Grammalecte  Check-in [c661a09a71]

Overview
Comment:[cli] grammatical analysis update
Downloads: Tarball | ZIP archive | SQL archive
Timelines: family | ancestors | descendants | both | cli | salxg
Files: files | file ages | folders
SHA3-256: c661a09a710b24d283d9c9b03c05245c69a0513df9883ed4dbaf61d101f03bfe
User & Date: olr on 2020-08-26 08:17:41
Other Links: branch diff | manifest | tags
Context
2020-08-26
12:19
[graphspell][js] useless return check-in: be32ffb142 user: olr tags: graphspell, salxg
08:17
[cli] grammatical analysis update check-in: c661a09a71 user: olr tags: cli, salxg
08:16
[graphspell] spellchecker: fix call to setLabelsOnToken check-in: dca1db07b3 user: olr tags: graphspell, salxg
Changes

Modified grammalecte-cli.py from [d8f015f794] to [906ad28942].

128
129
130
131
132
133
134




135
136
137
138
139
140
141
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145







+
+
+
+







            else:
                vSugg = m.group(2)[1:]
            return (nError, cAction, vSugg)


def main ():
    "launch the CLI (command line interface)"
    if sys.version < "3.7":
        print("Python 3.7+ required")
        return

    xParser = argparse.ArgumentParser()
    xParser.add_argument("-f", "--file", help="parse file (UTF-8 required!) [on Windows, -f is similar to -ff]", type=str)
    xParser.add_argument("-ff", "--file_to_file", help="parse file (UTF-8 required!) and create a result file (*.res.txt)", type=str)
    xParser.add_argument("-iff", "--interactive_file_to_file", help="parse file (UTF-8 required!) and create a result file (*.res.txt)", type=str)
    xParser.add_argument("-owe", "--only_when_errors", help="display results only when there are errors", action="store_true")
    xParser.add_argument("-j", "--json", help="generate list of errors in JSON (only with option --file or --file_to_file)", action="store_true")
    xParser.add_argument("-cl", "--concat_lines", help="concatenate lines not separated by an empty paragraph (only with option --file or --file_to_file)", action="store_true")
334
335
336
337
338
339
340
341

342
343

344
345


346
347
348
349
350
351








352
353
354
355
356
357
358
338
339
340
341
342
343
344

345
346

347

348
349
350






351
352
353
354
355
356
357
358
359
360
361
362
363
364
365







-
+

-
+
-

+
+
-
-
-
-
-
-
+
+
+
+
+
+
+
+







                # 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)
                    echo(txt.getReadableErrors(lParagraphErrors, xArgs.width))
                    #echo(txt.getReadableErrors(lParagraphErrors, xArgs.width))
                    for dSentence in lSentences:
                        echo("{nStart}:{nEnd}".format(**dSentence))
                        echo("{nStart}:{nEnd}  <{sSentence}>".format(**dSentence))
                        echo("   <" + dSentence["sSentence"]+">")
                        for dToken in dSentence["lTokens"]:
                            if dToken["sType"] == "INFO":
                                continue
                            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))
                            echo("  {0[nStart]:>3}:{0[nEnd]:<3} {1} {0[sType]:<14} {2} {0[sValue]:<16} {3}".format(dToken, \
                                                                                                        "×" if dToken.get("bToRemove", False) else " ",
                                                                                                        "!" if dToken["sType"] == "WORD" and not dToken.get("bValidToken", False) else " ",
                                                                                                        " ".join(dToken.get("aTags", "")) ) )
                            if "lMorph" in dToken:
                                for sMorph, sLabel in zip(dToken["lMorph"], dToken["aLabels"]):
                                    echo("            {0:40}  {1}".format(sMorph, sLabel))
                        #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)
                    if sRes:
                        echo("\n" + sRes)