Задачка на самый быстрый подсчет встречаемости слов

time echo '2 10000000 ^ p'|dc

time cat huge.txt > /dev/null

Сижу рыдаю ...

Современные технологии они такие ...

Загрузка данных из любой конфигурации 1С 7.7 без использования самой 1С в свою иерархическую базу 

#![feature(exclusive_range_pattern)]
use std::collections::hash_map::Entry::{Occupied, Vacant};
use std::collections::HashMap;
use std::fs;

fn main() {
    let file = fs::read_to_string("huge.txt").unwrap();
    let word = String::new();
    let mut result: HashMap<String, i32> = HashMap::new();
    for mut letter in &mut file.chars() {
        if letter.is_ascii() {
            letter = letter.to_lowercase().next().unwrap();
        }
        let mut word = word.clone();
        match letter {
            'a'..'z' => {
                word.push(letter);
            }
            _ => {
                let val = match result.entry(word) {
                    Occupied(entry) => entry.into_mut(),
                    Vacant(entry) => entry.insert(0),
                };
                *val += 1;
            }
        }
    }
    for (i, j) in result {
        println!("{}\t{}", i, j);
    }
}

<?php
$words = str_word_count(strtolower(file_get_contents('./huge.txt')), 1);
$count = array_count_values($words);
arsort($count, SORT_NUMERIC);
file_put_contents('./res.txt', print_r($count, true));

~/s/ct ❯❯❯ time php8.0 count.php

________________________________________________________
Executed in    6,53 secs   fish           external
   usr time    4,92 secs  775,00 micros    4,92 secs
   sys time    1,59 secs  288,00 micros    1,59 secs

  'the' => 3327272,
  'and' => 1826748,
  'of' => 1711781,
  'to' => 1536721,
  'a' => 1307257,

<?php
setlocale(LC_ALL, 'C');
$text = str_replace(['-', "'"], ' ', strtolower(file_get_contents('./huge.txt')));
$words = str_word_count($text, 1);
$count = array_count_values($words);
arsort($count, SORT_NUMERIC);
file_put_contents('./res2.txt', var_export($count, true));

  'the' => 3343241,
  'and' => 1852717,
  'of' => 1715705,
  'to' => 1560152,
  'a' => 1324244,

~/s/ct ❯❯❯ time php8.0 count.php

________________________________________________________
Executed in    6,82 secs   fish           external 
   usr time    4,96 secs  681,00 micros    4,95 secs 
   sys time    1,85 secs  361,00 micros    1,85 secs 

Fatal error: Allowed memory size of 134217728 bytes exhausted (tried to allocate 336191496 bytes) in /Users/tho/Developer/freqc/builddir/main.php on line 2

$ time php words.php
PHP Fatal error:  Allowed memory size of 134217728 bytes exhausted (tried to allocate 336191496 bytes) in php/words.php on line 3

real    0m0.011s
user    0m0.006s
sys     0m0.005s

$ time perl -ne '$h{lc($1)}++ while (/([A-Za-z]+)/gc); END { printf "$h{$_} $_\n" for (sort {$h{$b} <=> $h{$a}} keys(%h)) }' huge.txt | head
3343241 the
1852717 and
1715705 of
1560152 to
1324244 a
956926 in
933954 i
781286 he
713514 that
690876 was

real    0m18.868s
user    0m18.812s
sys     0m0.057s

use std::collections::hash_map::Entry::{Occupied, Vacant};
use std::collections::HashMap;
use std::fs::File;
use std::io::Read;
use std::iter::FromIterator;

fn main() {
    let mut file_content = Vec::new();
    let mut file = File::open("huge.txt").expect("Unable to open file");
    file.read_to_end(&mut file_content).expect("Unable to read");
    let mut word = String::new();
    let mut result: HashMap<String, i32> = HashMap::new();
    for letter in &mut file_content {
        if letter.is_ascii() {
            *letter = letter.to_ascii_lowercase();
        }
        match letter {
            97..=122 => {
                word.push(*letter as char);
            }
            _ => {
                let val = match result.entry(word) {
                    Occupied(entry) => entry.into_mut(),
                    Vacant(entry) => entry.insert(1),
                };
                *val += 1;
                word = String::new();
            }
        }
    }
    let mut result = Vec::from_iter(result);
    result.sort_by(|&(_, a), &(_, b)| a.cmp(&b));
    for (i, j) in result {
        println!("{}\t{}", i, j);
    }
}