transword_puzzle.py

import os, sys, string, pprint
pp = pprint.PrettyPrinter()
# Display large wordlist in nice format
def display(split=10):
    data = '\n'.join(['     '.join(data[i * split:min((i * split) + split, len(data))]) for i in range(int(len(data) / split)+1)])

# OWL 3 Wordlist 
"""
import re
path = os.path.join(sys.path[0], 'OWL3.txt')
with open(path, 'r') as file:
    data = re.split('\s+', file.read())
    print(data)
"""

# OTCWL2014 Wordlist
path = os.path.join(sys.path[0], 'twl3.txt')
with open(path, 'r') as file:
    data = file.read().split('\n') # Data does not need stripping, works fine AS IS

# Determines hamming distance with length difference, can determine indexes
def hammingDistance(source, destination, indexes=False):
    hamming = [] if indexes else 0
    if len(source) != len(destination):
        if len(source) > len(destination):
            source, destination = list(destination), list(source)
        if not indexes:
            hamming += abs(len(source) - len(destination))
    else:
        source, destination = list(source), list(destination)
    # If dealing with indexes
    if indexes:
        for index, char in enumerate(source):
            if destination[index] != char:
                hamming.append(index)
    else:
        for index, char in enumerate(source):
            if destination[index] != char:
                hamming += 1
    return hamming

# Identifies the number of character changes that are positive from source -> new relating to destination
# Does not account for length changes!
def poschange(source, new, destination):
    changes = hammingDistance(source, new, indexes=True)
    score = 0
    for change in changes:
        if new[change] == destination[change]:
            score += 1
        else:
            score -= 1
    return len(changes), score

def identifier(wordlist, source, destination, lengthChange=False, maxChange=1):
    if not lengthChange:
        wordlist = list(filter(lambda x : len(x) == len(source), wordlist))
    possible = [(index, poschange(source, word, destination)) for index, word in enumerate(wordlist)]
    changeFilter = (lambda n : n > 0) if maxChange == 0 else (lambda n : n == maxChange)
    possible = [wordlist[i] for (i, (tot, pos)) in possible if pos >= 0]
    # possible = [identifier(wordlist, word, destination, lengthChange=lengthChange, maxChange=maxChange) for word in possible]
    return possible

x = identifier(data, 'four', 'five', maxChange=1)
pp.pprint(x)