Struct ParquetEncoder 

pub struct ParquetEncoder {
    pub option: EncoderOption,
}

An encoder for converting FASTA records to Parquet format.

This struct provides functionality to encode FASTA sequence data into Parquet files, which are an efficient columnar storage format.

Fields

• option - Configuration options for the encoder, including which bases to consider

Example

use deepbiop_fa::encode::{option::EncoderOption, parquet::ParquetEncoder};

let options = EncoderOption::default();
let encoder = ParquetEncoder::new(options);

Fields

option: EncoderOption

Implementations

impl ParquetEncoder

pub fn new(option: EncoderOption) -> Self

pub fn encode_chunk<P: AsRef<Path>>( &mut self, path: P, chunk_size: usize, parallel: bool, ) -> Result<()>

Trait Implementations

impl Clone for ParquetEncoder

fn clone(&self) -> ParquetEncoder

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for ParquetEncoder

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl Default for ParquetEncoder

fn default() -> ParquetEncoder

Returns the “default value” for a type.

impl<'de> Deserialize<'de> for ParquetEncoder

fn deserialize<__D>(__deserializer: __D) -> Result<Self, __D::Error>

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Display for ParquetEncoder

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl Encoder for ParquetEncoder

type EncodeOutput = Result<(Vec<RecordBatch>, Arc<Schema>), Error>

type RecordOutput = Result<RecordData, Error>

fn encode_multiple( &mut self, _paths: &[PathBuf], _parallel: bool, ) -> Self::EncodeOutput

fn encode<P: AsRef<Path>>(&mut self, path: P) -> Self::EncodeOutput

fn encode_record(&self, id: &[u8], seq: &[u8]) -> Self::RecordOutput

fn fetch_records<P: AsRef<Path>>(&mut self, path: P) -> Result<Vec<RecordData>>

impl<'py> IntoPyObject<'py> for ParquetEncoder

type Target = ParquetEncoder

The Python output type

type Output = Bound<'py, <ParquetEncoder as IntoPyObject<'py>>::Target>

The smart pointer type to use.

type Error = PyErr

The type returned in the event of a conversion error.

fn into_pyobject( self, py: Python<'py>, ) -> Result<<Self as IntoPyObject<'_>>::Output, <Self as IntoPyObject<'_>>::Error>

Performs the conversion.

impl PyClass for ParquetEncoder

type Frozen = False

Whether the pyclass is frozen.

impl PyClassImpl for ParquetEncoder

const IS_BASETYPE: bool = false

#[pyclass(subclass)]

const IS_SUBCLASS: bool = false

#[pyclass(extends=…)]

const IS_MAPPING: bool = false

#[pyclass(mapping)]

const IS_SEQUENCE: bool = false

#[pyclass(sequence)]

const IS_IMMUTABLE_TYPE: bool = false

#[pyclass(immutable_type)]

const RAW_DOC: &'static CStr = /// An encoder for converting FASTA records to Parquet format. /// /// This struct provides functionality to encode FASTA sequence data into Parquet files, /// which are an efficient columnar storage format. /// /// # Fields /// /// * `option` - Configuration options for the encoder, including which bases to consider /// /// # Example /// /// ``` /// use deepbiop_fa::encode::{option::EncoderOption, parquet::ParquetEncoder}; /// /// let options = EncoderOption::default(); /// let encoder = ParquetEncoder::new(options); /// ```

Docstring for the class provided on the struct or enum.

const DOC: &'static CStr

Fully rendered class doc, including the text_signature if a constructor is defined.

type BaseType = PyAny

Base class

type ThreadChecker = SendablePyClass<ParquetEncoder>

This handles following two situations:

type PyClassMutability = <<PyAny as PyClassBaseType>::PyClassMutability as PyClassMutability>::MutableChild

Immutable or mutable

type Dict = PyClassDummySlot

Specify this class has #[pyclass(dict)] or not.

type WeakRef = PyClassDummySlot

Specify this class has #[pyclass(weakref)] or not.

type BaseNativeType = PyAny

The closest native ancestor. This is PyAny by default, and when you declare #[pyclass(extends=PyDict)], it’s PyDict.

fn items_iter() -> PyClassItemsIter

fn lazy_type_object() -> &'static LazyTypeObject<Self>

fn dict_offset() -> Option<isize>

fn weaklist_offset() -> Option<isize>

impl PyStubType for ParquetEncoder

fn type_output() -> TypeInfo

The type to be used in the output signature, i.e. return type of the Python function or methods.

fn type_input() -> TypeInfo

The type to be used in the input signature, i.e. the arguments of the Python function or methods.

impl PyTypeInfo for ParquetEncoder

const NAME: &'static str = "ParquetEncoder"

Class name.

const MODULE: Option<&'static str>

Module name, if any.

fn type_object_raw(py: Python<'_>) -> *mut PyTypeObject

Returns the PyTypeObject instance for this type.

fn type_object(py: Python<'_>) -> Bound<'_, PyType>

Returns the safe abstraction over the type object.

fn is_type_of(object: &Bound<'_, PyAny>) -> bool

Checks if object is an instance of this type or a subclass of this type.

fn is_exact_type_of(object: &Bound<'_, PyAny>) -> bool

Checks if object is an instance of this type.

impl Serialize for ParquetEncoder

fn serialize<__S>(&self, __serializer: __S) -> Result<__S::Ok, __S::Error>

where __S: Serializer,

Serialize this value into the given Serde serializer.

impl DerefToPyAny for ParquetEncoder

impl ExtractPyClassWithClone for ParquetEncoder