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
|
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
|
-
+
+
+
-
+
+
+
+
-
+
+
-
+
-
+
-
+
-
-
+
-
-
+
-
+
-
+
-
-
+
+
+
+
+
+
+
+
-
-
+
+
+
+
+
+
+
+
+
+
+
-
-
+
+
+
+
+
+
+
+
+
+
+
-
-
-
-
-
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
-
+
-
-
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
-
+
-
+
-
+
-
+
-
+
+
+
+
+
+
+
+
+
-
-
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
-
-
+
+
+
+
+
+
-
-
+
+
+
+
|
if not bValid:
del lPointer[i]
for dNode in self._getNextMatchingNodes(dToken, dGraph):
lPointer.append({"nOffset": 0, "dNode": dNode})
for dPointer in lPointer:
if "<rules>" in dPointer["dNode"]:
for dNode in dGraph[dPointer["dNode"]["<rules>"]]:
dErr = self._executeActions(dNode)
dErr = self._executeActions(dNode, nOffset)
return dErr
def _getNextMatchingNodes (self, dToken, dNode):
# token value
if dToken["sValue"] in dNode:
yield dGraph[dNode[dToken["sValue"]]]
# token lemmas
for sLemma in dToken["sLemma"]:
for sLemma in dToken["lLemma"]:
if sLemma in dNode:
yield dGraph[dNode[sLemma]]
# universal arc
if "*" in dNode:
yield dGraph[dNode[dToken["sValue"]]]
def _executeActions (self, dNode):
def _executeActions (self, dNode, nOffset):
for sLineId, nextNodeKey in dNode.items():
for sArc in dGraph[nextNodeKey]:
bCondMemo = None
sFuncCond, cActionType, sWhat, *eAct = dRule[sArc]
# action in lActions: [ condition, action type, replacement/suggestion/action[, iGroupStart, iGroupEnd[, message, URL]] ]
try:
bCondMemo = not sFuncCond or globals()[sFuncCond](self, dDA, sCountry, bCondMemo)
bCondMemo = not sFuncCond or globals()[sFuncCond](self, sCountry, bCondMemo)
if bCondMemo:
if cActionType == "-":
# grammar error
nErrorStart = nSentenceOffset + m.start(eAct[0])
nErrorEnd = nSentenceOffset + m.start(eAct[1])
if nErrorStart not in dErrs or nPriority > dPriority[nErrorStart]:
dErrs[nErrorStart] = _createError(self, sWhat, nErrorStart, nErrorEnd, sLineId, bUppercase, eAct[2], eAct[3], bIdRule, sOption, bContext)
dPriority[nErrorStart] = nPriority
elif cActionType == "~":
# text processor
self.lToken = _rewrite(self, sWhat, nErrorStart, nErrorEnd, bUppercase)
self._rewrite(sWhat, nErrorStart, nErrorEnd)
bChange = True
# text processor
# jump
self.lToken = _rewrite(self, sWhat, nErrorStart, nErrorEnd, bUppercase)
bChange = True
globals()[sWhat](self, dDA)
globals()[sWhat](self.lToken)
elif cActionType == ">":
# we do nothing, this test is just a condition to apply all following actions
pass
else:
echo("# error: unknown action at " + sLineId)
print("# error: unknown action at " + sLineId)
elif cActionType == ">":
break
except Exception as e:
raise Exception(str(e), "# " + sLineId + " # " + sRuleId)
def _createWriterError (self):
d = {}
return d
def _createDictError (self):
d = {}
return d
#### Common functions
def _rewrite (self, sWhat, nErrorStart, nErrorEnd):
"text processor: rewrite tokens between <nErrorStart> and <nErrorEnd> position"
lTokenValue = sWhat.split("|")
if len(lTokenValue) != (nErrorEnd - nErrorStart + 1):
print("Error. Text processor: number of replacements != number of tokens.")
return
for i, sValue in zip(range(nErrorStart, nErrorEnd+1), lTokenValue):
self.lToken[i]["sValue"] = sValue
def option ():
pass
def _jump (self, sWhat):
try:
nFrom, nTo = sWhat.split(">")
self.lToken[int(nFrom)]["iJump"] = int(nTo)
except:
print("# Error. Jump failed: ", sWhat)
traceback.print_exc()
return
#### Analyse tokens
def g_morph (dToken, sPattern, bStrict=True):
"analyse a token, return True if <sPattern> in morphologies"
if "lMorph" in dToken:
def morph ():
pass
def morphex ():
pass
def analyse ():
pass
def g_morphex (dToken, sPattern, sNegPattern):
"analyse a token, return True if <sNegPattern> not in morphologies and <sPattern> in morphologies"
if "lMorph" in dToken:
lMorph = dToken["lMorph"]
else:
if dToken["sValue"] not in _dAnalyses and not _storeMorphFromFSA(dToken["sValue"]):
return False
if not _dAnalyses[dToken["sValue"]]:
return False
lMorph = _dAnalyses[dToken["sValue"]]
# check negative condition
zNegPattern = re.compile(sNegPattern)
if any(zNegPattern.search(sMorph) for sMorph in lMorph):
return False
# search sPattern
zPattern = re.compile(sPattern)
return any(zPattern.search(sMorph) for sMorph in lMorph)
def analysex ():
def g_analyse (dToken, sPattern, bStrict=True):
pass
#### Go outside scope
#### Go outside the rule scope
def nextToken ():
def g_nextToken (i):
pass
def prevToken ():
def g_prevToken (i):
pass
def look ():
def g_look ():
pass
def lookAndCheck ():
def g_lookAndCheck ():
pass
#### Disambiguator
def g_select (dToken, sPattern, lDefault=None):
"select morphologies for <dToken> according to <sPattern>, always return True"
if dToken["sValue"] not in _dAnalyses and not _storeMorphFromFSA(dToken["sValue"]):
return True
if len(_dAnalyses[dToken["sValue"]]) == 1:
return True
lMorph = dToken["lMorph"] or _dAnalyses[dToken["sValue"]]
lSelect = [ sMorph for sMorph in lMorph if re.search(sPattern, sMorph) ]
def select ():
pass
def exclude ():
pass
def define ():
pass
|