0x100000000
  C   ˆl–Ðz¾”Š_)%ÕÆ…p©‹Fÿ�þDë Y¹AËí8û@þÐ„ È¿Ï_ŠI|¥�+Wé3ž¯ÄÍ '0    ######################## BEGIN LICENSE BLOCK ########################
# The Original Code is Mozilla Communicator client code.
#
# The Initial Developer of the Original Code is
# Netscape Communications Corporation.
# Portions created by the Initial Developer are Copyright (C) 1998
# the Initial Developer. All Rights Reserved.
#
# Contributor(s):
#   Mark Pilgrim - port to Python
#
# This library is free software; you can redistribute it and/or
# modify it under the terms of the GNU Lesser General Public
# License as published by the Free Software Foundation; either
# version 2.1 of the License, or (at your option) any later version.
#
# This library is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
# Lesser General Public License for more details.
#
# You should have received a copy of the GNU Lesser General Public
# License along with this library; if not, write to the Free Software
# Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA
# 02110-1301  USA
######################### END LICENSE BLOCK #########################

from typing import Tuple, Union

from .big5freq import (
    BIG5_CHAR_TO_FREQ_ORDER,
    BIG5_TABLE_SIZE,
    BIG5_TYPICAL_DISTRIBUTION_RATIO,
)
from .euckrfreq import (
    EUCKR_CHAR_TO_FREQ_ORDER,
    EUCKR_TABLE_SIZE,
    EUCKR_TYPICAL_DISTRIBUTION_RATIO,
)
from .euctwfreq import (
    EUCTW_CHAR_TO_FREQ_ORDER,
    EUCTW_TABLE_SIZE,
    EUCTW_TYPICAL_DISTRIBUTION_RATIO,
)
from .gb2312freq import (
    GB2312_CHAR_TO_FREQ_ORDER,
    GB2312_TABLE_SIZE,
    GB2312_TYPICAL_DISTRIBUTION_RATIO,
)
from .jisfreq import (
    JIS_CHAR_TO_FREQ_ORDER,
    JIS_TABLE_SIZE,
    JIS_TYPICAL_DISTRIBUTION_RATIO,
)
from .johabfreq import JOHAB_TO_EUCKR_ORDER_TABLE


class CharDistributionAnalysis:
    ENOUGH_DATA_THRESHOLD = 1024
    SURE_YES = 0.99
    SURE_NO = 0.01
    MINIMUM_DATA_THRESHOLD = 3

    def __init__(self) -> None:
        # Mapping table to get frequency order from char order (get from
        # GetOrder())
        self._char_to_freq_order: Tuple[int, ...] = tuple()
        self._table_size = 0  # Size of above table
        # This is a constant value which varies from language to language,
        # used in calculating confidence.  See
        # http://www.mozilla.org/projects/intl/UniversalCharsetDetection.html
        # for further detail.
        self.typical_distribution_ratio = 0.0
        self._done = False
        self._total_chars = 0
        self._freq_chars = 0
        self.reset()

    def reset(self) -> None:
        """reset analyser, clear any state"""
        # If this flag is set to True, detection is done and conclusion has
        # been made
        self._done = False
        self._total_chars = 0  # Total characters encountered
        # The number of characters whose frequency order is less than 512
        self._freq_chars = 0

    def feed(self, char: Union[bytes, bytearray], char_len: int) -> None:
        """feed a character with known length"""
        if char_len == 2:
            # we only care about 2-bytes character in our distribution analysis
            order = self.get_order(char)
        else:
            order = -1
        if order >= 0:
            self._total_chars += 1
            # order is valid
            if order < self._table_size:
                if 512 > self._char_to_freq_order[order]:
                    self._freq_chars += 1

    def get_confidence(self) -> float:
        """return confidence based on existing data"""
        # if we didn't receive any character in our consideration range,
        # return negative answer
        if self._total_chars <= 0 or self._freq_chars <= self.MINIMUM_DATA_THRESHOLD:
            return self.SURE_NO

        if self._total_chars != self._freq_chars:
            r = self._freq_chars / (
                (self._total_chars - self._freq_chars) * self.typical_distribution_ratio
  