rust/lancedb
1
0
Fork 0
mirror of https://github.com/lancedb/lancedb.git synced 2026-08-18 03:58:26 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge origin/main into gatekeeper/fix-2325-1

Browse Source
This commit is contained in:
Gatefixer
2026-08-14 21:59:28 +00:00
parent edf95e53fc fc0d917d32
commit 40cff9b644
77 changed files with 5758 additions and 548 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.bumpversion.toml
+1 -1
View File
@@ -1,5 +1,5 @@
[tool.bumpversion]
current_version = "0.37.1-beta.0"
current_version = "0.38.0-beta.0"
parse = """(?x)
(?P<major>0|[1-9]\\d*)\\.
(?P<minor>0|[1-9]\\d*)\\.
.github/workflows/codex-update-lance-dependency.yml
+2 -2
View File
@@ -4,14 +4,14 @@ on:
workflow_call:
inputs:
tag:
description: "Tag name from Lance. If omitted, the skill will use the latest Lance release that needs an update."
description: "Tag name from Lance (e.g. `v7.2.0-beta.1`). If omitted, the newest release is resolved automatically — stable releases are preferred over pre-releases — and the run is skipped if it is not newer than the version currently pinned in Cargo.toml."
required: false
default: ""
type: string
workflow_dispatch:
inputs:
tag:
description: "Tag name from Lance. Leave empty to use the latest Lance release that needs an update."
description: "Tag name from Lance (e.g. `v7.2.0-beta.1`). Leave empty to resolve the newest release automatically — stable releases are preferred over pre-releases — and skip the run if it is not newer than the version currently pinned in Cargo.toml."
required: false
default: ""
type: string
.github/workflows/docs-link-check.yml
+70 -49
View File
@@ -36,7 +36,9 @@ jobs:
permissions:
contents: read
outputs:
checker_outcome: ${{ steps.lychee.outcome }}
exit_code: ${{ steps.lychee.outputs.exit_code }}
status: ${{ steps.validate.outputs.status }}
steps:
- name: Checkout
uses: actions/checkout@v6
@@ -50,6 +52,7 @@ jobs:
- name: Check links
id: lychee
continue-on-error: true
uses: lycheeverse/lychee-action@e7477775783ea5526144ba13e8db5eec57747ce8 # v2.9.0
with:
# Restricted to http(s) on purpose. Much of docs/src is generated
@@ -68,38 +71,50 @@ jobs:
format: json
output: ./lychee/out.json
jobSummary: false
# The report, not a red build, is the signal for broken links. The
# validation step below still fails the run if the check itself
# breaks.
# The report issue, not a red workflow run, is the signal for link
# findings and checker failures alike.
fail: false
- name: Validate report
id: validate
# lychee does not reserve exit code 2 for broken links: its CLI
# parser also exits 2 on an invalid option, before any link was
# checked or any report written. Only a parseable report whose
# counts agree with the exit code counts as a link verdict; anything
# else fails here, and the report job below is skipped entirely, so
# the tracking issue is never touched. Exit 2 covers timeouts as
# well as errors, and a timed-out host is exactly the transient
# unavailability this report exists to surface, so both count as
# findings. Requiring total > 0 also catches a glob that silently
# stopped matching any file.
if: steps.lychee.outputs.exit_code == 0 || steps.lychee.outputs.exit_code == 2
# counts agree with a completed exit code (0 or 2) counts as a link
# verdict. Everything else becomes a checker-error report instead of
# failing the workflow. Exit 2 covers timeouts as well as errors, and a
# timed-out host is exactly the transient unavailability this report
# exists to surface, so both count as findings. Requiring total > 0
# also catches a glob that silently stopped matching any file.
if: always()
env:
CHECKER_OUTCOME: ${{ steps.lychee.outcome }}
EXIT_CODE: ${{ steps.lychee.outputs.exit_code }}
run: |
jq -e --argjson code "$EXIT_CODE" '
(.total > 0) and
(if $code == 0
then .errors == 0 and .timeouts == 0
and (.error_map | length == 0) and (.timeout_map | length == 0)
else (.errors + .timeouts) > 0
and ((.error_map | length) + (.timeout_map | length)) > 0
end)
' ./lychee/out.json
status=checker-error
if [[ "$CHECKER_OUTCOME" == success ]] &&
[[ "$EXIT_CODE" == 0 || "$EXIT_CODE" == 2 ]] &&
jq -e --argjson code "$EXIT_CODE" '
(.total > 0) and
(if $code == 0
then .errors == 0 and .timeouts == 0
and (.error_map | length == 0) and (.timeout_map | length == 0)
else (.errors + .timeouts) > 0
and ((.error_map | length) + (.timeout_map | length)) > 0
end)
' ./lychee/out.json
then
if [[ "$EXIT_CODE" == 0 ]]; then
status=healthy
else
status=findings
fi
fi
echo "status=$status" >> "$GITHUB_OUTPUT"
echo "Validated link check as $status"
- name: Upload report
if: steps.lychee.outputs.exit_code == 2
if: steps.validate.outputs.status == 'findings'
uses: actions/upload-artifact@v7
with:
name: link-report
@@ -115,26 +130,11 @@ jobs:
permissions:
issues: write
env:
CHECKER_OUTCOME: ${{ needs.scan.outputs.checker_outcome }}
EXIT_CODE: ${{ needs.scan.outputs.exit_code }}
STATUS: ${{ needs.scan.outputs.status }}
GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
steps:
- name: Classify checker result
# lychee exits 0 when every link resolves and 2 when links fail,
# both already cross-checked against the report by the scan job's
# validation step. Anything else (1 runtime, 3 bad config) means the
# check never produced a link verdict, which must surface as a failed
# run rather than be published as "broken documentation links".
run: |
case "$EXIT_CODE" in
0|2)
echo "lychee exit code $EXIT_CODE"
;;
*)
echo "::error::lychee exited with '$EXIT_CODE': the link check did not complete. Leaving the report issue untouched."
exit 1
;;
esac
- name: Find existing report issue
id: report
# Matched on title alone, and through search rather than a listing:
@@ -144,7 +144,7 @@ jobs:
# Closed issues are included because a healthy run closes the report:
# an open-only lookup would forget that identity and the next failing
# run would open a duplicate. The oldest match stays the canonical
# report and is reopened below when links break again.
# report and is reopened below when a problem recurs.
run: |
match=$(gh issue list --repo "$GITHUB_REPOSITORY" --state all \
--search "in:title \"$REPORT_TITLE\" author:app/github-actions" \
@@ -154,14 +154,14 @@ jobs:
echo "state=$(jq -r '.state // empty' <<<"$match")" >> "$GITHUB_OUTPUT"
- name: Download report
if: env.EXIT_CODE == 2
if: env.STATUS == 'findings'
uses: actions/download-artifact@v8
with:
name: link-report
path: ./lychee
- name: Compose report
if: env.EXIT_CODE == 2
if: env.STATUS == 'findings'
run: |
run_url="$GITHUB_SERVER_URL/$GITHUB_REPOSITORY/actions/runs/$GITHUB_RUN_ID"
{
@@ -185,22 +185,41 @@ jobs:
' ./lychee/out.json
} > ./lychee/issue.md
- name: Compose checker error report
if: env.STATUS == 'checker-error'
run: |
mkdir -p ./lychee
run_url="$GITHUB_SERVER_URL/$GITHUB_REPOSITORY/actions/runs/$GITHUB_RUN_ID"
{
echo "The documentation link check did not complete in [the latest run]($run_url)."
echo
echo "This issue is rewritten by every scheduled run and closed automatically once a trustworthy run finds that all links resolve."
echo
echo "The checker did not produce a trustworthy link verdict. Treat the previous result, if any, as stale until a later run completes."
echo
echo "* Action outcome: \`$CHECKER_OUTCOME\`"
echo "* Exit code: \`${EXIT_CODE:-not reported}\`"
echo "* Verdict validation: \`failed\`"
} > ./lychee/issue.md
- name: Reopen report issue
# A healthy run closes the report, and the issue action below only
# rewrites the body of whatever number it is given. Without an
# explicit reopen, the 2 -> 0 -> 2 sequence would keep rewriting a
# closed issue while links are broken. A CLOSED state implies the
# lookup found a canonical issue, so no separate emptiness check.
if: env.EXIT_CODE == 2 && steps.report.outputs.state == 'CLOSED'
# explicit reopen, a later finding or checker error would rewrite a
# closed issue. A CLOSED state implies the lookup found a canonical
# issue, so no separate emptiness check.
if: >-
env.STATUS != 'healthy' &&
steps.report.outputs.state == 'CLOSED'
env:
ISSUE_NUMBER: ${{ steps.report.outputs.number }}
run: |
run_url="$GITHUB_SERVER_URL/$GITHUB_REPOSITORY/actions/runs/$GITHUB_RUN_ID"
gh issue reopen "$ISSUE_NUMBER" --repo "$GITHUB_REPOSITORY" \
--comment "Broken documentation links found again in [the latest run]($run_url)."
--comment "The documentation link checker reported a problem again in [the latest run]($run_url)."
- name: Report broken links
if: env.EXIT_CODE == 2
- name: Report link-check problem
if: env.STATUS != 'healthy'
uses: peter-evans/create-issue-from-file@fca9117c27cdc29c6c4db3b86c48e4115a786710 # v6.0.0
with:
# Empty on the first failing run, which creates the issue; afterwards
@@ -213,7 +232,9 @@ jobs:
- name: Close report issue once links are healthy
# An OPEN state implies the lookup found a canonical issue; a report
# that is already closed needs nothing.
if: env.EXIT_CODE == 0 && steps.report.outputs.state == 'OPEN'
if: >-
env.STATUS == 'healthy' &&
steps.report.outputs.state == 'OPEN'
env:
ISSUE_NUMBER: ${{ steps.report.outputs.number }}
run: |
.github/workflows/pypi-publish.yml
+10
View File
@@ -69,6 +69,16 @@ jobs:
uses: actions/setup-python@v6
with:
python-version: "3.10"
- name: Add swap for Arm fat LTO
if: matrix.config.platform == 'aarch64'
shell: bash
run: |
swap_file="$RUNNER_TEMP/lancedb-swap"
sudo fallocate --length 16G "$swap_file"
sudo chmod 600 "$swap_file"
sudo mkswap "$swap_file"
sudo swapon "$swap_file"
free -h
- uses: ./.github/workflows/build_linux_wheel
with:
python-minor-version: 10
Cargo.lock
Generated
+47 -60
View File
@@ -3455,8 +3455,8 @@ checksum = "42703706b716c37f96a77aea830392ad231f44c9e9a67872fa5548707e11b11c"
[[package]]
name = "fsst"
version = "11.0.0-beta.3"
source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.3#f7d475539cefbd140cc46a828f3d843e68cd10f1"
version = "11.0.0-beta.11"
source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.11#5ef1e969030b79fe8c6d31fff9e40d18b24ebbd3"
dependencies = [
"arrow-array",
"rand 0.9.5",
@@ -4815,8 +4815,8 @@ checksum = "e037a2e1d8d5fdbd49b16a4ea09d5d6401c1f29eca5ff29d03d3824dba16256a"
[[package]]
name = "lance"
version = "11.0.0-beta.3"
source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.3#f7d475539cefbd140cc46a828f3d843e68cd10f1"
version = "11.0.0-beta.11"
source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.11#5ef1e969030b79fe8c6d31fff9e40d18b24ebbd3"
dependencies = [
"arc-swap",
"arrow",
@@ -4832,7 +4832,6 @@ dependencies = [
"async-recursion",
"async-trait",
"async_cell",
"aws-credential-types",
"aws-sdk-dynamodb",
"byteorder",
"bytes",
@@ -4848,7 +4847,6 @@ dependencies = [
"either",
"fst",
"futures",
"half",
"humantime",
"itertools 0.14.0",
"lance-arrow",
@@ -4890,8 +4888,8 @@ dependencies = [
[[package]]
name = "lance-arrow"
version = "11.0.0-beta.3"
source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.3#f7d475539cefbd140cc46a828f3d843e68cd10f1"
version = "11.0.0-beta.11"
source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.11#5ef1e969030b79fe8c6d31fff9e40d18b24ebbd3"
dependencies = [
"arrow-array",
"arrow-buffer",
@@ -4913,7 +4911,7 @@ dependencies = [
[[package]]
name = "lance-arrow-scalar"
version = "58.0.0"
source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.3#f7d475539cefbd140cc46a828f3d843e68cd10f1"
source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.11#5ef1e969030b79fe8c6d31fff9e40d18b24ebbd3"
dependencies = [
"arrow-array",
"arrow-buffer",
@@ -4927,7 +4925,7 @@ dependencies = [
[[package]]
name = "lance-arrow-stats"
version = "58.0.0"
source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.3#f7d475539cefbd140cc46a828f3d843e68cd10f1"
source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.11#5ef1e969030b79fe8c6d31fff9e40d18b24ebbd3"
dependencies = [
"arrow-array",
"arrow-schema",
@@ -4936,8 +4934,8 @@ dependencies = [
[[package]]
name = "lance-bitpacking"
version = "11.0.0-beta.3"
source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.3#f7d475539cefbd140cc46a828f3d843e68cd10f1"
version = "11.0.0-beta.11"
source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.11#5ef1e969030b79fe8c6d31fff9e40d18b24ebbd3"
dependencies = [
"arrayref",
"crunchy",
@@ -4947,8 +4945,8 @@ dependencies = [
[[package]]
name = "lance-core"
version = "11.0.0-beta.3"
source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.3#f7d475539cefbd140cc46a828f3d843e68cd10f1"
version = "11.0.0-beta.11"
source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.11#5ef1e969030b79fe8c6d31fff9e40d18b24ebbd3"
dependencies = [
"arrow-array",
"arrow-buffer",
@@ -4956,12 +4954,10 @@ dependencies = [
"arrow-schema",
"async-trait",
"blake3",
"byteorder",
"bytes",
"datafusion-common",
"datafusion-sql",
"futures",
"itertools 0.14.0",
"lance-arrow",
"lance-derive",
"libc",
@@ -4979,7 +4975,6 @@ dependencies = [
"snafu 0.9.0",
"tempfile",
"tokio",
"tokio-stream",
"tokio-util",
"tracing",
"twox-hash",
@@ -4988,8 +4983,8 @@ dependencies = [
[[package]]
name = "lance-datafusion"
version = "11.0.0-beta.3"
source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.3#f7d475539cefbd140cc46a828f3d843e68cd10f1"
version = "11.0.0-beta.11"
source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.11#5ef1e969030b79fe8c6d31fff9e40d18b24ebbd3"
dependencies = [
"arrow",
"arrow-array",
@@ -5008,7 +5003,6 @@ dependencies = [
"jsonb",
"lance-arrow",
"lance-core",
"lance-datagen",
"log",
"pin-project",
"prost",
@@ -5019,8 +5013,8 @@ dependencies = [
[[package]]
name = "lance-datagen"
version = "11.0.0-beta.3"
source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.3#f7d475539cefbd140cc46a828f3d843e68cd10f1"
version = "11.0.0-beta.11"
source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.11#5ef1e969030b79fe8c6d31fff9e40d18b24ebbd3"
dependencies = [
"arrow",
"arrow-array",
@@ -5037,8 +5031,8 @@ dependencies = [
[[package]]
name = "lance-derive"
version = "11.0.0-beta.3"
source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.3#f7d475539cefbd140cc46a828f3d843e68cd10f1"
version = "11.0.0-beta.11"
source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.11#5ef1e969030b79fe8c6d31fff9e40d18b24ebbd3"
dependencies = [
"proc-macro2",
"quote",
@@ -5047,8 +5041,8 @@ dependencies = [
[[package]]
name = "lance-encoding"
version = "11.0.0-beta.3"
source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.3#f7d475539cefbd140cc46a828f3d843e68cd10f1"
version = "11.0.0-beta.11"
source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.11#5ef1e969030b79fe8c6d31fff9e40d18b24ebbd3"
dependencies = [
"arrow-arith",
"arrow-array",
@@ -5073,7 +5067,6 @@ dependencies = [
"num-traits",
"prost",
"prost-build",
"rand 0.9.5",
"tokio",
"tracing",
"xxhash-rust",
@@ -5082,8 +5075,8 @@ dependencies = [
[[package]]
name = "lance-file"
version = "11.0.0-beta.3"
source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.3#f7d475539cefbd140cc46a828f3d843e68cd10f1"
version = "11.0.0-beta.11"
source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.11#5ef1e969030b79fe8c6d31fff9e40d18b24ebbd3"
dependencies = [
"arrow-arith",
"arrow-array",
@@ -5114,8 +5107,8 @@ dependencies = [
[[package]]
name = "lance-index"
version = "11.0.0-beta.3"
source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.3#f7d475539cefbd140cc46a828f3d843e68cd10f1"
version = "11.0.0-beta.11"
source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.11#5ef1e969030b79fe8c6d31fff9e40d18b24ebbd3"
dependencies = [
"arc-swap",
"arrow",
@@ -5130,7 +5123,6 @@ dependencies = [
"async-trait",
"bitvec",
"bytes",
"chrono",
"crossbeam-queue",
"datafusion",
"datafusion-common",
@@ -5148,7 +5140,6 @@ dependencies = [
"lance-bitpacking",
"lance-core",
"lance-datafusion",
"lance-datagen",
"lance-encoding",
"lance-file",
"lance-index-core",
@@ -5177,13 +5168,12 @@ dependencies = [
"tempfile",
"tokio",
"tracing",
"uuid",
]
[[package]]
name = "lance-index-core"
version = "11.0.0-beta.3"
source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.3#f7d475539cefbd140cc46a828f3d843e68cd10f1"
version = "11.0.0-beta.11"
source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.11#5ef1e969030b79fe8c6d31fff9e40d18b24ebbd3"
dependencies = [
"arrow-array",
"arrow-schema",
@@ -5205,8 +5195,8 @@ dependencies = [
[[package]]
name = "lance-io"
version = "11.0.0-beta.3"
source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.3#f7d475539cefbd140cc46a828f3d843e68cd10f1"
version = "11.0.0-beta.11"
source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.11#5ef1e969030b79fe8c6d31fff9e40d18b24ebbd3"
dependencies = [
"arrow",
"arrow-array",
@@ -5220,7 +5210,6 @@ dependencies = [
"futures",
"http 1.5.0",
"io-uring",
"lance-arrow",
"lance-core",
"lance-namespace",
"log",
@@ -5238,29 +5227,28 @@ dependencies = [
"tokio",
"tracing",
"url",
"uuid",
]
[[package]]
name = "lance-linalg"
version = "11.0.0-beta.3"
source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.3#f7d475539cefbd140cc46a828f3d843e68cd10f1"
version = "11.0.0-beta.11"
source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.11#5ef1e969030b79fe8c6d31fff9e40d18b24ebbd3"
dependencies = [
"arrow-array",
"arrow-buffer",
"arrow-schema",
"cc",
"half",
"lance-arrow",
"lance-core",
"num-traits",
"rand 0.9.5",
"rayon",
]
[[package]]
name = "lance-namespace"
version = "11.0.0-beta.3"
source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.3#f7d475539cefbd140cc46a828f3d843e68cd10f1"
version = "11.0.0-beta.11"
source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.11#5ef1e969030b79fe8c6d31fff9e40d18b24ebbd3"
dependencies = [
"arrow",
"async-trait",
@@ -5272,8 +5260,8 @@ dependencies = [
[[package]]
name = "lance-namespace-impls"
version = "11.0.0-beta.3"
source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.3#f7d475539cefbd140cc46a828f3d843e68cd10f1"
version = "11.0.0-beta.11"
source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.11#5ef1e969030b79fe8c6d31fff9e40d18b24ebbd3"
dependencies = [
"arrow",
"arrow-ipc",
@@ -5326,14 +5314,13 @@ dependencies = [
[[package]]
name = "lance-select"
version = "11.0.0-beta.3"
source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.3#f7d475539cefbd140cc46a828f3d843e68cd10f1"
version = "11.0.0-beta.11"
source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.11#5ef1e969030b79fe8c6d31fff9e40d18b24ebbd3"
dependencies = [
"arrow-array",
"arrow-buffer",
"arrow-schema",
"byteorder",
"bytes",
"itertools 0.14.0",
"lance-core",
"roaring",
@@ -5342,8 +5329,8 @@ dependencies = [
[[package]]
name = "lance-table"
version = "11.0.0-beta.3"
source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.3#f7d475539cefbd140cc46a828f3d843e68cd10f1"
version = "11.0.0-beta.11"
source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.11#5ef1e969030b79fe8c6d31fff9e40d18b24ebbd3"
dependencies = [
"arrow",
"arrow-array",
@@ -5383,8 +5370,8 @@ dependencies = [
[[package]]
name = "lance-testing"
version = "11.0.0-beta.3"
source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.3#f7d475539cefbd140cc46a828f3d843e68cd10f1"
version = "11.0.0-beta.11"
source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.11#5ef1e969030b79fe8c6d31fff9e40d18b24ebbd3"
dependencies = [
"arrow-array",
"arrow-schema",
@@ -5397,8 +5384,8 @@ dependencies = [
[[package]]
name = "lance-tokenizer"
version = "11.0.0-beta.3"
source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.3#f7d475539cefbd140cc46a828f3d843e68cd10f1"
version = "11.0.0-beta.11"
source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.11#5ef1e969030b79fe8c6d31fff9e40d18b24ebbd3"
dependencies = [
"frostem",
"icu_segmenter",
@@ -5411,7 +5398,7 @@ dependencies = [
[[package]]
name = "lancedb"
version = "0.37.1-beta.0"
version = "0.38.0-beta.0"
dependencies = [
"ahash",
"anyhow",
@@ -5447,7 +5434,6 @@ dependencies = [
"datafusion-physical-plan",
"datafusion-sql",
"futures",
"goosefs-sdk",
"half",
"hf-hub",
"http 1.5.0",
@@ -5480,6 +5466,7 @@ dependencies = [
"random_word",
"regex",
"reqwest 0.12.28",
"roaring",
"rstest",
"semver",
"serde",
@@ -5499,7 +5486,7 @@ dependencies = [
[[package]]
name = "lancedb-nodejs"
version = "0.37.1-beta.0"
version = "0.38.0-beta.0"
dependencies = [
"arrow-array",
"arrow-buffer",
@@ -5524,7 +5511,7 @@ dependencies = [
[[package]]
name = "lancedb-python"
version = "0.37.1-beta.0"
version = "0.38.0-beta.0"
dependencies = [
"arrow",
"async-trait",
Cargo.toml
+14 -14
View File
@@ -13,20 +13,20 @@ categories = ["database-implementations"]
rust-version = "1.91.0"
[workspace.dependencies]
lance = { "version" = "=11.0.0-beta.3", default-features = false, "tag" = "v11.0.0-beta.3", "git" = "https://github.com/lance-format/lance.git" }
lance-core = { "version" = "=11.0.0-beta.3", "tag" = "v11.0.0-beta.3", "git" = "https://github.com/lance-format/lance.git" }
lance-datagen = { "version" = "=11.0.0-beta.3", "tag" = "v11.0.0-beta.3", "git" = "https://github.com/lance-format/lance.git" }
lance-file = { "version" = "=11.0.0-beta.3", "tag" = "v11.0.0-beta.3", "git" = "https://github.com/lance-format/lance.git" }
lance-io = { "version" = "=11.0.0-beta.3", default-features = false, "tag" = "v11.0.0-beta.3", "git" = "https://github.com/lance-format/lance.git" }
lance-index = { "version" = "=11.0.0-beta.3", "tag" = "v11.0.0-beta.3", "git" = "https://github.com/lance-format/lance.git" }
lance-linalg = { "version" = "=11.0.0-beta.3", "tag" = "v11.0.0-beta.3", "git" = "https://github.com/lance-format/lance.git" }
lance-namespace = { "version" = "=11.0.0-beta.3", "tag" = "v11.0.0-beta.3", "git" = "https://github.com/lance-format/lance.git" }
lance-namespace-impls = { "version" = "=11.0.0-beta.3", default-features = false, "tag" = "v11.0.0-beta.3", "git" = "https://github.com/lance-format/lance.git" }
lance-table = { "version" = "=11.0.0-beta.3", "tag" = "v11.0.0-beta.3", "git" = "https://github.com/lance-format/lance.git" }
lance-testing = { "version" = "=11.0.0-beta.3", "tag" = "v11.0.0-beta.3", "git" = "https://github.com/lance-format/lance.git" }
lance-datafusion = { "version" = "=11.0.0-beta.3", "tag" = "v11.0.0-beta.3", "git" = "https://github.com/lance-format/lance.git" }
lance-encoding = { "version" = "=11.0.0-beta.3", "tag" = "v11.0.0-beta.3", "git" = "https://github.com/lance-format/lance.git" }
lance-arrow = { "version" = "=11.0.0-beta.3", "tag" = "v11.0.0-beta.3", "git" = "https://github.com/lance-format/lance.git" }
lance = { "version" = "=11.0.0-beta.11", default-features = false, "tag" = "v11.0.0-beta.11", "git" = "https://github.com/lance-format/lance.git" }
lance-core = { "version" = "=11.0.0-beta.11", "tag" = "v11.0.0-beta.11", "git" = "https://github.com/lance-format/lance.git" }
lance-datagen = { "version" = "=11.0.0-beta.11", "tag" = "v11.0.0-beta.11", "git" = "https://github.com/lance-format/lance.git" }
lance-file = { "version" = "=11.0.0-beta.11", "tag" = "v11.0.0-beta.11", "git" = "https://github.com/lance-format/lance.git" }
lance-io = { "version" = "=11.0.0-beta.11", default-features = false, "tag" = "v11.0.0-beta.11", "git" = "https://github.com/lance-format/lance.git" }
lance-index = { "version" = "=11.0.0-beta.11", "tag" = "v11.0.0-beta.11", "git" = "https://github.com/lance-format/lance.git" }
lance-linalg = { "version" = "=11.0.0-beta.11", "tag" = "v11.0.0-beta.11", "git" = "https://github.com/lance-format/lance.git" }
lance-namespace = { "version" = "=11.0.0-beta.11", "tag" = "v11.0.0-beta.11", "git" = "https://github.com/lance-format/lance.git" }
lance-namespace-impls = { "version" = "=11.0.0-beta.11", default-features = false, "tag" = "v11.0.0-beta.11", "git" = "https://github.com/lance-format/lance.git" }
lance-table = { "version" = "=11.0.0-beta.11", "tag" = "v11.0.0-beta.11", "git" = "https://github.com/lance-format/lance.git" }
lance-testing = { "version" = "=11.0.0-beta.11", "tag" = "v11.0.0-beta.11", "git" = "https://github.com/lance-format/lance.git" }
lance-datafusion = { "version" = "=11.0.0-beta.11", "tag" = "v11.0.0-beta.11", "git" = "https://github.com/lance-format/lance.git" }
lance-encoding = { "version" = "=11.0.0-beta.11", "tag" = "v11.0.0-beta.11", "git" = "https://github.com/lance-format/lance.git" }
lance-arrow = { "version" = "=11.0.0-beta.11", "tag" = "v11.0.0-beta.11", "git" = "https://github.com/lance-format/lance.git" }
ahash = "0.8"
# Note that this one does not include pyarrow
arrow = { version = "58.0.0", optional = false }
deny.toml
+7
View File
@@ -101,6 +101,13 @@ ignore = [
# https://rustsec.org/advisories/RUSTSEC-2026-0195
{ id = "RUSTSEC-2026-0194", reason = "transitive via inferno/lance/opendal; XML from trusted cloud endpoints, not attacker-controlled" },
{ id = "RUSTSEC-2026-0195", reason = "transitive via inferno/lance/opendal; XML from trusted cloud endpoints, not attacker-controlled" },
# smartstring: unmaintained — the repository was archived by its author on
# 2026-05-03. Not a vulnerability. Reached only transitively through polars
# (polars-core/-io/-ops/-time/-utils); nothing in LanceDB depends on it directly.
# The advisory states no safe upgrade is available: upstream recommends
# compact_str/smol_str, so clearing this requires polars to migrate.
# https://rustsec.org/advisories/RUSTSEC-2026-0249
{ id = "RUSTSEC-2026-0249", reason = "smartstring unmaintained via polars; no fixed upstream release" },
]
# ---------------------------------------------------------------------------
docs/src/java/java.md
+1 -1
View File
@@ -14,7 +14,7 @@ Add the following dependency to your `pom.xml`:
<dependency>
<groupId>com.lancedb</groupId>
<artifactId>lancedb-core</artifactId>
<version>0.37.1-beta.0</version>
<version>0.38.0-beta.0</version>
</dependency>
```
docs/src/js/classes/Connection.md
+23
View File
@@ -386,6 +386,29 @@ Drop an existing table.
***
### dropTableAsync()
```ts
abstract dropTableAsync(name, namespacePath?): Promise<Job>
```
Start dropping a table and return its cleanup job.
The table may become unavailable before its data files are removed. Wait
on the returned job to know when cleanup has finished.
#### Parameters
* **name**: `string`
* **namespacePath?**: `string`[]
#### Returns
`Promise`&lt;[`Job`](Job.md)&gt;
***
### getJob()
```ts
docs/src/js/classes/Table.md
+62 -4
View File
@@ -69,14 +69,33 @@ abstract addColumns(newColumnTransforms): Promise<AddColumnsResult>
Add new columns with defined values.
The `{ computed }` form stores the expression rather than evaluating it
now: the column is committed with no values, and rows get them from
[Table#refreshColumn](Table.md#refreshcolumn). Declaring one therefore costs the same on a
large table as on an empty one.
A refresh does not revisit rows it has already filled, so mutating an
input leaves the value computed at fill time; recomputing means dropping
the column and declaring it again. While a declaration reads a column,
that column cannot be renamed, retyped or dropped.
Computed columns are local-only: LanceDB Cloud and Enterprise reject a
declaration.
#### Parameters
* **newColumnTransforms**: `Field`&lt;`any`&gt; \| `Field`&lt;`any`&gt;[] \| `Schema`&lt;`any`&gt; \| [`AddColumnsSql`](../interfaces/AddColumnsSql.md)[]
* **newColumnTransforms**:
\| `Field`&lt;`any`&gt;
\| `Field`&lt;`any`&gt;[]
\| `Schema`&lt;`any`&gt;
\| [`AddColumnsSql`](../interfaces/AddColumnsSql.md)[]
\| `object`
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)
- `{ computed }`, declaring columns defined by a SQL expression whose type and inputs are derived from it
#### Returns
@@ -85,6 +104,13 @@ Add new columns with defined values.
A promise that resolves to an object
containing the new version number of the table after adding the columns.
#### Example
```ts
await table.addColumns({ computed: [{ name: "doubled", valueSql: "x * 2" }] });
const { rowsFilled } = await table.refreshColumn("doubled");
```
***
### alterColumns()
@@ -431,9 +457,10 @@ Read the [LsmWriteSpec](../interfaces/LsmWriteSpec.md) currently installed on th
Resolves to `undefined` when the MemWAL LSM write path is not enabled (no
spec has been set, or it was removed with [Table#unsetLsmWriteSpec](Table.md#unsetlsmwritespec)).
The returned spec — including its `maintainedIndexes` and
`writerConfigDefaults` — mirrors what was passed to
[Table#setLsmWriteSpec](Table.md#setlsmwritespec).
The returned spec mirrors what was passed to
[Table#setLsmWriteSpec](Table.md#setlsmwritespec), except that `maintainedIndexes` always
reports the concrete list resolved when the spec was set — `undefined`
never round-trips.
#### Returns
@@ -717,6 +744,32 @@ for await (const batch of table.query()) {
***
### refreshColumn()
```ts
abstract refreshColumn(column): Promise<RefreshColumnResult>
```
Fill the rows of a computed column that hold no value yet.
Rows appended since the last refresh are filled by the next one; rows
already filled are left as they are, so the call is idempotent and does
not observe a mutated input. Local tables only.
#### Parameters
* **column**: `string`
The name of the computed column to fill.
#### Returns
`Promise`&lt;[`RefreshColumnResult`](../interfaces/RefreshColumnResult.md)&gt;
A promise that resolves to the
number of rows filled and the new version number of the table.
***
### restore()
```ts
@@ -806,6 +859,11 @@ All variants require the table to have an unenforced primary key
([Table#setUnenforcedPrimaryKey](Table.md#setunenforcedprimarykey)); bucket sharding additionally
requires it to be the single column being bucketed.
Omitting `maintainedIndexes` maintains every index on the table, resolved
here, failing if one cannot be maintained — name them to install anyway.
Naming them pins an exact set, and a still-building index is rejected
rather than quietly omitted.
#### Parameters
* **spec**: [`LsmWriteSpec`](../interfaces/LsmWriteSpec.md)
docs/src/js/globals.md
+1
View File
@@ -105,6 +105,7 @@
- [OptimizeOptions](interfaces/OptimizeOptions.md)
- [OptimizeStats](interfaces/OptimizeStats.md)
- [QueryExecutionOptions](interfaces/QueryExecutionOptions.md)
- [RefreshColumnResult](interfaces/RefreshColumnResult.md)
- [RemovalStats](interfaces/RemovalStats.md)
- [RenameTableOptions](interfaces/RenameTableOptions.md)
- [RestNamespaceConfig](interfaces/RestNamespaceConfig.md)
docs/src/js/interfaces/LsmWriteSpec.md
+3 -1
View File
@@ -34,7 +34,9 @@ Bucket and identity variants: the sharding column.
optional maintainedIndexes: string[];
```
Names of indexes the MemWAL should keep up to date during writes.
Indexes the MemWAL keeps up to date. Omit to maintain every supported
index, resolved on install — a snapshot, so indexes created later are not
maintained. Pass `[]` for none.
***
docs/src/js/interfaces/RefreshColumnResult.md
+23
View File
@@ -0,0 +1,23 @@
[**@lancedb/lancedb**](../README.md) • **Docs**
***
[@lancedb/lancedb](../globals.md) / RefreshColumnResult
# Interface: RefreshColumnResult
## Properties
### rowsFilled
```ts
rowsFilled: number;
```
***
### version
```ts
version: number;
```
docs/src/js/interfaces/TableStatistics.md
+4 -1
View File
@@ -44,4 +44,7 @@ The number of rows in the table
totalBytes: number;
```
The total number of bytes in the table
The total size, in bytes, of the table's data files, index files, and
overlay files
Read from the manifest, so this excludes deletion files and manifests.
java/lancedb-core/pom.xml
+1 -1
View File
@@ -8,7 +8,7 @@
<parent>
<groupId>com.lancedb</groupId>
<artifactId>lancedb-parent</artifactId>
<version>0.37.1-beta.0</version>
<version>0.38.0-beta.0</version>
<relativePath>../pom.xml</relativePath>
</parent>
java/pom.xml
+2 -2
View File
@@ -6,7 +6,7 @@
<groupId>com.lancedb</groupId>
<artifactId>lancedb-parent</artifactId>
<version>0.37.1-beta.0</version>
<version>0.38.0-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>11.0.0-beta.3</lance-core.version>
<lance-core.version>11.0.0-beta.11</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>
nodejs/Cargo.toml
+1 -1
View File
@@ -1,7 +1,7 @@
[package]
name = "lancedb-nodejs"
edition.workspace = true
version = "0.37.1-beta.0"
version = "0.38.0-beta.0"
publish = false
license.workspace = true
description.workspace = true
nodejs/__test__/arrow.test.ts
+115
View File
@@ -6,7 +6,9 @@ import * as arrow17 from "apache-arrow-17";
import * as arrow18 from "apache-arrow-18";
import {
Vector as CurrentVector,
convertToTable,
tableFromIPC as currentTableFromIPC,
fromBufferToRecordBatch,
fromDataToBuffer,
fromRecordBatchToBuffer,
@@ -19,6 +21,7 @@ import {
FunctionOptions,
} from "../lancedb/embedding/embedding_function";
import { EmbeddingFunctionConfig } from "../lancedb/embedding/registry";
import { sanitizeTable } from "../lancedb/sanitize";
// biome-ignore lint/suspicious/noExplicitAny: skip
function sampleRecords(): Array<Record<string, any>> {
@@ -64,7 +67,11 @@ describe.each([arrow15, arrow16, arrow17, arrow18])(
tableFromIPC,
DataType,
Dictionary,
RecordBatch: ArrowRecordBatch,
Table: ArrowTable,
Uint8: ArrowUint8,
makeData: arrowMakeData,
vectorFromArray,
// biome-ignore lint/suspicious/noExplicitAny: <explanation>
} = <any>arrow;
type Schema = ApacheArrow["Schema"];
@@ -1054,6 +1061,114 @@ describe.each([arrow15, arrow16, arrow17, arrow18])(
});
describe("when using two versions of arrow", function () {
it("preserves a dictionary shared by multiple fields", async function () {
const values = ["alpha", "beta", "alpha"];
const dictionaryVector = vectorFromArray(values);
const batch = new ArrowRecordBatch({
first: dictionaryVector.data[0],
second: dictionaryVector.data[0],
});
const table = new ArrowTable([batch]);
const sanitized = sanitizeTable(table);
expect([...sanitized.getChild("first")!]).toEqual(values);
expect([...sanitized.getChild("second")!]).toEqual(values);
const firstType = sanitized.schema.fields[0].type as {
dictionary: unknown;
};
const secondType = sanitized.schema.fields[1].type as {
dictionary: unknown;
};
expect(secondType.dictionary).toBe(firstType.dictionary);
expect(sanitized.batches[0].data.children[1].dictionary).toBe(
sanitized.batches[0].data.children[0].dictionary,
);
const buf = await fromDataToBuffer(table);
const actual = currentTableFromIPC(buf);
expect([...actual.getChild("first")!]).toEqual(values);
expect([...actual.getChild("second")!]).toEqual(values);
});
it("preserves shared dictionary data from another Arrow version", async function () {
const values = ["alpha", "beta", "alpha"];
const dictionaryVector = vectorFromArray(values);
const firstBatch = new ArrowRecordBatch({
label: dictionaryVector.slice(0, 2).data[0],
});
const secondBatch = new ArrowRecordBatch({
label: dictionaryVector.slice(2).data[0],
});
const table = new ArrowTable([firstBatch, secondBatch]);
const sanitized = sanitizeTable(table);
expect([...sanitized.getChild("label")!]).toEqual(values);
const dictionaries = sanitized.batches.map(
(batch) => batch.data.children[0].dictionary,
);
expect(dictionaries[0]).toBeInstanceOf(CurrentVector);
expect(dictionaries[1]).toBe(dictionaries[0]);
const buf = await fromDataToBuffer(table);
const actual = currentTableFromIPC(buf);
expect([...actual.getChild("label")!]).toEqual(values);
});
it("preserves shared chunks in growing dictionaries", async function () {
const type = new Dictionary(new Utf8(), new Int32(), 42, false);
const firstDictionary = vectorFromArray(["alpha", "beta"], new Utf8());
const secondDictionary = firstDictionary.concat(
vectorFromArray(["gamma"], new Utf8()),
);
const firstData = arrowMakeData({
type,
data: Int32Array.from([0, 1]),
dictionary: firstDictionary,
});
const secondData = arrowMakeData({
type,
data: Int32Array.from([2]),
dictionary: secondDictionary,
});
const table = new ArrowTable([
new ArrowRecordBatch({ label: firstData }),
new ArrowRecordBatch({ label: secondData }),
]);
const sanitized = sanitizeTable(table);
const expected = ["alpha", "beta", "gamma"];
expect([...sanitized.getChild("label")!]).toEqual(expected);
const firstLocalDictionary =
sanitized.batches[0].data.children[0].dictionary!;
const secondLocalDictionary =
sanitized.batches[1].data.children[0].dictionary!;
expect(secondLocalDictionary.data[0]).toBe(
firstLocalDictionary.data[0],
);
const buf = await fromTableToBuffer(sanitized);
const actual = currentTableFromIPC(buf);
expect([...actual.getChild("label")!]).toEqual(expected);
});
it("can serialize list data from another Arrow version", async function () {
const values = [["anime", "action"], [], null];
const vector = vectorFromArray(
values,
new List(new Field("item", new Utf8(), true)),
);
const table = new ArrowTable({ tags: vector });
const buf = await fromDataToBuffer(table);
const actual = currentTableFromIPC(buf);
const actualTags = actual.getChild("tags");
expect(actualTags?.get(0)?.toJSON()).toEqual(values[0]);
expect(actualTags?.get(1)?.toJSON()).toEqual(values[1]);
expect(actualTags?.get(2)).toBeNull();
});
it("can still import data", async function () {
const schema = new arrow15.Schema([
new arrow15.Field("id", new arrow15.Int32()),
nodejs/__test__/connection.test.ts
+10
View File
@@ -89,6 +89,16 @@ describe("given a connection", () => {
await db.createTable("test4", [{ id: 1 }, { id: 2 }]);
});
it("should return a completed job when dropping a local table", async () => {
await db.createTable("async-drop", [{ id: 1 }]);
const job = await db.dropTableAsync("async-drop");
expect(job.id).toBeNull();
await expect(job.status()).resolves.toBe("finished");
await job.wait();
await expect(db.tableNames()).resolves.toEqual([]);
});
it("should fail if creating table twice, unless overwrite is true", async () => {
let tbl = await db.createTable("test", [{ id: 1 }, { id: 2 }]);
await expect(tbl.countRows()).resolves.toBe(2);
nodejs/__test__/table.test.ts
+51 -1
View File
@@ -277,8 +277,16 @@ describe.each([arrow15, arrow16, arrow17, arrow18])(
},
numIndices: 0,
numRows: 3,
totalBytes: 44,
// Full on-disk size of the two data files, footers and metadata included.
totalBytes: 684,
});
// Index files count toward totalBytes too (only deletion files and
// manifests are excluded).
await table.createIndex("id", { config: Index.btree() });
const statsWithIndex = await table.stats();
expect(statsWithIndex.numIndices).toBe(1);
expect(statsWithIndex.totalBytes).toBeGreaterThan(684);
});
it("should overwrite data if asked", async () => {
@@ -3332,3 +3340,45 @@ describe("LSM merge insert", () => {
await expect(table.query().useLsm(true).toArray()).rejects.toThrow();
});
});
describe("computed columns", () => {
let tmpDir: tmp.DirResult;
beforeEach(() => {
tmpDir = tmp.dirSync({ unsafeCleanup: true });
});
afterEach(() => tmpDir.removeCallback());
it("declares a column and fills it on refresh", async () => {
const db = await connect(tmpDir.name);
const table = await db.createTable("computed", [{ x: 1 }, { x: 2 }]);
await table.addColumns({
computed: [{ name: "doubled", valueSql: "x * 2" }],
});
let rows = await table.query().toArray();
expect(rows.map((r) => r.doubled)).toEqual([null, null]);
const result = await table.refreshColumn("doubled");
expect(result.rowsFilled).toBe(2);
rows = await table.query().toArray();
expect(rows.map((r) => r.doubled).sort()).toEqual([2, 4]);
});
it("fills rows added since the last refresh", async () => {
const db = await connect(tmpDir.name);
const table = await db.createTable("computed_append", [{ x: 1 }]);
await table.addColumns({
computed: [{ name: "doubled", valueSql: "x * 2" }],
});
await table.refreshColumn("doubled");
await table.add([{ x: 5 }]);
const result = await table.refreshColumn("doubled");
expect(result.rowsFilled).toBe(1);
const rows = await table.query().toArray();
expect(rows.map((r) => r.doubled).sort()).toEqual([10, 2]);
});
});
nodejs/lancedb/connection.ts
+12
View File
@@ -327,6 +327,14 @@ export abstract class Connection {
*/
abstract dropTable(name: string, namespacePath?: string[]): Promise<void>;
/**
* Start dropping a table and return its cleanup job.
*
* The table may become unavailable before its data files are removed. Wait
* on the returned job to know when cleanup has finished.
*/
abstract dropTableAsync(name: string, namespacePath?: string[]): Promise<Job>;
/**
* Drop all tables in the database.
* @param {string[]} namespacePath The namespace path to drop tables from (defaults to root namespace).
@@ -705,6 +713,10 @@ export class LocalConnection extends Connection {
return this.inner.dropTable(name, namespacePath ?? []);
}
async dropTableAsync(name: string, namespacePath?: string[]): Promise<Job> {
return this.inner.dropTableAsync(name, namespacePath ?? []);
}
async dropAllTables(namespacePath?: string[]): Promise<void> {
return this.inner.dropAllTables(namespacePath ?? []);
}
nodejs/lancedb/index.ts
+1
View File
@@ -50,6 +50,7 @@ export {
MergeResult,
AddResult,
AddColumnsResult,
RefreshColumnResult,
AlterColumnsResult,
UpdateFieldMetadataResult,
DeleteResult,
nodejs/lancedb/sanitize.ts
+174 -29
View File
@@ -9,7 +9,7 @@
// comes from the exact same library instance. This is not always the case
// and so we must sanitize the input to ensure that it is compatible.
import { BufferType, Data } from "apache-arrow";
import { BufferType, Data, Vector } from "apache-arrow";
import type { IntBitWidth, TKeys, TimeBitWidth } from "apache-arrow/type";
import {
Binary,
@@ -74,6 +74,20 @@ import {
Utf8,
} from "./arrow";
type SanitizationContext = {
types: WeakMap<object, DataType>;
vectors: WeakMap<object, Vector>;
data: WeakMap<object, Data<DataType>>;
};
function createSanitizationContext(): SanitizationContext {
return {
types: new WeakMap(),
vectors: new WeakMap(),
data: new WeakMap(),
};
}
export function sanitizeMetadata(
metadataLike?: unknown,
): Map<string, string> | undefined {
@@ -186,6 +200,13 @@ export function sanitizeInterval(typeLike: object) {
}
export function sanitizeList(typeLike: object) {
return sanitizeListWithContext(typeLike, createSanitizationContext());
}
function sanitizeListWithContext(
typeLike: object,
context: SanitizationContext,
) {
if (!("children" in typeLike) || !Array.isArray(typeLike.children)) {
throw Error(
"Expected a List type to have an array-like `children` property",
@@ -194,19 +215,35 @@ export function sanitizeList(typeLike: object) {
if (typeLike.children.length !== 1) {
throw Error("Expected a List type to have exactly one child");
}
return new List(sanitizeField(typeLike.children[0]));
return new List(sanitizeFieldWithContext(typeLike.children[0], context));
}
export function sanitizeStruct(typeLike: object) {
return sanitizeStructWithContext(typeLike, createSanitizationContext());
}
function sanitizeStructWithContext(
typeLike: object,
context: SanitizationContext,
) {
if (!("children" in typeLike) || !Array.isArray(typeLike.children)) {
throw Error(
"Expected a Struct type to have an array-like `children` property",
);
}
return new Struct(typeLike.children.map((child) => sanitizeField(child)));
return new Struct(
typeLike.children.map((child) => sanitizeFieldWithContext(child, context)),
);
}
export function sanitizeUnion(typeLike: object) {
return sanitizeUnionWithContext(typeLike, createSanitizationContext());
}
function sanitizeUnionWithContext(
typeLike: object,
context: SanitizationContext,
) {
if (
!("typeIds" in typeLike) ||
!("mode" in typeLike) ||
@@ -226,7 +263,7 @@ export function sanitizeUnion(typeLike: object) {
typeLike.mode,
// biome-ignore lint/suspicious/noExplicitAny: skip
typeLike.typeIds as any,
typeLike.children.map((child) => sanitizeField(child)),
typeLike.children.map((child) => sanitizeFieldWithContext(child, context)),
);
}
@@ -234,6 +271,19 @@ export function sanitizeTypedUnion(
typeLike: object,
// eslint-disable-next-line @typescript-eslint/naming-convention
UnionType: typeof DenseUnion | typeof SparseUnion,
) {
return sanitizeTypedUnionWithContext(
typeLike,
UnionType,
createSanitizationContext(),
);
}
function sanitizeTypedUnionWithContext(
typeLike: object,
// eslint-disable-next-line @typescript-eslint/naming-convention
UnionType: typeof DenseUnion | typeof SparseUnion,
context: SanitizationContext,
) {
if (!("typeIds" in typeLike)) {
throw Error(
@@ -248,7 +298,7 @@ export function sanitizeTypedUnion(
return new UnionType(
typeLike.typeIds as Int32Array | number[],
typeLike.children.map((child) => sanitizeField(child)),
typeLike.children.map((child) => sanitizeFieldWithContext(child, context)),
);
}
@@ -262,6 +312,16 @@ export function sanitizeFixedSizeBinary(typeLike: object) {
}
export function sanitizeFixedSizeList(typeLike: object) {
return sanitizeFixedSizeListWithContext(
typeLike,
createSanitizationContext(),
);
}
function sanitizeFixedSizeListWithContext(
typeLike: object,
context: SanitizationContext,
) {
if (!("listSize" in typeLike) || typeof typeLike.listSize !== "number") {
throw Error("Expected a FixedSizeList type to have a `listSize` property");
}
@@ -275,11 +335,18 @@ export function sanitizeFixedSizeList(typeLike: object) {
}
return new FixedSizeList(
typeLike.listSize,
sanitizeField(typeLike.children[0]),
sanitizeFieldWithContext(typeLike.children[0], context),
);
}
export function sanitizeMap(typeLike: object) {
return sanitizeMapWithContext(typeLike, createSanitizationContext());
}
function sanitizeMapWithContext(
typeLike: object,
context: SanitizationContext,
) {
if (!("children" in typeLike) || !Array.isArray(typeLike.children)) {
throw Error(
"Expected a Map type to have an array-like `children` property",
@@ -292,7 +359,10 @@ export function sanitizeMap(typeLike: object) {
throw Error("Expected a Map type to have exactly one child");
}
return new Map_(sanitizeField(typeLike.children[0]), typeLike.keysSorted);
return new Map_(
sanitizeFieldWithContext(typeLike.children[0], context),
typeLike.keysSorted,
);
}
export function sanitizeDuration(typeLike: object) {
@@ -303,6 +373,13 @@ export function sanitizeDuration(typeLike: object) {
}
export function sanitizeDictionary(typeLike: object) {
return sanitizeDictionaryWithContext(typeLike, createSanitizationContext());
}
function sanitizeDictionaryWithContext(
typeLike: object,
context: SanitizationContext,
) {
if (!("id" in typeLike) || typeof typeLike.id !== "number") {
throw Error("Expected a Dictionary type to have an `id` property");
}
@@ -316,8 +393,8 @@ export function sanitizeDictionary(typeLike: object) {
throw Error("Expected a Dictionary type to have an `isOrdered` property");
}
return new Dictionary(
sanitizeType(typeLike.dictionary),
sanitizeType(typeLike.indices) as TKeys,
sanitizeTypeWithContext(typeLike.dictionary, context),
sanitizeTypeWithContext(typeLike.indices, context) as TKeys,
typeLike.id,
typeLike.isOrdered,
);
@@ -325,12 +402,23 @@ export function sanitizeDictionary(typeLike: object) {
// biome-ignore lint/suspicious/noExplicitAny: skip
export function sanitizeType(typeLike: unknown): DataType<any> {
return sanitizeTypeWithContext(typeLike, createSanitizationContext());
}
function sanitizeTypeWithContext(
typeLike: unknown,
context: SanitizationContext,
): DataType {
if (typeof typeLike === "string") {
return dataTypeFromName(typeLike);
}
if (typeof typeLike !== "object" || typeLike === null) {
throw Error("Expected a Type but object was null/undefined");
}
const cached = context.types.get(typeLike);
if (cached !== undefined) {
return cached;
}
if (
!("typeId" in typeLike) ||
!(
@@ -349,6 +437,16 @@ export function sanitizeType(typeLike: unknown): DataType<any> {
throw Error("Type's typeId property was not a function or number");
}
const type = sanitizeTypeById(typeLike, typeId, context);
context.types.set(typeLike, type);
return type;
}
function sanitizeTypeById(
typeLike: object,
typeId: Type,
context: SanitizationContext,
): DataType {
switch (typeId) {
case Type.NONE:
throw Error("Received a Type with a typeId of NONE");
@@ -375,21 +473,21 @@ export function sanitizeType(typeLike: unknown): DataType<any> {
case Type.Interval:
return sanitizeInterval(typeLike);
case Type.List:
return sanitizeList(typeLike);
return sanitizeListWithContext(typeLike, context);
case Type.Struct:
return sanitizeStruct(typeLike);
return sanitizeStructWithContext(typeLike, context);
case Type.Union:
return sanitizeUnion(typeLike);
return sanitizeUnionWithContext(typeLike, context);
case Type.FixedSizeBinary:
return sanitizeFixedSizeBinary(typeLike);
case Type.FixedSizeList:
return sanitizeFixedSizeList(typeLike);
return sanitizeFixedSizeListWithContext(typeLike, context);
case Type.Map:
return sanitizeMap(typeLike);
return sanitizeMapWithContext(typeLike, context);
case Type.Duration:
return sanitizeDuration(typeLike);
case Type.Dictionary:
return sanitizeDictionary(typeLike);
return sanitizeDictionaryWithContext(typeLike, context);
case Type.Int8:
return new Int8();
case Type.Int16:
@@ -433,9 +531,9 @@ export function sanitizeType(typeLike: unknown): DataType<any> {
case Type.TimestampSecond:
return sanitizeTypedTimestamp(typeLike, TimestampSecond);
case Type.DenseUnion:
return sanitizeTypedUnion(typeLike, DenseUnion);
return sanitizeTypedUnionWithContext(typeLike, DenseUnion, context);
case Type.SparseUnion:
return sanitizeTypedUnion(typeLike, SparseUnion);
return sanitizeTypedUnionWithContext(typeLike, SparseUnion, context);
case Type.IntervalDayTime:
return new IntervalDayTime();
case Type.IntervalYearMonth:
@@ -454,6 +552,13 @@ export function sanitizeType(typeLike: unknown): DataType<any> {
}
export function sanitizeField(fieldLike: unknown): Field {
return sanitizeFieldWithContext(fieldLike, createSanitizationContext());
}
function sanitizeFieldWithContext(
fieldLike: unknown,
context: SanitizationContext,
): Field {
if (fieldLike instanceof Field) {
return fieldLike;
}
@@ -471,7 +576,7 @@ export function sanitizeField(fieldLike: unknown): Field {
}
let type: DataType;
try {
type = sanitizeType(fieldLike.type);
type = sanitizeTypeWithContext(fieldLike.type, context);
} catch (error: unknown) {
throw Error(
`Unable to sanitize type for field: ${fieldLike.name} due to error: ${error}`,
@@ -501,6 +606,13 @@ export function sanitizeField(fieldLike: unknown): Field {
* than lancedb is using.
*/
export function sanitizeSchema(schemaLike: SchemaLike): Schema {
return sanitizeSchemaWithContext(schemaLike, createSanitizationContext());
}
function sanitizeSchemaWithContext(
schemaLike: SchemaLike,
context: SanitizationContext,
): Schema {
if (schemaLike instanceof Schema) {
return schemaLike;
}
@@ -522,7 +634,7 @@ export function sanitizeSchema(schemaLike: SchemaLike): Schema {
);
}
const sanitizedFields = schemaLike.fields.map((field) =>
sanitizeField(field),
sanitizeFieldWithContext(field, context),
);
return new Schema(sanitizedFields, metadata);
}
@@ -544,13 +656,18 @@ export function sanitizeTable(tableLike: TableLike): Table {
"The table passed in does not appear to be a table (no 'columns' property)",
);
}
const schema = sanitizeSchema(tableLike.schema);
const batches = tableLike.batches.map(sanitizeRecordBatch);
const context = createSanitizationContext();
const schema = sanitizeSchemaWithContext(tableLike.schema, context);
const batches = tableLike.batches.map((batch) =>
sanitizeRecordBatch(batch, context),
);
return new Table(schema, batches);
}
function sanitizeRecordBatch(batchLike: RecordBatchLike): RecordBatch {
function sanitizeRecordBatch(
batchLike: RecordBatchLike,
context: SanitizationContext,
): RecordBatch {
if (batchLike instanceof RecordBatch) {
return batchLike;
}
@@ -567,19 +684,43 @@ function sanitizeRecordBatch(batchLike: RecordBatchLike): RecordBatch {
"The record batch passed in does not appear to be a record batch (no 'data' property)",
);
}
const schema = sanitizeSchema(batchLike.schema);
const data = sanitizeData(batchLike.data);
const schema = sanitizeSchemaWithContext(batchLike.schema, context);
const data = sanitizeData(batchLike.data, context) as Data<Struct>;
return new RecordBatch(schema, data);
}
type DictionaryVectorLike = {
data: readonly DataLike[];
};
type DictionaryDataLike = DataLike & {
dictionary?: DictionaryVectorLike;
};
function sanitizeData(
dataLike: DataLike,
// biome-ignore lint/suspicious/noExplicitAny: <explanation>
): import("apache-arrow").Data<Struct<any>> {
context: SanitizationContext,
): Data<DataType> {
if (dataLike instanceof Data) {
return dataLike;
}
return new Data(
dataLike.type,
const cachedData = context.data.get(dataLike);
if (cachedData !== undefined) {
return cachedData;
}
const dictionaryLike = (dataLike as DictionaryDataLike).dictionary;
let dictionary: Vector | undefined;
if (dictionaryLike !== undefined) {
dictionary = context.vectors.get(dictionaryLike);
if (dictionary === undefined) {
dictionary = new Vector(
dictionaryLike.data.map((data) => sanitizeData(data, context)),
);
context.vectors.set(dictionaryLike, dictionary);
}
}
const data = new Data(
sanitizeTypeWithContext(dataLike.type, context),
dataLike.offset,
dataLike.length,
dataLike.nullCount,
@@ -589,7 +730,11 @@ function sanitizeData(
[BufferType.VALIDITY]: dataLike.nullBitmap,
[BufferType.TYPE]: dataLike.typeIds,
},
dataLike.children.map((child) => sanitizeData(child, context)),
dictionary,
);
context.data.set(dataLike, data);
return data;
}
const constructorsByTypeName = {
nodejs/lancedb/table.ts
+71 -6
View File
@@ -33,6 +33,7 @@ import {
Job,
Branches as NativeBranches,
OptimizeStats,
RefreshColumnResult,
TableStatistics,
Tags,
UpdateFieldMetadataResult,
@@ -197,7 +198,11 @@ export interface LsmWriteSpec {
column?: string;
/** Bucket variant: the number of buckets, in `[1, 1024]`. */
numBuckets?: number;
/** Names of indexes the MemWAL should keep up to date during writes. */
/**
* Indexes the MemWAL keeps up to date. Omit to maintain every supported
* index, resolved on install — a snapshot, so indexes created later are not
* maintained. Pass `[]` for none.
*/
maintainedIndexes?: string[];
/** Default `ShardWriter` configuration recorded in the MemWAL index. */
writerConfigDefaults?: Record<string, string>;
@@ -521,18 +526,54 @@ export abstract class Table {
abstract vectorSearch(vector: IntoVector | MultiVector): VectorQuery;
/**
* Add new columns with defined values.
*
* The `{ computed }` form stores the expression rather than evaluating it
* now: the column is committed with no values, and rows get them from
* {@link Table#refreshColumn}. Declaring one therefore costs the same on a
* large table as on an empty one.
*
* A refresh does not revisit rows it has already filled, so mutating an
* input leaves the value computed at fill time; recomputing means dropping
* the column and declaring it again. While a declaration reads a column,
* that column cannot be renamed, retyped or dropped.
*
* Computed columns are local-only: LanceDB Cloud and Enterprise reject a
* declaration.
* @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)
* - `{ computed }`, declaring columns defined by a SQL expression whose type and inputs are derived from it
* @returns {Promise<AddColumnsResult>} A promise that resolves to an object
* containing the new version number of the table after adding the columns.
* @example
* ```ts
* await table.addColumns({ computed: [{ name: "doubled", valueSql: "x * 2" }] });
* const { rowsFilled } = await table.refreshColumn("doubled");
* ```
*/
abstract addColumns(
newColumnTransforms: AddColumnsSql[] | Field | Field[] | Schema,
newColumnTransforms:
| AddColumnsSql[]
| Field
| Field[]
| Schema
| { computed: AddColumnsSql[] },
): Promise<AddColumnsResult>;
/**
* Fill the rows of a computed column that hold no value yet.
*
* Rows appended since the last refresh are filled by the next one; rows
* already filled are left as they are, so the call is idempotent and does
* not observe a mutated input. Local tables only.
* @param {string} column The name of the computed column to fill.
* @returns {Promise<RefreshColumnResult>} A promise that resolves to the
* number of rows filled and the new version number of the table.
*/
abstract refreshColumn(column: string): Promise<RefreshColumnResult>;
/**
* Alter the name or nullability of columns.
* @param {ColumnAlteration[]} columnAlterations One or more alterations to
@@ -595,6 +636,11 @@ export abstract class Table {
* All variants require the table to have an unenforced primary key
* ({@link Table#setUnenforcedPrimaryKey}); bucket sharding additionally
* requires it to be the single column being bucketed.
*
* Omitting `maintainedIndexes` maintains every index on the table, resolved
* here, failing if one cannot be maintained — name them to install anyway.
* Naming them pins an exact set, and a still-building index is rejected
* rather than quietly omitted.
* @param {LsmWriteSpec} spec The sharding spec to install.
* @returns {Promise<void>}
* @example
@@ -622,9 +668,10 @@ export abstract class Table {
*
* Resolves to `undefined` when the MemWAL LSM write path is not enabled (no
* spec has been set, or it was removed with {@link Table#unsetLsmWriteSpec}).
* The returned spec — including its `maintainedIndexes` and
* `writerConfigDefaults` — mirrors what was passed to
* {@link Table#setLsmWriteSpec}.
* The returned spec mirrors what was passed to
* {@link Table#setLsmWriteSpec}, except that `maintainedIndexes` always
* reports the concrete list resolved when the spec was set — `undefined`
* never round-trips.
* @returns {Promise<LsmWriteSpec | undefined>}
*/
abstract getLsmWriteSpec(): Promise<LsmWriteSpec | undefined>;
@@ -1078,8 +1125,22 @@ export class LocalTable extends Table {
// TODO: Support BatchUDF
async addColumns(
newColumnTransforms: AddColumnsSql[] | Field | Field[] | Schema,
newColumnTransforms:
| AddColumnsSql[]
| Field
| Field[]
| Schema
| { computed: AddColumnsSql[] },
): Promise<AddColumnsResult> {
// Columns defined by an expression are declared, not materialized here.
if (
typeof newColumnTransforms === "object" &&
!Array.isArray(newColumnTransforms) &&
"computed" in newColumnTransforms
) {
return await this.inner.addComputedColumns(newColumnTransforms.computed);
}
// Handle single Field -> convert to array of Fields
if (newColumnTransforms instanceof Field) {
newColumnTransforms = [newColumnTransforms];
@@ -1114,6 +1175,10 @@ export class LocalTable extends Table {
throw new Error("Invalid input type for addColumns");
}
async refreshColumn(column: string): Promise<RefreshColumnResult> {
return await this.inner.refreshColumn(column);
}
async alterColumns(
columnAlterations: ColumnAlteration[],
): Promise<AlterColumnsResult> {
nodejs/npm/darwin-arm64/package.json
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "@lancedb/lancedb-darwin-arm64",
"version": "0.37.1-beta.0",
"version": "0.38.0-beta.0",
"os": ["darwin"],
"cpu": ["arm64"],
"main": "lancedb.darwin-arm64.node",
nodejs/npm/linux-arm64-gnu/package.json
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "@lancedb/lancedb-linux-arm64-gnu",
"version": "0.37.1-beta.0",
"version": "0.38.0-beta.0",
"os": ["linux"],
"cpu": ["arm64"],
"main": "lancedb.linux-arm64-gnu.node",
nodejs/npm/linux-arm64-musl/package.json
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "@lancedb/lancedb-linux-arm64-musl",
"version": "0.37.1-beta.0",
"version": "0.38.0-beta.0",
"os": ["linux"],
"cpu": ["arm64"],
"main": "lancedb.linux-arm64-musl.node",
nodejs/npm/linux-x64-gnu/package.json
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "@lancedb/lancedb-linux-x64-gnu",
"version": "0.37.1-beta.0",
"version": "0.38.0-beta.0",
"os": ["linux"],
"cpu": ["x64"],
"main": "lancedb.linux-x64-gnu.node",
nodejs/npm/linux-x64-musl/package.json
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "@lancedb/lancedb-linux-x64-musl",
"version": "0.37.1-beta.0",
"version": "0.38.0-beta.0",
"os": ["linux"],
"cpu": ["x64"],
"main": "lancedb.linux-x64-musl.node",
nodejs/npm/win32-arm64-msvc/package.json
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "@lancedb/lancedb-win32-arm64-msvc",
"version": "0.37.1-beta.0",
"version": "0.38.0-beta.0",
"os": [
"win32"
],
nodejs/npm/win32-x64-msvc/package.json
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "@lancedb/lancedb-win32-x64-msvc",
"version": "0.37.1-beta.0",
"version": "0.38.0-beta.0",
"os": ["win32"],
"cpu": ["x64"],
"main": "lancedb.win32-x64-msvc.node",
nodejs/package-lock.json
Generated
+2 -2
View File
@@ -1,12 +1,12 @@
{
"name": "@lancedb/lancedb",
"version": "0.37.1-beta.0",
"version": "0.38.0-beta.0",
"lockfileVersion": 3,
"requires": true,
"packages": {
"": {
"name": "@lancedb/lancedb",
"version": "0.37.1-beta.0",
"version": "0.38.0-beta.0",
"cpu": [
"x64",
"arm64"
nodejs/package.json
+1 -1
View File
@@ -11,7 +11,7 @@
"ann"
],
"private": false,
"version": "0.37.1-beta.0",
"version": "0.38.0-beta.0",
"main": "dist/index.js",
"exports": {
".": "./dist/index.js",
nodejs/src/connection.rs
+16
View File
@@ -334,6 +334,22 @@ impl Connection {
.default_error()
}
/// Start dropping a table and return its cleanup job.
#[napi(catch_unwind)]
pub async fn drop_table_async(
&self,
name: String,
namespace_path: Option<Vec<String>>,
) -> napi::Result<crate::job::Job> {
let ns = namespace_path.unwrap_or_default();
let job = self
.get_inner()?
.drop_table_async(&name, &ns)
.await
.default_error()?;
Ok(crate::job::Job::new(job))
}
#[napi(catch_unwind)]
pub async fn drop_all_tables(&self, namespace_path: Option<Vec<String>>) -> napi::Result<()> {
let ns = namespace_path.unwrap_or_default();
nodejs/src/table.rs
+49 -7
View File
@@ -347,6 +347,30 @@ impl Table {
Ok(res.into())
}
#[napi(catch_unwind)]
pub async fn add_computed_columns(
&self,
columns: Vec<AddColumnsSql>,
) -> napi::Result<AddColumnsResult> {
let table = self.inner_ref()?;
let mut builder = table.add_columns();
for column in columns {
builder = builder.computed(column.name, column.value_sql);
}
let res = builder.execute().await.default_error()?;
Ok(res.into())
}
#[napi(catch_unwind)]
pub async fn refresh_column(&self, column: String) -> napi::Result<RefreshColumnResult> {
let res = self
.inner_ref()?
.refresh_column(column)
.await
.default_error()?;
Ok(res.into())
}
#[napi(catch_unwind)]
pub async fn add_columns_with_schema(
&self,
@@ -772,7 +796,8 @@ pub struct LsmWriteSpec {
pub column: Option<String>,
/// Bucket variant: the number of buckets, in `[1, 1024]`.
pub num_buckets: Option<u32>,
/// Names of indexes the MemWAL should keep up to date during writes.
/// Indexes the MemWAL keeps up to date. Omitted resolves every
/// maintainable index on install; an empty array means none.
pub maintained_indexes: Option<Vec<String>>,
/// Default `ShardWriter` configuration recorded in the MemWAL index.
pub writer_config_defaults: Option<HashMap<String, String>>,
@@ -782,7 +807,6 @@ impl TryFrom<LsmWriteSpec> for lancedb::table::LsmWriteSpec {
type Error = napi::Error;
fn try_from(value: LsmWriteSpec) -> napi::Result<Self> {
let maintained = value.maintained_indexes.unwrap_or_default();
let writer_config_defaults = value.writer_config_defaults.unwrap_or_default();
let spec = match value.spec_type.as_str() {
"bucket" => {
@@ -809,7 +833,7 @@ impl TryFrom<LsmWriteSpec> for lancedb::table::LsmWriteSpec {
}
};
Ok(spec
.with_maintained_indexes(maintained)
.with_maintained_indexes(value.maintained_indexes)
.with_writer_config_defaults(writer_config_defaults))
}
}
@@ -827,7 +851,7 @@ impl From<lancedb::table::LsmWriteSpec> for LsmWriteSpec {
spec_type: "bucket".to_string(),
column: Some(column),
num_buckets: Some(num_buckets),
maintained_indexes: Some(maintained_indexes),
maintained_indexes,
writer_config_defaults: Some(writer_config_defaults),
},
Native::Identity {
@@ -838,7 +862,7 @@ impl From<lancedb::table::LsmWriteSpec> for LsmWriteSpec {
spec_type: "identity".to_string(),
column: Some(column),
num_buckets: None,
maintained_indexes: Some(maintained_indexes),
maintained_indexes,
writer_config_defaults: Some(writer_config_defaults),
},
Native::Unsharded {
@@ -848,7 +872,7 @@ impl From<lancedb::table::LsmWriteSpec> for LsmWriteSpec {
spec_type: "unsharded".to_string(),
column: None,
num_buckets: None,
maintained_indexes: Some(maintained_indexes),
maintained_indexes,
writer_config_defaults: Some(writer_config_defaults),
},
}
@@ -1043,7 +1067,10 @@ impl From<lancedb::index::IndexStatistics> for IndexStatistics {
#[napi(object)]
pub struct TableStatistics {
/// The total number of bytes in the table
/// The total size, in bytes, of the table's data files, index files, and
/// overlay files
///
/// Read from the manifest, so this excludes deletion files and manifests.
pub total_bytes: i64,
/// The number of rows in the table
@@ -1193,6 +1220,21 @@ pub struct AddColumnsResult {
pub version: i64,
}
#[napi(object)]
pub struct RefreshColumnResult {
pub rows_filled: i64,
pub version: i64,
}
impl From<lancedb::table::RefreshColumnResult> for RefreshColumnResult {
fn from(value: lancedb::table::RefreshColumnResult) -> Self {
Self {
rows_filled: value.rows_filled as i64,
version: value.version as i64,
}
}
}
impl From<lancedb::table::AddColumnsResult> for AddColumnsResult {
fn from(value: lancedb::table::AddColumnsResult) -> Self {
Self {
python/Cargo.toml
+1 -1
View File
@@ -1,6 +1,6 @@
[package]
name = "lancedb-python"
version = "0.37.1-beta.0"
version = "0.38.0-beta.0"
publish = false
edition.workspace = true
description = "Python bindings for LanceDB"
python/python/lancedb/_lancedb.pyi
+18 -4
View File
@@ -198,6 +198,9 @@ class Connection(object):
async def drop_table(
self, name: str, namespace_path: Optional[List[str]] = None
) -> None: ...
async def drop_table_async(
self, name: str, namespace_path: Optional[List[str]] = None
) -> Job: ...
async def drop_all_tables(
self, namespace_path: Optional[List[str]] = None
) -> None: ...
@@ -335,6 +338,10 @@ class Table:
) -> list[FtsToken]: ...
async def delete(self, filter: Union[str, PyExpr]) -> DeleteResult: ...
async def add_columns(self, columns: list[tuple[str, str]]) -> AddColumnsResult: ...
async def add_computed_columns(
self, columns: list[tuple[str, str]]
) -> AddColumnsResult: ...
async def refresh_column(self, column: str) -> RefreshColumnResult: ...
async def add_columns_with_schema(self, schema: pa.Schema) -> AddColumnsResult: ...
async def alter_columns(
self, columns: list[dict[str, Any]]
@@ -654,9 +661,10 @@ class LsmWriteSpec:
def identity(column: str) -> "LsmWriteSpec": ...
@staticmethod
def unsharded() -> "LsmWriteSpec": ...
def with_maintained_indexes(self, indexes: List[str]) -> "LsmWriteSpec":
"""Return a copy of this spec asking the MemWAL to keep the named
indexes up to date as rows are appended."""
def with_maintained_indexes(self, indexes: Optional[List[str]]) -> "LsmWriteSpec":
"""Set which indexes the MemWAL keeps up to date. None resolves every
index on the table at install, failing if one cannot be maintained;
a list is verbatim, empty means none."""
...
def with_writer_config_defaults(self, defaults: Dict[str, str]) -> "LsmWriteSpec":
"""Return a copy of this spec recording the given default
@@ -671,13 +679,19 @@ class LsmWriteSpec:
@property
def num_buckets(self) -> Optional[int]: ...
@property
def maintained_indexes(self) -> List[str]: ...
def maintained_indexes(self) -> Optional[List[str]]:
"""Indexes the MemWAL keeps up to date, or None for every supported one."""
...
@property
def writer_config_defaults(self) -> Dict[str, str]: ...
class AddColumnsResult:
version: int
class RefreshColumnResult:
rows_filled: int
version: int
class AlterColumnsResult:
version: int
python/python/lancedb/db.py
+37
View File
@@ -524,6 +524,12 @@ class DBConnection(EnforceOverrides):
namespace_path = []
raise NotImplementedError
def drop_table_async(
self, name: str, namespace_path: Optional[List[str]] = None
) -> Job:
"""Start dropping a table and return its cleanup job."""
raise NotImplementedError
def rename_table(
self,
cur_name: str,
@@ -1186,6 +1192,20 @@ class LanceDBConnection(DBConnection):
)
)
@override
def drop_table_async(
self, name: str, namespace_path: Optional[List[str]] = None
) -> Job:
"""Start dropping a table and return its cleanup job.
The table may become unavailable before its data files are removed.
Call :meth:`Job.wait` to wait for cleanup to finish.
"""
if namespace_path is None:
namespace_path = []
job = LOOP.run(self._conn.drop_table_async(name, namespace_path=namespace_path))
return Job(job if isinstance(job, AsyncJob) else AsyncJob(job))
@override
def drop_all_tables(self, namespace_path: Optional[List[str]] = None):
if namespace_path is None:
@@ -1963,6 +1983,23 @@ class AsyncConnection(object):
if f"Table '{name}' was not found" not in str(e):
raise e
async def drop_table_async(
self,
name: str,
*,
namespace_path: Optional[List[str]] = None,
) -> AsyncJob:
"""Start dropping a table and return its cleanup job.
The table may become unavailable before its data files are removed.
Await :meth:`AsyncJob.wait` to wait for cleanup to finish.
"""
if namespace_path is None:
namespace_path = []
return AsyncJob(
await self._inner.drop_table_async(name, namespace_path=namespace_path)
)
async def drop_all_tables(self, namespace_path: Optional[List[str]] = None):
"""Drop all tables from the database.
python/python/lancedb/embeddings/jinaai.py
+4 -3
View File
@@ -87,12 +87,13 @@ class JinaEmbeddings(EmbeddingFunction):
if isinstance(image, bytes):
image_dict = {"image": base64.b64encode(image).decode("utf-8")}
elif isinstance(image, (str, Path)):
parsed = urlparse.urlparse(image)
# TODO handle drive letter on windows.
parsed = urlparse(str(image))
PIL_Image = attempt_import_or_raise("PIL.Image", "pillow")
if parsed.scheme == "file":
pil_image = PIL_Image.open(parsed.path)
elif parsed.scheme == "":
elif parsed.scheme == "" or (os.name == "nt" and len(parsed.scheme) == 1):
# A Windows drive letter parses as a one-character scheme
# ("C:\\img.png" -> scheme="c"), so treat it as a local path.
pil_image = PIL_Image.open(image if os.name == "nt" else parsed.path)
elif parsed.scheme.startswith("http"):
pil_image = PIL_Image.open(io.BytesIO(url_retrieve(image)))
python/python/lancedb/namespace.py
+21
View File
@@ -49,6 +49,7 @@ from lancedb._lancedb import (
)
from lancedb.background_loop import LOOP
from lancedb.db import AsyncConnection, DBConnection
from lancedb.job import AsyncJob, Job
from lance_namespace import (
LanceNamespace,
connect as namespace_connect,
@@ -624,6 +625,18 @@ class LanceNamespaceDBConnection(DBConnection):
namespace_path = []
LOOP.run(self._inner.drop_table(name, namespace_path=namespace_path))
@override
def drop_table_async(
self, name: str, namespace_path: Optional[List[str]] = None
) -> Job:
"""Start dropping a table and return its cleanup job."""
if namespace_path is None:
namespace_path = []
job = LOOP.run(
self._inner.drop_table_async(name, namespace_path=namespace_path)
)
return Job(job if isinstance(job, AsyncJob) else AsyncJob(job))
@override
def rename_table(
self,
@@ -1134,6 +1147,14 @@ class AsyncLanceNamespaceDBConnection:
namespace_path = []
await self._inner.drop_table(name, namespace_path=namespace_path)
async def drop_table_async(
self, name: str, namespace_path: Optional[List[str]] = None
) -> AsyncJob:
"""Start dropping a table and return its cleanup job."""
if namespace_path is None:
namespace_path = []
return await self._inner.drop_table_async(name, namespace_path=namespace_path)
async def rename_table(
self,
cur_name: str,
python/python/lancedb/remote/db.py
+11 -1
View File
@@ -23,7 +23,7 @@ import pyarrow as pa
from ..common import DATA
from ..db import DBConnection, LOOP
from ..job import Job
from ..job import AsyncJob, Job
if TYPE_CHECKING:
from .._lancedb import JobDescription, JobInfo
@@ -663,6 +663,16 @@ class RemoteDBConnection(DBConnection):
namespace_path = []
LOOP.run(self._conn.drop_table(name, namespace_path=namespace_path))
@override
def drop_table_async(
self, name: str, namespace_path: Optional[List[str]] = None
) -> Job:
"""Start dropping a table and return its cleanup job."""
if namespace_path is None:
namespace_path = []
job = LOOP.run(self._conn.drop_table_async(name, namespace_path=namespace_path))
return Job(job if isinstance(job, AsyncJob) else AsyncJob(job))
@override
def rename_table(
self,
python/python/lancedb/remote/table.py
+13 -1
View File
@@ -968,9 +968,21 @@ class RemoteTable(Table):
def count_rows(self, filter: Optional[str] = None) -> int:
return LOOP.run(self._table.count_rows(filter))
def add_columns(self, transforms: Dict[str, str]) -> AddColumnsResult:
def add_columns(
self,
transforms: Dict[str, str] | None = None,
*,
computed: Dict[str, str] | None = None,
) -> AddColumnsResult:
if computed:
raise NotImplementedError(
"computed columns are supported only on local tables"
)
return LOOP.run(self._table.add_columns(transforms))
def refresh_column(self, column: str):
raise NotImplementedError("computed columns are supported only on local tables")
def alter_columns(
self, *alterations: Iterable[Dict[str, str]]
) -> AlterColumnsResult:
python/python/lancedb/streaming.py
+315 -27
View File
@@ -11,6 +11,11 @@ Provides StreamingDataset, a PyTorch IterableDataset that guarantees:
- **Resumability**: state_dict / load_state_dict capture per-split consumption
counts so training can resume from an exact mid-epoch position even when the
distributed topology changes between runs.
Transform failures on bad rows (e.g. nulls or NaNs from incomplete data) can
be tolerated with ``on_transform_error="skip"``; see the parameter
documentation on StreamingDataset for how this interacts with the guarantees
above.
"""
import ctypes
@@ -22,7 +27,7 @@ import time
from collections import deque
from concurrent.futures import ThreadPoolExecutor
from multiprocessing import RawArray
from typing import Any, Callable, Iterator, Optional
from typing import Any, Callable, Iterator, Optional, Union
from torch.utils.data import IterableDataset, get_worker_info
@@ -127,6 +132,49 @@ class StreamingDataset(IterableDataset):
Maximum number of transforms to run concurrently. Must be greater
than zero. When ``None`` (the default), uses ``os.cpu_count()`` or 1
when the CPU count is unavailable.
on_transform_error:
What to do when the transform raises an exception:
- ``"raise"`` (the default): the exception propagates and iteration
aborts.
- ``"skip"``: the failing rows are dropped and iteration continues.
- ``"warn"``: like ``"skip"``, but a warning is logged for each
failing batch.
- a callable ``handler(exc) -> bool``: called with the exception;
return ``True`` to skip the failing rows or ``False`` to re-raise.
Useful to skip only expected error types (compatible with
``webdataset.handlers`` style handlers).
When a batch fails, the transform is re-invoked on each single-row
slice of the batch so that only the rows that actually fail are
dropped. Transforms should therefore be deterministic and accept
batches of any size (including one row). Skipped rows are counted in
``rows_skipped``.
Skipping weakens the elastic-determinism guarantee at the end of the
epoch: splits that lose more rows than others run dry earlier, and
each rank's iterator ends at the last cycle where every split *it
owns* still has a row. Because bad rows are not distributed evenly
across splits, this means one rank's iterator can yield noticeably
fewer or more steps than another rank's *in the same run* — there is
no cross-rank coordination that stops every rank at the same global
step. This is generally safe for asynchronous or single-rank use,
but synchronous distributed training (e.g. ranks that call
``all_reduce`` every step) can hang or deadlock if one rank's
iterator is exhausted while others are still stepping; callers doing
synchronous multi-rank training with ``on_transform_error != "raise"``
are responsible for their own cross-rank stopping mechanism (e.g.
broadcasting a stop signal on ``StopIteration``). The final few
global steps can also differ across topologies (bounded by the skew
in bad-row counts across splits). The sequence of samples yielded
from each split remains deterministic. Mid-epoch
checkpoints remain exact provided the transform fails
deterministically; in multi-rank training each rank must save its
own ``state_dict`` and the states must be combined with
``merge_state_dicts`` before resuming on a different topology.
Prefer the ``filter`` parameter when bad rows can be expressed as a
SQL predicate (e.g. ``"col IS NOT NULL"``) — filtering happens before
splits are built, so every guarantee is fully preserved.
worker_info_override:
If set, used in place of ``torch.utils.data.get_worker_info()`` to
determine the DataLoader worker assignment. Intended for unit tests
@@ -152,6 +200,7 @@ class StreamingDataset(IterableDataset):
filter: Optional[str] = None,
transform: Optional[Callable] = None,
transform_parallelism: Optional[int] = None,
on_transform_error: Union[str, Callable[[Exception], bool]] = "raise",
connection_factory: Optional[Callable[[str], Any]] = None,
worker_info_override=None,
):
@@ -167,6 +216,13 @@ class StreamingDataset(IterableDataset):
)
if transform_parallelism is not None and transform_parallelism <= 0:
raise ValueError("transform_parallelism must be greater than 0")
if on_transform_error not in ("raise", "skip", "warn") and not callable(
on_transform_error
):
raise ValueError(
"on_transform_error must be 'raise', 'skip', 'warn', or a "
f"callable, got {on_transform_error!r}"
)
self._table = table
self._num_splits = num_splits
@@ -182,6 +238,7 @@ class StreamingDataset(IterableDataset):
self._filter = filter
self._transform = transform
self._transform_parallelism = transform_parallelism
self._on_transform_error = on_transform_error
self._connection_factory = connection_factory
self._worker_info_override = worker_info_override
@@ -199,19 +256,28 @@ class StreamingDataset(IterableDataset):
# in the main process. RawArray is picklable via the forkserver
# reduction protocol so it survives the dataset pickle round-trip.
# Layout: [unscanned_rows, raw_rows, cooked_rows, consumed_rows,
# bytes_loaded, fetch_time_us, transform_time_us]
self._worker_stats: RawArray = RawArray(ctypes.c_int64, 7)
# bytes_loaded, fetch_time_us, transform_time_us,
# rows_skipped]
self._worker_stats: RawArray = RawArray(ctypes.c_int64, 8)
# Cumulative bytes of Arrow buffer data fetched across all iterations.
self._bytes_loaded: int = 0
# Cumulative seconds spent in LanceDB I/O and in transform functions.
self._fetch_time: float = 0.0
self._transform_time: float = 0.0
# Cumulative rows dropped by on_transform_error across all iterations.
self._rows_skipped: int = 0
# Number of samples each split has already been consumed. At global
# step boundaries all splits have consumed this many samples, so a
# single scalar captures the topology-independent checkpoint state.
self._resume_offset: int = 0
# Permutation position each split has consumed through, keyed by
# global split index. Equal to _resume_offset for every split unless
# on_transform_error skipped rows, in which case skipped positions
# push the watermark of the affected splits further ahead. Splits
# this instance has never iterated have no entry.
self._resume_positions: dict[int, int] = {}
# Build the permutation table once, deterministically.
builder = permutation_builder(table)
@@ -275,6 +341,7 @@ class StreamingDataset(IterableDataset):
# Set identity transform on each Permutation so __getitems__ returns
# the raw RecordBatch. Stage 2 applies the real transform.
permutations: list[Permutation] = []
initial_positions: list[int] = []
for split_idx in my_splits:
perm = Permutation.from_tables(
self._table, self._perm_table, split=split_idx
@@ -282,14 +349,20 @@ class StreamingDataset(IterableDataset):
if self._columns is not None:
perm = perm.select_columns(self._columns)
perm = perm.with_transform(lambda batch: batch)
if self._resume_offset > 0:
perm = perm.with_skip(self._resume_offset)
start_pos = self._resume_positions.get(split_idx, self._resume_offset)
if start_pos > 0:
perm = perm.with_skip(start_pos)
initial_positions.append(start_pos)
permutations.append(perm)
n = len(permutations)
split_sizes = [perm.num_rows for perm in permutations]
initial_offset = self._resume_offset
local_consumed = [0] * n
# Permutation position each split has consumed through (absolute,
# i.e. counted from the start of the unskipped split). Runs ahead of
# initial + local_consumed when rows are skipped.
pos_consumed = list(initial_positions)
batch_size = self._read_batch_size
max_prefetch = self._prefetch_batches
@@ -302,12 +375,14 @@ class StreamingDataset(IterableDataset):
self._transform if self._transform is not None else Transforms.arrow2python
)
# Per-split pipeline state.
# Per-split pipeline state. Batches are paired with the absolute
# permutation position of their first row so that skipped rows can be
# accounted for in pos_consumed.
fetch_head = [0] * n
io_pending = [deque() for _ in range(n)] # Future[RecordBatch]
raw_batches = [deque() for _ in range(n)] # RecordBatch — fetched, awaiting tx
tx_pending = [deque() for _ in range(n)] # Future[list[Any]]
cooked = [deque() for _ in range(n)] # rows ready to yield
io_pending = [deque() for _ in range(n)] # (abs_start, Future[RecordBatch])
raw_batches = [deque() for _ in range(n)] # (abs_start, RecordBatch)
tx_pending = [deque() for _ in range(n)] # Future[list[(abs_pos, row)]]
cooked = [deque() for _ in range(n)] # (abs_pos, row) ready to yield
# Limit simultaneous transforms to transform_workers across all splits.
tx_semaphore = threading.Semaphore(transform_workers)
@@ -330,7 +405,8 @@ class StreamingDataset(IterableDataset):
fetch_head[i] += fetch
perm_i = permutations[i]
indices = list(range(start, start + fetch))
io_pending[i].append(io_pool.submit(_io_call, perm_i, indices))
abs_start = initial_positions[i] + start
io_pending[i].append((abs_start, io_pool.submit(_io_call, perm_i, indices)))
def _fill_io(i: int) -> None:
while len(io_pending[i]) < max_prefetch and fetch_head[i] < split_sizes[i]:
@@ -338,15 +414,72 @@ class StreamingDataset(IterableDataset):
def _drain_io(i: int) -> None:
"""Move completed I/O futures into raw_batches non-blockingly."""
while io_pending[i] and io_pending[i][0].done():
raw_batches[i].append(io_pending[i].popleft().result())
while io_pending[i] and io_pending[i][0][1].done():
abs_start, fut = io_pending[i].popleft()
raw_batches[i].append((abs_start, fut.result()))
# ── Stage 2 helpers ───────────────────────────────────────────────────
def _tx_call_guarded(batch):
on_error = self._on_transform_error
def _should_skip(exc: Exception) -> bool:
if on_error == "raise":
return False
if callable(on_error):
return bool(on_error(exc))
return True # "skip" or "warn"
def _check_row_count(rows: list, num_rows: int) -> None:
if len(rows) != num_rows:
raise ValueError(
f"transform returned {len(rows)} rows for a batch of "
f"{num_rows}; transforms must return exactly one output "
"row per input row. To drop bad rows, raise inside the "
"transform and pass on_transform_error='skip'."
)
def _transform_isolated(abs_start, batch, batch_exc):
"""Re-run the transform on single-row slices, dropping failures."""
out = []
skipped = 0
first_exc = None
for j in range(batch.num_rows):
try:
rows = list(final_transform(batch.slice(j, 1)))
except Exception as exc:
if not _should_skip(exc):
raise
skipped += 1
if first_exc is None:
first_exc = exc
continue
_check_row_count(rows, 1)
out.append((abs_start + j, rows[0]))
self._rows_skipped += skipped
if skipped and on_error == "warn":
logger.warning(
"Skipped %d of %d rows whose transform failed (first error: %r)",
skipped,
batch.num_rows,
first_exc if first_exc is not None else batch_exc,
)
return out
def _transform_batch(abs_start, batch):
"""Apply the transform, returning [(abs_pos, row), ...]."""
try:
rows = list(final_transform(batch))
except Exception as exc:
if not _should_skip(exc):
raise
return _transform_isolated(abs_start, batch, exc)
_check_row_count(rows, batch.num_rows)
return [(abs_start + j, row) for j, row in enumerate(rows)]
def _tx_call_guarded(abs_start, batch):
try:
t0 = time.perf_counter()
result = final_transform(batch)
result = _transform_batch(abs_start, batch)
self._transform_time += time.perf_counter() - t0
return result
finally:
@@ -355,8 +488,8 @@ class StreamingDataset(IterableDataset):
def _try_submit_tx(i: int) -> None:
"""Submit transforms for raw_batches[i] up to available capacity."""
while raw_batches[i] and tx_semaphore.acquire(blocking=False):
batch = raw_batches[i].popleft()
tx_pending[i].append(tx_pool.submit(_tx_call_guarded, batch))
abs_start, batch = raw_batches[i].popleft()
tx_pending[i].append(tx_pool.submit(_tx_call_guarded, abs_start, batch))
def _drain_tx(i: int) -> None:
"""Move completed transform futures into cooked non-blockingly."""
@@ -384,11 +517,14 @@ class StreamingDataset(IterableDataset):
# Acquire a transform slot (may block briefly if all
# transform_workers are busy with other splits).
tx_semaphore.acquire()
batch = raw_batches[i].popleft()
tx_pending[i].append(tx_pool.submit(_tx_call_guarded, batch))
abs_start, batch = raw_batches[i].popleft()
tx_pending[i].append(
tx_pool.submit(_tx_call_guarded, abs_start, batch)
)
elif io_pending[i]:
# Block on the oldest in-flight I/O fetch.
raw_batches[i].append(io_pending[i].popleft().result())
abs_start, fut = io_pending[i].popleft()
raw_batches[i].append((abs_start, fut.result()))
_advance(i)
else:
break # split exhausted
@@ -407,15 +543,28 @@ class StreamingDataset(IterableDataset):
_fill_io(i)
while True:
# Stop when any split is exhausted (all exhaust
# simultaneously: equal split sizes + round-robin).
if any(local_consumed[i] >= split_sizes[i] for i in range(n)):
# A cycle only runs if every split can still produce a
# row. Without skips all splits exhaust simultaneously
# (equal split sizes + round-robin); when
# on_transform_error drops rows a split can run dry
# early, ending the epoch at the last complete cycle.
# This check only sees splits owned by this rank/worker
# (my_splits) — there is no cross-rank coordination, so
# a different rank with fewer skipped rows keeps going;
# see the on_transform_error docstring.
exhausted = False
for i in range(n):
_ensure_cooked(i)
if not cooked[i]:
exhausted = True
break
if exhausted:
break
for i in range(n):
_ensure_cooked(i)
row = cooked[i].popleft()
pos, row = cooked[i].popleft()
local_consumed[i] += 1
pos_consumed[i] = pos + 1
_advance(i)
# After the last split in each cycle: update the
@@ -424,21 +573,39 @@ class StreamingDataset(IterableDataset):
# even when __iter__ runs in a worker process.
if i == n - 1:
self._resume_offset = initial_offset + local_consumed[i]
for j, split_idx in enumerate(my_splits):
self._resume_positions[split_idx] = pos_consumed[j]
ws = self._worker_stats
ws[0] = sum(
split_sizes[j] - fetch_head[j] for j in range(n)
)
ws[1] = sum(
batch.num_rows for q in raw_batches for batch in q
batch.num_rows
for q in raw_batches
for _, batch in q
)
ws[2] = sum(len(q) for q in cooked)
ws[3] = sum(local_consumed)
ws[4] = self._bytes_loaded
ws[5] = int(self._fetch_time * 1_000_000)
ws[6] = int(self._transform_time * 1_000_000)
ws[7] = self._rows_skipped
yield row
finally:
# Final stats flush: the per-cycle write above never runs
# when iteration ends mid-cycle (e.g. a split whose rows
# were all skipped before completing a single cycle), so
# counters like rows_skipped would otherwise be stale.
ws = self._worker_stats
ws[0] = sum(split_sizes[j] - fetch_head[j] for j in range(n))
ws[1] = 0 # queue-depth properties document 0 when idle
ws[2] = 0
ws[3] = sum(local_consumed)
ws[4] = self._bytes_loaded
ws[5] = int(self._fetch_time * 1_000_000)
ws[6] = int(self._transform_time * 1_000_000)
ws[7] = self._rows_skipped
self._raw_batches_ref = None
self._cooked_ref = None
self._fetch_head_ref = None
@@ -492,7 +659,7 @@ class StreamingDataset(IterableDataset):
batches. Returns 0 when not iterating.
"""
if self._raw_batches_ref is not None:
return sum(batch.num_rows for q in self._raw_batches_ref for batch in q)
return sum(batch.num_rows for q in self._raw_batches_ref for _, batch in q)
return int(self._worker_stats[1])
@property
@@ -522,6 +689,19 @@ class StreamingDataset(IterableDataset):
)
return int(self._worker_stats[0])
@property
def rows_skipped(self) -> int:
"""Number of rows dropped because their transform raised an exception.
Only ever non-zero when ``on_transform_error`` is set to ``"skip"``,
``"warn"``, or a callable that returned ``True``. Accumulates across
multiple iterations of the same dataset instance and is never reset
automatically.
"""
if self._raw_batches_ref is not None:
return self._rows_skipped
return int(self._worker_stats[7])
@property
def consumed_rows(self) -> int:
"""Number of rows already yielded to the caller across all splits.
@@ -587,12 +767,27 @@ class StreamingDataset(IterableDataset):
every split has been consumed the same number of times (by the
round-robin design), so the per-split count is a single uniform value
that is identical across all ranks and DataLoader workers.
``positions_consumed_per_split`` records how far into each split's
permutation iteration has advanced. It only differs from
``samples_consumed_per_split`` when ``on_transform_error`` skipped
rows, in which case entries are exact for the splits this instance
iterated and a lower bound (the sample count) for splits owned by
other ranks or workers. Combine the state dicts from all ranks with
[merge_state_dicts][lancedb.streaming.StreamingDataset.merge_state_dicts]
to recover the exact value for every split before resuming on a
different topology.
"""
positions = [
self._resume_positions.get(split, self._resume_offset)
for split in range(self._num_splits)
]
return {
"shuffle_seed": self._shuffle_seed,
"num_splits": self._num_splits,
"epoch": self._epoch,
"samples_consumed_per_split": [self._resume_offset] * self._num_splits,
"positions_consumed_per_split": positions,
}
def load_state_dict(self, state: dict) -> None:
@@ -618,3 +813,96 @@ class StreamingDataset(IterableDataset):
self._resume_offset = consumed[0] if consumed else 0
else:
self._resume_offset = int(consumed)
# Older checkpoints predate positions_consumed_per_split; without
# skipped rows positions equal sample counts, so falling back to
# _resume_offset (the .get default in __iter__) is exact.
positions = state.get("positions_consumed_per_split")
if positions is None:
self._resume_positions = {}
else:
self._resume_positions = {
split: int(pos) for split, pos in enumerate(positions)
}
@staticmethod
def merge_state_dicts(states: list[dict]) -> dict:
"""Merge state dicts saved by different ranks into one exact state.
Only needed when ``on_transform_error`` skips rows in multi-rank
training: each rank then knows the exact permutation position only for
its own splits, and records a lower bound for the rest. Because
exactly one rank owns each split, the elementwise maximum across all
ranks' ``positions_consumed_per_split`` recovers the exact position of
every split. Without skipped rows every rank's state is already
identical and merging is a no-op.
Raises ``ValueError`` if the states are empty or were not produced by
the same run (mismatched seed, split count, epoch, or sample counts).
The merge is always all-to-all and topology-agnostic: collect the
``state_dict()`` from every rank of the *previous* run into one list,
merge that whole list, and hand the identical merged result to every
rank of the *next* run — regardless of whether the rank count grew,
shrank, or stayed the same. There is no pairwise or subset merging
step, because each split's exact position is only known to whichever
rank owned that split, and the elementwise maximum needs every rank's
contribution to be correct.
For example, checkpointing 8 ranks and resuming on 4 (the same
pattern applies when growing, e.g. 4 ranks resuming on 8)::
states = [ds.state_dict() for ds in previous_run_datasets] # 8
merged = StreamingDataset.merge_state_dicts(states)
for ds in resumed_datasets: # now only 4 ranks
ds.load_state_dict(merged) # same dict on every rank
The rank count on either side never affects the merge itself, since
``merge_state_dicts`` only cares about the list of states it is
given. Each split's position is recovered by elementwise maximum;
here rank 0 owned split 0 (and skipped two rows there) while rank 1
owned split 1 (and skipped one row):
>>> rank0 = {
... "shuffle_seed": 0, "num_splits": 2, "epoch": 0,
... "samples_consumed_per_split": [3, 3],
... "positions_consumed_per_split": [5, 3],
... }
>>> rank1 = {
... "shuffle_seed": 0, "num_splits": 2, "epoch": 0,
... "samples_consumed_per_split": [3, 3],
... "positions_consumed_per_split": [3, 4],
... }
>>> merged = StreamingDataset.merge_state_dicts([rank0, rank1])
>>> merged["positions_consumed_per_split"]
[5, 4]
"""
if not states:
raise ValueError("merge_state_dicts requires at least one state dict")
first = states[0]
for state in states[1:]:
for key in ("shuffle_seed", "num_splits", "epoch"):
if state[key] != first[key]:
raise ValueError(
f"{key} mismatch across state dicts: "
f"{state[key]} != {first[key]}"
)
if (
state["samples_consumed_per_split"]
!= first["samples_consumed_per_split"]
):
raise ValueError(
"samples_consumed_per_split mismatch across state dicts; "
"state_dict() must be called at the same global step "
"boundary on every rank"
)
merged = dict(first)
all_positions = [
state.get(
"positions_consumed_per_split", state["samples_consumed_per_split"]
)
for state in states
]
merged["positions_consumed_per_split"] = [
max(per_split) for per_split in zip(*all_positions)
]
return merged
python/python/lancedb/table.py
+148 -8
View File
@@ -177,6 +177,7 @@ if TYPE_CHECKING:
CompactionStats,
Tag,
AddColumnsResult,
RefreshColumnResult,
AddResult,
AlterColumnsResult,
UpdateFieldMetadataResult,
@@ -1985,7 +1986,14 @@ class Table(ABC):
@abstractmethod
def add_columns(
self, transforms: Dict[str, str] | pa.Field | List[pa.Field] | pa.Schema
self,
transforms: Dict[str, str]
| pa.Field
| List[pa.Field]
| pa.Schema
| None = None,
*,
computed: Dict[str, str] | None = None,
):
"""
Add new columns with defined values.
@@ -1999,11 +2007,68 @@ class Table(ABC):
Alternatively, a pyarrow Field or Schema can be provided to add
new columns with the specified data types. The new columns will
be initialized with null values.
computed: Dict[str, str], optional
A map of column name to a SQL expression defining the column. The
column's type and inputs are derived from the expression, so no
data type is supplied.
Unlike ``transforms``, the expression is stored rather than
evaluated now: the column is committed with no values, and rows get
them from [`refresh_column`][lancedb.table.Table.refresh_column].
Declaring one therefore costs the same on a large table as on an
empty one.
A refresh does not revisit rows it has already filled, so mutating
an input leaves the value computed at fill time; recomputing means
dropping the column and declaring it again. While a declaration
reads a column, that column cannot be renamed, retyped or dropped.
Local tables only; LanceDB Cloud and Enterprise raise
``NotImplementedError``. Cannot be combined with ``transforms``.
Returns
-------
AddColumnsResult
version: the new version number of the table after adding columns.
Examples
--------
>>> import lancedb
>>> db = lancedb.connect("./.lancedb")
>>> table = db.create_table("computed_demo", [{"x": 1}, {"x": 2}])
>>> table.add_columns(computed={"doubled": "x * 2"})
AddColumnsResult(version=2)
>>> table.refresh_column("doubled")
RefreshColumnResult(rows_filled=2, version=3)
>>> table.to_arrow().sort_by("x").to_pandas()
x doubled
0 1 2
1 2 4
"""
@abstractmethod
def refresh_column(self, column: str) -> "RefreshColumnResult":
"""
Fill the rows of a computed column that hold no value yet.
Declared with ``add_columns(computed=...)``, a column starts empty and
gets its values here. Rows appended since the last refresh are filled
by the next one; rows already filled are left as they are, so the call
is idempotent and does not observe a mutated input.
Local tables only; LanceDB Cloud and Enterprise raise
``NotImplementedError``.
Parameters
----------
column: str
The name of the computed column to fill.
Returns
-------
RefreshColumnResult
rows_filled: the number of rows given a value.
version: the new version number of the table.
"""
@abstractmethod
@@ -4014,9 +4079,21 @@ class LanceTable(Table):
return LOOP.run(self._table.index_stats(index_name))
def add_columns(
self, transforms: Dict[str, str] | pa.field | List[pa.field] | pa.Schema
self,
transforms: Dict[str, str]
| pa.field
| List[pa.field]
| pa.Schema
| None = None,
*,
computed: Dict[str, str] | None = None,
) -> AddColumnsResult:
return LOOP.run(self._table.add_columns(transforms))
return LOOP.run(self._table.add_columns(transforms, computed=computed))
def refresh_column(self, column: str) -> "RefreshColumnResult":
"""Fill a computed column's unfilled rows. See
[`AsyncTable.refresh_column`][lancedb.AsyncTable.refresh_column]."""
return LOOP.run(self._table.refresh_column(column))
def alter_columns(
self, *alterations: Iterable[Dict[str, str]]
@@ -4751,6 +4828,13 @@ class AsyncTable:
via [`set_unenforced_primary_key`]; bucket sharding additionally
requires it to be the single column being bucketed.
By default the MemWAL maintains every index on the table, resolved
here — a snapshot, so an index created afterwards needs the spec unset
and set again. This fails if one cannot be maintained; name the set
with ``with_maintained_indexes`` to install anyway. That pins an exact
set (a still-building index is rejected, not omitted); ``[]`` maintains
none.
Parameters
----------
spec : LsmWriteSpec
@@ -4777,9 +4861,9 @@ class AsyncTable:
Returns ``None`` when the MemWAL LSM write path is not enabled (no
spec has been set, or it was removed with `unset_lsm_write_spec`).
The returned spec — including its ``maintained_indexes`` and
``writer_config_defaults`` — mirrors what was passed to
`set_lsm_write_spec`.
The returned spec mirrors what was passed to `set_lsm_write_spec`,
except that ``maintained_indexes`` always reports the concrete list
resolved when the spec was set — ``None`` never round-trips.
"""
return await self._inner.get_lsm_write_spec()
@@ -5924,7 +6008,14 @@ class AsyncTable:
return await self._inner.update(updates_sql, where)
async def add_columns(
self, transforms: dict[str, str] | pa.field | List[pa.field] | pa.Schema
self,
transforms: dict[str, str]
| pa.field
| List[pa.field]
| pa.Schema
| None = None,
*,
computed: dict[str, str] | None = None,
) -> AddColumnsResult:
"""
Add new columns with defined values.
@@ -5937,6 +6028,21 @@ class AsyncTable:
each row in the table, and can reference existing columns.
Alternatively, you can pass a pyarrow field or schema to add
new columns with NULLs.
computed: Dict[str, str], optional
A map of column name to a SQL expression defining the column. The
column's type and inputs are derived from the expression.
Unlike ``transforms``, the expression is stored rather than
evaluated now: the column is committed with no values, and rows get
them from
[`refresh_column`][lancedb.table.AsyncTable.refresh_column].
A refresh does not revisit rows it has already filled, so mutating
an input leaves the value computed at fill time. While a
declaration reads a column, that column cannot be renamed, retyped
or dropped.
Local tables only. Cannot be combined with ``transforms``.
Returns
-------
@@ -5950,11 +6056,43 @@ class AsyncTable:
{isinstance(f, pa.Field) for f in transforms}
):
transforms = pa.schema(transforms)
if computed:
if transforms:
raise ValueError(
"add_columns cannot take both transforms and computed columns"
)
return await self._inner.add_computed_columns(list(computed.items()))
if transforms is None:
raise ValueError("add_columns requires transforms or computed columns")
if isinstance(transforms, pa.Schema):
return await self._inner.add_columns_with_schema(transforms)
else:
return await self._inner.add_columns(list(transforms.items()))
async def refresh_column(self, column: str) -> RefreshColumnResult:
"""
Fill the rows of a computed column that hold no value yet.
Declared with ``add_columns(computed=...)``, a column starts empty and
gets its values here. Rows appended since the last refresh are filled
by the next one; rows already filled are left as they are, so the call
is idempotent and does not observe a mutated input.
Local tables only; LanceDB Cloud and Enterprise raise
``NotImplementedError``.
Parameters
----------
column: str
The name of the computed column to fill.
Returns
-------
RefreshColumnResult
The number of rows filled and the new version of the table.
"""
return await self._inner.refresh_column(column)
async def alter_columns(
self, *alterations: Iterable[dict[str, Any]]
) -> AlterColumnsResult:
@@ -6415,7 +6553,9 @@ class TableStatistics:
Attributes
----------
total_bytes: int
The total number of bytes in the table.
The total size, in bytes, of the table's data files, index files, and
overlay files. Read from the manifest, so this excludes deletion files
and manifests.
num_rows: int
The total number of rows in the table.
num_indices: int
python/python/tests/test_db.py
+16 -3
View File
@@ -755,8 +755,7 @@ def test_delete_table(tmp_db: lancedb.DBConnection):
assert tmp_db.table_names() == []
@pytest.mark.asyncio
async def test_delete_table_async(tmp_db: lancedb.DBConnection):
def test_drop_table_async(tmp_db: lancedb.DBConnection):
data = pd.DataFrame(
{
"vector": [[3.1, 4.1], [5.9, 26.5]],
@@ -772,7 +771,10 @@ async def test_delete_table_async(tmp_db: lancedb.DBConnection):
assert tmp_db.table_names() == ["test"]
tmp_db.drop_table("test")
job = tmp_db.drop_table_async("test")
assert job.id is None
assert job.status() == "finished"
job.wait()
assert tmp_db.table_names() == []
tmp_db.create_table("test", data=data)
@@ -781,6 +783,17 @@ async def test_delete_table_async(tmp_db: lancedb.DBConnection):
tmp_db.drop_table("does_not_exist", ignore_missing=True)
@pytest.mark.asyncio
async def test_drop_table_async_connection(tmp_db_async: lancedb.AsyncConnection):
await tmp_db_async.create_table("test", data=pa.table({"id": [1, 2]}))
job = await tmp_db_async.drop_table_async("test")
assert job.id is None
assert await job.status() == "finished"
await job.wait()
assert await tmp_db_async.table_names() == []
def test_drop_database(tmp_db: lancedb.DBConnection):
data = pd.DataFrame(
{
python/python/tests/test_elastic_dataloader.py
+402
View File
@@ -1456,6 +1456,408 @@ def test_shuffle_clump_size_yields_all_rows(lance_table):
)
# ---------------------------------------------------------------------------
# on_transform_error tests
# ---------------------------------------------------------------------------
class BadRowError(ValueError):
"""Raised by the failing transforms below when a batch contains a bad id."""
def _failing_transform(bad_ids: set):
"""A transform that raises BadRowError whenever the batch has a bad id.
Raises on the full batch and on any single-row slice containing a bad id,
so per-row isolation drops exactly the bad rows.
"""
def transform(batch: pa.RecordBatch) -> list:
ids = batch.column("id").to_pylist()
bad = sorted(set(ids) & bad_ids)
if bad:
raise BadRowError(f"bad ids in batch: {bad}")
return [{"id": i} for i in ids]
return transform
def _sequential_split_members(table) -> list[list[int]]:
"""Return each split's ids in yield order for shuffle=False.
With a single rank and no workers the round-robin yields one row per split
per cycle, so item k of a clean run belongs to split k % NUM_SPLITS.
"""
ds = StreamingDataset(table, num_splits=NUM_SPLITS, shuffle=False)
members: list[list[int]] = [[] for _ in range(NUM_SPLITS)]
for k, row in enumerate(ds):
members[k % NUM_SPLITS].append(row["id"])
return members
def test_on_transform_error_default_raises(lance_table):
"""By default a transform exception propagates and aborts iteration."""
ds = StreamingDataset(
lance_table,
num_splits=NUM_SPLITS,
shuffle_seed=SHUFFLE_SEED,
transform=_failing_transform({7}),
)
with pytest.raises(BadRowError):
list(ds)
def test_on_transform_error_invalid_value(lance_table):
with pytest.raises(ValueError, match="on_transform_error"):
StreamingDataset(lance_table, num_splits=NUM_SPLITS, on_transform_error="bogus")
def test_on_transform_error_skip_drops_bad_rows(lance_table):
"""With one bad row per split, 'skip' yields every good row exactly once
and counts the dropped rows in rows_skipped."""
members = _sequential_split_members(lance_table)
bad_ids = {members[i][4] for i in range(NUM_SPLITS)}
ds = StreamingDataset(
lance_table,
num_splits=NUM_SPLITS,
shuffle=False,
transform=_failing_transform(bad_ids),
on_transform_error="skip",
)
assert ds.rows_skipped == 0
ids = [row["id"] for row in ds]
assert sorted(ids) == sorted(set(range(NUM_ROWS)) - bad_ids)
assert ds.rows_skipped == NUM_SPLITS
def test_on_transform_error_skip_uneven_ends_at_last_complete_cycle(lance_table):
"""When one split loses more rows than the others, the epoch ends at the
last cycle where every split still has a row — no crash, no bad rows, and
every step remains one sample per split."""
members = _sequential_split_members(lance_table)
bad_ids = set(members[0][:3]) # all 3 bad rows in split 0
ds = StreamingDataset(
lance_table,
num_splits=NUM_SPLITS,
shuffle=False,
transform=_failing_transform(bad_ids),
on_transform_error="skip",
)
items = [row["id"] for row in ds]
rows_per_split = NUM_ROWS // NUM_SPLITS
expected_cycles = rows_per_split - len(bad_ids)
assert len(items) == expected_cycles * NUM_SPLITS
assert len(set(items)) == len(items), "duplicate samples yielded"
assert not set(items) & bad_ids, "a bad row was yielded"
# Split 0 contributed exactly its surviving rows, in order, one per cycle.
survivors = [i for i in members[0] if i not in bad_ids]
assert items[0::NUM_SPLITS] == survivors[:expected_cycles]
def test_on_transform_error_warn_logs(lance_table, caplog):
"""'warn' skips like 'skip' but logs a warning for the failing batch."""
members = _sequential_split_members(lance_table)
bad_ids = {members[i][3] for i in range(NUM_SPLITS)}
ds = StreamingDataset(
lance_table,
num_splits=NUM_SPLITS,
shuffle=False,
transform=_failing_transform(bad_ids),
on_transform_error="warn",
)
with caplog.at_level(logging.WARNING, logger="lancedb.streaming"):
items = list(ds)
assert len(items) == NUM_ROWS - NUM_SPLITS
assert ds.rows_skipped == NUM_SPLITS
assert "Skipped" in caplog.text
assert "BadRowError" in caplog.text
def test_on_transform_error_callable_selective(lance_table):
"""A callable handler can skip expected errors and re-raise the rest."""
members = _sequential_split_members(lance_table)
bad_ids = {members[i][0] for i in range(NUM_SPLITS)}
handled: list[Exception] = []
def handler(exc: Exception) -> bool:
handled.append(exc)
return isinstance(exc, BadRowError)
ds = StreamingDataset(
lance_table,
num_splits=NUM_SPLITS,
shuffle=False,
transform=_failing_transform(bad_ids),
on_transform_error=handler,
)
items = list(ds)
assert len(items) == NUM_ROWS - NUM_SPLITS
assert handled and all(isinstance(exc, BadRowError) for exc in handled)
def broken_transform(batch: pa.RecordBatch) -> list:
raise TypeError("boom")
ds2 = StreamingDataset(
lance_table,
num_splits=NUM_SPLITS,
shuffle=False,
transform=broken_transform,
on_transform_error=handler,
)
with pytest.raises(TypeError, match="boom"):
list(ds2)
def test_transform_wrong_row_count_raises(lance_table):
"""A transform that returns the wrong number of rows is an error even with
on_transform_error='skip' — silent shrinkage would corrupt accounting."""
def drops_rows(batch: pa.RecordBatch) -> list:
return batch.column("id").to_pylist()[:-1]
ds = StreamingDataset(
lance_table,
num_splits=NUM_SPLITS,
shuffle_seed=SHUFFLE_SEED,
transform=drops_rows,
on_transform_error="skip",
)
with pytest.raises(ValueError, match="one output row per input row"):
list(ds)
def test_skip_deterministic_across_runs(lance_table):
"""With a fixed seed, skipping produces the identical sample sequence on
every run — skips are data-dependent, not run-dependent."""
bad_ids = {5, 17, 46}
def run() -> tuple[list[int], int]:
ds = StreamingDataset(
lance_table,
num_splits=NUM_SPLITS,
shuffle_seed=SHUFFLE_SEED,
transform=_failing_transform(bad_ids),
on_transform_error="skip",
)
return [row["id"] for row in ds], ds.rows_skipped
ids_a, skipped_a = run()
ids_b, skipped_b = run()
assert ids_a == ids_b
assert skipped_a == skipped_b
assert not set(ids_a) & bad_ids
def test_skip_elastic_det_across_world_sizes(lance_table):
"""With equal bad-row counts per split, skipping preserves the full
elastic-determinism guarantee: identical global batches at every step for
every compatible world_size."""
members = _sequential_split_members(lance_table)
bad_ids = {members[i][6] for i in range(NUM_SPLITS)}
def collect(world_size: int) -> list[frozenset[int]]:
micro = GLOBAL_BATCH_SIZE // world_size
iters = [
iter(
StreamingDataset(
lance_table,
num_splits=NUM_SPLITS,
shuffle=False,
rank=rank,
world_size=world_size,
transform=_failing_transform(bad_ids),
on_transform_error="skip",
)
)
for rank in range(world_size)
]
_STOP = object()
batches: list[frozenset[int]] = []
while True:
step_samples: set[int] = set()
exhausted = 0
for it in iters:
for _ in range(micro):
val = next(it, _STOP)
if val is _STOP:
exhausted += 1
break
step_samples.add(val["id"])
if exhausted == len(iters):
break
assert exhausted == 0, (
"Rank iterators exhausted at different steps despite equal "
"bad-row counts per split"
)
batches.append(frozenset(step_samples))
return batches
reference = collect(1)
assert len(reference) == NUM_ROWS // NUM_SPLITS - 1
for ws in (2, 3, 4):
assert collect(ws) == reference, f"world_size={ws} diverged"
def test_resumability_with_skips_same_topology(lance_table):
"""Checkpointing mid-epoch with skipped rows resumes exactly: no sample
repeated, no sample lost, skipped rows stay skipped."""
members = _sequential_split_members(lance_table)
# Uneven skips: positions diverge across splits (2 bad in split 0, 1 in
# split 5), which only a position-based checkpoint can resume exactly.
bad_ids = {members[0][2], members[0][3], members[5][7]}
kwargs = dict(
num_splits=NUM_SPLITS,
shuffle=False,
transform=_failing_transform(bad_ids),
on_transform_error="skip",
)
reference = [row["id"] for row in StreamingDataset(lance_table, **kwargs)]
rows_per_split = NUM_ROWS // NUM_SPLITS
assert len(reference) == (rows_per_split - 2) * NUM_SPLITS
steps = 3
ds = StreamingDataset(lance_table, **kwargs)
it = iter(ds)
consumed = [next(it)["id"] for _ in range(steps * NUM_SPLITS)]
checkpoint = ds.state_dict()
it.close()
# Split 0 skipped positions 2 and 3 within its first 3 yields; split 5's
# bad row is beyond the checkpoint. Everything else is at 3 = the sample
# count.
positions = checkpoint["positions_consumed_per_split"]
assert positions[0] == 5
assert positions[1:] == [3] * (NUM_SPLITS - 1)
assert checkpoint["samples_consumed_per_split"] == [3] * NUM_SPLITS
ds2 = StreamingDataset(lance_table, **kwargs)
ds2.load_state_dict(checkpoint)
resumed = [row["id"] for row in ds2]
assert consumed == reference[: steps * NUM_SPLITS]
assert resumed == reference[steps * NUM_SPLITS :]
def test_resumability_with_skips_elastic_merge(lance_table):
"""Elastic resume with skips: each rank's checkpoint knows exact positions
only for its own splits; merge_state_dicts recovers the global state, and
a run on a different world_size continues exactly."""
members = _sequential_split_members(lance_table)
# Bad rows early in split 0 (rank 0) and split 6 (rank 1 of a ws=2 run) so
# both ranks' position vectors diverge before the checkpoint.
bad_ids = {members[0][0], members[0][2], members[6][1]}
kwargs = dict(
num_splits=NUM_SPLITS,
shuffle=False,
transform=_failing_transform(bad_ids),
on_transform_error="skip",
)
reference = [row["id"] for row in StreamingDataset(lance_table, **kwargs)]
steps = 3
world_size = 2
micro = GLOBAL_BATCH_SIZE // world_size
datasets = [
StreamingDataset(lance_table, rank=rank, world_size=world_size, **kwargs)
for rank in range(world_size)
]
iters = [iter(ds) for ds in datasets]
seen: list[frozenset[int]] = []
for _ in range(steps):
step_samples = set()
for it in iters:
for _ in range(micro):
step_samples.add(next(it)["id"])
seen.append(frozenset(step_samples))
states = [ds.state_dict() for ds in datasets]
for it in iters:
it.close()
merged = StreamingDataset.merge_state_dicts(states)
expected_positions = [3] * NUM_SPLITS
expected_positions[0] = 5 # skipped positions 0 and 2
expected_positions[6] = 4 # skipped position 1
assert merged["positions_consumed_per_split"] == expected_positions
# The first 3 global batches match the world_size=1 reference.
ref_batches = [
frozenset(reference[s * NUM_SPLITS : (s + 1) * NUM_SPLITS])
for s in range(len(reference) // NUM_SPLITS)
]
assert seen == ref_batches[:steps]
# Resume on world_size=1 from the merged state.
ds_resume = StreamingDataset(lance_table, **kwargs)
ds_resume.load_state_dict(merged)
resumed = [row["id"] for row in ds_resume]
assert resumed == reference[steps * NUM_SPLITS :]
def test_rows_skipped_flushed_when_split_entirely_bad(lance_table):
"""A split whose rows all fail never completes a cycle, so the epoch ends
immediately — but rows_skipped must still report the drops after the
iterator exits (the shared-memory counter is flushed on exhaustion)."""
members = _sequential_split_members(lance_table)
bad_ids = set(members[0]) # every row of split 0 is bad
ds = StreamingDataset(
lance_table,
num_splits=NUM_SPLITS,
shuffle=False,
transform=_failing_transform(bad_ids),
on_transform_error="skip",
)
assert list(ds) == []
assert ds.rows_skipped == len(bad_ids)
def test_merge_state_dicts_validates_consistency(lance_table):
ds = StreamingDataset(lance_table, num_splits=NUM_SPLITS, shuffle_seed=SHUFFLE_SEED)
state = ds.state_dict()
other = dict(state, shuffle_seed=SHUFFLE_SEED + 1)
with pytest.raises(ValueError, match="shuffle_seed mismatch"):
StreamingDataset.merge_state_dicts([state, other])
with pytest.raises(ValueError, match="at least one"):
StreamingDataset.merge_state_dicts([])
def test_load_state_dict_without_positions_key(lance_table):
"""Checkpoints from before positions_consumed_per_split existed still
resume exactly (positions equal sample counts when nothing is skipped)."""
reference = [
row["id"]
for row in StreamingDataset(
lance_table, num_splits=NUM_SPLITS, shuffle_seed=SHUFFLE_SEED
)
]
steps = 4
ds = StreamingDataset(lance_table, num_splits=NUM_SPLITS, shuffle_seed=SHUFFLE_SEED)
it = iter(ds)
for _ in range(steps * NUM_SPLITS):
next(it)
checkpoint = ds.state_dict()
it.close()
del checkpoint["positions_consumed_per_split"]
ds2 = StreamingDataset(
lance_table, num_splits=NUM_SPLITS, shuffle_seed=SHUFFLE_SEED
)
ds2.load_state_dict(checkpoint)
resumed = [row["id"] for row in ds2]
assert resumed == reference[steps * NUM_SPLITS :]
def test_num_splits_defaults_to_world_size(lance_table):
"""Omitting num_splits gives world_size splits (one per rank)."""
ds = StreamingDataset(
python/python/tests/test_embeddings.py
+20
View File
@@ -631,3 +631,23 @@ def test_url_retrieve_downloads_image():
image_bytes = url_retrieve(image_url)
img = Image.open(io.BytesIO(image_bytes))
assert img.size[0] > 0 and img.size[1] > 0
def test_jina_generate_image_input_dict_local_path(tmp_path):
"""
JinaEmbeddings._generate_image_input_dict must accept a local image path
(str or Path), not just bytes. Previously it crashed with
`AttributeError: 'function' object has no attribute 'urlparse'` on any
str/Path input because it called `urlparse.urlparse(image)` instead of
`urlparse(image)` (urlparse was imported as a function, not a module).
"""
Image = pytest.importorskip("PIL.Image")
from lancedb.embeddings.jinaai import JinaEmbeddings
image_path = tmp_path / "test.png"
Image.new("RGB", (4, 4), color="red").save(image_path, format="PNG")
for image in (str(image_path), image_path):
image_dict = JinaEmbeddings._generate_image_input_dict(image)
assert "image" in image_dict
assert isinstance(image_dict["image"], str) and len(image_dict["image"]) > 0
python/python/tests/test_lsm_write_spec.py
+11 -4
View File
@@ -83,7 +83,9 @@ def test_lsm_write_spec_repr():
assert s.spec_type == "bucket"
assert s.column == "id"
assert s.num_buckets == 4
assert s.maintained_indexes == []
# A fresh spec defers its maintained set to install time.
assert s.maintained_indexes is None
assert s.with_maintained_indexes([]).maintained_indexes == []
assert "bucket" in repr(s)
assert "id" in repr(s)
assert "4" in repr(s)
@@ -169,18 +171,23 @@ def test_get_lsm_write_spec(tmp_path):
table.unset_lsm_write_spec()
assert table.get_lsm_write_spec() is None
# Identity round-trips (column recovered from the schema).
# Identity round-trips (column recovered from the schema). Leaving the
# maintained set to be inferred picks up the index on the table, so the
# spec reads back naming it rather than as "infer".
table.set_lsm_write_spec(LsmWriteSpec.identity("id"))
spec = table.get_lsm_write_spec()
assert spec.spec_type == "identity"
assert spec.column == "id"
assert spec.maintained_indexes == [idx_name]
table.unset_lsm_write_spec()
# Unsharded round-trips (no routing column).
table.set_lsm_write_spec(LsmWriteSpec.unsharded())
# Unsharded round-trips (no routing column). Opting out is distinct from
# the inferred default.
table.set_lsm_write_spec(LsmWriteSpec.unsharded().with_maintained_indexes([]))
spec = table.get_lsm_write_spec()
assert spec.spec_type == "unsharded"
assert spec.column is None
assert spec.maintained_indexes == []
@pytest.mark.asyncio
python/python/tests/test_merge_insert_lsm.py
+2 -2
View File
@@ -544,7 +544,7 @@ def test_lsm_read_fts_unmaintained_index_errors(tmp_path):
table.create_index("text", config=FTS())
# No maintained indexes: the active memtable FTS arm cannot serve un-compacted
# docs, so the search would silently omit them — reject instead.
table.set_lsm_write_spec(LsmWriteSpec.unsharded())
table.set_lsm_write_spec(LsmWriteSpec.unsharded().with_maintained_indexes([]))
with pytest.raises(Exception, match="maintained"):
table.search("fox", query_type="fts", fts_columns="text").to_arrow()
@@ -631,7 +631,7 @@ def test_lsm_read_vector_unmaintained_index_errors(tmp_path):
)
# Spec with NO maintained indexes: the base vector index's catch-up is untracked,
# so the scanner rejects rather than risk dropping compacted-but-unindexed rows.
table.set_lsm_write_spec(LsmWriteSpec.unsharded())
table.set_lsm_write_spec(LsmWriteSpec.unsharded().with_maintained_indexes([]))
with pytest.raises(Exception, match="maintained"):
table.search([1.0] * VECTOR_DIM).to_arrow()
python/python/tests/test_table.py
+43 -1
View File
@@ -3758,7 +3758,8 @@ def test_stats(mem_db: DBConnection):
stats = table.stats()
print(f"{stats=}")
assert stats == {
"total_bytes": 60,
# Full on-disk size of the data file, footer and metadata included.
"total_bytes": 633,
"num_rows": 2,
"num_indices": 0,
"fragment_stats": {
@@ -3776,6 +3777,13 @@ def test_stats(mem_db: DBConnection):
},
}
# Index files count toward total_bytes too (only deletion files and
# manifests are excluded).
table.create_index("id", config=BTree())
stats_with_index = table.stats()
assert stats_with_index["num_indices"] == 1
assert stats_with_index["total_bytes"] > stats["total_bytes"]
def test_create_table_empty_list_with_schema(mem_db: DBConnection):
"""Test creating table with empty list data and schema
@@ -3891,3 +3899,37 @@ async def test_async_search_runs_embedding_on_dedicated_executor(
assert all(name.startswith("lancedb-embedding") for name in captured_threads), (
f"embedding ran off the dedicated executor: {captured_threads}"
)
def test_computed_column_declare_and_refresh(tmp_path):
db = lancedb.connect(tmp_path)
table = db.create_table("computed", [{"x": 1}, {"x": 2}])
table.add_columns(computed={"doubled": "x * 2"})
assert table.to_arrow()["doubled"].to_pylist() == [None, None]
result = table.refresh_column("doubled")
assert result.rows_filled == 2
assert sorted(table.to_arrow()["doubled"].to_pylist()) == [2, 4]
table.add([{"x": 5}])
assert table.refresh_column("doubled").rows_filled == 1
assert sorted(table.to_arrow()["doubled"].to_pylist()) == [2, 4, 10]
def test_computed_column_rejects_transforms_and_computed_together(tmp_path):
db = lancedb.connect(tmp_path)
table = db.create_table("computed_mixed", [{"x": 1}])
with pytest.raises(ValueError):
table.add_columns({"a": "x + 1"}, computed={"b": "x * 2"})
@pytest.mark.asyncio
async def test_computed_column_async(tmp_path):
db = await lancedb.connect_async(tmp_path)
table = await db.create_table("computed_async", [{"x": 3}])
await table.add_columns(computed={"tripled": "x * 3"})
await table.refresh_column("tripled")
assert (await table.to_arrow())["tripled"].to_pylist() == [9]
python/src/connection.rs
+17
View File
@@ -346,6 +346,23 @@ impl Connection {
})
}
#[pyo3(signature = (name, namespace_path=None))]
pub fn drop_table_async(
self_: PyRef<'_, Self>,
name: String,
namespace_path: Option<Vec<String>>,
) -> PyResult<Bound<'_, PyAny>> {
let inner = self_.get_inner()?.clone();
let ns_path = namespace_path.unwrap_or_default();
future_into_py(self_.py(), async move {
inner
.drop_table_async(name, &ns_path)
.await
.infer_error()
.map(crate::job::Job::new)
})
}
#[pyo3(signature = (namespace_path=None,))]
pub fn drop_all_tables(
self_: PyRef<'_, Self>,
python/src/index.rs
+1 -1
View File
@@ -289,7 +289,7 @@ struct IvfHnswFlatParams {
target_partition_size: Option<u32>,
}
#[pyclass(get_all)]
#[pyclass(module = "lancedb._lancedb", get_all)]
/// A description of an index currently configured on a column
pub struct IndexConfig {
/// The type of the index
python/src/lib.rs
+3 -1
View File
@@ -16,7 +16,8 @@ use query::{FTSQuery, HybridQuery, Query, VectorQuery};
use session::Session;
use table::{
AddColumnsResult, AddResult, AlterColumnsResult, DeleteResult, DropColumnsResult, FtsToken,
LsmWriteSpec, MergeResult, PyBlobFile, Table, UpdateFieldMetadataResult, UpdateResult,
LsmWriteSpec, MergeResult, PyBlobFile, RefreshColumnResult, Table, UpdateFieldMetadataResult,
UpdateResult,
};
pub mod arrow;
@@ -57,6 +58,7 @@ pub fn _lancedb(_py: Python, m: &Bound<'_, PyModule>) -> PyResult<()> {
m.add_class::<VectorQuery>()?;
m.add_class::<RecordBatchStream>()?;
m.add_class::<AddColumnsResult>()?;
m.add_class::<RefreshColumnResult>()?;
m.add_class::<AlterColumnsResult>()?;
m.add_class::<UpdateFieldMetadataResult>()?;
m.add_class::<AddResult>()?;
python/src/session.rs
+1 -1
View File
@@ -11,7 +11,7 @@ use pyo3::{PyResult, pyclass, pymethods};
/// Sessions allow you to configure cache sizes for index and metadata caches,
/// which can significantly impact memory use and performance. They can
/// also be re-used across multiple connections to share the same cache state.
#[pyclass(from_py_object)]
#[pyclass(module = "lancedb._lancedb", from_py_object)]
#[derive(Clone)]
pub struct Session {
pub(crate) inner: Arc<LanceSession>,
python/src/table.rs
+81 -16
View File
@@ -341,12 +341,22 @@ impl From<lancedb::table::MergeResult> for MergeResult {
}
}
/// Render for `__repr__`, so the default reads as Python's `None` rather than
/// Rust's `Some([..])`.
fn fmt_maintained(maintained: &Option<Vec<String>>) -> String {
match maintained {
Some(names) => format!("{:?}", names),
None => "None".to_string(),
}
}
/// Specification selecting Lance's MemWAL LSM-style write path for
/// `merge_insert`.
///
/// Constructed via the `bucket(...)`, `identity(...)`, or `unsharded()`
/// classmethods, then optionally chain `with_maintained_indexes(...)` and
/// `with_writer_config_defaults(...)`.
/// `with_writer_config_defaults(...)`. A fresh spec maintains every index the
/// MemWAL supports, resolved on install.
#[pyclass(from_py_object)]
#[derive(Clone, Debug)]
pub struct LsmWriteSpec {
@@ -386,11 +396,11 @@ impl LsmWriteSpec {
}
}
/// Replace the list of indexes the MemWAL should keep up to date as
/// rows are appended. Each name must reference an index that
/// already exists on the table at the time `set_lsm_write_spec`
/// is called.
pub fn with_maintained_indexes(&self, indexes: Vec<String>) -> Self {
/// Set which indexes the MemWAL maintains. `None` (the default)
/// resolves every supported index on install; a list is verbatim,
/// and an empty list maintains nothing.
#[pyo3(signature = (indexes))]
pub fn with_maintained_indexes(&self, indexes: Option<Vec<String>>) -> Self {
Self {
inner: self.inner.clone().with_maintained_indexes(indexes),
}
@@ -412,23 +422,29 @@ impl LsmWriteSpec {
maintained_indexes,
writer_config_defaults,
} => format!(
"LsmWriteSpec.bucket(column={:?}, num_buckets={}, maintained_indexes={:?}, writer_config_defaults={:?})",
column, num_buckets, maintained_indexes, writer_config_defaults,
"LsmWriteSpec.bucket(column={:?}, num_buckets={}, maintained_indexes={}, writer_config_defaults={:?})",
column,
num_buckets,
fmt_maintained(maintained_indexes),
writer_config_defaults,
),
lancedb::table::LsmWriteSpec::Identity {
column,
maintained_indexes,
writer_config_defaults,
} => format!(
"LsmWriteSpec.identity(column={:?}, maintained_indexes={:?}, writer_config_defaults={:?})",
column, maintained_indexes, writer_config_defaults,
"LsmWriteSpec.identity(column={:?}, maintained_indexes={}, writer_config_defaults={:?})",
column,
fmt_maintained(maintained_indexes),
writer_config_defaults,
),
lancedb::table::LsmWriteSpec::Unsharded {
maintained_indexes,
writer_config_defaults,
} => format!(
"LsmWriteSpec.unsharded(maintained_indexes={:?}, writer_config_defaults={:?})",
maintained_indexes, writer_config_defaults,
"LsmWriteSpec.unsharded(maintained_indexes={}, writer_config_defaults={:?})",
fmt_maintained(maintained_indexes),
writer_config_defaults,
),
}
}
@@ -463,10 +479,10 @@ impl LsmWriteSpec {
}
}
/// Names of indexes the MemWAL should keep up to date during writes.
/// Indexes the MemWAL keeps up to date, or `None` for every supported one.
#[getter]
pub fn maintained_indexes(&self) -> Vec<String> {
self.inner.maintained_indexes().to_vec()
pub fn maintained_indexes(&self) -> Option<Vec<String>> {
self.inner.maintained_indexes().map(<[String]>::to_vec)
}
/// Default `ShardWriter` configuration recorded by this spec.
@@ -494,6 +510,32 @@ pub struct AddColumnsResult {
pub version: u64,
}
#[pyclass(get_all, from_py_object)]
#[derive(Clone, Debug)]
pub struct RefreshColumnResult {
pub rows_filled: u64,
pub version: u64,
}
#[pymethods]
impl RefreshColumnResult {
pub fn __repr__(&self) -> String {
format!(
"RefreshColumnResult(rows_filled={}, version={})",
self.rows_filled, self.version
)
}
}
impl From<lancedb::table::RefreshColumnResult> for RefreshColumnResult {
fn from(result: lancedb::table::RefreshColumnResult) -> Self {
Self {
rows_filled: result.rows_filled,
version: result.version,
}
}
}
#[pymethods]
impl AddColumnsResult {
pub fn __repr__(&self) -> String {
@@ -658,7 +700,7 @@ impl PyBlobFile {
}
}
#[pyclass(get_all, from_py_object)]
#[pyclass(module = "lancedb._lancedb", get_all, from_py_object)]
#[derive(Clone, Debug)]
pub struct FtsToken {
pub text: String,
@@ -1591,6 +1633,29 @@ impl Table {
})
}
pub fn add_computed_columns(
self_: PyRef<'_, Self>,
columns: Vec<(String, String)>,
) -> PyResult<Bound<'_, PyAny>> {
let inner = self_.inner_ref()?.clone();
future_into_py(self_.py(), async move {
let mut builder = inner.add_columns();
for (name, expression) in columns {
builder = builder.computed(name, expression);
}
let result = builder.execute().await.infer_error()?;
Ok(AddColumnsResult::from(result))
})
}
pub fn refresh_column(self_: PyRef<'_, Self>, column: String) -> PyResult<Bound<'_, PyAny>> {
let inner = self_.inner_ref()?.clone();
future_into_py(self_.py(), async move {
let result = inner.refresh_column(column).await.infer_error()?;
Ok(RefreshColumnResult::from(result))
})
}
pub fn add_columns_with_schema(
self_: PyRef<'_, Self>,
schema: PyArrowType<Schema>,
rust/lancedb/Cargo.toml
+5 -4
View File
@@ -1,6 +1,6 @@
[package]
name = "lancedb"
version = "0.37.1-beta.0"
version = "0.38.0-beta.0"
edition.workspace = true
description = "LanceDB: A serverless, low-latency vector database for AI applications"
license.workspace = true
@@ -49,8 +49,6 @@ lance-namespace = { workspace = true }
lance-namespace-impls = { workspace = true }
metrics = { workspace = true, optional = true }
metrics-util = { workspace = true, optional = true }
# Pin the GooseFS SDK to the version required by Lance's OpenDAL dependency.
goosefs-sdk = { version = "=0.1.9", optional = true }
moka = { workspace = true }
pin-project = { workspace = true }
tokio = { version = "1.23", features = ["rt-multi-thread", "sync"] }
@@ -100,6 +98,7 @@ anyhow = "1"
lance-testing = { workspace = true }
tempfile = "3.5.0"
random_word = { version = "0.4.3", features = ["en"] }
roaring = "0.11.4"
tokio = { version = "1.23", features = ["io-util", "macros", "net", "rt-multi-thread", "sync", "test-util"] }
uuid = { version = "1.7.0", features = ["v4"] }
walkdir = "2"
@@ -135,7 +134,6 @@ azure = [
]
cos = ["lance/tencent", "lance-io/tencent"]
goosefs = [
"dep:goosefs-sdk",
"lance/goosefs",
"lance-io/goosefs",
"lance-namespace-impls/dir-goosefs",
@@ -190,6 +188,9 @@ required-features = ["bedrock"]
[[example]]
name = "bench_streaming_dataloader"
[[example]]
name = "bench_open_missing_table"
[[example]]
name = "simple"
rust/lancedb/examples/bench_open_missing_table.rs
+150
View File
@@ -0,0 +1,150 @@
// SPDX-License-Identifier: Apache-2.0
// SPDX-FileCopyrightText: Copyright The LanceDB Authors
// Release benchmark for opening a missing table as sibling-table cardinality grows.
//
// The fixture uses real `.lance` directories and marker files. Fixture creation is
// outside the timed section. Defaults intentionally cover 1k, 10k, and 100k siblings
// with 10 warmups and 100 distinct missing-table opens per scale:
//
// ```text
// cargo run --release -p lancedb --example bench_open_missing_table
// ```
//
// `BENCH_SIBLINGS`, `BENCH_WARMUPS`, and `BENCH_TRIALS` override those defaults.
// Reduced settings are useful only as a smoke test. Performance comparisons require
// the same machine, filesystem, fixture sizes, settings, lockfile, and alternating
// baseline/candidate execution order.
use std::time::{Duration, Instant};
use anyhow::{Context, Result, bail};
use lancedb::connection::Connection;
use lancedb::{Error, connect};
use object_store::ObjectStoreExt as _;
use object_store::path::Path;
const MAX_SIBLINGS: usize = 1_000_000;
const MAX_WARMUPS: usize = 10_000;
const MAX_TRIALS: usize = 100_000;
fn env_usize(key: &str, default: usize, max: usize) -> Result<usize> {
let value = match std::env::var(key) {
Ok(value) => value
.parse()
.with_context(|| format!("invalid {key} value: {value}"))?,
Err(std::env::VarError::NotPresent) => default,
Err(error) => return Err(error).with_context(|| format!("reading {key}")),
};
if value == 0 || value > max {
bail!("{key} must be between 1 and {max}");
}
Ok(value)
}
fn sibling_counts() -> Result<Vec<usize>> {
let raw = std::env::var("BENCH_SIBLINGS").unwrap_or_else(|_| "1000,10000,100000".into());
let mut counts = raw
.split(',')
.map(|value| {
value
.trim()
.parse::<usize>()
.with_context(|| format!("invalid BENCH_SIBLINGS value: {value}"))
})
.collect::<Result<Vec<_>>>()?;
counts.sort_unstable();
counts.dedup();
if counts.is_empty() || counts[0] == 0 || counts[counts.len() - 1] > MAX_SIBLINGS {
bail!("BENCH_SIBLINGS values must be between 1 and {MAX_SIBLINGS}");
}
Ok(counts)
}
async fn add_siblings(
store: &object_store::local::LocalFileSystem,
start: usize,
end: usize,
) -> Result<()> {
for index in start..end {
let marker = Path::from(format!("sibling_{index:06}.lance/_marker"));
store
.put(&marker, bytes::Bytes::new().into())
.await
.with_context(|| format!("creating benchmark marker {marker}"))?;
}
Ok(())
}
async fn time_missing_open(db: &Connection, name: &str) -> Result<Duration> {
let started = Instant::now();
let result = db.open_table(name).execute().await;
let elapsed = started.elapsed();
match result {
Err(Error::TableNotFound { .. }) => Ok(elapsed),
Err(error) => bail!("expected TableNotFound for {name}, got {error:?}"),
Ok(_) => bail!("benchmark missing-table name unexpectedly exists: {name}"),
}
}
fn percentile(sorted: &[Duration], percentile: usize) -> Duration {
let rank = (sorted.len() * percentile).div_ceil(100).saturating_sub(1);
sorted[rank]
}
#[tokio::main]
async fn main() -> Result<()> {
let counts = sibling_counts()?;
let warmups = env_usize("BENCH_WARMUPS", 10, MAX_WARMUPS)?;
let trials = env_usize("BENCH_TRIALS", 100, MAX_TRIALS)?;
let fixture = tempfile::tempdir().context("creating benchmark fixture")?;
let database_path = fixture.path();
let fixture_store = object_store::local::LocalFileSystem::new_with_prefix(database_path)
.context("creating benchmark object store")?;
let db = connect(database_path.to_str().context("non-UTF-8 fixture path")?)
.execute()
.await?;
println!(
"config: siblings={counts:?} warmups={warmups} trials={trials} profile={} os={} arch={}",
if cfg!(debug_assertions) {
"debug"
} else {
"release"
},
std::env::consts::OS,
std::env::consts::ARCH,
);
println!("lower is better; fixture setup and teardown are excluded");
println!("| siblings | samples | p50 | p95 | max |");
println!("| ---: | ---: | ---: | ---: | ---: |");
let mut created = 0;
for sibling_count in counts {
add_siblings(&fixture_store, created, sibling_count).await?;
created = sibling_count;
for index in 0..warmups {
let name = format!("__missing_warmup_{sibling_count}_{index}");
let _ = time_missing_open(&db, &name).await?;
}
let mut samples = Vec::with_capacity(trials);
for index in 0..trials {
let name = format!("__missing_trial_{sibling_count}_{index}");
samples.push(time_missing_open(&db, &name).await?);
}
samples.sort_unstable();
println!(
"| {sibling_count} | {} | {:?} | {:?} | {:?} |",
samples.len(),
percentile(&samples, 50),
percentile(&samples, 95),
samples[samples.len() - 1],
);
}
Ok(())
}
rust/lancedb/src/blob.rs
+7 -4
View File
@@ -17,7 +17,7 @@ use arrow_array::builder::LargeBinaryBuilder;
use arrow_schema::{DataType, Field, Schema};
use lance::dataset::{BlobRangeRequest as LanceBlobRangeRequest, Dataset, WriteParams};
use lance_arrow::FieldExt;
use lance_file::version::LanceFileVersion;
use lance_file::version::{ConcreteFileVersion, LanceFileVersion};
use lance_io::object_store::ObjectStore;
use object_store::path::Path;
@@ -333,7 +333,10 @@ pub(crate) fn ensure_blob_storage_version(schema: &Schema, params: &mut WritePar
.data_storage_version
.unwrap_or(LanceFileVersion::Stable)
.resolve();
if resolved < LanceFileVersion::V2_2 {
if matches!(
resolved,
ConcreteFileVersion::V1 | ConcreteFileVersion::V2_0 | ConcreteFileVersion::V2_1
) {
params.data_storage_version = Some(LanceFileVersion::V2_2);
}
}
@@ -499,7 +502,7 @@ mod tests {
ensure_blob_storage_version(&blob_schema(), &mut params);
assert_eq!(
params.data_storage_version.unwrap().resolve(),
LanceFileVersion::V2_2
ConcreteFileVersion::V2_2
);
}
@@ -512,7 +515,7 @@ mod tests {
ensure_blob_storage_version(&blob_schema(), &mut params);
assert_eq!(
params.data_storage_version.unwrap().resolve(),
LanceFileVersion::V2_2
ConcreteFileVersion::V2_2
);
}
rust/lancedb/src/connection.rs
+23 -4
View File
@@ -409,6 +409,11 @@ impl Connection {
///
/// The names will be returned in lexicographical order (ascending)
///
/// Listing databases discover physical `*.lance` entries without opening every
/// dataset. The result is a point-in-time discovery snapshot: an entry may still be
/// under creation, may contain only uncommitted storage, or may be concurrently
/// dropped before it is opened.
///
/// The parameters `page_token` and `limit` can be used to paginate the results
pub fn table_names(&self) -> TableNamesBuilder {
TableNamesBuilder::new(self.internal.clone())
@@ -456,10 +461,9 @@ impl Connection {
///
/// # Returns
/// Created [`TableRef`], or [`Error::TableNotFound`] if the table does not exist.
/// If the table's storage is present but holds no readable dataset (for example a
/// `<name>.lance` directory left behind by an interrupted drop and re-create, which
/// [`Self::table_names`] still lists) this returns [`Error::TableCorrupted`]
/// instead.
/// On listing databases, a committed Lance manifest is authoritative for table
/// existence. Uncommitted files or a physical `<name>.lance` directory alone do not
/// make a table openable.
pub fn open_table(&self, name: impl Into<String>) -> OpenTableBuilder {
OpenTableBuilder::new(
self.internal.clone(),
@@ -561,6 +565,21 @@ impl Connection {
.await
}
/// Start dropping a table and return a handle to the cleanup job.
///
/// The table may become unavailable before its physical data is removed.
/// Call [`crate::job::Job::wait`] to wait for cleanup to finish. Local
/// backends may complete the drop before returning the handle.
pub async fn drop_table_async(
&self,
name: impl AsRef<str>,
namespace_path: &[String],
) -> Result<crate::job::Job> {
self.internal
.drop_table_async(name.as_ref(), namespace_path)
.await
}
/// Drop the database
///
/// This is the same as dropping all of the tables
rust/lancedb/src/connection/create_table.rs
+2 -3
View File
@@ -438,10 +438,9 @@ mod tests {
.await
.unwrap()
.data_storage_format
.lance_file_version()
.unwrap();
.lance_file_format();
// Compare resolved versions since Stable/Next are aliases that resolve at storage time
assert_eq!(storage_format.resolve(), data_storage_version.resolve());
assert_eq!(storage_format, data_storage_version.resolve());
}
#[tokio::test]
rust/lancedb/src/database.rs
+12
View File
@@ -323,6 +323,18 @@ pub trait Database:
) -> Result<()>;
/// Drop a table in the database
async fn drop_table(&self, name: &str, namespace_path: &[String]) -> Result<()>;
/// Start dropping a table and return a handle to the cleanup job.
///
/// Backends without asynchronous cleanup complete the drop before
/// returning an already-finished job.
async fn drop_table_async(
&self,
name: &str,
namespace_path: &[String],
) -> Result<crate::job::Job> {
self.drop_table(name, namespace_path).await?;
Ok(crate::job::Job::new_done())
}
/// Drop all tables in the database
async fn drop_all_tables(&self, namespace_path: &[String]) -> Result<()>;
fn as_any(&self) -> &dyn std::any::Any;
rust/lancedb/src/database/listing.rs
+115 -2
View File
@@ -1291,16 +1291,21 @@ impl Database for ListingDatabase {
mod tests {
use super::*;
use crate::Table;
use crate::arrow::{SendableRecordBatchStream, SimpleRecordBatchStream};
use crate::connection::ConnectRequest;
use crate::data::scannable::Scannable;
use crate::database::{CreateTableMode, CreateTableRequest};
use crate::query::QueryRequest;
use crate::table::{AnyQuery, WriteOptions};
use arrow_array::{Int32Array, RecordBatch, StringArray};
use arrow_schema::{DataType, Field, Schema};
use futures::TryStreamExt;
use arrow_schema::{DataType, Field, Schema, SchemaRef};
use futures::{TryStreamExt, stream::once};
use std::path::PathBuf;
use std::sync::Arc;
use std::time::Duration;
use tempfile::tempdir;
use tokio::sync::Barrier;
use tokio::time::timeout;
async fn setup_database() -> (tempfile::TempDir, ListingDatabase) {
let tempdir = tempdir().unwrap();
@@ -1324,6 +1329,114 @@ mod tests {
(tempdir, db)
}
struct BarrierScannable {
batch: RecordBatch,
barrier: Arc<Barrier>,
}
impl Scannable for BarrierScannable {
fn schema(&self) -> SchemaRef {
self.batch.schema()
}
fn scan_as_stream(&mut self) -> SendableRecordBatchStream {
let batch = self.batch.clone();
let schema = batch.schema();
let barrier = self.barrier.clone();
Box::pin(SimpleRecordBatchStream {
schema,
stream: once(async move {
barrier.wait().await;
Ok(batch)
}),
})
}
}
fn create_request(name: &str, data: Box<dyn Scannable>) -> CreateTableRequest {
CreateTableRequest {
name: name.to_string(),
namespace_path: vec![],
data,
mode: CreateTableMode::Create,
write_options: Default::default(),
location: None,
namespace_client: None,
}
}
#[tokio::test]
async fn test_create_ignores_uncommitted_storage_without_manifest() {
let (tmp_dir, db) = setup_database().await;
let data_dir = tmp_dir.path().join("test.lance/data");
std::fs::create_dir_all(&data_dir).unwrap();
std::fs::write(data_dir.join("orphan.lance"), b"uncommitted").unwrap();
let schema = Arc::new(Schema::new(vec![Field::new("id", DataType::Int32, false)]));
let batch =
RecordBatch::try_new(schema, vec![Arc::new(Int32Array::from(vec![1]))]).unwrap();
let table = db
.create_table(create_request("test", Box::new(batch)))
.await
.unwrap();
assert_eq!(table.count_rows(None).await.unwrap(), 1);
}
#[tokio::test]
async fn test_concurrent_create_is_arbitrated_by_manifest_commit() {
let uri = format!("memory:///concurrent-create-{}", uuid::Uuid::new_v4());
let db = crate::connect(&uri).execute().await.unwrap();
let store: Arc<dyn object_store::ObjectStore> =
Arc::new(object_store::memory::InMemory::new());
let table_url = url::Url::parse("memory:///database/test.lance").unwrap();
let schema = Arc::new(Schema::new(vec![Field::new("id", DataType::Int32, false)]));
let batch =
RecordBatch::try_new(schema, vec![Arc::new(Int32Array::from(vec![1]))]).unwrap();
let barrier = Arc::new(Barrier::new(2));
#[allow(deprecated)]
let request = |batch, barrier| {
let mut request = create_request("test", Box::new(BarrierScannable { batch, barrier }));
request.write_options = WriteOptions {
lance_write_params: Some(lance::dataset::WriteParams {
store_params: Some(ObjectStoreParams {
object_store: Some((store.clone(), table_url.clone())),
..Default::default()
}),
commit_handler: Some(Arc::new(
lance_table::io::commit::ConditionalPutCommitHandler,
)),
..Default::default()
}),
};
request
};
let left = db
.database()
.create_table(request(batch.clone(), barrier.clone()));
let right = db.database().create_table(request(batch, barrier));
let (left, right) = timeout(Duration::from_secs(30), async { tokio::join!(left, right) })
.await
.expect("concurrent creates deadlocked");
let results = [left, right];
assert_eq!(
results.iter().filter(|result| result.is_ok()).count(),
1,
"expected one successful create, got {results:?}"
);
assert_eq!(
results
.iter()
.filter(|result| matches!(result, Err(Error::TableAlreadyExists { .. })))
.count(),
1,
"expected one manifest conflict, got {results:?}"
);
}
#[tokio::test]
async fn test_listing_database_root_ops_do_not_create_manifest() {
let tempdir = tempdir().unwrap();
rust/lancedb/src/error.rs
+8
View File
@@ -71,6 +71,14 @@ pub enum Error {
IndexNotFound { name: String },
#[snafu(display("Embedding function '{name}' was not found. : {reason}"))]
EmbeddingFunctionNotFound { name: String, reason: String },
#[snafu(display("Column '{name}' was not found"))]
ColumnNotFound { name: String },
#[snafu(display("Column '{name}' already exists"))]
ColumnAlreadyExists { name: String },
#[snafu(display("Column '{name}' is not a computed column"))]
NotAComputedColumn { name: String },
#[snafu(display("Invalid expression for column '{column}': {message}"))]
InvalidExpression { column: String, message: String },
#[snafu(display("Table '{name}' already exists"))]
TableAlreadyExists { name: String },
rust/lancedb/src/remote.rs
+9
View File
@@ -19,6 +19,15 @@ const ARROW_FILE_CONTENT_TYPE: &str = "application/vnd.apache.arrow.file";
#[cfg(test)]
const JSON_CONTENT_TYPE: &str = "application/json";
fn extract_job_id(body: &str) -> Option<String> {
serde_json::from_str::<serde_json::Value>(body)
.ok()?
.get("job_id")?
.as_str()
.filter(|job_id| !job_id.is_empty())
.map(str::to_string)
}
pub use client::{ClientConfig, HeaderProvider, RetryConfig, TimeoutConfig, TlsConfig};
pub use db::{RemoteDatabaseOptions, RemoteDatabaseOptionsBuilder};
pub use oauth::{OAuthConfig, OAuthFlow, OAuthHeaderProvider};
rust/lancedb/src/remote/db.rs
+103 -8
View File
@@ -9,6 +9,7 @@ use http::StatusCode;
use lance_io::object_store::StorageOptions;
use lance_namespace_impls::{DynamicContextProvider, OperationInfo};
use moka::future::Cache;
use reqwest::Response;
use reqwest::header::CONTENT_TYPE;
use lance_namespace::models::{
@@ -23,15 +24,17 @@ use crate::database::{
JobDescription, JobInfo, OpenTableRequest, ReadConsistency, TableNamesRequest,
};
use crate::error::Result;
use crate::job::Job;
use crate::remote::job::RemoteJob;
use crate::remote::util::stream_as_body;
use crate::table::BaseTable;
use super::ARROW_STREAM_CONTENT_TYPE;
use super::client::{
ClientConfig, HeaderProvider, HttpSend, RequestResultExt, RestfulLanceDbClient, Sender,
};
use super::table::RemoteTable;
use super::util::parse_server_version;
use super::{ARROW_STREAM_CONTENT_TYPE, extract_job_id};
// Request structure for the remote clone table API
#[derive(serde::Serialize)]
@@ -326,6 +329,22 @@ impl RemoteDatabase {
}
}
impl<S: HttpSend> RemoteDatabase<S> {
async fn submit_drop_table(
&self,
name: &str,
namespace_path: &[String],
) -> Result<(String, Response)> {
let identifier = build_table_identifier(name, namespace_path, &self.client.id_delimiter);
let cache_key = build_cache_key(name, namespace_path);
let req = self.client.post(&format!("/v1/table/{}/drop/", identifier));
let (request_id, resp) = self.client.send(req).await?;
let resp = self.client.check_response(&request_id, resp).await?;
self.table_cache.remove(&cache_key).await;
Ok((request_id, resp))
}
}
#[cfg(all(test, feature = "remote"))]
mod test_utils {
use super::*;
@@ -894,13 +913,28 @@ impl<S: HttpSend> Database for RemoteDatabase<S> {
}
async fn drop_table(&self, name: &str, namespace_path: &[String]) -> Result<()> {
let identifier = build_table_identifier(name, namespace_path, &self.client.id_delimiter);
let cache_key = build_cache_key(name, namespace_path);
let req = self.client.post(&format!("/v1/table/{}/drop/", identifier));
let (request_id, resp) = self.client.send(req).await?;
self.client.check_response(&request_id, resp).await?;
self.table_cache.remove(&cache_key).await;
Ok(())
self.submit_drop_table(name, namespace_path)
.await
.map(|_| ())
}
async fn drop_table_async(&self, name: &str, namespace_path: &[String]) -> Result<Job> {
let (request_id, response) = self.submit_drop_table(name, namespace_path).await?;
let status = response.status();
let body = response.text().await.err_to_http(request_id.clone())?;
let job_id = extract_job_id(&body);
Ok(match job_id {
Some(job_id) => Job::new(Box::new(RemoteJob::new(self.client.clone(), job_id))),
None if status == StatusCode::ACCEPTED => {
return Err(Error::Http {
source: "asynchronous drop-table response did not contain a valid job_id"
.into(),
request_id,
status_code: Some(status),
});
}
None => Job::new_done(),
})
}
async fn drop_all_tables(&self, namespace_path: &[String]) -> Result<()> {
@@ -1492,6 +1526,67 @@ mod tests {
// NOTE: the API will return 200 even if the table does not exist. So we shouldn't expect 404.
}
#[tokio::test]
async fn test_drop_table_does_not_read_response_body() {
let conn = Connection::new_with_handler(|_| {
http::Response::builder()
.status(200)
.body(vec![0xff])
.unwrap()
});
conn.drop_table("table1", &[]).await.unwrap();
}
#[tokio::test]
async fn test_drop_table_async_returns_job() {
let conn = Connection::new_with_handler(|request| {
assert_eq!(request.method(), &reqwest::Method::POST);
assert_eq!(request.url().path(), "/v1/table/table1/drop/");
http::Response::builder()
.status(202)
.body(r#"{"job_id":"drop-job-123"}"#)
.unwrap()
});
let job = conn.drop_table_async("table1", &[]).await.unwrap();
assert_eq!(job.id(), Some("drop-job-123"));
}
#[tokio::test]
async fn test_drop_table_async_old_server_returns_done_job() {
let conn = Connection::new_with_handler(|_| {
http::Response::builder().status(200).body("").unwrap()
});
let job = conn.drop_table_async("table1", &[]).await.unwrap();
assert_eq!(job.id(), None);
assert_eq!(job.status().await.unwrap(), "finished");
}
#[tokio::test]
async fn test_drop_table_async_rejects_accepted_response_without_job_id() {
let conn = Connection::new_with_handler(|_| {
http::Response::builder().status(202).body("{}").unwrap()
});
let error = conn.drop_table_async("table1", &[]).await.err().unwrap();
assert!(error.to_string().contains("valid job_id"));
}
#[tokio::test]
async fn test_drop_table_async_rejects_empty_job_id() {
let conn = Connection::new_with_handler(|_| {
http::Response::builder()
.status(202)
.body(r#"{"job_id":""}"#)
.unwrap()
});
let error = conn.drop_table_async("table1", &[]).await.err().unwrap();
assert!(error.to_string().contains("valid job_id"));
}
#[tokio::test]
async fn test_rename_table() {
let conn = Connection::new_with_handler(|request| {
rust/lancedb/src/remote/table.rs
+64 -14
View File
@@ -8,7 +8,7 @@ use self::insert::{RemoteWriteExec, WriteOp};
use super::client::RequestResultExt;
use super::client::{HttpSend, RestfulLanceDbClient, Sender};
use super::db::ServerVersion;
use super::{ARROW_FILE_CONTENT_TYPE, ARROW_STREAM_CONTENT_TYPE};
use super::{ARROW_FILE_CONTENT_TYPE, ARROW_STREAM_CONTENT_TYPE, extract_job_id};
use crate::blob::BlobFile;
use crate::data::scannable::{PeekedScannable, Scannable, estimate_write_partitions};
use crate::expr::expr_to_sql_string;
@@ -392,13 +392,7 @@ impl<S: HttpSend> RemoteTable<S> {
.text()
.await
.ok()
.and_then(|body| serde_json::from_str::<serde_json::Value>(&body).ok())
.and_then(|value| {
value
.get("job_id")
.and_then(|id| id.as_str())
.map(str::to_string)
});
.and_then(|body| extract_job_id(&body));
if let Some(wait_timeout) = index.wait_timeout {
let index_name = index.name.unwrap_or_else(|| format!("{}_idx", column));
@@ -2520,9 +2514,9 @@ impl<S: HttpSend> BaseTable for RemoteTable<S> {
self.check_mutable().await?;
// Map the spec onto the server's request DTO. `sharding` is internally
// tagged on `mode` to mirror sophon's `Sharding` enum; `maintained_indexes`
// and `writer_config_defaults` are sent verbatim (an empty list means "no
// maintained indexes", not "default to all").
// tagged on `mode` to mirror sophon's `Sharding` enum. A null
// `maintained_indexes` asks the server to resolve every maintainable
// index at HEAD; a list is verbatim, an empty one meaning none.
let sharding = match &spec {
LsmWriteSpec::Bucket {
column,
@@ -2706,6 +2700,13 @@ impl<S: HttpSend> BaseTable for RemoteTable<S> {
Ok(result)
}
// A declaration reaches here as AllNulls, which the remote protocol
// has no representation for.
NewColumnTransform::AllNulls(_) => {
return Err(Error::NotSupported {
message: "computed columns are supported only on local tables".into(),
});
}
_ => {
return Err(Error::NotSupported {
message: "Only SQL expressions are supported for adding columns".into(),
@@ -6455,6 +6456,37 @@ mod tests {
assert_eq!(result.version, if old_server { 0 } else { 43 });
}
/// Computed columns are local-only. Both halves say so here rather than
/// reaching the wire and failing somewhere less legible.
#[tokio::test]
async fn test_computed_columns_are_refused() {
let table = Table::new_with_handler("my_table", |request| -> http::Response<String> {
panic!("unexpected request: {}", request.url().path())
});
let declared = Arc::new(Schema::new(vec![Field::new(
"doubled",
DataType::Int32,
true,
)]));
let err = table
.add_columns()
.transform(NewColumnTransform::AllNulls(declared))
.execute()
.await
.unwrap_err();
assert!(
matches!(&err, Error::NotSupported { message } if message.contains("local tables")),
"{err:?}"
);
let err = table.refresh_column("doubled").await.unwrap_err();
assert!(
matches!(&err, Error::NotSupported { message } if message.contains("local tables")),
"{err:?}"
);
}
#[tokio::test]
async fn test_prewarm_index() {
let table = Table::new_with_handler("my_table", |request| {
@@ -6599,7 +6631,7 @@ mod tests {
.unwrap()
});
let spec = crate::table::LsmWriteSpec::unsharded()
.with_maintained_indexes(["id_idx"])
.with_maintained_indexes(vec!["id_idx".to_string()])
.with_writer_config_defaults([("max_memtable_rows", "1000")]);
table.set_lsm_write_spec(spec).await.unwrap();
}
@@ -6618,7 +6650,8 @@ mod tests {
body["sharding"],
serde_json::json!({ "mode": "bucket", "column": "id", "num_buckets": 16 })
);
assert_eq!(body["maintained_indexes"], serde_json::json!([]));
// An unpinned maintained set sends null: resolve server-side.
assert_eq!(body["maintained_indexes"], serde_json::Value::Null);
http::Response::builder().status(200).body("{}").unwrap()
});
table
@@ -6627,6 +6660,23 @@ mod tests {
.unwrap();
}
/// `[]` (none) must stay distinguishable on the wire from null (all).
#[tokio::test]
async fn test_set_lsm_write_spec_no_maintained_indexes() {
let table = Table::new_with_handler("my_table", |request| {
let body = request.body().unwrap().as_bytes().unwrap();
let body: serde_json::Value = serde_json::from_slice(body).unwrap();
assert_eq!(body["maintained_indexes"], serde_json::json!([]));
http::Response::builder().status(200).body("{}").unwrap()
});
table
.set_lsm_write_spec(
crate::table::LsmWriteSpec::bucket("id", 16).with_maintained_indexes(Vec::new()),
)
.await
.unwrap();
}
#[tokio::test]
async fn test_set_lsm_write_spec_identity() {
let table = Table::new_with_handler("my_table", |request| {
@@ -6701,7 +6751,7 @@ mod tests {
} => {
assert_eq!(column, "id");
assert_eq!(num_buckets, 4);
assert_eq!(maintained_indexes, vec!["id_idx".to_string()]);
assert_eq!(maintained_indexes, Some(vec!["id_idx".to_string()]));
assert_eq!(
writer_config_defaults
.get("durable_write")
rust/lancedb/src/table.rs
+684 -143
View File
File diff suppressed because it is too large Load Diff
rust/lancedb/src/table/add_columns.rs
+118 -22
View File
@@ -15,6 +15,7 @@ use crate::{Error, Result};
pub struct AddColumnsBuilder {
parent: Arc<dyn BaseTable>,
transform: Option<NewColumnTransform>,
computed: Vec<(String, String)>,
read_columns: Option<Vec<String>>,
}
@@ -23,6 +24,7 @@ impl std::fmt::Debug for AddColumnsBuilder {
f.debug_struct("AddColumnsBuilder")
.field("parent", &self.parent)
.field("has_transform", &self.transform.is_some())
.field("computed", &self.computed)
.field("read_columns", &self.read_columns)
.finish()
}
@@ -33,19 +35,57 @@ impl AddColumnsBuilder {
Self {
parent,
transform: None,
computed: Vec::new(),
read_columns: None,
}
}
/// Set how the new columns' values are produced. Required.
/// Set how the new columns' values are produced.
pub fn transform(mut self, transform: NewColumnTransform) -> Self {
self.transform = Some(transform);
self
}
/// Add a column defined by `expression`, evaluated by a later refresh
/// rather than by this commit. Its type and inputs are derived from the
/// expression.
///
/// The column is committed with no values, so declaring one costs the same
/// on an empty table as on a large one. Rows get values from
/// [`Table::refresh_column`](super::Table::refresh_column), which fills
/// every fragment that has none -- including fragments appended since the
/// last refresh.
///
/// Refresh does not revisit a fragment it has filled, so mutating an input
/// leaves the value computed at fill time; recomputing means dropping the
/// column and declaring it again. An input cannot be renamed, retyped or
/// dropped while a declaration reads it, since the expression names it.
///
/// Local tables only: LanceDB Cloud and Enterprise reject a declaration
/// with `NotSupported`.
///
/// ```
/// # use lancedb::Table;
/// # async fn declare(table: &Table) -> Result<(), Box<dyn std::error::Error>> {
/// table
/// .add_columns()
/// .computed("doubled", "x * 2")
/// .execute()
/// .await?;
/// let filled = table.refresh_column("doubled").await?;
/// println!("filled {} rows", filled.rows_filled);
/// # Ok(())
/// # }
/// ```
pub fn computed(mut self, name: impl Into<String>, expression: impl Into<String>) -> Self {
self.computed.push((name.into(), expression.into()));
self
}
/// Limit which existing columns a [`NewColumnTransform::BatchUDF`] mapper
/// receives. Every other transform determines what it reads, so setting
/// this alongside one is an error rather than a silent no-op.
/// receives. Every other transform, and a computed column, determines what
/// it reads, so setting this alongside one is an error rather than a silent
/// no-op.
pub fn read_columns(mut self, columns: impl IntoIterator<Item = impl Into<String>>) -> Self {
self.read_columns = Some(columns.into_iter().map(Into::into).collect());
self
@@ -56,24 +96,42 @@ impl AddColumnsBuilder {
let Self {
parent,
transform,
computed,
read_columns,
} = self;
let Some(transform) = transform else {
return Err(Error::InvalidInput {
message: "add_columns requires a transform".into(),
});
};
if read_columns.is_some() && !matches!(transform, NewColumnTransform::BatchUDF(_)) {
return Err(Error::InvalidInput {
message: "read_columns applies only to a BatchUDF transform; \
every other transform determines what it reads"
match (transform, computed.is_empty()) {
(None, true) => Err(Error::InvalidInput {
message: "add_columns requires a transform or a computed column".into(),
}),
// The two commit through different transforms, so one call covering
// both would be two commits and could half-apply.
(Some(_), false) => Err(Error::InvalidInput {
message: "add_columns cannot mix a transform with computed columns; \
they cannot be added atomically in one call"
.into(),
});
}),
(Some(transform), true) => {
if read_columns.is_some() && !matches!(transform, NewColumnTransform::BatchUDF(_)) {
return Err(Error::InvalidInput {
message: "read_columns applies only to a BatchUDF transform; \
every other transform determines what it reads"
.into(),
});
}
parent.add_columns(transform, read_columns).await
}
(None, false) => {
if read_columns.is_some() {
return Err(Error::InvalidInput {
message: "read_columns applies only to a BatchUDF transform; \
a computed column's inputs come from its expression"
.into(),
});
}
parent.add_computed_columns(&computed).await
}
}
parent.add_columns(transform, read_columns).await
}
}
@@ -85,8 +143,8 @@ mod tests {
use arrow_schema::{DataType, Field, Schema};
use lance::dataset::{BatchUDF, NewColumnTransform};
use crate::Table;
use crate::connect;
use crate::{Error, Table};
async fn table_with_two_columns(name: &str) -> Table {
let conn = connect("memory://").execute().await.unwrap();
@@ -98,10 +156,7 @@ mod tests {
async fn test_requires_a_transform() {
let table = table_with_two_columns("no_transform").await;
let err = table.add_columns().execute().await.unwrap_err();
assert!(
err.to_string().contains("requires a transform"),
"got: {err}"
);
assert!(matches!(err, Error::InvalidInput { .. }));
}
#[tokio::test]
@@ -117,7 +172,7 @@ mod tests {
.execute()
.await
.unwrap_err();
assert!(err.to_string().contains("BatchUDF"), "got: {err}");
assert!(matches!(err, Error::InvalidInput { .. }));
let schema = table.schema().await.unwrap();
assert!(
@@ -126,6 +181,47 @@ mod tests {
);
}
#[tokio::test]
async fn test_mixing_transform_and_computed_is_rejected() {
let table = table_with_two_columns("mixed_add").await;
let err = table
.add_columns()
.transform(NewColumnTransform::SqlExpressions(vec![(
"eager".into(),
"x * 2".into(),
)]))
.computed("lazy", "x * 3")
.execute()
.await
.unwrap_err();
assert!(matches!(err, Error::InvalidInput { .. }));
let schema = table.schema().await.unwrap();
assert!(schema.field_with_name("eager").is_err());
assert!(schema.field_with_name("lazy").is_err());
}
#[tokio::test]
async fn test_read_columns_with_computed_is_rejected() {
let table = table_with_two_columns("read_cols_computed").await;
let err = table
.add_columns()
.computed("doubled", "x * 2")
.read_columns(["x"])
.execute()
.await
.unwrap_err();
assert!(matches!(err, Error::InvalidInput { .. }));
assert!(
table
.schema()
.await
.unwrap()
.field_with_name("doubled")
.is_err()
);
}
#[tokio::test]
async fn test_read_columns_limits_what_a_batch_udf_sees() {
let table = table_with_two_columns("read_cols_udf").await;
rust/lancedb/src/table/computed_columns.rs
+1348
View File
File diff suppressed because it is too large Load Diff
rust/lancedb/src/table/datafusion/insert.rs
+14 -3
View File
@@ -17,7 +17,7 @@ use datafusion_physical_plan::stream::RecordBatchStreamAdapter;
use datafusion_physical_plan::{
DisplayAs, DisplayFormatType, ExecutionPlan, ExecutionPlanProperties, PlanProperties,
};
use futures::TryStreamExt;
use futures::StreamExt;
use lance::Dataset;
use lance::dataset::transaction::{Operation, Transaction};
use lance::dataset::{CommitBuilder, InsertBuilder, WriteParams, WriteProgressFn};
@@ -194,12 +194,23 @@ impl ExecutionPlan for InsertExec {
let output_bytes = MetricBuilder::new(&self.metrics).output_bytes(partition);
let input_schema = input_stream.schema();
let declared: Vec<String> = crate::table::computed_columns::computed_columns(
&arrow_schema::Schema::from(self.dataset.schema()),
)
.into_iter()
.map(|declaration| declaration.name)
.collect();
let input_stream: SendableRecordBatchStream =
Box::pin(InstrumentedRecordBatchStreamAdapter::new(
input_schema,
input_stream.map_ok(move |batch| {
input_stream.map(move |batch| {
let batch = batch?;
crate::table::computed_columns::ensure_batch_writes_no_computed_values(
&declared, &batch,
)
.map_err(|e| datafusion::error::DataFusionError::External(Box::new(e)))?;
output_bytes.add(batch.get_array_memory_size());
batch
Ok(batch)
}),
partition,
&self.metrics,
rust/lancedb/src/table/merge.rs
+2 -2
View File
@@ -1161,7 +1161,7 @@ mod lsm_tests {
.unwrap();
let fts_index = table.list_indices().await.unwrap()[0].name.clone();
table
.set_lsm_write_spec(LsmWriteSpec::unsharded().with_maintained_indexes([fts_index]))
.set_lsm_write_spec(LsmWriteSpec::unsharded().with_maintained_indexes(vec![fts_index]))
.await
.unwrap();
@@ -1254,7 +1254,7 @@ mod lsm_tests {
.unwrap();
let vec_index = table.list_indices().await.unwrap()[0].name.clone();
table
.set_lsm_write_spec(LsmWriteSpec::unsharded().with_maintained_indexes([vec_index]))
.set_lsm_write_spec(LsmWriteSpec::unsharded().with_maintained_indexes(vec![vec_index]))
.await
.unwrap();
rust/lancedb/src/table/merge/lsm.rs
+113 -8
View File
@@ -29,6 +29,7 @@ use arrow_schema::{DataType, Schema as ArrowSchema, SchemaRef};
use lance::Dataset;
use lance::dataset::mem_wal::{
DatasetMemWalExt, ShardWriter, ShardWriterConfig, evaluate_sharding_spec,
validate_maintained_indexes,
};
use lance::index::DatasetIndexExt;
use lance_core::datatypes::Schema as LanceSchema;
@@ -37,8 +38,9 @@ use tokio::sync::RwLock;
use uuid::Uuid;
use crate::error::{Error, Result};
use crate::index::IndexConfig;
use crate::table::merge::{MergeInsertBuilder, MergeResult};
use crate::table::{LsmWriteSpec, NativeTable};
use crate::table::{BaseTable, LsmWriteSpec, NativeTable};
/// Spec id of the sole sharding spec installed by [`set_lsm_write_spec`].
/// Must match Lance's `InitializeMemWalBuilder` (`SHARDING_SPEC_ID`).
@@ -80,32 +82,53 @@ pub(crate) async fn set_lsm_write_spec(table: &NativeTable, spec: LsmWriteSpec)
}
}
// Before the builder borrows the dataset clone. `list_indices` merges an
// index's segments into one entry, so the result needs no dedup.
let maintained_indexes = {
let dataset = table.dataset.get().await?;
resolve_maintained_indexes(
&dataset,
&table.list_indices().await?,
spec.maintained_indexes(),
)
.await?
};
table.checkout_latest().await?;
let mut dataset = (*table.dataset.get().await?).clone();
let schema = arrow_schema::Schema::from(dataset.schema());
if !crate::table::computed_columns::computed_columns(&schema).is_empty() {
return Err(Error::NotSupported {
message: "an LSM write spec cannot be installed on a table with computed \
columns: rows in un-compacted tiers are invisible to refresh"
.into(),
});
}
let mut builder = dataset.initialize_mem_wal();
let (maintained_indexes, writer_config_defaults) = match spec {
let writer_config_defaults = match spec {
LsmWriteSpec::Bucket {
column,
num_buckets,
maintained_indexes,
writer_config_defaults,
..
} => {
builder = builder.bucket_sharding(column, num_buckets);
(maintained_indexes, writer_config_defaults)
writer_config_defaults
}
LsmWriteSpec::Identity {
column,
maintained_indexes,
writer_config_defaults,
..
} => {
builder = builder.identity_sharding(column);
(maintained_indexes, writer_config_defaults)
writer_config_defaults
}
LsmWriteSpec::Unsharded {
maintained_indexes,
writer_config_defaults,
..
} => {
builder = builder.unsharded();
(maintained_indexes, writer_config_defaults)
writer_config_defaults
}
};
builder = builder.maintained_indexes(maintained_indexes);
@@ -117,6 +140,88 @@ pub(crate) async fn set_lsm_write_spec(table: &NativeTable, spec: LsmWriteSpec)
Ok(())
}
/// Resolve a spec's maintained-index selection against `indices`, as reported
/// by [`Table::list_indices`](crate::Table::list_indices).
///
/// `None` means every index on the table, snapshotted now. Lance validates
/// either selection against its shard-writer rules, so a spec that installs is
/// one the MemWAL can open.
///
/// An unmaintainable index fails an inferred set rather than being dropped from
/// it — dropping would leave the caller believing it is maintained.
async fn resolve_maintained_indexes(
dataset: &Dataset,
indices: &[IndexConfig],
requested: Option<&[String]>,
) -> Result<Vec<String>> {
let Some(requested) = requested else {
let all: Vec<String> = indices.iter().map(|index| index.name.clone()).collect();
validate_maintained_indexes(dataset, &all)
.await
.map_err(|source| Error::InvalidInput {
message: format!(
"cannot maintain every index on this table: {source}. Set \
maintained_indexes explicitly to choose from {}",
index_name_list(indices),
),
})?;
return Ok(all);
};
for name in requested {
if !indices.iter().any(|index| &index.name == name) {
return Err(Error::InvalidInput {
message: format!(
"maintained index '{}' does not exist on this table; it has {}",
name,
index_name_list(indices),
),
});
}
}
validate_maintained_indexes(dataset, requested).await?;
Ok(requested.to_vec())
}
/// Index names for an error message.
fn index_name_list(indices: &[IndexConfig]) -> String {
if indices.is_empty() {
return "no indexes".to_string();
}
let mut names: Vec<&str> = indices.iter().map(|index| index.name.as_str()).collect();
names.sort_unstable();
format!("[{}]", names.join(", "))
}
// =============================================================================
// require_mem_wal_index_catchup
// =============================================================================
/// Switch this table to required index catch-up, one way.
///
/// Deliberately **not** part of installing the write spec. Until something can
/// actually repair coverage, a table carrying the bit reports every index as
/// not known to hold the compacted rows, so its SSTables are retained
/// indefinitely -- and the WAL pod trims on the legacy rule meanwhile, leaving
/// readers pointed at files that are gone. Turn this on only once remote
/// maintenance owns the merge and the repair for the table.
///
/// Lance refuses the activation if the table already records SSTable
/// compaction progress: those numbers predate this protocol and cannot be
/// validated, so such a table must be drained rather than activated.
#[allow(clippy::redundant_pub_crate)]
pub(crate) async fn require_mem_wal_index_catchup(table: &NativeTable) -> Result<()> {
table.dataset.ensure_mutable()?;
let mut dataset = (*table.dataset.get().await?).clone();
if dataset.mem_wal_index_details().await?.is_none() {
return Err(Error::InvalidInput {
message: "require_mem_wal_index_catchup: no LSM write spec is set on this table".into(),
});
}
dataset.require_mem_wal_index_catchup().await?;
table.dataset.update(dataset);
Ok(())
}
// =============================================================================
// unset_lsm_write_spec
// =============================================================================
rust/lancedb/src/table/query/lsm.rs
+202 -52
View File
@@ -36,6 +36,7 @@ use lance::dataset::mem_wal::{
DatasetMemWalExt, LsmScanner, ShardManifestStore, ShardSnapshot, ShardWriterConfig,
};
use lance_index::mem_wal::{MemWalIndexDetails, ShardManifest};
use lance_table::feature_flags::FLAG_MEM_WAL_INDEX_CATCHUP;
use uuid::Uuid;
use super::NativeTable;
@@ -84,9 +85,8 @@ pub(super) async fn create_lsm_plan(
let pk_columns = pk_columns(&ds_ref)?;
// The base index an indexed arm relies on may lag compaction; resolve it so the
// snapshot retains SSTables the index has not yet caught up to.
let arm_index = arm_maintained_index_name(&ds_ref, &query, &details).await?;
let (snapshots, in_memory) =
build_read_context(table, &ds_ref, &details, arm_index.as_deref()).await?;
let arm_indexes = arm_maintained_index_names(&ds_ref, &query, &details).await?;
let (snapshots, in_memory) = build_read_context(table, &ds_ref, &details, &arm_indexes).await?;
let limit = query.base.limit;
let offset = query.base.offset;
@@ -232,28 +232,44 @@ fn pk_columns(dataset: &Dataset) -> Result<Vec<String>> {
Ok(pk)
}
/// Per-shard SSTable exclusion watermark: the generation at or below which SSTables
/// are safe to drop for this arm. A generation is droppable only once it is
/// compacted into the base table AND covered by `index_name`'s catch-up (for an
/// indexed arm); a plain scan (`index_name == None`) uses the compaction watermark
/// alone. Capping at the index catch-up keeps rows the base index has not yet
/// indexed visible through their SSTable. First occurrence per shard mirrors Lance's
/// `compacted_generation_for_shard`.
/// Per-shard SSTable exclusion watermark: the generation at or below which
/// SSTables are safe to drop for this query.
///
/// A generation is droppable only once it is compacted into the base table AND
/// covered by the catch-up of every index the query relies on, so the watermark
/// is the minimum across `index_names`. Gating on fewer than all of them would
/// drop SSTables holding rows an uncounted index has not yet indexed, and that
/// arm would silently return fewer rows.
///
/// See [`arm_maintained_index_names`] for which indexes are collected today: a
/// vector search with a scalar prefilter is not yet among them.
///
/// An empty `index_names` (a plain scan) uses the compaction watermark alone.
/// First occurrence per shard mirrors Lance's `compacted_generation_for_shard`.
fn exclusion_watermarks(
details: &MemWalIndexDetails,
index_name: Option<&str>,
index_names: &[String],
catchup_required: bool,
) -> HashMap<Uuid, u64> {
let mut exclude: HashMap<Uuid, u64> = HashMap::new();
for entry in &details.compacted_sstables {
let mut watermark = entry.generation;
if let Some(name) = index_name
&& let Some(caught_up) = details
for name in index_names {
match details
.index_catchup
.iter()
.find(|icp| icp.index_name == name)
.find(|icp| icp.index_name == *name)
.and_then(|icp| icp.caught_up_generation_for_shard(&entry.shard_id))
{
watermark = watermark.min(caught_up);
{
Some(caught_up) => watermark = watermark.min(caught_up),
// No entry. On a table that requires catch-up this means the
// index is *not* known to hold these rows, and the base arm is
// index-only -- so every generation stays readable from its
// SSTable. Without the bit the field is not maintained at all,
// and absence carries no information.
None if catchup_required => watermark = 0,
None => {}
}
}
exclude.entry(entry.shard_id).or_insert(watermark);
}
@@ -267,13 +283,26 @@ fn exclusion_watermarks(
/// with a live cached `ShardWriter` (this session's in-flight writes) the
/// writer's authoritative in-memory manifest and memtables override the
/// on-disk view so a read sees data not yet flushed.
/// Whether this table reads a missing `index_catchup` entry as "not caught up".
///
/// Both words must be set. A reader honouring the bit while a writer does not
/// would retain SSTables the writer had already trimmed, and the reverse would
/// serve rows from files the writer still expects to be excluded -- so a
/// half-set manifest is treated as legacy, which is the conservative side.
fn requires_index_catchup(dataset: &Dataset) -> bool {
let manifest = dataset.manifest();
manifest.reader_feature_flags & FLAG_MEM_WAL_INDEX_CATCHUP != 0
&& manifest.writer_feature_flags & FLAG_MEM_WAL_INDEX_CATCHUP != 0
}
async fn build_read_context(
table: &NativeTable,
dataset: &Dataset,
details: &MemWalIndexDetails,
index_name: Option<&str>,
index_names: &[String],
) -> Result<(Vec<ShardSnapshot>, HashMap<Uuid, InMemoryMemTables>)> {
let exclude = exclusion_watermarks(details, index_name);
let catchup_required = requires_index_catchup(dataset);
let exclude = exclusion_watermarks(details, index_names, catchup_required);
let shard_ids = dataset.list_mem_wal_latest_shard_ids().await?;
// Use the dataset's own object store (not `ObjectStore::from_uri`, which
@@ -487,19 +516,33 @@ async fn index_maintained(
}))
}
/// The maintained base index the query's arm relies on (vector index for ANN, FTS
/// index for full-text), used to gate SSTable compaction exclusion by index catch-up.
/// `None` for a plain scan or when no maintained index covers the searched column.
async fn arm_maintained_index_name(
/// Every maintained base index this query relies on, used to gate SSTable
/// exclusion by index catch-up.
///
/// Returns a list because the watermark must be the lowest across every index a
/// query relies on. Today it never holds more than one: `reject_unsupported`
/// refuses hybrid search, so the vector and full-text arms are mutually
/// exclusive.
///
/// The case that is genuinely multi-index -- a vector search with a scalar or
/// bitmap prefilter -- is **not collected yet**. Identifying those needs the
/// planner's chosen indexes, not the columns the filter names, and no Lance API
/// exposes them. Until it does, such a query is gated on its vector index alone.
///
/// Empty for a plain scan, or when no maintained index covers the searched
/// column.
async fn arm_maintained_index_names(
dataset: &Dataset,
query: &VectorQueryRequest,
details: &MemWalIndexDetails,
) -> Result<Option<String>> {
) -> Result<Vec<String>> {
use lance::index::DatasetIndexExt;
// Resolve the arm's searched column, the index-detail type it relies on, and a
// Each arm's searched column, the index-detail type it relies on, and a
// label for diagnostics — catch-up is taken from the vector/FTS index
// specifically, not a BTree on the same column.
let (column, type_url_suffix, arm) = if !query.query_vector.is_empty() {
let mut arms: Vec<(String, &str, &str)> = Vec::new();
if !query.query_vector.is_empty() {
let arrow_schema = ArrowSchema::from(dataset.schema());
let column = match &query.column {
Some(column) => column.clone(),
@@ -508,31 +551,43 @@ async fn arm_maintained_index_name(
default_vector_column(&arrow_schema, dim)?
}
};
(column, "VectorIndexDetails", "vector")
} else if let Some(fts) = &query.base.full_text_search {
match fts.columns().into_iter().next() {
Some(column) => (column, "InvertedIndexDetails", "full-text"),
None => return Ok(None),
}
} else {
return Ok(None);
};
let Some(field) = dataset.schema().field(&column) else {
return Ok(None);
};
arms.push((column, "VectorIndexDetails", "vector"));
}
if let Some(fts) = &query.base.full_text_search
&& let Some(column) = fts.columns().into_iter().next()
{
arms.push((column, "InvertedIndexDetails", "full-text"));
}
if arms.is_empty() {
return Ok(Vec::new());
}
let indices = dataset.load_indices().await?;
let segment_names: Vec<String> = indices
.iter()
.filter(|idx| {
idx.fields.contains(&field.id)
&& idx
.index_details
.as_ref()
.is_some_and(|d| d.type_url.ends_with(type_url_suffix))
})
.map(|idx| idx.name.clone())
.collect();
resolve_single_index(segment_names, &details.maintained_indexes, arm, &column)
let mut names = Vec::with_capacity(arms.len());
for (column, type_url_suffix, arm) in arms {
let Some(field) = dataset.schema().field(&column) else {
continue;
};
let segment_names: Vec<String> = indices
.iter()
.filter(|idx| {
idx.fields.contains(&field.id)
&& idx
.index_details
.as_ref()
.is_some_and(|d| d.type_url.ends_with(type_url_suffix))
})
.map(|idx| idx.name.clone())
.collect();
if let Some(name) =
resolve_single_index(segment_names, &details.maintained_indexes, arm, &column)?
{
names.push(name);
}
}
names.sort();
names.dedup();
Ok(names)
}
/// Resolve the single logical index from the names of its matching physical
@@ -734,22 +789,117 @@ mod tests {
};
// Plain scan: drop every compacted generation (through 5).
assert_eq!(exclusion_watermarks(&details, None).get(&shard), Some(&5));
assert_eq!(
exclusion_watermarks(&details, &[], false).get(&shard),
Some(&5)
);
// FTS arm with a lagging index: exclusion is capped at the index catch-up
// (2), so SSTable generations 3..=5 are retained until the index covers
// them — otherwise those documents would silently vanish from FTS results.
assert_eq!(
exclusion_watermarks(&details, Some("fts_idx")).get(&shard),
exclusion_watermarks(&details, &["fts_idx".to_string()], false).get(&shard),
Some(&2)
);
// A caught-up index — or one untracked in index_catchup — falls back to the
// compaction watermark.
assert_eq!(
exclusion_watermarks(&details, Some("caught_up_idx")).get(&shard),
exclusion_watermarks(&details, &["caught_up_idx".to_string()], false).get(&shard),
Some(&5)
);
// The same missing entry, once the table requires catch-up: absence now
// means "not known to hold these rows", so nothing may be excluded and
// every generation stays readable from its SSTable. This is the whole
// point of the protocol -- an indexed query against a table whose index
// has not caught up must not silently lose rows.
assert_eq!(
exclusion_watermarks(&details, &["untracked_idx".to_string()], true).get(&shard),
Some(&0)
);
// A tracked index is unaffected by the mode: the recorded position is
// information either way, and it still caps the exclusion.
assert_eq!(
exclusion_watermarks(&details, &["fts_idx".to_string()], true).get(&shard),
Some(&2)
);
// One missing entry is enough to hold everything back, even alongside an
// index that has caught up.
let mixed = vec!["fts_idx".to_string(), "untracked_idx".to_string()];
assert_eq!(
exclusion_watermarks(&details, &mixed, true).get(&shard),
Some(&0)
);
}
/// A hybrid search reads a vector and a full-text index, and either may lag.
/// Retaining to the lower of the two is what keeps both arms complete;
/// gating on one alone would drop SSTables the other has not indexed.
#[test]
fn exclusion_watermark_takes_the_minimum_across_every_index_used() {
let shard = Uuid::from_u128(1);
let details = MemWalIndexDetails {
compacted_sstables: vec![CompactedSsTable::new(shard, 9)],
index_catchup: vec![
IndexCatchupProgress::new(
"vec_idx".to_string(),
vec![CompactedSsTable::new(shard, 7)],
),
IndexCatchupProgress::new(
"fts_idx".to_string(),
vec![CompactedSsTable::new(shard, 4)],
),
],
maintained_indexes: vec!["vec_idx".to_string(), "fts_idx".to_string()],
..Default::default()
};
// Each index alone stops at its own catch-up.
assert_eq!(
exclusion_watermarks(&details, &["vec_idx".to_string()], false).get(&shard),
Some(&7)
);
assert_eq!(
exclusion_watermarks(&details, &["fts_idx".to_string()], false).get(&shard),
Some(&4)
);
// Used together, the lower one governs regardless of order.
let both = ["vec_idx".to_string(), "fts_idx".to_string()];
assert_eq!(
exclusion_watermarks(&details, &both, false).get(&shard),
Some(&4)
);
let reversed = ["fts_idx".to_string(), "vec_idx".to_string()];
assert_eq!(
exclusion_watermarks(&details, &reversed, false).get(&shard),
Some(&4)
);
}
/// An index with no catch-up entry contributes no cap today, so a lagging
/// sibling must still govern rather than being widened by the untracked one.
#[test]
fn an_untracked_index_does_not_widen_a_lagging_sibling() {
let shard = Uuid::from_u128(1);
let details = MemWalIndexDetails {
compacted_sstables: vec![CompactedSsTable::new(shard, 9)],
index_catchup: vec![IndexCatchupProgress::new(
"fts_idx".to_string(),
vec![CompactedSsTable::new(shard, 4)],
)],
maintained_indexes: vec!["fts_idx".to_string(), "untracked_idx".to_string()],
..Default::default()
};
let both = ["fts_idx".to_string(), "untracked_idx".to_string()];
assert_eq!(
exclusion_watermarks(&details, &both, false).get(&shard),
Some(&4)
);
}
#[test]
rust/lancedb/src/table/refresh.rs
+708
View File
@@ -0,0 +1,708 @@
// SPDX-License-Identifier: Apache-2.0
// SPDX-FileCopyrightText: Copyright The LanceDB Authors
//! Filling computed columns.
//!
//! A row without a value gets one; a row that has one keeps it. Refresh is
//! therefore idempotent and does not observe input mutation -- once a row is
//! filled, changing what the expression reads leaves the stored result alone.
//!
//! Two passes per fragment. The first scans only the unfilled live rows and
//! evaluates the expression over them, which yields the exact fill count and
//! decides whether the fragment is staged at all -- a fragment where nothing
//! would change stages nothing, which is what lets an expression yielding
//! null settle instead of restaging forever. The second streams the
//! fragment's physical rows into `write_column` a batch at a time, so peak
//! memory is bounded by a scan batch. The expression is evaluated by this
//! module, never through a projection alias, and only over rows being
//! filled: every other row -- deleted, or already holding a value -- has its
//! inputs masked to null first, so a poison value in a row nobody is filling
//! cannot fail the refresh.
use std::sync::Arc;
use arrow_array::{ArrayRef, BooleanArray, RecordBatch, RecordBatchOptions};
use arrow_schema::Schema as ArrowSchema;
use datafusion_expr::ColumnarValue;
use futures::{Stream, StreamExt, TryStreamExt};
use lance::Dataset;
use lance::dataset::WriteDestination;
use lance::dataset::fragment::FileFragment;
use lance::dataset::transaction::Operation;
use lance_core::ROW_ID;
use lance_core::datatypes::Schema as LanceSchema;
use serde::{Deserialize, Serialize};
use super::computed_columns::{BoundExpression, ComputedColumnKind, computed_column_from_field};
use super::{BaseTable, NativeTable};
use crate::{Error, Result};
/// The result of refreshing a computed column.
#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize, Default)]
pub struct RefreshColumnResult {
/// Rows that had a value computed.
#[serde(default)]
pub rows_filled: u64,
/// The commit version associated with the operation.
#[serde(default)]
pub version: u64,
}
/// Internal implementation of the refresh logic.
pub(crate) async fn execute_refresh_column(
table: &NativeTable,
column: &str,
) -> Result<RefreshColumnResult> {
table.dataset.ensure_mutable()?;
ensure_no_lsm_write_spec(table).await?;
let dataset = table.dataset.get().await?;
let expression = declared_expression(&dataset, column)?;
let schema = Arc::new(ArrowSchema::from(dataset.schema()));
let bound = Arc::new(super::computed_columns::bind(schema, column, &expression)?);
let field = dataset
.schema()
.field(column)
.ok_or_else(|| Error::ColumnNotFound {
name: column.to_string(),
})?;
// The dataset's own field, so the identity write_column checks against the
// manifest holds by construction.
let column_schema = LanceSchema {
fields: vec![field.clone()],
metadata: Default::default(),
};
let mut rows_filled = 0u64;
let mut replacements = Vec::new();
for fragment in dataset.get_fragments() {
let gained = count_fragment_gains(&dataset, &fragment, &bound, column).await?;
if gained == 0 {
continue;
}
rows_filled += gained;
let values = fill_stream(&dataset, &fragment, bound.clone(), column).await?;
replacements.push(fragment.write_column(values, &column_schema).await?);
}
if replacements.is_empty() {
return Ok(RefreshColumnResult {
rows_filled: 0,
version: dataset.version().version,
});
}
let read_version = dataset.version().version;
// The dataset's own session, so registrations and caches survive the
// commit being installed on the handle.
let session = dataset.session();
let new_dataset = Dataset::commit(
WriteDestination::Dataset(dataset.clone()),
Operation::DataReplacement { replacements },
Some(read_version),
None,
None,
session,
false,
)
.await?;
let version = new_dataset.version().version;
table.dataset.update(new_dataset);
Ok(RefreshColumnResult {
rows_filled,
version,
})
}
/// Refuse to refresh under an LSM write spec.
///
/// Refresh enumerates base fragments, and a write spec keeps visible rows in
/// un-compacted MemWAL tiers it cannot reach -- success would silently omit
/// readable rows.
async fn ensure_no_lsm_write_spec(table: &NativeTable) -> Result<()> {
// The catch-up flag outlives unset and marks retained SSTable rows.
let catchup = table.dataset.get().await?.manifest().reader_feature_flags
& lance_table::feature_flags::FLAG_MEM_WAL_INDEX_CATCHUP
!= 0;
if catchup || table.get_lsm_write_spec().await?.is_some() {
return Err(Error::NotSupported {
message: "refresh_column is not supported on a table with an LSM write \
spec: rows in un-compacted tiers are invisible to refresh"
.into(),
});
}
Ok(())
}
/// The SQL expression `column` is declared with.
fn declared_expression(dataset: &Dataset, column: &str) -> Result<String> {
let schema = ArrowSchema::from(dataset.schema());
let field = schema
.field_with_name(column)
.map_err(|_| Error::ColumnNotFound {
name: column.to_string(),
})?;
let declaration =
computed_column_from_field(field).ok_or_else(|| Error::NotAComputedColumn {
name: column.to_string(),
})?;
match declaration.kind {
ComputedColumnKind::Sql { expression } => Ok(expression),
ComputedColumnKind::Unrecognized { kind } => Err(Error::NotSupported {
message: format!(
"computed column '{column}' is defined by '{kind}', which this version of \
lancedb cannot evaluate"
),
}),
}
}
/// Quote `name` as a lance SQL identifier.
///
/// Lance's dialect delimits with backticks, so a double-quoted name would
/// parse as a string literal rather than a column.
fn quote_identifier(name: &str) -> String {
format!("`{}`", name.replace('`', "``"))
}
/// Assemble the batch evaluation runs against: the bound roots, in read-schema
/// order. Built by name so scan-side column order never matters.
fn evaluation_batch(
batch: &RecordBatch,
bound: &BoundExpression,
mask_out: Option<&BooleanArray>,
) -> lance_core::Result<RecordBatch> {
let mut columns = Vec::with_capacity(bound.roots.len());
for name in &bound.roots {
let column = batch.column_by_name(name).ok_or_else(|| {
lance_core::Error::invalid_input(format!(
"refreshing a computed column read no {name} column"
))
})?;
// Rows outside the mask must not reach the expression: a value in a
// deleted or already-filled row can be one it would choke on.
columns.push(match mask_out {
Some(mask) => arrow::compute::nullif(column, mask)?,
None => column.clone(),
});
}
Ok(RecordBatch::try_new_with_options(
bound.read_schema.clone(),
columns,
&RecordBatchOptions::new().with_row_count(Some(batch.num_rows())),
)?)
}
/// Evaluate the expression over `batch`, materializing a constant result to
/// the batch's length.
fn evaluate(bound: &BoundExpression, batch: &RecordBatch) -> lance_core::Result<ArrayRef> {
let value = bound
.physical
.evaluate(batch)
.map_err(lance_core::Error::from)?;
match value {
ColumnarValue::Array(array) => Ok(array),
scalar => scalar
.into_array(batch.num_rows())
.map_err(lance_core::Error::from),
}
}
/// How many rows of one fragment would gain a value.
///
/// Scans only the unfilled live rows -- deleted rows never reach the
/// expression here, the filter having already excluded them -- and counts the
/// non-null results. Exact, so it is both the staging decision and the
/// fragment's contribution to `rows_filled`.
async fn count_fragment_gains(
dataset: &Dataset,
fragment: &FileFragment,
bound: &BoundExpression,
column: &str,
) -> Result<u64> {
let mut scanner = dataset.scan();
scanner
.with_fragments(vec![fragment.metadata().clone()])
.with_row_id()
.filter(&format!("{} IS NULL", quote_identifier(column)))?
.project(&bound.roots)?;
let mut gained = 0u64;
let mut batches = scanner.try_into_stream().await?;
while let Some(batch) = batches.try_next().await? {
let evaluated = evaluate(bound, &evaluation_batch(&batch, bound, None)?)?;
gained += (batch.num_rows() - evaluated.null_count()) as u64;
}
Ok(gained)
}
/// Stream one fragment's column in physical order, filling the unfilled live
/// rows and keeping every other value.
///
/// Deleted rows are carried through so the values line up positionally with
/// the fragment's data files; they are never read back, but the column file
/// has to cover them.
async fn fill_stream(
dataset: &Dataset,
fragment: &FileFragment,
bound: Arc<BoundExpression>,
column: &str,
) -> Result<impl Stream<Item = lance_core::Result<RecordBatch>> + Send + use<>> {
let mut projection: Vec<String> = bound.roots.clone();
projection.push(column.to_string());
let mut scanner = dataset.scan();
scanner
.with_fragments(vec![fragment.metadata().clone()])
.with_row_id()
.include_deleted_rows()
.project(&projection)?;
let projected = Arc::new(ArrowSchema::new(vec![
ArrowSchema::from(dataset.schema())
.field_with_name(column)
.map_err(|_| Error::ColumnNotFound {
name: column.to_string(),
})?
.clone(),
]));
let column = column.to_string();
let batches = scanner.try_into_stream().await?;
Ok(batches.map(move |batch| {
let batch = batch?;
let missing = |name: &str| {
lance_core::Error::invalid_input(format!(
"refreshing a computed column read no {name} column"
))
};
let existing = batch
.column_by_name(&column)
.ok_or_else(|| missing(&column))?;
let row_ids = batch
.column_by_name(ROW_ID)
.ok_or_else(|| missing(ROW_ID))?;
// Only an unfilled live row gains a value; a deleted row has a null
// row id and keeps its (null) slot.
let unfilled = arrow::compute::is_null(existing.as_ref())?;
let live = arrow::compute::is_not_null(row_ids.as_ref())?;
let fill = arrow::compute::and(&unfilled, &live)?;
let keep = arrow::compute::not(&fill)?;
let computed = evaluate(&bound, &evaluation_batch(&batch, &bound, Some(&keep))?)?;
let merged = arrow_select::zip::zip(&fill, &computed, existing)?;
Ok(RecordBatch::try_new(projected.clone(), vec![merged])?)
}))
}
#[cfg(test)]
mod tests {
use std::sync::Arc;
use arrow_array::{Int32Array, record_batch};
use futures::TryStreamExt;
use crate::connect;
use crate::query::{ExecutableQuery, QueryBase, Select};
use crate::{Error, Result, Table};
async fn table_with(name: &str, values: Vec<i32>) -> Table {
let conn = connect("memory://").execute().await.unwrap();
let batch = record_batch!(("x", Int32, values)).unwrap();
conn.create_table(name, batch).execute().await.unwrap()
}
async fn declare_doubled(table: &Table) -> Result<u64> {
Ok(table
.add_columns()
.computed("doubled", "x * 2")
.execute()
.await?
.version)
}
async fn read(table: &Table, column: &str) -> Vec<Option<i32>> {
let batches = table
.query()
.select(Select::columns(&[column]))
.execute()
.await
.unwrap()
.try_collect::<Vec<_>>()
.await
.unwrap();
let mut values: Vec<Option<i32>> = batches
.iter()
.flat_map(|batch| {
batch[column]
.as_any()
.downcast_ref::<Int32Array>()
.unwrap()
.iter()
.collect::<Vec<_>>()
})
.collect();
values.sort();
values
}
async fn append(table: &Table, values: Vec<i32>) {
let batch = record_batch!(("x", Int32, values)).unwrap();
table.add(batch).execute().await.unwrap();
}
#[tokio::test]
async fn test_refresh_fills_a_declared_column() {
let table = table_with("refresh_fills", vec![1, 2, 3]).await;
let declared = declare_doubled(&table).await.unwrap();
assert_eq!(read(&table, "doubled").await, vec![None, None, None]);
let result = table.refresh_column("doubled").await.unwrap();
assert!(result.version > declared);
assert_eq!(result.rows_filled, 3);
assert_eq!(
read(&table, "doubled").await,
vec![Some(2), Some(4), Some(6)]
);
}
/// Values written after the last refresh must be reachable by another one.
#[tokio::test]
async fn test_refresh_fills_rows_appended_since_the_last_refresh() {
let table = table_with("refresh_appended", vec![1, 2]).await;
declare_doubled(&table).await.unwrap();
table.refresh_column("doubled").await.unwrap();
append(&table, vec![5, 6]).await;
assert_eq!(
read(&table, "doubled").await,
vec![None, None, Some(2), Some(4)]
);
let result = table.refresh_column("doubled").await.unwrap();
assert_eq!(result.rows_filled, 2);
assert_eq!(
read(&table, "doubled").await,
vec![Some(2), Some(4), Some(10), Some(12)]
);
}
#[tokio::test]
async fn test_refresh_with_nothing_to_fill() {
let table = table_with("refresh_noop", vec![1, 2, 3]).await;
declare_doubled(&table).await.unwrap();
table.refresh_column("doubled").await.unwrap();
let again = table.refresh_column("doubled").await.unwrap();
assert_eq!(again.rows_filled, 0);
assert_eq!(
read(&table, "doubled").await,
vec![Some(2), Some(4), Some(6)]
);
}
/// A row is filled only by gaining a value, so an expression yielding null
/// settles at once instead of re-selecting the same rows forever. Nothing
/// is staged, so the version does not move either.
#[tokio::test]
async fn test_refresh_converges_on_a_null_result() {
let table = table_with("refresh_null_result", vec![1, 2, 3]).await;
let declared = table
.add_columns()
.computed("maybe", "nullif(x, x)")
.execute()
.await
.unwrap()
.version;
let first = table.refresh_column("maybe").await.unwrap();
assert_eq!(first.rows_filled, 0);
assert_eq!(first.version, declared);
assert_eq!(read(&table, "maybe").await, vec![None, None, None]);
let again = table.refresh_column("maybe").await.unwrap();
assert_eq!(again.rows_filled, 0);
assert_eq!(again.version, declared);
}
/// The contract's boundary: a filled fragment is not revisited, so
/// mutating an input leaves the value computed at fill time.
#[tokio::test]
async fn test_refresh_does_not_observe_input_mutation() {
let table = table_with("refresh_mutation", vec![1]).await;
declare_doubled(&table).await.unwrap();
table.refresh_column("doubled").await.unwrap();
assert_eq!(read(&table, "doubled").await, vec![Some(2)]);
table.update().column("x", "3").execute().await.unwrap();
let again = table.refresh_column("doubled").await.unwrap();
assert_eq!(again.rows_filled, 0);
assert_eq!(read(&table, "doubled").await, vec![Some(2)]);
}
/// A row rewrite before the first refresh materializes the declared
/// column as null behind a covering data file. Those rows are still
/// unfilled and a later refresh has to reach them.
#[tokio::test]
async fn test_update_before_the_first_refresh() {
let table = table_with("refresh_update_first", vec![1]).await;
declare_doubled(&table).await.unwrap();
table.update().column("x", "3").execute().await.unwrap();
let result = table.refresh_column("doubled").await.unwrap();
assert_eq!(result.rows_filled, 1);
assert_eq!(read(&table, "doubled").await, vec![Some(6)]);
}
/// The contract holds row by row, not fragment by fragment: revisiting a
/// fragment to fill one row must not recompute a filled row sitting beside
/// it, even where the input behind it has since changed.
#[tokio::test]
async fn test_refresh_does_not_recompute_a_filled_row_beside_an_unfilled_one() {
let table = table_with("refresh_mixed", vec![1, 2]).await;
declare_doubled(&table).await.unwrap();
table.refresh_column("doubled").await.unwrap();
append(&table, vec![5]).await;
table
.update()
.column("x", "100")
.only_if("x = 1")
.execute()
.await
.unwrap();
table
.optimize(crate::table::OptimizeAction::Compact {
options: crate::table::CompactionOptions::default(),
remap_options: None,
})
.await
.unwrap();
let result = table.refresh_column("doubled").await.unwrap();
assert_eq!(result.rows_filled, 1);
// 2 is the mutated row keeping the value it was filled with, not 200.
assert_eq!(
read(&table, "doubled").await,
vec![Some(2), Some(4), Some(10)]
);
}
/// Filling a fragment must not disturb the values it already holds, which
/// is what makes a compaction-mixed fragment safe to revisit.
#[tokio::test]
async fn test_refresh_preserves_already_filled_rows() {
let table = table_with("refresh_preserves", vec![1, 2]).await;
declare_doubled(&table).await.unwrap();
table.refresh_column("doubled").await.unwrap();
append(&table, vec![5]).await;
table
.optimize(crate::table::OptimizeAction::Compact {
options: crate::table::CompactionOptions::default(),
remap_options: None,
})
.await
.unwrap();
let result = table.refresh_column("doubled").await.unwrap();
assert_eq!(result.rows_filled, 1);
assert_eq!(
read(&table, "doubled").await,
vec![Some(2), Some(4), Some(10)]
);
}
#[tokio::test]
async fn test_refresh_leaves_deleted_rows_alone() {
let table = table_with("refresh_deleted", vec![1, 2, 3, 4]).await;
declare_doubled(&table).await.unwrap();
table.delete("x = 2").await.unwrap();
let result = table.refresh_column("doubled").await.unwrap();
assert_eq!(result.rows_filled, 3);
assert_eq!(
read(&table, "doubled").await,
vec![Some(2), Some(6), Some(8)]
);
}
#[tokio::test]
async fn test_refresh_a_constant_expression() {
let table = table_with("refresh_constant", vec![1, 2, 3]).await;
table
.add_columns()
.computed("answer", "42")
.execute()
.await
.unwrap();
let result = table.refresh_column("answer").await.unwrap();
assert_eq!(result.rows_filled, 3);
}
/// A name needing quotes reaches the evaluator intact: it is carried as a
/// projection alias, never spliced into SQL text.
#[tokio::test]
async fn test_refresh_a_column_whose_name_needs_quoting() {
let table = table_with("refresh_quoted", vec![1, 2, 3]).await;
table
.add_columns()
.computed("double value", "x * 2")
.execute()
.await
.unwrap();
let result = table.refresh_column("double value").await.unwrap();
assert_eq!(result.rows_filled, 3);
assert_eq!(
read(&table, "double value").await,
vec![Some(2), Some(4), Some(6)]
);
}
/// A fragment spanning several scan batches exercises the streamed fill:
/// the probe buffers only until the first gained value and the rest flows
/// through write_column a batch at a time.
#[tokio::test]
async fn test_refresh_streams_a_multi_batch_fragment() {
let values: Vec<i32> = (0..20_000).collect();
let table = table_with("refresh_multi_batch", values.clone()).await;
declare_doubled(&table).await.unwrap();
let result = table.refresh_column("doubled").await.unwrap();
assert_eq!(result.rows_filled, 20_000);
let read_back = read(&table, "doubled").await;
assert_eq!(read_back.len(), 20_000);
let mut expected: Vec<Option<i32>> = values.iter().map(|v| Some(v * 2)).collect();
expected.sort();
assert_eq!(read_back, expected);
}
/// The gate's reproducer: the commit must reuse the configured session,
/// or registrations and caches vanish from the handle after a refresh.
#[tokio::test]
async fn test_refresh_preserves_the_configured_session() {
let session = Arc::new(lance::session::Session::default());
let conn = crate::connect("memory://")
.session(session.clone())
.execute()
.await
.unwrap();
let batch = record_batch!(("x", Int32, [1, 2])).unwrap();
let table = conn
.create_table("session_kept", batch)
.execute()
.await
.unwrap();
declare_doubled(&table).await.unwrap();
table.refresh_column("doubled").await.unwrap();
let dataset = table.as_native().unwrap().dataset.get().await.unwrap();
assert!(Arc::ptr_eq(&dataset.session(), &session));
}
/// Both orders of declare+spec are refused at the source (see the
/// schema_evolution tests); refresh's own check covers a dataset another
/// writer left in that state.
#[tokio::test]
async fn test_refresh_refuses_a_foreign_lsm_state() {
use crate::table::LsmWriteSpec;
let tmp_dir = tempfile::tempdir().unwrap();
let conn = connect(tmp_dir.path().to_str().unwrap())
.execute()
.await
.unwrap();
let schema = Arc::new(arrow_schema::Schema::new(vec![arrow_schema::Field::new(
"x",
arrow_schema::DataType::Int32,
false,
)]));
let batch =
arrow_array::RecordBatch::try_new(schema, vec![Arc::new(Int32Array::from(vec![1]))])
.unwrap();
let table = conn.create_table("lsm", batch).execute().await.unwrap();
table.set_unenforced_primary_key(["x"]).await.unwrap();
table
.set_lsm_write_spec(LsmWriteSpec::unsharded())
.await
.unwrap();
super::super::computed_columns::add_foreign_kind(&table, "doubled", "sql").await;
let err = table.refresh_column("doubled").await.unwrap_err();
assert!(
matches!(&err, Error::NotSupported { message } if message.contains("LSM")),
"{err:?}"
);
}
/// After catch-up activation and unset, no spec remains but the catch-up
/// flag still marks retained SSTable rows; refresh refuses on the flag.
#[tokio::test]
async fn test_refresh_refuses_retained_catchup_state() {
use crate::table::LsmWriteSpec;
let tmp_dir = tempfile::tempdir().unwrap();
let conn = connect(tmp_dir.path().to_str().unwrap())
.execute()
.await
.unwrap();
let schema = Arc::new(arrow_schema::Schema::new(vec![arrow_schema::Field::new(
"x",
arrow_schema::DataType::Int32,
false,
)]));
let batch = arrow_array::RecordBatch::try_new(
schema.clone(),
vec![Arc::new(Int32Array::from(vec![1]))],
)
.unwrap();
let table = conn
.create_table("catchup", batch.clone())
.execute()
.await
.unwrap();
table.set_unenforced_primary_key(["x"]).await.unwrap();
table
.set_lsm_write_spec(LsmWriteSpec::unsharded())
.await
.unwrap();
table.require_mem_wal_index_catchup().await.unwrap();
let mut merge = table.merge_insert(&["x"]);
merge
.when_matched_update_all(None)
.when_not_matched_insert_all()
.use_lsm(true);
merge
.execute(Box::new(arrow_array::RecordBatchIterator::new(
vec![Ok(batch)],
schema,
)))
.await
.unwrap();
table.unset_lsm_write_spec().await.unwrap();
super::super::computed_columns::add_foreign_kind(&table, "doubled", "sql").await;
let err = table.refresh_column("doubled").await.unwrap_err();
assert!(
matches!(&err, Error::NotSupported { message } if message.contains("LSM")),
"{err:?}"
);
}
/// A declaration of a kind this version cannot evaluate is refused by
/// name, rather than mistaken for a plain column or fed to the SQL path.
#[tokio::test]
async fn test_refresh_rejects_a_kind_it_cannot_evaluate() {
let table = table_with("refresh_foreign", vec![1, 2, 3]).await;
super::super::computed_columns::add_foreign_kind(&table, "embedding", "udf").await;
let err = table.refresh_column("embedding").await.unwrap_err();
assert!(matches!(err, Error::NotSupported { message } if message.contains("udf")));
}
}
rust/lancedb/src/table/schema_evolution.rs
+103 -2
View File
@@ -8,12 +8,14 @@
//! - [`alter_columns`](execute_alter_columns): Rename columns, change types, or modify nullability
//! - [`drop_columns`](execute_drop_columns): Remove columns from the table
use arrow_schema::Schema as ArrowSchema;
use lance::dataset::{ColumnAlteration, NewColumnTransform};
use serde::{Deserialize, Serialize};
use std::collections::HashMap;
use super::NativeTable;
use crate::Result;
use super::computed_columns;
use super::{BaseTable, NativeTable};
use crate::{Error, Result};
/// The result of an add columns operation.
#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize, Default)]
@@ -98,6 +100,48 @@ pub(crate) async fn execute_add_columns(
table: &NativeTable,
transforms: NewColumnTransform,
read_columns: Option<Vec<String>>,
) -> Result<AddColumnsResult> {
// Declarations are admitted only through [`execute_declare`].
match &transforms {
NewColumnTransform::AllNulls(schema) => {
computed_columns::ensure_no_foreign_declarations(schema.fields())?
}
NewColumnTransform::BatchUDF(udf) => {
computed_columns::ensure_no_foreign_declarations(udf.output_schema.fields())?
}
_ => {}
}
commit_add_columns(table, transforms, read_columns).await
}
/// Declare validated computed columns. The only admission path for
/// declaration metadata.
pub(crate) async fn execute_declare(
table: &NativeTable,
columns: &[(String, String)],
) -> Result<AddColumnsResult> {
// An LSM write spec keeps visible rows in tiers refresh cannot reach;
// checked against latest committed state, not this handle's snapshot.
// The catch-up flag outlives unset and marks retained SSTable rows.
table.checkout_latest().await?;
let catchup = table.dataset.get().await?.manifest().reader_feature_flags
& lance_table::feature_flags::FLAG_MEM_WAL_INDEX_CATCHUP
!= 0;
if catchup || table.get_lsm_write_spec().await?.is_some() {
return Err(Error::NotSupported {
message: "computed columns are not supported on a table with an LSM write \
spec: rows in un-compacted tiers are invisible to refresh"
.into(),
});
}
let transform = computed_columns::declare(table.schema().await?, columns)?;
commit_add_columns(table, transform, None).await
}
pub(crate) async fn commit_add_columns(
table: &NativeTable,
transforms: NewColumnTransform,
read_columns: Option<Vec<String>>,
) -> Result<AddColumnsResult> {
table.dataset.ensure_mutable()?;
let mut dataset = (*table.dataset.get().await?).clone();
@@ -116,6 +160,21 @@ pub(crate) async fn execute_alter_columns(
) -> Result<AlterColumnsResult> {
table.dataset.ensure_mutable()?;
let mut dataset = (*table.dataset.get().await?).clone();
// Nullability is not part of what an expression resolves against, so only
// a rename or a retype can invalidate a binding.
let schema = std::sync::Arc::new(ArrowSchema::from(dataset.schema()));
let rebinding = alterations
.iter()
.filter(|alteration| alteration.rename.is_some() || alteration.data_type.is_some())
.map(|alteration| alteration.path.as_str())
.collect::<Vec<_>>();
computed_columns::ensure_not_an_input(&schema, &rebinding)?;
let retyped = alterations
.iter()
.filter(|alteration| alteration.data_type.is_some())
.map(|alteration| alteration.path.as_str())
.collect::<Vec<_>>();
computed_columns::ensure_not_retyped(schema.as_ref(), &retyped)?;
dataset.alter_columns(alterations).await?;
let version = dataset.version().version;
table.dataset.update(dataset);
@@ -131,6 +190,10 @@ pub(crate) async fn execute_drop_columns(
) -> Result<DropColumnsResult> {
table.dataset.ensure_mutable()?;
let mut dataset = (*table.dataset.get().await?).clone();
computed_columns::ensure_not_an_input(
&std::sync::Arc::new(ArrowSchema::from(dataset.schema())),
columns,
)?;
dataset.drop_columns(columns).await?;
let version = dataset.version().version;
table.dataset.update(dataset);
@@ -147,6 +210,44 @@ pub(crate) async fn execute_update_field_metadata(
table.dataset.ensure_mutable()?;
let mut dataset = (*table.dataset.get().await?).clone();
// A declaration is validated as a whole at declare time; editing its keys
// here would bypass that, fabricate one on a plain column, or move a
// binding out from under a refresh. A replace on a declared column would
// silently erase it.
let schema = ArrowSchema::from(dataset.schema());
let declared: Vec<String> = computed_columns::computed_columns(&schema)
.into_iter()
.map(|declaration| declaration.name)
.collect();
for update in updates {
if update
.metadata
.keys()
.any(|key| computed_columns::is_declaration_key(key))
{
return Err(Error::InvalidInput {
message: format!(
"metadata keys of a computed-column declaration cannot be edited \
(path '{}'); drop the column and declare it again",
update.path
),
});
}
if update.replace
&& declared
.iter()
.any(|name| name == computed_columns::root(&update.path))
{
return Err(Error::InvalidInput {
message: format!(
"replacing all metadata of computed column '{}' would erase its \
declaration; drop the column and declare it again",
update.path
),
});
}
}
let mut builder = dataset.update_field_metadata();
for update in updates {
let entries = update.metadata.iter().map(|(k, v)| (k.clone(), v.clone()));
rust/lancedb/src/table/update.rs
+4
View File
@@ -82,6 +82,10 @@ pub(crate) async fn execute_update(
// 1. Snapshot the current dataset
let dataset = table.dataset.get().await?;
super::computed_columns::ensure_not_written(
&arrow_schema::Schema::from(dataset.schema()),
update.columns.iter().map(|(name, _)| name.as_str()),
)?;
// 2. Initialize the Lance Core builder
let mut builder = LanceUpdateBuilder::new(dataset);
rust/lancedb/tests/blob_integration.rs
+18 -13
View File
@@ -10,7 +10,7 @@ use arrow_array::{
use arrow_schema::{DataType, Field, Fields, Schema};
use futures::TryStreamExt;
use lance::Dataset;
use lance_file::version::LanceFileVersion;
use lance_file::version::{ConcreteFileVersion, LanceFileVersion};
use lancedb::{
Connection, Error, Result, Table,
blob::{BlobRangeRequest, blob},
@@ -61,7 +61,7 @@ async fn create_inline_blob_table(
Ok(table)
}
async fn storage_format_version(table: &Table) -> LanceFileVersion {
async fn storage_format_version(table: &Table) -> ConcreteFileVersion {
table
.as_native()
.unwrap()
@@ -69,9 +69,14 @@ async fn storage_format_version(table: &Table) -> LanceFileVersion {
.await
.unwrap()
.data_storage_format
.lance_file_version()
.unwrap()
.resolve()
.lance_file_format()
}
fn supports_blob_v2(version: ConcreteFileVersion) -> bool {
matches!(
version,
ConcreteFileVersion::V2_2 | ConcreteFileVersion::V2_3
)
}
async fn uses_stable_row_ids(table: &Table) -> bool {
@@ -112,7 +117,7 @@ async fn declaring_blob_column_bumps_format_and_enables_stable_row_ids() -> Resu
.execute()
.await?;
assert!(storage_format_version(&table).await >= LanceFileVersion::V2_2);
assert!(supports_blob_v2(storage_format_version(&table).await));
assert!(uses_stable_row_ids(&table).await);
Ok(())
}
@@ -127,7 +132,7 @@ async fn explicit_stable_row_id_setting_wins_over_blob_default() -> Result<()> {
.execute()
.await?;
assert!(storage_format_version(&table).await >= LanceFileVersion::V2_2);
assert!(supports_blob_v2(storage_format_version(&table).await));
assert!(!uses_stable_row_ids(&table).await);
Ok(())
}
@@ -139,7 +144,7 @@ async fn non_blob_table_keeps_default_format_and_row_id_setting() -> Result<()>
let schema = Arc::new(Schema::new(vec![Field::new("id", DataType::Int64, false)]));
let table = db.create_empty_table("t", schema).execute().await?;
assert!(storage_format_version(&table).await < LanceFileVersion::V2_2);
assert!(!supports_blob_v2(storage_format_version(&table).await));
assert!(!uses_stable_row_ids(&table).await);
Ok(())
}
@@ -171,7 +176,7 @@ async fn creating_with_blob_data_bumps_format() -> Result<()> {
.unwrap();
let table = db.create_table("t", batch).execute().await?;
assert!(storage_format_version(&table).await >= LanceFileVersion::V2_2);
assert!(supports_blob_v2(storage_format_version(&table).await));
assert!(uses_stable_row_ids(&table).await);
assert_eq!(table.count_rows(None).await?, 1);
Ok(())
@@ -281,7 +286,7 @@ async fn connection_level_stable_row_id_setting_wins_over_blob_default() -> Resu
.execute()
.await?;
assert!(storage_format_version(&table).await >= LanceFileVersion::V2_2);
assert!(supports_blob_v2(storage_format_version(&table).await));
assert!(!uses_stable_row_ids(&table).await);
Ok(())
}
@@ -297,7 +302,7 @@ async fn namespace_create_applies_blob_defaults() -> Result<()> {
.execute()
.await?;
assert!(storage_format_version(&table).await >= LanceFileVersion::V2_2);
assert!(supports_blob_v2(storage_format_version(&table).await));
assert!(uses_stable_row_ids(&table).await);
Ok(())
}
@@ -474,7 +479,7 @@ async fn fetch_blobs_round_trips_nested_blob_column() -> Result<()> {
let batch = RecordBatch::try_new(schema, vec![Arc::new(info_array) as ArrayRef]).unwrap();
let table = db.create_table("t", batch).execute().await?;
assert!(storage_format_version(&table).await >= LanceFileVersion::V2_2);
assert!(supports_blob_v2(storage_format_version(&table).await));
assert!(uses_stable_row_ids(&table).await);
let ids = collect_row_ids(&table).await?;
@@ -1305,7 +1310,7 @@ async fn optimize_preserves_blob_v2_null_and_empty_distinction() -> Result<()> {
.await?;
table.add(null_empty_input_batch()).execute().await?;
assert!(
storage_format_version(&table).await >= LanceFileVersion::V2_2,
supports_blob_v2(storage_format_version(&table).await),
"blob v2 columns require storage >= 2.2"
);