Subversion Repositories LCARS

Rev

Rev 292 | Go to most recent revision | View as "text/plain" | Blame | Compare with Previous | Last modification | View Log | RSS feed

1
'''
Created on 2014-10-20

@author: Thomas 'PointedEars' Lahn <mail@PointedEars.de>
'''

from sys import argv, stderr
from re import findall, DOTALL, IGNORECASE, match, sub, compile, \
    split
from os import chdir
from os.path import dirname, realpath
from collections import OrderedDict
from functools import cmp_to_key
from copy import deepcopy
from collections.abc import MutableSequence

dictionary = {}

prepositions = {
    "fi'": 'on',
    "na'": 'at|to',
    "t'": 'of'
}

class MutableString2(MutableSequence):
    def __init__(self, value=None):
        self._values = [str(value)] if value is not None else []

    def __add__(self, value):
        return ''.join([self, value])

    def __delitem__(self):
        raise NotImplementedError

    def __getitem__(self, index):
        return str(self)[index]

    def __len__(self):
        return len(str(self))

    def __repr__(self):
        return ''.join(self._values)

    def __setitem__(self, index, value):
        raise NotImplementedError

    def __str__(self):
        return self.__repr__()

    def extend(self, values):
        self._values.append(values)

    def insert(self, index, value):
        raise NotImplementedError

def load_dictionary(dictionary, dictionary_file):
    print('Loading dictionary {0} ...'.format(dictionary_file), end='', file=stderr)

    chdir(dirname(realpath(__file__)))
    with open(dictionary_file) as f:
        keys = "ipa|en|lit|pos|com|tag|ex"
        indent = None
        value = None

        for line in f:
            m = match(r'^\s*vuh:\s*(?P<phrase>.+)', line)
            if m is not None:
                phrase = m.group("phrase")
                dictionary[phrase] = {}
                indent = None
            else:
                m = match(
                    r'(?P<indent>\s*)(?P<key>{0}):\s*(?P<value>.+)'.format(keys),
                    line)
                if m is not None:
                    indent = m.group("indent")
                    key = m.group("key")
                    value = m.group("value")
                    value = dictionary[phrase][key] = MutableString2(value)
                elif indent is not None:
                    m = match(r'(?P<indent>\s+)(?P<continuation>\S.*)', line)
                    if m is not None:
                        if len(m.group("indent")) == len(indent) + 2:
                            dictionary[phrase][key] += (" " + m.group("continuation"))

    print(' done ({0} entries).'.format(len(dictionary)), file=stderr)

def clean_dictionary(dictionary):
    braces_re = compile(r'^\s*\{(.+)\}\s*$')
    semicolon_re = compile(r'\s*;\s*')

    for orig_phrase, data in list(dictionary.items()):
        if orig_phrase.find(";") > -1:
            synonyms = map(
                lambda x: sub(braces_re, r'\1', orig_phrase),
                split(semicolon_re, orig_phrase))

            for synonym in synonyms:
                dictionary[synonym] = deepcopy(data)

            del dictionary[orig_phrase]
        else:
            m = match(braces_re, orig_phrase)
            if m is not None:
                dictionary[m.group(1)] = deepcopy(dictionary[orig_phrase])
                del dictionary[orig_phrase]

def sort_dict_alnum_english_key(phrase):
    return sub(r'\{(.+)\}', r'\1', phrase[0]).lower()

def get_sort_dict_alnum_vulcan_key():
    letters = list(map(str.lower, [
        " ", 'S', 'T', 'P', 'K', 'R', 'L', 'A', 'Sh', 'O', 'U', 'D',
        'V', 'Kh', 'E', 'H', 'G', 'Ch', 'I', 'N', 'Zh', 'M', 'Y', 'F', 'Z',
        'Th', 'W', 'B', "'", '-']))
    letter_values = dict(map(lambda x: (x[1], x[0]), enumerate(letters)))
    letters_re = compile(r'(?:{0})'.format('|'.join(sorted(letters, key=lambda char:-len(char)))))

    def sort_dict_alnum_vulcan (a, b):
        # split into Vulcan letters
        a = findall(letters_re, sort_dict_alnum_english_key(a))
        b = findall(letters_re, sort_dict_alnum_english_key(b))

        if len(a) < len(b):
            for index, char in enumerate(a):
                diff = letter_values[char] - letter_values[b[index]]
                if diff != 0:
                    return diff
            return -1

        # len(b) <= len(a)
        for index, char in enumerate(b):
            diff = letter_values[a[index]] - letter_values[char]
            if diff != 0:
                return diff

        return 1 if len(b) < len(a) else 0

    return cmp_to_key(sort_dict_alnum_vulcan)

def translate (word, recursion=False):
    translation = dictionary.get(word.lower(), None)
    if translation is not None:
        translation = translation["en"]
        if match('[A-Z]', word):
            return sub('[a-z]', lambda ch: ch.group(0).upper(), str(translation), count=1)
        return translation

    if not recursion:
        # prepositions attached?
        for prep, prep_transl in prepositions.items():
            if (match(prep, word)):
                real_word = word.replace(r'^' + prep, '')
                real_word_transl = translate(real_word, recursion=True)
                if real_word_transl is not None:
                    return prep_transl + ' ' + real_word_transl

    if recursion:
        return None
    else:
        # Not in dictionary: proper name or missing for other reasons
        return '{{{0}}}'.format(word)

if __name__ == '__main__':
    load_dictionary(dictionary, 'vuh-gol-en.dict.zdb.txt')
    clean_dictionary(dictionary)

#     try:
#         for phrase, data in OrderedDict(sorted(
#             dictionary.items(),
#             key=get_sort_dict_alnum_vulcan_key()
#         )).items():
#             print(phrase, "=", data)
#     except BrokenPipeError:
#         pass

    text = argv[1]
    sentences = findall(r'(?!\s+)(?:.+?\.{1,3}|.+$)', text, DOTALL)
    for sentence in sentences:
        print(sentence)

        words = findall(r"(?!\s+)[a-z'-]{2,}", sentence, IGNORECASE)
        print(words)

        translated_words = list(map(translate, words))
        print(translated_words)

        for index, word in enumerate(words):
            sentence = sentence.replace(word, str(translated_words[index]))
        print(sentence)

        # replace punctuation
        for symbol, replacement in ({" - ": ", "}).items():
            sentence = sentence.replace(symbol, replacement)

        print(sentence)