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
238
239
240
241
242
243
244
245
246
|
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
238
239
240
241
242
243
244
245
246
|
-
-
-
+
+
+
-
-
+
-
+
-
+
-
+
-
+
-
+
-
+
-
+
-
+
-
+
-
+
-
+
-
+
|
xParser.add_argument("-sug", "--suggest", help="get suggestions list for given word", type=str)
xParser.add_argument("-on", "--opt_on", nargs="+", help="activate options")
xParser.add_argument("-off", "--opt_off", nargs="+", help="deactivate options")
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()
oGrammarChecker = grammalecte.GrammarChecker("fr")
oSpellChecker = oGrammarChecker.getSpellChecker()
oLexicographer = oGrammarChecker.getLexicographer()
grammalecte.load()
oSpellChecker = grammalecte.getSpellChecker()
oLexicographer = grammalecte.getLexicographer()
oTextFormatter = oGrammarChecker.getTextFormatter()
echo("Grammalecte v{}".format(oGrammarChecker.gce.version))
echo("Grammalecte v{}".format(grammalecte.version))
# list options or rules
if xArgs.list_options or xArgs.list_rules:
if xArgs.list_options:
oGrammarChecker.gce.displayOptions("fr")
grammalecte.gc_options.displayOptions()
if xArgs.list_rules:
oGrammarChecker.gce.displayRules(None if xArgs.list_rules == "*" else xArgs.list_rules)
grammalecte.displayRules(None if xArgs.list_rules == "*" else xArgs.list_rules)
exit()
# spell suggestions
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()
# disable options
if not xArgs.json:
xArgs.context = False
if xArgs.concat_lines:
xArgs.textformatter = False
# grammar options
oGrammarChecker.gce.setOptions({"html": True, "latex": True})
grammalecte.gc_options.setOptions({"html": True, "latex": True})
if xArgs.opt_on:
oGrammarChecker.gce.setOptions({ opt:True for opt in xArgs.opt_on })
grammalecte.gc_options.setOptions({ opt:True for opt in xArgs.opt_on })
if xArgs.opt_off:
oGrammarChecker.gce.setOptions({ opt:False for opt in xArgs.opt_off })
grammalecte.gc_options.setOptions({ opt:False for opt in xArgs.opt_off })
# disable grammar rules
if xArgs.rule_off:
for sRule in xArgs.rule_off:
oGrammarChecker.gce.ignoreRule(sRule)
grammalecte.ignoreRule(sRule)
if xArgs.file or xArgs.file_to_file:
# file processing
sFile = xArgs.file or xArgs.file_to_file
hDst = open(sFile[:sFile.rfind(".")]+".res.txt", "w", encoding="utf-8", newline="\n") if xArgs.file_to_file or sys.platform == "win32" else None
bComma = False
if xArgs.json:
output('{ "grammalecte": "'+oGrammarChecker.gce.version+'", "lang": "'+oGrammarChecker.gce.lang+'", "data" : [\n', hDst)
output('{ "grammalecte": "'+grammalecte.version+'", "lang": "'+grammalecte.lang+'", "data" : [\n', hDst)
for i, sText, lLineSet in generateParagraphFromFile(sFile, xArgs.concat_lines):
if xArgs.textformatter or xArgs.textformatteronly:
sText = oTextFormatter.formatText(sText)
sText = tf.formatText(sText)
if xArgs.textformatteronly:
output(sText, hDst)
continue
if xArgs.json:
sText = oGrammarChecker.getParagraphErrorsAsJSON(i, sText, bContext=xArgs.context, bEmptyIfNoErrors=xArgs.only_when_errors, \
sText = grammalecte.getParagraphErrorsAsJSON(i, sText, bContext=xArgs.context, bEmptyIfNoErrors=xArgs.only_when_errors, \
bSpellSugg=xArgs.with_spell_sugg, bReturnText=xArgs.textformatter, lLineSet=lLineSet)
else:
sText, _ = oGrammarChecker.getParagraphWithErrors(sText, bEmptyIfNoErrors=xArgs.only_when_errors, bSpellSugg=xArgs.with_spell_sugg, nWidth=xArgs.width)
sText, _ = grammalecte.getParagraphWithErrors(sText, 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)
elif xArgs.interactive_file_to_file:
# file processing: interactive mode
sFile = xArgs.interactive_file_to_file
hDst = open(sFile[:sFile.rfind(".")]+".res.txt", "w", encoding="utf-8", newline="\n")
for i, sText, lLineSet in generateParagraphFromFile(sFile, xArgs.concat_lines):
if xArgs.textformatter:
sText = oTextFormatter.formatText(sText)
sText = tf.formatText(sText)
while True:
sResult, lErrors = oGrammarChecker.getParagraphWithErrors(sText, bEmptyIfNoErrors=False, bSpellSugg=True, nWidth=xArgs.width)
sResult, lErrors = grammalecte.getParagraphWithErrors(sText, bEmptyIfNoErrors=False, bSpellSugg=True, nWidth=xArgs.width)
print("\n\n============================== Paragraph " + str(i) + " ==============================\n")
echo(sResult)
print("\n")
vCommand = getCommand()
if vCommand == "q":
# quit
hDst.close()
|
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
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
|
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
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
|
-
+
-
+
-
+
-
+
-
+
-
+
-
+
-
-
+
+
-
-
+
+
|
sTagsPattern = sSearch[nCut+1:]
else:
sFlexPattern = sSearch
sTagsPattern = ""
for aRes in oSpellChecker.select(sFlexPattern, sTagsPattern):
echo("{:<30} {:<30} {}".format(*aRes))
elif sText.startswith("/o+ "):
oGrammarChecker.gce.setOptions({ opt:True for opt in sText[3:].strip().split() if opt in oGrammarChecker.gce.getOptions() })
grammalecte.gc_options.setOptions({ opt:True for opt in sText[3:].strip().split() if opt in grammalecte.gc_options.dOptions })
echo("done")
elif sText.startswith("/o- "):
oGrammarChecker.gce.setOptions({ opt:False for opt in sText[3:].strip().split() if opt in oGrammarChecker.gce.getOptions() })
grammalecte.gc_options.setOptions({ opt:False for opt in sText[3:].strip().split() if opt in grammalecte.gc_options.dOptions })
echo("done")
elif sText.startswith("/r- "):
for sRule in sText[3:].strip().split():
oGrammarChecker.gce.ignoreRule(sRule)
grammalecte.ignoreRule(sRule)
echo("done")
elif sText.startswith("/r+ "):
for sRule in sText[3:].strip().split():
oGrammarChecker.gce.reactivateRule(sRule)
grammalecte.reactivateRule(sRule)
echo("done")
elif sText in ("/debug", "/d"):
xArgs.debug = not xArgs.debug
echo("debug mode on" if xArgs.debug else "debug mode off")
elif sText in ("/textformatter", "/tf"):
xArgs.textformatter = not xArgs.textformatter
echo("textformatter on" if xArgs.debug else "textformatter off")
echo("textformatter on" if xArgs.textformatter else "textformatter off")
elif sText in ("/help", "/h"):
echo(_HELP)
elif sText in ("/lopt", "/lo"):
oGrammarChecker.gce.displayOptions("fr")
grammalecte.gc_options.displayOptions()
elif sText.startswith("/lr"):
sText = sText.strip()
sFilter = sText[sText.find(" "):].strip() if " " in sText else None
oGrammarChecker.gce.displayRules(sFilter)
grammalecte.displayRules(sFilter)
elif sText in ("/quit", "/q"):
break
elif sText.startswith("/rl"):
# reload (todo)
pass
elif sText.startswith("$"):
for sParagraph in txt.getParagraph(sText[1:]):
if xArgs.textformatter:
sParagraph = oTextFormatter.formatText(sParagraph)
lParagraphErrors, lSentences = oGrammarChecker.gce.parse(sParagraph, bDebug=xArgs.debug, bFullInfo=True)
sParagraph = tf.formatText(sParagraph)
lParagraphErrors, lSentences = grammalecte.parse(sParagraph, bDebug=xArgs.debug, bFullInfo=True)
echo(txt.getReadableErrors(lParagraphErrors, xArgs.width))
for dSentence in lSentences:
echo("{nStart}:{nEnd}".format(**dSentence))
echo(" <" + dSentence["sSentence"]+">")
for dToken in dSentence["lToken"]:
echo(" {0[nStart]:>3}:{0[nEnd]:<3} {1} {0[sType]:<14} {2} {0[sValue]:<16} {3:<10} {4}".format(dToken, \
"×" if dToken.get("bToRemove", False) else " ",
"!" if dToken["sType"] == "WORD" and not dToken.get("bValidToken", False) else " ",
" ".join(dToken.get("lMorph", "")), \
"·".join(dToken.get("aTags", "")) ) )
echo(txt.getReadableErrors(dSentence["lGrammarErrors"], xArgs.width))
else:
for sParagraph in txt.getParagraph(sText):
if xArgs.textformatter:
sParagraph = oTextFormatter.formatText(sParagraph)
sRes, _ = oGrammarChecker.getParagraphWithErrors(sParagraph, bEmptyIfNoErrors=xArgs.only_when_errors, nWidth=xArgs.width, bDebug=xArgs.debug)
sParagraph = tf.formatText(sParagraph)
sRes, _ = grammalecte.getParagraphWithErrors(sParagraph, bEmptyIfNoErrors=xArgs.only_when_errors, nWidth=xArgs.width, bDebug=xArgs.debug)
if sRes:
echo("\n" + sRes)
else:
echo("\nNo error found.")
sText = _getText(sInputText)
if __name__ == '__main__':
main()
|