Initial commit

.idea/encodings.xml

+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="Encoding" addBOMForNewFiles="with NO BOM" />
+</project>
\ No newline at end of file

.idea/misc.xml

+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="JavaScriptSettings">
+    <option name="languageLevel" value="ES6" />
+  </component>
+  <component name="ProjectRootManager" version="2" project-jdk-name="Python 3.7 (rota)" project-jdk-type="Python SDK" />
+</project>
\ No newline at end of file

.idea/modules.xml

+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectModuleManager">
+    <modules>
+      <module fileurl="file://$PROJECT_DIR$/.idea/rota.iml" filepath="$PROJECT_DIR$/.idea/rota.iml" />
+    </modules>
+  </component>
+</project>
\ No newline at end of file

.idea/rota.iml

+<?xml version="1.0" encoding="UTF-8"?>
+<module type="PYTHON_MODULE" version="4">
+  <component name="NewModuleRootManager">
+    <content url="file://$MODULE_DIR$">
+      <excludeFolder url="file://$MODULE_DIR$/venv" />
+    </content>
+    <orderEntry type="inheritedJdk" />
+    <orderEntry type="sourceFolder" forTests="false" />
+  </component>
+  <component name="TestRunnerService">
+    <option name="PROJECT_TEST_RUNNER" value="Unittests" />
+  </component>
+</module>
\ No newline at end of file

.idea/vcs.xml

+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="VcsDirectoryMappings">
+    <mapping directory="$PROJECT_DIR$" vcs="Git" />
+  </component>
+</project>
\ No newline at end of file

peizhi.py

+
+Personnel_list={
+    20210501:"莹莹，奉龙，伟男",
+    20210510:"刘丙寅"
+}
+

rota_gm.py

+import requests
+from pprint import pprint
+import peizhi
+def test():
+
+    from datetime import date
+    from datetime import timedelta
+    today = date.today()
+    format_today = today.strftime("%Y%m%d")
+    tomorrow = today + timedelta(days=2)
+    format_tomorrow = tomorrow.strftime("%Y%m%d")
+    print(format_today)
+    print(format_tomorrow)
+
+    days = []
+    url = "https://api.apihubs.cn/holiday/get"
+    params = {
+        "year":2021,
+        "size":1000
+    }
+    result = requests.get(url=url,params=params)
+    res = result.json()
+    list = res.get("data").get("list")
+    for i in range(len(list)):
+        workday = list[i].get("workday")
+        if workday == 2:
+            date = list[i].get("date")
+            days.append(date)
+    message = ""
+    if int(format_tomorrow) in days:
+        worker = peizhi.Personnel_list.get(int(format_tomorrow))
+        if worker ==None:
+            message = "明日假期但还没有分配值班人员"
+        else:
+            message = worker
+        dd_url = "https://oapi.dingtalk.com/robot/send?access_token=062ab7f98f47c85e6c200efd21ae5d532e4f1bbfd6782ae1268b9a1f4d3dc7b9"
+        text = "明日开始休息：值班人员为：%s  值班人员记得带 电脑，手机 vpn环境" % {message}
+        json_text = {
+            "msgtype": "text",
+            "at": {
+                "atMobiles": [
+
+                    "all"
+                ],
+                # 变为true 就会@所有人
+                "isAtAll": True
+            },
+            "text": {
+                "content": text
+            }
+        }
+
+        requests.post(url=dd_url, json=json_text, verify=False)
+
+
+
+
+
+
+
+
+if __name__ == '__main__':
+    test()
\ No newline at end of file

venv/bin/activate

+# This file must be used with "source bin/activate" *from bash*
+# you cannot run it directly
+
+deactivate () {
+    # reset old environment variables
+    if [ -n "${_OLD_VIRTUAL_PATH:-}" ] ; then
+        PATH="${_OLD_VIRTUAL_PATH:-}"
+        export PATH
+        unset _OLD_VIRTUAL_PATH
+    fi
+    if [ -n "${_OLD_VIRTUAL_PYTHONHOME:-}" ] ; then
+        PYTHONHOME="${_OLD_VIRTUAL_PYTHONHOME:-}"
+        export PYTHONHOME
+        unset _OLD_VIRTUAL_PYTHONHOME
+    fi
+
+    # This should detect bash and zsh, which have a hash command that must
+    # be called to get it to forget past commands.  Without forgetting
+    # past commands the $PATH changes we made may not be respected
+    if [ -n "${BASH:-}" -o -n "${ZSH_VERSION:-}" ] ; then
+        hash -r
+    fi
+
+    if [ -n "${_OLD_VIRTUAL_PS1:-}" ] ; then
+        PS1="${_OLD_VIRTUAL_PS1:-}"
+        export PS1
+        unset _OLD_VIRTUAL_PS1
+    fi
+
+    unset VIRTUAL_ENV
+    if [ ! "$1" = "nondestructive" ] ; then
+    # Self destruct!
+        unset -f deactivate
+    fi
+}
+
+# unset irrelevant variables
+deactivate nondestructive
+
+VIRTUAL_ENV="/Users/bingyinliu/PycharmProjects/rota/venv"
+export VIRTUAL_ENV
+
+_OLD_VIRTUAL_PATH="$PATH"
+PATH="$VIRTUAL_ENV/bin:$PATH"
+export PATH
+
+# unset PYTHONHOME if set
+# this will fail if PYTHONHOME is set to the empty string (which is bad anyway)
+# could use `if (set -u; : $PYTHONHOME) ;` in bash
+if [ -n "${PYTHONHOME:-}" ] ; then
+    _OLD_VIRTUAL_PYTHONHOME="${PYTHONHOME:-}"
+    unset PYTHONHOME
+fi
+
+if [ -z "${VIRTUAL_ENV_DISABLE_PROMPT:-}" ] ; then
+    _OLD_VIRTUAL_PS1="${PS1:-}"
+    if [ "x(venv) " != x ] ; then
+	PS1="(venv) ${PS1:-}"
+    else
+    if [ "`basename \"$VIRTUAL_ENV\"`" = "__" ] ; then
+        # special case for Aspen magic directories
+        # see http://www.zetadev.com/software/aspen/
+        PS1="[`basename \`dirname \"$VIRTUAL_ENV\"\``] $PS1"
+    else
+        PS1="(`basename \"$VIRTUAL_ENV\"`)$PS1"
+    fi
+    fi
+    export PS1
+fi
+
+# This should detect bash and zsh, which have a hash command that must
+# be called to get it to forget past commands.  Without forgetting
+# past commands the $PATH changes we made may not be respected
+if [ -n "${BASH:-}" -o -n "${ZSH_VERSION:-}" ] ; then
+    hash -r
+fi

venv/bin/activate.csh

+# This file must be used with "source bin/activate.csh" *from csh*.
+# You cannot run it directly.
+# Created by Davide Di Blasi <davidedb@gmail.com>.
+# Ported to Python 3.3 venv by Andrew Svetlov <andrew.svetlov@gmail.com>
+
+alias deactivate 'test $?_OLD_VIRTUAL_PATH != 0 && setenv PATH "$_OLD_VIRTUAL_PATH" && unset _OLD_VIRTUAL_PATH; rehash; test $?_OLD_VIRTUAL_PROMPT != 0 && set prompt="$_OLD_VIRTUAL_PROMPT" && unset _OLD_VIRTUAL_PROMPT; unsetenv VIRTUAL_ENV; test "\!:*" != "nondestructive" && unalias deactivate'
+
+# Unset irrelevant variables.
+deactivate nondestructive
+
+setenv VIRTUAL_ENV "/Users/bingyinliu/PycharmProjects/rota/venv"
+
+set _OLD_VIRTUAL_PATH="$PATH"
+setenv PATH "$VIRTUAL_ENV/bin:$PATH"
+
+
+set _OLD_VIRTUAL_PROMPT="$prompt"
+
+if (! "$?VIRTUAL_ENV_DISABLE_PROMPT") then
+    if ("venv" != "") then
+        set env_name = "venv"
+    else
+        if (`basename "VIRTUAL_ENV"` == "__") then
+            # special case for Aspen magic directories
+            # see http://www.zetadev.com/software/aspen/
+            set env_name = `basename \`dirname "$VIRTUAL_ENV"\``
+        else
+            set env_name = `basename "$VIRTUAL_ENV"`
+        endif
+    endif
+    set prompt = "[$env_name] $prompt"
+    unset env_name
+endif
+
+alias pydoc python -m pydoc
+
+rehash

venv/bin/activate.fish

+# This file must be used with ". bin/activate.fish" *from fish* (http://fishshell.org)
+# you cannot run it directly
+
+function deactivate  -d "Exit virtualenv and return to normal shell environment"
+    # reset old environment variables
+    if test -n "$_OLD_VIRTUAL_PATH"
+        set -gx PATH $_OLD_VIRTUAL_PATH
+        set -e _OLD_VIRTUAL_PATH
+    end
+    if test -n "$_OLD_VIRTUAL_PYTHONHOME"
+        set -gx PYTHONHOME $_OLD_VIRTUAL_PYTHONHOME
+        set -e _OLD_VIRTUAL_PYTHONHOME
+    end
+
+    if test -n "$_OLD_FISH_PROMPT_OVERRIDE"
+        functions -e fish_prompt
+        set -e _OLD_FISH_PROMPT_OVERRIDE
+        functions -c _old_fish_prompt fish_prompt
+        functions -e _old_fish_prompt
+    end
+
+    set -e VIRTUAL_ENV
+    if test "$argv[1]" != "nondestructive"
+        # Self destruct!
+        functions -e deactivate
+    end
+end
+
+# unset irrelevant variables
+deactivate nondestructive
+
+set -gx VIRTUAL_ENV "/Users/bingyinliu/PycharmProjects/rota/venv"
+
+set -gx _OLD_VIRTUAL_PATH $PATH
+set -gx PATH "$VIRTUAL_ENV/bin" $PATH
+
+# unset PYTHONHOME if set
+if set -q PYTHONHOME
+    set -gx _OLD_VIRTUAL_PYTHONHOME $PYTHONHOME
+    set -e PYTHONHOME
+end
+
+if test -z "$VIRTUAL_ENV_DISABLE_PROMPT"
+    # fish uses a function instead of an env var to generate the prompt.
+
+    # save the current fish_prompt function as the function _old_fish_prompt
+    functions -c fish_prompt _old_fish_prompt
+
+    # with the original prompt function renamed, we can override with our own.
+    function fish_prompt
+        # Save the return status of the last command
+        set -l old_status $status
+
+        # Prompt override?
+        if test -n "(venv) "
+            printf "%s%s" "(venv) " (set_color normal)
+        else
+            # ...Otherwise, prepend env
+            set -l _checkbase (basename "$VIRTUAL_ENV")
+            if test $_checkbase = "__"
+                # special case for Aspen magic directories
+                # see http://www.zetadev.com/software/aspen/
+                printf "%s[%s]%s " (set_color -b blue white) (basename (dirname "$VIRTUAL_ENV")) (set_color normal)
+            else
+                printf "%s(%s)%s" (set_color -b blue white) (basename "$VIRTUAL_ENV") (set_color normal)
+            end
+        end
+
+        # Restore the return status of the previous command.
+        echo "exit $old_status" | .
+        _old_fish_prompt
+    end
+
+    set -gx _OLD_FISH_PROMPT_OVERRIDE "$VIRTUAL_ENV"
+end

venv/bin/chardetect

+#!/Users/bingyinliu/PycharmProjects/rota/venv/bin/python
+
+# -*- coding: utf-8 -*-
+import re
+import sys
+
+from chardet.cli.chardetect import main
+
+if __name__ == '__main__':
+    sys.argv[0] = re.sub(r'(-script\.pyw?|\.exe)?$', '', sys.argv[0])
+    sys.exit(main())

venv/bin/easy_install

+#!/Users/bingyinliu/PycharmProjects/rota/venv/bin/python
+# EASY-INSTALL-ENTRY-SCRIPT: 'setuptools==39.1.0','console_scripts','easy_install'
+__requires__ = 'setuptools==39.1.0'
+import re
+import sys
+from pkg_resources import load_entry_point
+
+if __name__ == '__main__':
+    sys.argv[0] = re.sub(r'(-script\.pyw?|\.exe)?$', '', sys.argv[0])
+    sys.exit(
+        load_entry_point('setuptools==39.1.0', 'console_scripts', 'easy_install')()
+    )

venv/bin/easy_install-3.7

+#!/Users/bingyinliu/PycharmProjects/rota/venv/bin/python
+# EASY-INSTALL-ENTRY-SCRIPT: 'setuptools==39.1.0','console_scripts','easy_install-3.7'
+__requires__ = 'setuptools==39.1.0'
+import re
+import sys
+from pkg_resources import load_entry_point
+
+if __name__ == '__main__':
+    sys.argv[0] = re.sub(r'(-script\.pyw?|\.exe)?$', '', sys.argv[0])
+    sys.exit(
+        load_entry_point('setuptools==39.1.0', 'console_scripts', 'easy_install-3.7')()
+    )

venv/bin/pip

+#!/Users/bingyinliu/PycharmProjects/rota/venv/bin/python
+# EASY-INSTALL-ENTRY-SCRIPT: 'pip==10.0.1','console_scripts','pip'
+__requires__ = 'pip==10.0.1'
+import re
+import sys
+from pkg_resources import load_entry_point
+
+if __name__ == '__main__':
+    sys.argv[0] = re.sub(r'(-script\.pyw?|\.exe)?$', '', sys.argv[0])
+    sys.exit(
+        load_entry_point('pip==10.0.1', 'console_scripts', 'pip')()
+    )

venv/bin/pip3

+#!/Users/bingyinliu/PycharmProjects/rota/venv/bin/python
+# EASY-INSTALL-ENTRY-SCRIPT: 'pip==10.0.1','console_scripts','pip3'
+__requires__ = 'pip==10.0.1'
+import re
+import sys
+from pkg_resources import load_entry_point
+
+if __name__ == '__main__':
+    sys.argv[0] = re.sub(r'(-script\.pyw?|\.exe)?$', '', sys.argv[0])
+    sys.exit(
+        load_entry_point('pip==10.0.1', 'console_scripts', 'pip3')()
+    )

venv/bin/pip3.7

+#!/Users/bingyinliu/PycharmProjects/rota/venv/bin/python
+# EASY-INSTALL-ENTRY-SCRIPT: 'pip==10.0.1','console_scripts','pip3.7'
+__requires__ = 'pip==10.0.1'
+import re
+import sys
+from pkg_resources import load_entry_point
+
+if __name__ == '__main__':
+    sys.argv[0] = re.sub(r'(-script\.pyw?|\.exe)?$', '', sys.argv[0])
+    sys.exit(
+        load_entry_point('pip==10.0.1', 'console_scripts', 'pip3.7')()
+    )

venv/lib/python3.7/site-packages/certifi-2020.12.5.dist-info/INSTALLER

+pip

venv/lib/python3.7/site-packages/certifi-2020.12.5.dist-info/LICENSE

+This packge contains a modified version of ca-bundle.crt:
+
+ca-bundle.crt -- Bundle of CA Root Certificates
+
+Certificate data from Mozilla as of: Thu Nov  3 19:04:19 2011#
+This is a bundle of X.509 certificates of public Certificate Authorities
+(CA). These were automatically extracted from Mozilla's root certificates
+file (certdata.txt).  This file can be found in the mozilla source tree:
+http://mxr.mozilla.org/mozilla/source/security/nss/lib/ckfw/builtins/certdata.txt?raw=1#
+It contains the certificates in PEM format and therefore
+can be directly used with curl / libcurl / php_curl, or with
+an Apache+mod_ssl webserver for SSL client authentication.
+Just configure this file as the SSLCACertificateFile.#
+
+***** BEGIN LICENSE BLOCK *****
+This Source Code Form is subject to the terms of the Mozilla Public License,
+v. 2.0. If a copy of the MPL was not distributed with this file, You can obtain
+one at http://mozilla.org/MPL/2.0/.
+
+***** END LICENSE BLOCK *****
+@(#) $RCSfile: certdata.txt,v $ $Revision: 1.80 $ $Date: 2011/11/03 15:11:58 $

venv/lib/python3.7/site-packages/certifi-2020.12.5.dist-info/METADATA

+Metadata-Version: 2.1
+Name: certifi
+Version: 2020.12.5
+Summary: Python package for providing Mozilla's CA Bundle.
+Home-page: https://certifiio.readthedocs.io/en/latest/
+Author: Kenneth Reitz
+Author-email: me@kennethreitz.com
+License: MPL-2.0
+Project-URL: Documentation, https://certifiio.readthedocs.io/en/latest/
+Project-URL: Source, https://github.com/certifi/python-certifi
+Platform: UNKNOWN
+Classifier: Development Status :: 5 - Production/Stable
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: Mozilla Public License 2.0 (MPL 2.0)
+Classifier: Natural Language :: English
+Classifier: Programming Language :: Python
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.3
+Classifier: Programming Language :: Python :: 3.4
+Classifier: Programming Language :: Python :: 3.5
+Classifier: Programming Language :: Python :: 3.6
+Classifier: Programming Language :: Python :: 3.7
+Classifier: Programming Language :: Python :: 3.8
+Classifier: Programming Language :: Python :: 3.9
+
+Certifi: Python SSL Certificates
+================================
+
+`Certifi`_ provides Mozilla's carefully curated collection of Root Certificates for
+validating the trustworthiness of SSL certificates while verifying the identity
+of TLS hosts. It has been extracted from the `Requests`_ project.
+
+Installation
+------------
+
+``certifi`` is available on PyPI. Simply install it with ``pip``::
+
+    $ pip install certifi
+
+Usage
+-----
+
+To reference the installed certificate authority (CA) bundle, you can use the
+built-in function::
+
+    >>> import certifi
+
+    >>> certifi.where()
+    '/usr/local/lib/python3.7/site-packages/certifi/cacert.pem'
+
+Or from the command line::
+
+    $ python -m certifi
+    /usr/local/lib/python3.7/site-packages/certifi/cacert.pem
+
+Enjoy!
+
+1024-bit Root Certificates
+~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Browsers and certificate authorities have concluded that 1024-bit keys are
+unacceptably weak for certificates, particularly root certificates. For this
+reason, Mozilla has removed any weak (i.e. 1024-bit key) certificate from its
+bundle, replacing it with an equivalent strong (i.e. 2048-bit or greater key)
+certificate from the same CA. Because Mozilla removed these certificates from
+its bundle, ``certifi`` removed them as well.
+
+In previous versions, ``certifi`` provided the ``certifi.old_where()`` function
+to intentionally re-add the 1024-bit roots back into your bundle. This was not
+recommended in production and therefore was removed at the end of 2018.
+
+.. _`Certifi`: https://certifiio.readthedocs.io/en/latest/
+.. _`Requests`: https://requests.readthedocs.io/en/master/
+
+Addition/Removal of Certificates
+--------------------------------
+
+Certifi does not support any addition/removal or other modification of the
+CA trust store content. This project is intended to provide a reliable and
+highly portable root of trust to python deployments. Look to upstream projects
+for methods to use alternate trust.
+
+

venv/lib/python3.7/site-packages/certifi-2020.12.5.dist-info/RECORD

+certifi/__init__.py,sha256=SsmdmFHjHCY4VLtqwpp9P_jsOcAuHj-5c5WqoEz-oFg,62
+certifi/__main__.py,sha256=xBBoj905TUWBLRGANOcf7oi6e-3dMP4cEoG9OyMs11g,243
+certifi/cacert.pem,sha256=u3fxPT--yemLvyislQRrRBlsfY9Vq3cgBh6ZmRqCkZc,263774
+certifi/core.py,sha256=V0uyxKOYdz6ulDSusclrLmjbPgOXsD0BnEf0SQ7OnoE,2303
+certifi-2020.12.5.dist-info/LICENSE,sha256=anCkv2sBABbVmmS4rkrY3H9e8W8ftFPMLs13HFo0ETE,1048
+certifi-2020.12.5.dist-info/METADATA,sha256=SEw5GGHIeBwGwDJsIUaVfEQAc5Jqs_XofOfTX-_kCE0,2994
+certifi-2020.12.5.dist-info/WHEEL,sha256=ADKeyaGyKF5DwBNE0sRE5pvW-bSkFMJfBuhzZ3rceP4,110
+certifi-2020.12.5.dist-info/top_level.txt,sha256=KMu4vUCfsjLrkPbSNdgdekS-pVJzBAJFO__nI8NF6-U,8
+certifi-2020.12.5.dist-info/RECORD,,
+certifi-2020.12.5.dist-info/INSTALLER,sha256=zuuue4knoyJ-UwPPXg8fezS7VCrXJQrAP7zeNuwvFQg,4
+certifi/__pycache__/__main__.cpython-37.pyc,,
+certifi/__pycache__/core.cpython-37.pyc,,
+certifi/__pycache__/__init__.cpython-37.pyc,,

venv/lib/python3.7/site-packages/certifi-2020.12.5.dist-info/WHEEL

+Wheel-Version: 1.0
+Generator: bdist_wheel (0.35.1)
+Root-Is-Purelib: true
+Tag: py2-none-any
+Tag: py3-none-any
+

venv/lib/python3.7/site-packages/certifi-2020.12.5.dist-info/top_level.txt

+certifi

venv/lib/python3.7/site-packages/certifi/__init__.py

+from .core import contents, where
+
+__version__ = "2020.12.05"

venv/lib/python3.7/site-packages/certifi/__main__.py

+import argparse
+
+from certifi import contents, where
+
+parser = argparse.ArgumentParser()
+parser.add_argument("-c", "--contents", action="store_true")
+args = parser.parse_args()
+
+if args.contents:
+    print(contents())
+else:
+    print(where())

venv/lib/python3.7/site-packages/certifi/core.py

+# -*- coding: utf-8 -*-
+
+"""
+certifi.py
+~~~~~~~~~~
+
+This module returns the installation location of cacert.pem or its contents.
+"""
+import os
+
+try:
+    from importlib.resources import path as get_path, read_text
+
+    _CACERT_CTX = None
+    _CACERT_PATH = None
+
+    def where():
+        # This is slightly terrible, but we want to delay extracting the file
+        # in cases where we're inside of a zipimport situation until someone
+        # actually calls where(), but we don't want to re-extract the file
+        # on every call of where(), so we'll do it once then store it in a
+        # global variable.
+        global _CACERT_CTX
+        global _CACERT_PATH
+        if _CACERT_PATH is None:
+            # This is slightly janky, the importlib.resources API wants you to
+            # manage the cleanup of this file, so it doesn't actually return a
+            # path, it returns a context manager that will give you the path
+            # when you enter it and will do any cleanup when you leave it. In
+            # the common case of not needing a temporary file, it will just
+            # return the file system location and the __exit__() is a no-op.
+            #
+            # We also have to hold onto the actual context manager, because
+            # it will do the cleanup whenever it gets garbage collected, so
+            # we will also store that at the global level as well.
+            _CACERT_CTX = get_path("certifi", "cacert.pem")
+            _CACERT_PATH = str(_CACERT_CTX.__enter__())
+
+        return _CACERT_PATH
+
+
+except ImportError:
+    # This fallback will work for Python versions prior to 3.7 that lack the
+    # importlib.resources module but relies on the existing `where` function
+    # so won't address issues with environments like PyOxidizer that don't set
+    # __file__ on modules.
+    def read_text(_module, _path, encoding="ascii"):
+        with open(where(), "r", encoding=encoding) as data:
+            return data.read()
+
+    # If we don't have importlib.resources, then we will just do the old logic
+    # of assuming we're on the filesystem and munge the path directly.
+    def where():
+        f = os.path.dirname(__file__)
+
+        return os.path.join(f, "cacert.pem")
+
+
+def contents():
+    return read_text("certifi", "cacert.pem", encoding="ascii")

venv/lib/python3.7/site-packages/chardet-4.0.0.dist-info/INSTALLER

+pip

venv/lib/python3.7/site-packages/chardet-4.0.0.dist-info/METADATA

+Metadata-Version: 2.1
+Name: chardet
+Version: 4.0.0
+Summary: Universal encoding detector for Python 2 and 3
+Home-page: https://github.com/chardet/chardet
+Author: Mark Pilgrim
+Author-email: mark@diveintomark.org
+Maintainer: Daniel Blanchard
+Maintainer-email: dan.blanchard@gmail.com
+License: LGPL
+Keywords: encoding,i18n,xml
+Platform: UNKNOWN
+Classifier: Development Status :: 5 - Production/Stable
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: GNU Library or Lesser General Public License (LGPL)
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python
+Classifier: Programming Language :: Python :: 2
+Classifier: Programming Language :: Python :: 2.7
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.5
+Classifier: Programming Language :: Python :: 3.6
+Classifier: Programming Language :: Python :: 3.7
+Classifier: Programming Language :: Python :: 3.8
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: Implementation :: CPython
+Classifier: Programming Language :: Python :: Implementation :: PyPy
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Classifier: Topic :: Text Processing :: Linguistic
+Requires-Python: >=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*, !=3.4.*
+
+Chardet: The Universal Character Encoding Detector
+--------------------------------------------------
+
+.. image:: https://img.shields.io/travis/chardet/chardet/stable.svg
+   :alt: Build status
+   :target: https://travis-ci.org/chardet/chardet
+
+.. image:: https://img.shields.io/coveralls/chardet/chardet/stable.svg
+   :target: https://coveralls.io/r/chardet/chardet
+
+.. image:: https://img.shields.io/pypi/v/chardet.svg
+   :target: https://warehouse.python.org/project/chardet/
+   :alt: Latest version on PyPI
+
+.. image:: https://img.shields.io/pypi/l/chardet.svg
+   :alt: License
+
+
+Detects
+ - ASCII, UTF-8, UTF-16 (2 variants), UTF-32 (4 variants)
+ - Big5, GB2312, EUC-TW, HZ-GB-2312, ISO-2022-CN (Traditional and Simplified Chinese)
+ - EUC-JP, SHIFT_JIS, CP932, ISO-2022-JP (Japanese)
+ - EUC-KR, ISO-2022-KR (Korean)
+ - KOI8-R, MacCyrillic, IBM855, IBM866, ISO-8859-5, windows-1251 (Cyrillic)
+ - ISO-8859-5, windows-1251 (Bulgarian)
+ - ISO-8859-1, windows-1252 (Western European languages)
+ - ISO-8859-7, windows-1253 (Greek)
+ - ISO-8859-8, windows-1255 (Visual and Logical Hebrew)
+ - TIS-620 (Thai)
+
+.. note::
+   Our ISO-8859-2 and windows-1250 (Hungarian) probers have been temporarily
+   disabled until we can retrain the models.
+
+Requires Python 2.7 or 3.5+.
+
+Installation
+------------
+
+Install from `PyPI <https://pypi.org/project/chardet/>`_::
+
+    pip install chardet
+
+Documentation
+-------------
+
+For users, docs are now available at https://chardet.readthedocs.io/.
+
+Command-line Tool
+-----------------
+
+chardet comes with a command-line script which reports on the encodings of one
+or more files::
+
+    % chardetect somefile someotherfile
+    somefile: windows-1252 with confidence 0.5
+    someotherfile: ascii with confidence 1.0
+
+About
+-----
+
+This is a continuation of Mark Pilgrim's excellent chardet. Previously, two
+versions needed to be maintained: one that supported python 2.x and one that
+supported python 3.x.  We've recently merged with `Ian Cordasco <https://github.com/sigmavirus24>`_'s
+`charade <https://github.com/sigmavirus24/charade>`_ fork, so now we have one
+coherent version that works for Python 2.7+ and 3.4+.
+
+:maintainer: Dan Blanchard
+
+

venv/lib/python3.7/site-packages/chardet-4.0.0.dist-info/RECORD

+chardet/__init__.py,sha256=mWZaWmvZkhwfBEAT9O1Y6nRTfKzhT7FHhQTTAujbqUA,3271
+chardet/big5freq.py,sha256=D_zK5GyzoVsRes0HkLJziltFQX0bKCLOrFe9_xDvO_8,31254
+chardet/big5prober.py,sha256=kBxHbdetBpPe7xrlb-e990iot64g_eGSLd32lB7_h3M,1757
+chardet/chardistribution.py,sha256=3woWS62KrGooKyqz4zQSnjFbJpa6V7g02daAibTwcl8,9411
+chardet/charsetgroupprober.py,sha256=GZLReHP6FRRn43hvSOoGCxYamErKzyp6RgOQxVeC3kg,3839
+chardet/charsetprober.py,sha256=KSmwJErjypyj0bRZmC5F5eM7c8YQgLYIjZXintZNstg,5110
+chardet/codingstatemachine.py,sha256=VYp_6cyyki5sHgXDSZnXW4q1oelHc3cu9AyQTX7uug8,3590
+chardet/compat.py,sha256=40zr6wICZwknxyuLGGcIOPyve8DTebBCbbvttvnmp5Q,1200
+chardet/cp949prober.py,sha256=TZ434QX8zzBsnUvL_8wm4AQVTZ2ZkqEEQL_lNw9f9ow,1855
+chardet/enums.py,sha256=Aimwdb9as1dJKZaFNUH2OhWIVBVd6ZkJJ_WK5sNY8cU,1661
+chardet/escprober.py,sha256=kkyqVg1Yw3DIOAMJ2bdlyQgUFQhuHAW8dUGskToNWSc,3950
+chardet/escsm.py,sha256=RuXlgNvTIDarndvllNCk5WZBIpdCxQ0kcd9EAuxUh84,10510
+chardet/eucjpprober.py,sha256=iD8Jdp0ISRjgjiVN7f0e8xGeQJ5GM2oeZ1dA8nbSeUw,3749
+chardet/euckrfreq.py,sha256=-7GdmvgWez4-eO4SuXpa7tBiDi5vRXQ8WvdFAzVaSfo,13546
+chardet/euckrprober.py,sha256=MqFMTQXxW4HbzIpZ9lKDHB3GN8SP4yiHenTmf8g_PxY,1748
+chardet/euctwfreq.py,sha256=No1WyduFOgB5VITUA7PLyC5oJRNzRyMbBxaKI1l16MA,31621
+chardet/euctwprober.py,sha256=13p6EP4yRaxqnP4iHtxHOJ6R2zxHq1_m8hTRjzVZ95c,1747
+chardet/gb2312freq.py,sha256=JX8lsweKLmnCwmk8UHEQsLgkr_rP_kEbvivC4qPOrlc,20715
+chardet/gb2312prober.py,sha256=gGvIWi9WhDjE-xQXHvNIyrnLvEbMAYgyUSZ65HUfylw,1754
+chardet/hebrewprober.py,sha256=c3SZ-K7hvyzGY6JRAZxJgwJ_sUS9k0WYkvMY00YBYFo,13838
+chardet/jisfreq.py,sha256=vpmJv2Bu0J8gnMVRPHMFefTRvo_ha1mryLig8CBwgOg,25777
+chardet/jpcntx.py,sha256=PYlNqRUQT8LM3cT5FmHGP0iiscFlTWED92MALvBungo,19643
+chardet/langbulgarianmodel.py,sha256=r6tvOtO8FqhnbWBB5V4czcl1fWM4pB9lGiWQU-8gvsw,105685
+chardet/langgreekmodel.py,sha256=1cMu2wUgPB8bQ2RbVjR4LNwCCETgQ-Dwo0Eg2_uB11s,99559
+chardet/langhebrewmodel.py,sha256=urMmJHHIXtCwaWAqy1zEY_4SmwwNzt730bDOtjXzRjs,98764
+chardet/langhungarianmodel.py,sha256=ODAisvqCfes8B4FeyM_Pg9HY3ZDnEyaCiT4Bxyzoc6w,102486
+chardet/langrussianmodel.py,sha256=sPqkrBbX0QVwwy6oqRl-x7ERv2J4-zaMoCvLpkSsSJI,131168
+chardet/langthaimodel.py,sha256=ppoKOGL9OPdj9A4CUyG8R48zbnXt9MN1WXeCYepa6sc,103300
+chardet/langturkishmodel.py,sha256=H3ldicI_rhlv0r3VFpVWtUL6X30Wy596v7_YHz2sEdg,95934
+chardet/latin1prober.py,sha256=S2IoORhFk39FEFOlSFWtgVybRiP6h7BlLldHVclNkU8,5370
+chardet/mbcharsetprober.py,sha256=AR95eFH9vuqSfvLQZN-L5ijea25NOBCoXqw8s5O9xLQ,3413
+chardet/mbcsgroupprober.py,sha256=h6TRnnYq2OxG1WdD5JOyxcdVpn7dG0q-vB8nWr5mbh4,2012
+chardet/mbcssm.py,sha256=SY32wVIF3HzcjY3BaEspy9metbNSKxIIB0RKPn7tjpI,25481
+chardet/sbcharsetprober.py,sha256=nmyMyuxzG87DN6K3Rk2MUzJLMLR69MrWpdnHzOwVUwQ,6136
+chardet/sbcsgroupprober.py,sha256=hqefQuXmiFyDBArOjujH6hd6WFXlOD1kWCsxDhjx5Vc,4309
+chardet/sjisprober.py,sha256=IIt-lZj0WJqK4rmUZzKZP4GJlE8KUEtFYVuY96ek5MQ,3774
+chardet/universaldetector.py,sha256=DpZTXCX0nUHXxkQ9sr4GZxGB_hveZ6hWt3uM94cgWKs,12503
+chardet/utf8prober.py,sha256=IdD8v3zWOsB8OLiyPi-y_fqwipRFxV9Nc1eKBLSuIEw,2766
+chardet/version.py,sha256=A4CILFAd8MRVG1HoXPp45iK9RLlWyV73a1EtwE8Tvn8,242
+chardet/cli/__init__.py,sha256=AbpHGcgLb-kRsJGnwFEktk7uzpZOCcBY74-YBdrKVGs,1
+chardet/cli/chardetect.py,sha256=kUPeQCi-olObXpOq5MtlKuBn1EU19rkeenAMwxl7URY,2711
+chardet/metadata/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+chardet/metadata/languages.py,sha256=41tLq3eLSrBEbEVVQpVGFq9K7o1ln9b1HpY1l0hCUQo,19474
+chardet-4.0.0.dist-info/LICENSE,sha256=YJXp_6d33SKDn3gBqoRbMcntB_PWv4om3F0t7IzMDvM,26432
+chardet-4.0.0.dist-info/METADATA,sha256=ySYQAE7NPm3LwxgMqFi1zdLQ48mmwMbrJwqAWCtcbH8,3526
+chardet-4.0.0.dist-info/WHEEL,sha256=ADKeyaGyKF5DwBNE0sRE5pvW-bSkFMJfBuhzZ3rceP4,110
+chardet-4.0.0.dist-info/entry_points.txt,sha256=fAMmhu5eJ-zAJ-smfqQwRClQ3-nozOCmvJ6-E8lgGJo,60
+chardet-4.0.0.dist-info/top_level.txt,sha256=AowzBbZy4x8EirABDdJSLJZMkJ_53iIag8xfKR6D7kI,8
+chardet-4.0.0.dist-info/RECORD,,
+../../../bin/chardetect,sha256=xP0Sw8NB0oMWAAeIy2VF_2y3hzXVueP3uNoOkME19-8,263
+chardet-4.0.0.dist-info/INSTALLER,sha256=zuuue4knoyJ-UwPPXg8fezS7VCrXJQrAP7zeNuwvFQg,4
+chardet/__pycache__/mbcharsetprober.cpython-37.pyc,,
+chardet/__pycache__/eucjpprober.cpython-37.pyc,,
+chardet/__pycache__/langgreekmodel.cpython-37.pyc,,
+chardet/__pycache__/sjisprober.cpython-37.pyc,,
+chardet/__pycache__/gb2312prober.cpython-37.pyc,,
+chardet/__pycache__/euctwfreq.cpython-37.pyc,,
+chardet/__pycache__/cp949prober.cpython-37.pyc,,
+chardet/__pycache__/version.cpython-37.pyc,,
+chardet/__pycache__/langhebrewmodel.cpython-37.pyc,,
+chardet/__pycache__/langturkishmodel.cpython-37.pyc,,
+chardet/__pycache__/sbcsgroupprober.cpython-37.pyc,,
+chardet/__pycache__/euckrfreq.cpython-37.pyc,,
+chardet/__pycache__/euckrprober.cpython-37.pyc,,
+chardet/__pycache__/escsm.cpython-37.pyc,,
+chardet/__pycache__/chardistribution.cpython-37.pyc,,
+chardet/__pycache__/euctwprober.cpython-37.pyc,,
+chardet/__pycache__/langrussianmodel.cpython-37.pyc,,
+chardet/__pycache__/compat.cpython-37.pyc,,
+chardet/__pycache__/big5freq.cpython-37.pyc,,
+chardet/__pycache__/escprober.cpython-37.pyc,,
+chardet/__pycache__/universaldetector.cpython-37.pyc,,
+chardet/__pycache__/latin1prober.cpython-37.pyc,,
+chardet/__pycache__/hebrewprober.cpython-37.pyc,,
+chardet/__pycache__/utf8prober.cpython-37.pyc,,
+chardet/__pycache__/langhungarianmodel.cpython-37.pyc,,
+chardet/__pycache__/codingstatemachine.cpython-37.pyc,,
+chardet/__pycache__/langthaimodel.cpython-37.pyc,,
+chardet/__pycache__/enums.cpython-37.pyc,,
+chardet/__pycache__/gb2312freq.cpython-37.pyc,,
+chardet/__pycache__/big5prober.cpython-37.pyc,,
+chardet/__pycache__/mbcssm.cpython-37.pyc,,
+chardet/__pycache__/jpcntx.cpython-37.pyc,,
+chardet/__pycache__/sbcharsetprober.cpython-37.pyc,,
+chardet/__pycache__/jisfreq.cpython-37.pyc,,
+chardet/__pycache__/__init__.cpython-37.pyc,,
+chardet/__pycache__/charsetprober.cpython-37.pyc,,
+chardet/__pycache__/mbcsgroupprober.cpython-37.pyc,,
+chardet/__pycache__/langbulgarianmodel.cpython-37.pyc,,
+chardet/__pycache__/charsetgroupprober.cpython-37.pyc,,
+chardet/cli/__pycache__/chardetect.cpython-37.pyc,,
+chardet/cli/__pycache__/__init__.cpython-37.pyc,,
+chardet/metadata/__pycache__/__init__.cpython-37.pyc,,
+chardet/metadata/__pycache__/languages.cpython-37.pyc,,

venv/lib/python3.7/site-packages/chardet-4.0.0.dist-info/WHEEL

+Wheel-Version: 1.0
+Generator: bdist_wheel (0.35.1)
+Root-Is-Purelib: true
+Tag: py2-none-any
+Tag: py3-none-any
+

venv/lib/python3.7/site-packages/chardet-4.0.0.dist-info/entry_points.txt

+[console_scripts]
+chardetect = chardet.cli.chardetect:main
+

venv/lib/python3.7/site-packages/chardet-4.0.0.dist-info/top_level.txt

+chardet

venv/lib/python3.7/site-packages/chardet/__init__.py

+######################## BEGIN LICENSE BLOCK ########################
+# 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 .universaldetector import UniversalDetector
+from .enums import InputState
+from .version import __version__, VERSION
+
+
+__all__ = ['UniversalDetector', 'detect', 'detect_all', '__version__', 'VERSION']
+
+
+def detect(byte_str):
+    """
+    Detect the encoding of the given byte string.
+
+    :param byte_str:     The byte sequence to examine.
+    :type byte_str:      ``bytes`` or ``bytearray``
+    """
+    if not isinstance(byte_str, bytearray):
+        if not isinstance(byte_str, bytes):
+            raise TypeError('Expected object of type bytes or bytearray, got: '
+                            '{}'.format(type(byte_str)))
+        else:
+            byte_str = bytearray(byte_str)
+    detector = UniversalDetector()
+    detector.feed(byte_str)
+    return detector.close()
+
+
+def detect_all(byte_str):
+    """
+    Detect all the possible encodings of the given byte string.
+
+    :param byte_str:     The byte sequence to examine.
+    :type byte_str:      ``bytes`` or ``bytearray``
+    """
+    if not isinstance(byte_str, bytearray):
+        if not isinstance(byte_str, bytes):
+            raise TypeError('Expected object of type bytes or bytearray, got: '
+                            '{}'.format(type(byte_str)))
+        else:
+            byte_str = bytearray(byte_str)
+
+    detector = UniversalDetector()
+    detector.feed(byte_str)
+    detector.close()
+
+    if detector._input_state == InputState.HIGH_BYTE:
+        results = []
+        for prober in detector._charset_probers:
+            if prober.get_confidence() > detector.MINIMUM_THRESHOLD:
+                charset_name = prober.charset_name
+                lower_charset_name = prober.charset_name.lower()
+                # Use Windows encoding name instead of ISO-8859 if we saw any
+                # extra Windows-specific bytes
+                if lower_charset_name.startswith('iso-8859'):
+                    if detector._has_win_bytes:
+                        charset_name = detector.ISO_WIN_MAP.get(lower_charset_name,
+                                                            charset_name)
+                results.append({
+                    'encoding': charset_name,
+                    'confidence': prober.get_confidence(),
+                    'language': prober.language,
+                })
+        if len(results) > 0:
+            return sorted(results, key=lambda result: -result['confidence'])
+
+    return [detector.result]

venv/lib/python3.7/site-packages/chardet/big5prober.py

+######################## 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 .mbcharsetprober import MultiByteCharSetProber
+from .codingstatemachine import CodingStateMachine
+from .chardistribution import Big5DistributionAnalysis
+from .mbcssm import BIG5_SM_MODEL
+
+
+class Big5Prober(MultiByteCharSetProber):
+    def __init__(self):
+        super(Big5Prober, self).__init__()
+        self.coding_sm = CodingStateMachine(BIG5_SM_MODEL)
+        self.distribution_analyzer = Big5DistributionAnalysis()
+        self.reset()
+
+    @property
+    def charset_name(self):
+        return "Big5"
+
+    @property
+    def language(self):
+        return "Chinese"

venv/lib/python3.7/site-packages/chardet/chardistribution.py

+######################## 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 .euctwfreq import (EUCTW_CHAR_TO_FREQ_ORDER, EUCTW_TABLE_SIZE,
+                        EUCTW_TYPICAL_DISTRIBUTION_RATIO)
+from .euckrfreq import (EUCKR_CHAR_TO_FREQ_ORDER, EUCKR_TABLE_SIZE,
+                        EUCKR_TYPICAL_DISTRIBUTION_RATIO)
+from .gb2312freq import (GB2312_CHAR_TO_FREQ_ORDER, GB2312_TABLE_SIZE,
+                         GB2312_TYPICAL_DISTRIBUTION_RATIO)
+from .big5freq import (BIG5_CHAR_TO_FREQ_ORDER, BIG5_TABLE_SIZE,
+                       BIG5_TYPICAL_DISTRIBUTION_RATIO)
+from .jisfreq import (JIS_CHAR_TO_FREQ_ORDER, JIS_TABLE_SIZE,
+                      JIS_TYPICAL_DISTRIBUTION_RATIO)
+
+
+class CharDistributionAnalysis(object):
+    ENOUGH_DATA_THRESHOLD = 1024
+    SURE_YES = 0.99
+    SURE_NO = 0.01
+    MINIMUM_DATA_THRESHOLD = 3
+
+    def __init__(self):
+        # Mapping table to get frequency order from char order (get from
+        # GetOrder())
+        self._char_to_freq_order = None
+        self._table_size = None  # 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 = None
+        self._done = None
+        self._total_chars = None
+        self._freq_chars = None
+        self.reset()
+
+    def reset(self):
+        """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, char_len):
+        """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):
+        """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))
+            if r < self.SURE_YES:
+                return r
+
+        # normalize confidence (we don't want to be 100% sure)
+        return self.SURE_YES
+
+    def got_enough_data(self):
+        # It is not necessary to receive all data to draw conclusion.
+        # For charset detection, certain amount of data is enough
+        return self._total_chars > self.ENOUGH_DATA_THRESHOLD
+
+    def get_order(self, byte_str):
+        # We do not handle characters based on the original encoding string,
+        # but convert this encoding string to a number, here called order.
+        # This allows multiple encodings of a language to share one frequency
+        # table.
+        return -1
+
+
+class EUCTWDistributionAnalysis(CharDistributionAnalysis):
+    def __init__(self):
+        super(EUCTWDistributionAnalysis, self).__init__()
+        self._char_to_freq_order = EUCTW_CHAR_TO_FREQ_ORDER
+        self._table_size = EUCTW_TABLE_SIZE
+        self.typical_distribution_ratio = EUCTW_TYPICAL_DISTRIBUTION_RATIO
+
+    def get_order(self, byte_str):
+        # for euc-TW encoding, we are interested
+        #   first  byte range: 0xc4 -- 0xfe
+        #   second byte range: 0xa1 -- 0xfe
+        # no validation needed here. State machine has done that
+        first_char = byte_str[0]
+        if first_char >= 0xC4:
+            return 94 * (first_char - 0xC4) + byte_str[1] - 0xA1
+        else:
+            return -1
+
+
+class EUCKRDistributionAnalysis(CharDistributionAnalysis):
+    def __init__(self):
+        super(EUCKRDistributionAnalysis, self).__init__()
+        self._char_to_freq_order = EUCKR_CHAR_TO_FREQ_ORDER
+        self._table_size = EUCKR_TABLE_SIZE
+        self.typical_distribution_ratio = EUCKR_TYPICAL_DISTRIBUTION_RATIO
+
+    def get_order(self, byte_str):
+        # for euc-KR encoding, we are interested
+        #   first  byte range: 0xb0 -- 0xfe
+        #   second byte range: 0xa1 -- 0xfe
+        # no validation needed here. State machine has done that
+        first_char = byte_str[0]
+        if first_char >= 0xB0:
+            return 94 * (first_char - 0xB0) + byte_str[1] - 0xA1
+        else:
+            return -1
+
+
+class GB2312DistributionAnalysis(CharDistributionAnalysis):
+    def __init__(self):
+        super(GB2312DistributionAnalysis, self).__init__()
+        self._char_to_freq_order = GB2312_CHAR_TO_FREQ_ORDER
+        self._table_size = GB2312_TABLE_SIZE
+        self.typical_distribution_ratio = GB2312_TYPICAL_DISTRIBUTION_RATIO
+
+    def get_order(self, byte_str):
+        # for GB2312 encoding, we are interested
+        #  first  byte range: 0xb0 -- 0xfe
+        #  second byte range: 0xa1 -- 0xfe
+        # no validation needed here. State machine has done that
+        first_char, second_char = byte_str[0], byte_str[1]
+        if (first_char >= 0xB0) and (second_char >= 0xA1):
+            return 94 * (first_char - 0xB0) + second_char - 0xA1
+        else:
+            return -1
+
+
+class Big5DistributionAnalysis(CharDistributionAnalysis):
+    def __init__(self):
+        super(Big5DistributionAnalysis, self).__init__()
+        self._char_to_freq_order = BIG5_CHAR_TO_FREQ_ORDER
+        self._table_size = BIG5_TABLE_SIZE
+        self.typical_distribution_ratio = BIG5_TYPICAL_DISTRIBUTION_RATIO
+
+    def get_order(self, byte_str):
+        # for big5 encoding, we are interested
+        #   first  byte range: 0xa4 -- 0xfe
+        #   second byte range: 0x40 -- 0x7e , 0xa1 -- 0xfe
+        # no validation needed here. State machine has done that
+        first_char, second_char = byte_str[0], byte_str[1]
+        if first_char >= 0xA4:
+            if second_char >= 0xA1:
+                return 157 * (first_char - 0xA4) + second_char - 0xA1 + 63
+            else:
+                return 157 * (first_char - 0xA4) + second_char - 0x40
+        else:
+            return -1
+
+
+class SJISDistributionAnalysis(CharDistributionAnalysis):
+    def __init__(self):
+        super(SJISDistributionAnalysis, self).__init__()
+        self._char_to_freq_order = JIS_CHAR_TO_FREQ_ORDER
+        self._table_size = JIS_TABLE_SIZE
+        self.typical_distribution_ratio = JIS_TYPICAL_DISTRIBUTION_RATIO
+
+    def get_order(self, byte_str):
+        # for sjis encoding, we are interested
+        #   first  byte range: 0x81 -- 0x9f , 0xe0 -- 0xfe
+        #   second byte range: 0x40 -- 0x7e,  0x81 -- oxfe
+        # no validation needed here. State machine has done that
+        first_char, second_char = byte_str[0], byte_str[1]
+        if (first_char >= 0x81) and (first_char <= 0x9F):
+            order = 188 * (first_char - 0x81)
+        elif (first_char >= 0xE0) and (first_char <= 0xEF):
+            order = 188 * (first_char - 0xE0 + 31)
+        else:
+            return -1
+        order = order + second_char - 0x40
+        if second_char > 0x7F:
+            order = -1
+        return order
+
+
+class EUCJPDistributionAnalysis(CharDistributionAnalysis):
+    def __init__(self):
+        super(EUCJPDistributionAnalysis, self).__init__()
+        self._char_to_freq_order = JIS_CHAR_TO_FREQ_ORDER
+        self._table_size = JIS_TABLE_SIZE
+        self.typical_distribution_ratio = JIS_TYPICAL_DISTRIBUTION_RATIO
+
+    def get_order(self, byte_str):
+        # for euc-JP encoding, we are interested
+        #   first  byte range: 0xa0 -- 0xfe
+        #   second byte range: 0xa1 -- 0xfe
+        # no validation needed here. State machine has done that
+        char = byte_str[0]
+        if char >= 0xA0:
+            return 94 * (char - 0xA1) + byte_str[1] - 0xa1
+        else:
+            return -1

venv/lib/python3.7/site-packages/chardet/charsetgroupprober.py

+######################## 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 .enums import ProbingState
+from .charsetprober import CharSetProber
+
+
+class CharSetGroupProber(CharSetProber):
+    def __init__(self, lang_filter=None):
+        super(CharSetGroupProber, self).__init__(lang_filter=lang_filter)
+        self._active_num = 0
+        self.probers = []
+        self._best_guess_prober = None
+
+    def reset(self):
+        super(CharSetGroupProber, self).reset()
+        self._active_num = 0
+        for prober in self.probers:
+            if prober:
+                prober.reset()
+                prober.active = True
+                self._active_num += 1
+        self._best_guess_prober = None
+
+    @property
+    def charset_name(self):
+        if not self._best_guess_prober:
+            self.get_confidence()
+            if not self._best_guess_prober:
+                return None
+        return self._best_guess_prober.charset_name
+
+    @property
+    def language(self):
+        if not self._best_guess_prober:
+            self.get_confidence()
+            if not self._best_guess_prober:
+                return None
+        return self._best_guess_prober.language
+
+    def feed(self, byte_str):
+        for prober in self.probers:
+            if not prober:
+                continue
+            if not prober.active:
+                continue
+            state = prober.feed(byte_str)
+            if not state:
+                continue
+            if state == ProbingState.FOUND_IT:
+                self._best_guess_prober = prober
+                self._state = ProbingState.FOUND_IT
+                return self.state
+            elif state == ProbingState.NOT_ME:
+                prober.active = False
+                self._active_num -= 1
+                if self._active_num <= 0:
+                    self._state = ProbingState.NOT_ME
+                    return self.state
+        return self.state
+
+    def get_confidence(self):
+        state = self.state
+        if state == ProbingState.FOUND_IT:
+            return 0.99
+        elif state == ProbingState.NOT_ME:
+            return 0.01
+        best_conf = 0.0
+        self._best_guess_prober = None
+        for prober in self.probers:
+            if not prober:
+                continue
+            if not prober.active:
+                self.logger.debug('%s not active', prober.charset_name)
+                continue
+            conf = prober.get_confidence()
+            self.logger.debug('%s %s confidence = %s', prober.charset_name, prober.language, conf)
+            if best_conf < conf:
+                best_conf = conf
+                self._best_guess_prober = prober
+        if not self._best_guess_prober:
+            return 0.0
+        return best_conf

venv/lib/python3.7/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

venv/lib/python3.7/site-packages/chardet/cli/__init__.py

+

venv/lib/python3.7/site-packages/chardet/cli/chardetect.py

+"""
+Script which takes one or more file paths and reports on their detected
+encodings
+
+Example::
+
+    % chardetect somefile someotherfile
+    somefile: windows-1252 with confidence 0.5
+    someotherfile: ascii with confidence 1.0
+
+If no paths are provided, it takes its input from stdin.
+
+"""
+
+from __future__ import absolute_import, print_function, unicode_literals
+
+import argparse
+import sys
+
+from chardet import __version__
+from chardet.compat import PY2
+from chardet.universaldetector import UniversalDetector
+
+
+def description_of(lines, name='stdin'):
+    """
+    Return a string describing the probable encoding of a file or
+    list of strings.
+
+    :param lines: The lines to get the encoding of.
+    :type lines: Iterable of bytes
+    :param name: Name of file or collection of lines
+    :type name: str
+    """
+    u = UniversalDetector()
+    for line in lines:
+        line = bytearray(line)
+        u.feed(line)
+        # shortcut out of the loop to save reading further - particularly useful if we read a BOM.
+        if u.done:
+            break
+    u.close()
+    result = u.result
+    if PY2:
+        name = name.decode(sys.getfilesystemencoding(), 'ignore')
+    if result['encoding']:
+        return '{}: {} with confidence {}'.format(name, result['encoding'],
+                                                     result['confidence'])
+    else:
+        return '{}: no result'.format(name)
+
+
+def main(argv=None):
+    """
+    Handles command line arguments and gets things started.
+
+    :param argv: List of arguments, as if specified on the command-line.
+                 If None, ``sys.argv[1:]`` is used instead.
+    :type argv: list of str
+    """
+    # Get command line arguments
+    parser = argparse.ArgumentParser(
+        description="Takes one or more file paths and reports their detected \
+                     encodings")
+    parser.add_argument('input',
+                        help='File whose encoding we would like to determine. \
+                              (default: stdin)',
+                        type=argparse.FileType('rb'), nargs='*',
+                        default=[sys.stdin if PY2 else sys.stdin.buffer])
+    parser.add_argument('--version', action='version',
+                        version='%(prog)s {}'.format(__version__))
+    args = parser.parse_args(argv)
+
+    for f in args.input:
+        if f.isatty():
+            print("You are running chardetect interactively. Press " +
+                  "CTRL-D twice at the start of a blank line to signal the " +
+                  "end of your input. If you want help, run chardetect " +
+                  "--help\n", file=sys.stderr)
+        print(description_of(f, f.name))
+
+
+if __name__ == '__main__':
+    main()

venv/lib/python3.7/site-packages/chardet/codingstatemachine.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 #########################
+
+import logging
+
+from .enums import MachineState
+
+
+class CodingStateMachine(object):
+    """
+    A state machine to verify a byte sequence for a particular encoding. For
+    each byte the detector receives, it will feed that byte to every active
+    state machine available, one byte at a time. The state machine changes its
+    state based on its previous state and the byte it receives. There are 3
+    states in a state machine that are of interest to an auto-detector:
+
+    START state: This is the state to start with, or a legal byte sequence
+                 (i.e. a valid code point) for character has been identified.
+
+    ME state:  This indicates that the state machine identified a byte sequence
+               that is specific to the charset it is designed for and that
+               there is no other possible encoding which can contain this byte
+               sequence. This will to lead to an immediate positive answer for
+               the detector.
+
+    ERROR state: This indicates the state machine identified an illegal byte
+                 sequence for that encoding. This will lead to an immediate
+                 negative answer for this encoding. Detector will exclude this
+                 encoding from consideration from here on.
+    """
+    def __init__(self, sm):
+        self._model = sm
+        self._curr_byte_pos = 0
+        self._curr_char_len = 0
+        self._curr_state = None
+        self.logger = logging.getLogger(__name__)
+        self.reset()
+
+    def reset(self):
+        self._curr_state = MachineState.START
+
+    def next_state(self, c):
+        # for each byte we get its class
+        # if it is first byte, we also get byte length
+        byte_class = self._model['class_table'][c]
+        if self._curr_state == MachineState.START:
+            self._curr_byte_pos = 0
+            self._curr_char_len = self._model['char_len_table'][byte_class]
+        # from byte's class and state_table, we get its next state
+        curr_state = (self._curr_state * self._model['class_factor']
+                      + byte_class)
+        self._curr_state = self._model['state_table'][curr_state]
+        self._curr_byte_pos += 1
+        return self._curr_state
+
+    def get_current_charlen(self):
+        return self._curr_char_len
+
+    def get_coding_state_machine(self):
+        return self._model['name']
+
+    @property
+    def language(self):
+        return self._model['language']

venv/lib/python3.7/site-packages/chardet/compat.py

+######################## BEGIN LICENSE BLOCK ########################
+# Contributor(s):
+#   Dan Blanchard
+#   Ian Cordasco
+#
+# 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 sys
+
+
+if sys.version_info < (3, 0):
+    PY2 = True
+    PY3 = False
+    string_types = (str, unicode)
+    text_type = unicode
+    iteritems = dict.iteritems
+else:
+    PY2 = False
+    PY3 = True
+    string_types = (bytes, str)
+    text_type = str
+    iteritems = dict.items

venv/lib/python3.7/site-packages/chardet/cp949prober.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 .chardistribution import EUCKRDistributionAnalysis
+from .codingstatemachine import CodingStateMachine
+from .mbcharsetprober import MultiByteCharSetProber
+from .mbcssm import CP949_SM_MODEL
+
+
+class CP949Prober(MultiByteCharSetProber):
+    def __init__(self):
+        super(CP949Prober, self).__init__()
+        self.coding_sm = CodingStateMachine(CP949_SM_MODEL)
+        # NOTE: CP949 is a superset of EUC-KR, so the distribution should be
+        #       not different.
+        self.distribution_analyzer = EUCKRDistributionAnalysis()
+        self.reset()
+
+    @property
+    def charset_name(self):
+        return "CP949"
+
+    @property
+    def language(self):
+        return "Korean"

venv/lib/python3.7/site-packages/chardet/enums.py

+"""
+All of the Enums that are used throughout the chardet package.
+
+:author: Dan Blanchard (dan.blanchard@gmail.com)
+"""
+
+
+class InputState(object):
+    """
+    This enum represents the different states a universal detector can be in.
+    """
+    PURE_ASCII = 0
+    ESC_ASCII = 1
+    HIGH_BYTE = 2
+
+
+class LanguageFilter(object):
+    """
+    This enum represents the different language filters we can apply to a
+    ``UniversalDetector``.
+    """
+    CHINESE_SIMPLIFIED = 0x01
+    CHINESE_TRADITIONAL = 0x02
+    JAPANESE = 0x04
+    KOREAN = 0x08
+    NON_CJK = 0x10
+    ALL = 0x1F
+    CHINESE = CHINESE_SIMPLIFIED | CHINESE_TRADITIONAL
+    CJK = CHINESE | JAPANESE | KOREAN
+
+
+class ProbingState(object):
+    """
+    This enum represents the different states a prober can be in.
+    """
+    DETECTING = 0
+    FOUND_IT = 1
+    NOT_ME = 2
+
+
+class MachineState(object):
+    """
+    This enum represents the different states a state machine can be in.
+    """
+    START = 0
+    ERROR = 1
+    ITS_ME = 2
+
+
+class SequenceLikelihood(object):
+    """
+    This enum represents the likelihood of a character following the previous one.
+    """
+    NEGATIVE = 0
+    UNLIKELY = 1
+    LIKELY = 2
+    POSITIVE = 3
+
+    @classmethod
+    def get_num_categories(cls):
+        """:returns: The number of likelihood categories in the enum."""
+        return 4
+
+
+class CharacterCategory(object):
+    """
+    This enum represents the different categories language models for
+    ``SingleByteCharsetProber`` put characters into.
+
+    Anything less than CONTROL is considered a letter.
+    """
+    UNDEFINED = 255
+    LINE_BREAK = 254
+    SYMBOL = 253
+    DIGIT = 252
+    CONTROL = 251

venv/lib/python3.7/site-packages/chardet/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

venv/lib/python3.7/site-packages/chardet/eucjpprober.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 .enums import ProbingState, MachineState
+from .mbcharsetprober import MultiByteCharSetProber
+from .codingstatemachine import CodingStateMachine
+from .chardistribution import EUCJPDistributionAnalysis
+from .jpcntx import EUCJPContextAnalysis
+from .mbcssm import EUCJP_SM_MODEL
+
+
+class EUCJPProber(MultiByteCharSetProber):
+    def __init__(self):
+        super(EUCJPProber, self).__init__()
+        self.coding_sm = CodingStateMachine(EUCJP_SM_MODEL)
+        self.distribution_analyzer = EUCJPDistributionAnalysis()
+        self.context_analyzer = EUCJPContextAnalysis()
+        self.reset()
+
+    def reset(self):
+        super(EUCJPProber, self).reset()
+        self.context_analyzer.reset()
+
+    @property
+    def charset_name(self):
+        return "EUC-JP"
+
+    @property
+    def language(self):
+        return "Japanese"
+
+    def feed(self, byte_str):
+        for i in range(len(byte_str)):
+            # PY3K: byte_str is a byte array, so byte_str[i] is an int, not a byte
+            coding_state = self.coding_sm.next_state(byte_str[i])
+            if coding_state == MachineState.ERROR:
+                self.logger.debug('%s %s prober hit error at byte %s',
+                                  self.charset_name, self.language, i)
+                self._state = ProbingState.NOT_ME
+                break
+            elif coding_state == MachineState.ITS_ME:
+                self._state = ProbingState.FOUND_IT
+                break
+            elif coding_state == MachineState.START:
+                char_len = self.coding_sm.get_current_charlen()
+                if i == 0:
+                    self._last_char[1] = byte_str[0]
+                    self.context_analyzer.feed(self._last_char, char_len)
+                    self.distribution_analyzer.feed(self._last_char, char_len)
+                else:
+                    self.context_analyzer.feed(byte_str[i - 1:i + 1],
+                                                char_len)
+                    self.distribution_analyzer.feed(byte_str[i - 1:i + 1],
+                                                     char_len)
+
+        self._last_char[0] = byte_str[-1]
+
+        if self.state == ProbingState.DETECTING:
+            if (self.context_analyzer.got_enough_data() and
+               (self.get_confidence() > self.SHORTCUT_THRESHOLD)):
+                self._state = ProbingState.FOUND_IT
+
+        return self.state
+
+    def get_confidence(self):
+        context_conf = self.context_analyzer.get_confidence()
+        distrib_conf = self.distribution_analyzer.get_confidence()
+        return max(context_conf, distrib_conf)

venv/lib/python3.7/site-packages/chardet/euckrprober.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 .mbcharsetprober import MultiByteCharSetProber
+from .codingstatemachine import CodingStateMachine
+from .chardistribution import EUCKRDistributionAnalysis
+from .mbcssm import EUCKR_SM_MODEL
+
+
+class EUCKRProber(MultiByteCharSetProber):
+    def __init__(self):
+        super(EUCKRProber, self).__init__()
+        self.coding_sm = CodingStateMachine(EUCKR_SM_MODEL)
+        self.distribution_analyzer = EUCKRDistributionAnalysis()
+        self.reset()
+
+    @property
+    def charset_name(self):
+        return "EUC-KR"
+
+    @property
+    def language(self):
+        return "Korean"

venv/lib/python3.7/site-packages/chardet/euctwprober.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 .mbcharsetprober import MultiByteCharSetProber
+from .codingstatemachine import CodingStateMachine
+from .chardistribution import EUCTWDistributionAnalysis
+from .mbcssm import EUCTW_SM_MODEL
+
+class EUCTWProber(MultiByteCharSetProber):
+    def __init__(self):
+        super(EUCTWProber, self).__init__()
+        self.coding_sm = CodingStateMachine(EUCTW_SM_MODEL)
+        self.distribution_analyzer = EUCTWDistributionAnalysis()
+        self.reset()
+
+    @property
+    def charset_name(self):
+        return "EUC-TW"
+
+    @property
+    def language(self):
+        return "Taiwan"