lettergen2

#!/usr/bin/env python3

from collections import defaultdict
import sys
import re

args = sys.argv[1:]
NTILES = int(args.pop(0))
RE_VALID_WORD = re.compile(r'^([a-z][a-z]){1,%s}$' % NTILES)
RE_REPEATED_PAIR = re.compile(r'''
  ^(..)*
  (?P<letter1>.)(?P<letter2>.)
  (?P=letter1)(?P=letter2)
''', re.X)

words = defaultdict(set)

for word in open(args.pop(0)) if args else sys.stdin:
  word = word.rstrip('\n')

  # discard words with odd length, capitals, apostrophes.
  if not RE_VALID_WORD.match(word):
    continue

  # split the word into letter pairs.
  pairs = re.findall(r'.{2}', word)

  # discard words with repeated pairs.
  if RE_REPEATED_PAIR.match(''.join(sorted(pairs))):
    continue

  # add the word to each of its letter pair wordsets.
  for pair in pairs:
    words[pair].add(word)

# work backwards from 676 to NTILES.
# remove the least-damaging letter pair at each step.
damage = lambda pair: len(words[pair])
while len(words) > NTILES:
  least_damaging_pair = min(words.keys(), key=damage)
  lost_words = words.pop(least_damaging_pair)
  for wordset in words.values():
    wordset.difference_update(lost_words)

# report the tileset.
print(','.join(sorted(words.keys())))

# report all formable dictionary words.
for word in sorted(set().union(*words.values())):
  print(word)