mirror of
https://github.com/lancedb/lancedb.git
synced 2026-03-27 19:10:40 +00:00
Compare commits
1 Commits
python-v0.
...
codex/upda
| Author | SHA1 | Date | |
|---|---|---|---|
|
422e10ba43 |
@@ -1,5 +1,5 @@
|
||||
[tool.bumpversion]
|
||||
current_version = "0.26.1"
|
||||
current_version = "0.25.0-beta.0"
|
||||
parse = """(?x)
|
||||
(?P<major>0|[1-9]\\d*)\\.
|
||||
(?P<minor>0|[1-9]\\d*)\\.
|
||||
|
||||
2
.github/workflows/cargo-publish.yml
vendored
2
.github/workflows/cargo-publish.yml
vendored
@@ -42,7 +42,7 @@ jobs:
|
||||
name: Report Workflow Failure
|
||||
runs-on: ubuntu-latest
|
||||
needs: [build]
|
||||
if: always() && failure() && startsWith(github.ref, 'refs/tags/v')
|
||||
if: always() && (github.event_name == 'release' || github.event_name == 'workflow_dispatch')
|
||||
permissions:
|
||||
contents: read
|
||||
issues: write
|
||||
|
||||
@@ -86,17 +86,16 @@ jobs:
|
||||
You are running inside the lancedb repository on a GitHub Actions runner. Update the Lance dependency to version ${VERSION} and prepare a pull request for maintainers to review.
|
||||
|
||||
Follow these steps exactly:
|
||||
1. Use script "ci/set_lance_version.py" to update Lance Rust dependencies. The script already refreshes Cargo metadata, so allow it to finish even if it takes time.
|
||||
2. Update the Java lance-core dependency version in "java/pom.xml": change the "<lance-core.version>...</lance-core.version>" property to "${VERSION}".
|
||||
3. Run "cargo clippy --workspace --tests --all-features -- -D warnings". If diagnostics appear, fix them yourself and rerun clippy until it exits cleanly. Do not skip any warnings.
|
||||
4. After clippy succeeds, run "cargo fmt --all" to format the workspace.
|
||||
5. Ensure the repository is clean except for intentional changes. Inspect "git status --short" and "git diff" to confirm the dependency update and any required fixes.
|
||||
6. Create and switch to a new branch named "${BRANCH_NAME}" (replace any duplicated hyphens if necessary).
|
||||
7. Stage all relevant files with "git add -A". Commit using the message "${COMMIT_TYPE}: update lance dependency to v${VERSION}".
|
||||
8. Push the branch to origin. If the remote branch already exists, delete it first with "gh api -X DELETE repos/lancedb/lancedb/git/refs/heads/${BRANCH_NAME}" then push with "git push origin ${BRANCH_NAME}". Do NOT use "git push --force" or "git push -f".
|
||||
9. env "GH_TOKEN" is available, use "gh" tools for github related operations like creating pull request.
|
||||
10. Create a pull request targeting "main" with title "${COMMIT_TYPE}: update lance dependency to v${VERSION}". First, write the PR body to /tmp/pr-body.md using a heredoc (cat <<'EOF' > /tmp/pr-body.md). The body should summarize the dependency bump, clippy/fmt verification, and link the triggering tag (${TAG}). Then run "gh pr create --body-file /tmp/pr-body.md".
|
||||
11. After creating the PR, display the PR URL, "git status --short", and a concise summary of the commands run and their results.
|
||||
1. Use script "ci/set_lance_version.py" to update Lance dependencies. The script already refreshes Cargo metadata, so allow it to finish even if it takes time.
|
||||
2. Run "cargo clippy --workspace --tests --all-features -- -D warnings". If diagnostics appear, fix them yourself and rerun clippy until it exits cleanly. Do not skip any warnings.
|
||||
3. After clippy succeeds, run "cargo fmt --all" to format the workspace.
|
||||
4. Ensure the repository is clean except for intentional changes. Inspect "git status --short" and "git diff" to confirm the dependency update and any required fixes.
|
||||
5. Create and switch to a new branch named "${BRANCH_NAME}" (replace any duplicated hyphens if necessary).
|
||||
6. Stage all relevant files with "git add -A". Commit using the message "${COMMIT_TYPE}: update lance dependency to v${VERSION}".
|
||||
7. Push the branch to origin. If the branch already exists, force-push your changes.
|
||||
8. env "GH_TOKEN" is available, use "gh" tools for github related operations like creating pull request.
|
||||
9. Create a pull request targeting "main" with title "${COMMIT_TYPE}: update lance dependency to v${VERSION}". First, write the PR body to /tmp/pr-body.md using a heredoc (cat <<'EOF' > /tmp/pr-body.md). The body should summarize the dependency bump, clippy/fmt verification, and link the triggering tag (${TAG}). Then run "gh pr create --body-file /tmp/pr-body.md".
|
||||
10. After creating the PR, display the PR URL, "git status --short", and a concise summary of the commands run and their results.
|
||||
|
||||
Constraints:
|
||||
- Use bash commands; avoid modifying GitHub workflow files other than through the scripted task above.
|
||||
|
||||
1
.github/workflows/nodejs.yml
vendored
1
.github/workflows/nodejs.yml
vendored
@@ -8,7 +8,6 @@ on:
|
||||
paths:
|
||||
- Cargo.toml
|
||||
- nodejs/**
|
||||
- docs/src/js/**
|
||||
- .github/workflows/nodejs.yml
|
||||
- docker-compose.yml
|
||||
|
||||
|
||||
6
.github/workflows/npm-publish.yml
vendored
6
.github/workflows/npm-publish.yml
vendored
@@ -318,7 +318,7 @@ jobs:
|
||||
- name: Setup node
|
||||
uses: actions/setup-node@v4
|
||||
with:
|
||||
node-version: 24
|
||||
node-version: 20
|
||||
cache: npm
|
||||
cache-dependency-path: nodejs/package-lock.json
|
||||
registry-url: "https://registry.npmjs.org"
|
||||
@@ -348,9 +348,9 @@ jobs:
|
||||
run: find npm
|
||||
- name: Publish
|
||||
env:
|
||||
NODE_AUTH_TOKEN: ${{ secrets.LANCEDB_NPM_REGISTRY_TOKEN }}
|
||||
DRY_RUN: ${{ !startsWith(github.ref, 'refs/tags/v') }}
|
||||
run: |
|
||||
npm config set provenance true
|
||||
ARGS="--access public"
|
||||
if [[ $DRY_RUN == "true" ]]; then
|
||||
ARGS="$ARGS --dry-run"
|
||||
@@ -363,7 +363,7 @@ jobs:
|
||||
name: Report Workflow Failure
|
||||
runs-on: ubuntu-latest
|
||||
needs: [build-lancedb, test-lancedb, publish]
|
||||
if: always() && failure() && startsWith(github.ref, 'refs/tags/v')
|
||||
if: always() && (github.event_name == 'release' || github.event_name == 'workflow_dispatch')
|
||||
permissions:
|
||||
contents: read
|
||||
issues: write
|
||||
|
||||
2
.github/workflows/pypi-publish.yml
vendored
2
.github/workflows/pypi-publish.yml
vendored
@@ -181,7 +181,7 @@ jobs:
|
||||
permissions:
|
||||
contents: read
|
||||
issues: write
|
||||
if: always() && failure() && startsWith(github.ref, 'refs/tags/python-v')
|
||||
if: always() && (github.event_name == 'release' || github.event_name == 'workflow_dispatch')
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
- uses: ./.github/actions/create-failure-issue
|
||||
|
||||
107
Cargo.lock
generated
107
Cargo.lock
generated
@@ -1389,9 +1389,9 @@ checksum = "1fd0f2584146f6f2ef48085050886acf353beff7305ebd1ae69500e27c67f64b"
|
||||
|
||||
[[package]]
|
||||
name = "bytes"
|
||||
version = "1.10.1"
|
||||
version = "1.11.1"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "d71b6127be86fdcfddb610f7182ac57211d4b18a3e9c82eb2d17662f2227ad6a"
|
||||
checksum = "1e748733b7cbc798e1434b6ac524f0c1ff2ab456fe201501e6497c8417a4fc33"
|
||||
|
||||
[[package]]
|
||||
name = "bytes-utils"
|
||||
@@ -1783,6 +1783,16 @@ dependencies = [
|
||||
"crossbeam-utils",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "crossbeam-skiplist"
|
||||
version = "0.1.3"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "df29de440c58ca2cc6e587ec3d22347551a32435fbde9d2bff64e78a9ffa151b"
|
||||
dependencies = [
|
||||
"crossbeam-epoch",
|
||||
"crossbeam-utils",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "crossbeam-utils"
|
||||
version = "0.8.21"
|
||||
@@ -3072,9 +3082,8 @@ checksum = "42703706b716c37f96a77aea830392ad231f44c9e9a67872fa5548707e11b11c"
|
||||
|
||||
[[package]]
|
||||
name = "fsst"
|
||||
version = "2.0.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "0f03a771ab914e207dd26bd2f12666839555ec8ecc7e1770e1ed6f9900d899a4"
|
||||
version = "3.0.0-beta.1"
|
||||
source = "git+https://github.com/lance-format/lance.git?tag=v3.0.0-beta.1#62e2ebbb83c680f64f455ac5252c95e80599eb59"
|
||||
dependencies = [
|
||||
"arrow-array",
|
||||
"rand 0.9.2",
|
||||
@@ -4405,9 +4414,8 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "lance"
|
||||
version = "2.0.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "47b685aca3f97ee02997c83ded16f59c747ccb69e74c8abbbae4aa3d22cf1301"
|
||||
version = "3.0.0-beta.1"
|
||||
source = "git+https://github.com/lance-format/lance.git?tag=v3.0.0-beta.1#62e2ebbb83c680f64f455ac5252c95e80599eb59"
|
||||
dependencies = [
|
||||
"arrow",
|
||||
"arrow-arith",
|
||||
@@ -4426,6 +4434,7 @@ dependencies = [
|
||||
"byteorder",
|
||||
"bytes",
|
||||
"chrono",
|
||||
"crossbeam-skiplist",
|
||||
"dashmap",
|
||||
"datafusion",
|
||||
"datafusion-expr",
|
||||
@@ -4465,6 +4474,7 @@ dependencies = [
|
||||
"tantivy",
|
||||
"tokio",
|
||||
"tokio-stream",
|
||||
"tokio-util",
|
||||
"tracing",
|
||||
"url",
|
||||
"uuid",
|
||||
@@ -4472,9 +4482,8 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "lance-arrow"
|
||||
version = "2.0.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "daf00c7537df524cc518a089f0d156a036d95ca3f5bc2bc1f0a9f9293e9b62ef"
|
||||
version = "3.0.0-beta.1"
|
||||
source = "git+https://github.com/lance-format/lance.git?tag=v3.0.0-beta.1#62e2ebbb83c680f64f455ac5252c95e80599eb59"
|
||||
dependencies = [
|
||||
"arrow-array",
|
||||
"arrow-buffer",
|
||||
@@ -4493,9 +4502,8 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "lance-bitpacking"
|
||||
version = "2.0.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "46752e4ac8fc5590a445e780b63a8800adc7a770bd74770a8dc66963778e4e77"
|
||||
version = "3.0.0-beta.1"
|
||||
source = "git+https://github.com/lance-format/lance.git?tag=v3.0.0-beta.1#62e2ebbb83c680f64f455ac5252c95e80599eb59"
|
||||
dependencies = [
|
||||
"arrayref",
|
||||
"paste",
|
||||
@@ -4504,9 +4512,8 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "lance-core"
|
||||
version = "2.0.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "3d13d87d07305c6d4b4dc7780fb1107babf782a0e5b1dc7872e17ae1f8fd11ca"
|
||||
version = "3.0.0-beta.1"
|
||||
source = "git+https://github.com/lance-format/lance.git?tag=v3.0.0-beta.1#62e2ebbb83c680f64f455ac5252c95e80599eb59"
|
||||
dependencies = [
|
||||
"arrow-array",
|
||||
"arrow-buffer",
|
||||
@@ -4543,9 +4550,8 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "lance-datafusion"
|
||||
version = "2.0.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "6451b5af876eaef8bec4b38a39dadac9d44621e1ecf85d0cdf6097a5d0aa8721"
|
||||
version = "3.0.0-beta.1"
|
||||
source = "git+https://github.com/lance-format/lance.git?tag=v3.0.0-beta.1#62e2ebbb83c680f64f455ac5252c95e80599eb59"
|
||||
dependencies = [
|
||||
"arrow",
|
||||
"arrow-array",
|
||||
@@ -4575,9 +4581,8 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "lance-datagen"
|
||||
version = "2.0.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "e1736708dd7867dfbab8fcc930b21c96717c6c00be73b7d9a240336a4ed80375"
|
||||
version = "3.0.0-beta.1"
|
||||
source = "git+https://github.com/lance-format/lance.git?tag=v3.0.0-beta.1#62e2ebbb83c680f64f455ac5252c95e80599eb59"
|
||||
dependencies = [
|
||||
"arrow",
|
||||
"arrow-array",
|
||||
@@ -4595,9 +4600,8 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "lance-encoding"
|
||||
version = "2.0.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "d6b6ca4ff94833240d5ba4a94a742cba786d1949b3c3fa7e11d6f0050443432a"
|
||||
version = "3.0.0-beta.1"
|
||||
source = "git+https://github.com/lance-format/lance.git?tag=v3.0.0-beta.1#62e2ebbb83c680f64f455ac5252c95e80599eb59"
|
||||
dependencies = [
|
||||
"arrow-arith",
|
||||
"arrow-array",
|
||||
@@ -4634,9 +4638,8 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "lance-file"
|
||||
version = "2.0.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "55fbe959bffe185543aed3cbeb14484f1aa2e55886034fdb1ea3d8cc9b70aad8"
|
||||
version = "3.0.0-beta.1"
|
||||
source = "git+https://github.com/lance-format/lance.git?tag=v3.0.0-beta.1#62e2ebbb83c680f64f455ac5252c95e80599eb59"
|
||||
dependencies = [
|
||||
"arrow-arith",
|
||||
"arrow-array",
|
||||
@@ -4668,9 +4671,8 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "lance-geo"
|
||||
version = "2.0.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "a52b0adabc953d457f336a784a3b37353a180e6a79905f544949746e0d4c6483"
|
||||
version = "3.0.0-beta.1"
|
||||
source = "git+https://github.com/lance-format/lance.git?tag=v3.0.0-beta.1#62e2ebbb83c680f64f455ac5252c95e80599eb59"
|
||||
dependencies = [
|
||||
"datafusion",
|
||||
"geo-traits",
|
||||
@@ -4684,9 +4686,8 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "lance-index"
|
||||
version = "2.0.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "6b67654bf86fd942dd2cf08294ee7e91053427cd148225f49c9ff398ff9a40fd"
|
||||
version = "3.0.0-beta.1"
|
||||
source = "git+https://github.com/lance-format/lance.git?tag=v3.0.0-beta.1#62e2ebbb83c680f64f455ac5252c95e80599eb59"
|
||||
dependencies = [
|
||||
"arrow",
|
||||
"arrow-arith",
|
||||
@@ -4753,9 +4754,8 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "lance-io"
|
||||
version = "2.0.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "8eb0ccc1c414e31687d83992d546af0a0237c8d2f4bf2ae3d347d539fd0fc141"
|
||||
version = "3.0.0-beta.1"
|
||||
source = "git+https://github.com/lance-format/lance.git?tag=v3.0.0-beta.1#62e2ebbb83c680f64f455ac5252c95e80599eb59"
|
||||
dependencies = [
|
||||
"arrow",
|
||||
"arrow-arith",
|
||||
@@ -4795,9 +4795,8 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "lance-linalg"
|
||||
version = "2.0.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "083404cf12dcdb1a7df98fb58f9daf626b6e43a2f794b37b6b89b4012a0e1f78"
|
||||
version = "3.0.0-beta.1"
|
||||
source = "git+https://github.com/lance-format/lance.git?tag=v3.0.0-beta.1#62e2ebbb83c680f64f455ac5252c95e80599eb59"
|
||||
dependencies = [
|
||||
"arrow-array",
|
||||
"arrow-buffer",
|
||||
@@ -4813,9 +4812,8 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "lance-namespace"
|
||||
version = "2.0.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "c12778d2aabf9c2bfd16e2509ebe120e562a288d8ae630ec6b6b204868df41b2"
|
||||
version = "3.0.0-beta.1"
|
||||
source = "git+https://github.com/lance-format/lance.git?tag=v3.0.0-beta.1#62e2ebbb83c680f64f455ac5252c95e80599eb59"
|
||||
dependencies = [
|
||||
"arrow",
|
||||
"async-trait",
|
||||
@@ -4827,9 +4825,8 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "lance-namespace-impls"
|
||||
version = "2.0.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "8863aababdd13a6d2c8d6179dc6981f4f8f49d8b66a00c5dd75115aec4cadc99"
|
||||
version = "3.0.0-beta.1"
|
||||
source = "git+https://github.com/lance-format/lance.git?tag=v3.0.0-beta.1#62e2ebbb83c680f64f455ac5252c95e80599eb59"
|
||||
dependencies = [
|
||||
"arrow",
|
||||
"arrow-ipc",
|
||||
@@ -4872,9 +4869,8 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "lance-table"
|
||||
version = "2.0.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "f0fcc83f197ce2000c4abe4f5e0873490ab1f41788fa76571c4209b87d4daf50"
|
||||
version = "3.0.0-beta.1"
|
||||
source = "git+https://github.com/lance-format/lance.git?tag=v3.0.0-beta.1#62e2ebbb83c680f64f455ac5252c95e80599eb59"
|
||||
dependencies = [
|
||||
"arrow",
|
||||
"arrow-array",
|
||||
@@ -4913,9 +4909,8 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "lance-testing"
|
||||
version = "2.0.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "7fb1f7c7e06f91360e141ecee1cf2110f858c231705f69f2cd2fda9e30c1e9f4"
|
||||
version = "3.0.0-beta.1"
|
||||
source = "git+https://github.com/lance-format/lance.git?tag=v3.0.0-beta.1#62e2ebbb83c680f64f455ac5252c95e80599eb59"
|
||||
dependencies = [
|
||||
"arrow-array",
|
||||
"arrow-schema",
|
||||
@@ -4926,7 +4921,7 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "lancedb"
|
||||
version = "0.26.1"
|
||||
version = "0.25.0-beta.0"
|
||||
dependencies = [
|
||||
"ahash",
|
||||
"anyhow",
|
||||
@@ -5006,7 +5001,7 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "lancedb-nodejs"
|
||||
version = "0.26.1"
|
||||
version = "0.25.0-beta.0"
|
||||
dependencies = [
|
||||
"arrow-array",
|
||||
"arrow-ipc",
|
||||
@@ -5026,7 +5021,7 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "lancedb-python"
|
||||
version = "0.29.1"
|
||||
version = "0.27.0"
|
||||
dependencies = [
|
||||
"arrow",
|
||||
"async-trait",
|
||||
|
||||
28
Cargo.toml
28
Cargo.toml
@@ -15,20 +15,20 @@ categories = ["database-implementations"]
|
||||
rust-version = "1.88.0"
|
||||
|
||||
[workspace.dependencies]
|
||||
lance = { "version" = "=2.0.0", default-features = false }
|
||||
lance-core = "=2.0.0"
|
||||
lance-datagen = "=2.0.0"
|
||||
lance-file = "=2.0.0"
|
||||
lance-io = { "version" = "=2.0.0", default-features = false }
|
||||
lance-index = "=2.0.0"
|
||||
lance-linalg = "=2.0.0"
|
||||
lance-namespace = "=2.0.0"
|
||||
lance-namespace-impls = { "version" = "=2.0.0", default-features = false }
|
||||
lance-table = "=2.0.0"
|
||||
lance-testing = "=2.0.0"
|
||||
lance-datafusion = "=2.0.0"
|
||||
lance-encoding = "=2.0.0"
|
||||
lance-arrow = "=2.0.0"
|
||||
lance = { "version" = "=3.0.0-beta.1", default-features = false, "tag" = "v3.0.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-core = { "version" = "=3.0.0-beta.1", "tag" = "v3.0.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-datagen = { "version" = "=3.0.0-beta.1", "tag" = "v3.0.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-file = { "version" = "=3.0.0-beta.1", "tag" = "v3.0.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-io = { "version" = "=3.0.0-beta.1", default-features = false, "tag" = "v3.0.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-index = { "version" = "=3.0.0-beta.1", "tag" = "v3.0.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-linalg = { "version" = "=3.0.0-beta.1", "tag" = "v3.0.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-namespace = { "version" = "=3.0.0-beta.1", "tag" = "v3.0.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-namespace-impls = { "version" = "=3.0.0-beta.1", default-features = false, "tag" = "v3.0.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-table = { "version" = "=3.0.0-beta.1", "tag" = "v3.0.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-testing = { "version" = "=3.0.0-beta.1", "tag" = "v3.0.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-datafusion = { "version" = "=3.0.0-beta.1", "tag" = "v3.0.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-encoding = { "version" = "=3.0.0-beta.1", "tag" = "v3.0.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-arrow = { "version" = "=3.0.0-beta.1", "tag" = "v3.0.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
|
||||
ahash = "0.8"
|
||||
# Note that this one does not include pyarrow
|
||||
arrow = { version = "57.2", optional = false }
|
||||
|
||||
@@ -14,7 +14,7 @@ Add the following dependency to your `pom.xml`:
|
||||
<dependency>
|
||||
<groupId>com.lancedb</groupId>
|
||||
<artifactId>lancedb-core</artifactId>
|
||||
<version>0.26.1</version>
|
||||
<version>0.25.0-beta.0</version>
|
||||
</dependency>
|
||||
```
|
||||
|
||||
|
||||
@@ -367,27 +367,6 @@ Use [Table.listIndices](Table.md#listindices) to find the names of the indices.
|
||||
|
||||
***
|
||||
|
||||
### initialStorageOptions()
|
||||
|
||||
```ts
|
||||
abstract initialStorageOptions(): Promise<undefined | null | Record<string, string>>
|
||||
```
|
||||
|
||||
Get the initial storage options that were passed in when opening this table.
|
||||
|
||||
For dynamically refreshed options (e.g., credential vending), use
|
||||
[Table.latestStorageOptions](Table.md#lateststorageoptions).
|
||||
|
||||
Warning: This is an internal API and the return value is subject to change.
|
||||
|
||||
#### Returns
|
||||
|
||||
`Promise`<`undefined` \| `null` \| `Record`<`string`, `string`>>
|
||||
|
||||
The storage options, or undefined if no storage options were configured.
|
||||
|
||||
***
|
||||
|
||||
### isOpen()
|
||||
|
||||
```ts
|
||||
@@ -402,28 +381,6 @@ Return true if the table has not been closed
|
||||
|
||||
***
|
||||
|
||||
### latestStorageOptions()
|
||||
|
||||
```ts
|
||||
abstract latestStorageOptions(): Promise<undefined | null | Record<string, string>>
|
||||
```
|
||||
|
||||
Get the latest storage options, refreshing from provider if configured.
|
||||
|
||||
This method is useful for credential vending scenarios where storage options
|
||||
may be refreshed dynamically. If no dynamic provider is configured, this
|
||||
returns the initial static options.
|
||||
|
||||
Warning: This is an internal API and the return value is subject to change.
|
||||
|
||||
#### Returns
|
||||
|
||||
`Promise`<`undefined` \| `null` \| `Record`<`string`, `string`>>
|
||||
|
||||
The storage options, or undefined if no storage options were configured.
|
||||
|
||||
***
|
||||
|
||||
### listIndices()
|
||||
|
||||
```ts
|
||||
|
||||
@@ -8,7 +8,7 @@
|
||||
<parent>
|
||||
<groupId>com.lancedb</groupId>
|
||||
<artifactId>lancedb-parent</artifactId>
|
||||
<version>0.26.1-final.0</version>
|
||||
<version>0.25.0-beta.0</version>
|
||||
<relativePath>../pom.xml</relativePath>
|
||||
</parent>
|
||||
|
||||
|
||||
@@ -6,7 +6,7 @@
|
||||
|
||||
<groupId>com.lancedb</groupId>
|
||||
<artifactId>lancedb-parent</artifactId>
|
||||
<version>0.26.1-final.0</version>
|
||||
<version>0.25.0-beta.0</version>
|
||||
<packaging>pom</packaging>
|
||||
<name>${project.artifactId}</name>
|
||||
<description>LanceDB Java SDK Parent POM</description>
|
||||
@@ -28,7 +28,7 @@
|
||||
<properties>
|
||||
<project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
|
||||
<arrow.version>15.0.0</arrow.version>
|
||||
<lance-core.version>2.0.0</lance-core.version>
|
||||
<lance-core.version>1.0.4</lance-core.version>
|
||||
<spotless.skip>false</spotless.skip>
|
||||
<spotless.version>2.30.0</spotless.version>
|
||||
<spotless.java.googlejavaformat.version>1.7</spotless.java.googlejavaformat.version>
|
||||
@@ -292,12 +292,11 @@
|
||||
<plugin>
|
||||
<groupId>org.sonatype.central</groupId>
|
||||
<artifactId>central-publishing-maven-plugin</artifactId>
|
||||
<version>0.8.0</version>
|
||||
<version>0.4.0</version>
|
||||
<extensions>true</extensions>
|
||||
<configuration>
|
||||
<publishingServerId>ossrh</publishingServerId>
|
||||
<tokenAuth>true</tokenAuth>
|
||||
<autoPublish>true</autoPublish>
|
||||
</configuration>
|
||||
</plugin>
|
||||
<plugin>
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
[package]
|
||||
name = "lancedb-nodejs"
|
||||
edition.workspace = true
|
||||
version = "0.26.1"
|
||||
version = "0.25.0-beta.0"
|
||||
license.workspace = true
|
||||
description.workspace = true
|
||||
repository.workspace = true
|
||||
|
||||
@@ -542,35 +542,6 @@ export abstract class Table {
|
||||
*
|
||||
*/
|
||||
abstract stats(): Promise<TableStatistics>;
|
||||
|
||||
/**
|
||||
* Get the initial storage options that were passed in when opening this table.
|
||||
*
|
||||
* For dynamically refreshed options (e.g., credential vending), use
|
||||
* {@link Table.latestStorageOptions}.
|
||||
*
|
||||
* Warning: This is an internal API and the return value is subject to change.
|
||||
*
|
||||
* @returns The storage options, or undefined if no storage options were configured.
|
||||
*/
|
||||
abstract initialStorageOptions(): Promise<
|
||||
Record<string, string> | null | undefined
|
||||
>;
|
||||
|
||||
/**
|
||||
* Get the latest storage options, refreshing from provider if configured.
|
||||
*
|
||||
* This method is useful for credential vending scenarios where storage options
|
||||
* may be refreshed dynamically. If no dynamic provider is configured, this
|
||||
* returns the initial static options.
|
||||
*
|
||||
* Warning: This is an internal API and the return value is subject to change.
|
||||
*
|
||||
* @returns The storage options, or undefined if no storage options were configured.
|
||||
*/
|
||||
abstract latestStorageOptions(): Promise<
|
||||
Record<string, string> | null | undefined
|
||||
>;
|
||||
}
|
||||
|
||||
export class LocalTable extends Table {
|
||||
@@ -907,18 +878,6 @@ export class LocalTable extends Table {
|
||||
return await this.inner.stats();
|
||||
}
|
||||
|
||||
async initialStorageOptions(): Promise<
|
||||
Record<string, string> | null | undefined
|
||||
> {
|
||||
return await this.inner.initialStorageOptions();
|
||||
}
|
||||
|
||||
async latestStorageOptions(): Promise<
|
||||
Record<string, string> | null | undefined
|
||||
> {
|
||||
return await this.inner.latestStorageOptions();
|
||||
}
|
||||
|
||||
mergeInsert(on: string | string[]): MergeInsertBuilder {
|
||||
on = Array.isArray(on) ? on : [on];
|
||||
return new MergeInsertBuilder(this.inner.mergeInsert(on), this.schema());
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"name": "@lancedb/lancedb-darwin-arm64",
|
||||
"version": "0.26.1",
|
||||
"version": "0.25.0-beta.0",
|
||||
"os": ["darwin"],
|
||||
"cpu": ["arm64"],
|
||||
"main": "lancedb.darwin-arm64.node",
|
||||
@@ -8,9 +8,5 @@
|
||||
"license": "Apache-2.0",
|
||||
"engines": {
|
||||
"node": ">= 18"
|
||||
},
|
||||
"repository": {
|
||||
"type": "git",
|
||||
"url": "https://github.com/lancedb/lancedb"
|
||||
}
|
||||
}
|
||||
|
||||
3
nodejs/npm/darwin-x64/README.md
Normal file
3
nodejs/npm/darwin-x64/README.md
Normal file
@@ -0,0 +1,3 @@
|
||||
# `@lancedb/lancedb-darwin-x64`
|
||||
|
||||
This is the **x86_64-apple-darwin** binary for `@lancedb/lancedb`
|
||||
12
nodejs/npm/darwin-x64/package.json
Normal file
12
nodejs/npm/darwin-x64/package.json
Normal file
@@ -0,0 +1,12 @@
|
||||
{
|
||||
"name": "@lancedb/lancedb-darwin-x64",
|
||||
"version": "0.25.0-beta.0",
|
||||
"os": ["darwin"],
|
||||
"cpu": ["x64"],
|
||||
"main": "lancedb.darwin-x64.node",
|
||||
"files": ["lancedb.darwin-x64.node"],
|
||||
"license": "Apache-2.0",
|
||||
"engines": {
|
||||
"node": ">= 18"
|
||||
}
|
||||
}
|
||||
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"name": "@lancedb/lancedb-linux-arm64-gnu",
|
||||
"version": "0.26.1",
|
||||
"version": "0.25.0-beta.0",
|
||||
"os": ["linux"],
|
||||
"cpu": ["arm64"],
|
||||
"main": "lancedb.linux-arm64-gnu.node",
|
||||
@@ -9,9 +9,5 @@
|
||||
"engines": {
|
||||
"node": ">= 18"
|
||||
},
|
||||
"libc": ["glibc"],
|
||||
"repository": {
|
||||
"type": "git",
|
||||
"url": "https://github.com/lancedb/lancedb"
|
||||
}
|
||||
"libc": ["glibc"]
|
||||
}
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"name": "@lancedb/lancedb-linux-arm64-musl",
|
||||
"version": "0.26.1",
|
||||
"version": "0.25.0-beta.0",
|
||||
"os": ["linux"],
|
||||
"cpu": ["arm64"],
|
||||
"main": "lancedb.linux-arm64-musl.node",
|
||||
@@ -9,9 +9,5 @@
|
||||
"engines": {
|
||||
"node": ">= 18"
|
||||
},
|
||||
"libc": ["musl"],
|
||||
"repository": {
|
||||
"type": "git",
|
||||
"url": "https://github.com/lancedb/lancedb"
|
||||
}
|
||||
"libc": ["musl"]
|
||||
}
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"name": "@lancedb/lancedb-linux-x64-gnu",
|
||||
"version": "0.26.1",
|
||||
"version": "0.25.0-beta.0",
|
||||
"os": ["linux"],
|
||||
"cpu": ["x64"],
|
||||
"main": "lancedb.linux-x64-gnu.node",
|
||||
@@ -9,9 +9,5 @@
|
||||
"engines": {
|
||||
"node": ">= 18"
|
||||
},
|
||||
"libc": ["glibc"],
|
||||
"repository": {
|
||||
"type": "git",
|
||||
"url": "https://github.com/lancedb/lancedb"
|
||||
}
|
||||
"libc": ["glibc"]
|
||||
}
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"name": "@lancedb/lancedb-linux-x64-musl",
|
||||
"version": "0.26.1",
|
||||
"version": "0.25.0-beta.0",
|
||||
"os": ["linux"],
|
||||
"cpu": ["x64"],
|
||||
"main": "lancedb.linux-x64-musl.node",
|
||||
@@ -9,9 +9,5 @@
|
||||
"engines": {
|
||||
"node": ">= 18"
|
||||
},
|
||||
"libc": ["musl"],
|
||||
"repository": {
|
||||
"type": "git",
|
||||
"url": "https://github.com/lancedb/lancedb"
|
||||
}
|
||||
"libc": ["musl"]
|
||||
}
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"name": "@lancedb/lancedb-win32-arm64-msvc",
|
||||
"version": "0.26.1",
|
||||
"version": "0.25.0-beta.0",
|
||||
"os": [
|
||||
"win32"
|
||||
],
|
||||
@@ -14,9 +14,5 @@
|
||||
"license": "Apache-2.0",
|
||||
"engines": {
|
||||
"node": ">= 18"
|
||||
},
|
||||
"repository": {
|
||||
"type": "git",
|
||||
"url": "https://github.com/lancedb/lancedb"
|
||||
}
|
||||
}
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"name": "@lancedb/lancedb-win32-x64-msvc",
|
||||
"version": "0.26.1",
|
||||
"version": "0.25.0-beta.0",
|
||||
"os": ["win32"],
|
||||
"cpu": ["x64"],
|
||||
"main": "lancedb.win32-x64-msvc.node",
|
||||
@@ -8,9 +8,5 @@
|
||||
"license": "Apache-2.0",
|
||||
"engines": {
|
||||
"node": ">= 18"
|
||||
},
|
||||
"repository": {
|
||||
"type": "git",
|
||||
"url": "https://github.com/lancedb/lancedb"
|
||||
}
|
||||
}
|
||||
|
||||
4
nodejs/package-lock.json
generated
4
nodejs/package-lock.json
generated
@@ -1,12 +1,12 @@
|
||||
{
|
||||
"name": "@lancedb/lancedb",
|
||||
"version": "0.26.1",
|
||||
"version": "0.25.0-beta.0",
|
||||
"lockfileVersion": 3,
|
||||
"requires": true,
|
||||
"packages": {
|
||||
"": {
|
||||
"name": "@lancedb/lancedb",
|
||||
"version": "0.26.1",
|
||||
"version": "0.25.0-beta.0",
|
||||
"cpu": [
|
||||
"x64",
|
||||
"arm64"
|
||||
|
||||
@@ -11,7 +11,7 @@
|
||||
"ann"
|
||||
],
|
||||
"private": false,
|
||||
"version": "0.26.1",
|
||||
"version": "0.25.0-beta.0",
|
||||
"main": "dist/index.js",
|
||||
"exports": {
|
||||
".": "./dist/index.js",
|
||||
@@ -25,6 +25,7 @@
|
||||
"triples": {
|
||||
"defaults": false,
|
||||
"additional": [
|
||||
"x86_64-apple-darwin",
|
||||
"aarch64-apple-darwin",
|
||||
"x86_64-unknown-linux-gnu",
|
||||
"aarch64-unknown-linux-gnu",
|
||||
@@ -36,10 +37,6 @@
|
||||
}
|
||||
},
|
||||
"license": "Apache-2.0",
|
||||
"repository": {
|
||||
"type": "git",
|
||||
"url": "https://github.com/lancedb/lancedb"
|
||||
},
|
||||
"devDependencies": {
|
||||
"@aws-sdk/client-dynamodb": "^3.33.0",
|
||||
"@aws-sdk/client-kms": "^3.33.0",
|
||||
|
||||
@@ -166,19 +166,6 @@ impl Table {
|
||||
Ok(stats.into())
|
||||
}
|
||||
|
||||
#[napi(catch_unwind)]
|
||||
pub async fn initial_storage_options(&self) -> napi::Result<Option<HashMap<String, String>>> {
|
||||
Ok(self.inner_ref()?.initial_storage_options().await)
|
||||
}
|
||||
|
||||
#[napi(catch_unwind)]
|
||||
pub async fn latest_storage_options(&self) -> napi::Result<Option<HashMap<String, String>>> {
|
||||
self.inner_ref()?
|
||||
.latest_storage_options()
|
||||
.await
|
||||
.default_error()
|
||||
}
|
||||
|
||||
#[napi(catch_unwind)]
|
||||
pub async fn update(
|
||||
&self,
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
[tool.bumpversion]
|
||||
current_version = "0.29.2"
|
||||
current_version = "0.28.0-beta.0"
|
||||
parse = """(?x)
|
||||
(?P<major>0|[1-9]\\d*)\\.
|
||||
(?P<minor>0|[1-9]\\d*)\\.
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
[package]
|
||||
name = "lancedb-python"
|
||||
version = "0.29.2"
|
||||
version = "0.27.0"
|
||||
edition.workspace = true
|
||||
description = "Python bindings for LanceDB"
|
||||
license.workspace = true
|
||||
|
||||
@@ -180,8 +180,6 @@ class Table:
|
||||
delete_unverified: Optional[bool] = None,
|
||||
) -> OptimizeStats: ...
|
||||
async def uri(self) -> str: ...
|
||||
async def initial_storage_options(self) -> Optional[Dict[str, str]]: ...
|
||||
async def latest_storage_options(self) -> Optional[Dict[str, str]]: ...
|
||||
@property
|
||||
def tags(self) -> Tags: ...
|
||||
def query(self) -> Query: ...
|
||||
|
||||
@@ -2222,37 +2222,6 @@ class LanceTable(Table):
|
||||
def uri(self) -> str:
|
||||
return LOOP.run(self._table.uri())
|
||||
|
||||
def initial_storage_options(self) -> Optional[Dict[str, str]]:
|
||||
"""Get the initial storage options that were passed in when opening this table.
|
||||
|
||||
For dynamically refreshed options (e.g., credential vending), use
|
||||
:meth:`latest_storage_options`.
|
||||
|
||||
Warning: This is an internal API and the return value is subject to change.
|
||||
|
||||
Returns
|
||||
-------
|
||||
Optional[Dict[str, str]]
|
||||
The storage options, or None if no storage options were configured.
|
||||
"""
|
||||
return LOOP.run(self._table.initial_storage_options())
|
||||
|
||||
def latest_storage_options(self) -> Optional[Dict[str, str]]:
|
||||
"""Get the latest storage options, refreshing from provider if configured.
|
||||
|
||||
This method is useful for credential vending scenarios where storage options
|
||||
may be refreshed dynamically. If no dynamic provider is configured, this
|
||||
returns the initial static options.
|
||||
|
||||
Warning: This is an internal API and the return value is subject to change.
|
||||
|
||||
Returns
|
||||
-------
|
||||
Optional[Dict[str, str]]
|
||||
The storage options, or None if no storage options were configured.
|
||||
"""
|
||||
return LOOP.run(self._table.latest_storage_options())
|
||||
|
||||
def create_scalar_index(
|
||||
self,
|
||||
column: str,
|
||||
@@ -3655,37 +3624,6 @@ class AsyncTable:
|
||||
"""
|
||||
return await self._inner.uri()
|
||||
|
||||
async def initial_storage_options(self) -> Optional[Dict[str, str]]:
|
||||
"""Get the initial storage options that were passed in when opening this table.
|
||||
|
||||
For dynamically refreshed options (e.g., credential vending), use
|
||||
:meth:`latest_storage_options`.
|
||||
|
||||
Warning: This is an internal API and the return value is subject to change.
|
||||
|
||||
Returns
|
||||
-------
|
||||
Optional[Dict[str, str]]
|
||||
The storage options, or None if no storage options were configured.
|
||||
"""
|
||||
return await self._inner.initial_storage_options()
|
||||
|
||||
async def latest_storage_options(self) -> Optional[Dict[str, str]]:
|
||||
"""Get the latest storage options, refreshing from provider if configured.
|
||||
|
||||
This method is useful for credential vending scenarios where storage options
|
||||
may be refreshed dynamically. If no dynamic provider is configured, this
|
||||
returns the initial static options.
|
||||
|
||||
Warning: This is an internal API and the return value is subject to change.
|
||||
|
||||
Returns
|
||||
-------
|
||||
Optional[Dict[str, str]]
|
||||
The storage options, or None if no storage options were configured.
|
||||
"""
|
||||
return await self._inner.latest_storage_options()
|
||||
|
||||
async def add(
|
||||
self,
|
||||
data: DATA,
|
||||
|
||||
@@ -502,20 +502,6 @@ impl Table {
|
||||
future_into_py(self_.py(), async move { inner.uri().await.infer_error() })
|
||||
}
|
||||
|
||||
pub fn initial_storage_options(self_: PyRef<'_, Self>) -> PyResult<Bound<'_, PyAny>> {
|
||||
let inner = self_.inner_ref()?.clone();
|
||||
future_into_py(self_.py(), async move {
|
||||
Ok(inner.initial_storage_options().await)
|
||||
})
|
||||
}
|
||||
|
||||
pub fn latest_storage_options(self_: PyRef<'_, Self>) -> PyResult<Bound<'_, PyAny>> {
|
||||
let inner = self_.inner_ref()?.clone();
|
||||
future_into_py(self_.py(), async move {
|
||||
inner.latest_storage_options().await.infer_error()
|
||||
})
|
||||
}
|
||||
|
||||
pub fn __repr__(&self) -> String {
|
||||
match &self.inner {
|
||||
None => format!("ClosedTable({})", self.name),
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
[package]
|
||||
name = "lancedb"
|
||||
version = "0.26.1"
|
||||
version = "0.25.0-beta.0"
|
||||
edition.workspace = true
|
||||
description = "LanceDB: A serverless, low-latency vector database for AI applications"
|
||||
license.workspace = true
|
||||
@@ -51,7 +51,7 @@ pin-project = { workspace = true }
|
||||
tokio = { version = "1.23", features = ["rt-multi-thread"] }
|
||||
log.workspace = true
|
||||
async-trait = "0"
|
||||
bytes = "1"
|
||||
bytes = "1.11.1"
|
||||
futures.workspace = true
|
||||
num-traits.workspace = true
|
||||
url.workspace = true
|
||||
|
||||
@@ -1497,14 +1497,6 @@ impl<S: HttpSend> BaseTable for RemoteTable<S> {
|
||||
None
|
||||
}
|
||||
|
||||
async fn initial_storage_options(&self) -> Option<HashMap<String, String>> {
|
||||
None
|
||||
}
|
||||
|
||||
async fn latest_storage_options(&self) -> Result<Option<HashMap<String, String>>> {
|
||||
Ok(None)
|
||||
}
|
||||
|
||||
async fn stats(&self) -> Result<TableStatistics> {
|
||||
let request = self
|
||||
.client
|
||||
|
||||
@@ -79,7 +79,6 @@ pub mod datafusion;
|
||||
pub(crate) mod dataset;
|
||||
pub mod delete;
|
||||
pub mod merge;
|
||||
pub mod schema_evolution;
|
||||
pub mod update;
|
||||
|
||||
use crate::index::waiter::wait_for_index;
|
||||
@@ -92,7 +91,6 @@ pub use lance::dataset::scanner::DatasetRecordBatchStream;
|
||||
use lance::dataset::statistics::DatasetStatisticsExt;
|
||||
use lance_index::frag_reuse::FRAG_REUSE_INDEX_NAME;
|
||||
pub use lance_index::optimize::OptimizeOptions;
|
||||
pub use schema_evolution::{AddColumnsResult, AlterColumnsResult, DropColumnsResult};
|
||||
use serde_with::skip_serializing_none;
|
||||
pub use update::{UpdateBuilder, UpdateResult};
|
||||
|
||||
@@ -398,6 +396,33 @@ pub struct MergeResult {
|
||||
pub num_attempts: u32,
|
||||
}
|
||||
|
||||
#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize, Default)]
|
||||
pub struct AddColumnsResult {
|
||||
// The commit version associated with the operation.
|
||||
// A version of `0` indicates compatibility with legacy servers that do not return
|
||||
/// a commit version.
|
||||
#[serde(default)]
|
||||
pub version: u64,
|
||||
}
|
||||
|
||||
#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize, Default)]
|
||||
pub struct AlterColumnsResult {
|
||||
// The commit version associated with the operation.
|
||||
// A version of `0` indicates compatibility with legacy servers that do not return
|
||||
/// a commit version.
|
||||
#[serde(default)]
|
||||
pub version: u64,
|
||||
}
|
||||
|
||||
#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize, Default)]
|
||||
pub struct DropColumnsResult {
|
||||
// The commit version associated with the operation.
|
||||
// A version of `0` indicates compatibility with legacy servers that do not return
|
||||
/// a commit version.
|
||||
#[serde(default)]
|
||||
pub version: u64,
|
||||
}
|
||||
|
||||
/// A trait for anything "table-like". This is used for both native tables (which target
|
||||
/// Lance datasets) and remote tables (which target LanceDB cloud)
|
||||
///
|
||||
@@ -502,17 +527,7 @@ pub trait BaseTable: std::fmt::Display + std::fmt::Debug + Send + Sync {
|
||||
/// Get the table URI (storage location)
|
||||
async fn uri(&self) -> Result<String>;
|
||||
/// Get the storage options used when opening this table, if any.
|
||||
#[deprecated(since = "0.25.0", note = "Use initial_storage_options() instead")]
|
||||
async fn storage_options(&self) -> Option<HashMap<String, String>>;
|
||||
/// Get the initial storage options that were passed in when opening this table.
|
||||
///
|
||||
/// For dynamically refreshed options (e.g., credential vending), use [`Self::latest_storage_options`].
|
||||
async fn initial_storage_options(&self) -> Option<HashMap<String, String>>;
|
||||
/// Get the latest storage options, refreshing from provider if configured.
|
||||
///
|
||||
/// Returns `Ok(Some(options))` if storage options are available (static or refreshed),
|
||||
/// `Ok(None)` if no storage options were configured, or `Err(...)` if refresh failed.
|
||||
async fn latest_storage_options(&self) -> Result<Option<HashMap<String, String>>>;
|
||||
/// Poll until the columns are fully indexed. Will return Error::Timeout if the columns
|
||||
/// are not fully indexed within the timeout.
|
||||
async fn wait_for_index(
|
||||
@@ -1242,32 +1257,10 @@ impl Table {
|
||||
/// Get the storage options used when opening this table, if any.
|
||||
///
|
||||
/// Warning: This is an internal API and the return value is subject to change.
|
||||
#[deprecated(since = "0.25.0", note = "Use initial_storage_options() instead")]
|
||||
pub async fn storage_options(&self) -> Option<HashMap<String, String>> {
|
||||
#[allow(deprecated)]
|
||||
self.inner.storage_options().await
|
||||
}
|
||||
|
||||
/// Get the initial storage options that were passed in when opening this table.
|
||||
///
|
||||
/// For dynamically refreshed options (e.g., credential vending), use [`Self::latest_storage_options`].
|
||||
///
|
||||
/// Warning: This is an internal API and the return value is subject to change.
|
||||
pub async fn initial_storage_options(&self) -> Option<HashMap<String, String>> {
|
||||
self.inner.initial_storage_options().await
|
||||
}
|
||||
|
||||
/// Get the latest storage options, refreshing from provider if configured.
|
||||
///
|
||||
/// This method is useful for credential vending scenarios where storage options
|
||||
/// may be refreshed dynamically. If no dynamic provider is configured, this
|
||||
/// returns the initial static options.
|
||||
///
|
||||
/// Warning: This is an internal API and the return value is subject to change.
|
||||
pub async fn latest_storage_options(&self) -> Result<Option<HashMap<String, String>>> {
|
||||
self.inner.latest_storage_options().await
|
||||
}
|
||||
|
||||
/// Get statistics about an index.
|
||||
/// Returns None if the index does not exist.
|
||||
pub async fn index_stats(
|
||||
@@ -3066,15 +3059,27 @@ impl BaseTable for NativeTable {
|
||||
transforms: NewColumnTransform,
|
||||
read_columns: Option<Vec<String>>,
|
||||
) -> Result<AddColumnsResult> {
|
||||
schema_evolution::execute_add_columns(self, transforms, read_columns).await
|
||||
let mut dataset = self.dataset.get_mut().await?;
|
||||
dataset.add_columns(transforms, read_columns, None).await?;
|
||||
Ok(AddColumnsResult {
|
||||
version: dataset.version().version,
|
||||
})
|
||||
}
|
||||
|
||||
async fn alter_columns(&self, alterations: &[ColumnAlteration]) -> Result<AlterColumnsResult> {
|
||||
schema_evolution::execute_alter_columns(self, alterations).await
|
||||
let mut dataset = self.dataset.get_mut().await?;
|
||||
dataset.alter_columns(alterations).await?;
|
||||
Ok(AlterColumnsResult {
|
||||
version: dataset.version().version,
|
||||
})
|
||||
}
|
||||
|
||||
async fn drop_columns(&self, columns: &[&str]) -> Result<DropColumnsResult> {
|
||||
schema_evolution::execute_drop_columns(self, columns).await
|
||||
let mut dataset = self.dataset.get_mut().await?;
|
||||
dataset.drop_columns(columns).await?;
|
||||
Ok(DropColumnsResult {
|
||||
version: dataset.version().version,
|
||||
})
|
||||
}
|
||||
|
||||
async fn list_indices(&self) -> Result<Vec<IndexConfig>> {
|
||||
@@ -3137,10 +3142,6 @@ impl BaseTable for NativeTable {
|
||||
}
|
||||
|
||||
async fn storage_options(&self) -> Option<HashMap<String, String>> {
|
||||
self.initial_storage_options().await
|
||||
}
|
||||
|
||||
async fn initial_storage_options(&self) -> Option<HashMap<String, String>> {
|
||||
self.dataset
|
||||
.get()
|
||||
.await
|
||||
@@ -3148,11 +3149,6 @@ impl BaseTable for NativeTable {
|
||||
.and_then(|dataset| dataset.initial_storage_options().cloned())
|
||||
}
|
||||
|
||||
async fn latest_storage_options(&self) -> Result<Option<HashMap<String, String>>> {
|
||||
let dataset = self.dataset.get().await?;
|
||||
Ok(dataset.latest_storage_options().await?.map(|o| o.0))
|
||||
}
|
||||
|
||||
async fn index_stats(&self, index_name: &str) -> Result<Option<IndexStatistics>> {
|
||||
let stats = match self
|
||||
.dataset
|
||||
|
||||
@@ -1,666 +0,0 @@
|
||||
// SPDX-License-Identifier: Apache-2.0
|
||||
// SPDX-FileCopyrightText: Copyright The LanceDB Authors
|
||||
|
||||
//! Schema evolution operations for LanceDB tables.
|
||||
//!
|
||||
//! This module provides functionality to modify the schema of existing tables:
|
||||
//! - [`add_columns`](execute_add_columns): Add new columns using SQL expressions
|
||||
//! - [`alter_columns`](execute_alter_columns): Rename columns, change types, or modify nullability
|
||||
//! - [`drop_columns`](execute_drop_columns): Remove columns from the table
|
||||
|
||||
use lance::dataset::{ColumnAlteration, NewColumnTransform};
|
||||
use serde::{Deserialize, Serialize};
|
||||
|
||||
use super::NativeTable;
|
||||
use crate::Result;
|
||||
|
||||
/// The result of an add columns operation.
|
||||
#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize, Default)]
|
||||
pub struct AddColumnsResult {
|
||||
// The commit version associated with the operation.
|
||||
// A version of `0` indicates compatibility with legacy servers that do not return
|
||||
/// a commit version.
|
||||
#[serde(default)]
|
||||
pub version: u64,
|
||||
}
|
||||
|
||||
/// The result of an alter columns operation.
|
||||
#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize, Default)]
|
||||
pub struct AlterColumnsResult {
|
||||
// The commit version associated with the operation.
|
||||
// A version of `0` indicates compatibility with legacy servers that do not return
|
||||
/// a commit version.
|
||||
#[serde(default)]
|
||||
pub version: u64,
|
||||
}
|
||||
|
||||
/// The result of a drop columns operation.
|
||||
#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize, Default)]
|
||||
pub struct DropColumnsResult {
|
||||
// The commit version associated with the operation.
|
||||
// A version of `0` indicates compatibility with legacy servers that do not return
|
||||
/// a commit version.
|
||||
#[serde(default)]
|
||||
pub version: u64,
|
||||
}
|
||||
|
||||
/// Internal implementation of the add columns logic.
|
||||
///
|
||||
/// Adds new columns to the table using the provided transforms.
|
||||
pub(crate) async fn execute_add_columns(
|
||||
table: &NativeTable,
|
||||
transforms: NewColumnTransform,
|
||||
read_columns: Option<Vec<String>>,
|
||||
) -> Result<AddColumnsResult> {
|
||||
let mut dataset = table.dataset.get_mut().await?;
|
||||
dataset.add_columns(transforms, read_columns, None).await?;
|
||||
Ok(AddColumnsResult {
|
||||
version: dataset.version().version,
|
||||
})
|
||||
}
|
||||
|
||||
/// Internal implementation of the alter columns logic.
|
||||
///
|
||||
/// Alters existing columns in the table (rename, change type, or modify nullability).
|
||||
pub(crate) async fn execute_alter_columns(
|
||||
table: &NativeTable,
|
||||
alterations: &[ColumnAlteration],
|
||||
) -> Result<AlterColumnsResult> {
|
||||
let mut dataset = table.dataset.get_mut().await?;
|
||||
dataset.alter_columns(alterations).await?;
|
||||
Ok(AlterColumnsResult {
|
||||
version: dataset.version().version,
|
||||
})
|
||||
}
|
||||
|
||||
/// Internal implementation of the drop columns logic.
|
||||
///
|
||||
/// Removes columns from the table.
|
||||
pub(crate) async fn execute_drop_columns(
|
||||
table: &NativeTable,
|
||||
columns: &[&str],
|
||||
) -> Result<DropColumnsResult> {
|
||||
let mut dataset = table.dataset.get_mut().await?;
|
||||
dataset.drop_columns(columns).await?;
|
||||
Ok(DropColumnsResult {
|
||||
version: dataset.version().version,
|
||||
})
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod tests {
|
||||
use arrow_array::{record_batch, Int32Array, RecordBatchIterator, StringArray};
|
||||
use arrow_schema::DataType;
|
||||
use futures::TryStreamExt;
|
||||
use lance::dataset::ColumnAlteration;
|
||||
|
||||
use crate::connect;
|
||||
use crate::query::{ExecutableQuery, QueryBase, Select};
|
||||
use crate::table::NewColumnTransform;
|
||||
|
||||
// Add Columns Tests
|
||||
|
||||
#[tokio::test]
|
||||
async fn test_add_columns_with_sql_expression() {
|
||||
let conn = connect("memory://").execute().await.unwrap();
|
||||
|
||||
let batch = record_batch!(("id", Int32, [1, 2, 3, 4, 5])).unwrap();
|
||||
let schema = batch.schema();
|
||||
|
||||
let table = conn
|
||||
.create_table(
|
||||
"test_add_columns",
|
||||
RecordBatchIterator::new(vec![Ok(batch)], schema),
|
||||
)
|
||||
.execute()
|
||||
.await
|
||||
.unwrap();
|
||||
|
||||
let initial_version = table.version().await.unwrap();
|
||||
|
||||
// Add a computed column
|
||||
let result = table
|
||||
.add_columns(
|
||||
NewColumnTransform::SqlExpressions(vec![("doubled".into(), "id * 2".into())]),
|
||||
None,
|
||||
)
|
||||
.await
|
||||
.unwrap();
|
||||
|
||||
// Version should increment
|
||||
assert!(result.version > initial_version);
|
||||
|
||||
// Verify the new column exists with correct values
|
||||
let batches = table
|
||||
.query()
|
||||
.select(Select::columns(&["id", "doubled"]))
|
||||
.execute()
|
||||
.await
|
||||
.unwrap()
|
||||
.try_collect::<Vec<_>>()
|
||||
.await
|
||||
.unwrap();
|
||||
|
||||
let batch = &batches[0];
|
||||
let ids: Vec<i32> = batch
|
||||
.column(0)
|
||||
.as_any()
|
||||
.downcast_ref::<Int32Array>()
|
||||
.unwrap()
|
||||
.iter()
|
||||
.map(|v| v.unwrap())
|
||||
.collect();
|
||||
let doubled: Vec<i32> = batch
|
||||
.column(1)
|
||||
.as_any()
|
||||
.downcast_ref::<Int32Array>()
|
||||
.unwrap()
|
||||
.iter()
|
||||
.map(|v| v.unwrap())
|
||||
.collect();
|
||||
|
||||
for (id, d) in ids.iter().zip(doubled.iter()) {
|
||||
assert_eq!(*d, id * 2);
|
||||
}
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn test_add_multiple_columns() {
|
||||
let conn = connect("memory://").execute().await.unwrap();
|
||||
|
||||
let batch = record_batch!(("x", Int32, [10, 20, 30])).unwrap();
|
||||
let schema = batch.schema();
|
||||
|
||||
let table = conn
|
||||
.create_table(
|
||||
"test_add_multi_columns",
|
||||
RecordBatchIterator::new(vec![Ok(batch)], schema),
|
||||
)
|
||||
.execute()
|
||||
.await
|
||||
.unwrap();
|
||||
|
||||
// Add multiple columns at once
|
||||
table
|
||||
.add_columns(
|
||||
NewColumnTransform::SqlExpressions(vec![
|
||||
("y".into(), "x + 1".into()),
|
||||
("z".into(), "x * x".into()),
|
||||
]),
|
||||
None,
|
||||
)
|
||||
.await
|
||||
.unwrap();
|
||||
|
||||
// Verify schema has all columns
|
||||
let schema = table.schema().await.unwrap();
|
||||
assert_eq!(schema.fields().len(), 3);
|
||||
assert!(schema.field_with_name("x").is_ok());
|
||||
assert!(schema.field_with_name("y").is_ok());
|
||||
assert!(schema.field_with_name("z").is_ok());
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn test_add_column_with_constant_expression() {
|
||||
let conn = connect("memory://").execute().await.unwrap();
|
||||
|
||||
let batch = record_batch!(("id", Int32, [1, 2, 3])).unwrap();
|
||||
let schema = batch.schema();
|
||||
|
||||
let table = conn
|
||||
.create_table(
|
||||
"test_add_const_column",
|
||||
RecordBatchIterator::new(vec![Ok(batch)], schema),
|
||||
)
|
||||
.execute()
|
||||
.await
|
||||
.unwrap();
|
||||
|
||||
// Add a column with a constant value
|
||||
table
|
||||
.add_columns(
|
||||
NewColumnTransform::SqlExpressions(vec![("constant".into(), "42".into())]),
|
||||
None,
|
||||
)
|
||||
.await
|
||||
.unwrap();
|
||||
|
||||
let schema = table.schema().await.unwrap();
|
||||
assert!(schema.field_with_name("constant").is_ok());
|
||||
|
||||
// Verify all values are 42
|
||||
let batches = table
|
||||
.query()
|
||||
.select(Select::columns(&["constant"]))
|
||||
.execute()
|
||||
.await
|
||||
.unwrap()
|
||||
.try_collect::<Vec<_>>()
|
||||
.await
|
||||
.unwrap();
|
||||
|
||||
let batch = &batches[0];
|
||||
let values = batch["constant"]
|
||||
.as_any()
|
||||
.downcast_ref::<arrow_array::Int64Array>()
|
||||
.unwrap()
|
||||
.values();
|
||||
assert!(values.iter().all(|&v| v == 42));
|
||||
}
|
||||
|
||||
// Alter Columns Tests
|
||||
|
||||
#[tokio::test]
|
||||
async fn test_alter_column_rename() {
|
||||
let conn = connect("memory://").execute().await.unwrap();
|
||||
|
||||
let batch = record_batch!(("old_name", Int32, [1, 2, 3])).unwrap();
|
||||
let schema = batch.schema();
|
||||
|
||||
let table = conn
|
||||
.create_table(
|
||||
"test_alter_rename",
|
||||
RecordBatchIterator::new(vec![Ok(batch)], schema),
|
||||
)
|
||||
.execute()
|
||||
.await
|
||||
.unwrap();
|
||||
|
||||
let initial_version = table.version().await.unwrap();
|
||||
|
||||
// Rename the column
|
||||
let result = table
|
||||
.alter_columns(&[ColumnAlteration::new("old_name".into()).rename("new_name".into())])
|
||||
.await
|
||||
.unwrap();
|
||||
|
||||
// Version should increment
|
||||
assert!(result.version > initial_version);
|
||||
|
||||
// Verify rename
|
||||
let schema = table.schema().await.unwrap();
|
||||
assert!(schema.field_with_name("old_name").is_err());
|
||||
assert!(schema.field_with_name("new_name").is_ok());
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn test_alter_column_set_nullable() {
|
||||
use arrow_array::RecordBatch;
|
||||
use arrow_schema::{Field, Schema};
|
||||
use std::sync::Arc;
|
||||
|
||||
let conn = connect("memory://").execute().await.unwrap();
|
||||
|
||||
// Create a schema with a non-nullable field
|
||||
let schema = Arc::new(Schema::new(vec![Field::new(
|
||||
"value",
|
||||
DataType::Int32,
|
||||
false,
|
||||
)]));
|
||||
let batch = RecordBatch::try_new(
|
||||
schema.clone(),
|
||||
vec![Arc::new(Int32Array::from(vec![1, 2, 3]))],
|
||||
)
|
||||
.unwrap();
|
||||
|
||||
let table = conn
|
||||
.create_table(
|
||||
"test_alter_nullable",
|
||||
RecordBatchIterator::new(vec![Ok(batch)], schema),
|
||||
)
|
||||
.execute()
|
||||
.await
|
||||
.unwrap();
|
||||
|
||||
// Initially non-nullable
|
||||
let schema = table.schema().await.unwrap();
|
||||
assert!(!schema.field_with_name("value").unwrap().is_nullable());
|
||||
|
||||
// Make it nullable
|
||||
table
|
||||
.alter_columns(&[ColumnAlteration::new("value".into()).set_nullable(true)])
|
||||
.await
|
||||
.unwrap();
|
||||
|
||||
// Verify it's now nullable
|
||||
let schema = table.schema().await.unwrap();
|
||||
assert!(schema.field_with_name("value").unwrap().is_nullable());
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn test_alter_column_cast_type() {
|
||||
let conn = connect("memory://").execute().await.unwrap();
|
||||
|
||||
let batch = record_batch!(("num", Int32, [1, 2, 3])).unwrap();
|
||||
let schema = batch.schema();
|
||||
|
||||
let table = conn
|
||||
.create_table(
|
||||
"test_cast_type",
|
||||
RecordBatchIterator::new(vec![Ok(batch)], schema),
|
||||
)
|
||||
.execute()
|
||||
.await
|
||||
.unwrap();
|
||||
|
||||
// Cast Int32 to Int64 (a supported cast)
|
||||
table
|
||||
.alter_columns(&[ColumnAlteration::new("num".into()).cast_to(DataType::Int64)])
|
||||
.await
|
||||
.unwrap();
|
||||
|
||||
// Verify type changed
|
||||
let schema = table.schema().await.unwrap();
|
||||
assert_eq!(
|
||||
schema.field_with_name("num").unwrap().data_type(),
|
||||
&DataType::Int64
|
||||
);
|
||||
|
||||
// Query the data and verify the returned type is correct
|
||||
let batches = table
|
||||
.query()
|
||||
.execute()
|
||||
.await
|
||||
.unwrap()
|
||||
.try_collect::<Vec<_>>()
|
||||
.await
|
||||
.unwrap();
|
||||
let batch = &batches[0];
|
||||
let values = batch["num"]
|
||||
.as_any()
|
||||
.downcast_ref::<arrow_array::Int64Array>()
|
||||
.unwrap()
|
||||
.values();
|
||||
assert_eq!(values.as_ref(), &[1i64, 2, 3]);
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn test_alter_column_invalid_cast_fails() {
|
||||
let conn = connect("memory://").execute().await.unwrap();
|
||||
|
||||
let batch = record_batch!(("num", Int32, [1, 2, 3])).unwrap();
|
||||
let schema = batch.schema();
|
||||
|
||||
let table = conn
|
||||
.create_table(
|
||||
"test_invalid_cast",
|
||||
RecordBatchIterator::new(vec![Ok(batch)], schema),
|
||||
)
|
||||
.execute()
|
||||
.await
|
||||
.unwrap();
|
||||
|
||||
// Casting Int32 to Float64 is not supported
|
||||
let result = table
|
||||
.alter_columns(&[ColumnAlteration::new("num".into()).cast_to(DataType::Float64)])
|
||||
.await;
|
||||
let err = result.unwrap_err();
|
||||
assert!(
|
||||
err.to_string().contains("cast"),
|
||||
"Expected error message to contain 'cast', got: {}",
|
||||
err
|
||||
);
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn test_alter_multiple_columns() {
|
||||
let conn = connect("memory://").execute().await.unwrap();
|
||||
|
||||
let batch = record_batch!(("a", Int32, [1, 2, 3]), ("b", Int32, [4, 5, 6])).unwrap();
|
||||
let schema = batch.schema();
|
||||
|
||||
let table = conn
|
||||
.create_table(
|
||||
"test_alter_multi",
|
||||
RecordBatchIterator::new(vec![Ok(batch)], schema),
|
||||
)
|
||||
.execute()
|
||||
.await
|
||||
.unwrap();
|
||||
|
||||
// Alter multiple columns at once
|
||||
table
|
||||
.alter_columns(&[
|
||||
ColumnAlteration::new("a".into()).rename("alpha".into()),
|
||||
ColumnAlteration::new("b".into()).set_nullable(true),
|
||||
])
|
||||
.await
|
||||
.unwrap();
|
||||
|
||||
let schema = table.schema().await.unwrap();
|
||||
assert!(schema.field_with_name("alpha").is_ok());
|
||||
assert!(schema.field_with_name("a").is_err());
|
||||
assert!(schema.field_with_name("b").unwrap().is_nullable());
|
||||
}
|
||||
|
||||
// Drop Columns Tests
|
||||
|
||||
#[tokio::test]
|
||||
async fn test_drop_single_column() {
|
||||
let conn = connect("memory://").execute().await.unwrap();
|
||||
|
||||
let batch =
|
||||
record_batch!(("keep", Int32, [1, 2, 3]), ("remove", Int32, [4, 5, 6])).unwrap();
|
||||
let schema = batch.schema();
|
||||
|
||||
let table = conn
|
||||
.create_table(
|
||||
"test_drop_single",
|
||||
RecordBatchIterator::new(vec![Ok(batch)], schema),
|
||||
)
|
||||
.execute()
|
||||
.await
|
||||
.unwrap();
|
||||
|
||||
let initial_version = table.version().await.unwrap();
|
||||
|
||||
// Drop a column
|
||||
let result = table.drop_columns(&["remove"]).await.unwrap();
|
||||
|
||||
// Version should increment
|
||||
assert!(result.version > initial_version);
|
||||
|
||||
// Verify column was dropped
|
||||
let schema = table.schema().await.unwrap();
|
||||
assert_eq!(schema.fields().len(), 1);
|
||||
assert!(schema.field_with_name("keep").is_ok());
|
||||
assert!(schema.field_with_name("remove").is_err());
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn test_drop_multiple_columns() {
|
||||
let conn = connect("memory://").execute().await.unwrap();
|
||||
|
||||
let batch = record_batch!(
|
||||
("a", Int32, [1, 2]),
|
||||
("b", Int32, [3, 4]),
|
||||
("c", Int32, [5, 6]),
|
||||
("d", Int32, [7, 8])
|
||||
)
|
||||
.unwrap();
|
||||
let schema = batch.schema();
|
||||
|
||||
let table = conn
|
||||
.create_table(
|
||||
"test_drop_multi",
|
||||
RecordBatchIterator::new(vec![Ok(batch)], schema),
|
||||
)
|
||||
.execute()
|
||||
.await
|
||||
.unwrap();
|
||||
|
||||
// Drop multiple columns
|
||||
table.drop_columns(&["b", "d"]).await.unwrap();
|
||||
|
||||
// Verify only a and c remain
|
||||
let schema = table.schema().await.unwrap();
|
||||
assert_eq!(schema.fields().len(), 2);
|
||||
assert!(schema.field_with_name("a").is_ok());
|
||||
assert!(schema.field_with_name("c").is_ok());
|
||||
assert!(schema.field_with_name("b").is_err());
|
||||
assert!(schema.field_with_name("d").is_err());
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn test_drop_column_preserves_data() {
|
||||
let conn = connect("memory://").execute().await.unwrap();
|
||||
|
||||
let batch = record_batch!(
|
||||
("id", Int32, [1, 2, 3]),
|
||||
("name", Utf8, ["a", "b", "c"]),
|
||||
("extra", Int32, [10, 20, 30])
|
||||
)
|
||||
.unwrap();
|
||||
let schema = batch.schema();
|
||||
|
||||
let table = conn
|
||||
.create_table(
|
||||
"test_drop_preserves",
|
||||
RecordBatchIterator::new(vec![Ok(batch)], schema),
|
||||
)
|
||||
.execute()
|
||||
.await
|
||||
.unwrap();
|
||||
|
||||
// Drop the extra column
|
||||
table.drop_columns(&["extra"]).await.unwrap();
|
||||
|
||||
// Verify remaining data is intact
|
||||
let batches = table
|
||||
.query()
|
||||
.execute()
|
||||
.await
|
||||
.unwrap()
|
||||
.try_collect::<Vec<_>>()
|
||||
.await
|
||||
.unwrap();
|
||||
|
||||
let batch = &batches[0];
|
||||
assert_eq!(batch.num_columns(), 2);
|
||||
assert_eq!(batch.num_rows(), 3);
|
||||
|
||||
let ids: Vec<i32> = batch
|
||||
.column(0)
|
||||
.as_any()
|
||||
.downcast_ref::<Int32Array>()
|
||||
.unwrap()
|
||||
.iter()
|
||||
.map(|v| v.unwrap())
|
||||
.collect();
|
||||
assert_eq!(ids, vec![1, 2, 3]);
|
||||
|
||||
let names: Vec<&str> = batch
|
||||
.column(1)
|
||||
.as_any()
|
||||
.downcast_ref::<StringArray>()
|
||||
.unwrap()
|
||||
.iter()
|
||||
.map(|v| v.unwrap())
|
||||
.collect();
|
||||
assert_eq!(names, vec!["a", "b", "c"]);
|
||||
}
|
||||
|
||||
// Error Case Tests
|
||||
|
||||
#[tokio::test]
|
||||
async fn test_drop_nonexistent_column_fails() {
|
||||
let conn = connect("memory://").execute().await.unwrap();
|
||||
|
||||
let batch = record_batch!(("existing", Int32, [1, 2, 3])).unwrap();
|
||||
let schema = batch.schema();
|
||||
|
||||
let table = conn
|
||||
.create_table(
|
||||
"test_drop_nonexistent",
|
||||
RecordBatchIterator::new(vec![Ok(batch)], schema),
|
||||
)
|
||||
.execute()
|
||||
.await
|
||||
.unwrap();
|
||||
|
||||
// Try to drop a column that doesn't exist
|
||||
let result = table.drop_columns(&["nonexistent"]).await;
|
||||
let err = result.unwrap_err();
|
||||
assert!(
|
||||
err.to_string().contains("nonexistent"),
|
||||
"Expected error message to contain column name 'nonexistent', got: {}",
|
||||
err
|
||||
);
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn test_alter_nonexistent_column_fails() {
|
||||
let conn = connect("memory://").execute().await.unwrap();
|
||||
|
||||
let batch = record_batch!(("existing", Int32, [1, 2, 3])).unwrap();
|
||||
let schema = batch.schema();
|
||||
|
||||
let table = conn
|
||||
.create_table(
|
||||
"test_alter_nonexistent",
|
||||
RecordBatchIterator::new(vec![Ok(batch)], schema),
|
||||
)
|
||||
.execute()
|
||||
.await
|
||||
.unwrap();
|
||||
|
||||
// Try to alter a column that doesn't exist
|
||||
let result = table
|
||||
.alter_columns(&[ColumnAlteration::new("nonexistent".into()).rename("new".into())])
|
||||
.await;
|
||||
let err = result.unwrap_err();
|
||||
assert!(
|
||||
err.to_string().contains("nonexistent"),
|
||||
"Expected error message to contain column name 'nonexistent', got: {}",
|
||||
err
|
||||
);
|
||||
}
|
||||
|
||||
// Version Tracking Tests
|
||||
|
||||
#[tokio::test]
|
||||
async fn test_schema_operations_increment_version() {
|
||||
let conn = connect("memory://").execute().await.unwrap();
|
||||
|
||||
let batch = record_batch!(("a", Int32, [1, 2, 3]), ("b", Int32, [4, 5, 6])).unwrap();
|
||||
let schema = batch.schema();
|
||||
|
||||
let table = conn
|
||||
.create_table(
|
||||
"test_version_increment",
|
||||
RecordBatchIterator::new(vec![Ok(batch)], schema),
|
||||
)
|
||||
.execute()
|
||||
.await
|
||||
.unwrap();
|
||||
|
||||
let v1 = table.version().await.unwrap();
|
||||
|
||||
// Add column increments version
|
||||
let add_result = table
|
||||
.add_columns(
|
||||
NewColumnTransform::SqlExpressions(vec![("c".into(), "a + b".into())]),
|
||||
None,
|
||||
)
|
||||
.await
|
||||
.unwrap();
|
||||
assert!(add_result.version > v1);
|
||||
let v2 = table.version().await.unwrap();
|
||||
assert_eq!(add_result.version, v2);
|
||||
|
||||
// Alter column increments version
|
||||
let alter_result = table
|
||||
.alter_columns(&[ColumnAlteration::new("c".into()).rename("sum".into())])
|
||||
.await
|
||||
.unwrap();
|
||||
assert!(alter_result.version > v2);
|
||||
let v3 = table.version().await.unwrap();
|
||||
assert_eq!(alter_result.version, v3);
|
||||
|
||||
// Drop column increments version
|
||||
let drop_result = table.drop_columns(&["b"]).await.unwrap();
|
||||
assert!(drop_result.version > v3);
|
||||
let v4 = table.version().await.unwrap();
|
||||
assert_eq!(drop_result.version, v4);
|
||||
}
|
||||
}
|
||||
Reference in New Issue
Block a user