Struct PagesPruningStatistics 

struct PagesPruningStatistics<'a> {
    row_group_index: usize,
    row_group_metadatas: &'a [RowGroupMetaData],
    converter: StatisticsConverter<'a>,
    column_index: &'a ParquetColumnIndex,
    offset_index: &'a ParquetOffsetIndex,
    page_offsets: &'a Vec<PageLocation>,
}

Implement PruningStatistics for one column’s PageIndex (column_index + offset_index)

Fields

row_group_index: usize

row_group_metadatas: &'a [RowGroupMetaData]

converter: StatisticsConverter<'a>

column_index: &'a ParquetColumnIndex

offset_index: &'a ParquetOffsetIndex

page_offsets: &'a Vec<PageLocation>

Implementations

impl<'a> PagesPruningStatistics<'a>

fn try_new( row_group_index: usize, converter: StatisticsConverter<'a>, parquet_metadata: &'a ParquetMetaData, ) -> Option<Self>

Creates a new PagesPruningStatistics for a column in a row group, if possible.

Returns None if the parquet_metadata does not have sufficient information to create the statistics.

fn page_row_counts(&self) -> Option<Vec<usize>>

return the row counts in each data page, if possible.

Trait Implementations

impl<'a> Debug for PagesPruningStatistics<'a>

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

Formats the value using the given formatter.

impl PruningStatistics for PagesPruningStatistics<'_>

fn min_values(&self, _column: &Column) -> Option<ArrayRef>

Return the minimum values for the named column, if known.

fn max_values(&self, _column: &Column) -> Option<ArrayRef>

Return the maximum values for the named column, if known.

fn num_containers(&self) -> usize

Return the number of containers (e.g. Row Groups) being pruned with these statistics.

fn null_counts(&self, _column: &Column) -> Option<ArrayRef>

Return the number of null values for the named column as an UInt64Array

fn row_counts(&self, _column: &Column) -> Option<ArrayRef>

Return the number of rows for the named column in each container as an UInt64Array.

fn contained( &self, _column: &Column, _values: &HashSet<ScalarValue>, ) -> Option<BooleanArray>

Returns [BooleanArray] where each row represents information known about specific literal values in a column.