help@rskworld.in +91 93305 39277
RSK World
  • Home
  • Development
    • Web Development
    • Mobile Apps
    • Software
    • Games
    • Project
  • Technologies
    • Data Science
    • AI Development
    • Cloud Development
    • Blockchain
    • Cyber Security
    • Dev Tools
    • Testing Tools
  • Blog
  • About
  • Contact

Theme Settings

Color Scheme
Display Options
Font Size
100%
Back to Project
RSK World
travel-assistant-bot
/
.venv
/
Lib
/
site-packages
/
pip
/
_internal
/
commands
RSK World
travel-assistant-bot
Travel Assistant Bot - Python + Flask + OpenAI API + Travel Bot + Flight Search + Hotel Booking + Weather
commands
  • __pycache__
  • __init__.py3.8 KB
  • cache.py7.8 KB
  • check.py2.2 KB
  • completion.py4.2 KB
  • configuration.py9.5 KB
  • debug.py6.6 KB
  • download.py5.1 KB
  • freeze.py3.1 KB
  • hash.py1.7 KB
  • help.py1.1 KB
  • index.py4.6 KB
  • inspect.py3.1 KB
  • install.py28.7 KB
  • list.py12.5 KB
  • search.py5.5 KB
  • show.py7.3 KB
  • uninstall.py3.8 KB
  • wheel.py6.3 KB
console.pyutil.py_stack.pysources.py__init__.py__init__.py_structures.pyregexopt.pysearch_scope.pyheuristics.pyutils.py
.venv/Lib/site-packages/pip/_vendor/pygments/console.py
Raw Download
Find: Go to:
"""
    pygments.console
    ~~~~~~~~~~~~~~~~

    Format colored console output.

    :copyright: Copyright 2006-2024 by the Pygments team, see AUTHORS.
    :license: BSD, see LICENSE for details.
"""

esc = "\x1b["

codes = {}
codes[""] = ""
codes["reset"] = esc + "39;49;00m"

codes["bold"] = esc + "01m"
codes["faint"] = esc + "02m"
codes["standout"] = esc + "03m"
codes["underline"] = esc + "04m"
codes["blink"] = esc + "05m"
codes["overline"] = esc + "06m"

dark_colors = ["black", "red", "green", "yellow", "blue",
               "magenta", "cyan", "gray"]
light_colors = ["brightblack", "brightred", "brightgreen", "brightyellow", "brightblue",
                "brightmagenta", "brightcyan", "white"]

x = 30
for dark, light in zip(dark_colors, light_colors):
    codes[dark] = esc + "%im" % x
    codes[light] = esc + "%im" % (60 + x)
    x += 1

del dark, light, x

codes["white"] = codes["bold"]


def reset_color():
    return codes["reset"]


def colorize(color_key, text):
    return codes[color_key] + text + codes["reset"]


def ansiformat(attr, text):
    """
    Format ``text`` with a color and/or some attributes::

        color       normal color
        *color*     bold color
        _color_     underlined color
        +color+     blinking color
    """
    result = []
    if attr[:1] == attr[-1:] == '+':
        result.append(codes['blink'])
        attr = attr[1:-1]
    if attr[:1] == attr[-1:] == '*':
        result.append(codes['bold'])
        attr = attr[1:-1]
    if attr[:1] == attr[-1:] == '_':
        result.append(codes['underline'])
        attr = attr[1:-1]
    result.append(codes[attr])
    result.append(text)
    result.append(codes['reset'])
    return ''.join(result)
71 lines•1.7 KB
python
.venv/Lib/site-packages/pip/_vendor/pygments/util.py
Raw Download
Find: Go to:
"""
    pygments.util
    ~~~~~~~~~~~~~

    Utility functions.

    :copyright: Copyright 2006-2024 by the Pygments team, see AUTHORS.
    :license: BSD, see LICENSE for details.
"""

import re
from io import TextIOWrapper


split_path_re = re.compile(r'[/\\ ]')
doctype_lookup_re = re.compile(r'''
    <!DOCTYPE\s+(
     [a-zA-Z_][a-zA-Z0-9]*
     (?: \s+      # optional in HTML5
     [a-zA-Z_][a-zA-Z0-9]*\s+
     "[^"]*")?
     )
     [^>]*>
''', re.DOTALL | re.MULTILINE | re.VERBOSE)
tag_re = re.compile(r'<(.+?)(\s.*?)?>.*?</.+?>',
                    re.IGNORECASE | re.DOTALL | re.MULTILINE)
xml_decl_re = re.compile(r'\s*<\?xml[^>]*\?>', re.I)


class ClassNotFound(ValueError):
    """Raised if one of the lookup functions didn't find a matching class."""


class OptionError(Exception):
    """
    This exception will be raised by all option processing functions if
    the type or value of the argument is not correct.
    """

def get_choice_opt(options, optname, allowed, default=None, normcase=False):
    """
    If the key `optname` from the dictionary is not in the sequence
    `allowed`, raise an error, otherwise return it.
    """
    string = options.get(optname, default)
    if normcase:
        string = string.lower()
    if string not in allowed:
        raise OptionError('Value for option {} must be one of {}'.format(optname, ', '.join(map(str, allowed))))
    return string


def get_bool_opt(options, optname, default=None):
    """
    Intuitively, this is `options.get(optname, default)`, but restricted to
    Boolean value. The Booleans can be represented as string, in order to accept
    Boolean value from the command line arguments. If the key `optname` is
    present in the dictionary `options` and is not associated with a Boolean,
    raise an `OptionError`. If it is absent, `default` is returned instead.

    The valid string values for ``True`` are ``1``, ``yes``, ``true`` and
    ``on``, the ones for ``False`` are ``0``, ``no``, ``false`` and ``off``
    (matched case-insensitively).
    """
    string = options.get(optname, default)
    if isinstance(string, bool):
        return string
    elif isinstance(string, int):
        return bool(string)
    elif not isinstance(string, str):
        raise OptionError(f'Invalid type {string!r} for option {optname}; use '
                          '1/0, yes/no, true/false, on/off')
    elif string.lower() in ('1', 'yes', 'true', 'on'):
        return True
    elif string.lower() in ('0', 'no', 'false', 'off'):
        return False
    else:
        raise OptionError(f'Invalid value {string!r} for option {optname}; use '
                          '1/0, yes/no, true/false, on/off')


def get_int_opt(options, optname, default=None):
    """As :func:`get_bool_opt`, but interpret the value as an integer."""
    string = options.get(optname, default)
    try:
        return int(string)
    except TypeError:
        raise OptionError(f'Invalid type {string!r} for option {optname}; you '
                          'must give an integer value')
    except ValueError:
        raise OptionError(f'Invalid value {string!r} for option {optname}; you '
                          'must give an integer value')

def get_list_opt(options, optname, default=None):
    """
    If the key `optname` from the dictionary `options` is a string,
    split it at whitespace and return it. If it is already a list
    or a tuple, it is returned as a list.
    """
    val = options.get(optname, default)
    if isinstance(val, str):
        return val.split()
    elif isinstance(val, (list, tuple)):
        return list(val)
    else:
        raise OptionError(f'Invalid type {val!r} for option {optname}; you '
                          'must give a list value')


def docstring_headline(obj):
    if not obj.__doc__:
        return ''
    res = []
    for line in obj.__doc__.strip().splitlines():
        if line.strip():
            res.append(" " + line.strip())
        else:
            break
    return ''.join(res).lstrip()


def make_analysator(f):
    """Return a static text analyser function that returns float values."""
    def text_analyse(text):
        try:
            rv = f(text)
        except Exception:
            return 0.0
        if not rv:
            return 0.0
        try:
            return min(1.0, max(0.0, float(rv)))
        except (ValueError, TypeError):
            return 0.0
    text_analyse.__doc__ = f.__doc__
    return staticmethod(text_analyse)


def shebang_matches(text, regex):
    r"""Check if the given regular expression matches the last part of the
    shebang if one exists.

        >>> from pygments.util import shebang_matches
        >>> shebang_matches('#!/usr/bin/env python', r'python(2\.\d)?')
        True
        >>> shebang_matches('#!/usr/bin/python2.4', r'python(2\.\d)?')
        True
        >>> shebang_matches('#!/usr/bin/python-ruby', r'python(2\.\d)?')
        False
        >>> shebang_matches('#!/usr/bin/python/ruby', r'python(2\.\d)?')
        False
        >>> shebang_matches('#!/usr/bin/startsomethingwith python',
        ...                 r'python(2\.\d)?')
        True

    It also checks for common windows executable file extensions::

        >>> shebang_matches('#!C:\\Python2.4\\Python.exe', r'python(2\.\d)?')
        True

    Parameters (``'-f'`` or ``'--foo'`` are ignored so ``'perl'`` does
    the same as ``'perl -e'``)

    Note that this method automatically searches the whole string (eg:
    the regular expression is wrapped in ``'^$'``)
    """
    index = text.find('\n')
    if index >= 0:
        first_line = text[:index].lower()
    else:
        first_line = text.lower()
    if first_line.startswith('#!'):
        try:
            found = [x for x in split_path_re.split(first_line[2:].strip())
                     if x and not x.startswith('-')][-1]
        except IndexError:
            return False
        regex = re.compile(rf'^{regex}(\.(exe|cmd|bat|bin))?$', re.IGNORECASE)
        if regex.search(found) is not None:
            return True
    return False


def doctype_matches(text, regex):
    """Check if the doctype matches a regular expression (if present).

    Note that this method only checks the first part of a DOCTYPE.
    eg: 'html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN"'
    """
    m = doctype_lookup_re.search(text)
    if m is None:
        return False
    doctype = m.group(1)
    return re.compile(regex, re.I).match(doctype.strip()) is not None


def html_doctype_matches(text):
    """Check if the file looks like it has a html doctype."""
    return doctype_matches(text, r'html')


_looks_like_xml_cache = {}


def looks_like_xml(text):
    """Check if a doctype exists or if we have some tags."""
    if xml_decl_re.match(text):
        return True
    key = hash(text)
    try:
        return _looks_like_xml_cache[key]
    except KeyError:
        m = doctype_lookup_re.search(text)
        if m is not None:
            return True
        rv = tag_re.search(text[:1000]) is not None
        _looks_like_xml_cache[key] = rv
        return rv


def surrogatepair(c):
    """Given a unicode character code with length greater than 16 bits,
    return the two 16 bit surrogate pair.
    """
    # From example D28 of:
    # http://www.unicode.org/book/ch03.pdf
    return (0xd7c0 + (c >> 10), (0xdc00 + (c & 0x3ff)))


def format_lines(var_name, seq, raw=False, indent_level=0):
    """Formats a sequence of strings for output."""
    lines = []
    base_indent = ' ' * indent_level * 4
    inner_indent = ' ' * (indent_level + 1) * 4
    lines.append(base_indent + var_name + ' = (')
    if raw:
        # These should be preformatted reprs of, say, tuples.
        for i in seq:
            lines.append(inner_indent + i + ',')
    else:
        for i in seq:
            # Force use of single quotes
            r = repr(i + '"')
            lines.append(inner_indent + r[:-2] + r[-1] + ',')
    lines.append(base_indent + ')')
    return '\n'.join(lines)


def duplicates_removed(it, already_seen=()):
    """
    Returns a list with duplicates removed from the iterable `it`.

    Order is preserved.
    """
    lst = []
    seen = set()
    for i in it:
        if i in seen or i in already_seen:
            continue
        lst.append(i)
        seen.add(i)
    return lst


class Future:
    """Generic class to defer some work.

    Handled specially in RegexLexerMeta, to support regex string construction at
    first use.
    """
    def get(self):
        raise NotImplementedError


def guess_decode(text):
    """Decode *text* with guessed encoding.

    First try UTF-8; this should fail for non-UTF-8 encodings.
    Then try the preferred locale encoding.
    Fall back to latin-1, which always works.
    """
    try:
        text = text.decode('utf-8')
        return text, 'utf-8'
    except UnicodeDecodeError:
        try:
            import locale
            prefencoding = locale.getpreferredencoding()
            text = text.decode()
            return text, prefencoding
        except (UnicodeDecodeError, LookupError):
            text = text.decode('latin1')
            return text, 'latin1'


def guess_decode_from_terminal(text, term):
    """Decode *text* coming from terminal *term*.

    First try the terminal encoding, if given.
    Then try UTF-8.  Then try the preferred locale encoding.
    Fall back to latin-1, which always works.
    """
    if getattr(term, 'encoding', None):
        try:
            text = text.decode(term.encoding)
        except UnicodeDecodeError:
            pass
        else:
            return text, term.encoding
    return guess_decode(text)


def terminal_encoding(term):
    """Return our best guess of encoding for the given *term*."""
    if getattr(term, 'encoding', None):
        return term.encoding
    import locale
    return locale.getpreferredencoding()


class UnclosingTextIOWrapper(TextIOWrapper):
    # Don't close underlying buffer on destruction.
    def close(self):
        self.flush()
325 lines•9.8 KB
python
.venv/Lib/site-packages/pip/_vendor/rich/_stack.py
Raw Download
Find: Go to:
from typing import List, TypeVar

T = TypeVar("T")


class Stack(List[T]):
    """A small shim over builtin list."""

    @property
    def top(self) -> T:
        """Get top of stack."""
        return self[-1]

    def push(self, item: T) -> None:
        """Push an item on to the stack (append in stack nomenclature)."""
        self.append(item)
17 lines•351 B
python
.venv/Lib/site-packages/pip/_internal/index/sources.py
Raw Download
Find: Go to:
import logging
import mimetypes
import os
from collections import defaultdict
from typing import Callable, Dict, Iterable, List, Optional, Tuple

from pip._vendor.packaging.utils import (
    InvalidSdistFilename,
    InvalidWheelFilename,
    canonicalize_name,
    parse_sdist_filename,
    parse_wheel_filename,
)

from pip._internal.models.candidate import InstallationCandidate
from pip._internal.models.link import Link
from pip._internal.utils.urls import path_to_url, url_to_path
from pip._internal.vcs import is_url

logger = logging.getLogger(__name__)

FoundCandidates = Iterable[InstallationCandidate]
FoundLinks = Iterable[Link]
CandidatesFromPage = Callable[[Link], Iterable[InstallationCandidate]]
PageValidator = Callable[[Link], bool]


class LinkSource:
    @property
    def link(self) -> Optional[Link]:
        """Returns the underlying link, if there's one."""
        raise NotImplementedError()

    def page_candidates(self) -> FoundCandidates:
        """Candidates found by parsing an archive listing HTML file."""
        raise NotImplementedError()

    def file_links(self) -> FoundLinks:
        """Links found by specifying archives directly."""
        raise NotImplementedError()


def _is_html_file(file_url: str) -> bool:
    return mimetypes.guess_type(file_url, strict=False)[0] == "text/html"


class _FlatDirectoryToUrls:
    """Scans directory and caches results"""

    def __init__(self, path: str) -> None:
        self._path = path
        self._page_candidates: List[str] = []
        self._project_name_to_urls: Dict[str, List[str]] = defaultdict(list)
        self._scanned_directory = False

    def _scan_directory(self) -> None:
        """Scans directory once and populates both page_candidates
        and project_name_to_urls at the same time
        """
        for entry in os.scandir(self._path):
            url = path_to_url(entry.path)
            if _is_html_file(url):
                self._page_candidates.append(url)
                continue

            # File must have a valid wheel or sdist name,
            # otherwise not worth considering as a package
            try:
                project_filename = parse_wheel_filename(entry.name)[0]
            except InvalidWheelFilename:
                try:
                    project_filename = parse_sdist_filename(entry.name)[0]
                except InvalidSdistFilename:
                    continue

            self._project_name_to_urls[project_filename].append(url)
        self._scanned_directory = True

    @property
    def page_candidates(self) -> List[str]:
        if not self._scanned_directory:
            self._scan_directory()

        return self._page_candidates

    @property
    def project_name_to_urls(self) -> Dict[str, List[str]]:
        if not self._scanned_directory:
            self._scan_directory()

        return self._project_name_to_urls


class _FlatDirectorySource(LinkSource):
    """Link source specified by ``--find-links=<path-to-dir>``.

    This looks the content of the directory, and returns:

    * ``page_candidates``: Links listed on each HTML file in the directory.
    * ``file_candidates``: Archives in the directory.
    """

    _paths_to_urls: Dict[str, _FlatDirectoryToUrls] = {}

    def __init__(
        self,
        candidates_from_page: CandidatesFromPage,
        path: str,
        project_name: str,
    ) -> None:
        self._candidates_from_page = candidates_from_page
        self._project_name = canonicalize_name(project_name)

        # Get existing instance of _FlatDirectoryToUrls if it exists
        if path in self._paths_to_urls:
            self._path_to_urls = self._paths_to_urls[path]
        else:
            self._path_to_urls = _FlatDirectoryToUrls(path=path)
            self._paths_to_urls[path] = self._path_to_urls

    @property
    def link(self) -> Optional[Link]:
        return None

    def page_candidates(self) -> FoundCandidates:
        for url in self._path_to_urls.page_candidates:
            yield from self._candidates_from_page(Link(url))

    def file_links(self) -> FoundLinks:
        for url in self._path_to_urls.project_name_to_urls[self._project_name]:
            yield Link(url)


class _LocalFileSource(LinkSource):
    """``--find-links=<path-or-url>`` or ``--[extra-]index-url=<path-or-url>``.

    If a URL is supplied, it must be a ``file:`` URL. If a path is supplied to
    the option, it is converted to a URL first. This returns:

    * ``page_candidates``: Links listed on an HTML file.
    * ``file_candidates``: The non-HTML file.
    """

    def __init__(
        self,
        candidates_from_page: CandidatesFromPage,
        link: Link,
    ) -> None:
        self._candidates_from_page = candidates_from_page
        self._link = link

    @property
    def link(self) -> Optional[Link]:
        return self._link

    def page_candidates(self) -> FoundCandidates:
        if not _is_html_file(self._link.url):
            return
        yield from self._candidates_from_page(self._link)

    def file_links(self) -> FoundLinks:
        if _is_html_file(self._link.url):
            return
        yield self._link


class _RemoteFileSource(LinkSource):
    """``--find-links=<url>`` or ``--[extra-]index-url=<url>``.

    This returns:

    * ``page_candidates``: Links listed on an HTML file.
    * ``file_candidates``: The non-HTML file.
    """

    def __init__(
        self,
        candidates_from_page: CandidatesFromPage,
        page_validator: PageValidator,
        link: Link,
    ) -> None:
        self._candidates_from_page = candidates_from_page
        self._page_validator = page_validator
        self._link = link

    @property
    def link(self) -> Optional[Link]:
        return self._link

    def page_candidates(self) -> FoundCandidates:
        if not self._page_validator(self._link):
            return
        yield from self._candidates_from_page(self._link)

    def file_links(self) -> FoundLinks:
        yield self._link


class _IndexDirectorySource(LinkSource):
    """``--[extra-]index-url=<path-to-directory>``.

    This is treated like a remote URL; ``candidates_from_page`` contains logic
    for this by appending ``index.html`` to the link.
    """

    def __init__(
        self,
        candidates_from_page: CandidatesFromPage,
        link: Link,
    ) -> None:
        self._candidates_from_page = candidates_from_page
        self._link = link

    @property
    def link(self) -> Optional[Link]:
        return self._link

    def page_candidates(self) -> FoundCandidates:
        yield from self._candidates_from_page(self._link)

    def file_links(self) -> FoundLinks:
        return ()


def build_source(
    location: str,
    *,
    candidates_from_page: CandidatesFromPage,
    page_validator: PageValidator,
    expand_dir: bool,
    cache_link_parsing: bool,
    project_name: str,
) -> Tuple[Optional[str], Optional[LinkSource]]:
    path: Optional[str] = None
    url: Optional[str] = None
    if os.path.exists(location):  # Is a local path.
        url = path_to_url(location)
        path = location
    elif location.startswith("file:"):  # A file: URL.
        url = location
        path = url_to_path(location)
    elif is_url(location):
        url = location

    if url is None:
        msg = (
            "Location '%s' is ignored: "
            "it is either a non-existing path or lacks a specific scheme."
        )
        logger.warning(msg, location)
        return (None, None)

    if path is None:
        source: LinkSource = _RemoteFileSource(
            candidates_from_page=candidates_from_page,
            page_validator=page_validator,
            link=Link(url, cache_link_parsing=cache_link_parsing),
        )
        return (url, source)

    if os.path.isdir(path):
        if expand_dir:
            source = _FlatDirectorySource(
                candidates_from_page=candidates_from_page,
                path=path,
                project_name=project_name,
            )
        else:
            source = _IndexDirectorySource(
                candidates_from_page=candidates_from_page,
                link=Link(url, cache_link_parsing=cache_link_parsing),
            )
        return (url, source)
    elif os.path.isfile(path):
        source = _LocalFileSource(
            candidates_from_page=candidates_from_page,
            link=Link(url, cache_link_parsing=cache_link_parsing),
        )
        return (url, source)
    logger.warning(
        "Location '%s' is ignored: it is neither a file nor a directory.",
        location,
    )
    return (url, None)
285 lines•8.4 KB
python
.venv/Lib/site-packages/pip/_internal/operations/__init__.py
Raw Download
Find: Go to:
1 lines•0 B
python
.venv/Lib/site-packages/pip/_internal/locations/__init__.py
Raw Download
Find: Go to:
import functools
import logging
import os
import pathlib
import sys
import sysconfig
from typing import Any, Dict, Generator, Optional, Tuple

from pip._internal.models.scheme import SCHEME_KEYS, Scheme
from pip._internal.utils.compat import WINDOWS
from pip._internal.utils.deprecation import deprecated
from pip._internal.utils.virtualenv import running_under_virtualenv

from . import _sysconfig
from .base import (
    USER_CACHE_DIR,
    get_major_minor_version,
    get_src_prefix,
    is_osx_framework,
    site_packages,
    user_site,
)

__all__ = [
    "USER_CACHE_DIR",
    "get_bin_prefix",
    "get_bin_user",
    "get_major_minor_version",
    "get_platlib",
    "get_purelib",
    "get_scheme",
    "get_src_prefix",
    "site_packages",
    "user_site",
]


logger = logging.getLogger(__name__)


_PLATLIBDIR: str = getattr(sys, "platlibdir", "lib")

_USE_SYSCONFIG_DEFAULT = sys.version_info >= (3, 10)


def _should_use_sysconfig() -> bool:
    """This function determines the value of _USE_SYSCONFIG.

    By default, pip uses sysconfig on Python 3.10+.
    But Python distributors can override this decision by setting:
        sysconfig._PIP_USE_SYSCONFIG = True / False
    Rationale in https://github.com/pypa/pip/issues/10647

    This is a function for testability, but should be constant during any one
    run.
    """
    return bool(getattr(sysconfig, "_PIP_USE_SYSCONFIG", _USE_SYSCONFIG_DEFAULT))


_USE_SYSCONFIG = _should_use_sysconfig()

if not _USE_SYSCONFIG:
    # Import distutils lazily to avoid deprecation warnings,
    # but import it soon enough that it is in memory and available during
    # a pip reinstall.
    from . import _distutils

# Be noisy about incompatibilities if this platforms "should" be using
# sysconfig, but is explicitly opting out and using distutils instead.
if _USE_SYSCONFIG_DEFAULT and not _USE_SYSCONFIG:
    _MISMATCH_LEVEL = logging.WARNING
else:
    _MISMATCH_LEVEL = logging.DEBUG


def _looks_like_bpo_44860() -> bool:
    """The resolution to bpo-44860 will change this incorrect platlib.

    See <https://bugs.python.org/issue44860>.
    """
    from distutils.command.install import INSTALL_SCHEMES

    try:
        unix_user_platlib = INSTALL_SCHEMES["unix_user"]["platlib"]
    except KeyError:
        return False
    return unix_user_platlib == "$usersite"


def _looks_like_red_hat_patched_platlib_purelib(scheme: Dict[str, str]) -> bool:
    platlib = scheme["platlib"]
    if "/$platlibdir/" in platlib:
        platlib = platlib.replace("/$platlibdir/", f"/{_PLATLIBDIR}/")
    if "/lib64/" not in platlib:
        return False
    unpatched = platlib.replace("/lib64/", "/lib/")
    return unpatched.replace("$platbase/", "$base/") == scheme["purelib"]


@functools.lru_cache(maxsize=None)
def _looks_like_red_hat_lib() -> bool:
    """Red Hat patches platlib in unix_prefix and unix_home, but not purelib.

    This is the only way I can see to tell a Red Hat-patched Python.
    """
    from distutils.command.install import INSTALL_SCHEMES

    return all(
        k in INSTALL_SCHEMES
        and _looks_like_red_hat_patched_platlib_purelib(INSTALL_SCHEMES[k])
        for k in ("unix_prefix", "unix_home")
    )


@functools.lru_cache(maxsize=None)
def _looks_like_debian_scheme() -> bool:
    """Debian adds two additional schemes."""
    from distutils.command.install import INSTALL_SCHEMES

    return "deb_system" in INSTALL_SCHEMES and "unix_local" in INSTALL_SCHEMES


@functools.lru_cache(maxsize=None)
def _looks_like_red_hat_scheme() -> bool:
    """Red Hat patches ``sys.prefix`` and ``sys.exec_prefix``.

    Red Hat's ``00251-change-user-install-location.patch`` changes the install
    command's ``prefix`` and ``exec_prefix`` to append ``"/local"``. This is
    (fortunately?) done quite unconditionally, so we create a default command
    object without any configuration to detect this.
    """
    from distutils.command.install import install
    from distutils.dist import Distribution

    cmd: Any = install(Distribution())
    cmd.finalize_options()
    return (
        cmd.exec_prefix == f"{os.path.normpath(sys.exec_prefix)}/local"
        and cmd.prefix == f"{os.path.normpath(sys.prefix)}/local"
    )


@functools.lru_cache(maxsize=None)
def _looks_like_slackware_scheme() -> bool:
    """Slackware patches sysconfig but fails to patch distutils and site.

    Slackware changes sysconfig's user scheme to use ``"lib64"`` for the lib
    path, but does not do the same to the site module.
    """
    if user_site is None:  # User-site not available.
        return False
    try:
        paths = sysconfig.get_paths(scheme="posix_user", expand=False)
    except KeyError:  # User-site not available.
        return False
    return "/lib64/" in paths["purelib"] and "/lib64/" not in user_site


@functools.lru_cache(maxsize=None)
def _looks_like_msys2_mingw_scheme() -> bool:
    """MSYS2 patches distutils and sysconfig to use a UNIX-like scheme.

    However, MSYS2 incorrectly patches sysconfig ``nt`` scheme. The fix is
    likely going to be included in their 3.10 release, so we ignore the warning.
    See msys2/MINGW-packages#9319.

    MSYS2 MINGW's patch uses lowercase ``"lib"`` instead of the usual uppercase,
    and is missing the final ``"site-packages"``.
    """
    paths = sysconfig.get_paths("nt", expand=False)
    return all(
        "Lib" not in p and "lib" in p and not p.endswith("site-packages")
        for p in (paths[key] for key in ("platlib", "purelib"))
    )


def _fix_abiflags(parts: Tuple[str]) -> Generator[str, None, None]:
    ldversion = sysconfig.get_config_var("LDVERSION")
    abiflags = getattr(sys, "abiflags", None)

    # LDVERSION does not end with sys.abiflags. Just return the path unchanged.
    if not ldversion or not abiflags or not ldversion.endswith(abiflags):
        yield from parts
        return

    # Strip sys.abiflags from LDVERSION-based path components.
    for part in parts:
        if part.endswith(ldversion):
            part = part[: (0 - len(abiflags))]
        yield part


@functools.lru_cache(maxsize=None)
def _warn_mismatched(old: pathlib.Path, new: pathlib.Path, *, key: str) -> None:
    issue_url = "https://github.com/pypa/pip/issues/10151"
    message = (
        "Value for %s does not match. Please report this to <%s>"
        "\ndistutils: %s"
        "\nsysconfig: %s"
    )
    logger.log(_MISMATCH_LEVEL, message, key, issue_url, old, new)


def _warn_if_mismatch(old: pathlib.Path, new: pathlib.Path, *, key: str) -> bool:
    if old == new:
        return False
    _warn_mismatched(old, new, key=key)
    return True


@functools.lru_cache(maxsize=None)
def _log_context(
    *,
    user: bool = False,
    home: Optional[str] = None,
    root: Optional[str] = None,
    prefix: Optional[str] = None,
) -> None:
    parts = [
        "Additional context:",
        "user = %r",
        "home = %r",
        "root = %r",
        "prefix = %r",
    ]

    logger.log(_MISMATCH_LEVEL, "\n".join(parts), user, home, root, prefix)


def get_scheme(
    dist_name: str,
    user: bool = False,
    home: Optional[str] = None,
    root: Optional[str] = None,
    isolated: bool = False,
    prefix: Optional[str] = None,
) -> Scheme:
    new = _sysconfig.get_scheme(
        dist_name,
        user=user,
        home=home,
        root=root,
        isolated=isolated,
        prefix=prefix,
    )
    if _USE_SYSCONFIG:
        return new

    old = _distutils.get_scheme(
        dist_name,
        user=user,
        home=home,
        root=root,
        isolated=isolated,
        prefix=prefix,
    )

    warning_contexts = []
    for k in SCHEME_KEYS:
        old_v = pathlib.Path(getattr(old, k))
        new_v = pathlib.Path(getattr(new, k))

        if old_v == new_v:
            continue

        # distutils incorrectly put PyPy packages under ``site-packages/python``
        # in the ``posix_home`` scheme, but PyPy devs said they expect the
        # directory name to be ``pypy`` instead. So we treat this as a bug fix
        # and not warn about it. See bpo-43307 and python/cpython#24628.
        skip_pypy_special_case = (
            sys.implementation.name == "pypy"
            and home is not None
            and k in ("platlib", "purelib")
            and old_v.parent == new_v.parent
            and old_v.name.startswith("python")
            and new_v.name.startswith("pypy")
        )
        if skip_pypy_special_case:
            continue

        # sysconfig's ``osx_framework_user`` does not include ``pythonX.Y`` in
        # the ``include`` value, but distutils's ``headers`` does. We'll let
        # CPython decide whether this is a bug or feature. See bpo-43948.
        skip_osx_framework_user_special_case = (
            user
            and is_osx_framework()
            and k == "headers"
            and old_v.parent.parent == new_v.parent
            and old_v.parent.name.startswith("python")
        )
        if skip_osx_framework_user_special_case:
            continue

        # On Red Hat and derived Linux distributions, distutils is patched to
        # use "lib64" instead of "lib" for platlib.
        if k == "platlib" and _looks_like_red_hat_lib():
            continue

        # On Python 3.9+, sysconfig's posix_user scheme sets platlib against
        # sys.platlibdir, but distutils's unix_user incorrectly coninutes
        # using the same $usersite for both platlib and purelib. This creates a
        # mismatch when sys.platlibdir is not "lib".
        skip_bpo_44860 = (
            user
            and k == "platlib"
            and not WINDOWS
            and sys.version_info >= (3, 9)
            and _PLATLIBDIR != "lib"
            and _looks_like_bpo_44860()
        )
        if skip_bpo_44860:
            continue

        # Slackware incorrectly patches posix_user to use lib64 instead of lib,
        # but not usersite to match the location.
        skip_slackware_user_scheme = (
            user
            and k in ("platlib", "purelib")
            and not WINDOWS
            and _looks_like_slackware_scheme()
        )
        if skip_slackware_user_scheme:
            continue

        # Both Debian and Red Hat patch Python to place the system site under
        # /usr/local instead of /usr. Debian also places lib in dist-packages
        # instead of site-packages, but the /usr/local check should cover it.
        skip_linux_system_special_case = (
            not (user or home or prefix or running_under_virtualenv())
            and old_v.parts[1:3] == ("usr", "local")
            and len(new_v.parts) > 1
            and new_v.parts[1] == "usr"
            and (len(new_v.parts) < 3 or new_v.parts[2] != "local")
            and (_looks_like_red_hat_scheme() or _looks_like_debian_scheme())
        )
        if skip_linux_system_special_case:
            continue

        # MSYS2 MINGW's sysconfig patch does not include the "site-packages"
        # part of the path. This is incorrect and will be fixed in MSYS.
        skip_msys2_mingw_bug = (
            WINDOWS and k in ("platlib", "purelib") and _looks_like_msys2_mingw_scheme()
        )
        if skip_msys2_mingw_bug:
            continue

        # CPython's POSIX install script invokes pip (via ensurepip) against the
        # interpreter located in the source tree, not the install site. This
        # triggers special logic in sysconfig that's not present in distutils.
        # https://github.com/python/cpython/blob/8c21941ddaf/Lib/sysconfig.py#L178-L194
        skip_cpython_build = (
            sysconfig.is_python_build(check_home=True)
            and not WINDOWS
            and k in ("headers", "include", "platinclude")
        )
        if skip_cpython_build:
            continue

        warning_contexts.append((old_v, new_v, f"scheme.{k}"))

    if not warning_contexts:
        return old

    # Check if this path mismatch is caused by distutils config files. Those
    # files will no longer work once we switch to sysconfig, so this raises a
    # deprecation message for them.
    default_old = _distutils.distutils_scheme(
        dist_name,
        user,
        home,
        root,
        isolated,
        prefix,
        ignore_config_files=True,
    )
    if any(default_old[k] != getattr(old, k) for k in SCHEME_KEYS):
        deprecated(
            reason=(
                "Configuring installation scheme with distutils config files "
                "is deprecated and will no longer work in the near future. If you "
                "are using a Homebrew or Linuxbrew Python, please see discussion "
                "at https://github.com/Homebrew/homebrew-core/issues/76621"
            ),
            replacement=None,
            gone_in=None,
        )
        return old

    # Post warnings about this mismatch so user can report them back.
    for old_v, new_v, key in warning_contexts:
        _warn_mismatched(old_v, new_v, key=key)
    _log_context(user=user, home=home, root=root, prefix=prefix)

    return old


def get_bin_prefix() -> str:
    new = _sysconfig.get_bin_prefix()
    if _USE_SYSCONFIG:
        return new

    old = _distutils.get_bin_prefix()
    if _warn_if_mismatch(pathlib.Path(old), pathlib.Path(new), key="bin_prefix"):
        _log_context()
    return old


def get_bin_user() -> str:
    return _sysconfig.get_scheme("", user=True).scripts


def _looks_like_deb_system_dist_packages(value: str) -> bool:
    """Check if the value is Debian's APT-controlled dist-packages.

    Debian's ``distutils.sysconfig.get_python_lib()`` implementation returns the
    default package path controlled by APT, but does not patch ``sysconfig`` to
    do the same. This is similar to the bug worked around in ``get_scheme()``,
    but here the default is ``deb_system`` instead of ``unix_local``. Ultimately
    we can't do anything about this Debian bug, and this detection allows us to
    skip the warning when needed.
    """
    if not _looks_like_debian_scheme():
        return False
    if value == "/usr/lib/python3/dist-packages":
        return True
    return False


def get_purelib() -> str:
    """Return the default pure-Python lib location."""
    new = _sysconfig.get_purelib()
    if _USE_SYSCONFIG:
        return new

    old = _distutils.get_purelib()
    if _looks_like_deb_system_dist_packages(old):
        return old
    if _warn_if_mismatch(pathlib.Path(old), pathlib.Path(new), key="purelib"):
        _log_context()
    return old


def get_platlib() -> str:
    """Return the default platform-shared lib location."""
    new = _sysconfig.get_platlib()
    if _USE_SYSCONFIG:
        return new

    from . import _distutils

    old = _distutils.get_platlib()
    if _looks_like_deb_system_dist_packages(old):
        return old
    if _warn_if_mismatch(pathlib.Path(old), pathlib.Path(new), key="platlib"):
        _log_context()
    return old
457 lines•14.6 KB
python
.venv/Lib/site-packages/pip/_vendor/packaging/_structures.py
Raw Download
Find: Go to:
# This file is dual licensed under the terms of the Apache License, Version
# 2.0, and the BSD License. See the LICENSE file in the root of this repository
# for complete details.


class InfinityType:
    def __repr__(self) -> str:
        return "Infinity"

    def __hash__(self) -> int:
        return hash(repr(self))

    def __lt__(self, other: object) -> bool:
        return False

    def __le__(self, other: object) -> bool:
        return False

    def __eq__(self, other: object) -> bool:
        return isinstance(other, self.__class__)

    def __gt__(self, other: object) -> bool:
        return True

    def __ge__(self, other: object) -> bool:
        return True

    def __neg__(self: object) -> "NegativeInfinityType":
        return NegativeInfinity


Infinity = InfinityType()


class NegativeInfinityType:
    def __repr__(self) -> str:
        return "-Infinity"

    def __hash__(self) -> int:
        return hash(repr(self))

    def __lt__(self, other: object) -> bool:
        return True

    def __le__(self, other: object) -> bool:
        return True

    def __eq__(self, other: object) -> bool:
        return isinstance(other, self.__class__)

    def __gt__(self, other: object) -> bool:
        return False

    def __ge__(self, other: object) -> bool:
        return False

    def __neg__(self: object) -> InfinityType:
        return Infinity


NegativeInfinity = NegativeInfinityType()
62 lines•1.4 KB
python
.venv/Lib/site-packages/pip/_vendor/pygments/regexopt.py
Raw Download
Find: Go to:
"""
    pygments.regexopt
    ~~~~~~~~~~~~~~~~~

    An algorithm that generates optimized regexes for matching long lists of
    literal strings.

    :copyright: Copyright 2006-2024 by the Pygments team, see AUTHORS.
    :license: BSD, see LICENSE for details.
"""

import re
from re import escape
from os.path import commonprefix
from itertools import groupby
from operator import itemgetter

CS_ESCAPE = re.compile(r'[\[\^\\\-\]]')
FIRST_ELEMENT = itemgetter(0)


def make_charset(letters):
    return '[' + CS_ESCAPE.sub(lambda m: '\\' + m.group(), ''.join(letters)) + ']'


def regex_opt_inner(strings, open_paren):
    """Return a regex that matches any string in the sorted list of strings."""
    close_paren = open_paren and ')' or ''
    # print strings, repr(open_paren)
    if not strings:
        # print '-> nothing left'
        return ''
    first = strings[0]
    if len(strings) == 1:
        # print '-> only 1 string'
        return open_paren + escape(first) + close_paren
    if not first:
        # print '-> first string empty'
        return open_paren + regex_opt_inner(strings[1:], '(?:') \
            + '?' + close_paren
    if len(first) == 1:
        # multiple one-char strings? make a charset
        oneletter = []
        rest = []
        for s in strings:
            if len(s) == 1:
                oneletter.append(s)
            else:
                rest.append(s)
        if len(oneletter) > 1:  # do we have more than one oneletter string?
            if rest:
                # print '-> 1-character + rest'
                return open_paren + regex_opt_inner(rest, '') + '|' \
                    + make_charset(oneletter) + close_paren
            # print '-> only 1-character'
            return open_paren + make_charset(oneletter) + close_paren
    prefix = commonprefix(strings)
    if prefix:
        plen = len(prefix)
        # we have a prefix for all strings
        # print '-> prefix:', prefix
        return open_paren + escape(prefix) \
            + regex_opt_inner([s[plen:] for s in strings], '(?:') \
            + close_paren
    # is there a suffix?
    strings_rev = [s[::-1] for s in strings]
    suffix = commonprefix(strings_rev)
    if suffix:
        slen = len(suffix)
        # print '-> suffix:', suffix[::-1]
        return open_paren \
            + regex_opt_inner(sorted(s[:-slen] for s in strings), '(?:') \
            + escape(suffix[::-1]) + close_paren
    # recurse on common 1-string prefixes
    # print '-> last resort'
    return open_paren + \
        '|'.join(regex_opt_inner(list(group[1]), '')
                 for group in groupby(strings, lambda s: s[0] == first[0])) \
        + close_paren


def regex_opt(strings, prefix='', suffix=''):
    """Return a compiled regex that matches any string in the given list.

    The strings to match must be literal strings, not regexes.  They will be
    regex-escaped.

    *prefix* and *suffix* are pre- and appended to the final regex.
    """
    strings = sorted(strings)
    return prefix + regex_opt_inner(strings, '(') + suffix
92 lines•3 KB
python
.venv/Lib/site-packages/pip/_internal/models/search_scope.py
Raw Download
Find: Go to:
import itertools
import logging
import os
import posixpath
import urllib.parse
from dataclasses import dataclass
from typing import List

from pip._vendor.packaging.utils import canonicalize_name

from pip._internal.models.index import PyPI
from pip._internal.utils.compat import has_tls
from pip._internal.utils.misc import normalize_path, redact_auth_from_url

logger = logging.getLogger(__name__)


@dataclass(frozen=True)
class SearchScope:
    """
    Encapsulates the locations that pip is configured to search.
    """

    __slots__ = ["find_links", "index_urls", "no_index"]

    find_links: List[str]
    index_urls: List[str]
    no_index: bool

    @classmethod
    def create(
        cls,
        find_links: List[str],
        index_urls: List[str],
        no_index: bool,
    ) -> "SearchScope":
        """
        Create a SearchScope object after normalizing the `find_links`.
        """
        # Build find_links. If an argument starts with ~, it may be
        # a local file relative to a home directory. So try normalizing
        # it and if it exists, use the normalized version.
        # This is deliberately conservative - it might be fine just to
        # blindly normalize anything starting with a ~...
        built_find_links: List[str] = []
        for link in find_links:
            if link.startswith("~"):
                new_link = normalize_path(link)
                if os.path.exists(new_link):
                    link = new_link
            built_find_links.append(link)

        # If we don't have TLS enabled, then WARN if anyplace we're looking
        # relies on TLS.
        if not has_tls():
            for link in itertools.chain(index_urls, built_find_links):
                parsed = urllib.parse.urlparse(link)
                if parsed.scheme == "https":
                    logger.warning(
                        "pip is configured with locations that require "
                        "TLS/SSL, however the ssl module in Python is not "
                        "available."
                    )
                    break

        return cls(
            find_links=built_find_links,
            index_urls=index_urls,
            no_index=no_index,
        )

    def get_formatted_locations(self) -> str:
        lines = []
        redacted_index_urls = []
        if self.index_urls and self.index_urls != [PyPI.simple_url]:
            for url in self.index_urls:
                redacted_index_url = redact_auth_from_url(url)

                # Parse the URL
                purl = urllib.parse.urlsplit(redacted_index_url)

                # URL is generally invalid if scheme and netloc is missing
                # there are issues with Python and URL parsing, so this test
                # is a bit crude. See bpo-20271, bpo-23505. Python doesn't
                # always parse invalid URLs correctly - it should raise
                # exceptions for malformed URLs
                if not purl.scheme and not purl.netloc:
                    logger.warning(
                        'The index url "%s" seems invalid, please provide a scheme.',
                        redacted_index_url,
                    )

                redacted_index_urls.append(redacted_index_url)

            lines.append(
                "Looking in indexes: {}".format(", ".join(redacted_index_urls))
            )

        if self.find_links:
            lines.append(
                "Looking in links: {}".format(
                    ", ".join(redact_auth_from_url(url) for url in self.find_links)
                )
            )
        return "\n".join(lines)

    def get_index_urls_locations(self, project_name: str) -> List[str]:
        """Returns the locations found via self.index_urls

        Checks the url_name on the main (first in the list) index and
        use this url_name to produce all locations
        """

        def mkurl_pypi_url(url: str) -> str:
            loc = posixpath.join(
                url, urllib.parse.quote(canonicalize_name(project_name))
            )
            # For maximum compatibility with easy_install, ensure the path
            # ends in a trailing slash.  Although this isn't in the spec
            # (and PyPI can handle it without the slash) some other index
            # implementations might break if they relied on easy_install's
            # behavior.
            if not loc.endswith("/"):
                loc = loc + "/"
            return loc

        return [mkurl_pypi_url(url) for url in self.index_urls]
128 lines•4.4 KB
python
.venv/Lib/site-packages/pip/_vendor/cachecontrol/heuristics.py
Raw Download
Find: Go to:
# SPDX-FileCopyrightText: 2015 Eric Larson
#
# SPDX-License-Identifier: Apache-2.0
from __future__ import annotations

import calendar
import time
from datetime import datetime, timedelta, timezone
from email.utils import formatdate, parsedate, parsedate_tz
from typing import TYPE_CHECKING, Any, Mapping

if TYPE_CHECKING:
    from pip._vendor.urllib3 import HTTPResponse

TIME_FMT = "%a, %d %b %Y %H:%M:%S GMT"


def expire_after(delta: timedelta, date: datetime | None = None) -> datetime:
    date = date or datetime.now(timezone.utc)
    return date + delta


def datetime_to_header(dt: datetime) -> str:
    return formatdate(calendar.timegm(dt.timetuple()))


class BaseHeuristic:
    def warning(self, response: HTTPResponse) -> str | None:
        """
        Return a valid 1xx warning header value describing the cache
        adjustments.

        The response is provided too allow warnings like 113
        http://tools.ietf.org/html/rfc7234#section-5.5.4 where we need
        to explicitly say response is over 24 hours old.
        """
        return '110 - "Response is Stale"'

    def update_headers(self, response: HTTPResponse) -> dict[str, str]:
        """Update the response headers with any new headers.

        NOTE: This SHOULD always include some Warning header to
              signify that the response was cached by the client, not
              by way of the provided headers.
        """
        return {}

    def apply(self, response: HTTPResponse) -> HTTPResponse:
        updated_headers = self.update_headers(response)

        if updated_headers:
            response.headers.update(updated_headers)
            warning_header_value = self.warning(response)
            if warning_header_value is not None:
                response.headers.update({"Warning": warning_header_value})

        return response


class OneDayCache(BaseHeuristic):
    """
    Cache the response by providing an expires 1 day in the
    future.
    """

    def update_headers(self, response: HTTPResponse) -> dict[str, str]:
        headers = {}

        if "expires" not in response.headers:
            date = parsedate(response.headers["date"])
            expires = expire_after(timedelta(days=1), date=datetime(*date[:6], tzinfo=timezone.utc))  # type: ignore[index,misc]
            headers["expires"] = datetime_to_header(expires)
            headers["cache-control"] = "public"
        return headers


class ExpiresAfter(BaseHeuristic):
    """
    Cache **all** requests for a defined time period.
    """

    def __init__(self, **kw: Any) -> None:
        self.delta = timedelta(**kw)

    def update_headers(self, response: HTTPResponse) -> dict[str, str]:
        expires = expire_after(self.delta)
        return {"expires": datetime_to_header(expires), "cache-control": "public"}

    def warning(self, response: HTTPResponse) -> str | None:
        tmpl = "110 - Automatically cached for %s. Response might be stale"
        return tmpl % self.delta


class LastModified(BaseHeuristic):
    """
    If there is no Expires header already, fall back on Last-Modified
    using the heuristic from
    http://tools.ietf.org/html/rfc7234#section-4.2.2
    to calculate a reasonable value.

    Firefox also does something like this per
    https://developer.mozilla.org/en-US/docs/Web/HTTP/Caching_FAQ
    http://lxr.mozilla.org/mozilla-release/source/netwerk/protocol/http/nsHttpResponseHead.cpp#397
    Unlike mozilla we limit this to 24-hr.
    """

    cacheable_by_default_statuses = {
        200,
        203,
        204,
        206,
        300,
        301,
        404,
        405,
        410,
        414,
        501,
    }

    def update_headers(self, resp: HTTPResponse) -> dict[str, str]:
        headers: Mapping[str, str] = resp.headers

        if "expires" in headers:
            return {}

        if "cache-control" in headers and headers["cache-control"] != "public":
            return {}

        if resp.status not in self.cacheable_by_default_statuses:
            return {}

        if "date" not in headers or "last-modified" not in headers:
            return {}

        time_tuple = parsedate_tz(headers["date"])
        assert time_tuple is not None
        date = calendar.timegm(time_tuple[:6])
        last_modified = parsedate(headers["last-modified"])
        if last_modified is None:
            return {}

        now = time.time()
        current_age = max(0, now - date)
        delta = date - calendar.timegm(last_modified)
        freshness_lifetime = max(0, min(delta / 10, 24 * 3600))
        if freshness_lifetime <= current_age:
            return {}

        expires = date + freshness_lifetime
        return {"expires": time.strftime(TIME_FMT, time.gmtime(expires))}

    def warning(self, resp: HTTPResponse) -> str | None:
        return None
155 lines•4.7 KB
python
.venv/Lib/site-packages/pip/_vendor/requests/utils.py
Raw Download
Find: Go to:
"""
requests.utils
~~~~~~~~~~~~~~

This module provides utility functions that are used within Requests
that are also useful for external consumption.
"""

import codecs
import contextlib
import io
import os
import re
import socket
import struct
import sys
import tempfile
import warnings
import zipfile
from collections import OrderedDict

from pip._vendor.urllib3.util import make_headers, parse_url

from . import certs
from .__version__ import __version__

# to_native_string is unused here, but imported here for backwards compatibility
from ._internal_utils import (  # noqa: F401
    _HEADER_VALIDATORS_BYTE,
    _HEADER_VALIDATORS_STR,
    HEADER_VALIDATORS,
    to_native_string,
)
from .compat import (
    Mapping,
    basestring,
    bytes,
    getproxies,
    getproxies_environment,
    integer_types,
)
from .compat import parse_http_list as _parse_list_header
from .compat import (
    proxy_bypass,
    proxy_bypass_environment,
    quote,
    str,
    unquote,
    urlparse,
    urlunparse,
)
from .cookies import cookiejar_from_dict
from .exceptions import (
    FileModeWarning,
    InvalidHeader,
    InvalidURL,
    UnrewindableBodyError,
)
from .structures import CaseInsensitiveDict

NETRC_FILES = (".netrc", "_netrc")

DEFAULT_CA_BUNDLE_PATH = certs.where()

DEFAULT_PORTS = {"http": 80, "https": 443}

# Ensure that ', ' is used to preserve previous delimiter behavior.
DEFAULT_ACCEPT_ENCODING = ", ".join(
    re.split(r",\s*", make_headers(accept_encoding=True)["accept-encoding"])
)


if sys.platform == "win32":
    # provide a proxy_bypass version on Windows without DNS lookups

    def proxy_bypass_registry(host):
        try:
            import winreg
        except ImportError:
            return False

        try:
            internetSettings = winreg.OpenKey(
                winreg.HKEY_CURRENT_USER,
                r"Software\Microsoft\Windows\CurrentVersion\Internet Settings",
            )
            # ProxyEnable could be REG_SZ or REG_DWORD, normalizing it
            proxyEnable = int(winreg.QueryValueEx(internetSettings, "ProxyEnable")[0])
            # ProxyOverride is almost always a string
            proxyOverride = winreg.QueryValueEx(internetSettings, "ProxyOverride")[0]
        except (OSError, ValueError):
            return False
        if not proxyEnable or not proxyOverride:
            return False

        # make a check value list from the registry entry: replace the
        # '<local>' string by the localhost entry and the corresponding
        # canonical entry.
        proxyOverride = proxyOverride.split(";")
        # filter out empty strings to avoid re.match return true in the following code.
        proxyOverride = filter(None, proxyOverride)
        # now check if we match one of the registry values.
        for test in proxyOverride:
            if test == "<local>":
                if "." not in host:
                    return True
            test = test.replace(".", r"\.")  # mask dots
            test = test.replace("*", r".*")  # change glob sequence
            test = test.replace("?", r".")  # change glob char
            if re.match(test, host, re.I):
                return True
        return False

    def proxy_bypass(host):  # noqa
        """Return True, if the host should be bypassed.

        Checks proxy settings gathered from the environment, if specified,
        or the registry.
        """
        if getproxies_environment():
            return proxy_bypass_environment(host)
        else:
            return proxy_bypass_registry(host)


def dict_to_sequence(d):
    """Returns an internal sequence dictionary update."""

    if hasattr(d, "items"):
        d = d.items()

    return d


def super_len(o):
    total_length = None
    current_position = 0

    if isinstance(o, str):
        o = o.encode("utf-8")

    if hasattr(o, "__len__"):
        total_length = len(o)

    elif hasattr(o, "len"):
        total_length = o.len

    elif hasattr(o, "fileno"):
        try:
            fileno = o.fileno()
        except (io.UnsupportedOperation, AttributeError):
            # AttributeError is a surprising exception, seeing as how we've just checked
            # that `hasattr(o, 'fileno')`.  It happens for objects obtained via
            # `Tarfile.extractfile()`, per issue 5229.
            pass
        else:
            total_length = os.fstat(fileno).st_size

            # Having used fstat to determine the file length, we need to
            # confirm that this file was opened up in binary mode.
            if "b" not in o.mode:
                warnings.warn(
                    (
                        "Requests has determined the content-length for this "
                        "request using the binary size of the file: however, the "
                        "file has been opened in text mode (i.e. without the 'b' "
                        "flag in the mode). This may lead to an incorrect "
                        "content-length. In Requests 3.0, support will be removed "
                        "for files in text mode."
                    ),
                    FileModeWarning,
                )

    if hasattr(o, "tell"):
        try:
            current_position = o.tell()
        except OSError:
            # This can happen in some weird situations, such as when the file
            # is actually a special file descriptor like stdin. In this
            # instance, we don't know what the length is, so set it to zero and
            # let requests chunk it instead.
            if total_length is not None:
                current_position = total_length
        else:
            if hasattr(o, "seek") and total_length is None:
                # StringIO and BytesIO have seek but no usable fileno
                try:
                    # seek to end of file
                    o.seek(0, 2)
                    total_length = o.tell()

                    # seek back to current position to support
                    # partially read file-like objects
                    o.seek(current_position or 0)
                except OSError:
                    total_length = 0

    if total_length is None:
        total_length = 0

    return max(0, total_length - current_position)


def get_netrc_auth(url, raise_errors=False):
    """Returns the Requests tuple auth for a given url from netrc."""

    netrc_file = os.environ.get("NETRC")
    if netrc_file is not None:
        netrc_locations = (netrc_file,)
    else:
        netrc_locations = (f"~/{f}" for f in NETRC_FILES)

    try:
        from netrc import NetrcParseError, netrc

        netrc_path = None

        for f in netrc_locations:
            try:
                loc = os.path.expanduser(f)
            except KeyError:
                # os.path.expanduser can fail when $HOME is undefined and
                # getpwuid fails. See https://bugs.python.org/issue20164 &
                # https://github.com/psf/requests/issues/1846
                return

            if os.path.exists(loc):
                netrc_path = loc
                break

        # Abort early if there isn't one.
        if netrc_path is None:
            return

        ri = urlparse(url)

        # Strip port numbers from netloc. This weird `if...encode`` dance is
        # used for Python 3.2, which doesn't support unicode literals.
        splitstr = b":"
        if isinstance(url, str):
            splitstr = splitstr.decode("ascii")
        host = ri.netloc.split(splitstr)[0]

        try:
            _netrc = netrc(netrc_path).authenticators(host)
            if _netrc:
                # Return with login / password
                login_i = 0 if _netrc[0] else 1
                return (_netrc[login_i], _netrc[2])
        except (NetrcParseError, OSError):
            # If there was a parsing error or a permissions issue reading the file,
            # we'll just skip netrc auth unless explicitly asked to raise errors.
            if raise_errors:
                raise

    # App Engine hackiness.
    except (ImportError, AttributeError):
        pass


def guess_filename(obj):
    """Tries to guess the filename of the given object."""
    name = getattr(obj, "name", None)
    if name and isinstance(name, basestring) and name[0] != "<" and name[-1] != ">":
        return os.path.basename(name)


def extract_zipped_paths(path):
    """Replace nonexistent paths that look like they refer to a member of a zip
    archive with the location of an extracted copy of the target, or else
    just return the provided path unchanged.
    """
    if os.path.exists(path):
        # this is already a valid path, no need to do anything further
        return path

    # find the first valid part of the provided path and treat that as a zip archive
    # assume the rest of the path is the name of a member in the archive
    archive, member = os.path.split(path)
    while archive and not os.path.exists(archive):
        archive, prefix = os.path.split(archive)
        if not prefix:
            # If we don't check for an empty prefix after the split (in other words, archive remains unchanged after the split),
            # we _can_ end up in an infinite loop on a rare corner case affecting a small number of users
            break
        member = "/".join([prefix, member])

    if not zipfile.is_zipfile(archive):
        return path

    zip_file = zipfile.ZipFile(archive)
    if member not in zip_file.namelist():
        return path

    # we have a valid zip archive and a valid member of that archive
    tmp = tempfile.gettempdir()
    extracted_path = os.path.join(tmp, member.split("/")[-1])
    if not os.path.exists(extracted_path):
        # use read + write to avoid the creating nested folders, we only want the file, avoids mkdir racing condition
        with atomic_open(extracted_path) as file_handler:
            file_handler.write(zip_file.read(member))
    return extracted_path


@contextlib.contextmanager
def atomic_open(filename):
    """Write a file to the disk in an atomic fashion"""
    tmp_descriptor, tmp_name = tempfile.mkstemp(dir=os.path.dirname(filename))
    try:
        with os.fdopen(tmp_descriptor, "wb") as tmp_handler:
            yield tmp_handler
        os.replace(tmp_name, filename)
    except BaseException:
        os.remove(tmp_name)
        raise


def from_key_val_list(value):
    """Take an object and test to see if it can be represented as a
    dictionary. Unless it can not be represented as such, return an
    OrderedDict, e.g.,

    ::

        >>> from_key_val_list([('key', 'val')])
        OrderedDict([('key', 'val')])
        >>> from_key_val_list('string')
        Traceback (most recent call last):
        ...
        ValueError: cannot encode objects that are not 2-tuples
        >>> from_key_val_list({'key': 'val'})
        OrderedDict([('key', 'val')])

    :rtype: OrderedDict
    """
    if value is None:
        return None

    if isinstance(value, (str, bytes, bool, int)):
        raise ValueError("cannot encode objects that are not 2-tuples")

    return OrderedDict(value)


def to_key_val_list(value):
    """Take an object and test to see if it can be represented as a
    dictionary. If it can be, return a list of tuples, e.g.,

    ::

        >>> to_key_val_list([('key', 'val')])
        [('key', 'val')]
        >>> to_key_val_list({'key': 'val'})
        [('key', 'val')]
        >>> to_key_val_list('string')
        Traceback (most recent call last):
        ...
        ValueError: cannot encode objects that are not 2-tuples

    :rtype: list
    """
    if value is None:
        return None

    if isinstance(value, (str, bytes, bool, int)):
        raise ValueError("cannot encode objects that are not 2-tuples")

    if isinstance(value, Mapping):
        value = value.items()

    return list(value)


# From mitsuhiko/werkzeug (used with permission).
def parse_list_header(value):
    """Parse lists as described by RFC 2068 Section 2.

    In particular, parse comma-separated lists where the elements of
    the list may include quoted-strings.  A quoted-string could
    contain a comma.  A non-quoted string could have quotes in the
    middle.  Quotes are removed automatically after parsing.

    It basically works like :func:`parse_set_header` just that items
    may appear multiple times and case sensitivity is preserved.

    The return value is a standard :class:`list`:

    >>> parse_list_header('token, "quoted value"')
    ['token', 'quoted value']

    To create a header from the :class:`list` again, use the
    :func:`dump_header` function.

    :param value: a string with a list header.
    :return: :class:`list`
    :rtype: list
    """
    result = []
    for item in _parse_list_header(value):
        if item[:1] == item[-1:] == '"':
            item = unquote_header_value(item[1:-1])
        result.append(item)
    return result


# From mitsuhiko/werkzeug (used with permission).
def parse_dict_header(value):
    """Parse lists of key, value pairs as described by RFC 2068 Section 2 and
    convert them into a python dict:

    >>> d = parse_dict_header('foo="is a fish", bar="as well"')
    >>> type(d) is dict
    True
    >>> sorted(d.items())
    [('bar', 'as well'), ('foo', 'is a fish')]

    If there is no value for a key it will be `None`:

    >>> parse_dict_header('key_without_value')
    {'key_without_value': None}

    To create a header from the :class:`dict` again, use the
    :func:`dump_header` function.

    :param value: a string with a dict header.
    :return: :class:`dict`
    :rtype: dict
    """
    result = {}
    for item in _parse_list_header(value):
        if "=" not in item:
            result[item] = None
            continue
        name, value = item.split("=", 1)
        if value[:1] == value[-1:] == '"':
            value = unquote_header_value(value[1:-1])
        result[name] = value
    return result


# From mitsuhiko/werkzeug (used with permission).
def unquote_header_value(value, is_filename=False):
    r"""Unquotes a header value.  (Reversal of :func:`quote_header_value`).
    This does not use the real unquoting but what browsers are actually
    using for quoting.

    :param value: the header value to unquote.
    :rtype: str
    """
    if value and value[0] == value[-1] == '"':
        # this is not the real unquoting, but fixing this so that the
        # RFC is met will result in bugs with internet explorer and
        # probably some other browsers as well.  IE for example is
        # uploading files with "C:\foo\bar.txt" as filename
        value = value[1:-1]

        # if this is a filename and the starting characters look like
        # a UNC path, then just return the value without quotes.  Using the
        # replace sequence below on a UNC path has the effect of turning
        # the leading double slash into a single slash and then
        # _fix_ie_filename() doesn't work correctly.  See #458.
        if not is_filename or value[:2] != "\\\\":
            return value.replace("\\\\", "\\").replace('\\"', '"')
    return value


def dict_from_cookiejar(cj):
    """Returns a key/value dictionary from a CookieJar.

    :param cj: CookieJar object to extract cookies from.
    :rtype: dict
    """

    cookie_dict = {cookie.name: cookie.value for cookie in cj}
    return cookie_dict


def add_dict_to_cookiejar(cj, cookie_dict):
    """Returns a CookieJar from a key/value dictionary.

    :param cj: CookieJar to insert cookies into.
    :param cookie_dict: Dict of key/values to insert into CookieJar.
    :rtype: CookieJar
    """

    return cookiejar_from_dict(cookie_dict, cj)


def get_encodings_from_content(content):
    """Returns encodings from given content string.

    :param content: bytestring to extract encodings from.
    """
    warnings.warn(
        (
            "In requests 3.0, get_encodings_from_content will be removed. For "
            "more information, please see the discussion on issue #2266. (This"
            " warning should only appear once.)"
        ),
        DeprecationWarning,
    )

    charset_re = re.compile(r'<meta.*?charset=["\']*(.+?)["\'>]', flags=re.I)
    pragma_re = re.compile(r'<meta.*?content=["\']*;?charset=(.+?)["\'>]', flags=re.I)
    xml_re = re.compile(r'^<\?xml.*?encoding=["\']*(.+?)["\'>]')

    return (
        charset_re.findall(content)
        + pragma_re.findall(content)
        + xml_re.findall(content)
    )


def _parse_content_type_header(header):
    """Returns content type and parameters from given header

    :param header: string
    :return: tuple containing content type and dictionary of
         parameters
    """

    tokens = header.split(";")
    content_type, params = tokens[0].strip(), tokens[1:]
    params_dict = {}
    items_to_strip = "\"' "

    for param in params:
        param = param.strip()
        if param:
            key, value = param, True
            index_of_equals = param.find("=")
            if index_of_equals != -1:
                key = param[:index_of_equals].strip(items_to_strip)
                value = param[index_of_equals + 1 :].strip(items_to_strip)
            params_dict[key.lower()] = value
    return content_type, params_dict


def get_encoding_from_headers(headers):
    """Returns encodings from given HTTP Header Dict.

    :param headers: dictionary to extract encoding from.
    :rtype: str
    """

    content_type = headers.get("content-type")

    if not content_type:
        return None

    content_type, params = _parse_content_type_header(content_type)

    if "charset" in params:
        return params["charset"].strip("'\"")

    if "text" in content_type:
        return "ISO-8859-1"

    if "application/json" in content_type:
        # Assume UTF-8 based on RFC 4627: https://www.ietf.org/rfc/rfc4627.txt since the charset was unset
        return "utf-8"


def stream_decode_response_unicode(iterator, r):
    """Stream decodes an iterator."""

    if r.encoding is None:
        yield from iterator
        return

    decoder = codecs.getincrementaldecoder(r.encoding)(errors="replace")
    for chunk in iterator:
        rv = decoder.decode(chunk)
        if rv:
            yield rv
    rv = decoder.decode(b"", final=True)
    if rv:
        yield rv


def iter_slices(string, slice_length):
    """Iterate over slices of a string."""
    pos = 0
    if slice_length is None or slice_length <= 0:
        slice_length = len(string)
    while pos < len(string):
        yield string[pos : pos + slice_length]
        pos += slice_length


def get_unicode_from_response(r):
    """Returns the requested content back in unicode.

    :param r: Response object to get unicode content from.

    Tried:

    1. charset from content-type
    2. fall back and replace all unicode characters

    :rtype: str
    """
    warnings.warn(
        (
            "In requests 3.0, get_unicode_from_response will be removed. For "
            "more information, please see the discussion on issue #2266. (This"
            " warning should only appear once.)"
        ),
        DeprecationWarning,
    )

    tried_encodings = []

    # Try charset from content-type
    encoding = get_encoding_from_headers(r.headers)

    if encoding:
        try:
            return str(r.content, encoding)
        except UnicodeError:
            tried_encodings.append(encoding)

    # Fall back:
    try:
        return str(r.content, encoding, errors="replace")
    except TypeError:
        return r.content


# The unreserved URI characters (RFC 3986)
UNRESERVED_SET = frozenset(
    "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz" + "0123456789-._~"
)


def unquote_unreserved(uri):
    """Un-escape any percent-escape sequences in a URI that are unreserved
    characters. This leaves all reserved, illegal and non-ASCII bytes encoded.

    :rtype: str
    """
    parts = uri.split("%")
    for i in range(1, len(parts)):
        h = parts[i][0:2]
        if len(h) == 2 and h.isalnum():
            try:
                c = chr(int(h, 16))
            except ValueError:
                raise InvalidURL(f"Invalid percent-escape sequence: '{h}'")

            if c in UNRESERVED_SET:
                parts[i] = c + parts[i][2:]
            else:
                parts[i] = f"%{parts[i]}"
        else:
            parts[i] = f"%{parts[i]}"
    return "".join(parts)


def requote_uri(uri):
    """Re-quote the given URI.

    This function passes the given URI through an unquote/quote cycle to
    ensure that it is fully and consistently quoted.

    :rtype: str
    """
    safe_with_percent = "!#$%&'()*+,/:;=?@[]~"
    safe_without_percent = "!#$&'()*+,/:;=?@[]~"
    try:
        # Unquote only the unreserved characters
        # Then quote only illegal characters (do not quote reserved,
        # unreserved, or '%')
        return quote(unquote_unreserved(uri), safe=safe_with_percent)
    except InvalidURL:
        # We couldn't unquote the given URI, so let's try quoting it, but
        # there may be unquoted '%'s in the URI. We need to make sure they're
        # properly quoted so they do not cause issues elsewhere.
        return quote(uri, safe=safe_without_percent)


def address_in_network(ip, net):
    """This function allows you to check if an IP belongs to a network subnet

    Example: returns True if ip = 192.168.1.1 and net = 192.168.1.0/24
             returns False if ip = 192.168.1.1 and net = 192.168.100.0/24

    :rtype: bool
    """
    ipaddr = struct.unpack("=L", socket.inet_aton(ip))[0]
    netaddr, bits = net.split("/")
    netmask = struct.unpack("=L", socket.inet_aton(dotted_netmask(int(bits))))[0]
    network = struct.unpack("=L", socket.inet_aton(netaddr))[0] & netmask
    return (ipaddr & netmask) == (network & netmask)


def dotted_netmask(mask):
    """Converts mask from /xx format to xxx.xxx.xxx.xxx

    Example: if mask is 24 function returns 255.255.255.0

    :rtype: str
    """
    bits = 0xFFFFFFFF ^ (1 << 32 - mask) - 1
    return socket.inet_ntoa(struct.pack(">I", bits))


def is_ipv4_address(string_ip):
    """
    :rtype: bool
    """
    try:
        socket.inet_aton(string_ip)
    except OSError:
        return False
    return True


def is_valid_cidr(string_network):
    """
    Very simple check of the cidr format in no_proxy variable.

    :rtype: bool
    """
    if string_network.count("/") == 1:
        try:
            mask = int(string_network.split("/")[1])
        except ValueError:
            return False

        if mask < 1 or mask > 32:
            return False

        try:
            socket.inet_aton(string_network.split("/")[0])
        except OSError:
            return False
    else:
        return False
    return True


@contextlib.contextmanager
def set_environ(env_name, value):
    """Set the environment variable 'env_name' to 'value'

    Save previous value, yield, and then restore the previous value stored in
    the environment variable 'env_name'.

    If 'value' is None, do nothing"""
    value_changed = value is not None
    if value_changed:
        old_value = os.environ.get(env_name)
        os.environ[env_name] = value
    try:
        yield
    finally:
        if value_changed:
            if old_value is None:
                del os.environ[env_name]
            else:
                os.environ[env_name] = old_value


def should_bypass_proxies(url, no_proxy):
    """
    Returns whether we should bypass proxies or not.

    :rtype: bool
    """

    # Prioritize lowercase environment variables over uppercase
    # to keep a consistent behaviour with other http projects (curl, wget).
    def get_proxy(key):
        return os.environ.get(key) or os.environ.get(key.upper())

    # First check whether no_proxy is defined. If it is, check that the URL
    # we're getting isn't in the no_proxy list.
    no_proxy_arg = no_proxy
    if no_proxy is None:
        no_proxy = get_proxy("no_proxy")
    parsed = urlparse(url)

    if parsed.hostname is None:
        # URLs don't always have hostnames, e.g. file:/// urls.
        return True

    if no_proxy:
        # We need to check whether we match here. We need to see if we match
        # the end of the hostname, both with and without the port.
        no_proxy = (host for host in no_proxy.replace(" ", "").split(",") if host)

        if is_ipv4_address(parsed.hostname):
            for proxy_ip in no_proxy:
                if is_valid_cidr(proxy_ip):
                    if address_in_network(parsed.hostname, proxy_ip):
                        return True
                elif parsed.hostname == proxy_ip:
                    # If no_proxy ip was defined in plain IP notation instead of cidr notation &
                    # matches the IP of the index
                    return True
        else:
            host_with_port = parsed.hostname
            if parsed.port:
                host_with_port += f":{parsed.port}"

            for host in no_proxy:
                if parsed.hostname.endswith(host) or host_with_port.endswith(host):
                    # The URL does match something in no_proxy, so we don't want
                    # to apply the proxies on this URL.
                    return True

    with set_environ("no_proxy", no_proxy_arg):
        # parsed.hostname can be `None` in cases such as a file URI.
        try:
            bypass = proxy_bypass(parsed.hostname)
        except (TypeError, socket.gaierror):
            bypass = False

    if bypass:
        return True

    return False


def get_environ_proxies(url, no_proxy=None):
    """
    Return a dict of environment proxies.

    :rtype: dict
    """
    if should_bypass_proxies(url, no_proxy=no_proxy):
        return {}
    else:
        return getproxies()


def select_proxy(url, proxies):
    """Select a proxy for the url, if applicable.

    :param url: The url being for the request
    :param proxies: A dictionary of schemes or schemes and hosts to proxy URLs
    """
    proxies = proxies or {}
    urlparts = urlparse(url)
    if urlparts.hostname is None:
        return proxies.get(urlparts.scheme, proxies.get("all"))

    proxy_keys = [
        urlparts.scheme + "://" + urlparts.hostname,
        urlparts.scheme,
        "all://" + urlparts.hostname,
        "all",
    ]
    proxy = None
    for proxy_key in proxy_keys:
        if proxy_key in proxies:
            proxy = proxies[proxy_key]
            break

    return proxy


def resolve_proxies(request, proxies, trust_env=True):
    """This method takes proxy information from a request and configuration
    input to resolve a mapping of target proxies. This will consider settings
    such as NO_PROXY to strip proxy configurations.

    :param request: Request or PreparedRequest
    :param proxies: A dictionary of schemes or schemes and hosts to proxy URLs
    :param trust_env: Boolean declaring whether to trust environment configs

    :rtype: dict
    """
    proxies = proxies if proxies is not None else {}
    url = request.url
    scheme = urlparse(url).scheme
    no_proxy = proxies.get("no_proxy")
    new_proxies = proxies.copy()

    if trust_env and not should_bypass_proxies(url, no_proxy=no_proxy):
        environ_proxies = get_environ_proxies(url, no_proxy=no_proxy)

        proxy = environ_proxies.get(scheme, environ_proxies.get("all"))

        if proxy:
            new_proxies.setdefault(scheme, proxy)
    return new_proxies


def default_user_agent(name="python-requests"):
    """
    Return a string representing the default user agent.

    :rtype: str
    """
    return f"{name}/{__version__}"


def default_headers():
    """
    :rtype: requests.structures.CaseInsensitiveDict
    """
    return CaseInsensitiveDict(
        {
            "User-Agent": default_user_agent(),
            "Accept-Encoding": DEFAULT_ACCEPT_ENCODING,
            "Accept": "*/*",
            "Connection": "keep-alive",
        }
    )


def parse_header_links(value):
    """Return a list of parsed link headers proxies.

    i.e. Link: <http:/.../front.jpeg>; rel=front; type="image/jpeg",<http://.../back.jpeg>; rel=back;type="image/jpeg"

    :rtype: list
    """

    links = []

    replace_chars = " '\""

    value = value.strip(replace_chars)
    if not value:
        return links

    for val in re.split(", *<", value):
        try:
            url, params = val.split(";", 1)
        except ValueError:
            url, params = val, ""

        link = {"url": url.strip("<> '\"")}

        for param in params.split(";"):
            try:
                key, value = param.split("=")
            except ValueError:
                break

            link[key.strip(replace_chars)] = value.strip(replace_chars)

        links.append(link)

    return links


# Null bytes; no need to recreate these on each call to guess_json_utf
_null = "\x00".encode("ascii")  # encoding to ASCII for Python 3
_null2 = _null * 2
_null3 = _null * 3


def guess_json_utf(data):
    """
    :rtype: str
    """
    # JSON always starts with two ASCII characters, so detection is as
    # easy as counting the nulls and from their location and count
    # determine the encoding. Also detect a BOM, if present.
    sample = data[:4]
    if sample in (codecs.BOM_UTF32_LE, codecs.BOM_UTF32_BE):
        return "utf-32"  # BOM included
    if sample[:3] == codecs.BOM_UTF8:
        return "utf-8-sig"  # BOM included, MS style (discouraged)
    if sample[:2] in (codecs.BOM_UTF16_LE, codecs.BOM_UTF16_BE):
        return "utf-16"  # BOM included
    nullcount = sample.count(_null)
    if nullcount == 0:
        return "utf-8"
    if nullcount == 2:
        if sample[::2] == _null2:  # 1st and 3rd are null
            return "utf-16-be"
        if sample[1::2] == _null2:  # 2nd and 4th are null
            return "utf-16-le"
        # Did not detect 2 valid UTF-16 ascii-range characters
    if nullcount == 3:
        if sample[:3] == _null3:
            return "utf-32-be"
        if sample[1:] == _null3:
            return "utf-32-le"
        # Did not detect a valid UTF-32 ascii-range character
    return None


def prepend_scheme_if_needed(url, new_scheme):
    """Given a URL that may or may not have a scheme, prepend the given scheme.
    Does not replace a present scheme with the one provided as an argument.

    :rtype: str
    """
    parsed = parse_url(url)
    scheme, auth, host, port, path, query, fragment = parsed

    # A defect in urlparse determines that there isn't a netloc present in some
    # urls. We previously assumed parsing was overly cautious, and swapped the
    # netloc and path. Due to a lack of tests on the original defect, this is
    # maintained with parse_url for backwards compatibility.
    netloc = parsed.netloc
    if not netloc:
        netloc, path = path, netloc

    if auth:
        # parse_url doesn't provide the netloc with auth
        # so we'll add it ourselves.
        netloc = "@".join([auth, netloc])
    if scheme is None:
        scheme = new_scheme
    if path is None:
        path = ""

    return urlunparse((scheme, netloc, path, "", query, fragment))


def get_auth_from_url(url):
    """Given a url with authentication components, extract them into a tuple of
    username,password.

    :rtype: (str,str)
    """
    parsed = urlparse(url)

    try:
        auth = (unquote(parsed.username), unquote(parsed.password))
    except (AttributeError, TypeError):
        auth = ("", "")

    return auth


def check_header_validity(header):
    """Verifies that header parts don't contain leading whitespace
    reserved characters, or return characters.

    :param header: tuple, in the format (name, value).
    """
    name, value = header
    _validate_header_part(header, name, 0)
    _validate_header_part(header, value, 1)


def _validate_header_part(header, header_part, header_validator_index):
    if isinstance(header_part, str):
        validator = _HEADER_VALIDATORS_STR[header_validator_index]
    elif isinstance(header_part, bytes):
        validator = _HEADER_VALIDATORS_BYTE[header_validator_index]
    else:
        raise InvalidHeader(
            f"Header part ({header_part!r}) from {header} "
            f"must be of type str or bytes, not {type(header_part)}"
        )

    if not validator.match(header_part):
        header_kind = "name" if header_validator_index == 0 else "value"
        raise InvalidHeader(
            f"Invalid leading whitespace, reserved character(s), or return "
            f"character(s) in header {header_kind}: {header_part!r}"
        )


def urldefragauth(url):
    """
    Given a url remove the fragment and the authentication part.

    :rtype: str
    """
    scheme, netloc, path, params, query, fragment = urlparse(url)

    # see func:`prepend_scheme_if_needed`
    if not netloc:
        netloc, path = path, netloc

    netloc = netloc.rsplit("@", 1)[-1]

    return urlunparse((scheme, netloc, path, params, query, ""))


def rewind_body(prepared_request):
    """Move file pointer back to its recorded starting position
    so it can be read again on redirect.
    """
    body_seek = getattr(prepared_request.body, "seek", None)
    if body_seek is not None and isinstance(
        prepared_request._body_position, integer_types
    ):
        try:
            body_seek(prepared_request._body_position)
        except OSError:
            raise UnrewindableBodyError(
                "An error occurred when rewinding request body for redirect."
            )
    else:
        raise UnrewindableBodyError("Unable to rewind request body for redirect.")
1,097 lines•32.8 KB
python
🚀 Support RSK World

Subscribe to our YouTube channel for latest tutorials & updates!



Click subscribe & support our work ❤️

About RSK World

Founded by Molla Samser, with Designer & Tester Rima Khatun, RSK World is your one-stop destination for free programming resources, source code, and development tools.

Founder: Molla Samser
Designer & Tester: Rima Khatun

Development

  • Game Development
  • Web Development
  • Mobile Development
  • AI Development
  • Development Tools

Legal

  • Terms & Conditions
  • Privacy Policy
  • Disclaimer

Contact Info

Nutanhat, Mongolkote
Purba Burdwan, West Bengal
India, 713147

+91 93305 39277

hello@rskworld.in
support@rskworld.in

© 2026 RSK World. All rights reserved.

Content used for educational purposes only. View Disclaimer