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
|
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
|
-
+
-
+
-
+
-
-
+
+
-
-
+
+
|
if sys.platform == "win32":
# Apparently, the console transforms «’» in «'».
# So we reverse it to avoid many useless warnings.
sText = sText.replace("'", "’")
return sText
def _getErrors (sText, oTokenizer, oDict, bContext=False, bSpellSugg=False, bDebug=False):
def _getErrors (sText, oTokenizer, oSpellChecker, bContext=False, bSpellSugg=False, bDebug=False):
"returns a tuple: (grammar errors, spelling errors)"
aGrammErrs = gce.parse(sText, "FR", bDebug=bDebug, bContext=bContext)
aSpellErrs = []
for dToken in oTokenizer.genTokens(sText):
if dToken['sType'] == "WORD" and not oDict.isValidToken(dToken['sValue']):
if dToken['sType'] == "WORD" and not oSpellChecker.isValidToken(dToken['sValue']):
if bSpellSugg:
dToken['aSuggestions'] = oDict.suggest(dToken['sValue'])
dToken['aSuggestions'] = oSpellChecker.suggest(dToken['sValue'])
aSpellErrs.append(dToken)
return aGrammErrs, aSpellErrs
def generateText (sText, oTokenizer, oDict, bDebug=False, bEmptyIfNoErrors=False, bSpellSugg=False, nWidth=100):
aGrammErrs, aSpellErrs = _getErrors(sText, oTokenizer, oDict, False, bSpellSugg, bDebug)
def generateText (sText, oTokenizer, oSpellChecker, bDebug=False, bEmptyIfNoErrors=False, bSpellSugg=False, nWidth=100):
aGrammErrs, aSpellErrs = _getErrors(sText, oTokenizer, oSpellChecker, False, bSpellSugg, bDebug)
if bEmptyIfNoErrors and not aGrammErrs and not aSpellErrs:
return ""
return txt.generateParagraph(sText, aGrammErrs, aSpellErrs, nWidth)
def generateJSON (iIndex, sText, oTokenizer, oDict, bContext=False, bDebug=False, bEmptyIfNoErrors=False, bSpellSugg=False, lLineSet=None, bReturnText=False):
aGrammErrs, aSpellErrs = _getErrors(sText, oTokenizer, oDict, bContext, bSpellSugg, bDebug)
def generateJSON (iIndex, sText, oTokenizer, oSpellChecker, bContext=False, bDebug=False, bEmptyIfNoErrors=False, bSpellSugg=False, lLineSet=None, bReturnText=False):
aGrammErrs, aSpellErrs = _getErrors(sText, oTokenizer, oSpellChecker, bContext, bSpellSugg, bDebug)
aGrammErrs = list(aGrammErrs)
if bEmptyIfNoErrors and not aGrammErrs and not aSpellErrs:
return ""
if lLineSet:
aGrammErrs, aSpellErrs = txt.convertToXY(aGrammErrs, aSpellErrs, lLineSet)
return json.dumps({ "lGrammarErrors": aGrammErrs, "lSpellingErrors": aSpellErrs }, ensure_ascii=False)
if bReturnText:
|
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
|
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
|
-
+
-
+
-
+
-
+
-
+
-
-
+
+
-
+
-
+
|
for i, sText in enumerate(readfile(sFile), 1):
if xArgs.textformatter or xArgs.textformatteronly:
sText = oTF.formatText(sText)
if xArgs.textformatteronly:
output(sText, hDst)
else:
if xArgs.json:
sText = generateJSON(i, sText, oTokenizer, oDict, bContext=xArgs.context, bDebug=False, bEmptyIfNoErrors=xArgs.only_when_errors, bSpellSugg=xArgs.with_spell_sugg, bReturnText=xArgs.textformatter)
sText = generateJSON(i, sText, oTokenizer, oSpellChecker, bContext=xArgs.context, bDebug=False, bEmptyIfNoErrors=xArgs.only_when_errors, bSpellSugg=xArgs.with_spell_sugg, bReturnText=xArgs.textformatter)
else:
sText = generateText(sText, oTokenizer, oDict, bDebug=False, bEmptyIfNoErrors=xArgs.only_when_errors, bSpellSugg=xArgs.with_spell_sugg, nWidth=xArgs.width)
sText = generateText(sText, oTokenizer, oSpellChecker, bDebug=False, bEmptyIfNoErrors=xArgs.only_when_errors, bSpellSugg=xArgs.with_spell_sugg, nWidth=xArgs.width)
if sText:
if xArgs.json and bComma:
output(",\n", hDst)
output(sText, hDst)
bComma = True
if hDst:
echo("§ %d\r" % i, end="", flush=True)
else:
# concaténation des lignes non séparées par une ligne vide
for i, lLine in enumerate(readfileAndConcatLines(sFile), 1):
sText, lLineSet = txt.createParagraphWithLines(lLine)
if xArgs.json:
sText = generateJSON(i, sText, oTokenizer, oDict, bContext=xArgs.context, bDebug=False, bEmptyIfNoErrors=xArgs.only_when_errors, bSpellSugg=xArgs.with_spell_sugg, lLineSet=lLineSet)
sText = generateJSON(i, sText, oTokenizer, oSpellChecker, bContext=xArgs.context, bDebug=False, bEmptyIfNoErrors=xArgs.only_when_errors, bSpellSugg=xArgs.with_spell_sugg, lLineSet=lLineSet)
else:
sText = generateText(sText, oTokenizer, oDict, bDebug=False, bEmptyIfNoErrors=xArgs.only_when_errors, bSpellSugg=xArgs.with_spell_sugg, nWidth=xArgs.width)
sText = generateText(sText, oTokenizer, oSpellChecker, bDebug=False, bEmptyIfNoErrors=xArgs.only_when_errors, bSpellSugg=xArgs.with_spell_sugg, nWidth=xArgs.width)
if sText:
if xArgs.json and bComma:
output(",\n", hDst)
output(sText, hDst)
bComma = True
if hDst:
echo("§ %d\r" % i, end="", flush=True)
if xArgs.json:
output("\n]}\n", hDst)
else:
# pseudo-console
sInputText = "\n~==========~ Enter your text [/h /q] ~==========~\n"
sText = _getText(sInputText)
while True:
if sText.startswith("?"):
for sWord in sText[1:].strip().split():
if sWord:
echo("* " + sWord)
for sMorph in oDict.getMorph(sWord):
for sMorph in oSpellChecker.getMorph(sWord):
echo(" {:<32} {}".format(sMorph, oLexGraphe.formatTags(sMorph)))
elif sText.startswith("!"):
for sWord in sText[1:].strip().split():
if sWord:
echo(" | ".join(oDict.suggest(sWord)))
#echo(" | ".join(oDict.suggest2(sWord)))
echo(" | ".join(oSpellChecker.suggest(sWord)))
#echo(" | ".join(oSpellChecker.suggest2(sWord)))
elif sText.startswith(">"):
oDict.drawPath(sText[1:].strip())
oSpellChecker.drawPath(sText[1:].strip())
elif sText.startswith("="):
for sRes in oDict.select(sText[1:].strip()):
for sRes in oSpellChecker.select(sText[1:].strip()):
echo(sRes)
elif sText.startswith("/+ "):
gce.setOptions({ opt:True for opt in sText[3:].strip().split() if opt in gce.getOptions() })
echo("done")
elif sText.startswith("/- "):
gce.setOptions({ opt:False for opt in sText[3:].strip().split() if opt in gce.getOptions() })
echo("done")
|
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
|
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
|
-
+
|
elif sText.startswith("/rl"):
# reload (todo)
pass
else:
for sParagraph in txt.getParagraph(sText):
if xArgs.textformatter:
sText = oTF.formatText(sText)
sRes = generateText(sText, oTokenizer, oDict, bDebug=xArgs.debug, bEmptyIfNoErrors=xArgs.only_when_errors, nWidth=xArgs.width)
sRes = generateText(sText, oTokenizer, oSpellChecker, bDebug=xArgs.debug, bEmptyIfNoErrors=xArgs.only_when_errors, nWidth=xArgs.width)
if sRes:
echo("\n" + sRes)
else:
echo("\nNo error found.")
sText = _getText(sInputText)
if __name__ == '__main__':
main()
|