Struct datafusion::execution::options::CsvReadOptions

pub struct CsvReadOptions<'a> {
    pub has_header: bool,
    pub delimiter: u8,
    pub schema: Option<&'a Schema>,
    pub schema_infer_max_records: usize,
    pub file_extension: &'a str,
    pub table_partition_cols: Vec<(String, DataType)>,
    pub file_compression_type: FileCompressionType,
}

Options that control the reading of CSV files.

Note this structure is supplied when a datasource is created and can not not vary from statement to statement. For settings that can vary statement to statement see ConfigOptions.

Fields

has_header: bool

Does the CSV file have a header?

If schema inference is run on a file with no headers, default column names are created.

delimiter: u8

An optional column delimiter. Defaults to b','.

schema: Option<&'a Schema>

An optional schema representing the CSV files. If None, CSV reader will try to infer it based on data in file.

schema_infer_max_records: usize

Max number of rows to read from CSV files for schema inference if needed. Defaults to DEFAULT_SCHEMA_INFER_MAX_RECORD.

file_extension: &'a str

File extension; only files with this extension are selected for data input. Defaults to FileType::CSV.get_ext().as_str().

table_partition_cols: Vec<(String, DataType)>

Partition Columns

file_compression_type: FileCompressionType

File compression type

Implementations

impl<'a> CsvReadOptions<'a>

pub fn new() -> Self

Create a CSV read option with default presets

pub fn has_header(self, has_header: bool) -> Self

Configure has_header setting

pub fn delimiter(self, delimiter: u8) -> Self

Specify delimiter to use for CSV read

pub fn file_extension(self, file_extension: &'a str) -> Self

Specify the file extension for CSV file selection

pub fn delimiter_option(self, delimiter: Option<u8>) -> Self

Configure delimiter setting with Option, None value will be ignored

pub fn schema(self, schema: &'a Schema) -> Self

Specify schema to use for CSV read

pub fn table_partition_cols(
    self,
    table_partition_cols: Vec<(String, DataType)>
) -> Self

Specify table_partition_cols for partition pruning

pub fn schema_infer_max_records(self, max_records: usize) -> Self

Configure number of max records to read for schema inference

pub fn file_compression_type(
    self,
    file_compression_type: FileCompressionType
) -> Self

Configure file compression type

pub fn to_listing_options(&self, target_partitions: usize) -> ListingOptions

Helper to convert these user facing options to ListingTable options

Trait Implementations

impl<'a> Clone for CsvReadOptions<'a>

fn clone(&self) -> CsvReadOptions<'a>

Returns a copy of the value.

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

Performs copy-assignment from source.

impl<'a> Default for CsvReadOptions<'a>

fn default() -> Self

Returns the “default value” for a type.