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):
"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 bSpellSugg:
dToken['aSuggestions'] = oDict.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)
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)
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:
|
|
|
|
>
>
|
|
|
|
|
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
|
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, 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 oSpellChecker.isValidToken(dToken['sValue']):
if bSpellSugg:
dToken['aSuggestions'] = []
for lSugg in oSpellChecker.suggest(dToken['sValue']):
dToken['aSuggestions'].extend(lSugg)
aSpellErrs.append(dToken)
return aGrammErrs, aSpellErrs
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, 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:
|
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
|
xParser.add_argument("-roff", "--rule_off", nargs="+", help="deactivate rules")
xParser.add_argument("-d", "--debug", help="debugging mode (only in interactive mode)", action="store_true")
xArgs = xParser.parse_args()
gce.load()
if not xArgs.json:
echo("Grammalecte v{}".format(gce.version))
oDict = gce.getDictionary()
oTokenizer = tkz.Tokenizer("fr")
oLexGraphe = lxg.Lexicographe(oDict)
if xArgs.textformatter or xArgs.textformatteronly:
oTF = tf.TextFormatter()
if xArgs.list_options or xArgs.list_rules:
if xArgs.list_options:
gce.displayOptions("fr")
if xArgs.list_rules:
gce.displayRules(None if xArgs.list_rules == "*" else xArgs.list_rules)
exit()
if xArgs.suggest:
lSugg = oDict.suggest(xArgs.suggest)
if xArgs.json:
sText = json.dumps({ "aSuggestions": lSugg }, ensure_ascii=False)
else:
sText = "Suggestions : " + " | ".join(lSugg)
echo(sText)
exit()
if not xArgs.json:
xArgs.context = False
gce.setOptions({"html": True, "latex": True})
if xArgs.opt_on:
|
|
|
|
|
|
|
|
|
|
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
|
xParser.add_argument("-roff", "--rule_off", nargs="+", help="deactivate rules")
xParser.add_argument("-d", "--debug", help="debugging mode (only in interactive mode)", action="store_true")
xArgs = xParser.parse_args()
gce.load()
if not xArgs.json:
echo("Grammalecte v{}".format(gce.version))
oSpellChecker = gce.getSpellChecker()
oTokenizer = tkz.Tokenizer("fr")
oLexGraphe = lxg.Lexicographe(oSpellChecker)
if xArgs.textformatter or xArgs.textformatteronly:
oTF = tf.TextFormatter()
if xArgs.list_options or xArgs.list_rules:
if xArgs.list_options:
gce.displayOptions("fr")
if xArgs.list_rules:
gce.displayRules(None if xArgs.list_rules == "*" else xArgs.list_rules)
exit()
if xArgs.suggest:
for lSugg in oSpellChecker.suggest(xArgs.suggest):
if xArgs.json:
sText = json.dumps({ "aSuggestions": lSugg }, ensure_ascii=False)
else:
sText = "Suggestions : " + " | ".join(lSugg)
echo(sText)
exit()
if not xArgs.json:
xArgs.context = False
gce.setOptions({"html": True, "latex": True})
if xArgs.opt_on:
|
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)
else:
sText = generateText(sText, oTokenizer, oDict, 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)
else:
sText = generateText(sText, oTokenizer, oDict, 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):
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)))
elif sText.startswith(">"):
oDict.drawPath(sText[1:].strip())
elif sText.startswith("="):
for sRes in oDict.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")
|
|
|
|
|
|
|
|
|
|
|
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
|
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, oSpellChecker, bContext=xArgs.context, bDebug=False, bEmptyIfNoErrors=xArgs.only_when_errors, bSpellSugg=xArgs.with_spell_sugg, bReturnText=xArgs.textformatter)
else:
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, oSpellChecker, bContext=xArgs.context, bDebug=False, bEmptyIfNoErrors=xArgs.only_when_errors, bSpellSugg=xArgs.with_spell_sugg, lLineSet=lLineSet)
else:
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 oSpellChecker.getMorph(sWord):
echo(" {:<32} {}".format(sMorph, oLexGraphe.formatTags(sMorph)))
elif sText.startswith("!"):
for sWord in sText[1:].strip().split():
if sWord:
for lSugg in oSpellChecker.suggest(sWord):
echo(" | ".join(lSugg))
elif sText.startswith(">"):
oSpellChecker.drawPath(sText[1:].strip())
elif sText.startswith("="):
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
|
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)
if sRes:
echo("\n" + sRes)
else:
echo("\nNo error found.")
sText = _getText(sInputText)
if __name__ == '__main__':
main()
|
|
|
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
|
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, 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()
|