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)

freqs = defaultdict(lambda: 0)
words = []

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 to valid word list. update letter pair statistics.
  words.append(word)
  for pair in pairs:
    freqs[pair] += 1

# our tileset is the top N most frequently occurring pairs.
metric = lambda pair: freqs[pair]
tileset = set(sorted(freqs.keys(), key=metric)[-NTILES:])

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

# report all formable dictionary words.
for word in words:
  if not set(re.findall(r'.{2}', word)).difference(tileset):
    print(word)