ariesdevil commented on code in PR #146:
URL: https://github.com/apache/datasketches-rust/pull/146#discussion_r3558637431
##########
datasketches/src/theta/hash_table.rs:
##########
@@ -38,130 +32,26 @@ const STRIDE_MASK: u64 = (1 << STRIDE_HASH_BITS) - 1;
/// * After it reaches the capacity bigger than 2^lg_nom_size, every time the
number of entries
/// exceeds the threshold, it will rebuild the table: only keep the min
2^lg_nom_size entries and
/// update the theta to the k-th smallest entry.
-#[derive(Debug)]
-pub(super) struct ThetaHashTable {
- lg_cur_size: u8,
- lg_nom_size: u8,
- lg_max_size: u8,
- resize_factor: ResizeFactor,
- sampling_probability: f32,
- hash_seed: u64,
-
- // Logical emptiness of the source set.
- //
- // * `false` if any update has been attempted (even if screened by theta)
- // * `true` if no updates have been attempted.
- //
- // This can be false even when `num_retained` is 0.
- is_empty: bool,
-
- theta: u64,
-
- entries: Vec<u64>,
-
- // Number of retained non-zero hashes currently stored in `entries`.
- num_retained: usize,
-}
-
-impl ThetaHashTable {
- /// Create a new hash table
- pub fn new(
- lg_nom_size: u8,
- resize_factor: ResizeFactor,
- sampling_probability: f32,
- hash_seed: u64,
- ) -> Self {
- let lg_max_size = lg_nom_size + 1;
- let lg_cur_size = starting_sub_multiple(lg_max_size, MIN_LG_K,
resize_factor.lg_value());
- Self::from_raw_parts(
- lg_cur_size,
- lg_nom_size,
- resize_factor,
- sampling_probability,
- starting_theta_from_sampling_probability(sampling_probability),
- hash_seed,
- true,
- )
- }
+pub(super) type ThetaHashTable = RawHashTable<ThetaEntry>;
- /// Constructs a table from raw internal state.
- ///
- /// # Panics
- ///
- /// Panics if `lg_cur_size > lg_nom_size + 1`. (`lg_nom_size + 1 ==
lg_max_size`)
- pub fn from_raw_parts(
- lg_cur_size: u8,
- lg_nom_size: u8,
- resize_factor: ResizeFactor,
- sampling_probability: f32,
- theta: u64,
- hash_seed: u64,
- is_empty: bool,
- ) -> Self {
- let lg_max_size = lg_nom_size + 1;
- assert!(
- lg_cur_size <= lg_max_size,
- "lg_cur_size must be <= lg_nom_size + 1, got
lg_cur_size={lg_cur_size}, lg_nom_size={lg_nom_size}"
- );
- let size = if lg_cur_size > 0 { 1 << lg_cur_size } else { 0 };
- let entries = vec![0u64; size];
- Self {
- lg_cur_size,
- lg_nom_size,
- lg_max_size,
- resize_factor,
- sampling_probability,
- hash_seed,
- is_empty,
- theta,
- entries,
- num_retained: 0,
- }
- }
+#[derive(Debug, Clone, Copy)]
+pub(crate) struct ThetaEntry {
+ hash: NonZeroU64,
+}
- /// Hash a value with the table seed and return the hash.
- fn hash<T: Hash>(&self, value: T) -> u64 {
- let mut hasher = MurmurHash3X64128::with_seed(self.hash_seed);
- value.hash(&mut hasher);
- let (h1, _) = hasher.finish128();
- h1 >> 1 // To make it compatible with Java version
+impl ThetaEntry {
+ fn new(hash: u64) -> Option<Self> {
Review Comment:
Nice catch, fixed.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
