Struct parquet::encoding::DictEncoder [−][src]
pub struct DictEncoder<T: DataType> { /* fields omitted */ }
Expand description
Dictionary encoder. The dictionary encoding builds a dictionary of values encountered in a given column. The dictionary page is written first, before the data pages of the column chunk.
Dictionary page format: the entries in the dictionary - in dictionary order - using the plain encoding.
Data page format: the bit width used to encode the entry ids stored as 1 byte (max bit width = 32), followed by the values encoded using RLE/Bit packed described above (with the given bit width).
Implementations
impl<T: DataType> DictEncoder<T>
[src]
impl<T: DataType> DictEncoder<T>
[src]pub fn new(desc: ColumnDescPtr, mem_tracker: MemTrackerPtr) -> Self
[src]
pub fn new(desc: ColumnDescPtr, mem_tracker: MemTrackerPtr) -> Self
[src]Creates new dictionary encoder.
pub fn num_entries(&self) -> usize
[src]
pub fn num_entries(&self) -> usize
[src]Returns number of unique values (keys) in the dictionary.
pub fn dict_encoded_size(&self) -> usize
[src]
pub fn dict_encoded_size(&self) -> usize
[src]Returns size of unique values (keys) in the dictionary, in bytes.
pub fn write_dict(&self) -> Result<ByteBufferPtr>
[src]
pub fn write_dict(&self) -> Result<ByteBufferPtr>
[src]Writes out the dictionary values with PLAIN encoding in a byte buffer, and return the result.
pub fn write_indices(&mut self) -> Result<ByteBufferPtr>
[src]
pub fn write_indices(&mut self) -> Result<ByteBufferPtr>
[src]Writes out the dictionary values with RLE encoding in a byte buffer, and return the result.
Trait Implementations
impl<T: DataType> Encoder<T> for DictEncoder<T>
[src]
impl<T: DataType> Encoder<T> for DictEncoder<T>
[src]fn estimated_data_encoded_size(&self) -> usize
[src]
fn estimated_data_encoded_size(&self) -> usize
[src]Returns an estimate of the encoded data, in bytes. Method call must be O(1). Read more
fn flush_buffer(&mut self) -> Result<ByteBufferPtr>
[src]
fn flush_buffer(&mut self) -> Result<ByteBufferPtr>
[src]Flushes the underlying byte buffer that’s being processed by this encoder, and return the immutable copy of it. This will also reset the internal state. Read more
Auto Trait Implementations
impl<T> RefUnwindSafe for DictEncoder<T> where
<T as DataType>::T: RefUnwindSafe,
<T as DataType>::T: RefUnwindSafe,
impl<T> Send for DictEncoder<T> where
<T as DataType>::T: Send,
<T as DataType>::T: Send,
impl<T> Sync for DictEncoder<T> where
<T as DataType>::T: Sync,
<T as DataType>::T: Sync,
impl<T> Unpin for DictEncoder<T> where
<T as DataType>::T: Unpin,
<T as DataType>::T: Unpin,
impl<T> UnwindSafe for DictEncoder<T> where
<T as DataType>::T: UnwindSafe,
<T as DataType>::T: UnwindSafe,
Blanket Implementations
impl<T> BorrowMut<T> for T where
T: ?Sized,
[src]
impl<T> BorrowMut<T> for T where
T: ?Sized,
[src]pub fn borrow_mut(&mut self) -> &mut T
[src]
pub fn borrow_mut(&mut self) -> &mut T
[src]Mutably borrows from an owned value. Read more
impl<V, T> VZip<V> for T where
V: MultiLane<T>,
impl<V, T> VZip<V> for T where
V: MultiLane<T>,