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
/
_vendor
/
idna
RSK World
travel-assistant-bot
Travel Assistant Bot - Python + Flask + OpenAI API + Travel Bot + Flight Search + Hotel Booking + Weather
idna
  • __pycache__
  • __init__.py849 B
  • codec.py3.3 KB
  • compat.py321 B
  • core.py12.4 KB
  • idnadata.py76.5 KB
  • intranges.py1.8 KB
  • package_data.py21 B
  • py.typed0 B
  • uts46data.py201.7 KB
rule.pyhighlighter.pystatus_codes.pymanifest.pycore.py
.venv/Lib/site-packages/pip/_vendor/rich/rule.py
Raw Download
Find: Go to:
from typing import Union

from .align import AlignMethod
from .cells import cell_len, set_cell_size
from .console import Console, ConsoleOptions, RenderResult
from .jupyter import JupyterMixin
from .measure import Measurement
from .style import Style
from .text import Text


class Rule(JupyterMixin):
    """A console renderable to draw a horizontal rule (line).

    Args:
        title (Union[str, Text], optional): Text to render in the rule. Defaults to "".
        characters (str, optional): Character(s) used to draw the line. Defaults to "─".
        style (StyleType, optional): Style of Rule. Defaults to "rule.line".
        end (str, optional): Character at end of Rule. defaults to "\\\\n"
        align (str, optional): How to align the title, one of "left", "center", or "right". Defaults to "center".
    """

    def __init__(
        self,
        title: Union[str, Text] = "",
        *,
        characters: str = "─",
        style: Union[str, Style] = "rule.line",
        end: str = "\n",
        align: AlignMethod = "center",
    ) -> None:
        if cell_len(characters) < 1:
            raise ValueError(
                "'characters' argument must have a cell width of at least 1"
            )
        if align not in ("left", "center", "right"):
            raise ValueError(
                f'invalid value for align, expected "left", "center", "right" (not {align!r})'
            )
        self.title = title
        self.characters = characters
        self.style = style
        self.end = end
        self.align = align

    def __repr__(self) -> str:
        return f"Rule({self.title!r}, {self.characters!r})"

    def __rich_console__(
        self, console: Console, options: ConsoleOptions
    ) -> RenderResult:
        width = options.max_width

        characters = (
            "-"
            if (options.ascii_only and not self.characters.isascii())
            else self.characters
        )

        chars_len = cell_len(characters)
        if not self.title:
            yield self._rule_line(chars_len, width)
            return

        if isinstance(self.title, Text):
            title_text = self.title
        else:
            title_text = console.render_str(self.title, style="rule.text")

        title_text.plain = title_text.plain.replace("\n", " ")
        title_text.expand_tabs()

        required_space = 4 if self.align == "center" else 2
        truncate_width = max(0, width - required_space)
        if not truncate_width:
            yield self._rule_line(chars_len, width)
            return

        rule_text = Text(end=self.end)
        if self.align == "center":
            title_text.truncate(truncate_width, overflow="ellipsis")
            side_width = (width - cell_len(title_text.plain)) // 2
            left = Text(characters * (side_width // chars_len + 1))
            left.truncate(side_width - 1)
            right_length = width - cell_len(left.plain) - cell_len(title_text.plain)
            right = Text(characters * (side_width // chars_len + 1))
            right.truncate(right_length)
            rule_text.append(left.plain + " ", self.style)
            rule_text.append(title_text)
            rule_text.append(" " + right.plain, self.style)
        elif self.align == "left":
            title_text.truncate(truncate_width, overflow="ellipsis")
            rule_text.append(title_text)
            rule_text.append(" ")
            rule_text.append(characters * (width - rule_text.cell_len), self.style)
        elif self.align == "right":
            title_text.truncate(truncate_width, overflow="ellipsis")
            rule_text.append(characters * (width - title_text.cell_len - 1), self.style)
            rule_text.append(" ")
            rule_text.append(title_text)

        rule_text.plain = set_cell_size(rule_text.plain, width)
        yield rule_text

    def _rule_line(self, chars_len: int, width: int) -> Text:
        rule_text = Text(self.characters * ((width // chars_len) + 1), self.style)
        rule_text.truncate(width)
        rule_text.plain = set_cell_size(rule_text.plain, width)
        return rule_text

    def __rich_measure__(
        self, console: Console, options: ConsoleOptions
    ) -> Measurement:
        return Measurement(1, 1)


if __name__ == "__main__":  # pragma: no cover
    import sys

    from pip._vendor.rich.console import Console

    try:
        text = sys.argv[1]
    except IndexError:
        text = "Hello, World"
    console = Console()
    console.print(Rule(title=text))

    console = Console()
    console.print(Rule("foo"), width=4)
131 lines•4.5 KB
python
.venv/Lib/site-packages/pip/_vendor/rich/highlighter.py
Raw Download
Find: Go to:
import re
from abc import ABC, abstractmethod
from typing import List, Union

from .text import Span, Text


def _combine_regex(*regexes: str) -> str:
    """Combine a number of regexes in to a single regex.

    Returns:
        str: New regex with all regexes ORed together.
    """
    return "|".join(regexes)


class Highlighter(ABC):
    """Abstract base class for highlighters."""

    def __call__(self, text: Union[str, Text]) -> Text:
        """Highlight a str or Text instance.

        Args:
            text (Union[str, ~Text]): Text to highlight.

        Raises:
            TypeError: If not called with text or str.

        Returns:
            Text: A test instance with highlighting applied.
        """
        if isinstance(text, str):
            highlight_text = Text(text)
        elif isinstance(text, Text):
            highlight_text = text.copy()
        else:
            raise TypeError(f"str or Text instance required, not {text!r}")
        self.highlight(highlight_text)
        return highlight_text

    @abstractmethod
    def highlight(self, text: Text) -> None:
        """Apply highlighting in place to text.

        Args:
            text (~Text): A text object highlight.
        """


class NullHighlighter(Highlighter):
    """A highlighter object that doesn't highlight.

    May be used to disable highlighting entirely.

    """

    def highlight(self, text: Text) -> None:
        """Nothing to do"""


class RegexHighlighter(Highlighter):
    """Applies highlighting from a list of regular expressions."""

    highlights: List[str] = []
    base_style: str = ""

    def highlight(self, text: Text) -> None:
        """Highlight :class:`rich.text.Text` using regular expressions.

        Args:
            text (~Text): Text to highlighted.

        """

        highlight_regex = text.highlight_regex
        for re_highlight in self.highlights:
            highlight_regex(re_highlight, style_prefix=self.base_style)


class ReprHighlighter(RegexHighlighter):
    """Highlights the text typically produced from ``__repr__`` methods."""

    base_style = "repr."
    highlights = [
        r"(?P<tag_start><)(?P<tag_name>[-\w.:|]*)(?P<tag_contents>[\w\W]*)(?P<tag_end>>)",
        r'(?P<attrib_name>[\w_]{1,50})=(?P<attrib_value>"?[\w_]+"?)?',
        r"(?P<brace>[][{}()])",
        _combine_regex(
            r"(?P<ipv4>[0-9]{1,3}\.[0-9]{1,3}\.[0-9]{1,3}\.[0-9]{1,3})",
            r"(?P<ipv6>([A-Fa-f0-9]{1,4}::?){1,7}[A-Fa-f0-9]{1,4})",
            r"(?P<eui64>(?:[0-9A-Fa-f]{1,2}-){7}[0-9A-Fa-f]{1,2}|(?:[0-9A-Fa-f]{1,2}:){7}[0-9A-Fa-f]{1,2}|(?:[0-9A-Fa-f]{4}\.){3}[0-9A-Fa-f]{4})",
            r"(?P<eui48>(?:[0-9A-Fa-f]{1,2}-){5}[0-9A-Fa-f]{1,2}|(?:[0-9A-Fa-f]{1,2}:){5}[0-9A-Fa-f]{1,2}|(?:[0-9A-Fa-f]{4}\.){2}[0-9A-Fa-f]{4})",
            r"(?P<uuid>[a-fA-F0-9]{8}-[a-fA-F0-9]{4}-[a-fA-F0-9]{4}-[a-fA-F0-9]{4}-[a-fA-F0-9]{12})",
            r"(?P<call>[\w.]*?)\(",
            r"\b(?P<bool_true>True)\b|\b(?P<bool_false>False)\b|\b(?P<none>None)\b",
            r"(?P<ellipsis>\.\.\.)",
            r"(?P<number_complex>(?<!\w)(?:\-?[0-9]+\.?[0-9]*(?:e[-+]?\d+?)?)(?:[-+](?:[0-9]+\.?[0-9]*(?:e[-+]?\d+)?))?j)",
            r"(?P<number>(?<!\w)\-?[0-9]+\.?[0-9]*(e[-+]?\d+?)?\b|0x[0-9a-fA-F]*)",
            r"(?P<path>\B(/[-\w._+]+)*\/)(?P<filename>[-\w._+]*)?",
            r"(?<![\\\w])(?P<str>b?'''.*?(?<!\\)'''|b?'.*?(?<!\\)'|b?\"\"\".*?(?<!\\)\"\"\"|b?\".*?(?<!\\)\")",
            r"(?P<url>(file|https|http|ws|wss)://[-0-9a-zA-Z$_+!`(),.?/;:&=%#~]*)",
        ),
    ]


class JSONHighlighter(RegexHighlighter):
    """Highlights JSON"""

    # Captures the start and end of JSON strings, handling escaped quotes
    JSON_STR = r"(?<![\\\w])(?P<str>b?\".*?(?<!\\)\")"
    JSON_WHITESPACE = {" ", "\n", "\r", "\t"}

    base_style = "json."
    highlights = [
        _combine_regex(
            r"(?P<brace>[\{\[\(\)\]\}])",
            r"\b(?P<bool_true>true)\b|\b(?P<bool_false>false)\b|\b(?P<null>null)\b",
            r"(?P<number>(?<!\w)\-?[0-9]+\.?[0-9]*(e[\-\+]?\d+?)?\b|0x[0-9a-fA-F]*)",
            JSON_STR,
        ),
    ]

    def highlight(self, text: Text) -> None:
        super().highlight(text)

        # Additional work to handle highlighting JSON keys
        plain = text.plain
        append = text.spans.append
        whitespace = self.JSON_WHITESPACE
        for match in re.finditer(self.JSON_STR, plain):
            start, end = match.span()
            cursor = end
            while cursor < len(plain):
                char = plain[cursor]
                cursor += 1
                if char == ":":
                    append(Span(start, end, "json.key"))
                elif char in whitespace:
                    continue
                break


class ISO8601Highlighter(RegexHighlighter):
    """Highlights the ISO8601 date time strings.
    Regex reference: https://www.oreilly.com/library/view/regular-expressions-cookbook/9781449327453/ch04s07.html
    """

    base_style = "iso8601."
    highlights = [
        #
        # Dates
        #
        # Calendar month (e.g. 2008-08). The hyphen is required
        r"^(?P<year>[0-9]{4})-(?P<month>1[0-2]|0[1-9])$",
        # Calendar date w/o hyphens (e.g. 20080830)
        r"^(?P<date>(?P<year>[0-9]{4})(?P<month>1[0-2]|0[1-9])(?P<day>3[01]|0[1-9]|[12][0-9]))$",
        # Ordinal date (e.g. 2008-243). The hyphen is optional
        r"^(?P<date>(?P<year>[0-9]{4})-?(?P<day>36[0-6]|3[0-5][0-9]|[12][0-9]{2}|0[1-9][0-9]|00[1-9]))$",
        #
        # Weeks
        #
        # Week of the year (e.g., 2008-W35). The hyphen is optional
        r"^(?P<date>(?P<year>[0-9]{4})-?W(?P<week>5[0-3]|[1-4][0-9]|0[1-9]))$",
        # Week date (e.g., 2008-W35-6). The hyphens are optional
        r"^(?P<date>(?P<year>[0-9]{4})-?W(?P<week>5[0-3]|[1-4][0-9]|0[1-9])-?(?P<day>[1-7]))$",
        #
        # Times
        #
        # Hours and minutes (e.g., 17:21). The colon is optional
        r"^(?P<time>(?P<hour>2[0-3]|[01][0-9]):?(?P<minute>[0-5][0-9]))$",
        # Hours, minutes, and seconds w/o colons (e.g., 172159)
        r"^(?P<time>(?P<hour>2[0-3]|[01][0-9])(?P<minute>[0-5][0-9])(?P<second>[0-5][0-9]))$",
        # Time zone designator (e.g., Z, +07 or +07:00). The colons and the minutes are optional
        r"^(?P<timezone>(Z|[+-](?:2[0-3]|[01][0-9])(?::?(?:[0-5][0-9]))?))$",
        # Hours, minutes, and seconds with time zone designator (e.g., 17:21:59+07:00).
        # All the colons are optional. The minutes in the time zone designator are also optional
        r"^(?P<time>(?P<hour>2[0-3]|[01][0-9])(?P<minute>[0-5][0-9])(?P<second>[0-5][0-9]))(?P<timezone>Z|[+-](?:2[0-3]|[01][0-9])(?::?(?:[0-5][0-9]))?)$",
        #
        # Date and Time
        #
        # Calendar date with hours, minutes, and seconds (e.g., 2008-08-30 17:21:59 or 20080830 172159).
        # A space is required between the date and the time. The hyphens and colons are optional.
        # This regex matches dates and times that specify some hyphens or colons but omit others.
        # This does not follow ISO 8601
        r"^(?P<date>(?P<year>[0-9]{4})(?P<hyphen>-)?(?P<month>1[0-2]|0[1-9])(?(hyphen)-)(?P<day>3[01]|0[1-9]|[12][0-9])) (?P<time>(?P<hour>2[0-3]|[01][0-9])(?(hyphen):)(?P<minute>[0-5][0-9])(?(hyphen):)(?P<second>[0-5][0-9]))$",
        #
        # XML Schema dates and times
        #
        # Date, with optional time zone (e.g., 2008-08-30 or 2008-08-30+07:00).
        # Hyphens are required. This is the XML Schema 'date' type
        r"^(?P<date>(?P<year>-?(?:[1-9][0-9]*)?[0-9]{4})-(?P<month>1[0-2]|0[1-9])-(?P<day>3[01]|0[1-9]|[12][0-9]))(?P<timezone>Z|[+-](?:2[0-3]|[01][0-9]):[0-5][0-9])?$",
        # Time, with optional fractional seconds and time zone (e.g., 01:45:36 or 01:45:36.123+07:00).
        # There is no limit on the number of digits for the fractional seconds. This is the XML Schema 'time' type
        r"^(?P<time>(?P<hour>2[0-3]|[01][0-9]):(?P<minute>[0-5][0-9]):(?P<second>[0-5][0-9])(?P<frac>\.[0-9]+)?)(?P<timezone>Z|[+-](?:2[0-3]|[01][0-9]):[0-5][0-9])?$",
        # Date and time, with optional fractional seconds and time zone (e.g., 2008-08-30T01:45:36 or 2008-08-30T01:45:36.123Z).
        # This is the XML Schema 'dateTime' type
        r"^(?P<date>(?P<year>-?(?:[1-9][0-9]*)?[0-9]{4})-(?P<month>1[0-2]|0[1-9])-(?P<day>3[01]|0[1-9]|[12][0-9]))T(?P<time>(?P<hour>2[0-3]|[01][0-9]):(?P<minute>[0-5][0-9]):(?P<second>[0-5][0-9])(?P<ms>\.[0-9]+)?)(?P<timezone>Z|[+-](?:2[0-3]|[01][0-9]):[0-5][0-9])?$",
    ]


if __name__ == "__main__":  # pragma: no cover
    from .console import Console

    console = Console()
    console.print("[bold green]hello world![/bold green]")
    console.print("'[bold green]hello world![/bold green]'")

    console.print(" /foo")
    console.print("/foo/")
    console.print("/foo/bar")
    console.print("foo/bar/baz")

    console.print("/foo/bar/baz?foo=bar+egg&egg=baz")
    console.print("/foo/bar/baz/")
    console.print("/foo/bar/baz/egg")
    console.print("/foo/bar/baz/egg.py")
    console.print("/foo/bar/baz/egg.py word")
    console.print(" /foo/bar/baz/egg.py word")
    console.print("foo /foo/bar/baz/egg.py word")
    console.print("foo /foo/bar/ba._++z/egg+.py word")
    console.print("https://example.org?foo=bar#header")

    console.print(1234567.34)
    console.print(1 / 2)
    console.print(-1 / 123123123123)

    console.print(
        "127.0.1.1 bar 192.168.1.4 2001:0db8:85a3:0000:0000:8a2e:0370:7334 foo"
    )
    import json

    console.print_json(json.dumps(obj={"name": "apple", "count": 1}), indent=None)
233 lines•9.4 KB
python
.venv/Lib/site-packages/pip/_vendor/requests/status_codes.py
Raw Download
Find: Go to:
r"""
The ``codes`` object defines a mapping from common names for HTTP statuses
to their numerical codes, accessible either as attributes or as dictionary
items.

Example::

    >>> import requests
    >>> requests.codes['temporary_redirect']
    307
    >>> requests.codes.teapot
    418
    >>> requests.codes['\o/']
    200

Some codes have multiple names, and both upper- and lower-case versions of
the names are allowed. For example, ``codes.ok``, ``codes.OK``, and
``codes.okay`` all correspond to the HTTP status code 200.
"""

from .structures import LookupDict

_codes = {
    # Informational.
    100: ("continue",),
    101: ("switching_protocols",),
    102: ("processing", "early-hints"),
    103: ("checkpoint",),
    122: ("uri_too_long", "request_uri_too_long"),
    200: ("ok", "okay", "all_ok", "all_okay", "all_good", "\\o/", "✓"),
    201: ("created",),
    202: ("accepted",),
    203: ("non_authoritative_info", "non_authoritative_information"),
    204: ("no_content",),
    205: ("reset_content", "reset"),
    206: ("partial_content", "partial"),
    207: ("multi_status", "multiple_status", "multi_stati", "multiple_stati"),
    208: ("already_reported",),
    226: ("im_used",),
    # Redirection.
    300: ("multiple_choices",),
    301: ("moved_permanently", "moved", "\\o-"),
    302: ("found",),
    303: ("see_other", "other"),
    304: ("not_modified",),
    305: ("use_proxy",),
    306: ("switch_proxy",),
    307: ("temporary_redirect", "temporary_moved", "temporary"),
    308: (
        "permanent_redirect",
        "resume_incomplete",
        "resume",
    ),  # "resume" and "resume_incomplete" to be removed in 3.0
    # Client Error.
    400: ("bad_request", "bad"),
    401: ("unauthorized",),
    402: ("payment_required", "payment"),
    403: ("forbidden",),
    404: ("not_found", "-o-"),
    405: ("method_not_allowed", "not_allowed"),
    406: ("not_acceptable",),
    407: ("proxy_authentication_required", "proxy_auth", "proxy_authentication"),
    408: ("request_timeout", "timeout"),
    409: ("conflict",),
    410: ("gone",),
    411: ("length_required",),
    412: ("precondition_failed", "precondition"),
    413: ("request_entity_too_large", "content_too_large"),
    414: ("request_uri_too_large", "uri_too_long"),
    415: ("unsupported_media_type", "unsupported_media", "media_type"),
    416: (
        "requested_range_not_satisfiable",
        "requested_range",
        "range_not_satisfiable",
    ),
    417: ("expectation_failed",),
    418: ("im_a_teapot", "teapot", "i_am_a_teapot"),
    421: ("misdirected_request",),
    422: ("unprocessable_entity", "unprocessable", "unprocessable_content"),
    423: ("locked",),
    424: ("failed_dependency", "dependency"),
    425: ("unordered_collection", "unordered", "too_early"),
    426: ("upgrade_required", "upgrade"),
    428: ("precondition_required", "precondition"),
    429: ("too_many_requests", "too_many"),
    431: ("header_fields_too_large", "fields_too_large"),
    444: ("no_response", "none"),
    449: ("retry_with", "retry"),
    450: ("blocked_by_windows_parental_controls", "parental_controls"),
    451: ("unavailable_for_legal_reasons", "legal_reasons"),
    499: ("client_closed_request",),
    # Server Error.
    500: ("internal_server_error", "server_error", "/o\\", "✗"),
    501: ("not_implemented",),
    502: ("bad_gateway",),
    503: ("service_unavailable", "unavailable"),
    504: ("gateway_timeout",),
    505: ("http_version_not_supported", "http_version"),
    506: ("variant_also_negotiates",),
    507: ("insufficient_storage",),
    509: ("bandwidth_limit_exceeded", "bandwidth"),
    510: ("not_extended",),
    511: ("network_authentication_required", "network_auth", "network_authentication"),
}

codes = LookupDict(name="status_codes")


def _init():
    for code, titles in _codes.items():
        for title in titles:
            setattr(codes, title, code)
            if not title.startswith(("\\", "/")):
                setattr(codes, title.upper(), code)

    def doc(code):
        names = ", ".join(f"``{n}``" for n in _codes[code])
        return "* %d: %s" % (code, names)

    global __doc__
    __doc__ = (
        __doc__ + "\n" + "\n".join(doc(code) for code in sorted(_codes))
        if __doc__ is not None
        else None
    )


_init()
129 lines•4.2 KB
python
.venv/Lib/site-packages/pip/_vendor/distlib/manifest.py
Raw Download
Find: Go to:
# -*- coding: utf-8 -*-
#
# Copyright (C) 2012-2023 Python Software Foundation.
# See LICENSE.txt and CONTRIBUTORS.txt.
#
"""
Class representing the list of files in a distribution.

Equivalent to distutils.filelist, but fixes some problems.
"""
import fnmatch
import logging
import os
import re
import sys

from . import DistlibException
from .compat import fsdecode
from .util import convert_path


__all__ = ['Manifest']

logger = logging.getLogger(__name__)

# a \ followed by some spaces + EOL
_COLLAPSE_PATTERN = re.compile('\\\\w*\n', re.M)
_COMMENTED_LINE = re.compile('#.*?(?=\n)|\n(?=$)', re.M | re.S)

#
# Due to the different results returned by fnmatch.translate, we need
# to do slightly different processing for Python 2.7 and 3.2 ... this needed
# to be brought in for Python 3.6 onwards.
#
_PYTHON_VERSION = sys.version_info[:2]


class Manifest(object):
    """
    A list of files built by exploring the filesystem and filtered by applying various
    patterns to what we find there.
    """

    def __init__(self, base=None):
        """
        Initialise an instance.

        :param base: The base directory to explore under.
        """
        self.base = os.path.abspath(os.path.normpath(base or os.getcwd()))
        self.prefix = self.base + os.sep
        self.allfiles = None
        self.files = set()

    #
    # Public API
    #

    def findall(self):
        """Find all files under the base and set ``allfiles`` to the absolute
        pathnames of files found.
        """
        from stat import S_ISREG, S_ISDIR, S_ISLNK

        self.allfiles = allfiles = []
        root = self.base
        stack = [root]
        pop = stack.pop
        push = stack.append

        while stack:
            root = pop()
            names = os.listdir(root)

            for name in names:
                fullname = os.path.join(root, name)

                # Avoid excess stat calls -- just one will do, thank you!
                stat = os.stat(fullname)
                mode = stat.st_mode
                if S_ISREG(mode):
                    allfiles.append(fsdecode(fullname))
                elif S_ISDIR(mode) and not S_ISLNK(mode):
                    push(fullname)

    def add(self, item):
        """
        Add a file to the manifest.

        :param item: The pathname to add. This can be relative to the base.
        """
        if not item.startswith(self.prefix):
            item = os.path.join(self.base, item)
        self.files.add(os.path.normpath(item))

    def add_many(self, items):
        """
        Add a list of files to the manifest.

        :param items: The pathnames to add. These can be relative to the base.
        """
        for item in items:
            self.add(item)

    def sorted(self, wantdirs=False):
        """
        Return sorted files in directory order
        """

        def add_dir(dirs, d):
            dirs.add(d)
            logger.debug('add_dir added %s', d)
            if d != self.base:
                parent, _ = os.path.split(d)
                assert parent not in ('', '/')
                add_dir(dirs, parent)

        result = set(self.files)    # make a copy!
        if wantdirs:
            dirs = set()
            for f in result:
                add_dir(dirs, os.path.dirname(f))
            result |= dirs
        return [os.path.join(*path_tuple) for path_tuple in
                sorted(os.path.split(path) for path in result)]

    def clear(self):
        """Clear all collected files."""
        self.files = set()
        self.allfiles = []

    def process_directive(self, directive):
        """
        Process a directive which either adds some files from ``allfiles`` to
        ``files``, or removes some files from ``files``.

        :param directive: The directive to process. This should be in a format
                     compatible with distutils ``MANIFEST.in`` files:

                     http://docs.python.org/distutils/sourcedist.html#commands
        """
        # Parse the line: split it up, make sure the right number of words
        # is there, and return the relevant words.  'action' is always
        # defined: it's the first word of the line.  Which of the other
        # three are defined depends on the action; it'll be either
        # patterns, (dir and patterns), or (dirpattern).
        action, patterns, thedir, dirpattern = self._parse_directive(directive)

        # OK, now we know that the action is valid and we have the
        # right number of words on the line for that action -- so we
        # can proceed with minimal error-checking.
        if action == 'include':
            for pattern in patterns:
                if not self._include_pattern(pattern, anchor=True):
                    logger.warning('no files found matching %r', pattern)

        elif action == 'exclude':
            for pattern in patterns:
                self._exclude_pattern(pattern, anchor=True)

        elif action == 'global-include':
            for pattern in patterns:
                if not self._include_pattern(pattern, anchor=False):
                    logger.warning('no files found matching %r '
                                   'anywhere in distribution', pattern)

        elif action == 'global-exclude':
            for pattern in patterns:
                self._exclude_pattern(pattern, anchor=False)

        elif action == 'recursive-include':
            for pattern in patterns:
                if not self._include_pattern(pattern, prefix=thedir):
                    logger.warning('no files found matching %r '
                                   'under directory %r', pattern, thedir)

        elif action == 'recursive-exclude':
            for pattern in patterns:
                self._exclude_pattern(pattern, prefix=thedir)

        elif action == 'graft':
            if not self._include_pattern(None, prefix=dirpattern):
                logger.warning('no directories found matching %r',
                               dirpattern)

        elif action == 'prune':
            if not self._exclude_pattern(None, prefix=dirpattern):
                logger.warning('no previously-included directories found '
                               'matching %r', dirpattern)
        else:   # pragma: no cover
            # This should never happen, as it should be caught in
            # _parse_template_line
            raise DistlibException(
                'invalid action %r' % action)

    #
    # Private API
    #

    def _parse_directive(self, directive):
        """
        Validate a directive.
        :param directive: The directive to validate.
        :return: A tuple of action, patterns, thedir, dir_patterns
        """
        words = directive.split()
        if len(words) == 1 and words[0] not in ('include', 'exclude',
                                                'global-include',
                                                'global-exclude',
                                                'recursive-include',
                                                'recursive-exclude',
                                                'graft', 'prune'):
            # no action given, let's use the default 'include'
            words.insert(0, 'include')

        action = words[0]
        patterns = thedir = dir_pattern = None

        if action in ('include', 'exclude',
                      'global-include', 'global-exclude'):
            if len(words) < 2:
                raise DistlibException(
                    '%r expects <pattern1> <pattern2> ...' % action)

            patterns = [convert_path(word) for word in words[1:]]

        elif action in ('recursive-include', 'recursive-exclude'):
            if len(words) < 3:
                raise DistlibException(
                    '%r expects <dir> <pattern1> <pattern2> ...' % action)

            thedir = convert_path(words[1])
            patterns = [convert_path(word) for word in words[2:]]

        elif action in ('graft', 'prune'):
            if len(words) != 2:
                raise DistlibException(
                    '%r expects a single <dir_pattern>' % action)

            dir_pattern = convert_path(words[1])

        else:
            raise DistlibException('unknown action %r' % action)

        return action, patterns, thedir, dir_pattern

    def _include_pattern(self, pattern, anchor=True, prefix=None,
                         is_regex=False):
        """Select strings (presumably filenames) from 'self.files' that
        match 'pattern', a Unix-style wildcard (glob) pattern.

        Patterns are not quite the same as implemented by the 'fnmatch'
        module: '*' and '?'  match non-special characters, where "special"
        is platform-dependent: slash on Unix; colon, slash, and backslash on
        DOS/Windows; and colon on Mac OS.

        If 'anchor' is true (the default), then the pattern match is more
        stringent: "*.py" will match "foo.py" but not "foo/bar.py".  If
        'anchor' is false, both of these will match.

        If 'prefix' is supplied, then only filenames starting with 'prefix'
        (itself a pattern) and ending with 'pattern', with anything in between
        them, will match.  'anchor' is ignored in this case.

        If 'is_regex' is true, 'anchor' and 'prefix' are ignored, and
        'pattern' is assumed to be either a string containing a regex or a
        regex object -- no translation is done, the regex is just compiled
        and used as-is.

        Selected strings will be added to self.files.

        Return True if files are found.
        """
        # XXX docstring lying about what the special chars are?
        found = False
        pattern_re = self._translate_pattern(pattern, anchor, prefix, is_regex)

        # delayed loading of allfiles list
        if self.allfiles is None:
            self.findall()

        for name in self.allfiles:
            if pattern_re.search(name):
                self.files.add(name)
                found = True
        return found

    def _exclude_pattern(self, pattern, anchor=True, prefix=None,
                         is_regex=False):
        """Remove strings (presumably filenames) from 'files' that match
        'pattern'.

        Other parameters are the same as for 'include_pattern()', above.
        The list 'self.files' is modified in place. Return True if files are
        found.

        This API is public to allow e.g. exclusion of SCM subdirs, e.g. when
        packaging source distributions
        """
        found = False
        pattern_re = self._translate_pattern(pattern, anchor, prefix, is_regex)
        for f in list(self.files):
            if pattern_re.search(f):
                self.files.remove(f)
                found = True
        return found

    def _translate_pattern(self, pattern, anchor=True, prefix=None,
                           is_regex=False):
        """Translate a shell-like wildcard pattern to a compiled regular
        expression.

        Return the compiled regex.  If 'is_regex' true,
        then 'pattern' is directly compiled to a regex (if it's a string)
        or just returned as-is (assumes it's a regex object).
        """
        if is_regex:
            if isinstance(pattern, str):
                return re.compile(pattern)
            else:
                return pattern

        if _PYTHON_VERSION > (3, 2):
            # ditch start and end characters
            start, _, end = self._glob_to_re('_').partition('_')

        if pattern:
            pattern_re = self._glob_to_re(pattern)
            if _PYTHON_VERSION > (3, 2):
                assert pattern_re.startswith(start) and pattern_re.endswith(end)
        else:
            pattern_re = ''

        base = re.escape(os.path.join(self.base, ''))
        if prefix is not None:
            # ditch end of pattern character
            if _PYTHON_VERSION <= (3, 2):
                empty_pattern = self._glob_to_re('')
                prefix_re = self._glob_to_re(prefix)[:-len(empty_pattern)]
            else:
                prefix_re = self._glob_to_re(prefix)
                assert prefix_re.startswith(start) and prefix_re.endswith(end)
                prefix_re = prefix_re[len(start): len(prefix_re) - len(end)]
            sep = os.sep
            if os.sep == '\\':
                sep = r'\\'
            if _PYTHON_VERSION <= (3, 2):
                pattern_re = '^' + base + sep.join((prefix_re,
                                                    '.*' + pattern_re))
            else:
                pattern_re = pattern_re[len(start): len(pattern_re) - len(end)]
                pattern_re = r'%s%s%s%s.*%s%s' % (start, base, prefix_re, sep,
                                                  pattern_re, end)
        else:  # no prefix -- respect anchor flag
            if anchor:
                if _PYTHON_VERSION <= (3, 2):
                    pattern_re = '^' + base + pattern_re
                else:
                    pattern_re = r'%s%s%s' % (start, base, pattern_re[len(start):])

        return re.compile(pattern_re)

    def _glob_to_re(self, pattern):
        """Translate a shell-like glob pattern to a regular expression.

        Return a string containing the regex.  Differs from
        'fnmatch.translate()' in that '*' does not match "special characters"
        (which are platform-specific).
        """
        pattern_re = fnmatch.translate(pattern)

        # '?' and '*' in the glob pattern become '.' and '.*' in the RE, which
        # IMHO is wrong -- '?' and '*' aren't supposed to match slash in Unix,
        # and by extension they shouldn't match such "special characters" under
        # any OS.  So change all non-escaped dots in the RE to match any
        # character except the special characters (currently: just os.sep).
        sep = os.sep
        if os.sep == '\\':
            # we're using a regex to manipulate a regex, so we need
            # to escape the backslash twice
            sep = r'\\\\'
        escaped = r'\1[^%s]' % sep
        pattern_re = re.sub(r'((?<!\\)(\\\\)*)\.', escaped, pattern_re)
        return pattern_re
385 lines•13.8 KB
python
.venv/Lib/site-packages/pip/_vendor/idna/core.py
Raw Download
Find: Go to:
from . import idnadata
import bisect
import unicodedata
import re
from typing import Union, Optional
from .intranges import intranges_contain

_virama_combining_class = 9
_alabel_prefix = b'xn--'
_unicode_dots_re = re.compile('[\u002e\u3002\uff0e\uff61]')

class IDNAError(UnicodeError):
    """ Base exception for all IDNA-encoding related problems """
    pass


class IDNABidiError(IDNAError):
    """ Exception when bidirectional requirements are not satisfied """
    pass


class InvalidCodepoint(IDNAError):
    """ Exception when a disallowed or unallocated codepoint is used """
    pass


class InvalidCodepointContext(IDNAError):
    """ Exception when the codepoint is not valid in the context it is used """
    pass


def _combining_class(cp: int) -> int:
    v = unicodedata.combining(chr(cp))
    if v == 0:
        if not unicodedata.name(chr(cp)):
            raise ValueError('Unknown character in unicodedata')
    return v

def _is_script(cp: str, script: str) -> bool:
    return intranges_contain(ord(cp), idnadata.scripts[script])

def _punycode(s: str) -> bytes:
    return s.encode('punycode')

def _unot(s: int) -> str:
    return 'U+{:04X}'.format(s)


def valid_label_length(label: Union[bytes, str]) -> bool:
    if len(label) > 63:
        return False
    return True


def valid_string_length(label: Union[bytes, str], trailing_dot: bool) -> bool:
    if len(label) > (254 if trailing_dot else 253):
        return False
    return True


def check_bidi(label: str, check_ltr: bool = False) -> bool:
    # Bidi rules should only be applied if string contains RTL characters
    bidi_label = False
    for (idx, cp) in enumerate(label, 1):
        direction = unicodedata.bidirectional(cp)
        if direction == '':
            # String likely comes from a newer version of Unicode
            raise IDNABidiError('Unknown directionality in label {} at position {}'.format(repr(label), idx))
        if direction in ['R', 'AL', 'AN']:
            bidi_label = True
    if not bidi_label and not check_ltr:
        return True

    # Bidi rule 1
    direction = unicodedata.bidirectional(label[0])
    if direction in ['R', 'AL']:
        rtl = True
    elif direction == 'L':
        rtl = False
    else:
        raise IDNABidiError('First codepoint in label {} must be directionality L, R or AL'.format(repr(label)))

    valid_ending = False
    number_type = None  # type: Optional[str]
    for (idx, cp) in enumerate(label, 1):
        direction = unicodedata.bidirectional(cp)

        if rtl:
            # Bidi rule 2
            if not direction in ['R', 'AL', 'AN', 'EN', 'ES', 'CS', 'ET', 'ON', 'BN', 'NSM']:
                raise IDNABidiError('Invalid direction for codepoint at position {} in a right-to-left label'.format(idx))
            # Bidi rule 3
            if direction in ['R', 'AL', 'EN', 'AN']:
                valid_ending = True
            elif direction != 'NSM':
                valid_ending = False
            # Bidi rule 4
            if direction in ['AN', 'EN']:
                if not number_type:
                    number_type = direction
                else:
                    if number_type != direction:
                        raise IDNABidiError('Can not mix numeral types in a right-to-left label')
        else:
            # Bidi rule 5
            if not direction in ['L', 'EN', 'ES', 'CS', 'ET', 'ON', 'BN', 'NSM']:
                raise IDNABidiError('Invalid direction for codepoint at position {} in a left-to-right label'.format(idx))
            # Bidi rule 6
            if direction in ['L', 'EN']:
                valid_ending = True
            elif direction != 'NSM':
                valid_ending = False

    if not valid_ending:
        raise IDNABidiError('Label ends with illegal codepoint directionality')

    return True


def check_initial_combiner(label: str) -> bool:
    if unicodedata.category(label[0])[0] == 'M':
        raise IDNAError('Label begins with an illegal combining character')
    return True


def check_hyphen_ok(label: str) -> bool:
    if label[2:4] == '--':
        raise IDNAError('Label has disallowed hyphens in 3rd and 4th position')
    if label[0] == '-' or label[-1] == '-':
        raise IDNAError('Label must not start or end with a hyphen')
    return True


def check_nfc(label: str) -> None:
    if unicodedata.normalize('NFC', label) != label:
        raise IDNAError('Label must be in Normalization Form C')


def valid_contextj(label: str, pos: int) -> bool:
    cp_value = ord(label[pos])

    if cp_value == 0x200c:

        if pos > 0:
            if _combining_class(ord(label[pos - 1])) == _virama_combining_class:
                return True

        ok = False
        for i in range(pos-1, -1, -1):
            joining_type = idnadata.joining_types.get(ord(label[i]))
            if joining_type == ord('T'):
                continue
            elif joining_type in [ord('L'), ord('D')]:
                ok = True
                break
            else:
                break

        if not ok:
            return False

        ok = False
        for i in range(pos+1, len(label)):
            joining_type = idnadata.joining_types.get(ord(label[i]))
            if joining_type == ord('T'):
                continue
            elif joining_type in [ord('R'), ord('D')]:
                ok = True
                break
            else:
                break
        return ok

    if cp_value == 0x200d:

        if pos > 0:
            if _combining_class(ord(label[pos - 1])) == _virama_combining_class:
                return True
        return False

    else:

        return False


def valid_contexto(label: str, pos: int, exception: bool = False) -> bool:
    cp_value = ord(label[pos])

    if cp_value == 0x00b7:
        if 0 < pos < len(label)-1:
            if ord(label[pos - 1]) == 0x006c and ord(label[pos + 1]) == 0x006c:
                return True
        return False

    elif cp_value == 0x0375:
        if pos < len(label)-1 and len(label) > 1:
            return _is_script(label[pos + 1], 'Greek')
        return False

    elif cp_value == 0x05f3 or cp_value == 0x05f4:
        if pos > 0:
            return _is_script(label[pos - 1], 'Hebrew')
        return False

    elif cp_value == 0x30fb:
        for cp in label:
            if cp == '\u30fb':
                continue
            if _is_script(cp, 'Hiragana') or _is_script(cp, 'Katakana') or _is_script(cp, 'Han'):
                return True
        return False

    elif 0x660 <= cp_value <= 0x669:
        for cp in label:
            if 0x6f0 <= ord(cp) <= 0x06f9:
                return False
        return True

    elif 0x6f0 <= cp_value <= 0x6f9:
        for cp in label:
            if 0x660 <= ord(cp) <= 0x0669:
                return False
        return True

    return False


def check_label(label: Union[str, bytes, bytearray]) -> None:
    if isinstance(label, (bytes, bytearray)):
        label = label.decode('utf-8')
    if len(label) == 0:
        raise IDNAError('Empty Label')

    check_nfc(label)
    check_hyphen_ok(label)
    check_initial_combiner(label)

    for (pos, cp) in enumerate(label):
        cp_value = ord(cp)
        if intranges_contain(cp_value, idnadata.codepoint_classes['PVALID']):
            continue
        elif intranges_contain(cp_value, idnadata.codepoint_classes['CONTEXTJ']):
            if not valid_contextj(label, pos):
                raise InvalidCodepointContext('Joiner {} not allowed at position {} in {}'.format(
                    _unot(cp_value), pos+1, repr(label)))
        elif intranges_contain(cp_value, idnadata.codepoint_classes['CONTEXTO']):
            if not valid_contexto(label, pos):
                raise InvalidCodepointContext('Codepoint {} not allowed at position {} in {}'.format(_unot(cp_value), pos+1, repr(label)))
        else:
            raise InvalidCodepoint('Codepoint {} at position {} of {} not allowed'.format(_unot(cp_value), pos+1, repr(label)))

    check_bidi(label)


def alabel(label: str) -> bytes:
    try:
        label_bytes = label.encode('ascii')
        ulabel(label_bytes)
        if not valid_label_length(label_bytes):
            raise IDNAError('Label too long')
        return label_bytes
    except UnicodeEncodeError:
        pass

    check_label(label)
    label_bytes = _alabel_prefix + _punycode(label)

    if not valid_label_length(label_bytes):
        raise IDNAError('Label too long')

    return label_bytes


def ulabel(label: Union[str, bytes, bytearray]) -> str:
    if not isinstance(label, (bytes, bytearray)):
        try:
            label_bytes = label.encode('ascii')
        except UnicodeEncodeError:
            check_label(label)
            return label
    else:
        label_bytes = label

    label_bytes = label_bytes.lower()
    if label_bytes.startswith(_alabel_prefix):
        label_bytes = label_bytes[len(_alabel_prefix):]
        if not label_bytes:
            raise IDNAError('Malformed A-label, no Punycode eligible content found')
        if label_bytes.decode('ascii')[-1] == '-':
            raise IDNAError('A-label must not end with a hyphen')
    else:
        check_label(label_bytes)
        return label_bytes.decode('ascii')

    try:
        label = label_bytes.decode('punycode')
    except UnicodeError:
        raise IDNAError('Invalid A-label')
    check_label(label)
    return label


def uts46_remap(domain: str, std3_rules: bool = True, transitional: bool = False) -> str:
    """Re-map the characters in the string according to UTS46 processing."""
    from .uts46data import uts46data
    output = ''

    for pos, char in enumerate(domain):
        code_point = ord(char)
        try:
            uts46row = uts46data[code_point if code_point < 256 else
                bisect.bisect_left(uts46data, (code_point, 'Z')) - 1]
            status = uts46row[1]
            replacement = None  # type: Optional[str]
            if len(uts46row) == 3:
                replacement = uts46row[2]
            if (status == 'V' or
                    (status == 'D' and not transitional) or
                    (status == '3' and not std3_rules and replacement is None)):
                output += char
            elif replacement is not None and (status == 'M' or
                    (status == '3' and not std3_rules) or
                    (status == 'D' and transitional)):
                output += replacement
            elif status != 'I':
                raise IndexError()
        except IndexError:
            raise InvalidCodepoint(
                'Codepoint {} not allowed at position {} in {}'.format(
                _unot(code_point), pos + 1, repr(domain)))

    return unicodedata.normalize('NFC', output)


def encode(s: Union[str, bytes, bytearray], strict: bool = False, uts46: bool = False, std3_rules: bool = False, transitional: bool = False) -> bytes:
    if not isinstance(s, str):
        try:
            s = str(s, 'ascii')
        except UnicodeDecodeError:
            raise IDNAError('should pass a unicode string to the function rather than a byte string.')
    if uts46:
        s = uts46_remap(s, std3_rules, transitional)
    trailing_dot = False
    result = []
    if strict:
        labels = s.split('.')
    else:
        labels = _unicode_dots_re.split(s)
    if not labels or labels == ['']:
        raise IDNAError('Empty domain')
    if labels[-1] == '':
        del labels[-1]
        trailing_dot = True
    for label in labels:
        s = alabel(label)
        if s:
            result.append(s)
        else:
            raise IDNAError('Empty label')
    if trailing_dot:
        result.append(b'')
    s = b'.'.join(result)
    if not valid_string_length(s, trailing_dot):
        raise IDNAError('Domain too long')
    return s


def decode(s: Union[str, bytes, bytearray], strict: bool = False, uts46: bool = False, std3_rules: bool = False) -> str:
    try:
        if not isinstance(s, str):
            s = str(s, 'ascii')
    except UnicodeDecodeError:
        raise IDNAError('Invalid ASCII in A-label')
    if uts46:
        s = uts46_remap(s, std3_rules, False)
    trailing_dot = False
    result = []
    if not strict:
        labels = _unicode_dots_re.split(s)
    else:
        labels = s.split('.')
    if not labels or labels == ['']:
        raise IDNAError('Empty domain')
    if not labels[-1]:
        del labels[-1]
        trailing_dot = True
    for label in labels:
        s = ulabel(label)
        if s:
            result.append(s)
        else:
            raise IDNAError('Empty label')
    if trailing_dot:
        result.append('')
    return '.'.join(result)
396 lines•12.4 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