| ︙ | | | ︙ | |
8
9
10
11
12
13
14
15
16
17
18
19
20
21
|
#import unicodedata
from itertools import chain
from ..graphspell.spellchecker import SpellChecker
from ..graphspell.echo import echo
from . import gc_options
__all__ = [ "lang", "locales", "pkg", "name", "version", "author", \
"load", "parse", "getSpellChecker", \
"setOption", "setOptions", "getOptions", "getDefaultOptions", "getOptionsLabels", "resetOptions", "displayOptions", \
"ignoreRule", "resetIgnoreRules", "reactivateRule", "listRules", "displayRules" ]
__version__ = "${version}"
|
>
>
>
|
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
|
#import unicodedata
from itertools import chain
from ..graphspell.spellchecker import SpellChecker
from ..graphspell.echo import echo
from . import gc_options
from ..graphspell.tokenizer import Tokenizer
from .gc_rules_graph import dGraph, dRule
__all__ = [ "lang", "locales", "pkg", "name", "version", "author", \
"load", "parse", "getSpellChecker", \
"setOption", "setOptions", "getOptions", "getDefaultOptions", "getOptionsLabels", "resetOptions", "displayOptions", \
"ignoreRule", "resetIgnoreRules", "reactivateRule", "listRules", "displayRules" ]
__version__ = "${version}"
|
| ︙ | | | ︙ | |
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
|
_rules = None # module gc_rules
# data
_sAppContext = "" # what software is running
_dOptions = None
_aIgnoredRules = set()
_oSpellChecker = None
_dAnalyses = {} # cache for data from dictionary
sAlt = sText
dDA = {} # Disambiguisator. Key = position; value = list of morphologies
dPriority = {} # Key = position; value = priority
dOpt = _dOptions if not dOptions else dOptions
# parse paragraph
try:
sNew, aErrors = _proofread(sText, sAlt, 0, True, dDA, dPriority, sCountry, dOpt, bDebug, bContext)
if sNew:
sText = sNew
except:
raise
# cleanup
if " " in sText:
sText = sText.replace(" ", ' ') # nbsp
if " " in sText:
sText = sText.replace(" ", ' ') # nnbsp
if "'" in sText:
sText = sText.replace("'", "’")
if "‑" in sText:
sText = sText.replace("‑", "-") # nobreakdash
# parse sentences
for iStart, iEnd in _getSentenceBoundaries(sText):
if 4 < (iEnd - iStart) < 2000:
dDA.clear()
try:
_, errs = _proofread(sText[iStart:iEnd], sAlt[iStart:iEnd], iStart, False, dDA, dPriority, sCountry, dOpt, bDebug, bContext)
aErrors.update(errs)
except:
raise
return aErrors.values() # this is a view (iterable)
def _getSentenceBoundaries (sText):
iStart = _zBeginOfParagraph.match(sText).end()
for m in _zEndOfSentence.finditer(sText):
yield (iStart, m.end())
iStart = m.end()
def _proofread (s, sx, nOffset, bParagraph, dDA, dPriority, sCountry, dOptions, bDebug, bContext):
dErrs = {}
bChange = False
bIdRule = option('idrule')
dErrs[nErrorStart] = _createError(s, sx, sWhat, nOffset, m, eAct[0], sLineId, sRuleId, bUppercase, eAct[1], eAct[2], bIdRule, sOption, bContext)
dPriority[nErrorStart] = nPriority
elif cActionType == "~":
# text processor
s = _rewrite(s, sWhat, eAct[0], m, bUppercase)
bChange = True
if bDebug:
echo("~ " + s + " -- " + m.group(eAct[0]) + " # " + sLineId)
|
<
|
|
>
|
>
|
>
>
>
>
|
<
<
|
|
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
|
_rules = None # module gc_rules
# data
_sAppContext = "" # what software is running
_dOptions = None
_aIgnoredRules = set()
_oSpellChecker = None
_oTokenizer = None
#### Parsing
def parse (sText, sCountry="${country_default}", bDebug=False, dOptions=None, bContext=False):
"analyses the paragraph sText and returns list of errors"
#sText = unicodedata.normalize("NFC", sText)
aErrors = None
sRealText = sText
dDA = {} # Disambiguisator. Key = position; value = list of morphologies
dPriority = {} # Key = position; value = priority
dOpt = _dOptions if not dOptions else dOptions
bShowRuleId = option('idrule')
# parse paragraph
try:
sNew, aErrors = _proofread(sText, sRealText, 0, True, dDA, dPriority, sCountry, dOpt, bShowRuleId, bDebug, bContext)
if sNew:
sText = sNew
except:
raise
# cleanup
if " " in sText:
sText = sText.replace(" ", ' ') # nbsp
if " " in sText:
sText = sText.replace(" ", ' ') # nnbsp
if "'" in sText:
sText = sText.replace("'", "’")
if "‑" in sText:
sText = sText.replace("‑", "-") # nobreakdash
# parse sentences
for iStart, iEnd in _getSentenceBoundaries(sText):
if 4 < (iEnd - iStart) < 2000:
dDA.clear()
try:
# regex parser
_, errs = _proofread(sText[iStart:iEnd], sRealText[iStart:iEnd], iStart, False, dDA, dPriority, sCountry, dOpt, bShowRuleId, bDebug, bContext)
aErrors.update(errs)
# token parser
oSentence = TokenSentence(sText[iStart:iEnd], sRealText[iStart:iEnd], iStart)
_, errs = oSentence.parse(dPriority, sCountry, dOpt, bShowRuleId, bDebug, bContext)
aErrors.update(errs)
except:
raise
return aErrors.values() # this is a view (iterable)
def _getSentenceBoundaries (sText):
iStart = _zBeginOfParagraph.match(sText).end()
for m in _zEndOfSentence.finditer(sText):
yield (iStart, m.end())
iStart = m.end()
def _proofread (s, sx, nOffset, bParagraph, dDA, dPriority, sCountry, dOptions, bShowRuleId, bDebug, bContext):
dErrs = {}
bChange = False
for sOption, lRuleGroup in _getRules(bParagraph):
if not sOption or dOptions.get(sOption, False):
for zRegex, bUppercase, sLineId, sRuleId, nPriority, lActions in lRuleGroup:
if sRuleId not in _aIgnoredRules:
for m in zRegex.finditer(s):
bCondMemo = None
for sFuncCond, cActionType, sWhat, *eAct in lActions:
# action in lActions: [ condition, action type, replacement/suggestion/action[, iGroup[, message, URL]] ]
try:
bCondMemo = not sFuncCond or globals()[sFuncCond](s, sx, m, dDA, sCountry, bCondMemo)
if bCondMemo:
if cActionType == "-":
# grammar error
nErrorStart = nOffset + m.start(eAct[0])
if nErrorStart not in dErrs or nPriority > dPriority[nErrorStart]:
dErrs[nErrorStart] = _createRegexError(s, sx, sWhat, nOffset, m, eAct[0], sLineId, sRuleId, bUppercase, eAct[1], eAct[2], bShowRuleId, sOption, bContext)
dPriority[nErrorStart] = nPriority
elif cActionType == "~":
# text processor
s = _rewrite(s, sWhat, eAct[0], m, bUppercase)
bChange = True
if bDebug:
echo("~ " + s + " -- " + m.group(eAct[0]) + " # " + sLineId)
|
| ︙ | | | ︙ | |
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
|
except Exception as e:
raise Exception(str(e), "# " + sLineId + " # " + sRuleId)
if bChange:
return (s, dErrs)
return (False, dErrs)
def _createWriterError (s, sx, sRepl, nOffset, m, iGroup, sLineId, sRuleId, bUppercase, sMsg, sURL, bIdRule, sOption, bContext):
"error for Writer (LO/OO)"
xErr = SingleProofreadingError()
#xErr = uno.createUnoStruct( "com.sun.star.linguistic2.SingleProofreadingError" )
xErr.nErrorStart = nOffset + m.start(iGroup)
xErr.nErrorLength = m.end(iGroup) - m.start(iGroup)
xErr.nErrorType = PROOFREADING
xErr.aRuleIdentifier = sRuleId
|
|
|
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
|
except Exception as e:
raise Exception(str(e), "# " + sLineId + " # " + sRuleId)
if bChange:
return (s, dErrs)
return (False, dErrs)
def _createRegexWriterError (s, sx, sRepl, nOffset, m, iGroup, sLineId, sRuleId, bUppercase, sMsg, sURL, bShowRuleId, sOption, bContext):
"error for Writer (LO/OO)"
xErr = SingleProofreadingError()
#xErr = uno.createUnoStruct( "com.sun.star.linguistic2.SingleProofreadingError" )
xErr.nErrorStart = nOffset + m.start(iGroup)
xErr.nErrorLength = m.end(iGroup) - m.start(iGroup)
xErr.nErrorType = PROOFREADING
xErr.aRuleIdentifier = sRuleId
|
| ︙ | | | ︙ | |
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
|
# Message
if sMsg[0:1] == "=":
sMessage = globals()[sMsg[1:]](s, m)
else:
sMessage = m.expand(sMsg)
xErr.aShortComment = sMessage # sMessage.split("|")[0] # in context menu
xErr.aFullComment = sMessage # sMessage.split("|")[-1] # in dialog
if bIdRule:
xErr.aShortComment += " # " + sLineId + " # " + sRuleId
# URL
if sURL:
p = PropertyValue()
p.Name = "FullCommentURL"
p.Value = sURL
xErr.aProperties = (p,)
else:
xErr.aProperties = ()
return xErr
def _createDictError (s, sx, sRepl, nOffset, m, iGroup, sLineId, sRuleId, bUppercase, sMsg, sURL, bIdRule, sOption, bContext):
"error as a dictionary"
dErr = {}
dErr["nStart"] = nOffset + m.start(iGroup)
dErr["nEnd"] = nOffset + m.end(iGroup)
dErr["sLineId"] = sLineId
dErr["sRuleId"] = sRuleId
dErr["sType"] = sOption if sOption else "notype"
# suggestions
if sRepl[0:1] == "=":
sugg = globals()[sRepl[1:]](s, m)
if sugg:
if bUppercase and m.group(iGroup)[0:1].isupper():
dErr["aSuggestions"] = list(map(str.capitalize, sugg.split("|")))
else:
dErr["aSuggestions"] = sugg.split("|")
else:
dErr["aSuggestions"] = ()
elif sRepl == "_":
dErr["aSuggestions"] = ()
else:
if bUppercase and m.group(iGroup)[0:1].isupper():
dErr["aSuggestions"] = list(map(str.capitalize, m.expand(sRepl).split("|")))
else:
dErr["aSuggestions"] = m.expand(sRepl).split("|")
# Message
if sMsg[0:1] == "=":
sMessage = globals()[sMsg[1:]](s, m)
else:
sMessage = m.expand(sMsg)
dErr["sMessage"] = sMessage
if bIdRule:
dErr["sMessage"] += " # " + sLineId + " # " + sRuleId
# URL
dErr["URL"] = sURL if sURL else ""
# Context
if bContext:
dErr['sUnderlined'] = sx[m.start(iGroup):m.end(iGroup)]
dErr['sBefore'] = sx[max(0,m.start(iGroup)-80):m.start(iGroup)]
dErr['sAfter'] = sx[m.end(iGroup):m.end(iGroup)+80]
return dErr
def _rewrite (s, sRepl, iGroup, m, bUppercase):
"text processor: write sRepl in s at iGroup position"
nLen = m.end(iGroup) - m.start(iGroup)
if sRepl == "*":
sNew = " " * nLen
elif sRepl == ">" or sRepl == "_" or sRepl == "~":
sNew = sRepl + " " * (nLen-1)
elif sRepl == "@":
sNew = "@" * nLen
sNew = globals()[sRepl[1:]](s, m)
sNew = sNew + " " * (nLen-len(sNew))
if bUppercase and m.group(iGroup)[0:1].isupper():
sNew = sNew.capitalize()
else:
sNew = m.expand(sRepl)
sNew = sNew + " " * (nLen-len(sNew))
return s[0:m.start(iGroup)] + sNew + s[m.end(iGroup):]
def ignoreRule (sRuleId):
_aIgnoredRules.add(sRuleId)
def resetIgnoreRules ():
|
|
|
|
|
|
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
|
|
|
<
<
|
|
|
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
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
|
# Message
if sMsg[0:1] == "=":
sMessage = globals()[sMsg[1:]](s, m)
else:
sMessage = m.expand(sMsg)
xErr.aShortComment = sMessage # sMessage.split("|")[0] # in context menu
xErr.aFullComment = sMessage # sMessage.split("|")[-1] # in dialog
if bShowRuleId:
xErr.aShortComment += " # " + sLineId + " # " + sRuleId
# URL
if sURL:
p = PropertyValue()
p.Name = "FullCommentURL"
p.Value = sURL
xErr.aProperties = (p,)
else:
xErr.aProperties = ()
return xErr
def _createRegexDictError (s, sx, sRepl, nOffset, m, iGroup, sLineId, sRuleId, bUppercase, sMsg, sURL, bShowRuleId, sOption, bContext):
"error as a dictionary"
dErr = {}
dErr["nStart"] = nOffset + m.start(iGroup)
dErr["nEnd"] = nOffset + m.end(iGroup)
dErr["sLineId"] = sLineId
dErr["sRuleId"] = sRuleId
dErr["sType"] = sOption if sOption else "notype"
# suggestions
if sRepl[0:1] == "=":
sugg = globals()[sRepl[1:]](s, m)
if sugg:
if bUppercase and m.group(iGroup)[0:1].isupper():
dErr["aSuggestions"] = list(map(str.capitalize, sugg.split("|")))
else:
dErr["aSuggestions"] = sugg.split("|")
else:
dErr["aSuggestions"] = []
elif sRepl == "_":
dErr["aSuggestions"] = []
else:
if bUppercase and m.group(iGroup)[0:1].isupper():
dErr["aSuggestions"] = list(map(str.capitalize, m.expand(sRepl).split("|")))
else:
dErr["aSuggestions"] = m.expand(sRepl).split("|")
# Message
if sMsg[0:1] == "=":
sMessage = globals()[sMsg[1:]](s, m)
else:
sMessage = m.expand(sMsg)
dErr["sMessage"] = sMessage
if bShowRuleId:
dErr["sMessage"] += " # " + sLineId + " # " + sRuleId
# URL
dErr["URL"] = sURL if sURL else ""
# Context
if bContext:
dErr['sUnderlined'] = sx[m.start(iGroup):m.end(iGroup)]
dErr['sBefore'] = sx[max(0,m.start(iGroup)-80):m.start(iGroup)]
dErr['sAfter'] = sx[m.end(iGroup):m.end(iGroup)+80]
return dErr
def _createTokenWriterError (lToken, sSentence, sSentence0, sRepl, iFirstToken, nStart, nEnd, sLineId, sRuleId, bUppercase, sMsg, sURL, bShowRuleId, sOption, bContext):
"error for Writer (LO/OO)"
xErr = SingleProofreadingError()
#xErr = uno.createUnoStruct( "com.sun.star.linguistic2.SingleProofreadingError" )
xErr.nErrorStart = nStart
xErr.nErrorLength = nEnd - nStart
xErr.nErrorType = PROOFREADING
xErr.aRuleIdentifier = sRuleId
# suggestions
if sRepl[0:1] == "=":
sSugg = globals()[sRepl[1:]](lToken)
if sSugg:
if bUppercase and lToken[iFirstToken]["sValue"][0:1].isupper():
xErr.aSuggestions = tuple(map(str.capitalize, sSugg.split("|")))
else:
xErr.aSuggestions = tuple(sSugg.split("|"))
else:
xErr.aSuggestions = ()
elif sRepl == "_":
xErr.aSuggestions = ()
else:
if bUppercase and lToken[iFirstToken]["sValue"][0:1].isupper():
xErr.aSuggestions = tuple(map(str.capitalize, sRepl.split("|")))
else:
xErr.aSuggestions = tuple(sRepl.split("|"))
# Message
if sMsg[0:1] == "=":
sMessage = globals()[sMsg[1:]](lToken)
else:
sMessage = sMsg
xErr.aShortComment = sMessage # sMessage.split("|")[0] # in context menu
xErr.aFullComment = sMessage # sMessage.split("|")[-1] # in dialog
if bShowRuleId:
xErr.aShortComment += " " + sLineId + " # " + sRuleId
# URL
if sURL:
p = PropertyValue()
p.Name = "FullCommentURL"
p.Value = sURL
xErr.aProperties = (p,)
else:
xErr.aProperties = ()
return xErr
def _createTokenDictError (lToken, sSentence, sSentence0, sRepl, iFirstToken, nStart, nEnd, sLineId, sRuleId, bUppercase, sMsg, sURL, bShowRuleId, sOption, bContext):
"error as a dictionary"
dErr = {}
dErr["nStart"] = nStart
dErr["nEnd"] = nEnd
dErr["sLineId"] = sLineId
dErr["sRuleId"] = sRuleId
dErr["sType"] = sOption if sOption else "notype"
# suggestions
if sRepl[0:1] == "=":
sugg = globals()[sRepl[1:]](lToken)
if sugg:
if bUppercase and lToken[iFirstToken]["sValue"][0:1].isupper():
dErr["aSuggestions"] = list(map(str.capitalize, sugg.split("|")))
else:
dErr["aSuggestions"] = sugg.split("|")
else:
dErr["aSuggestions"] = []
elif sRepl == "_":
dErr["aSuggestions"] = []
else:
if bUppercase and lToken[iFirstToken]["sValue"][0:1].isupper():
dErr["aSuggestions"] = list(map(str.capitalize, sRepl.split("|")))
else:
dErr["aSuggestions"] = sRepl.split("|")
# Message
if sMsg[0:1] == "=":
sMessage = globals()[sMsg[1:]](lToken)
else:
sMessage = sMsg
dErr["sMessage"] = sMessage
if bShowRuleId:
dErr["sMessage"] += " " + sLineId + " # " + sRuleId
# URL
dErr["URL"] = sURL if sURL else ""
# Context
if bContext:
dErr['sUnderlined'] = sSentence0[dErr["nStart"]:dErr["nEnd"]]
dErr['sBefore'] = sSentence0[max(0,dErr["nStart"]-80):dErr["nStart"]]
dErr['sAfter'] = sSentence0[dErr["nEnd"]:dErr["nEnd"]+80]
return dErr
def _rewrite (sSentence, sRepl, iGroup, m, bUppercase):
"text processor: write <sRepl> in <sSentence> at <iGroup> position"
nLen = m.end(iGroup) - m.start(iGroup)
if sRepl == "*":
sNew = " " * nLen
elif sRepl == "_":
sNew = sRepl + " " * (nLen-1)
elif sRepl[0:1] == "=":
sNew = globals()[sRepl[1:]](sSentence, m)
sNew = sNew + " " * (nLen-len(sNew))
if bUppercase and m.group(iGroup)[0:1].isupper():
sNew = sNew.capitalize()
else:
sNew = m.expand(sRepl)
sNew = sNew + " " * (nLen-len(sNew))
return sSentence[0:m.start(iGroup)] + sNew + sSentence[m.end(iGroup):]
def ignoreRule (sRuleId):
_aIgnoredRules.add(sRuleId)
def resetIgnoreRules ():
|
| ︙ | | | ︙ | |
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
|
try:
# LibreOffice / OpenOffice
from com.sun.star.linguistic2 import SingleProofreadingError
from com.sun.star.text.TextMarkupType import PROOFREADING
from com.sun.star.beans import PropertyValue
#import lightproof_handler_${implname} as opt
_createError = _createWriterError
except ImportError:
_createError = _createDictError
def load (sContext="Python"):
global _oSpellChecker
global _sAppContext
global _dOptions
try:
_oSpellChecker = SpellChecker("${lang}", "${dic_main_filename_py}", "${dic_extended_filename_py}", "${dic_community_filename_py}", "${dic_personal_filename_py}")
_sAppContext = sContext
_dOptions = dict(gc_options.getOptions(sContext)) # duplication necessary, to be able to reset to default
except:
traceback.print_exc()
def setOption (sOpt, bVal):
if sOpt in _dOptions:
_dOptions[sOpt] = bVal
|
|
>
|
>
>
>
>
|
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
|
try:
# LibreOffice / OpenOffice
from com.sun.star.linguistic2 import SingleProofreadingError
from com.sun.star.text.TextMarkupType import PROOFREADING
from com.sun.star.beans import PropertyValue
#import lightproof_handler_${implname} as opt
_createRegexError = _createRegexWriterError
_createTokenError = _createTokenWriterError
except ImportError:
_createRegexError = _createRegexDictError
_createTokenError = _createTokenDictError
def load (sContext="Python"):
global _oSpellChecker
global _sAppContext
global _dOptions
global _oTokenizer
try:
_oSpellChecker = SpellChecker("${lang}", "${dic_main_filename_py}", "${dic_extended_filename_py}", "${dic_community_filename_py}", "${dic_personal_filename_py}")
_sAppContext = sContext
_dOptions = dict(gc_options.getOptions(sContext)) # duplication necessary, to be able to reset to default
_oTokenizer = _oSpellChecker.getTokenizer()
_oSpellChecker.activateStorage()
except:
traceback.print_exc()
def setOption (sOpt, bVal):
if sOpt in _dOptions:
_dOptions[sOpt] = bVal
|
| ︙ | | | ︙ | |
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
|
return os.path.join(os.path.dirname(sys.modules[__name__].__file__), __name__ + ".py")
#### common functions
# common regexes
_zEndOfSentence = re.compile('([.?!:;…][ .?!… »”")]*|.$)')
_zBeginOfParagraph = re.compile("^\W*")
_zEndOfParagraph = re.compile("\W*$")
_zNextWord = re.compile(" +(\w[\w-]*)")
_zPrevWord = re.compile("(\w[\w-]*) +$")
def option (sOpt):
"return True if option sOpt is active"
return _dOptions.get(sOpt, False)
def displayInfo (dDA, tWord):
"for debugging: retrieve info of word"
if not tWord:
echo("> nothing to find")
return True
if tWord[1] not in _dAnalyses and not _storeMorphFromFSA(tWord[1]):
echo("> not in FSA")
return True
if tWord[0] in dDA:
echo("DA: " + str(dDA[tWord[0]]))
echo("FSA: " + str(_dAnalyses[tWord[1]]))
return True
def _storeMorphFromFSA (sWord):
"retrieves morphologies list from _oSpellChecker -> _dAnalyses"
global _dAnalyses
_dAnalyses[sWord] = _oSpellChecker.getMorph(sWord)
return True if _dAnalyses[sWord] else False
if tWord[1] not in _dAnalyses and not _storeMorphFromFSA(tWord[1]):
return False
lMorph = dDA[tWord[0]] if tWord[0] in dDA else _dAnalyses[tWord[1]]
if tWord[1] not in _dAnalyses and not _storeMorphFromFSA(tWord[1]):
return False
lMorph = dDA[tWord[0]] if tWord[0] in dDA else _dAnalyses[tWord[1]]
if sWord not in _dAnalyses and not _storeMorphFromFSA(sWord):
return False
if not _dAnalyses[sWord]:
return False
p = re.compile(sPattern)
if bStrict:
return all(p.search(s) for s in _dAnalyses[sWord])
return any(p.search(s) for s in _dAnalyses[sWord])
def analysex (sWord, sPattern, sNegPattern):
"analyse a word, returns True if not sNegPattern in word morphologies and sPattern in word morphologies (disambiguation off)"
if sWord not in _dAnalyses and not _storeMorphFromFSA(sWord):
return False
# check negative condition
np = re.compile(sNegPattern)
if any(np.search(s) for s in _dAnalyses[sWord]):
return False
# search sPattern
p = re.compile(sPattern)
return any(p.search(s) for s in _dAnalyses[sWord])
def stem (sWord):
"returns a list of sWord's stems"
if not sWord:
return []
if sWord not in _dAnalyses and not _storeMorphFromFSA(sWord):
return []
return [ s[1:s.find(" ")] for s in _dAnalyses[sWord] ]
|
|
|
|
|
|
|
>
|
|
<
<
<
<
<
<
<
<
<
|
|
>
<
|
<
|
|
|
|
>
|
|
<
<
<
<
<
<
<
<
|
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
|
return os.path.join(os.path.dirname(sys.modules[__name__].__file__), __name__ + ".py")
#### common functions
# common regexes
_zEndOfSentence = re.compile(r'([.?!:;…][ .?!… »”")]*|.$)')
_zBeginOfParagraph = re.compile(r"^\W*")
_zEndOfParagraph = re.compile(r"\W*$")
_zNextWord = re.compile(r" +(\w[\w-]*)")
_zPrevWord = re.compile(r"(\w[\w-]*) +$")
def option (sOpt):
"return True if option sOpt is active"
return _dOptions.get(sOpt, False)
def displayInfo (dDA, tWord):
"for debugging: retrieve info of word"
if not tWord:
echo("> nothing to find")
return True
lMorph = _oSpellChecker.getMorph(tWord[1])
if not lMorph:
echo("> not in dictionary")
return True
if tWord[0] in dDA:
echo("DA: " + str(dDA[tWord[0]]))
echo("FSA: " + str(lMorph))
return True
def morph (dDA, tWord, sPattern, bStrict=True, bNoWord=False):
"analyse a tuple (position, word), return True if sPattern in morphologies (disambiguation on)"
if not tWord:
return bNoWord
lMorph = dDA[tWord[0]] if tWord[0] in dDA else _oSpellChecker.getMorph(tWord[1])
if not lMorph:
return False
p = re.compile(sPattern)
if bStrict:
return all(p.search(s) for s in lMorph)
return any(p.search(s) for s in lMorph)
def morphex (dDA, tWord, sPattern, sNegPattern, bNoWord=False):
"analyse a tuple (position, word), returns True if not sNegPattern in word morphologies and sPattern in word morphologies (disambiguation on)"
if not tWord:
return bNoWord
lMorph = dDA[tWord[0]] if tWord[0] in dDA else _oSpellChecker.getMorph(tWord[1])
if not lMorph:
return False
# check negative condition
np = re.compile(sNegPattern)
if any(np.search(s) for s in lMorph):
return False
# search sPattern
p = re.compile(sPattern)
return any(p.search(s) for s in lMorph)
def analyse (sWord, sPattern, bStrict=True):
"analyse a word, return True if sPattern in morphologies (disambiguation off)"
lMorph = _oSpellChecker.getMorph(sWord)
if not lMorph:
return False
p = re.compile(sPattern)
if bStrict:
return all(p.search(s) for s in lMorph)
return any(p.search(s) for s in lMorph)
def analysex (sWord, sPattern, sNegPattern):
"analyse a word, returns True if not sNegPattern in word morphologies and sPattern in word morphologies (disambiguation off)"
lMorph = _oSpellChecker.getMorph(sWord)
if not lMorph:
return False
# check negative condition
np = re.compile(sNegPattern)
if any(np.search(s) for s in lMorph):
return False
# search sPattern
p = re.compile(sPattern)
return any(p.search(s) for s in lMorph)
## functions to get text outside pattern scope
# warning: check compile_rules.py to understand how it works
def nextword (s, iStart, n):
|
| ︙ | | | ︙ | |
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
|
#### Disambiguator
def select (dDA, nPos, sWord, sPattern, lDefault=None):
if not sWord:
return True
if nPos in dDA:
return True
if sWord not in _dAnalyses and not _storeMorphFromFSA(sWord):
return True
if len(_dAnalyses[sWord]) == 1:
return True
lSelect = [ sMorph for sMorph in _dAnalyses[sWord] if re.search(sPattern, sMorph) ]
if lSelect:
if len(lSelect) != len(_dAnalyses[sWord]):
dDA[nPos] = lSelect
#echo("= "+sWord+" "+str(dDA.get(nPos, "null")))
#echo("= "+sWord+" "+str(dDA.get(nPos, "null")))
if sWord not in _dAnalyses and not _storeMorphFromFSA(sWord):
return True
if len(_dAnalyses[sWord]) == 1:
return True
lSelect = [ sMorph for sMorph in _dAnalyses[sWord] if not re.search(sPattern, sMorph) ]
if lSelect:
if len(lSelect) != len(_dAnalyses[sWord]):
dDA[nPos] = lSelect
#echo("= "+sWord+" "+str(dDA.get(nPos, "null")))
#echo("= "+sWord+" "+str(dDA.get(nPos, "null")))
#echo("= "+str(nPos)+" "+str(dDA[nPos]))
|
|
<
|
|
|
<
<
|
<
|
|
|
<
<
<
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
|
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
|
#### Disambiguator
def select (dDA, nPos, sWord, sPattern, lDefault=None):
if not sWord:
return True
if nPos in dDA:
return True
lMorph = _oSpellChecker.getMorph(sWord)
if not lMorph or len(lMorph) == 1:
return True
lSelect = [ sMorph for sMorph in lMorph if re.search(sPattern, sMorph) ]
if lSelect:
if len(lSelect) != len(lMorph):
dDA[nPos] = lSelect
elif lDefault:
dDA[nPos] = lDefault
return True
def exclude (dDA, nPos, sWord, sPattern, lDefault=None):
if not sWord:
return True
if nPos in dDA:
return True
lMorph = _oSpellChecker.getMorph(sWord)
if not lMorph or len(lMorph) == 1:
return True
lSelect = [ sMorph for sMorph in lMorph if not re.search(sPattern, sMorph) ]
if lSelect:
if len(lSelect) != len(lMorph):
dDA[nPos] = lSelect
elif lDefault:
dDA[nPos] = lDefault
return True
def define (dDA, nPos, lMorph):
dDA[nPos] = lMorph
return True
#### GRAMMAR CHECKER PLUGINS
${plugins}
#### CALLABLES (generated code)
${callables}
#### TOKEN SENTENCE CHECKER
class TokenSentence:
def __init__ (self, sSentence, sSentence0, iStart):
self.sSentence = sSentence
self.sSentence0 = sSentence0
self.iStart = iStart
self.lToken = list(_oTokenizer.genTokens(sSentence, True))
def _getNextMatchingNodes (self, dToken, dNode):
"generator: return nodes where <dToken> “values” match <dNode> arcs"
# token value
if dToken["sValue"] in dNode:
#print("value found: ", dToken["sValue"])
yield dGraph[dNode[dToken["sValue"]]]
# token lemmas
if "<lemmas>" in dNode:
for sLemma in _oSpellChecker.getLemma(dToken["sValue"]):
if sLemma in dNode["<lemmas>"]:
#print("lemma found: ", sLemma)
yield dGraph[dNode["<lemmas>"][sLemma]]
# universal arc
if "*" in dNode:
#print("generic arc")
yield dGraph[dNode["*"]]
# regex value arcs
if "<re_value>" in dNode:
for sRegex in dNode["<re_value>"]:
if re.search(sRegex, dToken["sValue"]):
#print("value regex matching: ", sRegex)
yield dGraph[dNode["<re_value>"][sRegex]]
# regex morph arcs
if "<re_morph>" in dNode:
for sRegex in dNode["<re_morph>"]:
for sMorph in _oSpellChecker.getMorph(dToken["sValue"]):
if re.search(sRegex, sMorph):
#print("morph regex matching: ", sRegex)
yield dGraph[dNode["<re_morph>"][sRegex]]
def parse (self, dPriority, sCountry="${country_default}", dOptions=None, bShowRuleId=False, bDebug=False, bContext=False):
dErr = {}
dPriority = {} # Key = position; value = priority
dOpt = _dOptions if not dOptions else dOptions
lPointer = []
bChange = False
for dToken in self.lToken:
# check arcs for each existing pointer
lNewPointer = []
for i, dPointer in enumerate(lPointer):
bValid = False
bFirst = True
for dNode in self._getNextMatchingNodes(dToken, dPointer["dNode"]):
if bFirst:
dPointer["dNode"] = dNode
else:
lNewPointer.append({"nOffset": dPointer["nOffset"], "dNode": dNode})
bFirst = False
bValid = True
if not bValid:
del lPointer[i]
lPointer.extend(lNewPointer)
# check arcs of first nodes
for dNode in self._getNextMatchingNodes(dToken, dGraph[0]):
lPointer.append({"nOffset": dToken["i"], "dNode": dNode})
# check if there is rules to check for each pointer
for dPointer in lPointer:
if "<rules>" in dPointer["dNode"]:
bHasChanged, errs = self._executeActions(dPointer["dNode"]["<rules>"], dPointer["nOffset"]-1, dPriority, dOpt, sCountry, bShowRuleId, bContext)
dErr.update(errs)
if bHasChanged:
bChange = True
if dErr:
print(dErr)
return (bChange, dErr)
def _executeActions (self, dNode, nTokenOffset, dPriority, dOpt, sCountry, bShowRuleId, bContext):
#print(locals())
dErrs = {}
bChange = False
for sLineId, nextNodeKey in dNode.items():
for sRuleId in dGraph[nextNodeKey]:
print(sRuleId)
bCondMemo = None
sFuncCond, cActionType, sWhat, *eAct = dRule[sRuleId]
# action in lActions: [ condition, action type, replacement/suggestion/action[, iTokenStart, iTokenEnd[, nPriority, message, URL]] ]
try:
bCondMemo = not sFuncCond or globals()[sFuncCond](self.lToken, nTokenOffset, sCountry, bCondMemo)
if bCondMemo:
if cActionType == "-":
# grammar error
print("-")
nTokenErrorStart = nTokenOffset + eAct[0]
nTokenErrorEnd = nTokenOffset + eAct[1]
nErrorStart = self.iStart + self.lToken[nTokenErrorStart]["nStart"]
nErrorEnd = self.iStart + self.lToken[nTokenErrorEnd]["nEnd"]
if nErrorStart not in dErrs or eAct[2] > dPriority[nErrorStart]:
dErrs[nErrorStart] = _createTokenError(self.lToken, self.sSentence, self.sSentence0, sWhat, nTokenErrorStart, nErrorStart, nErrorEnd, sLineId, sRuleId, True, eAct[3], eAct[4], bShowRuleId, "notype", bContext)
dPriority[nErrorStart] = eAct[2]
elif cActionType == "~":
# text processor
print("~")
self._rewrite(sWhat, nErrorStart, nErrorEnd)
elif cActionType == "@":
# jump
print("@")
self._jump(sWhat)
elif cActionType == "=":
# disambiguation
print("=")
globals()[sWhat](self.lToken)
elif cActionType == ">":
# we do nothing, this test is just a condition to apply all following actions
print(">")
pass
else:
print("# error: unknown action at " + sLineId)
elif cActionType == ">":
break
except Exception as e:
raise Exception(str(e), sLineId)
return bChange, dErrs
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 _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:
lMorph = dToken["lMorph"]
else:
lMorph = _oSpellChecker.getMorph(dToken["sValue"])
if not lMorph:
return False
zPattern = re.compile(sPattern)
if bStrict:
return all(zPattern.search(sMorph) for sMorph in lMorph)
return any(zPattern.search(sMorph) for sMorph in lMorph)
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:
lMorph = _oSpellChecker.getMorph(dToken["sValue"])
if not lMorph:
return False
# 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 g_analyse (dToken, sPattern, bStrict=True):
"analyse a token, return True if <sPattern> in morphologies (disambiguation off)"
lMorph = _oSpellChecker.getMorph(dToken["sValue"])
if not lMorph:
return False
zPattern = re.compile(sPattern)
if bStrict:
return all(zPattern.search(sMorph) for sMorph in lMorph)
return any(zPattern.search(sMorph) for sMorph in lMorph)
def g_analysex (dToken, sPattern, sNegPattern):
"analyse a token, return True if <sNegPattern> not in morphologies and <sPattern> in morphologies (disambiguation off)"
lMorph = _oSpellChecker.getMorph(dToken["sValue"])
if not lMorph:
return False
# 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)
#### Disambiguator
def g_select (dToken, sPattern, lDefault=None):
"select morphologies for <dToken> according to <sPattern>, always return True"
lMorph = dToken["lMorph"] if "lMorph" in dToken else _oSpellChecker.getMorph(dToken["sValue"])
if not lMorph or len(lMorph) == 1:
return True
lSelect = [ sMorph for sMorph in lMorph if re.search(sPattern, sMorph) ]
if lSelect:
if len(lSelect) != len(lMorph):
dToken["lMorph"] = lSelect
elif lDefault:
dToken["lMorph"] = lDefault
return True
def g_exclude (dToken, sPattern, lDefault=None):
"select morphologies for <dToken> according to <sPattern>, always return True"
lMorph = dToken["lMorph"] if "lMorph" in dToken else _oSpellChecker.getMorph(dToken["sValue"])
if not lMorph or len(lMorph) == 1:
return True
lSelect = [ sMorph for sMorph in lMorph if not re.search(sPattern, sMorph) ]
if lSelect:
if len(lSelect) != len(lMorph):
dToken["lMorph"] = lSelect
elif lDefault:
dToken["lMorph"] = lDefault
return True
def g_define (dToken, lMorph):
"set morphologies of <dToken>, always return True"
dToken["lMorph"] = lMorph
return True
#### CALLABLES (generated code)
${graph_callables}
|