Created
November 29, 2014 23:52
-
-
Save archer884/c5456d7488a338fec186 to your computer and use it in GitHub Desktop.
Checks files for spelling errors.
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::HashSet; | |
use std::io::{BufferedReader, File}; | |
use std::io::fs::PathExtensions; | |
static WORD_PATTERN: Regex = regex!(r"(\w)+('\w+)?([.])?"); | |
fn main() { | |
let dict_set = get_dict(); | |
let content = get_content(); | |
let mut has_errors = false; | |
let mut line_counter = 0i; | |
for line in content.iter() { | |
line_counter += 1; | |
for word in get_words(line.as_slice()).iter() { | |
if !dict_set.contains(word) && !dict_set.contains(&word.replace(".", "")) { | |
has_errors = true; | |
println!("{}: {}", line_counter.to_string(), word); | |
} | |
} | |
} | |
if !has_errors { println!("Good!"); } | |
} | |
fn get_words(text: &str) -> Vec<String> { | |
WORD_PATTERN.captures_iter(text).map(|cap| cap.at(0).to_ascii_upper()).collect() | |
} | |
fn get_content() -> Vec<String> { | |
let args = std::os::args(); | |
if args.len() > 1 { | |
BufferedReader::new(File::open(&Path::new(&args[1]))).lines().map(|line| line.unwrap()).collect() | |
} else { | |
std::io::stdin().lines().map(|line| line.unwrap()).collect() | |
} | |
} | |
fn get_dict() -> HashSet<String> { | |
let std_word_path = Path::new("/usr/share/dict/words"); | |
let spc_word_path = Path::new("./.spelling"); | |
let mut dict_set: HashSet<String> = HashSet::new(); | |
if std_word_path.exists() { | |
populate_hash(&mut dict_set, &std_word_path); | |
} | |
if spc_word_path.exists() { | |
populate_hash(&mut dict_set, &spc_word_path); | |
} | |
dict_set | |
} | |
fn populate_hash(dict_set: &mut HashSet<String>, path: &Path) { | |
for word in BufferedReader::new(File::open(path)).lines().map(|line| line.unwrap()) { | |
if !dict_set.contains(&word) { | |
dict_set.insert(word.trim().to_ascii_upper()); | |
} | |
} | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment