mirror of
https://github.com/lancedb/lancedb.git
synced 2026-03-30 20:40:42 +00:00
Compare commits
6 Commits
codex/upda
...
jack/fix-c
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
78c2cb3a9d | ||
|
|
f8bf9a63a1 | ||
|
|
6329b57604 | ||
|
|
c51b13e70f | ||
|
|
0859312b83 | ||
|
|
a6e8ec8d48 |
2
.github/workflows/cargo-publish.yml
vendored
2
.github/workflows/cargo-publish.yml
vendored
@@ -42,7 +42,7 @@ jobs:
|
||||
name: Report Workflow Failure
|
||||
runs-on: ubuntu-latest
|
||||
needs: [build]
|
||||
if: always() && (github.event_name == 'release' || github.event_name == 'workflow_dispatch')
|
||||
if: always() && failure() && startsWith(github.ref, 'refs/tags/v')
|
||||
permissions:
|
||||
contents: read
|
||||
issues: write
|
||||
|
||||
@@ -86,16 +86,17 @@ jobs:
|
||||
You are running inside the lancedb repository on a GitHub Actions runner. Update the Lance dependency to version ${VERSION} and prepare a pull request for maintainers to review.
|
||||
|
||||
Follow these steps exactly:
|
||||
1. Use script "ci/set_lance_version.py" to update Lance dependencies. The script already refreshes Cargo metadata, so allow it to finish even if it takes time.
|
||||
2. Run "cargo clippy --workspace --tests --all-features -- -D warnings". If diagnostics appear, fix them yourself and rerun clippy until it exits cleanly. Do not skip any warnings.
|
||||
3. After clippy succeeds, run "cargo fmt --all" to format the workspace.
|
||||
4. Ensure the repository is clean except for intentional changes. Inspect "git status --short" and "git diff" to confirm the dependency update and any required fixes.
|
||||
5. Create and switch to a new branch named "${BRANCH_NAME}" (replace any duplicated hyphens if necessary).
|
||||
6. Stage all relevant files with "git add -A". Commit using the message "${COMMIT_TYPE}: update lance dependency to v${VERSION}".
|
||||
7. Push the branch to origin. If the branch already exists, force-push your changes.
|
||||
8. env "GH_TOKEN" is available, use "gh" tools for github related operations like creating pull request.
|
||||
9. Create a pull request targeting "main" with title "${COMMIT_TYPE}: update lance dependency to v${VERSION}". First, write the PR body to /tmp/pr-body.md using a heredoc (cat <<'EOF' > /tmp/pr-body.md). The body should summarize the dependency bump, clippy/fmt verification, and link the triggering tag (${TAG}). Then run "gh pr create --body-file /tmp/pr-body.md".
|
||||
10. After creating the PR, display the PR URL, "git status --short", and a concise summary of the commands run and their results.
|
||||
1. Use script "ci/set_lance_version.py" to update Lance Rust dependencies. The script already refreshes Cargo metadata, so allow it to finish even if it takes time.
|
||||
2. Update the Java lance-core dependency version in "java/pom.xml": change the "<lance-core.version>...</lance-core.version>" property to "${VERSION}".
|
||||
3. Run "cargo clippy --workspace --tests --all-features -- -D warnings". If diagnostics appear, fix them yourself and rerun clippy until it exits cleanly. Do not skip any warnings.
|
||||
4. After clippy succeeds, run "cargo fmt --all" to format the workspace.
|
||||
5. Ensure the repository is clean except for intentional changes. Inspect "git status --short" and "git diff" to confirm the dependency update and any required fixes.
|
||||
6. Create and switch to a new branch named "${BRANCH_NAME}" (replace any duplicated hyphens if necessary).
|
||||
7. Stage all relevant files with "git add -A". Commit using the message "${COMMIT_TYPE}: update lance dependency to v${VERSION}".
|
||||
8. Push the branch to origin. If the remote branch already exists, delete it first with "gh api -X DELETE repos/lancedb/lancedb/git/refs/heads/${BRANCH_NAME}" then push with "git push origin ${BRANCH_NAME}". Do NOT use "git push --force" or "git push -f".
|
||||
9. env "GH_TOKEN" is available, use "gh" tools for github related operations like creating pull request.
|
||||
10. Create a pull request targeting "main" with title "${COMMIT_TYPE}: update lance dependency to v${VERSION}". First, write the PR body to /tmp/pr-body.md using a heredoc (cat <<'EOF' > /tmp/pr-body.md). The body should summarize the dependency bump, clippy/fmt verification, and link the triggering tag (${TAG}). Then run "gh pr create --body-file /tmp/pr-body.md".
|
||||
11. After creating the PR, display the PR URL, "git status --short", and a concise summary of the commands run and their results.
|
||||
|
||||
Constraints:
|
||||
- Use bash commands; avoid modifying GitHub workflow files other than through the scripted task above.
|
||||
|
||||
1
.github/workflows/nodejs.yml
vendored
1
.github/workflows/nodejs.yml
vendored
@@ -8,6 +8,7 @@ on:
|
||||
paths:
|
||||
- Cargo.toml
|
||||
- nodejs/**
|
||||
- docs/src/js/**
|
||||
- .github/workflows/nodejs.yml
|
||||
- docker-compose.yml
|
||||
|
||||
|
||||
3
.github/workflows/npm-publish.yml
vendored
3
.github/workflows/npm-publish.yml
vendored
@@ -348,7 +348,6 @@ jobs:
|
||||
run: find npm
|
||||
- name: Publish
|
||||
env:
|
||||
NODE_AUTH_TOKEN: ${{ secrets.LANCEDB_NPM_REGISTRY_TOKEN }}
|
||||
DRY_RUN: ${{ !startsWith(github.ref, 'refs/tags/v') }}
|
||||
run: |
|
||||
ARGS="--access public"
|
||||
@@ -363,7 +362,7 @@ jobs:
|
||||
name: Report Workflow Failure
|
||||
runs-on: ubuntu-latest
|
||||
needs: [build-lancedb, test-lancedb, publish]
|
||||
if: always() && (github.event_name == 'release' || github.event_name == 'workflow_dispatch')
|
||||
if: always() && failure() && startsWith(github.ref, 'refs/tags/v')
|
||||
permissions:
|
||||
contents: read
|
||||
issues: write
|
||||
|
||||
2
.github/workflows/pypi-publish.yml
vendored
2
.github/workflows/pypi-publish.yml
vendored
@@ -181,7 +181,7 @@ jobs:
|
||||
permissions:
|
||||
contents: read
|
||||
issues: write
|
||||
if: always() && (github.event_name == 'release' || github.event_name == 'workflow_dispatch')
|
||||
if: always() && failure() && startsWith(github.ref, 'refs/tags/python-v')
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
- uses: ./.github/actions/create-failure-issue
|
||||
|
||||
@@ -367,6 +367,27 @@ Use [Table.listIndices](Table.md#listindices) to find the names of the indices.
|
||||
|
||||
***
|
||||
|
||||
### initialStorageOptions()
|
||||
|
||||
```ts
|
||||
abstract initialStorageOptions(): Promise<undefined | null | Record<string, string>>
|
||||
```
|
||||
|
||||
Get the initial storage options that were passed in when opening this table.
|
||||
|
||||
For dynamically refreshed options (e.g., credential vending), use
|
||||
[Table.latestStorageOptions](Table.md#lateststorageoptions).
|
||||
|
||||
Warning: This is an internal API and the return value is subject to change.
|
||||
|
||||
#### Returns
|
||||
|
||||
`Promise`<`undefined` \| `null` \| `Record`<`string`, `string`>>
|
||||
|
||||
The storage options, or undefined if no storage options were configured.
|
||||
|
||||
***
|
||||
|
||||
### isOpen()
|
||||
|
||||
```ts
|
||||
@@ -381,6 +402,28 @@ Return true if the table has not been closed
|
||||
|
||||
***
|
||||
|
||||
### latestStorageOptions()
|
||||
|
||||
```ts
|
||||
abstract latestStorageOptions(): Promise<undefined | null | Record<string, string>>
|
||||
```
|
||||
|
||||
Get the latest storage options, refreshing from provider if configured.
|
||||
|
||||
This method is useful for credential vending scenarios where storage options
|
||||
may be refreshed dynamically. If no dynamic provider is configured, this
|
||||
returns the initial static options.
|
||||
|
||||
Warning: This is an internal API and the return value is subject to change.
|
||||
|
||||
#### Returns
|
||||
|
||||
`Promise`<`undefined` \| `null` \| `Record`<`string`, `string`>>
|
||||
|
||||
The storage options, or undefined if no storage options were configured.
|
||||
|
||||
***
|
||||
|
||||
### listIndices()
|
||||
|
||||
```ts
|
||||
|
||||
@@ -542,6 +542,35 @@ export abstract class Table {
|
||||
*
|
||||
*/
|
||||
abstract stats(): Promise<TableStatistics>;
|
||||
|
||||
/**
|
||||
* Get the initial storage options that were passed in when opening this table.
|
||||
*
|
||||
* For dynamically refreshed options (e.g., credential vending), use
|
||||
* {@link Table.latestStorageOptions}.
|
||||
*
|
||||
* Warning: This is an internal API and the return value is subject to change.
|
||||
*
|
||||
* @returns The storage options, or undefined if no storage options were configured.
|
||||
*/
|
||||
abstract initialStorageOptions(): Promise<
|
||||
Record<string, string> | null | undefined
|
||||
>;
|
||||
|
||||
/**
|
||||
* Get the latest storage options, refreshing from provider if configured.
|
||||
*
|
||||
* This method is useful for credential vending scenarios where storage options
|
||||
* may be refreshed dynamically. If no dynamic provider is configured, this
|
||||
* returns the initial static options.
|
||||
*
|
||||
* Warning: This is an internal API and the return value is subject to change.
|
||||
*
|
||||
* @returns The storage options, or undefined if no storage options were configured.
|
||||
*/
|
||||
abstract latestStorageOptions(): Promise<
|
||||
Record<string, string> | null | undefined
|
||||
>;
|
||||
}
|
||||
|
||||
export class LocalTable extends Table {
|
||||
@@ -878,6 +907,18 @@ export class LocalTable extends Table {
|
||||
return await this.inner.stats();
|
||||
}
|
||||
|
||||
async initialStorageOptions(): Promise<
|
||||
Record<string, string> | null | undefined
|
||||
> {
|
||||
return await this.inner.initialStorageOptions();
|
||||
}
|
||||
|
||||
async latestStorageOptions(): Promise<
|
||||
Record<string, string> | null | undefined
|
||||
> {
|
||||
return await this.inner.latestStorageOptions();
|
||||
}
|
||||
|
||||
mergeInsert(on: string | string[]): MergeInsertBuilder {
|
||||
on = Array.isArray(on) ? on : [on];
|
||||
return new MergeInsertBuilder(this.inner.mergeInsert(on), this.schema());
|
||||
|
||||
@@ -166,6 +166,19 @@ impl Table {
|
||||
Ok(stats.into())
|
||||
}
|
||||
|
||||
#[napi(catch_unwind)]
|
||||
pub async fn initial_storage_options(&self) -> napi::Result<Option<HashMap<String, String>>> {
|
||||
Ok(self.inner_ref()?.initial_storage_options().await)
|
||||
}
|
||||
|
||||
#[napi(catch_unwind)]
|
||||
pub async fn latest_storage_options(&self) -> napi::Result<Option<HashMap<String, String>>> {
|
||||
self.inner_ref()?
|
||||
.latest_storage_options()
|
||||
.await
|
||||
.default_error()
|
||||
}
|
||||
|
||||
#[napi(catch_unwind)]
|
||||
pub async fn update(
|
||||
&self,
|
||||
|
||||
@@ -180,6 +180,8 @@ class Table:
|
||||
delete_unverified: Optional[bool] = None,
|
||||
) -> OptimizeStats: ...
|
||||
async def uri(self) -> str: ...
|
||||
async def initial_storage_options(self) -> Optional[Dict[str, str]]: ...
|
||||
async def latest_storage_options(self) -> Optional[Dict[str, str]]: ...
|
||||
@property
|
||||
def tags(self) -> Tags: ...
|
||||
def query(self) -> Query: ...
|
||||
|
||||
@@ -2222,6 +2222,37 @@ class LanceTable(Table):
|
||||
def uri(self) -> str:
|
||||
return LOOP.run(self._table.uri())
|
||||
|
||||
def initial_storage_options(self) -> Optional[Dict[str, str]]:
|
||||
"""Get the initial storage options that were passed in when opening this table.
|
||||
|
||||
For dynamically refreshed options (e.g., credential vending), use
|
||||
:meth:`latest_storage_options`.
|
||||
|
||||
Warning: This is an internal API and the return value is subject to change.
|
||||
|
||||
Returns
|
||||
-------
|
||||
Optional[Dict[str, str]]
|
||||
The storage options, or None if no storage options were configured.
|
||||
"""
|
||||
return LOOP.run(self._table.initial_storage_options())
|
||||
|
||||
def latest_storage_options(self) -> Optional[Dict[str, str]]:
|
||||
"""Get the latest storage options, refreshing from provider if configured.
|
||||
|
||||
This method is useful for credential vending scenarios where storage options
|
||||
may be refreshed dynamically. If no dynamic provider is configured, this
|
||||
returns the initial static options.
|
||||
|
||||
Warning: This is an internal API and the return value is subject to change.
|
||||
|
||||
Returns
|
||||
-------
|
||||
Optional[Dict[str, str]]
|
||||
The storage options, or None if no storage options were configured.
|
||||
"""
|
||||
return LOOP.run(self._table.latest_storage_options())
|
||||
|
||||
def create_scalar_index(
|
||||
self,
|
||||
column: str,
|
||||
@@ -3624,6 +3655,37 @@ class AsyncTable:
|
||||
"""
|
||||
return await self._inner.uri()
|
||||
|
||||
async def initial_storage_options(self) -> Optional[Dict[str, str]]:
|
||||
"""Get the initial storage options that were passed in when opening this table.
|
||||
|
||||
For dynamically refreshed options (e.g., credential vending), use
|
||||
:meth:`latest_storage_options`.
|
||||
|
||||
Warning: This is an internal API and the return value is subject to change.
|
||||
|
||||
Returns
|
||||
-------
|
||||
Optional[Dict[str, str]]
|
||||
The storage options, or None if no storage options were configured.
|
||||
"""
|
||||
return await self._inner.initial_storage_options()
|
||||
|
||||
async def latest_storage_options(self) -> Optional[Dict[str, str]]:
|
||||
"""Get the latest storage options, refreshing from provider if configured.
|
||||
|
||||
This method is useful for credential vending scenarios where storage options
|
||||
may be refreshed dynamically. If no dynamic provider is configured, this
|
||||
returns the initial static options.
|
||||
|
||||
Warning: This is an internal API and the return value is subject to change.
|
||||
|
||||
Returns
|
||||
-------
|
||||
Optional[Dict[str, str]]
|
||||
The storage options, or None if no storage options were configured.
|
||||
"""
|
||||
return await self._inner.latest_storage_options()
|
||||
|
||||
async def add(
|
||||
self,
|
||||
data: DATA,
|
||||
|
||||
@@ -502,6 +502,20 @@ impl Table {
|
||||
future_into_py(self_.py(), async move { inner.uri().await.infer_error() })
|
||||
}
|
||||
|
||||
pub fn initial_storage_options(self_: PyRef<'_, Self>) -> PyResult<Bound<'_, PyAny>> {
|
||||
let inner = self_.inner_ref()?.clone();
|
||||
future_into_py(self_.py(), async move {
|
||||
Ok(inner.initial_storage_options().await)
|
||||
})
|
||||
}
|
||||
|
||||
pub fn latest_storage_options(self_: PyRef<'_, Self>) -> PyResult<Bound<'_, PyAny>> {
|
||||
let inner = self_.inner_ref()?.clone();
|
||||
future_into_py(self_.py(), async move {
|
||||
inner.latest_storage_options().await.infer_error()
|
||||
})
|
||||
}
|
||||
|
||||
pub fn __repr__(&self) -> String {
|
||||
match &self.inner {
|
||||
None => format!("ClosedTable({})", self.name),
|
||||
|
||||
@@ -1497,6 +1497,14 @@ impl<S: HttpSend> BaseTable for RemoteTable<S> {
|
||||
None
|
||||
}
|
||||
|
||||
async fn initial_storage_options(&self) -> Option<HashMap<String, String>> {
|
||||
None
|
||||
}
|
||||
|
||||
async fn latest_storage_options(&self) -> Result<Option<HashMap<String, String>>> {
|
||||
Ok(None)
|
||||
}
|
||||
|
||||
async fn stats(&self) -> Result<TableStatistics> {
|
||||
let request = self
|
||||
.client
|
||||
|
||||
@@ -527,7 +527,17 @@ pub trait BaseTable: std::fmt::Display + std::fmt::Debug + Send + Sync {
|
||||
/// Get the table URI (storage location)
|
||||
async fn uri(&self) -> Result<String>;
|
||||
/// Get the storage options used when opening this table, if any.
|
||||
#[deprecated(since = "0.25.0", note = "Use initial_storage_options() instead")]
|
||||
async fn storage_options(&self) -> Option<HashMap<String, String>>;
|
||||
/// Get the initial storage options that were passed in when opening this table.
|
||||
///
|
||||
/// For dynamically refreshed options (e.g., credential vending), use [`Self::latest_storage_options`].
|
||||
async fn initial_storage_options(&self) -> Option<HashMap<String, String>>;
|
||||
/// Get the latest storage options, refreshing from provider if configured.
|
||||
///
|
||||
/// Returns `Ok(Some(options))` if storage options are available (static or refreshed),
|
||||
/// `Ok(None)` if no storage options were configured, or `Err(...)` if refresh failed.
|
||||
async fn latest_storage_options(&self) -> Result<Option<HashMap<String, String>>>;
|
||||
/// Poll until the columns are fully indexed. Will return Error::Timeout if the columns
|
||||
/// are not fully indexed within the timeout.
|
||||
async fn wait_for_index(
|
||||
@@ -1257,10 +1267,32 @@ impl Table {
|
||||
/// Get the storage options used when opening this table, if any.
|
||||
///
|
||||
/// Warning: This is an internal API and the return value is subject to change.
|
||||
#[deprecated(since = "0.25.0", note = "Use initial_storage_options() instead")]
|
||||
pub async fn storage_options(&self) -> Option<HashMap<String, String>> {
|
||||
#[allow(deprecated)]
|
||||
self.inner.storage_options().await
|
||||
}
|
||||
|
||||
/// Get the initial storage options that were passed in when opening this table.
|
||||
///
|
||||
/// For dynamically refreshed options (e.g., credential vending), use [`Self::latest_storage_options`].
|
||||
///
|
||||
/// Warning: This is an internal API and the return value is subject to change.
|
||||
pub async fn initial_storage_options(&self) -> Option<HashMap<String, String>> {
|
||||
self.inner.initial_storage_options().await
|
||||
}
|
||||
|
||||
/// Get the latest storage options, refreshing from provider if configured.
|
||||
///
|
||||
/// This method is useful for credential vending scenarios where storage options
|
||||
/// may be refreshed dynamically. If no dynamic provider is configured, this
|
||||
/// returns the initial static options.
|
||||
///
|
||||
/// Warning: This is an internal API and the return value is subject to change.
|
||||
pub async fn latest_storage_options(&self) -> Result<Option<HashMap<String, String>>> {
|
||||
self.inner.latest_storage_options().await
|
||||
}
|
||||
|
||||
/// Get statistics about an index.
|
||||
/// Returns None if the index does not exist.
|
||||
pub async fn index_stats(
|
||||
@@ -3142,6 +3174,10 @@ impl BaseTable for NativeTable {
|
||||
}
|
||||
|
||||
async fn storage_options(&self) -> Option<HashMap<String, String>> {
|
||||
self.initial_storage_options().await
|
||||
}
|
||||
|
||||
async fn initial_storage_options(&self) -> Option<HashMap<String, String>> {
|
||||
self.dataset
|
||||
.get()
|
||||
.await
|
||||
@@ -3149,6 +3185,11 @@ impl BaseTable for NativeTable {
|
||||
.and_then(|dataset| dataset.initial_storage_options().cloned())
|
||||
}
|
||||
|
||||
async fn latest_storage_options(&self) -> Result<Option<HashMap<String, String>>> {
|
||||
let dataset = self.dataset.get().await?;
|
||||
Ok(dataset.latest_storage_options().await?.map(|o| o.0))
|
||||
}
|
||||
|
||||
async fn index_stats(&self, index_name: &str) -> Result<Option<IndexStatistics>> {
|
||||
let stats = match self
|
||||
.dataset
|
||||
|
||||
Reference in New Issue
Block a user