Geforce File Manager

NAME	SIZE	ACTIONS
📁 __pycache__		[ DEL ]
📁 cli		[ DEL ]
📄 __init__.py	1,559 B	[ EDIT ] \| [ DEL ]
📄 big5freq.py	31,254 B	[ EDIT ] \| [ DEL ]
📄 big5prober.py	1,757 B	[ EDIT ] \| [ DEL ]
📄 chardistribution.py	9,411 B	[ EDIT ] \| [ DEL ]
📄 charsetgroupprober.py	3,787 B	[ EDIT ] \| [ DEL ]
📄 charsetprober.py	5,110 B	[ EDIT ] \| [ DEL ]
📄 codingstatemachine.py	3,590 B	[ EDIT ] \| [ DEL ]
📄 compat.py	1,134 B	[ EDIT ] \| [ DEL ]
📄 cp949prober.py	1,855 B	[ EDIT ] \| [ DEL ]
📄 enums.py	1,661 B	[ EDIT ] \| [ DEL ]
📄 escprober.py	3,950 B	[ EDIT ] \| [ DEL ]
📄 escsm.py	10,510 B	[ EDIT ] \| [ DEL ]
📄 eucjpprober.py	3,749 B	[ EDIT ] \| [ DEL ]
📄 euckrfreq.py	13,546 B	[ EDIT ] \| [ DEL ]
📄 euckrprober.py	1,748 B	[ EDIT ] \| [ DEL ]
📄 euctwfreq.py	31,621 B	[ EDIT ] \| [ DEL ]
📄 euctwprober.py	1,747 B	[ EDIT ] \| [ DEL ]
📄 gb2312freq.py	20,715 B	[ EDIT ] \| [ DEL ]
📄 gb2312prober.py	1,754 B	[ EDIT ] \| [ DEL ]
📄 hebrewprober.py	13,838 B	[ EDIT ] \| [ DEL ]
📄 jisfreq.py	25,777 B	[ EDIT ] \| [ DEL ]
📄 jpcntx.py	19,643 B	[ EDIT ] \| [ DEL ]
📄 langbulgarianmodel.py	12,839 B	[ EDIT ] \| [ DEL ]
📄 langcyrillicmodel.py	17,948 B	[ EDIT ] \| [ DEL ]
📄 langgreekmodel.py	12,688 B	[ EDIT ] \| [ DEL ]
📄 langhebrewmodel.py	11,345 B	[ EDIT ] \| [ DEL ]
📄 langhungarianmodel.py	12,592 B	[ EDIT ] \| [ DEL ]
📄 langthaimodel.py	11,290 B	[ EDIT ] \| [ DEL ]
📄 langturkishmodel.py	11,102 B	[ EDIT ] \| [ DEL ]
📄 latin1prober.py	5,370 B	[ EDIT ] \| [ DEL ]
📄 mbcharsetprober.py	3,413 B	[ EDIT ] \| [ DEL ]
📄 mbcsgroupprober.py	2,012 B	[ EDIT ] \| [ DEL ]
📄 mbcssm.py	25,481 B	[ EDIT ] \| [ DEL ]
📄 sbcharsetprober.py	5,657 B	[ EDIT ] \| [ DEL ]
📄 sbcsgroupprober.py	3,546 B	[ EDIT ] \| [ DEL ]
📄 sjisprober.py	3,774 B	[ EDIT ] \| [ DEL ]
📄 universaldetector.py	12,485 B	[ EDIT ] \| [ DEL ]
📄 utf8prober.py	2,766 B	[ EDIT ] \| [ DEL ]
📄 version.py	242 B	[ EDIT ] \| [ DEL ]

[ CLOSE ]

EDIT: charsetprober.py

######################## BEGIN LICENSE BLOCK ########################
# The Original Code is Mozilla Universal charset detector code.
#
# The Initial Developer of the Original Code is
# Netscape Communications Corporation.
# Portions created by the Initial Developer are Copyright (C) 2001
# the Initial Developer. All Rights Reserved.
#
# Contributor(s):
#   Mark Pilgrim - port to Python
#   Shy Shalom - original C code
#
# 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 #########################

import logging
import re

from .enums import ProbingState

class CharSetProber(object):

SHORTCUT_THRESHOLD = 0.95

def __init__(self, lang_filter=None):
        self._state = None
        self.lang_filter = lang_filter
        self.logger = logging.getLogger(__name__)

def reset(self):
        self._state = ProbingState.DETECTING

@property
    def charset_name(self):
        return None

def feed(self, buf):
        pass

@property
    def state(self):
        return self._state

def get_confidence(self):
        return 0.0

@staticmethod
    def filter_high_byte_only(buf):
        buf = re.sub(b'([\x00-\x7F])+', b' ', buf)
        return buf

@staticmethod
    def filter_international_words(buf):
        """
        We define three types of bytes:
        alphabet: english alphabets [a-zA-Z]
        international: international characters [\x80-\xFF]
        marker: everything else [^a-zA-Z\x80-\xFF]

The input buffer can be thought to contain a series of words delimited
        by markers. This function works to filter all words that contain at
        least one international character. All contiguous sequences of markers
        are replaced by a single space ascii character.

This filter applies to all scripts which do not use English characters.
        """
        filtered = bytearray()

# This regex expression filters out only words that have at-least one
        # international character. The word may include one marker character at
        # the end.
        words = re.findall(b'[a-zA-Z]*[\x80-\xFF]+[a-zA-Z]*[^a-zA-Z\x80-\xFF]?',
                           buf)

for word in words:
            filtered.extend(word[:-1])

# If the last character in the word is a marker, replace it with a
            # space as markers shouldn't affect our analysis (they are used
            # similarly across all languages and may thus have similar
            # frequencies).
            last_char = word[-1:]
            if not last_char.isalpha() and last_char < b'\x80':
                last_char = b' '
            filtered.extend(last_char)

return filtered

@staticmethod
    def filter_with_english_letters(buf):
        """
        Returns a copy of ``buf`` that retains only the sequences of English
        alphabet and high byte characters that are not between <> characters.
        Also retains English alphabet and high byte characters immediately
        before occurrences of >.

This filter can be applied to all scripts which contain both English
        characters and extended ASCII characters, but is currently only used by
        ``Latin1Prober``.
        """
        filtered = bytearray()
        in_tag = False
        prev = 0

for curr in range(len(buf)):
            # Slice here to get bytes instead of an int with Python 3
            buf_char = buf[curr:curr + 1]
            # Check if we're coming out of or entering an HTML tag
            if buf_char == b'>':
                in_tag = False
            elif buf_char == b'<':
                in_tag = True

# If current character is not extended-ASCII and not alphabetic...
            if buf_char < b'\x80' and not buf_char.isalpha():
                # ...and we're not in a tag
                if curr > prev and not in_tag:
                    # Keep everything after last non-extended-ASCII,
                    # non-alphabetic character
                    filtered.extend(buf[prev:curr])
                    # Output a space to delimit stretch we kept
                    filtered.extend(b' ')
                prev = curr + 1

# If we're not in a tag...
        if not in_tag:
            # Keep everything after last non-extended-ASCII, non-alphabetic
            # character
            filtered.extend(buf[prev:])

return filtered