Subversion Repositories LCARS

Rev

Rev 292 | Go to most recent revision | Details | Last modification | View Log | RSS feed

Rev Author Line No. Line
291 PointedEar 1
'''
2
Created on 2014-10-20
3
 
4
@author: Thomas 'PointedEars' Lahn <mail@PointedEars.de>
5
'''
6
from sys import argv, stderr
7
from re import findall, DOTALL, IGNORECASE, match, sub, compile, \
8
    split
9
from os import chdir
10
from os.path import dirname, realpath
11
from collections import OrderedDict
12
from functools import cmp_to_key
13
from copy import deepcopy
14
from collections.abc import MutableSequence
15
 
16
dictionary = {}
17
 
18
prepositions = {
19
    "fi'": 'on',
20
    "na'": 'at|to',
21
    "t'": 'of'
22
}
23
 
24
class MutableString2(MutableSequence):
25
    def __init__(self, value=None):
26
        self._values = [str(value)] if value is not None else []
27
 
28
    def __add__(self, value):
29
        return ''.join([self, value])
30
 
31
    def __delitem__(self):
32
        raise NotImplementedError
33
 
34
    def __getitem__(self, index):
35
        return str(self)[index]
36
 
37
    def __len__(self):
38
        return len(str(self))
39
 
40
    def __repr__(self):
41
        return ''.join(self._values)
42
 
43
    def __setitem__(self, index, value):
44
        raise NotImplementedError
45
 
46
    def __str__(self):
47
        return self.__repr__()
48
 
49
    def extend(self, values):
50
        self._values.append(values)
51
 
52
    def insert(self, index, value):
53
        raise NotImplementedError
54
 
55
def load_dictionary(dictionary, dictionary_file):
56
    print('Loading dictionary {0} ...'.format(dictionary_file), end='', file=stderr)
57
 
58
    chdir(dirname(realpath(__file__)))
59
    with open(dictionary_file) as f:
60
        keys = "ipa|en|lit|pos|com|tag|ex"
61
        indent = None
62
        value = None
63
 
64
        for line in f:
65
            m = match(r'^\s*vuh:\s*(?P<phrase>.+)', line)
66
            if m is not None:
67
                phrase = m.group("phrase")
68
                dictionary[phrase] = {}
69
                indent = None
70
            else:
71
                m = match(
72
                    r'(?P<indent>\s*)(?P<key>{0}):\s*(?P<value>.+)'.format(keys),
73
                    line)
74
                if m is not None:
75
                    indent = m.group("indent")
76
                    key = m.group("key")
77
                    value = m.group("value")
78
                    value = dictionary[phrase][key] = MutableString2(value)
79
                elif indent is not None:
80
                    m = match(r'(?P<indent>\s+)(?P<continuation>\S.*)', line)
81
                    if m is not None:
82
                        if len(m.group("indent")) == len(indent) + 2:
83
                            dictionary[phrase][key] += (" " + m.group("continuation"))
84
 
85
    print(' done ({0} entries).'.format(len(dictionary)), file=stderr)
86
 
87
def clean_dictionary(dictionary):
88
    braces_re = compile(r'^\s*\{(.+)\}\s*$')
89
    semicolon_re = compile(r'\s*;\s*')
90
 
91
    for orig_phrase, data in list(dictionary.items()):
92
        if orig_phrase.find(";") > -1:
93
            synonyms = map(
94
                lambda x: sub(braces_re, r'\1', orig_phrase),
95
                split(semicolon_re, orig_phrase))
96
 
97
            for synonym in synonyms:
98
                dictionary[synonym] = deepcopy(data)
99
 
100
            del dictionary[orig_phrase]
101
        else:
102
            m = match(braces_re, orig_phrase)
103
            if m is not None:
104
                dictionary[m.group(1)] = deepcopy(dictionary[orig_phrase])
105
                del dictionary[orig_phrase]
106
 
107
def sort_dict_alnum_english_key(phrase):
108
    return sub(r'\{(.+)\}', r'\1', phrase[0]).lower()
109
 
110
def get_sort_dict_alnum_vulcan_key():
111
    letters = list(map(str.lower, [
112
        " ", 'S', 'T', 'P', 'K', 'R', 'L', 'A', 'Sh', 'O', 'U', 'D',
113
        'V', 'Kh', 'E', 'H', 'G', 'Ch', 'I', 'N', 'Zh', 'M', 'Y', 'F', 'Z',
114
        'Th', 'W', 'B', "'", '-']))
115
    letter_values = dict(map(lambda x: (x[1], x[0]), enumerate(letters)))
116
    letters_re = compile(r'(?:{0})'.format('|'.join(sorted(letters, key=lambda char:-len(char)))))
117
 
118
    def sort_dict_alnum_vulcan (a, b):
119
        # split into Vulcan letters
120
        a = findall(letters_re, sort_dict_alnum_english_key(a))
121
        b = findall(letters_re, sort_dict_alnum_english_key(b))
122
 
123
        if len(a) < len(b):
124
            for index, char in enumerate(a):
125
                diff = letter_values[char] - letter_values[b[index]]
126
                if diff != 0:
127
                    return diff
128
            return -1
129
 
130
        # len(b) <= len(a)
131
        for index, char in enumerate(b):
132
            diff = letter_values[a[index]] - letter_values[char]
133
            if diff != 0:
134
                return diff
135
 
136
        return 1 if len(b) < len(a) else 0
137
 
138
    return cmp_to_key(sort_dict_alnum_vulcan)
139
 
140
def translate (word, recursion=False):
141
    translation = dictionary.get(word.lower(), None)
142
    if translation is not None:
143
        translation = translation["en"]
144
        if match('[A-Z]', word):
145
            return sub('[a-z]', lambda ch: ch.group(0).upper(), str(translation), count=1)
146
        return translation
147
 
148
    if not recursion:
149
        # prepositions attached?
150
        for prep, prep_transl in prepositions.items():
151
            if (match(prep, word)):
152
                real_word = word.replace(r'^' + prep, '')
153
                real_word_transl = translate(real_word, recursion=True)
154
                if real_word_transl is not None:
155
                    return prep_transl + ' ' + real_word_transl
156
 
157
    if recursion:
158
        return None
159
    else:
160
        # Not in dictionary: proper name or missing for other reasons
161
        return '{{{0}}}'.format(word)
162
 
163
if __name__ == '__main__':
164
    load_dictionary(dictionary, 'vuh-gol-en.dict.zdb.txt')
165
    clean_dictionary(dictionary)
166
 
167
#     try:
168
#         for phrase, data in OrderedDict(sorted(
169
#             dictionary.items(),
170
#             key=get_sort_dict_alnum_vulcan_key()
171
#         )).items():
172
#             print(phrase, "=", data)
173
#     except BrokenPipeError:
174
#         pass
175
 
176
    text = argv[1]
177
    sentences = findall(r'(?!\s+)(?:.+?\.{1,3}|.+$)', text, DOTALL)
178
    for sentence in sentences:
179
        print(sentence)
180
 
181
        words = findall(r"(?!\s+)[a-z'-]{2,}", sentence, IGNORECASE)
182
        print(words)
183
 
184
        translated_words = list(map(translate, words))
185
        print(translated_words)
186
 
187
        for index, word in enumerate(words):
188
            sentence = sentence.replace(word, str(translated_words[index]))
189
        print(sentence)
190
 
191
        # replace punctuation
192
        for symbol, replacement in ({" - ": ", "}).items():
193
            sentence = sentence.replace(symbol, replacement)
194
 
195
        print(sentence)