def main ():
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("-j", "--json", help="generate list of errors in JSON", action="store_true")
xParser.add_argument("-w", "--width", help="width in characters (40 < width < 200; default: 100)", type=int, choices=range(40,201,10), default=100)
xParser.add_argument("-tf", "--textformatter", help="auto-format text according to typographical rules", action="store_true")
xParser.add_argument("-tfo", "--textformatteronly", help="auto-format text and disable grammar checking (only with option 'file' or 'file_to_file')", action="store_true")
xArgs = xParser.parse_args()
gce.load()
gce.setOptions({"html": True})
oDict = gce.getDictionary()
oTokenizer = tkz.Tokenizer("fr")
oLexGraphe = lxg.Lexicographe(oDict)
if xArgs.textformatter or xArgs.textformatteronly:
oTF = tf.TextFormatter()
sText = clipboard.get()
bDebug = False
for sParagraph in txt.getParagraph(sText):
if xArgs.textformatter:
sText = oTF.formatText(sText)
sRes = generateText(0, sText, oTokenizer, oDict, xArgs.json, nWidth=xArgs.width, bDebug=bDebug, bEmptyIfNoErrors=True)
if sRes:
clipboard.set(sRes)
else:
clipboard.set("No errors found.")
print(sRes)
def main():
'''Read the file and run grammalecte on it'''
# Load grammalecte.
gce.load()
dictionary = gce.getDictionary()
tokenizer = tkz.Tokenizer("fr")
# Read input from stdin or first arg.
text_input = [line for line in fileinput.input()]
text, lineset = txt.createParagraphWithLines(list(enumerate(text_input)))
# Grammar errors
gramm_err = gce.parse(text, "FR", bDebug=False, bContext=True)
# Spelling errors
spell_err = []
for token in tokenizer.genTokens(text):
if token['sType'] == "WORD" and not dictionary.isValidToken(
token['sValue']):
spell_err.append(token)
# Get colums and lines.
gramm_err, spell_err = txt.convertToXY(gramm_err, spell_err, lineset)
# Output
for i in list(gramm_err):
print('grammaire|{}|{}|{}\n'.format(i['nStartY'] + 1, i['nStartX'] + 1,
i['sMessage']))
for i in list(spell_err):
print('orthographe|{}|{}|{}\n'.format(i['nStartY'] + 1,
i['nStartX'] + 1,
'Mot absent du dictionnaire'))
def main ():
xParser = argparse.ArgumentParser()
xParser.add_argument("-d", "--debug", help="display text transformation and disambiguation", action="store_true")
xParser.add_argument("-p", "--parse", help="parse and display sentence structure", action="store_true")
xParser.add_argument("-v", "--validate", help="validate text only", action="store_true")
xParser.add_argument("-a", "--autocorrect", help="try to correct automatically", action="store_true")
xParser.add_argument("-i", "--ignore-rule", help="ignore this rule (can be used more than once)", action="append", default=[])
xParser.add_argument("-tf", "--textformatter", help="auto-format text", action="store_true")
xArgs = xParser.parse_args()
gce.load()
gce.setOptions({"html": True})
oDict = gce.getDictionary()
oTokenizer = tzr.Tokenizer("fr")
oLexGraphe = lxg.Lexicographe(oDict)
if xArgs.textformatter:
oTF = tf.TextFormatter()
sInputText = "> "
sText = _getText(sInputText)
errors = False
while sText:
if xArgs.parse:
for sWord in sText.split():
if sWord:
echo("* {}".format(sWord))
for sMorph in oDict.getMorph(sWord):
echo(" {:<32} {}".format(sMorph, oLexGraphe.formatTags(sMorph)))
else:
if xArgs.textformatter:
sText = oTF.formatText(sText)
sys.stdout.write(sText)
res = parser(sText, oTokenizer, oDict, bDebug=xArgs.debug, aIgnoredRules=xArgs.ignore_rule)
if xArgs.validate:
if res:
errors = True
else:
if res:
showResult(sText, res, xArgs.autocorrect)
errors = True
else:
echo("No error found")
sText = _getText(sInputText)
if errors:
sys.exit(1)
def perf(sVersion):
print("\nPerformance tests")
gce.load()
aErrs = gce.parse(
"Texte sans importance… utile pour la compilation des règles avant le calcul des perfs."
)
with open("./tests/fr/perf.txt", "r", encoding="utf-8") as hSrc, \
open("./tests/fr/perf_memo.txt", "a", encoding="utf-8") as hDst:
hDst.write("{:<12}{:<20}".format(sVersion,
time.strftime("%Y.%m.%d %H:%M")))
for sText in (s.strip() for s in hSrc
if not s.startswith("#") and s.strip()):
with timeblock(sText[:sText.find(".")], hDst):
aErrs = gce.parse(sText)
hDst.write("\n")
def __init__ (self, ctx, *args):
self.ctx = ctx
self.ServiceName = "com.sun.star.linguistic2.Proofreader"
self.ImplementationName = "org.openoffice.comp.pyuno.Lightproof." + gce.pkg
self.SupportedServiceNames = (self.ServiceName, )
self.locales = []
for i in gce.locales:
l = gce.locales[i]
self.locales.append(Locale(l[0], l[1], l[2]))
self.locales = tuple(self.locales)
xCurCtx = uno.getComponentContext()
# init
gce.load()
# GC options
# opt_handler.load(xCurCtx)
dOpt = Options.load(xCurCtx)
gce.setOptions(dOpt)
# store for results of big paragraphs
self.dResult = {}
self.nMaxRes = 1500
self.lLastRes = deque(maxlen=self.nMaxRes)
self.nRes = 0
def __init__(self, ctx, *args):
self.ctx = ctx
self.ServiceName = "com.sun.star.linguistic2.Proofreader"
self.ImplementationName = "org.openoffice.comp.pyuno.Lightproof." + gce.pkg
self.SupportedServiceNames = (self.ServiceName, )
self.locales = []
for i in gce.locales:
l = gce.locales[i]
self.locales.append(Locale(l[0], l[1], l[2]))
self.locales = tuple(self.locales)
xCurCtx = uno.getComponentContext()
# init
gce.load()
# GC options
# opt_handler.load(xCurCtx)
dOpt = Options.load(xCurCtx)
gce.setOptions(dOpt)
# store for results of big paragraphs
self.dResult = {}
self.nMaxRes = 1500
self.lLastRes = deque(maxlen=self.nMaxRes)
self.nRes = 0
def main ():
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("-j", "--json", help="generate list of errors in JSON", action="store_true")
xParser.add_argument("-w", "--width", help="width in characters (40 < width < 200; default: 100)", type=int, choices=range(40,201,10), default=100)
xParser.add_argument("-tf", "--textformatter", help="auto-format text according to typographical rules", action="store_true")
xParser.add_argument("-tfo", "--textformatteronly", help="auto-format text and disable grammar checking (only with option 'file' or 'file_to_file')", action="store_true")
xArgs = xParser.parse_args()
gce.load()
gce.setOptions({"html": True})
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()
sFile = xArgs.file or xArgs.file_to_file
if sFile:
# file processing
hDst = open(sFile[:sFile.rfind(".")]+".res.txt", "w", encoding="utf-8") if xArgs.file_to_file or sys.platform == "win32" else None
bComma = False
if xArgs.json:
output('{ "grammalecte": "'+gce.version+'", "lang": "'+gce.lang+'", "data" : [\n', hDst)
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:
sText = generateText(i, sText, oTokenizer, oDict, xArgs.json, 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)
bDebug = False
while True:
if sText.startswith("?"):
for sWord in sText[1:].strip().split():
if sWord:
echo("* {}".format(sWord))
for sMorph in oDict.getMorph(sWord):
echo(" {:<32} {}".format(sMorph, oLexGraphe.formatTags(sMorph)))
elif sText.startswith("/+"):
gce.setOptions({ opt:True for opt in sText[2:].strip().split() if opt in gce.getOptions() })
elif sText.startswith("/-"):
gce.setOptions({ opt:False for opt in sText[2:].strip().split() if opt in gce.getOptions() })
elif sText == "/debug" or sText == "/d":
bDebug = not(bDebug)
echo("debug mode on" if bDebug else "debug mode off")
elif sText == "/help" or sText == "/h":
echo(_HELP)
elif sText == "/lopt" or sText == "/l":
echo("\n".join( [ k+":\t"+str(v) for k, v in sorted(gce.getOptions().items()) ] ))
elif sText == "/quit" or sText == "/q":
break
elif sText.startswith("/rl"):
# reload (todo)
pass
else:
for sParagraph in txt.getParagraph(sText):
if xArgs.textformatter:
sText = oTF.formatText(sText)
sRes = generateText(0, sText, oTokenizer, oDict, xArgs.json, nWidth=xArgs.width, bDebug=bDebug, bEmptyIfNoErrors=True)
if sRes:
echo("\n" + sRes)
else:
echo("\nNo error found.")
sText = _getText(sInputText)
def main ():
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("-d", "--debug", help="display text transformation and disambiguation", action="store_true")
xParser.add_argument("-w", "--width", help="width in characters (40 < width < 200; default: 100)", type=int, choices=range(40,201,10), default=100)
xParser.add_argument("-tf", "--textformatter", help="auto-format text", action="store_true")
xArgs = xParser.parse_args()
if sys.platform == "win32" and xArgs.file:
xArgs.file_to_file = xArgs.file
xArgs.file = None
gce.load()
gce.setOptions({"html": True})
echo("Grammalecte v{}".format(gce.version))
oDict = gce.getDictionary()
oTokenizer = tzr.Tokenizer("fr")
oLexGraphe = lxg.Lexicographe(oDict)
if xArgs.textformatter:
oTF = tf.TextFormatter()
if xArgs.file:
if os.path.isfile(xArgs.file):
with open(xArgs.file, "r", encoding="utf-8") as hSrc:
for sText in hSrc:
if xArgs.textformatter:
sText = oTF.formatText(sText)
echo(parser(sText, oTokenizer, oDict, nWidth=xArgs.width, bDebug=xArgs.debug))
else:
print("# Error: file not found.")
elif xArgs.file_to_file:
if os.path.isfile(xArgs.file_to_file):
with open(xArgs.file_to_file, "r", encoding="utf-8") as hSrc, \
open(xArgs.file_to_file[:xArgs.file_to_file.rfind(".")]+".res.txt", "w", encoding="utf-8") as hDst:
for i, sText in enumerate(hSrc, 1):
if xArgs.textformatter:
sText = oTF.formatText(sText)
hDst.write(parser(sText, oTokenizer, oDict, nWidth=xArgs.width, bDebug=xArgs.debug))
print("§ %d\r" % i, end="", flush=True)
else:
print("# Error: file not found.")
else:
sInputText = "\n~==========~ Écrivez votre texte [Entrée pour quitter] ~==========~\n"
sText = _getText(sInputText)
while sText:
if sText.startswith("?"):
for sWord in sText[1:].split():
if sWord:
echo("* {}".format(sWord))
for sMorph in oDict.getMorph(sWord):
echo(" {:<32} {}".format(sMorph, oLexGraphe.formatTags(sMorph)))
elif sText == "rl":
# reload (todo)
pass
else:
if xArgs.textformatter:
sText = oTF.formatText(sText)
res = parser(sText, oTokenizer, oDict, nWidth=xArgs.width, bDebug=xArgs.debug, bEmptyIfNoErrors=True)
echo("\n"+res if res else "\nNo error found.")
sText = _getText(sInputText)
def main():
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("-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")
xParser.add_argument(
"-tf",
"--textformatter",
help=
"auto-format text according to typographical rules (unavailable with option --concat_lines)",
action="store_true")
xParser.add_argument(
"-tfo",
"--textformatteronly",
help=
"auto-format text and disable grammar checking (only with option --file or --file_to_file)",
action="store_true")
xParser.add_argument(
"-ctx",
"--context",
help="return errors with context (only with option --json)",
action="store_true")
xParser.add_argument(
"-w",
"--width",
help="width in characters (40 < width < 200; default: 100)",
type=int,
choices=range(40, 201, 10),
default=100)
xParser.add_argument("-lo",
"--list_options",
help="list options",
action="store_true")
xParser.add_argument("-lr",
"--list_rules",
nargs="?",
help="list rules [regex pattern as filter]",
const="*")
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()
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 not xArgs.json:
xArgs.context = False
gce.setOptions({"html": True, "latex": True})
if xArgs.opt_on:
gce.setOptions(
{opt: True
for opt in xArgs.opt_on if opt in gce.getOptions()})
if xArgs.opt_off:
gce.setOptions(
{opt: False
for opt in xArgs.opt_off if opt in gce.getOptions()})
if xArgs.rule_off:
for sRule in xArgs.rule_off:
gce.ignoreRule(sRule)
sFile = xArgs.file or xArgs.file_to_file
if sFile:
# file processing
hDst = open(
sFile[:sFile.rfind(".")] + ".res.txt", "w", encoding="utf-8"
) if xArgs.file_to_file or sys.platform == "win32" else None
bComma = False
if xArgs.json:
output(
'{ "grammalecte": "' + gce.version + '", "lang": "' +
gce.lang + '", "data" : [\n', hDst)
if not xArgs.concat_lines:
# pas de concaténation des lignes
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,
bReturnText=xArgs.textformatter)
else:
sText = generateText(
sText,
oTokenizer,
oDict,
bDebug=False,
bEmptyIfNoErrors=xArgs.only_when_errors,
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,
lLineSet=lLineSet)
else:
sText = generateText(
sText,
oTokenizer,
oDict,
bDebug=False,
bEmptyIfNoErrors=xArgs.only_when_errors,
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("* {}".format(sWord))
for sMorph in oDict.getMorph(sWord):
echo(" {:<32} {}".format(
sMorph, oLexGraphe.formatTags(sMorph)))
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")
elif sText.startswith("/-- "):
for sRule in sText[3:].strip().split():
gce.ignoreRule(sRule)
echo("done")
elif sText.startswith("/++ "):
for sRule in sText[3:].strip().split():
gce.reactivateRule(sRule)
echo("done")
elif sText == "/debug" or sText == "/d":
xArgs.debug = not (xArgs.debug)
echo("debug mode on" if xArgs.debug else "debug mode off")
elif sText == "/textformatter" or sText == "/tf":
xArgs.textformatter = not (xArgs.textformatter)
echo(
"textformatter on" if xArgs.debug else "textformatter off")
elif sText == "/help" or sText == "/h":
echo(_HELP)
elif sText == "/lopt" or sText == "/l":
gce.displayOptions("fr")
elif sText.startswith("/lr"):
sText = sText.strip()
sFilter = sText[sText.find(" "):].strip(
) if sText != "/lr" and sText != "/rules" else None
gce.displayRules(sFilter)
elif sText == "/quit" or sText == "/q":
break
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)
dToken['sValue']):
aSpellErrs.append(dToken)
if bEmptyIfNoErrors and not aGrammErrs and not aSpellErrs:
return ""
return " " + json.dumps(
{
"iParagraph": iParagraph,
"lGrammarErrors": aGrammErrs,
"lSpellingErrors": aSpellErrs
},
ensure_ascii=False)
if __name__ == '__main__':
gce.load()
echo("Grammalecte v{}".format(gce.version))
dServerOptions = getServerOptions()
dGCOptions = getConfigOptions("fr")
if dGCOptions:
gce.setOptions(dGCOptions)
dServerGCOptions = gce.getOptions()
echo("Grammar options:\n" + " | ".join(
[k + ": " + str(v) for k, v in sorted(dServerGCOptions.items())]))
oDict = gce.getDictionary()
oTokenizer = tkz.Tokenizer("fr")
oTF = tf.TextFormatter()
dUser = {}
userGenerator = genUserId()
app = Bottle()
def setUpClass(cls):
gce.load()
cls._zError = re.compile(r"\{\{.*?\}\}")
cls._aRuleTested = set()