Struct PageIndex 

pub struct PageIndex {
    column_indexes: Option<Vec<Vec<Option<ColumnIndexMetaData>>>>,
    offset_indexes: Option<Vec<Vec<Option<OffsetIndexMetaData>>>>,
}

Struct to encapsulate the Parquet Page Index

This struct provides a dense representation of the Page Index. It is used internally by this crate when assembling and writing the Page Index. It is also the default implementation of the PageIndexProvider contained in the ParquetMetaData.

Example: Constructing a synthetic PageIndex

This example builds a ParquetMetaData for a file with a single row group containing a single BYTE_ARRAY column with one data page, and attaches a matching PageIndex, as might be done in tests that exercise page-level statistics handling.

// Create metadata for a file with a single row group containing a
// single BYTE_ARRAY column "s" with three values
let file_metadata = FileMetaData::new(1, 3, None, None, schema, None);
let metadata = ParquetMetaData::new(file_metadata, vec![row_group]);

// Build a column index with min/max statistics for the single page
let mut column_index = ColumnIndexBuilder::new(PhysicalType::BYTE_ARRAY);
column_index.append(false, b"az".to_vec(), b"b".to_vec(), 0, None);
column_index.set_boundary_order(BoundaryOrder::ASCENDING);
let column_index = column_index.build().unwrap();

// Build an offset index recording the location of the single page
let mut offset_index = OffsetIndexBuilder::new();
offset_index.append_row_count(3);
offset_index.append_offset_and_size(4, 100);
let offset_index = offset_index.build();

// Assemble the PageIndex (one entry per row group, each with one
// entry per column) and attach it to the metadata
let mut page_index = PageIndexBuilder::new(1, 1);
page_index.put_column_index(column_index, 0, 0);
page_index.put_offset_index(offset_index, 0, 0);
let page_index = page_index.build();
let metadata = metadata
    .into_builder()
    .set_page_index(Some(Arc::new(page_index)))
    .build();
assert!(metadata.page_index().unwrap().is_complete());

Fields

column_indexes: Option<Vec<Vec<Option<ColumnIndexMetaData>>>>

offset_indexes: Option<Vec<Vec<Option<OffsetIndexMetaData>>>>

Implementations

impl PageIndex

pub(crate) fn new( column_indexes: Option<Vec<Vec<Option<ColumnIndexMetaData>>>>, offset_indexes: Option<Vec<Vec<Option<OffsetIndexMetaData>>>>, ) -> Self

pub fn into_builder(self) -> PageIndexBuilder

Convert this PageIndex into a PageIndexBuilder

pub(crate) fn column_indexes_raw( &self, ) -> Option<&Vec<Vec<Option<ColumnIndexMetaData>>>>

Returns a reference to the raw column indexes structure

This method provides access to the underlying column index data for serialization and other low-level operations.

pub(crate) fn offset_indexes_raw( &self, ) -> Option<&Vec<Vec<Option<OffsetIndexMetaData>>>>

Returns a reference to the raw offset indexes structure

This method provides access to the underlying offset index data for serialization and other low-level operations.

Trait Implementations

impl Clone for PageIndex

fn clone(&self) -> PageIndex

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for PageIndex

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

Formats the value using the given formatter.

impl From<PageIndex> for PageIndexBuilder

fn from(page_index: PageIndex) -> Self

Converts to this type from the input type.

impl HeapSize for PageIndex

fn heap_size(&self) -> usize

Return the size of any bytes allocated on the heap by this object, including heap memory in those structures

impl PageIndexProvider for PageIndex

fn has_offset_indexes(&self) -> bool

Returns true if offset index structures are available via this provider

fn has_column_indexes(&self) -> bool

Returns true if column index structures are available via this provider

fn column_index( &self, row_group_idx: usize, column_idx: usize, ) -> Option<&ColumnIndexMetaData>

Returns the column index for a specific row group and column

fn offset_index( &self, row_group_idx: usize, column_idx: usize, ) -> Option<&OffsetIndexMetaData>

Returns the offset index for a specific row group and column

fn as_any(&self) -> &dyn Any

Returns a reference to the trait object as &dyn Any for downcasting

fn is_complete(&self) -> bool

Returns true if both the offset and column index structures are present

fn num_data_pages( &self, row_group_idx: usize, column_idx: usize, ) -> Option<usize>

Returns the expected number of data pages for a specific column chunk

fn page_locations( &self, row_group_idx: usize, column_idx: usize, ) -> Option<&Vec<PageLocation>>

Returns the physical locations of all data pages in a column chunk

impl PartialEq for PageIndex

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

Equality operator ==.

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

Inequality operator !=.

impl StructuralPartialEq for PageIndex