-
Notifications
You must be signed in to change notification settings - Fork 32
/
morTrans.py
258 lines (247 loc) · 8.93 KB
/
morTrans.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
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
# -*- coding: utf-8 -*-
def loadDict():
file_dict = open('dir.txt','rb')
Dict = {}
for line in file_dict.readlines():
tmp=[]
lineVec = str(line).strip().split('\\xef\\xa3\\xb5')
for content in lineVec[1:-1]:
if '.' in str(content) :#and len(content)<=6:
tmp.append(content)
Dict[lineVec[0]] = tmp
Dict_final ={}
for key in Dict.keys():
Dict_final[key.replace("b'",'')] = Dict[key]
return Dict_final
def htmlParse():
import re
from bs4 import BeautifulSoup
file_html = open('HTML.html','rb')
file_txt = open('irregular verbs.txt','w+')
soup = BeautifulSoup(file_html,'html.parser')
tr = soup.find_all('tr')
for i in range(1,len(tr)):
tmpStr = ''
tds = tr[i].find_all('td')
#print(tds[1])
L1 = tds[1].text.strip().split(',')
L2 = tds[2].text.strip().split(',')
tmpStr = tmpStr + str(tds[0].text.strip())
for content in L1:
tmpStr = tmpStr +'\t'+ str(content)
for content in L2:
tmpStr = tmpStr + '\t' + str(content)
tmpStr = tmpStr + '\n'
file_txt.write(tmpStr)
def loadIrVerb(): # 读入不规则动词表
file_dict = open('irregular verbs.txt','rb')
Dict = {}
for line in file_dict.readlines():
lineVec = str(line).replace('\\r\\n','').split('\\t')
for word in lineVec[1:-1]:
Dict[str(word)] = str(lineVec[0])
return Dict
def loadIrNoun():
file_dict = open('irregular nouns.txt','rb')
Dict = {}
for line in file_dict.readlines():
lineVec = str(line).strip().split('\\t')
#print(lineVec[1],lineVec[3])
Dict[lineVec[3]] = lineVec[1]
return Dict
def verbJudge(word,wholeDict):
flag = False
if 'ies' == word[-3:len(word)]:
tmp = word[0:-3]+'y'
if tmp in wholeDict.keys():
print("original form: " + tmp)
tmpStr = ''
for inst in wholeDict[tmp]:
tmpStr += (inst + '\t')
print("part of speech: " + tmpStr)
flag = True
if not flag:
if 'es' == word[-2:len(word)]:
tmp = word[0:-2]
if tmp in wholeDict.keys():
print("original form: " + tmp)
tmpStr = ''
for inst in wholeDict[tmp]:
tmpStr += (inst + '\t')
print("part of speech: " + tmpStr)
flag = True
if not flag:
if 's' == word[-1:len(word)]:
tmp = word[0:-1]
if tmp in wholeDict.keys():
print("original form: " + tmp)
tmpStr = ''
for inst in wholeDict[tmp]:
tmpStr += (inst + '\t')
print("part of speech: " + tmpStr)
flag = True
if not flag:
if 'ing' == word[-3:len(word)] and word[-4] == word[-5]:
tmp = word[0:-4]
if tmp in wholeDict.keys():
print("original form: " + tmp)
tmpStr = ''
for inst in wholeDict[tmp]:
tmpStr += (inst + '\t')
print("part of speech: " + tmpStr)
flag = True
if not flag:
if 'ying' == word[-4:len(word)]:
tmp = word[0:-4] + 'ie'
if tmp in wholeDict.keys():
print("original form: " + tmp)
tmpStr = ''
for inst in wholeDict[tmp]:
tmpStr += (inst + '\t')
print("part of speech: " + tmpStr)
flag = True
if not flag:
if 'ing' == word[-3:len(word)]:
if word[0:-3] in wholeDict.keys():
tmp = word[0:-3]
print("original form: " + tmp)
tmpStr = ''
for inst in wholeDict[tmp]:
tmpStr += (inst + '\t')
print("part of speech: " + tmpStr)
flag = True
elif word[0:-3]+'e' in wholeDict.keys():
tmp = word[0:-3]+'e'
print("original form: " + tmp)
tmpStr = ''
for inst in wholeDict[tmp]:
tmpStr += (inst + '\t')
print("part of speech: " + tmpStr)
flag = True
if not flag:
if 'ed' == word[-2:len(word)] and word[-3]==word[-4]:
tmp = word[0:-2] + word[-3]
if tmp in wholeDict.keys():
print("original form: " + tmp)
tmpStr = ''
for inst in wholeDict[tmp]:
tmpStr += (inst + '\t')
print("part of speech: " + tmpStr)
flag = True
if not flag:
if 'ied' == word[-3:len(word)]:
tmp = word[0:-3] + 'y'
if tmp in wholeDict.keys():
print("original form: " + tmp)
tmpStr = ''
for inst in wholeDict[tmp]:
tmpStr += (inst + '\t')
print("part of speech: " + tmpStr)
flag = True
if not flag:
if 'ed' == word[-2:len(word)]:
if word[0:-2] in wholeDict.keys():
tmp = word[0:-2]
print("original form: " + tmp)
tmpStr = ''
for inst in wholeDict[tmp]:
tmpStr += (inst + '\t')
print("part of speech: " + tmpStr)
flag = True
elif word[0:-2]+'e' in wholeDict.keys():
tmp = word[0:-2]+'e'
print("original form: " + tmp)
tmpStr = ''
for inst in wholeDict[tmp]:
tmpStr += (inst + '\t')
print("part of speech: " + tmpStr)
flag = True
return flag
def nounJudge(word,wholeDict):
flag = False
if 'ves' == word[-3:len(word)]:
if word[0:-3]+'f' in wholeDict.keys():
tmp = word[0:-3]+'f'
print("original form: " + tmp)
tmpStr = ''
for inst in wholeDict[tmp]:
tmpStr += (inst + '\t')
print("part of speech: " + tmpStr)
flag = True
elif word[0:-3] + 'fe' in wholeDict.keys():
tmp = word[0:-3]+'fe'
print("original form: " + tmp)
tmpStr = ''
for inst in wholeDict[tmp]:
tmpStr += (inst + '\t')
print("part of speech: " + tmpStr)
flag = True
if not flag and 'ies' == word[-3:len(word)]:
if word[0:-3]+'y' in wholeDict.keys():
tmp = word[0:-3]+'y'
print("original form: " + tmp)
tmpStr = ''
for inst in wholeDict[tmp]:
tmpStr += (inst + '\t')
print("part of speech: " + tmpStr)
flag = True
if not flag and 'es' == word[-2:len(word)]:
if word[0:-2] in wholeDict.keys():
tmp = word[0:-2]
print("original form: " + tmp)
tmpStr = ''
for inst in wholeDict[tmp]:
tmpStr += (inst + '\t')
print("part of speech: " + tmpStr)
flag = True
if not flag and 's'==word[len(word)-1]:
if word[0:-1] in wholeDict.keys():
tmp = word[0:-1]
print("original form: " + tmp)
tmpStr = ''
for inst in wholeDict[tmp]:
tmpStr += (inst + '\t')
print("part of speech: " + tmpStr)
flag = True
return flag
def otherJudge(word,wholeDict):
flag = False
flag = verbJudge(word, wholeDict)
if not flag:
flag = nounJudge(word, wholeDict)
return flag
def main():
irVerbDict = loadIrVerb()
irNounDict = loadIrNoun()
wholeDict = loadDict()
#print(irNounDict)
wordInput = input("Input an English word: ")
if wordInput in wholeDict.keys():
#print("1")
print("original form: " + wordInput)
tmpStr = ''
for inst in wholeDict[wordInput]:
tmpStr += (inst+'\t')
print("part of speech: " + tmpStr)
elif wordInput in irVerbDict.keys():
#print("2")
print("original form: " + irVerbDict[wordInput])
tmpStr = ''
for inst in wholeDict[irVerbDict[wordInput]]:
tmpStr += (inst + '\t')
print("part of speech: " + tmpStr)
elif wordInput in irNounDict.keys():
#print("3")
print("original form: " + irNounDict[wordInput])
tmpStr = ''
for inst in wholeDict[irNounDict[wordInput]]:
tmpStr += (inst + '\t')
print("part of speech: " + tmpStr)
else:
#print("4")
flag = otherJudge(wordInput,wholeDict)
if not flag:
print("Transformation Failure......")
if __name__ == '__main__':
while 1:
main()