Struct arrow2::io::json::Reader

pub struct Reader<R: Read> { /* fields omitted */ }

JSON Reader

This JSON reader allows JSON line-delimited files to be read into the Arrow memory model. Records are loaded in batches and are then converted from row-based data to columnar data.

Example:

use std::sync::Arc;
use arrow2::datatypes::{DataType, Field, Schema};
use arrow2::io::json;
use std::fs::File;
use std::io::BufReader;

let schema = Arc::new(Schema::new(vec![
    Field::new("a", DataType::Float64, false),
    Field::new("b", DataType::Float64, false),
    Field::new("c", DataType::Float64, false),
]));

let file = File::open("test/data/basic.json").unwrap();

let mut json = json::Reader::new(BufReader::new(file), schema, 1024, None);
let batch = json.next().unwrap().unwrap();

Implementations

impl<R: Read> Reader<R>

pub fn new(
    reader: R,
    schema: Arc<Schema>,
    batch_size: usize,
    projection: Option<Vec<String>>
) -> Self

Create a new JSON Reader from any value that implements the Read trait.

If reading a File, you can customise the Reader, such as to enable schema inference, use ReaderBuilder.

pub fn from_buf_reader(
    reader: BufReader<R>,
    schema: Arc<Schema>,
    batch_size: usize,
    projection: Option<Vec<String>>
) -> Self

Create a new JSON Reader from a BufReader<R: Read>

To customize the schema, such as to enable schema inference, use ReaderBuilder

pub fn schema(&self) -> &Arc<Schema>

Returns the schema of the reader, useful for getting the schema without reading record batches

pub fn next(&mut self) -> Result<Option<RecordBatch>>

Read the next batch of records

Trait Implementations

impl<R: Debug + Read> Debug for Reader<R>

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

Formats the value using the given formatter.