import urllib.parse


class PackageIndex:
    """Represents a Package Index and provides easier access to endpoints"""

    __slots__ = ["url", "netloc", "simple_url", "pypi_url", "file_storage_domain"]

    def __init__(self, url: str, file_storage_domain: str) -> None:
        super().__init__()
        self.url = url
        self.netloc = urllib.parse.urlsplit(url).netloc
        self.simple_url = self._url_for_path("simple")
        self.pypi_url = self._url_for_path("pypi")

        # This is part of a temporary hack used to block installs of PyPI
        # packages which depend on external urls only necessary until PyPI can
        # block such packages themselves
        self.file_storage_domain = file_storage_domain

    def _url_for_path(self, path: str) -> str:
        return urllib.parse.urljoin(self.url, path)


PyPI = PackageIndex("https://pypi.org/", file_storage_domain="files.pythonhosted.org")
TestPyPI = PackageIndex(
    "https://test.pypi.org/", file_storage_domain="test-files.pythonhosted.org"
)

"""
requests.exceptions
~~~~~~~~~~~~~~~~~~~

This module contains the set of Requests' exceptions.
"""
from pip._vendor.urllib3.exceptions import HTTPError as BaseHTTPError

from .compat import JSONDecodeError as CompatJSONDecodeError


class RequestException(IOError):
    """There was an ambiguous exception that occurred while handling your
    request.
    """

    def __init__(self, *args, **kwargs):
        """Initialize RequestException with `request` and `response` objects."""
        response = kwargs.pop("response", None)
        self.response = response
        self.request = kwargs.pop("request", None)
        if response is not None and not self.request and hasattr(response, "request"):
            self.request = self.response.request
        super().__init__(*args, **kwargs)


class InvalidJSONError(RequestException):
    """A JSON error occurred."""


class JSONDecodeError(InvalidJSONError, CompatJSONDecodeError):
    """Couldn't decode the text into json"""

    def __init__(self, *args, **kwargs):
        """
        Construct the JSONDecodeError instance first with all
        args. Then use it's args to construct the IOError so that
        the json specific args aren't used as IOError specific args
        and the error message from JSONDecodeError is preserved.
        """
        CompatJSONDecodeError.__init__(self, *args)
        InvalidJSONError.__init__(self, *self.args, **kwargs)

    def __reduce__(self):
        """
        The __reduce__ method called when pickling the object must
        be the one from the JSONDecodeError (be it json/simplejson)
        as it expects all the arguments for instantiation, not just
        one like the IOError, and the MRO would by default call the
        __reduce__ method from the IOError due to the inheritance order.
        """
        return CompatJSONDecodeError.__reduce__(self)


class HTTPError(RequestException):
    """An HTTP error occurred."""


class ConnectionError(RequestException):
    """A Connection error occurred."""


class ProxyError(ConnectionError):
    """A proxy error occurred."""


class SSLError(ConnectionError):
    """An SSL error occurred."""


class Timeout(RequestException):
    """The request timed out.

    Catching this error will catch both
    :exc:`~requests.exceptions.ConnectTimeout` and
    :exc:`~requests.exceptions.ReadTimeout` errors.
    """


class ConnectTimeout(ConnectionError, Timeout):
    """The request timed out while trying to connect to the remote server.

    Requests that produced this error are safe to retry.
    """


class ReadTimeout(Timeout):
    """The server did not send any data in the allotted amount of time."""


class URLRequired(RequestException):
    """A valid URL is required to make a request."""


class TooManyRedirects(RequestException):
    """Too many redirects."""


class MissingSchema(RequestException, ValueError):
    """The URL scheme (e.g. http or https) is missing."""


class InvalidSchema(RequestException, ValueError):
    """The URL scheme provided is either invalid or unsupported."""


class InvalidURL(RequestException, ValueError):
    """The URL provided was somehow invalid."""


class InvalidHeader(RequestException, ValueError):
    """The header value provided was somehow invalid."""


class InvalidProxyURL(InvalidURL):
    """The proxy URL provided is invalid."""


class ChunkedEncodingError(RequestException):
    """The server declared chunked encoding but sent an invalid chunk."""


class ContentDecodingError(RequestException, BaseHTTPError):
    """Failed to decode response content."""


class StreamConsumedError(RequestException, TypeError):
    """The content for this response was already consumed."""


class RetryError(RequestException):
    """Custom retries logic failed"""


class UnrewindableBodyError(RequestException):
    """Requests encountered an error when trying to rewind a body."""


# Warnings


class RequestsWarning(Warning):
    """Base warning for Requests."""


class FileModeWarning(RequestsWarning, DeprecationWarning):
    """A file was opened in text mode, but Requests determined its binary length."""


class RequestsDependencyWarning(RequestsWarning):
    """An imported dependency doesn't match the expected version range."""

import collections
import logging
from dataclasses import dataclass
from typing import Generator, List, Optional, Sequence, Tuple

from pip._internal.utils.logging import indent_log

from .req_file import parse_requirements
from .req_install import InstallRequirement
from .req_set import RequirementSet

__all__ = [
    "RequirementSet",
    "InstallRequirement",
    "parse_requirements",
    "install_given_reqs",
]

logger = logging.getLogger(__name__)


@dataclass(frozen=True)
class InstallationResult:
    name: str


def _validate_requirements(
    requirements: List[InstallRequirement],
) -> Generator[Tuple[str, InstallRequirement], None, None]:
    for req in requirements:
        assert req.name, f"invalid to-be-installed requirement: {req}"
        yield req.name, req


def install_given_reqs(
    requirements: List[InstallRequirement],
    global_options: Sequence[str],
    root: Optional[str],
    home: Optional[str],
    prefix: Optional[str],
    warn_script_location: bool,
    use_user_site: bool,
    pycompile: bool,
) -> List[InstallationResult]:
    """
    Install everything in the given list.

    (to be called after having downloaded and unpacked the packages)
    """
    to_install = collections.OrderedDict(_validate_requirements(requirements))

    if to_install:
        logger.info(
            "Installing collected packages: %s",
            ", ".join(to_install.keys()),
        )

    installed = []

    with indent_log():
        for req_name, requirement in to_install.items():
            if requirement.should_reinstall:
                logger.info("Attempting uninstall: %s", req_name)
                with indent_log():
                    uninstalled_pathset = requirement.uninstall(auto_confirm=True)
            else:
                uninstalled_pathset = None

            try:
                requirement.install(
                    global_options,
                    root=root,
                    home=home,
                    prefix=prefix,
                    warn_script_location=warn_script_location,
                    use_user_site=use_user_site,
                    pycompile=pycompile,
                )
            except Exception:
                # if install did not succeed, rollback previous uninstall
                if uninstalled_pathset and not requirement.install_succeeded:
                    uninstalled_pathset.rollback()
                raise
            else:
                if uninstalled_pathset and requirement.install_succeeded:
                    uninstalled_pathset.commit()

            installed.append(InstallationResult(req_name))

    return installed

# 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.

__title__ = "packaging"
__summary__ = "Core utilities for Python packages"
__uri__ = "https://github.com/pypa/packaging"

__version__ = "24.1"

__author__ = "Donald Stufft and individual contributors"
__email__ = "donald@stufft.io"

__license__ = "BSD-2-Clause or Apache-2.0"
__copyright__ = "2014 %s" % __author__

from typing import Iterable, Tuple, TypeVar

T = TypeVar("T")


def loop_first(values: Iterable[T]) -> Iterable[Tuple[bool, T]]:
    """Iterate and generate a tuple with a flag for first value."""
    iter_values = iter(values)
    try:
        value = next(iter_values)
    except StopIteration:
        return
    yield True, value
    for value in iter_values:
        yield False, value


def loop_last(values: Iterable[T]) -> Iterable[Tuple[bool, T]]:
    """Iterate and generate a tuple with a flag for last value."""
    iter_values = iter(values)
    try:
        previous_value = next(iter_values)
    except StopIteration:
        return
    for value in iter_values:
        yield False, previous_value
        previous_value = value
    yield True, previous_value


def loop_first_last(values: Iterable[T]) -> Iterable[Tuple[bool, bool, T]]:
    """Iterate and generate a tuple with a flag for first and last value."""
    iter_values = iter(values)
    try:
        previous_value = next(iter_values)
    except StopIteration:
        return
    first = True
    for value in iter_values:
        yield first, False, previous_value
        first = False
        previous_value = value
    yield first, True, previous_value

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)