1
|
|
|
"""Helpers to normalize inputs and text.""" |
2
|
|
|
|
3
|
|
|
import re |
4
|
|
|
import string |
5
|
|
|
from collections import defaultdict |
6
|
|
|
|
7
|
|
|
from nltk.corpus import stopwords |
|
|
|
|
8
|
|
|
|
9
|
|
|
from pattern.vector import PORTER |
|
|
|
|
10
|
|
|
from pattern.vector import stem |
|
|
|
|
11
|
|
|
|
12
|
|
|
import settings as namebot_settings |
|
|
|
|
13
|
|
|
|
14
|
|
|
_regexes = namebot_settings.regexes |
15
|
|
|
|
16
|
|
|
|
17
|
|
|
def flatten(lst): |
18
|
|
|
"""Flatten a list with arbitrary levels of nesting. |
19
|
|
|
|
20
|
|
|
CREDIT: http://stackoverflow.com/questions/10823877/ |
21
|
|
|
what-is-the-fastest-way-to-flatten-arbitrarily-nested-lists-in-python |
22
|
|
|
Changes made include: |
23
|
|
|
1. Adding error handling, |
24
|
|
|
2. Renaming variables, |
25
|
|
|
3. Using `any` instead of `or`. |
26
|
|
|
See http://creativecommons.org/licenses/by-sa/3.0/ for specific details. |
27
|
|
|
|
28
|
|
|
Args: |
29
|
|
|
lst (list): The nested list. |
30
|
|
|
|
31
|
|
|
Returns: |
32
|
|
|
(generator): The new flattened list of words. |
33
|
|
|
""" |
34
|
|
|
if not isinstance(lst, list): |
35
|
|
|
yield [] |
36
|
|
|
for i in lst: |
37
|
|
|
if any([isinstance(i, list), isinstance(i, tuple)]): |
38
|
|
|
for j in flatten(i): |
39
|
|
|
yield j |
40
|
|
|
else: |
41
|
|
|
yield i |
42
|
|
|
|
43
|
|
|
|
44
|
|
|
def remove_odd_sounding_words(words): |
45
|
|
|
"""Remove random odd sounding word combinations via regular expressions. |
46
|
|
|
|
47
|
|
|
Args: |
48
|
|
|
words (list): The list of words |
49
|
|
|
|
50
|
|
|
Returns: |
51
|
|
|
list: An updated word list with words cleaned. |
52
|
|
|
""" |
53
|
|
|
odd_regexes = [ |
54
|
|
|
re.compile(r'^a|e|i|o|u|y{3,6}'), |
55
|
|
|
# bk, ck, dk, gk, etc... |
56
|
|
|
re.compile(r'\b[^aeiouys]k|zt|ksd|kd|zhr'), |
57
|
|
|
re.compile(r'\bzt|ksd|kd|zhr') |
58
|
|
|
] |
59
|
|
|
cleaned = [] |
60
|
|
|
if words is None or len(words) == 0: |
61
|
|
|
return words |
62
|
|
|
# Loop through any number of |
63
|
|
|
# regexes and add only if no matches exist |
64
|
|
|
[cleaned.append(word) for word in words if not any( |
|
|
|
|
65
|
|
|
re.match(regex, word) for regex in odd_regexes)] |
66
|
|
|
return cleaned |
67
|
|
|
|
68
|
|
|
|
69
|
|
|
def stem_words(words): |
70
|
|
|
"""Stem words to their base linguistic stem to remove redundancy. |
71
|
|
|
|
72
|
|
|
Args: |
73
|
|
|
words (list): The list of words |
74
|
|
|
|
75
|
|
|
Returns: |
76
|
|
|
list: An updated word list with words stemmed. |
77
|
|
|
""" |
78
|
|
|
return [stem(word, stemmer=PORTER) for word in words] |
79
|
|
|
|
80
|
|
|
|
81
|
|
|
def remove_stop_words(words): |
82
|
|
|
"""Remove all stop words. |
83
|
|
|
|
84
|
|
|
Args: |
85
|
|
|
words (list): The list of words |
86
|
|
|
|
87
|
|
|
Returns: |
88
|
|
|
list: An updated word list with stopwords removed. |
89
|
|
|
""" |
90
|
|
|
# http://stackoverflow.com/questions/5486337/ |
91
|
|
|
# how-to-remove-stop-words-using-nltk-or-python |
92
|
|
|
return [w for w in words if w.lower() not in stopwords.words('english')] |
93
|
|
|
|
94
|
|
|
|
95
|
|
|
def remove_bad_words(words): |
96
|
|
|
"""Remove naughty words that might come from wordnet synsets and lemmata. |
97
|
|
|
|
98
|
|
|
Args: |
99
|
|
|
words (list): The list of words |
100
|
|
|
|
101
|
|
|
Returns: |
102
|
|
|
list: An updated word list with bad words removed. |
103
|
|
|
""" |
104
|
|
|
bad_words = ["nigger", "wop", |
105
|
|
|
"kike", "faggot", |
106
|
|
|
"fuck", "pussy", "cunt"] |
107
|
|
|
return [word for word in words if word.lower() not in bad_words] |
108
|
|
|
|
109
|
|
|
|
110
|
|
|
def filter_words(words): |
111
|
|
|
"""Filter words by default min/max settings in the settings module. |
112
|
|
|
|
113
|
|
|
Args: |
114
|
|
|
words (list): The list of words |
115
|
|
|
|
116
|
|
|
Returns: |
117
|
|
|
list: The filtered words |
118
|
|
|
""" |
119
|
|
|
new_arr = [] |
120
|
|
|
for word in words: |
121
|
|
|
if not re.search(' ', word): |
122
|
|
|
lte = len(word) <= namebot_settings.MAX_LENGTH |
123
|
|
|
gte = len(word) >= namebot_settings.MIN_LENGTH |
124
|
|
|
if all([lte, gte]): |
125
|
|
|
new_arr.append(word) |
126
|
|
|
elif re.search(' ', word): |
127
|
|
|
split = re.split(' ', word) |
128
|
|
|
split_join = [] |
129
|
|
|
for chunks in split: |
130
|
|
|
length = len(chunks) |
131
|
|
|
lte = length <= namebot_settings.SPACED_MAX_LENGTH |
132
|
|
|
gte = length >= namebot_settings.MIN_LENGTH |
133
|
|
|
if all([lte, gte]): |
134
|
|
|
split_join.append(chunks) |
135
|
|
|
new_arr.append( |
136
|
|
|
' '.join(split_join)) |
137
|
|
|
return new_arr |
138
|
|
|
|
139
|
|
|
|
140
|
|
|
def uniquify(words): |
141
|
|
|
"""Remove duplicates from a list. |
142
|
|
|
|
143
|
|
|
Args: |
144
|
|
|
words (list): The list of words |
145
|
|
|
|
146
|
|
|
Returns: |
147
|
|
|
list: An updated word list with duplicates removed. |
148
|
|
|
""" |
149
|
|
|
return {}.fromkeys(words).keys() if words is not None else words |
150
|
|
|
|
151
|
|
|
|
152
|
|
|
def clean_sort(words): |
153
|
|
|
"""A function for cleaning and prepping words for techniques. |
154
|
|
|
|
155
|
|
|
Args: |
156
|
|
|
words (list): The list of words |
157
|
|
|
|
158
|
|
|
Returns: |
159
|
|
|
list: An updated word list with words cleaned and sorted. |
160
|
|
|
""" |
161
|
|
|
if isinstance(words, basestring): |
|
|
|
|
162
|
|
|
return words |
163
|
|
|
chars = '!"#$%\'()*+,._/:;<=>?@[\\]^`{|}~01234567890' |
164
|
|
|
if words is not None: |
165
|
|
|
try: |
166
|
|
|
words = [word.strip().lower().translate( |
167
|
|
|
string.maketrans('', ''), |
|
|
|
|
168
|
|
|
chars) for word in words if len(word) > 1] |
169
|
|
|
except TypeError: |
|
|
|
|
170
|
|
|
pass |
171
|
|
|
return words |
172
|
|
|
|
173
|
|
|
|
174
|
|
|
def chop_duplicate_ends(word): |
175
|
|
|
"""Remove duplicate letters on either end, if the are adjacent. |
176
|
|
|
|
177
|
|
|
Args: |
178
|
|
|
words (list): The list of words |
179
|
|
|
|
180
|
|
|
Returns: |
181
|
|
|
list: An updated word list with duplicate ends removed for each word. |
182
|
|
|
""" |
183
|
|
|
if word[0] == word[1]: |
184
|
|
|
word = word[1:] |
185
|
|
|
if word[-2:-1] == word[-1:]: |
186
|
|
|
word = word[:-1] |
187
|
|
|
return word |
188
|
|
|
|
189
|
|
|
|
190
|
|
|
def key_words_by_pos_tag(words): |
191
|
|
|
"""Key words by the pos tag name, given when using pos_tag on a list. |
192
|
|
|
|
193
|
|
|
Args: |
194
|
|
|
words (list): The list of words, where each item is a 2-tuple. |
195
|
|
|
|
196
|
|
|
Returns: |
197
|
|
|
dict: An updated dictionary keyed by pos tag, |
198
|
|
|
with values as a list of matching pos matching words. |
199
|
|
|
""" |
200
|
|
|
alltags = defaultdict(list) |
201
|
|
|
for word, pos in words: |
202
|
|
|
alltags[pos].append(word) |
203
|
|
|
return alltags |
204
|
|
|
|
This can be caused by one of the following:
1. Missing Dependencies
This error could indicate a configuration issue of Pylint. Make sure that your libraries are available by adding the necessary commands.
2. Missing __init__.py files
This error could also result from missing
__init__.py
files in your module folders. Make sure that you place one file in each sub-folder.