def synt(i, analysis, tag, mult_anal):
if analysis["case"][0] in cases.keys():
form = analysis["number"][0] + " " + cases[analysis["case"][0]]
new_word = synthesize(analysis["lemma"], form=form)
if len(new_word) > 0 and i.lower() in new_word:
info = i + "\t" + i + "\t" + tag
lines_list.append(info)
else:
if mult_anal == False:
add_manual_correction_if_available(i)
else:
form = analysis["number"][0] + " " + analysis["case"][0]
new_word = synthesize(analysis["lemma"], form=form)
if len(new_word) > 0 and i.lower() in new_word:
info = i + "\t" + i + "\t" + tag
lines_list.append(info)
else:
if mult_anal == False:
add_manual_correction_if_available(i)
def synthesizeWord(word, f):
"""
Changes the word's form without changing it form plural to singular or vice versa
:param word: word to be formed
:param f: desired form
:return: word in desired form
"""
# need to check if the title is plural or not.
form = analyze(word)[0]["analysis"][0]["form"]
return synthesize(word, form[:2] + " " + f, "S")[0]
def answer(self, layer):
"""
Creates answer for email question
:param structUnits: asked structuralunits
:return: structuralunits email
"""
results = []
structUnits = layer[wt.structureUnitCode]
for id in structUnits:
json = oisStructuralUnits.getStructuralUnit(id)
name = json['name']['et'].split(" ")
name[-1] = synthesize(name[-1], 'sg g')[0]
results.append(" ".join(name).capitalize() + "(" + json['code'] +
")" + " email on " + json['email'])
return "\n".join(results) + "."
def answer(self, layer):
"""
Creates answer for language question
:param layer: Current frame layer
:return: courses language
"""
courseIds = layer[wt.courseID]
results = []
for id in courseIds:
json = oisCourses.coursesId(id)
lang = json['target']['language']['et'].split(" ")
lang[-1] = synthesize(lang[-1], "sg in", "S")[0]
results.append("Aine " + json['title']['et'] + "(" + id + ")" +
" on " + " ".join(lang))
return "\n".join(results) + "."
def others_check(morph, analysis, tagged_i, i, mult_anal):
if ("unknown_attribute" in analysis.keys() and "Emo"
in analysis["unknown_attribute"]) or (analysis["partofspeech"]
== "E"):
info = i + "\t" + analysis["lemma"] + "\t" + "Emo"
lines_list.append(info)
elif analysis["partofspeech"] == "Z":
info = i + "\t" + analysis["lemma"] + "\t" + "Punct"
lines_list.append(info)
else:
if "subtype" in analysis.keys(
) and "prop" in analysis["subtype"] and not re.search(
"\d", analysis["lemma"]):
if analysis["case"][0] in cases.keys():
form = analysis["number"][0] + " " + cases[analysis["case"][0]]
new_word = synthesize(analysis["lemma"], form=form)
else:
form = analysis["number"][0] + " " + analysis["case"][0]
new_word = synthesize(analysis["lemma"], form=form)
if len(new_word) > 0:
if i.lower() in new_word:
info = i + "\t" + i + "\t" + "Name"
lines_list.append(info)
elif analysis["case"][0] == "gen" or analysis["case"][
0] == "part":
if new_word[-1][-1] in [
"a", "e", "i", "o", "u", "õ", "ä", "ö"
] and new_word[-1][-1] != i[-1]:
if analysis["case"][0] == "gen":
info = i + "\t" + new_word[
-1] + "\t" + "Spell_Unknown_Gen"
lines_list.append(info)
else:
info = i + "\t" + new_word[
-1] + "\t" + "Spell_Unknown_Part"
lines_list.append(info)
else:
info = i + "\t" + new_word[-1].capitalize(
) + "\t" + "Name"
lines_list.append(info)
else:
info = i + "\t" + new_word[-1].capitalize() + "\t" + "Name"
lines_list.append(info)
else:
if mult_anal == False:
add_manual_correction_if_available(i)
elif ("subtype" in analysis.keys()
and "prop" in analysis["subtype"]) or (
(analysis["partofspeech"] == "Y" or analysis["partofspeech"]
== "S") and re.search("\d", analysis["lemma"])):
if (("case" not in analysis.keys()) or
("case" in analysis.keys() and "nom" in analysis["case"])
and "sg" in analysis["number"]):
if i in new_analyses.keys():
info = new_analyses[i]
lines_list.append(info)
else:
info = i + "\t" + analysis["lemma"] + "\t" + "Abbrev_Num"
lines_list.append(info)
else:
if i.lower() == analysis["lemma"].lower():
info = i + "\t" + analysis["lemma"] + "\t" + "Abbrev_Num"
lines_list.append(info)
else:
if mult_anal == False:
add_manual_correction_if_available(i)
elif analysis["partofspeech"] == "Y" and not re.search(
"\d", analysis["lemma"]):
if ("case" in analysis.keys() and "nom" in analysis["case"] and
"sg" in analysis["number"]) or ("case"
not in analysis.keys()):
info = i + "\t" + analysis["lemma"] + "\t" + "Abbrev"
lines_list.append(info)
else:
if "case" in analysis.keys():
if analysis["case"][0] in cases.keys():
new_word = synthesize(analysis["lemma"],
form=analysis["number"][0] +
" " + cases[analysis["case"][0]])
else:
new_word = synthesize(analysis["lemma"],
form=analysis["number"][0] +
" " + analysis["case"][0])
if len(new_word) > 0:
info = i + "\t" + new_word[-1] + "\t" + "Abbrev"
lines_list.append(info)
else:
if mult_anal == False:
add_manual_correction_if_available(i)
else:
if mult_anal == False:
add_manual_correction_if_available(i)
else:
if morph.lemma != None and analysis["lemma"].lower(
) == morph.lemma.lower():
info = i + "\t" + tagged_i.text + "\t" + "Ok"
lines_list.append(info)
elif ("-" in i or ":" in i or "/" in i):
if i == analysis["lemma"]:
info = i + "\t" + analysis["lemma"] + "\t" + "Word_w_Punct"
lines_list.append(info)
else:
if "case" in analysis.keys():
if mult_anal == False:
synt(i, analysis, "Word_w_Punct",
mult_anal == False)
elif mult_anal == True:
synt(i, analysis, "Word_w_Punct",
mult_anal == True)
else:
if "partofspeech" in analysis.keys() and (
analysis["partofspeech"] == "J"
or analysis["partofspeech"] == "K"
or analysis["partofspeech"] == "D"
or analysis["partofspeech"] == "B"):
if analysis["lemma"].lower() == i.lower():
info = i + "\t" + analysis[
"lemma"] + "\t" + "Ok"
lines_list.append(info)
else:
ld = distance(i.lower(),
analysis["lemma"].lower())
if ld > 1:
if i[0].isupper():
info = i + "\t" + analysis[
"lemma"].capitalize(
) + "\t" + "Spell_ED>1"
lines_list.append(info)
else:
info = i + "\t" + analysis[
"lemma"] + "\t" + "Spell_ED>1"
lines_list.append(info)
elif ld == 1:
if i[0].isupper():
info = i + "\t" + analysis[
"lemma"].capitalize(
) + "\t" + "Spell_ED_1"
lines_list.append(info)
else:
info = i + "\t" + analysis[
"lemma"] + "\t" + "Spell_ED_1"
lines_list.append(info)
else:
if mult_anal == False:
add_manual_correction_if_available(i)
else:
if mult_anal == False:
add_manual_correction_if_available(i)
else:
if "partofspeech" in analysis.keys() and (
analysis["partofspeech"] == "J"
or analysis["partofspeech"] == "K"
or analysis["partofspeech"] == "D"
or analysis["partofspeech"] == "B"):
if analysis["lemma"].lower() == i.lower():
info = i + "\t" + analysis["lemma"] + "\t" + "Ok"
lines_list.append(info)
else:
if len(re.findall("ä|Ä|ö|Ö|ü|Ü|Õ|õ", i)) < len(
re.findall("ä|Ä|ö|Ö|ü|Ü|Õ|õ",
analysis["lemma"])):
if i[0].isupper():
info = i + "\t" + analysis["lemma"].capitalize(
) + "\t" + "Spell_Missing_Diacritics"
lines_list.append(info)
else:
info = i + "\t" + analysis[
"lemma"] + "\t" + "Spell_Missing_Diacritics"
lines_list.append(info)
else:
ld = distance(i.lower(), analysis["lemma"].lower())
if ld > 1:
if i[0].isupper():
info = i + "\t" + analysis[
"lemma"].capitalize(
) + "\t" + "Spell_ED>1"
lines_list.append(info)
else:
info = i + "\t" + analysis[
"lemma"] + "\t" + "Spell_ED>1"
lines_list.append(info)
elif ld == 1:
if i[0].isupper():
info = i + "\t" + analysis[
"lemma"].capitalize(
) + "\t" + "Spell_ED_1"
lines_list.append(info)
else:
info = i + "\t" + analysis[
"lemma"] + "\t" + "Spell_ED_1"
lines_list.append(info)
else:
if mult_anal == False:
add_manual_correction_if_available(i)
elif "case" in analysis.keys():
if analysis["case"][0] in cases.keys():
form = analysis["number"][0] + " " + cases[
analysis["case"][0]]
else:
form = analysis["number"][0] + " " + analysis["case"][0]
if mult_anal == False:
use_edit_distance(analysis, form, i, i2,
mult_anal == False)
elif mult_anal == True:
use_edit_distance(analysis, form, i, i2,
mult_anal == True)
else:
if i.lower() == analysis["lemma"].lower():
info = i + "\t" + analysis["lemma"] + "\t" + "Ok"
lines_list.append(info)
else:
if mult_anal == False:
add_manual_correction_if_available(i)
def verb_check(morph_root, analysis, tagged_i, i, mult_anal):
if morph_root.lemma != None:
morph_root.root = morph_root.root.replace("_", "")
if morph_root.lemma != None and analysis["lemma"] == morph_root.root:
info = i + "\t" + tagged_i.text + "\t" + "Ok"
lines_list.append(info)
else:
if len(re.findall("ä|Ä|ö|Ö|ü|Ü|Õ|õ", i)) < len(
re.findall("ä|Ä|ö|Ö|ü|Ü|Õ|õ", analysis["lemma"])):
if analysis["ending"] == "0" and "tense" in analysis.keys(
) and "polarity" in analysis.keys() and "pres" in analysis[
"tense"] and "neg" in analysis["polarity"]:
new_word = synthesize(analysis["lemma"] + "ma", form="o")
else:
new_word = synthesize(analysis["lemma"] + "ma",
form=analysis["ending"])
if len(new_word) > 0:
if i.lower() in new_word:
info = i + "\t" + i + "\t" + "Spell_Missing_Diacritics"
lines_list.append(info)
else:
if i[0].isupper():
info = i + "\t" + new_word[-1].capitalize(
) + "\t" + "Spell_Missing_Diacritics"
lines_list.append(info)
else:
info = i + "\t" + new_word[
-1] + "\t" + "Spell_Missing_Diacritics"
lines_list.append(info)
else:
if mult_anal == False:
add_manual_correction_if_available(i)
else:
if analysis["ending"] == "0" and "tense" in analysis.keys(
) and "polarity" in analysis.keys() and "pres" in analysis[
"tense"] and "neg" in analysis["polarity"]:
new_word = synthesize(analysis["lemma"] + "ma", form="o")
else:
new_word = synthesize(analysis["lemma"] + "ma",
form=analysis["ending"])
if len(new_word) > 0:
ld = distance(i.lower(), new_word[-1].lower())
if i.lower() in new_word:
info = i + "\t" + i + "\t" + "Ok"
lines_list.append(info)
elif ld > 1:
if i in new_analyses.keys():
info = new_analyses[i]
lines_list.append(info)
else:
if i[0].isupper():
info = i + "\t" + new_word[-1].capitalize(
) + "\t" + "Spell_ED>1"
lines_list.append(info)
else:
info = i + "\t" + new_word[-1] + "\t" + "Spell_ED>1"
lines_list.append(info)
elif ld == 1:
if i[0].isupper():
info = i + "\t" + new_word[-1].capitalize(
) + "\t" + "Spell_ED_1"
lines_list.append(info)
else:
info = i + "\t" + new_word[-1] + "\t" + "Spell_ED_1"
lines_list.append(info)
elif ld == 0:
if i[0].isupper():
info = i + "\t" + new_word[-1].capitalize(
) + "\t" + "Ok"
lines_list.append(info)
else:
info = i + "\t" + new_word[-1] + "\t" + "Ok"
lines_list.append(info)
else:
if mult_anal == False:
add_manual_correction_if_available(i)
else:
if mult_anal == False:
add_manual_correction_if_available(i)
def use_edit_distance(analysis, form, i, i2, mult_anal):
if analysis["case"][0] in cases.keys():
form = analysis["number"][0] + " " + cases[analysis["case"][0]]
new_word = synthesize(analysis["lemma"], form=form)
else:
form = analysis["number"][0] + " " + analysis["case"][0]
new_word = synthesize(analysis["lemma"], form=form)
if len(new_word) > 0:
if i.lower() in new_word:
info = i + "\t" + i + "\t" + "Ok"
lines_list.append(info)
elif analysis["case"][0] == "gen" or analysis["case"][0] == "part":
if new_word[-1][-1] in ["a", "e", "i", "o", "u", "õ", "ä", "ö"
] and new_word[-1][-1] != i[-1]:
if analysis["case"][0] == "gen":
info = i + "\t" + new_word[-1] + "\t" + "Spell_Unknown_Gen"
lines_list.append(info)
else:
info = i + "\t" + new_word[-1] + "\t" + "Spell_Unknown_Part"
lines_list.append(info)
elif len(re.findall("ä|Ä|ö|Ö|ü|Ü|Õ|õ", i)) < len(
re.findall("ä|Ä|ö|Ö|ü|Ü|Õ|õ", new_word[-1])):
info = i + "\t" + new_word[
-1] + "\t" + "Spell_Missing_Diacritics"
lines_list.append(info)
else:
ld = distance(i.lower(), new_word[-1].lower())
if ld > 1:
new_form = analysis["ending"].replace("_", "")
new_word2 = analysis["lemma"] + new_form
if new_word2.lower() == i.lower():
if i[0].isupper():
info = i + "\t" + new_word2.capitalize(
) + "\t" + "Ok"
lines_list.append(info)
else:
info = i + "\t" + new_word2 + "\t" + "Ok"
lines_list.append(info)
else:
if i[0].isupper():
info = i + "\t" + new_word[-1].capitalize(
) + "\t" + "Spell_ED>1"
lines_list.append(info)
else:
info = i + "\t" + new_word[-1] + "\t" + "Spell_ED>1"
lines_list.append(info)
elif ld == 1:
if i[0].isupper():
info = i + "\t" + new_word[-1].capitalize(
) + "\t" + "Spell_ED_1"
lines_list.append(info)
else:
info = i + "\t" + new_word[-1] + "\t" + "Spell_ED_1"
lines_list.append(info)
elif ld == 0:
if i[0].isupper():
info = i + "\t" + new_word[-1].capitalize(
) + "\t" + "Ok"
lines_list.append(info)
else:
info = i + "\t" + new_word[-1] + "\t" + "Ok"
lines_list.append(info)
else:
ld = distance(i.lower(), new_word[-1].lower())
if len(re.findall("ä|Ä|ö|Ö|ü|Ü|Õ|õ", i)) < len(
re.findall("ä|Ä|ö|Ö|ü|Ü|Õ|õ", new_word[-1])):
info = i + "\t" + new_word[
-1] + "\t" + "Spell_Missing_Diacritics"
lines_list.append(info)
elif ld > 1:
new_form = analysis["ending"].replace("_", "")
new_word2 = analysis["lemma"] + new_form
if new_word2.lower() == i.lower():
if i[0].isupper():
info = i + "\t" + new_word2.capitalize() + "\t" + "Ok"
lines_list.append(info)
else:
info = i + "\t" + new_word2 + "\t" + "Ok"
lines_list.append(info)
else:
if i[0].isupper():
info = i + "\t" + new_word[-1].capitalize(
) + "\t" + "Spell_ED>1"
lines_list.append(info)
else:
info = i + "\t" + new_word[-1] + "\t" + "Spell_ED>1"
lines_list.append(info)
elif ld == 1:
if i[0].isupper():
info = i + "\t" + new_word[-1].capitalize(
) + "\t" + "Spell_ED_1"
lines_list.append(info)
else:
info = i + "\t" + new_word[-1] + "\t" + "Spell_ED_1"
lines_list.append(info)
elif ld == 0:
if i[0].isupper():
info = i + "\t" + new_word[-1].capitalize() + "\t" + "Ok"
lines_list.append(info)
else:
info = i + "\t" + new_word[-1] + "\t" + "Ok"
lines_list.append(info)
else:
if analysis["case"][0] in cases.keys():
form = analysis["number"][0] + " " + cases[analysis["case"][0]]
new_word = synthesize(i2[0].lemma, form=form)
else:
form = analysis["number"][0] + " " + analysis["case"][0]
new_word = synthesize(i2[0].lemma, form=form)
if len(new_word) > 0 and i.lower() in new_word:
info = i + "\t" + i + "\t" + "Ok"
lines_list.append(info)
else:
if mult_anal == False:
add_manual_correction_if_available(i)