Struct ReaderBuilder

pub struct ReaderBuilder { /* private fields */ }

CSV file reader builder

Implementations

impl ReaderBuilder

pub fn new(schema: Arc<Schema>) -> ReaderBuilder

Create a new builder for configuring CSV parsing options.

To convert a builder into a reader, call ReaderBuilder::build

Example

let mut file = File::open("test/data/uk_cities_with_headers.csv").unwrap();
// Infer the schema with the first 100 records
let (schema, _) = Format::default().infer_schema(&mut file, Some(100)).unwrap();
file.rewind().unwrap();

// create a builder
ReaderBuilder::new(Arc::new(schema)).build(file).unwrap();

pub fn with_header(self, has_header: bool) -> ReaderBuilder

Set whether the CSV file has a header

pub fn with_format(self, format: Format) -> ReaderBuilder

Overrides the Format of this ReaderBuilder

pub fn with_delimiter(self, delimiter: u8) -> ReaderBuilder

Set the CSV file’s column delimiter as a byte character

pub fn with_escape(self, escape: u8) -> ReaderBuilder

Set the given character as the CSV file’s escape character

pub fn with_quote(self, quote: u8) -> ReaderBuilder

Set the given character as the CSV file’s quote character, by default it is double quote

pub fn with_terminator(self, terminator: u8) -> ReaderBuilder

Provide a custom terminator character, defaults to CRLF

pub fn with_comment(self, comment: u8) -> ReaderBuilder

Provide a comment character, lines starting with this character will be ignored

pub fn with_null_regex(self, null_regex: Regex) -> ReaderBuilder

Provide a regex to match null values, defaults to ^$

pub fn with_batch_size(self, batch_size: usize) -> ReaderBuilder

Set the batch size (number of records to load at one time)

pub fn with_bounds(self, start: usize, end: usize) -> ReaderBuilder

Set the bounds over which to scan the reader. start and end are line numbers.

pub fn with_projection(self, projection: Vec<usize>) -> ReaderBuilder

Set the reader’s column projection

pub fn with_truncated_rows(self, allow: bool) -> ReaderBuilder

Whether to allow truncated rows when parsing.

By default this is set to false and will error if the CSV rows have different lengths. When set to true then it will allow records with less than the expected number of columns and fill the missing columns with nulls. If the record’s schema is not nullable, then it will still return an error.

pub fn build<R>(self, reader: R) -> Result<BufReader<BufReader<R>>, ArrowError>

where R: Read,

Create a new Reader from a non-buffered reader

If R: BufRead consider using Self::build_buffered to avoid unnecessary additional buffering, as internally this method wraps reader in std::io::BufReader

pub fn build_buffered<R>(self, reader: R) -> Result<BufReader<R>, ArrowError>

where R: BufRead,

Create a new BufReader from a buffered reader

pub fn build_decoder(self) -> Decoder

Builds a decoder that can be used to decode CSV from an arbitrary byte stream

Trait Implementations

impl Debug for ReaderBuilder

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

Formats the value using the given formatter.