def _addValue(self, begin : 'Token', end : 'Token') -> None:
tmp = io.StringIO()
t = begin
first_pass2889 = True
while True:
if first_pass2889: first_pass2889 = False
else: t = t.next0_
if (not (t is not None and t.previous != end)): break
if (isinstance(t, NumberToken)):
print(t.getSourceText(), end="", file=tmp)
continue
if (isinstance(t, TextToken)):
s = (t).term
if (t.isCharOf("-\\/")):
s = "-"
print(s, end="", file=tmp)
i = 0
while i < tmp.tell():
if (Utils.getCharAtStringIO(tmp, i) == '-' and i > 0 and ((i + 1) < tmp.tell())):
ch0 = Utils.getCharAtStringIO(tmp, i - 1)
ch1 = Utils.getCharAtStringIO(tmp, i + 1)
if (str.isalnum(ch0) and str.isalnum(ch1)):
if (str.isdigit(ch0) and not str.isdigit(ch1)):
Utils.removeStringIO(tmp, i, 1)
elif (not str.isdigit(ch0) and str.isdigit(ch1)):
Utils.removeStringIO(tmp, i, 1)
i += 1
self.addSlot(DenominationReferent.ATTR_VALUE, Utils.toStringStringIO(tmp), False, 0)
self.__m_names = (None)
def correct_word(w: str) -> str:
""" Откорректировать слово (перевод в верхний регистр и замена некоторых букв типа Ё->Е)
Args:
w(str): исходное слово
Returns:
str: откорректированное слово
"""
if (w is None):
return None
w = w.upper()
for ch in w:
if (LanguageHelper.__m_rus0.find(ch) >= 0):
tmp = io.StringIO()
print(w, end="", file=tmp)
i = 0
while i < tmp.tell():
j = LanguageHelper.__m_rus0.find(
Utils.getCharAtStringIO(tmp, i))
if (j >= 0):
Utils.setCharAtStringIO(tmp, i,
LanguageHelper.__m_rus1[j])
i += 1
w = Utils.toStringStringIO(tmp)
break
if (w.find(chr(0x00AD)) >= 0):
w = w.replace(chr(0x00AD), '-')
if (w.startswith("АГЕНС")):
w = ("АГЕНТС" + w[5:])
return w
def attach_url(t0: 'Token') -> 'UriItemToken':
srv = UriItemToken.attach_domain_name(t0, True, False)
if (srv is None):
return None
txt = Utils.newStringIO(srv.value)
t1 = srv.end_token
if (t1.next0_ is not None and t1.next0_.is_char(':')
and (isinstance(t1.next0_.next0_, NumberToken))):
t1 = t1.next0_.next0_
print(":{0}".format(t1.value), end="", file=txt, flush=True)
elif ((srv.value == "vk.com" and t1.next0_ is not None
and t1.next0_.is_hiphen) and t1.next0_.next0_ is not None):
t1 = t1.next0_.next0_
dat = UriItemToken.__attach_uri_content(t1, ".-_+%", False)
if (dat is not None):
t1 = dat.end_token
print("/{0}".format(dat.value), end="", file=txt, flush=True)
t = t1.next0_
while t is not None:
if (t.is_whitespace_before):
break
if (not t.is_char('/')):
break
if (t.is_whitespace_after):
t1 = t
break
dat = UriItemToken.__attach_uri_content(t.next0_, ".-_+%", False)
if (dat is None):
t1 = t
break
t1 = dat.end_token
t = t1
print("/{0}".format(dat.value), end="", file=txt, flush=True)
t = t.next0_
if ((t1.next0_ is not None and t1.next0_.is_char('?')
and not t1.next0_.is_whitespace_after)
and not t1.is_whitespace_after):
dat = UriItemToken.__attach_uri_content(t1.next0_.next0_,
".-_+%=&", False)
if (dat is not None):
t1 = dat.end_token
print("?{0}".format(dat.value), end="", file=txt, flush=True)
if ((t1.next0_ is not None and t1.next0_.is_char('#')
and not t1.next0_.is_whitespace_after)
and not t1.is_whitespace_after):
dat = UriItemToken.__attach_uri_content(t1.next0_.next0_, ".-_+%",
False)
if (dat is not None):
t1 = dat.end_token
print("#{0}".format(dat.value), end="", file=txt, flush=True)
i = 0
i = 0
while i < txt.tell():
if (str.isalpha(Utils.getCharAtStringIO(txt, i))):
break
i += 1
if (i >= txt.tell()):
return None
return UriItemToken._new2706(t0, t1, Utils.toStringStringIO(txt))
def attachisbn(t0: 'Token') -> 'UriItemToken':
txt = io.StringIO()
t1 = t0
digs = 0
t = t0
first_pass3417 = True
while True:
if first_pass3417: first_pass3417 = False
else: t = t.next0_
if (not (t is not None)): break
if (t.is_table_control_char):
break
if (t.is_newline_before and t != t0):
if (t.previous is not None and t.previous.is_hiphen):
pass
else:
break
if (isinstance(t, NumberToken)):
nt = Utils.asObjectOrNull(t, NumberToken)
if (nt.typ != NumberSpellingType.DIGIT
or not nt.morph.class0_.is_undefined):
break
d = nt.get_source_text()
print(d, end="", file=txt)
digs += len(d)
t1 = t
if (digs > 13):
break
continue
tt = Utils.asObjectOrNull(t, TextToken)
if (tt is None):
break
s = tt.term
if (s != "-" and s != "Х" and s != "X"):
break
if (s == "Х"):
s = "X"
print(s, end="", file=txt)
t1 = t
if (s != "-"):
break
i = 0
dig = 0
i = 0
while i < txt.tell():
if (str.isdigit(Utils.getCharAtStringIO(txt, i))):
dig += 1
i += 1
if (dig < 7):
return None
return UriItemToken._new2706(t0, t1, Utils.toStringStringIO(txt))
def attachbbk(t0: 'Token') -> 'UriItemToken':
txt = io.StringIO()
t1 = t0
digs = 0
t = t0
first_pass3418 = True
while True:
if first_pass3418: first_pass3418 = False
else: t = t.next0_
if (not (t is not None)): break
if (t.is_newline_before and t != t0):
break
if (t.is_table_control_char):
break
if (isinstance(t, NumberToken)):
nt = Utils.asObjectOrNull(t, NumberToken)
if (nt.typ != NumberSpellingType.DIGIT
or not nt.morph.class0_.is_undefined):
break
d = nt.get_source_text()
print(d, end="", file=txt)
digs += len(d)
t1 = t
continue
tt = Utils.asObjectOrNull(t, TextToken)
if (tt is None):
break
if (tt.is_char(',')):
break
if (tt.is_char('(')):
if (not (isinstance(tt.next0_, NumberToken))):
break
s = tt.get_source_text()
if (str.isalpha(s[0])):
if (tt.is_whitespace_before):
break
print(s, end="", file=txt)
t1 = t
if ((txt.tell() < 3) or (digs < 2)):
return None
if (Utils.getCharAtStringIO(txt, txt.tell() - 1) == '.'):
Utils.setLengthStringIO(txt, txt.tell() - 1)
t1 = t1.previous
return UriItemToken._new2706(t0, t1, Utils.toStringStringIO(txt))
def to_string(self,
short_variant: bool,
lang: 'MorphLang' = None,
lev: int = 0) -> str:
res = Utils.newStringIO(self.template)
vals = list()
for s in self.slots:
if (s.type_name == MeasureReferent.ATTR_VALUE):
if (isinstance(s.value, str)):
val = Utils.asObjectOrNull(s.value, str)
if (val == "NaN"):
val = "?"
vals.append(val)
elif (isinstance(s.value, Referent)):
vals.append(s.value.to_string(True, lang, 0))
for i in range(res.tell() - 1, -1, -1):
ch = Utils.getCharAtStringIO(res, i)
if (not str.isdigit(ch)):
continue
j = ((ord(ch)) - (ord('1')))
if ((j < 0) or j >= len(vals)):
continue
Utils.removeStringIO(res, i, 1)
Utils.insertStringIO(res, i, vals[j])
print(self.out_units(lang), end="", file=res)
if (not short_variant):
nam = self.get_string_value(MeasureReferent.ATTR_NAME)
if (nam is not None):
print(" - {0}".format(nam), end="", file=res, flush=True)
for s in self.slots:
if (s.type_name == MeasureReferent.ATTR_REF
and (isinstance(s.value, MeasureReferent))):
print(" / {0}".format(s.value.to_string(True, lang, 0)),
end="",
file=res,
flush=True)
ki = self.kind
if (ki != MeasureKind.UNDEFINED):
print(" ({0})".format(Utils.enumToString(ki).upper()),
end="",
file=res,
flush=True)
return Utils.toStringStringIO(res)
def toString(self, short_variant : bool, lang : 'MorphLang'=None, lev : int=0) -> str:
res = Utils.newStringIO(self.template)
vals = list()
for s in self.slots:
if (s.type_name == MeasureReferent.ATTR_VALUE):
if (isinstance(s.value, str)):
vals.append(Utils.asObjectOrNull(s.value, str))
elif (isinstance(s.value, Referent)):
vals.append((s.value).toString(True, lang, 0))
for i in range(res.tell() - 1, -1, -1):
ch = Utils.getCharAtStringIO(res, i)
if (not str.isdigit(ch)):
continue
j = ((ord(ch)) - (ord('1')))
if ((j < 0) or j >= len(vals)):
continue
Utils.removeStringIO(res, i, 1)
Utils.insertStringIO(res, i, vals[j])
uu = self.units
if (len(uu) > 0):
print(uu[0].toString(True, lang, 0), end="", file=res)
i = 1
while i < len(uu):
pow0_ = uu[i].getStringValue(UnitReferent.ATTR_POW)
if (not Utils.isNullOrEmpty(pow0_) and pow0_[0] == '-'):
print("/{0}".format(uu[i].toString(True, lang, 1)), end="", file=res, flush=True)
if (pow0_ != "-1"):
print("<{0}>".format(pow0_[1:]), end="", file=res, flush=True)
else:
print("*{0}".format(uu[i].toString(True, lang, 0)), end="", file=res, flush=True)
i += 1
if (not short_variant):
nam = self.getStringValue(MeasureReferent.ATTR_NAME)
if (nam is not None):
print(" - {0}".format(nam), end="", file=res, flush=True)
for s in self.slots:
if (s.type_name == MeasureReferent.ATTR_REF and (isinstance(s.value, MeasureReferent))):
print(" / {0}".format((s.value).toString(True, lang, 0)), end="", file=res, flush=True)
ki = self.kind
if (ki != MeasureKind.UNDEFINED):
print(" ({0})".format(Utils.enumToString(ki).upper()), end="", file=res, flush=True)
return Utils.toStringStringIO(res)
def correct_word(w: str) -> str:
if (w is None):
return None
res = w.upper()
for ch in res:
if (LanguageHelper.__m_rus0.find(ch) >= 0):
tmp = io.StringIO()
print(res, end="", file=tmp)
i = 0
while i < tmp.tell():
j = LanguageHelper.__m_rus0.find(
Utils.getCharAtStringIO(tmp, i))
if (j >= 0):
Utils.setCharAtStringIO(tmp, i,
LanguageHelper.__m_rus1[j])
i += 1
res = Utils.toStringStringIO(tmp)
break
if (res.find(chr(0x00AD)) >= 0):
res = res.replace(chr(0x00AD), '-')
if (res.startswith("АГЕНС")):
res = ("АГЕНТС" + res[5:])
return res
def attach_domain_name(t0: 'Token', check_: bool,
can_be_whitspaces: bool) -> 'UriItemToken':
txt = io.StringIO()
t1 = t0
ip_count = 0
is_ip = True
t = t0
first_pass3413 = True
while True:
if first_pass3413: first_pass3413 = False
else: t = t.next0_
if (not (t is not None)): break
if (t.is_whitespace_before and t != t0):
ok = False
if (not t.is_newline_before and can_be_whitspaces):
tt1 = t
first_pass3414 = True
while True:
if first_pass3414: first_pass3414 = False
else: tt1 = tt1.next0_
if (not (tt1 is not None)): break
if (tt1.is_char('.') or tt1.is_hiphen):
continue
if (tt1.is_whitespace_before):
if (tt1.is_newline_before):
break
if (tt1.previous is not None
and ((tt1.previous.is_char('.')
or tt1.previous.is_hiphen))):
pass
else:
break
if (not (isinstance(tt1, TextToken))):
break
if (UriItemToken.__m_std_groups.try_parse(
tt1, TerminParseAttr.NO) is not None):
ok = True
break
if (not tt1.chars.is_latin_letter):
break
if (not ok):
break
if (isinstance(t, NumberToken)):
nt = Utils.asObjectOrNull(t, NumberToken)
if (nt.int_value is None):
break
print(nt.get_source_text(), end="", file=txt)
t1 = t
if (nt.typ == NumberSpellingType.DIGIT and nt.int_value >= 0
and (nt.int_value < 256)):
ip_count += 1
else:
is_ip = False
continue
tt = Utils.asObjectOrNull(t, TextToken)
if (tt is None):
break
src = tt.term
ch = src[0]
if (not str.isalpha(ch)):
if (".-_".find(ch) < 0):
break
if (ch != '.'):
is_ip = False
if (ch == '-'):
if (Utils.compareStrings(Utils.toStringStringIO(txt),
"vk.com", True) == 0):
return UriItemToken._new2706(
t0, t1,
Utils.toStringStringIO(txt).lower())
else:
is_ip = False
print(src.lower(), end="", file=txt)
t1 = t
if (txt.tell() == 0):
return None
if (ip_count != 4):
is_ip = False
i = 0
points = 0
i = 0
while i < txt.tell():
if (Utils.getCharAtStringIO(txt, i) == '.'):
if (i == 0):
return None
if (i >= (txt.tell() - 1)):
Utils.setLengthStringIO(txt, txt.tell() - 1)
t1 = t1.previous
break
if (Utils.getCharAtStringIO(txt, i - 1) == '.'
or Utils.getCharAtStringIO(txt, i + 1) == '.'):
return None
points += 1
i += 1
if (points == 0):
return None
uri_ = Utils.toStringStringIO(txt)
if (check_):
ok = is_ip
if (not is_ip):
if (Utils.toStringStringIO(txt) == "localhost"):
ok = True
if (not ok and t1.previous is not None
and t1.previous.is_char('.')):
if (UriItemToken.__m_std_groups.try_parse(
t1, TerminParseAttr.NO) is not None):
ok = True
if (not ok):
return None
return UriItemToken._new2706(t0, t1,
Utils.toStringStringIO(txt).lower())
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 get_variants(rus_or_lat: str) -> typing.List[str]:
res = list()
if (Utils.isNullOrEmpty(rus_or_lat)):
return res
rus_or_lat = rus_or_lat.upper()
is_rus = LanguageHelper.is_cyrillic_char(rus_or_lat[0])
stack = list()
i = 0
i = 0
while i < len(rus_or_lat):
li = list()
maxlen = 0
for a in RusLatAccord.__get_accords():
pref = None
if (is_rus and len(a.rus) > 0):
pref = a.rus
elif (not is_rus and len(a.lat) > 0):
pref = a.lat
else:
continue
if (len(pref) < maxlen):
continue
if (not RusLatAccord.__is_pref(rus_or_lat, i, pref)):
continue
if (a.on_tail):
if ((len(pref) + i) < len(rus_or_lat)):
continue
if (len(pref) > maxlen):
maxlen = len(pref)
li.clear()
li.append(a)
if (len(li) == 0 or maxlen == 0):
return res
stack.append(li)
i += (maxlen - 1)
i += 1
if (len(stack) == 0):
return res
ind = list()
i = 0
while i < len(stack):
ind.append(0)
i += 1
tmp = io.StringIO()
while True:
Utils.setLengthStringIO(tmp, 0)
i = 0
while i < len(ind):
a = stack[i][ind[i]]
print((a.lat if is_rus else a.rus), end="", file=tmp)
i += 1
ok = True
if (not is_rus):
i = 0
while i < tmp.tell():
if (Utils.getCharAtStringIO(tmp, i) == 'Й'):
if (i == 0):
ok = False
break
if (not LanguageHelper.is_cyrillic_vowel(
Utils.getCharAtStringIO(tmp, i - 1))):
ok = False
break
i += 1
if (ok):
res.append(Utils.toStringStringIO(tmp))
for i in range(len(ind) - 1, -1, -1):
ind[i] += 1
if (ind[i] < len(stack[i])):
break
else:
ind[i] = 0
else:
i = -1
if (i < 0):
break
return res
def transliteral_correction(value: str,
prev_value: str,
always: bool = False) -> str:
""" Транслитеральная корректировка
Args:
value(str):
prev_value(str):
always(bool):
"""
pure_cyr = 0
pure_lat = 0
ques_cyr = 0
ques_lat = 0
udar_cyr = 0
y = False
udaren = False
i = 0
first_pass2897 = True
while True:
if first_pass2897: first_pass2897 = False
else: i += 1
if (not (i < len(value))): break
ch = value[i]
ui = UnicodeInfo.ALL_CHARS[ord(ch)]
if (not ui.is_letter):
if (ui.is_udaren):
udaren = True
continue
if (ui.is_apos and len(value) > 2):
return LanguageHelper.transliteral_correction(
value.replace("{0}".format(ch), ""), prev_value, False)
return value
if (ui.is_cyrillic):
if (LanguageHelper._m_cyr_chars.find(ch) >= 0):
ques_cyr += 1
else:
pure_cyr += 1
elif (ui.is_latin):
if (LanguageHelper._m_lat_chars.find(ch) >= 0):
ques_lat += 1
else:
pure_lat += 1
elif (LanguageHelper.__m_udar_chars.find(ch) >= 0):
udar_cyr += 1
else:
return value
if (ch == 'Ь' and ((i + 1) < len(value)) and value[i + 1] == 'I'):
y = True
to_rus = False
to_lat = False
if (pure_lat > 0 and pure_cyr > 0):
return value
if (((pure_lat > 0 or always)) and ques_cyr > 0):
to_lat = True
elif (((pure_cyr > 0 or always)) and ques_lat > 0):
to_rus = True
elif (pure_cyr == 0 and pure_lat == 0):
if (ques_cyr > 0 and ques_lat > 0):
if (not Utils.isNullOrEmpty(prev_value)):
if (LanguageHelper.is_cyrillic_char(prev_value[0])):
to_rus = True
elif (LanguageHelper.is_latin_char(prev_value[0])):
to_lat = True
if (not to_lat and not to_rus):
if (ques_cyr > ques_lat):
to_rus = True
elif (ques_cyr < ques_lat):
to_lat = True
if (not to_rus and not to_lat):
if (not y and not udaren and udar_cyr == 0):
return value
tmp = Utils.newStringIO(value)
i = 0
first_pass2898 = True
while True:
if first_pass2898: first_pass2898 = False
else: i += 1
if (not (i < tmp.tell())): break
if (Utils.getCharAtStringIO(tmp, i) == 'Ь'
and ((i + 1) < tmp.tell())
and Utils.getCharAtStringIO(tmp, i + 1) == 'I'):
Utils.setCharAtStringIO(tmp, i, 'Ы')
Utils.removeStringIO(tmp, i + 1, 1)
continue
cod = ord(Utils.getCharAtStringIO(tmp, i))
if (cod >= 0x300 and (cod < 0x370)):
Utils.removeStringIO(tmp, i, 1)
continue
if (to_rus):
ii = LanguageHelper._m_lat_chars.find(
Utils.getCharAtStringIO(tmp, i))
if (ii >= 0):
Utils.setCharAtStringIO(tmp, i,
LanguageHelper._m_cyr_chars[ii])
else:
ii = LanguageHelper.__m_udar_chars.find(
Utils.getCharAtStringIO(tmp, i))
if (((ii)) >= 0):
Utils.setCharAtStringIO(
tmp, i, LanguageHelper.__m_udar_cyr_chars[ii])
elif (to_lat):
ii = LanguageHelper._m_cyr_chars.find(
Utils.getCharAtStringIO(tmp, i))
if (ii >= 0):
Utils.setCharAtStringIO(tmp, i,
LanguageHelper._m_lat_chars[ii])
else:
ii = LanguageHelper.__m_udar_chars.find(
Utils.getCharAtStringIO(tmp, i))
if (ii >= 0):
Utils.setCharAtStringIO(
tmp, i, LanguageHelper.__m_udar_cyr_chars[ii])
return Utils.toStringStringIO(tmp)
def getNameEx(begin: 'Token',
end: 'Token',
cla: 'MorphClass',
mc: 'MorphCase',
gender: 'MorphGender' = MorphGender.UNDEFINED,
ignore_brackets_and_hiphens: bool = False,
ignore_geo_referent: bool = False) -> str:
if (end is None or begin is None):
return None
if (begin.end_char > end.begin_char and begin != end):
return None
res = io.StringIO()
prefix = None
t = begin
first_pass2809 = True
while True:
if first_pass2809: first_pass2809 = False
else: t = t.next0_
if (not (t is not None and t.end_char <= end.end_char)): break
if (res.tell() > 1000):
break
if (t.is_table_control_char):
continue
if (ignore_brackets_and_hiphens):
if (BracketHelper.isBracket(t, False)):
if (t == end):
break
if (t.isCharOf("(<[")):
br = BracketHelper.tryParse(t, BracketParseAttr.NO,
100)
if (br is not None and br.end_char <= end.end_char):
tmp = ProperNameHelper.getNameEx(
br.begin_token.next0_, br.end_token.previous,
MorphClass.UNDEFINED, MorphCase.UNDEFINED,
MorphGender.UNDEFINED,
ignore_brackets_and_hiphens, False)
if (tmp is not None):
if ((br.end_char == end.end_char
and br.begin_token.next0_
== br.end_token.previous and
not br.begin_token.next0_.chars.is_letter)
and not ((isinstance(
br.begin_token.next0_,
ReferentToken)))):
pass
else:
print(" {0}{1}{2}".format(
t.getSourceText(), tmp,
br.end_token.getSourceText()),
end="",
file=res,
flush=True)
t = br.end_token
continue
if (t.is_hiphen):
if (t == end):
break
elif (t.is_whitespace_before or t.is_whitespace_after):
continue
tt = Utils.asObjectOrNull(t, TextToken)
if (tt is not None):
if (not ignore_brackets_and_hiphens):
if ((tt.next0_ is not None and tt.next0_.is_hiphen and
(isinstance(tt.next0_.next0_, TextToken)))
and tt != end and tt.next0_ != end):
if (prefix is None):
prefix = tt.term
else:
prefix = "{0}-{1}".format(prefix, tt.term)
t = tt.next0_
if (t == end):
break
else:
continue
s = None
if (cla.value != (0) or not mc.is_undefined
or gender != MorphGender.UNDEFINED):
for wff in tt.morph.items:
wf = Utils.asObjectOrNull(wff, MorphWordForm)
if (wf is None):
continue
if (cla.value != (0)):
if ((((wf.class0_.value) & (cla.value))) == 0):
continue
if (not mc.is_undefined):
if (((wf.case_) & mc).is_undefined):
continue
if (gender != MorphGender.UNDEFINED):
if ((((wf.gender) &
(gender))) == (MorphGender.UNDEFINED)):
continue
if (s is None or wf.normal_case == tt.term):
s = wf.normal_case
if (s is None and gender != MorphGender.UNDEFINED):
for wff in tt.morph.items:
wf = Utils.asObjectOrNull(wff, MorphWordForm)
if (wf is None):
continue
if (cla.value != (0)):
if ((((wf.class0_.value) & (cla.value))) == 0):
continue
if (not mc.is_undefined):
if (((wf.case_) & mc).is_undefined):
continue
if (s is None or wf.normal_case == tt.term):
s = wf.normal_case
if (s is None):
s = tt.term
if (tt.chars.is_last_lower and tt.length_char > 2):
s = tt.getSourceText()
for i in range(len(s) - 1, -1, -1):
if (str.isupper(s[i])):
s = s[0:0 + i + 1]
break
if (prefix is not None):
delim = "-"
if (ignore_brackets_and_hiphens):
delim = " "
s = "{0}{1}{2}".format(prefix, delim, s)
prefix = (None)
if (res.tell() > 0 and len(s) > 0):
if (str.isalnum(s[0])):
ch0 = Utils.getCharAtStringIO(res, res.tell() - 1)
if (ch0 == '-'):
pass
else:
print(' ', end="", file=res)
elif (not ignore_brackets_and_hiphens
and BracketHelper.canBeStartOfSequence(
tt, False, False)):
print(' ', end="", file=res)
print(s, end="", file=res)
elif (isinstance(t, NumberToken)):
if (res.tell() > 0):
if (not t.is_whitespace_before and Utils.getCharAtStringIO(
res,
res.tell() - 1) == '-'):
pass
else:
print(' ', end="", file=res)
nt = Utils.asObjectOrNull(t, NumberToken)
if ((t.morph.class0_.is_adjective
and nt.typ == NumberSpellingType.WORDS
and nt.begin_token == nt.end_token)
and (isinstance(nt.begin_token, TextToken))):
print((nt.begin_token).term, end="", file=res)
else:
print(nt.value, end="", file=res)
elif (isinstance(t, MetaToken)):
if ((ignore_geo_referent and t != begin
and t.getReferent() is not None)
and t.getReferent().type_name == "GEO"):
continue
s = ProperNameHelper.getNameEx(
(t).begin_token, (t).end_token, cla, mc, gender,
ignore_brackets_and_hiphens, ignore_geo_referent)
if (not Utils.isNullOrEmpty(s)):
if (res.tell() > 0):
if (not t.is_whitespace_before
and Utils.getCharAtStringIO(
res,
res.tell() - 1) == '-'):
pass
else:
print(' ', end="", file=res)
print(s, end="", file=res)
if (t == end):
break
if (res.tell() == 0):
return None
return Utils.toStringStringIO(res)
def __doCrLfCorrection(self, txt: str) -> str:
""" Это анализ случаев принудительно отформатированного текста
Args:
txt(str):
"""
cou = 0
total_len = 0
i = 0
first_pass3166 = True
while True:
if first_pass3166: first_pass3166 = False
else: i += 1
if (not (i < len(txt))): break
ch = txt[i]
if ((ord(ch)) != 0xD and (ord(ch)) != 0xA):
continue
len0_ = 0
last_char = ch
j = (i + 1)
while j < len(txt):
ch = txt[j]
if ((ord(ch)) == 0xD or (ord(ch)) == 0xA):
break
elif ((ord(ch)) == 0x9):
len0_ += 5
else:
last_char = ch
len0_ += 1
j += 1
if (j >= len(txt)):
break
if (len0_ < 30):
continue
if (last_char != '.' and last_char != ':' and last_char != ';'):
next_is_dig = False
k = j + 1
while k < len(txt):
if (not Utils.isWhitespace(txt[k])):
if (str.isdigit(txt[k])):
next_is_dig = True
break
k += 1
if (not next_is_dig):
cou += 1
total_len += len0_
i = j
if (cou < 4):
return txt
total_len = math.floor(total_len / cou)
if ((total_len < 50) or total_len > 100):
return txt
tmp = Utils.newStringIO(txt)
i = 0
while i < tmp.tell():
ch = Utils.getCharAtStringIO(tmp, i)
len0_ = 0
last_char = ch
j = (i + 1)
while j < tmp.tell():
ch = Utils.getCharAtStringIO(tmp, j)
if ((ord(ch)) == 0xD or (ord(ch)) == 0xA):
break
elif ((ord(ch)) == 0x9):
len0_ += 5
else:
last_char = ch
len0_ += 1
j += 1
if (j >= tmp.tell()):
break
for jj in range(j - 1, -1, -1):
last_char = Utils.getCharAtStringIO(tmp, jj)
if (not Utils.isWhitespace(last_char)):
break
else:
jj = -1
not_single = False
jj = (j + 1)
if ((jj < tmp.tell())
and (ord(Utils.getCharAtStringIO(tmp, j))) == 0xD
and (ord(Utils.getCharAtStringIO(tmp, jj))) == 0xA):
jj += 1
while jj < tmp.tell():
ch = Utils.getCharAtStringIO(tmp, jj)
if (not Utils.isWhitespace(ch)):
break
if ((ord(ch)) == 0xD or (ord(ch)) == 0xA):
not_single = True
break
jj += 1
if (((not not_single and len0_ >
(total_len - 20) and (len0_ < (total_len + 10)))
and last_char != '.' and last_char != ':')
and last_char != ';'):
Utils.setCharAtStringIO(tmp, j, ' ')
self.crlf_corrected_count += 1
if ((j + 1) < tmp.tell()):
ch = Utils.getCharAtStringIO(tmp, j + 1)
if ((ord(ch)) == 0xA):
Utils.setCharAtStringIO(tmp, j + 1, ' ')
j += 1
i = (j - 1)
i += 1
return Utils.toStringStringIO(tmp)
def __toFullString(self, last_name_first : bool, 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_)
sss = self.getStringValue("NAMETYPE")
if (sss == "china"):
last_name_first = True
n = self.getStringValue(PersonReferent.ATTR_LASTNAME)
if (n is not None):
res = io.StringIO()
if (last_name_first):
print("{0} ".format(n), end="", file=res, flush=True)
s = self.__findForSurname(PersonReferent.ATTR_FIRSTNAME, n, False)
if (s is not None):
print("{0}".format(s), end="", file=res, flush=True)
if (PersonReferent.__isInitial(s)):
print('.', end="", file=res)
else:
print(' ', end="", file=res)
s = self.__findForSurname(PersonReferent.ATTR_MIDDLENAME, n, False)
if (s is not None):
print("{0}".format(s), end="", file=res, flush=True)
if (PersonReferent.__isInitial(s)):
print('.', end="", file=res)
else:
print(' ', end="", file=res)
if (not last_name_first):
print(n, end="", file=res)
elif (Utils.getCharAtStringIO(res, res.tell() - 1) == ' '):
Utils.setLengthStringIO(res, res.tell() - 1)
if (LanguageHelper.isCyrillicChar(n[0])):
nl = None
for sl in self.slots:
if (sl.type_name == PersonReferent.ATTR_LASTNAME):
ss = Utils.asObjectOrNull(sl.value, str)
if (len(ss) > 0 and LanguageHelper.isLatinChar(ss[0])):
nl = ss
break
if (nl is not None):
nal = self.__findForSurname(PersonReferent.ATTR_FIRSTNAME, nl, False)
if (nal is None):
print(" ({0})".format(nl), end="", file=res, flush=True)
elif (PersonReferent.SHOW_LASTNAME_ON_FIRST_POSITION):
print(" ({0} {1})".format(nl, nal), end="", file=res, flush=True)
else:
print(" ({0} {1})".format(nal, nl), end="", file=res, flush=True)
return MiscHelper.convertFirstCharUpperAndOtherLower(Utils.toStringStringIO(res))
else:
n = self.getStringValue(PersonReferent.ATTR_FIRSTNAME)
if ((n) is not None):
s = self.__findForSurname(PersonReferent.ATTR_MIDDLENAME, n, False)
if (s is not None):
n = "{0} {1}".format(n, s)
n = MiscHelper.convertFirstCharUpperAndOtherLower(n)
nik = self.getStringValue(PersonReferent.ATTR_NICKNAME)
tit = self.__findShortestKingTitul(False)
if (tit is not None):
n = "{0} {1}".format(tit, n)
if (nik is not None):
n = "{0} {1}".format(n, nik)
return n
return "?"
def toString(self,
short_variant: bool,
lang: 'MorphLang',
lev: int = 0) -> str:
res = io.StringIO()
ki = self.kind
str0_ = (Utils.asObjectOrNull(
MetaInstrumentBlock.GLOBAL_META.kind_feature.
convertInnerValueToOuterValue(Utils.enumToString(ki), lang), str))
if (str0_ is not None):
print(str0_, end="", file=res)
if (self.kind2 != InstrumentKind.UNDEFINED):
str0_ = (Utils.asObjectOrNull(
MetaInstrumentBlock.GLOBAL_META.kind_feature.
convertInnerValueToOuterValue(
Utils.enumToString(self.kind2), lang), str))
if (str0_ is not None):
print(" ({0})".format(str0_), end="", file=res, flush=True)
if (self.number > 0):
if (ki == InstrumentKind.TABLE):
print(" {0} строк, {1} столбцов".format(
len(self.children), self.number),
end="",
file=res,
flush=True)
else:
print(" №{0}".format(self.number),
end="",
file=res,
flush=True)
if (self.sub_number > 0):
print(".{0}".format(self.sub_number),
end="",
file=res,
flush=True)
if (self.sub_number2 > 0):
print(".{0}".format(self.sub_number2),
end="",
file=res,
flush=True)
if (self.sub_number3 > 0):
print(".{0}".format(self.sub_number3),
end="",
file=res,
flush=True)
if (self.min_number > 0):
for i in range(res.tell() - 1, -1, -1):
if (Utils.getCharAtStringIO(res, i) == ' '
or Utils.getCharAtStringIO(res, i) == '.'):
Utils.insertStringIO(
res, i + 1, "{0}-".format(self.min_number))
break
ignore_ref = False
if (self.is_expired):
print(" (утратить силу)", end="", file=res)
ignore_ref = True
elif (ki != InstrumentKind.EDITIONS and ki != InstrumentKind.APPROVED
and (isinstance(self.ref, DecreeReferent))):
print(" (*)", end="", file=res)
ignore_ref = True
str0_ = self.getStringValue(InstrumentBlockReferent.ATTR_NAME)
if ((str0_) is None):
str0_ = self.getStringValue(InstrumentBlockReferent.ATTR_VALUE)
if (str0_ is not None):
if (len(str0_) > 100):
str0_ = (str0_[0:0 + 100] + "...")
print(" \"{0}\"".format(str0_), end="", file=res, flush=True)
elif (not ignore_ref and (isinstance(self.ref, Referent))
and (lev < 30)):
print(" \"{0}\"".format(
self.ref.toString(short_variant, lang, lev + 1)),
end="",
file=res,
flush=True)
return Utils.toStringStringIO(res).strip()
def _attachNumber(t: 'Token',
ignore_region: bool = False) -> 'TransItemToken':
if (t is None):
return None
t0 = t
t1 = t
if (t.isValue("НА", None)):
npt = NounPhraseHelper.tryParse(t.next0_, NounPhraseParseAttr.NO,
0)
if (npt is not None and npt.noun.isValue("ФОН", None)):
t = npt.end_token.next0_
res = None
first_pass3135 = True
while True:
if first_pass3135: first_pass3135 = False
else: t = t.next0_
if (not (t is not None)): break
if (t.is_newline_before):
break
if (t != t0 and t.whitespaces_before_count > 1):
break
if (t.getReferent() is not None):
break
if (t.is_hiphen):
continue
nt = Utils.asObjectOrNull(t, NumberToken)
if (nt is not None):
if (nt.typ != NumberSpellingType.DIGIT
or nt.morph.class0_.is_adjective):
break
if (res is None):
res = io.StringIO()
elif (str.isdigit(Utils.getCharAtStringIO(res,
res.tell() - 1))):
print(' ', end="", file=res)
print(nt.getSourceText(), end="", file=res)
t1 = t
continue
tt = Utils.asObjectOrNull(t, TextToken)
if (tt is None):
break
if (not tt.chars.is_letter):
break
if (not tt.chars.is_all_upper and tt.is_whitespace_before):
break
if (tt.length_char > 3):
break
if (res is None):
res = io.StringIO()
print(tt.term, end="", file=res)
t1 = t
if (res is None or (res.tell() < 5)):
return None
re = TransItemToken._new2526(t0, t1, TransItemToken.Typs.NUMBER,
Utils.toStringStringIO(res))
if (not ignore_region):
k = 0
i = res.tell() - 1
while i > 4:
if (not str.isdigit(Utils.getCharAtStringIO(res, i))):
if (Utils.getCharAtStringIO(res, i) == ' '
and ((k == 2 or k == 3))):
re.alt_value = re.value[i + 1:]
re.value = re.value[0:0 + i]
break
i -= 1
k += 1
re.value = re.value.replace(" ", "")
if (ignore_region):
re.alt_value = MiscHelper.createCyrLatAlternative(re.value)
return re
def toString(self,
short_variant: bool,
lang: 'MorphLang' = None,
lev: int = 0) -> str:
res = io.StringIO()
str0_ = self.getStringValue(AddressReferent.ATTR_DETAIL)
if (str0_ is not None):
str0_ = (Utils.asObjectOrNull(
MetaAddress._global_meta.detail_feature.
convertInnerValueToOuterValue(str0_, lang), str))
if (str0_ is not None):
print("[{0}".format(str0_.lower()), end="", file=res, flush=True)
str0_ = self.getStringValue(AddressReferent.ATTR_DETAILPARAM)
if ((str0_) is not None):
print(", {0}".format(str0_), end="", file=res, flush=True)
print(']', end="", file=res)
strs = self.streets
if (len(strs) == 0):
if (self.metro is not None):
if (res.tell() > 0):
print(' ', end="", file=res)
print(Utils.ifNotNull(self.metro, ""), end="", file=res)
else:
if (res.tell() > 0):
print(' ', end="", file=res)
i = 0
while i < len(strs):
if (i > 0):
print(", ", end="", file=res)
print(strs[i].toString(True, lang, 0), end="", file=res)
i += 1
if (self.kilometer is not None):
print(" {0}км.".format(self.kilometer),
end="",
file=res,
flush=True)
if (self.house is not None):
ty = self.house_type
if (ty == AddressHouseType.ESTATE):
print(" влад.", end="", file=res)
elif (ty == AddressHouseType.HOUSEESTATE):
print(" домовл.", end="", file=res)
else:
print(" д.", end="", file=res)
print(("Б/Н" if self.house == "0" else self.house),
end="",
file=res)
if (self.corpus is not None):
print(" корп.{0}".format(
("Б/Н" if self.corpus == "0" else self.corpus)),
end="",
file=res,
flush=True)
if (self.building is not None):
ty = self.building_type
if (ty == AddressBuildingType.CONSTRUCTION):
print(" сооруж.", end="", file=res)
elif (ty == AddressBuildingType.LITER):
print(" лит.", end="", file=res)
else:
print(" стр.", end="", file=res)
print(("Б/Н" if self.building == "0" else self.building),
end="",
file=res)
if (self.potch is not None):
print(" под.{0}".format(self.potch), end="", file=res, flush=True)
if (self.floor0_ is not None):
print(" эт.{0}".format(self.floor0_), end="", file=res, flush=True)
if (self.flat is not None):
print(" кв.{0}".format(self.flat), end="", file=res, flush=True)
if (self.corpus_or_flat is not None):
print(" корп.(кв.?){0}".format(self.corpus_or_flat),
end="",
file=res,
flush=True)
if (self.office is not None):
print(" оф.{0}".format(self.office), end="", file=res, flush=True)
if (self.block is not None):
print(" блок {0}".format(self.block), end="", file=res, flush=True)
if (self.plot is not None):
print(" уч.{0}".format(self.plot), end="", file=res, flush=True)
if (self.box is not None):
print(" бокс {0}".format(self.box), end="", file=res, flush=True)
if (self.post_office_box is not None):
print(" а\\я{0}".format(self.post_office_box),
end="",
file=res,
flush=True)
if (self.csp is not None):
print(" ГСП-{0}".format(self.csp), end="", file=res, flush=True)
kladr = self.getSlotValue(AddressReferent.ATTR_FIAS)
if (isinstance(kladr, Referent)):
print(" (ФИАС: {0}".format(
Utils.ifNotNull((kladr).getStringValue("GUID"), "?")),
end="",
file=res,
flush=True)
for s in self.slots:
if (s.type_name == AddressReferent.ATTR_FIAS
and (isinstance(s.value, Referent))
and s.value != kladr):
print(", {0}".format(
Utils.ifNotNull((s.value).getStringValue("GUID"),
"?")),
end="",
file=res,
flush=True)
print(')', end="", file=res)
bti = self.getStringValue(AddressReferent.ATTR_BTI)
if (bti is not None):
print(" (БТИ {0})".format(bti), end="", file=res, flush=True)
for g in self.geos:
if (res.tell() > 0
and Utils.getCharAtStringIO(res,
res.tell() - 1) == ' '):
Utils.setLengthStringIO(res, res.tell() - 1)
if (res.tell() > 0
and Utils.getCharAtStringIO(res,
res.tell() - 1) == ']'):
pass
elif (res.tell() > 0):
print(';', end="", file=res)
print(" {0}".format(g.toString(True, lang, lev + 1)),
end="",
file=res,
flush=True)
if (self.zip0_ is not None):
print("; {0}".format(self.zip0_), end="", file=res, flush=True)
return Utils.toStringStringIO(res).strip()
def _to_string(self, short_variant: bool, lang: 'MorphLang', lev: int,
from_range: int) -> str:
from pullenti.ner.date.internal.DateRelHelper import DateRelHelper
res = io.StringIO()
p = self.pointer
if (lang is None):
lang = MorphLang.RU
if (self.is_relative):
if (self.pointer == DatePointerType.TODAY):
print("сейчас".format(), end="", file=res, flush=True)
if (not short_variant):
DateRelHelper.append_to_string(self, res)
return Utils.toStringStringIO(res)
word = None
val = 0
back = False
is_local_rel = self.get_string_value(
DateReferent.ATTR_ISRELATIVE) == "true"
for s in self.slots:
if (s.type_name == DateReferent.ATTR_CENTURY):
word = "век"
wrapval784 = RefOutArgWrapper(0)
Utils.tryParseInt(Utils.asObjectOrNull(s.value, str),
wrapval784)
val = wrapval784.value
elif (s.type_name == DateReferent.ATTR_YEAR):
word = "год"
wrapval785 = RefOutArgWrapper(0)
Utils.tryParseInt(Utils.asObjectOrNull(s.value, str),
wrapval785)
val = wrapval785.value
elif (s.type_name == DateReferent.ATTR_MONTH):
word = "месяц"
wrapval786 = RefOutArgWrapper(0)
Utils.tryParseInt(Utils.asObjectOrNull(s.value, str),
wrapval786)
val = wrapval786.value
if (not is_local_rel and val >= 1 and val <= 12):
print(DateReferent.__m_month0[val - 1],
end="",
file=res)
elif (s.type_name == DateReferent.ATTR_DAY):
word = "день"
wrapval787 = RefOutArgWrapper(0)
Utils.tryParseInt(Utils.asObjectOrNull(s.value, str),
wrapval787)
val = wrapval787.value
if ((not is_local_rel and self.month > 0
and self.month <= 12) and self.higher is not None
and self.higher.get_string_value(
DateReferent.ATTR_ISRELATIVE) != "true"):
print("{0} {1}".format(
val, DateReferent.__m_month[self.month - 1]),
end="",
file=res,
flush=True)
elif (not is_local_rel):
print("{0} число".format(val),
end="",
file=res,
flush=True)
elif (s.type_name == DateReferent.ATTR_QUARTAL):
word = "квартал"
wrapval788 = RefOutArgWrapper(0)
Utils.tryParseInt(Utils.asObjectOrNull(s.value, str),
wrapval788)
val = wrapval788.value
elif (s.type_name == DateReferent.ATTR_WEEK):
word = "неделя"
wrapval789 = RefOutArgWrapper(0)
Utils.tryParseInt(Utils.asObjectOrNull(s.value, str),
wrapval789)
val = wrapval789.value
elif (s.type_name == DateReferent.ATTR_HOUR):
word = "час"
wrapval790 = RefOutArgWrapper(0)
Utils.tryParseInt(Utils.asObjectOrNull(s.value, str),
wrapval790)
val = wrapval790.value
if (not is_local_rel):
print("{0}:{1}".format("{:02d}".format(val),
"{:02d}".format(self.minute)),
end="",
file=res,
flush=True)
elif (s.type_name == DateReferent.ATTR_MINUTE):
word = "минута"
wrapval791 = RefOutArgWrapper(0)
Utils.tryParseInt(Utils.asObjectOrNull(s.value, str),
wrapval791)
val = wrapval791.value
elif (s.type_name == DateReferent.ATTR_DAYOFWEEK):
wrapval792 = RefOutArgWrapper(0)
Utils.tryParseInt(Utils.asObjectOrNull(s.value, str),
wrapval792)
val = wrapval792.value
if (not is_local_rel):
print((DateReferent.__m_week_day_ex[val - 1]
if val >= 1 and val <= 7 else "?"),
end="",
file=res)
else:
if (val < 0):
val = (-val)
back = True
if (val >= 0 and val <= 7):
print("{0} {1}".format(
((("прошлое" if back else "будущее"))
if val == 7 else
((("прошлая" if back else "будущая")) if
(val == 3 or val == 6) else
(("прошлый" if back else "будущий")))),
DateReferent.__m_week_day_ex[val - 1]),
end="",
file=res,
flush=True)
break
if (word is not None and is_local_rel):
if (val == 0):
print("{0} {1}".format(
("текущая" if word == "неделя" or word == "минута" else
"текущий"), word),
end="",
file=res,
flush=True)
elif (val > 0 and not back):
print("{0} {1} вперёд".format(
val,
MiscHelper.get_text_morph_var_by_case_and_number_ex(
word, None, MorphNumber.UNDEFINED, str(val))),
end="",
file=res,
flush=True)
else:
val = (-val)
print("{0} {1} назад".format(
val,
MiscHelper.get_text_morph_var_by_case_and_number_ex(
word, None, MorphNumber.UNDEFINED, str(val))),
end="",
file=res,
flush=True)
elif (not is_local_rel and res.tell() == 0):
print("{0} {1}".format(
val,
MiscHelper.get_text_morph_var_by_case_and_number_ex(
word, None, MorphNumber.UNDEFINED, str(val))),
end="",
file=res,
flush=True)
if (not short_variant):
DateRelHelper.append_to_string(self, res)
if (from_range == 1):
Utils.insertStringIO(
res, 0, "{0} ".format(("з" if lang.is_ua else
("from" if lang.is_en else "с"))))
elif (from_range == 2):
Utils.insertStringIO(res, 0, ("to " if lang.is_en else "по "))
return Utils.toStringStringIO(res)
if (from_range == 1):
print("{0} ".format(("з" if lang.is_ua else
("from" if lang.is_en else "с"))),
end="",
file=res,
flush=True)
elif (from_range == 2):
print(("to " if lang.is_en else "по ").format(),
end="",
file=res,
flush=True)
if (p != DatePointerType.NO):
val = MetaDate.POINTER.convert_inner_value_to_outer_value(
Utils.enumToString(p), lang)
if (from_range == 0 or lang.is_en):
pass
elif (from_range == 1):
if (p == DatePointerType.BEGIN):
val = ("початку" if lang.is_ua else "начала")
elif (p == DatePointerType.CENTER):
val = ("середини" if lang.is_ua else "середины")
elif (p == DatePointerType.END):
val = ("кінця" if lang.is_ua else "конца")
elif (p == DatePointerType.TODAY):
val = ("цього часу"
if lang.is_ua else "настоящего времени")
elif (from_range == 2):
if (p == DatePointerType.BEGIN):
val = ("початок" if lang.is_ua else "начало")
elif (p == DatePointerType.CENTER):
val = ("середину" if lang.is_ua else "середину")
elif (p == DatePointerType.END):
val = ("кінець" if lang.is_ua else "конец")
elif (p == DatePointerType.TODAY):
val = ("теперішній час"
if lang.is_ua else "настоящее время")
print("{0} ".format(val), end="", file=res, flush=True)
if (self.day_of_week > 0):
if (lang.is_en):
print("{0}, ".format(
DateReferent.__m_week_day_en[self.day_of_week - 1]),
end="",
file=res,
flush=True)
else:
print("{0}, ".format(
DateReferent.__m_week_day[self.day_of_week - 1]),
end="",
file=res,
flush=True)
y = self.year
m = self.month
d = self.day
cent = self.century
if (y == 0 and cent != 0):
is_bc = cent < 0
if (cent < 0):
cent = (-cent)
print(NumberHelper.get_number_roman(cent), end="", file=res)
if (lang.is_ua):
print(" century", end="", file=res)
elif (m > 0 or p != DatePointerType.NO or from_range == 1):
print((" віка" if lang.is_ua else " века"), end="", file=res)
else:
print((" вік" if lang.is_ua else " век"), end="", file=res)
if (is_bc):
print((" до н.е." if lang.is_ua else " до н.э."),
end="",
file=res)
return Utils.toStringStringIO(res)
if (d > 0):
print(d, end="", file=res)
if (m > 0 and m <= 12):
if (res.tell() > 0
and Utils.getCharAtStringIO(res,
res.tell() - 1) != ' '):
print(' ', end="", file=res)
if (lang.is_ua):
print((DateReferent.__m_monthua[m - 1]
if d > 0 or p != DatePointerType.NO or from_range != 0
else DateReferent.__m_month0ua[m - 1]),
end="",
file=res)
elif (lang.is_en):
print(DateReferent.__m_monthen[m - 1], end="", file=res)
else:
print((DateReferent.__m_month[m - 1]
if d > 0 or p != DatePointerType.NO or from_range != 0
else DateReferent.__m_month0[m - 1]),
end="",
file=res)
if (y != 0):
is_bc = y < 0
if (y < 0):
y = (-y)
if (res.tell() > 0
and Utils.getCharAtStringIO(res,
res.tell() - 1) != ' '):
print(' ', end="", file=res)
if (lang is not None and lang.is_en):
print("{0}".format(y), end="", file=res, flush=True)
elif (short_variant):
print("{0}{1}".format(y, ("р" if lang.is_ua else "г")),
end="",
file=res,
flush=True)
elif (m > 0 or p != DatePointerType.NO or from_range == 1):
print("{0} {1}".format(y, ("року" if lang.is_ua else "года")),
end="",
file=res,
flush=True)
else:
print("{0} {1}".format(y, ("рік" if lang.is_ua else "год")),
end="",
file=res,
flush=True)
if (is_bc):
print((" до н.е." if lang.is_ua else
("BC" if lang.is_en else " до н.э.")),
end="",
file=res)
h = self.hour
mi = self.minute
se = self.second
if (h >= 0 and mi >= 0):
if (res.tell() > 0):
print(' ', end="", file=res)
print("{0}:{1}".format("{:02d}".format(h), "{:02d}".format(mi)),
end="",
file=res,
flush=True)
if (se >= 0):
print(":{0}".format("{:02d}".format(se)),
end="",
file=res,
flush=True)
if (res.tell() == 0):
if (self.quartal != 0):
print("{0}-й квартал".format(self.quartal),
end="",
file=res,
flush=True)
if (res.tell() == 0):
return "?"
while Utils.getCharAtStringIO(
res,
res.tell() - 1) == ' ' or Utils.getCharAtStringIO(
res,
res.tell() - 1) == ',':
Utils.setLengthStringIO(res, res.tell() - 1)
if (not short_variant and self.is_relative):
DateRelHelper.append_to_string(self, res)
return Utils.toStringStringIO(res).strip()
def try_attach(self, t : 'Token', for_ontology : bool=False) -> 'ReferentToken':
if (t is None):
return None
rt0 = self.__try_attach_spec(t)
if (rt0 is not None):
return rt0
if (t.chars.is_all_lower):
if (not t.is_whitespace_after and (isinstance(t.next0_, NumberToken))):
if (t.previous is None or t.is_whitespace_before or t.previous.is_char_of(",:")):
pass
else:
return None
else:
return None
tmp = io.StringIO()
t1 = t
hiph = False
ok = True
nums = 0
chars = 0
w = t1.next0_
first_pass3148 = True
while True:
if first_pass3148: first_pass3148 = False
else: w = w.next0_
if (not (w is not None)): break
if (w.is_whitespace_before and not for_ontology):
break
if (w.is_char_of("/\\_") or w.is_hiphen):
hiph = True
print('-', end="", file=tmp)
continue
hiph = False
nt = Utils.asObjectOrNull(w, NumberToken)
if (nt is not None):
if (nt.typ != NumberSpellingType.DIGIT):
break
t1 = (nt)
print(nt.get_source_text(), end="", file=tmp)
nums += 1
continue
tt = Utils.asObjectOrNull(w, TextToken)
if (tt is None):
break
if (tt.length_char > 3):
ok = False
break
if (not str.isalpha(tt.term[0])):
if (tt.is_char_of(",:") or BracketHelper.can_be_end_of_sequence(tt, False, None, False)):
break
if (not tt.is_char_of("+*&^#@!")):
ok = False
break
chars += 1
t1 = (tt)
print(tt.get_source_text(), end="", file=tmp)
if (not for_ontology):
if ((tmp.tell() < 1) or not ok or hiph):
return None
if (tmp.tell() > 12):
return None
last = Utils.getCharAtStringIO(tmp, tmp.tell() - 1)
if (last == '!'):
return None
if ((nums + chars) == 0):
return None
if (not self.__check_attach(t, t1)):
return None
new_dr = DenominationReferent()
new_dr._add_value(t, t1)
return ReferentToken(new_dr, t, t1)
def __doTransliteralCorrection(txt: io.StringIO, info: io.StringIO) -> int:
""" Произвести транслитеральную коррекцию
Args:
txt(io.StringIO): корректируемый текст
info(io.StringIO): информация о замене (может быть null)
Returns:
int: количество замен
"""
stat = 0
pref_rus_word = False
i = 0
while i < txt.tell():
if (str.isalpha(Utils.getCharAtStringIO(txt, i))):
rus = 0
pure_lat = 0
unknown = 0
j = i
while j < txt.tell():
ch = Utils.getCharAtStringIO(txt, j)
if (not str.isalpha(ch)):
break
code = ord(ch)
if (code >= 0x400 and (code < 0x500)):
rus += 1
elif (SourceOfAnalysis.__m_lat_chars.find(ch) >= 0):
unknown += 1
else:
pure_lat += 1
j += 1
if (((unknown > 0 and rus > 0)) or
((unknown > 0 and pure_lat == 0 and pref_rus_word))):
if (info is not None):
if (info.tell() > 0):
print("\r\n", end="", file=info)
k = i
while k < j:
print(Utils.getCharAtStringIO(txt, k),
end="",
file=info)
k += 1
print(": ", end="", file=info)
k = i
while k < j:
ii = SourceOfAnalysis.__m_lat_chars.find(
Utils.getCharAtStringIO(txt, k))
if (ii >= 0):
if (info is not None):
print("{0}->{1} ".format(
Utils.getCharAtStringIO(txt, k),
SourceOfAnalysis.__m_rus_chars[ii]),
end="",
file=info,
flush=True)
Utils.setCharAtStringIO(
txt, k, SourceOfAnalysis.__m_rus_chars[ii])
k += 1
stat += unknown
pref_rus_word = True
else:
pref_rus_word = rus > 0
i = j
i += 1
return stat
def __attach_uri_content(
t0: 'Token',
chars_: str,
can_be_whitespaces: bool = False) -> 'UriItemToken':
txt = io.StringIO()
t1 = t0
dom = UriItemToken.attach_domain_name(t0, True, can_be_whitespaces)
if (dom is not None):
if (len(dom.value) < 3):
return None
open_char = chr(0)
t = t0
if (dom is not None):
t = dom.end_token.next0_
first_pass3411 = True
while True:
if first_pass3411: first_pass3411 = False
else: t = t.next0_
if (not (t is not None)): break
if (t != t0 and t.is_whitespace_before):
if (t.is_newline_before or not can_be_whitespaces):
break
if (dom is None):
break
if (t.previous.is_hiphen):
pass
elif (t.previous.is_char_of(",;")):
break
elif (t.previous.is_char('.') and t.chars.is_letter
and t.length_char == 2):
pass
else:
ok = False
tt1 = t
if (t.is_char_of("\\/")):
tt1 = t.next0_
tt0 = tt1
first_pass3412 = True
while True:
if first_pass3412: first_pass3412 = False
else: tt1 = tt1.next0_
if (not (tt1 is not None)): break
if (tt1 != tt0 and tt1.is_whitespace_before):
break
if (isinstance(tt1, NumberToken)):
continue
if (not (isinstance(tt1, TextToken))):
break
term1 = tt1.term
if (((term1 == "HTM" or term1 == "HTML" or term1
== "SHTML") or term1 == "ASP" or term1 == "ASPX")
or term1 == "JSP"):
ok = True
break
if (not tt1.chars.is_letter):
if (tt1.is_char_of("\\/")):
ok = True
break
if (not tt1.is_char_of(chars_)):
break
elif (not tt1.chars.is_latin_letter):
break
if (not ok):
break
if (isinstance(t, NumberToken)):
nt = Utils.asObjectOrNull(t, NumberToken)
print(nt.get_source_text(), end="", file=txt)
t1 = t
continue
tt = Utils.asObjectOrNull(t, TextToken)
if (tt is None):
rt = Utils.asObjectOrNull(t, ReferentToken)
if (rt is not None and rt.begin_token.is_value("РФ", None)):
if (txt.tell() > 0 and Utils.getCharAtStringIO(
txt,
txt.tell() - 1) == '.'):
print(rt.begin_token.get_source_text(),
end="",
file=txt)
t1 = t
continue
if (rt is not None and rt.chars.is_latin_letter
and rt.begin_token == rt.end_token):
print(rt.begin_token.get_source_text(), end="", file=txt)
t1 = t
continue
break
src = tt.get_source_text()
ch = src[0]
if (not str.isalpha(ch)):
if (chars_.find(ch) < 0):
break
if (ch == '(' or ch == '['):
open_char = ch
elif (ch == ')'):
if (open_char != '('):
break
open_char = (chr(0))
elif (ch == ']'):
if (open_char != '['):
break
open_char = (chr(0))
print(src, end="", file=txt)
t1 = t
if (txt.tell() == 0):
return dom
i = 0
i = 0
while i < txt.tell():
if (str.isalnum(Utils.getCharAtStringIO(txt, i))):
break
i += 1
if (i >= txt.tell()):
return dom
if (Utils.getCharAtStringIO(txt,
txt.tell() - 1) == '.'
or Utils.getCharAtStringIO(txt,
txt.tell() - 1) == '/'):
Utils.setLengthStringIO(txt, txt.tell() - 1)
t1 = t1.previous
if (dom is not None):
Utils.insertStringIO(txt, 0, dom.value)
tmp = Utils.toStringStringIO(txt)
if (tmp.startswith("\\\\")):
Utils.replaceStringIO(txt, "\\\\", "//")
tmp = Utils.toStringStringIO(txt)
if (tmp.startswith("//")):
tmp = tmp[2:]
if (Utils.compareStrings(tmp, "WWW", True) == 0):
return None
res = UriItemToken._new2706(t0, t1, Utils.toStringStringIO(txt))
return res
def _ToString(self, short_variant : bool, lang : 'MorphLang', lev : int, from_range : int) -> str:
res = io.StringIO()
p = self.pointer
if (lang is None):
lang = MorphLang.RU
if (from_range == 1):
print("{0} ".format(("з" if lang.is_ua else ("from" if lang.is_en else "с"))), end="", file=res, flush=True)
elif (from_range == 2):
print(("to " if lang.is_en else "по ").format(), end="", file=res, flush=True)
if (p != DatePointerType.NO):
val = MetaDate.POINTER.convertInnerValueToOuterValue(Utils.enumToString(p), lang)
if (from_range == 0 or lang.is_en):
pass
elif (from_range == 1):
if (p == DatePointerType.BEGIN):
val = ("початку" if lang.is_ua else "начала")
elif (p == DatePointerType.CENTER):
val = ("середини" if lang.is_ua else "середины")
elif (p == DatePointerType.END):
val = ("кінця" if lang.is_ua else "конца")
elif (p == DatePointerType.TODAY):
val = ("цього часу" if lang.is_ua else "настоящего времени")
elif (from_range == 2):
if (p == DatePointerType.BEGIN):
val = ("початок" if lang.is_ua else "начало")
elif (p == DatePointerType.CENTER):
val = ("середину" if lang.is_ua else "середину")
elif (p == DatePointerType.END):
val = ("кінець" if lang.is_ua else "конец")
elif (p == DatePointerType.TODAY):
val = ("теперішній час" if lang.is_ua else "настоящее время")
print("{0} ".format(val), end="", file=res, flush=True)
if (self.day_of_week > 0):
if (lang.is_en):
print("{0}, ".format(DateReferent.__m_week_day_en[self.day_of_week - 1]), end="", file=res, flush=True)
else:
print("{0}, ".format(DateReferent.__m_week_day[self.day_of_week - 1]), end="", file=res, flush=True)
y = self.year
m = self.month
d = self.day
cent = self.century
if (y == 0 and cent != 0):
is_bc = cent < 0
if (cent < 0):
cent = (- cent)
print(NumberHelper.getNumberRoman(cent), end="", file=res)
if (lang.is_ua):
print(" century", end="", file=res)
elif (m > 0 or p != DatePointerType.NO or from_range == 1):
print((" віка" if lang.is_ua else " века"), end="", file=res)
else:
print((" вік" if lang.is_ua else " век"), end="", file=res)
if (is_bc):
print((" до н.е." if lang.is_ua else " до н.э."), end="", file=res)
return Utils.toStringStringIO(res)
if (d > 0):
print(d, end="", file=res)
if (m > 0 and m <= 12):
if (res.tell() > 0 and Utils.getCharAtStringIO(res, res.tell() - 1) != ' '):
print(' ', end="", file=res)
if (lang.is_ua):
print((DateReferent.__m_monthua[m - 1] if d > 0 or p != DatePointerType.NO or from_range != 0 else DateReferent.__m_month0ua[m - 1]), end="", file=res)
elif (lang.is_en):
print(DateReferent.__m_monthen[m - 1], end="", file=res)
else:
print((DateReferent.__m_month[m - 1] if d > 0 or p != DatePointerType.NO or from_range != 0 else DateReferent.__m_month0[m - 1]), end="", file=res)
if (y != 0):
is_bc = y < 0
if (y < 0):
y = (- y)
if (res.tell() > 0 and Utils.getCharAtStringIO(res, res.tell() - 1) != ' '):
print(' ', end="", file=res)
if (lang is not None and lang.is_en):
print("{0}".format(y), end="", file=res, flush=True)
elif (short_variant):
print("{0}{1}".format(y, ("р" if lang.is_ua else "г")), end="", file=res, flush=True)
elif (m > 0 or p != DatePointerType.NO or from_range == 1):
print("{0} {1}".format(y, ("року" if lang.is_ua else "года")), end="", file=res, flush=True)
else:
print("{0} {1}".format(y, ("рік" if lang.is_ua else "год")), end="", file=res, flush=True)
if (is_bc):
print((" до н.е." if lang.is_ua else ("BC" if lang.is_en else " до н.э.")), end="", file=res)
h = self.hour
mi = self.minute
se = self.second
if (h >= 0 and mi >= 0):
if (res.tell() > 0):
print(' ', end="", file=res)
print("{0}:{1}".format("{:02d}".format(h), "{:02d}".format(mi)), end="", file=res, flush=True)
if (se >= 0):
print(":{0}".format("{:02d}".format(se)), end="", file=res, flush=True)
if (res.tell() == 0):
return "?"
while Utils.getCharAtStringIO(res, res.tell() - 1) == ' ' or Utils.getCharAtStringIO(res, res.tell() - 1) == ',':
Utils.setLengthStringIO(res, res.tell() - 1)
return Utils.toStringStringIO(res).strip()