acrofinder.py

"""Acronym Finder, rearranges letters to find words then ranks them based on a frequency list.

Usage:
    acrofinder [-of --language=<lc> --format=<fmt> --save=<file>] <letters>
    acrofinder --list-supported
    acrofinder -h | --help

Options:
    -h --help           Show this screen.
    -l --language=<lc>  Language code of the database to run against [defualt: he].
    -o --oneletter      Include single-letters.
    -f --full           Run against the full list (and not the 50K most common).
    -F --format=<fmt>   Format of exported table (csv or tsv) [defualt: tsv].
    -s --save=<file>    File name of exported table.
    --list-supported    List supported language codes.
"""
from docopt import docopt
import urllib.request
from sys import exit
from itertools import permutations

DEFAULT_LANGUAGE = 'he'
SUPPORTED_LANGUAGES = ('af', 'ar', 'bg', 'bn', 'br', 'bs', 'ca', 'cs', 'da', 'de', 'el', 'en', 'eo', 'es', 'et', 'eu', 'fa', 'fi', 'fr', 'gl', 'he', 'hi', 'hr', 'hu', 'hy', 'id', 'is', 'it', 'ja', 'ka', 'kk', 'ko', 'lt', 'lv', 'mk', 'ml', 'ms', 'nl', 'no', 'pl', 'pt', 'pt_br', 'ro', 'ru', 'si', 'sk', 'sl', 'sq', 'sr', 'sv', 'ta', 'te', 'th', 'tl', 'tr', 'uk', 'vi', 'zh', 'zh_tw')

def get_frequency_dictionary(language=DEFAULT_LANGUAGE, fullness='50k'):
    """Retrives frequency list and makes it into a dictionary."""
    url = 'https://github.com/hermitdave/FrequencyWords/raw/master/content/2016/{lc}/{lc}_{fullness}.txt'.format(lc=language, fullness=fullness)
    response = urllib.request.urlopen(url)
    data = response.read()
    text = data.decode('utf-8')

    frequencies = {}

    for line in text.split("\n"):
        arr = line.split(" ")
        if (arr != ['']):
            frequencies[arr[0]] = int(arr[1])

    return frequencies

def permutate(letters, spaces=1):
    for x in letters:
        for y in permutations(x + ' '*spaces):
            if (y[-1] == ' '):
                continue
            yield ''.join(y).split()

def filter_rank_word(words, dictionary, oneletter=False):
    rank = 0
    for word in words:
        if (word in dictionary) and (oneletter or len(word) != 1):
            rank += dictionary[word]
        else:
            return None

    return (rank / len(words)**5)

if __name__ == '__main__':
    arguments = docopt(__doc__)

    if (arguments['--list-supported']):
        print("The supported language codes are:")
        print(', '.join(SUPPORTED_LANGUAGES[:-1]) + '.')
        exit(-1)

    if (arguments['--language'] == None) or (not arguments['--language'] in SUPPORTED_LANGUAGES):
        print("Unsupported language code.")
        exit(-1)

    frequencies = get_frequency_dictionary(arguments['--language'])

    if arguments['--format'] == 'csv':
        line_format = "{:.5f},{}\n"
    else:
        line_format = "{:.5f}\t{}\n"

    out = ""
    for word_set in permutate([arguments['<letters>']]):
        rank = filter_rank_word(word_set, frequencies, arguments['--oneletter'])
        if rank != None:
            out += line_format.format(rank, ' '.join(word_set))

    if (arguments['--save'] == None):
        print(out)
    else:
        with open(arguments['--save'], 'w') as f:
            f.write(out)