fn hash_dictionary()

in datafusion/physical-expr/src/hash_utils.rs [180:208]

• 28 lines of code
• 11 McCabe index (conditional complexity)

fn hash_dictionary<K: ArrowDictionaryKeyType>(
    array: &DictionaryArray<K>,
    random_state: &RandomState,
    hashes_buffer: &mut [u64],
    multi_col: bool,
) -> Result<()> {
    // Hash each dictionary value once, and then use that computed
    // hash for each key value to avoid a potentially expensive
    // redundant hashing for large dictionary elements (e.g. strings)
    let values = Arc::clone(array.values());
    let mut dict_hashes = vec![0; values.len()];
    create_hashes(&[values], random_state, &mut dict_hashes)?;

    // combine hash for each index in values
    if multi_col {
        for (hash, key) in hashes_buffer.iter_mut().zip(array.keys().iter()) {
            if let Some(key) = key {
                *hash = combine_hashes(dict_hashes[key.as_usize()], *hash)
            } // no update for Null, consistent with other hashes
        }
    } else {
        for (hash, key) in hashes_buffer.iter_mut().zip(array.keys().iter()) {
            if let Some(key) = key {
                *hash = dict_hashes[key.as_usize()]
            } // no update for Null, consistent with other hashes
        }
    }
    Ok(())
}