def __tryParse(t: 'Token') -> 'AutoannoSentToken':
if (t is None or not MiscHelper.canBeStartOfSentence(t)):
return None
res = AutoannoSentToken(t, t)
has_verb = False
while t is not None:
if (MiscHelper.canBeStartOfSentence(t) and t != res.begin_token):
break
r = t.getReferent()
if (isinstance(r, KeywordReferent)):
res.rank += (r).rank
if ((r).typ == KeywordType.PREDICATE):
has_verb = True
elif (isinstance(t, TextToken)):
mc = t.getMorphClassInDictionary()
if (mc.is_pronoun or mc.is_personal_pronoun):
res.rank -= (1)
elif (t.length_char > 1):
res.rank -= .1
res.end_token = t
t = t.next0_
if (not has_verb):
res.rank /= (3)
res.value = MiscHelper.getTextValueOfMetaToken(
res,
Utils.valToEnum(
(GetTextAttr.KEEPREGISTER) | (GetTextAttr.KEEPQUOTES),
GetTextAttr))
return res
def try_parse(t : 'Token', prev : 'WeaponItemToken', after_conj : bool, attach_high : bool=False) -> 'WeaponItemToken':
res = WeaponItemToken.__try_parse(t, prev, after_conj, attach_high)
if (res is None):
npt = NounPhraseHelper.try_parse(t, NounPhraseParseAttr.NO, 0, None)
if (npt is not None and npt.noun.begin_char > npt.begin_char):
res = WeaponItemToken.__try_parse(npt.noun.begin_token, prev, after_conj, attach_high)
if (res is not None):
if (res.typ == WeaponItemToken.Typs.NOUN):
str0_ = npt.get_normal_case_text(None, MorphNumber.SINGULAR, MorphGender.UNDEFINED, False)
if (str0_ == "РУЧНОЙ ГРАНАТ"):
str0_ = "РУЧНАЯ ГРАНАТА"
if ((Utils.ifNotNull(str0_, "")).endswith(res.value)):
if (res.alt_value is None):
res.alt_value = str0_
else:
str0_ = str0_[0:0+len(str0_) - len(res.value)].strip()
res.alt_value = "{0} {1}".format(str0_, res.alt_value)
res.begin_token = t
return res
return None
if (res.typ == WeaponItemToken.Typs.NAME):
br = BracketHelper.try_parse(res.end_token.next0_, BracketParseAttr.NO, 100)
if (br is not None and br.is_char('(')):
alt = MiscHelper.get_text_value_of_meta_token(br, GetTextAttr.NO)
if (MiscHelper.can_be_equal_cyr_and_latss(res.value, alt)):
res.alt_value = alt
res.end_token = br.end_token
return res
def __try_parse(t: 'Token') -> 'AutoannoSentToken':
if (t is None or not MiscHelper.can_be_start_of_sentence(t)):
return None
res = AutoannoSentToken(t, t)
has_verb = False
while t is not None:
if (MiscHelper.can_be_start_of_sentence(t)
and t != res.begin_token):
break
r = t.get_referent()
if (isinstance(r, KeywordReferent)):
res.rank += r.rank
if (r.typ == KeywordType.PREDICATE):
has_verb = True
elif (isinstance(t, TextToken)):
mc = t.get_morph_class_in_dictionary()
if (mc.is_pronoun or mc.is_personal_pronoun):
res.rank -= (1)
elif (t.length_char > 1):
res.rank -= 0.1
res.end_token = t
t = t.next0_
if (not has_verb):
res.rank /= (3)
res.value = MiscHelper.get_text_value_of_meta_token(
res,
Utils.valToEnum(
(GetTextAttr.KEEPREGISTER) | (GetTextAttr.KEEPQUOTES),
GetTextAttr))
return res
def __toShortString(self, lang : 'MorphLang') -> str:
id0_ = None
for a in self.slots:
if (a.type_name == PersonReferent.ATTR_IDENTITY):
s = str(a.value)
if (id0_ is None or (len(s) < len(id0_))):
id0_ = s
if (id0_ is not None):
return MiscHelper.convertFirstCharUpperAndOtherLower(id0_)
n = self.getStringValue(PersonReferent.ATTR_LASTNAME)
if (n is not None):
res = io.StringIO()
print(n, end="", file=res)
s = self.__findForSurname(PersonReferent.ATTR_FIRSTNAME, n, True)
if (s is not None):
print(" {0}.".format(s[0]), end="", file=res, flush=True)
s = self.__findForSurname(PersonReferent.ATTR_MIDDLENAME, n, False)
if (s is not None):
print("{0}.".format(s[0]), end="", file=res, flush=True)
return MiscHelper.convertFirstCharUpperAndOtherLower(Utils.toStringStringIO(res))
tit = self.__findShortestKingTitul(True)
if (tit is not None):
nam = self.getStringValue(PersonReferent.ATTR_FIRSTNAME)
if (nam is not None):
return MiscHelper.convertFirstCharUpperAndOtherLower("{0} {1}".format(tit, nam))
return self.__toFullString(False, lang)
def to_string(self,
short_variant: bool,
lang: 'MorphLang' = None,
lev: int = 0) -> str:
if (short_variant):
return self.__to_short_string(lang)
else:
res = self.__to_full_string(
PersonReferent.SHOW_LASTNAME_ON_FIRST_POSITION, lang)
if (self.find_slot(PersonReferent.ATTR_NICKNAME, None, True) is
None):
return res
niks = self.get_string_values(PersonReferent.ATTR_NICKNAME)
if (len(niks) == 1):
return "{0} ({1})".format(
res,
MiscHelper.convert_first_char_upper_and_other_lower(
niks[0]))
tmp = io.StringIO()
print(res, end="", file=tmp)
print(" (", end="", file=tmp)
for s in niks:
if (s != niks[0]):
print(", ", end="", file=tmp)
print(MiscHelper.convert_first_char_upper_and_other_lower(s),
end="",
file=tmp)
print(")", end="", file=tmp)
return Utils.toStringStringIO(tmp)
def __compare_surnames_strs(self, s1: str, s2: str) -> bool:
# Сравнение с учётом возможных окончаний
if (s1.startswith(s2) or s2.startswith(s1)):
return True
if (PersonReferent._del_surname_end(s1) ==
PersonReferent._del_surname_end(s2)):
return True
n1 = MiscHelper.get_absolute_normal_value(s1, False)
if (n1 is not None):
if (n1 == MiscHelper.get_absolute_normal_value(s2, False)):
return True
if (MiscHelper.can_be_equals(s1, s2, True, True, False)):
return True
return False
def __checkNames(self, attr_name : str, p : 'PersonReferent') -> bool:
names1 = list()
inits1 = list()
normn1 = list()
for s in self.slots:
if (s.type_name == attr_name):
n = str(s.value)
if (PersonReferent.__isInitial(n)):
inits1.append(n)
else:
names1.append(n)
sn = MiscHelper.getAbsoluteNormalValue(n, False)
if (sn is not None):
normn1.append(sn)
names2 = list()
inits2 = list()
normn2 = list()
for s in p.slots:
if (s.type_name == attr_name):
n = str(s.value)
if (PersonReferent.__isInitial(n)):
inits2.append(n)
else:
names2.append(n)
sn = MiscHelper.getAbsoluteNormalValue(n, False)
if (sn is not None):
normn2.append(sn)
if (len(names1) > 0 and len(names2) > 0):
for n in names1:
if (n in names2):
return True
for n in normn1:
if (n in normn2):
return True
return False
if (len(inits1) > 0):
for n in inits1:
if (n in inits2):
return True
for nn in names2:
if (nn.startswith(n)):
return True
if (len(inits2) > 0):
for n in inits2:
if (n in inits1):
return True
for nn in names1:
if (nn.startswith(n)):
return True
return False
def tryParse(t: 'Token',
prev: 'TransItemToken',
after_conj: bool,
attach_high: bool = False) -> 'TransItemToken':
res = TransItemToken.__TryParse(t, prev, after_conj, attach_high)
if (res is None):
return None
if (res.typ == TransItemToken.Typs.NAME):
br = BracketHelper.tryParse(res.end_token.next0_,
BracketParseAttr.NO, 100)
if (br is not None and br.begin_token.isChar('(')):
alt = MiscHelper.getTextValueOfMetaToken(br, GetTextAttr.NO)
if (MiscHelper.canBeEqualCyrAndLatSS(res.value, alt)):
res.alt_value = alt
res.end_token = br.end_token
return res
def to_string(self,
short_variant: bool,
lang: 'MorphLang',
lev: int = 0) -> str:
res = io.StringIO()
print(MiscHelper.convert_first_char_upper_and_other_lower(
Utils.ifNotNull(self.typ, "?")),
end="",
file=res)
org0_ = Utils.asObjectOrNull(
self.get_slot_value(InstrumentParticipantReferent.ATTR_REF),
Referent)
del0_ = Utils.asObjectOrNull(
self.get_slot_value(InstrumentParticipantReferent.ATTR_DELEGATE),
Referent)
if (org0_ is not None):
print(": {0}".format(org0_.to_string(short_variant, lang, 0)),
end="",
file=res,
flush=True)
if (not short_variant and del0_ is not None):
print(" (в лице {0})".format(
del0_.to_string(True, lang, lev + 1)),
end="",
file=res,
flush=True)
elif (del0_ is not None):
print(": в лице {0}".format(
del0_.to_string(short_variant, lang, lev + 1)),
end="",
file=res,
flush=True)
return Utils.toStringStringIO(res)
def to_string(self,
short_variant: bool,
lang: 'MorphLang',
lev: int = 0) -> str:
res = io.StringIO()
str0_ = None
str0_ = self.get_string_value(InstrumentReferent.ATTR_APPENDIX)
if ((str0_) is not None):
strs = self.get_string_values(InstrumentReferent.ATTR_APPENDIX)
if (len(strs) == 1):
print("Приложение{0}{1}; ".format(
("" if len(str0_) == 0 else " "), str0_),
end="",
file=res,
flush=True)
else:
print("Приложения ", end="", file=res)
i = 0
while i < len(strs):
if (i > 0):
print(",", end="", file=res)
print(strs[i], end="", file=res)
i += 1
print("; ", end="", file=res)
str0_ = self.get_string_value(InstrumentReferent.ATTR_PART)
if ((str0_) is not None):
print("Часть {0}; ".format(str0_), end="", file=res, flush=True)
if (self.typ is not None):
print(MiscHelper.convert_first_char_upper_and_other_lower(
self.typ),
end="",
file=res)
else:
print("Документ", end="", file=res)
if (self.reg_number is not None):
print(" №{0}".format(self.reg_number),
end="",
file=res,
flush=True)
for s in self.slots:
if (s.type_name == InstrumentReferent.ATTR_REGNUMBER
and str(s.value) != self.reg_number):
print("/{0}".format(s.value), end="", file=res, flush=True)
if (self.case_number is not None):
print(" дело №{0}".format(self.case_number),
end="",
file=res,
flush=True)
dt = self.get_string_value(InstrumentReferent.ATTR_DATE)
if (dt is not None):
print(" от {0}".format(dt), end="", file=res, flush=True)
str0_ = self.get_string_value(InstrumentBlockReferent.ATTR_NAME)
if ((str0_) is not None):
if (len(str0_) > 100):
str0_ = (str0_[0:0 + 100] + "...")
print(" \"{0}\"".format(str0_), end="", file=res, flush=True)
str0_ = self.get_string_value(InstrumentReferent.ATTR_GEO)
if ((str0_) is not None):
print(" ({0})".format(str0_), end="", file=res, flush=True)
return Utils.toStringStringIO(res).strip()
def tryAttach(t: 'Token',
can_be_pure_number: bool = False,
typ: 'OrgItemTypeToken' = None) -> 'OrgItemNumberToken':
if (t is None):
return None
tt = Utils.asObjectOrNull(t, TextToken)
if (tt is not None):
t1 = MiscHelper.checkNumberPrefix(tt)
if ((isinstance(t1, NumberToken)) and not t1.is_newline_before):
return OrgItemNumberToken._new1704(tt, t1, str((t1).value))
if ((t.is_hiphen and (isinstance(t.next0_, NumberToken))
and not t.is_whitespace_before) and not t.is_whitespace_after):
if (NumberHelper.tryParseAge(t.next0_) is None):
return OrgItemNumberToken._new1704(t, t.next0_,
str((t.next0_).value))
if (isinstance(t, NumberToken)):
if ((not t.is_whitespace_before and t.previous is not None
and t.previous.is_hiphen)):
return OrgItemNumberToken._new1704(t, t, str((t).value))
if (typ is not None and typ.typ is not None and ((
(typ.typ == "войсковая часть" or typ.typ == "військова частина"
or "колония" in typ.typ) or "колонія" in typ.typ))):
if (t.length_char >= 4 or t.length_char <= 6):
res = OrgItemNumberToken._new1704(t, t, str((t).value))
if (t.next0_ is not None and
((t.next0_.is_hiphen or t.next0_.isCharOf("\\/")))
and not t.next0_.is_whitespace_after):
if ((isinstance(t.next0_.next0_, NumberToken)) and
((t.length_char + t.next0_.next0_.length_char) <
9)):
res.end_token = t.next0_.next0_
res.number = "{0}-{1}".format(
res.number, (res.end_token).value)
elif ((isinstance(t.next0_.next0_, TextToken))
and t.next0_.next0_.length_char == 1
and t.next0_.next0_.chars.is_letter):
res.end_token = t.next0_.next0_
res.number = "{0}{1}".format(
res.number, (res.end_token).term)
elif ((isinstance(t.next0_, TextToken))
and t.next0_.length_char == 1
and t.next0_.chars.is_letter):
res.end_token = t.next0_
res.number = "{0}{1}".format(res.number,
(res.end_token).term)
return res
if (((isinstance(t, TextToken)) and t.length_char == 1
and t.chars.is_letter) and not t.is_whitespace_after):
if (typ is not None and typ.typ is not None and ((
(typ.typ == "войсковая часть" or typ.typ == "військова частина"
or "колония" in typ.typ) or "колонія" in typ.typ))):
tt1 = t.next0_
if (tt1 is not None and tt1.is_hiphen):
tt1 = tt1.next0_
if ((isinstance(tt1, NumberToken))
and not tt1.is_whitespace_before):
res = OrgItemNumberToken(t, tt1)
res.number = "{0}{1}".format((t).term, (tt1).value)
return res
return None
def __ToString(self, short_variant : bool, lang : 'MorphLang', out_cladr : bool, lev : int) -> str:
if (self.is_union and not self.is_state):
res = io.StringIO()
print(self.getStringValue(GeoReferent.ATTR_TYPE), end="", file=res)
for s in self.slots:
if (s.type_name == GeoReferent.ATTR_REF and (isinstance(s.value, Referent))):
print("; {0}".format((s.value).toString(True, lang, 0)), end="", file=res, flush=True)
return Utils.toStringStringIO(res)
name = MiscHelper.convertFirstCharUpperAndOtherLower(self.__getName(lang is not None and lang.is_en))
if (not short_variant):
if (not self.is_state):
if (self.is_city and self.is_region):
pass
else:
typ = self.getStringValue(GeoReferent.ATTR_TYPE)
if (typ is not None):
if (not self.is_city):
i = typ.rfind(' ')
if (i > 0):
typ = typ[i + 1:]
name = "{0} {1}".format(typ, name)
if (not short_variant and out_cladr):
kladr = self.getSlotValue(GeoReferent.ATTR_FIAS)
if (isinstance(kladr, Referent)):
name = "{0} (ФИАС: {1})".format(name, Utils.ifNotNull((kladr).getStringValue("GUID"), "?"))
bti = self.getStringValue(GeoReferent.ATTR_BTI)
if (bti is not None):
name = "{0} (БТИ {1})".format(name, bti)
if (not short_variant and self.higher is not None and (lev < 10)):
if (((self.higher.is_city and self.is_region)) or ((self.findSlot(GeoReferent.ATTR_TYPE, "город", True) is None and self.findSlot(GeoReferent.ATTR_TYPE, "місто", True) is None and self.is_city))):
return "{0}; {1}".format(name, self.higher.__ToString(False, lang, False, lev + 1))
return name
def __tryParseRu(t: 'Token') -> 'VerbPhraseToken':
res = None
t0 = t
not0_ = None
has_verb = False
first_pass2814 = True
while True:
if first_pass2814: first_pass2814 = False
else: t = t.next0_
if (not (t is not None)): break
if (not ((isinstance(t, TextToken)))):
break
tt = Utils.asObjectOrNull(t, TextToken)
if (tt.term == "НЕ"):
not0_ = t
continue
ty = 0
mc = tt.getMorphClassInDictionary()
if (tt.term == "НЕТ"):
ty = 1
elif (mc.is_adverb):
ty = 2
elif (tt.is_pure_verb or tt.is_verb_be):
ty = 1
elif (mc.is_verb):
if (mc.is_preposition or mc.is_misc):
pass
elif (mc.is_noun):
if (tt.term == "СТАЛИ"):
ty = 1
elif (not tt.chars.is_all_lower
and not MiscHelper.canBeStartOfSentence(tt)):
ty = 1
elif (mc.is_proper):
if (tt.chars.is_all_lower):
ty = 1
else:
ty = 1
if (ty == 0):
break
if (res is None):
res = VerbPhraseToken(t0, t)
res.end_token = t
it = VerbPhraseItemToken._new638(t, t, MorphCollection(t.morph))
if (not0_ is not None):
it.begin_token = not0_
it.not0_ = True
not0_ = (None)
it.is_adverb = ty == 2
it.normal = t.getNormalCaseText(
(MorphClass.ADVERB if ty == 2 else MorphClass.VERB), False,
MorphGender.UNDEFINED, False)
res.items.append(it)
if (not has_verb and ty == 1):
res.morph = it.morph
has_verb = True
if (not has_verb):
return None
return res
def __corr_chars(str0_: str, ci: 'CharsInfo', keep_chars: bool) -> str:
if (not keep_chars):
return str0_
if (ci.is_all_lower):
return str0_.lower()
if (ci.is_capital_upper):
return MiscHelper.convert_first_char_upper_and_other_lower(str0_)
return str0_
def __corrChars(self, str0_: str, keep: bool) -> str:
if (not keep):
return str0_
if (self.chars.is_all_lower):
return str0_.lower()
if (self.chars.is_capital_upper):
return MiscHelper.convertFirstCharUpperAndOtherLower(str0_)
return str0_
def __corr_chars(self, str0_: str, keep: bool) -> str:
if (not keep):
return str0_
if (self.chars.is_all_lower):
return str0_.lower()
if (self.chars.is_capital_upper):
return MiscHelper.convert_first_char_upper_and_other_lower(str0_)
return str0_
def to_string(self,
short_variant: bool,
lang: 'MorphLang' = None,
lev: int = 0) -> str:
res = io.StringIO()
str0_ = None
for s in self.slots:
if (s.type_name == WeaponReferent.ATTR_TYPE):
n = s.value
if (str0_ is None or (len(n) < len(str0_))):
str0_ = n
if (str0_ is not None):
print(str0_.lower(), end="", file=res)
str0_ = self.get_string_value(WeaponReferent.ATTR_BRAND)
if ((str0_) is not None):
print(" {0}".format(
MiscHelper.convert_first_char_upper_and_other_lower(str0_)),
end="",
file=res,
flush=True)
str0_ = self.get_string_value(WeaponReferent.ATTR_MODEL)
if ((str0_) is not None):
print(" {0}".format(str0_), end="", file=res, flush=True)
str0_ = self.get_string_value(WeaponReferent.ATTR_NAME)
if ((str0_) is not None):
print(" \"{0}\"".format(
MiscHelper.convert_first_char_upper_and_other_lower(str0_)),
end="",
file=res,
flush=True)
for s in self.slots:
if (s.type_name == WeaponReferent.ATTR_NAME and str0_ !=
(s.value)):
if (LanguageHelper.is_cyrillic_char(str0_[0]) !=
LanguageHelper.is_cyrillic_char(s.value[0])):
print(" ({0})".format(
MiscHelper.
convert_first_char_upper_and_other_lower(s.value)),
end="",
file=res,
flush=True)
break
str0_ = self.get_string_value(WeaponReferent.ATTR_NUMBER)
if ((str0_) is not None):
print(", номер {0}".format(str0_), end="", file=res, flush=True)
return Utils.toStringStringIO(res)
def toString(self,
short_variant: bool,
lang: 'MorphLang',
lev: int = 0) -> str:
res = io.StringIO()
if (self.typ is not None):
print(MiscHelper.convertFirstCharUpperAndOtherLower(self.typ),
end="",
file=res)
else:
kind_ = self.getStringValue(FundsReferent.ATTR_KIND)
if (kind_ is not None):
kind_ = (Utils.asObjectOrNull(
FundsMeta.GLOBAL_META.kind_feature.
convertInnerValueToOuterValue(kind_, None), str))
if (kind_ is not None):
print(MiscHelper.convertFirstCharUpperAndOtherLower(kind_),
end="",
file=res)
else:
print("?", end="", file=res)
if (self.source is not None):
print("; {0}".format(self.source.toString(short_variant, lang, 0)),
end="",
file=res,
flush=True)
if (self.count > 0):
print("; кол-во {0}".format(self.count),
end="",
file=res,
flush=True)
if (self.percent > 0):
print("; {0}%".format(self.percent), end="", file=res, flush=True)
if (not short_variant):
if (self.sum0_ is not None):
print("; {0}".format(self.sum0_.toString(False, lang, 0)),
end="",
file=res,
flush=True)
if (self.price is not None):
print("; номинал {0}".format(
self.price.toString(False, lang, 0)),
end="",
file=res,
flush=True)
return Utils.toStringStringIO(res)
def __corrChars(str0_: str, ci: 'CharsInfo', keep_chars: bool) -> str:
if (not keep_chars):
return str0_
if (ci.is_all_lower):
return str0_.lower()
if (ci.is_capital_upper):
return MiscHelper.convertFirstCharUpperAndOtherLower(str0_)
return str0_
def __checkDetail(rt : 'ReferentToken') -> None:
if (rt.end_token.whitespaces_after_count > 2 or rt.end_token.next0_ is None):
return
if (rt.end_token.next0_.isChar('(')):
br = BracketHelper.tryParse(rt.end_token.next0_, BracketParseAttr.NO, 100)
if (br is not None):
(rt.referent).detail = MiscHelper.getTextValue(br.begin_token.next0_, br.end_token.previous, GetTextAttr.NO)
rt.end_token = br.end_token
def process_ontology_item(self, begin: 'Token') -> 'ReferentToken':
if (begin is None):
return None
ga = GoodAttributeReferent()
if (begin.chars.is_latin_letter):
if (begin.is_value("KEYWORD", None)):
ga.typ = GoodAttrType.KEYWORD
begin = begin.next0_
elif (begin.is_value("CHARACTER", None)):
ga.typ = GoodAttrType.CHARACTER
begin = begin.next0_
elif (begin.is_value("PROPER", None)):
ga.typ = GoodAttrType.PROPER
begin = begin.next0_
elif (begin.is_value("MODEL", None)):
ga.typ = GoodAttrType.MODEL
begin = begin.next0_
if (begin is None):
return None
res = ReferentToken(ga, begin, begin)
t = begin
first_pass3181 = True
while True:
if first_pass3181: first_pass3181 = False
else: t = t.next0_
if (not (t is not None)): break
if (t.is_char(';')):
ga.add_slot(
GoodAttributeReferent.ATTR_VALUE,
MiscHelper.get_text_value(begin, t.previous,
GetTextAttr.NO), False, 0)
begin = t.next0_
continue
res.end_token = t
if (res.end_char > begin.begin_char):
ga.add_slot(
GoodAttributeReferent.ATTR_VALUE,
MiscHelper.get_text_value(begin, res.end_token,
GetTextAttr.NO), False, 0)
if (ga.typ == GoodAttrType.UNDEFINED):
if (not begin.chars.is_all_lower):
ga.typ = GoodAttrType.PROPER
return res
def __compareSurnamesStrs(self, s1 : str, s2 : str) -> bool:
""" Сравнение с учётом возможных окончаний
Args:
s1(str):
s2(str):
"""
if (s1.startswith(s2) or s2.startswith(s1)):
return True
if (PersonReferent._DelSurnameEnd(s1) == PersonReferent._DelSurnameEnd(s2)):
return True
n1 = MiscHelper.getAbsoluteNormalValue(s1, False)
if (n1 is not None):
if (n1 == MiscHelper.getAbsoluteNormalValue(s2, False)):
return True
if (MiscHelper.canBeEquals(s1, s2, True, True, False)):
return True
return False
def get_normal_case_text(self, mc : 'MorphClass'=None, num : 'MorphNumber'=MorphNumber.UNDEFINED, gender : 'MorphGender'=MorphGender.UNDEFINED, keep_chars : bool=False) -> str:
res = self.normal
if (keep_chars):
if (self.chars.is_all_lower):
res = res.lower()
elif (self.chars.is_all_upper):
pass
elif (self.chars.is_capital_upper):
res = MiscHelper.convert_first_char_upper_and_other_lower(res)
return res
def try_parse_author(
t: 'Token',
prev_pers_template: 'FioTemplateType' = FioTemplateType.UNDEFINED
) -> 'BookLinkToken':
if (t is None):
return None
rtp = PersonItemToken.try_parse_person(t, prev_pers_template)
if (rtp is not None):
re = None
if (rtp.data is None):
re = BookLinkToken._new326(t,
(t if rtp == t else rtp.end_token),
BookLinkTyp.PERSON, rtp.referent)
else:
re = BookLinkToken._new327(t, rtp.end_token,
BookLinkTyp.PERSON, rtp)
re.person_template = (Utils.valToEnum(rtp.misc_attrs,
FioTemplateType))
tt = rtp.begin_token
first_pass3018 = True
while True:
if first_pass3018: first_pass3018 = False
else: tt = tt.next0_
if (not (tt is not None and tt.end_char <= rtp.end_char)):
break
if (not (isinstance(tt.get_referent(),
PersonPropertyReferent))):
continue
rt = Utils.asObjectOrNull(tt, ReferentToken)
if (rt.begin_token.chars.is_capital_upper
and tt != rtp.begin_token):
re.start_of_name = MiscHelper.get_text_value_of_meta_token(
rt, GetTextAttr.KEEPREGISTER)
break
return None
return re
if (t.is_char('[')):
re = BookLinkToken.try_parse_author(t.next0_,
FioTemplateType.UNDEFINED)
if (re is not None and re.end_token.next0_ is not None
and re.end_token.next0_.is_char(']')):
re.begin_token = t
re.end_token = re.end_token.next0_
return re
if (((t.is_value("И", None) or t.is_value("ET", None)))
and t.next0_ is not None):
if (t.next0_.is_value("ДРУГИЕ", None)
or t.next0_.is_value("ДР", None)
or t.next0_.is_value("AL", None)):
res = BookLinkToken._new328(t, t.next0_, BookLinkTyp.ANDOTHERS)
if (t.next0_.next0_ is not None
and t.next0_.next0_.is_char('.')):
res.end_token = res.end_token.next0_
return res
return None
def get_morph_variant(self, cas : 'MorphCase', plural : bool) -> str:
""" Сгенерировать текст именной группы в нужном падеже и числе
Args:
cas(MorphCase): нужный падеж
plural(bool): нужное число
Returns:
str: результирующая строка
"""
mi = MorphBaseInfo._new499(cas, MorphLang.RU)
if (plural):
mi.number = MorphNumber.PLURAL
else:
mi.number = MorphNumber.SINGULAR
res = None
for a in self.adjectives:
tt = MiscHelper.get_text_value_of_meta_token(a, GetTextAttr.NO)
if (a.begin_token != a.end_token or not (isinstance(a.begin_token, TextToken))):
pass
else:
tt2 = MorphologyService.get_wordform(tt, mi)
if (tt2 is not None):
tt = tt2
if (res is None):
res = tt
else:
res = "{0} {1}".format(res, tt)
if (self.noun is not None):
tt = MiscHelper.get_text_value_of_meta_token(self.noun, GetTextAttr.NO)
if (self.noun.begin_token != self.noun.end_token or not (isinstance(self.noun.begin_token, TextToken))):
pass
else:
tt2 = MorphologyService.get_wordform(tt, mi)
if (tt2 is not None):
tt = tt2
if (res is None):
res = tt
else:
res = "{0} {1}".format(res, tt)
return res
def getMorphVariant(self, cas: 'MorphCase', plural: bool) -> str:
""" Сгенерировать текст именной группы в нужном падеже и числе
Args:
cas(MorphCase):
plural(bool):
"""
mi = MorphBaseInfo._new551(cas, MorphLang.RU)
if (plural):
mi.number = MorphNumber.PLURAL
else:
mi.number = MorphNumber.SINGULAR
res = None
for a in self.adjectives:
tt = MiscHelper.getTextValueOfMetaToken(a, GetTextAttr.NO)
if (a.begin_token != a.end_token
or not ((isinstance(a.begin_token, TextToken)))):
pass
else:
tt2 = Morphology.getWordform(tt, mi)
if (tt2 is not None):
tt = tt2
if (res is None):
res = tt
else:
res = "{0} {1}".format(res, tt)
if (self.noun is not None):
tt = MiscHelper.getTextValueOfMetaToken(self.noun, GetTextAttr.NO)
if (self.noun.begin_token != self.noun.end_token
or not ((isinstance(self.noun.begin_token, TextToken)))):
pass
else:
tt2 = Morphology.getWordform(tt, mi)
if (tt2 is not None):
tt = tt2
if (res is None):
res = tt
else:
res = "{0} {1}".format(res, tt)
return res
def __attachRusAutoNumber(t: 'Token') -> 'TransItemToken':
v1 = MiscHelper.getCyrLatWord(t, 1)
if (v1 is None or v1.cyr_word is None):
return None
t0 = t
doubt = 0
if (not t.chars.is_all_upper or t.is_whitespace_after):
doubt += 1
t = t.next0_
nt = Utils.asObjectOrNull(t, NumberToken)
if ((nt is None or nt.typ != NumberSpellingType.DIGIT
or nt.morph.class0_.is_adjective)
or (nt.end_char - nt.begin_char) != 2):
return None
t = t.next0_
v2 = MiscHelper.getCyrLatWord(t, 2)
if (v2 is None or v2.cyr_word is None or v2.length != 2):
return None
if (not t.chars.is_all_upper or t.is_whitespace_after):
doubt += 1
res = TransItemToken._new2533(t0, t, TransItemToken.Typs.NUMBER,
TransportKind.AUTO)
res.value = "{0}{1}{2}".format(v1.cyr_word, nt.getSourceText(),
v2.cyr_word)
nt = (Utils.asObjectOrNull(t.next0_, NumberToken))
if (((nt is not None and nt.int_value is not None
and nt.typ == NumberSpellingType.DIGIT)
and not nt.morph.class0_.is_adjective and (nt.int_value < 200))
and (t.whitespaces_after_count < 2)):
n = nt.value
if (len(n) < 2):
n = ("0" + n)
res.alt_value = n
res.end_token = nt
if (res.end_token.next0_ is not None
and res.end_token.next0_.isValue("RUS", None)):
res.end_token = res.end_token.next0_
doubt = 0
if (doubt > 1):
res.is_doubt = True
return res
def __getShortName(self) -> str:
nam = self.name
if (nam is None):
return None
if (len(nam) > 100):
i = 100
while i < len(nam):
if (not str.isalpha(nam[i])):
break
i += 1
if (i < len(nam)):
nam = (nam[0:0 + i] + "...")
return MiscHelper.convertFirstCharUpperAndOtherLower(nam)
def __get_short_name(self) -> str:
nam = self.name
if (nam is None):
return None
if (len(nam) > 100):
i = 100
while i < len(nam):
if (not str.isalpha(nam[i])):
break
i += 1
if (i < len(nam)):
nam = (nam[0:0 + i] + "...")
return MiscHelper.convert_first_char_upper_and_other_lower(nam)
def __correctModel(self) -> None:
tt = self.end_token.next0_
if (tt is None or tt.whitespaces_before_count > 2):
return
if (tt.isValue(":\\/.", None) or tt.is_hiphen):
tt = tt.next0_
if (isinstance(tt, NumberToken)):
tmp = io.StringIO()
print((tt).value, end="", file=tmp)
is_lat = LanguageHelper.isLatinChar(self.value[0])
self.end_token = tt
tt = tt.next0_
first_pass3157 = True
while True:
if first_pass3157: first_pass3157 = False
else: tt = tt.next0_
if (not (tt is not None)): break
if ((isinstance(tt, TextToken)) and tt.length_char == 1
and tt.chars.is_letter):
if (not tt.is_whitespace_before or
((tt.previous is not None and tt.previous.is_hiphen))):
ch = (tt).term[0]
self.end_token = tt
ch2 = chr(0)
if (LanguageHelper.isLatinChar(ch) and not is_lat):
ch2 = LanguageHelper.getCyrForLat(ch)
if (ch2 != (chr(0))):
ch = ch2
elif (LanguageHelper.isCyrillicChar(ch) and is_lat):
ch2 = LanguageHelper.getLatForCyr(ch)
if (ch2 != (chr(0))):
ch = ch2
print(ch, end="", file=tmp)
continue
break
self.value = "{0}-{1}".format(self.value,
Utils.toStringStringIO(tmp))
self.alt_value = MiscHelper.createCyrLatAlternative(self.value)
if (not self.end_token.is_whitespace_after
and self.end_token.next0_ is not None
and ((self.end_token.next0_.is_hiphen
or self.end_token.next0_.isCharOf("\\/")))):
if (not self.end_token.next0_.is_whitespace_after and
(isinstance(self.end_token.next0_.next0_, NumberToken))):
self.end_token = self.end_token.next0_.next0_
self.value = "{0}-{1}".format(self.value,
(self.end_token).value)
if (self.alt_value is not None):
self.alt_value = "{0}-{1}".format(self.alt_value,
(self.end_token).value)