def tryAttachToExist(t: 'Token', p1: 'InstrumentParticipant',
p2: 'InstrumentParticipant') -> 'ReferentToken':
if (t is None):
return None
if (t.begin_char >= 7674 and (t.begin_char < 7680)):
pass
pp = ParticipantToken.tryAttach(t, p1, p2, False)
p = None
rt = None
if (pp is None or pp.kind != ParticipantToken.Kinds.PURE):
pers = t.getReferent()
if ((isinstance(pers, PersonReferent))
or (isinstance(pers, GeoReferent))
or (isinstance(pers, OrganizationReferent))):
if (p1 is not None and p1._containsRef(pers)):
p = p1
elif (p2 is not None and p2._containsRef(pers)):
p = p2
if (p is not None):
rt = ReferentToken(p, t, t)
else:
if (p1 is not None
and ParticipantToken.__isTypesEqual(pp.typ, p1.typ)):
p = p1
elif (p2 is not None
and ParticipantToken.__isTypesEqual(pp.typ, p2.typ)):
p = p2
if (p is not None):
rt = ReferentToken(p, pp.begin_token, pp.end_token)
if (rt.begin_token.previous is not None
and rt.begin_token.previous.isValue("ОТ", None)):
rt.begin_token = rt.begin_token.previous
if (rt is None):
return None
if (rt.end_token.next0_ is not None
and rt.end_token.next0_.isChar(':')):
rt1 = ParticipantToken.tryAttachRequisites(
rt.end_token.next0_.next0_, p, (p2 if p == p1 else p1), False)
if (rt1 is not None):
rt1.begin_token = rt.begin_token
return rt1
rt.end_token = rt.end_token.next0_
while rt.end_token.next0_ is not None and (isinstance(
rt.end_token.next0_.getReferent(), OrganizationReferent)):
org0_ = Utils.asObjectOrNull(rt.end_token.next0_.getReferent(),
OrganizationReferent)
if (rt.referent.findSlot(None, org0_, True) is not None):
rt.end_token = rt.end_token.next0_
continue
break
return rt
def __try_attach_(self, pli : typing.List['PhoneItemToken'], ind : int, is_phone_before : bool, prev_phone : 'PhoneReferent', lev : int=0) -> 'ReferentToken':
if (ind >= len(pli) or lev > 4):
return None
country_code = None
city_code = None
j = ind
if (prev_phone is not None and prev_phone._m_template is not None and pli[j].item_type == PhoneItemToken.PhoneItemType.NUMBER):
tmp = io.StringIO()
jj = j
first_pass3391 = True
while True:
if first_pass3391: first_pass3391 = False
else: jj += 1
if (not (jj < len(pli))): break
if (pli[jj].item_type == PhoneItemToken.PhoneItemType.NUMBER):
print(len(pli[jj].value), end="", file=tmp)
elif (pli[jj].item_type == PhoneItemToken.PhoneItemType.DELIM):
if (pli[jj].value == " "):
break
print(pli[jj].value, end="", file=tmp)
continue
else:
break
templ0 = Utils.toStringStringIO(tmp)
if (templ0 == prev_phone._m_template):
if ((jj + 1) < len(pli)):
if (pli[jj + 1].item_type == PhoneItemToken.PhoneItemType.PREFIX and (jj + 2) == len(pli)):
pass
else:
del pli[jj + 1:jj + 1+len(pli) - jj - 1]
break
if ((j < len(pli)) and pli[j].item_type == PhoneItemToken.PhoneItemType.COUNTRYCODE):
country_code = pli[j].value
if (country_code != "8"):
cc = PhoneHelper.get_country_prefix(country_code)
if (cc is not None and (len(cc) < len(country_code))):
city_code = country_code[len(cc):]
country_code = cc
j += 1
elif ((j < len(pli)) and pli[j].can_be_country_prefix):
k = j + 1
if ((k < len(pli)) and pli[k].item_type == PhoneItemToken.PhoneItemType.DELIM):
k += 1
rrt = self.__try_attach_(pli, k, is_phone_before, None, lev + 1)
if (rrt is not None):
if ((((is_phone_before and pli[j + 1].item_type == PhoneItemToken.PhoneItemType.DELIM and pli[j + 1].begin_token.is_hiphen) and pli[j].item_type == PhoneItemToken.PhoneItemType.NUMBER and len(pli[j].value) == 3) and ((j + 2) < len(pli)) and pli[j + 2].item_type == PhoneItemToken.PhoneItemType.NUMBER) and len(pli[j + 2].value) == 3):
pass
else:
country_code = pli[j].value
j += 1
if (((j < len(pli)) and pli[j].item_type == PhoneItemToken.PhoneItemType.NUMBER and ((pli[j].value[0] == '8' or pli[j].value[0] == '7'))) and country_code is None):
if (len(pli[j].value) == 1):
country_code = pli[j].value
j += 1
elif (len(pli[j].value) == 4):
country_code = pli[j].value[0:0+1]
if (city_code is None):
city_code = pli[j].value[1:]
else:
city_code += pli[j].value[1:]
j += 1
elif (len(pli[j].value) == 11 and j == (len(pli) - 1) and is_phone_before):
ph0 = PhoneReferent()
if (pli[j].value[0] != '8'):
ph0.country_code = pli[j].value[0:0+1]
ph0.number = pli[j].value[1:1+3] + pli[j].value[4:]
return ReferentToken(ph0, pli[0].begin_token, pli[j].end_token)
elif (city_code is None and len(pli[j].value) > 3 and ((j + 1) < len(pli))):
sum0_ = 0
for it in pli:
if (it.item_type == PhoneItemToken.PhoneItemType.NUMBER):
sum0_ += len(it.value)
if (sum0_ == 11):
city_code = pli[j].value[1:]
j += 1
if ((j < len(pli)) and pli[j].item_type == PhoneItemToken.PhoneItemType.CITYCODE):
if (city_code is None):
city_code = pli[j].value
else:
city_code += pli[j].value
j += 1
if ((j < len(pli)) and pli[j].item_type == PhoneItemToken.PhoneItemType.DELIM):
j += 1
if ((country_code == "8" and city_code is None and ((j + 3) < len(pli))) and pli[j].item_type == PhoneItemToken.PhoneItemType.NUMBER):
if (len(pli[j].value) == 3 or len(pli[j].value) == 4):
city_code = pli[j].value
j += 1
if ((j < len(pli)) and pli[j].item_type == PhoneItemToken.PhoneItemType.DELIM):
j += 1
normal_num_len = 0
if (country_code == "421"):
normal_num_len = 9
num = io.StringIO()
templ = io.StringIO()
part_length = list()
delim = None
ok = False
additional = None
std = False
if (country_code is not None and ((j + 4) < len(pli)) and j > 0):
if (((((pli[j - 1].value == "-" or pli[j - 1].item_type == PhoneItemToken.PhoneItemType.COUNTRYCODE)) and pli[j].item_type == PhoneItemToken.PhoneItemType.NUMBER and pli[j + 1].item_type == PhoneItemToken.PhoneItemType.DELIM) and pli[j + 2].item_type == PhoneItemToken.PhoneItemType.NUMBER and pli[j + 3].item_type == PhoneItemToken.PhoneItemType.DELIM) and pli[j + 4].item_type == PhoneItemToken.PhoneItemType.NUMBER):
if ((((len(pli[j].value) + len(pli[j + 2].value)) == 6 or ((len(pli[j].value) == 4 and len(pli[j + 2].value) == 5)))) and ((len(pli[j + 4].value) == 4 or len(pli[j + 4].value) == 1))):
print(pli[j].value, end="", file=num)
print(pli[j + 2].value, end="", file=num)
print(pli[j + 4].value, end="", file=num)
print("{0}{1}{2}{3}{4}".format(len(pli[j].value), pli[j + 1].value, len(pli[j + 2].value), pli[j + 3].value, len(pli[j + 4].value)), end="", file=templ, flush=True)
std = True
ok = True
j += 5
first_pass3392 = True
while True:
if first_pass3392: first_pass3392 = False
else: j += 1
if (not (j < len(pli))): break
if (std):
break
if (pli[j].item_type == PhoneItemToken.PhoneItemType.DELIM):
if (pli[j].is_in_brackets):
continue
if (j > 0 and pli[j - 1].is_in_brackets):
continue
if (templ.tell() > 0):
print(pli[j].value, end="", file=templ)
if (delim is None):
delim = pli[j].value
elif (pli[j].value != delim):
if ((len(part_length) == 2 and ((part_length[0] == 3 or part_length[0] == 4)) and city_code is None) and part_length[1] == 3):
city_code = Utils.toStringStringIO(num)[0:0+part_length[0]]
Utils.removeStringIO(num, 0, part_length[0])
del part_length[0]
delim = pli[j].value
continue
if (is_phone_before and ((j + 1) < len(pli)) and pli[j + 1].item_type == PhoneItemToken.PhoneItemType.NUMBER):
if (num.tell() < 6):
continue
if (normal_num_len > 0 and (num.tell() + len(pli[j + 1].value)) == normal_num_len):
continue
break
else:
continue
ok = False
elif (pli[j].item_type == PhoneItemToken.PhoneItemType.NUMBER):
if (num.tell() == 0 and pli[j].begin_token.previous is not None and pli[j].begin_token.previous.is_table_control_char):
tt = pli[len(pli) - 1].end_token.next0_
if (tt is not None and tt.is_char_of(",.")):
tt = tt.next0_
if (isinstance(tt, NumberToken)):
return None
if ((num.tell() + len(pli[j].value)) > 13):
if (j > 0 and pli[j - 1].item_type == PhoneItemToken.PhoneItemType.DELIM):
j -= 1
ok = True
break
print(pli[j].value, end="", file=num)
part_length.append(len(pli[j].value))
print(len(pli[j].value), end="", file=templ)
ok = True
if (num.tell() > 10):
j += 1
if ((j < len(pli)) and pli[j].item_type == PhoneItemToken.PhoneItemType.ADDNUMBER):
additional = pli[j].value
j += 1
break
elif (pli[j].item_type == PhoneItemToken.PhoneItemType.ADDNUMBER):
additional = pli[j].value
j += 1
break
else:
break
if ((j == (len(pli) - 1) and pli[j].is_in_brackets and ((len(pli[j].value) == 3 or len(pli[j].value) == 4))) and additional is None):
additional = pli[j].value
j += 1
if ((j < len(pli)) and pli[j].item_type == PhoneItemToken.PhoneItemType.PREFIX and pli[j].is_in_brackets):
is_phone_before = True
j += 1
if ((country_code is None and city_code is not None and len(city_code) > 3) and (num.tell() < 8) and city_code[0] != '8'):
if ((len(city_code) + num.tell()) == 10):
pass
else:
cc = PhoneHelper.get_country_prefix(city_code)
if (cc is not None):
if (len(cc) > 1 and (len(city_code) - len(cc)) > 1):
country_code = cc
city_code = city_code[len(cc):]
if (country_code is None and city_code is not None and city_code.startswith("00")):
cc = PhoneHelper.get_country_prefix(city_code[2:])
if (cc is not None):
if (len(city_code) > (len(cc) + 3)):
country_code = cc
city_code = city_code[len(cc) + 2:]
if (num.tell() == 0 and city_code is not None):
if (len(city_code) == 10):
print(city_code[3:], end="", file=num)
part_length.append(num.tell())
city_code = city_code[0:0+3]
ok = True
elif (((len(city_code) == 9 or len(city_code) == 11 or len(city_code) == 8)) and ((is_phone_before or country_code is not None))):
print(city_code, end="", file=num)
part_length.append(num.tell())
city_code = (None)
ok = True
if (num.tell() < 4):
ok = False
if (num.tell() < 7):
if (city_code is not None and (len(city_code) + num.tell()) > 7):
if (not is_phone_before and len(city_code) == 3):
ii = 0
ii = 0
while ii < len(part_length):
if (part_length[ii] == 3):
pass
elif (part_length[ii] > 3):
break
elif ((ii < (len(part_length) - 1)) or (part_length[ii] < 2)):
break
ii += 1
if (ii >= len(part_length)):
if (country_code == "61"):
pass
else:
ok = False
elif (((num.tell() == 6 or num.tell() == 5)) and ((len(part_length) >= 1 and len(part_length) <= 3)) and is_phone_before):
if (pli[0].item_type == PhoneItemToken.PhoneItemType.PREFIX and pli[0].kind == PhoneKind.HOME):
ok = False
elif (prev_phone is not None and prev_phone.number is not None and ((len(prev_phone.number) == num.tell() or len(prev_phone.number) == (num.tell() + 3) or len(prev_phone.number) == (num.tell() + 4)))):
pass
elif (num.tell() > 4 and prev_phone is not None and Utils.toStringStringIO(templ) == prev_phone._m_template):
ok = True
else:
ok = False
if (delim == "." and country_code is None and city_code is None):
ok = False
if ((is_phone_before and country_code is None and city_code is None) and num.tell() > 10):
cc = PhoneHelper.get_country_prefix(Utils.toStringStringIO(num))
if (cc is not None):
if ((num.tell() - len(cc)) == 9):
country_code = cc
Utils.removeStringIO(num, 0, len(cc))
ok = True
if (ok):
if (std):
pass
elif (prev_phone is not None and prev_phone.number is not None and (((len(prev_phone.number) == num.tell() or len(prev_phone.number) == (num.tell() + 3) or len(prev_phone.number) == (num.tell() + 4)) or prev_phone._m_template == Utils.toStringStringIO(templ)))):
pass
elif ((len(part_length) == 3 and part_length[0] == 3 and part_length[1] == 2) and part_length[2] == 2):
pass
elif (len(part_length) == 3 and is_phone_before):
pass
elif ((len(part_length) == 4 and (((part_length[0] + part_length[1]) == 3)) and part_length[2] == 2) and part_length[3] == 2):
pass
elif ((len(part_length) == 4 and part_length[0] == 3 and part_length[1] == 3) and part_length[2] == 2 and part_length[3] == 2):
pass
elif (len(part_length) == 5 and (part_length[1] + part_length[2]) == 4 and (part_length[3] + part_length[4]) == 4):
pass
elif (len(part_length) > 4):
ok = False
elif (len(part_length) > 3 and city_code is not None):
ok = False
elif ((is_phone_before or city_code is not None or country_code is not None) or additional is not None):
ok = True
else:
ok = False
if (((num.tell() == 6 or num.tell() == 7)) and (len(part_length) < 4) and j > 0):
next_ph = self.__get_next_phone(pli[j - 1].end_token.next0_, lev + 1)
if (next_ph is not None):
d = len(next_ph.number) - num.tell()
if (d == 0 or d == 3 or d == 4):
ok = True
end = (pli[j - 1].end_token if j > 0 else None)
if (end is None):
ok = False
if ((ok and city_code is None and country_code is None) and prev_phone is None and not is_phone_before):
if (not end.is_whitespace_after and end.next0_ is not None):
tt = end.next0_
if (tt.is_char_of(".,)") and tt.next0_ is not None):
tt = tt.next0_
if (not tt.is_whitespace_before):
ok = False
if (not ok):
return None
if (templ.tell() > 0 and not str.isdigit(Utils.getCharAtStringIO(templ, templ.tell() - 1))):
Utils.setLengthStringIO(templ, templ.tell() - 1)
if ((country_code is None and city_code is not None and len(city_code) > 3) and num.tell() > 6):
cc = PhoneHelper.get_country_prefix(city_code)
if (cc is not None and ((len(cc) + 1) < len(city_code))):
country_code = cc
city_code = city_code[len(cc):]
if (pli[0].begin_token.previous is not None):
if (pli[0].begin_token.previous.is_value("ГОСТ", None) or pli[0].begin_token.previous.is_value("ТУ", None)):
return None
ph = PhoneReferent()
if (country_code is not None):
ph.country_code = country_code
number = Utils.toStringStringIO(num)
if ((city_code is None and num.tell() > 7 and len(part_length) > 0) and (part_length[0] < 5)):
city_code = number[0:0+part_length[0]]
number = number[part_length[0]:]
if (city_code is None and num.tell() == 11 and Utils.getCharAtStringIO(num, 0) == '8'):
city_code = number[1:1+3]
number = number[4:]
if (city_code is None and num.tell() == 10):
city_code = number[0:0+3]
number = number[3:]
if (city_code is not None):
number = (city_code + number)
elif (country_code is None and prev_phone is not None):
ok1 = False
if (len(prev_phone.number) >= (len(number) + 2)):
ok1 = True
elif (templ.tell() > 0 and prev_phone._m_template is not None and LanguageHelper.ends_with(prev_phone._m_template, Utils.toStringStringIO(templ))):
ok1 = True
if (ok1 and len(prev_phone.number) > len(number)):
number = (prev_phone.number[0:0+len(prev_phone.number) - len(number)] + number)
if (ph.country_code is None and prev_phone is not None and prev_phone.country_code is not None):
if (len(prev_phone.number) == len(number)):
ph.country_code = prev_phone.country_code
ok = False
for d in number:
if (d != '0'):
ok = True
break
if (not ok):
return None
if (country_code is not None):
if (len(number) < 7):
return None
else:
s = PhoneHelper.get_country_prefix(number)
if (s is not None):
num2 = number[len(s):]
if (len(num2) >= 10 and len(num2) <= 11):
number = num2
if (s != "7"):
ph.country_code = s
if (len(number) == 8 and prev_phone is None):
return None
if (len(number) > 11):
if ((len(number) < 14) and ((country_code == "1" or country_code == "43"))):
pass
else:
return None
ph.number = number
if (additional is not None):
ph.add_slot(PhoneReferent.ATTR_ADDNUMBER, additional, True, 0)
if (not is_phone_before and end.next0_ is not None and not end.is_newline_after):
if (end.next0_.is_char_of("+=") or end.next0_.is_hiphen):
return None
if (country_code is not None and country_code == "7"):
if (len(number) != 10):
return None
ph._m_template = Utils.toStringStringIO(templ)
if (j == (len(pli) - 1) and pli[j].item_type == PhoneItemToken.PhoneItemType.PREFIX and not pli[j].is_newline_before):
end = pli[j].end_token
if (pli[j].kind != PhoneKind.UNDEFINED):
ph.kind = pli[j].kind
res = ReferentToken(ph, pli[0].begin_token, end)
if (pli[0].item_type == PhoneItemToken.PhoneItemType.PREFIX and pli[0].end_token.next0_.is_table_control_char):
res.begin_token = pli[1].begin_token
return res
def process(self, kit : 'AnalysisKit') -> None:
""" Основная функция выделения объектов
Args:
container:
lastStage:
"""
ad = kit.getAnalyzerData(self)
t = kit.first_token
first_pass3149 = True
while True:
if first_pass3149: first_pass3149 = False
else: t = t.next0_
if (not (t is not None)): break
tt = t
tok = UriAnalyzer.__m_schemes.tryParse(t, TerminParseAttr.NO)
if (tok is not None):
i = (tok.termin.tag)
tt = tok.end_token
if (tt.next0_ is not None and tt.next0_.isChar('(')):
tok1 = UriAnalyzer.__m_schemes.tryParse(tt.next0_.next0_, TerminParseAttr.NO)
if ((tok1 is not None and tok1.termin.canonic_text == tok.termin.canonic_text and tok1.end_token.next0_ is not None) and tok1.end_token.next0_.isChar(')')):
tt = tok1.end_token.next0_
if (i == 0):
if ((tt.next0_ is None or ((not tt.next0_.isCharOf(":|") and not tt.is_table_control_char)) or tt.next0_.is_whitespace_before) or tt.next0_.whitespaces_after_count > 2):
continue
t1 = tt.next0_.next0_
while t1 is not None and t1.isCharOf("/\\"):
t1 = t1.next0_
if (t1 is None or t1.whitespaces_before_count > 2):
continue
ut = UriItemToken.attachUriContent(t1, False)
if (ut is None):
continue
ur = Utils.asObjectOrNull(ad.registerReferent(UriReferent._new2557(tok.termin.canonic_text.lower(), ut.value)), UriReferent)
rt = ReferentToken(ad.registerReferent(ur), t, ut.end_token)
rt.begin_token = Utils.ifNotNull(UriAnalyzer.__siteBefore(t.previous), t)
if (rt.end_token.next0_ is not None and rt.end_token.next0_.isCharOf("/\\")):
rt.end_token = rt.end_token.next0_
kit.embedToken(rt)
t = (rt)
continue
if (i == 10):
tt = tt.next0_
if (tt is None or not tt.isChar(':')):
continue
tt = tt.next0_
while tt is not None:
if (tt.isCharOf("/\\")):
pass
else:
break
tt = tt.next0_
if (tt is None):
continue
if (tt.isValue("WWW", None) and tt.next0_ is not None and tt.next0_.isChar('.')):
tt = tt.next0_.next0_
if (tt is None or tt.is_newline_before):
continue
ut = UriItemToken.attachUriContent(tt, True)
if (ut is None):
continue
if (len(ut.value) < 4):
continue
ur = Utils.asObjectOrNull(ad.registerReferent(UriReferent._new2557(tok.termin.canonic_text.lower(), ut.value)), UriReferent)
rt = ReferentToken(ad.registerReferent(ur), t, ut.end_token)
rt.begin_token = Utils.ifNotNull(UriAnalyzer.__siteBefore(t.previous), t)
if (rt.end_token.next0_ is not None and rt.end_token.next0_.isCharOf("/\\")):
rt.end_token = rt.end_token.next0_
kit.embedToken(rt)
t = (rt)
continue
if (i == 2):
if (tt.next0_ is None or not tt.next0_.isChar('.') or tt.next0_.is_whitespace_before):
continue
if (tt.next0_.is_whitespace_after and tok.termin.canonic_text != "WWW"):
continue
ut = UriItemToken.attachUriContent(tt.next0_.next0_, True)
if (ut is None):
continue
ur = Utils.asObjectOrNull(ad.registerReferent(UriReferent._new2557("http", ut.value)), UriReferent)
rt = ReferentToken(ur, t, ut.end_token)
rt.begin_token = Utils.ifNotNull(UriAnalyzer.__siteBefore(t.previous), t)
if (rt.end_token.next0_ is not None and rt.end_token.next0_.isCharOf("/\\")):
rt.end_token = rt.end_token.next0_
kit.embedToken(rt)
t = (rt)
continue
if (i == 1):
sch = tok.termin.canonic_text
ut = None
if (sch == "ISBN"):
ut = UriItemToken.attachISBN(tt.next0_)
if ((ut is None and t.previous is not None and t.previous.isChar('(')) and t.next0_ is not None and t.next0_.isChar(')')):
tt0 = t.previous.previous
while tt0 is not None:
if (tt0.whitespaces_after_count > 2):
break
if (tt0.is_whitespace_before):
ut = UriItemToken.attachISBN(tt0)
if (ut is not None and ut.end_token.next0_ != t.previous):
ut = (None)
break
tt0 = tt0.previous
elif ((sch == "RFC" or sch == "ISO" or sch == "ОКФС") or sch == "ОКОПФ"):
ut = UriItemToken.attachISOContent(tt.next0_, ":")
elif (sch == "ГОСТ"):
ut = UriItemToken.attachISOContent(tt.next0_, "-.")
elif (sch == "ТУ"):
if (tok.chars.is_all_upper):
ut = UriItemToken.attachISOContent(tt.next0_, "-.")
if (ut is not None and (ut.length_char < 10)):
ut = (None)
else:
ut = UriItemToken.attachBBK(tt.next0_)
if (ut is None):
continue
ur = Utils.asObjectOrNull(ad.registerReferent(UriReferent._new2560(ut.value, sch)), UriReferent)
if (ut.begin_char < t.begin_char):
rt = ReferentToken(ur, ut.begin_token, t)
if (t.next0_ is not None and t.next0_.isChar(')')):
rt.end_token = t.next0_
else:
rt = ReferentToken(ur, t, ut.end_token)
if (t.previous is not None and t.previous.isValue("КОД", None)):
rt.begin_token = t.previous
if (ur.scheme.startswith("ОК")):
UriAnalyzer.__checkDetail(rt)
kit.embedToken(rt)
t = (rt)
if (ur.scheme.startswith("ОК")):
while t.next0_ is not None:
if (t.next0_.is_comma_and and (isinstance(t.next0_.next0_, NumberToken))):
pass
else:
break
ut = UriItemToken.attachBBK(t.next0_.next0_)
if (ut is None):
break
ur = (Utils.asObjectOrNull(ad.registerReferent(UriReferent._new2560(ut.value, sch)), UriReferent))
rt = ReferentToken(ur, t.next0_.next0_, ut.end_token)
UriAnalyzer.__checkDetail(rt)
kit.embedToken(rt)
t = (rt)
continue
if (i == 3):
t0 = tt.next0_
while t0 is not None:
if (t0.isCharOf(":|") or t0.is_table_control_char or t0.is_hiphen):
t0 = t0.next0_
else:
break
if (t0 is None):
continue
ut = UriItemToken.attachSkype(t0)
if (ut is None):
continue
ur = Utils.asObjectOrNull(ad.registerReferent(UriReferent._new2560(ut.value.lower(), ("skype" if tok.termin.canonic_text == "SKYPE" else tok.termin.canonic_text))), UriReferent)
rt = ReferentToken(ur, t, ut.end_token)
kit.embedToken(rt)
t = (rt)
continue
if (i == 4):
t0 = tt.next0_
if (t0 is not None and ((t0.isChar(':') or t0.is_hiphen))):
t0 = t0.next0_
if (t0 is None):
continue
ut = UriItemToken.attachIcqContent(t0)
if (ut is None):
continue
ur = Utils.asObjectOrNull(ad.registerReferent(UriReferent._new2560(ut.value, "ICQ")), UriReferent)
rt = ReferentToken(ur, t, t0)
kit.embedToken(rt)
t = (rt)
continue
if (i == 5 or i == 6):
t0 = tt.next0_
has_tab_cel = False
is_iban = False
first_pass3150 = True
while True:
if first_pass3150: first_pass3150 = False
else: t0 = t0.next0_
if (not (t0 is not None)): break
if ((((t0.isValue("БАНК", None) or t0.morph.class0_.is_preposition or t0.is_hiphen) or t0.isCharOf(".:") or t0.isValue("РУБЛЬ", None)) or t0.isValue("РУБ", None) or t0.isValue("ДОЛЛАР", None)) or t0.isValue("№", None) or t0.isValue("N", None)):
pass
elif (t0.is_table_control_char):
has_tab_cel = True
elif (t0.isCharOf("\\/") and t0.next0_ is not None and t0.next0_.isValue("IBAN", None)):
is_iban = True
t0 = t0.next0_
elif (t0.isValue("IBAN", None)):
is_iban = True
elif (isinstance(t0, TextToken)):
npt = NounPhraseHelper.tryParse(t0, NounPhraseParseAttr.NO, 0)
if (npt is not None and npt.morph.case_.is_genitive):
t0 = npt.end_token
continue
break
else:
break
if (t0 is None):
continue
ur2 = None
ur2begin = None
ur2end = None
t00 = t0
val = t0.getSourceText()
if (str.isdigit(val[0]) and ((((i == 6 or tok.termin.canonic_text == "ИНН" or tok.termin.canonic_text == "БИК") or tok.termin.canonic_text == "ОГРН" or tok.termin.canonic_text == "СНИЛС") or tok.termin.canonic_text == "ОКПО"))):
if (t0.chars.is_letter):
continue
if (Utils.isNullOrEmpty(val) or not str.isdigit(val[0])):
continue
if (t0.length_char < 9):
tmp = io.StringIO()
print(val, end="", file=tmp)
ttt = t0.next0_
first_pass3151 = True
while True:
if first_pass3151: first_pass3151 = False
else: ttt = ttt.next0_
if (not (ttt is not None)): break
if (ttt.whitespaces_before_count > 1):
break
if (isinstance(ttt, NumberToken)):
print(ttt.getSourceText(), end="", file=tmp)
t0 = ttt
continue
if (ttt.is_hiphen or ttt.isChar('.')):
if (ttt.next0_ is None or not ((isinstance(ttt.next0_, NumberToken)))):
break
if (ttt.is_whitespace_after or ttt.is_whitespace_before):
break
continue
break
val = (None)
if (tmp.tell() == 20):
val = Utils.toStringStringIO(tmp)
elif (tmp.tell() == 9 and tok.termin.canonic_text == "БИК"):
val = Utils.toStringStringIO(tmp)
elif (((tmp.tell() == 10 or tmp.tell() == 12)) and tok.termin.canonic_text == "ИНН"):
val = Utils.toStringStringIO(tmp)
elif (tmp.tell() >= 15 and tok.termin.canonic_text == "Л/С"):
val = Utils.toStringStringIO(tmp)
elif (tmp.tell() >= 11 and ((tok.termin.canonic_text == "ОГРН" or tok.termin.canonic_text == "СНИЛС"))):
val = Utils.toStringStringIO(tmp)
elif (tok.termin.canonic_text == "ОКПО"):
val = Utils.toStringStringIO(tmp)
if (val is None):
continue
elif (not ((isinstance(t0, NumberToken)))):
if ((isinstance(t0, TextToken)) and is_iban):
tmp1 = io.StringIO()
t1 = None
ttt = t0
first_pass3152 = True
while True:
if first_pass3152: first_pass3152 = False
else: ttt = ttt.next0_
if (not (ttt is not None)): break
if (ttt.is_newline_before and ttt != t0):
break
if (ttt.is_hiphen):
continue
if (not ((isinstance(ttt, NumberToken)))):
if (not ((isinstance(ttt, TextToken))) or not ttt.chars.is_latin_letter):
break
print(ttt.getSourceText(), end="", file=tmp1)
t1 = ttt
if (tmp1.tell() >= 34):
break
if (tmp1.tell() < 10):
continue
ur1 = UriReferent._new2560(Utils.toStringStringIO(tmp1), tok.termin.canonic_text)
ur1.addSlot(UriReferent.ATTR_DETAIL, "IBAN", False, 0)
rt1 = ReferentToken(ad.registerReferent(ur1), t, t1)
kit.embedToken(rt1)
t = (rt1)
continue
if (not t0.isCharOf("/\\") or t0.next0_ is None):
continue
tok2 = UriAnalyzer.__m_schemes.tryParse(t0.next0_, TerminParseAttr.NO)
if (tok2 is None or not ((isinstance(tok2.termin.tag, int))) or (tok2.termin.tag) != i):
continue
t0 = tok2.end_token.next0_
while t0 is not None:
if (t0.isCharOf(":N№")):
t0 = t0.next0_
elif (t0.is_table_control_char):
t0 = t0.next0_
t00 = t0
has_tab_cel = True
else:
break
if (not ((isinstance(t0, NumberToken)))):
continue
tmp = io.StringIO()
while t0 is not None:
if (not ((isinstance(t0, NumberToken)))):
break
print(t0.getSourceText(), end="", file=tmp)
t0 = t0.next0_
if (t0 is None or not t0.isCharOf("/\\,") or not ((isinstance(t0.next0_, NumberToken)))):
continue
val = Utils.toStringStringIO(tmp)
Utils.setLengthStringIO(tmp, 0)
ur2begin = t0.next0_
t0 = t0.next0_
while t0 is not None:
if (not ((isinstance(t0, NumberToken)))):
break
if (t0.whitespaces_before_count > 4 and tmp.tell() > 0):
break
print(t0.getSourceText(), end="", file=tmp)
ur2end = t0
t0 = t0.next0_
ur2 = (Utils.asObjectOrNull(ad.registerReferent(UriReferent._new2557(tok2.termin.canonic_text, Utils.toStringStringIO(tmp))), UriReferent))
if (len(val) < 5):
continue
ur = Utils.asObjectOrNull(ad.registerReferent(UriReferent._new2560(val, tok.termin.canonic_text)), UriReferent)
rt = ReferentToken(ur, t, (t0 if ur2begin is None else ur2begin.previous))
if (has_tab_cel):
rt.begin_token = t00
if (ur.scheme.startswith("ОК")):
UriAnalyzer.__checkDetail(rt)
ttt = t.previous
first_pass3153 = True
while True:
if first_pass3153: first_pass3153 = False
else: ttt = ttt.previous
if (not (ttt is not None)): break
if (ttt.is_table_control_char):
break
if (ttt.morph.class0_.is_preposition):
continue
if (ttt.isValue("ОРГАНИЗАЦИЯ", None)):
continue
if (ttt.isValue("НОМЕР", None) or ttt.isValue("КОД", None)):
rt.begin_token = ttt
t = rt.begin_token
break
kit.embedToken(rt)
t = (rt)
if (ur2 is not None):
rt2 = ReferentToken(ur2, ur2begin, ur2end)
kit.embedToken(rt2)
t = (rt2)
continue
continue
if (t.isChar('@')):
u1s = UriItemToken.attachMailUsers(t.previous)
if (u1s is None):
continue
u2 = UriItemToken.attachDomainName(t.next0_, False, True)
if (u2 is None):
continue
for ii in range(len(u1s) - 1, -1, -1):
ur = Utils.asObjectOrNull(ad.registerReferent(UriReferent._new2560("{0}@{1}".format(u1s[ii].value, u2.value).lower(), "mailto")), UriReferent)
b = u1s[ii].begin_token
t0 = b.previous
if (t0 is not None and t0.isChar(':')):
t0 = t0.previous
if (t0 is not None and ii == 0):
br = False
ttt = t0
first_pass3154 = True
while True:
if first_pass3154: first_pass3154 = False
else: ttt = ttt.previous
if (not (ttt is not None)): break
if (not ((isinstance(ttt, TextToken)))):
break
if (ttt != t0 and ttt.whitespaces_after_count > 1):
break
if (ttt.isChar(')')):
br = True
continue
if (ttt.isChar('(')):
if (not br):
break
br = False
continue
if (ttt.isValue("EMAIL", None) or ttt.isValue("MAILTO", None)):
b = ttt
break
if (ttt.isValue("MAIL", None)):
b = ttt
if ((ttt.previous is not None and ttt.previous.is_hiphen and ttt.previous.previous is not None) and ((ttt.previous.previous.isValue("E", None) or ttt.previous.previous.isValue("Е", None)))):
b = ttt.previous.previous
break
if (ttt.isValue("ПОЧТА", None) or ttt.isValue("АДРЕС", None)):
b = t0
ttt = ttt.previous
if (ttt is not None and ttt.isChar('.')):
ttt = ttt.previous
if (ttt is not None and ((t0.isValue("ЭЛ", None) or ttt.isValue("ЭЛЕКТРОННЫЙ", None)))):
b = ttt
if (b.previous is not None and b.previous.isValue("АДРЕС", None)):
b = b.previous
break
if (ttt.morph.class0_.is_preposition):
continue
rt = ReferentToken(ur, b, (u2.end_token if ii == (len(u1s) - 1) else u1s[ii].end_token))
kit.embedToken(rt)
t = (rt)
continue
if (not t.morph.language.is_cyrillic):
if (t.is_whitespace_before or ((t.previous is not None and t.previous.isCharOf(",(")))):
u1 = UriItemToken.attachUrl(t)
if (u1 is not None):
if (u1.is_whitespace_after or u1.end_token.next0_ is None or not u1.end_token.next0_.isChar('@')):
ur = Utils.asObjectOrNull(ad.registerReferent(UriReferent._new2557("http", u1.value)), UriReferent)
rt = ReferentToken(ur, u1.begin_token, u1.end_token)
rt.begin_token = Utils.ifNotNull(UriAnalyzer.__siteBefore(u1.begin_token.previous), u1.begin_token)
kit.embedToken(rt)
t = (rt)
continue
if ((isinstance(t, TextToken)) and not t.is_whitespace_after and t.length_char > 2):
if (UriAnalyzer.__siteBefore(t.previous) is not None):
ut = UriItemToken.attachUriContent(t, True)
if (ut is None or ut.value.find('.') <= 0 or ut.value.find('@') > 0):
continue
ur = Utils.asObjectOrNull(ad.registerReferent(UriReferent._new2557("http", ut.value)), UriReferent)
rt = ReferentToken(ur, t, ut.end_token)
rt.begin_token = UriAnalyzer.__siteBefore(t.previous)
if (rt.end_token.next0_ is not None and rt.end_token.next0_.isCharOf("/\\")):
rt.end_token = rt.end_token.next0_
kit.embedToken(rt)
t = (rt)
continue
if ((t.chars.is_latin_letter and not t.chars.is_all_lower and t.next0_ is not None) and not t.is_whitespace_after):
if (t.next0_.isChar('/')):
rt = UriAnalyzer.__TryAttachLotus(Utils.asObjectOrNull(t, TextToken))
if (rt is not None):
rt.referent = ad.registerReferent(rt.referent)
kit.embedToken(rt)
t = (rt)
continue
def try_attach_territory(
li: typing.List['TerrItemToken'],
ad: 'AnalyzerData',
attach_always: bool = False,
cits: typing.List['CityItemToken'] = None,
exists: typing.List['GeoReferent'] = None) -> 'ReferentToken':
if (li is None or len(li) == 0):
return None
ex_obj = None
new_name = None
adj_list = list()
noun = None
add_noun = None
rt = TerrAttachHelper.__try_attach_moscowao(li, ad)
if (rt is not None):
return rt
if (li[0].termin_item is not None
and li[0].termin_item.canonic_text == "ТЕРРИТОРИЯ"):
res2 = TerrAttachHelper.__try_attach_pure_terr(li, ad)
return res2
if (len(li) == 2):
if (li[0].rzd is not None and li[1].rzd_dir is not None):
rzd = GeoReferent()
rzd._add_name(li[1].rzd_dir)
rzd._add_typ_ter(li[0].kit.base_language)
rzd.add_slot(GeoReferent.ATTR_REF, li[0].rzd.referent, False,
0)
rzd.add_ext_referent(li[0].rzd)
return ReferentToken(rzd, li[0].begin_token, li[1].end_token)
if (li[1].rzd is not None and li[0].rzd_dir is not None):
rzd = GeoReferent()
rzd._add_name(li[0].rzd_dir)
rzd._add_typ_ter(li[0].kit.base_language)
rzd.add_slot(GeoReferent.ATTR_REF, li[1].rzd.referent, False,
0)
rzd.add_ext_referent(li[1].rzd)
return ReferentToken(rzd, li[0].begin_token, li[1].end_token)
can_be_city_before = False
adj_terr_before = False
if (cits is not None):
if (cits[0].typ == CityItemToken.ItemType.CITY):
can_be_city_before = True
elif (cits[0].typ == CityItemToken.ItemType.NOUN
and len(cits) > 1):
can_be_city_before = True
k = 0
k = 0
while k < len(li):
if (li[k].onto_item is not None):
if (ex_obj is not None or new_name is not None):
break
if (noun is not None):
if (k == 1):
if (noun.termin_item.canonic_text == "РАЙОН"
or noun.termin_item.canonic_text == "ОБЛАСТЬ"
or noun.termin_item.canonic_text == "СОЮЗ"):
if (isinstance(li[k].onto_item.referent,
GeoReferent)):
if (li[k].onto_item.referent.is_state):
break
ok = False
tt = li[k].end_token.next0_
if (tt is None):
ok = True
elif (tt.is_char_of(",.")):
ok = True
if (not ok):
ok = MiscLocationHelper.check_geo_object_before(
li[0].begin_token)
if (not ok):
adr = AddressItemToken.try_parse(
tt, None, False, False, None)
if (adr is not None):
if (adr.typ ==
AddressItemToken.ItemType.STREET):
ok = True
if (not ok):
break
if (li[k].onto_item is not None):
if (noun.begin_token.is_value("МО", None)
or noun.begin_token.is_value("ЛО", None)):
return None
ex_obj = li[k]
elif (li[k].termin_item is not None):
if (noun is not None):
break
if (li[k].termin_item.is_always_prefix and k > 0):
break
if (k > 0 and li[k].is_doubt):
if (li[k].begin_token == li[k].end_token
and li[k].begin_token.is_value("ЗАО", None)):
break
if (li[k].termin_item.is_adjective
or li[k].is_geo_in_dictionary):
adj_list.append(li[k])
else:
if (ex_obj is not None):
geo_ = Utils.asObjectOrNull(ex_obj.onto_item.referent,
GeoReferent)
if (geo_ is None):
break
if (ex_obj.is_adjective and
((li[k].termin_item.canonic_text == "СОЮЗ" or
li[k].termin_item.canonic_text == "ФЕДЕРАЦИЯ"))):
str0_ = str(ex_obj.onto_item)
if (not li[k].termin_item.canonic_text in str0_):
return None
if (li[k].termin_item.canonic_text == "РАЙОН"
or li[k].termin_item.canonic_text == "ОКРУГ"
or li[k].termin_item.canonic_text == "КРАЙ"):
tmp = io.StringIO()
for s in geo_.slots:
if (s.type_name == GeoReferent.ATTR_TYPE):
print("{0};".format(s.value),
end="",
file=tmp,
flush=True)
if (not li[k].termin_item.canonic_text
in Utils.toStringStringIO(tmp).upper()):
if (k != 1 or new_name is not None):
break
new_name = li[0]
new_name.is_adjective = True
new_name.onto_item = (None)
ex_obj = (None)
noun = li[k]
if (k == 0):
tt = TerrItemToken.try_parse(
li[k].begin_token.previous, None, True, False,
None)
if (tt is not None and tt.morph.class0_.is_adjective):
adj_terr_before = True
else:
if (ex_obj is not None):
break
if (new_name is not None):
break
new_name = li[k]
k += 1
name = None
alt_name = None
full_name = None
morph_ = None
if (ex_obj is not None):
if (ex_obj.is_adjective and not ex_obj.morph.language.is_en
and noun is None):
if (attach_always and ex_obj.end_token.next0_ is not None):
npt = NounPhraseHelper.try_parse(ex_obj.begin_token,
NounPhraseParseAttr.NO, 0,
None)
if (ex_obj.end_token.next0_.is_comma_and):
pass
elif (npt is None):
pass
else:
str0_ = StreetItemToken.try_parse(
ex_obj.end_token.next0_, None, False, None, False)
if (str0_ is not None):
if (str0_.typ == StreetItemType.NOUN
and str0_.end_token == npt.end_token):
return None
else:
cit = CityItemToken.try_parse(ex_obj.end_token.next0_,
None, False, None)
if (cit is not None
and ((cit.typ == CityItemToken.ItemType.NOUN
or cit.typ == CityItemToken.ItemType.CITY))):
npt = NounPhraseHelper.try_parse(
ex_obj.begin_token, NounPhraseParseAttr.NO, 0,
None)
if (npt is not None
and npt.end_token == cit.end_token):
pass
else:
return None
elif (ex_obj.begin_token.is_value("ПОДНЕБЕСНЫЙ", None)):
pass
else:
return None
if (noun is None and ex_obj.can_be_city):
cit0 = CityItemToken.try_parse_back(
ex_obj.begin_token.previous)
if (cit0 is not None
and cit0.typ != CityItemToken.ItemType.PROPERNAME):
return None
if (ex_obj.is_doubt and noun is None):
ok2 = False
if (TerrAttachHelper.__can_be_geo_after(
ex_obj.end_token.next0_)):
ok2 = True
elif (not ex_obj.can_be_surname and not ex_obj.can_be_city):
if ((ex_obj.end_token.next0_ is not None
and ex_obj.end_token.next0_.is_char(')')
and ex_obj.begin_token.previous is not None)
and ex_obj.begin_token.previous.is_char('(')):
ok2 = True
elif (ex_obj.chars.is_latin_letter
and ex_obj.begin_token.previous is not None):
if (ex_obj.begin_token.previous.is_value("IN", None)):
ok2 = True
elif (ex_obj.begin_token.previous.is_value(
"THE", None) and
ex_obj.begin_token.previous.previous is not None
and
ex_obj.begin_token.previous.previous.is_value(
"IN", None)):
ok2 = True
if (not ok2):
cit0 = CityItemToken.try_parse_back(
ex_obj.begin_token.previous)
if (cit0 is not None
and cit0.typ != CityItemToken.ItemType.PROPERNAME):
pass
elif (MiscLocationHelper.check_geo_object_before(
ex_obj.begin_token.previous)):
pass
else:
return None
name = ex_obj.onto_item.canonic_text
morph_ = ex_obj.morph
elif (new_name is not None):
if (noun is None):
return None
j = 1
while j < k:
if (li[j].is_newline_before and not li[0].is_newline_before):
if (BracketHelper.can_be_start_of_sequence(
li[j].begin_token, False, False)):
pass
else:
return None
j += 1
morph_ = noun.morph
if (new_name.is_adjective):
if (noun.termin_item.acronym == "АО"):
if (noun.begin_token != noun.end_token):
return None
if (new_name.morph.gender != MorphGender.FEMINIE):
return None
geo_before = None
tt0 = li[0].begin_token.previous
if (tt0 is not None and tt0.is_comma_and):
tt0 = tt0.previous
if (not li[0].is_newline_before and tt0 is not None):
geo_before = (Utils.asObjectOrNull(tt0.get_referent(),
GeoReferent))
if (Utils.indexOfList(li, noun, 0) < Utils.indexOfList(
li, new_name, 0)):
if (noun.termin_item.is_state):
return None
if (new_name.can_be_surname and geo_before is None):
if (((noun.morph.case_)
& new_name.morph.case_).is_undefined):
return None
if (MiscHelper.is_exists_in_dictionary(
new_name.begin_token, new_name.end_token,
(MorphClass.ADJECTIVE) | MorphClass.PRONOUN
| MorphClass.VERB)):
if (noun.begin_token != new_name.begin_token):
if (geo_before is None):
if (len(li) == 2 and
TerrAttachHelper.__can_be_geo_after(
li[1].end_token.next0_)):
pass
elif (len(li) == 3
and li[2].termin_item is not None
and TerrAttachHelper.__can_be_geo_after(
li[2].end_token.next0_)):
pass
elif (new_name.is_geo_in_dictionary):
pass
elif (new_name.end_token.is_newline_after):
pass
else:
return None
npt = NounPhraseHelper.try_parse(
new_name.end_token, NounPhraseParseAttr.PARSEPRONOUNS,
0, None)
if (npt is not None
and npt.end_token != new_name.end_token):
if (len(li) >= 3 and li[2].termin_item is not None
and npt.end_token == li[2].end_token):
add_noun = li[2]
else:
return None
rtp = new_name.kit.process_referent(
"PERSON", new_name.begin_token)
if (rtp is not None):
return None
name = ProperNameHelper.get_name_ex(
new_name.begin_token, new_name.end_token,
MorphClass.ADJECTIVE, MorphCase.UNDEFINED,
noun.termin_item.gender, False, False)
else:
ok = False
if (((k + 1) < len(li)) and li[k].termin_item is None
and li[k + 1].termin_item is not None):
ok = True
elif ((k < len(li)) and li[k].onto_item is not None):
ok = True
elif (k == len(li) and not new_name.is_adj_in_dictionary):
ok = True
elif (MiscLocationHelper.check_geo_object_before(
li[0].begin_token) or can_be_city_before):
ok = True
elif (MiscLocationHelper.check_geo_object_after(
li[k - 1].end_token, False)):
ok = True
elif (len(li) == 3 and k == 2):
cit = CityItemToken.try_parse(li[2].begin_token, None,
False, None)
if (cit is not None):
if (cit.typ == CityItemToken.ItemType.CITY
or cit.typ == CityItemToken.ItemType.NOUN):
ok = True
elif (len(li) == 2):
ok = TerrAttachHelper.__can_be_geo_after(
li[len(li) - 1].end_token.next0_)
if (not ok and not li[0].is_newline_before
and not li[0].chars.is_all_lower):
rt00 = li[0].kit.process_referent(
"PERSONPROPERTY", li[0].begin_token.previous)
if (rt00 is not None):
ok = True
if (noun.termin_item is not None
and noun.termin_item.is_strong
and new_name.is_adjective):
ok = True
if (noun.is_doubt and len(adj_list) == 0
and geo_before is None):
return None
name = ProperNameHelper.get_name_ex(
new_name.begin_token, new_name.end_token,
MorphClass.ADJECTIVE, MorphCase.UNDEFINED,
noun.termin_item.gender, False, False)
if (not ok and not attach_always):
if (MiscHelper.is_exists_in_dictionary(
new_name.begin_token, new_name.end_token,
(MorphClass.ADJECTIVE) | MorphClass.PRONOUN
| MorphClass.VERB)):
if (exists is not None):
for e0_ in exists:
if (e0_.find_slot(GeoReferent.ATTR_NAME,
name, True) is not None):
ok = True
break
if (not ok):
return None
full_name = "{0} {1}".format(
ProperNameHelper.get_name_ex(li[0].begin_token,
noun.begin_token.previous,
MorphClass.ADJECTIVE,
MorphCase.UNDEFINED,
noun.termin_item.gender,
False, False),
noun.termin_item.canonic_text)
else:
if (not attach_always or
((noun.termin_item is not None
and noun.termin_item.canonic_text == "ФЕДЕРАЦИЯ"))):
is_latin = noun.chars.is_latin_letter and new_name.chars.is_latin_letter
if (Utils.indexOfList(li, noun, 0) > Utils.indexOfList(
li, new_name, 0)):
if (not is_latin):
return None
if (not new_name.is_district_name
and not BracketHelper.can_be_start_of_sequence(
new_name.begin_token, False, False)):
if (len(adj_list) == 0
and MiscHelper.is_exists_in_dictionary(
new_name.begin_token, new_name.end_token,
(MorphClass.NOUN) | MorphClass.PRONOUN)):
if (len(li) == 2 and noun.is_city_region
and (noun.whitespaces_after_count < 2)):
pass
else:
return None
if (not is_latin):
if ((noun.termin_item.is_region
and not attach_always and
((not adj_terr_before or new_name.is_doubt)))
and not noun.is_city_region and
not noun.termin_item.is_specific_prefix):
if (not MiscLocationHelper.
check_geo_object_before(
noun.begin_token)):
if (not noun.is_doubt and noun.begin_token
!= noun.end_token):
pass
elif ((noun.termin_item.is_always_prefix
and len(li) == 2 and li[0] == noun)
and li[1] == new_name):
pass
else:
return None
if (noun.is_doubt and len(adj_list) == 0):
if (noun.termin_item.acronym == "МО"
or noun.termin_item.acronym == "ЛО"):
if (k == (len(li) - 1)
and li[k].termin_item is not None):
add_noun = li[k]
k += 1
elif (len(li) == 2 and noun == li[0]
and str(new_name).endswith("совет")):
pass
else:
return None
else:
return None
pers = new_name.kit.process_referent(
"PERSON", new_name.begin_token)
if (pers is not None):
return None
name = MiscHelper.get_text_value(new_name.begin_token,
new_name.end_token,
GetTextAttr.NO)
if (new_name.begin_token != new_name.end_token):
ttt = new_name.begin_token.next0_
while ttt is not None and ttt.end_char <= new_name.end_char:
if (ttt.chars.is_letter):
ty = TerrItemToken.try_parse(
ttt, None, False, False, None)
if ((ty is not None and ty.termin_item is not None
and noun is not None)
and ((noun.termin_item.canonic_text
in ty.termin_item.canonic_text
or ty.termin_item.canonic_text
in noun.termin_item.canonic_text))):
name = MiscHelper.get_text_value(
new_name.begin_token, ttt.previous,
GetTextAttr.NO)
break
ttt = ttt.next0_
if (len(adj_list) > 0):
npt = NounPhraseHelper.try_parse(adj_list[0].begin_token,
NounPhraseParseAttr.NO, 0,
None)
if (npt is not None and npt.end_token == noun.end_token):
alt_name = "{0} {1}".format(
npt.get_normal_case_text(None,
MorphNumber.UNDEFINED,
MorphGender.UNDEFINED,
False), name)
else:
if ((len(li) == 1 and noun is not None
and noun.end_token.next0_ is not None) and (isinstance(
noun.end_token.next0_.get_referent(), GeoReferent))):
g = Utils.asObjectOrNull(noun.end_token.next0_.get_referent(),
GeoReferent)
if (noun.termin_item is not None):
tyy = noun.termin_item.canonic_text.lower()
ooo = False
if (g.find_slot(GeoReferent.ATTR_TYPE, tyy, True)
is not None):
ooo = True
elif (tyy.endswith("район") and g.find_slot(
GeoReferent.ATTR_TYPE, "район", True) is not None):
ooo = True
if (ooo):
return ReferentToken._new734(g, noun.begin_token,
noun.end_token.next0_,
noun.begin_token.morph)
if ((len(li) == 1 and noun == li[0]
and li[0].termin_item is not None)
and TerrItemToken.try_parse(li[0].end_token.next0_, None,
True, False, None) is None and
TerrItemToken.try_parse(li[0].begin_token.previous, None,
True, False, None) is None):
if (li[0].morph.number == MorphNumber.PLURAL):
return None
cou = 0
str0_ = li[0].termin_item.canonic_text.lower()
tt = li[0].begin_token.previous
first_pass3158 = True
while True:
if first_pass3158: first_pass3158 = False
else: tt = tt.previous
if (not (tt is not None)): break
if (tt.is_newline_after):
cou += 10
else:
cou += 1
if (cou > 500):
break
g = Utils.asObjectOrNull(tt.get_referent(), GeoReferent)
if (g is None):
continue
ok = True
cou = 0
tt = li[0].end_token.next0_
first_pass3159 = True
while True:
if first_pass3159: first_pass3159 = False
else: tt = tt.next0_
if (not (tt is not None)): break
if (tt.is_newline_before):
cou += 10
else:
cou += 1
if (cou > 500):
break
tee = TerrItemToken.try_parse(tt, None, True, False,
None)
if (tee is None):
continue
ok = False
break
if (ok):
ii = 0
while g is not None and (ii < 3):
if (g.find_slot(GeoReferent.ATTR_TYPE, str0_, True)
is not None):
return ReferentToken._new734(
g, li[0].begin_token, li[0].end_token,
noun.begin_token.morph)
g = g.higher
ii += 1
break
return None
ter = None
if (ex_obj is not None and (isinstance(ex_obj.tag, GeoReferent))):
ter = (Utils.asObjectOrNull(ex_obj.tag, GeoReferent))
else:
ter = GeoReferent()
if (ex_obj is not None):
geo_ = Utils.asObjectOrNull(ex_obj.onto_item.referent,
GeoReferent)
if (geo_ is not None and not geo_.is_city):
ter._merge_slots2(geo_, li[0].kit.base_language)
else:
ter._add_name(name)
if (noun is None and ex_obj.can_be_city):
ter._add_typ_city(li[0].kit.base_language)
else:
pass
elif (new_name is not None):
ter._add_name(name)
if (alt_name is not None):
ter._add_name(alt_name)
if (noun is not None):
if (noun.termin_item.canonic_text == "АО"):
ter._add_typ(
("АВТОНОМНИЙ ОКРУГ" if li[0].kit.base_language.is_ua
else "АВТОНОМНЫЙ ОКРУГ"))
elif (noun.termin_item.canonic_text == "МУНИЦИПАЛЬНОЕ СОБРАНИЕ"
or noun.termin_item.canonic_text
== "МУНІЦИПАЛЬНЕ ЗБОРИ"):
ter._add_typ(("МУНІЦИПАЛЬНЕ УТВОРЕННЯ"
if li[0].kit.base_language.is_ua else
"МУНИЦИПАЛЬНОЕ ОБРАЗОВАНИЕ"))
elif (noun.termin_item.acronym == "МО"
and add_noun is not None):
ter._add_typ(add_noun.termin_item.canonic_text)
else:
if (noun.termin_item.canonic_text == "СОЮЗ"
and ex_obj is not None
and ex_obj.end_char > noun.end_char):
return ReferentToken._new734(ter, ex_obj.begin_token,
ex_obj.end_token,
ex_obj.morph)
ter._add_typ(noun.termin_item.canonic_text)
if (noun.termin_item.is_region and ter.is_state):
ter._add_typ_reg(li[0].kit.base_language)
if (ter.is_state and ter.is_region):
for a in adj_list:
if (a.termin_item.is_region):
ter._add_typ_reg(li[0].kit.base_language)
break
if (ter.is_state):
if (full_name is not None):
ter._add_name(full_name)
res = ReferentToken(ter, li[0].begin_token, li[k - 1].end_token)
if (noun is not None and noun.morph.class0_.is_noun):
res.morph = noun.morph
else:
res.morph = MorphCollection()
ii = 0
while ii < k:
for v in li[ii].morph.items:
bi = MorphBaseInfo()
bi.copy_from(v)
if (noun is not None):
if (bi.class0_.is_adjective):
bi.class0_ = MorphClass.NOUN
res.morph.add_item(bi)
ii += 1
if (li[0].termin_item is not None
and li[0].termin_item.is_specific_prefix):
res.begin_token = li[0].end_token.next0_
if (add_noun is not None and add_noun.end_char > res.end_char):
res.end_token = add_noun.end_token
if ((isinstance(res.begin_token.previous, TextToken))
and (res.whitespaces_before_count < 2)):
tt = Utils.asObjectOrNull(res.begin_token.previous, TextToken)
if (tt.term == "АР"):
for ty in ter.typs:
if ("республика" in ty or "республіка" in ty):
res.begin_token = tt
break
return res
def attach_first(self, p : 'InstrumentParticipantReferent', min_char : int, max_char : int) -> 'ReferentToken':
t = None
tt0 = self.begin_token
refs = list()
t = tt0.previous
first_pass3287 = True
while True:
if first_pass3287: first_pass3287 = False
else: t = t.previous
if (not (t is not None and t.begin_char >= min_char)): break
if (t.is_newline_after):
if (t.newlines_after_count > 1):
break
if (isinstance(t.next0_, NumberToken)):
break
tt = ParticipantToken.__try_attach_contract_ground(t, p, False)
if (tt is not None):
continue
r = t.get_referent()
if (((((isinstance(r, OrganizationReferent)) or (isinstance(r, PhoneReferent)) or (isinstance(r, PersonReferent))) or (isinstance(r, PersonPropertyReferent)) or (isinstance(r, AddressReferent))) or (isinstance(r, UriReferent)) or (isinstance(r, PersonIdentityReferent))) or (isinstance(r, BankDataReferent))):
if (not r in refs):
refs.insert(0, r)
tt0 = t
if (len(refs) > 0):
for r in refs:
if (r != refs[0] and (isinstance(refs[0], OrganizationReferent)) and (((isinstance(r, PersonReferent)) or (isinstance(r, PersonPropertyReferent))))):
p.add_slot(InstrumentParticipantReferent.ATTR_DELEGATE, r, False, 0)
else:
p.add_slot(InstrumentParticipantReferent.ATTR_REF, r, False, 0)
rt = ReferentToken(p, tt0, self.end_token)
t = self.end_token.next0_
if (BracketHelper.is_bracket(t, False)):
t = t.next0_
if (t is not None and t.is_char(',')):
t = t.next0_
first_pass3288 = True
while True:
if first_pass3288: first_pass3288 = False
else: t = t.next0_
if (not (t is not None and ((max_char == 0 or t.begin_char <= max_char)))): break
if (t.is_value("СТОРОНА", None)):
break
r = t.get_referent()
if (((((isinstance(r, OrganizationReferent)) or (isinstance(r, PhoneReferent)) or (isinstance(r, PersonReferent))) or (isinstance(r, PersonPropertyReferent)) or (isinstance(r, AddressReferent))) or (isinstance(r, UriReferent)) or (isinstance(r, PersonIdentityReferent))) or (isinstance(r, BankDataReferent))):
if ((((isinstance(r, PersonPropertyReferent)) and t.next0_ is not None and t.next0_.is_comma) and (isinstance(t.next0_.next0_, ReferentToken)) and (isinstance(t.next0_.next0_.get_referent(), PersonReferent))) and not t.next0_.is_newline_after):
pe = Utils.asObjectOrNull(t.next0_.next0_.get_referent(), PersonReferent)
pe.add_slot(PersonReferent.ATTR_ATTR, r, False, 0)
r = (pe)
t = t.next0_.next0_
is_delegate = False
if (t.previous.is_value("ЛИЦО", None) or t.previous.is_value("ИМЯ", None)):
is_delegate = True
if (t.previous.is_value("КОТОРЫЙ", None) and t.previous.previous is not None and ((t.previous.previous.is_value("ИМЯ", None) or t.previous.previous.is_value("ЛИЦО", None)))):
is_delegate = True
p.add_slot((InstrumentParticipantReferent.ATTR_DELEGATE if (((isinstance(r, PersonReferent)) or (isinstance(r, PersonPropertyReferent)))) and is_delegate else InstrumentParticipantReferent.ATTR_REF), r, False, 0)
rt.end_token = t
continue
tt = ParticipantToken.__try_attach_contract_ground(t, p, False)
if (tt is not None):
rt.end_token = tt
t = rt.end_token
if (rt.begin_char == tt.begin_char):
rt.begin_token = tt
continue
if (t.is_value("В", None) and t.next0_ is not None and t.next0_.is_value("ЛИЦО", None)):
t = t.next0_
continue
if (t.is_value("ОТ", None) and t.next0_ is not None and t.next0_.is_value("ИМЯ", None)):
t = t.next0_
continue
if (t.is_value("ПО", None) and t.next0_ is not None and t.next0_.is_value("ПОРУЧЕНИЕ", None)):
t = t.next0_
continue
if (t.is_newline_before):
break
if (t.get_morph_class_in_dictionary() == MorphClass.VERB):
if ((not t.is_value("УДОСТОВЕРЯТЬ", None) and not t.is_value("ПРОЖИВАТЬ", None) and not t.is_value("ЗАРЕГИСТРИРОВАТЬ", None)) and not t.is_value("ДЕЙСТВОВАТЬ", None)):
break
if (t.is_and and t.previous is not None and t.previous.is_comma):
break
if (t.is_and and t.next0_.get_referent() is not None):
if (isinstance(t.next0_.get_referent(), OrganizationReferent)):
break
pe = Utils.asObjectOrNull(t.next0_.get_referent(), PersonReferent)
if (pe is not None):
has_ip = False
for s in pe.slots:
if (s.type_name == PersonReferent.ATTR_ATTR):
if (str(s.value).startswith("индивидуальный предприниматель")):
has_ip = True
break
if (has_ip):
break
t = rt.begin_token
while t is not None and t.end_char <= rt.end_char:
tt = ParticipantToken.__try_attach_contract_ground(t, p, True)
if (tt is not None):
if (tt.end_char > rt.end_char):
rt.end_token = tt
t = tt
t = t.next0_
return rt
def __try1(li: typing.List['CityItemToken'], oi: 'IntOntologyItem',
ad: 'AnalyzerDataWithOntology') -> 'ReferentToken':
oi.value = (None)
if (li is None or (len(li) < 1)):
return None
elif (li[0].typ != CityItemToken.ItemType.CITY):
if (len(li) != 2 or li[0].typ != CityItemToken.ItemType.PROPERNAME
or li[1].typ != CityItemToken.ItemType.NOUN):
return None
i = 1
oi.value = li[0].onto_item
ok = not li[0].doubtful
if ((ok and li[0].onto_item is not None
and li[0].onto_item.misc_attr is None) and ad is not None):
if (li[0].onto_item.owner != ad.local_ontology
and not li[0].onto_item.owner.is_ext_ontology):
if (li[0].begin_token.previous is not None
and li[0].begin_token.previous.isValue("В", None)):
pass
else:
ok = False
if (len(li) == 1 and li[0].begin_token.morph.class0_.is_adjective):
sits = StreetItemToken.tryParseList(li[0].begin_token, None, 3)
if (sits is not None and len(sits) == 2
and sits[1].typ == StreetItemType.NOUN):
return None
typ = None
alttyp = None
mc = li[0].morph
if (i < len(li)):
if (li[i].typ == CityItemToken.ItemType.NOUN):
at = None
if (not li[i].chars.is_all_lower
and (li[i].whitespaces_after_count < 2)):
sit = StreetItemToken.tryParse(li[i].end_token.next0_,
None, False, None, False)
if (sit is not None and sit.typ == StreetItemType.NOUN):
at = AddressItemToken.tryParse(li[i].begin_token, None,
False, False, None)
if (at is not None):
at2 = AddressItemToken.tryParse(
li[i].end_token.next0_, None, False, False,
None)
if (at2 is not None and at2.typ
== AddressItemToken.ItemType.STREET):
at = (None)
if (at is None):
typ = li[i].value
alttyp = li[i].alt_value
if (li[i].begin_token.isValue("СТ", None)
and li[i].begin_token.chars.is_all_upper):
return None
if ((i + 1) == len(li)):
ok = True
if (not li[i].morph.case_.is_undefined):
mc = li[i].morph
i += 1
elif (ok):
i += 1
else:
tt0 = li[0].begin_token.previous
if ((isinstance(tt0, TextToken))
and (tt0.whitespaces_after_count < 3)):
if (tt0.isValue("МЭР", "МЕР")
or tt0.isValue("ГЛАВА", None)
or tt0.isValue("ГРАДОНАЧАЛЬНИК", None)):
ok = True
i += 1
if (not ok and oi.value is not None
and (len(oi.value.canonic_text) < 4)):
return None
if (not ok and li[0].begin_token.morph.class0_.is_proper_name):
return None
if (not ok):
if (not MiscHelper.isExistsInDictionary(
li[0].begin_token, li[0].end_token, (MorphClass.ADJECTIVE)
| MorphClass.NOUN | MorphClass.PRONOUN)):
ok = (li[0].geo_object_before or li[i - 1].geo_object_after)
if (ok and li[0].begin_token == li[0].end_token):
mcc = li[0].begin_token.getMorphClassInDictionary()
if (mcc.is_proper_name or mcc.is_proper_surname):
ok = False
elif (li[0].geo_object_before
and (li[0].whitespaces_after_count < 2)):
ad1 = AddressItemToken.tryParse(
li[0].begin_token, None, False, False, None)
if (ad1 is not None and ad1.typ
== AddressItemToken.ItemType.STREET):
ad2 = AddressItemToken.tryParse(
li[0].end_token.next0_, None, False, False,
None)
if (ad2 is None or ad2.typ !=
AddressItemToken.ItemType.STREET):
ok = False
elif (AddressItemToken.tryAttachOrg(li[0].begin_token)
is not None):
ok = False
if (ok):
if (li[0].kit.processReferent("PERSON", li[0].begin_token)
is not None):
ok = False
if (not ok):
ok = CityAttachHelper.checkYearAfter(li[0].end_token.next0_)
if (not ok and ((not li[0].begin_token.morph.class0_.is_adjective
or li[0].begin_token != li[0].end_token))):
ok = CityAttachHelper.checkCityAfter(li[0].end_token.next0_)
if (not ok):
return None
if (i < len(li)):
del li[i:i + len(li) - i]
rt = None
if (oi.value is None):
if (li[0].value is not None and li[0].higher_geo is not None):
cap = GeoReferent()
cap._addName(li[0].value)
cap._addTypCity(li[0].kit.base_language)
cap.higher = li[0].higher_geo
if (typ is not None):
cap._addTyp(typ)
if (alttyp is not None):
cap._addTyp(alttyp)
rt = ReferentToken(cap, li[0].begin_token, li[0].end_token)
else:
if (li[0].value is None):
return None
if (typ is None):
if ((len(li) == 1
and li[0].begin_token.previous is not None
and li[0].begin_token.previous.is_hiphen) and
(isinstance(li[0].begin_token.previous.previous,
ReferentToken)) and
(isinstance(
li[0].begin_token.previous.previous.getReferent(),
GeoReferent))):
pass
else:
return None
else:
if (not LanguageHelper.endsWithEx(typ, "ПУНКТ",
"ПОСЕЛЕНИЕ", "ПОСЕЛЕННЯ",
"ПОСЕЛОК")):
if (not LanguageHelper.endsWith(typ, "CITY")):
if (typ == "СТАНЦИЯ" and
((MiscLocationHelper.checkGeoObjectBefore(
li[0].begin_token)))):
pass
elif (len(li) > 1
and li[1].typ == CityItemToken.ItemType.NOUN
and li[0].typ
== CityItemToken.ItemType.CITY):
pass
else:
return None
if (li[0].begin_token.morph.class0_.is_adjective):
li[0].value = ProperNameHelper.getNameEx(
li[0].begin_token, li[0].end_token,
MorphClass.ADJECTIVE, li[1].morph.case_,
li[1].morph.gender, False, False)
elif (isinstance(oi.value.referent, GeoReferent)):
rt = ReferentToken._new719(
Utils.asObjectOrNull(oi.value.referent, GeoReferent),
li[0].begin_token, li[len(li) - 1].end_token, mc)
elif (typ is None):
typ = oi.value.typ
if (rt is None):
city = GeoReferent()
city._addName(
(li[0].value if oi.value is None else oi.value.canonic_text))
if (typ is not None):
city._addTyp(typ)
else:
city._addTypCity(li[0].kit.base_language)
if (alttyp is not None):
city._addTyp(alttyp)
rt = ReferentToken._new719(city, li[0].begin_token,
li[len(li) - 1].end_token, mc)
if ((isinstance(rt.referent, GeoReferent)) and len(li) == 1
and (rt.referent).is_city):
if (rt.begin_token.previous is not None
and rt.begin_token.previous.isValue("Г", None)):
rt.begin_token = rt.begin_token.previous
elif ((rt.begin_token.previous is not None
and rt.begin_token.previous.isChar('.')
and rt.begin_token.previous.previous is not None)
and rt.begin_token.previous.previous.isValue("Г", None)):
rt.begin_token = rt.begin_token.previous.previous
elif (rt.end_token.next0_ is not None
and (rt.whitespaces_after_count < 2)
and rt.end_token.next0_.isValue("Г", None)):
rt.end_token = rt.end_token.next0_
if (rt.end_token.next0_ is not None
and rt.end_token.next0_.isChar('.')):
rt.end_token = rt.end_token.next0_
return rt