140
141
142
143
144
145
146
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
|
lAllSugg = []
for dErr in sorted(aErrs, key=lambda d: d["nStart"]):
sRes = sRes[:dErr["nStart"]] + "~" * (dErr["nEnd"] - dErr["nStart"]) + sRes[dErr["nEnd"]:]
sListErr += " * {sLineId} / {sRuleId} at {nStart}:{nEnd}\n".format(**dErr)
lAllSugg.append("|".join(dErr["aSuggestions"]))
self._aTestedRules.add(dErr["sRuleId"].rstrip("0123456789"))
# test messages
if False:
aGramErrs = gc_engine.parse(purgeMessage(dErr["sMessage"]))
aGramErrs = [ dMsgErr for dMsgErr in sorted(aGramErrs, key=lambda d: d["nStart"]) if self._zRuleEnd.sub("", dMsgErr["sRuleId"]) != self._zRuleEnd.sub("", dErr["sRuleId"]) ]
aSpellErrs = self._oSpellChecker.parseParagraph(re.sub("‹\\w+›", lambda m: " " * len(m.group(0)), dErr["sMessage"]))
if aGramErrs or aSpellErrs or "<start>" in dErr["sMessage"] or "<end>" in dErr["sMessage"]:
print("\n# Error in: <" + dErr["sMessage"] + ">\n " + dErr["sLineId"] + " / " + dErr["sRuleId"])
for dMsgErr in aGramErrs:
print(" error: {sLineId} / {sRuleId} at {nStart}:{nEnd}".format(**dMsgErr))
for dMsgErr in aSpellErrs:
print(" spelling mistake: <{sValue}> at {nStart}:{nEnd}".format(**dMsgErr))
sMessage = sMessage.replace("l’ ", "l’").replace("d’ ", "d’").replace("m’ ", "m’").replace("t’ ", "t’").replace("s’ ", "s’").replace("qu’ ", "qu’")
sMessage = sMessage.replace("L’ ", "L’").replace("D’ ", "D’").replace("M’ ", "M’").replace("T’ ", "T’").replace("S’ ", "S’").replace("QU’ ", "QU’")
return sMessage
def main():
"start function"
unittest.main()
if __name__ == '__main__':
main()
|
<
|
|
|
|
|
|
|
|
|
>
|
>
>
|
|
140
141
142
143
144
145
146
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
|
lAllSugg = []
for dErr in sorted(aErrs, key=lambda d: d["nStart"]):
sRes = sRes[:dErr["nStart"]] + "~" * (dErr["nEnd"] - dErr["nStart"]) + sRes[dErr["nEnd"]:]
sListErr += " * {sLineId} / {sRuleId} at {nStart}:{nEnd}\n".format(**dErr)
lAllSugg.append("|".join(dErr["aSuggestions"]))
self._aTestedRules.add(dErr["sRuleId"].rstrip("0123456789"))
# test messages
aGramErrs = gc_engine.parse(purgeMessage(dErr["sMessage"]))
aGramErrs = [ dMsgErr for dMsgErr in sorted(aGramErrs, key=lambda d: d["nStart"]) if self._zRuleEnd.sub("", dMsgErr["sRuleId"]) != self._zRuleEnd.sub("", dErr["sRuleId"]) ]
aSpellErrs = self._oSpellChecker.parseParagraph(re.sub("‹[\\w ’-]+›", lambda m: " " * len(m.group(0)), dErr["sMessage"]))
if aGramErrs or aSpellErrs or "<start>" in dErr["sMessage"] or "<end>" in dErr["sMessage"]:
print("\n# Error in: <" + dErr["sMessage"] + ">\n " + dErr["sLineId"] + " / " + dErr["sRuleId"])
for dMsgErr in aGramErrs:
print(" error: {sLineId} / {sRuleId} at {nStart}:{nEnd}".format(**dMsgErr))
for dMsgErr in aSpellErrs:
print(" spelling mistake: <{sValue}> at {nStart}:{nEnd}".format(**dMsgErr))
return sRes, sListErr, "|||".join(lAllSugg)
def _getExpectedErrors (self, sLine):
sRes = " " * len(sLine)
for i, m in enumerate(self._zError.finditer(sLine)):
nStart = m.start() - (4 * i)
nEnd = m.end() - (4 * (i+1))
sRes = sRes[:nStart] + "~" * (nEnd - nStart) + sRes[nEnd:-4]
return sRes
def purgeMessage (sMessage):
for sToReplace, sReplacement in [
("l’ ", "l’"), ("d’ ", "d’"), ("n’ ", "n’"), ("j’ ", "j’"), ("m’ ", "m’"), ("t’ ", "t’"), ("s’ ", "s’"), ("qu’ ", "qu’"),
("L’ ", "L’"), ("D’ ", "D’"), ("N’ ", "N’"), ("J’ ", "J’"), ("M’ ", "M’"), ("T’ ", "T’"), ("S’ ", "S’"), ("QU’ ", "QU’")
]:
sMessage = sMessage.replace(sToReplace, sReplacement)
return sMessage
def main():
"start function"
unittest.main()
if __name__ == '__main__':
main()
|