Решение на Spell Checker от Людмил Данаилов

Обратно към всички решения

Към профила на Людмил Данаилов

Код

use std::fmt;

use std::collections::HashSet;

pub const ALPHABET_EN: &'static str = "abcdefghijklmnopqrstuvwxyz";

pub const ALPHABET_BG: &'static str = "абвгдежзийклмнопрстуфхцчшщъьюя";

pub fn clean_line(input: &str) -> String {

let chars: String = input.chars().filter(|&n| n.is_alphabetic() || n == '-' || n == '\'' || n.is_whitespace()).collect::<String>().trim().to_string();

return chars;

}

pub struct WordCounter {

word_counter: Vec<(String, u32)>

}

impl WordCounter {

pub fn new() -> Self {

let vec: Vec<(String, u32)> = Vec::new();

return WordCounter{word_counter: vec};

}

pub fn from_str(input: &str) -> Self {

let mut vec: Vec<(String, u32)> = Vec::new();

for x in input.lines() {

let a = clean_line(x);

if a == "" {

return WordCounter{word_counter: vec![]};

}

vec = a.split(' ').collect::<Vec<&str>>().iter().map(|n| (n.to_string(), 1)).collect::<Vec<(String, u32)>>();

}

return WordCounter{word_counter: vec};

}

pub fn words(&self) -> Vec<&String> {

let vec: Vec<&String> = self.word_counter.iter().map(|n| &(n.0)).collect::<Vec<&String>>();

return vec;

}

pub fn add(&mut self, item: &str) {

let string: String = clean_line(item).to_lowercase();

while let Some(mut i) = self.word_counter.clone().into_iter().next() {

if string == item {

i.1 += 1;

return;

}

}

self.word_counter.push((string, 1));

}

pub fn get(&self, word: &str) -> u32 {

while let Some(i) = self.word_counter.clone().into_iter().next() {

if i.0 == word.to_string() {

return i.1;

}

}

return 0;

}

pub fn total_count(&self) -> u32 {

let sum: u32 = self.word_counter.iter().map(|n| n.1 as u32).sum();

return sum;

}

}

impl fmt::Display for WordCounter {

fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {

write!(f, "WordCounter, total count: {:?}\n", self.total_count())?;

self.word_counter.iter().map(|n| write!(f, "{}: {}", n.0, n.1)).collect()

}

}

pub struct SpellChecker {

alphabet: String,

word_counter: WordCounter

}

impl SpellChecker {

pub fn new(corpus: &str, alphabet: &str) -> Self {

let word_counter = WordCounter::from_str(corpus);

return SpellChecker{alphabet: alphabet.to_string(), word_counter: word_counter}

}

pub fn correction(&self, word: &str) -> String {

unimplemented!();

}

pub fn probability(&self, word: &str) -> f64 {

return (self.word_counter.get(word) / self.word_counter.total_count()) as f64;

}

pub fn known(&self, words: &HashSet<String>) -> Vec<String> {

let mut vector: Vec<String> = Vec::new();

for x in words {

if self.word_counter.get(&x) != 0 {

vector.push(x.to_string());

}

}

return vector;

}

pub fn candidates<'a>(&self, word: &str) -> Vec<String> {

let a = HashSet::new();

if self.known(&a).len() != 0 {

return self.known(&a);

}

if self.known(&self.edits1(word)).len() != 0 {

return self.known(&self.edits1(word));

}

if self.known(&self.edits2(word)).len() != 0 {

return self.known(&self.edits2(word));

}

return self.known(&a);

}

/// Всички думи, които са на една промяна разстояние от дадената дума:

///

/// - Една буква изтрита на коя да е позиция

/// - Две букви разменени (една до друга)

/// - Една буква от азбуката замества коя да е буква от думата

/// - Една буква от азбуката добавена в думата на която и да е позиция

///

/// Изхода е HashSet, понеже две различни промени е възможно да продуцират един и същ резултат,

/// а дубликати не ни интересуват.

///

pub fn edits1(&self, word: &str) -> HashSet<String> {

unimplemented!()

}

/// Всички думи, които са на две промени разстояние от дадената дума. Вижте инструкциите на

/// edits1 за това какво е "промяна" и направете тези промени по променените веднъж думи.

///

pub fn edits2(&self, word: &str) -> HashSet<String> {

unimplemented!()

}

}

Лог от изпълнението

Compiling solution v0.1.0 (/tmp/d20200114-2173579-1suh1c9/solution)
warning: unused variable: `word`
  --> src/lib.rs:90:30
   |
90 |     pub fn correction(&self, word: &str) -> String {
   |                              ^^^^ help: consider prefixing with an underscore: `_word`
   |
   = note: `#[warn(unused_variables)]` on by default

warning: unused variable: `word`
   --> src/lib.rs:133:26
    |
133 |     pub fn edits1(&self, word: &str) -> HashSet<String> {
    |                          ^^^^ help: consider prefixing with an underscore: `_word`

warning: unused variable: `word`
   --> src/lib.rs:140:26
    |
140 |     pub fn edits2(&self, word: &str) -> HashSet<String> {
    |                          ^^^^ help: consider prefixing with an underscore: `_word`

warning: field is never used: `alphabet`
  --> src/lib.rs:80:5
   |
80 |     alphabet: String,
   |     ^^^^^^^^^^^^^^^^
   |
   = note: `#[warn(dead_code)]` on by default

warning: unused variable: `word`
  --> src/lib.rs:90:30
   |
90 |     pub fn correction(&self, word: &str) -> String {
   |                              ^^^^ help: consider prefixing with an underscore: `_word`
   |
   = note: `#[warn(unused_variables)]` on by default

warning: unused variable: `word`
   --> src/lib.rs:133:26
    |
133 |     pub fn edits1(&self, word: &str) -> HashSet<String> {
    |                          ^^^^ help: consider prefixing with an underscore: `_word`

warning: unused variable: `word`
   --> src/lib.rs:140:26
    |
140 |     pub fn edits2(&self, word: &str) -> HashSet<String> {
    |                          ^^^^ help: consider prefixing with an underscore: `_word`

warning: field is never used: `alphabet`
  --> src/lib.rs:80:5
   |
80 |     alphabet: String,
   |     ^^^^^^^^^^^^^^^^
   |
   = note: `#[warn(dead_code)]` on by default

error[E0277]: can't compare `std::string::String` with `&std::string::String`
   --> tests/solution_test.rs:169:5
    |
169 |     assert_eq!(known_words, vec![&String::from("four"), &String::from("one")]);
    |     ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ no implementation for `std::string::String == &std::string::String`
    |
    = help: the trait `std::cmp::PartialEq<&std::string::String>` is not implemented for `std::string::String`
    = note: required because of the requirements on the impl of `std::cmp::PartialEq<std::vec::Vec<&std::string::String>>` for `std::vec::Vec<std::string::String>`
    = note: this error originates in a macro outside of the current crate (in Nightly builds, run with -Z external-macro-backtrace for more info)

error: aborting due to previous error

For more information about this error, try `rustc --explain E0277`.
error: could not compile `solution`.

To learn more, run the command again with --verbose.

История (1 версия и 1 коментар)

pub fn known(&self, words: &HashSet<String>) -> Vec<String> {