-
Notifications
You must be signed in to change notification settings - Fork 4
/
Copy pathrhyme.py
217 lines (210 loc) · 6.35 KB
/
rhyme.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
import operator
import functools
from nltk.corpus import cmudict
e = cmudict.entries()
d = cmudict.dict()
def make_word_list(tokenized_text):
word_list = []
for i in tokenized_text:
if (i.lower() == "'s") and (d.get(i.lower()) is not None):
pass
elif i[-1] == "." and (d.get(i.lower()) is not None):
pass
elif d.get(i.lower()) is not None:
word_list.append((i.lower(), d[i.lower()][0]))
return word_list
def unique(s):
u = []
for x in s:
if x not in u:
u.append(x)
else:
pass
return u
def meter(word):
pron = d[word]
m1 = []
m2 = []
mx = []
if len(pron) == 1:
for i in pron[0]:
if '0' in i:
m1.append(0)
elif '1' in i:
m1.append(1)
elif '2' in i:
m1.append(2)
else:
pass
mx = [m1]
elif len(pron) >= 2:
for i in pron[0]:
if '0' in i:
m1.append(0)
elif '1' in i:
m1.append(1)
elif '2' in i:
m1.append(2)
else:
pass
for i in pron[1]:
if '0' in i:
m2.append(0)
elif '1' in i:
m2.append(1)
elif '2' in i:
m2.append(2)
else:
pass
mx = [m1, m2]
m = []
if len(mx) == 1:
w0 = functools.reduce(operator.mul, mx[0], 1)
if w0 >= 2:
for i in mx[0]:
if i == 1:
m.append('u')
elif i == 2:
m.append('s')
elif w0 == 1:
for i in mx[0]:
m.append('s')
elif w0 == 0:
for i in mx[0]:
if i == 0:
m.append('u')
elif i == 1 or i == 2:
m.append('s')
elif len(mx) == 2:
w0 = functools.reduce(operator.mul, mx[0], 1)
w1 = functools.reduce(operator.mul, mx[1], 1)
if w0 >= 2 and w1 >= 2:
for (i, j) in zip(mx[0], mx[1]):
if i * j == 1:
m.append('u')
elif i * j == 4:
m.append('s')
elif i * j == 2:
m.append('x')
elif w0 == 1 and w1 == 1:
for (i, j) in zip(mx[0], mx[1]):
m.append('s')
elif w0 == 0 and w1 == 0:
for (i, j) in zip(mx[0], mx[1]):
if i == j and i * j >= 1:
m.append('s')
elif i != j and i * j == 0:
m.append('x')
elif i == j and i * j == 0:
m.append('u')
elif w0 >= 2 and w1 == 0:
for (i, j) in zip(mx[0], mx[1]):
if i == 1 and j == 0:
m.append('u')
elif ((i == 2 and j == 0)
or (i == 1 and j == 1)
or (i == 1 and j == 2)):
m.append('x')
elif ((i == 2 and j == 1)
or (i == 2 and j == 2)):
m.append('s')
elif w0 == 0 and w1 >= 2:
for (i, j) in zip(mx[0], mx[1]):
if i == 0 and j == 1:
m.append('u')
elif ((i == 0 and j == 2)
or (i == 1 and j == 1)
or (i == 2 and j == 1)):
m.append('x')
elif ((i == 1 and j == 2)
or (i == 2 and j == 2)):
m.append('s')
elif w0 == 1 and w1 >= 2:
for (i, j) in zip(mx[0], mx[1]):
if j == 1:
m.append('x')
elif j == 2:
m.append('s')
elif w0 >= 2 and w1 == 1:
for (i, j) in zip(mx[0], mx[1]):
if i == 1:
m.append('x')
elif i == 2:
m.append('s')
elif w0 == 1 and w1 == 0:
for (i, j) in zip(mx[0], mx[1]):
if j == 0:
m.append('x')
elif j == 1 or j == 2:
m.append('s')
elif w0 == 0 and w1 == 1:
for (i, j) in zip(mx[0], mx[1]):
if i == 0:
m.append('x')
if i == 1 or i == 2:
m.append('s')
return m
def strip_numbers(x):
xj = '.'.join(x)
xl = re.split('0|1|2', xj)
xjx = ''.join(xl)
xlx = xjx.split('.')
return xlx
def last_stressed_vowel(word):
if len(d[word]) <= 1:
pron = d[word][0]
else:
p0 = d[word][0]
p1 = d[word][1]
sj0 = ''.join(p0)
sl0 = re.split('0|1|2', sj0)
sj1 = ''.join(p1)
sl1 = re.split('0|1|2', sj1)
if len(sl1) < len(sl0):
pron = p1
else:
pron = p0
mtr = meter(word)
vowel_index = []
if len(mtr) == 1:
lsv = -1
for i in range(-1, -11, -1):
if mtr[i] == 's' or mtr[i] == 's':
lsv = i
else:
lsv = -1
for i in pron:
if ('0' in i) or ('1' in i) or ('2' in i):
vowel_index.append(pron.index(i))
else:
continue
return vowel_index[lsv]
def rhyme_finder(word, tokenized_text):
word_list = make_word_list(tokenized_text)
word_list_u = unique(word_list)
rhyming_words = []
if len(d[word]) <= 1:
pron = d[word][0]
else:
p0 = d[word][0]
p1 = d[word][1]
sj0 = ''.join(p0)
sl0 = re.split('0|1|2', sj0)
sj1 = ''.join(p1)
sl1 = re.split('0|1|2', sj1)
if len(sl1) < len(sl0):
pron = p1
else:
pron = p0
pron = strip_numbers(pron)
lsv = last_stressed_vowel(word)
rhyme_part = pron[lsv:]
lrp = len(rhyme_part) * -1
for (x, y) in word_list_u:
ps = strip_numbers(y)
if ps[lrp:] == rhyme_part and ps[lrp-1:] != pron[lsv-1:]:
rhyming_words.append(x)
else:
pass
rw = [i for i in rhyming_words if not (i == word)]
return rw