Struct ParquetWriter

Source
pub struct ParquetWriter<F: WriterFactory, I: IndexerBuilder, P: FilePathProvider> {
    path_provider: P,
    writer: Option<AsyncArrowWriter<SizeAwareWriter<F::Writer>>>,
    current_file: FileId,
    writer_factory: F,
    metadata: RegionMetadataRef,
    indexer_builder: I,
    current_indexer: Option<Indexer>,
    bytes_written: Arc<AtomicUsize>,
    file_cleaner: Option<TempFileCleaner>,
    metrics: Metrics,
}
Expand description

Parquet SST writer.

Fields§

§path_provider: P

Path provider that creates SST and index file paths according to file id.

§writer: Option<AsyncArrowWriter<SizeAwareWriter<F::Writer>>>§current_file: FileId

Current active file id.

§writer_factory: F§metadata: RegionMetadataRef

Region metadata of the source and the target SST.

§indexer_builder: I

Indexer build that can create indexer for multiple files.

§current_indexer: Option<Indexer>

Current active indexer.

§bytes_written: Arc<AtomicUsize>§file_cleaner: Option<TempFileCleaner>

Cleaner to remove temp files on failure.

§metrics: Metrics

Write metrics

Implementations§

Source§

impl<I, P> ParquetWriter<ObjectStoreWriterFactory, I, P>

Source

pub async fn new_with_object_store( object_store: ObjectStore, metadata: RegionMetadataRef, indexer_builder: I, path_provider: P, metrics: Metrics, ) -> ParquetWriter<ObjectStoreWriterFactory, I, P>

Source

pub(crate) fn with_file_cleaner(self, cleaner: TempFileCleaner) -> Self

Source§

impl<F, I, P> ParquetWriter<F, I, P>

Source

pub async fn new( factory: F, metadata: RegionMetadataRef, indexer_builder: I, path_provider: P, metrics: Metrics, ) -> ParquetWriter<F, I, P>

Creates a new parquet SST writer.

Source

async fn finish_current_file( &mut self, ssts: &mut SstInfoArray, stats: &mut SourceStats, ) -> Result<()>

Finishes current SST file and index file.

Source

pub async fn write_all( &mut self, source: Source, override_sequence: Option<SequenceNumber>, opts: &WriteOptions, ) -> Result<SstInfoArray>

Iterates source and writes all rows to Parquet file.

Returns the SstInfo if the SST is written.

Source

async fn write_all_without_cleaning( &mut self, source: Source, override_sequence: Option<SequenceNumber>, opts: &WriteOptions, ) -> Result<SstInfoArray>

Source

pub async fn write_all_flat( &mut self, source: FlatSource, opts: &WriteOptions, ) -> Result<SstInfoArray>

Iterates FlatSource and writes all RecordBatch in flat format to Parquet file.

Returns the SstInfo if the SST is written.

Source

async fn write_all_flat_without_cleaning( &mut self, source: FlatSource, opts: &WriteOptions, ) -> Result<SstInfoArray>

Source

fn customize_column_config( builder: WriterPropertiesBuilder, region_metadata: &RegionMetadataRef, ) -> WriterPropertiesBuilder

Customizes per-column config according to schema and maybe column cardinality.

Source

async fn write_next_batch( &mut self, source: &mut Source, write_format: &PrimaryKeyWriteFormat, opts: &WriteOptions, ) -> Result<Option<Batch>>

Source

async fn write_next_flat_batch( &mut self, source: &mut FlatSource, flat_format: &FlatWriteFormat, opts: &WriteOptions, ) -> Result<Option<RecordBatch>>

Source

async fn maybe_init_writer( &mut self, schema: &SchemaRef, opts: &WriteOptions, ) -> Result<&mut AsyncArrowWriter<SizeAwareWriter<F::Writer>>>

Source

pub fn into_metrics(self) -> Metrics

Consumes write and return the collected metrics.

Auto Trait Implementations§

§

impl<F, I, P> Freeze for ParquetWriter<F, I, P>
where P: Freeze, F: Freeze, I: Freeze, <F as WriterFactory>::Writer: Freeze,

§

impl<F, I, P> !RefUnwindSafe for ParquetWriter<F, I, P>

§

impl<F, I, P> Send for ParquetWriter<F, I, P>
where F: Send, I: Send,

§

impl<F, I, P> !Sync for ParquetWriter<F, I, P>

§

impl<F, I, P> Unpin for ParquetWriter<F, I, P>
where P: Unpin, F: Unpin, I: Unpin,

§

impl<F, I, P> !UnwindSafe for ParquetWriter<F, I, P>

Blanket Implementations§

Source§

impl<T> Any for T
where T: 'static + ?Sized,

Source§

fn type_id(&self) -> TypeId

Gets the TypeId of self. Read more
§

impl<T> Any for T
where T: Any,

§

fn into_any(self: Box<T>) -> Box<dyn Any>

§

fn into_any_rc(self: Rc<T>) -> Rc<dyn Any>

§

fn type_name(&self) -> &'static str

Source§

impl<T> Borrow<T> for T
where T: ?Sized,

Source§

fn borrow(&self) -> &T

Immutably borrows from an owned value. Read more
Source§

impl<T> BorrowMut<T> for T
where T: ?Sized,

Source§

fn borrow_mut(&mut self) -> &mut T

Mutably borrows from an owned value. Read more
§

impl<T> Conv for T

§

fn conv<T>(self) -> T
where Self: Into<T>,

Converts self into T using Into<T>. Read more
§

impl<T, V> Convert<T> for V
where V: Into<T>,

§

fn convert(value: Self) -> T

§

fn convert_box(value: Box<Self>) -> Box<T>

§

fn convert_vec(value: Vec<Self>) -> Vec<T>

§

fn convert_vec_box(value: Vec<Box<Self>>) -> Vec<Box<T>>

§

fn convert_matrix(value: Vec<Vec<Self>>) -> Vec<Vec<T>>

§

fn convert_option(value: Option<Self>) -> Option<T>

§

fn convert_option_box(value: Option<Box<Self>>) -> Option<Box<T>>

§

fn convert_option_vec(value: Option<Vec<Self>>) -> Option<Vec<T>>

§

impl<T> Downcast for T
where T: Any,

§

fn into_any(self: Box<T>) -> Box<dyn Any>

Converts Box<dyn Trait> (where Trait: Downcast) to Box<dyn Any>, which can then be downcast into Box<dyn ConcreteType> where ConcreteType implements Trait.
§

fn into_any_rc(self: Rc<T>) -> Rc<dyn Any>

Converts Rc<Trait> (where Trait: Downcast) to Rc<Any>, which can then be further downcast into Rc<ConcreteType> where ConcreteType implements Trait.
§

fn as_any(&self) -> &(dyn Any + 'static)

Converts &Trait (where Trait: Downcast) to &Any. This is needed since Rust cannot generate &Any’s vtable from &Trait’s.
§

fn as_any_mut(&mut self) -> &mut (dyn Any + 'static)

Converts &mut Trait (where Trait: Downcast) to &Any. This is needed since Rust cannot generate &mut Any’s vtable from &mut Trait’s.
§

impl<T> DowncastSend for T
where T: Any + Send,

§

fn into_any_send(self: Box<T>) -> Box<dyn Any + Send>

Converts Box<Trait> (where Trait: DowncastSend) to Box<dyn Any + Send>, which can then be downcast into Box<ConcreteType> where ConcreteType implements Trait.
§

impl<T> FmtForward for T

§

fn fmt_binary(self) -> FmtBinary<Self>
where Self: Binary,

Causes self to use its Binary implementation when Debug-formatted.
§

fn fmt_display(self) -> FmtDisplay<Self>
where Self: Display,

Causes self to use its Display implementation when Debug-formatted.
§

fn fmt_lower_exp(self) -> FmtLowerExp<Self>
where Self: LowerExp,

Causes self to use its LowerExp implementation when Debug-formatted.
§

fn fmt_lower_hex(self) -> FmtLowerHex<Self>
where Self: LowerHex,

Causes self to use its LowerHex implementation when Debug-formatted.
§

fn fmt_octal(self) -> FmtOctal<Self>
where Self: Octal,

Causes self to use its Octal implementation when Debug-formatted.
§

fn fmt_pointer(self) -> FmtPointer<Self>
where Self: Pointer,

Causes self to use its Pointer implementation when Debug-formatted.
§

fn fmt_upper_exp(self) -> FmtUpperExp<Self>
where Self: UpperExp,

Causes self to use its UpperExp implementation when Debug-formatted.
§

fn fmt_upper_hex(self) -> FmtUpperHex<Self>
where Self: UpperHex,

Causes self to use its UpperHex implementation when Debug-formatted.
§

fn fmt_list(self) -> FmtList<Self>
where &'a Self: for<'a> IntoIterator,

Formats each item in a sequence. Read more
Source§

impl<T> From<T> for T

Source§

fn from(t: T) -> T

Returns the argument unchanged.

§

impl<T> FutureExt for T

§

fn with_context(self, otel_cx: Context) -> WithContext<Self>

Attaches the provided Context to this type, returning a WithContext wrapper. Read more
§

fn with_current_context(self) -> WithContext<Self>

Attaches the current Context to this type, returning a WithContext wrapper. Read more
§

impl<T> Instrument for T

§

fn instrument(self, span: Span) -> Instrumented<Self>

Instruments this type with the provided [Span], returning an Instrumented wrapper. Read more
§

fn in_current_span(self) -> Instrumented<Self>

Instruments this type with the current Span, returning an Instrumented wrapper. Read more
Source§

impl<T, U> Into<U> for T
where U: From<T>,

Source§

fn into(self) -> U

Calls U::from(self).

That is, this conversion is whatever the implementation of From<T> for U chooses to do.

Source§

impl<T> IntoEither for T

Source§

fn into_either(self, into_left: bool) -> Either<Self, Self>

Converts self into a Left variant of Either<Self, Self> if into_left is true. Converts self into a Right variant of Either<Self, Self> otherwise. Read more
Source§

fn into_either_with<F>(self, into_left: F) -> Either<Self, Self>
where F: FnOnce(&Self) -> bool,

Converts self into a Left variant of Either<Self, Self> if into_left(&self) returns true. Converts self into a Right variant of Either<Self, Self> otherwise. Read more
§

impl<T> IntoRequest<T> for T

§

fn into_request(self) -> Request<T>

Wrap the input message T in a tonic::Request
§

impl<L> LayerExt<L> for L

§

fn named_layer<S>(&self, service: S) -> Layered<<L as Layer<S>>::Service, S>
where L: Layer<S>,

Applies the layer to a service and wraps it in [Layered].
§

impl<T> Pipe for T
where T: ?Sized,

§

fn pipe<R>(self, func: impl FnOnce(Self) -> R) -> R
where Self: Sized,

Pipes by value. This is generally the method you want to use. Read more
§

fn pipe_ref<'a, R>(&'a self, func: impl FnOnce(&'a Self) -> R) -> R
where R: 'a,

Borrows self and passes that borrow into the pipe function. Read more
§

fn pipe_ref_mut<'a, R>(&'a mut self, func: impl FnOnce(&'a mut Self) -> R) -> R
where R: 'a,

Mutably borrows self and passes that borrow into the pipe function. Read more
§

fn pipe_borrow<'a, B, R>(&'a self, func: impl FnOnce(&'a B) -> R) -> R
where Self: Borrow<B>, B: 'a + ?Sized, R: 'a,

Borrows self, then passes self.borrow() into the pipe function. Read more
§

fn pipe_borrow_mut<'a, B, R>( &'a mut self, func: impl FnOnce(&'a mut B) -> R, ) -> R
where Self: BorrowMut<B>, B: 'a + ?Sized, R: 'a,

Mutably borrows self, then passes self.borrow_mut() into the pipe function. Read more
§

fn pipe_as_ref<'a, U, R>(&'a self, func: impl FnOnce(&'a U) -> R) -> R
where Self: AsRef<U>, U: 'a + ?Sized, R: 'a,

Borrows self, then passes self.as_ref() into the pipe function.
§

fn pipe_as_mut<'a, U, R>(&'a mut self, func: impl FnOnce(&'a mut U) -> R) -> R
where Self: AsMut<U>, U: 'a + ?Sized, R: 'a,

Mutably borrows self, then passes self.as_mut() into the pipe function.
§

fn pipe_deref<'a, T, R>(&'a self, func: impl FnOnce(&'a T) -> R) -> R
where Self: Deref<Target = T>, T: 'a + ?Sized, R: 'a,

Borrows self, then passes self.deref() into the pipe function.
§

fn pipe_deref_mut<'a, T, R>( &'a mut self, func: impl FnOnce(&'a mut T) -> R, ) -> R
where Self: DerefMut<Target = T> + Deref, T: 'a + ?Sized, R: 'a,

Mutably borrows self, then passes self.deref_mut() into the pipe function.
§

impl<T> Pointable for T

§

const ALIGN: usize

The alignment of pointer.
§

type Init = T

The type for initializers.
§

unsafe fn init(init: <T as Pointable>::Init) -> usize

Initializes a with the given initializer. Read more
§

unsafe fn deref<'a>(ptr: usize) -> &'a T

Dereferences the given pointer. Read more
§

unsafe fn deref_mut<'a>(ptr: usize) -> &'a mut T

Mutably dereferences the given pointer. Read more
§

unsafe fn drop(ptr: usize)

Drops the object pointed to by the given pointer. Read more
§

impl<T> PolicyExt for T
where T: ?Sized,

§

fn and<P, B, E>(self, other: P) -> And<T, P>
where T: Policy<B, E>, P: Policy<B, E>,

Create a new Policy that returns [Action::Follow] only if self and other return Action::Follow. Read more
§

fn or<P, B, E>(self, other: P) -> Or<T, P>
where T: Policy<B, E>, P: Policy<B, E>,

Create a new Policy that returns [Action::Follow] if either self or other returns Action::Follow. Read more
Source§

impl<T> Same for T

Source§

type Output = T

Should always be Self
§

impl<T> ServiceExt for T

§

fn propagate_header(self, header: HeaderName) -> PropagateHeader<Self>
where Self: Sized,

Propagate a header from the request to the response. Read more
§

fn add_extension<T>(self, value: T) -> AddExtension<Self, T>
where Self: Sized,

Add some shareable value to request extensions. Read more
§

fn map_request_body<F>(self, f: F) -> MapRequestBody<Self, F>
where Self: Sized,

Apply a transformation to the request body. Read more
§

fn map_response_body<F>(self, f: F) -> MapResponseBody<Self, F>
where Self: Sized,

Apply a transformation to the response body. Read more
§

fn compression(self) -> Compression<Self>
where Self: Sized,

Compresses response bodies. Read more
§

fn decompression(self) -> Decompression<Self>
where Self: Sized,

Decompress response bodies. Read more
§

fn trace_for_http(self) -> Trace<Self, SharedClassifier<ServerErrorsAsFailures>>
where Self: Sized,

High level tracing that classifies responses using HTTP status codes. Read more
§

fn trace_for_grpc(self) -> Trace<Self, SharedClassifier<GrpcErrorsAsFailures>>
where Self: Sized,

High level tracing that classifies responses using gRPC headers. Read more
§

fn follow_redirects(self) -> FollowRedirect<Self>
where Self: Sized,

Follow redirect resposes using the Standard policy. Read more
§

fn sensitive_headers( self, headers: impl IntoIterator<Item = HeaderName>, ) -> SetSensitiveRequestHeaders<SetSensitiveResponseHeaders<Self>>
where Self: Sized,

Mark headers as sensitive on both requests and responses. Read more
§

fn sensitive_request_headers( self, headers: impl IntoIterator<Item = HeaderName>, ) -> SetSensitiveRequestHeaders<Self>
where Self: Sized,

Mark headers as sensitive on requests. Read more
§

fn sensitive_response_headers( self, headers: impl IntoIterator<Item = HeaderName>, ) -> SetSensitiveResponseHeaders<Self>
where Self: Sized,

Mark headers as sensitive on responses. Read more
§

fn override_request_header<M>( self, header_name: HeaderName, make: M, ) -> SetRequestHeader<Self, M>
where Self: Sized,

Insert a header into the request. Read more
§

fn append_request_header<M>( self, header_name: HeaderName, make: M, ) -> SetRequestHeader<Self, M>
where Self: Sized,

Append a header into the request. Read more
§

fn insert_request_header_if_not_present<M>( self, header_name: HeaderName, make: M, ) -> SetRequestHeader<Self, M>
where Self: Sized,

Insert a header into the request, if the header is not already present. Read more
§

fn override_response_header<M>( self, header_name: HeaderName, make: M, ) -> SetResponseHeader<Self, M>
where Self: Sized,

Insert a header into the response. Read more
§

fn append_response_header<M>( self, header_name: HeaderName, make: M, ) -> SetResponseHeader<Self, M>
where Self: Sized,

Append a header into the response. Read more
§

fn insert_response_header_if_not_present<M>( self, header_name: HeaderName, make: M, ) -> SetResponseHeader<Self, M>
where Self: Sized,

Insert a header into the response, if the header is not already present. Read more
§

fn set_request_id<M>( self, header_name: HeaderName, make_request_id: M, ) -> SetRequestId<Self, M>
where Self: Sized, M: MakeRequestId,

Add request id header and extension. Read more
§

fn set_x_request_id<M>(self, make_request_id: M) -> SetRequestId<Self, M>
where Self: Sized, M: MakeRequestId,

Add request id header and extension, using x-request-id as the header name. Read more
§

fn propagate_request_id( self, header_name: HeaderName, ) -> PropagateRequestId<Self>
where Self: Sized,

Propgate request ids from requests to responses. Read more
§

fn propagate_x_request_id(self) -> PropagateRequestId<Self>
where Self: Sized,

Propgate request ids from requests to responses, using x-request-id as the header name. Read more
§

fn catch_panic(self) -> CatchPanic<Self, DefaultResponseForPanic>
where Self: Sized,

Catch panics and convert them into 500 Internal Server responses. Read more
§

fn request_body_limit(self, limit: usize) -> RequestBodyLimit<Self>
where Self: Sized,

Intercept requests with over-sized payloads and convert them into 413 Payload Too Large responses. Read more
§

fn trim_trailing_slash(self) -> NormalizePath<Self>
where Self: Sized,

Remove trailing slashes from paths. Read more
§

fn append_trailing_slash(self) -> NormalizePath<Self>
where Self: Sized,

Append trailing slash to paths. Read more
§

impl<SS, SP> SupersetOf<SS> for SP
where SS: SubsetOf<SP>,

§

fn to_subset(&self) -> Option<SS>

The inverse inclusion map: attempts to construct self from the equivalent element of its superset. Read more
§

fn is_in_subset(&self) -> bool

Checks if self is actually part of its subset T (and can be converted to it).
§

fn to_subset_unchecked(&self) -> SS

Use with care! Same as self.to_subset but without any property checks. Always succeeds.
§

fn from_subset(element: &SS) -> SP

The inclusion map: converts self to the equivalent element of its superset.
§

impl<T> Tap for T

§

fn tap(self, func: impl FnOnce(&Self)) -> Self

Immutable access to a value. Read more
§

fn tap_mut(self, func: impl FnOnce(&mut Self)) -> Self

Mutable access to a value. Read more
§

fn tap_borrow<B>(self, func: impl FnOnce(&B)) -> Self
where Self: Borrow<B>, B: ?Sized,

Immutable access to the Borrow<B> of a value. Read more
§

fn tap_borrow_mut<B>(self, func: impl FnOnce(&mut B)) -> Self
where Self: BorrowMut<B>, B: ?Sized,

Mutable access to the BorrowMut<B> of a value. Read more
§

fn tap_ref<R>(self, func: impl FnOnce(&R)) -> Self
where Self: AsRef<R>, R: ?Sized,

Immutable access to the AsRef<R> view of a value. Read more
§

fn tap_ref_mut<R>(self, func: impl FnOnce(&mut R)) -> Self
where Self: AsMut<R>, R: ?Sized,

Mutable access to the AsMut<R> view of a value. Read more
§

fn tap_deref<T>(self, func: impl FnOnce(&T)) -> Self
where Self: Deref<Target = T>, T: ?Sized,

Immutable access to the Deref::Target of a value. Read more
§

fn tap_deref_mut<T>(self, func: impl FnOnce(&mut T)) -> Self
where Self: DerefMut<Target = T> + Deref, T: ?Sized,

Mutable access to the Deref::Target of a value. Read more
§

fn tap_dbg(self, func: impl FnOnce(&Self)) -> Self

Calls .tap() only in debug builds, and is erased in release builds.
§

fn tap_mut_dbg(self, func: impl FnOnce(&mut Self)) -> Self

Calls .tap_mut() only in debug builds, and is erased in release builds.
§

fn tap_borrow_dbg<B>(self, func: impl FnOnce(&B)) -> Self
where Self: Borrow<B>, B: ?Sized,

Calls .tap_borrow() only in debug builds, and is erased in release builds.
§

fn tap_borrow_mut_dbg<B>(self, func: impl FnOnce(&mut B)) -> Self
where Self: BorrowMut<B>, B: ?Sized,

Calls .tap_borrow_mut() only in debug builds, and is erased in release builds.
§

fn tap_ref_dbg<R>(self, func: impl FnOnce(&R)) -> Self
where Self: AsRef<R>, R: ?Sized,

Calls .tap_ref() only in debug builds, and is erased in release builds.
§

fn tap_ref_mut_dbg<R>(self, func: impl FnOnce(&mut R)) -> Self
where Self: AsMut<R>, R: ?Sized,

Calls .tap_ref_mut() only in debug builds, and is erased in release builds.
§

fn tap_deref_dbg<T>(self, func: impl FnOnce(&T)) -> Self
where Self: Deref<Target = T>, T: ?Sized,

Calls .tap_deref() only in debug builds, and is erased in release builds.
§

fn tap_deref_mut_dbg<T>(self, func: impl FnOnce(&mut T)) -> Self
where Self: DerefMut<Target = T> + Deref, T: ?Sized,

Calls .tap_deref_mut() only in debug builds, and is erased in release builds.
§

impl<T> TryConv for T

§

fn try_conv<T>(self) -> Result<T, Self::Error>
where Self: TryInto<T>,

Attempts to convert self into T using TryInto<T>. Read more
Source§

impl<T, U> TryFrom<U> for T
where U: Into<T>,

Source§

type Error = Infallible

The type returned in the event of a conversion error.
Source§

fn try_from(value: U) -> Result<T, <T as TryFrom<U>>::Error>

Performs the conversion.
Source§

impl<T, U> TryInto<U> for T
where U: TryFrom<T>,

Source§

type Error = <U as TryFrom<T>>::Error

The type returned in the event of a conversion error.
Source§

fn try_into(self) -> Result<U, <U as TryFrom<T>>::Error>

Performs the conversion.
§

impl<V, T> VZip<V> for T
where V: MultiLane<T>,

§

fn vzip(self) -> V

§

impl<T> WithSubscriber for T

§

fn with_subscriber<S>(self, subscriber: S) -> WithDispatch<Self>
where S: Into<Dispatch>,

Attaches the provided Subscriber to this type, returning a [WithDispatch] wrapper. Read more
§

fn with_current_subscriber(self) -> WithDispatch<Self>

Attaches the current default Subscriber to this type, returning a [WithDispatch] wrapper. Read more
§

impl<G1, G2> Within<G2> for G1
where G2: Contains<G1>,

§

fn is_within(&self, b: &G2) -> bool

§

impl<T> Any for T
where T: Any,

§

impl<T> ErasedDestructor for T
where T: 'static,

§

impl<T> Fruit for T
where T: Send + Downcast,

§

impl<T> MaybeSend for T
where T: Send,