Struct lance_core::datatypes::Schema

pub struct Schema {
    pub fields: Vec<Field>,
    pub metadata: HashMap<String, String>,
}

Lance Schema.

Fields

fields: Vec<Field>

Top-level fields in the dataset.

metadata: HashMap<String, String>

Metadata of the schema

Implementations

impl Schema

pub fn compare_with_options( &self, expected: &Self, options: &SchemaCompareOptions, ) -> bool

pub fn explain_difference( &self, expected: &Self, options: &SchemaCompareOptions, ) -> Option<String>

pub fn has_dictionary_types(&self) -> bool

pub fn check_compatible( &self, expected: &Self, options: &SchemaCompareOptions, ) -> Result<()>

pub fn project<T: AsRef<str>>(&self, columns: &[T]) -> Result<Self>

Project the columns over the schema.

let schema = Schema::from(...);
let projected = schema.project(&["col1", "col2.sub_col3.field4"])?;

pub fn validate(&self) -> Result<()>

Check that the top level fields don’t contain . in their names to distinguish from nested fields.

pub fn intersection(&self, other: &Self) -> Result<Self>

Intersection between two Schema.

pub fn fields_pre_order(&self) -> impl Iterator<Item = &Field>

Iterates over the fields using a pre-order traversal

This is a DFS traversal where the parent is visited before its children

pub fn project_by_ids(&self, column_ids: &[i32]) -> Self

Returns a new schema that only contains the fields in column_ids.

This projection can filter out both top-level and nested fields

pub fn project_by_schema<S: TryInto<Self, Error = Error>>( &self, projection: S, ) -> Result<Self>

Project the schema by another schema, and preserves field metadata, i.e., Field IDs.

Parameters

• projection: The schema to project by. Can be arrow_schema::Schema or Schema.

pub fn exclude<T: TryInto<Self> + Debug>(&self, schema: T) -> Result<Self>

Exclude the fields from other Schema, and returns a new Schema.

pub fn field(&self, name: &str) -> Option<&Field>

Get a field by name. Return None if the field does not exist.

pub fn field_id(&self, column: &str) -> Result<i32>

pub fn top_level_field_ids(&self) -> Vec<i32>

pub fn field_ids(&self) -> Vec<i32>

pub fn field_by_id(&self, id: impl Into<i32>) -> Option<&Field>

Get field by its id.

pub fn field_ancestry_by_id(&self, id: i32) -> Option<Vec<&Field>>

Get the sequence of fields from the root to the field with the given id.

pub fn mut_field_by_id(&mut self, id: impl Into<i32>) -> Option<&mut Field>

pub fn max_field_id(&self) -> Option<i32>

Get the maximum field id in the schema.

Note: When working with Datasets, you should prefer [Manifest::max_field_id()] over this method. This method does not take into account the field IDs of dropped fields.

pub fn set_dictionary(&mut self, batch: &RecordBatch) -> Result<()>

Recursively attach set up dictionary values to the dictionary fields.

pub fn set_field_id(&mut self, max_existing_id: Option<i32>)

Walk through the fields and assign a new field id to each field that does not have one (e.g. is set to -1)

If this schema is on an existing dataset, pass the result of Manifest::max_field_id to max_existing_id. If for some reason that id is lower than the maximum field id in this schema, the field IDs will be reassigned starting from the maximum field id in this schema.

If this schema is not associated with a dataset, pass None to max_existing_id. This is the same as passing Self::max_field_id().

pub fn extend(&mut self, fields: &[ArrowField]) -> Result<()>

Create a new schema by adding fields to the end of this schema

pub fn merge<S: TryInto<Self, Error = Error>>(&self, other: S) -> Result<Self>

Merge this schema from the other schema.

After merging, the field IDs from other schema will be reassigned, following the fields in self.

Trait Implementations

impl Clone for Schema

fn clone(&self) -> Schema

Returns a copy of the value.

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

Performs copy-assignment from source.

impl Debug for Schema

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

Formats the value using the given formatter.

impl DeepSizeOf for Schema

fn deep_size_of_children(&self, context: &mut Context) -> usize

Returns an estimation of the heap-managed storage of this object. This does not include the size of the object itself.

fn deep_size_of(&self) -> usize

Returns an estimation of a total size of memory owned by the object, including heap-managed storage.

impl Default for Schema

fn default() -> Schema

Returns the “default value” for a type.

impl Display for Schema

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

Formats the value using the given formatter.

impl From<&Schema> for Schema

Convert Lance Schema to Arrow Schema

fn from(schema: &Schema) -> Self

Converts to this type from the input type.

impl PartialEq for Schema

fn eq(&self, other: &Self) -> 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 TryFrom<&Schema> for Schema

Convert arrow2::datatype::Schema to Lance

type Error = Error

The type returned in the event of a conversion error.

fn try_from(schema: &ArrowSchema) -> Result<Self>

Performs the conversion.

impl TryFrom<&Schema> for Schema

Make API cleaner to accept both Schema and Arrow Schema.

type Error = Error

The type returned in the event of a conversion error.

fn try_from(schema: &Self) -> Result<Self>

Performs the conversion.