Struct ArrowColumnWriter

pub struct ArrowColumnWriter {
    writer: ArrowColumnWriterImpl,
    chunk: Arc<Mutex<ArrowColumnChunkData>>,
}

Encodes ArrowLeafColumn to ArrowColumnChunk

Note: This is a low-level interface for applications that require fine-grained control of encoding, see ArrowWriter for a higher-level interface

// The arrow schema
let schema = Arc::new(Schema::new(vec![
    Field::new("i32", DataType::Int32, false),
    Field::new("f32", DataType::Float32, false),
]));

// Compute the parquet schema
let props = Arc::new(WriterProperties::default());
let parquet_schema = arrow_to_parquet_schema(schema.as_ref(), props.coerce_types()).unwrap();

// Create writers for each of the leaf columns
let col_writers = get_column_writers(&parquet_schema, &props, &schema).unwrap();

// Spawn a worker thread for each column
// This is for demonstration purposes, a thread-pool e.g. rayon or tokio, would be better
let mut workers: Vec<_> = col_writers
    .into_iter()
    .map(|mut col_writer| {
        let (send, recv) = std::sync::mpsc::channel::<ArrowLeafColumn>();
        let handle = std::thread::spawn(move || {
            for col in recv {
                col_writer.write(&col)?;
            }
            col_writer.close()
        });
        (handle, send)
    })
    .collect();

// Create parquet writer
let root_schema = parquet_schema.root_schema_ptr();
let mut out = Vec::with_capacity(1024); // This could be a File
let mut writer = SerializedFileWriter::new(&mut out, root_schema, props.clone()).unwrap();

// Start row group
let mut row_group = writer.next_row_group().unwrap();

// Columns to encode
let to_write = vec![
    Arc::new(Int32Array::from_iter_values([1, 2, 3])) as _,
    Arc::new(Float32Array::from_iter_values([1., 45., -1.])) as _,
];

// Spawn work to encode columns
let mut worker_iter = workers.iter_mut();
for (arr, field) in to_write.iter().zip(&schema.fields) {
    for leaves in compute_leaves(field, arr).unwrap() {
        worker_iter.next().unwrap().1.send(leaves).unwrap();
    }
}

// Finish up parallel column encoding
for (handle, send) in workers {
    drop(send); // Drop send side to signal termination
    let chunk = handle.join().unwrap().unwrap();
    chunk.append_to_row_group(&mut row_group).unwrap();
}
row_group.close().unwrap();

let metadata = writer.close().unwrap();
assert_eq!(metadata.num_rows, 3);

Fields

writer: ArrowColumnWriterImpl

chunk: Arc<Mutex<ArrowColumnChunkData>>

Implementations

impl ArrowColumnWriter

pub fn write(&mut self, col: &ArrowLeafColumn) -> Result<()>

Write an ArrowLeafColumn

pub fn close(self) -> Result<ArrowColumnChunk>

Close this column returning the written ArrowColumnChunk

pub fn memory_size(&self) -> usize

Returns the estimated total memory usage by the writer.

This Self::get_estimated_total_bytes this is an estimate of the current memory usage and not it’s anticipated encoded size.

This includes:

1. Data buffered in encoded form
2. Data buffered in un-encoded form (e.g. usize dictionary keys)

This value should be greater than or equal to Self::get_estimated_total_bytes

pub fn get_estimated_total_bytes(&self) -> usize

Returns the estimated total encoded bytes for this column writer.

This includes:

1. Data buffered in encoded form
2. An estimate of how large the data buffered in un-encoded form would be once encoded

This value should be less than or equal to Self::memory_size

Trait Implementations

impl Debug for ArrowColumnWriter

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

Formats the value using the given formatter.