Python实现单词拼写检查

#!/usr/bin/python
# A simple spell checker

import os, sys, subprocess, signal

alphabet = 'abcdefghijklmnopqrstuvwxyz'

def found(word, args, cwd = None, shell = True):
  child = subprocess.Popen(args, 
    shell = shell, 
    stdin = subprocess.PIPE, 
    stdout = subprocess.PIPE, 
    cwd = cwd, 
    universal_newlines = True) 
  child.stdout.readline()
  (stdout, stderr) = child.communicate(word)
  if ": " in stdout:
    # remove \n\n
    stdout = stdout.rstrip("\n")
    # remove left part until :
    left, candidates = stdout.split(": ", 1) 
    candidates = candidates.split(", ")
    # making an error on the first letter of a word is less 
    # probable, so we remove those candidates and append them 
    # to the tail of queue, make them less priority
    for item in candidates:
      if item[0] != word[0]: 
        candidates.remove(item)
        candidates.append(item)
    return candidates
  else:
    return None

# copy from http://norvig.com/spell-correct.html
def edits1(word):
  n = len(word)
  return set([word[0:i]+word[i+1:] for i in range(n)] +           
    [word[0:i]+word[i+1]+word[i]+word[i+2:] for i in range(n-1)] +
    [word[0:i]+c+word[i+1:] for i in range(n) for c in alphabet] +
    [word[0:i]+c+word[i:] for i in range(n+1) for c in alphabet])

def correct(word):
  candidates1 = found(word, 'aspell -a')
  if not candidates1:
    print "no suggestion"
    return 

  candidates2 = edits1(word)
  candidates = []
  for word in candidates1:
    if word in candidates2:
      candidates.append(word)
  if not candidates:
    print "suggestion: %s" % candidates1[0]
  else:
    print "suggestion: %s" % max(candidates)

def signal_handler(signal, frame):
  sys.exit(0)

if __name__ == '__main__':
  signal.signal(signal.SIGINT, signal_handler)
  while True:
    input = raw_input()
    correct(input)

>>> import enchant
>>> d = enchant.Dict("en_US")
>>> d.check("Hello")
True
>>> d.check("Helo")
False
>>> d.suggest("Helo")
['He lo', 'He-lo', 'Hello', 'Helot', 'Help', 'Halo', 'Hell', 'Held', 'Helm', 'Hero', "He'll"]
>>>