kmerutils 0.0.14

Kmer counting, hashing, sequence sketching
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
104
105
106
107
108
109
110
111
112
113

//! Basic stuff about hashed items

use std::cmp::Ordering;
use std::marker::PhantomData;

/// We use maximum size to store hash value but with invertible 32 hash
/// the value stored is in fact a u32.
/// We would like to template over item hash but Hasher has u64 as arrival type
pub type ItemHash = u64;

// If we use an inversible hash we do not need to keep item (the kmer)
// for other hash  we need copying and storing of Kmer... whence the Option<T> field

/// A HashedItem is a hashed item and possibly the associated object (of type T) if
/// we want to keep track of objects contributiong to minhash signature.
/// Note that using invertible hash if objects hashes
/// are stored in a u32 or a u64 (as in some Kmer representation) we can retrive objects
/// from hashed value. (See module invhash)
#[derive(Debug, Clone, Copy)]
pub struct HashedItem<T: Clone + Copy> {
    pub(crate) hash: ItemHash,
    //
    #[allow(unused)]
    pub(crate) item: Option<T>,
}

impl<T: Clone + Copy> PartialEq for HashedItem<T> {
    fn eq(&self, other: &HashedItem<T>) -> bool {
        other.hash.eq(&self.hash)
    }
}

impl<T: Clone + Copy> Eq for HashedItem<T> {}

impl<T: Clone + Copy> Ord for HashedItem<T> {
    fn cmp(&self, other: &HashedItem<T>) -> Ordering {
        self.hash.cmp(&other.hash)
    }
}

impl<T: Clone + Copy> PartialOrd for HashedItem<T> {
    fn partial_cmp(&self, other: &HashedItem<T>) -> Option<Ordering> {
        Some(self.hash.cmp(&other.hash))
    }
}

// size is 2*8+2 bytes !!
/// to store count of object
#[derive(Clone, Debug, Eq, PartialEq)]
pub struct HashCount<T: Clone + Copy> {
    pub hashed: HashedItem<T>,
    pub count: u16,
}

//===================   For items hashed by invertible hash

/// possibly something can be hashed with some inversible hash so we do not need to store the original item
#[derive(Debug, Clone)]
pub struct InvHashedItem<T: Clone + Copy> {
    pub(crate) hash: ItemHash,
    pub(crate) t_marker: PhantomData<T>,
}

impl<T: Clone + Copy> InvHashedItem<T> {
    pub fn new(hash: ItemHash) -> Self {
        InvHashedItem {
            hash,
            t_marker: PhantomData,
        }
    }
    pub fn get_hash(&self) -> ItemHash {
        self.hash
    } // end of get impl
} // end of impl InvHashedItem

impl<T: Copy + Clone> PartialEq for InvHashedItem<T> {
    fn eq(&self, other: &InvHashedItem<T>) -> bool {
        other.hash.eq(&self.hash)
    }
}

impl<T: Copy + Clone> Eq for InvHashedItem<T> {}

impl<T: Clone + Copy> Ord for InvHashedItem<T> {
    fn cmp(&self, other: &InvHashedItem<T>) -> Ordering {
        self.hash.cmp(&other.hash)
    }
}

impl<T: Clone + Copy> PartialOrd for InvHashedItem<T> {
    fn partial_cmp(&self, other: &InvHashedItem<T>) -> Option<Ordering> {
        Some(self.hash.cmp(&other.hash))
    }
}

//====================================================================================//

/// To count occurences of an inversible hashed objects
// size is 8 + 1 bytes !!
#[derive(Clone, Debug, Eq, PartialEq)]
pub struct InvHashCount<T: Clone + Copy> {
    pub hashed: InvHashedItem<T>,
    pub(crate) count: u8,
}

impl<T: Clone + Copy> InvHashCount<T> {
    pub fn new(hashed: InvHashedItem<T>, count: u8) -> Self {
        InvHashCount { hashed, count }
    }
    pub fn get_count(&self) -> u8 {
        self.count
    }
} // end of impl block for InvHashCount