def parseDateTime(str0_ : str) -> datetime.datetime:
if (Utils.isNullOrEmpty(str0_)):
return None
try:
prts = Utils.splitString(str0_, '.', False)
wrapy804 = RefOutArgWrapper(0)
inoutres805 = Utils.tryParseInt(prts[0], wrapy804)
y = wrapy804.value
if (not inoutres805):
return None
mon = 0
day = 0
if (len(prts) > 1):
wrapmon802 = RefOutArgWrapper(0)
inoutres803 = Utils.tryParseInt(prts[1], wrapmon802)
mon = wrapmon802.value
if (inoutres803):
if (len(prts) > 2):
wrapday801 = RefOutArgWrapper(0)
Utils.tryParseInt(prts[2], wrapday801)
day = wrapday801.value
if (mon <= 0):
mon = 1
if (day <= 0):
day = 1
if (day > Utils.lastDayOfMonth(y, mon)):
day = Utils.lastDayOfMonth(y, mon)
return datetime.datetime(y, mon, day, 0, 0, 0)
except Exception as ex:
pass
return None
def parse_date_time(str0_: str) -> datetime.datetime:
if (Utils.isNullOrEmpty(str0_)):
return None
try:
prts = Utils.splitString(str0_, '.', False)
y = 0
wrapy831 = RefOutArgWrapper(0)
inoutres832 = Utils.tryParseInt(prts[0], wrapy831)
y = wrapy831.value
if (not inoutres832):
return None
mon = 0
day = 0
if (len(prts) > 1):
wrapmon829 = RefOutArgWrapper(0)
inoutres830 = Utils.tryParseInt(prts[1], wrapmon829)
mon = wrapmon829.value
if (inoutres830):
if (len(prts) > 2):
wrapday828 = RefOutArgWrapper(0)
Utils.tryParseInt(prts[2], wrapday828)
day = wrapday828.value
if (mon <= 0):
mon = 1
if (day <= 0):
day = 1
if (day > Utils.lastDayOfMonth(y, mon)):
day = Utils.lastDayOfMonth(y, mon)
return datetime.datetime(y, mon, day, 0, 0, 0)
except Exception as ex:
pass
return None
def create_diap(s1 : str, s2 : str) -> typing.List[str]:
n1 = 0
n2 = 0
i = 0
pref = None
if (s2.startswith(s1)):
i = len(s1)
if (((i + 1) < len(s2)) and s2[i] == '.' and str.isdigit(s2[i + 1])):
wrapn21563 = RefOutArgWrapper(0)
inoutres1564 = Utils.tryParseInt(s2[i + 1:], wrapn21563)
n2 = wrapn21563.value
if (inoutres1564):
res0 = list()
res0.append(s1)
i = 1
while i <= n2:
res0.append("{0}.{1}".format(s1, i))
i += 1
return res0
i = s1.rfind('.')
if (((i)) > 0):
pref = s1[0:0+i + 1]
wrapn11567 = RefOutArgWrapper(0)
inoutres1568 = Utils.tryParseInt(s1[i + 1:], wrapn11567)
n1 = wrapn11567.value
if (not inoutres1568):
return None
if (not s2.startswith(pref)):
return None
wrapn21565 = RefOutArgWrapper(0)
inoutres1566 = Utils.tryParseInt(s2[i + 1:], wrapn21565)
n2 = wrapn21565.value
if (not inoutres1566):
return None
else:
wrapn11571 = RefOutArgWrapper(0)
inoutres1572 = Utils.tryParseInt(s1, wrapn11571)
n1 = wrapn11571.value
if (not inoutres1572):
return None
wrapn21569 = RefOutArgWrapper(0)
inoutres1570 = Utils.tryParseInt(s2, wrapn21569)
n2 = wrapn21569.value
if (not inoutres1570):
return None
if (n2 <= n1):
return None
res = list()
i = n1
while i <= n2:
if (pref is None):
res.append(str(i))
else:
res.append(pref + ((str(i))))
i += 1
return res
def correct_app_list(lines : typing.List['InstrToken1']) -> None:
i = 0
while i < (len(lines) - 1):
if ((lines[i].typ == InstrToken1.Types.LINE and len(lines[i].numbers) == 0 and lines[i].begin_token.is_value("ПРИЛОЖЕНИЯ", "ДОДАТОК")) and len(lines[i + 1].numbers) > 0 and lines[i].end_token.is_char(':')):
num = 1
i += 1
first_pass3278 = True
while True:
if first_pass3278: first_pass3278 = False
else: i += 1
if (not (i < len(lines))): break
if (len(lines[i].numbers) == 0):
if (((i + 1) < len(lines)) and len(lines[i + 1].numbers) == 1 and lines[i + 1].numbers[0] == str(num)):
lines[i - 1].end_token = lines[i].end_token
del lines[i]
i -= 1
continue
break
else:
nn = 0
wrapnn1553 = RefOutArgWrapper(0)
inoutres1554 = Utils.tryParseInt(lines[i].numbers[0], wrapnn1553)
nn = wrapnn1553.value
if (inoutres1554):
num = (nn + 1)
lines[i].num_typ = NumberTypes.UNDEFINED
lines[i].numbers.clear()
i += 1
def year(self) -> int:
wrapyear395 = RefOutArgWrapper(0)
inoutres396 = Utils.tryParseInt(
Utils.ifNotNull(self.getStringValue(BookLinkReferent.ATTR_YEAR),
""), wrapyear395)
year_ = wrapyear395.value
if (inoutres396):
return year_
else:
return 0
def coef(self) -> int:
val = self.getStringValue(SentimentReferent.ATTR_COEF)
if (val is None):
return 0
wrapi2498 = RefOutArgWrapper(0)
inoutres2499 = Utils.tryParseInt(val, wrapi2498)
i = wrapi2498.value
if (not inoutres2499):
return 0
return i
def min_number(self) -> int:
""" Минимальный номер, если задан диапазон """
str0_ = self.getStringValue(InstrumentBlockReferent.ATTR_MINNUMBER)
if (str0_ is None):
return 0
wrapi1486 = RefOutArgWrapper(0)
inoutres1487 = Utils.tryParseInt(str0_, wrapi1486)
i = wrapi1486.value
if (inoutres1487):
return i
return 0
def sub_number2(self) -> int:
""" Дополнительный второй номер (через точку за дополнительным) """
str0_ = self.getStringValue(InstrumentBlockReferent.ATTR_SUB2NUMBER)
if (str0_ is None):
return 0
wrapi1482 = RefOutArgWrapper(0)
inoutres1483 = Utils.tryParseInt(str0_, wrapi1482)
i = wrapi1482.value
if (inoutres1483):
return i
return 0
def sub_number3(self) -> int:
""" Дополнительный третий номер (через точку за вторым дополнительным) """
str0_ = self.getStringValue(InstrumentBlockReferent.ATTR_SUB3NUMBER)
if (str0_ is None):
return 0
wrapi1484 = RefOutArgWrapper(0)
inoutres1485 = Utils.tryParseInt(str0_, wrapi1484)
i = wrapi1484.value
if (inoutres1485):
return i
return 0
def number(self) -> int:
""" Номер (для диапазона - максимальный номер) """
str0_ = self.getStringValue(InstrumentBlockReferent.ATTR_NUMBER)
if (str0_ is None):
return 0
wrapi1478 = RefOutArgWrapper(0)
inoutres1479 = Utils.tryParseInt(str0_, wrapi1478)
i = wrapi1478.value
if (inoutres1479):
return i
return 0
def alt_rest(self) -> int:
""" Остаток (от 0 до 99) - копеек, центов и т.п. """
val = self.getStringValue(MoneyReferent.ATTR_ALTREST)
if (val is None):
return None
wrapv1633 = RefOutArgWrapper(0)
inoutres1634 = Utils.tryParseInt(val, wrapv1633)
v = wrapv1633.value
if (not inoutres1634):
return None
return v
def checkLinkBefore(t0 : 'Token', num : str) -> bool:
if (num is None or t0 is None):
return False
if (t0.previous is not None and (isinstance(t0.previous.getReferent(), BookLinkRefReferent))):
wrapnn366 = RefOutArgWrapper(0)
inoutres367 = Utils.tryParseInt(Utils.ifNotNull((t0.previous.getReferent()).number, ""), wrapnn366)
nn = wrapnn366.value
if (inoutres367):
if (str((nn + 1)) == num):
return True
return False
def count(self) -> int:
""" Количество """
val = self.getStringValue(FundsReferent.ATTR_COUNT)
if (val is None):
return 0
wrapv450 = RefOutArgWrapper(0)
inoutres451 = Utils.tryParseInt(val, wrapv450)
v = wrapv450.value
if (not inoutres451):
return 0
return v
def rest(self) -> int:
""" Остаток (от 0 до 99) - копеек, центов и т.п. """
val = self.getStringValue(MoneyReferent.ATTR_REST)
if (val is None):
return 0
wrapv1631 = RefOutArgWrapper(0)
inoutres1632 = Utils.tryParseInt(val, wrapv1631)
v = wrapv1631.value
if (not inoutres1632):
return 0
return v
def year(self) -> int:
""" Год """
year_ = 0
wrapyear378 = RefOutArgWrapper(0)
inoutres379 = Utils.tryParseInt(
Utils.ifNotNull(self.get_string_value(BookLinkReferent.ATTR_YEAR),
""), wrapyear378)
year_ = wrapyear378.value
if (inoutres379):
return year_
else:
return 0
def getNumberDiff(r1 : 'Referent', r2 : 'Referent') -> int:
""" Возвращает разницу номеров r2 - r1, иначе null, если номеров нет
Args:
r1(Referent):
r2(Referent):
"""
num1 = r1.getStringValue(BookLinkRefReferent.ATTR_NUMBER)
num2 = r2.getStringValue(BookLinkRefReferent.ATTR_NUMBER)
if (num1 is None or num2 is None):
return None
wrapn1398 = RefOutArgWrapper(0)
inoutres399 = Utils.tryParseInt(num1, wrapn1398)
wrapn2400 = RefOutArgWrapper(0)
inoutres401 = Utils.tryParseInt(num2, wrapn2400)
n1 = wrapn1398.value
n2 = wrapn2400.value
if (not inoutres399 or not inoutres401):
return None
return n2 - n1
def sub_number(self) -> int:
""" Дополнительный номер (через точку за основным) """
str0_ = self.get_string_value(InstrumentBlockReferent.ATTR_SUBNUMBER)
if (str0_ is None):
return 0
i = 0
wrapi1586 = RefOutArgWrapper(0)
inoutres1587 = Utils.tryParseInt(str0_, wrapi1586)
i = wrapi1586.value
if (inoutres1587):
return i
return 0
def rest(self) -> int:
""" Остаток (от 0 до 99) - копеек, центов и т.п. """
val = self.get_string_value(MoneyReferent.ATTR_REST)
if (val is None):
return 0
v = 0
wrapv1754 = RefOutArgWrapper(0)
inoutres1755 = Utils.tryParseInt(val, wrapv1754)
v = wrapv1754.value
if (not inoutres1755):
return 0
return v
def alt_rest(self) -> int:
""" Альтернативный остаток (от 0 до 99) - копеек, центов и т.п. """
val = self.get_string_value(MoneyReferent.ATTR_ALTREST)
if (val is None):
return None
v = 0
wrapv1756 = RefOutArgWrapper(0)
inoutres1757 = Utils.tryParseInt(val, wrapv1756)
v = wrapv1756.value
if (not inoutres1757):
return None
return v
def checkLinkAfter(t1 : 'Token', num : str) -> bool:
if (num is None or t1 is None):
return False
if (t1.is_newline_after):
bbb = BookLinkToken.tryParse(t1.next0_, 0)
if (bbb is not None and bbb.typ == BookLinkTyp.NUMBER):
wrapnn368 = RefOutArgWrapper(0)
inoutres369 = Utils.tryParseInt(Utils.ifNotNull(bbb.value, ""), wrapnn368)
nn = wrapnn368.value
if (inoutres369):
if (str((nn - 1)) == num):
return True
return False
def get_number_diff(r1 : 'Referent', r2 : 'Referent') -> int:
""" Возвращает разницу номеров r2 - r1, иначе null, если номеров нет
Args:
r1(Referent): первая ссылка
r2(Referent): вторая ссылка
"""
num1 = r1.get_string_value(BookLinkRefReferent.ATTR_NUMBER)
num2 = r2.get_string_value(BookLinkRefReferent.ATTR_NUMBER)
if (num1 is None or num2 is None):
return None
n1 = 0
n2 = 0
wrapn1381 = RefOutArgWrapper(0)
inoutres382 = Utils.tryParseInt(num1, wrapn1381)
wrapn2383 = RefOutArgWrapper(0)
inoutres384 = Utils.tryParseInt(num2, wrapn2383)
n1 = wrapn1381.value
n2 = wrapn2383.value
if (not inoutres382 or not inoutres384):
return None
return n2 - n1
def __all_years(self) -> typing.List[int]:
res = list()
for s in self.slots:
if (s.type_name == DecreeReferent.ATTR_DATE):
str0_ = str(s.value)
i = str0_.find('.')
if (i == 4):
str0_ = str0_[0:0 + 4]
wrapi1113 = RefOutArgWrapper(0)
inoutres1114 = Utils.tryParseInt(str0_, wrapi1113)
i = wrapi1113.value
if (inoutres1114):
res.append(i)
return res
def getIntValue(self, attr_name: str, def_value: int) -> int:
""" Получить числовое значение (если их несколько, то вернёт первое)
Args:
attr_name(str):
def_value(int):
"""
str0_ = self.getStringValue(attr_name)
if (Utils.isNullOrEmpty(str0_)):
return def_value
wrapres2686 = RefOutArgWrapper(0)
inoutres2687 = Utils.tryParseInt(str0_, wrapres2686)
res = wrapres2686.value
if (not inoutres2687):
return def_value
return res
def get_int_value(self, attr_name: str, def_value: int) -> int:
""" Получить числовое значение (если их несколько, то вернёт первое)
Args:
attr_name(str): имя атрибута
def_value(int): дефолтовое значение, если не найдено
Returns:
int: число
"""
str0_ = self.get_string_value(attr_name)
if (Utils.isNullOrEmpty(str0_)):
return def_value
res = 0
wrapres2858 = RefOutArgWrapper(0)
inoutres2859 = Utils.tryParseInt(str0_, wrapres2858)
res = wrapres2858.value
if (not inoutres2859):
return def_value
return res
def value(self, value_) -> str:
from pullenti.ner.core.NumberHelper import NumberHelper
self.__m_value = (Utils.ifNotNull(value_, ""))
if (len(self.__m_value) > 2 and self.__m_value.endswith(".0")):
self.__m_value = self.__m_value[0:0 + len(self.__m_value) - 2]
while len(self.__m_value) > 1 and self.__m_value[
0] == '0' and self.__m_value[1] != '.':
self.__m_value = self.__m_value[1:]
wrapn2664 = RefOutArgWrapper(0)
inoutres2665 = Utils.tryParseInt(self.__m_value, wrapn2664)
n = wrapn2664.value
if (inoutres2665):
self.__m_int_val = n
else:
self.__m_int_val = (None)
d = NumberHelper.stringToDouble(self.__m_value)
if (d is None):
self.__m_real_val = math.nan
else:
self.__m_real_val = d
return value_
def _initialize() -> None:
if (NumberExHelper._m_postfixes is not None):
return
NumberExHelper._m_postfixes = TerminCollection()
t = Termin._new481("КВАДРАТНЫЙ МЕТР", MorphLang.RU, True, "кв.м.",
NumberExType.METER2)
t.addAbridge("КВ.МЕТР")
t.addAbridge("КВ.МЕТРА")
t.addAbridge("КВ.М.")
NumberExHelper._m_postfixes.add(t)
t = Termin._new481("КВАДРАТНИЙ МЕТР", MorphLang.UA, True, "КВ.М.",
NumberExType.METER2)
t.addAbridge("КВ.МЕТР")
t.addAbridge("КВ.МЕТРА")
t.addAbridge("КВ.М.")
NumberExHelper._m_postfixes.add(t)
t = Termin._new481("КВАДРАТНЫЙ КИЛОМЕТР", MorphLang.RU, True, "кв.км.",
NumberExType.KILOMETER2)
t.addVariant("КВАДРАТНИЙ КІЛОМЕТР", True)
t.addAbridge("КВ.КМ.")
NumberExHelper._m_postfixes.add(t)
t = Termin._new481("ГЕКТАР", MorphLang.RU, True, "га",
NumberExType.GEKTAR)
t.addAbridge("ГА")
NumberExHelper._m_postfixes.add(t)
t = Termin._new481("АР", MorphLang.RU, True, "ар", NumberExType.AR)
t.addVariant("СОТКА", True)
NumberExHelper._m_postfixes.add(t)
t = Termin._new481("КУБИЧЕСКИЙ МЕТР", MorphLang.RU, True, "куб.м.",
NumberExType.METER3)
t.addVariant("КУБІЧНИЙ МЕТР", True)
t.addAbridge("КУБ.МЕТР")
t.addAbridge("КУБ.М.")
NumberExHelper._m_postfixes.add(t)
t = Termin._new481("МЕТР", MorphLang.RU, True, "м.",
NumberExType.METER)
t.addAbridge("М.")
t.addAbridge("M.")
NumberExHelper._m_postfixes.add(t)
t = Termin._new481("МЕТРОВЫЙ", MorphLang.RU, True, "м.",
NumberExType.METER)
t.addVariant("МЕТРОВИЙ", True)
NumberExHelper._m_postfixes.add(t)
t = Termin._new481("МИЛЛИМЕТР", MorphLang.RU, True, "мм.",
NumberExType.MILLIMETER)
t.addAbridge("ММ")
t.addAbridge("MM")
t.addVariant("МІЛІМЕТР", True)
NumberExHelper._m_postfixes.add(t)
t = Termin._new481("МИЛЛИМЕТРОВЫЙ", MorphLang.RU, True, "мм.",
NumberExType.MILLIMETER)
t.addVariant("МІЛІМЕТРОВИЙ", True)
NumberExHelper._m_postfixes.add(t)
t = Termin._new481("САНТИМЕТР", MorphLang.RU, True, "см.",
NumberExType.SANTIMETER)
t.addAbridge("СМ")
t.addAbridge("CM")
NumberExHelper._m_postfixes.add(t)
t = Termin._new481("САНТИМЕТРОВЫЙ", MorphLang.RU, True, "см.",
NumberExType.SANTIMETER)
t.addVariant("САНТИМЕТРОВИЙ", True)
NumberExHelper._m_postfixes.add(t)
t = Termin._new481("КВАДРАТНЫЙ САНТИМЕТР", MorphLang.RU, True,
"кв.см.", NumberExType.SANTIMETER2)
t.addVariant("КВАДРАТНИЙ САНТИМЕТР", True)
t.addAbridge("КВ.СМ.")
t.addAbridge("СМ.КВ.")
NumberExHelper._m_postfixes.add(t)
t = Termin._new481("КУБИЧЕСКИЙ САНТИМЕТР", MorphLang.RU, True,
"куб.см.", NumberExType.SANTIMETER3)
t.addVariant("КУБІЧНИЙ САНТИМЕТР", True)
t.addAbridge("КУБ.САНТИМЕТР")
t.addAbridge("КУБ.СМ.")
t.addAbridge("СМ.КУБ.")
NumberExHelper._m_postfixes.add(t)
t = Termin._new481("КИЛОМЕТР", MorphLang.RU, True, "км.",
NumberExType.KILOMETER)
t.addAbridge("КМ")
t.addAbridge("KM")
t.addVariant("КІЛОМЕТР", True)
NumberExHelper._m_postfixes.add(t)
t = Termin._new481("КИЛОМЕТРОВЫЙ", MorphLang.RU, True, "км.",
NumberExType.KILOMETER)
t.addVariant("КІЛОМЕТРОВИЙ", True)
NumberExHelper._m_postfixes.add(t)
t = Termin._new481("МИЛЯ", MorphLang.RU, True, "миль",
NumberExType.KILOMETER)
NumberExHelper._m_postfixes.add(t)
t = Termin._new481("ГРАММ", MorphLang.RU, True, "гр.",
NumberExType.GRAMM)
t.addAbridge("ГР")
t.addAbridge("Г")
t.addVariant("ГРАМ", True)
NumberExHelper._m_postfixes.add(t)
t = Termin._new481("ГРАММОВЫЙ", MorphLang.RU, True, "гр.",
NumberExType.GRAMM)
NumberExHelper._m_postfixes.add(t)
t = Termin._new481("КИЛОГРАММ", MorphLang.RU, True, "кг.",
NumberExType.KILOGRAM)
t.addAbridge("КГ")
t.addVariant("КІЛОГРАМ", True)
NumberExHelper._m_postfixes.add(t)
t = Termin._new481("КИЛОГРАММОВЫЙ", MorphLang.RU, True, "кг.",
NumberExType.KILOGRAM)
t.addVariant("КІЛОГРАМОВИЙ", True)
NumberExHelper._m_postfixes.add(t)
t = Termin._new481("МИЛЛИГРАММ", MorphLang.RU, True, "мг.",
NumberExType.MILLIGRAM)
t.addAbridge("МГ")
t.addVariant("МІЛІГРАМ", True)
NumberExHelper._m_postfixes.add(t)
t = Termin._new481("МИЛЛИГРАММОВЫЙ", MorphLang.RU, True, "мг.",
NumberExType.MILLIGRAM)
t.addVariant("МИЛЛИГРАМОВЫЙ", True)
t.addVariant("МІЛІГРАМОВИЙ", True)
NumberExHelper._m_postfixes.add(t)
t = Termin._new481("ТОННА", MorphLang.RU, True, "т.",
NumberExType.TONNA)
t.addAbridge("Т")
t.addAbridge("T")
NumberExHelper._m_postfixes.add(t)
t = Termin._new481("ТОННЫЙ", MorphLang.RU, True, "т.",
NumberExType.TONNA)
t.addVariant("ТОННИЙ", True)
NumberExHelper._m_postfixes.add(t)
t = Termin._new481("ЛИТР", MorphLang.RU, True, "л.", NumberExType.LITR)
t.addAbridge("Л")
t.addVariant("ЛІТР", True)
NumberExHelper._m_postfixes.add(t)
t = Termin._new481("ЛИТРОВЫЙ", MorphLang.RU, True, "л.",
NumberExType.LITR)
t.addVariant("ЛІТРОВИЙ", True)
NumberExHelper._m_postfixes.add(t)
t = Termin._new481("МИЛЛИЛИТР", MorphLang.RU, True, "мл.",
NumberExType.MILLILITR)
t.addAbridge("МЛ")
t.addVariant("МІЛІЛІТР", True)
NumberExHelper._m_postfixes.add(t)
t = Termin._new481("МИЛЛИЛИТРОВЫЙ", MorphLang.RU, True, "мл.",
NumberExType.MILLILITR)
t.addVariant("МІЛІЛІТРОВИЙ", True)
NumberExHelper._m_postfixes.add(t)
t = Termin._new481("ЧАС", MorphLang.RU, True, "ч.", NumberExType.HOUR)
t.addAbridge("Ч.")
t.addVariant("ГОДИНА", True)
NumberExHelper._m_postfixes.add(t)
t = Termin._new481("МИНУТА", MorphLang.RU, True, "мин.",
NumberExType.MINUTE)
t.addAbridge("МИН.")
t.addVariant("ХВИЛИНА", True)
NumberExHelper._m_postfixes.add(t)
t = Termin._new481("СЕКУНДА", MorphLang.RU, True, "сек.",
NumberExType.SECOND)
t.addAbridge("СЕК.")
NumberExHelper._m_postfixes.add(t)
t = Termin._new481("ГОД", MorphLang.RU, True, "г.", NumberExType.YEAR)
t.addAbridge("Г.")
t.addAbridge("ЛЕТ")
t.addVariant("ЛЕТНИЙ", True)
NumberExHelper._m_postfixes.add(t)
t = Termin._new481("МЕСЯЦ", MorphLang.RU, True, "мес.",
NumberExType.MONTH)
t.addAbridge("МЕС.")
t.addVariant("МЕСЯЧНЫЙ", True)
t.addVariant("КАЛЕНДАРНЫЙ МЕСЯЦ", True)
NumberExHelper._m_postfixes.add(t)
t = Termin._new481("ДЕНЬ", MorphLang.RU, True, "дн.", NumberExType.DAY)
t.addAbridge("ДН.")
t.addVariant("ДНЕВНЫЙ", True)
t.addVariant("СУТКИ", True)
t.addVariant("СУТОЧНЫЙ", True)
t.addVariant("КАЛЕНДАРНЫЙ ДЕНЬ", True)
t.addVariant("РАБОЧИЙ ДЕНЬ", True)
NumberExHelper._m_postfixes.add(t)
t = Termin._new481("НЕДЕЛЯ", MorphLang.RU, True, "нед.",
NumberExType.WEEK)
t.addVariant("НЕДЕЛЬНЫЙ", True)
t.addVariant("КАЛЕНДАРНАЯ НЕДЕЛЯ", False)
NumberExHelper._m_postfixes.add(t)
t = Termin._new481("ПРОЦЕНТ", MorphLang.RU, True, "%",
NumberExType.PERCENT)
t.addVariant("%", False)
t.addVariant("ПРОЦ", True)
t.addAbridge("ПРОЦ.")
NumberExHelper._m_postfixes.add(t)
t = Termin._new481("ШТУКА", MorphLang.RU, True, "шт.",
NumberExType.SHUK)
t.addVariant("ШТ", False)
t.addAbridge("ШТ.")
t.addAbridge("ШТ-К")
NumberExHelper._m_postfixes.add(t)
t = Termin._new481("УПАКОВКА", MorphLang.RU, True, "уп.",
NumberExType.UPAK)
t.addVariant("УПАК", True)
t.addVariant("УП", True)
t.addAbridge("УПАК.")
t.addAbridge("УП.")
t.addAbridge("УП-КА")
NumberExHelper._m_postfixes.add(t)
t = Termin._new481("РУЛОН", MorphLang.RU, True, "рулон",
NumberExType.RULON)
t.addVariant("РУЛ", True)
t.addAbridge("РУЛ.")
NumberExHelper._m_postfixes.add(t)
t = Termin._new481("НАБОР", MorphLang.RU, True, "набор",
NumberExType.NABOR)
t.addVariant("НАБ", True)
t.addAbridge("НАБ.")
NumberExHelper._m_postfixes.add(t)
t = Termin._new481("КОМПЛЕКТ", MorphLang.RU, True, "компл.",
NumberExType.KOMPLEKT)
t.addVariant("КОМПЛ", True)
t.addAbridge("КОМПЛ.")
NumberExHelper._m_postfixes.add(t)
t = Termin._new481("ПАРА", MorphLang.RU, True, "пар",
NumberExType.PARA)
NumberExHelper._m_postfixes.add(t)
t = Termin._new481("ФЛАКОН", MorphLang.RU, True, "флак.",
NumberExType.FLAKON)
t.addVariant("ФЛ", True)
t.addAbridge("ФЛ.")
t.addVariant("ФЛАК", True)
t.addAbridge("ФЛАК.")
NumberExHelper._m_postfixes.add(t)
for te in NumberExHelper._m_postfixes.termins:
ty = Utils.valToEnum(te.tag, NumberExType)
if (not ty in NumberExHelper._m_normals_typs):
NumberExHelper._m_normals_typs[ty] = te.canonic_text
NumberExHelper.__m_small_money = TerminCollection()
t = Termin._new141("УСЛОВНАЯ ЕДИНИЦА", "УЕ", NumberExType.MONEY)
t.addAbridge("У.Е.")
t.addAbridge("У.E.")
t.addAbridge("Y.Е.")
t.addAbridge("Y.E.")
NumberExHelper._m_postfixes.add(t)
for k in range(3):
str0_ = EpNerCoreInternalResourceHelper.getString(
("Money.csv" if k == 0 else
("MoneyUA.csv" if k == 1 else "MoneyEN.csv")))
if (str0_ is None):
continue
lang = (MorphLang.RU if k == 0 else
(MorphLang.UA if k == 1 else MorphLang.EN))
if (str0_ is None):
continue
for line0 in Utils.splitString(str0_, '\n', False):
line = line0.strip()
if (Utils.isNullOrEmpty(line)):
continue
parts = Utils.splitString(line.upper(), ';', False)
if (parts is None or len(parts) != 5):
continue
if (Utils.isNullOrEmpty(parts[1])
or Utils.isNullOrEmpty(parts[2])):
continue
t = Termin()
t.initByNormalText(parts[1], lang)
t.canonic_text = parts[2]
t.tag = NumberExType.MONEY
for p in Utils.splitString(parts[0], ',', False):
if (p != parts[1]):
t0 = Termin()
t0.initByNormalText(p, None)
t.addVariantTerm(t0)
if (parts[1] == "РУБЛЬ"):
t.addAbridge("РУБ.")
elif (parts[1] == "ГРИВНЯ"):
t.addAbridge("ГРН.")
elif (parts[1] == "ДОЛЛАР"):
t.addAbridge("ДОЛ.")
t.addAbridge("ДОЛЛ.")
elif (parts[1] == "ДОЛАР"):
t.addAbridge("ДОЛ.")
NumberExHelper._m_postfixes.add(t)
if (Utils.isNullOrEmpty(parts[3])):
continue
num = 0
i = parts[3].find(' ')
if (i < 2):
continue
wrapnum526 = RefOutArgWrapper(0)
inoutres527 = Utils.tryParseInt(parts[3][0:0 + i], wrapnum526)
num = wrapnum526.value
if (not inoutres527):
continue
vv = parts[3][i:].strip()
t = Termin()
t.initByNormalText(parts[4], lang)
t.tag = (num)
if (vv != parts[4]):
t0 = Termin()
t0.initByNormalText(vv, None)
t.addVariantTerm(t0)
if (parts[4] == "КОПЕЙКА" or parts[4] == "КОПІЙКА"):
t.addAbridge("КОП.")
NumberExHelper.__m_small_money.add(t)
def calc_delta(prev : 'InstrToken1', next0_ : 'InstrToken1', can_sub_numbers : bool) -> int:
n1 = prev.last_number
n2 = next0_.last_number
if (next0_.last_min_number > 0):
n2 = next0_.last_min_number
if (len(prev.numbers) == len(next0_.numbers)):
if (prev.typ_container_rank > 0 and prev.typ_container_rank == next0_.typ_container_rank):
pass
elif (prev.num_typ == next0_.num_typ):
pass
else:
return 0
if (len(prev.numbers) > 1):
i = 0
while i < (len(prev.numbers) - 1):
if (prev.numbers[i] != next0_.numbers[i]):
return 0
i += 1
if (n1 >= n2):
return 0
return n2 - n1
if (not can_sub_numbers):
return 0
if ((len(prev.numbers) + 1) == len(next0_.numbers) and len(next0_.numbers) > 0):
if (prev.typ_container_rank > 0 and prev.typ_container_rank == next0_.typ_container_rank):
pass
elif (prev.num_typ == NumberTypes.DIGIT and next0_.num_typ == NumberTypes.TWODIGITS):
pass
elif (prev.num_typ == NumberTypes.TWODIGITS and next0_.num_typ == NumberTypes.THREEDIGITS):
pass
elif (prev.num_typ == NumberTypes.THREEDIGITS and next0_.num_typ == NumberTypes.FOURDIGITS):
pass
elif (prev.num_typ == NumberTypes.LETTER and next0_.num_typ == NumberTypes.TWODIGITS and str.isalpha(next0_.numbers[0][0])):
pass
else:
return 0
i = 0
while i < len(prev.numbers):
if (prev.numbers[i] != next0_.numbers[i]):
return 0
i += 1
return n2
if ((len(prev.numbers) - 1) == len(next0_.numbers) and len(prev.numbers) > 1):
if (prev.typ_container_rank > 0 and prev.typ_container_rank == next0_.typ_container_rank):
pass
elif (prev.num_typ == NumberTypes.TWODIGITS):
if (next0_.num_typ == NumberTypes.DIGIT):
pass
elif (next0_.num_typ == NumberTypes.LETTER and str.isalpha(prev.numbers[0][0])):
pass
elif (prev.num_typ == NumberTypes.THREEDIGITS and next0_.num_typ == NumberTypes.TWODIGITS):
pass
elif (prev.num_typ == NumberTypes.FOURDIGITS and next0_.num_typ == NumberTypes.THREEDIGITS):
pass
else:
return 0
i = 0
while i < (len(prev.numbers) - 2):
if (prev.numbers[i] != next0_.numbers[i]):
return 0
i += 1
wrapn11556 = RefOutArgWrapper(0)
inoutres1557 = Utils.tryParseInt(prev.numbers[len(prev.numbers) - 2], wrapn11556)
n1 = wrapn11556.value
if (not inoutres1557):
if (len(prev.numbers) == 2):
n1 = prev.first_number
else:
return 0
if ((n1 + 1) != n2):
return 0
return n2 - n1
if ((len(prev.numbers) - 2) == len(next0_.numbers) and len(prev.numbers) > 2):
if (prev.typ_container_rank > 0 and prev.typ_container_rank == next0_.typ_container_rank):
pass
elif (prev.num_typ == NumberTypes.THREEDIGITS and next0_.num_typ == NumberTypes.DIGIT):
pass
elif (prev.num_typ == NumberTypes.FOURDIGITS and next0_.num_typ == NumberTypes.TWODIGITS):
pass
else:
return 0
i = 0
while i < (len(prev.numbers) - 3):
if (prev.numbers[i] != next0_.numbers[i]):
return 0
i += 1
wrapn11558 = RefOutArgWrapper(0)
inoutres1559 = Utils.tryParseInt(prev.numbers[len(prev.numbers) - 3], wrapn11558)
n1 = wrapn11558.value
if (not inoutres1559):
return 0
if ((n1 + 1) != n2):
return 0
return n2 - n1
if ((len(prev.numbers) - 3) == len(next0_.numbers) and len(prev.numbers) > 3):
if (prev.typ_container_rank > 0 and prev.typ_container_rank == next0_.typ_container_rank):
pass
elif (prev.num_typ == NumberTypes.FOURDIGITS and next0_.num_typ == NumberTypes.DIGIT):
pass
else:
return 0
i = 0
while i < (len(prev.numbers) - 4):
if (prev.numbers[i] != next0_.numbers[i]):
return 0
i += 1
wrapn11560 = RefOutArgWrapper(0)
inoutres1561 = Utils.tryParseInt(prev.numbers[len(prev.numbers) - 4], wrapn11560)
n1 = wrapn11560.value
if (not inoutres1561):
return 0
if ((n1 + 1) != n2):
return 0
return n2 - n1
return 0
def calcDelta(prev : 'InstrToken1', next0_ : 'InstrToken1', can_sub_numbers : bool) -> int:
""" Разница между двумя номерами
Args:
prev(InstrToken1):
next0_(InstrToken1):
can_sub_numbers(bool): может быть 1. - 1.1 - 2.
Returns:
int: больше 0 - отличаются на это число, 0 не стыкуются
"""
n1 = prev.last_number
n2 = next0_.last_number
if (next0_.last_min_number > 0):
n2 = next0_.last_min_number
if (len(prev.numbers) == len(next0_.numbers)):
if (prev.typ_container_rank > 0 and prev.typ_container_rank == next0_.typ_container_rank):
pass
elif (prev.num_typ == next0_.num_typ):
pass
else:
return 0
if (len(prev.numbers) > 1):
i = 0
while i < (len(prev.numbers) - 1):
if (prev.numbers[i] != next0_.numbers[i]):
return 0
i += 1
if (n1 >= n2):
return 0
return n2 - n1
if (not can_sub_numbers):
return 0
if ((len(prev.numbers) + 1) == len(next0_.numbers) and len(next0_.numbers) > 0):
if (prev.typ_container_rank > 0 and prev.typ_container_rank == next0_.typ_container_rank):
pass
elif (prev.num_typ == NumberTypes.DIGIT and next0_.num_typ == NumberTypes.TWODIGITS):
pass
elif (prev.num_typ == NumberTypes.TWODIGITS and next0_.num_typ == NumberTypes.THREEDIGITS):
pass
elif (prev.num_typ == NumberTypes.THREEDIGITS and next0_.num_typ == NumberTypes.FOURDIGITS):
pass
elif (prev.num_typ == NumberTypes.LETTER and next0_.num_typ == NumberTypes.TWODIGITS and str.isalpha(next0_.numbers[0][0])):
pass
else:
return 0
i = 0
while i < len(prev.numbers):
if (prev.numbers[i] != next0_.numbers[i]):
return 0
i += 1
return n2
if ((len(prev.numbers) - 1) == len(next0_.numbers) and len(prev.numbers) > 1):
if (prev.typ_container_rank > 0 and prev.typ_container_rank == next0_.typ_container_rank):
pass
elif (prev.num_typ == NumberTypes.TWODIGITS):
if (next0_.num_typ == NumberTypes.DIGIT):
pass
elif (next0_.num_typ == NumberTypes.LETTER and str.isalpha(prev.numbers[0][0])):
pass
elif (prev.num_typ == NumberTypes.THREEDIGITS and next0_.num_typ == NumberTypes.TWODIGITS):
pass
elif (prev.num_typ == NumberTypes.FOURDIGITS and next0_.num_typ == NumberTypes.THREEDIGITS):
pass
else:
return 0
i = 0
while i < (len(prev.numbers) - 2):
if (prev.numbers[i] != next0_.numbers[i]):
return 0
i += 1
wrapn11450 = RefOutArgWrapper(0)
inoutres1451 = Utils.tryParseInt(prev.numbers[len(prev.numbers) - 2], wrapn11450)
n1 = wrapn11450.value
if (not inoutres1451):
if (len(prev.numbers) == 2):
n1 = prev.first_number
else:
return 0
if ((n1 + 1) != n2):
return 0
return n2 - n1
if ((len(prev.numbers) - 2) == len(next0_.numbers) and len(prev.numbers) > 2):
if (prev.typ_container_rank > 0 and prev.typ_container_rank == next0_.typ_container_rank):
pass
elif (prev.num_typ == NumberTypes.THREEDIGITS and next0_.num_typ == NumberTypes.DIGIT):
pass
elif (prev.num_typ == NumberTypes.FOURDIGITS and next0_.num_typ == NumberTypes.TWODIGITS):
pass
else:
return 0
i = 0
while i < (len(prev.numbers) - 3):
if (prev.numbers[i] != next0_.numbers[i]):
return 0
i += 1
wrapn11452 = RefOutArgWrapper(0)
inoutres1453 = Utils.tryParseInt(prev.numbers[len(prev.numbers) - 3], wrapn11452)
n1 = wrapn11452.value
if (not inoutres1453):
return 0
if ((n1 + 1) != n2):
return 0
return n2 - n1
if ((len(prev.numbers) - 3) == len(next0_.numbers) and len(prev.numbers) > 3):
if (prev.typ_container_rank > 0 and prev.typ_container_rank == next0_.typ_container_rank):
pass
elif (prev.num_typ == NumberTypes.FOURDIGITS and next0_.num_typ == NumberTypes.DIGIT):
pass
else:
return 0
i = 0
while i < (len(prev.numbers) - 4):
if (prev.numbers[i] != next0_.numbers[i]):
return 0
i += 1
wrapn11454 = RefOutArgWrapper(0)
inoutres1455 = Utils.tryParseInt(prev.numbers[len(prev.numbers) - 4], wrapn11454)
n1 = wrapn11454.value
if (not inoutres1455):
return 0
if ((n1 + 1) != n2):
return 0
return n2 - n1
return 0
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 _process(begin : 'Token', max_char_pos : int, kit : 'AnalysisKit', end_token : 'Token') -> 'TitlePageReferent':
end_token.value = begin
res = TitlePageReferent()
term = None
lines = Line.parse(begin, 30, 1500, max_char_pos)
if (len(lines) < 1):
return None
cou = len(lines)
min_newlines_count = 10
lines_count_stat = dict()
i = 0
while i < len(lines):
if (TitleNameToken.can_be_start_of_text_or_content(lines[i].begin_token, lines[i].end_token)):
cou = i
break
j = lines[i].newlines_before_count
if (i > 0 and j > 0):
if (not j in lines_count_stat):
lines_count_stat[j] = 1
else:
lines_count_stat[j] += 1
i += 1
max0_ = 0
for kp in lines_count_stat.items():
if (kp[1] > max0_):
max0_ = kp[1]
min_newlines_count = kp[0]
end_char = (lines[cou - 1].end_char if cou > 0 else 0)
if (max_char_pos > 0 and end_char > max_char_pos):
end_char = max_char_pos
names = list()
i = 0
while i < cou:
if (i == 6):
pass
j = i
while (j < cou) and (j < (i + 5)):
if (i == 6 and j == 8):
pass
if (j > i):
if (lines[j - 1].is_pure_en and lines[j].is_pure_ru):
break
if (lines[j - 1].is_pure_ru and lines[j].is_pure_en):
break
if (lines[j].newlines_before_count >= (min_newlines_count * 2)):
break
ttt = TitleNameToken.try_parse(lines[i].begin_token, lines[j].end_token, min_newlines_count)
if (ttt is not None):
if (lines[i].is_pure_en):
ttt.morph.language = MorphLang.EN
elif (lines[i].is_pure_ru):
ttt.morph.language = MorphLang.RU
names.append(ttt)
j += 1
i += 1
TitleNameToken.sort(names)
name_rt = None
if (len(names) > 0):
i0 = 0
if (names[i0].morph.language.is_en):
ii = 1
while ii < len(names):
if (names[ii].morph.language.is_ru and names[ii].rank > 0):
i0 = ii
break
ii += 1
term = res._add_name(names[i0].begin_name_token, names[i0].end_name_token)
if (names[i0].type_value is not None):
res._add_type(names[i0].type_value)
if (names[i0].speciality is not None):
res.speciality = names[i0].speciality
rt = ReferentToken(res, names[i0].begin_token, names[i0].end_token)
if (kit is not None):
kit.embed_token(rt)
else:
res.add_occurence(TextAnnotation(rt.begin_token, rt.end_token))
end_token.value = rt.end_token
name_rt = rt
if (begin.begin_char == rt.begin_char):
begin = (rt)
if (term is not None and kit is not None):
t = kit.first_token
first_pass3397 = True
while True:
if first_pass3397: first_pass3397 = False
else: t = t.next0_
if (not (t is not None)): break
tok = term.try_parse(t, TerminParseAttr.NO)
if (tok is None):
continue
t0 = t
t1 = tok.end_token
if (t1.next0_ is not None and t1.next0_.is_char('.')):
t1 = t1.next0_
if (BracketHelper.can_be_start_of_sequence(t0.previous, False, False) and BracketHelper.can_be_end_of_sequence(t1.next0_, False, None, False)):
t0 = t0.previous
t1 = t1.next0_
rt = ReferentToken(res, t0, t1)
kit.embed_token(rt)
t = (rt)
pr = PersonRelations()
pers_typ = TitleItemToken.Types.UNDEFINED
pers_types = pr.rel_types
t = begin
first_pass3398 = True
while True:
if first_pass3398: first_pass3398 = False
else: t = t.next0_
if (not (t is not None)): break
if (max_char_pos > 0 and t.begin_char > max_char_pos):
break
if (t == name_rt):
continue
tpt = TitleItemToken.try_attach(t)
if (tpt is not None):
pers_typ = TitleItemToken.Types.UNDEFINED
if (tpt.typ == TitleItemToken.Types.TYP):
if (len(res.types) == 0):
res._add_type(tpt.value)
elif (len(res.types) == 1):
ty = res.types[0].upper()
if (ty == "РЕФЕРАТ"):
res._add_type(tpt.value)
elif (ty == "АВТОРЕФЕРАТ"):
if (tpt.value == "КАНДИДАТСКАЯ ДИССЕРТАЦИЯ"):
res.add_slot(TitlePageReferent.ATTR_TYPE, "автореферат кандидатской диссертации", True, 0)
elif (tpt.value == "ДОКТОРСКАЯ ДИССЕРТАЦИЯ"):
res.add_slot(TitlePageReferent.ATTR_TYPE, "автореферат докторской диссертации", True, 0)
elif (tpt.value == "МАГИСТЕРСКАЯ ДИССЕРТАЦИЯ"):
res.add_slot(TitlePageReferent.ATTR_TYPE, "автореферат магистерской диссертации", True, 0)
elif (tpt.value == "КАНДИДАТСЬКА ДИСЕРТАЦІЯ"):
res.add_slot(TitlePageReferent.ATTR_TYPE, "автореферат кандидатської дисертації", True, 0)
elif (tpt.value == "ДОКТОРСЬКА ДИСЕРТАЦІЯ"):
res.add_slot(TitlePageReferent.ATTR_TYPE, "автореферат докторської дисертації", True, 0)
elif (tpt.value == "МАГІСТЕРСЬКА ДИСЕРТАЦІЯ"):
res.add_slot(TitlePageReferent.ATTR_TYPE, "автореферат магістерської дисертації", True, 0)
else:
res._add_type(tpt.value)
elif (tpt.value == "РЕФЕРАТ" or tpt.value == "АВТОРЕФЕРАТ"):
if (not tpt.value in ty):
res._add_type(tpt.value)
elif (tpt.typ == TitleItemToken.Types.SPECIALITY):
if (res.speciality is None):
res.speciality = tpt.value
elif (tpt.typ in pers_types):
pers_typ = tpt.typ
t = tpt.end_token
if (t.end_char > end_token.value.end_char):
end_token.value = t
if (t.next0_ is not None and t.next0_.is_char_of(":-")):
t = t.next0_
continue
if (t.end_char > end_char):
break
rli = t.get_referents()
if (rli is None):
continue
if (not t.is_newline_before and (isinstance(t.previous, TextToken))):
s = t.previous.term
if (s == "ИМЕНИ" or s == "ИМ"):
continue
if (s == "." and t.previous.previous is not None and t.previous.previous.is_value("ИМ", None)):
continue
for r in rli:
if (isinstance(r, PersonReferent)):
if (r != rli[0]):
continue
p = Utils.asObjectOrNull(r, PersonReferent)
if (pers_typ != TitleItemToken.Types.UNDEFINED):
if (t.previous is not None and t.previous.is_char('.')):
pers_typ = TitleItemToken.Types.UNDEFINED
typ = pr.calc_typ_from_attrs(p)
if (typ != TitleItemToken.Types.UNDEFINED):
pr.add(p, typ, 1)
pers_typ = typ
elif (pers_typ != TitleItemToken.Types.UNDEFINED):
pr.add(p, pers_typ, 1)
elif (t.previous is not None and t.previous.is_char('©')):
pers_typ = TitleItemToken.Types.WORKER
pr.add(p, pers_typ, 1)
else:
tt = t.next0_
first_pass3399 = True
while True:
if first_pass3399: first_pass3399 = False
else: tt = tt.next0_
if (not (tt is not None)): break
rr = tt.get_referent()
if (rr == res):
pers_typ = TitleItemToken.Types.WORKER
break
if (isinstance(rr, PersonReferent)):
if (pr.calc_typ_from_attrs(Utils.asObjectOrNull(r, PersonReferent)) != TitleItemToken.Types.UNDEFINED):
break
else:
continue
if (rr is not None):
break
tpt = TitleItemToken.try_attach(tt)
if (tpt is not None):
if (tpt.typ != TitleItemToken.Types.TYP and tpt.typ != TitleItemToken.Types.TYPANDTHEME):
break
tt = tpt.end_token
if (tt.end_char > end_token.value.end_char):
end_token.value = tt
continue
if (pers_typ == TitleItemToken.Types.UNDEFINED):
tt = t.previous
while tt is not None:
rr = tt.get_referent()
if (rr == res):
pers_typ = TitleItemToken.Types.WORKER
break
if (rr is not None):
break
if ((tt.is_value("СТУДЕНТ", None) or tt.is_value("СТУДЕНТКА", None) or tt.is_value("СЛУШАТЕЛЬ", None)) or tt.is_value("ДИПЛОМНИК", None) or tt.is_value("ИСПОЛНИТЕЛЬ", None)):
pers_typ = TitleItemToken.Types.WORKER
break
tpt = TitleItemToken.try_attach(tt)
if (tpt is not None and tpt.typ != TitleItemToken.Types.TYP):
break
tt = tt.previous
if (pers_typ != TitleItemToken.Types.UNDEFINED):
pr.add(p, pers_typ, 1)
else:
pr.add(p, pers_typ, 0.5)
if (t.end_char > end_token.value.end_char):
end_token.value = t
continue
if (r == rli[0]):
pers_typ = TitleItemToken.Types.UNDEFINED
if (isinstance(r, DateReferent)):
if (res.date is None):
res.date = Utils.asObjectOrNull(r, DateReferent)
if (t.end_char > end_token.value.end_char):
end_token.value = t
elif (isinstance(r, GeoReferent)):
if (res.city is None and r.is_city):
res.city = Utils.asObjectOrNull(r, GeoReferent)
if (t.end_char > end_token.value.end_char):
end_token.value = t
if (isinstance(r, OrganizationReferent)):
org0_ = Utils.asObjectOrNull(r, OrganizationReferent)
if ("курс" in org0_.types and org0_.number is not None):
i = 0
wrapi2673 = RefOutArgWrapper(0)
inoutres2674 = Utils.tryParseInt(org0_.number, wrapi2673)
i = wrapi2673.value
if (inoutres2674):
if (i > 0 and (i < 8)):
res.student_year = i
while org0_.higher is not None:
if (org0_.kind != OrganizationKind.DEPARTMENT):
break
org0_ = org0_.higher
if (org0_.kind != OrganizationKind.DEPARTMENT):
if (res.org0_ is None):
res.org0_ = org0_
elif (OrganizationReferent.can_be_higher(res.org0_, org0_)):
res.org0_ = org0_
if (t.end_char > end_token.value.end_char):
end_token.value = t
if ((isinstance(r, UriReferent)) or (isinstance(r, GeoReferent))):
if (t.end_char > end_token.value.end_char):
end_token.value = t
for ty in pers_types:
for p in pr.get_persons(ty):
if (pr.get_attr_name_for_type(ty) is not None):
res.add_slot(pr.get_attr_name_for_type(ty), p, False, 0)
if (res.get_slot_value(TitlePageReferent.ATTR_AUTHOR) is None):
for p in pr.get_persons(TitleItemToken.Types.UNDEFINED):
res.add_slot(TitlePageReferent.ATTR_AUTHOR, p, False, 0)
break
if (res.city is None and res.org0_ is not None):
s = res.org0_.find_slot(OrganizationReferent.ATTR_GEO, None, True)
if (s is not None and (isinstance(s.value, GeoReferent))):
if (s.value.is_city):
res.city = Utils.asObjectOrNull(s.value, GeoReferent)
if (res.date is None):
t = begin
first_pass3400 = True
while True:
if first_pass3400: first_pass3400 = False
else: t = t.next0_
if (not (t is not None and t.end_char <= end_char)): break
city = Utils.asObjectOrNull(t.get_referent(), GeoReferent)
if (city is None):
continue
if (isinstance(t.next0_, TextToken)):
if (t.next0_.is_char_of(":,") or t.next0_.is_hiphen):
t = t.next0_
rt = t.kit.process_referent(DateAnalyzer.ANALYZER_NAME, t.next0_)
if (rt is not None):
rt.save_to_local_ontology()
res.date = Utils.asObjectOrNull(rt.referent, DateReferent)
if (kit is not None):
kit.embed_token(rt)
break
if (len(res.slots) == 0):
return None
else:
return res
