Created
December 1, 2014 22:10
-
-
Save archer884/0961fe708f43718efd1a to your computer and use it in GitHub Desktop.
Rust word usage counter
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
#![feature(phase)] | |
#[phase(plugin)] | |
extern crate regex_macros; | |
extern crate regex; | |
use regex::Regex; | |
use std::ascii::AsciiExt; | |
use std::collections::{HashMap}; | |
use std::collections::hash_map::Entry::{Vacant, Occupied}; | |
use std::io::{BufferedReader, File}; | |
static WORD_PATTERN: Regex = regex!(r"(\w)+('\w+)?"); | |
struct Item { | |
word: String, | |
count: int, | |
} | |
fn main() { | |
let content = get_content(); | |
let mut map: HashMap<String, int> = HashMap::new(); | |
for word in content.into_iter() { | |
match map.entry(word) { | |
Occupied(mut entry) => *entry.get_mut() += 1, | |
Vacant(entry) => { entry.set(1); }, | |
}; | |
} | |
let mut items = Vec::new(); | |
for (key, val) in map.iter() { | |
items.push(Item { word: key.to_string(), count: *val }); | |
} | |
items.sort_by(|a, b| a.word.cmp(&b.word)); | |
items.sort_by(|a, b| b.count.cmp(&a.count)); | |
for i in items.iter() { | |
println!("{}: {}", i.word, i.count); | |
} | |
} | |
fn get_content() -> Vec<String> { | |
let args = std::os::args(); | |
let text = File::open(&Path::new(&args[1])).read_to_string().unwrap(); | |
WORD_PATTERN.captures_iter(text.as_slice()) | |
.map(|cap| cap.at(0).to_ascii_upper()) | |
.collect() | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment