Created
October 18, 2020 07:59
-
-
Save miquels/b93ed7af98bc3bc6022b474c4fd66ab2 to your computer and use it in GitHub Desktop.
word count
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
[package] | |
name = "wc" | |
version = "0.1.0" | |
edition = "2018" | |
[dependencies] | |
regex = "1" | |
lazy_static = "1" |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
use std::collections::HashMap; | |
use std::fs; | |
use std::io::{self, BufRead}; | |
use regex::Regex; | |
lazy_static::lazy_static! { | |
static ref WORD_REGEX: Regex = Regex::new(r"(?i)[a-z]{2,}").unwrap(); | |
static ref FNAME_REGEX: Regex = Regex::new(r"(?i)\.txt$").unwrap(); | |
} | |
fn main() -> io::Result<()> { | |
let mut word_counts = HashMap::new(); | |
for path in fs::read_dir(".")? | |
.filter_map(|p| p.ok()) | |
.map(|p| p.path()) | |
.filter(|p| p.is_file() && FNAME_REGEX.is_match(&p.to_string_lossy())) { | |
let file = fs::File::open(path)?; | |
for line in io::BufReader::new(file).lines() { | |
for cap in WORD_REGEX.captures_iter(&line?) { | |
*word_counts.entry(cap[0].to_string()).or_insert(0) += 1u32; | |
} | |
} | |
} | |
let mut word_array: Vec<(String, u32)> = word_counts.into_iter().collect(); | |
word_array.sort_by(|a, b| b.1.partial_cmp(&a.1).unwrap()); | |
let final_size = std::cmp::min(word_array.len(), 10); | |
for entry in &word_array[..final_size] { | |
println!("{} {}", entry.1, entry.0); | |
} | |
Ok(()) | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment