File Manager

X7ROOT File Manager

Current Path: /usr/lib/python3.6/site-packages/chardet

usr / lib / python3.6 / site-packages / chardet /

?? ..
?? __init__.py(1.52 KB)
?? __pycache__
?? big5freq.py(30.52 KB)
?? big5prober.py(1.72 KB)
?? chardistribution.py(9.19 KB)
?? charsetgroupprober.py(3.7 KB)
?? charsetprober.py(4.99 KB)
?? cli
?? codingstatemachine.py(3.51 KB)
?? compat.py(1.11 KB)
?? cp949prober.py(1.81 KB)
?? enums.py(1.62 KB)
?? escprober.py(3.86 KB)
?? escsm.py(10.26 KB)
?? eucjpprober.py(3.66 KB)
?? euckrfreq.py(13.23 KB)
?? euckrprober.py(1.71 KB)
?? euctwfreq.py(30.88 KB)
?? euctwprober.py(1.71 KB)
?? gb2312freq.py(20.23 KB)
?? gb2312prober.py(1.71 KB)
?? hebrewprober.py(13.51 KB)
?? jisfreq.py(25.17 KB)
?? jpcntx.py(19.18 KB)
?? langbulgarianmodel.py(12.54 KB)
?? langcyrillicmodel.py(17.53 KB)
?? langgreekmodel.py(12.39 KB)
?? langhebrewmodel.py(11.08 KB)
?? langhungarianmodel.py(12.3 KB)
?? langthaimodel.py(11.03 KB)
?? langturkishmodel.py(10.84 KB)
?? latin1prober.py(5.24 KB)
?? mbcharsetprober.py(3.33 KB)
?? mbcsgroupprober.py(1.96 KB)
?? mbcssm.py(24.88 KB)
?? sbcharsetprober.py(5.52 KB)
?? sbcsgroupprober.py(3.46 KB)
?? sjisprober.py(3.69 KB)
?? universaldetector.py(12.19 KB)
?? utf8prober.py(2.7 KB)
?? version.py(242 B)

Editing: escprober.py

######################## BEGIN LICENSE BLOCK ########################
# The Original Code is mozilla.org 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 .charsetprober import CharSetProber
from .codingstatemachine import CodingStateMachine
from .enums import LanguageFilter, ProbingState, MachineState
from .escsm import (HZ_SM_MODEL, ISO2022CN_SM_MODEL, ISO2022JP_SM_MODEL,
                    ISO2022KR_SM_MODEL)

class EscCharSetProber(CharSetProber):
    """
    This CharSetProber uses a "code scheme" approach for detecting encodings,
    whereby easily recognizable escape or shift sequences are relied on to
    identify these encodings.
    """

def __init__(self, lang_filter=None):
        super(EscCharSetProber, self).__init__(lang_filter=lang_filter)
        self.coding_sm = []
        if self.lang_filter & LanguageFilter.CHINESE_SIMPLIFIED:
            self.coding_sm.append(CodingStateMachine(HZ_SM_MODEL))
            self.coding_sm.append(CodingStateMachine(ISO2022CN_SM_MODEL))
        if self.lang_filter & LanguageFilter.JAPANESE:
            self.coding_sm.append(CodingStateMachine(ISO2022JP_SM_MODEL))
        if self.lang_filter & LanguageFilter.KOREAN:
            self.coding_sm.append(CodingStateMachine(ISO2022KR_SM_MODEL))
        self.active_sm_count = None
        self._detected_charset = None
        self._detected_language = None
        self._state = None
        self.reset()

def reset(self):
        super(EscCharSetProber, self).reset()
        for coding_sm in self.coding_sm:
            if not coding_sm:
                continue
            coding_sm.active = True
            coding_sm.reset()
        self.active_sm_count = len(self.coding_sm)
        self._detected_charset = None
        self._detected_language = None

@property
    def charset_name(self):
        return self._detected_charset

@property
    def language(self):
        return self._detected_language

def get_confidence(self):
        if self._detected_charset:
            return 0.99
        else:
            return 0.00

def feed(self, byte_str):
        for c in byte_str:
            for coding_sm in self.coding_sm:
                if not coding_sm or not coding_sm.active:
                    continue
                coding_state = coding_sm.next_state(c)
                if coding_state == MachineState.ERROR:
                    coding_sm.active = False
                    self.active_sm_count -= 1
                    if self.active_sm_count <= 0:
                        self._state = ProbingState.NOT_ME
                        return self.state
                elif coding_state == MachineState.ITS_ME:
                    self._state = ProbingState.FOUND_IT
                    self._detected_charset = coding_sm.get_coding_state_machine()
                    self._detected_language = coding_sm.language
                    return self.state

return self.state

X7ROOT File Manager

Editing: escprober.py

Upload File

Create Folder