-
Notifications
You must be signed in to change notification settings - Fork 2
/
ellyBufferEN.py
executable file
·211 lines (177 loc) · 6.65 KB
/
ellyBufferEN.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
#!/usr/bin/python
# PyElly - scripting tool for analyzing natural language
#
# ellyBufferEN.py : 04oct2017 CPM
# ------------------------------------------------------------------------------
# Copyright (c) 2013, Clinton Prentiss Mah
# All rights reserved.
#
# Redistribution and use in source and binary forms, with or without
# modification, are permitted provided that the following conditions are met:
#
# Redistributions of source code must retain the above copyright notice, this
# list of conditions and the following disclaimer.
#
# Redistributions in binary form must reproduce the above copyright notice,
# this list of conditions and the following disclaimer in the documentation
# and/or other materials provided with the distribution.
#
# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
# AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
# DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE
# FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
# DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
# SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
# CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
# OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
# OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
# -----------------------------------------------------------------------------
"""
framework for integrating English inflectional stemming into basic tokenization
"""
import sys
import ellyBuffer
import ellyChar
import ellyStemmer
import ellyException
import ellyConfiguration
import inflectionStemmerEN
APO = ellyChar.APO # literal ASCII apostrophe
APX = u'\u2019' # formatted Unicode apostrophe
ESS = u's' # literal S
SFX = '-' + APO + ESS # -'S suffix
class EllyBufferEN(ellyBuffer.EllyBuffer):
"""
input text buffer with methods for getting successive tokens
attributes:
stemmer - inflectional stemmer
divided - saved flag for next token
"""
def __init__ ( self ):
"""
constructor to set up buffer
arguments:
self -
"""
# print 'init' , super(EllyBufferEN,self)
super(EllyBufferEN,self).__init__()
if ellyConfiguration.inflectionalStemming: # English inflectional stemmer?
try: # of so, try to load
self.stemmer = inflectionStemmerEN.InflectionStemmerEN()
except ellyException.TableFailure:
self.stemmer = ellyStemmer.EllyStemmer() # null stemmer
print >> sys.stderr , 'stemmer failure'
else:
self.stemmer = ellyStemmer.EllyStemmer() # null stemmer
self.divided = False
def getNext ( self ):
"""
override EllyBuffer method to get next token from buffer
with automatic inflectional stemming
arguments:
self
returns:
a token or None if buffer is empty
exceptions:
StemmingError
"""
# print super(EllyBufferEN,self) , 'EN getNext'
# print 'buffer=' , self.buffer
w = super(EllyBufferEN,self).getNext() # use getNext() without inflectional stemmer
if w == None: return None
# print 'got unstemmed:' , w , 'divided=' , self.divided
if self.divided:
w.dvdd = True
self.divided = False
if not w.isSplit(): # check for stemming
self.divide(w) # if not, do inflectional stemming
# print 'return token=' , w
# print 'EN extracted'
# print 'buffer=' , self.buffer
return w
def putSuffixBack ( self , suffix ):
"""
return suffix to input buffer
arguments:
self -
suffix - as a string
"""
# print 'EN put back' , suffix
if self.atToken(): self.prepend(ellyChar.SPC)
self.prepend(suffix)
def divide ( self , word ):
"""
apply inflectional analysis, including for -'s and -s'
arguments:
self -
word - ellyToken
exceptions:
StemmingError
"""
# print "divide" , word
wl = word.getLength() # if so, is word long enought to be divided
if wl < 3:
return # if not, done
if word.isAffix(): # if term is already product of division, stop
return
# print 'word suffixes=' , word.sufs , word.dvdd
x = word.charAt(wl-1) # get last two chars of word
y = word.charAt(wl-2)
# print 'word= ...' , y , x
if x == ESS and (
y == APO or y == APX # check for -'S
):
# print "-'s ending"
word.shortenBy(2)
self.putSuffixBack(SFX)
# print 'word=' , word , 'without -\'S'
return
elif y == ESS and (
x == APO or x == APX # check for implied -'S
):
# print "-s' ending"
word.shortenBy(1)
self.putSuffixBack(SFX)
# print 'word=' , word , 'without -\''
return
if ellyChar.isLetter(word.charAt(0)):
# print 'apply stemmer'
self.stemmer.apply(word) # apply any inflectional stemmer
# print 'word= ' , word
if word.isSplit():
# print 'is split'
sufs = word.getSuffixes()
# print 'pres=' , word.getPrefixes()
# print 'sufs=' , sufs
while len(sufs) > 0:
self.putSuffixBack(sufs.pop())
#
# unit test
#
if __name__ == "__main__":
buf = EllyBufferEN()
print 'enter text lines to get tokens from'
while True:
try:
sys.stdout.write("> ")
l = sys.stdin.readline().decode('utf8')
except KeyboardInterrupt:
break
l = l.strip()
if len(l) == 0: break
buf.clear()
buf.append(list(l))
print buf.buffer
try:
while True:
print "len=" , len(buf.buffer)
t = buf.getNext()
if t == None: break
print ">>>> " , unicode(t)
print ">>>> " , t.pres , t.sufs
except ellyException.StemmingError:
print >> sys.stderr , 'stemming error'
continue
print "------------"
sys.stdout.write("\n")