golden hour

/opt/saltstack/salt/lib/python3.10/site-packages/pip/_vendor/chardet

File/Folder	Size	Actions
__init__.py	3.62 KB
__pycache__	-
big5freq.py	30.54 KB
big5prober.py	1.7 KB
chardistribution.py	9.38 KB
charsetgroupprober.py	3.73 KB
charsetprober.py	4.69 KB
cli	-
codingstatemachine.py	3.48 KB
cp949prober.py	1.79 KB
enums.py	1.58 KB
escprober.py	3.77 KB
escsm.py	11.74 KB
eucjpprober.py	3.59 KB
euckrfreq.py	13.25 KB
euckrprober.py	1.69 KB
euctwfreq.py	36.05 KB
euctwprober.py	1.69 KB
gb2312freq.py	20.25 KB
gb2312prober.py	1.7 KB
hebrewprober.py	13.59 KB
jisfreq.py	25.19 KB
johabfreq.py	41.5 KB
johabprober.py	1.69 KB
jpcntx.py	26.17 KB
langbulgarianmodel.py	102.11 KB
langgreekmodel.py	96.18 KB
langhebrewmodel.py	95.89 KB
langhungarianmodel.py	98.99 KB
langrussianmodel.py	125.03 KB
langthaimodel.py	100.37 KB
langturkishmodel.py	93.14 KB
latin1prober.py	5.14 KB
mbcharsetprober.py	3.29 KB
mbcsgroupprober.py	2.01 KB
mbcssm.py	29.36 KB
metadata	-
sbcharsetprober.py	6.05 KB
sbcsgroupprober.py	4.03 KB
sjisprober.py	3.66 KB
universaldetector.py	12.98 KB
utf1632prober.py	8.09 KB
utf8prober.py	2.65 KB
version.py	242 B

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

INTERNATIONAL_WORDS_PATTERN = re.compile(
    b"[a-zA-Z]*[\x80-\xFF]+[a-zA-Z]*[^a-zA-Z\x80-\xFF]?"
)

class CharSetProber:

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, byte_str):
        raise NotImplementedError

@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 = INTERNATIONAL_WORDS_PATTERN.findall(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 remove_xml_tags(buf):
        """
        Returns a copy of ``buf`` that retains only the sequences of English
        alphabet and high byte characters that are not between <> characters.
        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
        buf = memoryview(buf).cast("c")

for curr, buf_char in enumerate(buf):
            # Check if we're coming out of or entering an XML tag
            if buf_char == b">":
                prev = curr + 1
                in_tag = False
            elif buf_char == b"<":
                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" ")
                in_tag = True

# 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