/// What type of statistics should be extracted?
#[derive(Debug, Clone, Copy, PartialEq, Eq, PartialOrd, Ord, Hash)]
pub enum RequestedStatistics {
    /// Minimum Value
    Min,
    /// Maximum Value
    Max,
    /// Null Count, returned as a [`UInt64Array`])
    NullCount,
}

/// Extracts Parquet statistics as Arrow arrays
///
/// This is used to convert Parquet statistics to Arrow arrays, with proper type
/// conversions. This information can be used for pruning parquet files or row
/// groups based on the statistics embedded in parquet files
///
/// # Schemas
///
/// The schema of the parquet file and the arrow schema are used to convert the
/// underlying statistics value (stored as a parquet value) into the
/// corresponding Arrow  value. For example, Decimals are stored as binary in
/// parquet files.
///
/// The parquet_schema and arrow _schema do not have to be identical (for
/// example, the columns may be in different orders and one or the other schemas
/// may have additional columns). The function [`parquet_column`] is used to
/// match the column in the parquet file to the column in the arrow schema.
///
/// # Multiple parquet files
///
/// This API is designed to support efficiently extracting statistics from
/// multiple parquet files (hence why the parquet schema is passed in as an
/// argument). This is useful when building an index for a directory of parquet
/// files.
///
#[derive(Debug)]
pub struct StatisticsConverter<'a> {
    /// The name of the column to extract statistics for
    column_name: &'a str,
    /// The type of statistics to extract
    statistics_type: RequestedStatistics,
    /// The arrow schema of the query
    arrow_schema: &'a Schema,
    /// The field (with data type) of the column in the arrow schema
    arrow_field: &'a Field,
}

impl<'a> StatisticsConverter<'a> {
    /// Returns a [`UInt64Array`] with counts for each row group
    ///
    /// The returned array has no nulls, and has one value for each row group.
    /// Each value is the number of rows in the row group.
    pub fn row_counts(metadata: &ParquetMetaData) -> Result<UInt64Array> {
...
    }

    /// create an new statistics converter
    pub fn try_new(
        column_name: &'a str,
        statistics_type: RequestedStatistics,
        arrow_schema: &'a Schema,
    ) -> Result<Self> {
...
    }

    /// extract the statistics from a parquet file, given the parquet file's metadata
    ///
    /// The returned array contains 1 value for each row group in the parquet
    /// file in order
    ///
    /// Each value is either
    /// * the requested statistics type for the column
    /// * a null value, if the statistics can not be extracted
    ///
    /// Note that a null value does NOT mean the min or max value was actually
    /// `null` it means it the requested statistic is unknown
    ///
    /// Reasons for not being able to extract the statistics include:
    /// * the column is not present in the parquet file
    /// * statistics for the column are not present in the row group
    /// * the stored statistic value can not be converted to the requested type
    pub fn extract(&self, metadata: &ParquetMetaData) -> Result<ArrayRef> {
...
    }
}

impl<'a> StatisticsConverter<'a> {
..
/// Extract metadata from multiple parquet files into an single arrow array
/// one element per row group per file
fn extract_multi(&self, metadata: impl IntoIterator<Item = &ParquetMetadata>))-> Result<ArrayRef> {
...
}

impl<'a> StatisticsConverter<'a> {
..
/// Extract metadata from page indexes across all row groups. The returned array has one element
/// per page across all row groups
fn extract_page(&self, metadata: impl IntoIterator<Item = &ParquetMetadata>))-> Result<ArrayRef> {
...
}