2.0.0",
|
||||
"resolved": "https://registry.npmjs.org/shebang-command/-/shebang-command-2.0.0.tgz",
|
||||
"integrity": "sha512-kHxr2zZpYtdmrN1qDjrrX/Z1rR1kG8Dx+gkpK1G4eXmvXswmcE1hTWBWYUzlraYw1/yZp6YuDY77YtvbN0dmDA==",
|
||||
"dev": true,
|
||||
"dependencies": {
|
||||
"shebang-regex": "^3.0.0"
|
||||
},
|
||||
@@ -4365,6 +4311,7 @@
|
||||
"version": "3.0.0",
|
||||
"resolved": "https://registry.npmjs.org/shebang-regex/-/shebang-regex-3.0.0.tgz",
|
||||
"integrity": "sha512-7++dFhtcx3353uBaq8DDR4NuxBetBzC7ZQOhmTQInHEd6bSrXdiEyzCvG07Z44UYdLShWUyXt5M/yhz8ekcb1A==",
|
||||
"dev": true,
|
||||
"engines": {
|
||||
"node": ">=8"
|
||||
}
|
||||
@@ -4452,20 +4399,7 @@
|
||||
"version": "4.2.3",
|
||||
"resolved": "https://registry.npmjs.org/string-width/-/string-width-4.2.3.tgz",
|
||||
"integrity": "sha512-wKyQRQpjJ0sIp62ErSZdGsjMJWsap5oRNihHhu6G7JVO/9jIB6UyevL+tXuOqrng8j/cxKTWyWUwvSTriiZz/g==",
|
||||
"dependencies": {
|
||||
"emoji-regex": "^8.0.0",
|
||||
"is-fullwidth-code-point": "^3.0.0",
|
||||
"strip-ansi": "^6.0.1"
|
||||
},
|
||||
"engines": {
|
||||
"node": ">=8"
|
||||
}
|
||||
},
|
||||
"node_modules/string-width-cjs": {
|
||||
"name": "string-width",
|
||||
"version": "4.2.3",
|
||||
"resolved": "https://registry.npmjs.org/string-width/-/string-width-4.2.3.tgz",
|
||||
"integrity": "sha512-wKyQRQpjJ0sIp62ErSZdGsjMJWsap5oRNihHhu6G7JVO/9jIB6UyevL+tXuOqrng8j/cxKTWyWUwvSTriiZz/g==",
|
||||
"dev": true,
|
||||
"dependencies": {
|
||||
"emoji-regex": "^8.0.0",
|
||||
"is-fullwidth-code-point": "^3.0.0",
|
||||
@@ -4479,18 +4413,7 @@
|
||||
"version": "6.0.1",
|
||||
"resolved": "https://registry.npmjs.org/strip-ansi/-/strip-ansi-6.0.1.tgz",
|
||||
"integrity": "sha512-Y38VPSHcqkFrCpFnQ9vuSXmquuv5oXOKpGeT6aGrr3o3Gc9AlVa6JBfUSOCnbxGGZF+/0ooI7KrPuUSztUdU5A==",
|
||||
"dependencies": {
|
||||
"ansi-regex": "^5.0.1"
|
||||
},
|
||||
"engines": {
|
||||
"node": ">=8"
|
||||
}
|
||||
},
|
||||
"node_modules/strip-ansi-cjs": {
|
||||
"name": "strip-ansi",
|
||||
"version": "6.0.1",
|
||||
"resolved": "https://registry.npmjs.org/strip-ansi/-/strip-ansi-6.0.1.tgz",
|
||||
"integrity": "sha512-Y38VPSHcqkFrCpFnQ9vuSXmquuv5oXOKpGeT6aGrr3o3Gc9AlVa6JBfUSOCnbxGGZF+/0ooI7KrPuUSztUdU5A==",
|
||||
"dev": true,
|
||||
"dependencies": {
|
||||
"ansi-regex": "^5.0.1"
|
||||
},
|
||||
@@ -4541,15 +4464,15 @@
|
||||
}
|
||||
},
|
||||
"node_modules/tar": {
|
||||
"version": "7.4.3",
|
||||
"resolved": "https://registry.npmjs.org/tar/-/tar-7.4.3.tgz",
|
||||
"integrity": "sha512-5S7Va8hKfV7W5U6g3aYxXmlPoZVAwUMy9AOKyF2fVuZa2UD3qZjg578OrLRt8PcNN1PleVaL/5/yYATNL0ICUw==",
|
||||
"version": "7.5.10",
|
||||
"resolved": "https://registry.npmjs.org/tar/-/tar-7.5.10.tgz",
|
||||
"integrity": "sha512-8mOPs1//5q/rlkNSPcCegA6hiHJYDmSLEI8aMH/CdSQJNWztHC9WHNam5zdQlfpTwB9Xp7IBEsHfV5LKMJGVAw==",
|
||||
"license": "BlueOak-1.0.0",
|
||||
"dependencies": {
|
||||
"@isaacs/fs-minipass": "^4.0.0",
|
||||
"chownr": "^3.0.0",
|
||||
"minipass": "^7.1.2",
|
||||
"minizlib": "^3.0.1",
|
||||
"mkdirp": "^3.0.1",
|
||||
"minizlib": "^3.1.0",
|
||||
"yallist": "^5.0.0"
|
||||
},
|
||||
"engines": {
|
||||
@@ -4782,6 +4705,7 @@
|
||||
"version": "2.0.2",
|
||||
"resolved": "https://registry.npmjs.org/which/-/which-2.0.2.tgz",
|
||||
"integrity": "sha512-BLI3Tl1TW3Pvl70l3yq3Y64i+awpwXqsGBYWkkqMtnbXgrMD+yj7rhW0kuEDxzJaYXGjEW5ogapKNMEKNMjibA==",
|
||||
"dev": true,
|
||||
"dependencies": {
|
||||
"isexe": "^2.0.0"
|
||||
},
|
||||
@@ -4809,23 +4733,6 @@
|
||||
"url": "https://github.com/chalk/wrap-ansi?sponsor=1"
|
||||
}
|
||||
},
|
||||
"node_modules/wrap-ansi-cjs": {
|
||||
"name": "wrap-ansi",
|
||||
"version": "7.0.0",
|
||||
"resolved": "https://registry.npmjs.org/wrap-ansi/-/wrap-ansi-7.0.0.tgz",
|
||||
"integrity": "sha512-YVGIj2kamLSTxw6NsZjoBxfSwsn0ycdesmc4p+Q21c5zPuZ1pl+NfxVdxPtdHvmNVOQ6XSYG4AUtyt/Fi7D16Q==",
|
||||
"dependencies": {
|
||||
"ansi-styles": "^4.0.0",
|
||||
"string-width": "^4.1.0",
|
||||
"strip-ansi": "^6.0.0"
|
||||
},
|
||||
"engines": {
|
||||
"node": ">=10"
|
||||
},
|
||||
"funding": {
|
||||
"url": "https://github.com/chalk/wrap-ansi?sponsor=1"
|
||||
}
|
||||
},
|
||||
"node_modules/wrappy": {
|
||||
"version": "1.0.2",
|
||||
"resolved": "https://registry.npmjs.org/wrappy/-/wrappy-1.0.2.tgz",
|
||||
|
||||
@@ -20,6 +20,8 @@ import {
|
||||
Float32,
|
||||
Float64,
|
||||
Int,
|
||||
Int8,
|
||||
Int16,
|
||||
Int32,
|
||||
Int64,
|
||||
LargeBinary,
|
||||
@@ -35,6 +37,8 @@ import {
|
||||
Timestamp,
|
||||
Type,
|
||||
Uint8,
|
||||
Uint16,
|
||||
Uint32,
|
||||
Utf8,
|
||||
Vector,
|
||||
makeVector as arrowMakeVector,
|
||||
@@ -529,7 +533,8 @@ function isObject(value: unknown): value is Record<string, unknown> {
|
||||
!(value instanceof Date) &&
|
||||
!(value instanceof Set) &&
|
||||
!(value instanceof Map) &&
|
||||
!(value instanceof Buffer)
|
||||
!(value instanceof Buffer) &&
|
||||
!ArrayBuffer.isView(value)
|
||||
);
|
||||
}
|
||||
|
||||
@@ -588,6 +593,13 @@ function inferType(
|
||||
return new Bool();
|
||||
} else if (value instanceof Buffer) {
|
||||
return new Binary();
|
||||
} else if (ArrayBuffer.isView(value) && !(value instanceof DataView)) {
|
||||
const info = typedArrayToArrowType(value);
|
||||
if (info !== undefined) {
|
||||
const child = new Field("item", info.elementType, true);
|
||||
return new FixedSizeList(info.length, child);
|
||||
}
|
||||
return undefined;
|
||||
} else if (Array.isArray(value)) {
|
||||
if (value.length === 0) {
|
||||
return undefined; // Without any values we can't infer the type
|
||||
@@ -746,6 +758,32 @@ function makeListVector(lists: unknown[][]): Vector<unknown> {
|
||||
return listBuilder.finish().toVector();
|
||||
}
|
||||
|
||||
/**
|
||||
* Map a JS TypedArray instance to the corresponding Arrow element DataType
|
||||
* and its length. Returns undefined if the value is not a recognized TypedArray.
|
||||
*/
|
||||
function typedArrayToArrowType(
|
||||
value: ArrayBufferView,
|
||||
): { elementType: DataType; length: number } | undefined {
|
||||
if (value instanceof Float32Array)
|
||||
return { elementType: new Float32(), length: value.length };
|
||||
if (value instanceof Float64Array)
|
||||
return { elementType: new Float64(), length: value.length };
|
||||
if (value instanceof Uint8Array)
|
||||
return { elementType: new Uint8(), length: value.length };
|
||||
if (value instanceof Uint16Array)
|
||||
return { elementType: new Uint16(), length: value.length };
|
||||
if (value instanceof Uint32Array)
|
||||
return { elementType: new Uint32(), length: value.length };
|
||||
if (value instanceof Int8Array)
|
||||
return { elementType: new Int8(), length: value.length };
|
||||
if (value instanceof Int16Array)
|
||||
return { elementType: new Int16(), length: value.length };
|
||||
if (value instanceof Int32Array)
|
||||
return { elementType: new Int32(), length: value.length };
|
||||
return undefined;
|
||||
}
|
||||
|
||||
/** Helper function to convert an Array of JS values to an Arrow Vector */
|
||||
function makeVector(
|
||||
values: unknown[],
|
||||
@@ -814,6 +852,16 @@ function makeVector(
|
||||
"makeVector cannot infer the type if all values are null or undefined",
|
||||
);
|
||||
}
|
||||
if (ArrayBuffer.isView(sampleValue) && !(sampleValue instanceof DataView)) {
|
||||
const info = typedArrayToArrowType(sampleValue);
|
||||
if (info !== undefined) {
|
||||
const fslType = new FixedSizeList(
|
||||
info.length,
|
||||
new Field("item", info.elementType, true),
|
||||
);
|
||||
return vectorFromArray(values, fslType);
|
||||
}
|
||||
}
|
||||
if (Array.isArray(sampleValue)) {
|
||||
// Default Arrow inference doesn't handle list types
|
||||
return makeListVector(values as unknown[][]);
|
||||
|
||||
@@ -5,12 +5,15 @@ import {
|
||||
Table as ArrowTable,
|
||||
Data,
|
||||
DataType,
|
||||
Field,
|
||||
IntoVector,
|
||||
MultiVector,
|
||||
Schema,
|
||||
dataTypeToJson,
|
||||
fromDataToBuffer,
|
||||
fromTableToBuffer,
|
||||
isMultiVector,
|
||||
makeEmptyTable,
|
||||
tableFromIPC,
|
||||
} from "./arrow";
|
||||
|
||||
@@ -84,6 +87,16 @@ export interface OptimizeOptions {
|
||||
* tbl.optimize({cleanupOlderThan: new Date()});
|
||||
*/
|
||||
cleanupOlderThan: Date;
|
||||
/**
|
||||
* Because they may be part of an in-progress transaction, files newer than
|
||||
* 7 days old are not deleted by default. If you are sure that there are no
|
||||
* in-progress transactions, then you can set this to true to delete all
|
||||
* files older than `cleanupOlderThan`.
|
||||
*
|
||||
* **WARNING**: This should only be set to true if you can guarantee that
|
||||
* no other process is currently working on this dataset. Otherwise the
|
||||
* dataset could be put into a corrupted state.
|
||||
*/
|
||||
deleteUnverified: boolean;
|
||||
}
|
||||
|
||||
@@ -381,15 +394,16 @@ export abstract class Table {
|
||||
abstract vectorSearch(vector: IntoVector | MultiVector): VectorQuery;
|
||||
/**
|
||||
* Add new columns with defined values.
|
||||
* @param {AddColumnsSql[]} newColumnTransforms pairs of column names and
|
||||
* the SQL expression to use to calculate the value of the new column. These
|
||||
* expressions will be evaluated for each row in the table, and can
|
||||
* reference existing columns in the table.
|
||||
* @param {AddColumnsSql[] | Field | Field[] | Schema} newColumnTransforms Either:
|
||||
* - An array of objects with column names and SQL expressions to calculate values
|
||||
* - A single Arrow Field defining one column with its data type (column will be initialized with null values)
|
||||
* - An array of Arrow Fields defining columns with their data types (columns will be initialized with null values)
|
||||
* - An Arrow Schema defining columns with their data types (columns will be initialized with null values)
|
||||
* @returns {Promise<AddColumnsResult>} A promise that resolves to an object
|
||||
* containing the new version number of the table after adding the columns.
|
||||
*/
|
||||
abstract addColumns(
|
||||
newColumnTransforms: AddColumnsSql[],
|
||||
newColumnTransforms: AddColumnsSql[] | Field | Field[] | Schema,
|
||||
): Promise<AddColumnsResult>;
|
||||
|
||||
/**
|
||||
@@ -501,19 +515,7 @@ export abstract class Table {
|
||||
* - Index: Optimizes the indices, adding new data to existing indices
|
||||
*
|
||||
*
|
||||
* Experimental API
|
||||
* ----------------
|
||||
*
|
||||
* The optimization process is undergoing active development and may change.
|
||||
* Our goal with these changes is to improve the performance of optimization and
|
||||
* reduce the complexity.
|
||||
*
|
||||
* That being said, it is essential today to run optimize if you want the best
|
||||
* performance. It should be stable and safe to use in production, but it our
|
||||
* hope that the API may be simplified (or not even need to be called) in the
|
||||
* future.
|
||||
*
|
||||
* The frequency an application shoudl call optimize is based on the frequency of
|
||||
* The frequency an application should call optimize is based on the frequency of
|
||||
* data modifications. If data is frequently added, deleted, or updated then
|
||||
* optimize should be run frequently. A good rule of thumb is to run optimize if
|
||||
* you have added or modified 100,000 or more records or run more than 20 data
|
||||
@@ -806,9 +808,40 @@ export class LocalTable extends Table {
|
||||
// TODO: Support BatchUDF
|
||||
|
||||
async addColumns(
|
||||
newColumnTransforms: AddColumnsSql[],
|
||||
newColumnTransforms: AddColumnsSql[] | Field | Field[] | Schema,
|
||||
): Promise<AddColumnsResult> {
|
||||
return await this.inner.addColumns(newColumnTransforms);
|
||||
// Handle single Field -> convert to array of Fields
|
||||
if (newColumnTransforms instanceof Field) {
|
||||
newColumnTransforms = [newColumnTransforms];
|
||||
}
|
||||
|
||||
// Handle array of Fields -> convert to Schema
|
||||
if (
|
||||
Array.isArray(newColumnTransforms) &&
|
||||
newColumnTransforms.length > 0 &&
|
||||
newColumnTransforms[0] instanceof Field
|
||||
) {
|
||||
const fields = newColumnTransforms as Field[];
|
||||
newColumnTransforms = new Schema(fields);
|
||||
}
|
||||
|
||||
// Handle Schema -> use schema-based approach
|
||||
if (newColumnTransforms instanceof Schema) {
|
||||
const schema = newColumnTransforms;
|
||||
// Convert schema to buffer using Arrow IPC format
|
||||
const emptyTable = makeEmptyTable(schema);
|
||||
const schemaBuf = await fromTableToBuffer(emptyTable);
|
||||
return await this.inner.addColumnsWithSchema(schemaBuf);
|
||||
}
|
||||
|
||||
// Handle SQL expressions (existing functionality)
|
||||
if (Array.isArray(newColumnTransforms)) {
|
||||
return await this.inner.addColumns(
|
||||
newColumnTransforms as AddColumnsSql[],
|
||||
);
|
||||
}
|
||||
|
||||
throw new Error("Invalid input type for addColumns");
|
||||
}
|
||||
|
||||
async alterColumns(
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"name": "@lancedb/lancedb-darwin-arm64",
|
||||
"version": "0.27.0-beta.3",
|
||||
"version": "0.27.1",
|
||||
"os": ["darwin"],
|
||||
"cpu": ["arm64"],
|
||||
"main": "lancedb.darwin-arm64.node",
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"name": "@lancedb/lancedb-linux-arm64-gnu",
|
||||
"version": "0.27.0-beta.3",
|
||||
"version": "0.27.1",
|
||||
"os": ["linux"],
|
||||
"cpu": ["arm64"],
|
||||
"main": "lancedb.linux-arm64-gnu.node",
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"name": "@lancedb/lancedb-linux-arm64-musl",
|
||||
"version": "0.27.0-beta.3",
|
||||
"version": "0.27.1",
|
||||
"os": ["linux"],
|
||||
"cpu": ["arm64"],
|
||||
"main": "lancedb.linux-arm64-musl.node",
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"name": "@lancedb/lancedb-linux-x64-gnu",
|
||||
"version": "0.27.0-beta.3",
|
||||
"version": "0.27.1",
|
||||
"os": ["linux"],
|
||||
"cpu": ["x64"],
|
||||
"main": "lancedb.linux-x64-gnu.node",
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"name": "@lancedb/lancedb-linux-x64-musl",
|
||||
"version": "0.27.0-beta.3",
|
||||
"version": "0.27.1",
|
||||
"os": ["linux"],
|
||||
"cpu": ["x64"],
|
||||
"main": "lancedb.linux-x64-musl.node",
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"name": "@lancedb/lancedb-win32-arm64-msvc",
|
||||
"version": "0.27.0-beta.3",
|
||||
"version": "0.27.1",
|
||||
"os": [
|
||||
"win32"
|
||||
],
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"name": "@lancedb/lancedb-win32-x64-msvc",
|
||||
"version": "0.27.0-beta.3",
|
||||
"version": "0.27.1",
|
||||
"os": ["win32"],
|
||||
"cpu": ["x64"],
|
||||
"main": "lancedb.win32-x64-msvc.node",
|
||||
|
||||
4289
nodejs/package-lock.json
generated
4289
nodejs/package-lock.json
generated
File diff suppressed because it is too large
Load Diff
@@ -11,7 +11,7 @@
|
||||
"ann"
|
||||
],
|
||||
"private": false,
|
||||
"version": "0.27.0-beta.3",
|
||||
"version": "0.27.1",
|
||||
"main": "dist/index.js",
|
||||
"exports": {
|
||||
".": "./dist/index.js",
|
||||
|
||||
@@ -3,7 +3,7 @@
|
||||
|
||||
use std::collections::HashMap;
|
||||
|
||||
use lancedb::ipc::ipc_file_to_batches;
|
||||
use lancedb::ipc::{ipc_file_to_batches, ipc_file_to_schema};
|
||||
use lancedb::table::{
|
||||
AddDataMode, ColumnAlteration as LanceColumnAlteration, Duration, NewColumnTransform,
|
||||
OptimizeAction, OptimizeOptions, Table as LanceDbTable,
|
||||
@@ -279,6 +279,23 @@ impl Table {
|
||||
Ok(res.into())
|
||||
}
|
||||
|
||||
#[napi(catch_unwind)]
|
||||
pub async fn add_columns_with_schema(
|
||||
&self,
|
||||
schema_buf: Buffer,
|
||||
) -> napi::Result<AddColumnsResult> {
|
||||
let schema = ipc_file_to_schema(schema_buf.to_vec())
|
||||
.map_err(|e| napi::Error::from_reason(format!("Failed to read IPC schema: {}", e)))?;
|
||||
|
||||
let transforms = NewColumnTransform::AllNulls(schema);
|
||||
let res = self
|
||||
.inner_ref()?
|
||||
.add_columns(transforms, None)
|
||||
.await
|
||||
.default_error()?;
|
||||
Ok(res.into())
|
||||
}
|
||||
|
||||
#[napi(catch_unwind)]
|
||||
pub async fn alter_columns(
|
||||
&self,
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
[tool.bumpversion]
|
||||
current_version = "0.30.0-beta.3"
|
||||
current_version = "0.30.1"
|
||||
parse = """(?x)
|
||||
(?P<major>0|[1-9]\\d*)\\.
|
||||
(?P<minor>0|[1-9]\\d*)\\.
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
[package]
|
||||
name = "lancedb-python"
|
||||
version = "0.30.0-beta.3"
|
||||
version = "0.30.1"
|
||||
edition.workspace = true
|
||||
description = "Python bindings for LanceDB"
|
||||
license.workspace = true
|
||||
@@ -16,9 +16,11 @@ crate-type = ["cdylib"]
|
||||
[dependencies]
|
||||
arrow = { version = "57.2", features = ["pyarrow"] }
|
||||
async-trait = "0.1"
|
||||
bytes = "1"
|
||||
lancedb = { path = "../rust/lancedb", default-features = false }
|
||||
lance-core.workspace = true
|
||||
lance-namespace.workspace = true
|
||||
lance-namespace-impls.workspace = true
|
||||
lance-io.workspace = true
|
||||
env_logger.workspace = true
|
||||
pyo3 = { version = "0.26", features = ["extension-module", "abi3-py39"] }
|
||||
@@ -28,6 +30,8 @@ pyo3-async-runtimes = { version = "0.26", features = [
|
||||
] }
|
||||
pin-project = "1.1.5"
|
||||
futures.workspace = true
|
||||
serde = "1"
|
||||
serde_json = "1"
|
||||
snafu.workspace = true
|
||||
tokio = { version = "1.40", features = ["sync"] }
|
||||
|
||||
|
||||
@@ -1,4 +1,4 @@
|
||||
# LanceDB
|
||||
# LanceDB Python SDK
|
||||
|
||||
A Python library for [LanceDB](https://github.com/lancedb/lancedb).
|
||||
|
||||
|
||||
@@ -3,10 +3,10 @@ name = "lancedb"
|
||||
# version in Cargo.toml
|
||||
dynamic = ["version"]
|
||||
dependencies = [
|
||||
"deprecation",
|
||||
"numpy",
|
||||
"deprecation>=2.1.0",
|
||||
"numpy>=1.24.0",
|
||||
"overrides>=0.7; python_version<'3.12'",
|
||||
"packaging",
|
||||
"packaging>=23.0",
|
||||
"pyarrow>=16",
|
||||
"pydantic>=1.10",
|
||||
"tqdm>=4.27.0",
|
||||
@@ -45,51 +45,51 @@ repository = "https://github.com/lancedb/lancedb"
|
||||
|
||||
[project.optional-dependencies]
|
||||
pylance = [
|
||||
"pylance>=1.0.0b14",
|
||||
"pylance>=4.0.0b7",
|
||||
]
|
||||
tests = [
|
||||
"aiohttp",
|
||||
"boto3",
|
||||
"aiohttp>=3.9.0",
|
||||
"boto3>=1.28.57",
|
||||
"pandas>=1.4",
|
||||
"pytest",
|
||||
"pytest-mock",
|
||||
"pytest-asyncio",
|
||||
"duckdb",
|
||||
"pytz",
|
||||
"pytest>=7.0",
|
||||
"pytest-mock>=3.10",
|
||||
"pytest-asyncio>=0.21",
|
||||
"duckdb>=0.9.0",
|
||||
"pytz>=2023.3",
|
||||
"polars>=0.19, <=1.3.0",
|
||||
"tantivy",
|
||||
"pyarrow-stubs",
|
||||
"pylance>=1.0.0b14,<3.0.0",
|
||||
"requests",
|
||||
"datafusion<52",
|
||||
"tantivy>=0.20.0",
|
||||
"pyarrow-stubs>=16.0",
|
||||
"pylance>=4.0.0b7",
|
||||
"requests>=2.31.0",
|
||||
"datafusion>=52,<53",
|
||||
]
|
||||
dev = [
|
||||
"ruff",
|
||||
"pre-commit",
|
||||
"pyright",
|
||||
"ruff>=0.3.0",
|
||||
"pre-commit>=3.5.0",
|
||||
"pyright>=1.1.350",
|
||||
'typing-extensions>=4.0.0; python_version < "3.11"',
|
||||
]
|
||||
docs = ["mkdocs", "mkdocs-jupyter", "mkdocs-material", "mkdocstrings-python"]
|
||||
clip = ["torch", "pillow", "open-clip-torch"]
|
||||
siglip = ["torch", "pillow", "transformers>=4.41.0","sentencepiece"]
|
||||
clip = ["torch", "pillow>=12.1.1", "open-clip-torch"]
|
||||
siglip = ["torch", "pillow>=12.1.1", "transformers>=4.41.0","sentencepiece"]
|
||||
embeddings = [
|
||||
"requests>=2.31.0",
|
||||
"openai>=1.6.1",
|
||||
"sentence-transformers",
|
||||
"torch",
|
||||
"pillow",
|
||||
"open-clip-torch",
|
||||
"cohere",
|
||||
"sentence-transformers>=2.2.0",
|
||||
"torch>=2.0.0",
|
||||
"pillow>=12.1.1",
|
||||
"open-clip-torch>=2.20.0",
|
||||
"cohere>=4.0",
|
||||
"colpali-engine>=0.3.10",
|
||||
"huggingface_hub",
|
||||
"InstructorEmbedding",
|
||||
"google.generativeai",
|
||||
"huggingface_hub>=0.19.0",
|
||||
"InstructorEmbedding>=1.0.1",
|
||||
"google.generativeai>=0.3.0",
|
||||
"boto3>=1.28.57",
|
||||
"awscli>=1.29.57",
|
||||
"awscli>=1.44.38",
|
||||
"botocore>=1.31.57",
|
||||
'ibm-watsonx-ai>=1.1.2; python_version >= "3.10"',
|
||||
"ollama>=0.3.0",
|
||||
"sentencepiece"
|
||||
"sentencepiece>=0.1.99"
|
||||
]
|
||||
azure = ["adlfs>=2024.2.0"]
|
||||
|
||||
|
||||
@@ -166,6 +166,8 @@ class Table:
|
||||
async def checkout(self, version: Union[int, str]): ...
|
||||
async def checkout_latest(self): ...
|
||||
async def restore(self, version: Optional[Union[int, str]] = None): ...
|
||||
async def prewarm_index(self, index_name: str) -> None: ...
|
||||
async def prewarm_data(self, columns: Optional[List[str]] = None) -> None: ...
|
||||
async def list_indices(self) -> list[IndexConfig]: ...
|
||||
async def delete(self, filter: str) -> DeleteResult: ...
|
||||
async def add_columns(self, columns: list[tuple[str, str]]) -> AddColumnsResult: ...
|
||||
|
||||
@@ -8,7 +8,7 @@ from abc import abstractmethod
|
||||
from datetime import timedelta
|
||||
from pathlib import Path
|
||||
import sys
|
||||
from typing import TYPE_CHECKING, Dict, Iterable, List, Literal, Optional, Union
|
||||
from typing import TYPE_CHECKING, Any, Dict, Iterable, List, Literal, Optional, Union
|
||||
|
||||
if sys.version_info >= (3, 12):
|
||||
from typing import override
|
||||
@@ -1541,6 +1541,8 @@ class AsyncConnection(object):
|
||||
storage_options_provider: Optional["StorageOptionsProvider"] = None,
|
||||
index_cache_size: Optional[int] = None,
|
||||
location: Optional[str] = None,
|
||||
namespace_client: Optional[Any] = None,
|
||||
managed_versioning: Optional[bool] = None,
|
||||
) -> AsyncTable:
|
||||
"""Open a Lance Table in the database.
|
||||
|
||||
@@ -1573,6 +1575,9 @@ class AsyncConnection(object):
|
||||
The explicit location (URI) of the table. If provided, the table will be
|
||||
opened from this location instead of deriving it from the database URI
|
||||
and table name.
|
||||
managed_versioning: bool, optional
|
||||
Whether managed versioning is enabled for this table. If provided,
|
||||
avoids a redundant describe_table call when namespace_client is set.
|
||||
|
||||
Returns
|
||||
-------
|
||||
@@ -1587,6 +1592,8 @@ class AsyncConnection(object):
|
||||
storage_options_provider=storage_options_provider,
|
||||
index_cache_size=index_cache_size,
|
||||
location=location,
|
||||
namespace_client=namespace_client,
|
||||
managed_versioning=managed_versioning,
|
||||
)
|
||||
return AsyncTable(table)
|
||||
|
||||
|
||||
@@ -12,7 +12,7 @@ from __future__ import annotations
|
||||
|
||||
import asyncio
|
||||
import sys
|
||||
from typing import Dict, Iterable, List, Optional, Union
|
||||
from typing import Any, Dict, Iterable, List, Optional, Union
|
||||
|
||||
if sys.version_info >= (3, 12):
|
||||
from typing import override
|
||||
@@ -240,7 +240,7 @@ class LanceNamespaceDBConnection(DBConnection):
|
||||
session : Optional[Session]
|
||||
A session to use for this connection
|
||||
"""
|
||||
self._ns = namespace
|
||||
self._namespace_client = namespace
|
||||
self.read_consistency_interval = read_consistency_interval
|
||||
self.storage_options = storage_options or {}
|
||||
self.session = session
|
||||
@@ -269,7 +269,7 @@ class LanceNamespaceDBConnection(DBConnection):
|
||||
if namespace is None:
|
||||
namespace = []
|
||||
request = ListTablesRequest(id=namespace, page_token=page_token, limit=limit)
|
||||
response = self._ns.list_tables(request)
|
||||
response = self._namespace_client.list_tables(request)
|
||||
return response.tables if response.tables else []
|
||||
|
||||
@override
|
||||
@@ -309,7 +309,9 @@ class LanceNamespaceDBConnection(DBConnection):
|
||||
# Try to describe the table first to see if it exists
|
||||
try:
|
||||
describe_request = DescribeTableRequest(id=table_id)
|
||||
describe_response = self._ns.describe_table(describe_request)
|
||||
describe_response = self._namespace_client.describe_table(
|
||||
describe_request
|
||||
)
|
||||
location = describe_response.location
|
||||
namespace_storage_options = describe_response.storage_options
|
||||
except Exception:
|
||||
@@ -323,7 +325,7 @@ class LanceNamespaceDBConnection(DBConnection):
|
||||
location=None,
|
||||
properties=self.storage_options if self.storage_options else None,
|
||||
)
|
||||
declare_response = self._ns.declare_table(declare_request)
|
||||
declare_response = self._namespace_client.declare_table(declare_request)
|
||||
|
||||
if not declare_response.location:
|
||||
raise ValueError(
|
||||
@@ -353,7 +355,7 @@ class LanceNamespaceDBConnection(DBConnection):
|
||||
# Only create if namespace returned storage_options (not None)
|
||||
if storage_options_provider is None and namespace_storage_options is not None:
|
||||
storage_options_provider = LanceNamespaceStorageOptionsProvider(
|
||||
namespace=self._ns,
|
||||
namespace=self._namespace_client,
|
||||
table_id=table_id,
|
||||
)
|
||||
|
||||
@@ -371,6 +373,7 @@ class LanceNamespaceDBConnection(DBConnection):
|
||||
storage_options=merged_storage_options,
|
||||
storage_options_provider=storage_options_provider,
|
||||
location=location,
|
||||
namespace_client=self._namespace_client,
|
||||
)
|
||||
|
||||
return tbl
|
||||
@@ -389,7 +392,7 @@ class LanceNamespaceDBConnection(DBConnection):
|
||||
namespace = []
|
||||
table_id = namespace + [name]
|
||||
request = DescribeTableRequest(id=table_id)
|
||||
response = self._ns.describe_table(request)
|
||||
response = self._namespace_client.describe_table(request)
|
||||
|
||||
# Merge storage options: self.storage_options < user options < namespace options
|
||||
merged_storage_options = dict(self.storage_options)
|
||||
@@ -402,10 +405,14 @@ class LanceNamespaceDBConnection(DBConnection):
|
||||
# Only create if namespace returned storage_options (not None)
|
||||
if storage_options_provider is None and response.storage_options is not None:
|
||||
storage_options_provider = LanceNamespaceStorageOptionsProvider(
|
||||
namespace=self._ns,
|
||||
namespace=self._namespace_client,
|
||||
table_id=table_id,
|
||||
)
|
||||
|
||||
# Pass managed_versioning to avoid redundant describe_table call in Rust.
|
||||
# Convert None to False since we already have the answer from describe_table.
|
||||
managed_versioning = response.managed_versioning is True
|
||||
|
||||
return self._lance_table_from_uri(
|
||||
name,
|
||||
response.location,
|
||||
@@ -413,6 +420,8 @@ class LanceNamespaceDBConnection(DBConnection):
|
||||
storage_options=merged_storage_options,
|
||||
storage_options_provider=storage_options_provider,
|
||||
index_cache_size=index_cache_size,
|
||||
namespace_client=self._namespace_client,
|
||||
managed_versioning=managed_versioning,
|
||||
)
|
||||
|
||||
@override
|
||||
@@ -422,7 +431,7 @@ class LanceNamespaceDBConnection(DBConnection):
|
||||
namespace = []
|
||||
table_id = namespace + [name]
|
||||
request = DropTableRequest(id=table_id)
|
||||
self._ns.drop_table(request)
|
||||
self._namespace_client.drop_table(request)
|
||||
|
||||
@override
|
||||
def rename_table(
|
||||
@@ -484,7 +493,7 @@ class LanceNamespaceDBConnection(DBConnection):
|
||||
request = ListNamespacesRequest(
|
||||
id=namespace, page_token=page_token, limit=limit
|
||||
)
|
||||
response = self._ns.list_namespaces(request)
|
||||
response = self._namespace_client.list_namespaces(request)
|
||||
return ListNamespacesResponse(
|
||||
namespaces=response.namespaces if response.namespaces else [],
|
||||
page_token=response.page_token,
|
||||
@@ -520,7 +529,7 @@ class LanceNamespaceDBConnection(DBConnection):
|
||||
mode=_normalize_create_namespace_mode(mode),
|
||||
properties=properties,
|
||||
)
|
||||
response = self._ns.create_namespace(request)
|
||||
response = self._namespace_client.create_namespace(request)
|
||||
return CreateNamespaceResponse(
|
||||
properties=response.properties if hasattr(response, "properties") else None
|
||||
)
|
||||
@@ -555,7 +564,7 @@ class LanceNamespaceDBConnection(DBConnection):
|
||||
mode=_normalize_drop_namespace_mode(mode),
|
||||
behavior=_normalize_drop_namespace_behavior(behavior),
|
||||
)
|
||||
response = self._ns.drop_namespace(request)
|
||||
response = self._namespace_client.drop_namespace(request)
|
||||
return DropNamespaceResponse(
|
||||
properties=(
|
||||
response.properties if hasattr(response, "properties") else None
|
||||
@@ -581,7 +590,7 @@ class LanceNamespaceDBConnection(DBConnection):
|
||||
Response containing the namespace properties.
|
||||
"""
|
||||
request = DescribeNamespaceRequest(id=namespace)
|
||||
response = self._ns.describe_namespace(request)
|
||||
response = self._namespace_client.describe_namespace(request)
|
||||
return DescribeNamespaceResponse(
|
||||
properties=response.properties if hasattr(response, "properties") else None
|
||||
)
|
||||
@@ -615,7 +624,7 @@ class LanceNamespaceDBConnection(DBConnection):
|
||||
if namespace is None:
|
||||
namespace = []
|
||||
request = ListTablesRequest(id=namespace, page_token=page_token, limit=limit)
|
||||
response = self._ns.list_tables(request)
|
||||
response = self._namespace_client.list_tables(request)
|
||||
return ListTablesResponse(
|
||||
tables=response.tables if response.tables else [],
|
||||
page_token=response.page_token,
|
||||
@@ -630,6 +639,8 @@ class LanceNamespaceDBConnection(DBConnection):
|
||||
storage_options: Optional[Dict[str, str]] = None,
|
||||
storage_options_provider: Optional[StorageOptionsProvider] = None,
|
||||
index_cache_size: Optional[int] = None,
|
||||
namespace_client: Optional[Any] = None,
|
||||
managed_versioning: Optional[bool] = None,
|
||||
) -> LanceTable:
|
||||
# Open a table directly from a URI using the location parameter
|
||||
# Note: storage_options should already be merged by the caller
|
||||
@@ -643,6 +654,8 @@ class LanceNamespaceDBConnection(DBConnection):
|
||||
)
|
||||
|
||||
# Open the table using the temporary connection with the location parameter
|
||||
# Pass namespace_client to enable managed versioning support
|
||||
# Pass managed_versioning to avoid redundant describe_table call
|
||||
return LanceTable.open(
|
||||
temp_conn,
|
||||
name,
|
||||
@@ -651,6 +664,8 @@ class LanceNamespaceDBConnection(DBConnection):
|
||||
storage_options_provider=storage_options_provider,
|
||||
index_cache_size=index_cache_size,
|
||||
location=table_uri,
|
||||
namespace_client=namespace_client,
|
||||
managed_versioning=managed_versioning,
|
||||
)
|
||||
|
||||
|
||||
@@ -685,7 +700,7 @@ class AsyncLanceNamespaceDBConnection:
|
||||
session : Optional[Session]
|
||||
A session to use for this connection
|
||||
"""
|
||||
self._ns = namespace
|
||||
self._namespace_client = namespace
|
||||
self.read_consistency_interval = read_consistency_interval
|
||||
self.storage_options = storage_options or {}
|
||||
self.session = session
|
||||
@@ -713,7 +728,7 @@ class AsyncLanceNamespaceDBConnection:
|
||||
if namespace is None:
|
||||
namespace = []
|
||||
request = ListTablesRequest(id=namespace, page_token=page_token, limit=limit)
|
||||
response = self._ns.list_tables(request)
|
||||
response = self._namespace_client.list_tables(request)
|
||||
return response.tables if response.tables else []
|
||||
|
||||
async def create_table(
|
||||
@@ -750,7 +765,9 @@ class AsyncLanceNamespaceDBConnection:
|
||||
# Try to describe the table first to see if it exists
|
||||
try:
|
||||
describe_request = DescribeTableRequest(id=table_id)
|
||||
describe_response = self._ns.describe_table(describe_request)
|
||||
describe_response = self._namespace_client.describe_table(
|
||||
describe_request
|
||||
)
|
||||
location = describe_response.location
|
||||
namespace_storage_options = describe_response.storage_options
|
||||
except Exception:
|
||||
@@ -764,7 +781,7 @@ class AsyncLanceNamespaceDBConnection:
|
||||
location=None,
|
||||
properties=self.storage_options if self.storage_options else None,
|
||||
)
|
||||
declare_response = self._ns.declare_table(declare_request)
|
||||
declare_response = self._namespace_client.declare_table(declare_request)
|
||||
|
||||
if not declare_response.location:
|
||||
raise ValueError(
|
||||
@@ -797,7 +814,7 @@ class AsyncLanceNamespaceDBConnection:
|
||||
and namespace_storage_options is not None
|
||||
):
|
||||
provider = LanceNamespaceStorageOptionsProvider(
|
||||
namespace=self._ns,
|
||||
namespace=self._namespace_client,
|
||||
table_id=table_id,
|
||||
)
|
||||
else:
|
||||
@@ -817,6 +834,7 @@ class AsyncLanceNamespaceDBConnection:
|
||||
storage_options=merged_storage_options,
|
||||
storage_options_provider=provider,
|
||||
location=location,
|
||||
namespace_client=self._namespace_client,
|
||||
)
|
||||
|
||||
lance_table = await asyncio.to_thread(_create_table)
|
||||
@@ -837,7 +855,7 @@ class AsyncLanceNamespaceDBConnection:
|
||||
namespace = []
|
||||
table_id = namespace + [name]
|
||||
request = DescribeTableRequest(id=table_id)
|
||||
response = self._ns.describe_table(request)
|
||||
response = self._namespace_client.describe_table(request)
|
||||
|
||||
# Merge storage options: self.storage_options < user options < namespace options
|
||||
merged_storage_options = dict(self.storage_options)
|
||||
@@ -849,10 +867,14 @@ class AsyncLanceNamespaceDBConnection:
|
||||
# Create a storage options provider if not provided by user
|
||||
if storage_options_provider is None and response.storage_options is not None:
|
||||
storage_options_provider = LanceNamespaceStorageOptionsProvider(
|
||||
namespace=self._ns,
|
||||
namespace=self._namespace_client,
|
||||
table_id=table_id,
|
||||
)
|
||||
|
||||
# Capture managed_versioning from describe response.
|
||||
# Convert None to False since we already have the answer from describe_table.
|
||||
managed_versioning = response.managed_versioning is True
|
||||
|
||||
# Open table in a thread
|
||||
def _open_table():
|
||||
temp_conn = LanceDBConnection(
|
||||
@@ -870,6 +892,8 @@ class AsyncLanceNamespaceDBConnection:
|
||||
storage_options_provider=storage_options_provider,
|
||||
index_cache_size=index_cache_size,
|
||||
location=response.location,
|
||||
namespace_client=self._namespace_client,
|
||||
managed_versioning=managed_versioning,
|
||||
)
|
||||
|
||||
lance_table = await asyncio.to_thread(_open_table)
|
||||
@@ -881,7 +905,7 @@ class AsyncLanceNamespaceDBConnection:
|
||||
namespace = []
|
||||
table_id = namespace + [name]
|
||||
request = DropTableRequest(id=table_id)
|
||||
self._ns.drop_table(request)
|
||||
self._namespace_client.drop_table(request)
|
||||
|
||||
async def rename_table(
|
||||
self,
|
||||
@@ -943,7 +967,7 @@ class AsyncLanceNamespaceDBConnection:
|
||||
request = ListNamespacesRequest(
|
||||
id=namespace, page_token=page_token, limit=limit
|
||||
)
|
||||
response = self._ns.list_namespaces(request)
|
||||
response = self._namespace_client.list_namespaces(request)
|
||||
return ListNamespacesResponse(
|
||||
namespaces=response.namespaces if response.namespaces else [],
|
||||
page_token=response.page_token,
|
||||
@@ -978,7 +1002,7 @@ class AsyncLanceNamespaceDBConnection:
|
||||
mode=_normalize_create_namespace_mode(mode),
|
||||
properties=properties,
|
||||
)
|
||||
response = self._ns.create_namespace(request)
|
||||
response = self._namespace_client.create_namespace(request)
|
||||
return CreateNamespaceResponse(
|
||||
properties=response.properties if hasattr(response, "properties") else None
|
||||
)
|
||||
@@ -1012,7 +1036,7 @@ class AsyncLanceNamespaceDBConnection:
|
||||
mode=_normalize_drop_namespace_mode(mode),
|
||||
behavior=_normalize_drop_namespace_behavior(behavior),
|
||||
)
|
||||
response = self._ns.drop_namespace(request)
|
||||
response = self._namespace_client.drop_namespace(request)
|
||||
return DropNamespaceResponse(
|
||||
properties=(
|
||||
response.properties if hasattr(response, "properties") else None
|
||||
@@ -1039,7 +1063,7 @@ class AsyncLanceNamespaceDBConnection:
|
||||
Response containing the namespace properties.
|
||||
"""
|
||||
request = DescribeNamespaceRequest(id=namespace)
|
||||
response = self._ns.describe_namespace(request)
|
||||
response = self._namespace_client.describe_namespace(request)
|
||||
return DescribeNamespaceResponse(
|
||||
properties=response.properties if hasattr(response, "properties") else None
|
||||
)
|
||||
@@ -1072,7 +1096,7 @@ class AsyncLanceNamespaceDBConnection:
|
||||
if namespace is None:
|
||||
namespace = []
|
||||
request = ListTablesRequest(id=namespace, page_token=page_token, limit=limit)
|
||||
response = self._ns.list_tables(request)
|
||||
response = self._namespace_client.list_tables(request)
|
||||
return ListTablesResponse(
|
||||
tables=response.tables if response.tables else [],
|
||||
page_token=response.page_token,
|
||||
|
||||
@@ -2205,8 +2205,8 @@ class LanceHybridQueryBuilder(LanceQueryBuilder):
|
||||
self._vector_query.select(self._columns)
|
||||
self._fts_query.select(self._columns)
|
||||
if self._where:
|
||||
self._vector_query.where(self._where, self._postfilter)
|
||||
self._fts_query.where(self._where, self._postfilter)
|
||||
self._vector_query.where(self._where, not self._postfilter)
|
||||
self._fts_query.where(self._where, not self._postfilter)
|
||||
if self._with_row_id:
|
||||
self._vector_query.with_row_id(True)
|
||||
self._fts_query.with_row_id(True)
|
||||
|
||||
@@ -640,6 +640,45 @@ class RemoteTable(Table):
|
||||
def drop_index(self, index_name: str):
|
||||
return LOOP.run(self._table.drop_index(index_name))
|
||||
|
||||
def prewarm_index(self, name: str) -> None:
|
||||
"""Prewarm an index in the table.
|
||||
|
||||
This is a hint to the database that the index will be accessed in the
|
||||
future and should be loaded into memory if possible. This can reduce
|
||||
cold-start latency for subsequent queries.
|
||||
|
||||
This call initiates prewarming and returns once the request is accepted.
|
||||
It is idempotent and safe to call from multiple clients concurrently.
|
||||
|
||||
Parameters
|
||||
----------
|
||||
name: str
|
||||
The name of the index to prewarm
|
||||
"""
|
||||
return LOOP.run(self._table.prewarm_index(name))
|
||||
|
||||
def prewarm_data(self, columns: Optional[List[str]] = None) -> None:
|
||||
"""Prewarm data for the table.
|
||||
|
||||
This is a hint to the database that the given columns will be accessed
|
||||
in the future and the database should prefetch the data if possible.
|
||||
Currently only supported on remote tables.
|
||||
|
||||
This call initiates prewarming and returns once the request is accepted.
|
||||
It is idempotent and safe to call from multiple clients concurrently.
|
||||
|
||||
This operation has a large upfront cost but can speed up future queries
|
||||
that need to fetch the given columns. Large columns such as embeddings
|
||||
or binary data may not be practical to prewarm. This feature is intended
|
||||
for workloads that issue many queries against the same columns.
|
||||
|
||||
Parameters
|
||||
----------
|
||||
columns: list of str, optional
|
||||
The columns to prewarm. If None, all columns are prewarmed.
|
||||
"""
|
||||
return LOOP.run(self._table.prewarm_data(columns))
|
||||
|
||||
def wait_for_index(
|
||||
self, index_names: Iterable[str], timeout: timedelta = timedelta(seconds=300)
|
||||
):
|
||||
|
||||
@@ -1506,22 +1506,17 @@ class Table(ABC):
|
||||
in-progress operation (e.g. appending new data) and these files will not
|
||||
be deleted unless they are at least 7 days old. If delete_unverified is True
|
||||
then these files will be deleted regardless of their age.
|
||||
|
||||
.. warning::
|
||||
|
||||
This should only be set to True if you can guarantee that no other
|
||||
process is currently working on this dataset. Otherwise the dataset
|
||||
could be put into a corrupted state.
|
||||
|
||||
retrain: bool, default False
|
||||
This parameter is no longer used and is deprecated.
|
||||
|
||||
Experimental API
|
||||
----------------
|
||||
|
||||
The optimization process is undergoing active development and may change.
|
||||
Our goal with these changes is to improve the performance of optimization and
|
||||
reduce the complexity.
|
||||
|
||||
That being said, it is essential today to run optimize if you want the best
|
||||
performance. It should be stable and safe to use in production, but it our
|
||||
hope that the API may be simplified (or not even need to be called) in the
|
||||
future.
|
||||
|
||||
The frequency an application shoudl call optimize is based on the frequency of
|
||||
The frequency an application should call optimize is based on the frequency of
|
||||
data modifications. If data is frequently added, deleted, or updated then
|
||||
optimize should be run frequently. A good rule of thumb is to run optimize if
|
||||
you have added or modified 100,000 or more records or run more than 20 data
|
||||
@@ -1746,6 +1741,8 @@ class LanceTable(Table):
|
||||
storage_options_provider: Optional["StorageOptionsProvider"] = None,
|
||||
index_cache_size: Optional[int] = None,
|
||||
location: Optional[str] = None,
|
||||
namespace_client: Optional[Any] = None,
|
||||
managed_versioning: Optional[bool] = None,
|
||||
_async: AsyncTable = None,
|
||||
):
|
||||
if namespace is None:
|
||||
@@ -1753,6 +1750,7 @@ class LanceTable(Table):
|
||||
self._conn = connection
|
||||
self._namespace = namespace
|
||||
self._location = location # Store location for use in _dataset_path
|
||||
self._namespace_client = namespace_client
|
||||
if _async is not None:
|
||||
self._table = _async
|
||||
else:
|
||||
@@ -1764,6 +1762,8 @@ class LanceTable(Table):
|
||||
storage_options_provider=storage_options_provider,
|
||||
index_cache_size=index_cache_size,
|
||||
location=location,
|
||||
namespace_client=namespace_client,
|
||||
managed_versioning=managed_versioning,
|
||||
)
|
||||
)
|
||||
|
||||
@@ -1806,6 +1806,8 @@ class LanceTable(Table):
|
||||
storage_options_provider: Optional["StorageOptionsProvider"] = None,
|
||||
index_cache_size: Optional[int] = None,
|
||||
location: Optional[str] = None,
|
||||
namespace_client: Optional[Any] = None,
|
||||
managed_versioning: Optional[bool] = None,
|
||||
):
|
||||
if namespace is None:
|
||||
namespace = []
|
||||
@@ -1817,6 +1819,8 @@ class LanceTable(Table):
|
||||
storage_options_provider=storage_options_provider,
|
||||
index_cache_size=index_cache_size,
|
||||
location=location,
|
||||
namespace_client=namespace_client,
|
||||
managed_versioning=managed_versioning,
|
||||
)
|
||||
|
||||
# check the dataset exists
|
||||
@@ -1848,6 +1852,16 @@ class LanceTable(Table):
|
||||
"Please install with `pip install pylance`."
|
||||
)
|
||||
|
||||
if self._namespace_client is not None:
|
||||
table_id = self._namespace + [self.name]
|
||||
return lance.dataset(
|
||||
version=self.version,
|
||||
storage_options=self._conn.storage_options,
|
||||
namespace=self._namespace_client,
|
||||
table_id=table_id,
|
||||
**kwargs,
|
||||
)
|
||||
|
||||
return lance.dataset(
|
||||
self._dataset_path,
|
||||
version=self.version,
|
||||
@@ -2200,12 +2214,18 @@ class LanceTable(Table):
|
||||
|
||||
def prewarm_index(self, name: str) -> None:
|
||||
"""
|
||||
Prewarms an index in the table
|
||||
Prewarm an index in the table.
|
||||
|
||||
This loads the entire index into memory
|
||||
This is a hint to the database that the index will be accessed in the
|
||||
future and should be loaded into memory if possible. This can reduce
|
||||
cold-start latency for subsequent queries.
|
||||
|
||||
If the index does not fit into the available cache this call
|
||||
may be wasteful
|
||||
This call initiates prewarming and returns once the request is accepted.
|
||||
It is idempotent and safe to call from multiple clients concurrently.
|
||||
|
||||
It is generally wasteful to call this if the index does not fit into the
|
||||
available cache. Not all index types support prewarming; unsupported
|
||||
indices will silently ignore the request.
|
||||
|
||||
Parameters
|
||||
----------
|
||||
@@ -2214,6 +2234,29 @@ class LanceTable(Table):
|
||||
"""
|
||||
return LOOP.run(self._table.prewarm_index(name))
|
||||
|
||||
def prewarm_data(self, columns: Optional[List[str]] = None) -> None:
|
||||
"""
|
||||
Prewarm data for the table.
|
||||
|
||||
This is a hint to the database that the given columns will be accessed
|
||||
in the future and the database should prefetch the data if possible.
|
||||
Currently only supported on remote tables.
|
||||
|
||||
This call initiates prewarming and returns once the request is accepted.
|
||||
It is idempotent and safe to call from multiple clients concurrently.
|
||||
|
||||
This operation has a large upfront cost but can speed up future queries
|
||||
that need to fetch the given columns. Large columns such as embeddings
|
||||
or binary data may not be practical to prewarm. This feature is intended
|
||||
for workloads that issue many queries against the same columns.
|
||||
|
||||
Parameters
|
||||
----------
|
||||
columns: list of str, optional
|
||||
The columns to prewarm. If None, all columns are prewarmed.
|
||||
"""
|
||||
return LOOP.run(self._table.prewarm_data(columns))
|
||||
|
||||
def wait_for_index(
|
||||
self, index_names: Iterable[str], timeout: timedelta = timedelta(seconds=300)
|
||||
) -> None:
|
||||
@@ -2713,6 +2756,7 @@ class LanceTable(Table):
|
||||
data_storage_version: Optional[str] = None,
|
||||
enable_v2_manifest_paths: Optional[bool] = None,
|
||||
location: Optional[str] = None,
|
||||
namespace_client: Optional[Any] = None,
|
||||
):
|
||||
"""
|
||||
Create a new table.
|
||||
@@ -2773,6 +2817,7 @@ class LanceTable(Table):
|
||||
self._conn = db
|
||||
self._namespace = namespace
|
||||
self._location = location
|
||||
self._namespace_client = namespace_client
|
||||
|
||||
if data_storage_version is not None:
|
||||
warnings.warn(
|
||||
@@ -2997,22 +3042,17 @@ class LanceTable(Table):
|
||||
in-progress operation (e.g. appending new data) and these files will not
|
||||
be deleted unless they are at least 7 days old. If delete_unverified is True
|
||||
then these files will be deleted regardless of their age.
|
||||
|
||||
.. warning::
|
||||
|
||||
This should only be set to True if you can guarantee that no other
|
||||
process is currently working on this dataset. Otherwise the dataset
|
||||
could be put into a corrupted state.
|
||||
|
||||
retrain: bool, default False
|
||||
This parameter is no longer used and is deprecated.
|
||||
|
||||
Experimental API
|
||||
----------------
|
||||
|
||||
The optimization process is undergoing active development and may change.
|
||||
Our goal with these changes is to improve the performance of optimization and
|
||||
reduce the complexity.
|
||||
|
||||
That being said, it is essential today to run optimize if you want the best
|
||||
performance. It should be stable and safe to use in production, but it our
|
||||
hope that the API may be simplified (or not even need to be called) in the
|
||||
future.
|
||||
|
||||
The frequency an application shoudl call optimize is based on the frequency of
|
||||
The frequency an application should call optimize is based on the frequency of
|
||||
data modifications. If data is frequently added, deleted, or updated then
|
||||
optimize should be run frequently. A good rule of thumb is to run optimize if
|
||||
you have added or modified 100,000 or more records or run more than 20 data
|
||||
@@ -3613,19 +3653,47 @@ class AsyncTable:
|
||||
"""
|
||||
Prewarm an index in the table.
|
||||
|
||||
This is a hint to the database that the index will be accessed in the
|
||||
future and should be loaded into memory if possible. This can reduce
|
||||
cold-start latency for subsequent queries.
|
||||
|
||||
This call initiates prewarming and returns once the request is accepted.
|
||||
It is idempotent and safe to call from multiple clients concurrently.
|
||||
|
||||
It is generally wasteful to call this if the index does not fit into the
|
||||
available cache. Not all index types support prewarming; unsupported
|
||||
indices will silently ignore the request.
|
||||
|
||||
Parameters
|
||||
----------
|
||||
name: str
|
||||
The name of the index to prewarm
|
||||
|
||||
Notes
|
||||
-----
|
||||
This will load the index into memory. This may reduce the cold-start time for
|
||||
future queries. If the index does not fit in the cache then this call may be
|
||||
wasteful.
|
||||
"""
|
||||
await self._inner.prewarm_index(name)
|
||||
|
||||
async def prewarm_data(self, columns: Optional[List[str]] = None) -> None:
|
||||
"""
|
||||
Prewarm data for the table.
|
||||
|
||||
This is a hint to the database that the given columns will be accessed
|
||||
in the future and the database should prefetch the data if possible.
|
||||
Currently only supported on remote tables.
|
||||
|
||||
This call initiates prewarming and returns once the request is accepted.
|
||||
It is idempotent and safe to call from multiple clients concurrently.
|
||||
|
||||
This operation has a large upfront cost but can speed up future queries
|
||||
that need to fetch the given columns. Large columns such as embeddings
|
||||
or binary data may not be practical to prewarm. This feature is intended
|
||||
for workloads that issue many queries against the same columns.
|
||||
|
||||
Parameters
|
||||
----------
|
||||
columns: list of str, optional
|
||||
The columns to prewarm. If None, all columns are prewarmed.
|
||||
"""
|
||||
await self._inner.prewarm_data(columns)
|
||||
|
||||
async def wait_for_index(
|
||||
self, index_names: Iterable[str], timeout: timedelta = timedelta(seconds=300)
|
||||
) -> None:
|
||||
@@ -4552,22 +4620,17 @@ class AsyncTable:
|
||||
in-progress operation (e.g. appending new data) and these files will not
|
||||
be deleted unless they are at least 7 days old. If delete_unverified is True
|
||||
then these files will be deleted regardless of their age.
|
||||
|
||||
.. warning::
|
||||
|
||||
This should only be set to True if you can guarantee that no other
|
||||
process is currently working on this dataset. Otherwise the dataset
|
||||
could be put into a corrupted state.
|
||||
|
||||
retrain: bool, default False
|
||||
This parameter is no longer used and is deprecated.
|
||||
|
||||
Experimental API
|
||||
----------------
|
||||
|
||||
The optimization process is undergoing active development and may change.
|
||||
Our goal with these changes is to improve the performance of optimization and
|
||||
reduce the complexity.
|
||||
|
||||
That being said, it is essential today to run optimize if you want the best
|
||||
performance. It should be stable and safe to use in production, but it our
|
||||
hope that the API may be simplified (or not even need to be called) in the
|
||||
future.
|
||||
|
||||
The frequency an application shoudl call optimize is based on the frequency of
|
||||
The frequency an application should call optimize is based on the frequency of
|
||||
data modifications. If data is frequently added, deleted, or updated then
|
||||
optimize should be run frequently. A good rule of thumb is to run optimize if
|
||||
you have added or modified 100,000 or more records or run more than 20 data
|
||||
|
||||
@@ -177,6 +177,60 @@ async def test_analyze_plan(table: AsyncTable):
|
||||
assert "metrics=" in res
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def table_with_id(tmpdir_factory) -> Table:
|
||||
tmp_path = str(tmpdir_factory.mktemp("data"))
|
||||
db = lancedb.connect(tmp_path)
|
||||
data = pa.table(
|
||||
{
|
||||
"id": pa.array([1, 2, 3, 4], type=pa.int64()),
|
||||
"text": pa.array(["a", "b", "cat", "dog"]),
|
||||
"vector": pa.array(
|
||||
[[0.1, 0.1], [2, 2], [-0.1, -0.1], [0.5, -0.5]],
|
||||
type=pa.list_(pa.float32(), list_size=2),
|
||||
),
|
||||
}
|
||||
)
|
||||
table = db.create_table("test_with_id", data)
|
||||
table.create_fts_index("text", with_position=False, use_tantivy=False)
|
||||
return table
|
||||
|
||||
|
||||
def test_hybrid_prefilter_explain_plan(table_with_id: Table):
|
||||
"""
|
||||
Verify that the prefilter logic is not inverted in LanceHybridQueryBuilder.
|
||||
"""
|
||||
plan_prefilter = (
|
||||
table_with_id.search(query_type="hybrid")
|
||||
.vector([0.0, 0.0])
|
||||
.text("dog")
|
||||
.where("id = 1", prefilter=True)
|
||||
.limit(2)
|
||||
.explain_plan(verbose=True)
|
||||
)
|
||||
|
||||
plan_postfilter = (
|
||||
table_with_id.search(query_type="hybrid")
|
||||
.vector([0.0, 0.0])
|
||||
.text("dog")
|
||||
.where("id = 1", prefilter=False)
|
||||
.limit(2)
|
||||
.explain_plan(verbose=True)
|
||||
)
|
||||
|
||||
# prefilter=True: filter is pushed into the LanceRead scan.
|
||||
# The FTS sub-plan exposes this as "full_filter=id = Int64(1)" inside LanceRead.
|
||||
assert "full_filter=id = Int64(1)" in plan_prefilter, (
|
||||
f"Should push the filter into the scan.\nPlan:\n{plan_prefilter}"
|
||||
)
|
||||
|
||||
# prefilter=False: filter is applied as a separate FilterExec after the search.
|
||||
# The filter must NOT be embedded in the scan.
|
||||
assert "full_filter=id = Int64(1)" not in plan_postfilter, (
|
||||
f"Should NOT push the filter into the scan.\nPlan:\n{plan_postfilter}"
|
||||
)
|
||||
|
||||
|
||||
def test_normalize_scores():
|
||||
cases = [
|
||||
(pa.array([0.1, 0.4]), pa.array([0.0, 1.0])),
|
||||
|
||||
@@ -147,7 +147,12 @@ class TrackingNamespace(LanceNamespace):
|
||||
This simulates a credential rotation system where each call returns
|
||||
new credentials that expire after credential_expires_in_seconds.
|
||||
"""
|
||||
modified = copy.deepcopy(storage_options) if storage_options else {}
|
||||
# Start from base storage options (endpoint, region, allow_http, etc.)
|
||||
# because DirectoryNamespace returns None for storage_options from
|
||||
# describe_table/declare_table when no credential vendor is configured.
|
||||
modified = copy.deepcopy(self.base_storage_options)
|
||||
if storage_options:
|
||||
modified.update(storage_options)
|
||||
|
||||
# Increment credentials to simulate rotation
|
||||
modified["aws_access_key_id"] = f"AKID_{count}"
|
||||
|
||||
@@ -326,6 +326,24 @@ def test_add_struct(mem_db: DBConnection):
|
||||
table = mem_db.create_table("test2", schema=schema)
|
||||
table.add(data)
|
||||
|
||||
struct_type = pa.struct(
|
||||
[
|
||||
("b", pa.int64()),
|
||||
("a", pa.int64()),
|
||||
]
|
||||
)
|
||||
expected = pa.table(
|
||||
{
|
||||
"s_list": [
|
||||
[
|
||||
pa.scalar({"b": 1, "a": 2}, type=struct_type),
|
||||
pa.scalar({"b": 4, "a": None}, type=struct_type),
|
||||
]
|
||||
],
|
||||
}
|
||||
)
|
||||
assert table.to_arrow() == expected
|
||||
|
||||
|
||||
def test_add_subschema(mem_db: DBConnection):
|
||||
schema = pa.schema(
|
||||
|
||||
@@ -17,7 +17,8 @@ use pyo3::{
|
||||
use pyo3_async_runtimes::tokio::future_into_py;
|
||||
|
||||
use crate::{
|
||||
error::PythonErrorExt, storage_options::py_object_to_storage_options_provider, table::Table,
|
||||
error::PythonErrorExt, namespace::extract_namespace_arc,
|
||||
storage_options::py_object_to_storage_options_provider, table::Table,
|
||||
};
|
||||
|
||||
#[pyclass]
|
||||
@@ -182,7 +183,8 @@ impl Connection {
|
||||
})
|
||||
}
|
||||
|
||||
#[pyo3(signature = (name, namespace=vec![], storage_options = None, storage_options_provider=None, index_cache_size = None, location=None))]
|
||||
#[allow(clippy::too_many_arguments)]
|
||||
#[pyo3(signature = (name, namespace=vec![], storage_options = None, storage_options_provider=None, index_cache_size = None, location=None, namespace_client=None, managed_versioning=None))]
|
||||
pub fn open_table(
|
||||
self_: PyRef<'_, Self>,
|
||||
name: String,
|
||||
@@ -191,11 +193,13 @@ impl Connection {
|
||||
storage_options_provider: Option<Py<PyAny>>,
|
||||
index_cache_size: Option<u32>,
|
||||
location: Option<String>,
|
||||
namespace_client: Option<Py<PyAny>>,
|
||||
managed_versioning: Option<bool>,
|
||||
) -> PyResult<Bound<'_, PyAny>> {
|
||||
let inner = self_.get_inner()?.clone();
|
||||
|
||||
let mut builder = inner.open_table(name);
|
||||
builder = builder.namespace(namespace);
|
||||
builder = builder.namespace(namespace.clone());
|
||||
if let Some(storage_options) = storage_options {
|
||||
builder = builder.storage_options(storage_options);
|
||||
}
|
||||
@@ -209,6 +213,20 @@ impl Connection {
|
||||
if let Some(location) = location {
|
||||
builder = builder.location(location);
|
||||
}
|
||||
// Extract namespace client from Python object if provided
|
||||
let ns_client = if let Some(ns_obj) = namespace_client {
|
||||
let py = self_.py();
|
||||
Some(extract_namespace_arc(py, ns_obj)?)
|
||||
} else {
|
||||
None
|
||||
};
|
||||
if let Some(ns_client) = ns_client {
|
||||
builder = builder.namespace_client(ns_client);
|
||||
}
|
||||
// Pass managed_versioning if provided to avoid redundant describe_table call
|
||||
if let Some(enabled) = managed_versioning {
|
||||
builder = builder.managed_versioning(enabled);
|
||||
}
|
||||
|
||||
future_into_py(self_.py(), async move {
|
||||
let table = builder.execute().await.infer_error()?;
|
||||
|
||||
@@ -23,6 +23,7 @@ pub mod connection;
|
||||
pub mod error;
|
||||
pub mod header;
|
||||
pub mod index;
|
||||
pub mod namespace;
|
||||
pub mod permutation;
|
||||
pub mod query;
|
||||
pub mod session;
|
||||
|
||||
696
python/src/namespace.rs
Normal file
696
python/src/namespace.rs
Normal file
@@ -0,0 +1,696 @@
|
||||
// SPDX-License-Identifier: Apache-2.0
|
||||
// SPDX-FileCopyrightText: Copyright The LanceDB Authors
|
||||
|
||||
//! Namespace utilities for Python bindings
|
||||
|
||||
use std::collections::HashMap;
|
||||
use std::sync::Arc;
|
||||
|
||||
use async_trait::async_trait;
|
||||
use bytes::Bytes;
|
||||
use lance_namespace::LanceNamespace as LanceNamespaceTrait;
|
||||
use lance_namespace::models::*;
|
||||
use pyo3::prelude::*;
|
||||
use pyo3::types::PyDict;
|
||||
|
||||
/// Wrapper that allows any Python object implementing LanceNamespace protocol
|
||||
/// to be used as a Rust LanceNamespace.
|
||||
///
|
||||
/// This is similar to PyLanceNamespace in lance's Python bindings - it wraps a Python
|
||||
/// object and calls back into Python when namespace methods are invoked.
|
||||
pub struct PyLanceNamespace {
|
||||
py_namespace: Arc<Py<PyAny>>,
|
||||
namespace_id: String,
|
||||
}
|
||||
|
||||
impl PyLanceNamespace {
|
||||
/// Create a new PyLanceNamespace wrapper around a Python namespace object.
|
||||
pub fn new(_py: Python<'_>, py_namespace: &Bound<'_, PyAny>) -> PyResult<Self> {
|
||||
let namespace_id = py_namespace
|
||||
.call_method0("namespace_id")?
|
||||
.extract::<String>()?;
|
||||
|
||||
Ok(Self {
|
||||
py_namespace: Arc::new(py_namespace.clone().unbind()),
|
||||
namespace_id,
|
||||
})
|
||||
}
|
||||
|
||||
/// Create an Arc<dyn LanceNamespace> from a Python namespace object.
|
||||
pub fn create_arc(
|
||||
py: Python<'_>,
|
||||
py_namespace: &Bound<'_, PyAny>,
|
||||
) -> PyResult<Arc<dyn LanceNamespaceTrait>> {
|
||||
let wrapper = Self::new(py, py_namespace)?;
|
||||
Ok(Arc::new(wrapper))
|
||||
}
|
||||
}
|
||||
|
||||
impl std::fmt::Debug for PyLanceNamespace {
|
||||
fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
|
||||
write!(f, "PyLanceNamespace {{ id: {} }}", self.namespace_id)
|
||||
}
|
||||
}
|
||||
|
||||
/// Get or create the DictWithModelDump class in Python.
|
||||
/// This class acts like a dict but also has model_dump() method.
|
||||
/// This allows it to work with both:
|
||||
/// - depythonize (which expects a dict/Mapping)
|
||||
/// - Python code that calls .model_dump() (like DirectoryNamespace wrapper)
|
||||
fn get_dict_with_model_dump_class(py: Python<'_>) -> PyResult<Bound<'_, PyAny>> {
|
||||
// Use a module-level cache via __builtins__
|
||||
let builtins = py.import("builtins")?;
|
||||
if builtins.hasattr("_DictWithModelDump")? {
|
||||
return builtins.getattr("_DictWithModelDump");
|
||||
}
|
||||
|
||||
// Create the class using exec
|
||||
let locals = PyDict::new(py);
|
||||
py.run(
|
||||
c"class DictWithModelDump(dict):
|
||||
def model_dump(self):
|
||||
return dict(self)",
|
||||
None,
|
||||
Some(&locals),
|
||||
)?;
|
||||
let class = locals.get_item("DictWithModelDump")?.ok_or_else(|| {
|
||||
pyo3::exceptions::PyRuntimeError::new_err("Failed to create DictWithModelDump class")
|
||||
})?;
|
||||
|
||||
// Cache it
|
||||
builtins.setattr("_DictWithModelDump", &class)?;
|
||||
Ok(class)
|
||||
}
|
||||
|
||||
/// Helper to call a Python namespace method with JSON serialization.
|
||||
/// For methods that take a request and return a response.
|
||||
/// Uses DictWithModelDump to pass a dict that also has model_dump() method,
|
||||
/// making it compatible with both depythonize and Python wrappers.
|
||||
async fn call_py_method<Req, Resp>(
|
||||
py_namespace: Arc<Py<PyAny>>,
|
||||
method_name: &'static str,
|
||||
request: Req,
|
||||
) -> lance_core::Result<Resp>
|
||||
where
|
||||
Req: serde::Serialize + Send + 'static,
|
||||
Resp: serde::de::DeserializeOwned + Send + 'static,
|
||||
{
|
||||
let request_json = serde_json::to_string(&request).map_err(|e| {
|
||||
lance_core::Error::io(format!(
|
||||
"Failed to serialize request for {}: {}",
|
||||
method_name, e
|
||||
))
|
||||
})?;
|
||||
|
||||
let response_json = tokio::task::spawn_blocking(move || {
|
||||
Python::attach(|py| {
|
||||
let json_module = py.import("json")?;
|
||||
let request_dict = json_module.call_method1("loads", (&request_json,))?;
|
||||
|
||||
// Wrap dict in DictWithModelDump so it works with both depythonize and .model_dump()
|
||||
let dict_class = get_dict_with_model_dump_class(py)?;
|
||||
let request_arg = dict_class.call1((request_dict,))?;
|
||||
|
||||
// Call the Python method
|
||||
let result = py_namespace.call_method1(py, method_name, (request_arg,))?;
|
||||
|
||||
// Convert response to dict, then to JSON
|
||||
// Pydantic models have model_dump() method
|
||||
let result_dict = if result.bind(py).hasattr("model_dump")? {
|
||||
result.call_method0(py, "model_dump")?
|
||||
} else {
|
||||
result
|
||||
};
|
||||
let response_json: String = json_module
|
||||
.call_method1("dumps", (result_dict,))?
|
||||
.extract()?;
|
||||
Ok::<_, PyErr>(response_json)
|
||||
})
|
||||
})
|
||||
.await
|
||||
.map_err(|e| lance_core::Error::io(format!("Task join error for {}: {}", method_name, e)))?
|
||||
.map_err(|e: PyErr| lance_core::Error::io(format!("Python error in {}: {}", method_name, e)))?;
|
||||
|
||||
serde_json::from_str(&response_json).map_err(|e| {
|
||||
lance_core::Error::io(format!(
|
||||
"Failed to deserialize response from {}: {}",
|
||||
method_name, e
|
||||
))
|
||||
})
|
||||
}
|
||||
|
||||
/// Helper for methods that return () on success
|
||||
async fn call_py_method_unit<Req>(
|
||||
py_namespace: Arc<Py<PyAny>>,
|
||||
method_name: &'static str,
|
||||
request: Req,
|
||||
) -> lance_core::Result<()>
|
||||
where
|
||||
Req: serde::Serialize + Send + 'static,
|
||||
{
|
||||
let request_json = serde_json::to_string(&request).map_err(|e| {
|
||||
lance_core::Error::io(format!(
|
||||
"Failed to serialize request for {}: {}",
|
||||
method_name, e
|
||||
))
|
||||
})?;
|
||||
|
||||
tokio::task::spawn_blocking(move || {
|
||||
Python::attach(|py| {
|
||||
let json_module = py.import("json")?;
|
||||
let request_dict = json_module.call_method1("loads", (&request_json,))?;
|
||||
|
||||
// Wrap dict in DictWithModelDump
|
||||
let dict_class = get_dict_with_model_dump_class(py)?;
|
||||
let request_arg = dict_class.call1((request_dict,))?;
|
||||
|
||||
// Call the Python method
|
||||
py_namespace.call_method1(py, method_name, (request_arg,))?;
|
||||
Ok::<_, PyErr>(())
|
||||
})
|
||||
})
|
||||
.await
|
||||
.map_err(|e| lance_core::Error::io(format!("Task join error for {}: {}", method_name, e)))?
|
||||
.map_err(|e: PyErr| lance_core::Error::io(format!("Python error in {}: {}", method_name, e)))
|
||||
}
|
||||
|
||||
/// Helper for methods that return a primitive type
|
||||
async fn call_py_method_primitive<Req, Resp>(
|
||||
py_namespace: Arc<Py<PyAny>>,
|
||||
method_name: &'static str,
|
||||
request: Req,
|
||||
) -> lance_core::Result<Resp>
|
||||
where
|
||||
Req: serde::Serialize + 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!(
|
||||
"Failed to serialize request for {}: {}",
|
||||
method_name, e
|
||||
))
|
||||
})?;
|
||||
|
||||
tokio::task::spawn_blocking(move || {
|
||||
Python::attach(|py| {
|
||||
let json_module = py.import("json")?;
|
||||
let request_dict = json_module.call_method1("loads", (&request_json,))?;
|
||||
|
||||
// Wrap dict in DictWithModelDump
|
||||
let dict_class = get_dict_with_model_dump_class(py)?;
|
||||
let request_arg = dict_class.call1((request_dict,))?;
|
||||
|
||||
// Call the Python method
|
||||
let result = py_namespace.call_method1(py, method_name, (request_arg,))?;
|
||||
let value: Resp = result.extract(py)?;
|
||||
Ok::<_, PyErr>(value)
|
||||
})
|
||||
})
|
||||
.await
|
||||
.map_err(|e| lance_core::Error::io(format!("Task join error for {}: {}", method_name, e)))?
|
||||
.map_err(|e: PyErr| lance_core::Error::io(format!("Python error in {}: {}", method_name, e)))
|
||||
}
|
||||
|
||||
/// Helper for methods that return Bytes
|
||||
async fn call_py_method_bytes<Req>(
|
||||
py_namespace: Arc<Py<PyAny>>,
|
||||
method_name: &'static str,
|
||||
request: Req,
|
||||
) -> lance_core::Result<Bytes>
|
||||
where
|
||||
Req: serde::Serialize + Send + 'static,
|
||||
{
|
||||
let request_json = serde_json::to_string(&request).map_err(|e| {
|
||||
lance_core::Error::io(format!(
|
||||
"Failed to serialize request for {}: {}",
|
||||
method_name, e
|
||||
))
|
||||
})?;
|
||||
|
||||
tokio::task::spawn_blocking(move || {
|
||||
Python::attach(|py| {
|
||||
let json_module = py.import("json")?;
|
||||
let request_dict = json_module.call_method1("loads", (&request_json,))?;
|
||||
|
||||
// Wrap dict in DictWithModelDump
|
||||
let dict_class = get_dict_with_model_dump_class(py)?;
|
||||
let request_arg = dict_class.call1((request_dict,))?;
|
||||
|
||||
// Call the Python method
|
||||
let result = py_namespace.call_method1(py, method_name, (request_arg,))?;
|
||||
let bytes_data: Vec<u8> = result.extract(py)?;
|
||||
Ok::<_, PyErr>(Bytes::from(bytes_data))
|
||||
})
|
||||
})
|
||||
.await
|
||||
.map_err(|e| lance_core::Error::io(format!("Task join error for {}: {}", method_name, e)))?
|
||||
.map_err(|e: PyErr| lance_core::Error::io(format!("Python error in {}: {}", method_name, e)))
|
||||
}
|
||||
|
||||
/// Helper for methods that take request + data and return a response
|
||||
async fn call_py_method_with_data<Req, Resp>(
|
||||
py_namespace: Arc<Py<PyAny>>,
|
||||
method_name: &'static str,
|
||||
request: Req,
|
||||
data: Bytes,
|
||||
) -> lance_core::Result<Resp>
|
||||
where
|
||||
Req: serde::Serialize + Send + 'static,
|
||||
Resp: serde::de::DeserializeOwned + Send + 'static,
|
||||
{
|
||||
let request_json = serde_json::to_string(&request).map_err(|e| {
|
||||
lance_core::Error::io(format!(
|
||||
"Failed to serialize request for {}: {}",
|
||||
method_name, e
|
||||
))
|
||||
})?;
|
||||
|
||||
let response_json = tokio::task::spawn_blocking(move || {
|
||||
Python::attach(|py| {
|
||||
let json_module = py.import("json")?;
|
||||
let request_dict = json_module.call_method1("loads", (&request_json,))?;
|
||||
|
||||
// Wrap dict in DictWithModelDump
|
||||
let dict_class = get_dict_with_model_dump_class(py)?;
|
||||
let request_arg = dict_class.call1((request_dict,))?;
|
||||
|
||||
// Pass request and bytes to Python method
|
||||
let py_bytes = pyo3::types::PyBytes::new(py, &data);
|
||||
let result = py_namespace.call_method1(py, method_name, (request_arg, py_bytes))?;
|
||||
|
||||
// Convert response dict to JSON
|
||||
let response_json: String = json_module.call_method1("dumps", (result,))?.extract()?;
|
||||
Ok::<_, PyErr>(response_json)
|
||||
})
|
||||
})
|
||||
.await
|
||||
.map_err(|e| lance_core::Error::io(format!("Task join error for {}: {}", method_name, e)))?
|
||||
.map_err(|e: PyErr| lance_core::Error::io(format!("Python error in {}: {}", method_name, e)))?;
|
||||
|
||||
serde_json::from_str(&response_json).map_err(|e| {
|
||||
lance_core::Error::io(format!(
|
||||
"Failed to deserialize response from {}: {}",
|
||||
method_name, e
|
||||
))
|
||||
})
|
||||
}
|
||||
|
||||
#[async_trait]
|
||||
impl LanceNamespaceTrait for PyLanceNamespace {
|
||||
fn namespace_id(&self) -> String {
|
||||
self.namespace_id.clone()
|
||||
}
|
||||
|
||||
async fn list_namespaces(
|
||||
&self,
|
||||
request: ListNamespacesRequest,
|
||||
) -> lance_core::Result<ListNamespacesResponse> {
|
||||
call_py_method(self.py_namespace.clone(), "list_namespaces", request).await
|
||||
}
|
||||
|
||||
async fn describe_namespace(
|
||||
&self,
|
||||
request: DescribeNamespaceRequest,
|
||||
) -> lance_core::Result<DescribeNamespaceResponse> {
|
||||
call_py_method(self.py_namespace.clone(), "describe_namespace", request).await
|
||||
}
|
||||
|
||||
async fn create_namespace(
|
||||
&self,
|
||||
request: CreateNamespaceRequest,
|
||||
) -> lance_core::Result<CreateNamespaceResponse> {
|
||||
call_py_method(self.py_namespace.clone(), "create_namespace", request).await
|
||||
}
|
||||
|
||||
async fn drop_namespace(
|
||||
&self,
|
||||
request: DropNamespaceRequest,
|
||||
) -> lance_core::Result<DropNamespaceResponse> {
|
||||
call_py_method(self.py_namespace.clone(), "drop_namespace", request).await
|
||||
}
|
||||
|
||||
async fn namespace_exists(&self, request: NamespaceExistsRequest) -> lance_core::Result<()> {
|
||||
call_py_method_unit(self.py_namespace.clone(), "namespace_exists", request).await
|
||||
}
|
||||
|
||||
async fn list_tables(
|
||||
&self,
|
||||
request: ListTablesRequest,
|
||||
) -> lance_core::Result<ListTablesResponse> {
|
||||
call_py_method(self.py_namespace.clone(), "list_tables", request).await
|
||||
}
|
||||
|
||||
async fn describe_table(
|
||||
&self,
|
||||
request: DescribeTableRequest,
|
||||
) -> lance_core::Result<DescribeTableResponse> {
|
||||
call_py_method(self.py_namespace.clone(), "describe_table", request).await
|
||||
}
|
||||
|
||||
async fn register_table(
|
||||
&self,
|
||||
request: RegisterTableRequest,
|
||||
) -> lance_core::Result<RegisterTableResponse> {
|
||||
call_py_method(self.py_namespace.clone(), "register_table", request).await
|
||||
}
|
||||
|
||||
async fn table_exists(&self, request: TableExistsRequest) -> lance_core::Result<()> {
|
||||
call_py_method_unit(self.py_namespace.clone(), "table_exists", request).await
|
||||
}
|
||||
|
||||
async fn drop_table(&self, request: DropTableRequest) -> lance_core::Result<DropTableResponse> {
|
||||
call_py_method(self.py_namespace.clone(), "drop_table", request).await
|
||||
}
|
||||
|
||||
async fn deregister_table(
|
||||
&self,
|
||||
request: DeregisterTableRequest,
|
||||
) -> lance_core::Result<DeregisterTableResponse> {
|
||||
call_py_method(self.py_namespace.clone(), "deregister_table", request).await
|
||||
}
|
||||
|
||||
async fn count_table_rows(&self, request: CountTableRowsRequest) -> lance_core::Result<i64> {
|
||||
call_py_method_primitive(self.py_namespace.clone(), "count_table_rows", request).await
|
||||
}
|
||||
|
||||
async fn create_table(
|
||||
&self,
|
||||
request: CreateTableRequest,
|
||||
request_data: Bytes,
|
||||
) -> lance_core::Result<CreateTableResponse> {
|
||||
call_py_method_with_data(
|
||||
self.py_namespace.clone(),
|
||||
"create_table",
|
||||
request,
|
||||
request_data,
|
||||
)
|
||||
.await
|
||||
}
|
||||
|
||||
async fn declare_table(
|
||||
&self,
|
||||
request: DeclareTableRequest,
|
||||
) -> lance_core::Result<DeclareTableResponse> {
|
||||
call_py_method(self.py_namespace.clone(), "declare_table", request).await
|
||||
}
|
||||
|
||||
async fn insert_into_table(
|
||||
&self,
|
||||
request: InsertIntoTableRequest,
|
||||
request_data: Bytes,
|
||||
) -> lance_core::Result<InsertIntoTableResponse> {
|
||||
call_py_method_with_data(
|
||||
self.py_namespace.clone(),
|
||||
"insert_into_table",
|
||||
request,
|
||||
request_data,
|
||||
)
|
||||
.await
|
||||
}
|
||||
|
||||
async fn merge_insert_into_table(
|
||||
&self,
|
||||
request: MergeInsertIntoTableRequest,
|
||||
request_data: Bytes,
|
||||
) -> lance_core::Result<MergeInsertIntoTableResponse> {
|
||||
call_py_method_with_data(
|
||||
self.py_namespace.clone(),
|
||||
"merge_insert_into_table",
|
||||
request,
|
||||
request_data,
|
||||
)
|
||||
.await
|
||||
}
|
||||
|
||||
async fn update_table(
|
||||
&self,
|
||||
request: UpdateTableRequest,
|
||||
) -> lance_core::Result<UpdateTableResponse> {
|
||||
call_py_method(self.py_namespace.clone(), "update_table", request).await
|
||||
}
|
||||
|
||||
async fn delete_from_table(
|
||||
&self,
|
||||
request: DeleteFromTableRequest,
|
||||
) -> lance_core::Result<DeleteFromTableResponse> {
|
||||
call_py_method(self.py_namespace.clone(), "delete_from_table", request).await
|
||||
}
|
||||
|
||||
async fn query_table(&self, request: QueryTableRequest) -> lance_core::Result<Bytes> {
|
||||
call_py_method_bytes(self.py_namespace.clone(), "query_table", request).await
|
||||
}
|
||||
|
||||
async fn create_table_index(
|
||||
&self,
|
||||
request: CreateTableIndexRequest,
|
||||
) -> lance_core::Result<CreateTableIndexResponse> {
|
||||
call_py_method(self.py_namespace.clone(), "create_table_index", request).await
|
||||
}
|
||||
|
||||
async fn list_table_indices(
|
||||
&self,
|
||||
request: ListTableIndicesRequest,
|
||||
) -> lance_core::Result<ListTableIndicesResponse> {
|
||||
call_py_method(self.py_namespace.clone(), "list_table_indices", request).await
|
||||
}
|
||||
|
||||
async fn describe_table_index_stats(
|
||||
&self,
|
||||
request: DescribeTableIndexStatsRequest,
|
||||
) -> lance_core::Result<DescribeTableIndexStatsResponse> {
|
||||
call_py_method(
|
||||
self.py_namespace.clone(),
|
||||
"describe_table_index_stats",
|
||||
request,
|
||||
)
|
||||
.await
|
||||
}
|
||||
|
||||
async fn describe_transaction(
|
||||
&self,
|
||||
request: DescribeTransactionRequest,
|
||||
) -> lance_core::Result<DescribeTransactionResponse> {
|
||||
call_py_method(self.py_namespace.clone(), "describe_transaction", request).await
|
||||
}
|
||||
|
||||
async fn alter_transaction(
|
||||
&self,
|
||||
request: AlterTransactionRequest,
|
||||
) -> lance_core::Result<AlterTransactionResponse> {
|
||||
call_py_method(self.py_namespace.clone(), "alter_transaction", request).await
|
||||
}
|
||||
|
||||
async fn create_table_scalar_index(
|
||||
&self,
|
||||
request: CreateTableIndexRequest,
|
||||
) -> lance_core::Result<CreateTableScalarIndexResponse> {
|
||||
call_py_method(
|
||||
self.py_namespace.clone(),
|
||||
"create_table_scalar_index",
|
||||
request,
|
||||
)
|
||||
.await
|
||||
}
|
||||
|
||||
async fn drop_table_index(
|
||||
&self,
|
||||
request: DropTableIndexRequest,
|
||||
) -> lance_core::Result<DropTableIndexResponse> {
|
||||
call_py_method(self.py_namespace.clone(), "drop_table_index", request).await
|
||||
}
|
||||
|
||||
async fn list_all_tables(
|
||||
&self,
|
||||
request: ListTablesRequest,
|
||||
) -> lance_core::Result<ListTablesResponse> {
|
||||
call_py_method(self.py_namespace.clone(), "list_all_tables", request).await
|
||||
}
|
||||
|
||||
async fn restore_table(
|
||||
&self,
|
||||
request: RestoreTableRequest,
|
||||
) -> lance_core::Result<RestoreTableResponse> {
|
||||
call_py_method(self.py_namespace.clone(), "restore_table", request).await
|
||||
}
|
||||
|
||||
async fn rename_table(
|
||||
&self,
|
||||
request: RenameTableRequest,
|
||||
) -> lance_core::Result<RenameTableResponse> {
|
||||
call_py_method(self.py_namespace.clone(), "rename_table", request).await
|
||||
}
|
||||
|
||||
async fn list_table_versions(
|
||||
&self,
|
||||
request: ListTableVersionsRequest,
|
||||
) -> lance_core::Result<ListTableVersionsResponse> {
|
||||
call_py_method(self.py_namespace.clone(), "list_table_versions", request).await
|
||||
}
|
||||
|
||||
async fn create_table_version(
|
||||
&self,
|
||||
request: CreateTableVersionRequest,
|
||||
) -> lance_core::Result<CreateTableVersionResponse> {
|
||||
call_py_method(self.py_namespace.clone(), "create_table_version", request).await
|
||||
}
|
||||
|
||||
async fn describe_table_version(
|
||||
&self,
|
||||
request: DescribeTableVersionRequest,
|
||||
) -> lance_core::Result<DescribeTableVersionResponse> {
|
||||
call_py_method(self.py_namespace.clone(), "describe_table_version", request).await
|
||||
}
|
||||
|
||||
async fn batch_delete_table_versions(
|
||||
&self,
|
||||
request: BatchDeleteTableVersionsRequest,
|
||||
) -> lance_core::Result<BatchDeleteTableVersionsResponse> {
|
||||
call_py_method(
|
||||
self.py_namespace.clone(),
|
||||
"batch_delete_table_versions",
|
||||
request,
|
||||
)
|
||||
.await
|
||||
}
|
||||
|
||||
async fn update_table_schema_metadata(
|
||||
&self,
|
||||
request: UpdateTableSchemaMetadataRequest,
|
||||
) -> lance_core::Result<UpdateTableSchemaMetadataResponse> {
|
||||
call_py_method(
|
||||
self.py_namespace.clone(),
|
||||
"update_table_schema_metadata",
|
||||
request,
|
||||
)
|
||||
.await
|
||||
}
|
||||
|
||||
async fn get_table_stats(
|
||||
&self,
|
||||
request: GetTableStatsRequest,
|
||||
) -> lance_core::Result<GetTableStatsResponse> {
|
||||
call_py_method(self.py_namespace.clone(), "get_table_stats", request).await
|
||||
}
|
||||
|
||||
async fn explain_table_query_plan(
|
||||
&self,
|
||||
request: ExplainTableQueryPlanRequest,
|
||||
) -> lance_core::Result<String> {
|
||||
call_py_method_primitive(
|
||||
self.py_namespace.clone(),
|
||||
"explain_table_query_plan",
|
||||
request,
|
||||
)
|
||||
.await
|
||||
}
|
||||
|
||||
async fn analyze_table_query_plan(
|
||||
&self,
|
||||
request: AnalyzeTableQueryPlanRequest,
|
||||
) -> lance_core::Result<String> {
|
||||
call_py_method_primitive(
|
||||
self.py_namespace.clone(),
|
||||
"analyze_table_query_plan",
|
||||
request,
|
||||
)
|
||||
.await
|
||||
}
|
||||
|
||||
async fn alter_table_add_columns(
|
||||
&self,
|
||||
request: AlterTableAddColumnsRequest,
|
||||
) -> lance_core::Result<AlterTableAddColumnsResponse> {
|
||||
call_py_method(
|
||||
self.py_namespace.clone(),
|
||||
"alter_table_add_columns",
|
||||
request,
|
||||
)
|
||||
.await
|
||||
}
|
||||
|
||||
async fn alter_table_alter_columns(
|
||||
&self,
|
||||
request: AlterTableAlterColumnsRequest,
|
||||
) -> lance_core::Result<AlterTableAlterColumnsResponse> {
|
||||
call_py_method(
|
||||
self.py_namespace.clone(),
|
||||
"alter_table_alter_columns",
|
||||
request,
|
||||
)
|
||||
.await
|
||||
}
|
||||
|
||||
async fn alter_table_drop_columns(
|
||||
&self,
|
||||
request: AlterTableDropColumnsRequest,
|
||||
) -> lance_core::Result<AlterTableDropColumnsResponse> {
|
||||
call_py_method(
|
||||
self.py_namespace.clone(),
|
||||
"alter_table_drop_columns",
|
||||
request,
|
||||
)
|
||||
.await
|
||||
}
|
||||
|
||||
async fn list_table_tags(
|
||||
&self,
|
||||
request: ListTableTagsRequest,
|
||||
) -> lance_core::Result<ListTableTagsResponse> {
|
||||
call_py_method(self.py_namespace.clone(), "list_table_tags", request).await
|
||||
}
|
||||
|
||||
async fn create_table_tag(
|
||||
&self,
|
||||
request: CreateTableTagRequest,
|
||||
) -> lance_core::Result<CreateTableTagResponse> {
|
||||
call_py_method(self.py_namespace.clone(), "create_table_tag", request).await
|
||||
}
|
||||
|
||||
async fn delete_table_tag(
|
||||
&self,
|
||||
request: DeleteTableTagRequest,
|
||||
) -> lance_core::Result<DeleteTableTagResponse> {
|
||||
call_py_method(self.py_namespace.clone(), "delete_table_tag", request).await
|
||||
}
|
||||
|
||||
async fn update_table_tag(
|
||||
&self,
|
||||
request: UpdateTableTagRequest,
|
||||
) -> lance_core::Result<UpdateTableTagResponse> {
|
||||
call_py_method(self.py_namespace.clone(), "update_table_tag", request).await
|
||||
}
|
||||
|
||||
async fn get_table_tag_version(
|
||||
&self,
|
||||
request: GetTableTagVersionRequest,
|
||||
) -> lance_core::Result<GetTableTagVersionResponse> {
|
||||
call_py_method(self.py_namespace.clone(), "get_table_tag_version", request).await
|
||||
}
|
||||
}
|
||||
|
||||
/// Convert Python dict to HashMap<String, String>
|
||||
#[allow(dead_code)]
|
||||
fn dict_to_hashmap(dict: &Bound<'_, PyDict>) -> PyResult<HashMap<String, String>> {
|
||||
let mut map = HashMap::new();
|
||||
for (key, value) in dict.iter() {
|
||||
let key_str: String = key.extract()?;
|
||||
let value_str: String = value.extract()?;
|
||||
map.insert(key_str, value_str);
|
||||
}
|
||||
Ok(map)
|
||||
}
|
||||
|
||||
/// Extract an Arc<dyn LanceNamespace> from a Python namespace object.
|
||||
///
|
||||
/// This function wraps any Python namespace object with PyLanceNamespace.
|
||||
/// The PyLanceNamespace wrapper uses DictWithModelDump to pass requests,
|
||||
/// which works with both:
|
||||
/// - Native namespaces (DirectoryNamespace, RestNamespace) that use depythonize (expects dict)
|
||||
/// - Custom Python implementations that call .model_dump() on the request
|
||||
pub fn extract_namespace_arc(
|
||||
py: Python<'_>,
|
||||
ns: Py<PyAny>,
|
||||
) -> PyResult<Arc<dyn LanceNamespaceTrait>> {
|
||||
let ns_ref = ns.bind(py);
|
||||
PyLanceNamespace::create_arc(py, ns_ref)
|
||||
}
|
||||
@@ -316,6 +316,19 @@ impl<'py> IntoPyObject<'py> for PySelect {
|
||||
Select::All => Ok(py.None().into_bound(py).into_any()),
|
||||
Select::Columns(columns) => Ok(columns.into_pyobject(py)?.into_any()),
|
||||
Select::Dynamic(columns) => Ok(columns.into_pyobject(py)?.into_any()),
|
||||
Select::Expr(pairs) => {
|
||||
// Serialize DataFusion Expr -> SQL string so Python sees the same
|
||||
// format as Select::Dynamic: a list of (name, sql_string) tuples.
|
||||
let sql_pairs: PyResult<Vec<(String, String)>> = pairs
|
||||
.into_iter()
|
||||
.map(|(name, expr)| {
|
||||
lancedb::expr::expr_to_sql_string(&expr)
|
||||
.map(|sql| (name, sql))
|
||||
.map_err(|e| PyRuntimeError::new_err(e.to_string()))
|
||||
})
|
||||
.collect();
|
||||
Ok(sql_pairs?.into_pyobject(py)?.into_any())
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
@@ -66,13 +66,10 @@ impl StorageOptionsProvider for PyStorageOptionsProviderWrapper {
|
||||
.inner
|
||||
.bind(py)
|
||||
.call_method0("fetch_storage_options")
|
||||
.map_err(|e| lance_core::Error::IO {
|
||||
source: Box::new(std::io::Error::other(format!(
|
||||
"Failed to call fetch_storage_options: {}",
|
||||
e
|
||||
))),
|
||||
location: snafu::location!(),
|
||||
})?;
|
||||
.map_err(|e| lance_core::Error::io_source(Box::new(std::io::Error::other(format!(
|
||||
"Failed to call fetch_storage_options: {}",
|
||||
e
|
||||
)))))?;
|
||||
|
||||
// If result is None, return None
|
||||
if result.is_none() {
|
||||
@@ -81,26 +78,19 @@ impl StorageOptionsProvider for PyStorageOptionsProviderWrapper {
|
||||
|
||||
// Extract the result dict - should be a flat Map<String, String>
|
||||
let result_dict = result.downcast::<PyDict>().map_err(|_| {
|
||||
lance_core::Error::InvalidInput {
|
||||
source: "fetch_storage_options() must return None or a dict of string key-value pairs".into(),
|
||||
location: snafu::location!(),
|
||||
}
|
||||
lance_core::Error::invalid_input(
|
||||
"fetch_storage_options() must return a dict of string key-value pairs or None",
|
||||
)
|
||||
})?;
|
||||
|
||||
// Convert all entries to HashMap<String, String>
|
||||
let mut storage_options = HashMap::new();
|
||||
for (key, value) in result_dict.iter() {
|
||||
let key_str: String = key.extract().map_err(|e| {
|
||||
lance_core::Error::InvalidInput {
|
||||
source: format!("Storage option key must be a string: {}", e).into(),
|
||||
location: snafu::location!(),
|
||||
}
|
||||
lance_core::Error::invalid_input(format!("Storage option key must be a string: {}", e))
|
||||
})?;
|
||||
let value_str: String = value.extract().map_err(|e| {
|
||||
lance_core::Error::InvalidInput {
|
||||
source: format!("Storage option value must be a string: {}", e).into(),
|
||||
location: snafu::location!(),
|
||||
}
|
||||
lance_core::Error::invalid_input(format!("Storage option value must be a string: {}", e))
|
||||
})?;
|
||||
storage_options.insert(key_str, value_str);
|
||||
}
|
||||
@@ -109,13 +99,10 @@ impl StorageOptionsProvider for PyStorageOptionsProviderWrapper {
|
||||
})
|
||||
})
|
||||
.await
|
||||
.map_err(|e| lance_core::Error::IO {
|
||||
source: Box::new(std::io::Error::other(format!(
|
||||
"Task join error: {}",
|
||||
e
|
||||
))),
|
||||
location: snafu::location!(),
|
||||
})?
|
||||
.map_err(|e| lance_core::Error::io_source(Box::new(std::io::Error::other(format!(
|
||||
"Task join error: {}",
|
||||
e
|
||||
)))))?
|
||||
}
|
||||
|
||||
fn provider_id(&self) -> String {
|
||||
|
||||
@@ -426,6 +426,17 @@ impl Table {
|
||||
})
|
||||
}
|
||||
|
||||
pub fn prewarm_data(
|
||||
self_: PyRef<'_, Self>,
|
||||
columns: Option<Vec<String>>,
|
||||
) -> PyResult<Bound<'_, PyAny>> {
|
||||
let inner = self_.inner_ref()?.clone();
|
||||
future_into_py(self_.py(), async move {
|
||||
inner.prewarm_data(columns).await.infer_error()?;
|
||||
Ok(())
|
||||
})
|
||||
}
|
||||
|
||||
pub fn list_indices(self_: PyRef<'_, Self>) -> PyResult<Bound<'_, PyAny>> {
|
||||
let inner = self_.inner_ref()?.clone();
|
||||
future_into_py(self_.py(), async move {
|
||||
|
||||
4
python/uv.lock
generated
4
python/uv.lock
generated
@@ -2006,7 +2006,7 @@ requires-dist = [
|
||||
{ name = "botocore", marker = "extra == 'embeddings'", specifier = ">=1.31.57" },
|
||||
{ name = "cohere", marker = "extra == 'embeddings'" },
|
||||
{ name = "colpali-engine", marker = "extra == 'embeddings'", specifier = ">=0.3.10" },
|
||||
{ name = "datafusion", marker = "extra == 'tests'" },
|
||||
{ name = "datafusion", marker = "extra == 'tests'", specifier = "<52" },
|
||||
{ name = "deprecation" },
|
||||
{ name = "duckdb", marker = "extra == 'tests'" },
|
||||
{ name = "google-generativeai", marker = "extra == 'embeddings'" },
|
||||
@@ -2035,7 +2035,7 @@ requires-dist = [
|
||||
{ name = "pyarrow-stubs", marker = "extra == 'tests'" },
|
||||
{ name = "pydantic", specifier = ">=1.10" },
|
||||
{ name = "pylance", marker = "extra == 'pylance'", specifier = ">=1.0.0b14" },
|
||||
{ name = "pylance", marker = "extra == 'tests'", specifier = ">=1.0.0b14" },
|
||||
{ name = "pylance", marker = "extra == 'tests'", specifier = ">=1.0.0b14,<3.0.0" },
|
||||
{ name = "pyright", marker = "extra == 'dev'" },
|
||||
{ name = "pytest", marker = "extra == 'tests'" },
|
||||
{ name = "pytest-asyncio", marker = "extra == 'tests'" },
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
[package]
|
||||
name = "lancedb"
|
||||
version = "0.27.0-beta.3"
|
||||
version = "0.27.1"
|
||||
edition.workspace = true
|
||||
description = "LanceDB: A serverless, low-latency vector database for AI applications"
|
||||
license.workspace = true
|
||||
|
||||
@@ -1,4 +1,4 @@
|
||||
# LanceDB Rust
|
||||
# LanceDB Rust SDK
|
||||
|
||||
<a href="https://crates.io/crates/vectordb"></a>
|
||||
<a href="https://docs.rs/vectordb/latest/vectordb/"></a>
|
||||
|
||||
@@ -136,6 +136,7 @@ impl OpenTableBuilder {
|
||||
lance_read_params: None,
|
||||
location: None,
|
||||
namespace_client: None,
|
||||
managed_versioning: None,
|
||||
},
|
||||
embedding_registry,
|
||||
}
|
||||
@@ -235,6 +236,29 @@ impl OpenTableBuilder {
|
||||
self
|
||||
}
|
||||
|
||||
/// Set a namespace client for managed versioning support.
|
||||
///
|
||||
/// When a namespace client is provided and the table has `managed_versioning` enabled,
|
||||
/// the table will use the namespace's commit handler to notify the namespace of
|
||||
/// version changes. This enables features like event emission for table modifications.
|
||||
pub fn namespace_client(mut self, client: Arc<dyn lance_namespace::LanceNamespace>) -> Self {
|
||||
self.request.namespace_client = Some(client);
|
||||
self
|
||||
}
|
||||
|
||||
/// Set whether managed versioning is enabled for this table.
|
||||
///
|
||||
/// When set to `Some(true)`, the table will use namespace-managed commits.
|
||||
/// When set to `Some(false)`, the table will use local commits even if namespace_client is set.
|
||||
/// When set to `None` (default), the value will be fetched from the namespace if namespace_client is set.
|
||||
///
|
||||
/// This is typically set when the caller has already queried the namespace and knows the
|
||||
/// managed_versioning status, avoiding a redundant describe_table call.
|
||||
pub fn managed_versioning(mut self, enabled: bool) -> Self {
|
||||
self.request.managed_versioning = Some(enabled);
|
||||
self
|
||||
}
|
||||
|
||||
/// Open the table
|
||||
pub async fn execute(self) -> Result<Table> {
|
||||
let table = self.parent.open_table(self.request).await?;
|
||||
@@ -294,6 +318,12 @@ impl CloneTableBuilder {
|
||||
self
|
||||
}
|
||||
|
||||
/// Set a namespace client for managed versioning support.
|
||||
pub fn namespace_client(mut self, client: Arc<dyn lance_namespace::LanceNamespace>) -> Self {
|
||||
self.request.namespace_client = Some(client);
|
||||
self
|
||||
}
|
||||
|
||||
/// Execute the clone operation
|
||||
pub async fn execute(self) -> Result<Table> {
|
||||
let parent = self.parent.clone();
|
||||
|
||||
@@ -66,6 +66,10 @@ pub struct OpenTableRequest {
|
||||
/// Optional namespace client for server-side query execution.
|
||||
/// When set, queries will be executed on the namespace server instead of locally.
|
||||
pub namespace_client: Option<Arc<dyn LanceNamespace>>,
|
||||
/// Whether managed versioning is enabled for this table.
|
||||
/// When Some(true), the table will use namespace-managed commits instead of local commits.
|
||||
/// When None and namespace_client is provided, the value will be fetched from the namespace.
|
||||
pub managed_versioning: Option<bool>,
|
||||
}
|
||||
|
||||
impl std::fmt::Debug for OpenTableRequest {
|
||||
@@ -77,6 +81,7 @@ impl std::fmt::Debug for OpenTableRequest {
|
||||
.field("lance_read_params", &self.lance_read_params)
|
||||
.field("location", &self.location)
|
||||
.field("namespace_client", &self.namespace_client)
|
||||
.field("managed_versioning", &self.managed_versioning)
|
||||
.finish()
|
||||
}
|
||||
}
|
||||
@@ -161,6 +166,9 @@ pub struct CloneTableRequest {
|
||||
/// Whether to perform a shallow clone (true) or deep clone (false). Defaults to true.
|
||||
/// Currently only shallow clone is supported.
|
||||
pub is_shallow: bool,
|
||||
/// Optional namespace client for managed versioning support.
|
||||
/// When set, enables the commit handler to track table versions through the namespace.
|
||||
pub namespace_client: Option<Arc<dyn LanceNamespace>>,
|
||||
}
|
||||
|
||||
impl CloneTableRequest {
|
||||
@@ -172,6 +180,7 @@ impl CloneTableRequest {
|
||||
source_version: None,
|
||||
source_tag: None,
|
||||
is_shallow: true,
|
||||
namespace_client: None,
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
@@ -669,6 +669,7 @@ impl ListingDatabase {
|
||||
lance_read_params: None,
|
||||
location: None,
|
||||
namespace_client: None,
|
||||
managed_versioning: None,
|
||||
};
|
||||
let req = (callback)(req);
|
||||
let table = self.open_table(req).await?;
|
||||
@@ -869,6 +870,7 @@ impl Database for ListingDatabase {
|
||||
Some(write_params),
|
||||
self.read_consistency_interval,
|
||||
request.namespace_client,
|
||||
false, // server_side_query_enabled - listing database doesn't support server-side queries
|
||||
)
|
||||
.await
|
||||
{
|
||||
@@ -946,7 +948,9 @@ impl Database for ListingDatabase {
|
||||
self.store_wrapper.clone(),
|
||||
None,
|
||||
self.read_consistency_interval,
|
||||
None,
|
||||
request.namespace_client,
|
||||
false, // server_side_query_enabled - listing database doesn't support server-side queries
|
||||
None, // managed_versioning - will be queried if namespace_client is provided
|
||||
)
|
||||
.await?;
|
||||
|
||||
@@ -1022,6 +1026,8 @@ impl Database for ListingDatabase {
|
||||
Some(read_params),
|
||||
self.read_consistency_interval,
|
||||
request.namespace_client,
|
||||
false, // server_side_query_enabled - listing database doesn't support server-side queries
|
||||
request.managed_versioning, // Pass through managed_versioning from request
|
||||
)
|
||||
.await?,
|
||||
);
|
||||
@@ -1162,6 +1168,7 @@ mod tests {
|
||||
source_version: None,
|
||||
source_tag: None,
|
||||
is_shallow: true,
|
||||
namespace_client: None,
|
||||
})
|
||||
.await
|
||||
.unwrap();
|
||||
@@ -1222,6 +1229,7 @@ mod tests {
|
||||
source_version: None,
|
||||
source_tag: None,
|
||||
is_shallow: true,
|
||||
namespace_client: None,
|
||||
})
|
||||
.await
|
||||
.unwrap();
|
||||
@@ -1281,6 +1289,7 @@ mod tests {
|
||||
source_version: None,
|
||||
source_tag: None,
|
||||
is_shallow: true,
|
||||
namespace_client: None,
|
||||
})
|
||||
.await;
|
||||
|
||||
@@ -1317,6 +1326,7 @@ mod tests {
|
||||
source_version: None,
|
||||
source_tag: None,
|
||||
is_shallow: false, // Request deep clone
|
||||
namespace_client: None,
|
||||
})
|
||||
.await;
|
||||
|
||||
@@ -1357,6 +1367,7 @@ mod tests {
|
||||
source_version: None,
|
||||
source_tag: None,
|
||||
is_shallow: true,
|
||||
namespace_client: None,
|
||||
})
|
||||
.await;
|
||||
|
||||
@@ -1397,6 +1408,7 @@ mod tests {
|
||||
source_version: None,
|
||||
source_tag: None,
|
||||
is_shallow: true,
|
||||
namespace_client: None,
|
||||
})
|
||||
.await;
|
||||
|
||||
@@ -1416,6 +1428,7 @@ mod tests {
|
||||
source_version: None,
|
||||
source_tag: None,
|
||||
is_shallow: true,
|
||||
namespace_client: None,
|
||||
})
|
||||
.await;
|
||||
|
||||
@@ -1452,6 +1465,7 @@ mod tests {
|
||||
source_version: Some(1),
|
||||
source_tag: Some("v1.0".to_string()),
|
||||
is_shallow: true,
|
||||
namespace_client: None,
|
||||
})
|
||||
.await;
|
||||
|
||||
@@ -1525,6 +1539,7 @@ mod tests {
|
||||
source_version: Some(initial_version),
|
||||
source_tag: None,
|
||||
is_shallow: true,
|
||||
namespace_client: None,
|
||||
})
|
||||
.await
|
||||
.unwrap();
|
||||
@@ -1603,6 +1618,7 @@ mod tests {
|
||||
source_version: None,
|
||||
source_tag: Some("v1.0".to_string()),
|
||||
is_shallow: true,
|
||||
namespace_client: None,
|
||||
})
|
||||
.await
|
||||
.unwrap();
|
||||
@@ -1654,6 +1670,7 @@ mod tests {
|
||||
source_version: None,
|
||||
source_tag: None,
|
||||
is_shallow: true,
|
||||
namespace_client: None,
|
||||
})
|
||||
.await
|
||||
.unwrap();
|
||||
@@ -1746,6 +1763,7 @@ mod tests {
|
||||
source_version: None,
|
||||
source_tag: None,
|
||||
is_shallow: true,
|
||||
namespace_client: None,
|
||||
})
|
||||
.await
|
||||
.unwrap();
|
||||
|
||||
@@ -7,18 +7,20 @@ use std::collections::HashMap;
|
||||
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_namespace::{
|
||||
LanceNamespace,
|
||||
models::{
|
||||
CreateEmptyTableRequest, CreateNamespaceRequest, CreateNamespaceResponse,
|
||||
DeclareTableRequest, DescribeNamespaceRequest, DescribeNamespaceResponse,
|
||||
DescribeTableRequest, DropNamespaceRequest, DropNamespaceResponse, DropTableRequest,
|
||||
ListNamespacesRequest, ListNamespacesResponse, ListTablesRequest, ListTablesResponse,
|
||||
CreateNamespaceRequest, CreateNamespaceResponse, DeclareTableRequest,
|
||||
DescribeNamespaceRequest, DescribeNamespaceResponse, DescribeTableRequest,
|
||||
DropNamespaceRequest, DropNamespaceResponse, DropTableRequest, ListNamespacesRequest,
|
||||
ListNamespacesResponse, ListTablesRequest, ListTablesResponse,
|
||||
},
|
||||
};
|
||||
use lance_namespace_impls::ConnectBuilder;
|
||||
use log::warn;
|
||||
use lance_table::io::commit::CommitHandler;
|
||||
use lance_table::io::commit::external_manifest::ExternalManifestCommitHandler;
|
||||
|
||||
use crate::database::ReadConsistency;
|
||||
use crate::error::{Error, Result};
|
||||
@@ -206,83 +208,48 @@ impl Database for LanceNamespaceDatabase {
|
||||
let mut table_id = request.namespace.clone();
|
||||
table_id.push(request.name.clone());
|
||||
|
||||
// Try declare_table first, falling back to create_empty_table for backwards
|
||||
// compatibility with older namespace clients that don't support declare_table
|
||||
let declare_request = DeclareTableRequest {
|
||||
id: Some(table_id.clone()),
|
||||
..Default::default()
|
||||
};
|
||||
|
||||
let (location, initial_storage_options) =
|
||||
match self.namespace.declare_table(declare_request).await {
|
||||
Ok(response) => {
|
||||
let loc = response.location.ok_or_else(|| Error::Runtime {
|
||||
message: "Table location is missing from declare_table response"
|
||||
.to_string(),
|
||||
})?;
|
||||
// Use storage options from response, fall back to self.storage_options
|
||||
let opts = response
|
||||
.storage_options
|
||||
.or_else(|| Some(self.storage_options.clone()))
|
||||
.filter(|o| !o.is_empty());
|
||||
(loc, opts)
|
||||
}
|
||||
Err(e) => {
|
||||
// Check if the error is "not supported" and try create_empty_table as fallback
|
||||
let err_str = e.to_string().to_lowercase();
|
||||
if err_str.contains("not supported") || err_str.contains("not implemented") {
|
||||
warn!(
|
||||
"declare_table is not supported by the namespace client, \
|
||||
falling back to deprecated create_empty_table. \
|
||||
create_empty_table is deprecated and will be removed in Lance 3.0.0. \
|
||||
Please upgrade your namespace client to support declare_table."
|
||||
);
|
||||
#[allow(deprecated)]
|
||||
let create_empty_request = CreateEmptyTableRequest {
|
||||
id: Some(table_id.clone()),
|
||||
..Default::default()
|
||||
};
|
||||
let (location, initial_storage_options, managed_versioning) = {
|
||||
let response = self.namespace.declare_table(declare_request).await?;
|
||||
let loc = response.location.ok_or_else(|| Error::Runtime {
|
||||
message: "Table location is missing from declare_table response".to_string(),
|
||||
})?;
|
||||
// Use storage options from response, fall back to self.storage_options
|
||||
let opts = response
|
||||
.storage_options
|
||||
.or_else(|| Some(self.storage_options.clone()))
|
||||
.filter(|o| !o.is_empty());
|
||||
(loc, opts, response.managed_versioning)
|
||||
};
|
||||
|
||||
#[allow(deprecated)]
|
||||
let create_response = self
|
||||
.namespace
|
||||
.create_empty_table(create_empty_request)
|
||||
.await
|
||||
.map_err(|e| Error::Runtime {
|
||||
message: format!("Failed to create empty table: {}", e),
|
||||
})?;
|
||||
// Build write params with storage options and commit handler
|
||||
let mut params = request.write_options.lance_write_params.unwrap_or_default();
|
||||
|
||||
let loc = create_response.location.ok_or_else(|| Error::Runtime {
|
||||
message: "Table location is missing from create_empty_table response"
|
||||
.to_string(),
|
||||
})?;
|
||||
// For deprecated path, use self.storage_options
|
||||
let opts = if self.storage_options.is_empty() {
|
||||
None
|
||||
} else {
|
||||
Some(self.storage_options.clone())
|
||||
};
|
||||
(loc, opts)
|
||||
} else {
|
||||
return Err(Error::Runtime {
|
||||
message: format!("Failed to declare table: {}", e),
|
||||
});
|
||||
}
|
||||
}
|
||||
};
|
||||
|
||||
let write_params = if let Some(storage_opts) = initial_storage_options {
|
||||
let mut params = request.write_options.lance_write_params.unwrap_or_default();
|
||||
// Set up storage options if provided
|
||||
if let Some(storage_opts) = initial_storage_options {
|
||||
let store_params = params
|
||||
.store_params
|
||||
.get_or_insert_with(ObjectStoreParams::default);
|
||||
store_params.storage_options_accessor = Some(Arc::new(
|
||||
StorageOptionsAccessor::with_static_options(storage_opts),
|
||||
));
|
||||
Some(params)
|
||||
} else {
|
||||
request.write_options.lance_write_params
|
||||
};
|
||||
}
|
||||
|
||||
// Set up commit handler when managed_versioning is enabled
|
||||
if managed_versioning == Some(true) {
|
||||
let external_store =
|
||||
LanceNamespaceExternalManifestStore::new(self.namespace.clone(), table_id.clone());
|
||||
let commit_handler: Arc<dyn CommitHandler> = Arc::new(ExternalManifestCommitHandler {
|
||||
external_manifest_store: Arc::new(external_store),
|
||||
});
|
||||
params.commit_handler = Some(commit_handler);
|
||||
}
|
||||
|
||||
let write_params = Some(params);
|
||||
|
||||
let native_table = NativeTable::create_from_namespace(
|
||||
self.namespace.clone(),
|
||||
|
||||
@@ -339,6 +339,12 @@ impl PermutationReader {
|
||||
}
|
||||
Ok(false)
|
||||
}
|
||||
Select::Expr(columns) => {
|
||||
// For Expr projections, we check if any alias is _rowid.
|
||||
// We can't validate the expression itself (it may differ from _rowid)
|
||||
// but we allow it through; the column will be included.
|
||||
Ok(columns.iter().any(|(alias, _)| alias == ROW_ID))
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
@@ -47,6 +47,25 @@ pub enum Select {
|
||||
///
|
||||
/// See [`Query::select`] for more details and examples
|
||||
Dynamic(Vec<(String, String)>),
|
||||
/// Advanced selection using type-safe DataFusion expressions
|
||||
///
|
||||
/// Similar to [`Select::Dynamic`] but uses [`datafusion_expr::Expr`] instead of
|
||||
/// raw SQL strings. Use [`crate::expr`] helpers to build expressions:
|
||||
///
|
||||
/// ```
|
||||
/// use lancedb::expr::{col, lit};
|
||||
/// use lancedb::query::Select;
|
||||
///
|
||||
/// // SELECT id, id * 2 AS id2 FROM ...
|
||||
/// let selection = Select::expr_projection(&[
|
||||
/// ("id", col("id")),
|
||||
/// ("id2", col("id") * lit(2)),
|
||||
/// ]);
|
||||
/// ```
|
||||
///
|
||||
/// Note: For remote/server-side queries the expressions are serialized to SQL strings
|
||||
/// automatically (same as [`Select::Dynamic`]).
|
||||
Expr(Vec<(String, datafusion_expr::Expr)>),
|
||||
}
|
||||
|
||||
impl Select {
|
||||
@@ -69,6 +88,29 @@ impl Select {
|
||||
.collect(),
|
||||
)
|
||||
}
|
||||
/// Create a typed-expression projection.
|
||||
///
|
||||
/// This is a convenience method for creating a [`Select::Expr`] variant from
|
||||
/// a slice of `(name, expr)` pairs where each `expr` is a [`datafusion_expr::Expr`].
|
||||
///
|
||||
/// # Example
|
||||
/// ```
|
||||
/// use lancedb::expr::{col, lit};
|
||||
/// use lancedb::query::Select;
|
||||
///
|
||||
/// let selection = Select::expr_projection(&[
|
||||
/// ("id", col("id")),
|
||||
/// ("id2", col("id") * lit(2)),
|
||||
/// ]);
|
||||
/// ```
|
||||
pub fn expr_projection(columns: &[(impl AsRef<str>, datafusion_expr::Expr)]) -> Self {
|
||||
Self::Expr(
|
||||
columns
|
||||
.iter()
|
||||
.map(|(name, expr)| (name.as_ref().to_string(), expr.clone()))
|
||||
.collect(),
|
||||
)
|
||||
}
|
||||
}
|
||||
|
||||
/// A trait for converting a type to a query vector
|
||||
@@ -1591,6 +1633,58 @@ mod tests {
|
||||
});
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn test_select_with_expr_projection() {
|
||||
// Mirrors test_select_with_transform but uses Select::Expr instead of Select::Dynamic
|
||||
let tmp_dir = tempdir().unwrap();
|
||||
let dataset_path = tmp_dir.path().join("test_expr.lance");
|
||||
let uri = dataset_path.to_str().unwrap();
|
||||
|
||||
let batches = make_non_empty_batches();
|
||||
let conn = connect(uri).execute().await.unwrap();
|
||||
let table = conn
|
||||
.create_table("my_table", batches)
|
||||
.execute()
|
||||
.await
|
||||
.unwrap();
|
||||
|
||||
use crate::expr::{col, lit};
|
||||
let query = table.query().limit(10).select(Select::expr_projection(&[
|
||||
("id2", col("id") * lit(2i32)),
|
||||
("id", col("id")),
|
||||
]));
|
||||
|
||||
let schema = query.output_schema().await.unwrap();
|
||||
assert_eq!(
|
||||
schema,
|
||||
Arc::new(ArrowSchema::new(vec![
|
||||
ArrowField::new("id2", DataType::Int32, true),
|
||||
ArrowField::new("id", DataType::Int32, true),
|
||||
]))
|
||||
);
|
||||
|
||||
let result = query.execute().await;
|
||||
let mut batches = result
|
||||
.expect("should have result")
|
||||
.try_collect::<Vec<_>>()
|
||||
.await
|
||||
.unwrap();
|
||||
assert_eq!(batches.len(), 1);
|
||||
let batch = batches.pop().unwrap();
|
||||
|
||||
// id and id2
|
||||
assert_eq!(batch.num_columns(), 2);
|
||||
|
||||
let id: &Int32Array = batch.column_by_name("id").unwrap().as_primitive();
|
||||
let id2: &Int32Array = batch.column_by_name("id2").unwrap().as_primitive();
|
||||
|
||||
id.iter().zip(id2.iter()).for_each(|(id, id2)| {
|
||||
let id = id.unwrap();
|
||||
let id2 = id2.unwrap();
|
||||
assert_eq!(id * 2, id2);
|
||||
});
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn test_execute_no_vector() {
|
||||
// TODO: Switch back to memory://foo after https://github.com/lancedb/lancedb/issues/1051
|
||||
|
||||
@@ -426,14 +426,11 @@ impl<S: HttpSend> RestfulLanceDbClient<S> {
|
||||
})?,
|
||||
);
|
||||
}
|
||||
if db_prefix.is_some() {
|
||||
if let Some(prefix) = db_prefix {
|
||||
headers.insert(
|
||||
HeaderName::from_static("x-lancedb-database-prefix"),
|
||||
HeaderValue::from_str(db_prefix.unwrap()).map_err(|_| Error::InvalidInput {
|
||||
message: format!(
|
||||
"non-ascii database prefix '{}' provided",
|
||||
db_prefix.unwrap()
|
||||
),
|
||||
HeaderValue::from_str(prefix).map_err(|_| Error::InvalidInput {
|
||||
message: format!("non-ascii database prefix '{}' provided", prefix),
|
||||
})?,
|
||||
);
|
||||
}
|
||||
|
||||
@@ -464,6 +464,7 @@ impl<S: HttpSend> Database for RemoteDatabase<S> {
|
||||
lance_read_params: None,
|
||||
location: None,
|
||||
namespace_client: None,
|
||||
managed_versioning: None,
|
||||
};
|
||||
let req = (callback)(req);
|
||||
self.open_table(req).await
|
||||
|
||||
@@ -477,6 +477,16 @@ impl<S: HttpSend> RemoteTable<S> {
|
||||
}));
|
||||
body["columns"] = alias_map.into();
|
||||
}
|
||||
Select::Expr(pairs) => {
|
||||
let alias_map: Result<serde_json::Map<String, serde_json::Value>> = pairs
|
||||
.iter()
|
||||
.map(|(name, expr)| {
|
||||
expr_to_sql_string(expr)
|
||||
.map(|sql| (name.clone(), serde_json::Value::String(sql)))
|
||||
})
|
||||
.collect();
|
||||
body["columns"] = alias_map?.into();
|
||||
}
|
||||
}
|
||||
|
||||
if params.fast_search {
|
||||
@@ -1645,10 +1655,33 @@ impl<S: HttpSend> BaseTable for RemoteTable<S> {
|
||||
Ok(())
|
||||
}
|
||||
|
||||
async fn prewarm_index(&self, _index_name: &str) -> Result<()> {
|
||||
Err(Error::NotSupported {
|
||||
message: "prewarm_index is not yet supported on LanceDB cloud.".into(),
|
||||
})
|
||||
async fn prewarm_index(&self, index_name: &str) -> Result<()> {
|
||||
let request = self.client.post(&format!(
|
||||
"/v1/table/{}/index/{}/prewarm/",
|
||||
self.identifier, index_name
|
||||
));
|
||||
let (request_id, response) = self.send(request, true).await?;
|
||||
if response.status() == StatusCode::NOT_FOUND {
|
||||
return Err(Error::IndexNotFound {
|
||||
name: index_name.to_string(),
|
||||
});
|
||||
}
|
||||
self.check_table_response(&request_id, response).await?;
|
||||
Ok(())
|
||||
}
|
||||
|
||||
async fn prewarm_data(&self, columns: Option<Vec<String>>) -> Result<()> {
|
||||
let mut request = self.client.post(&format!(
|
||||
"/v1/table/{}/page_cache/prewarm/",
|
||||
self.identifier
|
||||
));
|
||||
let body = serde_json::json!({
|
||||
"columns": columns.unwrap_or_default(),
|
||||
});
|
||||
request = request.json(&body);
|
||||
let (request_id, response) = self.send(request, true).await?;
|
||||
self.check_table_response(&request_id, response).await?;
|
||||
Ok(())
|
||||
}
|
||||
|
||||
async fn table_definition(&self) -> Result<TableDefinition> {
|
||||
@@ -3529,6 +3562,64 @@ mod tests {
|
||||
assert_eq!(result.version, if old_server { 0 } else { 43 });
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn test_prewarm_index() {
|
||||
let table = Table::new_with_handler("my_table", |request| {
|
||||
assert_eq!(request.method(), "POST");
|
||||
assert_eq!(
|
||||
request.url().path(),
|
||||
"/v1/table/my_table/index/my_index/prewarm/"
|
||||
);
|
||||
http::Response::builder().status(200).body("{}").unwrap()
|
||||
});
|
||||
table.prewarm_index("my_index").await.unwrap();
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn test_prewarm_index_not_found() {
|
||||
let table = Table::new_with_handler("my_table", |request| {
|
||||
assert_eq!(
|
||||
request.url().path(),
|
||||
"/v1/table/my_table/index/my_index/prewarm/"
|
||||
);
|
||||
http::Response::builder().status(404).body("{}").unwrap()
|
||||
});
|
||||
let e = table.prewarm_index("my_index").await.unwrap_err();
|
||||
assert!(matches!(e, Error::IndexNotFound { .. }));
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn test_prewarm_data() {
|
||||
let table = Table::new_with_handler("my_table", |request| {
|
||||
assert_eq!(request.method(), "POST");
|
||||
assert_eq!(
|
||||
request.url().path(),
|
||||
"/v1/table/my_table/page_cache/prewarm/"
|
||||
);
|
||||
http::Response::builder().status(200).body("{}").unwrap()
|
||||
});
|
||||
table.prewarm_data(None).await.unwrap();
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn test_prewarm_data_with_columns() {
|
||||
let table = Table::new_with_handler("my_table", |request| {
|
||||
assert_eq!(request.method(), "POST");
|
||||
assert_eq!(
|
||||
request.url().path(),
|
||||
"/v1/table/my_table/page_cache/prewarm/"
|
||||
);
|
||||
let body = request.body().unwrap().as_bytes().unwrap();
|
||||
let body: serde_json::Value = serde_json::from_slice(body).unwrap();
|
||||
assert_eq!(body["columns"], serde_json::json!(["col_a", "col_b"]));
|
||||
http::Response::builder().status(200).body("{}").unwrap()
|
||||
});
|
||||
table
|
||||
.prewarm_data(Some(vec!["col_a".into(), "col_b".into()]))
|
||||
.await
|
||||
.unwrap();
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn test_drop_index() {
|
||||
let table = Table::new_with_handler("my_table", |request| {
|
||||
|
||||
@@ -34,9 +34,13 @@ use lance_index::vector::sq::builder::SQBuildParams;
|
||||
use lance_io::object_store::{LanceNamespaceStorageOptionsProvider, StorageOptionsAccessor};
|
||||
pub use query::AnyQuery;
|
||||
|
||||
use lance::io::commit::namespace_manifest::LanceNamespaceExternalManifestStore;
|
||||
use lance_namespace::LanceNamespace;
|
||||
use lance_namespace::models::DescribeTableRequest;
|
||||
use lance_table::format::Manifest;
|
||||
use lance_table::io::commit::CommitHandler;
|
||||
use lance_table::io::commit::ManifestNamingScheme;
|
||||
use lance_table::io::commit::external_manifest::ExternalManifestCommitHandler;
|
||||
use serde::{Deserialize, Serialize};
|
||||
use std::collections::HashMap;
|
||||
use std::format;
|
||||
@@ -273,8 +277,13 @@ pub trait BaseTable: std::fmt::Display + std::fmt::Debug + Send + Sync {
|
||||
async fn list_indices(&self) -> Result<Vec<IndexConfig>>;
|
||||
/// Drop an index from the table.
|
||||
async fn drop_index(&self, name: &str) -> Result<()>;
|
||||
/// Prewarm an index in the table
|
||||
/// Prewarm an index in the table.
|
||||
async fn prewarm_index(&self, name: &str) -> Result<()>;
|
||||
/// Prewarm data for the table.
|
||||
///
|
||||
/// Currently only supported on remote tables.
|
||||
/// If `columns` is `None`, all columns are prewarmed.
|
||||
async fn prewarm_data(&self, columns: Option<Vec<String>>) -> Result<()>;
|
||||
/// Get statistics about the index.
|
||||
async fn index_stats(&self, index_name: &str) -> Result<Option<IndexStatistics>>;
|
||||
/// Merge insert new records into the table.
|
||||
@@ -942,17 +951,7 @@ impl Table {
|
||||
/// * Prune: Removes old versions of the dataset
|
||||
/// * Index: Optimizes the indices, adding new data to existing indices
|
||||
///
|
||||
/// <section class="warning">Experimental API</section>
|
||||
///
|
||||
/// The optimization process is undergoing active development and may change.
|
||||
/// Our goal with these changes is to improve the performance of optimization and
|
||||
/// reduce the complexity.
|
||||
///
|
||||
/// That being said, it is essential today to run optimize if you want the best
|
||||
/// performance. It should be stable and safe to use in production, but it our
|
||||
/// hope that the API may be simplified (or not even need to be called) in the future.
|
||||
///
|
||||
/// The frequency an application shoudl call optimize is based on the frequency of
|
||||
/// The frequency an application should call optimize is based on the frequency of
|
||||
/// data modifications. If data is frequently added, deleted, or updated then
|
||||
/// optimize should be run frequently. A good rule of thumb is to run optimize if
|
||||
/// you have added or modified 100,000 or more records or run more than 20 data
|
||||
@@ -1119,22 +1118,45 @@ impl Table {
|
||||
self.inner.drop_index(name).await
|
||||
}
|
||||
|
||||
/// Prewarm an index in the table
|
||||
/// Prewarm an index in the table.
|
||||
///
|
||||
/// This is a hint to fully load the index into memory. It can be used to
|
||||
/// avoid cold starts
|
||||
/// This is a hint to the database that the index will be accessed in the
|
||||
/// future and should be loaded into memory if possible. This can reduce
|
||||
/// cold-start latency for subsequent queries.
|
||||
///
|
||||
/// This call initiates prewarming and returns once the request is accepted.
|
||||
/// It is idempotent and safe to call from multiple clients concurrently.
|
||||
///
|
||||
/// It is generally wasteful to call this if the index does not fit into the
|
||||
/// available cache.
|
||||
///
|
||||
/// Note: This function is not yet supported on all indices, in which case it
|
||||
/// may do nothing.
|
||||
/// available cache. Not all index types support prewarming; unsupported
|
||||
/// indices will silently ignore the request.
|
||||
///
|
||||
/// Use [`Self::list_indices()`] to find the names of the indices.
|
||||
pub async fn prewarm_index(&self, name: &str) -> Result<()> {
|
||||
self.inner.prewarm_index(name).await
|
||||
}
|
||||
|
||||
/// Prewarm data for the table.
|
||||
///
|
||||
/// This is a hint to the database that the given columns will be accessed in
|
||||
/// the future and the database should prefetch the data if possible. This
|
||||
/// can reduce cold-start latency for subsequent queries. Currently only
|
||||
/// supported on remote tables.
|
||||
///
|
||||
/// This call initiates prewarming and returns once the request is accepted.
|
||||
/// It is idempotent and safe to call from multiple clients concurrently —
|
||||
/// calling it on already-prewarmed columns is a no-op on the server.
|
||||
///
|
||||
/// This operation has a large upfront cost but can speed up future queries
|
||||
/// that need to fetch the given columns. Large columns such as embeddings
|
||||
/// or binary data may not be practical to prewarm. This feature is intended
|
||||
/// for workloads that issue many queries against the same columns.
|
||||
///
|
||||
/// If `columns` is `None`, all columns are prewarmed.
|
||||
pub async fn prewarm_data(&self, columns: Option<Vec<String>>) -> Result<()> {
|
||||
self.inner.prewarm_data(columns).await
|
||||
}
|
||||
|
||||
/// Poll until the columns are fully indexed. Will return Error::Timeout if the columns
|
||||
/// are not fully indexed within the timeout.
|
||||
pub async fn wait_for_index(
|
||||
@@ -1212,10 +1234,13 @@ pub struct NativeTable {
|
||||
// This comes from the connection options. We store here so we can pass down
|
||||
// to the dataset when we recreate it (for example, in checkout_latest).
|
||||
read_consistency_interval: Option<std::time::Duration>,
|
||||
// Optional namespace client for server-side query execution.
|
||||
// When set, queries will be executed on the namespace server instead of locally.
|
||||
// pub (crate) namespace_client so query.rs can access the fields
|
||||
// Optional namespace client for namespace operations (e.g., managed versioning).
|
||||
// pub(crate) so query.rs can access the field for server-side query execution.
|
||||
pub(crate) namespace_client: Option<Arc<dyn LanceNamespace>>,
|
||||
// Whether to enable server-side query execution via the namespace client.
|
||||
// When true and namespace_client is set, queries will be executed on the
|
||||
// namespace server instead of locally.
|
||||
pub(crate) server_side_query_enabled: bool,
|
||||
}
|
||||
|
||||
impl std::fmt::Debug for NativeTable {
|
||||
@@ -1227,6 +1252,7 @@ impl std::fmt::Debug for NativeTable {
|
||||
.field("uri", &self.uri)
|
||||
.field("read_consistency_interval", &self.read_consistency_interval)
|
||||
.field("namespace_client", &self.namespace_client)
|
||||
.field("server_side_query_enabled", &self.server_side_query_enabled)
|
||||
.finish()
|
||||
}
|
||||
}
|
||||
@@ -1263,7 +1289,7 @@ impl NativeTable {
|
||||
/// * A [NativeTable] object.
|
||||
pub async fn open(uri: &str) -> Result<Self> {
|
||||
let name = Self::get_table_name(uri)?;
|
||||
Self::open_with_params(uri, &name, vec![], None, None, None, None).await
|
||||
Self::open_with_params(uri, &name, vec![], None, None, None, None, false, None).await
|
||||
}
|
||||
|
||||
/// Opens an existing Table
|
||||
@@ -1273,7 +1299,10 @@ impl NativeTable {
|
||||
/// * `base_path` - The base path where the table is located
|
||||
/// * `name` The Table name
|
||||
/// * `params` The [ReadParams] to use when opening the table
|
||||
/// * `namespace_client` - Optional namespace client for server-side query execution
|
||||
/// * `namespace_client` - Optional namespace client for namespace operations
|
||||
/// * `server_side_query_enabled` - Whether to enable server-side query execution
|
||||
/// * `managed_versioning` - Whether managed versioning is enabled. If None and namespace_client
|
||||
/// is provided, the value will be fetched via describe_table.
|
||||
///
|
||||
/// # Returns
|
||||
///
|
||||
@@ -1287,6 +1316,8 @@ impl NativeTable {
|
||||
params: Option<ReadParams>,
|
||||
read_consistency_interval: Option<std::time::Duration>,
|
||||
namespace_client: Option<Arc<dyn LanceNamespace>>,
|
||||
server_side_query_enabled: bool,
|
||||
managed_versioning: Option<bool>,
|
||||
) -> Result<Self> {
|
||||
let params = params.unwrap_or_default();
|
||||
// patch the params if we have a write store wrapper
|
||||
@@ -1295,17 +1326,54 @@ impl NativeTable {
|
||||
None => params,
|
||||
};
|
||||
|
||||
let dataset = DatasetBuilder::from_uri(uri)
|
||||
.with_read_params(params)
|
||||
.load()
|
||||
.await
|
||||
.map_err(|e| match e {
|
||||
lance::Error::DatasetNotFound { .. } => Error::TableNotFound {
|
||||
name: name.to_string(),
|
||||
source: Box::new(e),
|
||||
},
|
||||
e => e.into(),
|
||||
})?;
|
||||
// Build table_id from namespace + name
|
||||
let mut table_id = namespace.clone();
|
||||
table_id.push(name.to_string());
|
||||
|
||||
// Determine if managed_versioning is enabled
|
||||
// Use the provided value if available, otherwise query the namespace
|
||||
let managed_versioning = match managed_versioning {
|
||||
Some(value) => value,
|
||||
None if namespace_client.is_some() => {
|
||||
let ns_client = namespace_client.as_ref().unwrap();
|
||||
let describe_request = DescribeTableRequest {
|
||||
id: Some(table_id.clone()),
|
||||
..Default::default()
|
||||
};
|
||||
let response = ns_client
|
||||
.describe_table(describe_request)
|
||||
.await
|
||||
.map_err(|e| Error::Runtime {
|
||||
message: format!(
|
||||
"Failed to describe table via namespace client: {}. \
|
||||
If you don't need managed versioning, don't pass namespace_client.",
|
||||
e
|
||||
),
|
||||
})?;
|
||||
response.managed_versioning == Some(true)
|
||||
}
|
||||
None => false,
|
||||
};
|
||||
|
||||
let mut builder = DatasetBuilder::from_uri(uri).with_read_params(params);
|
||||
|
||||
// Set up commit handler when managed_versioning is enabled
|
||||
if managed_versioning && let Some(ref ns_client) = namespace_client {
|
||||
let external_store =
|
||||
LanceNamespaceExternalManifestStore::new(ns_client.clone(), table_id.clone());
|
||||
let commit_handler: Arc<dyn CommitHandler> = Arc::new(ExternalManifestCommitHandler {
|
||||
external_manifest_store: Arc::new(external_store),
|
||||
});
|
||||
builder = builder.with_commit_handler(commit_handler);
|
||||
}
|
||||
|
||||
let dataset = builder.load().await.map_err(|e| match e {
|
||||
lance::Error::DatasetNotFound { .. } => Error::TableNotFound {
|
||||
name: name.to_string(),
|
||||
source: Box::new(e),
|
||||
},
|
||||
e => e.into(),
|
||||
})?;
|
||||
|
||||
let dataset = DatasetConsistencyWrapper::new_latest(dataset, read_consistency_interval);
|
||||
let id = Self::build_id(&namespace, name);
|
||||
@@ -1318,6 +1386,7 @@ impl NativeTable {
|
||||
dataset,
|
||||
read_consistency_interval,
|
||||
namespace_client,
|
||||
server_side_query_enabled,
|
||||
})
|
||||
}
|
||||
|
||||
@@ -1421,6 +1490,7 @@ impl NativeTable {
|
||||
dataset,
|
||||
read_consistency_interval,
|
||||
namespace_client: stored_namespace_client,
|
||||
server_side_query_enabled,
|
||||
})
|
||||
}
|
||||
|
||||
@@ -1460,7 +1530,8 @@ impl NativeTable {
|
||||
/// * `namespace` - The namespace path. When non-empty, an explicit URI must be provided.
|
||||
/// * `batches` RecordBatch to be saved in the database.
|
||||
/// * `params` - Write parameters.
|
||||
/// * `namespace_client` - Optional namespace client for server-side query execution
|
||||
/// * `namespace_client` - Optional namespace client for namespace operations
|
||||
/// * `server_side_query_enabled` - Whether to enable server-side query execution
|
||||
///
|
||||
/// # Returns
|
||||
///
|
||||
@@ -1475,6 +1546,7 @@ impl NativeTable {
|
||||
params: Option<WriteParams>,
|
||||
read_consistency_interval: Option<std::time::Duration>,
|
||||
namespace_client: Option<Arc<dyn LanceNamespace>>,
|
||||
server_side_query_enabled: bool,
|
||||
) -> Result<Self> {
|
||||
// Default params uses format v1.
|
||||
let params = params.unwrap_or(WriteParams {
|
||||
@@ -1507,6 +1579,7 @@ impl NativeTable {
|
||||
dataset: DatasetConsistencyWrapper::new_latest(dataset, read_consistency_interval),
|
||||
read_consistency_interval,
|
||||
namespace_client,
|
||||
server_side_query_enabled,
|
||||
})
|
||||
}
|
||||
|
||||
@@ -1520,6 +1593,7 @@ impl NativeTable {
|
||||
params: Option<WriteParams>,
|
||||
read_consistency_interval: Option<std::time::Duration>,
|
||||
namespace_client: Option<Arc<dyn LanceNamespace>>,
|
||||
server_side_query_enabled: bool,
|
||||
) -> Result<Self> {
|
||||
let data: Box<dyn Scannable> = Box::new(RecordBatch::new_empty(schema));
|
||||
Self::create(
|
||||
@@ -1531,6 +1605,7 @@ impl NativeTable {
|
||||
params,
|
||||
read_consistency_interval,
|
||||
namespace_client,
|
||||
server_side_query_enabled,
|
||||
)
|
||||
.await
|
||||
}
|
||||
@@ -1634,6 +1709,7 @@ impl NativeTable {
|
||||
dataset: DatasetConsistencyWrapper::new_latest(dataset, read_consistency_interval),
|
||||
read_consistency_interval,
|
||||
namespace_client: stored_namespace_client,
|
||||
server_side_query_enabled,
|
||||
})
|
||||
}
|
||||
|
||||
@@ -2232,6 +2308,12 @@ impl BaseTable for NativeTable {
|
||||
Ok(dataset.prewarm_index(index_name).await?)
|
||||
}
|
||||
|
||||
async fn prewarm_data(&self, _columns: Option<Vec<String>>) -> Result<()> {
|
||||
Err(Error::NotSupported {
|
||||
message: "prewarm_data is currently only supported on remote tables.".into(),
|
||||
})
|
||||
}
|
||||
|
||||
async fn update(&self, update: UpdateBuilder) -> Result<UpdateResult> {
|
||||
// Delegate to the submodule implementation
|
||||
update::execute_update(self, update).await
|
||||
@@ -2625,7 +2707,7 @@ mod tests {
|
||||
vec![Ok(batch.clone())],
|
||||
batch.schema(),
|
||||
));
|
||||
let table = NativeTable::create(uri, "test", vec![], reader, None, None, None, None)
|
||||
let table = NativeTable::create(uri, "test", vec![], reader, None, None, None, None, false)
|
||||
.await
|
||||
.unwrap();
|
||||
|
||||
|
||||
@@ -3,12 +3,13 @@
|
||||
|
||||
use std::sync::Arc;
|
||||
|
||||
use arrow_cast::can_cast_types;
|
||||
use arrow_schema::{DataType, Field, FieldRef, Fields, Schema};
|
||||
use datafusion::functions::core::{get_field, named_struct};
|
||||
use datafusion_common::ScalarValue;
|
||||
use datafusion_common::config::ConfigOptions;
|
||||
use datafusion_physical_expr::ScalarFunctionExpr;
|
||||
use datafusion_physical_expr::expressions::{Literal, cast};
|
||||
use datafusion_physical_expr::expressions::{CastExpr, Literal};
|
||||
use datafusion_physical_plan::expressions::Column;
|
||||
use datafusion_physical_plan::projection::ProjectionExec;
|
||||
use datafusion_physical_plan::{ExecutionPlan, PhysicalExpr};
|
||||
@@ -25,12 +26,9 @@ pub fn cast_to_table_schema(
|
||||
return Ok(input);
|
||||
}
|
||||
|
||||
let exprs = build_field_exprs(
|
||||
input_schema.fields(),
|
||||
table_schema.fields(),
|
||||
&|idx| Arc::new(Column::new(input_schema.field(idx).name(), idx)) as Arc<dyn PhysicalExpr>,
|
||||
&input_schema,
|
||||
)?;
|
||||
let exprs = build_field_exprs(input_schema.fields(), table_schema.fields(), &|idx| {
|
||||
Arc::new(Column::new(input_schema.field(idx).name(), idx)) as Arc<dyn PhysicalExpr>
|
||||
})?;
|
||||
|
||||
let exprs: Vec<(Arc<dyn PhysicalExpr>, String)> = exprs
|
||||
.into_iter()
|
||||
@@ -51,7 +49,6 @@ fn build_field_exprs(
|
||||
input_fields: &Fields,
|
||||
table_fields: &Fields,
|
||||
get_input_expr: &dyn Fn(usize) -> Arc<dyn PhysicalExpr>,
|
||||
input_schema: &Schema,
|
||||
) -> Result<Vec<(Arc<dyn PhysicalExpr>, FieldRef)>> {
|
||||
let config = Arc::new(ConfigOptions::default());
|
||||
let mut result = Vec::new();
|
||||
@@ -72,24 +69,19 @@ fn build_field_exprs(
|
||||
(DataType::Struct(in_children), DataType::Struct(tbl_children))
|
||||
if in_children != tbl_children =>
|
||||
{
|
||||
let sub_exprs = build_field_exprs(
|
||||
in_children,
|
||||
tbl_children,
|
||||
&|child_idx| {
|
||||
let child_name = in_children[child_idx].name();
|
||||
Arc::new(ScalarFunctionExpr::new(
|
||||
&format!("get_field({child_name})"),
|
||||
get_field(),
|
||||
vec![
|
||||
input_expr.clone(),
|
||||
Arc::new(Literal::new(ScalarValue::from(child_name.as_str()))),
|
||||
],
|
||||
Arc::new(in_children[child_idx].as_ref().clone()),
|
||||
config.clone(),
|
||||
)) as Arc<dyn PhysicalExpr>
|
||||
},
|
||||
input_schema,
|
||||
)?;
|
||||
let sub_exprs = build_field_exprs(in_children, tbl_children, &|child_idx| {
|
||||
let child_name = in_children[child_idx].name();
|
||||
Arc::new(ScalarFunctionExpr::new(
|
||||
&format!("get_field({child_name})"),
|
||||
get_field(),
|
||||
vec![
|
||||
input_expr.clone(),
|
||||
Arc::new(Literal::new(ScalarValue::from(child_name.as_str()))),
|
||||
],
|
||||
Arc::new(in_children[child_idx].as_ref().clone()),
|
||||
config.clone(),
|
||||
)) as Arc<dyn PhysicalExpr>
|
||||
})?;
|
||||
|
||||
let output_struct_fields: Fields = sub_exprs
|
||||
.iter()
|
||||
@@ -125,17 +117,21 @@ fn build_field_exprs(
|
||||
// Types match: pass through.
|
||||
(inp, tbl) if inp == tbl => input_expr,
|
||||
// Types differ: cast.
|
||||
_ => cast(input_expr, input_schema, table_field.data_type().clone()).map_err(|e| {
|
||||
Error::InvalidInput {
|
||||
// safe: false (the default) means overflow/truncation errors surface at execution time.
|
||||
(_, _) if can_cast_types(input_field.data_type(), table_field.data_type()) => Arc::new(
|
||||
CastExpr::new(input_expr, table_field.data_type().clone(), None),
|
||||
)
|
||||
as Arc<dyn PhysicalExpr>,
|
||||
(inp, tbl) => {
|
||||
return Err(Error::InvalidInput {
|
||||
message: format!(
|
||||
"cannot cast field '{}' from {} to {}: {}",
|
||||
"cannot cast field '{}' from {} to {}",
|
||||
table_field.name(),
|
||||
input_field.data_type(),
|
||||
table_field.data_type(),
|
||||
e
|
||||
inp,
|
||||
tbl,
|
||||
),
|
||||
}
|
||||
})?,
|
||||
});
|
||||
}
|
||||
};
|
||||
|
||||
let output_field = Arc::new(Field::new(
|
||||
@@ -153,10 +149,12 @@ fn build_field_exprs(
|
||||
mod tests {
|
||||
use std::sync::Arc;
|
||||
|
||||
use arrow::buffer::OffsetBuffer;
|
||||
use arrow_array::{
|
||||
Float32Array, Float64Array, Int32Array, Int64Array, RecordBatch, StringArray, StructArray,
|
||||
Array, Float32Array, Float64Array, Int32Array, Int64Array, ListArray, RecordBatch,
|
||||
StringArray, StructArray, UInt32Array, UInt64Array,
|
||||
};
|
||||
use arrow_schema::{DataType, Field, Schema};
|
||||
use arrow_schema::{DataType, Field, Fields, Schema};
|
||||
use datafusion::prelude::SessionContext;
|
||||
use datafusion_catalog::MemTable;
|
||||
use futures::TryStreamExt;
|
||||
@@ -495,4 +493,129 @@ mod tests {
|
||||
assert_eq!(b.value(0), "hello");
|
||||
assert_eq!(b.value(1), "world");
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn test_narrowing_numeric_cast_success() {
|
||||
let input_batch = RecordBatch::try_new(
|
||||
Arc::new(Schema::new(vec![Field::new("a", DataType::UInt64, false)])),
|
||||
vec![Arc::new(UInt64Array::from(vec![1u64, 2, 3]))],
|
||||
)
|
||||
.unwrap();
|
||||
|
||||
let table_schema = Schema::new(vec![Field::new("a", DataType::UInt32, false)]);
|
||||
|
||||
let plan = plan_from_batch(input_batch).await;
|
||||
let casted = cast_to_table_schema(plan, &table_schema).unwrap();
|
||||
let result = collect(casted).await;
|
||||
|
||||
assert_eq!(result.schema().field(0).data_type(), &DataType::UInt32);
|
||||
let a: &UInt32Array = result.column(0).as_any().downcast_ref().unwrap();
|
||||
assert_eq!(a.values(), &[1u32, 2, 3]);
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn test_narrowing_numeric_cast_overflow_errors() {
|
||||
let overflow_val = u32::MAX as u64 + 1;
|
||||
let input_batch = RecordBatch::try_new(
|
||||
Arc::new(Schema::new(vec![Field::new("a", DataType::UInt64, false)])),
|
||||
vec![Arc::new(UInt64Array::from(vec![overflow_val]))],
|
||||
)
|
||||
.unwrap();
|
||||
|
||||
let table_schema = Schema::new(vec![Field::new("a", DataType::UInt32, false)]);
|
||||
|
||||
let plan = plan_from_batch(input_batch).await;
|
||||
// Planning succeeds — the overflow is only detected at execution time.
|
||||
let casted = cast_to_table_schema(plan, &table_schema).unwrap();
|
||||
|
||||
let ctx = SessionContext::new();
|
||||
let stream = casted.execute(0, ctx.task_ctx()).unwrap();
|
||||
let result: Result<Vec<RecordBatch>, _> = stream.try_collect().await;
|
||||
assert!(result.is_err(), "expected overflow error at execution time");
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn test_list_struct_field_reorder() {
|
||||
// list<struct<a: Int32, b: Int32>> → list<struct<b: Int64, a: Int64>>
|
||||
// Tests both reordering (a,b → b,a) and element-type widening (Int32 → Int64).
|
||||
let inner_fields: Fields = vec![
|
||||
Field::new("a", DataType::Int32, true),
|
||||
Field::new("b", DataType::Int32, true),
|
||||
]
|
||||
.into();
|
||||
let struct_array = StructArray::from(vec![
|
||||
(
|
||||
Arc::new(inner_fields[0].as_ref().clone()),
|
||||
Arc::new(Int32Array::from(vec![1, 3])) as _,
|
||||
),
|
||||
(
|
||||
Arc::new(inner_fields[1].as_ref().clone()),
|
||||
Arc::new(Int32Array::from(vec![2, 4])) as _,
|
||||
),
|
||||
]);
|
||||
// Offsets: one list element containing two struct rows (0..2).
|
||||
let offsets = OffsetBuffer::from_lengths(vec![2]);
|
||||
let list_array = ListArray::try_new(
|
||||
Arc::new(Field::new("item", DataType::Struct(inner_fields), true)),
|
||||
offsets,
|
||||
Arc::new(struct_array),
|
||||
None,
|
||||
)
|
||||
.unwrap();
|
||||
let input_batch = RecordBatch::try_new(
|
||||
Arc::new(Schema::new(vec![Field::new(
|
||||
"s_list",
|
||||
list_array.data_type().clone(),
|
||||
false,
|
||||
)])),
|
||||
vec![Arc::new(list_array)],
|
||||
)
|
||||
.unwrap();
|
||||
|
||||
let table_inner: Fields = vec![
|
||||
Field::new("b", DataType::Int64, true),
|
||||
Field::new("a", DataType::Int64, true),
|
||||
]
|
||||
.into();
|
||||
let table_schema = Schema::new(vec![Field::new(
|
||||
"s_list",
|
||||
DataType::List(Arc::new(Field::new(
|
||||
"item",
|
||||
DataType::Struct(table_inner),
|
||||
true,
|
||||
))),
|
||||
false,
|
||||
)]);
|
||||
|
||||
let plan = plan_from_batch(input_batch).await;
|
||||
let casted = cast_to_table_schema(plan, &table_schema).unwrap();
|
||||
let result = collect(casted).await;
|
||||
|
||||
let list_col = result
|
||||
.column(0)
|
||||
.as_any()
|
||||
.downcast_ref::<ListArray>()
|
||||
.unwrap();
|
||||
let struct_col = list_col
|
||||
.values()
|
||||
.as_any()
|
||||
.downcast_ref::<StructArray>()
|
||||
.unwrap();
|
||||
assert_eq!(struct_col.num_columns(), 2);
|
||||
|
||||
let b: &Int64Array = struct_col
|
||||
.column_by_name("b")
|
||||
.unwrap()
|
||||
.as_any()
|
||||
.downcast_ref()
|
||||
.unwrap();
|
||||
assert_eq!(b.values(), &[2, 4]);
|
||||
let a: &Int64Array = struct_col
|
||||
.column_by_name("a")
|
||||
.unwrap()
|
||||
.as_any()
|
||||
.downcast_ref()
|
||||
.unwrap();
|
||||
assert_eq!(a.values(), &[1, 3]);
|
||||
}
|
||||
}
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
use futures::FutureExt;
|
||||
// SPDX-License-Identifier: Apache-2.0
|
||||
// SPDX-FileCopyrightText: Copyright The LanceDB Authors
|
||||
use serde::{Deserialize, Serialize};
|
||||
@@ -23,7 +24,7 @@ pub struct DeleteResult {
|
||||
pub(crate) async fn execute_delete(table: &NativeTable, predicate: &str) -> Result<DeleteResult> {
|
||||
table.dataset.ensure_mutable()?;
|
||||
let mut dataset = (*table.dataset.get().await?).clone();
|
||||
let delete_result = dataset.delete(predicate).await?;
|
||||
let delete_result = dataset.delete(predicate).boxed().await?;
|
||||
let num_deleted_rows = delete_result.num_deleted_rows;
|
||||
let version = dataset.version().version;
|
||||
table.dataset.update(dataset);
|
||||
|
||||
@@ -64,6 +64,9 @@ pub enum OptimizeAction {
|
||||
older_than: Option<Duration>,
|
||||
/// Because they may be part of an in-progress transaction, files newer than 7 days old are not deleted by default.
|
||||
/// If you are sure that there are no in-progress transactions, then you can set this to True to delete all files older than `older_than`.
|
||||
///
|
||||
/// **WARNING**: This should only be set to true if you can guarantee that no other process is
|
||||
/// currently working on this dataset. Otherwise the dataset could be put into a corrupted state.
|
||||
delete_unverified: Option<bool>,
|
||||
/// If true, an error will be returned if there are any old versions that are still tagged.
|
||||
error_if_tagged_old_versions: Option<bool>,
|
||||
@@ -117,6 +120,10 @@ pub(crate) async fn optimize_indices(table: &NativeTable, options: &OptimizeOpti
|
||||
/// If you are sure that there are no in-progress transactions, then you
|
||||
/// can set this to True to delete all files older than `older_than`.
|
||||
///
|
||||
/// **WARNING**: This should only be set to true if you can guarantee that
|
||||
/// no other process is currently working on this dataset. Otherwise the
|
||||
/// dataset could be put into a corrupted state.
|
||||
///
|
||||
/// This calls into [lance::dataset::Dataset::cleanup_old_versions] and
|
||||
/// returns the result.
|
||||
pub(crate) async fn cleanup_old_versions(
|
||||
|
||||
@@ -40,8 +40,10 @@ pub async fn execute_query(
|
||||
query: &AnyQuery,
|
||||
options: QueryExecutionOptions,
|
||||
) -> Result<DatasetRecordBatchStream> {
|
||||
// If namespace client is configured, use server-side query execution
|
||||
if let Some(ref namespace_client) = table.namespace_client {
|
||||
// If server-side query is enabled and namespace client is configured, use server-side query execution
|
||||
if table.server_side_query_enabled
|
||||
&& let Some(ref namespace_client) = table.namespace_client
|
||||
{
|
||||
return execute_namespace_query(table, namespace_client.clone(), query, options).await;
|
||||
}
|
||||
execute_generic_query(table, query, options).await
|
||||
@@ -184,6 +186,13 @@ pub async fn create_plan(
|
||||
Select::Dynamic(ref select_with_transform) => {
|
||||
scanner.project_with_transform(select_with_transform.as_slice())?;
|
||||
}
|
||||
Select::Expr(ref expr_pairs) => {
|
||||
let sql_pairs: crate::Result<Vec<(String, String)>> = expr_pairs
|
||||
.iter()
|
||||
.map(|(name, expr)| expr_to_sql_string(expr).map(|sql| (name.clone(), sql)))
|
||||
.collect();
|
||||
scanner.project_with_transform(sql_pairs?.as_slice())?;
|
||||
}
|
||||
Select::All => {}
|
||||
}
|
||||
|
||||
@@ -338,6 +347,17 @@ fn convert_to_namespace_query(query: &AnyQuery) -> Result<NsQueryTableRequest> {
|
||||
.to_string(),
|
||||
});
|
||||
}
|
||||
Select::Expr(pairs) => {
|
||||
let sql_pairs: crate::Result<Vec<(String, String)>> = pairs
|
||||
.iter()
|
||||
.map(|(name, expr)| expr_to_sql_string(expr).map(|sql| (name.clone(), sql)))
|
||||
.collect();
|
||||
let sql_pairs = sql_pairs?;
|
||||
Some(Box::new(QueryTableRequestColumns {
|
||||
column_names: None,
|
||||
column_aliases: Some(sql_pairs.into_iter().collect()),
|
||||
}))
|
||||
}
|
||||
};
|
||||
|
||||
// Check for unsupported features
|
||||
@@ -409,6 +429,17 @@ fn convert_to_namespace_query(query: &AnyQuery) -> Result<NsQueryTableRequest> {
|
||||
.to_string(),
|
||||
});
|
||||
}
|
||||
Select::Expr(pairs) => {
|
||||
let sql_pairs: crate::Result<Vec<(String, String)>> = pairs
|
||||
.iter()
|
||||
.map(|(name, expr)| expr_to_sql_string(expr).map(|sql| (name.clone(), sql)))
|
||||
.collect();
|
||||
let sql_pairs = sql_pairs?;
|
||||
Some(Box::new(QueryTableRequestColumns {
|
||||
column_names: None,
|
||||
column_aliases: Some(sql_pairs.into_iter().collect()),
|
||||
}))
|
||||
}
|
||||
};
|
||||
|
||||
// Handle full text search if present
|
||||
|
||||
Reference in New Issue
Block a user