Created
October 29, 2014 15:16
-
-
Save stefanoc/52537ef37232d0c1d850 to your computer and use it in GitHub Desktop.
Word freqs
This file contains hidden or 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
require 'pp' | |
dict = Hash.new(0) | |
File.open(ARGV[0], 'r') do |src| | |
while line = src.gets | |
line.strip.scan(/\w+/) { |word| dict[word] += 1 } | |
end | |
end | |
pp dict |
This file contains hidden or 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)] | |
extern crate regex; | |
#[phase(plugin)] extern crate regex_macros; | |
use std::collections::HashMap; | |
use std::collections::hashmap::{Vacant, Occupied}; | |
use std::io::fs::File; | |
use std::io::BufferedReader; | |
use std::os::args; | |
fn main() { | |
let mut dict = HashMap::<String, uint>::new(); | |
let re = regex!(r"\w+"); | |
let mut lines = 0u; | |
let filename = match args().len() { | |
1 => fail!("You must enter a filename to read line by line"), | |
_ => args()[1].clone() | |
}; | |
let file = File::open(&Path::new(filename.as_slice())); | |
let mut reader = BufferedReader::new(file); | |
for line in reader.lines() { | |
match line { | |
Ok(line) => { | |
lines += 1; | |
for pos in re.find_iter(line.as_slice()) { | |
let (a, b) = pos; | |
let word = line.as_slice().slice_chars(a, b).to_string(); | |
match dict.entry(word) { | |
Vacant(entry) => { entry.set(1u); }, | |
Occupied(mut entry) => *entry.get_mut() += 1, | |
}; | |
} | |
}, | |
Err(err) => { | |
println!("ERR: {}", err); | |
break; | |
} | |
} | |
} | |
println!("Read {} lines", lines); | |
println!("{}", dict); | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment