number_word_finder.py

from ahocorapy.keywordtree import KeywordTree


digit2letter = {
    1: [],
    2: ['a', 'b', 'c'],
    3: ['d', 'e', 'f'],
    4: ['g', 'h', 'i'],
    5: ['j', 'k', 'l'],
    6: ['m', 'n', 'o'],
    7: ['p', 'q', 'r', 's'],
    8: ['t', 'u', 'v'],
    9: ['w', 'x', 'y', 'z']
}

def get_all_texts(number):
    digit, rest = number[0], number[1:]
    def _get_text(digit, rest):
        if not digit:
            return [""]

        results = []
        for letter in digit2letter[int(digit)]:
            for r in _get_text(rest[:1], rest[1:]):
                results.append(letter + r)
        return results
    return _get_text(digit, rest)


class NumberFinder:
    def __init__(self):
        words = open("/usr/share/dict/american-english").read().split("\n")
        self.kwtree = KeywordTree(case_insensitive=True)
        for word in words:
            self.kwtree.add(word.lower())
        self.kwtree.finalize()

    def find(self, number, min_length=4):
        texts = get_all_texts(number)
        final = set()
        for text in texts:
            for word, _ in self.kwtree.search_all(text):
                if len(word) > min_length:
                    index = text.index(word)
                    _word = "{} {} {}".format(number[:index], word.upper(), number[index+len(word):])
                    final.add(_word)
        return list(final)