datasketches 0.6.0

A software library of stochastic streaming algorithms (a.k.a. sketches)
Documentation 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103

// Licensed to the Apache Software Foundation (ASF) under one
// or more contributor license agreements.  See the NOTICE file
// distributed with this work for additional information
// regarding copyright ownership.  The ASF licenses this file
// to you under the Apache License, Version 2.0 (the
// "License"); you may not use this file except in compliance
// with the License.  You may obtain a copy of the License at
//
//   http://www.apache.org/licenses/LICENSE-2.0
//
// Unless required by applicable law or agreed to in writing,
// software distributed under the License is distributed on an
// "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
// KIND, either express or implied.  See the License for the
// specific language governing permissions and limitations
// under the License.

//! Hashing support for sketches.

pub mod value;

#[cfg(any(
    feature = "countmin",
    feature = "cpc",
    feature = "frequencies",
    feature = "hll",
    feature = "theta",
    feature = "tuple",
))]
mod murmurhash;
#[cfg(any(
    feature = "countmin",
    feature = "cpc",
    feature = "frequencies",
    feature = "hll",
    feature = "theta",
    feature = "tuple",
))]
pub(crate) use self::murmurhash::*;

#[cfg(feature = "bloom")]
mod xxhash;
#[cfg(feature = "bloom")]
pub(crate) use self::xxhash::*;

#[cfg(any(
    feature = "countmin",
    feature = "cpc",
    feature = "theta",
    feature = "tuple",
))]
mod seed;
#[cfg(any(
    feature = "countmin",
    feature = "cpc",
    feature = "theta",
    feature = "tuple",
))]
pub(crate) use self::seed::*;

/// The seed 9001 used in the sketch update methods is a prime number that was chosen very early
/// on in experimental testing.
///
/// Choosing a seed is somewhat arbitrary, and the author cannot prove that this particular seed
/// is somehow superior to other seeds. There was some early Internet discussion that a seed of 0
/// did not produce as clean avalanche diagrams as non-zero seeds, but this may have been more
/// related to the MurmurHash2 release, which did have some issues. As far as the author can
/// determine, MurmurHash3 does not have these problems.
///
/// In order to perform set operations on two sketches it is critical that the same hash function
/// and seed are identical for both sketches, otherwise the assumed 1:1 relationship between the
/// original source key value and the hashed bit string would be violated. Once you have developed
/// a history of stored sketches you are stuck with it.
#[cfg(any(
    feature = "bloom",
    feature = "countmin",
    feature = "cpc",
    feature = "frequencies",
    feature = "hll",
    feature = "theta",
    feature = "tuple",
))]
pub(crate) const DEFAULT_UPDATE_SEED: u64 = 9001;

#[cfg(feature = "bloom")]
#[inline(always)]
fn read_u32_le(bytes: &[u8]) -> u32 {
    u32::from_le_bytes(bytes.try_into().expect("four-byte hash input"))
}

#[cfg(any(
    feature = "bloom",
    feature = "countmin",
    feature = "cpc",
    feature = "frequencies",
    feature = "hll",
    feature = "theta",
    feature = "tuple",
))]
#[inline(always)]
fn read_u64_le(bytes: &[u8]) -> u64 {
    u64::from_le_bytes(bytes.try_into().expect("eight-byte hash input"))
}