encode.py
4.42 KB
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
'''
Created on Oct 23, 2013
@author: mlenart
'''
import logging
class Encoder(object):
'''
classdocs
'''
def __init__(self, encoding='utf8'):
'''
Constructor
'''
self.encoding = encoding
def encodeWord(self, word, lowercase=True):
assert type(word) == unicode
res = bytearray(word.lower() if lowercase else word, self.encoding)
return res
def encodeData(self, data):
raise NotImplementedError()
# return bytearray(u'|'.join(data).encode(self.encoding)) + bytearray([0])
def decodeData(self, rawData):
return NotImplementedError()
def decodeWord(self, rawWord):
return unicode(str(rawWord).strip('\x00'), self.encoding)
def word2SortKey(self, word):
return word.lower().encode(self.encoding)
def _encodeTypeNum(self, typenum):
assert typenum >= 0 and typenum < 256
return bytearray([typenum])
def _encodeEncodedForm(self, form, withCasePattern):
res = bytearray()
assert form.cutLength < 256 and form.cutLength >= 0
res.append(form.cutLength)
res.extend(self.encodeWord(form.suffixToAdd, lowercase=False))
res.append(0)
if withCasePattern:
res.extend(self._encodeCasePattern(form.casePattern))
return res
def _encodeCasePattern(self, casePattern):
res = bytearray()
if True not in casePattern:
res.append(self.LEMMA_ONLY_LOWER)
return res
elif self._hasUpperPrefix(casePattern):
res.append(self.LEMMA_UPPER_PREFIX)
res.append(self._getUpperPrefixLength(casePattern))
return res
else:
assert len(casePattern) < 256
res.append(self.LEMMA_MIXED_CASE)
res.append(len([c for c in casePattern if c]))
for idx in range(len(casePattern)):
if casePattern[idx]:
res.append(idx)
return res
def _hasUpperPrefix(self, casePattern):
for i in range(len(casePattern) + 1):
if all(casePattern[:i]) and not any(casePattern[i:]):
return True
return False
def _getUpperPrefixLength(self, casePattern):
assert self._hasUpperPrefix(casePattern)
for i in range(len(casePattern)):
if not casePattern[i]:
return i
return len(casePattern)
def _encodeTagNum(self, tagnum):
res = bytearray()
# logging.info((tagnum & 0xFF00) >> 8)
assert tagnum < 65536 and tagnum >= 0
res.append((tagnum & 0xFF00) >> 8)
res.append(tagnum & 0x00FF)
# logging.info('%d %s %s' % (tagnum, hex(res[0]), hex(res[1])))
return res
def _encodeNameNum(self, namenum):
assert namenum < 256 and namenum >= 0
return bytearray([namenum])
class MorphEncoder(Encoder):
def __init__(self, encoding='utf8'):
super(MorphEncoder, self).__init__(encoding)
self.LEMMA_ONLY_LOWER = 0
self.LEMMA_UPPER_PREFIX = 1
self.LEMMA_MIXED_CASE = 2
def encodeData(self, interpsList):
res = bytearray()
# print interpsList
firstByte = len(interpsList)
assert firstByte < 256
assert firstByte > 0
res.append(firstByte)
assert type(interpsList) == frozenset
for interp in sorted(interpsList, key=lambda i: i.getSortKey()):
res.extend(self._encodeTypeNum(interp.typenum))
res.extend(self._encodeEncodedForm(interp.lemma, withCasePattern=True))
res.extend(self._encodeTagNum(interp.tagnum))
res.extend(self._encodeNameNum(interp.namenum))
return res
class Encoder4Generator(Encoder):
def __init__(self, encoding='utf8'):
super(Encoder4Generator, self).__init__(encoding)
def encodeData(self, interpsList):
res = bytearray()
firstByte = len(interpsList)
assert firstByte < 256
assert firstByte > 0
res.append(firstByte)
assert type(interpsList) == frozenset
for interp in sorted(interpsList, key=lambda i: i.getSortKey()):
res.extend(self._encodeEncodedForm(interp.orth, withCasePattern=False))
res.extend(self._encodeTagNum(interp.tagnum))
res.extend(self._encodeNameNum(interp.namenum))
return res
#
# def decodeData(self, data):
#