Struct bio::alphabets::Alphabet

source ·

pub struct Alphabet {
    pub symbols: BitSet,
}

Expand description

Representation of an alphabet.

Fields§

§symbols: BitSet

Implementations§

source §

impl Alphabet

source

pub fn new<C, T>(symbols: T) -> Selfwhere C: Borrow<u8>, T: IntoIterator<Item = C>,

Create new alphabet from given symbols.

Complexity: O(n), where n is the number of symbols in the alphabet.

Example

use bio::alphabets;

// Create an alphabet (note that a DNA alphabet is already available in bio::alphabets::dna).
let dna_alphabet = alphabets::Alphabet::new(b"ACGTacgt");
// Check whether a given text is a word over the alphabet.
assert!(dna_alphabet.is_word(b"GAttACA"));

source

pub fn insert(&mut self, a: u8)

Insert symbol into alphabet.

Complexity: O(1)

Example

use bio::alphabets;

let mut dna_alphabet = alphabets::Alphabet::new(b"ACGTacgt");
assert!(!dna_alphabet.is_word(b"N"));
dna_alphabet.insert(78);
assert!(dna_alphabet.is_word(b"N"));

source

pub fn is_word<C, T>(&self, text: T) -> boolwhere C: Borrow<u8>, T: IntoIterator<Item = C>,

Check if given text is a word over the alphabet.

Complexity: O(n), where n is the length of the text.

Example

use bio::alphabets;

let dna_alphabet = alphabets::Alphabet::new(b"ACGTacgt");
assert!(dna_alphabet.is_word(b"GAttACA"));
assert!(!dna_alphabet.is_word(b"42"));

source

pub fn max_symbol(&self) -> Option<u8>

Return lexicographically maximal symbol.

Complexity: O(n), where n is the number of symbols in the alphabet.

Example

use bio::alphabets;

let dna_alphabet = alphabets::Alphabet::new(b"acgtACGT");
assert_eq!(dna_alphabet.max_symbol(), Some(116)); // max symbol is "t"
let empty_alphabet = alphabets::Alphabet::new(b"");
assert_eq!(empty_alphabet.max_symbol(), None);

source

pub fn len(&self) -> usize

Return size of the alphabet.

Upper and lower case representations of the same character are counted as distinct characters.

Complexity: O(n), where n is the number of symbols in the alphabet.

Example

use bio::alphabets;

let dna_alphabet = alphabets::Alphabet::new(b"acgtACGT");
assert_eq!(dna_alphabet.len(), 8);

source

pub fn is_empty(&self) -> bool

Is this alphabet empty?

Complexity: O(n), where n is the number of symbols in the alphabet.

Example

use bio::alphabets;

let dna_alphabet = alphabets::Alphabet::new(b"acgtACGT");
assert!(!dna_alphabet.is_empty());
let empty_alphabet = alphabets::Alphabet::new(b"");
assert!(empty_alphabet.is_empty());

source

pub fn intersection(&self, other: &Alphabet) -> Self

Return a new alphabet taking the intersect between this and other.

Example

use bio::alphabets;

let alpha_a = alphabets::Alphabet::new(b"acgtACGT");
let alpha_b = alphabets::Alphabet::new(b"atcgMVP");
let intersect_alpha = alpha_a.intersection(&alpha_b);

assert_eq!(intersect_alpha, alphabets::Alphabet::new(b"atcg"));

source

pub fn difference(&self, other: &Alphabet) -> Self

Return a new alphabet taking the difference between this and other.

Example

use bio::alphabets;

let dna_alphabet = alphabets::Alphabet::new(b"acgtACGT");
let dna_alphabet_upper = alphabets::Alphabet::new(b"ACGT");
let dna_lower = dna_alphabet.difference(&dna_alphabet_upper);

assert_eq!(dna_lower, alphabets::Alphabet::new(b"atcg"));

source

pub fn union(&self, other: &Alphabet) -> Self

Return a new alphabet taking the union between this and other.

Example

use bio::alphabets;

let dna_alphabet = alphabets::Alphabet::new(b"ATCG");
let tokenize_alpha = alphabets::Alphabet::new(b"?|");
let alpha = dna_alphabet.union(&tokenize_alpha);

assert_eq!(alpha, alphabets::Alphabet::new(b"ATCG?|"));