Subversion Repositories LCARS

Rev

Rev 291 | Rev 293 | Go to most recent revision | View as "text/plain" | Blame | Compare with Previous | Last modification | View Log | RSS feed

1
#!/usr/bin/env python3

'''
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, stat
from os.path import dirname, realpath, basename
from collections import OrderedDict
from functools import cmp_to_key
from copy import deepcopy
from collections.abc import MutableSequence
from pickle import dump, load

debug_level = 2
dictionary = {}

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

def dmsg(*args, **kwargs):
    if not hasattr(kwargs, 'min_level') or kwargs['min_level'] is None:
        kwargs['min_level'] = 1

    if not hasattr(kwargs, 'file'):
        kwargs['file'] = stderr

    if debug_level >= kwargs['min_level']:
        del kwargs['min_level']
        print(*args, **kwargs)

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 cli_help():
    print('Usage: {0} TEXT...'.format(basename(argv[0])))

def load_dictionary(dictionary, dictionary_file):
    dmsg('Loading dictionary '.format(dictionary_file), end='', min_level=1)

    chdir(dirname(realpath(__file__)))

    pickle_file = basename(dictionary_file) + '.pickle'

    try:
        pickle_mtime = stat(pickle_file).st_mtime
    except FileNotFoundError:
        pickle_mtime = None

    if pickle_mtime is None or stat(dictionary_file).st_mtime > pickle_mtime:
        dmsg('from {0} ...'.format(dictionary_file), end='', min_level=1)
        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"))

        dmsg('\nSaving pickle {0} ...'.format(pickle_file), end='', min_level=1)
        # TODO: Pickle should only contain strings to be small
        with open(pickle_file, mode='wb') as f: dump(dictionary, f)
        dmsg(' done.', min_level=1)
    else:
        dmsg('from {0} ...'.format(pickle_file), end='', min_level=1)
        with open(pickle_file, mode='rb') as f: pickle = load(f)
        for key, value in pickle.items():
            dictionary[key] = value

    dmsg(' done ({0} entries).'.format(len(dictionary)), min_level=1)

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 (phrase):
    translation = dictionary.get(phrase.lower(), None)
    if translation is not None:
        return translation

    return None

if __name__ == '__main__':
    if len(argv) < 2:
        print('Nothing to translate.', end='\n\n', file=stderr)
        cli_help()
        exit(1)

    text = argv[1]

    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

    sentences = findall(r'(?!\s+)(?:.+?\.{1,3}|.+$)', text, DOTALL)
    dmsg("sentences:", sentences, min_level=2)
    for sentence in sentences:
        dmsg("sentence:", sentence, min_level=2)

        clauses = split(r'\s+[-–—]\s+', sentence)
        dmsg("clauses:", clauses, min_level=2)
        for clause in clauses:
            dmsg("clause:", clause, min_level=2)

            words = findall(r'[^\s.]+', clause)
            dmsg("words:", words, min_level=2)

            offset = 0
            while offset < len(words):
                translation = None

                for i in reversed(range(offset + 1, len(words) + 1)):
                    phrase = ' '.join(words[offset:i])

                    dmsg("phrase:", phrase, min_level=2)

                    translation = translate(phrase)

                    if translation is not None:
                        dmsg("phrase-translation:", translation, min_level=2)
                        dmsg("words[{0}:{1}] = [\"{2}\"]".format(offset, i, translation), min_level=2)
                        words[offset:i] = [translation]
                        offset += i - 1
                        break

                if translation is None:
                    dmsg("phrase-translation:", translation, min_level=2)
                    offset += 1

            dmsg("words-translation:", words, min_level=2)