Trait StringZilla

pub trait StringZilla<'a, N>
where
    N: AsRef<[u8]> + 'a,
{
    // Required methods
    fn sz_find(&self, needle: N) -> Option<usize> ;
    fn sz_rfind(&self, needle: N) -> Option<usize> ;
    fn sz_find_char_from(&self, needles: N) -> Option<usize> ;
    fn sz_rfind_char_from(&self, needles: N) -> Option<usize> ;
    fn sz_find_char_not_from(&self, needles: N) -> Option<usize> ;
    fn sz_rfind_char_not_from(&self, needles: N) -> Option<usize> ;
    fn sz_edit_distance(&self, other: N) -> usize;
    fn sz_alignment_score(
        &self,
        other: N,
        matrix: [[i8; 256]; 256],
        gap: i8,
    ) -> isize;
    fn sz_matches(&'a self, needle: &'a N) -> RangeMatches<'a> ;
    fn sz_rmatches(&'a self, needle: &'a N) -> RangeRMatches<'a> ;
    fn sz_splits(&'a self, needle: &'a N) -> RangeSplits<'a> ;
    fn sz_rsplits(&'a self, needle: &'a N) -> RangeRSplits<'a> ;
    fn sz_find_first_of(&'a self, needles: &'a N) -> RangeMatches<'a> ;
    fn sz_find_last_of(&'a self, needles: &'a N) -> RangeRMatches<'a> ;
    fn sz_find_first_not_of(&'a self, needles: &'a N) -> RangeMatches<'a> ;
    fn sz_find_last_not_of(&'a self, needles: &'a N) -> RangeRMatches<'a> ;
}

Available on crate feature dep_stringzilla only.

Provides extensions for string searching and manipulation functionalities on types that can reference byte slices (u8). This trait extends the capability of any type implementing AsRef<[u8]>, allowing easy integration of SIMD-accelerated string processing functions.

Examples

Basic usage on a Vec<u8>:

use stringzilla::StringZilla;

let haystack: &[u8] = &[b'a', b'b', b'c', b'd', b'e'];
let needle: &[u8] = &[b'c', b'd'];

assert_eq!(haystack.sz_find(needle.as_ref()), Some(2));

Searching in a string slice:

use stringzilla::StringZilla;

let haystack = "abcdef";
let needle = "cd";

assert_eq!(haystack.sz_find(needle.as_bytes()), Some(2));

Required Methods

fn sz_find(&self, needle: N) -> Option<usize>

Searches for the first occurrence of needle in self.

Examples

use stringzilla::StringZilla;

let haystack = "Hello, world!";
assert_eq!(haystack.sz_find("world".as_bytes()), Some(7));

fn sz_rfind(&self, needle: N) -> Option<usize>

Searches for the last occurrence of needle in self.

Examples

use stringzilla::StringZilla;

let haystack = "Hello, world, world!";
assert_eq!(haystack.sz_rfind("world".as_bytes()), Some(14));

fn sz_find_char_from(&self, needles: N) -> Option<usize>

Finds the index of the first character in self that is also present in needles.

Examples

use stringzilla::StringZilla;

let haystack = "Hello, world!";
assert_eq!(haystack.sz_find_char_from("aeiou".as_bytes()), Some(1));

fn sz_rfind_char_from(&self, needles: N) -> Option<usize>

Finds the index of the last character in self that is also present in needles.

Examples

use stringzilla::StringZilla;

let haystack = "Hello, world!";
assert_eq!(haystack.sz_rfind_char_from("aeiou".as_bytes()), Some(8));

fn sz_find_char_not_from(&self, needles: N) -> Option<usize>

Finds the index of the first character in self that is not present in needles.

Examples

use stringzilla::StringZilla;

let haystack = "Hello, world!";
assert_eq!(haystack.sz_find_char_not_from("aeiou".as_bytes()), Some(0));

fn sz_rfind_char_not_from(&self, needles: N) -> Option<usize>

Finds the index of the last character in self that is not present in needles.

Examples

use stringzilla::StringZilla;

let haystack = "Hello, world!";
assert_eq!(haystack.sz_rfind_char_not_from("aeiou".as_bytes()), Some(12));

fn sz_edit_distance(&self, other: N) -> usize

Computes the Levenshtein edit distance between self and other.

Examples

use stringzilla::StringZilla;

let first = "kitten";
let second = "sitting";
assert_eq!(first.sz_edit_distance(second.as_bytes()), 3);

fn sz_alignment_score( &self, other: N, matrix: [[i8; 256]; 256], gap: i8, ) -> isize

Computes the alignment score between self and other using the specified substitution matrix and gap penalty.

Examples

use stringzilla::{sz, StringZilla};

let first = "kitten";
let second = "sitting";
let matrix = sz::unary_substitution_costs();
let gap_penalty = -1;
assert_eq!(first.sz_alignment_score(second.as_bytes(), matrix, gap_penalty), -3);

fn sz_matches(&'a self, needle: &'a N) -> RangeMatches<'a>

Returns an iterator over all non-overlapping matches of the given needle in self.

Arguments

• needle: The byte slice to search for within self.

Examples

use stringzilla::StringZilla;

let haystack = b"abababa";
let needle = b"aba";
let matches: Vec<&[u8]> = haystack.sz_matches(needle).collect();
assert_eq!(matches, vec![b"aba", b"aba", b"aba"]);

fn sz_rmatches(&'a self, needle: &'a N) -> RangeRMatches<'a>

Returns an iterator over all non-overlapping matches of the given needle in self, searching from the end.

Arguments

• needle: The byte slice to search for within self.

Examples

use stringzilla::StringZilla;

let haystack = b"abababa";
let needle = b"aba";
let matches: Vec<&[u8]> = haystack.sz_rmatches(needle).collect();
assert_eq!(matches, vec![b"aba", b"aba", b"aba"]);

fn sz_splits(&'a self, needle: &'a N) -> RangeSplits<'a>

Returns an iterator over the substrings of self that are separated by the given needle.

Arguments

• needle: The byte slice to split self by.

Examples

use stringzilla::StringZilla;

let haystack = b"a,b,c,d";
let needle = b",";
let splits: Vec<&[u8]> = haystack.sz_splits(needle).collect();
assert_eq!(splits, vec![b"a", b"b", b"c", b"d"]);

fn sz_rsplits(&'a self, needle: &'a N) -> RangeRSplits<'a>

Returns an iterator over the substrings of self that are separated by the given needle, searching from the end.

Arguments

• needle: The byte slice to split self by.

Examples

use stringzilla::StringZilla;

let haystack = b"a,b,c,d";
let needle = b",";
let splits: Vec<&[u8]> = haystack.sz_rsplits(needle).collect();
assert_eq!(splits, vec![b"d", b"c", b"b", b"a"]);

fn sz_find_first_of(&'a self, needles: &'a N) -> RangeMatches<'a>

Returns an iterator over all non-overlapping matches of any of the bytes in needles within self.

Arguments

• needles: The set of bytes to search for within self.

Examples

use stringzilla::StringZilla;

let haystack = b"Hello, world!";
let needles = b"aeiou";
let matches: Vec<&[u8]> = haystack.sz_find_first_of(needles).collect();
assert_eq!(matches, vec![b"e", b"o", b"o"]);

fn sz_find_last_of(&'a self, needles: &'a N) -> RangeRMatches<'a>

Returns an iterator over all non-overlapping matches of any of the bytes in needles within self, searching from the end.

Arguments

• needles: The set of bytes to search for within self.

Examples

use stringzilla::StringZilla;

let haystack = b"Hello, world!";
let needles = b"aeiou";
let matches: Vec<&[u8]> = haystack.sz_find_last_of(needles).collect();
assert_eq!(matches, vec![b"o", b"o", b"e"]);

fn sz_find_first_not_of(&'a self, needles: &'a N) -> RangeMatches<'a>

Returns an iterator over all non-overlapping matches of any byte not in needles within self.

Arguments

• needles: The set of bytes that should not be matched within self.

Examples

use stringzilla::StringZilla;

let haystack = b"Hello, world!";
let needles = b"aeiou";
let matches: Vec<&[u8]> = haystack.sz_find_first_not_of(needles).collect();
assert_eq!(matches, vec![b"H", b"l", b"l", b",", b" ", b"w", b"r", b"l", b"d", b"!"]);

fn sz_find_last_not_of(&'a self, needles: &'a N) -> RangeRMatches<'a>

Returns an iterator over all non-overlapping matches of any byte not in needles within self, searching from the end.

Arguments

• needles: The set of bytes that should not be matched within self. q

Examples

use stringzilla::StringZilla;

let haystack = b"Hello, world!";
let needles = b"aeiou";
let matches: Vec<&[u8]> = haystack.sz_find_last_not_of(needles).collect();
assert_eq!(matches, vec![b"!", b"d", b"l", b"r", b"w", b" ", b",", b"l", b"l", b"H"]);

Implementors

impl<'a, T, N> StringZilla<'a, N> for T

where T: AsRef<[u8]> + ?Sized, N: AsRef<[u8]> + 'a,