Struct FileLoadingConfig 

pub struct FileLoadingConfig {

    pub delimiter: Option<u8>,
    pub has_header: Option<bool>,
    pub skip_lines: Option<usize>,
    pub skip_rows: Option<usize>,
    pub skip_tail_rows: Option<usize>,
    pub parse_dates: Option<bool>,
    pub decompress_in_memory: Option<bool>,
    pub temp_dir: Option<String>,
    pub single_spine_schema: Option<bool>,
    pub null_values: Option<Vec<String>>,
    pub parse_strings: Option<bool>,
    pub parse_strings_sample_rows: Option<usize>,
    pub infer_schema_length: Option<usize>,
    pub ignore_errors: Option<bool>,
}

Fields

delimiter: Option<u8>

has_header: Option<bool>

skip_lines: Option<usize>

skip_rows: Option<usize>

skip_tail_rows: Option<usize>

Skip this many rows at the end of the file (e.g. vendor footer or trailing garbage). CSV only.

parse_dates: Option<bool>

When true, CSV reader tries to parse string columns as dates (YYYY-MM-DD, ISO datetime). Default: true.

decompress_in_memory: Option<bool>

When true, decompress compressed CSV into memory (eager read). When false (default), decompress to a temp file and use lazy scan.

temp_dir: Option<String>

Directory for decompression temp files. null = system default (e.g. TMPDIR).

single_spine_schema: Option<bool>

When true (default), infer Hive/partitioned Parquet schema from one file (single-spine) for faster “Caching schema”. When false, use Polars collect_schema() over all files.

null_values: Option<Vec<String>>

CSV null values: list of strings. Plain string = treat as null in all columns; “COL=VAL” = treat VAL as null only in column COL (first “=” separates). Example: [“NA”, “amount=”].

parse_strings: Option<bool>

When false, disable parse-strings for CSV. When true or unset, trim and parse all CSV string columns (default). Use CLI –parse-strings=COL for specific columns, –no-parse-strings to disable.

parse_strings_sample_rows: Option<usize>

Number of rows to sample for parse_strings type inference (single file or multiple/partitioned). Default 1000.

infer_schema_length: Option<usize>

Number of rows to use when inferring CSV schema. null = use default (1000 in datui). Larger values reduce risk of wrong type (e.g. int then N/A).

ignore_errors: Option<bool>

When true, CSV reader ignores parse errors and continues with the next batch. Default false.

Implementations

impl FileLoadingConfig

pub fn merge(&mut self, other: Self)

Trait Implementations

impl Clone for FileLoadingConfig

fn clone(&self) -> FileLoadingConfig

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for FileLoadingConfig

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

Formats the value using the given formatter.

impl Default for FileLoadingConfig

fn default() -> FileLoadingConfig

Returns the “default value” for a type.

impl<'de> Deserialize<'de> for FileLoadingConfig

where FileLoadingConfig: Default,

fn deserialize<__D>(__deserializer: __D) -> Result<Self, __D::Error>

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Serialize for FileLoadingConfig

fn serialize<__S>(&self, __serializer: __S) -> Result<__S::Ok, __S::Error>

where __S: Serializer,

Serialize this value into the given Serde serializer.