Struct DataFileV1

pub struct DataFileV1 {

    pub file_path: String,
    pub file_format: FileFormat,
    pub partition: Struct,
    pub record_count: i64,
    pub file_size_in_bytes: i64,
    pub block_size_in_bytes: i64,
    pub file_ordinal: Option<i32>,
    pub sort_columns: Option<Vec<i32>>,
    pub column_sizes: Option<AvroMap<i64>>,
    pub value_counts: Option<AvroMap<i64>>,
    pub null_value_counts: Option<AvroMap<i64>>,
    pub nan_value_counts: Option<AvroMap<i64>>,
    pub lower_bounds: Option<AvroMap<ByteBuf>>,
    pub upper_bounds: Option<AvroMap<ByteBuf>>,
    pub key_metadata: Option<ByteBuf>,
    pub split_offsets: Option<Vec<i64>>,
    pub sort_order_id: Option<i32>,
}

DataFile found in Manifest.

Fields

file_path: String

Full URI for the file with a FS scheme.

file_format: FileFormat

String file format name, avro, orc or parquet

partition: Struct

Partition data tuple, schema based on the partition spec output using partition field ids for the struct field ids

record_count: i64

Number of records in this file

file_size_in_bytes: i64

Total file size in bytes

block_size_in_bytes: i64

Block size

file_ordinal: Option<i32>

File ordinal

sort_columns: Option<Vec<i32>>

Columns to sort

column_sizes: Option<AvroMap<i64>>

Map from column id to total size on disk

value_counts: Option<AvroMap<i64>>

Map from column id to number of values in the column (including null and NaN values)

null_value_counts: Option<AvroMap<i64>>

Map from column id to number of null values

nan_value_counts: Option<AvroMap<i64>>

Map from column id to number of NaN values

lower_bounds: Option<AvroMap<ByteBuf>>

Map from column id to lower bound in the column

upper_bounds: Option<AvroMap<ByteBuf>>

Map from column id to upper bound in the column

key_metadata: Option<ByteBuf>

Implementation specific key metadata for encryption

split_offsets: Option<Vec<i64>>

Split offsets for the data file.

sort_order_id: Option<i32>

ID representing sort order for this file

Implementations

impl DataFileV1

pub fn schema(partition_schema: &str) -> String

Get schema

Trait Implementations

impl Clone for DataFileV1

fn clone(&self) -> DataFileV1

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for DataFileV1

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

Formats the value using the given formatter.

impl<'de> Deserialize<'de> for DataFileV1

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

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl From<DataFile> for DataFileV1

fn from(value: DataFile) -> Self

Converts to this type from the input type.

impl From<DataFileV1> for DataFileV2

fn from(v1: DataFileV1) -> Self

Converts to this type from the input type.

impl PartialEq for DataFileV1

fn eq(&self, other: &DataFileV1) -> bool

Tests for self and other values to be equal, and is used by ==.

fn ne(&self, other: &Rhs) -> bool

Tests for !=. The default implementation is almost always sufficient, and should not be overridden without very good reason.

impl Serialize for DataFileV1

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

where __S: Serializer,

Serialize this value into the given Serde serializer.

impl StructuralPartialEq for DataFileV1