playing around with Rust

README

actors.list is a +1GB text file fetched from IMDB partial database.

Obs: the Rust 3rd party Regex package feels slow at this time

actors.rb

filename = 'actors.list'
target_movie = 'Star Wars: Episode V - The Empire Strikes Back'
actors = []
actor = nil
File.foreach(filename).with_index do |line, line_num|
  next if line_num < 239
  line.encode!(line.encoding, 'binary', invalid: :replace, undef: :replace)
  if line.strip == ''
    actor = nil
    next
  end
  slices = line.split(/\t/)
  actor_buffer = slices.first
  movie        = slices.last
  if actor.nil? && !actor_buffer.nil? && actor_buffer != ''
    actor = actor_buffer
  end
  if !movie.nil? && movie.include?(target_movie)
    actors << actor
  end
end
for actor_name in actors
  puts actor_name
end

Cargo.toml

[package]
name = "actors"
version = "0.1.0"
authors = ["vagrant"]

[dependencies]
regex = "0.1.8"

main.rs

use std::fs::File;
use std::io::prelude::*;
use std::io::BufReader;
extern crate regex;
use regex::Regex;

fn main() {
    let filename = "actors.list";
    let target_movie = "Star Wars: Episode V - The Empire Strikes Back";

    let file = File::open(filename).unwrap();
    let mut reader = BufReader::new(&file).lines().skip(239);

    let mut actor = String::new();
    let mut actors : Vec<String> = Vec::new();
    let regex = Regex::new(r"^(.*?)\t+(.*?)$").unwrap();
    loop {
        let line = match reader.next() {
            Some(line) => match line {
                Ok(line) => line,
                Err(_) => String::new(),
            },
            None => break,
        };

        match regex.captures(&line) {
            Some(captures) => {
                let actor_buffer = captures.at(1).unwrap();
                let movie = captures.at(2).unwrap();

                if actor.is_empty() && !actor_buffer.is_empty() {
                    actor = actor_buffer.to_string();
                }

                if !movie.is_empty() && movie.contains(&target_movie) {
                    actors.push(actor.to_string());
                    println!("{}", actor);
                }
            },
            None => {
                actor = String::new();
            }
        };
    }

    for actor_name in actors {
        println!("{}", actor_name);
    }
}